diff options
781 files changed, 22450 insertions, 5921 deletions
diff --git a/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png Binary files differnew file mode 100644 index 000000000000..7496a55e4e7b --- /dev/null +++ b/Documentation/RCU/Design/Requirements/2013-08-is-it-dead.png diff --git a/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg b/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg new file mode 100644 index 000000000000..4b4014fda770 --- /dev/null +++ b/Documentation/RCU/Design/Requirements/GPpartitionReaders1.svg @@ -0,0 +1,374 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="447.99197" + height="428.19299" + id="svg2" + version="1.1" + inkscape:version="0.48.3.1 r9886" + sodipodi:docname="GPpartitionReaders1.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.6184291" + inkscape:cx="223.99599" + inkscape:cy="214.0965" + inkscape:document-units="px" + inkscape:current-layer="layer1" + showgrid="false" + inkscape:window-width="979" + inkscape:window-height="836" + inkscape:window-x="571" + inkscape:window-y="335" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title></dc:title> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-28.441125,-185.60612)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991"></flowPara></flowRoot> <g + id="g4433" + transform="translate(2,0)"> + <text + sodipodi:linespacing="125%" + id="text2993" + y="-261.66608" + x="412.12299" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + xml:space="preserve" + transform="matrix(0,1,-1,0,0,0)"><tspan + y="-261.66608" + x="412.12299" + id="tspan2995" + sodipodi:role="line">synchronize_rcu()</tspan></text> + <g + id="g4417" + transform="matrix(0,1,-1,0,730.90257,222.4928)"> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)" + d="m 97.580736,477.4048 183.140664,0" + id="path2997" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 96.752718,465.38398 0,22.62742" + id="path4397" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 281.54942,465.38397 0,22.62742" + id="path4397-5" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + </g> + </g> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.04738" + y="268.18076" + id="text4429" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431" + x="112.04738" + y="268.18076">WRITE_ONCE(a, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.04738" + y="439.13766" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="112.04738" + y="439.13766">WRITE_ONCE(b, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="255.60869" + y="309.29346" + id="text4445" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4447" + x="255.60869" + y="309.29346">r1 = READ_ONCE(a);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="255.14423" + y="520.61786" + id="text4449" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4451" + x="255.14423" + y="520.61786">WRITE_ONCE(c, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="384.71124" + id="text4453" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4455" + x="396.10254" + y="384.71124">r2 = READ_ONCE(b);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="582.13617" + id="text4457" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4459" + x="396.10254" + y="582.13617">r3 = READ_ONCE(c);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.08231" + y="213.91006" + id="text4461" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463" + x="112.08231" + y="213.91006">thread0()</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="252.34512" + y="213.91006" + id="text4461-6" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463-0" + x="252.34512" + y="213.91006">thread1()</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.42557" + y="213.91006" + id="text4461-2" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463-2" + x="396.42557" + y="213.91006">thread2()</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect4495" + width="436.28488" + height="416.4859" + x="34.648232" + y="191.10612" /> + <path + style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + d="m 183.14066,191.10612 0,417.193 -0.70711,0" + id="path4497" + inkscape:connector-curvature="0" /> + <path + style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + d="m 325.13867,191.10612 0,417.193 -0.70711,0" + id="path4497-5" + inkscape:connector-curvature="0" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="111.75929" + y="251.53981" + id="text4429-8" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9" + x="111.75929" + y="251.53981">rcu_read_lock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="367.91556" + id="text4429-8-9" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4" + x="396.10254" + y="367.91556">rcu_read_lock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="597.40289" + id="text4429-8-9-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4-4" + x="396.10254" + y="597.40289">rcu_read_unlock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="111.75929" + y="453.15311" + id="text4429-8-9-3-1" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4-4-6" + x="111.75929" + y="453.15311">rcu_read_unlock();</tspan></text> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 33.941125,227.87568 436.284885,0 0,0.7071" + id="path4608" + inkscape:connector-curvature="0" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="394.94427" + y="345.66351" + id="text4648" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650" + x="394.94427" + y="345.66351">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(36.441125,199.60612)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.11968" + y="475.77856" + id="text4648-4" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-4" + x="112.11968" + y="475.77856">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-7" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(-246.38346,329.72117)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <path + sodipodi:type="arc" + style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-7-7" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(-103.65246,202.90878)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="254.85066" + y="348.96619" + id="text4648-4-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-4-5" + x="254.85066" + y="348.96619">QS</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Requirements/RCUApplicability.svg b/Documentation/RCU/Design/Requirements/RCUApplicability.svg new file mode 100644 index 000000000000..ebcbeee391ed --- /dev/null +++ b/Documentation/RCU/Design/Requirements/RCUApplicability.svg @@ -0,0 +1,237 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Creator: fig2dev Version 3.2 Patchlevel 5d --> + +<!-- CreationDate: Tue Mar 4 18:34:25 2014 --> + +<!-- Magnification: 3.000 --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="1089.1382" + height="668.21368" + viewBox="-2121 -36 14554.634 8876.4061" + id="svg2" + version="1.1" + inkscape:version="0.48.3.1 r9886" + sodipodi:docname="RCUApplicability.svg"> + <metadata + id="metadata40"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <defs + id="defs38" /> + <sodipodi:namedview + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1" + objecttolerance="10" + gridtolerance="10" + guidetolerance="10" + inkscape:pageopacity="0" + inkscape:pageshadow="2" + inkscape:window-width="849" + inkscape:window-height="639" + id="namedview36" + showgrid="false" + inkscape:zoom="0.51326165" + inkscape:cx="544.56912" + inkscape:cy="334.10686" + inkscape:window-x="149" + inkscape:window-y="448" + inkscape:window-maximized="0" + inkscape:current-layer="g4" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <g + style="fill:none;stroke-width:0.025in" + id="g4" + transform="translate(-2043.6828,14.791398)"> + <!-- Line: box --> + <rect + x="0" + y="0" + width="14400" + height="8775" + rx="0" + style="fill:#ffa1a1;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" + id="rect6" /> + <!-- Line: box --> + <rect + x="1350" + y="0" + width="11700" + height="6075" + rx="0" + style="fill:#ffff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" + id="rect8" /> + <!-- Line: box --> + <rect + x="2700" + y="0" + width="9000" + height="4275" + rx="0" + style="fill:#00ff00;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" + id="rect10" /> + <!-- Line: box --> + <rect + x="4050" + y="0" + width="6300" + height="2475" + rx="0" + style="fill:#87cfff;stroke:#000000;stroke-width:21;stroke-linecap:butt;stroke-linejoin:miter" + id="rect12" /> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="900" + font-style="normal" + font-weight="normal" + font-size="324" + id="text14" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3017">Read-Mostly, Stale &</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="1350" + font-style="normal" + font-weight="normal" + font-size="324" + id="text16" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3019">Inconsistent Data OK</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="1800" + font-style="normal" + font-weight="normal" + font-size="324" + id="text18" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3021">(RCU Works Great!!!)</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="3825" + font-style="normal" + font-weight="normal" + font-size="324" + id="text20" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3023">(RCU Works Well)</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="3375" + font-style="normal" + font-weight="normal" + font-size="324" + id="text22" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3025">Read-Mostly, Need Consistent Data</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="5175" + font-style="normal" + font-weight="normal" + font-size="324" + id="text24" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3027">Read-Write, Need Consistent Data</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="6975" + font-style="normal" + font-weight="normal" + font-size="324" + id="text26" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + sodipodi:linespacing="125%">Update-Mostly, Need Consistent Data</text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="5625" + font-style="normal" + font-weight="normal" + font-size="324" + id="text28" + sodipodi:linespacing="125%" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L"><tspan + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + id="tspan3029">(RCU Might Be OK...)</tspan></text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="7875" + font-style="normal" + font-weight="normal" + font-size="324" + id="text30" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + sodipodi:linespacing="125%">(1) Provide Existence Guarantees For Update-Friendly Mechanisms</text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="8325" + font-style="normal" + font-weight="normal" + font-size="324" + id="text32" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + sodipodi:linespacing="125%">(2) Provide Wait-Free Read-Side Primitives for Real-Time Use)</text> + <!-- Text --> + <text + xml:space="preserve" + x="7200" + y="7425" + font-style="normal" + font-weight="normal" + font-size="324" + id="text34" + style="font-size:427.63009644px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;writing-mode:lr-tb;text-anchor:middle;fill:#000000;font-family:Nimbus Sans L;-inkscape-font-specification:Nimbus Sans L" + sodipodi:linespacing="125%">(RCU is Very Unlikely to be the Right Tool For The Job, But it Can:</text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg b/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg new file mode 100644 index 000000000000..48cd1623d4d4 --- /dev/null +++ b/Documentation/RCU/Design/Requirements/ReadersPartitionGP1.svg @@ -0,0 +1,639 @@ +<?xml version="1.0" encoding="UTF-8" standalone="no"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> + +<svg + xmlns:dc="http://purl.org/dc/elements/1.1/" + xmlns:cc="http://creativecommons.org/ns#" + xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns="http://www.w3.org/2000/svg" + xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd" + xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape" + width="735.25" + height="516.21875" + id="svg2" + version="1.1" + inkscape:version="0.48.3.1 r9886" + sodipodi:docname="ReadersPartitionGP1.svg"> + <defs + id="defs4"> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend" + style="overflow:visible"> + <path + id="path3792" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart" + style="overflow:visible"> + <path + id="path3789" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lstart" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lstart-4" + style="overflow:visible"> + <path + id="path3789-9" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(1.1,0,0,1.1,1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + <marker + inkscape:stockid="Arrow2Lend" + orient="auto" + refY="0" + refX="0" + id="Arrow2Lend-4" + style="overflow:visible"> + <path + id="path3792-4" + style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round" + d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z" + transform="matrix(-1.1,0,0,-1.1,-1.1,0)" + inkscape:connector-curvature="0" /> + </marker> + </defs> + <sodipodi:namedview + id="base" + pagecolor="#ffffff" + bordercolor="#666666" + borderopacity="1.0" + inkscape:pageopacity="0.0" + inkscape:pageshadow="2" + inkscape:zoom="1.3670394" + inkscape:cx="367.26465" + inkscape:cy="258.46182" + inkscape:document-units="px" + inkscape:current-layer="g4433-6" + showgrid="false" + inkscape:window-width="1351" + inkscape:window-height="836" + inkscape:window-x="438" + inkscape:window-y="335" + inkscape:window-maximized="0" + fit-margin-top="5" + fit-margin-left="5" + fit-margin-right="5" + fit-margin-bottom="5" /> + <metadata + id="metadata7"> + <rdf:RDF> + <cc:Work + rdf:about=""> + <dc:format>image/svg+xml</dc:format> + <dc:type + rdf:resource="http://purl.org/dc/dcmitype/StillImage" /> + <dc:title /> + </cc:Work> + </rdf:RDF> + </metadata> + <g + inkscape:label="Layer 1" + inkscape:groupmode="layer" + id="layer1" + transform="translate(-29.15625,-185.59375)"> + <flowRoot + xml:space="preserve" + id="flowRoot2985" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion + id="flowRegion2987"><rect + id="rect2989" + width="82.85714" + height="11.428572" + x="240" + y="492.36218" /></flowRegion><flowPara + id="flowPara2991" /></flowRoot> <g + id="g4433" + transform="translate(2,-12)"> + <text + sodipodi:linespacing="125%" + id="text2993" + y="-261.66608" + x="436.12299" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + xml:space="preserve" + transform="matrix(0,1,-1,0,0,0)"><tspan + y="-261.66608" + x="436.12299" + id="tspan2995" + sodipodi:role="line">synchronize_rcu()</tspan></text> + <g + id="g4417" + transform="matrix(0,1,-1,0,730.90257,222.4928)"> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)" + d="M 97.580736,477.4048 327.57913,476.09759" + id="path2997" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 96.752718,465.38398 0,22.62742" + id="path4397" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 328.40703,465.38397 0,22.62742" + id="path4397-5" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + </g> + </g> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.04738" + y="268.18076" + id="text4429" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431" + x="112.04738" + y="268.18076">WRITE_ONCE(a, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.04738" + y="487.13766" + id="text4441" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4443" + x="112.04738" + y="487.13766">WRITE_ONCE(b, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="255.60869" + y="297.29346" + id="text4445" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4447" + x="255.60869" + y="297.29346">r1 = READ_ONCE(a);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="255.14423" + y="554.61786" + id="text4449" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4451" + x="255.14423" + y="554.61786">WRITE_ONCE(c, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="370.71124" + id="text4453" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4455" + x="396.10254" + y="370.71124">WRITE_ONCE(d, 1);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="572.13617" + id="text4457" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4459" + x="396.10254" + y="572.13617">r2 = READ_ONCE(c);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.08231" + y="213.91006" + id="text4461" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463" + x="112.08231" + y="213.91006">thread0()</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="252.34512" + y="213.91006" + id="text4461-6" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463-0" + x="252.34512" + y="213.91006">thread1()</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.42557" + y="213.91006" + id="text4461-2" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463-2" + x="396.42557" + y="213.91006">thread2()</tspan></text> + <rect + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="rect4495" + width="724.25244" + height="505.21201" + x="34.648232" + y="191.10612" /> + <path + style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + d="m 183.14066,191.10612 0,504.24243" + id="path4497" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + d="m 325.13867,191.10612 0,504.24243" + id="path4497-5" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="111.75929" + y="251.53981" + id="text4429-8" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9" + x="111.75929" + y="251.53981">rcu_read_lock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="353.91556" + id="text4429-8-9" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4" + x="396.10254" + y="353.91556">rcu_read_lock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="396.10254" + y="587.40289" + id="text4429-8-9-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4-4" + x="396.10254" + y="587.40289">rcu_read_unlock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="111.75929" + y="501.15311" + id="text4429-8-9-3-1" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4-4-6" + x="111.75929" + y="501.15311">rcu_read_unlock();</tspan></text> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 33.941125,227.87568 724.941765,0" + id="path4608" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="394.94427" + y="331.66351" + id="text4648" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650" + x="394.94427" + y="331.66351">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(36.441125,185.60612)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="112.11968" + y="523.77856" + id="text4648-4" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-4" + x="112.11968" + y="523.77856">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-7" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(-246.38346,377.72117)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <path + sodipodi:type="arc" + style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-7-7" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(-103.65246,190.90878)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="254.85066" + y="336.96619" + id="text4648-4-3" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-4-5" + x="254.85066" + y="336.96619">QS</tspan></text> + <path + style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + d="m 470.93311,190.39903 0,504.24243" + id="path4497-5-6" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + d="m 616.22755,190.38323 0,504.24243" + id="path4497-5-2" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <g + id="g4433-6" + transform="translate(288.0964,78.32827)"> + <text + sodipodi:linespacing="125%" + id="text2993-7" + y="-261.66608" + x="440.12299" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + xml:space="preserve" + transform="matrix(0,1,-1,0,0,0)"><tspan + y="-261.66608" + x="440.12299" + id="tspan2995-1" + sodipodi:role="line">synchronize_rcu()</tspan></text> + <g + id="g4417-1" + transform="matrix(0,1,-1,0,730.90257,222.4928)"> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-start:url(#Arrow2Lstart);marker-end:url(#Arrow2Lend)" + d="M 97.580736,477.4048 328.5624,477.07246" + id="path2997-2" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 96.752718,465.38398 0,22.62742" + id="path4397-3" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + <path + style="fill:none;stroke:#000000;stroke-width:1px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1" + d="m 329.39039,465.38397 0,22.62742" + id="path4397-5-4" + inkscape:connector-curvature="0" + sodipodi:nodetypes="cc" /> + </g> + </g> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="541.70508" + y="387.6217" + id="text4445-0" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4447-5" + x="541.70508" + y="387.6217">r3 = READ_ONCE(d);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="541.2406" + y="646.94611" + id="text4449-6" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4451-6" + x="541.2406" + y="646.94611">WRITE_ONCE(e, 1);</tspan></text> + <path + sodipodi:type="arc" + style="fill:#ffffff;fill-opacity:1;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-7-7-5" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(182.44393,281.23704)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="540.94702" + y="427.29443" + id="text4648-4-3-1" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-4-5-7" + x="540.94702" + y="427.29443">QS</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="686.27747" + y="461.83929" + id="text4453-7" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4455-1" + x="686.27747" + y="461.83929">r4 = READ_ONCE(b);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="686.27747" + y="669.26422" + id="text4457-9" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4459-2" + x="686.27747" + y="669.26422">r5 = READ_ONCE(e);</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="686.27747" + y="445.04358" + id="text4429-8-9-33" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4-2" + x="686.27747" + y="445.04358">rcu_read_lock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="686.27747" + y="684.53094" + id="text4429-8-9-3-8" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4431-9-4-4-5" + x="686.27747" + y="684.53094">rcu_read_unlock();</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="685.11914" + y="422.79153" + id="text4648-9" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-7" + x="685.11914" + y="422.79153">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-8" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(326.61602,276.73415)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="397.85934" + y="609.59003" + id="text4648-5" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-77" + x="397.85934" + y="609.59003">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-80" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(39.356201,463.53264)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="256.75986" + y="586.99133" + id="text4648-5-2" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4650-77-7" + x="256.75986" + y="586.99133">QS</tspan></text> + <path + sodipodi:type="arc" + style="fill:none;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" + id="path4652-80-5" + sodipodi:cx="358.85669" + sodipodi:cy="142.87541" + sodipodi:rx="10.960155" + sodipodi:ry="10.253048" + d="m 358.86939,132.62237 a 10.960155,10.253048 0 1 1 -0.0228,0" + transform="translate(-101.74328,440.93395)" + sodipodi:start="4.7135481" + sodipodi:end="10.994651" + sodipodi:open="true" /> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="546.22791" + y="213.91006" + id="text4461-2-5" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463-2-6" + x="546.22791" + y="213.91006">thread3()</tspan></text> + <text + xml:space="preserve" + style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol" + x="684.00067" + y="213.91006" + id="text4461-2-1" + sodipodi:linespacing="125%"><tspan + sodipodi:role="line" + id="tspan4463-2-0" + x="684.00067" + y="213.91006">thread4()</tspan></text> + </g> +</svg> diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html new file mode 100644 index 000000000000..a725f9900ec8 --- /dev/null +++ b/Documentation/RCU/Design/Requirements/Requirements.html @@ -0,0 +1,2897 @@ +<!-- DO NOT HAND EDIT. --> +<!-- Instead, edit Documentation/RCU/Design/Requirements/Requirements.htmlx and run 'sh htmlqqz.sh Documentation/RCU/Design/Requirements/Requirements' --> +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> + <html> + <head><title>A Tour Through RCU's Requirements [LWN.net]</title> + <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8"> + +<h1>A Tour Through RCU's Requirements</h1> + +<p>Copyright IBM Corporation, 2015</p> +<p>Author: Paul E. McKenney</p> +<p><i>The initial version of this document appeared in the +<a href="https://lwn.net/">LWN</a> articles +<a href="https://lwn.net/Articles/652156/">here</a>, +<a href="https://lwn.net/Articles/652677/">here</a>, and +<a href="https://lwn.net/Articles/653326/">here</a>.</i></p> + +<h2>Introduction</h2> + +<p> +Read-copy update (RCU) is a synchronization mechanism that is often +used as a replacement for reader-writer locking. +RCU is unusual in that updaters do not block readers, +which means that RCU's read-side primitives can be exceedingly fast +and scalable. +In addition, updaters can make useful forward progress concurrently +with readers. +However, all this concurrency between RCU readers and updaters does raise +the question of exactly what RCU readers are doing, which in turn +raises the question of exactly what RCU's requirements are. + +<p> +This document therefore summarizes RCU's requirements, and can be thought +of as an informal, high-level specification for RCU. +It is important to understand that RCU's specification is primarily +empirical in nature; +in fact, I learned about many of these requirements the hard way. +This situation might cause some consternation, however, not only +has this learning process been a lot of fun, but it has also been +a great privilege to work with so many people willing to apply +technologies in interesting new ways. + +<p> +All that aside, here are the categories of currently known RCU requirements: +</p> + +<ol> +<li> <a href="#Fundamental Requirements"> + Fundamental Requirements</a> +<li> <a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a> +<li> <a href="#Parallelism Facts of Life"> + Parallelism Facts of Life</a> +<li> <a href="#Quality-of-Implementation Requirements"> + Quality-of-Implementation Requirements</a> +<li> <a href="#Linux Kernel Complications"> + Linux Kernel Complications</a> +<li> <a href="#Software-Engineering Requirements"> + Software-Engineering Requirements</a> +<li> <a href="#Other RCU Flavors"> + Other RCU Flavors</a> +<li> <a href="#Possible Future Changes"> + Possible Future Changes</a> +</ol> + +<p> +This is followed by a <a href="#Summary">summary</a>, +which is in turn followed by the inevitable +<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>. + +<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2> + +<p> +RCU's fundamental requirements are the closest thing RCU has to hard +mathematical requirements. +These are: + +<ol> +<li> <a href="#Grace-Period Guarantee"> + Grace-Period Guarantee</a> +<li> <a href="#Publish-Subscribe Guarantee"> + Publish-Subscribe Guarantee</a> +<li> <a href="#Memory-Barrier Guarantees"> + Memory-Barrier Guarantees</a> +<li> <a href="#RCU Primitives Guaranteed to Execute Unconditionally"> + RCU Primitives Guaranteed to Execute Unconditionally</a> +<li> <a href="#Guaranteed Read-to-Write Upgrade"> + Guaranteed Read-to-Write Upgrade</a> +</ol> + +<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3> + +<p> +RCU's grace-period guarantee is unusual in being premeditated: +Jack Slingwine and I had this guarantee firmly in mind when we started +work on RCU (then called “rclock”) in the early 1990s. +That said, the past two decades of experience with RCU have produced +a much more detailed understanding of this guarantee. + +<p> +RCU's grace-period guarantee allows updaters to wait for the completion +of all pre-existing RCU read-side critical sections. +An RCU read-side critical section +begins with the marker <tt>rcu_read_lock()</tt> and ends with +the marker <tt>rcu_read_unlock()</tt>. +These markers may be nested, and RCU treats a nested set as one +big RCU read-side critical section. +Production-quality implementations of <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> are extremely lightweight, and in +fact have exactly zero overhead in Linux kernels built for production +use with <tt>CONFIG_PREEMPT=n</tt>. + +<p> +This guarantee allows ordering to be enforced with extremely low +overhead to readers, for example: + +<blockquote> +<pre> + 1 int x, y; + 2 + 3 void thread0(void) + 4 { + 5 rcu_read_lock(); + 6 r1 = READ_ONCE(x); + 7 r2 = READ_ONCE(y); + 8 rcu_read_unlock(); + 9 } +10 +11 void thread1(void) +12 { +13 WRITE_ONCE(x, 1); +14 synchronize_rcu(); +15 WRITE_ONCE(y, 1); +16 } +</pre> +</blockquote> + +<p> +Because the <tt>synchronize_rcu()</tt> on line 14 waits for +all pre-existing readers, any instance of <tt>thread0()</tt> that +loads a value of zero from <tt>x</tt> must complete before +<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must +also load a value of zero from <tt>y</tt>. +Similarly, any instance of <tt>thread0()</tt> that loads a value of +one from <tt>y</tt> must have started after the +<tt>synchronize_rcu()</tt> started, and must therefore also load +a value of one from <tt>x</tt>. +Therefore, the outcome: +<blockquote> +<pre> +(r1 == 0 && r2 == 1) +</pre> +</blockquote> +cannot happen. + +<p><a name="Quick Quiz 1"><b>Quick Quiz 1</b>:</a> +Wait a minute! +You said that updaters can make useful forward progress concurrently +with readers, but pre-existing readers will block +<tt>synchronize_rcu()</tt>!!! +Just who are you trying to fool??? +<br><a href="#qq1answer">Answer</a> + +<p> +This scenario resembles one of the first uses of RCU in +<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>, +which managed a distributed lock manager's transition into +a state suitable for handling recovery from node failure, +more or less as follows: + +<blockquote> +<pre> + 1 #define STATE_NORMAL 0 + 2 #define STATE_WANT_RECOVERY 1 + 3 #define STATE_RECOVERING 2 + 4 #define STATE_WANT_NORMAL 3 + 5 + 6 int state = STATE_NORMAL; + 7 + 8 void do_something_dlm(void) + 9 { +10 int state_snap; +11 +12 rcu_read_lock(); +13 state_snap = READ_ONCE(state); +14 if (state_snap == STATE_NORMAL) +15 do_something(); +16 else +17 do_something_carefully(); +18 rcu_read_unlock(); +19 } +20 +21 void start_recovery(void) +22 { +23 WRITE_ONCE(state, STATE_WANT_RECOVERY); +24 synchronize_rcu(); +25 WRITE_ONCE(state, STATE_RECOVERING); +26 recovery(); +27 WRITE_ONCE(state, STATE_WANT_NORMAL); +28 synchronize_rcu(); +29 WRITE_ONCE(state, STATE_NORMAL); +30 } +</pre> +</blockquote> + +<p> +The RCU read-side critical section in <tt>do_something_dlm()</tt> +works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt> +to guarantee that <tt>do_something()</tt> never runs concurrently +with <tt>recovery()</tt>, but with little or no synchronization +overhead in <tt>do_something_dlm()</tt>. + +<p><a name="Quick Quiz 2"><b>Quick Quiz 2</b>:</a> +Why is the <tt>synchronize_rcu()</tt> on line 28 needed? +<br><a href="#qq2answer">Answer</a> + +<p> +In order to avoid fatal problems such as deadlocks, +an RCU read-side critical section must not contain calls to +<tt>synchronize_rcu()</tt>. +Similarly, an RCU read-side critical section must not +contain anything that waits, directly or indirectly, on completion of +an invocation of <tt>synchronize_rcu()</tt>. + +<p> +Although RCU's grace-period guarantee is useful in and of itself, with +<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>, +it would be good to be able to use RCU to coordinate read-side +access to linked data structures. +For this, the grace-period guarantee is not sufficient, as can +be seen in function <tt>add_gp_buggy()</tt> below. +We will look at the reader's code later, but in the meantime, just think of +the reader as locklessly picking up the <tt>gp</tt> pointer, +and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the +<tt>->a</tt> and <tt>->b</tt> fields. + +<blockquote> +<pre> + 1 bool add_gp_buggy(int a, int b) + 2 { + 3 p = kmalloc(sizeof(*p), GFP_KERNEL); + 4 if (!p) + 5 return -ENOMEM; + 6 spin_lock(&gp_lock); + 7 if (rcu_access_pointer(gp)) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +11 p->a = a; +12 p->b = a; +13 gp = p; /* ORDERING BUG */ +14 spin_unlock(&gp_lock); +15 return true; +16 } +</pre> +</blockquote> + +<p> +The problem is that both the compiler and weakly ordered CPUs are within +their rights to reorder this code as follows: + +<blockquote> +<pre> + 1 bool add_gp_buggy_optimized(int a, int b) + 2 { + 3 p = kmalloc(sizeof(*p), GFP_KERNEL); + 4 if (!p) + 5 return -ENOMEM; + 6 spin_lock(&gp_lock); + 7 if (rcu_access_pointer(gp)) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +<b>11 gp = p; /* ORDERING BUG */ +12 p->a = a; +13 p->b = a;</b> +14 spin_unlock(&gp_lock); +15 return true; +16 } +</pre> +</blockquote> + +<p> +If an RCU reader fetches <tt>gp</tt> just after +<tt>add_gp_buggy_optimized</tt> executes line 11, +it will see garbage in the <tt>->a</tt> and <tt>->b</tt> +fields. +And this is but one of many ways in which compiler and hardware optimizations +could cause trouble. +Therefore, we clearly need some way to prevent the compiler and the CPU from +reordering in this manner, which brings us to the publish-subscribe +guarantee discussed in the next section. + +<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3> + +<p> +RCU's publish-subscribe guarantee allows data to be inserted +into a linked data structure without disrupting RCU readers. +The updater uses <tt>rcu_assign_pointer()</tt> to insert the +new data, and readers use <tt>rcu_dereference()</tt> to +access data, whether new or old. +The following shows an example of insertion: + +<blockquote> +<pre> + 1 bool add_gp(int a, int b) + 2 { + 3 p = kmalloc(sizeof(*p), GFP_KERNEL); + 4 if (!p) + 5 return -ENOMEM; + 6 spin_lock(&gp_lock); + 7 if (rcu_access_pointer(gp)) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +11 p->a = a; +12 p->b = a; +13 rcu_assign_pointer(gp, p); +14 spin_unlock(&gp_lock); +15 return true; +16 } +</pre> +</blockquote> + +<p> +The <tt>rcu_assign_pointer()</tt> on line 13 is conceptually +equivalent to a simple assignment statement, but also guarantees +that its assignment will +happen after the two assignments in lines 11 and 12, +similar to the C11 <tt>memory_order_release</tt> store operation. +It also prevents any number of “interesting” compiler +optimizations, for example, the use of <tt>gp</tt> as a scratch +location immediately preceding the assignment. + +<p><a name="Quick Quiz 3"><b>Quick Quiz 3</b>:</a> +But <tt>rcu_assign_pointer()</tt> does nothing to prevent the +two assignments to <tt>p->a</tt> and <tt>p->b</tt> +from being reordered. +Can't that also cause problems? +<br><a href="#qq3answer">Answer</a> + +<p> +It is tempting to assume that the reader need not do anything special +to control its accesses to the RCU-protected data, +as shown in <tt>do_something_gp_buggy()</tt> below: + +<blockquote> +<pre> + 1 bool do_something_gp_buggy(void) + 2 { + 3 rcu_read_lock(); + 4 p = gp; /* OPTIMIZATIONS GALORE!!! */ + 5 if (p) { + 6 do_something(p->a, p->b); + 7 rcu_read_unlock(); + 8 return true; + 9 } +10 rcu_read_unlock(); +11 return false; +12 } +</pre> +</blockquote> + +<p> +However, this temptation must be resisted because there are a +surprisingly large number of ways that the compiler +(to say nothing of +<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>) +can trip this code up. +For but one example, if the compiler were short of registers, it +might choose to refetch from <tt>gp</tt> rather than keeping +a separate copy in <tt>p</tt> as follows: + +<blockquote> +<pre> + 1 bool do_something_gp_buggy_optimized(void) + 2 { + 3 rcu_read_lock(); + 4 if (gp) { /* OPTIMIZATIONS GALORE!!! */ +<b> 5 do_something(gp->a, gp->b);</b> + 6 rcu_read_unlock(); + 7 return true; + 8 } + 9 rcu_read_unlock(); +10 return false; +11 } +</pre> +</blockquote> + +<p> +If this function ran concurrently with a series of updates that +replaced the current structure with a new one, +the fetches of <tt>gp->a</tt> +and <tt>gp->b</tt> might well come from two different structures, +which could cause serious confusion. +To prevent this (and much else besides), <tt>do_something_gp()</tt> uses +<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>: + +<blockquote> +<pre> + 1 bool do_something_gp(void) + 2 { + 3 rcu_read_lock(); + 4 p = rcu_dereference(gp); + 5 if (p) { + 6 do_something(p->a, p->b); + 7 rcu_read_unlock(); + 8 return true; + 9 } +10 rcu_read_unlock(); +11 return false; +12 } +</pre> +</blockquote> + +<p> +The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha) +memory barriers in the Linux kernel. +Should a +<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a> +ever appear, then <tt>rcu_dereference()</tt> could be implemented +as a <tt>memory_order_consume</tt> load. +Regardless of the exact implementation, a pointer fetched by +<tt>rcu_dereference()</tt> may not be used outside of the +outermost RCU read-side critical section containing that +<tt>rcu_dereference()</tt>, unless protection of +the corresponding data element has been passed from RCU to some +other synchronization mechanism, most commonly locking or +<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>. + +<p> +In short, updaters use <tt>rcu_assign_pointer()</tt> and readers +use <tt>rcu_dereference()</tt>, and these two RCU API elements +work together to ensure that readers have a consistent view of +newly added data elements. + +<p> +Of course, it is also necessary to remove elements from RCU-protected +data structures, for example, using the following process: + +<ol> +<li> Remove the data element from the enclosing structure. +<li> Wait for all pre-existing RCU read-side critical sections + to complete (because only pre-existing readers can possibly have + a reference to the newly removed data element). +<li> At this point, only the updater has a reference to the + newly removed data element, so it can safely reclaim + the data element, for example, by passing it to <tt>kfree()</tt>. +</ol> + +This process is implemented by <tt>remove_gp_synchronous()</tt>: + +<blockquote> +<pre> + 1 bool remove_gp_synchronous(void) + 2 { + 3 struct foo *p; + 4 + 5 spin_lock(&gp_lock); + 6 p = rcu_access_pointer(gp); + 7 if (!p) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +11 rcu_assign_pointer(gp, NULL); +12 spin_unlock(&gp_lock); +13 synchronize_rcu(); +14 kfree(p); +15 return true; +16 } +</pre> +</blockquote> + +<p> +This function is straightforward, with line 13 waiting for a grace +period before line 14 frees the old data element. +This waiting ensures that readers will reach line 7 of +<tt>do_something_gp()</tt> before the data element referenced by +<tt>p</tt> is freed. +The <tt>rcu_access_pointer()</tt> on line 6 is similar to +<tt>rcu_dereference()</tt>, except that: + +<ol> +<li> The value returned by <tt>rcu_access_pointer()</tt> + cannot be dereferenced. + If you want to access the value pointed to as well as + the pointer itself, use <tt>rcu_dereference()</tt> + instead of <tt>rcu_access_pointer()</tt>. +<li> The call to <tt>rcu_access_pointer()</tt> need not be + protected. + In contrast, <tt>rcu_dereference()</tt> must either be + within an RCU read-side critical section or in a code + segment where the pointer cannot change, for example, in + code protected by the corresponding update-side lock. +</ol> + +<p><a name="Quick Quiz 4"><b>Quick Quiz 4</b>:</a> +Without the <tt>rcu_dereference()</tt> or the +<tt>rcu_access_pointer()</tt>, what destructive optimizations +might the compiler make use of? +<br><a href="#qq4answer">Answer</a> + +<p> +In short, RCU's publish-subscribe guarantee is provided by the combination +of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>. +This guarantee allows data elements to be safely added to RCU-protected +linked data structures without disrupting RCU readers. +This guarantee can be used in combination with the grace-period +guarantee to also allow data elements to be removed from RCU-protected +linked data structures, again without disrupting RCU readers. + +<p> +This guarantee was only partially premeditated. +DYNIX/ptx used an explicit memory barrier for publication, but had nothing +resembling <tt>rcu_dereference()</tt> for subscription, nor did it +have anything resembling the <tt>smp_read_barrier_depends()</tt> +that was later subsumed into <tt>rcu_dereference()</tt>. +The need for these operations made itself known quite suddenly at a +late-1990s meeting with the DEC Alpha architects, back in the days when +DEC was still a free-standing company. +It took the Alpha architects a good hour to convince me that any sort +of barrier would ever be needed, and it then took me a good <i>two</i> hours +to convince them that their documentation did not make this point clear. +More recent work with the C and C++ standards committees have provided +much education on tricks and traps from the compiler. +In short, compilers were much less tricky in the early 1990s, but in +2015, don't even think about omitting <tt>rcu_dereference()</tt>! + +<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3> + +<p> +The previous section's simple linked-data-structure scenario clearly +demonstrates the need for RCU's stringent memory-ordering guarantees on +systems with more than one CPU: + +<ol> +<li> Each CPU that has an RCU read-side critical section that + begins before <tt>synchronize_rcu()</tt> starts is + guaranteed to execute a full memory barrier between the time + that the RCU read-side critical section ends and the time that + <tt>synchronize_rcu()</tt> returns. + Without this guarantee, a pre-existing RCU read-side critical section + might hold a reference to the newly removed <tt>struct foo</tt> + after the <tt>kfree()</tt> on line 14 of + <tt>remove_gp_synchronous()</tt>. +<li> Each CPU that has an RCU read-side critical section that ends + after <tt>synchronize_rcu()</tt> returns is guaranteed + to execute a full memory barrier between the time that + <tt>synchronize_rcu()</tt> begins and the time that the RCU + read-side critical section begins. + Without this guarantee, a later RCU read-side critical section + running after the <tt>kfree()</tt> on line 14 of + <tt>remove_gp_synchronous()</tt> might + later run <tt>do_something_gp()</tt> and find the + newly deleted <tt>struct foo</tt>. +<li> If the task invoking <tt>synchronize_rcu()</tt> remains + on a given CPU, then that CPU is guaranteed to execute a full + memory barrier sometime during the execution of + <tt>synchronize_rcu()</tt>. + This guarantee ensures that the <tt>kfree()</tt> on + line 14 of <tt>remove_gp_synchronous()</tt> really does + execute after the removal on line 11. +<li> If the task invoking <tt>synchronize_rcu()</tt> migrates + among a group of CPUs during that invocation, then each of the + CPUs in that group is guaranteed to execute a full memory barrier + sometime during the execution of <tt>synchronize_rcu()</tt>. + This guarantee also ensures that the <tt>kfree()</tt> on + line 14 of <tt>remove_gp_synchronous()</tt> really does + execute after the removal on + line 11, but also in the case where the thread executing the + <tt>synchronize_rcu()</tt> migrates in the meantime. +</ol> + +<p><a name="Quick Quiz 5"><b>Quick Quiz 5</b>:</a> +Given that multiple CPUs can start RCU read-side critical sections +at any time without any ordering whatsoever, how can RCU possibly tell whether +or not a given RCU read-side critical section starts before a +given instance of <tt>synchronize_rcu()</tt>? +<br><a href="#qq5answer">Answer</a> + +<p><a name="Quick Quiz 6"><b>Quick Quiz 6</b>:</a> +The first and second guarantees require unbelievably strict ordering! +Are all these memory barriers <i> really</i> required? +<br><a href="#qq6answer">Answer</a> + +<p> +Note that these memory-barrier requirements do not replace the fundamental +RCU requirement that a grace period wait for all pre-existing readers. +On the contrary, the memory barriers called out in this section must operate in +such a way as to <i>enforce</i> this fundamental requirement. +Of course, different implementations enforce this requirement in different +ways, but enforce it they must. + +<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3> + +<p> +The common-case RCU primitives are unconditional. +They are invoked, they do their job, and they return, with no possibility +of error, and no need to retry. +This is a key RCU design philosophy. + +<p> +However, this philosophy is pragmatic rather than pigheaded. +If someone comes up with a good justification for a particular conditional +RCU primitive, it might well be implemented and added. +After all, this guarantee was reverse-engineered, not premeditated. +The unconditional nature of the RCU primitives was initially an +accident of implementation, and later experience with synchronization +primitives with conditional primitives caused me to elevate this +accident to a guarantee. +Therefore, the justification for adding a conditional primitive to +RCU would need to be based on detailed and compelling use cases. + +<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3> + +<p> +As far as RCU is concerned, it is always possible to carry out an +update within an RCU read-side critical section. +For example, that RCU read-side critical section might search for +a given data element, and then might acquire the update-side +spinlock in order to update that element, all while remaining +in that RCU read-side critical section. +Of course, it is necessary to exit the RCU read-side critical section +before invoking <tt>synchronize_rcu()</tt>, however, this +inconvenience can be avoided through use of the +<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members +described later in this document. + +<p><a name="Quick Quiz 7"><b>Quick Quiz 7</b>:</a> +But how does the upgrade-to-write operation exclude other readers? +<br><a href="#qq7answer">Answer</a> + +<p> +This guarantee allows lookup code to be shared between read-side +and update-side code, and was premeditated, appearing in the earliest +DYNIX/ptx RCU documentation. + +<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2> + +<p> +RCU provides extremely lightweight readers, and its read-side guarantees, +though quite useful, are correspondingly lightweight. +It is therefore all too easy to assume that RCU is guaranteeing more +than it really is. +Of course, the list of things that RCU does not guarantee is infinitely +long, however, the following sections list a few non-guarantees that +have caused confusion. +Except where otherwise noted, these non-guarantees were premeditated. + +<ol> +<li> <a href="#Readers Impose Minimal Ordering"> + Readers Impose Minimal Ordering</a> +<li> <a href="#Readers Do Not Exclude Updaters"> + Readers Do Not Exclude Updaters</a> +<li> <a href="#Updaters Only Wait For Old Readers"> + Updaters Only Wait For Old Readers</a> +<li> <a href="#Grace Periods Don't Partition Read-Side Critical Sections"> + Grace Periods Don't Partition Read-Side Critical Sections</a> +<li> <a href="#Read-Side Critical Sections Don't Partition Grace Periods"> + Read-Side Critical Sections Don't Partition Grace Periods</a> +<li> <a href="#Disabling Preemption Does Not Block Grace Periods"> + Disabling Preemption Does Not Block Grace Periods</a> +</ol> + +<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3> + +<p> +Reader-side markers such as <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees +except through their interaction with the grace-period APIs such as +<tt>synchronize_rcu()</tt>. +To see this, consider the following pair of threads: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(x, 1); + 5 rcu_read_unlock(); + 6 rcu_read_lock(); + 7 WRITE_ONCE(y, 1); + 8 rcu_read_unlock(); + 9 } +10 +11 void thread1(void) +12 { +13 rcu_read_lock(); +14 r1 = READ_ONCE(y); +15 rcu_read_unlock(); +16 rcu_read_lock(); +17 r2 = READ_ONCE(x); +18 rcu_read_unlock(); +19 } +</pre> +</blockquote> + +<p> +After <tt>thread0()</tt> and <tt>thread1()</tt> execute +concurrently, it is quite possible to have + +<blockquote> +<pre> +(r1 == 1 && r2 == 0) +</pre> +</blockquote> + +(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>), +which would not be possible if <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> had much in the way of ordering +properties. +But they do not, so the CPU is within its rights +to do significant reordering. +This is by design: Any significant ordering constraints would slow down +these fast-path APIs. + +<p><a name="Quick Quiz 8"><b>Quick Quiz 8</b>:</a> +Can't the compiler also reorder this code? +<br><a href="#qq8answer">Answer</a> + +<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3> + +<p> +Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt> +exclude updates. +All they do is to prevent grace periods from ending. +The following example illustrates this: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 r1 = READ_ONCE(y); + 5 if (r1) { + 6 do_something_with_nonzero_x(); + 7 r2 = READ_ONCE(x); + 8 WARN_ON(!r2); /* BUG!!! */ + 9 } +10 rcu_read_unlock(); +11 } +12 +13 void thread1(void) +14 { +15 spin_lock(&my_lock); +16 WRITE_ONCE(x, 1); +17 WRITE_ONCE(y, 1); +18 spin_unlock(&my_lock); +19 } +</pre> +</blockquote> + +<p> +If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt> +excluded the <tt>thread1()</tt> function's update, +the <tt>WARN_ON()</tt> could never fire. +But the fact is that <tt>rcu_read_lock()</tt> does not exclude +much of anything aside from subsequent grace periods, of which +<tt>thread1()</tt> has none, so the +<tt>WARN_ON()</tt> can and does fire. + +<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3> + +<p> +It might be tempting to assume that after <tt>synchronize_rcu()</tt> +completes, there are no readers executing. +This temptation must be avoided because +new readers can start immediately after <tt>synchronize_rcu()</tt> +starts, and <tt>synchronize_rcu()</tt> is under no +obligation to wait for these new readers. + +<p><a name="Quick Quiz 9"><b>Quick Quiz 9</b>:</a> +Suppose that synchronize_rcu() did wait until all readers had completed. +Would the updater be able to rely on this? +<br><a href="#qq9answer">Answer</a> + +<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections"> +Grace Periods Don't Partition Read-Side Critical Sections</a></h3> + +<p> +It is tempting to assume that if any part of one RCU read-side critical +section precedes a given grace period, and if any part of another RCU +read-side critical section follows that same grace period, then all of +the first RCU read-side critical section must precede all of the second. +However, this just isn't the case: A single grace period does not +partition the set of RCU read-side critical sections. +An example of this situation can be illustrated as follows, where +<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(a, 1); + 5 WRITE_ONCE(b, 1); + 6 rcu_read_unlock(); + 7 } + 8 + 9 void thread1(void) +10 { +11 r1 = READ_ONCE(a); +12 synchronize_rcu(); +13 WRITE_ONCE(c, 1); +14 } +15 +16 void thread2(void) +17 { +18 rcu_read_lock(); +19 r2 = READ_ONCE(b); +20 r3 = READ_ONCE(c); +21 rcu_read_unlock(); +22 } +</pre> +</blockquote> + +<p> +It turns out that the outcome: + +<blockquote> +<pre> +(r1 == 1 && r2 == 0 && r3 == 1) +</pre> +</blockquote> + +is entirely possible. +The following figure show how this can happen, with each circled +<tt>QS</tt> indicating the point at which RCU recorded a +<i>quiescent state</i> for each thread, that is, a state in which +RCU knows that the thread cannot be in the midst of an RCU read-side +critical section that started before the current grace period: + +<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p> + +<p> +If it is necessary to partition RCU read-side critical sections in this +manner, it is necessary to use two grace periods, where the first +grace period is known to end before the second grace period starts: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(a, 1); + 5 WRITE_ONCE(b, 1); + 6 rcu_read_unlock(); + 7 } + 8 + 9 void thread1(void) +10 { +11 r1 = READ_ONCE(a); +12 synchronize_rcu(); +13 WRITE_ONCE(c, 1); +14 } +15 +16 void thread2(void) +17 { +18 r2 = READ_ONCE(c); +19 synchronize_rcu(); +20 WRITE_ONCE(d, 1); +21 } +22 +23 void thread3(void) +24 { +25 rcu_read_lock(); +26 r3 = READ_ONCE(b); +27 r4 = READ_ONCE(d); +28 rcu_read_unlock(); +29 } +</pre> +</blockquote> + +<p> +Here, if <tt>(r1 == 1)</tt>, then +<tt>thread0()</tt>'s write to <tt>b</tt> must happen +before the end of <tt>thread1()</tt>'s grace period. +If in addition <tt>(r4 == 1)</tt>, then +<tt>thread3()</tt>'s read from <tt>b</tt> must happen +after the beginning of <tt>thread2()</tt>'s grace period. +If it is also the case that <tt>(r2 == 1)</tt>, then the +end of <tt>thread1()</tt>'s grace period must precede the +beginning of <tt>thread2()</tt>'s grace period. +This mean that the two RCU read-side critical sections cannot overlap, +guaranteeing that <tt>(r3 == 1)</tt>. +As a result, the outcome: + +<blockquote> +<pre> +(r1 == 1 && r2 == 1 && r3 == 0 && r4 == 1) +</pre> +</blockquote> + +cannot happen. + +<p> +This non-requirement was also non-premeditated, but became apparent +when studying RCU's interaction with memory ordering. + +<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods"> +Read-Side Critical Sections Don't Partition Grace Periods</a></h3> + +<p> +It is also tempting to assume that if an RCU read-side critical section +happens between a pair of grace periods, then those grace periods cannot +overlap. +However, this temptation leads nowhere good, as can be illustrated by +the following, with all variables initially zero: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(a, 1); + 5 WRITE_ONCE(b, 1); + 6 rcu_read_unlock(); + 7 } + 8 + 9 void thread1(void) +10 { +11 r1 = READ_ONCE(a); +12 synchronize_rcu(); +13 WRITE_ONCE(c, 1); +14 } +15 +16 void thread2(void) +17 { +18 rcu_read_lock(); +19 WRITE_ONCE(d, 1); +20 r2 = READ_ONCE(c); +21 rcu_read_unlock(); +22 } +23 +24 void thread3(void) +25 { +26 r3 = READ_ONCE(d); +27 synchronize_rcu(); +28 WRITE_ONCE(e, 1); +29 } +30 +31 void thread4(void) +32 { +33 rcu_read_lock(); +34 r4 = READ_ONCE(b); +35 r5 = READ_ONCE(e); +36 rcu_read_unlock(); +37 } +</pre> +</blockquote> + +<p> +In this case, the outcome: + +<blockquote> +<pre> +(r1 == 1 && r2 == 1 && r3 == 1 && r4 == 0 && r5 == 1) +</pre> +</blockquote> + +is entirely possible, as illustrated below: + +<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p> + +<p> +Again, an RCU read-side critical section can overlap almost all of a +given grace period, just so long as it does not overlap the entire +grace period. +As a result, an RCU read-side critical section cannot partition a pair +of RCU grace periods. + +<p><a name="Quick Quiz 10"><b>Quick Quiz 10</b>:</a> +How long a sequence of grace periods, each separated by an RCU read-side +critical section, would be required to partition the RCU read-side +critical sections at the beginning and end of the chain? +<br><a href="#qq10answer">Answer</a> + +<h3><a name="Disabling Preemption Does Not Block Grace Periods"> +Disabling Preemption Does Not Block Grace Periods</a></h3> + +<p> +There was a time when disabling preemption on any given CPU would block +subsequent grace periods. +However, this was an accident of implementation and is not a requirement. +And in the current Linux-kernel implementation, disabling preemption +on a given CPU in fact does not block grace periods, as Oleg Nesterov +<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>. + +<p> +If you need a preempt-disable region to block grace periods, you need to add +<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example +as follows: + +<blockquote> +<pre> + 1 preempt_disable(); + 2 rcu_read_lock(); + 3 do_something(); + 4 rcu_read_unlock(); + 5 preempt_enable(); + 6 + 7 /* Spinlocks implicitly disable preemption. */ + 8 spin_lock(&mylock); + 9 rcu_read_lock(); +10 do_something(); +11 rcu_read_unlock(); +12 spin_unlock(&mylock); +</pre> +</blockquote> + +<p> +In theory, you could enter the RCU read-side critical section first, +but it is more efficient to keep the entire RCU read-side critical +section contained in the preempt-disable region as shown above. +Of course, RCU read-side critical sections that extend outside of +preempt-disable regions will work correctly, but such critical sections +can be preempted, which forces <tt>rcu_read_unlock()</tt> to do +more work. +And no, this is <i>not</i> an invitation to enclose all of your RCU +read-side critical sections within preempt-disable regions, because +doing so would degrade real-time response. + +<p> +This non-requirement appeared with preemptible RCU. +If you need a grace period that waits on non-preemptible code regions, use +<a href="#Sched Flavor">RCU-sched</a>. + +<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2> + +<p> +These parallelism facts of life are by no means specific to RCU, but +the RCU implementation must abide by them. +They therefore bear repeating: + +<ol> +<li> Any CPU or task may be delayed at any time, + and any attempts to avoid these delays by disabling + preemption, interrupts, or whatever are completely futile. + This is most obvious in preemptible user-level + environments and in virtualized environments (where + a given guest OS's VCPUs can be preempted at any time by + the underlying hypervisor), but can also happen in bare-metal + environments due to ECC errors, NMIs, and other hardware + events. + Although a delay of more than about 20 seconds can result + in splats, the RCU implementation is obligated to use + algorithms that can tolerate extremely long delays, but where + “extremely long” is not long enough to allow + wrap-around when incrementing a 64-bit counter. +<li> Both the compiler and the CPU can reorder memory accesses. + Where it matters, RCU must use compiler directives and + memory-barrier instructions to preserve ordering. +<li> Conflicting writes to memory locations in any given cache line + will result in expensive cache misses. + Greater numbers of concurrent writes and more-frequent + concurrent writes will result in more dramatic slowdowns. + RCU is therefore obligated to use algorithms that have + sufficient locality to avoid significant performance and + scalability problems. +<li> As a rough rule of thumb, only one CPU's worth of processing + may be carried out under the protection of any given exclusive + lock. + RCU must therefore use scalable locking designs. +<li> Counters are finite, especially on 32-bit systems. + RCU's use of counters must therefore tolerate counter wrap, + or be designed such that counter wrap would take way more + time than a single system is likely to run. + An uptime of ten years is quite possible, a runtime + of a century much less so. + As an example of the latter, RCU's dyntick-idle nesting counter + allows 54 bits for interrupt nesting level (this counter + is 64 bits even on a 32-bit system). + Overflowing this counter requires 2<sup>54</sup> + half-interrupts on a given CPU without that CPU ever going idle. + If a half-interrupt happened every microsecond, it would take + 570 years of runtime to overflow this counter, which is currently + believed to be an acceptably long time. +<li> Linux systems can have thousands of CPUs running a single + Linux kernel in a single shared-memory environment. + RCU must therefore pay close attention to high-end scalability. +</ol> + +<p> +This last parallelism fact of life means that RCU must pay special +attention to the preceding facts of life. +The idea that Linux might scale to systems with thousands of CPUs would +have been met with some skepticism in the 1990s, but these requirements +would have otherwise have been unsurprising, even in the early 1990s. + +<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2> + +<p> +These sections list quality-of-implementation requirements. +Although an RCU implementation that ignores these requirements could +still be used, it would likely be subject to limitations that would +make it inappropriate for industrial-strength production use. +Classes of quality-of-implementation requirements are as follows: + +<ol> +<li> <a href="#Specialization">Specialization</a> +<li> <a href="#Performance and Scalability">Performance and Scalability</a> +<li> <a href="#Composability">Composability</a> +<li> <a href="#Corner Cases">Corner Cases</a> +</ol> + +<p> +These classes is covered in the following sections. + +<h3><a name="Specialization">Specialization</a></h3> + +<p> +RCU is and always has been intended primarily for read-mostly situations, as +illustrated by the following figure. +This means that RCU's read-side primitives are optimized, often at the +expense of its update-side primitives. + +<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p> + +<p> +This focus on read-mostly situations means that RCU must interoperate +with other synchronization primitives. +For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt> +examples discussed earlier use RCU to protect readers and locking to +coordinate updaters. +However, the need extends much farther, requiring that a variety of +synchronization primitives be legal within RCU read-side critical sections, +including spinlocks, sequence locks, atomic operations, reference +counters, and memory barriers. + +<p><a name="Quick Quiz 11"><b>Quick Quiz 11</b>:</a> +What about sleeping locks? +<br><a href="#qq11answer">Answer</a> + +<p> +It often comes as a surprise that many algorithms do not require a +consistent view of data, but many can function in that mode, +with network routing being the poster child. +Internet routing algorithms take significant time to propagate +updates, so that by the time an update arrives at a given system, +that system has been sending network traffic the wrong way for +a considerable length of time. +Having a few threads continue to send traffic the wrong way for a +few more milliseconds is clearly not a problem: In the worst case, +TCP retransmissions will eventually get the data where it needs to go. +In general, when tracking the state of the universe outside of the +computer, some level of inconsistency must be tolerated due to +speed-of-light delays if nothing else. + +<p> +Furthermore, uncertainty about external state is inherent in many cases. +For example, a pair of veternarians might use heartbeat to determine +whether or not a given cat was alive. +But how long should they wait after the last heartbeat to decide that +the cat is in fact dead? +Waiting less than 400 milliseconds makes no sense because this would +mean that a relaxed cat would be considered to cycle between death +and life more than 100 times per minute. +Moreover, just as with human beings, a cat's heart might stop for +some period of time, so the exact wait period is a judgment call. +One of our pair of veternarians might wait 30 seconds before pronouncing +the cat dead, while the other might insist on waiting a full minute. +The two veternarians would then disagree on the state of the cat during +the final 30 seconds of the minute following the last heartbeat, as +fancifully illustrated below: + +<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p> + +<p> +Interestingly enough, this same situation applies to hardware. +When push comes to shove, how do we tell whether or not some +external server has failed? +We send messages to it periodically, and declare it failed if we +don't receive a response within a given period of time. +Policy decisions can usually tolerate short +periods of inconsistency. +The policy was decided some time ago, and is only now being put into +effect, so a few milliseconds of delay is normally inconsequential. + +<p> +However, there are algorithms that absolutely must see consistent data. +For example, the translation between a user-level SystemV semaphore +ID to the corresponding in-kernel data structure is protected by RCU, +but it is absolutely forbidden to update a semaphore that has just been +removed. +In the Linux kernel, this need for consistency is accommodated by acquiring +spinlocks located in the in-kernel data structure from within +the RCU read-side critical section, and this is indicated by the +green box in the figure above. +Many other techniques may be used, and are in fact used within the +Linux kernel. + +<p> +In short, RCU is not required to maintain consistency, and other +mechanisms may be used in concert with RCU when consistency is required. +RCU's specialization allows it to do its job extremely well, and its +ability to interoperate with other synchronization mechanisms allows +the right mix of synchronization tools to be used for a given job. + +<h3><a name="Performance and Scalability">Performance and Scalability</a></h3> + +<p> +Energy efficiency is a critical component of performance today, +and Linux-kernel RCU implementations must therefore avoid unnecessarily +awakening idle CPUs. +I cannot claim that this requirement was premeditated. +In fact, I learned of it during a telephone conversation in which I +was given “frank and open” feedback on the importance +of energy efficiency in battery-powered systems and on specific +energy-efficiency shortcomings of the Linux-kernel RCU implementation. +In my experience, the battery-powered embedded community will consider +any unnecessary wakeups to be extremely unfriendly acts. +So much so that mere Linux-kernel-mailing-list posts are +insufficient to vent their ire. + +<p> +Memory consumption is not particularly important for in most +situations, and has become decreasingly +so as memory sizes have expanded and memory +costs have plummeted. +However, as I learned from Matt Mackall's +<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a> +efforts, memory footprint is critically important on single-CPU systems with +non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus +<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a> +was born. +Josh Triplett has since taken over the small-memory banner with his +<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a> +project, which resulted in +<a href="#Sleepable RCU">SRCU</a> +becoming optional for those kernels not needing it. + +<p> +The remaining performance requirements are, for the most part, +unsurprising. +For example, in keeping with RCU's read-side specialization, +<tt>rcu_dereference()</tt> should have negligible overhead (for +example, suppression of a few minor compiler optimizations). +Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> should have exactly zero overhead. + +<p> +In preemptible environments, in the case where the RCU read-side +critical section was not preempted (as will be the case for the +highest-priority real-time process), <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> should have minimal overhead. +In particular, they should not contain atomic read-modify-write +operations, memory-barrier instructions, preemption disabling, +interrupt disabling, or backwards branches. +However, in the case where the RCU read-side critical section was preempted, +<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts. +This is why it is better to nest an RCU read-side critical section +within a preempt-disable region than vice versa, at least in cases +where that critical section is short enough to avoid unduly degrading +real-time latencies. + +<p> +The <tt>synchronize_rcu()</tt> grace-period-wait primitive is +optimized for throughput. +It may therefore incur several milliseconds of latency in addition to +the duration of the longest RCU read-side critical section. +On the other hand, multiple concurrent invocations of +<tt>synchronize_rcu()</tt> are required to use batching optimizations +so that they can be satisfied by a single underlying grace-period-wait +operation. +For example, in the Linux kernel, it is not unusual for a single +grace-period-wait operation to serve more than +<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a> +of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation +overhead down to nearly zero. +However, the grace-period optimization is also required to avoid +measurable degradation of real-time scheduling and interrupt latencies. + +<p> +In some cases, the multi-millisecond <tt>synchronize_rcu()</tt> +latencies are unacceptable. +In these cases, <tt>synchronize_rcu_expedited()</tt> may be used +instead, reducing the grace-period latency down to a few tens of +microseconds on small systems, at least in cases where the RCU read-side +critical sections are short. +There are currently no special latency requirements for +<tt>synchronize_rcu_expedited()</tt> on large systems, but, +consistent with the empirical nature of the RCU specification, +that is subject to change. +However, there most definitely are scalability requirements: +A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096 +CPUs should at least make reasonable forward progress. +In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt> +is permitted to impose modest degradation of real-time latency +on non-idle online CPUs. +That said, it will likely be necessary to take further steps to reduce this +degradation, hopefully to roughly that of a scheduling-clock interrupt. + +<p> +There are a number of situations where even +<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period +latency is unacceptable. +In these situations, the asynchronous <tt>call_rcu()</tt> can be +used in place of <tt>synchronize_rcu()</tt> as follows: + +<blockquote> +<pre> + 1 struct foo { + 2 int a; + 3 int b; + 4 struct rcu_head rh; + 5 }; + 6 + 7 static void remove_gp_cb(struct rcu_head *rhp) + 8 { + 9 struct foo *p = container_of(rhp, struct foo, rh); +10 +11 kfree(p); +12 } +13 +14 bool remove_gp_asynchronous(void) +15 { +16 struct foo *p; +17 +18 spin_lock(&gp_lock); +19 p = rcu_dereference(gp); +20 if (!p) { +21 spin_unlock(&gp_lock); +22 return false; +23 } +24 rcu_assign_pointer(gp, NULL); +25 call_rcu(&p->rh, remove_gp_cb); +26 spin_unlock(&gp_lock); +27 return true; +28 } +</pre> +</blockquote> + +<p> +A definition of <tt>struct foo</tt> is finally needed, and appears +on lines 1-5. +The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt> +on line 25, and will be invoked after the end of a subsequent +grace period. +This gets the same effect as <tt>remove_gp_synchronous()</tt>, +but without forcing the updater to wait for a grace period to elapse. +The <tt>call_rcu()</tt> function may be used in a number of +situations where neither <tt>synchronize_rcu()</tt> nor +<tt>synchronize_rcu_expedited()</tt> would be legal, +including within preempt-disable code, <tt>local_bh_disable()</tt> code, +interrupt-disable code, and interrupt handlers. +However, even <tt>call_rcu()</tt> is illegal within NMI handlers. +The callback function (<tt>remove_gp_cb()</tt> in this case) will be +executed within softirq (software interrupt) environment within the +Linux kernel, +either within a real softirq handler or under the protection +of <tt>local_bh_disable()</tt>. +In both the Linux kernel and in userspace, it is bad practice to +write an RCU callback function that takes too long. +Long-running operations should be relegated to separate threads or +(in the Linux kernel) workqueues. + +<p><a name="Quick Quiz 12"><b>Quick Quiz 12</b>:</a> +Why does line 19 use <tt>rcu_access_pointer()</tt>? +After all, <tt>call_rcu()</tt> on line 25 stores into the +structure, which would interact badly with concurrent insertions. +Doesn't this mean that <tt>rcu_dereference()</tt> is required? +<br><a href="#qq12answer">Answer</a> + +<p> +However, all that <tt>remove_gp_cb()</tt> is doing is +invoking <tt>kfree()</tt> on the data element. +This is a common idiom, and is supported by <tt>kfree_rcu()</tt>, +which allows “fire and forget” operation as shown below: + +<blockquote> +<pre> + 1 struct foo { + 2 int a; + 3 int b; + 4 struct rcu_head rh; + 5 }; + 6 + 7 bool remove_gp_faf(void) + 8 { + 9 struct foo *p; +10 +11 spin_lock(&gp_lock); +12 p = rcu_dereference(gp); +13 if (!p) { +14 spin_unlock(&gp_lock); +15 return false; +16 } +17 rcu_assign_pointer(gp, NULL); +18 kfree_rcu(p, rh); +19 spin_unlock(&gp_lock); +20 return true; +21 } +</pre> +</blockquote> + +<p> +Note that <tt>remove_gp_faf()</tt> simply invokes +<tt>kfree_rcu()</tt> and proceeds, without any need to pay any +further attention to the subsequent grace period and <tt>kfree()</tt>. +It is permissible to invoke <tt>kfree_rcu()</tt> from the same +environments as for <tt>call_rcu()</tt>. +Interestingly enough, DYNIX/ptx had the equivalents of +<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not +<tt>synchronize_rcu()</tt>. +This was due to the fact that RCU was not heavily used within DYNIX/ptx, +so the very few places that needed something like +<tt>synchronize_rcu()</tt> simply open-coded it. + +<p><a name="Quick Quiz 13"><b>Quick Quiz 13</b>:</a> +Earlier it was claimed that <tt>call_rcu()</tt> and +<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked +by readers. +But how can that be correct, given that the invocation of the callback +and the freeing of the memory (respectively) must still wait for +a grace period to elapse? +<br><a href="#qq13answer">Answer</a> + +<p> +But what if the updater must wait for the completion of code to be +executed after the end of the grace period, but has other tasks +that can be carried out in the meantime? +The polling-style <tt>get_state_synchronize_rcu()</tt> and +<tt>cond_synchronize_rcu()</tt> functions may be used for this +purpose, as shown below: + +<blockquote> +<pre> + 1 bool remove_gp_poll(void) + 2 { + 3 struct foo *p; + 4 unsigned long s; + 5 + 6 spin_lock(&gp_lock); + 7 p = rcu_access_pointer(gp); + 8 if (!p) { + 9 spin_unlock(&gp_lock); +10 return false; +11 } +12 rcu_assign_pointer(gp, NULL); +13 spin_unlock(&gp_lock); +14 s = get_state_synchronize_rcu(); +15 do_something_while_waiting(); +16 cond_synchronize_rcu(s); +17 kfree(p); +18 return true; +19 } +</pre> +</blockquote> + +<p> +On line 14, <tt>get_state_synchronize_rcu()</tt> obtains a +“cookie” from RCU, +then line 15 carries out other tasks, +and finally, line 16 returns immediately if a grace period has +elapsed in the meantime, but otherwise waits as required. +The need for <tt>get_state_synchronize_rcu</tt> and +<tt>cond_synchronize_rcu()</tt> has appeared quite recently, +so it is too early to tell whether they will stand the test of time. + +<p> +RCU thus provides a range of tools to allow updaters to strike the +required tradeoff between latency, flexibility and CPU overhead. + +<h3><a name="Composability">Composability</a></h3> + +<p> +Composability has received much attention in recent years, perhaps in part +due to the collision of multicore hardware with object-oriented techniques +designed in single-threaded environments for single-threaded use. +And in theory, RCU read-side critical sections may be composed, and in +fact may be nested arbitrarily deeply. +In practice, as with all real-world implementations of composable +constructs, there are limitations. + +<p> +Implementations of RCU for which <tt>rcu_read_lock()</tt> +and <tt>rcu_read_unlock()</tt> generate no code, such as +Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be +nested arbitrarily deeply. +After all, there is no overhead. +Except that if all these instances of <tt>rcu_read_lock()</tt> +and <tt>rcu_read_unlock()</tt> are visible to the compiler, +compilation will eventually fail due to exhausting memory, +mass storage, or user patience, whichever comes first. +If the nesting is not visible to the compiler, as is the case with +mutually recursive functions each in its own translation unit, +stack overflow will result. +If the nesting takes the form of loops, either the control variable +will overflow or (in the Linux kernel) you will get an RCU CPU stall warning. +Nevertheless, this class of RCU implementations is one +of the most composable constructs in existence. + +<p> +RCU implementations that explicitly track nesting depth +are limited by the nesting-depth counter. +For example, the Linux kernel's preemptible RCU limits nesting to +<tt>INT_MAX</tt>. +This should suffice for almost all practical purposes. +That said, a consecutive pair of RCU read-side critical sections +between which there is an operation that waits for a grace period +cannot be enclosed in another RCU read-side critical section. +This is because it is not legal to wait for a grace period within +an RCU read-side critical section: To do so would result either +in deadlock or +in RCU implicitly splitting the enclosing RCU read-side critical +section, neither of which is conducive to a long-lived and prosperous +kernel. + +<p> +It is worth noting that RCU is not alone in limiting composability. +For example, many transactional-memory implementations prohibit +composing a pair of transactions separated by an irrevocable +operation (for example, a network receive operation). +For another example, lock-based critical sections can be composed +surprisingly freely, but only if deadlock is avoided. + +<p> +In short, although RCU read-side critical sections are highly composable, +care is required in some situations, just as is the case for any other +composable synchronization mechanism. + +<h3><a name="Corner Cases">Corner Cases</a></h3> + +<p> +A given RCU workload might have an endless and intense stream of +RCU read-side critical sections, perhaps even so intense that there +was never a point in time during which there was not at least one +RCU read-side critical section in flight. +RCU cannot allow this situation to block grace periods: As long as +all the RCU read-side critical sections are finite, grace periods +must also be finite. + +<p> +That said, preemptible RCU implementations could potentially result +in RCU read-side critical sections being preempted for long durations, +which has the effect of creating a long-duration RCU read-side +critical section. +This situation can arise only in heavily loaded systems, but systems using +real-time priorities are of course more vulnerable. +Therefore, RCU priority boosting is provided to help deal with this +case. +That said, the exact requirements on RCU priority boosting will likely +evolve as more experience accumulates. + +<p> +Other workloads might have very high update rates. +Although one can argue that such workloads should instead use +something other than RCU, the fact remains that RCU must +handle such workloads gracefully. +This requirement is another factor driving batching of grace periods, +but it is also the driving force behind the checks for large numbers +of queued RCU callbacks in the <tt>call_rcu()</tt> code path. +Finally, high update rates should not delay RCU read-side critical +sections, although some read-side delays can occur when using +<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use +of <tt>try_stop_cpus()</tt>. +(In the future, <tt>synchronize_rcu_expedited()</tt> will be +converted to use lighter-weight inter-processor interrupts (IPIs), +but this will still disturb readers, though to a much smaller degree.) + +<p> +Although all three of these corner cases were understood in the early +1990s, a simple user-level test consisting of <tt>close(open(path))</tt> +in a tight loop +in the early 2000s suddenly provided a much deeper appreciation of the +high-update-rate corner case. +This test also motivated addition of some RCU code to react to high update +rates, for example, if a given CPU finds itself with more than 10,000 +RCU callbacks queued, it will cause RCU to take evasive action by +more aggressively starting grace periods and more aggressively forcing +completion of grace-period processing. +This evasive action causes the grace period to complete more quickly, +but at the cost of restricting RCU's batching optimizations, thus +increasing the CPU overhead incurred by that grace period. + +<h2><a name="Software-Engineering Requirements"> +Software-Engineering Requirements</a></h2> + +<p> +Between Murphy's Law and “To err is human”, it is necessary to +guard against mishaps and misuse: + +<ol> +<li> It is all too easy to forget to use <tt>rcu_read_lock()</tt> + everywhere that it is needed, so kernels built with + <tt>CONFIG_PROVE_RCU=y</tt> will spat if + <tt>rcu_dereference()</tt> is used outside of an + RCU read-side critical section. + Update-side code can use <tt>rcu_dereference_protected()</tt>, + which takes a + <a href="https://lwn.net/Articles/371986/">lockdep expression</a> + to indicate what is providing the protection. + If the indicated protection is not provided, a lockdep splat + is emitted. + + <p> + Code shared between readers and updaters can use + <tt>rcu_dereference_check()</tt>, which also takes a + lockdep expression, and emits a lockdep splat if neither + <tt>rcu_read_lock()</tt> nor the indicated protection + is in place. + In addition, <tt>rcu_dereference_raw()</tt> is used in those + (hopefully rare) cases where the required protection cannot + be easily described. + Finally, <tt>rcu_read_lock_held()</tt> is provided to + allow a function to verify that it has been invoked within + an RCU read-side critical section. + I was made aware of this set of requirements shortly after Thomas + Gleixner audited a number of RCU uses. +<li> A given function might wish to check for RCU-related preconditions + upon entry, before using any other RCU API. + The <tt>rcu_lockdep_assert()</tt> does this job, + asserting the expression in kernels having lockdep enabled + and doing nothing otherwise. +<li> It is also easy to forget to use <tt>rcu_assign_pointer()</tt> + and <tt>rcu_dereference()</tt>, perhaps (incorrectly) + substituting a simple assignment. + To catch this sort of error, a given RCU-protected pointer may be + tagged with <tt>__rcu</tt>, after which running sparse + with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain + about simple-assignment accesses to that pointer. + Arnd Bergmann made me aware of this requirement, and also + supplied the needed + <a href="https://lwn.net/Articles/376011/">patch series</a>. +<li> Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt> + will splat if a data element is passed to <tt>call_rcu()</tt> + twice in a row, without a grace period in between. + (This error is similar to a double free.) + The corresponding <tt>rcu_head</tt> structures that are + dynamically allocated are automatically tracked, but + <tt>rcu_head</tt> structures allocated on the stack + must be initialized with <tt>init_rcu_head_on_stack()</tt> + and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>. + Similarly, statically allocated non-stack <tt>rcu_head</tt> + structures must be initialized with <tt>init_rcu_head()</tt> + and cleaned up with <tt>destroy_rcu_head()</tt>. + Mathieu Desnoyers made me aware of this requirement, and also + supplied the needed + <a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>. +<li> An infinite loop in an RCU read-side critical section will + eventually trigger an RCU CPU stall warning splat, with + the duration of “eventually” being controlled by the + <tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or, + alternatively, by the + <tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs + parameter. + However, RCU is not obligated to produce this splat + unless there is a grace period waiting on that particular + RCU read-side critical section. + <p> + Some extreme workloads might intentionally delay + RCU grace periods, and systems running those workloads can + be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt> + to suppress the splats. + This kernel parameter may also be set via <tt>sysfs</tt>. + Furthermore, RCU CPU stall warnings are counter-productive + during sysrq dumps and during panics. + RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and + <tt>rcu_sysrq_end()</tt> API members to be called before + and after long sysrq dumps. + RCU also supplies the <tt>rcu_panic()</tt> notifier that is + automatically invoked at the beginning of a panic to suppress + further RCU CPU stall warnings. + + <p> + This requirement made itself known in the early 1990s, pretty + much the first time that it was necessary to debug a CPU stall. + That said, the initial implementation in DYNIX/ptx was quite + generic in comparison with that of Linux. +<li> Although it would be very good to detect pointers leaking out + of RCU read-side critical sections, there is currently no + good way of doing this. + One complication is the need to distinguish between pointers + leaking and pointers that have been handed off from RCU to + some other synchronization mechanism, for example, reference + counting. +<li> In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related + information is provided via both debugfs and event tracing. +<li> Open-coded use of <tt>rcu_assign_pointer()</tt> and + <tt>rcu_dereference()</tt> to create typical linked + data structures can be surprisingly error-prone. + Therefore, RCU-protected + <a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a> + and, more recently, RCU-protected + <a href="https://lwn.net/Articles/612100/">hash tables</a> + are available. + Many other special-purpose RCU-protected data structures are + available in the Linux kernel and the userspace RCU library. +<li> Some linked structures are created at compile time, but still + require <tt>__rcu</tt> checking. + The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this + purpose. +<li> It is not necessary to use <tt>rcu_assign_pointer()</tt> + when creating linked structures that are to be published via + a single external pointer. + The <tt>RCU_INIT_POINTER()</tt> macro is provided for + this task and also for assigning <tt>NULL</tt> pointers + at runtime. +</ol> + +<p> +This not a hard-and-fast list: RCU's diagnostic capabilities will +continue to be guided by the number and type of usage bugs found +in real-world RCU usage. + +<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2> + +<p> +The Linux kernel provides an interesting environment for all kinds of +software, including RCU. +Some of the relevant points of interest are as follows: + +<ol> +<li> <a href="#Configuration">Configuration</a>. +<li> <a href="#Firmware Interface">Firmware Interface</a>. +<li> <a href="#Early Boot">Early Boot</a>. +<li> <a href="#Interrupts and NMIs"> + Interrupts and non-maskable interrupts (NMIs)</a>. +<li> <a href="#Loadable Modules">Loadable Modules</a>. +<li> <a href="#Hotplug CPU">Hotplug CPU</a>. +<li> <a href="#Scheduler and RCU">Scheduler and RCU</a>. +<li> <a href="#Tracing and RCU">Tracing and RCU</a>. +<li> <a href="#Energy Efficiency">Energy Efficiency</a>. +<li> <a href="#Memory Efficiency">Memory Efficiency</a>. +<li> <a href="#Performance, Scalability, Response Time, and Reliability"> + Performance, Scalability, Response Time, and Reliability</a>. +</ol> + +<p> +This list is probably incomplete, but it does give a feel for the +most notable Linux-kernel complications. +Each of the following sections covers one of the above topics. + +<h3><a name="Configuration">Configuration</a></h3> + +<p> +RCU's goal is automatic configuration, so that almost nobody +needs to worry about RCU's <tt>Kconfig</tt> options. +And for almost all users, RCU does in fact work well +“out of the box.” + +<p> +However, there are specialized use cases that are handled by +kernel boot parameters and <tt>Kconfig</tt> options. +Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users +about new <tt>Kconfig</tt> options, which requires almost all of them +be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option. + +<p> +This all should be quite obvious, but the fact remains that +Linus Torvalds recently had to +<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a> +me of this requirement. + +<h3><a name="Firmware Interface">Firmware Interface</a></h3> + +<p> +In many cases, kernel obtains information about the system from the +firmware, and sometimes things are lost in translation. +Or the translation is accurate, but the original message is bogus. + +<p> +For example, some systems' firmware overreports the number of CPUs, +sometimes by a large factor. +If RCU naively believed the firmware, as it used to do, +it would create too many per-CPU kthreads. +Although the resulting system will still run correctly, the extra +kthreads needlessly consume memory and can cause confusion +when they show up in <tt>ps</tt> listings. + +<p> +RCU must therefore wait for a given CPU to actually come online before +it can allow itself to believe that the CPU actually exists. +The resulting “ghost CPUs” (which are never going to +come online) cause a number of +<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>. + +<h3><a name="Early Boot">Early Boot</a></h3> + +<p> +The Linux kernel's boot sequence is an interesting process, +and RCU is used early, even before <tt>rcu_init()</tt> +is invoked. +In fact, a number of RCU's primitives can be used as soon as the +initial task's <tt>task_struct</tt> is available and the +boot CPU's per-CPU variables are set up. +The read-side primitives (<tt>rcu_read_lock()</tt>, +<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>, +and <tt>rcu_access_pointer()</tt>) will operate normally very early on, +as will <tt>rcu_assign_pointer()</tt>. + +<p> +Although <tt>call_rcu()</tt> may be invoked at any +time during boot, callbacks are not guaranteed to be invoked until after +the scheduler is fully up and running. +This delay in callback invocation is due to the fact that RCU does not +invoke callbacks until it is fully initialized, and this full initialization +cannot occur until after the scheduler has initialized itself to the +point where RCU can spawn and run its kthreads. +In theory, it would be possible to invoke callbacks earlier, +however, this is not a panacea because there would be severe restrictions +on what operations those callbacks could invoke. + +<p> +Perhaps surprisingly, <tt>synchronize_rcu()</tt>, +<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a> +(<a href="#Bottom-Half Flavor">discussed below</a>), +and +<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a> +will all operate normally +during very early boot, the reason being that there is only one CPU +and preemption is disabled. +This means that the call <tt>synchronize_rcu()</tt> (or friends) +itself is a quiescent +state and thus a grace period, so the early-boot implementation can +be a no-op. + +<p> +Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt> +continue to operate normally through the remainder of boot, courtesy +of the fact that preemption is disabled across their RCU read-side +critical sections and also courtesy of the fact that there is still +only one CPU. +However, once the scheduler starts initializing, preemption is enabled. +There is still only a single CPU, but the fact that preemption is enabled +means that the no-op implementation of <tt>synchronize_rcu()</tt> no +longer works in <tt>CONFIG_PREEMPT=y</tt> kernels. +Therefore, as soon as the scheduler starts initializing, the early-boot +fastpath is disabled. +This means that <tt>synchronize_rcu()</tt> switches to its runtime +mode of operation where it posts callbacks, which in turn means that +any call to <tt>synchronize_rcu()</tt> will block until the corresponding +callback is invoked. +Unfortunately, the callback cannot be invoked until RCU's runtime +grace-period machinery is up and running, which cannot happen until +the scheduler has initialized itself sufficiently to allow RCU's +kthreads to be spawned. +Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler +initialization can result in deadlock. + +<p><a name="Quick Quiz 14"><b>Quick Quiz 14</b>:</a> +So what happens with <tt>synchronize_rcu()</tt> during +scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> +kernels? +<br><a href="#qq14answer">Answer</a> + +<p> +I learned of these boot-time requirements as a result of a series of +system hangs. + +<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3> + +<p> +The Linux kernel has interrupts, and RCU read-side critical sections are +legal within interrupt handlers and within interrupt-disabled regions +of code, as are invocations of <tt>call_rcu()</tt>. + +<p> +Some Linux-kernel architectures can enter an interrupt handler from +non-idle process context, and then just never leave it, instead stealthily +transitioning back to process context. +This trick is sometimes used to invoke system calls from inside the kernel. +These “half-interrupts” mean that RCU has to be very careful +about how it counts interrupt nesting levels. +I learned of this requirement the hard way during a rewrite +of RCU's dyntick-idle code. + +<p> +The Linux kernel has non-maskable interrupts (NMIs), and +RCU read-side critical sections are legal within NMI handlers. +Thankfully, RCU update-side primitives, including +<tt>call_rcu()</tt>, are prohibited within NMI handlers. + +<p> +The name notwithstanding, some Linux-kernel architectures +can have nested NMIs, which RCU must handle correctly. +Andy Lutomirski +<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a> +with this requirement; +he also kindly surprised me with +<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a> +that meets this requirement. + +<h3><a name="Loadable Modules">Loadable Modules</a></h3> + +<p> +The Linux kernel has loadable modules, and these modules can +also be unloaded. +After a given module has been unloaded, any attempt to call +one of its functions results in a segmentation fault. +The module-unload functions must therefore cancel any +delayed calls to loadable-module functions, for example, +any outstanding <tt>mod_timer()</tt> must be dealt with +via <tt>del_timer_sync()</tt> or similar. + +<p> +Unfortunately, there is no way to cancel an RCU callback; +once you invoke <tt>call_rcu()</tt>, the callback function is +going to eventually be invoked, unless the system goes down first. +Because it is normally considered socially irresponsible to crash the system +in response to a module unload request, we need some other way +to deal with in-flight RCU callbacks. + +<p> +RCU therefore provides +<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>, +which waits until all in-flight RCU callbacks have been invoked. +If a module uses <tt>call_rcu()</tt>, its exit function should therefore +prevent any future invocation of <tt>call_rcu()</tt>, then invoke +<tt>rcu_barrier()</tt>. +In theory, the underlying module-unload code could invoke +<tt>rcu_barrier()</tt> unconditionally, but in practice this would +incur unacceptable latencies. + +<p> +Nikita Danilov noted this requirement for an analogous filesystem-unmount +situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU. +The need for <tt>rcu_barrier()</tt> for module unloading became +apparent later. + +<h3><a name="Hotplug CPU">Hotplug CPU</a></h3> + +<p> +The Linux kernel supports CPU hotplug, which means that CPUs +can come and go. +It is of course illegal to use any RCU API member from an offline CPU. +This requirement was present from day one in DYNIX/ptx, but +on the other hand, the Linux kernel's CPU-hotplug implementation +is “interesting.” + +<p> +The Linux-kernel CPU-hotplug implementation has notifiers that +are used to allow the various kernel subsystems (including RCU) +to respond appropriately to a given CPU-hotplug operation. +Most RCU operations may be invoked from CPU-hotplug notifiers, +including even normal synchronous grace-period operations +such as <tt>synchronize_rcu()</tt>. +However, expedited grace-period operations such as +<tt>synchronize_rcu_expedited()</tt> are not supported, +due to the fact that current implementations block CPU-hotplug +operations, which could result in deadlock. + +<p> +In addition, all-callback-wait operations such as +<tt>rcu_barrier()</tt> are also not supported, due to the +fact that there are phases of CPU-hotplug operations where +the outgoing CPU's callbacks will not be invoked until after +the CPU-hotplug operation ends, which could also result in deadlock. + +<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3> + +<p> +RCU depends on the scheduler, and the scheduler uses RCU to +protect some of its data structures. +This means the scheduler is forbidden from acquiring +the runqueue locks and the priority-inheritance locks +in the middle of an outermost RCU read-side critical section unless either +(1) it releases them before exiting that same +RCU read-side critical section, or +(2) interrupts are disabled across +that entire RCU read-side critical section. +This same prohibition also applies (recursively!) to any lock that is acquired +while holding any lock to which this prohibition applies. +Adhering to this rule prevents preemptible RCU from invoking +<tt>rcu_read_unlock_special()</tt> while either runqueue or +priority-inheritance locks are held, thus avoiding deadlock. + +<p> +Prior to v4.4, it was only necessary to disable preemption across +RCU read-side critical sections that acquired scheduler locks. +In v4.4, expedited grace periods started using IPIs, and these +IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath. +Therefore, this expedited-grace-period change required disabling of +interrupts, not just preemption. + +<p> +For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt> +implementation must be written carefully to avoid similar deadlocks. +In particular, <tt>rcu_read_unlock()</tt> must tolerate an +interrupt where the interrupt handler invokes both +<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. +This possibility requires <tt>rcu_read_unlock()</tt> to use +negative nesting levels to avoid destructive recursion via +interrupt handler's use of RCU. + +<p> +This pair of mutual scheduler-RCU requirements came as a +<a href="https://lwn.net/Articles/453002/">complete surprise</a>. + +<p> +As noted above, RCU makes use of kthreads, and it is necessary to +avoid excessive CPU-time accumulation by these kthreads. +This requirement was no surprise, but RCU's violation of it +when running context-switch-heavy workloads when built with +<tt>CONFIG_NO_HZ_FULL=y</tt> +<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>. +RCU has made good progress towards meeting this requirement, even +for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads, +but there is room for further improvement. + +<h3><a name="Tracing and RCU">Tracing and RCU</a></h3> + +<p> +It is possible to use tracing on RCU code, but tracing itself +uses RCU. +For this reason, <tt>rcu_dereference_raw_notrace()</tt> +is provided for use by tracing, which avoids the destructive +recursion that could otherwise ensue. +This API is also used by virtualization in some architectures, +where RCU readers execute in environments in which tracing +cannot be used. +The tracing folks both located the requirement and provided the +needed fix, so this surprise requirement was relatively painless. + +<h3><a name="Energy Efficiency">Energy Efficiency</a></h3> + +<p> +Interrupting idle CPUs is considered socially unacceptable, +especially by people with battery-powered embedded systems. +RCU therefore conserves energy by detecting which CPUs are +idle, including tracking CPUs that have been interrupted from idle. +This is a large part of the energy-efficiency requirement, +so I learned of this via an irate phone call. + +<p> +Because RCU avoids interrupting idle CPUs, it is illegal to +execute an RCU read-side critical section on an idle CPU. +(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat +if you try it.) +The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt> +event tracing is provided to work around this restriction. +In addition, <tt>rcu_is_watching()</tt> may be used to +test whether or not it is currently legal to run RCU read-side +critical sections on this CPU. +I learned of the need for diagnostics on the one hand +and <tt>RCU_NONIDLE()</tt> on the other while inspecting +idle-loop code. +Steven Rostedt supplied <tt>_rcuidle</tt> event tracing, +which is used quite heavily in the idle loop. + +<p> +It is similarly socially unacceptable to interrupt an +<tt>nohz_full</tt> CPU running in userspace. +RCU must therefore track <tt>nohz_full</tt> userspace +execution. +And in +<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a> +kernels, RCU must separately track idle CPUs on the one hand and +CPUs that are either idle or executing in userspace on the other. +In both cases, RCU must be able to sample state at two points in +time, and be able to determine whether or not some other CPU spent +any time idle and/or executing in userspace. + +<p> +These energy-efficiency requirements have proven quite difficult to +understand and to meet, for example, there have been more than five +clean-sheet rewrites of RCU's energy-efficiency code, the last of +which was finally able to demonstrate +<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>. +As noted earlier, +I learned of many of these requirements via angry phone calls: +Flaming me on the Linux-kernel mailing list was apparently not +sufficient to fully vent their ire at RCU's energy-efficiency bugs! + +<h3><a name="Memory Efficiency">Memory Efficiency</a></h3> + +<p> +Although small-memory non-realtime systems can simply use Tiny RCU, +code size is only one aspect of memory efficiency. +Another aspect is the size of the <tt>rcu_head</tt> structure +used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>. +Although this structure contains nothing more than a pair of pointers, +it does appear in many RCU-protected data structures, including +some that are size critical. +The <tt>page</tt> structure is a case in point, as evidenced by +the many occurrences of the <tt>union</tt> keyword within that structure. + +<p> +This need for memory efficiency is one reason that RCU uses hand-crafted +singly linked lists to track the <tt>rcu_head</tt> structures that +are waiting for a grace period to elapse. +It is also the reason why <tt>rcu_head</tt> structures do not contain +debug information, such as fields tracking the file and line of the +<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them. +Although this information might appear in debug-only kernel builds at some +point, in the meantime, the <tt>->func</tt> field will often provide +the needed debug information. + +<p> +However, in some cases, the need for memory efficiency leads to even +more extreme measures. +Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field +shares storage with a great many other structures that are used at +various points in the corresponding page's lifetime. +In order to correctly resolve certain +<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>, +the Linux kernel's memory-management subsystem needs a particular bit +to remain zero during all phases of grace-period processing, +and that bit happens to map to the bottom bit of the +<tt>rcu_head</tt> structure's <tt>->next</tt> field. +RCU makes this guarantee as long as <tt>call_rcu()</tt> +is used to post the callback, as opposed to <tt>kfree_rcu()</tt> +or some future “lazy” +variant of <tt>call_rcu()</tt> that might one day be created for +energy-efficiency purposes. + +<h3><a name="Performance, Scalability, Response Time, and Reliability"> +Performance, Scalability, Response Time, and Reliability</a></h3> + +<p> +Expanding on the +<a href="#Performance and Scalability">earlier discussion</a>, +RCU is used heavily by hot code paths in performance-critical +portions of the Linux kernel's networking, security, virtualization, +and scheduling code paths. +RCU must therefore use efficient implementations, especially in its +read-side primitives. +To that end, it would be good if preemptible RCU's implementation +of <tt>rcu_read_lock()</tt> could be inlined, however, doing +this requires resolving <tt>#include</tt> issues with the +<tt>task_struct</tt> structure. + +<p> +The Linux kernel supports hardware configurations with up to +4096 CPUs, which means that RCU must be extremely scalable. +Algorithms that involve frequent acquisitions of global locks or +frequent atomic operations on global variables simply cannot be +tolerated within the RCU implementation. +RCU therefore makes heavy use of a combining tree based on the +<tt>rcu_node</tt> structure. +RCU is required to tolerate all CPUs continuously invoking any +combination of RCU's runtime primitives with minimal per-operation +overhead. +In fact, in many cases, increasing load must <i>decrease</i> the +per-operation overhead, witness the batching optimizations for +<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>, +<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>. +As a general rule, RCU must cheerfully accept whatever the +rest of the Linux kernel decides to throw at it. + +<p> +The Linux kernel is used for real-time workloads, especially +in conjunction with the +<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>. +The real-time-latency response requirements are such that the +traditional approach of disabling preemption across RCU +read-side critical sections is inappropriate. +Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore +use an RCU implementation that allows RCU read-side critical +sections to be preempted. +This requirement made its presence known after users made it +clear that an earlier +<a href="https://lwn.net/Articles/107930/">real-time patch</a> +did not meet their needs, in conjunction with some +<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a> +encountered by a very early version of the -rt patchset. + +<p> +In addition, RCU must make do with a sub-100-microsecond real-time latency +budget. +In fact, on smaller systems with the -rt patchset, the Linux kernel +provides sub-20-microsecond real-time latencies for the whole kernel, +including RCU. +RCU's scalability and latency must therefore be sufficient for +these sorts of configurations. +To my surprise, the sub-100-microsecond real-time latency budget +<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf"> +applies to even the largest systems [PDF]</a>, +up to and including systems with 4096 CPUs. +This real-time requirement motivated the grace-period kthread, which +also simplified handling of a number of race conditions. + +<p> +Finally, RCU's status as a synchronization primitive means that +any RCU failure can result in arbitrary memory corruption that can be +extremely difficult to debug. +This means that RCU must be extremely reliable, which in +practice also means that RCU must have an aggressive stress-test +suite. +This stress-test suite is called <tt>rcutorture</tt>. + +<p> +Although the need for <tt>rcutorture</tt> was no surprise, +the current immense popularity of the Linux kernel is posing +interesting—and perhaps unprecedented—validation +challenges. +To see this, keep in mind that there are well over one billion +instances of the Linux kernel running today, given Android +smartphones, Linux-powered televisions, and servers. +This number can be expected to increase sharply with the advent of +the celebrated Internet of Things. + +<p> +Suppose that RCU contains a race condition that manifests on average +once per million years of runtime. +This bug will be occurring about three times per <i>day</i> across +the installed base. +RCU could simply hide behind hardware error rates, given that no one +should really expect their smartphone to last for a million years. +However, anyone taking too much comfort from this thought should +consider the fact that in most jurisdictions, a successful multi-year +test of a given mechanism, which might include a Linux kernel, +suffices for a number of types of safety-critical certifications. +In fact, rumor has it that the Linux kernel is already being used +in production for safety-critical applications. +I don't know about you, but I would feel quite bad if a bug in RCU +killed someone. +Which might explain my recent focus on validation and verification. + +<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2> + +<p> +One of the more surprising things about RCU is that there are now +no fewer than five <i>flavors</i>, or API families. +In addition, the primary flavor that has been the sole focus up to +this point has two different implementations, non-preemptible and +preemptible. +The other four flavors are listed below, with requirements for each +described in a separate section. + +<ol> +<li> <a href="#Bottom-Half Flavor">Bottom-Half Flavor</a> +<li> <a href="#Sched Flavor">Sched Flavor</a> +<li> <a href="#Sleepable RCU">Sleepable RCU</a> +<li> <a href="#Tasks RCU">Tasks RCU</a> +</ol> + +<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3> + +<p> +The softirq-disable (AKA “bottom-half”, +hence the “_bh” abbreviations) +flavor of RCU, or <i>RCU-bh</i>, was developed by +Dipankar Sarma to provide a flavor of RCU that could withstand the +network-based denial-of-service attacks researched by Robert +Olsson. +These attacks placed so much networking load on the system +that some of the CPUs never exited softirq execution, +which in turn prevented those CPUs from ever executing a context switch, +which, in the RCU implementation of that time, prevented grace periods +from ever ending. +The result was an out-of-memory condition and a system hang. + +<p> +The solution was the creation of RCU-bh, which does +<tt>local_bh_disable()</tt> +across its read-side critical sections, and which uses the transition +from one type of softirq processing to another as a quiescent state +in addition to context switch, idle, user mode, and offline. +This means that RCU-bh grace periods can complete even when some of +the CPUs execute in softirq indefinitely, thus allowing algorithms +based on RCU-bh to withstand network-based denial-of-service attacks. + +<p> +Because +<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt> +disable and re-enable softirq handlers, any attempt to start a softirq +handlers during the +RCU-bh read-side critical section will be deferred. +In this case, <tt>rcu_read_unlock_bh()</tt> +will invoke softirq processing, which can take considerable time. +One can of course argue that this softirq overhead should be associated +with the code following the RCU-bh read-side critical section rather +than <tt>rcu_read_unlock_bh()</tt>, but the fact +is that most profiling tools cannot be expected to make this sort +of fine distinction. +For example, suppose that a three-millisecond-long RCU-bh read-side +critical section executes during a time of heavy networking load. +There will very likely be an attempt to invoke at least one softirq +handler during that three milliseconds, but any such invocation will +be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>. +This can of course make it appear at first glance as if +<tt>rcu_read_unlock_bh()</tt> was executing very slowly. + +<p> +The +<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a> +includes +<tt>rcu_read_lock_bh()</tt>, +<tt>rcu_read_unlock_bh()</tt>, +<tt>rcu_dereference_bh()</tt>, +<tt>rcu_dereference_bh_check()</tt>, +<tt>synchronize_rcu_bh()</tt>, +<tt>synchronize_rcu_bh_expedited()</tt>, +<tt>call_rcu_bh()</tt>, +<tt>rcu_barrier_bh()</tt>, and +<tt>rcu_read_lock_bh_held()</tt>. + +<h3><a name="Sched Flavor">Sched Flavor</a></h3> + +<p> +Before preemptible RCU, waiting for an RCU grace period had the +side effect of also waiting for all pre-existing interrupt +and NMI handlers. +However, there are legitimate preemptible-RCU implementations that +do not have this property, given that any point in the code outside +of an RCU read-side critical section can be a quiescent state. +Therefore, <i>RCU-sched</i> was created, which follows “classic” +RCU in that an RCU-sched grace period waits for for pre-existing +interrupt and NMI handlers. +In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched +APIs have identical implementations, while kernels built with +<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each. + +<p> +Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels, +<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt> +disable and re-enable preemption, respectively. +This means that if there was a preemption attempt during the +RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt> +will enter the scheduler, with all the latency and overhead entailed. +Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look +as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly. +However, the highest-priority task won't be preempted, so that task +will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations. + +<p> +The +<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a> +includes +<tt>rcu_read_lock_sched()</tt>, +<tt>rcu_read_unlock_sched()</tt>, +<tt>rcu_read_lock_sched_notrace()</tt>, +<tt>rcu_read_unlock_sched_notrace()</tt>, +<tt>rcu_dereference_sched()</tt>, +<tt>rcu_dereference_sched_check()</tt>, +<tt>synchronize_sched()</tt>, +<tt>synchronize_rcu_sched_expedited()</tt>, +<tt>call_rcu_sched()</tt>, +<tt>rcu_barrier_sched()</tt>, and +<tt>rcu_read_lock_sched_held()</tt>. +However, anything that disables preemption also marks an RCU-sched +read-side critical section, including +<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>, +<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>, +and so on. + +<h3><a name="Sleepable RCU">Sleepable RCU</a></h3> + +<p> +For well over a decade, someone saying “I need to block within +an RCU read-side critical section” was a reliable indication +that this someone did not understand RCU. +After all, if you are always blocking in an RCU read-side critical +section, you can probably afford to use a higher-overhead synchronization +mechanism. +However, that changed with the advent of the Linux kernel's notifiers, +whose RCU read-side critical +sections almost never sleep, but sometimes need to. +This resulted in the introduction of +<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>, +or <i>SRCU</i>. + +<p> +SRCU allows different domains to be defined, with each such domain +defined by an instance of an <tt>srcu_struct</tt> structure. +A pointer to this structure must be passed in to each SRCU function, +for example, <tt>synchronize_srcu(&ss)</tt>, where +<tt>ss</tt> is the <tt>srcu_struct</tt> structure. +The key benefit of these domains is that a slow SRCU reader in one +domain does not delay an SRCU grace period in some other domain. +That said, one consequence of these domains is that read-side code +must pass a “cookie” from <tt>srcu_read_lock()</tt> +to <tt>srcu_read_unlock()</tt>, for example, as follows: + +<blockquote> +<pre> + 1 int idx; + 2 + 3 idx = srcu_read_lock(&ss); + 4 do_something(); + 5 srcu_read_unlock(&ss, idx); +</pre> +</blockquote> + +<p> +As noted above, it is legal to block within SRCU read-side critical sections, +however, with great power comes great responsibility. +If you block forever in one of a given domain's SRCU read-side critical +sections, then that domain's grace periods will also be blocked forever. +Of course, one good way to block forever is to deadlock, which can +happen if any operation in a given domain's SRCU read-side critical +section can block waiting, either directly or indirectly, for that domain's +grace period to elapse. +For example, this results in a self-deadlock: + +<blockquote> +<pre> + 1 int idx; + 2 + 3 idx = srcu_read_lock(&ss); + 4 do_something(); + 5 synchronize_srcu(&ss); + 6 srcu_read_unlock(&ss, idx); +</pre> +</blockquote> + +<p> +However, if line 5 acquired a mutex that was held across +a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>, +deadlock would still be possible. +Furthermore, if line 5 acquired a mutex that was held across +a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>, +and if an <tt>ss1</tt>-domain SRCU read-side critical section +acquired another mutex that was held across as <tt>ss</tt>-domain +<tt>synchronize_srcu()</tt>, +deadlock would again be possible. +Such a deadlock cycle could extend across an arbitrarily large number +of different SRCU domains. +Again, with great power comes great responsibility. + +<p> +Unlike the other RCU flavors, SRCU read-side critical sections can +run on idle and even offline CPUs. +This ability requires that <tt>srcu_read_lock()</tt> and +<tt>srcu_read_unlock()</tt> contain memory barriers, which means +that SRCU readers will run a bit slower than would RCU readers. +It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt> +API, which, in combination with <tt>srcu_read_unlock()</tt>, +guarantees a full memory barrier. + +<p> +The +<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a> +includes +<tt>srcu_read_lock()</tt>, +<tt>srcu_read_unlock()</tt>, +<tt>srcu_dereference()</tt>, +<tt>srcu_dereference_check()</tt>, +<tt>synchronize_srcu()</tt>, +<tt>synchronize_srcu_expedited()</tt>, +<tt>call_srcu()</tt>, +<tt>srcu_barrier()</tt>, and +<tt>srcu_read_lock_held()</tt>. +It also includes +<tt>DEFINE_SRCU()</tt>, +<tt>DEFINE_STATIC_SRCU()</tt>, and +<tt>init_srcu_struct()</tt> +APIs for defining and initializing <tt>srcu_struct</tt> structures. + +<h3><a name="Tasks RCU">Tasks RCU</a></h3> + +<p> +Some forms of tracing use “tramopolines” to handle the +binary rewriting required to install different types of probes. +It would be good to be able to free old trampolines, which sounds +like a job for some form of RCU. +However, because it is necessary to be able to install a trace +anywhere in the code, it is not possible to use read-side markers +such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. +In addition, it does not work to have these markers in the trampoline +itself, because there would need to be instructions following +<tt>rcu_read_unlock()</tt>. +Although <tt>synchronize_rcu()</tt> would guarantee that execution +reached the <tt>rcu_read_unlock()</tt>, it would not be able to +guarantee that execution had completely left the trampoline. + +<p> +The solution, in the form of +<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>, +is to have implicit +read-side critical sections that are delimited by voluntary context +switches, that is, calls to <tt>schedule()</tt>, +<tt>cond_resched_rcu_qs()</tt>, and +<tt>synchronize_rcu_tasks()</tt>. +In addition, transitions to and from userspace execution also delimit +tasks-RCU read-side critical sections. + +<p> +The tasks-RCU API is quite compact, consisting only of +<tt>call_rcu_tasks()</tt>, +<tt>synchronize_rcu_tasks()</tt>, and +<tt>rcu_barrier_tasks()</tt>. + +<h2><a name="Possible Future Changes">Possible Future Changes</a></h2> + +<p> +One of the tricks that RCU uses to attain update-side scalability is +to increase grace-period latency with increasing numbers of CPUs. +If this becomes a serious problem, it will be necessary to rework the +grace-period state machine so as to avoid the need for the additional +latency. + +<p> +Expedited grace periods scan the CPUs, so their latency and overhead +increases with increasing numbers of CPUs. +If this becomes a serious problem on large systems, it will be necessary +to do some redesign to avoid this scalability problem. + +<p> +RCU disables CPU hotplug in a few places, perhaps most notably in the +expedited grace-period and <tt>rcu_barrier()</tt> operations. +If there is a strong reason to use expedited grace periods in CPU-hotplug +notifiers, it will be necessary to avoid disabling CPU hotplug. +This would introduce some complexity, so there had better be a <i>very</i> +good reason. + +<p> +The tradeoff between grace-period latency on the one hand and interruptions +of other CPUs on the other hand may need to be re-examined. +The desire is of course for zero grace-period latency as well as zero +interprocessor interrupts undertaken during an expedited grace period +operation. +While this ideal is unlikely to be achievable, it is quite possible that +further improvements can be made. + +<p> +The multiprocessor implementations of RCU use a combining tree that +groups CPUs so as to reduce lock contention and increase cache locality. +However, this combining tree does not spread its memory across NUMA +nodes nor does it align the CPU groups with hardware features such +as sockets or cores. +Such spreading and alignment is currently believed to be unnecessary +because the hotpath read-side primitives do not access the combining +tree, nor does <tt>call_rcu()</tt> in the common case. +If you believe that your architecture needs such spreading and alignment, +then your architecture should also benefit from the +<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set +to the number of CPUs in a socket, NUMA node, or whatever. +If the number of CPUs is too large, use a fraction of the number of +CPUs. +If the number of CPUs is a large prime number, well, that certainly +is an “interesting” architectural choice! +More flexible arrangements might be considered, but only if +<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only +if the inadequacy has been demonstrated by a carefully run and +realistic system-level workload. + +<p> +Please note that arrangements that require RCU to remap CPU numbers will +require extremely good demonstration of need and full exploration of +alternatives. + +<p> +There is an embarrassingly large number of flavors of RCU, and this +number has been increasing over time. +Perhaps it will be possible to combine some at some future date. + +<p> +RCU's various kthreads are reasonably recent additions. +It is quite likely that adjustments will be required to more gracefully +handle extreme loads. +It might also be necessary to be able to relate CPU utilization by +RCU's kthreads and softirq handlers to the code that instigated this +CPU utilization. +For example, RCU callback overhead might be charged back to the +originating <tt>call_rcu()</tt> instance, though probably not +in production kernels. + +<h2><a name="Summary">Summary</a></h2> + +<p> +This document has presented more than two decade's worth of RCU +requirements. +Given that the requirements keep changing, this will not be the last +word on this subject, but at least it serves to get an important +subset of the requirements set forth. + +<h2><a name="Acknowledgments">Acknowledgments</a></h2> + +I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar, +Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and +Andy Lutomirski for their help in rendering +this article human readable, and to Michelle Rankin for her support +of this effort. +Other contributions are acknowledged in the Linux kernel's git archive. +The cartoon is copyright (c) 2013 by Melissa Broussard, +and is provided +under the terms of the Creative Commons Attribution-Share Alike 3.0 +United States license. + +<h3><a name="Answers to Quick Quizzes"> +Answers to Quick Quizzes</a></h3> + +<a name="qq1answer"></a> +<p><b>Quick Quiz 1</b>: +Wait a minute! +You said that updaters can make useful forward progress concurrently +with readers, but pre-existing readers will block +<tt>synchronize_rcu()</tt>!!! +Just who are you trying to fool??? + + +</p><p><b>Answer</b>: +First, if updaters do not wish to be blocked by readers, they can use +<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will +be discussed later. +Second, even when using <tt>synchronize_rcu()</tt>, the other +update-side code does run concurrently with readers, whether pre-existing +or not. + + +</p><p><a href="#Quick%20Quiz%201"><b>Back to Quick Quiz 1</b>.</a> + +<a name="qq2answer"></a> +<p><b>Quick Quiz 2</b>: +Why is the <tt>synchronize_rcu()</tt> on line 28 needed? + + +</p><p><b>Answer</b>: +Without that extra grace period, memory reordering could result in +<tt>do_something_dlm()</tt> executing <tt>do_something()</tt> +concurrently with the last bits of <tt>recovery()</tt>. + + +</p><p><a href="#Quick%20Quiz%202"><b>Back to Quick Quiz 2</b>.</a> + +<a name="qq3answer"></a> +<p><b>Quick Quiz 3</b>: +But <tt>rcu_assign_pointer()</tt> does nothing to prevent the +two assignments to <tt>p->a</tt> and <tt>p->b</tt> +from being reordered. +Can't that also cause problems? + + +</p><p><b>Answer</b>: +No, it cannot. +The readers cannot see either of these two fields until +the assignment to <tt>gp</tt>, by which time both fields are +fully initialized. +So reordering the assignments +to <tt>p->a</tt> and <tt>p->b</tt> cannot possibly +cause any problems. + + +</p><p><a href="#Quick%20Quiz%203"><b>Back to Quick Quiz 3</b>.</a> + +<a name="qq4answer"></a> +<p><b>Quick Quiz 4</b>: +Without the <tt>rcu_dereference()</tt> or the +<tt>rcu_access_pointer()</tt>, what destructive optimizations +might the compiler make use of? + + +</p><p><b>Answer</b>: +Let's start with what happens to <tt>do_something_gp()</tt> +if it fails to use <tt>rcu_dereference()</tt>. +It could reuse a value formerly fetched from this same pointer. +It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time +manner, resulting in <i>load tearing</i>, in turn resulting a bytewise +mash-up of two distince pointer values. +It might even use value-speculation optimizations, where it makes a wrong +guess, but by the time it gets around to checking the value, an update +has changed the pointer to match the wrong guess. +Too bad about any dereferences that returned pre-initialization garbage +in the meantime! + +<p> +For <tt>remove_gp_synchronous()</tt>, as long as all modifications +to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, +the above optimizations are harmless. +However, +with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>, +<tt>sparse</tt> will complain if you +define <tt>gp</tt> with <tt>__rcu</tt> and then +access it without using +either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. + + +</p><p><a href="#Quick%20Quiz%204"><b>Back to Quick Quiz 4</b>.</a> + +<a name="qq5answer"></a> +<p><b>Quick Quiz 5</b>: +Given that multiple CPUs can start RCU read-side critical sections +at any time without any ordering whatsoever, how can RCU possibly tell whether +or not a given RCU read-side critical section starts before a +given instance of <tt>synchronize_rcu()</tt>? + + +</p><p><b>Answer</b>: +If RCU cannot tell whether or not a given +RCU read-side critical section starts before a +given instance of <tt>synchronize_rcu()</tt>, +then it must assume that the RCU read-side critical section +started first. +In other words, a given instance of <tt>synchronize_rcu()</tt> +can avoid waiting on a given RCU read-side critical section only +if it can prove that <tt>synchronize_rcu()</tt> started first. + + +</p><p><a href="#Quick%20Quiz%205"><b>Back to Quick Quiz 5</b>.</a> + +<a name="qq6answer"></a> +<p><b>Quick Quiz 6</b>: +The first and second guarantees require unbelievably strict ordering! +Are all these memory barriers <i> really</i> required? + + +</p><p><b>Answer</b>: +Yes, they really are required. +To see why the first guarantee is required, consider the following +sequence of events: + +<ol> +<li> CPU 1: <tt>rcu_read_lock()</tt> +<li> CPU 1: <tt>q = rcu_dereference(gp); + /* Very likely to return p. */</tt> +<li> CPU 0: <tt>list_del_rcu(p);</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> starts. +<li> CPU 1: <tt>do_something_with(q->a); + /* No smp_mb(), so might happen after kfree(). */</tt> +<li> CPU 1: <tt>rcu_read_unlock()</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> returns. +<li> CPU 0: <tt>kfree(p);</tt> +</ol> + +<p> +Therefore, there absolutely must be a full memory barrier between the +end of the RCU read-side critical section and the end of the +grace period. + +<p> +The sequence of events demonstrating the necessity of the second rule +is roughly similar: + +<ol> +<li> CPU 0: <tt>list_del_rcu(p);</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> starts. +<li> CPU 1: <tt>rcu_read_lock()</tt> +<li> CPU 1: <tt>q = rcu_dereference(gp); + /* Might return p if no memory barrier. */</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> returns. +<li> CPU 0: <tt>kfree(p);</tt> +<li> CPU 1: <tt>do_something_with(q->a); /* Boom!!! */</tt> +<li> CPU 1: <tt>rcu_read_unlock()</tt> +</ol> + +<p> +And similarly, without a memory barrier between the beginning of the +grace period and the beginning of the RCU read-side critical section, +CPU 1 might end up accessing the freelist. + +<p> +The “as if” rule of course applies, so that any implementation +that acts as if the appropriate memory barriers were in place is a +correct implementation. +That said, it is much easier to fool yourself into believing that you have +adhered to the as-if rule than it is to actually adhere to it! + + +</p><p><a href="#Quick%20Quiz%206"><b>Back to Quick Quiz 6</b>.</a> + +<a name="qq7answer"></a> +<p><b>Quick Quiz 7</b>: +But how does the upgrade-to-write operation exclude other readers? + + +</p><p><b>Answer</b>: +It doesn't, just like normal RCU updates, which also do not exclude +RCU readers. + + +</p><p><a href="#Quick%20Quiz%207"><b>Back to Quick Quiz 7</b>.</a> + +<a name="qq8answer"></a> +<p><b>Quick Quiz 8</b>: +Can't the compiler also reorder this code? + + +</p><p><b>Answer</b>: +No, the volatile casts in <tt>READ_ONCE()</tt> and +<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in +this particular case. + + +</p><p><a href="#Quick%20Quiz%208"><b>Back to Quick Quiz 8</b>.</a> + +<a name="qq9answer"></a> +<p><b>Quick Quiz 9</b>: +Suppose that synchronize_rcu() did wait until all readers had completed. +Would the updater be able to rely on this? + + +</p><p><b>Answer</b>: +No. +Even if <tt>synchronize_rcu()</tt> were to wait until +all readers had completed, a new reader might start immediately after +<tt>synchronize_rcu()</tt> completed. +Therefore, the code following +<tt>synchronize_rcu()</tt> cannot rely on there being no readers +in any case. + + +</p><p><a href="#Quick%20Quiz%209"><b>Back to Quick Quiz 9</b>.</a> + +<a name="qq10answer"></a> +<p><b>Quick Quiz 10</b>: +How long a sequence of grace periods, each separated by an RCU read-side +critical section, would be required to partition the RCU read-side +critical sections at the beginning and end of the chain? + + +</p><p><b>Answer</b>: +In theory, an infinite number. +In practice, an unknown number that is sensitive to both implementation +details and timing considerations. +Therefore, even in practice, RCU users must abide by the theoretical rather +than the practical answer. + + +</p><p><a href="#Quick%20Quiz%2010"><b>Back to Quick Quiz 10</b>.</a> + +<a name="qq11answer"></a> +<p><b>Quick Quiz 11</b>: +What about sleeping locks? + + +</p><p><b>Answer</b>: +These are forbidden within Linux-kernel RCU read-side critical sections +because it is not legal to place a quiescent state (in this case, +voluntary context switch) within an RCU read-side critical section. +However, sleeping locks may be used within userspace RCU read-side critical +sections, and also within Linux-kernel sleepable RCU +<a href="#Sleepable RCU">(SRCU)</a> +read-side critical sections. +In addition, the -rt patchset turns spinlocks into a sleeping locks so +that the corresponding critical sections can be preempted, which +also means that these sleeplockified spinlocks (but not other sleeping locks!) +may be acquire within -rt-Linux-kernel RCU read-side critical sections. + +<p> +Note that it <i>is</i> legal for a normal RCU read-side critical section +to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>), +but only as long as it does not loop indefinitely attempting to +conditionally acquire that sleeping locks. +The key point is that things like <tt>mutex_trylock()</tt> +either return with the mutex held, or return an error indication if +the mutex was not immediately available. +Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping. + + +</p><p><a href="#Quick%20Quiz%2011"><b>Back to Quick Quiz 11</b>.</a> + +<a name="qq12answer"></a> +<p><b>Quick Quiz 12</b>: +Why does line 19 use <tt>rcu_access_pointer()</tt>? +After all, <tt>call_rcu()</tt> on line 25 stores into the +structure, which would interact badly with concurrent insertions. +Doesn't this mean that <tt>rcu_dereference()</tt> is required? + + +</p><p><b>Answer</b>: +Presumably the <tt>->gp_lock</tt> acquired on line 18 excludes +any changes, including any insertions that <tt>rcu_dereference()</tt> +would protect against. +Therefore, any insertions will be delayed until after <tt>->gp_lock</tt> +is released on line 25, which in turn means that +<tt>rcu_access_pointer()</tt> suffices. + + +</p><p><a href="#Quick%20Quiz%2012"><b>Back to Quick Quiz 12</b>.</a> + +<a name="qq13answer"></a> +<p><b>Quick Quiz 13</b>: +Earlier it was claimed that <tt>call_rcu()</tt> and +<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked +by readers. +But how can that be correct, given that the invocation of the callback +and the freeing of the memory (respectively) must still wait for +a grace period to elapse? + + +</p><p><b>Answer</b>: +We could define things this way, but keep in mind that this sort of +definition would say that updates in garbage-collected languages +cannot complete until the next time the garbage collector runs, +which does not seem at all reasonable. +The key point is that in most cases, an updater using either +<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the +next update as soon as it has invoked <tt>call_rcu()</tt> or +<tt>kfree_rcu()</tt>, without having to wait for a subsequent +grace period. + + +</p><p><a href="#Quick%20Quiz%2013"><b>Back to Quick Quiz 13</b>.</a> + +<a name="qq14answer"></a> +<p><b>Quick Quiz 14</b>: +So what happens with <tt>synchronize_rcu()</tt> during +scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> +kernels? + + +</p><p><b>Answer</b>: +In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt> +maps directly to <tt>synchronize_sched()</tt>. +Therefore, <tt>synchronize_rcu()</tt> works normally throughout +boot in <tt>CONFIG_PREEMPT=n</tt> kernels. +However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels, +so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt> +during scheduler initialization. + + +</p><p><a href="#Quick%20Quiz%2014"><b>Back to Quick Quiz 14</b>.</a> + + +</body></html> diff --git a/Documentation/RCU/Design/Requirements/Requirements.htmlx b/Documentation/RCU/Design/Requirements/Requirements.htmlx new file mode 100644 index 000000000000..3a97ba490c42 --- /dev/null +++ b/Documentation/RCU/Design/Requirements/Requirements.htmlx @@ -0,0 +1,2741 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> + <html> + <head><title>A Tour Through RCU's Requirements [LWN.net]</title> + <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8"> + +<h1>A Tour Through RCU's Requirements</h1> + +<p>Copyright IBM Corporation, 2015</p> +<p>Author: Paul E. McKenney</p> +<p><i>The initial version of this document appeared in the +<a href="https://lwn.net/">LWN</a> articles +<a href="https://lwn.net/Articles/652156/">here</a>, +<a href="https://lwn.net/Articles/652677/">here</a>, and +<a href="https://lwn.net/Articles/653326/">here</a>.</i></p> + +<h2>Introduction</h2> + +<p> +Read-copy update (RCU) is a synchronization mechanism that is often +used as a replacement for reader-writer locking. +RCU is unusual in that updaters do not block readers, +which means that RCU's read-side primitives can be exceedingly fast +and scalable. +In addition, updaters can make useful forward progress concurrently +with readers. +However, all this concurrency between RCU readers and updaters does raise +the question of exactly what RCU readers are doing, which in turn +raises the question of exactly what RCU's requirements are. + +<p> +This document therefore summarizes RCU's requirements, and can be thought +of as an informal, high-level specification for RCU. +It is important to understand that RCU's specification is primarily +empirical in nature; +in fact, I learned about many of these requirements the hard way. +This situation might cause some consternation, however, not only +has this learning process been a lot of fun, but it has also been +a great privilege to work with so many people willing to apply +technologies in interesting new ways. + +<p> +All that aside, here are the categories of currently known RCU requirements: +</p> + +<ol> +<li> <a href="#Fundamental Requirements"> + Fundamental Requirements</a> +<li> <a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a> +<li> <a href="#Parallelism Facts of Life"> + Parallelism Facts of Life</a> +<li> <a href="#Quality-of-Implementation Requirements"> + Quality-of-Implementation Requirements</a> +<li> <a href="#Linux Kernel Complications"> + Linux Kernel Complications</a> +<li> <a href="#Software-Engineering Requirements"> + Software-Engineering Requirements</a> +<li> <a href="#Other RCU Flavors"> + Other RCU Flavors</a> +<li> <a href="#Possible Future Changes"> + Possible Future Changes</a> +</ol> + +<p> +This is followed by a <a href="#Summary">summary</a>, +which is in turn followed by the inevitable +<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>. + +<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2> + +<p> +RCU's fundamental requirements are the closest thing RCU has to hard +mathematical requirements. +These are: + +<ol> +<li> <a href="#Grace-Period Guarantee"> + Grace-Period Guarantee</a> +<li> <a href="#Publish-Subscribe Guarantee"> + Publish-Subscribe Guarantee</a> +<li> <a href="#Memory-Barrier Guarantees"> + Memory-Barrier Guarantees</a> +<li> <a href="#RCU Primitives Guaranteed to Execute Unconditionally"> + RCU Primitives Guaranteed to Execute Unconditionally</a> +<li> <a href="#Guaranteed Read-to-Write Upgrade"> + Guaranteed Read-to-Write Upgrade</a> +</ol> + +<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3> + +<p> +RCU's grace-period guarantee is unusual in being premeditated: +Jack Slingwine and I had this guarantee firmly in mind when we started +work on RCU (then called “rclock”) in the early 1990s. +That said, the past two decades of experience with RCU have produced +a much more detailed understanding of this guarantee. + +<p> +RCU's grace-period guarantee allows updaters to wait for the completion +of all pre-existing RCU read-side critical sections. +An RCU read-side critical section +begins with the marker <tt>rcu_read_lock()</tt> and ends with +the marker <tt>rcu_read_unlock()</tt>. +These markers may be nested, and RCU treats a nested set as one +big RCU read-side critical section. +Production-quality implementations of <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> are extremely lightweight, and in +fact have exactly zero overhead in Linux kernels built for production +use with <tt>CONFIG_PREEMPT=n</tt>. + +<p> +This guarantee allows ordering to be enforced with extremely low +overhead to readers, for example: + +<blockquote> +<pre> + 1 int x, y; + 2 + 3 void thread0(void) + 4 { + 5 rcu_read_lock(); + 6 r1 = READ_ONCE(x); + 7 r2 = READ_ONCE(y); + 8 rcu_read_unlock(); + 9 } +10 +11 void thread1(void) +12 { +13 WRITE_ONCE(x, 1); +14 synchronize_rcu(); +15 WRITE_ONCE(y, 1); +16 } +</pre> +</blockquote> + +<p> +Because the <tt>synchronize_rcu()</tt> on line 14 waits for +all pre-existing readers, any instance of <tt>thread0()</tt> that +loads a value of zero from <tt>x</tt> must complete before +<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must +also load a value of zero from <tt>y</tt>. +Similarly, any instance of <tt>thread0()</tt> that loads a value of +one from <tt>y</tt> must have started after the +<tt>synchronize_rcu()</tt> started, and must therefore also load +a value of one from <tt>x</tt>. +Therefore, the outcome: +<blockquote> +<pre> +(r1 == 0 && r2 == 1) +</pre> +</blockquote> +cannot happen. + +<p>@@QQ@@ +Wait a minute! +You said that updaters can make useful forward progress concurrently +with readers, but pre-existing readers will block +<tt>synchronize_rcu()</tt>!!! +Just who are you trying to fool??? +<p>@@QQA@@ +First, if updaters do not wish to be blocked by readers, they can use +<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will +be discussed later. +Second, even when using <tt>synchronize_rcu()</tt>, the other +update-side code does run concurrently with readers, whether pre-existing +or not. +<p>@@QQE@@ + +<p> +This scenario resembles one of the first uses of RCU in +<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>, +which managed a distributed lock manager's transition into +a state suitable for handling recovery from node failure, +more or less as follows: + +<blockquote> +<pre> + 1 #define STATE_NORMAL 0 + 2 #define STATE_WANT_RECOVERY 1 + 3 #define STATE_RECOVERING 2 + 4 #define STATE_WANT_NORMAL 3 + 5 + 6 int state = STATE_NORMAL; + 7 + 8 void do_something_dlm(void) + 9 { +10 int state_snap; +11 +12 rcu_read_lock(); +13 state_snap = READ_ONCE(state); +14 if (state_snap == STATE_NORMAL) +15 do_something(); +16 else +17 do_something_carefully(); +18 rcu_read_unlock(); +19 } +20 +21 void start_recovery(void) +22 { +23 WRITE_ONCE(state, STATE_WANT_RECOVERY); +24 synchronize_rcu(); +25 WRITE_ONCE(state, STATE_RECOVERING); +26 recovery(); +27 WRITE_ONCE(state, STATE_WANT_NORMAL); +28 synchronize_rcu(); +29 WRITE_ONCE(state, STATE_NORMAL); +30 } +</pre> +</blockquote> + +<p> +The RCU read-side critical section in <tt>do_something_dlm()</tt> +works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt> +to guarantee that <tt>do_something()</tt> never runs concurrently +with <tt>recovery()</tt>, but with little or no synchronization +overhead in <tt>do_something_dlm()</tt>. + +<p>@@QQ@@ +Why is the <tt>synchronize_rcu()</tt> on line 28 needed? +<p>@@QQA@@ +Without that extra grace period, memory reordering could result in +<tt>do_something_dlm()</tt> executing <tt>do_something()</tt> +concurrently with the last bits of <tt>recovery()</tt>. +<p>@@QQE@@ + +<p> +In order to avoid fatal problems such as deadlocks, +an RCU read-side critical section must not contain calls to +<tt>synchronize_rcu()</tt>. +Similarly, an RCU read-side critical section must not +contain anything that waits, directly or indirectly, on completion of +an invocation of <tt>synchronize_rcu()</tt>. + +<p> +Although RCU's grace-period guarantee is useful in and of itself, with +<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>, +it would be good to be able to use RCU to coordinate read-side +access to linked data structures. +For this, the grace-period guarantee is not sufficient, as can +be seen in function <tt>add_gp_buggy()</tt> below. +We will look at the reader's code later, but in the meantime, just think of +the reader as locklessly picking up the <tt>gp</tt> pointer, +and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the +<tt>->a</tt> and <tt>->b</tt> fields. + +<blockquote> +<pre> + 1 bool add_gp_buggy(int a, int b) + 2 { + 3 p = kmalloc(sizeof(*p), GFP_KERNEL); + 4 if (!p) + 5 return -ENOMEM; + 6 spin_lock(&gp_lock); + 7 if (rcu_access_pointer(gp)) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +11 p->a = a; +12 p->b = a; +13 gp = p; /* ORDERING BUG */ +14 spin_unlock(&gp_lock); +15 return true; +16 } +</pre> +</blockquote> + +<p> +The problem is that both the compiler and weakly ordered CPUs are within +their rights to reorder this code as follows: + +<blockquote> +<pre> + 1 bool add_gp_buggy_optimized(int a, int b) + 2 { + 3 p = kmalloc(sizeof(*p), GFP_KERNEL); + 4 if (!p) + 5 return -ENOMEM; + 6 spin_lock(&gp_lock); + 7 if (rcu_access_pointer(gp)) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +<b>11 gp = p; /* ORDERING BUG */ +12 p->a = a; +13 p->b = a;</b> +14 spin_unlock(&gp_lock); +15 return true; +16 } +</pre> +</blockquote> + +<p> +If an RCU reader fetches <tt>gp</tt> just after +<tt>add_gp_buggy_optimized</tt> executes line 11, +it will see garbage in the <tt>->a</tt> and <tt>->b</tt> +fields. +And this is but one of many ways in which compiler and hardware optimizations +could cause trouble. +Therefore, we clearly need some way to prevent the compiler and the CPU from +reordering in this manner, which brings us to the publish-subscribe +guarantee discussed in the next section. + +<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3> + +<p> +RCU's publish-subscribe guarantee allows data to be inserted +into a linked data structure without disrupting RCU readers. +The updater uses <tt>rcu_assign_pointer()</tt> to insert the +new data, and readers use <tt>rcu_dereference()</tt> to +access data, whether new or old. +The following shows an example of insertion: + +<blockquote> +<pre> + 1 bool add_gp(int a, int b) + 2 { + 3 p = kmalloc(sizeof(*p), GFP_KERNEL); + 4 if (!p) + 5 return -ENOMEM; + 6 spin_lock(&gp_lock); + 7 if (rcu_access_pointer(gp)) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +11 p->a = a; +12 p->b = a; +13 rcu_assign_pointer(gp, p); +14 spin_unlock(&gp_lock); +15 return true; +16 } +</pre> +</blockquote> + +<p> +The <tt>rcu_assign_pointer()</tt> on line 13 is conceptually +equivalent to a simple assignment statement, but also guarantees +that its assignment will +happen after the two assignments in lines 11 and 12, +similar to the C11 <tt>memory_order_release</tt> store operation. +It also prevents any number of “interesting” compiler +optimizations, for example, the use of <tt>gp</tt> as a scratch +location immediately preceding the assignment. + +<p>@@QQ@@ +But <tt>rcu_assign_pointer()</tt> does nothing to prevent the +two assignments to <tt>p->a</tt> and <tt>p->b</tt> +from being reordered. +Can't that also cause problems? +<p>@@QQA@@ +No, it cannot. +The readers cannot see either of these two fields until +the assignment to <tt>gp</tt>, by which time both fields are +fully initialized. +So reordering the assignments +to <tt>p->a</tt> and <tt>p->b</tt> cannot possibly +cause any problems. +<p>@@QQE@@ + +<p> +It is tempting to assume that the reader need not do anything special +to control its accesses to the RCU-protected data, +as shown in <tt>do_something_gp_buggy()</tt> below: + +<blockquote> +<pre> + 1 bool do_something_gp_buggy(void) + 2 { + 3 rcu_read_lock(); + 4 p = gp; /* OPTIMIZATIONS GALORE!!! */ + 5 if (p) { + 6 do_something(p->a, p->b); + 7 rcu_read_unlock(); + 8 return true; + 9 } +10 rcu_read_unlock(); +11 return false; +12 } +</pre> +</blockquote> + +<p> +However, this temptation must be resisted because there are a +surprisingly large number of ways that the compiler +(to say nothing of +<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>) +can trip this code up. +For but one example, if the compiler were short of registers, it +might choose to refetch from <tt>gp</tt> rather than keeping +a separate copy in <tt>p</tt> as follows: + +<blockquote> +<pre> + 1 bool do_something_gp_buggy_optimized(void) + 2 { + 3 rcu_read_lock(); + 4 if (gp) { /* OPTIMIZATIONS GALORE!!! */ +<b> 5 do_something(gp->a, gp->b);</b> + 6 rcu_read_unlock(); + 7 return true; + 8 } + 9 rcu_read_unlock(); +10 return false; +11 } +</pre> +</blockquote> + +<p> +If this function ran concurrently with a series of updates that +replaced the current structure with a new one, +the fetches of <tt>gp->a</tt> +and <tt>gp->b</tt> might well come from two different structures, +which could cause serious confusion. +To prevent this (and much else besides), <tt>do_something_gp()</tt> uses +<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>: + +<blockquote> +<pre> + 1 bool do_something_gp(void) + 2 { + 3 rcu_read_lock(); + 4 p = rcu_dereference(gp); + 5 if (p) { + 6 do_something(p->a, p->b); + 7 rcu_read_unlock(); + 8 return true; + 9 } +10 rcu_read_unlock(); +11 return false; +12 } +</pre> +</blockquote> + +<p> +The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha) +memory barriers in the Linux kernel. +Should a +<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a> +ever appear, then <tt>rcu_dereference()</tt> could be implemented +as a <tt>memory_order_consume</tt> load. +Regardless of the exact implementation, a pointer fetched by +<tt>rcu_dereference()</tt> may not be used outside of the +outermost RCU read-side critical section containing that +<tt>rcu_dereference()</tt>, unless protection of +the corresponding data element has been passed from RCU to some +other synchronization mechanism, most commonly locking or +<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>. + +<p> +In short, updaters use <tt>rcu_assign_pointer()</tt> and readers +use <tt>rcu_dereference()</tt>, and these two RCU API elements +work together to ensure that readers have a consistent view of +newly added data elements. + +<p> +Of course, it is also necessary to remove elements from RCU-protected +data structures, for example, using the following process: + +<ol> +<li> Remove the data element from the enclosing structure. +<li> Wait for all pre-existing RCU read-side critical sections + to complete (because only pre-existing readers can possibly have + a reference to the newly removed data element). +<li> At this point, only the updater has a reference to the + newly removed data element, so it can safely reclaim + the data element, for example, by passing it to <tt>kfree()</tt>. +</ol> + +This process is implemented by <tt>remove_gp_synchronous()</tt>: + +<blockquote> +<pre> + 1 bool remove_gp_synchronous(void) + 2 { + 3 struct foo *p; + 4 + 5 spin_lock(&gp_lock); + 6 p = rcu_access_pointer(gp); + 7 if (!p) { + 8 spin_unlock(&gp_lock); + 9 return false; +10 } +11 rcu_assign_pointer(gp, NULL); +12 spin_unlock(&gp_lock); +13 synchronize_rcu(); +14 kfree(p); +15 return true; +16 } +</pre> +</blockquote> + +<p> +This function is straightforward, with line 13 waiting for a grace +period before line 14 frees the old data element. +This waiting ensures that readers will reach line 7 of +<tt>do_something_gp()</tt> before the data element referenced by +<tt>p</tt> is freed. +The <tt>rcu_access_pointer()</tt> on line 6 is similar to +<tt>rcu_dereference()</tt>, except that: + +<ol> +<li> The value returned by <tt>rcu_access_pointer()</tt> + cannot be dereferenced. + If you want to access the value pointed to as well as + the pointer itself, use <tt>rcu_dereference()</tt> + instead of <tt>rcu_access_pointer()</tt>. +<li> The call to <tt>rcu_access_pointer()</tt> need not be + protected. + In contrast, <tt>rcu_dereference()</tt> must either be + within an RCU read-side critical section or in a code + segment where the pointer cannot change, for example, in + code protected by the corresponding update-side lock. +</ol> + +<p>@@QQ@@ +Without the <tt>rcu_dereference()</tt> or the +<tt>rcu_access_pointer()</tt>, what destructive optimizations +might the compiler make use of? +<p>@@QQA@@ +Let's start with what happens to <tt>do_something_gp()</tt> +if it fails to use <tt>rcu_dereference()</tt>. +It could reuse a value formerly fetched from this same pointer. +It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time +manner, resulting in <i>load tearing</i>, in turn resulting a bytewise +mash-up of two distince pointer values. +It might even use value-speculation optimizations, where it makes a wrong +guess, but by the time it gets around to checking the value, an update +has changed the pointer to match the wrong guess. +Too bad about any dereferences that returned pre-initialization garbage +in the meantime! + +<p> +For <tt>remove_gp_synchronous()</tt>, as long as all modifications +to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, +the above optimizations are harmless. +However, +with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt>, +<tt>sparse</tt> will complain if you +define <tt>gp</tt> with <tt>__rcu</tt> and then +access it without using +either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. +<p>@@QQE@@ + +<p> +In short, RCU's publish-subscribe guarantee is provided by the combination +of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>. +This guarantee allows data elements to be safely added to RCU-protected +linked data structures without disrupting RCU readers. +This guarantee can be used in combination with the grace-period +guarantee to also allow data elements to be removed from RCU-protected +linked data structures, again without disrupting RCU readers. + +<p> +This guarantee was only partially premeditated. +DYNIX/ptx used an explicit memory barrier for publication, but had nothing +resembling <tt>rcu_dereference()</tt> for subscription, nor did it +have anything resembling the <tt>smp_read_barrier_depends()</tt> +that was later subsumed into <tt>rcu_dereference()</tt>. +The need for these operations made itself known quite suddenly at a +late-1990s meeting with the DEC Alpha architects, back in the days when +DEC was still a free-standing company. +It took the Alpha architects a good hour to convince me that any sort +of barrier would ever be needed, and it then took me a good <i>two</i> hours +to convince them that their documentation did not make this point clear. +More recent work with the C and C++ standards committees have provided +much education on tricks and traps from the compiler. +In short, compilers were much less tricky in the early 1990s, but in +2015, don't even think about omitting <tt>rcu_dereference()</tt>! + +<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3> + +<p> +The previous section's simple linked-data-structure scenario clearly +demonstrates the need for RCU's stringent memory-ordering guarantees on +systems with more than one CPU: + +<ol> +<li> Each CPU that has an RCU read-side critical section that + begins before <tt>synchronize_rcu()</tt> starts is + guaranteed to execute a full memory barrier between the time + that the RCU read-side critical section ends and the time that + <tt>synchronize_rcu()</tt> returns. + Without this guarantee, a pre-existing RCU read-side critical section + might hold a reference to the newly removed <tt>struct foo</tt> + after the <tt>kfree()</tt> on line 14 of + <tt>remove_gp_synchronous()</tt>. +<li> Each CPU that has an RCU read-side critical section that ends + after <tt>synchronize_rcu()</tt> returns is guaranteed + to execute a full memory barrier between the time that + <tt>synchronize_rcu()</tt> begins and the time that the RCU + read-side critical section begins. + Without this guarantee, a later RCU read-side critical section + running after the <tt>kfree()</tt> on line 14 of + <tt>remove_gp_synchronous()</tt> might + later run <tt>do_something_gp()</tt> and find the + newly deleted <tt>struct foo</tt>. +<li> If the task invoking <tt>synchronize_rcu()</tt> remains + on a given CPU, then that CPU is guaranteed to execute a full + memory barrier sometime during the execution of + <tt>synchronize_rcu()</tt>. + This guarantee ensures that the <tt>kfree()</tt> on + line 14 of <tt>remove_gp_synchronous()</tt> really does + execute after the removal on line 11. +<li> If the task invoking <tt>synchronize_rcu()</tt> migrates + among a group of CPUs during that invocation, then each of the + CPUs in that group is guaranteed to execute a full memory barrier + sometime during the execution of <tt>synchronize_rcu()</tt>. + This guarantee also ensures that the <tt>kfree()</tt> on + line 14 of <tt>remove_gp_synchronous()</tt> really does + execute after the removal on + line 11, but also in the case where the thread executing the + <tt>synchronize_rcu()</tt> migrates in the meantime. +</ol> + +<p>@@QQ@@ +Given that multiple CPUs can start RCU read-side critical sections +at any time without any ordering whatsoever, how can RCU possibly tell whether +or not a given RCU read-side critical section starts before a +given instance of <tt>synchronize_rcu()</tt>? +<p>@@QQA@@ +If RCU cannot tell whether or not a given +RCU read-side critical section starts before a +given instance of <tt>synchronize_rcu()</tt>, +then it must assume that the RCU read-side critical section +started first. +In other words, a given instance of <tt>synchronize_rcu()</tt> +can avoid waiting on a given RCU read-side critical section only +if it can prove that <tt>synchronize_rcu()</tt> started first. +<p>@@QQE@@ + +<p>@@QQ@@ +The first and second guarantees require unbelievably strict ordering! +Are all these memory barriers <i> really</i> required? +<p>@@QQA@@ +Yes, they really are required. +To see why the first guarantee is required, consider the following +sequence of events: + +<ol> +<li> CPU 1: <tt>rcu_read_lock()</tt> +<li> CPU 1: <tt>q = rcu_dereference(gp); + /* Very likely to return p. */</tt> +<li> CPU 0: <tt>list_del_rcu(p);</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> starts. +<li> CPU 1: <tt>do_something_with(q->a); + /* No smp_mb(), so might happen after kfree(). */</tt> +<li> CPU 1: <tt>rcu_read_unlock()</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> returns. +<li> CPU 0: <tt>kfree(p);</tt> +</ol> + +<p> +Therefore, there absolutely must be a full memory barrier between the +end of the RCU read-side critical section and the end of the +grace period. + +<p> +The sequence of events demonstrating the necessity of the second rule +is roughly similar: + +<ol> +<li> CPU 0: <tt>list_del_rcu(p);</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> starts. +<li> CPU 1: <tt>rcu_read_lock()</tt> +<li> CPU 1: <tt>q = rcu_dereference(gp); + /* Might return p if no memory barrier. */</tt> +<li> CPU 0: <tt>synchronize_rcu()</tt> returns. +<li> CPU 0: <tt>kfree(p);</tt> +<li> CPU 1: <tt>do_something_with(q->a); /* Boom!!! */</tt> +<li> CPU 1: <tt>rcu_read_unlock()</tt> +</ol> + +<p> +And similarly, without a memory barrier between the beginning of the +grace period and the beginning of the RCU read-side critical section, +CPU 1 might end up accessing the freelist. + +<p> +The “as if” rule of course applies, so that any implementation +that acts as if the appropriate memory barriers were in place is a +correct implementation. +That said, it is much easier to fool yourself into believing that you have +adhered to the as-if rule than it is to actually adhere to it! +<p>@@QQE@@ + +<p> +Note that these memory-barrier requirements do not replace the fundamental +RCU requirement that a grace period wait for all pre-existing readers. +On the contrary, the memory barriers called out in this section must operate in +such a way as to <i>enforce</i> this fundamental requirement. +Of course, different implementations enforce this requirement in different +ways, but enforce it they must. + +<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3> + +<p> +The common-case RCU primitives are unconditional. +They are invoked, they do their job, and they return, with no possibility +of error, and no need to retry. +This is a key RCU design philosophy. + +<p> +However, this philosophy is pragmatic rather than pigheaded. +If someone comes up with a good justification for a particular conditional +RCU primitive, it might well be implemented and added. +After all, this guarantee was reverse-engineered, not premeditated. +The unconditional nature of the RCU primitives was initially an +accident of implementation, and later experience with synchronization +primitives with conditional primitives caused me to elevate this +accident to a guarantee. +Therefore, the justification for adding a conditional primitive to +RCU would need to be based on detailed and compelling use cases. + +<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3> + +<p> +As far as RCU is concerned, it is always possible to carry out an +update within an RCU read-side critical section. +For example, that RCU read-side critical section might search for +a given data element, and then might acquire the update-side +spinlock in order to update that element, all while remaining +in that RCU read-side critical section. +Of course, it is necessary to exit the RCU read-side critical section +before invoking <tt>synchronize_rcu()</tt>, however, this +inconvenience can be avoided through use of the +<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members +described later in this document. + +<p>@@QQ@@ +But how does the upgrade-to-write operation exclude other readers? +<p>@@QQA@@ +It doesn't, just like normal RCU updates, which also do not exclude +RCU readers. +<p>@@QQE@@ + +<p> +This guarantee allows lookup code to be shared between read-side +and update-side code, and was premeditated, appearing in the earliest +DYNIX/ptx RCU documentation. + +<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2> + +<p> +RCU provides extremely lightweight readers, and its read-side guarantees, +though quite useful, are correspondingly lightweight. +It is therefore all too easy to assume that RCU is guaranteeing more +than it really is. +Of course, the list of things that RCU does not guarantee is infinitely +long, however, the following sections list a few non-guarantees that +have caused confusion. +Except where otherwise noted, these non-guarantees were premeditated. + +<ol> +<li> <a href="#Readers Impose Minimal Ordering"> + Readers Impose Minimal Ordering</a> +<li> <a href="#Readers Do Not Exclude Updaters"> + Readers Do Not Exclude Updaters</a> +<li> <a href="#Updaters Only Wait For Old Readers"> + Updaters Only Wait For Old Readers</a> +<li> <a href="#Grace Periods Don't Partition Read-Side Critical Sections"> + Grace Periods Don't Partition Read-Side Critical Sections</a> +<li> <a href="#Read-Side Critical Sections Don't Partition Grace Periods"> + Read-Side Critical Sections Don't Partition Grace Periods</a> +<li> <a href="#Disabling Preemption Does Not Block Grace Periods"> + Disabling Preemption Does Not Block Grace Periods</a> +</ol> + +<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3> + +<p> +Reader-side markers such as <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees +except through their interaction with the grace-period APIs such as +<tt>synchronize_rcu()</tt>. +To see this, consider the following pair of threads: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(x, 1); + 5 rcu_read_unlock(); + 6 rcu_read_lock(); + 7 WRITE_ONCE(y, 1); + 8 rcu_read_unlock(); + 9 } +10 +11 void thread1(void) +12 { +13 rcu_read_lock(); +14 r1 = READ_ONCE(y); +15 rcu_read_unlock(); +16 rcu_read_lock(); +17 r2 = READ_ONCE(x); +18 rcu_read_unlock(); +19 } +</pre> +</blockquote> + +<p> +After <tt>thread0()</tt> and <tt>thread1()</tt> execute +concurrently, it is quite possible to have + +<blockquote> +<pre> +(r1 == 1 && r2 == 0) +</pre> +</blockquote> + +(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>), +which would not be possible if <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> had much in the way of ordering +properties. +But they do not, so the CPU is within its rights +to do significant reordering. +This is by design: Any significant ordering constraints would slow down +these fast-path APIs. + +<p>@@QQ@@ +Can't the compiler also reorder this code? +<p>@@QQA@@ +No, the volatile casts in <tt>READ_ONCE()</tt> and +<tt>WRITE_ONCE()</tt> prevent the compiler from reordering in +this particular case. +<p>@@QQE@@ + +<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3> + +<p> +Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt> +exclude updates. +All they do is to prevent grace periods from ending. +The following example illustrates this: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 r1 = READ_ONCE(y); + 5 if (r1) { + 6 do_something_with_nonzero_x(); + 7 r2 = READ_ONCE(x); + 8 WARN_ON(!r2); /* BUG!!! */ + 9 } +10 rcu_read_unlock(); +11 } +12 +13 void thread1(void) +14 { +15 spin_lock(&my_lock); +16 WRITE_ONCE(x, 1); +17 WRITE_ONCE(y, 1); +18 spin_unlock(&my_lock); +19 } +</pre> +</blockquote> + +<p> +If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt> +excluded the <tt>thread1()</tt> function's update, +the <tt>WARN_ON()</tt> could never fire. +But the fact is that <tt>rcu_read_lock()</tt> does not exclude +much of anything aside from subsequent grace periods, of which +<tt>thread1()</tt> has none, so the +<tt>WARN_ON()</tt> can and does fire. + +<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3> + +<p> +It might be tempting to assume that after <tt>synchronize_rcu()</tt> +completes, there are no readers executing. +This temptation must be avoided because +new readers can start immediately after <tt>synchronize_rcu()</tt> +starts, and <tt>synchronize_rcu()</tt> is under no +obligation to wait for these new readers. + +<p>@@QQ@@ +Suppose that synchronize_rcu() did wait until all readers had completed. +Would the updater be able to rely on this? +<p>@@QQA@@ +No. +Even if <tt>synchronize_rcu()</tt> were to wait until +all readers had completed, a new reader might start immediately after +<tt>synchronize_rcu()</tt> completed. +Therefore, the code following +<tt>synchronize_rcu()</tt> cannot rely on there being no readers +in any case. +<p>@@QQE@@ + +<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections"> +Grace Periods Don't Partition Read-Side Critical Sections</a></h3> + +<p> +It is tempting to assume that if any part of one RCU read-side critical +section precedes a given grace period, and if any part of another RCU +read-side critical section follows that same grace period, then all of +the first RCU read-side critical section must precede all of the second. +However, this just isn't the case: A single grace period does not +partition the set of RCU read-side critical sections. +An example of this situation can be illustrated as follows, where +<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(a, 1); + 5 WRITE_ONCE(b, 1); + 6 rcu_read_unlock(); + 7 } + 8 + 9 void thread1(void) +10 { +11 r1 = READ_ONCE(a); +12 synchronize_rcu(); +13 WRITE_ONCE(c, 1); +14 } +15 +16 void thread2(void) +17 { +18 rcu_read_lock(); +19 r2 = READ_ONCE(b); +20 r3 = READ_ONCE(c); +21 rcu_read_unlock(); +22 } +</pre> +</blockquote> + +<p> +It turns out that the outcome: + +<blockquote> +<pre> +(r1 == 1 && r2 == 0 && r3 == 1) +</pre> +</blockquote> + +is entirely possible. +The following figure show how this can happen, with each circled +<tt>QS</tt> indicating the point at which RCU recorded a +<i>quiescent state</i> for each thread, that is, a state in which +RCU knows that the thread cannot be in the midst of an RCU read-side +critical section that started before the current grace period: + +<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p> + +<p> +If it is necessary to partition RCU read-side critical sections in this +manner, it is necessary to use two grace periods, where the first +grace period is known to end before the second grace period starts: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(a, 1); + 5 WRITE_ONCE(b, 1); + 6 rcu_read_unlock(); + 7 } + 8 + 9 void thread1(void) +10 { +11 r1 = READ_ONCE(a); +12 synchronize_rcu(); +13 WRITE_ONCE(c, 1); +14 } +15 +16 void thread2(void) +17 { +18 r2 = READ_ONCE(c); +19 synchronize_rcu(); +20 WRITE_ONCE(d, 1); +21 } +22 +23 void thread3(void) +24 { +25 rcu_read_lock(); +26 r3 = READ_ONCE(b); +27 r4 = READ_ONCE(d); +28 rcu_read_unlock(); +29 } +</pre> +</blockquote> + +<p> +Here, if <tt>(r1 == 1)</tt>, then +<tt>thread0()</tt>'s write to <tt>b</tt> must happen +before the end of <tt>thread1()</tt>'s grace period. +If in addition <tt>(r4 == 1)</tt>, then +<tt>thread3()</tt>'s read from <tt>b</tt> must happen +after the beginning of <tt>thread2()</tt>'s grace period. +If it is also the case that <tt>(r2 == 1)</tt>, then the +end of <tt>thread1()</tt>'s grace period must precede the +beginning of <tt>thread2()</tt>'s grace period. +This mean that the two RCU read-side critical sections cannot overlap, +guaranteeing that <tt>(r3 == 1)</tt>. +As a result, the outcome: + +<blockquote> +<pre> +(r1 == 1 && r2 == 1 && r3 == 0 && r4 == 1) +</pre> +</blockquote> + +cannot happen. + +<p> +This non-requirement was also non-premeditated, but became apparent +when studying RCU's interaction with memory ordering. + +<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods"> +Read-Side Critical Sections Don't Partition Grace Periods</a></h3> + +<p> +It is also tempting to assume that if an RCU read-side critical section +happens between a pair of grace periods, then those grace periods cannot +overlap. +However, this temptation leads nowhere good, as can be illustrated by +the following, with all variables initially zero: + +<blockquote> +<pre> + 1 void thread0(void) + 2 { + 3 rcu_read_lock(); + 4 WRITE_ONCE(a, 1); + 5 WRITE_ONCE(b, 1); + 6 rcu_read_unlock(); + 7 } + 8 + 9 void thread1(void) +10 { +11 r1 = READ_ONCE(a); +12 synchronize_rcu(); +13 WRITE_ONCE(c, 1); +14 } +15 +16 void thread2(void) +17 { +18 rcu_read_lock(); +19 WRITE_ONCE(d, 1); +20 r2 = READ_ONCE(c); +21 rcu_read_unlock(); +22 } +23 +24 void thread3(void) +25 { +26 r3 = READ_ONCE(d); +27 synchronize_rcu(); +28 WRITE_ONCE(e, 1); +29 } +30 +31 void thread4(void) +32 { +33 rcu_read_lock(); +34 r4 = READ_ONCE(b); +35 r5 = READ_ONCE(e); +36 rcu_read_unlock(); +37 } +</pre> +</blockquote> + +<p> +In this case, the outcome: + +<blockquote> +<pre> +(r1 == 1 && r2 == 1 && r3 == 1 && r4 == 0 && r5 == 1) +</pre> +</blockquote> + +is entirely possible, as illustrated below: + +<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p> + +<p> +Again, an RCU read-side critical section can overlap almost all of a +given grace period, just so long as it does not overlap the entire +grace period. +As a result, an RCU read-side critical section cannot partition a pair +of RCU grace periods. + +<p>@@QQ@@ +How long a sequence of grace periods, each separated by an RCU read-side +critical section, would be required to partition the RCU read-side +critical sections at the beginning and end of the chain? +<p>@@QQA@@ +In theory, an infinite number. +In practice, an unknown number that is sensitive to both implementation +details and timing considerations. +Therefore, even in practice, RCU users must abide by the theoretical rather +than the practical answer. +<p>@@QQE@@ + +<h3><a name="Disabling Preemption Does Not Block Grace Periods"> +Disabling Preemption Does Not Block Grace Periods</a></h3> + +<p> +There was a time when disabling preemption on any given CPU would block +subsequent grace periods. +However, this was an accident of implementation and is not a requirement. +And in the current Linux-kernel implementation, disabling preemption +on a given CPU in fact does not block grace periods, as Oleg Nesterov +<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>. + +<p> +If you need a preempt-disable region to block grace periods, you need to add +<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example +as follows: + +<blockquote> +<pre> + 1 preempt_disable(); + 2 rcu_read_lock(); + 3 do_something(); + 4 rcu_read_unlock(); + 5 preempt_enable(); + 6 + 7 /* Spinlocks implicitly disable preemption. */ + 8 spin_lock(&mylock); + 9 rcu_read_lock(); +10 do_something(); +11 rcu_read_unlock(); +12 spin_unlock(&mylock); +</pre> +</blockquote> + +<p> +In theory, you could enter the RCU read-side critical section first, +but it is more efficient to keep the entire RCU read-side critical +section contained in the preempt-disable region as shown above. +Of course, RCU read-side critical sections that extend outside of +preempt-disable regions will work correctly, but such critical sections +can be preempted, which forces <tt>rcu_read_unlock()</tt> to do +more work. +And no, this is <i>not</i> an invitation to enclose all of your RCU +read-side critical sections within preempt-disable regions, because +doing so would degrade real-time response. + +<p> +This non-requirement appeared with preemptible RCU. +If you need a grace period that waits on non-preemptible code regions, use +<a href="#Sched Flavor">RCU-sched</a>. + +<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2> + +<p> +These parallelism facts of life are by no means specific to RCU, but +the RCU implementation must abide by them. +They therefore bear repeating: + +<ol> +<li> Any CPU or task may be delayed at any time, + and any attempts to avoid these delays by disabling + preemption, interrupts, or whatever are completely futile. + This is most obvious in preemptible user-level + environments and in virtualized environments (where + a given guest OS's VCPUs can be preempted at any time by + the underlying hypervisor), but can also happen in bare-metal + environments due to ECC errors, NMIs, and other hardware + events. + Although a delay of more than about 20 seconds can result + in splats, the RCU implementation is obligated to use + algorithms that can tolerate extremely long delays, but where + “extremely long” is not long enough to allow + wrap-around when incrementing a 64-bit counter. +<li> Both the compiler and the CPU can reorder memory accesses. + Where it matters, RCU must use compiler directives and + memory-barrier instructions to preserve ordering. +<li> Conflicting writes to memory locations in any given cache line + will result in expensive cache misses. + Greater numbers of concurrent writes and more-frequent + concurrent writes will result in more dramatic slowdowns. + RCU is therefore obligated to use algorithms that have + sufficient locality to avoid significant performance and + scalability problems. +<li> As a rough rule of thumb, only one CPU's worth of processing + may be carried out under the protection of any given exclusive + lock. + RCU must therefore use scalable locking designs. +<li> Counters are finite, especially on 32-bit systems. + RCU's use of counters must therefore tolerate counter wrap, + or be designed such that counter wrap would take way more + time than a single system is likely to run. + An uptime of ten years is quite possible, a runtime + of a century much less so. + As an example of the latter, RCU's dyntick-idle nesting counter + allows 54 bits for interrupt nesting level (this counter + is 64 bits even on a 32-bit system). + Overflowing this counter requires 2<sup>54</sup> + half-interrupts on a given CPU without that CPU ever going idle. + If a half-interrupt happened every microsecond, it would take + 570 years of runtime to overflow this counter, which is currently + believed to be an acceptably long time. +<li> Linux systems can have thousands of CPUs running a single + Linux kernel in a single shared-memory environment. + RCU must therefore pay close attention to high-end scalability. +</ol> + +<p> +This last parallelism fact of life means that RCU must pay special +attention to the preceding facts of life. +The idea that Linux might scale to systems with thousands of CPUs would +have been met with some skepticism in the 1990s, but these requirements +would have otherwise have been unsurprising, even in the early 1990s. + +<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2> + +<p> +These sections list quality-of-implementation requirements. +Although an RCU implementation that ignores these requirements could +still be used, it would likely be subject to limitations that would +make it inappropriate for industrial-strength production use. +Classes of quality-of-implementation requirements are as follows: + +<ol> +<li> <a href="#Specialization">Specialization</a> +<li> <a href="#Performance and Scalability">Performance and Scalability</a> +<li> <a href="#Composability">Composability</a> +<li> <a href="#Corner Cases">Corner Cases</a> +</ol> + +<p> +These classes is covered in the following sections. + +<h3><a name="Specialization">Specialization</a></h3> + +<p> +RCU is and always has been intended primarily for read-mostly situations, as +illustrated by the following figure. +This means that RCU's read-side primitives are optimized, often at the +expense of its update-side primitives. + +<p><img src="RCUApplicability.svg" alt="RCUApplicability.svg" width="70%"></p> + +<p> +This focus on read-mostly situations means that RCU must interoperate +with other synchronization primitives. +For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt> +examples discussed earlier use RCU to protect readers and locking to +coordinate updaters. +However, the need extends much farther, requiring that a variety of +synchronization primitives be legal within RCU read-side critical sections, +including spinlocks, sequence locks, atomic operations, reference +counters, and memory barriers. + +<p>@@QQ@@ +What about sleeping locks? +<p>@@QQA@@ +These are forbidden within Linux-kernel RCU read-side critical sections +because it is not legal to place a quiescent state (in this case, +voluntary context switch) within an RCU read-side critical section. +However, sleeping locks may be used within userspace RCU read-side critical +sections, and also within Linux-kernel sleepable RCU +<a href="#Sleepable RCU">(SRCU)</a> +read-side critical sections. +In addition, the -rt patchset turns spinlocks into a sleeping locks so +that the corresponding critical sections can be preempted, which +also means that these sleeplockified spinlocks (but not other sleeping locks!) +may be acquire within -rt-Linux-kernel RCU read-side critical sections. + +<p> +Note that it <i>is</i> legal for a normal RCU read-side critical section +to conditionally acquire a sleeping locks (as in <tt>mutex_trylock()</tt>), +but only as long as it does not loop indefinitely attempting to +conditionally acquire that sleeping locks. +The key point is that things like <tt>mutex_trylock()</tt> +either return with the mutex held, or return an error indication if +the mutex was not immediately available. +Either way, <tt>mutex_trylock()</tt> returns immediately without sleeping. +<p>@@QQE@@ + +<p> +It often comes as a surprise that many algorithms do not require a +consistent view of data, but many can function in that mode, +with network routing being the poster child. +Internet routing algorithms take significant time to propagate +updates, so that by the time an update arrives at a given system, +that system has been sending network traffic the wrong way for +a considerable length of time. +Having a few threads continue to send traffic the wrong way for a +few more milliseconds is clearly not a problem: In the worst case, +TCP retransmissions will eventually get the data where it needs to go. +In general, when tracking the state of the universe outside of the +computer, some level of inconsistency must be tolerated due to +speed-of-light delays if nothing else. + +<p> +Furthermore, uncertainty about external state is inherent in many cases. +For example, a pair of veternarians might use heartbeat to determine +whether or not a given cat was alive. +But how long should they wait after the last heartbeat to decide that +the cat is in fact dead? +Waiting less than 400 milliseconds makes no sense because this would +mean that a relaxed cat would be considered to cycle between death +and life more than 100 times per minute. +Moreover, just as with human beings, a cat's heart might stop for +some period of time, so the exact wait period is a judgment call. +One of our pair of veternarians might wait 30 seconds before pronouncing +the cat dead, while the other might insist on waiting a full minute. +The two veternarians would then disagree on the state of the cat during +the final 30 seconds of the minute following the last heartbeat, as +fancifully illustrated below: + +<p><img src="2013-08-is-it-dead.png" alt="2013-08-is-it-dead.png" width="431"></p> + +<p> +Interestingly enough, this same situation applies to hardware. +When push comes to shove, how do we tell whether or not some +external server has failed? +We send messages to it periodically, and declare it failed if we +don't receive a response within a given period of time. +Policy decisions can usually tolerate short +periods of inconsistency. +The policy was decided some time ago, and is only now being put into +effect, so a few milliseconds of delay is normally inconsequential. + +<p> +However, there are algorithms that absolutely must see consistent data. +For example, the translation between a user-level SystemV semaphore +ID to the corresponding in-kernel data structure is protected by RCU, +but it is absolutely forbidden to update a semaphore that has just been +removed. +In the Linux kernel, this need for consistency is accommodated by acquiring +spinlocks located in the in-kernel data structure from within +the RCU read-side critical section, and this is indicated by the +green box in the figure above. +Many other techniques may be used, and are in fact used within the +Linux kernel. + +<p> +In short, RCU is not required to maintain consistency, and other +mechanisms may be used in concert with RCU when consistency is required. +RCU's specialization allows it to do its job extremely well, and its +ability to interoperate with other synchronization mechanisms allows +the right mix of synchronization tools to be used for a given job. + +<h3><a name="Performance and Scalability">Performance and Scalability</a></h3> + +<p> +Energy efficiency is a critical component of performance today, +and Linux-kernel RCU implementations must therefore avoid unnecessarily +awakening idle CPUs. +I cannot claim that this requirement was premeditated. +In fact, I learned of it during a telephone conversation in which I +was given “frank and open” feedback on the importance +of energy efficiency in battery-powered systems and on specific +energy-efficiency shortcomings of the Linux-kernel RCU implementation. +In my experience, the battery-powered embedded community will consider +any unnecessary wakeups to be extremely unfriendly acts. +So much so that mere Linux-kernel-mailing-list posts are +insufficient to vent their ire. + +<p> +Memory consumption is not particularly important for in most +situations, and has become decreasingly +so as memory sizes have expanded and memory +costs have plummeted. +However, as I learned from Matt Mackall's +<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a> +efforts, memory footprint is critically important on single-CPU systems with +non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus +<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a> +was born. +Josh Triplett has since taken over the small-memory banner with his +<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a> +project, which resulted in +<a href="#Sleepable RCU">SRCU</a> +becoming optional for those kernels not needing it. + +<p> +The remaining performance requirements are, for the most part, +unsurprising. +For example, in keeping with RCU's read-side specialization, +<tt>rcu_dereference()</tt> should have negligible overhead (for +example, suppression of a few minor compiler optimizations). +Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> should have exactly zero overhead. + +<p> +In preemptible environments, in the case where the RCU read-side +critical section was not preempted (as will be the case for the +highest-priority real-time process), <tt>rcu_read_lock()</tt> and +<tt>rcu_read_unlock()</tt> should have minimal overhead. +In particular, they should not contain atomic read-modify-write +operations, memory-barrier instructions, preemption disabling, +interrupt disabling, or backwards branches. +However, in the case where the RCU read-side critical section was preempted, +<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts. +This is why it is better to nest an RCU read-side critical section +within a preempt-disable region than vice versa, at least in cases +where that critical section is short enough to avoid unduly degrading +real-time latencies. + +<p> +The <tt>synchronize_rcu()</tt> grace-period-wait primitive is +optimized for throughput. +It may therefore incur several milliseconds of latency in addition to +the duration of the longest RCU read-side critical section. +On the other hand, multiple concurrent invocations of +<tt>synchronize_rcu()</tt> are required to use batching optimizations +so that they can be satisfied by a single underlying grace-period-wait +operation. +For example, in the Linux kernel, it is not unusual for a single +grace-period-wait operation to serve more than +<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a> +of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation +overhead down to nearly zero. +However, the grace-period optimization is also required to avoid +measurable degradation of real-time scheduling and interrupt latencies. + +<p> +In some cases, the multi-millisecond <tt>synchronize_rcu()</tt> +latencies are unacceptable. +In these cases, <tt>synchronize_rcu_expedited()</tt> may be used +instead, reducing the grace-period latency down to a few tens of +microseconds on small systems, at least in cases where the RCU read-side +critical sections are short. +There are currently no special latency requirements for +<tt>synchronize_rcu_expedited()</tt> on large systems, but, +consistent with the empirical nature of the RCU specification, +that is subject to change. +However, there most definitely are scalability requirements: +A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096 +CPUs should at least make reasonable forward progress. +In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt> +is permitted to impose modest degradation of real-time latency +on non-idle online CPUs. +That said, it will likely be necessary to take further steps to reduce this +degradation, hopefully to roughly that of a scheduling-clock interrupt. + +<p> +There are a number of situations where even +<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period +latency is unacceptable. +In these situations, the asynchronous <tt>call_rcu()</tt> can be +used in place of <tt>synchronize_rcu()</tt> as follows: + +<blockquote> +<pre> + 1 struct foo { + 2 int a; + 3 int b; + 4 struct rcu_head rh; + 5 }; + 6 + 7 static void remove_gp_cb(struct rcu_head *rhp) + 8 { + 9 struct foo *p = container_of(rhp, struct foo, rh); +10 +11 kfree(p); +12 } +13 +14 bool remove_gp_asynchronous(void) +15 { +16 struct foo *p; +17 +18 spin_lock(&gp_lock); +19 p = rcu_dereference(gp); +20 if (!p) { +21 spin_unlock(&gp_lock); +22 return false; +23 } +24 rcu_assign_pointer(gp, NULL); +25 call_rcu(&p->rh, remove_gp_cb); +26 spin_unlock(&gp_lock); +27 return true; +28 } +</pre> +</blockquote> + +<p> +A definition of <tt>struct foo</tt> is finally needed, and appears +on lines 1-5. +The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt> +on line 25, and will be invoked after the end of a subsequent +grace period. +This gets the same effect as <tt>remove_gp_synchronous()</tt>, +but without forcing the updater to wait for a grace period to elapse. +The <tt>call_rcu()</tt> function may be used in a number of +situations where neither <tt>synchronize_rcu()</tt> nor +<tt>synchronize_rcu_expedited()</tt> would be legal, +including within preempt-disable code, <tt>local_bh_disable()</tt> code, +interrupt-disable code, and interrupt handlers. +However, even <tt>call_rcu()</tt> is illegal within NMI handlers. +The callback function (<tt>remove_gp_cb()</tt> in this case) will be +executed within softirq (software interrupt) environment within the +Linux kernel, +either within a real softirq handler or under the protection +of <tt>local_bh_disable()</tt>. +In both the Linux kernel and in userspace, it is bad practice to +write an RCU callback function that takes too long. +Long-running operations should be relegated to separate threads or +(in the Linux kernel) workqueues. + +<p>@@QQ@@ +Why does line 19 use <tt>rcu_access_pointer()</tt>? +After all, <tt>call_rcu()</tt> on line 25 stores into the +structure, which would interact badly with concurrent insertions. +Doesn't this mean that <tt>rcu_dereference()</tt> is required? +<p>@@QQA@@ +Presumably the <tt>->gp_lock</tt> acquired on line 18 excludes +any changes, including any insertions that <tt>rcu_dereference()</tt> +would protect against. +Therefore, any insertions will be delayed until after <tt>->gp_lock</tt> +is released on line 25, which in turn means that +<tt>rcu_access_pointer()</tt> suffices. +<p>@@QQE@@ + +<p> +However, all that <tt>remove_gp_cb()</tt> is doing is +invoking <tt>kfree()</tt> on the data element. +This is a common idiom, and is supported by <tt>kfree_rcu()</tt>, +which allows “fire and forget” operation as shown below: + +<blockquote> +<pre> + 1 struct foo { + 2 int a; + 3 int b; + 4 struct rcu_head rh; + 5 }; + 6 + 7 bool remove_gp_faf(void) + 8 { + 9 struct foo *p; +10 +11 spin_lock(&gp_lock); +12 p = rcu_dereference(gp); +13 if (!p) { +14 spin_unlock(&gp_lock); +15 return false; +16 } +17 rcu_assign_pointer(gp, NULL); +18 kfree_rcu(p, rh); +19 spin_unlock(&gp_lock); +20 return true; +21 } +</pre> +</blockquote> + +<p> +Note that <tt>remove_gp_faf()</tt> simply invokes +<tt>kfree_rcu()</tt> and proceeds, without any need to pay any +further attention to the subsequent grace period and <tt>kfree()</tt>. +It is permissible to invoke <tt>kfree_rcu()</tt> from the same +environments as for <tt>call_rcu()</tt>. +Interestingly enough, DYNIX/ptx had the equivalents of +<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not +<tt>synchronize_rcu()</tt>. +This was due to the fact that RCU was not heavily used within DYNIX/ptx, +so the very few places that needed something like +<tt>synchronize_rcu()</tt> simply open-coded it. + +<p>@@QQ@@ +Earlier it was claimed that <tt>call_rcu()</tt> and +<tt>kfree_rcu()</tt> allowed updaters to avoid being blocked +by readers. +But how can that be correct, given that the invocation of the callback +and the freeing of the memory (respectively) must still wait for +a grace period to elapse? +<p>@@QQA@@ +We could define things this way, but keep in mind that this sort of +definition would say that updates in garbage-collected languages +cannot complete until the next time the garbage collector runs, +which does not seem at all reasonable. +The key point is that in most cases, an updater using either +<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the +next update as soon as it has invoked <tt>call_rcu()</tt> or +<tt>kfree_rcu()</tt>, without having to wait for a subsequent +grace period. +<p>@@QQE@@ + +<p> +But what if the updater must wait for the completion of code to be +executed after the end of the grace period, but has other tasks +that can be carried out in the meantime? +The polling-style <tt>get_state_synchronize_rcu()</tt> and +<tt>cond_synchronize_rcu()</tt> functions may be used for this +purpose, as shown below: + +<blockquote> +<pre> + 1 bool remove_gp_poll(void) + 2 { + 3 struct foo *p; + 4 unsigned long s; + 5 + 6 spin_lock(&gp_lock); + 7 p = rcu_access_pointer(gp); + 8 if (!p) { + 9 spin_unlock(&gp_lock); +10 return false; +11 } +12 rcu_assign_pointer(gp, NULL); +13 spin_unlock(&gp_lock); +14 s = get_state_synchronize_rcu(); +15 do_something_while_waiting(); +16 cond_synchronize_rcu(s); +17 kfree(p); +18 return true; +19 } +</pre> +</blockquote> + +<p> +On line 14, <tt>get_state_synchronize_rcu()</tt> obtains a +“cookie” from RCU, +then line 15 carries out other tasks, +and finally, line 16 returns immediately if a grace period has +elapsed in the meantime, but otherwise waits as required. +The need for <tt>get_state_synchronize_rcu</tt> and +<tt>cond_synchronize_rcu()</tt> has appeared quite recently, +so it is too early to tell whether they will stand the test of time. + +<p> +RCU thus provides a range of tools to allow updaters to strike the +required tradeoff between latency, flexibility and CPU overhead. + +<h3><a name="Composability">Composability</a></h3> + +<p> +Composability has received much attention in recent years, perhaps in part +due to the collision of multicore hardware with object-oriented techniques +designed in single-threaded environments for single-threaded use. +And in theory, RCU read-side critical sections may be composed, and in +fact may be nested arbitrarily deeply. +In practice, as with all real-world implementations of composable +constructs, there are limitations. + +<p> +Implementations of RCU for which <tt>rcu_read_lock()</tt> +and <tt>rcu_read_unlock()</tt> generate no code, such as +Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be +nested arbitrarily deeply. +After all, there is no overhead. +Except that if all these instances of <tt>rcu_read_lock()</tt> +and <tt>rcu_read_unlock()</tt> are visible to the compiler, +compilation will eventually fail due to exhausting memory, +mass storage, or user patience, whichever comes first. +If the nesting is not visible to the compiler, as is the case with +mutually recursive functions each in its own translation unit, +stack overflow will result. +If the nesting takes the form of loops, either the control variable +will overflow or (in the Linux kernel) you will get an RCU CPU stall warning. +Nevertheless, this class of RCU implementations is one +of the most composable constructs in existence. + +<p> +RCU implementations that explicitly track nesting depth +are limited by the nesting-depth counter. +For example, the Linux kernel's preemptible RCU limits nesting to +<tt>INT_MAX</tt>. +This should suffice for almost all practical purposes. +That said, a consecutive pair of RCU read-side critical sections +between which there is an operation that waits for a grace period +cannot be enclosed in another RCU read-side critical section. +This is because it is not legal to wait for a grace period within +an RCU read-side critical section: To do so would result either +in deadlock or +in RCU implicitly splitting the enclosing RCU read-side critical +section, neither of which is conducive to a long-lived and prosperous +kernel. + +<p> +It is worth noting that RCU is not alone in limiting composability. +For example, many transactional-memory implementations prohibit +composing a pair of transactions separated by an irrevocable +operation (for example, a network receive operation). +For another example, lock-based critical sections can be composed +surprisingly freely, but only if deadlock is avoided. + +<p> +In short, although RCU read-side critical sections are highly composable, +care is required in some situations, just as is the case for any other +composable synchronization mechanism. + +<h3><a name="Corner Cases">Corner Cases</a></h3> + +<p> +A given RCU workload might have an endless and intense stream of +RCU read-side critical sections, perhaps even so intense that there +was never a point in time during which there was not at least one +RCU read-side critical section in flight. +RCU cannot allow this situation to block grace periods: As long as +all the RCU read-side critical sections are finite, grace periods +must also be finite. + +<p> +That said, preemptible RCU implementations could potentially result +in RCU read-side critical sections being preempted for long durations, +which has the effect of creating a long-duration RCU read-side +critical section. +This situation can arise only in heavily loaded systems, but systems using +real-time priorities are of course more vulnerable. +Therefore, RCU priority boosting is provided to help deal with this +case. +That said, the exact requirements on RCU priority boosting will likely +evolve as more experience accumulates. + +<p> +Other workloads might have very high update rates. +Although one can argue that such workloads should instead use +something other than RCU, the fact remains that RCU must +handle such workloads gracefully. +This requirement is another factor driving batching of grace periods, +but it is also the driving force behind the checks for large numbers +of queued RCU callbacks in the <tt>call_rcu()</tt> code path. +Finally, high update rates should not delay RCU read-side critical +sections, although some read-side delays can occur when using +<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use +of <tt>try_stop_cpus()</tt>. +(In the future, <tt>synchronize_rcu_expedited()</tt> will be +converted to use lighter-weight inter-processor interrupts (IPIs), +but this will still disturb readers, though to a much smaller degree.) + +<p> +Although all three of these corner cases were understood in the early +1990s, a simple user-level test consisting of <tt>close(open(path))</tt> +in a tight loop +in the early 2000s suddenly provided a much deeper appreciation of the +high-update-rate corner case. +This test also motivated addition of some RCU code to react to high update +rates, for example, if a given CPU finds itself with more than 10,000 +RCU callbacks queued, it will cause RCU to take evasive action by +more aggressively starting grace periods and more aggressively forcing +completion of grace-period processing. +This evasive action causes the grace period to complete more quickly, +but at the cost of restricting RCU's batching optimizations, thus +increasing the CPU overhead incurred by that grace period. + +<h2><a name="Software-Engineering Requirements"> +Software-Engineering Requirements</a></h2> + +<p> +Between Murphy's Law and “To err is human”, it is necessary to +guard against mishaps and misuse: + +<ol> +<li> It is all too easy to forget to use <tt>rcu_read_lock()</tt> + everywhere that it is needed, so kernels built with + <tt>CONFIG_PROVE_RCU=y</tt> will spat if + <tt>rcu_dereference()</tt> is used outside of an + RCU read-side critical section. + Update-side code can use <tt>rcu_dereference_protected()</tt>, + which takes a + <a href="https://lwn.net/Articles/371986/">lockdep expression</a> + to indicate what is providing the protection. + If the indicated protection is not provided, a lockdep splat + is emitted. + + <p> + Code shared between readers and updaters can use + <tt>rcu_dereference_check()</tt>, which also takes a + lockdep expression, and emits a lockdep splat if neither + <tt>rcu_read_lock()</tt> nor the indicated protection + is in place. + In addition, <tt>rcu_dereference_raw()</tt> is used in those + (hopefully rare) cases where the required protection cannot + be easily described. + Finally, <tt>rcu_read_lock_held()</tt> is provided to + allow a function to verify that it has been invoked within + an RCU read-side critical section. + I was made aware of this set of requirements shortly after Thomas + Gleixner audited a number of RCU uses. +<li> A given function might wish to check for RCU-related preconditions + upon entry, before using any other RCU API. + The <tt>rcu_lockdep_assert()</tt> does this job, + asserting the expression in kernels having lockdep enabled + and doing nothing otherwise. +<li> It is also easy to forget to use <tt>rcu_assign_pointer()</tt> + and <tt>rcu_dereference()</tt>, perhaps (incorrectly) + substituting a simple assignment. + To catch this sort of error, a given RCU-protected pointer may be + tagged with <tt>__rcu</tt>, after which running sparse + with <tt>CONFIG_SPARSE_RCU_POINTER=y</tt> will complain + about simple-assignment accesses to that pointer. + Arnd Bergmann made me aware of this requirement, and also + supplied the needed + <a href="https://lwn.net/Articles/376011/">patch series</a>. +<li> Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt> + will splat if a data element is passed to <tt>call_rcu()</tt> + twice in a row, without a grace period in between. + (This error is similar to a double free.) + The corresponding <tt>rcu_head</tt> structures that are + dynamically allocated are automatically tracked, but + <tt>rcu_head</tt> structures allocated on the stack + must be initialized with <tt>init_rcu_head_on_stack()</tt> + and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>. + Similarly, statically allocated non-stack <tt>rcu_head</tt> + structures must be initialized with <tt>init_rcu_head()</tt> + and cleaned up with <tt>destroy_rcu_head()</tt>. + Mathieu Desnoyers made me aware of this requirement, and also + supplied the needed + <a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>. +<li> An infinite loop in an RCU read-side critical section will + eventually trigger an RCU CPU stall warning splat, with + the duration of “eventually” being controlled by the + <tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or, + alternatively, by the + <tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs + parameter. + However, RCU is not obligated to produce this splat + unless there is a grace period waiting on that particular + RCU read-side critical section. + <p> + Some extreme workloads might intentionally delay + RCU grace periods, and systems running those workloads can + be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt> + to suppress the splats. + This kernel parameter may also be set via <tt>sysfs</tt>. + Furthermore, RCU CPU stall warnings are counter-productive + during sysrq dumps and during panics. + RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and + <tt>rcu_sysrq_end()</tt> API members to be called before + and after long sysrq dumps. + RCU also supplies the <tt>rcu_panic()</tt> notifier that is + automatically invoked at the beginning of a panic to suppress + further RCU CPU stall warnings. + + <p> + This requirement made itself known in the early 1990s, pretty + much the first time that it was necessary to debug a CPU stall. + That said, the initial implementation in DYNIX/ptx was quite + generic in comparison with that of Linux. +<li> Although it would be very good to detect pointers leaking out + of RCU read-side critical sections, there is currently no + good way of doing this. + One complication is the need to distinguish between pointers + leaking and pointers that have been handed off from RCU to + some other synchronization mechanism, for example, reference + counting. +<li> In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related + information is provided via both debugfs and event tracing. +<li> Open-coded use of <tt>rcu_assign_pointer()</tt> and + <tt>rcu_dereference()</tt> to create typical linked + data structures can be surprisingly error-prone. + Therefore, RCU-protected + <a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a> + and, more recently, RCU-protected + <a href="https://lwn.net/Articles/612100/">hash tables</a> + are available. + Many other special-purpose RCU-protected data structures are + available in the Linux kernel and the userspace RCU library. +<li> Some linked structures are created at compile time, but still + require <tt>__rcu</tt> checking. + The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this + purpose. +<li> It is not necessary to use <tt>rcu_assign_pointer()</tt> + when creating linked structures that are to be published via + a single external pointer. + The <tt>RCU_INIT_POINTER()</tt> macro is provided for + this task and also for assigning <tt>NULL</tt> pointers + at runtime. +</ol> + +<p> +This not a hard-and-fast list: RCU's diagnostic capabilities will +continue to be guided by the number and type of usage bugs found +in real-world RCU usage. + +<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2> + +<p> +The Linux kernel provides an interesting environment for all kinds of +software, including RCU. +Some of the relevant points of interest are as follows: + +<ol> +<li> <a href="#Configuration">Configuration</a>. +<li> <a href="#Firmware Interface">Firmware Interface</a>. +<li> <a href="#Early Boot">Early Boot</a>. +<li> <a href="#Interrupts and NMIs"> + Interrupts and non-maskable interrupts (NMIs)</a>. +<li> <a href="#Loadable Modules">Loadable Modules</a>. +<li> <a href="#Hotplug CPU">Hotplug CPU</a>. +<li> <a href="#Scheduler and RCU">Scheduler and RCU</a>. +<li> <a href="#Tracing and RCU">Tracing and RCU</a>. +<li> <a href="#Energy Efficiency">Energy Efficiency</a>. +<li> <a href="#Memory Efficiency">Memory Efficiency</a>. +<li> <a href="#Performance, Scalability, Response Time, and Reliability"> + Performance, Scalability, Response Time, and Reliability</a>. +</ol> + +<p> +This list is probably incomplete, but it does give a feel for the +most notable Linux-kernel complications. +Each of the following sections covers one of the above topics. + +<h3><a name="Configuration">Configuration</a></h3> + +<p> +RCU's goal is automatic configuration, so that almost nobody +needs to worry about RCU's <tt>Kconfig</tt> options. +And for almost all users, RCU does in fact work well +“out of the box.” + +<p> +However, there are specialized use cases that are handled by +kernel boot parameters and <tt>Kconfig</tt> options. +Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users +about new <tt>Kconfig</tt> options, which requires almost all of them +be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option. + +<p> +This all should be quite obvious, but the fact remains that +Linus Torvalds recently had to +<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a> +me of this requirement. + +<h3><a name="Firmware Interface">Firmware Interface</a></h3> + +<p> +In many cases, kernel obtains information about the system from the +firmware, and sometimes things are lost in translation. +Or the translation is accurate, but the original message is bogus. + +<p> +For example, some systems' firmware overreports the number of CPUs, +sometimes by a large factor. +If RCU naively believed the firmware, as it used to do, +it would create too many per-CPU kthreads. +Although the resulting system will still run correctly, the extra +kthreads needlessly consume memory and can cause confusion +when they show up in <tt>ps</tt> listings. + +<p> +RCU must therefore wait for a given CPU to actually come online before +it can allow itself to believe that the CPU actually exists. +The resulting “ghost CPUs” (which are never going to +come online) cause a number of +<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>. + +<h3><a name="Early Boot">Early Boot</a></h3> + +<p> +The Linux kernel's boot sequence is an interesting process, +and RCU is used early, even before <tt>rcu_init()</tt> +is invoked. +In fact, a number of RCU's primitives can be used as soon as the +initial task's <tt>task_struct</tt> is available and the +boot CPU's per-CPU variables are set up. +The read-side primitives (<tt>rcu_read_lock()</tt>, +<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>, +and <tt>rcu_access_pointer()</tt>) will operate normally very early on, +as will <tt>rcu_assign_pointer()</tt>. + +<p> +Although <tt>call_rcu()</tt> may be invoked at any +time during boot, callbacks are not guaranteed to be invoked until after +the scheduler is fully up and running. +This delay in callback invocation is due to the fact that RCU does not +invoke callbacks until it is fully initialized, and this full initialization +cannot occur until after the scheduler has initialized itself to the +point where RCU can spawn and run its kthreads. +In theory, it would be possible to invoke callbacks earlier, +however, this is not a panacea because there would be severe restrictions +on what operations those callbacks could invoke. + +<p> +Perhaps surprisingly, <tt>synchronize_rcu()</tt>, +<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a> +(<a href="#Bottom-Half Flavor">discussed below</a>), +and +<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a> +will all operate normally +during very early boot, the reason being that there is only one CPU +and preemption is disabled. +This means that the call <tt>synchronize_rcu()</tt> (or friends) +itself is a quiescent +state and thus a grace period, so the early-boot implementation can +be a no-op. + +<p> +Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt> +continue to operate normally through the remainder of boot, courtesy +of the fact that preemption is disabled across their RCU read-side +critical sections and also courtesy of the fact that there is still +only one CPU. +However, once the scheduler starts initializing, preemption is enabled. +There is still only a single CPU, but the fact that preemption is enabled +means that the no-op implementation of <tt>synchronize_rcu()</tt> no +longer works in <tt>CONFIG_PREEMPT=y</tt> kernels. +Therefore, as soon as the scheduler starts initializing, the early-boot +fastpath is disabled. +This means that <tt>synchronize_rcu()</tt> switches to its runtime +mode of operation where it posts callbacks, which in turn means that +any call to <tt>synchronize_rcu()</tt> will block until the corresponding +callback is invoked. +Unfortunately, the callback cannot be invoked until RCU's runtime +grace-period machinery is up and running, which cannot happen until +the scheduler has initialized itself sufficiently to allow RCU's +kthreads to be spawned. +Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler +initialization can result in deadlock. + +<p>@@QQ@@ +So what happens with <tt>synchronize_rcu()</tt> during +scheduler initialization for <tt>CONFIG_PREEMPT=n</tt> +kernels? +<p>@@QQA@@ +In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt> +maps directly to <tt>synchronize_sched()</tt>. +Therefore, <tt>synchronize_rcu()</tt> works normally throughout +boot in <tt>CONFIG_PREEMPT=n</tt> kernels. +However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels, +so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt> +during scheduler initialization. +<p>@@QQE@@ + +<p> +I learned of these boot-time requirements as a result of a series of +system hangs. + +<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3> + +<p> +The Linux kernel has interrupts, and RCU read-side critical sections are +legal within interrupt handlers and within interrupt-disabled regions +of code, as are invocations of <tt>call_rcu()</tt>. + +<p> +Some Linux-kernel architectures can enter an interrupt handler from +non-idle process context, and then just never leave it, instead stealthily +transitioning back to process context. +This trick is sometimes used to invoke system calls from inside the kernel. +These “half-interrupts” mean that RCU has to be very careful +about how it counts interrupt nesting levels. +I learned of this requirement the hard way during a rewrite +of RCU's dyntick-idle code. + +<p> +The Linux kernel has non-maskable interrupts (NMIs), and +RCU read-side critical sections are legal within NMI handlers. +Thankfully, RCU update-side primitives, including +<tt>call_rcu()</tt>, are prohibited within NMI handlers. + +<p> +The name notwithstanding, some Linux-kernel architectures +can have nested NMIs, which RCU must handle correctly. +Andy Lutomirski +<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a> +with this requirement; +he also kindly surprised me with +<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a> +that meets this requirement. + +<h3><a name="Loadable Modules">Loadable Modules</a></h3> + +<p> +The Linux kernel has loadable modules, and these modules can +also be unloaded. +After a given module has been unloaded, any attempt to call +one of its functions results in a segmentation fault. +The module-unload functions must therefore cancel any +delayed calls to loadable-module functions, for example, +any outstanding <tt>mod_timer()</tt> must be dealt with +via <tt>del_timer_sync()</tt> or similar. + +<p> +Unfortunately, there is no way to cancel an RCU callback; +once you invoke <tt>call_rcu()</tt>, the callback function is +going to eventually be invoked, unless the system goes down first. +Because it is normally considered socially irresponsible to crash the system +in response to a module unload request, we need some other way +to deal with in-flight RCU callbacks. + +<p> +RCU therefore provides +<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>, +which waits until all in-flight RCU callbacks have been invoked. +If a module uses <tt>call_rcu()</tt>, its exit function should therefore +prevent any future invocation of <tt>call_rcu()</tt>, then invoke +<tt>rcu_barrier()</tt>. +In theory, the underlying module-unload code could invoke +<tt>rcu_barrier()</tt> unconditionally, but in practice this would +incur unacceptable latencies. + +<p> +Nikita Danilov noted this requirement for an analogous filesystem-unmount +situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU. +The need for <tt>rcu_barrier()</tt> for module unloading became +apparent later. + +<h3><a name="Hotplug CPU">Hotplug CPU</a></h3> + +<p> +The Linux kernel supports CPU hotplug, which means that CPUs +can come and go. +It is of course illegal to use any RCU API member from an offline CPU. +This requirement was present from day one in DYNIX/ptx, but +on the other hand, the Linux kernel's CPU-hotplug implementation +is “interesting.” + +<p> +The Linux-kernel CPU-hotplug implementation has notifiers that +are used to allow the various kernel subsystems (including RCU) +to respond appropriately to a given CPU-hotplug operation. +Most RCU operations may be invoked from CPU-hotplug notifiers, +including even normal synchronous grace-period operations +such as <tt>synchronize_rcu()</tt>. +However, expedited grace-period operations such as +<tt>synchronize_rcu_expedited()</tt> are not supported, +due to the fact that current implementations block CPU-hotplug +operations, which could result in deadlock. + +<p> +In addition, all-callback-wait operations such as +<tt>rcu_barrier()</tt> are also not supported, due to the +fact that there are phases of CPU-hotplug operations where +the outgoing CPU's callbacks will not be invoked until after +the CPU-hotplug operation ends, which could also result in deadlock. + +<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3> + +<p> +RCU depends on the scheduler, and the scheduler uses RCU to +protect some of its data structures. +This means the scheduler is forbidden from acquiring +the runqueue locks and the priority-inheritance locks +in the middle of an outermost RCU read-side critical section unless either +(1) it releases them before exiting that same +RCU read-side critical section, or +(2) interrupts are disabled across +that entire RCU read-side critical section. +This same prohibition also applies (recursively!) to any lock that is acquired +while holding any lock to which this prohibition applies. +Adhering to this rule prevents preemptible RCU from invoking +<tt>rcu_read_unlock_special()</tt> while either runqueue or +priority-inheritance locks are held, thus avoiding deadlock. + +<p> +Prior to v4.4, it was only necessary to disable preemption across +RCU read-side critical sections that acquired scheduler locks. +In v4.4, expedited grace periods started using IPIs, and these +IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath. +Therefore, this expedited-grace-period change required disabling of +interrupts, not just preemption. + +<p> +For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt> +implementation must be written carefully to avoid similar deadlocks. +In particular, <tt>rcu_read_unlock()</tt> must tolerate an +interrupt where the interrupt handler invokes both +<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. +This possibility requires <tt>rcu_read_unlock()</tt> to use +negative nesting levels to avoid destructive recursion via +interrupt handler's use of RCU. + +<p> +This pair of mutual scheduler-RCU requirements came as a +<a href="https://lwn.net/Articles/453002/">complete surprise</a>. + +<p> +As noted above, RCU makes use of kthreads, and it is necessary to +avoid excessive CPU-time accumulation by these kthreads. +This requirement was no surprise, but RCU's violation of it +when running context-switch-heavy workloads when built with +<tt>CONFIG_NO_HZ_FULL=y</tt> +<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>. +RCU has made good progress towards meeting this requirement, even +for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads, +but there is room for further improvement. + +<h3><a name="Tracing and RCU">Tracing and RCU</a></h3> + +<p> +It is possible to use tracing on RCU code, but tracing itself +uses RCU. +For this reason, <tt>rcu_dereference_raw_notrace()</tt> +is provided for use by tracing, which avoids the destructive +recursion that could otherwise ensue. +This API is also used by virtualization in some architectures, +where RCU readers execute in environments in which tracing +cannot be used. +The tracing folks both located the requirement and provided the +needed fix, so this surprise requirement was relatively painless. + +<h3><a name="Energy Efficiency">Energy Efficiency</a></h3> + +<p> +Interrupting idle CPUs is considered socially unacceptable, +especially by people with battery-powered embedded systems. +RCU therefore conserves energy by detecting which CPUs are +idle, including tracking CPUs that have been interrupted from idle. +This is a large part of the energy-efficiency requirement, +so I learned of this via an irate phone call. + +<p> +Because RCU avoids interrupting idle CPUs, it is illegal to +execute an RCU read-side critical section on an idle CPU. +(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat +if you try it.) +The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt> +event tracing is provided to work around this restriction. +In addition, <tt>rcu_is_watching()</tt> may be used to +test whether or not it is currently legal to run RCU read-side +critical sections on this CPU. +I learned of the need for diagnostics on the one hand +and <tt>RCU_NONIDLE()</tt> on the other while inspecting +idle-loop code. +Steven Rostedt supplied <tt>_rcuidle</tt> event tracing, +which is used quite heavily in the idle loop. + +<p> +It is similarly socially unacceptable to interrupt an +<tt>nohz_full</tt> CPU running in userspace. +RCU must therefore track <tt>nohz_full</tt> userspace +execution. +And in +<a href="https://lwn.net/Articles/558284/"><tt>CONFIG_NO_HZ_FULL_SYSIDLE=y</tt></a> +kernels, RCU must separately track idle CPUs on the one hand and +CPUs that are either idle or executing in userspace on the other. +In both cases, RCU must be able to sample state at two points in +time, and be able to determine whether or not some other CPU spent +any time idle and/or executing in userspace. + +<p> +These energy-efficiency requirements have proven quite difficult to +understand and to meet, for example, there have been more than five +clean-sheet rewrites of RCU's energy-efficiency code, the last of +which was finally able to demonstrate +<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>. +As noted earlier, +I learned of many of these requirements via angry phone calls: +Flaming me on the Linux-kernel mailing list was apparently not +sufficient to fully vent their ire at RCU's energy-efficiency bugs! + +<h3><a name="Memory Efficiency">Memory Efficiency</a></h3> + +<p> +Although small-memory non-realtime systems can simply use Tiny RCU, +code size is only one aspect of memory efficiency. +Another aspect is the size of the <tt>rcu_head</tt> structure +used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>. +Although this structure contains nothing more than a pair of pointers, +it does appear in many RCU-protected data structures, including +some that are size critical. +The <tt>page</tt> structure is a case in point, as evidenced by +the many occurrences of the <tt>union</tt> keyword within that structure. + +<p> +This need for memory efficiency is one reason that RCU uses hand-crafted +singly linked lists to track the <tt>rcu_head</tt> structures that +are waiting for a grace period to elapse. +It is also the reason why <tt>rcu_head</tt> structures do not contain +debug information, such as fields tracking the file and line of the +<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them. +Although this information might appear in debug-only kernel builds at some +point, in the meantime, the <tt>->func</tt> field will often provide +the needed debug information. + +<p> +However, in some cases, the need for memory efficiency leads to even +more extreme measures. +Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field +shares storage with a great many other structures that are used at +various points in the corresponding page's lifetime. +In order to correctly resolve certain +<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>, +the Linux kernel's memory-management subsystem needs a particular bit +to remain zero during all phases of grace-period processing, +and that bit happens to map to the bottom bit of the +<tt>rcu_head</tt> structure's <tt>->next</tt> field. +RCU makes this guarantee as long as <tt>call_rcu()</tt> +is used to post the callback, as opposed to <tt>kfree_rcu()</tt> +or some future “lazy” +variant of <tt>call_rcu()</tt> that might one day be created for +energy-efficiency purposes. + +<h3><a name="Performance, Scalability, Response Time, and Reliability"> +Performance, Scalability, Response Time, and Reliability</a></h3> + +<p> +Expanding on the +<a href="#Performance and Scalability">earlier discussion</a>, +RCU is used heavily by hot code paths in performance-critical +portions of the Linux kernel's networking, security, virtualization, +and scheduling code paths. +RCU must therefore use efficient implementations, especially in its +read-side primitives. +To that end, it would be good if preemptible RCU's implementation +of <tt>rcu_read_lock()</tt> could be inlined, however, doing +this requires resolving <tt>#include</tt> issues with the +<tt>task_struct</tt> structure. + +<p> +The Linux kernel supports hardware configurations with up to +4096 CPUs, which means that RCU must be extremely scalable. +Algorithms that involve frequent acquisitions of global locks or +frequent atomic operations on global variables simply cannot be +tolerated within the RCU implementation. +RCU therefore makes heavy use of a combining tree based on the +<tt>rcu_node</tt> structure. +RCU is required to tolerate all CPUs continuously invoking any +combination of RCU's runtime primitives with minimal per-operation +overhead. +In fact, in many cases, increasing load must <i>decrease</i> the +per-operation overhead, witness the batching optimizations for +<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>, +<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>. +As a general rule, RCU must cheerfully accept whatever the +rest of the Linux kernel decides to throw at it. + +<p> +The Linux kernel is used for real-time workloads, especially +in conjunction with the +<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>. +The real-time-latency response requirements are such that the +traditional approach of disabling preemption across RCU +read-side critical sections is inappropriate. +Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore +use an RCU implementation that allows RCU read-side critical +sections to be preempted. +This requirement made its presence known after users made it +clear that an earlier +<a href="https://lwn.net/Articles/107930/">real-time patch</a> +did not meet their needs, in conjunction with some +<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a> +encountered by a very early version of the -rt patchset. + +<p> +In addition, RCU must make do with a sub-100-microsecond real-time latency +budget. +In fact, on smaller systems with the -rt patchset, the Linux kernel +provides sub-20-microsecond real-time latencies for the whole kernel, +including RCU. +RCU's scalability and latency must therefore be sufficient for +these sorts of configurations. +To my surprise, the sub-100-microsecond real-time latency budget +<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf"> +applies to even the largest systems [PDF]</a>, +up to and including systems with 4096 CPUs. +This real-time requirement motivated the grace-period kthread, which +also simplified handling of a number of race conditions. + +<p> +Finally, RCU's status as a synchronization primitive means that +any RCU failure can result in arbitrary memory corruption that can be +extremely difficult to debug. +This means that RCU must be extremely reliable, which in +practice also means that RCU must have an aggressive stress-test +suite. +This stress-test suite is called <tt>rcutorture</tt>. + +<p> +Although the need for <tt>rcutorture</tt> was no surprise, +the current immense popularity of the Linux kernel is posing +interesting—and perhaps unprecedented—validation +challenges. +To see this, keep in mind that there are well over one billion +instances of the Linux kernel running today, given Android +smartphones, Linux-powered televisions, and servers. +This number can be expected to increase sharply with the advent of +the celebrated Internet of Things. + +<p> +Suppose that RCU contains a race condition that manifests on average +once per million years of runtime. +This bug will be occurring about three times per <i>day</i> across +the installed base. +RCU could simply hide behind hardware error rates, given that no one +should really expect their smartphone to last for a million years. +However, anyone taking too much comfort from this thought should +consider the fact that in most jurisdictions, a successful multi-year +test of a given mechanism, which might include a Linux kernel, +suffices for a number of types of safety-critical certifications. +In fact, rumor has it that the Linux kernel is already being used +in production for safety-critical applications. +I don't know about you, but I would feel quite bad if a bug in RCU +killed someone. +Which might explain my recent focus on validation and verification. + +<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2> + +<p> +One of the more surprising things about RCU is that there are now +no fewer than five <i>flavors</i>, or API families. +In addition, the primary flavor that has been the sole focus up to +this point has two different implementations, non-preemptible and +preemptible. +The other four flavors are listed below, with requirements for each +described in a separate section. + +<ol> +<li> <a href="#Bottom-Half Flavor">Bottom-Half Flavor</a> +<li> <a href="#Sched Flavor">Sched Flavor</a> +<li> <a href="#Sleepable RCU">Sleepable RCU</a> +<li> <a href="#Tasks RCU">Tasks RCU</a> +</ol> + +<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3> + +<p> +The softirq-disable (AKA “bottom-half”, +hence the “_bh” abbreviations) +flavor of RCU, or <i>RCU-bh</i>, was developed by +Dipankar Sarma to provide a flavor of RCU that could withstand the +network-based denial-of-service attacks researched by Robert +Olsson. +These attacks placed so much networking load on the system +that some of the CPUs never exited softirq execution, +which in turn prevented those CPUs from ever executing a context switch, +which, in the RCU implementation of that time, prevented grace periods +from ever ending. +The result was an out-of-memory condition and a system hang. + +<p> +The solution was the creation of RCU-bh, which does +<tt>local_bh_disable()</tt> +across its read-side critical sections, and which uses the transition +from one type of softirq processing to another as a quiescent state +in addition to context switch, idle, user mode, and offline. +This means that RCU-bh grace periods can complete even when some of +the CPUs execute in softirq indefinitely, thus allowing algorithms +based on RCU-bh to withstand network-based denial-of-service attacks. + +<p> +Because +<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt> +disable and re-enable softirq handlers, any attempt to start a softirq +handlers during the +RCU-bh read-side critical section will be deferred. +In this case, <tt>rcu_read_unlock_bh()</tt> +will invoke softirq processing, which can take considerable time. +One can of course argue that this softirq overhead should be associated +with the code following the RCU-bh read-side critical section rather +than <tt>rcu_read_unlock_bh()</tt>, but the fact +is that most profiling tools cannot be expected to make this sort +of fine distinction. +For example, suppose that a three-millisecond-long RCU-bh read-side +critical section executes during a time of heavy networking load. +There will very likely be an attempt to invoke at least one softirq +handler during that three milliseconds, but any such invocation will +be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>. +This can of course make it appear at first glance as if +<tt>rcu_read_unlock_bh()</tt> was executing very slowly. + +<p> +The +<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a> +includes +<tt>rcu_read_lock_bh()</tt>, +<tt>rcu_read_unlock_bh()</tt>, +<tt>rcu_dereference_bh()</tt>, +<tt>rcu_dereference_bh_check()</tt>, +<tt>synchronize_rcu_bh()</tt>, +<tt>synchronize_rcu_bh_expedited()</tt>, +<tt>call_rcu_bh()</tt>, +<tt>rcu_barrier_bh()</tt>, and +<tt>rcu_read_lock_bh_held()</tt>. + +<h3><a name="Sched Flavor">Sched Flavor</a></h3> + +<p> +Before preemptible RCU, waiting for an RCU grace period had the +side effect of also waiting for all pre-existing interrupt +and NMI handlers. +However, there are legitimate preemptible-RCU implementations that +do not have this property, given that any point in the code outside +of an RCU read-side critical section can be a quiescent state. +Therefore, <i>RCU-sched</i> was created, which follows “classic” +RCU in that an RCU-sched grace period waits for for pre-existing +interrupt and NMI handlers. +In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched +APIs have identical implementations, while kernels built with +<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each. + +<p> +Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels, +<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt> +disable and re-enable preemption, respectively. +This means that if there was a preemption attempt during the +RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt> +will enter the scheduler, with all the latency and overhead entailed. +Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look +as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly. +However, the highest-priority task won't be preempted, so that task +will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations. + +<p> +The +<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a> +includes +<tt>rcu_read_lock_sched()</tt>, +<tt>rcu_read_unlock_sched()</tt>, +<tt>rcu_read_lock_sched_notrace()</tt>, +<tt>rcu_read_unlock_sched_notrace()</tt>, +<tt>rcu_dereference_sched()</tt>, +<tt>rcu_dereference_sched_check()</tt>, +<tt>synchronize_sched()</tt>, +<tt>synchronize_rcu_sched_expedited()</tt>, +<tt>call_rcu_sched()</tt>, +<tt>rcu_barrier_sched()</tt>, and +<tt>rcu_read_lock_sched_held()</tt>. +However, anything that disables preemption also marks an RCU-sched +read-side critical section, including +<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>, +<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>, +and so on. + +<h3><a name="Sleepable RCU">Sleepable RCU</a></h3> + +<p> +For well over a decade, someone saying “I need to block within +an RCU read-side critical section” was a reliable indication +that this someone did not understand RCU. +After all, if you are always blocking in an RCU read-side critical +section, you can probably afford to use a higher-overhead synchronization +mechanism. +However, that changed with the advent of the Linux kernel's notifiers, +whose RCU read-side critical +sections almost never sleep, but sometimes need to. +This resulted in the introduction of +<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>, +or <i>SRCU</i>. + +<p> +SRCU allows different domains to be defined, with each such domain +defined by an instance of an <tt>srcu_struct</tt> structure. +A pointer to this structure must be passed in to each SRCU function, +for example, <tt>synchronize_srcu(&ss)</tt>, where +<tt>ss</tt> is the <tt>srcu_struct</tt> structure. +The key benefit of these domains is that a slow SRCU reader in one +domain does not delay an SRCU grace period in some other domain. +That said, one consequence of these domains is that read-side code +must pass a “cookie” from <tt>srcu_read_lock()</tt> +to <tt>srcu_read_unlock()</tt>, for example, as follows: + +<blockquote> +<pre> + 1 int idx; + 2 + 3 idx = srcu_read_lock(&ss); + 4 do_something(); + 5 srcu_read_unlock(&ss, idx); +</pre> +</blockquote> + +<p> +As noted above, it is legal to block within SRCU read-side critical sections, +however, with great power comes great responsibility. +If you block forever in one of a given domain's SRCU read-side critical +sections, then that domain's grace periods will also be blocked forever. +Of course, one good way to block forever is to deadlock, which can +happen if any operation in a given domain's SRCU read-side critical +section can block waiting, either directly or indirectly, for that domain's +grace period to elapse. +For example, this results in a self-deadlock: + +<blockquote> +<pre> + 1 int idx; + 2 + 3 idx = srcu_read_lock(&ss); + 4 do_something(); + 5 synchronize_srcu(&ss); + 6 srcu_read_unlock(&ss, idx); +</pre> +</blockquote> + +<p> +However, if line 5 acquired a mutex that was held across +a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>, +deadlock would still be possible. +Furthermore, if line 5 acquired a mutex that was held across +a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>, +and if an <tt>ss1</tt>-domain SRCU read-side critical section +acquired another mutex that was held across as <tt>ss</tt>-domain +<tt>synchronize_srcu()</tt>, +deadlock would again be possible. +Such a deadlock cycle could extend across an arbitrarily large number +of different SRCU domains. +Again, with great power comes great responsibility. + +<p> +Unlike the other RCU flavors, SRCU read-side critical sections can +run on idle and even offline CPUs. +This ability requires that <tt>srcu_read_lock()</tt> and +<tt>srcu_read_unlock()</tt> contain memory barriers, which means +that SRCU readers will run a bit slower than would RCU readers. +It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt> +API, which, in combination with <tt>srcu_read_unlock()</tt>, +guarantees a full memory barrier. + +<p> +The +<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a> +includes +<tt>srcu_read_lock()</tt>, +<tt>srcu_read_unlock()</tt>, +<tt>srcu_dereference()</tt>, +<tt>srcu_dereference_check()</tt>, +<tt>synchronize_srcu()</tt>, +<tt>synchronize_srcu_expedited()</tt>, +<tt>call_srcu()</tt>, +<tt>srcu_barrier()</tt>, and +<tt>srcu_read_lock_held()</tt>. +It also includes +<tt>DEFINE_SRCU()</tt>, +<tt>DEFINE_STATIC_SRCU()</tt>, and +<tt>init_srcu_struct()</tt> +APIs for defining and initializing <tt>srcu_struct</tt> structures. + +<h3><a name="Tasks RCU">Tasks RCU</a></h3> + +<p> +Some forms of tracing use “tramopolines” to handle the +binary rewriting required to install different types of probes. +It would be good to be able to free old trampolines, which sounds +like a job for some form of RCU. +However, because it is necessary to be able to install a trace +anywhere in the code, it is not possible to use read-side markers +such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. +In addition, it does not work to have these markers in the trampoline +itself, because there would need to be instructions following +<tt>rcu_read_unlock()</tt>. +Although <tt>synchronize_rcu()</tt> would guarantee that execution +reached the <tt>rcu_read_unlock()</tt>, it would not be able to +guarantee that execution had completely left the trampoline. + +<p> +The solution, in the form of +<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>, +is to have implicit +read-side critical sections that are delimited by voluntary context +switches, that is, calls to <tt>schedule()</tt>, +<tt>cond_resched_rcu_qs()</tt>, and +<tt>synchronize_rcu_tasks()</tt>. +In addition, transitions to and from userspace execution also delimit +tasks-RCU read-side critical sections. + +<p> +The tasks-RCU API is quite compact, consisting only of +<tt>call_rcu_tasks()</tt>, +<tt>synchronize_rcu_tasks()</tt>, and +<tt>rcu_barrier_tasks()</tt>. + +<h2><a name="Possible Future Changes">Possible Future Changes</a></h2> + +<p> +One of the tricks that RCU uses to attain update-side scalability is +to increase grace-period latency with increasing numbers of CPUs. +If this becomes a serious problem, it will be necessary to rework the +grace-period state machine so as to avoid the need for the additional +latency. + +<p> +Expedited grace periods scan the CPUs, so their latency and overhead +increases with increasing numbers of CPUs. +If this becomes a serious problem on large systems, it will be necessary +to do some redesign to avoid this scalability problem. + +<p> +RCU disables CPU hotplug in a few places, perhaps most notably in the +expedited grace-period and <tt>rcu_barrier()</tt> operations. +If there is a strong reason to use expedited grace periods in CPU-hotplug +notifiers, it will be necessary to avoid disabling CPU hotplug. +This would introduce some complexity, so there had better be a <i>very</i> +good reason. + +<p> +The tradeoff between grace-period latency on the one hand and interruptions +of other CPUs on the other hand may need to be re-examined. +The desire is of course for zero grace-period latency as well as zero +interprocessor interrupts undertaken during an expedited grace period +operation. +While this ideal is unlikely to be achievable, it is quite possible that +further improvements can be made. + +<p> +The multiprocessor implementations of RCU use a combining tree that +groups CPUs so as to reduce lock contention and increase cache locality. +However, this combining tree does not spread its memory across NUMA +nodes nor does it align the CPU groups with hardware features such +as sockets or cores. +Such spreading and alignment is currently believed to be unnecessary +because the hotpath read-side primitives do not access the combining +tree, nor does <tt>call_rcu()</tt> in the common case. +If you believe that your architecture needs such spreading and alignment, +then your architecture should also benefit from the +<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set +to the number of CPUs in a socket, NUMA node, or whatever. +If the number of CPUs is too large, use a fraction of the number of +CPUs. +If the number of CPUs is a large prime number, well, that certainly +is an “interesting” architectural choice! +More flexible arrangements might be considered, but only if +<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only +if the inadequacy has been demonstrated by a carefully run and +realistic system-level workload. + +<p> +Please note that arrangements that require RCU to remap CPU numbers will +require extremely good demonstration of need and full exploration of +alternatives. + +<p> +There is an embarrassingly large number of flavors of RCU, and this +number has been increasing over time. +Perhaps it will be possible to combine some at some future date. + +<p> +RCU's various kthreads are reasonably recent additions. +It is quite likely that adjustments will be required to more gracefully +handle extreme loads. +It might also be necessary to be able to relate CPU utilization by +RCU's kthreads and softirq handlers to the code that instigated this +CPU utilization. +For example, RCU callback overhead might be charged back to the +originating <tt>call_rcu()</tt> instance, though probably not +in production kernels. + +<h2><a name="Summary">Summary</a></h2> + +<p> +This document has presented more than two decade's worth of RCU +requirements. +Given that the requirements keep changing, this will not be the last +word on this subject, but at least it serves to get an important +subset of the requirements set forth. + +<h2><a name="Acknowledgments">Acknowledgments</a></h2> + +I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar, +Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and +Andy Lutomirski for their help in rendering +this article human readable, and to Michelle Rankin for her support +of this effort. +Other contributions are acknowledged in the Linux kernel's git archive. +The cartoon is copyright (c) 2013 by Melissa Broussard, +and is provided +under the terms of the Creative Commons Attribution-Share Alike 3.0 +United States license. + +<p>@@QQAL@@ + +</body></html> diff --git a/Documentation/RCU/Design/htmlqqz.sh b/Documentation/RCU/Design/htmlqqz.sh new file mode 100755 index 000000000000..d354f069559b --- /dev/null +++ b/Documentation/RCU/Design/htmlqqz.sh @@ -0,0 +1,108 @@ +#!/bin/sh +# +# Usage: sh htmlqqz.sh file +# +# Extracts and converts quick quizzes in a proto-HTML document file.htmlx. +# Commands, all of which must be on a line by themselves: +# +# "<p>@@QQ@@": Start of a quick quiz. +# "<p>@@QQA@@": Start of a quick-quiz answer. +# "<p>@@QQE@@": End of a quick-quiz answer, and thus of the quick quiz. +# "<p>@@QQAL@@": Place to put quick-quiz answer list. +# +# Places the result in file.html. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, you can access it online at +# http://www.gnu.org/licenses/gpl-2.0.html. +# +# Copyright (c) 2013 Paul E. McKenney, IBM Corporation. + +fn=$1 +if test ! -r $fn.htmlx +then + echo "Error: $fn.htmlx unreadable." + exit 1 +fi + +echo "<!-- DO NOT HAND EDIT. -->" > $fn.html +echo "<!-- Instead, edit $fn.htmlx and run 'sh htmlqqz.sh $fn' -->" >> $fn.html +awk < $fn.htmlx >> $fn.html ' + +state == "" && $1 != "<p>@@QQ@@" && $1 != "<p>@@QQAL@@" { + print $0; + if ($0 ~ /^<p>@@QQ/) + print "Bad Quick Quiz command: " NR " (expected <p>@@QQ@@ or <p>@@QQAL@@)." > "/dev/stderr" + next; +} + +state == "" && $1 == "<p>@@QQ@@" { + qqn++; + qqlineno = NR; + haveqq = 1; + state = "qq"; + print "<p><a name=\"Quick Quiz " qqn "\"><b>Quick Quiz " qqn "</b>:</a>" + next; +} + +state == "qq" && $1 != "<p>@@QQA@@" { + qq[qqn] = qq[qqn] $0 "\n"; + print $0 + if ($0 ~ /^<p>@@QQ/) + print "Bad Quick Quiz command: " NR ". (expected <p>@@QQA@@)" > "/dev/stderr" + next; +} + +state == "qq" && $1 == "<p>@@QQA@@" { + state = "qqa"; + print "<br><a href=\"#qq" qqn "answer\">Answer</a>" + next; +} + +state == "qqa" && $1 != "<p>@@QQE@@" { + qqa[qqn] = qqa[qqn] $0 "\n"; + if ($0 ~ /^<p>@@QQ/) + print "Bad Quick Quiz command: " NR " (expected <p>@@QQE@@)." > "/dev/stderr" + next; +} + +state == "qqa" && $1 == "<p>@@QQE@@" { + state = ""; + next; +} + +state == "" && $1 == "<p>@@QQAL@@" { + haveqq = ""; + print "<h3><a name=\"Answers to Quick Quizzes\">" + print "Answers to Quick Quizzes</a></h3>" + print ""; + for (i = 1; i <= qqn; i++) { + print "<a name=\"qq" i "answer\"></a>" + print "<p><b>Quick Quiz " i "</b>:" + print qq[i]; + print ""; + print "</p><p><b>Answer</b>:" + print qqa[i]; + print ""; + print "</p><p><a href=\"#Quick%20Quiz%20" i "\"><b>Back to Quick Quiz " i "</b>.</a>" + print ""; + } + next; +} + +END { + if (state != "") + print "Unterminated Quick Quiz: " qqlineno "." > "/dev/stderr" + else if (haveqq) + print "Missing \"<p>@@QQAL@@\", no Quick Quiz." > "/dev/stderr" +}' diff --git a/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt b/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt index b9c32f6fd687..4357e498ef04 100644 --- a/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt +++ b/Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt @@ -12,7 +12,7 @@ Each key is represented as a sub-node of "allwinner,sun4i-a10-lradc-keys": Required subnode-properties: - label: Descriptive name of the key. - linux,code: Keycode to emit. - - channel: Channel this key is attached to, mut be 0 or 1. + - channel: Channel this key is attached to, must be 0 or 1. - voltage: Voltage in µV at lradc input when this key is pressed. Example: diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 9853f8e70966..28a4781ab6d7 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -40,18 +40,18 @@ Optional properties: Slave Properties: Required properties: -- phy_id : Specifies slave phy id - phy-mode : See ethernet.txt file in the same directory Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports - mac-address : See ethernet.txt file in the same directory +- phy_id : Specifies slave phy id - phy-handle : See ethernet.txt file in the same directory Slave sub-nodes: - fixed-link : See fixed-link.txt file in the same directory - Either the properties phy_id and phy-mode, - or the sub-node fixed-link can be specified + Either the property phy_id, or the sub-node + fixed-link can be specified Note: "ti,hwmods" field is used to fetch the base address and irq resources from TI, omap hwmod data base during device registration. diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 06d443450f21..619af9bfdcb3 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -50,8 +50,7 @@ prototypes: int (*rename2) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); - const char *(*follow_link) (struct dentry *, void **); - void (*put_link) (struct inode *, void *); + const char *(*get_link) (struct dentry *, struct inode *, void **); void (*truncate) (struct inode *); int (*permission) (struct inode *, int, unsigned int); int (*get_acl)(struct inode *, int); @@ -83,8 +82,7 @@ rmdir: yes (both) (see below) rename: yes (all) (see below) rename2: yes (all) (see below) readlink: no -follow_link: no -put_link: no +get_link: no setattr: yes permission: no (may not block if called in rcu-walk mode) get_acl: no diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index f24d1b833957..0f88e6020487 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -504,3 +504,20 @@ in your dentry operations instead. [mandatory] __fd_install() & fd_install() can now sleep. Callers should not hold a spinlock or other resources that do not allow a schedule. +-- +[mandatory] + any symlink that might use page_follow_link_light/page_put_link() must + have inode_nohighmem(inode) called before anything might start playing with + its pagecache. +-- +[mandatory] + ->follow_link() is replaced with ->get_link(); same API, except that + * ->get_link() gets inode as a separate argument + * ->get_link() may be called in RCU mode - in that case NULL + dentry is passed +-- +[mandatory] + ->get_link() gets struct delayed_call *done now, and should do + set_delayed_call() where it used to set *cookie. + ->put_link() is gone - just give the destructor to set_delayed_call() + in ->get_link(). diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 8c6f07ad373a..b02a7d598258 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -350,8 +350,8 @@ struct inode_operations { int (*rename2) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*readlink) (struct dentry *, char __user *,int); - const char *(*follow_link) (struct dentry *, void **); - void (*put_link) (struct inode *, void *); + const char *(*get_link) (struct dentry *, struct inode *, + struct delayed_call *); int (*permission) (struct inode *, int); int (*get_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); @@ -434,20 +434,19 @@ otherwise noted. readlink: called by the readlink(2) system call. Only required if you want to support reading symbolic links - follow_link: called by the VFS to follow a symbolic link to the + get_link: called by the VFS to follow a symbolic link to the inode it points to. Only required if you want to support symbolic links. This method returns the symlink body to traverse (and possibly resets the current position with nd_jump_link()). If the body won't go away until the inode is gone, nothing else is needed; if it needs to be otherwise - pinned, the data needed to release whatever we'd grabbed - is to be stored in void * variable passed by address to - follow_link() instance. - - put_link: called by the VFS to release resources allocated by - follow_link(). The cookie stored by follow_link() is passed - to this method as the last parameter; only called when - cookie isn't NULL. + pinned, arrange for its release by having get_link(..., ..., done) + do set_delayed_call(done, destructor, argument). + In that case destructor(argument) will be called once VFS is + done with the body you've returned. + May be called in RCU mode; that is indicated by NULL dentry + argument. If request can't be handled without leaving RCU mode, + have it return ERR_PTR(-ECHILD). permission: called by the VFS to check for access rights on a POSIX-like filesystem. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 742f69d18fc8..1a44a7a7f71d 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -472,6 +472,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Change the amount of debugging information output when initialising the APIC and IO-APIC components. + apic_extnmi= [APIC,X86] External NMI delivery setting + Format: { bsp (default) | all | none } + bsp: External NMI is delivered only to CPU 0 + all: External NMIs are broadcast to all CPUs as a + backup of CPU 0 + none: External NMI is masked for all CPUs. This is + useful so that a dump capture kernel won't be + shot down by NMI + autoconf= [IPV6] See Documentation/networking/ipv6.txt. @@ -3296,18 +3305,35 @@ bytes respectively. Such letter suffixes can also be entirely omitted. rcutorture.verbose= [KNL] Enable additional printk() statements. + rcupdate.rcu_cpu_stall_suppress= [KNL] + Suppress RCU CPU stall warning messages. + + rcupdate.rcu_cpu_stall_timeout= [KNL] + Set timeout for RCU CPU stall warning messages. + rcupdate.rcu_expedited= [KNL] Use expedited grace-period primitives, for example, synchronize_rcu_expedited() instead of synchronize_rcu(). This reduces latency, but can increase CPU utilization, degrade real-time latency, and degrade energy efficiency. - - rcupdate.rcu_cpu_stall_suppress= [KNL] - Suppress RCU CPU stall warning messages. - - rcupdate.rcu_cpu_stall_timeout= [KNL] - Set timeout for RCU CPU stall warning messages. + No effect on CONFIG_TINY_RCU kernels. + + rcupdate.rcu_normal= [KNL] + Use only normal grace-period primitives, + for example, synchronize_rcu() instead of + synchronize_rcu_expedited(). This improves + real-time latency, CPU utilization, and + energy efficiency, but can expose users to + increased grace-period latency. This parameter + overrides rcupdate.rcu_expedited. No effect on + CONFIG_TINY_RCU kernels. + + rcupdate.rcu_normal_after_boot= [KNL] + Once boot has completed (that is, after + rcu_end_inkernel_boot() has been invoked), use + only normal grace-period primitives. No effect + on CONFIG_TINY_RCU kernels. rcupdate.rcu_task_stall_timeout= [KNL] Set timeout in jiffies for RCU task stall warning diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index aef9487303d0..a61be39c7b51 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -194,7 +194,7 @@ There are some minimal guarantees that may be expected of a CPU: (*) On any given CPU, dependent memory accesses will be issued in order, with respect to itself. This means that for: - WRITE_ONCE(Q, P); smp_read_barrier_depends(); D = READ_ONCE(*Q); + Q = READ_ONCE(P); smp_read_barrier_depends(); D = READ_ONCE(*Q); the CPU will issue the following memory operations: @@ -202,9 +202,9 @@ There are some minimal guarantees that may be expected of a CPU: and always in that order. On most systems, smp_read_barrier_depends() does nothing, but it is required for DEC Alpha. The READ_ONCE() - and WRITE_ONCE() are required to prevent compiler mischief. Please - note that you should normally use something like rcu_dereference() - instead of open-coding smp_read_barrier_depends(). + is required to prevent compiler mischief. Please note that you + should normally use something like rcu_dereference() instead of + open-coding smp_read_barrier_depends(). (*) Overlapping loads and stores within a particular CPU will appear to be ordered within that CPU. This means that for: @@ -1673,8 +1673,8 @@ There are some more advanced barrier functions: (*) smp_store_mb(var, value) This assigns the value to the variable and then inserts a full memory - barrier after it, depending on the function. It isn't guaranteed to - insert anything more than a compiler barrier in a UP compilation. + barrier after it. It isn't guaranteed to insert anything more than a + compiler barrier in a UP compilation. (*) smp_mb__before_atomic(); diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index af70d1541d3a..73c6b1ef0e84 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -551,6 +551,21 @@ the recommended setting is 60. ============================================================== +panic_on_io_nmi: + +Controls the kernel's behavior when a CPU receives an NMI caused by +an IO error. + +0: try to continue operation (default) + +1: panic immediately. The IO error triggered an NMI. This indicates a + serious system condition which could result in IO data corruption. + Rather than continuing, panicking might be a better choice. Some + servers issue this sort of NMI when the dump button is pushed, + and you can use this option to take a crash dump. + +============================================================== + panic_on_oops: Controls the kernel's behaviour when an oops or BUG is encountered. diff --git a/Documentation/trace/events-msr.txt b/Documentation/trace/events-msr.txt new file mode 100644 index 000000000000..78c383bf06aa --- /dev/null +++ b/Documentation/trace/events-msr.txt @@ -0,0 +1,37 @@ + +The x86 kernel supports tracing most MSR (Model Specific Register) accesses. +To see the definition of the MSRs on Intel systems please see the SDM +at http://www.intel.com/sdm (Volume 3) + +Available trace points: + +/sys/kernel/debug/tracing/events/msr/ + +Trace MSR reads + +read_msr + +msr: MSR number +val: Value written +failed: 1 if the access failed, otherwise 0 + + +Trace MSR writes + +write_msr + +msr: MSR number +val: Value written +failed: 1 if the access failed, otherwise 0 + + +Trace RDPMC in kernel + +rdpmc + +The trace data can be post processed with the postprocess/decode_msr.py script + +cat /sys/kernel/debug/tracing/trace | decode_msr.py /usr/src/linux/include/asm/msr-index.h + +to add symbolic MSR names. + diff --git a/Documentation/trace/postprocess/decode_msr.py b/Documentation/trace/postprocess/decode_msr.py new file mode 100644 index 000000000000..0ab40e0db580 --- /dev/null +++ b/Documentation/trace/postprocess/decode_msr.py @@ -0,0 +1,37 @@ +#!/usr/bin/python +# add symbolic names to read_msr / write_msr in trace +# decode_msr msr-index.h < trace +import sys +import re + +msrs = dict() + +with open(sys.argv[1] if len(sys.argv) > 1 else "msr-index.h", "r") as f: + for j in f: + m = re.match(r'#define (MSR_\w+)\s+(0x[0-9a-fA-F]+)', j) + if m: + msrs[int(m.group(2), 16)] = m.group(1) + +extra_ranges = ( + ( "MSR_LASTBRANCH_%d_FROM_IP", 0x680, 0x69F ), + ( "MSR_LASTBRANCH_%d_TO_IP", 0x6C0, 0x6DF ), + ( "LBR_INFO_%d", 0xdc0, 0xddf ), +) + +for j in sys.stdin: + m = re.search(r'(read|write)_msr:\s+([0-9a-f]+)', j) + if m: + r = None + num = int(m.group(2), 16) + if num in msrs: + r = msrs[num] + else: + for er in extra_ranges: + if er[1] <= num <= er[2]: + r = er[0] % (num - er[1],) + break + if r: + j = j.replace(" " + m.group(2), " " + r + "(" + m.group(2) + ")") + print j, + + diff --git a/MAINTAINERS b/MAINTAINERS index 6889a6dbb42d..026cea8b5a36 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5622,9 +5622,7 @@ F: Documentation/trace/intel_th.txt F: drivers/hwtracing/intel_th/ INTEL(R) TRUSTED EXECUTION TECHNOLOGY (TXT) -M: Richard L Maliszewski <richard.l.maliszewski@intel.com> -M: Gang Wei <gang.wei@intel.com> -M: Shane Wang <shane.wang@intel.com> +M: Ning Sun <ning.sun@intel.com> L: tboot-devel@lists.sourceforge.net W: http://tboot.sourceforge.net T: hg http://tboot.hg.sourceforge.net:8000/hgroot/tboot/tboot @@ -8380,6 +8378,14 @@ L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) S: Maintained F: drivers/pinctrl/samsung/ +PIN CONTROLLER - SINGLE +M: Tony Lindgren <tony@atomide.com> +M: Haojian Zhuang <haojian.zhuang@linaro.org> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-omap@vger.kernel.org +S: Maintained +F: drivers/pinctrl/pinctrl-single.c + PIN CONTROLLER - ST SPEAR M: Viresh Kumar <vireshk@kernel.org> L: spear-devel@list.st.com @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 4 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Blurry Fish Butt # *DOCUMENTATION* diff --git a/arch/arc/Makefile b/arch/arc/Makefile index cf0cf34eeb24..aeb19021099e 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -81,7 +81,7 @@ endif LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel -KBUILD_CFLAGS_MODULE += -mlong-calls +KBUILD_CFLAGS_MODULE += -mlong-calls -mno-millicode # Finally dump eveything into kernel build system KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index abf06e81c929..210ef3e72332 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -62,9 +62,7 @@ extern int ioc_exists; #define ARC_REG_IC_IVIC 0x10 #define ARC_REG_IC_CTRL 0x11 #define ARC_REG_IC_IVIL 0x19 -#if defined(CONFIG_ARC_MMU_V3) || defined(CONFIG_ARC_MMU_V4) #define ARC_REG_IC_PTAG 0x1E -#endif #define ARC_REG_IC_PTAG_HI 0x1F /* Bit val in IC_CTRL */ diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index cf2828ab0905..5eb707640e9c 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -293,13 +293,13 @@ static void init_unwind_hdr(struct unwind_table *table, const u32 *cie = cie_for_fde(fde, table); signed ptrType; - if (cie == ¬_fde) /* only process FDE here */ + if (cie == ¬_fde) continue; if (cie == NULL || cie == &bad_cie) - continue; /* say FDE->CIE.version != 1 */ + goto ret_err; ptrType = fde_pointer_type(cie); if (ptrType < 0) - continue; + goto ret_err; ptr = (const u8 *)(fde + 2); if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde, @@ -315,14 +315,14 @@ static void init_unwind_hdr(struct unwind_table *table, } if (tableSize || !n) - return; + goto ret_err; hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int) + 2 * n * sizeof(unsigned long); header = alloc(hdrSize); if (!header) - return; + goto ret_err; header->version = 1; header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native; @@ -343,10 +343,6 @@ static void init_unwind_hdr(struct unwind_table *table, if (fde[1] == 0xffffffff) continue; /* this is a CIE */ - - if (*(u8 *)(cie + 2) != 1) - continue; /* FDE->CIE.version not supported */ - ptr = (const u8 *)(fde + 2); header->table[n].start = read_pointer(&ptr, (const u8 *)(fde + 1) + @@ -365,6 +361,10 @@ static void init_unwind_hdr(struct unwind_table *table, table->hdrsz = hdrSize; smp_wmb(); table->header = (const void *)header; + return; + +ret_err: + panic("Attention !!! Dwarf FDE parsing errors\n");; } #ifdef CONFIG_MODULES @@ -523,8 +523,7 @@ static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table) if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde) || (*cie & (sizeof(*cie) - 1)) - || (cie[1] != 0xffffffff) - || ( *(u8 *)(cie + 2) != 1)) /* version 1 supported */ + || (cie[1] != 0xffffffff)) return NULL; /* this is not a (valid) CIE */ return cie; } @@ -605,9 +604,6 @@ static signed fde_pointer_type(const u32 *cie) const u8 *ptr = (const u8 *)(cie + 2); unsigned version = *ptr; - if (version != 1) - return -1; /* unsupported */ - if (*++ptr) { const char *aug; const u8 *end = (const u8 *)(cie + 1) + *cie; @@ -1019,9 +1015,7 @@ int arc_unwind(struct unwind_frame_info *frame) ptr = (const u8 *)(cie + 2); end = (const u8 *)(cie + 1) + *cie; frame->call_frame = 1; - if ((state.version = *ptr) != 1) - cie = NULL; /* unsupported version */ - else if (*++ptr) { + if (*++ptr) { /* check if augmentation size is first (thus present) */ if (*ptr == 'z') { while (++ptr < end && *ptr) { diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 065ee6bfa82a..92dd92cad7f9 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -111,7 +111,7 @@ void __kunmap_atomic(void *kv) } EXPORT_SYMBOL(__kunmap_atomic); -noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr) +static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr) { pgd_t *pgd_k; pud_t *pud_k; @@ -127,7 +127,7 @@ noinline pte_t *alloc_kmap_pgtable(unsigned long kvaddr) return pte_k; } -void kmap_init(void) +void __init kmap_init(void) { /* Due to recursive include hell, we can't do this in processor.h */ BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE)); diff --git a/arch/arm/boot/dts/imx6q-gw5400-a.dts b/arch/arm/boot/dts/imx6q-gw5400-a.dts index 58adf176425a..a51834e1dd27 100644 --- a/arch/arm/boot/dts/imx6q-gw5400-a.dts +++ b/arch/arm/boot/dts/imx6q-gw5400-a.dts @@ -154,7 +154,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi index 7b31fdb79ced..dc0cebfe22d7 100644 --- a/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw51xx.dtsi @@ -94,7 +94,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 1b66328a8498..18cd4114a23e 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -154,7 +154,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi index 7c51839ff934..eea90f37bbb8 100644 --- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi @@ -155,7 +155,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi index 929e0b37bd9e..6c11a2ae35ef 100644 --- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi @@ -145,7 +145,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 8263fc18a7d9..d354d406954d 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -113,14 +113,14 @@ &clks { assigned-clocks = <&clks IMX6QDL_PLL4_BYPASS_SRC>, <&clks IMX6QDL_PLL4_BYPASS>, - <&clks IMX6QDL_CLK_PLL4_POST_DIV>, <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, + <&clks IMX6QDL_CLK_PLL4_POST_DIV>; assigned-clock-parents = <&clks IMX6QDL_CLK_LVDS2_IN>, <&clks IMX6QDL_PLL4_BYPASS_SRC>, <&clks IMX6QDL_CLK_PLL3_USB_OTG>, <&clks IMX6QDL_CLK_PLL3_USB_OTG>; - assigned-clock-rates = <0>, <0>, <24576000>; + assigned-clock-rates = <0>, <0>, <0>, <0>, <24576000>; }; &ecspi1 { diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index 1a78f013f37a..b75f7b2b7c4a 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -189,3 +189,7 @@ }; }; +&uart3 { + interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH + &omap4_pmx_core OMAP4_UART3_RX>; +}; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index 314f59c12162..d0c743853318 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -25,9 +25,9 @@ cache-sets = <512>; cache-line-size = <32>; /* At full speed latency must be >=2 */ - arm,tag-latency = <2>; - arm,data-latency = <2 2>; - arm,dirty-latency = <2>; + arm,tag-latency = <8>; + arm,data-latency = <8 8>; + arm,dirty-latency = <8>; }; mtu0: mtu@101e2000 { diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts index 2d4250b1faf8..68b479b8772c 100644 --- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts +++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts @@ -83,6 +83,7 @@ reg = <0x5d>; interrupt-parent = <&pio>; interrupts = <0 3 IRQ_TYPE_LEVEL_HIGH>; /* PA3 */ + touchscreen-swapped-x-y; }; }; diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi index 40c23a0b7cfc..ec1aa64ded68 100644 --- a/arch/arm/boot/dts/tegra124-nyan.dtsi +++ b/arch/arm/boot/dts/tegra124-nyan.dtsi @@ -399,7 +399,7 @@ /* CPU DFLL clock */ clock@0,70110000 { - status = "okay"; + status = "disabled"; vdd-cpu-supply = <&vdd_cpu>; nvidia,i2c-fs-rate = <400000>; }; diff --git a/arch/arm/boot/dts/versatile-ab.dts b/arch/arm/boot/dts/versatile-ab.dts index 01f40197ea13..3279bf1a17a1 100644 --- a/arch/arm/boot/dts/versatile-ab.dts +++ b/arch/arm/boot/dts/versatile-ab.dts @@ -110,7 +110,11 @@ interrupt-parent = <&vic>; interrupts = <31>; /* Cascaded to vic */ clear-mask = <0xffffffff>; - valid-mask = <0xffc203f8>; + /* + * Valid interrupt lines mask according to + * table 4-36 page 4-50 of ARM DUI 0225D + */ + valid-mask = <0x0760031b>; }; dma@10130000 { @@ -266,8 +270,8 @@ }; mmc@5000 { compatible = "arm,pl180", "arm,primecell"; - reg = < 0x5000 0x1000>; - interrupts-extended = <&vic 22 &sic 2>; + reg = <0x5000 0x1000>; + interrupts-extended = <&vic 22 &sic 1>; clocks = <&xtal24mhz>, <&pclk>; clock-names = "mclk", "apb_pclk"; }; diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index b83137f66034..33a8eb28374e 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -5,6 +5,16 @@ compatible = "arm,versatile-pb"; amba { + /* The Versatile PB is using more SIC IRQ lines than the AB */ + sic: intc@10003000 { + clear-mask = <0xffffffff>; + /* + * Valid interrupt lines mask according to + * figure 3-30 page 3-74 of ARM DUI 0224B + */ + valid-mask = <0x7fe003ff>; + }; + gpio2: gpio@101e6000 { compatible = "arm,pl061", "arm,primecell"; reg = <0x101e6000 0x1000>; @@ -67,6 +77,13 @@ }; fpga { + mmc@5000 { + /* + * Overrides the interrupt assignment from + * the Versatile AB board file. + */ + interrupts-extended = <&sic 22 &sic 23>; + }; uart@9000 { compatible = "arm,pl011", "arm,primecell"; reg = <0x9000 0x1000>; @@ -86,7 +103,8 @@ mmc@b000 { compatible = "arm,pl180", "arm,primecell"; reg = <0xb000 0x1000>; - interrupts-extended = <&vic 23 &sic 2>; + interrupt-parent = <&sic>; + interrupts = <1>, <2>; clocks = <&xtal24mhz>, <&pclk>; clock-names = "mclk", "apb_pclk"; }; diff --git a/arch/arm/boot/dts/wm8650.dtsi b/arch/arm/boot/dts/wm8650.dtsi index b1c59a766a13..e12213d16693 100644 --- a/arch/arm/boot/dts/wm8650.dtsi +++ b/arch/arm/boot/dts/wm8650.dtsi @@ -187,6 +187,15 @@ interrupts = <43>; }; + sdhc@d800a000 { + compatible = "wm,wm8505-sdhc"; + reg = <0xd800a000 0x400>; + interrupts = <20>, <21>; + clocks = <&clksdhc>; + bus-width = <4>; + sdon-inverted; + }; + fb: fb@d8050800 { compatible = "wm,wm8505-fb"; reg = <0xd8050800 0x200>; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 69a22fdb52a5..cd7b198fc79e 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -366,6 +366,7 @@ CONFIG_BATTERY_MAX17042=m CONFIG_CHARGER_MAX14577=m CONFIG_CHARGER_MAX77693=m CONFIG_CHARGER_TPS65090=y +CONFIG_AXP20X_POWER=m CONFIG_POWER_RESET_AS3722=y CONFIG_POWER_RESET_GPIO=y CONFIG_POWER_RESET_GPIO_RESTART=y diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig index 3c36e16fcacf..b503a89441bf 100644 --- a/arch/arm/configs/sunxi_defconfig +++ b/arch/arm/configs/sunxi_defconfig @@ -84,6 +84,7 @@ CONFIG_SPI_SUN4I=y CONFIG_SPI_SUN6I=y CONFIG_GPIO_SYSFS=y CONFIG_POWER_SUPPLY=y +CONFIG_AXP20X_POWER=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y CONFIG_WATCHDOG=y diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index b83f3b7737fb..087acb569b63 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -193,15 +193,44 @@ struct oabi_flock64 { pid_t l_pid; } __attribute__ ((packed,aligned(4))); -asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, +static long do_locks(unsigned int fd, unsigned int cmd, unsigned long arg) { - struct oabi_flock64 user; struct flock64 kernel; - mm_segment_t fs = USER_DS; /* initialized to kill a warning */ - unsigned long local_arg = arg; - int ret; + struct oabi_flock64 user; + mm_segment_t fs; + long ret; + + if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, + sizeof(user))) + return -EFAULT; + kernel.l_type = user.l_type; + kernel.l_whence = user.l_whence; + kernel.l_start = user.l_start; + kernel.l_len = user.l_len; + kernel.l_pid = user.l_pid; + + fs = get_fs(); + set_fs(KERNEL_DS); + ret = sys_fcntl64(fd, cmd, (unsigned long)&kernel); + set_fs(fs); + + if (!ret && (cmd == F_GETLK64 || cmd == F_OFD_GETLK)) { + user.l_type = kernel.l_type; + user.l_whence = kernel.l_whence; + user.l_start = kernel.l_start; + user.l_len = kernel.l_len; + user.l_pid = kernel.l_pid; + if (copy_to_user((struct oabi_flock64 __user *)arg, + &user, sizeof(user))) + ret = -EFAULT; + } + return ret; +} +asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, + unsigned long arg) +{ switch (cmd) { case F_OFD_GETLK: case F_OFD_SETLK: @@ -209,39 +238,11 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: - if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, - sizeof(user))) - return -EFAULT; - kernel.l_type = user.l_type; - kernel.l_whence = user.l_whence; - kernel.l_start = user.l_start; - kernel.l_len = user.l_len; - kernel.l_pid = user.l_pid; - local_arg = (unsigned long)&kernel; - fs = get_fs(); - set_fs(KERNEL_DS); - } - - ret = sys_fcntl64(fd, cmd, local_arg); + return do_locks(fd, cmd, arg); - switch (cmd) { - case F_GETLK64: - if (!ret) { - user.l_type = kernel.l_type; - user.l_whence = kernel.l_whence; - user.l_start = kernel.l_start; - user.l_len = kernel.l_len; - user.l_pid = kernel.l_pid; - if (copy_to_user((struct oabi_flock64 __user *)arg, - &user, sizeof(user))) - ret = -EFAULT; - } - case F_SETLK64: - case F_SETLKW64: - set_fs(fs); + default: + return sys_fcntl64(fd, cmd, arg); } - - return ret; } struct oabi_epoll_event { diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 4b4371db5799..0517f0c1581a 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -65,6 +65,8 @@ config SOC_AM43XX select MACH_OMAP_GENERIC select MIGHT_HAVE_CACHE_L2X0 select HAVE_ARM_SCU + select GENERIC_CLOCKEVENTS_BROADCAST + select HAVE_ARM_TWD config SOC_DRA7XX bool "TI DRA7XX" diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 17a6f752a436..7b76ce01c21d 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -149,8 +149,8 @@ static int omap2_onenand_get_freq(struct omap_onenand_platform_data *cfg, freq = 104; break; default: - freq = 54; - break; + pr_err("onenand rate not detected, bad GPMC async timings?\n"); + freq = 0; } return freq; @@ -271,6 +271,11 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) struct gpmc_timings t; int ret; + /* + * Note that we need to keep sync_write set for the call to + * omap2_onenand_set_async_mode() to work to detect the onenand + * supported clock rate for the sync timings. + */ if (gpmc_onenand_data->of_node) { gpmc_read_settings_dt(gpmc_onenand_data->of_node, &onenand_async); @@ -281,12 +286,9 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) else gpmc_onenand_data->flags |= ONENAND_SYNC_READ; onenand_async.sync_read = false; - onenand_async.sync_write = false; } } - omap2_onenand_set_async_mode(onenand_base); - omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); @@ -310,6 +312,8 @@ static int omap2_onenand_setup_sync(void __iomem *onenand_base, int *freq_ptr) if (!freq) { /* Very first call freq is not known */ freq = omap2_onenand_get_freq(gpmc_onenand_data, onenand_base); + if (!freq) + return -ENODEV; set_onenand_cfg(onenand_base); } diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index b18ebbefae09..f86692dbcfd5 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -320,6 +320,12 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer, return r; } +#if !defined(CONFIG_SMP) && defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) +void tick_broadcast(const struct cpumask *mask) +{ +} +#endif + static void __init omap2_gp_clockevent_init(int gptimer_id, const char *fck_source, const char *property) diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 591f9db3bf40..93d0b6d0b63e 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -187,19 +187,6 @@ static inline int mem_words_used(struct jit_ctx *ctx) return fls(ctx->seen & SEEN_MEM); } -static inline bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void jit_fill_hole(void *area, unsigned int size) { u32 *ptr; @@ -211,7 +198,6 @@ static void jit_fill_hole(void *area, unsigned int size) static void build_prologue(struct jit_ctx *ctx) { u16 reg_set = saved_regs(ctx); - u16 first_inst = ctx->skf->insns[0].code; u16 off; #ifdef CONFIG_FRAME_POINTER @@ -241,7 +227,7 @@ static void build_prologue(struct jit_ctx *ctx) emit(ARM_MOV_I(r_X, 0), ctx); /* do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit(ARM_MOV_I(r_A, 0), ctx); /* stack space for the BPF_MEM words */ @@ -770,7 +756,8 @@ load_ind: case BPF_ALU | BPF_RSH | BPF_K: if (unlikely(k > 31)) return -1; - emit(ARM_LSR_I(r_A, r_A, k), ctx); + if (k) + emit(ARM_LSR_I(r_A, r_A, k), ctx); break; case BPF_ALU | BPF_RSH | BPF_X: update_on_xread(ctx); diff --git a/arch/blackfin/include/asm/cmpxchg.h b/arch/blackfin/include/asm/cmpxchg.h index c05868cc61c1..253928854299 100644 --- a/arch/blackfin/include/asm/cmpxchg.h +++ b/arch/blackfin/include/asm/cmpxchg.h @@ -128,6 +128,5 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, #endif /* !CONFIG_SMP */ #define xchg(ptr, x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) -#define tas(ptr) ((void)xchg((ptr), 1)) #endif /* __ARCH_BLACKFIN_CMPXCHG__ */ diff --git a/arch/c6x/include/asm/cmpxchg.h b/arch/c6x/include/asm/cmpxchg.h index b27c8cefb8c3..93d0a5a047a2 100644 --- a/arch/c6x/include/asm/cmpxchg.h +++ b/arch/c6x/include/asm/cmpxchg.h @@ -47,8 +47,6 @@ static inline unsigned int __xchg(unsigned int x, volatile void *ptr, int size) #define xchg(ptr, x) \ ((__typeof__(*(ptr)))__xchg((unsigned int)(x), (void *) (ptr), \ sizeof(*(ptr)))) -#define tas(ptr) xchg((ptr), 1) - #include <asm-generic/cmpxchg-local.h> diff --git a/arch/frv/include/asm/cmpxchg.h b/arch/frv/include/asm/cmpxchg.h index 5b04dd0aecab..a899765102ea 100644 --- a/arch/frv/include/asm/cmpxchg.h +++ b/arch/frv/include/asm/cmpxchg.h @@ -69,8 +69,6 @@ extern uint32_t __xchg_32(uint32_t i, volatile void *v); #endif -#define tas(ptr) (xchg((ptr), 1)) - /*****************************************************************************/ /* * compare and conditionally exchange value with memory diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h index df896a1c41d3..209c4b817c95 100644 --- a/arch/ia64/include/asm/barrier.h +++ b/arch/ia64/include/asm/barrier.h @@ -77,7 +77,7 @@ do { \ ___p1; \ }) -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) /* * The group barrier in front of the rsm & ssm are necessary to ensure diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild index fd104bd221ce..860e440611c9 100644 --- a/arch/m32r/include/asm/Kbuild +++ b/arch/m32r/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += clkdev.h generic-y += cputime.h generic-y += exec.h generic-y += irq_work.h +generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h index 61b8931bc192..4b0f5e001d4d 100644 --- a/arch/m32r/include/asm/io.h +++ b/arch/m32r/include/asm/io.h @@ -168,13 +168,21 @@ static inline void _writel(unsigned long l, unsigned long addr) #define writew_relaxed writew #define writel_relaxed writel -#define ioread8 read +#define ioread8 readb #define ioread16 readw #define ioread32 readl #define iowrite8 writeb #define iowrite16 writew #define iowrite32 writel +#define ioread8_rep(p, dst, count) insb((unsigned long)(p), (dst), (count)) +#define ioread16_rep(p, dst, count) insw((unsigned long)(p), (dst), (count)) +#define ioread32_rep(p, dst, count) insl((unsigned long)(p), (dst), (count)) + +#define iowrite8_rep(p, src, count) outsb((unsigned long)(p), (src), (count)) +#define iowrite16_rep(p, src, count) outsw((unsigned long)(p), (src), (count)) +#define iowrite32_rep(p, src, count) outsl((unsigned long)(p), (src), (count)) + #define ioread16be(addr) be16_to_cpu(readw(addr)) #define ioread32be(addr) be32_to_cpu(readl(addr)) #define iowrite16be(v, addr) writew(cpu_to_be16(v), (addr)) diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 5305d694ffe5..095ecafe6bd3 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -599,7 +599,7 @@ extern void __put_user_unknown(void); * On error, the variable @x is set to zero. */ #define __get_user_unaligned(x,ptr) \ - __get_user__unalignednocheck((x),(ptr),sizeof(*(ptr))) + __get_user_unaligned_nocheck((x),(ptr),sizeof(*(ptr))) /* * Yuck. We need two variants, one for 64bit operation and one @@ -620,8 +620,8 @@ extern void __get_user_unaligned_unknown(void); do { \ switch (size) { \ case 1: __get_data_asm(val, "lb", ptr); break; \ - case 2: __get_user_unaligned_asm(val, "ulh", ptr); break; \ - case 4: __get_user_unaligned_asm(val, "ulw", ptr); break; \ + case 2: __get_data_unaligned_asm(val, "ulh", ptr); break; \ + case 4: __get_data_unaligned_asm(val, "ulw", ptr); break; \ case 8: __GET_USER_UNALIGNED_DW(val, ptr); break; \ default: __get_user_unaligned_unknown(); break; \ } \ @@ -1122,9 +1122,15 @@ extern size_t __copy_in_user_eva(void *__to, const void *__from, size_t __n); __cu_to = (to); \ __cu_from = (from); \ __cu_len = (n); \ - might_fault(); \ - __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \ - __cu_len); \ + if (eva_kernel_access()) { \ + __cu_len = __invoke_copy_from_kernel(__cu_to, \ + __cu_from, \ + __cu_len); \ + } else { \ + might_fault(); \ + __cu_len = __invoke_copy_from_user(__cu_to, __cu_from, \ + __cu_len); \ + } \ __cu_len; \ }) @@ -1229,16 +1235,28 @@ __clear_user(void __user *addr, __kernel_size_t size) { __kernel_size_t res; - might_fault(); - __asm__ __volatile__( - "move\t$4, %1\n\t" - "move\t$5, $0\n\t" - "move\t$6, %2\n\t" - __MODULE_JAL(__bzero) - "move\t%0, $6" - : "=r" (res) - : "r" (addr), "r" (size) - : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + if (eva_kernel_access()) { + __asm__ __volatile__( + "move\t$4, %1\n\t" + "move\t$5, $0\n\t" + "move\t$6, %2\n\t" + __MODULE_JAL(__bzero_kernel) + "move\t%0, $6" + : "=r" (res) + : "r" (addr), "r" (size) + : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + } else { + might_fault(); + __asm__ __volatile__( + "move\t$4, %1\n\t" + "move\t$5, $0\n\t" + "move\t$6, %2\n\t" + __MODULE_JAL(__bzero) + "move\t%0, $6" + : "=r" (res) + : "r" (addr), "r" (size) + : "$4", "$5", "$6", __UA_t0, __UA_t1, "$31"); + } return res; } @@ -1384,7 +1402,7 @@ static inline long strlen_user(const char __user *s) might_fault(); __asm__ __volatile__( "move\t$4, %1\n\t" - __MODULE_JAL(__strlen_kernel_asm) + __MODULE_JAL(__strlen_user_asm) "move\t%0, $2" : "=r" (res) : "r" (s) diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 8fd5a276cad2..ac81edd44563 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -257,7 +257,6 @@ LEAF(mips_cps_core_init) has_mt t0, 3f .set push - .set mips64r2 .set mt /* Only allow 1 TC per VPE to execute... */ @@ -376,7 +375,6 @@ LEAF(mips_cps_boot_vpes) nop .set push - .set mips64r2 .set mt 1: /* Enter VPE configuration state */ diff --git a/arch/mips/kernel/mips_ksyms.c b/arch/mips/kernel/mips_ksyms.c index 291af0b5c482..e2b6ab74643d 100644 --- a/arch/mips/kernel/mips_ksyms.c +++ b/arch/mips/kernel/mips_ksyms.c @@ -17,6 +17,7 @@ #include <asm/fpu.h> #include <asm/msa.h> +extern void *__bzero_kernel(void *__s, size_t __count); extern void *__bzero(void *__s, size_t __count); extern long __strncpy_from_kernel_nocheck_asm(char *__to, const char *__from, long __len); @@ -64,6 +65,7 @@ EXPORT_SYMBOL(__copy_from_user_eva); EXPORT_SYMBOL(__copy_in_user_eva); EXPORT_SYMBOL(__copy_to_user_eva); EXPORT_SYMBOL(__copy_user_inatomic_eva); +EXPORT_SYMBOL(__bzero_kernel); #endif EXPORT_SYMBOL(__bzero); EXPORT_SYMBOL(__strncpy_from_kernel_nocheck_asm); diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index b8e63fd00375..8f0019a2e5c8 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -283,6 +283,8 @@ LEAF(memset) 1: #ifndef CONFIG_EVA FEXPORT(__bzero) +#else +FEXPORT(__bzero_kernel) #endif __BUILD_BZERO LEGACY_MODE diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 77cb27309db2..1a8c96035716 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -521,19 +521,6 @@ static inline u16 align_sp(unsigned int num) return num; } -static bool is_load_to_a(u16 inst) -{ - switch (inst) { - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - return true; - default: - return false; - } -} - static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset) { int i = 0, real_off = 0; @@ -614,7 +601,6 @@ static unsigned int get_stack_depth(struct jit_ctx *ctx) static void build_prologue(struct jit_ctx *ctx) { - u16 first_inst = ctx->skf->insns[0].code; int sp_off; /* Calculate the total offset for the stack pointer */ @@ -641,7 +627,7 @@ static void build_prologue(struct jit_ctx *ctx) emit_jit_reg_move(r_X, r_zero, ctx); /* Do not leak kernel data to userspace */ - if ((first_inst != (BPF_RET | BPF_K)) && !(is_load_to_a(first_inst))) + if (bpf_needs_clear_a(&ctx->skf->insns[0])) emit_jit_reg_move(r_A, r_zero, ctx); } diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c index dbbeccc3d714..a245cad4372a 100644 --- a/arch/mips/pci/pci-rt2880.c +++ b/arch/mips/pci/pci-rt2880.c @@ -221,7 +221,6 @@ int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) static int rt288x_pci_probe(struct platform_device *pdev) { void __iomem *io_map_base; - int i; rt2880_pci_base = ioremap_nocache(RT2880_PCI_BASE, PAGE_SIZE); diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c index 78b2ef49dbc7..9d293b3e9130 100644 --- a/arch/mips/pmcs-msp71xx/msp_setup.c +++ b/arch/mips/pmcs-msp71xx/msp_setup.c @@ -39,7 +39,6 @@ extern void msp_serial_setup(void); void msp7120_reset(void) { void *start, *end, *iptr; - register int i; /* Diasble all interrupts */ local_irq_disable(); diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c index db8f88b6a3af..6afa34346b81 100644 --- a/arch/mips/sni/reset.c +++ b/arch/mips/sni/reset.c @@ -26,7 +26,7 @@ static inline void kb_wait(void) /* XXX This ends up at the ARC firmware prompt ... */ void sni_machine_restart(char *command) { - int i, j; + int i; /* This does a normal via the keyboard controller like a PC. We can do that easier ... */ diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index ef5f348f386a..14568900fc1d 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -26,8 +26,8 @@ aflags-vdso := $(ccflags-vdso) \ # the comments on that file. # ifndef CONFIG_CPU_MIPSR6 - ifeq ($(call ld-ifversion, -gt, 22400000, y),) - $(warning MIPS VDSO requires binutils > 2.24) + ifeq ($(call ld-ifversion, -lt, 22500000, y),y) + $(warning MIPS VDSO requires binutils >= 2.25) obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO endif diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index dc1ea796fd60..2264f68f3c2f 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -435,6 +435,55 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs, int in_syscall) regs->gr[28]); } +/* + * Check how the syscall number gets loaded into %r20 within + * the delay branch in userspace and adjust as needed. + */ + +static void check_syscallno_in_delay_branch(struct pt_regs *regs) +{ + u32 opcode, source_reg; + u32 __user *uaddr; + int err; + + /* Usually we don't have to restore %r20 (the system call number) + * because it gets loaded in the delay slot of the branch external + * instruction via the ldi instruction. + * In some cases a register-to-register copy instruction might have + * been used instead, in which case we need to copy the syscall + * number into the source register before returning to userspace. + */ + + /* A syscall is just a branch, so all we have to do is fiddle the + * return pointer so that the ble instruction gets executed again. + */ + regs->gr[31] -= 8; /* delayed branching */ + + /* Get assembler opcode of code in delay branch */ + uaddr = (unsigned int *) ((regs->gr[31] & ~3) + 4); + err = get_user(opcode, uaddr); + if (err) + return; + + /* Check if delay branch uses "ldi int,%r20" */ + if ((opcode & 0xffff0000) == 0x34140000) + return; /* everything ok, just return */ + + /* Check if delay branch uses "nop" */ + if (opcode == INSN_NOP) + return; + + /* Check if delay branch uses "copy %rX,%r20" */ + if ((opcode & 0xffe0ffff) == 0x08000254) { + source_reg = (opcode >> 16) & 31; + regs->gr[source_reg] = regs->gr[20]; + return; + } + + pr_warn("syscall restart: %s (pid %d): unexpected opcode 0x%08x\n", + current->comm, task_pid_nr(current), opcode); +} + static inline void syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) { @@ -457,10 +506,7 @@ syscall_restart(struct pt_regs *regs, struct k_sigaction *ka) } /* fallthrough */ case -ERESTARTNOINTR: - /* A syscall is just a branch, so all - * we have to do is fiddle the return pointer. - */ - regs->gr[31] -= 8; /* delayed branching */ + check_syscallno_in_delay_branch(regs); break; } } @@ -510,15 +556,9 @@ insert_restart_trampoline(struct pt_regs *regs) } case -ERESTARTNOHAND: case -ERESTARTSYS: - case -ERESTARTNOINTR: { - /* Hooray for delayed branching. We don't - * have to restore %r20 (the system call - * number) because it gets loaded in the delay - * slot of the branch external instruction. - */ - regs->gr[31] -= 8; + case -ERESTARTNOINTR: + check_syscallno_in_delay_branch(regs); return; - } default: break; } diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index 0eca6efc0631..a7af5fb7b914 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -34,7 +34,7 @@ #define rmb() __asm__ __volatile__ ("sync" : : : "memory") #define wmb() __asm__ __volatile__ ("sync" : : : "memory") -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #ifdef __SUBARCH_HAS_LWSYNC # define SMPWMB LWSYNC diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index f2b0b1b0c72a..5654ece02c0d 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -370,16 +370,16 @@ COMPAT_SYS(execveat) PPC64ONLY(switch_endian) SYSCALL_SPU(userfaultfd) SYSCALL_SPU(membarrier) -SYSCALL(semop) -SYSCALL(semget) -COMPAT_SYS(semctl) -COMPAT_SYS(semtimedop) -COMPAT_SYS(msgsnd) -COMPAT_SYS(msgrcv) -SYSCALL(msgget) -COMPAT_SYS(msgctl) -COMPAT_SYS(shmat) -SYSCALL(shmdt) -SYSCALL(shmget) -COMPAT_SYS(shmctl) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) +SYSCALL(ni_syscall) SYSCALL(mlock2) diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 1effea5193d6..12a05652377a 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -388,18 +388,6 @@ #define __NR_switch_endian 363 #define __NR_userfaultfd 364 #define __NR_membarrier 365 -#define __NR_semop 366 -#define __NR_semget 367 -#define __NR_semctl 368 -#define __NR_semtimedop 369 -#define __NR_msgsnd 370 -#define __NR_msgrcv 371 -#define __NR_msgget 372 -#define __NR_msgctl 373 -#define __NR_shmat 374 -#define __NR_shmdt 375 -#define __NR_shmget 376 -#define __NR_shmctl 377 #define __NR_mlock2 378 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 54b45b73195f..a7352b59e6f9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -224,6 +224,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu) static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr) { + /* + * Check for illegal transactional state bit combination + * and if we find it, force the TS field to a safe state. + */ + if ((msr & MSR_TS_MASK) == MSR_TS_MASK) + msr &= ~MSR_TS_MASK; vcpu->arch.shregs.msr = msr; kvmppc_end_cede(vcpu); } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 04782164ee67..2d66a8446198 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -78,18 +78,9 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image, PPC_LI(r_X, 0); } - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* first instruction sets A register (or is RET 'constant') */ - break; - default: - /* make sure we dont leak kernel information to user */ + /* make sure we dont leak kernel information to user */ + if (bpf_needs_clear_a(&filter[0])) PPC_LI(r_A, 0); - } } static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index 0a00e2aed393..e505223b4ec5 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -83,7 +83,19 @@ static void opal_event_unmask(struct irq_data *d) set_bit(d->hwirq, &opal_event_irqchip.mask); opal_poll_events(&events); - opal_handle_events(be64_to_cpu(events)); + last_outstanding_events = be64_to_cpu(events); + + /* + * We can't just handle the events now with opal_handle_events(). + * If we did we would deadlock when opal_event_unmask() is called from + * handle_level_irq() with the irq descriptor lock held, because + * calling opal_handle_events() would call generic_handle_irq() and + * then handle_level_irq() which would try to take the descriptor lock + * again. Instead queue the events for later. + */ + if (last_outstanding_events & opal_event_irqchip.mask) + /* Need to retrigger the interrupt */ + irq_work_queue(&opal_event_irq_work); } static int opal_event_set_type(struct irq_data *d, unsigned int flow_type) diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 4296d55e88f3..57cffb80bc36 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -278,7 +278,7 @@ static void opal_handle_message(void) /* Sanity check */ if (type >= OPAL_MSG_TYPE_MAX) { - pr_warning("%s: Unknown message type: %u\n", __func__, type); + pr_warn_once("%s: Unknown message type: %u\n", __func__, type); return; } opal_message_do_notify(type, (void *)&msg); diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index d68e11e0df5e..7ffd0b19135c 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -36,7 +36,7 @@ #define smp_mb__before_atomic() smp_mb() #define smp_mb__after_atomic() smp_mb() -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #define smp_store_release(p, v) \ do { \ diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 8140d10c6785..6e72961608f0 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -1920,16 +1920,23 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr) } if (separator) ptr += sprintf(ptr, "%c", separator); + /* + * Use four '%' characters below because of the + * following two conversions: + * + * 1) sprintf: %%%%r -> %%r + * 2) printk : %%r -> %r + */ if (operand->flags & OPERAND_GPR) - ptr += sprintf(ptr, "%%r%i", value); + ptr += sprintf(ptr, "%%%%r%i", value); else if (operand->flags & OPERAND_FPR) - ptr += sprintf(ptr, "%%f%i", value); + ptr += sprintf(ptr, "%%%%f%i", value); else if (operand->flags & OPERAND_AR) - ptr += sprintf(ptr, "%%a%i", value); + ptr += sprintf(ptr, "%%%%a%i", value); else if (operand->flags & OPERAND_CR) - ptr += sprintf(ptr, "%%c%i", value); + ptr += sprintf(ptr, "%%%%c%i", value); else if (operand->flags & OPERAND_VR) - ptr += sprintf(ptr, "%%v%i", value); + ptr += sprintf(ptr, "%%%%v%i", value); else if (operand->flags & OPERAND_PCREL) ptr += sprintf(ptr, "%lx", (signed int) value + addr); diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h index 370ca1e71ffb..93310837c2df 100644 --- a/arch/sparc/include/asm/elf_64.h +++ b/arch/sparc/include/asm/elf_64.h @@ -95,6 +95,7 @@ * really available. So we simply advertise only "crypto" support. */ #define HWCAP_SPARC_CRYPTO 0x04000000 /* CRYPTO insns available */ +#define HWCAP_SPARC_ADI 0x08000000 /* ADI available */ #define CORE_DUMP_USE_REGSET diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index efe9479f837b..1c26d440d288 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -417,8 +417,13 @@ #define __NR_bpf 349 #define __NR_execveat 350 #define __NR_membarrier 351 +#define __NR_userfaultfd 352 +#define __NR_bind 353 +#define __NR_listen 354 +#define __NR_setsockopt 355 +#define __NR_mlock2 356 -#define NR_syscalls 352 +#define NR_syscalls 357 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index 3d61fcae7ee3..f2d30cab5b3f 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -946,6 +946,12 @@ ENTRY(__retl_one) mov 1, %o0 ENDPROC(__retl_one) +ENTRY(__retl_one_fp) + VISExitHalf + retl + mov 1, %o0 +ENDPROC(__retl_one_fp) + ENTRY(__ret_one_asi) wr %g0, ASI_AIUS, %asi ret @@ -958,6 +964,13 @@ ENTRY(__retl_one_asi) mov 1, %o0 ENDPROC(__retl_one_asi) +ENTRY(__retl_one_asi_fp) + wr %g0, ASI_AIUS, %asi + VISExitHalf + retl + mov 1, %o0 +ENDPROC(__retl_one_asi_fp) + ENTRY(__retl_o1) retl mov %o1, %o0 diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 3091267c5cc3..6596f66ce112 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1828,11 +1828,18 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry, void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { + u64 saved_fault_address = current_thread_info()->fault_address; + u8 saved_fault_code = get_thread_fault_code(); + mm_segment_t old_fs; + perf_callchain_store(entry, regs->tpc); if (!current->mm) return; + old_fs = get_fs(); + set_fs(USER_DS); + flushw_user(); pagefault_disable(); @@ -1843,4 +1850,8 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) perf_callchain_user_64(entry, regs); pagefault_enable(); + + set_fs(old_fs); + set_thread_fault_code(saved_fault_code); + current_thread_info()->fault_address = saved_fault_address; } diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index 39f0c662f4c8..d08bdaffdbfc 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -73,7 +73,13 @@ rtrap_nmi: ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 andn %l1, %l4, %l1 srl %l4, 20, %l4 ba,pt %xcc, rtrap_no_irq_enable - wrpr %l4, %pil + nop + /* Do not actually set the %pil here. We will do that + * below after we clear PSTATE_IE in the %pstate register. + * If we re-enable interrupts here, we can recurse down + * the hardirq stack potentially endlessly, causing a + * stack overflow. + */ .align 64 .globl rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index f7b261749383..f3185e2b028b 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -380,7 +380,8 @@ static const char *hwcaps[] = { */ "mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2", "ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau", - "ima", "cspare", "pause", "cbcond", + "ima", "cspare", "pause", "cbcond", NULL /*reserved for crypto */, + "adp", }; static const char *crypto_hwcaps[] = { @@ -396,7 +397,7 @@ void cpucap_info(struct seq_file *m) seq_puts(m, "cpucaps\t\t: "); for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (caps & bit) { + if (hwcaps[i] && (caps & bit)) { seq_printf(m, "%s%s", printed ? "," : "", hwcaps[i]); printed++; @@ -450,7 +451,7 @@ static void __init report_hwcaps(unsigned long caps) for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (caps & bit) + if (hwcaps[i] && (caps & bit)) report_one_hwcap(&printed, hwcaps[i]); } if (caps & HWCAP_SPARC_CRYPTO) @@ -485,7 +486,7 @@ static unsigned long __init mdesc_cpu_hwcap_list(void) for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { unsigned long bit = 1UL << i; - if (!strcmp(prop, hwcaps[i])) { + if (hwcaps[i] && !strcmp(prop, hwcaps[i])) { caps |= bit; break; } diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index cc23b62b6e38..e663b6c78de2 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -35,18 +35,18 @@ sys_call_table: /*80*/ .long sys_setgroups16, sys_getpgrp, sys_setgroups, sys_setitimer, sys_ftruncate64 /*85*/ .long sys_swapon, sys_getitimer, sys_setuid, sys_sethostname, sys_setgid /*90*/ .long sys_dup2, sys_setfsuid, sys_fcntl, sys_select, sys_setfsgid -/*95*/ .long sys_fsync, sys_setpriority, sys_nis_syscall, sys_nis_syscall, sys_nis_syscall +/*95*/ .long sys_fsync, sys_setpriority, sys_socket, sys_connect, sys_accept /*100*/ .long sys_getpriority, sys_rt_sigreturn, sys_rt_sigaction, sys_rt_sigprocmask, sys_rt_sigpending /*105*/ .long sys_rt_sigtimedwait, sys_rt_sigqueueinfo, sys_rt_sigsuspend, sys_setresuid, sys_getresuid -/*110*/ .long sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall -/*115*/ .long sys_getgroups, sys_gettimeofday, sys_getrusage, sys_nis_syscall, sys_getcwd +/*110*/ .long sys_setresgid, sys_getresgid, sys_setregid, sys_recvmsg, sys_sendmsg +/*115*/ .long sys_getgroups, sys_gettimeofday, sys_getrusage, sys_getsockopt, sys_getcwd /*120*/ .long sys_readv, sys_writev, sys_settimeofday, sys_fchown16, sys_fchmod -/*125*/ .long sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate -/*130*/ .long sys_ftruncate, sys_flock, sys_lstat64, sys_nis_syscall, sys_nis_syscall -/*135*/ .long sys_nis_syscall, sys_mkdir, sys_rmdir, sys_utimes, sys_stat64 -/*140*/ .long sys_sendfile64, sys_nis_syscall, sys_futex, sys_gettid, sys_getrlimit +/*125*/ .long sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, sys_truncate +/*130*/ .long sys_ftruncate, sys_flock, sys_lstat64, sys_sendto, sys_shutdown +/*135*/ .long sys_socketpair, sys_mkdir, sys_rmdir, sys_utimes, sys_stat64 +/*140*/ .long sys_sendfile64, sys_getpeername, sys_futex, sys_gettid, sys_getrlimit /*145*/ .long sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write -/*150*/ .long sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 +/*150*/ .long sys_getsockname, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 /*155*/ .long sys_fcntl64, sys_inotify_rm_watch, sys_statfs, sys_fstatfs, sys_oldumount /*160*/ .long sys_sched_setaffinity, sys_sched_getaffinity, sys_getdomainname, sys_setdomainname, sys_nis_syscall /*165*/ .long sys_quotactl, sys_set_tid_address, sys_mount, sys_ustat, sys_setxattr @@ -87,4 +87,5 @@ sys_call_table: /*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .long sys_execveat, sys_membarrier +/*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen +/*355*/ .long sys_setsockopt, sys_mlock2 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f229468a7479..1557121f4cdc 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -37,15 +37,15 @@ sys_call_table32: /*80*/ .word sys_setgroups16, sys_getpgrp, sys_setgroups, compat_sys_setitimer, sys32_ftruncate64 .word sys_swapon, compat_sys_getitimer, sys_setuid, sys_sethostname, sys_setgid /*90*/ .word sys_dup2, sys_setfsuid, compat_sys_fcntl, sys32_select, sys_setfsgid - .word sys_fsync, sys_setpriority, sys_nis_syscall, sys_nis_syscall, sys_nis_syscall + .word sys_fsync, sys_setpriority, sys_socket, sys_connect, sys_accept /*100*/ .word sys_getpriority, sys32_rt_sigreturn, compat_sys_rt_sigaction, compat_sys_rt_sigprocmask, compat_sys_rt_sigpending .word compat_sys_rt_sigtimedwait, compat_sys_rt_sigqueueinfo, compat_sys_rt_sigsuspend, sys_setresuid, sys_getresuid -/*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, sys_nis_syscall, sys_nis_syscall - .word sys_getgroups, compat_sys_gettimeofday, compat_sys_getrusage, sys_nis_syscall, sys_getcwd +/*110*/ .word sys_setresgid, sys_getresgid, sys_setregid, compat_sys_recvmsg, compat_sys_sendmsg + .word sys_getgroups, compat_sys_gettimeofday, compat_sys_getrusage, compat_sys_getsockopt, sys_getcwd /*120*/ .word compat_sys_readv, compat_sys_writev, compat_sys_settimeofday, sys_fchown16, sys_fchmod - .word sys_nis_syscall, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate -/*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_nis_syscall, sys_nis_syscall - .word sys_nis_syscall, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 + .word sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate +/*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_sendto, sys_shutdown + .word sys_socketpair, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 /*140*/ .word sys_sendfile64, sys_nis_syscall, sys32_futex, sys_gettid, compat_sys_getrlimit .word compat_sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write /*150*/ .word sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 @@ -88,7 +88,8 @@ sys_call_table32: .word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .word sys32_execveat, sys_membarrier +/*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen + .word compat_sys_setsockopt, sys_mlock2 #endif /* CONFIG_COMPAT */ @@ -168,4 +169,5 @@ sys_call_table: .word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf -/*350*/ .word sys64_execveat, sys_membarrier +/*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen + .word sys_setsockopt, sys_mlock2 diff --git a/arch/sparc/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S index 119ccb9a54f4..d5242b8c4f94 100644 --- a/arch/sparc/lib/NG2copy_from_user.S +++ b/arch/sparc/lib/NG2copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S index 7fe1ccefd9d0..4e962d993b10 100644 --- a/arch/sparc/lib/NG2copy_to_user.S +++ b/arch/sparc/lib/NG2copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S index 30eee6e8a81b..d5f585df2f3f 100644 --- a/arch/sparc/lib/NG2memcpy.S +++ b/arch/sparc/lib/NG2memcpy.S @@ -34,10 +34,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -134,40 +140,40 @@ fsrc2 %x6, %f12; \ fsrc2 %x7, %f14; #define FREG_LOAD_1(base, x0) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)) + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)) #define FREG_LOAD_2(base, x0, x1) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); #define FREG_LOAD_3(base, x0, x1, x2) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); #define FREG_LOAD_4(base, x0, x1, x2, x3) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); #define FREG_LOAD_5(base, x0, x1, x2, x3, x4) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); #define FREG_LOAD_6(base, x0, x1, x2, x3, x4, x5) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD(LOAD(ldd, base + 0x28, %x5)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); #define FREG_LOAD_7(base, x0, x1, x2, x3, x4, x5, x6) \ - EX_LD(LOAD(ldd, base + 0x00, %x0)); \ - EX_LD(LOAD(ldd, base + 0x08, %x1)); \ - EX_LD(LOAD(ldd, base + 0x10, %x2)); \ - EX_LD(LOAD(ldd, base + 0x18, %x3)); \ - EX_LD(LOAD(ldd, base + 0x20, %x4)); \ - EX_LD(LOAD(ldd, base + 0x28, %x5)); \ - EX_LD(LOAD(ldd, base + 0x30, %x6)); + EX_LD_FP(LOAD(ldd, base + 0x00, %x0)); \ + EX_LD_FP(LOAD(ldd, base + 0x08, %x1)); \ + EX_LD_FP(LOAD(ldd, base + 0x10, %x2)); \ + EX_LD_FP(LOAD(ldd, base + 0x18, %x3)); \ + EX_LD_FP(LOAD(ldd, base + 0x20, %x4)); \ + EX_LD_FP(LOAD(ldd, base + 0x28, %x5)); \ + EX_LD_FP(LOAD(ldd, base + 0x30, %x6)); .register %g2,#scratch .register %g3,#scratch @@ -275,11 +281,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop /* fall through for 0 < low bits < 8 */ 110: sub %o4, 64, %g2 - EX_LD(LOAD_BLK(%g2, %f0)) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) + EX_LD_FP(LOAD_BLK(%g2, %f0)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f14, f16) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_8(f16, f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -290,10 +296,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 120: sub %o4, 56, %g2 FREG_LOAD_7(%g2, f0, f2, f4, f6, f8, f10, f12) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f12, f16, f18) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_7(f18, f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -304,10 +310,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 130: sub %o4, 48, %g2 FREG_LOAD_6(%g2, f0, f2, f4, f6, f8, f10) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f10, f16, f18, f20) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_6(f20, f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -318,10 +324,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 140: sub %o4, 40, %g2 FREG_LOAD_5(%g2, f0, f2, f4, f6, f8) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f8, f16, f18, f20, f22) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_5(f22, f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -332,10 +338,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 150: sub %o4, 32, %g2 FREG_LOAD_4(%g2, f0, f2, f4, f6) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f6, f16, f18, f20, f22, f24) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_4(f24, f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -346,10 +352,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 160: sub %o4, 24, %g2 FREG_LOAD_3(%g2, f0, f2, f4) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f4, f16, f18, f20, f22, f24, f26) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_3(f26, f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -360,10 +366,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 170: sub %o4, 16, %g2 FREG_LOAD_2(%g2, f0, f2) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f2, f16, f18, f20, f22, f24, f26, f28) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_2(f28, f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -374,10 +380,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 180: sub %o4, 8, %g2 FREG_LOAD_1(%g2, f0) -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) - EX_LD(LOAD_BLK(%o4, %f16)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f16)) FREG_FROB(f0, f16, f18, f20, f22, f24, f26, f28, f30) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) FREG_MOVE_1(f30) subcc %g1, 64, %g1 add %o4, 64, %o4 @@ -387,10 +393,10 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ nop 190: -1: EX_ST(STORE_INIT(%g0, %o4 + %g3)) +1: EX_ST_FP(STORE_INIT(%g0, %o4 + %g3)) subcc %g1, 64, %g1 - EX_LD(LOAD_BLK(%o4, %f0)) - EX_ST(STORE_BLK(%f0, %o4 + %g3)) + EX_LD_FP(LOAD_BLK(%o4, %f0)) + EX_ST_FP(STORE_BLK(%f0, %o4 + %g3)) add %o4, 64, %o4 bne,pt %xcc, 1b LOAD(prefetch, %o4 + 64, #one_read) diff --git a/arch/sparc/lib/NG4copy_from_user.S b/arch/sparc/lib/NG4copy_from_user.S index fd9f903ffa32..2e8ee7ad07a9 100644 --- a/arch/sparc/lib/NG4copy_from_user.S +++ b/arch/sparc/lib/NG4copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG4copy_to_user.S b/arch/sparc/lib/NG4copy_to_user.S index 9744c4540a8d..be0bf4590df8 100644 --- a/arch/sparc/lib/NG4copy_to_user.S +++ b/arch/sparc/lib/NG4copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_asi_fp;\ + .text; \ + .align 4; + #ifndef ASI_AIUS #define ASI_AIUS 0x11 #endif diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S index 83aeeb1dffdb..8e13ee1f4454 100644 --- a/arch/sparc/lib/NG4memcpy.S +++ b/arch/sparc/lib/NG4memcpy.S @@ -48,10 +48,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -210,17 +216,17 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %o4, %o2 alignaddr %o1, %g0, %g1 add %o1, %o4, %o1 - EX_LD(LOAD(ldd, %g1 + 0x00, %f0)) -1: EX_LD(LOAD(ldd, %g1 + 0x08, %f2)) + EX_LD_FP(LOAD(ldd, %g1 + 0x00, %f0)) +1: EX_LD_FP(LOAD(ldd, %g1 + 0x08, %f2)) subcc %o4, 0x40, %o4 - EX_LD(LOAD(ldd, %g1 + 0x10, %f4)) - EX_LD(LOAD(ldd, %g1 + 0x18, %f6)) - EX_LD(LOAD(ldd, %g1 + 0x20, %f8)) - EX_LD(LOAD(ldd, %g1 + 0x28, %f10)) - EX_LD(LOAD(ldd, %g1 + 0x30, %f12)) - EX_LD(LOAD(ldd, %g1 + 0x38, %f14)) + EX_LD_FP(LOAD(ldd, %g1 + 0x10, %f4)) + EX_LD_FP(LOAD(ldd, %g1 + 0x18, %f6)) + EX_LD_FP(LOAD(ldd, %g1 + 0x20, %f8)) + EX_LD_FP(LOAD(ldd, %g1 + 0x28, %f10)) + EX_LD_FP(LOAD(ldd, %g1 + 0x30, %f12)) + EX_LD_FP(LOAD(ldd, %g1 + 0x38, %f14)) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %g1 + 0x40, %f0)) + EX_LD_FP(LOAD(ldd, %g1 + 0x40, %f0)) faligndata %f2, %f4, %f18 add %g1, 0x40, %g1 faligndata %f4, %f6, %f20 @@ -229,14 +235,14 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST(STORE(std, %f16, %o0 + 0x00)) - EX_ST(STORE(std, %f18, %o0 + 0x08)) - EX_ST(STORE(std, %f20, %o0 + 0x10)) - EX_ST(STORE(std, %f22, %o0 + 0x18)) - EX_ST(STORE(std, %f24, %o0 + 0x20)) - EX_ST(STORE(std, %f26, %o0 + 0x28)) - EX_ST(STORE(std, %f28, %o0 + 0x30)) - EX_ST(STORE(std, %f30, %o0 + 0x38)) + EX_ST_FP(STORE(std, %f16, %o0 + 0x00)) + EX_ST_FP(STORE(std, %f18, %o0 + 0x08)) + EX_ST_FP(STORE(std, %f20, %o0 + 0x10)) + EX_ST_FP(STORE(std, %f22, %o0 + 0x18)) + EX_ST_FP(STORE(std, %f24, %o0 + 0x20)) + EX_ST_FP(STORE(std, %f26, %o0 + 0x28)) + EX_ST_FP(STORE(std, %f28, %o0 + 0x30)) + EX_ST_FP(STORE(std, %f30, %o0 + 0x38)) add %o0, 0x40, %o0 bne,pt %icc, 1b LOAD(prefetch, %g1 + 0x200, #n_reads_strong) diff --git a/arch/sparc/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S index a6ae2ea04bf5..ecc5692fa2b4 100644 --- a/arch/sparc/lib/U1copy_from_user.S +++ b/arch/sparc/lib/U1copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME ___copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define LOAD_BLK(addr,dest) ldda [addr] ASI_BLK_AIUS, dest diff --git a/arch/sparc/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S index f4b970eeb485..9eea392e44d4 100644 --- a/arch/sparc/lib/U1copy_to_user.S +++ b/arch/sparc/lib/U1copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME ___copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S index b67142b7768e..3e6209ebb7d7 100644 --- a/arch/sparc/lib/U1memcpy.S +++ b/arch/sparc/lib/U1memcpy.S @@ -25,10 +25,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -73,8 +79,8 @@ faligndata %f8, %f9, %f62; #define MAIN_LOOP_CHUNK(src, dest, fdest, fsrc, len, jmptgt) \ - EX_LD(LOAD_BLK(%src, %fdest)); \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_LD_FP(LOAD_BLK(%src, %fdest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %src, 0x40, %src; \ subcc %len, 0x40, %len; \ be,pn %xcc, jmptgt; \ @@ -89,12 +95,12 @@ #define DO_SYNC membar #Sync; #define STORE_SYNC(dest, fsrc) \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %dest, 0x40, %dest; \ DO_SYNC #define STORE_JUMP(dest, fsrc, target) \ - EX_ST(STORE_BLK(%fsrc, %dest)); \ + EX_ST_FP(STORE_BLK(%fsrc, %dest)); \ add %dest, 0x40, %dest; \ ba,pt %xcc, target; \ nop; @@ -103,7 +109,7 @@ subcc %left, 8, %left;\ bl,pn %xcc, 95f; \ faligndata %f0, %f1, %f48; \ - EX_ST(STORE(std, %f48, %dest)); \ + EX_ST_FP(STORE(std, %f48, %dest)); \ add %dest, 8, %dest; #define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left) \ @@ -160,8 +166,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) + EX_ST_FP(STORE(stb, %o3, %o1 + %GLOBAL_SPARE)) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -172,20 +178,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD(LOAD(ldd, %o1, %f4)) -1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -208,13 +214,13 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ add %g1, %GLOBAL_SPARE, %g1 subcc %o2, %g3, %o2 - EX_LD(LOAD_BLK(%o1, %f0)) + EX_LD_FP(LOAD_BLK(%o1, %f0)) add %o1, 0x40, %o1 add %g1, %g3, %g1 - EX_LD(LOAD_BLK(%o1, %f16)) + EX_LD_FP(LOAD_BLK(%o1, %f16)) add %o1, 0x40, %o1 sub %GLOBAL_SPARE, 0x80, %GLOBAL_SPARE - EX_LD(LOAD_BLK(%o1, %f32)) + EX_LD_FP(LOAD_BLK(%o1, %f32)) add %o1, 0x40, %o1 /* There are 8 instances of the unrolled loop, @@ -426,28 +432,28 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ 62: FINISH_VISCHUNK(o0, f44, f46, g3) 63: UNEVEN_VISCHUNK_LAST(o0, f46, f0, g3) -93: EX_LD(LOAD(ldd, %o1, %f2)) +93: EX_LD_FP(LOAD(ldd, %o1, %f2)) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f0, %f2, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bl,pn %xcc, 95f add %o0, 8, %o0 - EX_LD(LOAD(ldd, %o1, %f0)) + EX_LD_FP(LOAD(ldd, %o1, %f0)) add %o1, 8, %o1 subcc %g3, 8, %g3 faligndata %f2, %f0, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bge,pt %xcc, 93b add %o0, 8, %o0 95: brz,pt %o2, 2f mov %g1, %o1 -1: EX_LD(LOAD(ldub, %o1, %o3)) +1: EX_LD_FP(LOAD(ldub, %o1, %o3)) add %o1, 1, %o1 subcc %o2, 1, %o2 - EX_ST(STORE(stb, %o3, %o0)) + EX_ST_FP(STORE(stb, %o3, %o0)) bne,pt %xcc, 1b add %o0, 1, %o0 diff --git a/arch/sparc/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S index b1acd1331c33..88ad73d86fe4 100644 --- a/arch/sparc/lib/U3copy_from_user.S +++ b/arch/sparc/lib/U3copy_from_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_LD_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME U3copy_from_user #define LOAD(type,addr,dest) type##a [addr] %asi, dest #define EX_RETVAL(x) 0 diff --git a/arch/sparc/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S index ef1e493afdfa..845139d75537 100644 --- a/arch/sparc/lib/U3copy_to_user.S +++ b/arch/sparc/lib/U3copy_to_user.S @@ -11,6 +11,14 @@ .text; \ .align 4; +#define EX_ST_FP(x) \ +98: x; \ + .section __ex_table,"a";\ + .align 4; \ + .word 98b, __retl_one_fp;\ + .text; \ + .align 4; + #define FUNC_NAME U3copy_to_user #define STORE(type,src,addr) type##a src, [addr] ASI_AIUS #define STORE_BLK(src,addr) stda src, [addr] ASI_BLK_AIUS diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S index 7cae9cc6a204..491ee69e4995 100644 --- a/arch/sparc/lib/U3memcpy.S +++ b/arch/sparc/lib/U3memcpy.S @@ -24,10 +24,16 @@ #ifndef EX_LD #define EX_LD(x) x #endif +#ifndef EX_LD_FP +#define EX_LD_FP(x) x +#endif #ifndef EX_ST #define EX_ST(x) x #endif +#ifndef EX_ST_FP +#define EX_ST_FP(x) x +#endif #ifndef EX_RETVAL #define EX_RETVAL(x) x @@ -120,8 +126,8 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ and %g2, 0x38, %g2 1: subcc %g1, 0x1, %g1 - EX_LD(LOAD(ldub, %o1 + 0x00, %o3)) - EX_ST(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) + EX_LD_FP(LOAD(ldub, %o1 + 0x00, %o3)) + EX_ST_FP(STORE(stb, %o3, %o1 + GLOBAL_SPARE)) bgu,pt %XCC, 1b add %o1, 0x1, %o1 @@ -132,20 +138,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ be,pt %icc, 3f alignaddr %o1, %g0, %o1 - EX_LD(LOAD(ldd, %o1, %f4)) -1: EX_LD(LOAD(ldd, %o1 + 0x8, %f6)) + EX_LD_FP(LOAD(ldd, %o1, %f4)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f6)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f4, %f6, %f0 - EX_ST(STORE(std, %f0, %o0)) + EX_ST_FP(STORE(std, %f0, %o0)) be,pn %icc, 3f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x8, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x8, %f4)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f6, %f4, %f2 - EX_ST(STORE(std, %f2, %o0)) + EX_ST_FP(STORE(std, %f2, %o0)) bne,pt %icc, 1b add %o0, 0x8, %o0 @@ -155,25 +161,25 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ LOAD(prefetch, %o1 + 0x080, #one_read) LOAD(prefetch, %o1 + 0x0c0, #one_read) LOAD(prefetch, %o1 + 0x100, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x000, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x000, %f0)) LOAD(prefetch, %o1 + 0x140, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) LOAD(prefetch, %o1 + 0x180, #one_read) - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) faligndata %f8, %f10, %f24 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f10, %f12, %f26 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) subcc GLOBAL_SPARE, 0x80, GLOBAL_SPARE add %o1, 0x40, %o1 @@ -184,26 +190,26 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ .align 64 1: - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) faligndata %f12, %f14, %f28 - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f0, %f2, %f16 add %o0, 0x40, %o0 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) subcc %o3, 0x01, %o3 faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f8, %f10, %f24 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) LOAD(prefetch, %o1 + 0x1c0, #one_read) faligndata %f10, %f12, %f26 bg,pt %XCC, 1b @@ -211,29 +217,29 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ /* Finally we copy the last full 64-byte block. */ 2: - EX_LD(LOAD(ldd, %o1 + 0x008, %f2)) + EX_LD_FP(LOAD(ldd, %o1 + 0x008, %f2)) faligndata %f12, %f14, %f28 - EX_LD(LOAD(ldd, %o1 + 0x010, %f4)) + EX_LD_FP(LOAD(ldd, %o1 + 0x010, %f4)) faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) - EX_LD(LOAD(ldd, %o1 + 0x018, %f6)) + EX_ST_FP(STORE_BLK(%f16, %o0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x018, %f6)) faligndata %f0, %f2, %f16 - EX_LD(LOAD(ldd, %o1 + 0x020, %f8)) + EX_LD_FP(LOAD(ldd, %o1 + 0x020, %f8)) faligndata %f2, %f4, %f18 - EX_LD(LOAD(ldd, %o1 + 0x028, %f10)) + EX_LD_FP(LOAD(ldd, %o1 + 0x028, %f10)) faligndata %f4, %f6, %f20 - EX_LD(LOAD(ldd, %o1 + 0x030, %f12)) + EX_LD_FP(LOAD(ldd, %o1 + 0x030, %f12)) faligndata %f6, %f8, %f22 - EX_LD(LOAD(ldd, %o1 + 0x038, %f14)) + EX_LD_FP(LOAD(ldd, %o1 + 0x038, %f14)) faligndata %f8, %f10, %f24 cmp %g1, 0 be,pt %XCC, 1f add %o0, 0x40, %o0 - EX_LD(LOAD(ldd, %o1 + 0x040, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x040, %f0)) 1: faligndata %f10, %f12, %f26 faligndata %f12, %f14, %f28 faligndata %f14, %f0, %f30 - EX_ST(STORE_BLK(%f16, %o0)) + EX_ST_FP(STORE_BLK(%f16, %o0)) add %o0, 0x40, %o0 add %o1, 0x40, %o1 membar #Sync @@ -253,20 +259,20 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ sub %o2, %g2, %o2 be,a,pt %XCC, 1f - EX_LD(LOAD(ldd, %o1 + 0x00, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x00, %f0)) -1: EX_LD(LOAD(ldd, %o1 + 0x08, %f2)) +1: EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f2)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f0, %f2, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) be,pn %XCC, 2f add %o0, 0x8, %o0 - EX_LD(LOAD(ldd, %o1 + 0x08, %f0)) + EX_LD_FP(LOAD(ldd, %o1 + 0x08, %f0)) add %o1, 0x8, %o1 subcc %g2, 0x8, %g2 faligndata %f2, %f0, %f8 - EX_ST(STORE(std, %f8, %o0)) + EX_ST_FP(STORE(std, %f8, %o0)) bne,pn %XCC, 1b add %o0, 0x8, %o0 diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c index 22564f5f2364..3e6e05a7c4c2 100644 --- a/arch/sparc/net/bpf_jit_comp.c +++ b/arch/sparc/net/bpf_jit_comp.c @@ -420,22 +420,9 @@ void bpf_jit_compile(struct bpf_prog *fp) } emit_reg_move(O7, r_saved_O7); - switch (filter[0].code) { - case BPF_RET | BPF_K: - case BPF_LD | BPF_W | BPF_LEN: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_B | BPF_ABS: - /* The first instruction sets the A register (or is - * a "RET 'constant'") - */ - break; - default: - /* Make sure we dont leak kernel information to the - * user. - */ + /* Make sure we dont leak kernel information to the user. */ + if (bpf_needs_clear_a(&filter[0])) emit_clear(r_A); /* A = 0 */ - } for (i = 0; i < flen; i++) { unsigned int K = filter[i].k; diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 106c21bd7f44..8ec7a4599c08 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -176,8 +176,6 @@ config NR_CPUS smaller kernel memory footprint results from using a smaller value on chips with fewer tiles. -if TILEGX - choice prompt "Kernel page size" default PAGE_SIZE_64KB @@ -188,8 +186,11 @@ choice connections, etc., it may be better to select 16KB, which uses memory more efficiently at some cost in TLB performance. - Note that this option is TILE-Gx specific; currently - TILEPro page size is set by rebuilding the hypervisor. + Note that for TILEPro, you must also rebuild the hypervisor + with a matching page size. + +config PAGE_SIZE_4KB + bool "4KB" if TILEPRO config PAGE_SIZE_16KB bool "16KB" @@ -199,8 +200,6 @@ config PAGE_SIZE_64KB endchoice -endif - source "kernel/Kconfig.hz" config KEXEC diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h index 0ccda3c425be..25d5899497be 100644 --- a/arch/tile/include/asm/cmpxchg.h +++ b/arch/tile/include/asm/cmpxchg.h @@ -127,8 +127,6 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n); #endif -#define tas(ptr) xchg((ptr), 1) - #endif /* __ASSEMBLY__ */ #endif /* _ASM_TILE_CMPXCHG_H */ diff --git a/arch/tile/include/asm/page.h b/arch/tile/include/asm/page.h index a213a8d84a95..8eca6a0e1762 100644 --- a/arch/tile/include/asm/page.h +++ b/arch/tile/include/asm/page.h @@ -20,15 +20,17 @@ #include <arch/chip.h> /* PAGE_SHIFT and HPAGE_SHIFT determine the page sizes. */ -#if defined(CONFIG_PAGE_SIZE_16KB) +#if defined(CONFIG_PAGE_SIZE_4KB) /* tilepro only */ +#define PAGE_SHIFT 12 +#define CTX_PAGE_FLAG HV_CTX_PG_SM_4K +#elif defined(CONFIG_PAGE_SIZE_16KB) #define PAGE_SHIFT 14 #define CTX_PAGE_FLAG HV_CTX_PG_SM_16K #elif defined(CONFIG_PAGE_SIZE_64KB) #define PAGE_SHIFT 16 #define CTX_PAGE_FLAG HV_CTX_PG_SM_64K #else -#define PAGE_SHIFT HV_LOG2_DEFAULT_PAGE_SIZE_SMALL -#define CTX_PAGE_FLAG 0 +#error Page size not specified in Kconfig #endif #define HPAGE_SHIFT HV_LOG2_DEFAULT_PAGE_SIZE_LARGE diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a2abc2fb6970..258965d56beb 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -698,6 +698,14 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. +config QUEUED_LOCK_STAT + bool "Paravirt queued spinlock statistics" + depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS + ---help--- + Enable the collection of statistical data on the slowpath + behavior of paravirtualized queued spinlocks and report + them on debugfs. + source "arch/x86/xen/Kconfig" config KVM_GUEST diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3c71dd947c7b..e32206e09868 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,5 @@ +#include <linux/jump_label.h> + /* x86 function call convention, 64-bit: @@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with #endif /* CONFIG_X86_64 */ +/* + * This does 'call enter_from_user_mode' unless we can avoid it based on + * kernel config or using the static jump infrastructure. + */ +.macro CALL_enter_from_user_mode +#ifdef CONFIG_CONTEXT_TRACKING +#ifdef HAVE_JUMP_LABEL + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 +#endif + call enter_from_user_mode +.Lafter_call_\@: +#endif +.endm diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index a89fdbc1f0be..03663740c866 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -421,7 +421,7 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) regs->ip = landing_pad; /* - * Fetch ECX from where the vDSO stashed it. + * Fetch EBP from where the vDSO stashed it. * * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! */ @@ -432,10 +432,10 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) * Micro-optimization: the pointer we're following is explicitly * 32 bits, so it can't be out of range. */ - __get_user(*(u32 *)®s->cx, + __get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #else - get_user(*(u32 *)®s->cx, + get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #endif ) { diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 3eb572ed3d7a..77d8c5112900 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -292,7 +292,7 @@ ENTRY(entry_SYSENTER_32) movl TSS_sysenter_sp0(%esp), %esp sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ecx /* pt_regs->cx */ + pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ @@ -308,8 +308,9 @@ sysenter_past_esp: movl %esp, %eax call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ @@ -328,7 +329,8 @@ sysenter_past_esp: * Return back to the vDSO, which will pop ecx and edx. * Don't bother with DS and ES (they already contain __USER_DS). */ - ENABLE_INTERRUPTS_SYSEXIT + sti + sysexit .pushsection .fixup, "ax" 2: movl $0, PT_FS(%esp) @@ -551,11 +553,6 @@ ENTRY(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) #endif ENTRY(overflow) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a55697d19824..9d34d3cfceb6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -520,9 +520,7 @@ END(irq_entries_start) */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode 1: /* @@ -1066,9 +1064,7 @@ ENTRY(error_entry) * (which can take locks). */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode ret .Lerror_entry_done: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index c3201830a85e..ff1c6d61f332 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -18,13 +18,6 @@ .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) -#endif - /* * 32-bit SYSENTER instruction entry. * @@ -63,7 +56,7 @@ ENTRY(entry_SYSENTER_compat) /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rcx /* pt_regs->sp */ + pushq %rbp /* pt_regs->sp (stashed in bp) */ /* * Push flags. This is nasty. First, interrupts are currently @@ -82,14 +75,14 @@ ENTRY(entry_SYSENTER_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 = 0 */ pushq %r8 /* pt_regs->r9 = 0 */ pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat) * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * - * NB.: sysenter_fix_flags is a label with the code under it moved + * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ testl $X86_EFLAGS_NT, EFLAGS(%rsp) - jnz sysenter_fix_flags -sysenter_flags_fixed: + jnz .Lsysenter_fix_flags +.Lsysenter_flags_fixed: /* * User mode is traced as though IRQs are on, and SYSENTER @@ -121,14 +114,15 @@ sysenter_flags_fixed: movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV jmp sysret32_from_system_call -sysenter_fix_flags: +.Lsysenter_fix_flags: pushq $X86_EFLAGS_FIXED popfq - jmp sysenter_flags_fixed + jmp .Lsysenter_flags_fixed ENDPROC(entry_SYSENTER_compat) /* @@ -178,7 +172,7 @@ ENTRY(entry_SYSCALL_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ xorq %r8,%r8 pushq %r8 /* pt_regs->r8 = 0 */ @@ -186,7 +180,7 @@ ENTRY(entry_SYSCALL_compat) pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -200,8 +194,9 @@ ENTRY(entry_SYSCALL_compat) movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSRET */ sysret32_from_system_call: @@ -236,7 +231,8 @@ sysret32_from_system_call: xorq %r9, %r9 xorq %r10, %r10 movq RSP-ORIG_RAX(%rsp), %rsp - USERGS_SYSRET32 + swapgs + sysretl END(entry_SYSCALL_compat) /* diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index ca94fa649251..8602f06c759f 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -17,8 +17,10 @@ #include <asm/vvar.h> #include <asm/unistd.h> #include <asm/msr.h> +#include <asm/pvclock.h> #include <linux/math64.h> #include <linux/time.h> +#include <linux/kernel.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void) } #endif -#ifndef BUILD_VDSO32 +#ifdef CONFIG_PARAVIRT_CLOCK +extern u8 pvclock_page + __attribute__((visibility("hidden"))); +#endif -#include <linux/kernel.h> -#include <asm/vsyscall.h> -#include <asm/fixmap.h> -#include <asm/pvclock.h> +#ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { @@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } -#ifdef CONFIG_PARAVIRT_CLOCK - -static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) -{ - const struct pvclock_vsyscall_time_info *pvti_base; - int idx = cpu / (PAGE_SIZE/PVTI_SIZE); - int offset = cpu % (PAGE_SIZE/PVTI_SIZE); - - BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); - - pvti_base = (struct pvclock_vsyscall_time_info *) - __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); - - return &pvti_base[offset]; -} - -static notrace cycle_t vread_pvclock(int *mode) -{ - const struct pvclock_vsyscall_time_info *pvti; - cycle_t ret; - u64 last; - u32 version; - u8 flags; - unsigned cpu, cpu1; - - - /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * - */ - do { - cpu = __getcpu() & VGETCPU_CPU_MASK; - /* TODO: We can put vcpu id into higher bits of pvti.version. - * This will save a couple of cycles by getting rid of - * __getcpu() calls (Gleb). - */ - - pvti = get_pvti(cpu); - - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); - - /* - * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. - */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); - - if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) - *mode = VCLOCK_NONE; - - /* refer to tsc.c read_tsc() comment for rationale */ - last = gtod->cycle_last; - - if (likely(ret >= last)) - return ret; - - return last; -} -#endif #else @@ -162,15 +95,77 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } +#endif + #ifdef CONFIG_PARAVIRT_CLOCK +static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void) +{ + return (const struct pvclock_vsyscall_time_info *)&pvclock_page; +} static notrace cycle_t vread_pvclock(int *mode) { - *mode = VCLOCK_NONE; - return 0; -} -#endif + const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; + cycle_t ret; + u64 tsc, pvti_tsc; + u64 last, delta, pvti_system_time; + u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift; + + /* + * Note: The kernel and hypervisor must guarantee that cpu ID + * number maps 1:1 to per-CPU pvclock time info. + * + * Because the hypervisor is entirely unaware of guest userspace + * preemption, it cannot guarantee that per-CPU pvclock time + * info is updated if the underlying CPU changes or that that + * version is increased whenever underlying CPU changes. + * + * On KVM, we are guaranteed that pvti updates for any vCPU are + * atomic as seen by *all* vCPUs. This is an even stronger + * guarantee than we get with a normal seqlock. + * + * On Xen, we don't appear to have that guarantee, but Xen still + * supplies a valid seqlock using the version field. + + * We only do pvclock vdso timing at all if + * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to + * mean that all vCPUs have matching pvti and that the TSC is + * synced, so we can just look at vCPU 0's pvti. + */ + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + + do { + version = pvti->version; + + smp_rmb(); + + tsc = rdtsc_ordered(); + pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; + pvti_tsc_shift = pvti->tsc_shift; + pvti_system_time = pvti->system_time; + pvti_tsc = pvti->tsc_timestamp; + + /* Make sure that the version double-check is last. */ + smp_rmb(); + } while (unlikely((version & 1) || version != pvti->version)); + + delta = tsc - pvti_tsc; + ret = pvti_system_time + + pvclock_scale_delta(delta, pvti_tsc_to_system_mul, + pvti_tsc_shift); + + /* refer to vread_tsc() comment for rationale */ + last = gtod->cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} #endif notrace static cycle_t vread_tsc(void) diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index de2c921025f5..4158acc17df0 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 2 * PAGE_SIZE; + vvar_start = . - 3 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -36,6 +36,7 @@ SECTIONS #undef EMIT_VVAR hpet_page = vvar_start + PAGE_SIZE; + pvclock_page = vvar_start + 2 * PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 785d9922b106..491020b2826d 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -73,6 +73,7 @@ enum { sym_vvar_start, sym_vvar_page, sym_hpet_page, + sym_pvclock_page, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -80,6 +81,7 @@ enum { const int special_pages[] = { sym_vvar_page, sym_hpet_page, + sym_pvclock_page, }; struct vdso_sym { @@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_start] = {"vvar_start", true}, [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, + [sym_pvclock_page] = {"pvclock_page", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 93bd8452383f..3a1d9297074b 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -1,5 +1,5 @@ /* - * Code for the vDSO. This version uses the old int $0x80 method. + * AT_SYSINFO entry point */ #include <asm/dwarf2.h> @@ -21,35 +21,67 @@ __kernel_vsyscall: /* * Reshuffle regs so that all of any of the entry instructions * will preserve enough state. + * + * A really nice entry sequence would be: + * pushl %edx + * pushl %ecx + * movl %esp, %ecx + * + * Unfortunately, naughty Android versions between July and December + * 2015 actually hardcode the traditional Linux SYSENTER entry + * sequence. That is severely broken for a number of reasons (ask + * anyone with an AMD CPU, for example). Nonetheless, we try to keep + * it working approximately as well as it ever worked. + * + * This link may eludicate some of the history: + * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 + * personally, I find it hard to understand what's going on there. + * + * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE. + * Execute an indirect call to the address in the AT_SYSINFO auxv + * entry. That is the ONLY correct way to make a fast 32-bit system + * call on Linux. (Open-coding int $0x80 is also fine, but it's + * slow.) */ + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 pushl %edx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET edx, 0 - pushl %ecx + pushl %ebp CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx, 0 - movl %esp, %ecx + CFI_REL_OFFSET ebp, 0 + + #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter" + #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall" #ifdef CONFIG_X86_64 /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */ - ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \ - "syscall", X86_FEATURE_SYSCALL32 + ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \ + SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32 #else - ALTERNATIVE "", "sysenter", X86_FEATURE_SEP + ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP #endif /* Enter using int $0x80 */ - movl (%esp), %ecx int $0x80 GLOBAL(int80_landing_pad) - /* Restore ECX and EDX in case they were clobbered. */ - popl %ecx - CFI_RESTORE ecx + /* + * Restore EDX and ECX in case they were clobbered. EBP is not + * clobbered (the kernel restores it), but it's cleaner and + * probably faster to pop it than to adjust ESP using addl. + */ + popl %ebp + CFI_RESTORE ebp CFI_ADJUST_CFA_OFFSET -4 popl %edx CFI_RESTORE edx CFI_ADJUST_CFA_OFFSET -4 + popl %ecx + CFI_RESTORE ecx + CFI_ADJUST_CFA_OFFSET -4 ret CFI_ENDPROC diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 64df47148160..b8f69e264ac4 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -12,6 +12,7 @@ #include <linux/random.h> #include <linux/elf.h> #include <linux/cpu.h> +#include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> @@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) .name = "[vvar]", .pages = no_pages, }; + struct pvclock_vsyscall_time_info *pvti; if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, @@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) } #endif + pvti = pvclock_pvti_cpu0_va(); + if (pvti && image->sym_pvclock_page) { + ret = remap_pfn_range(vma, + text_start + image->sym_pvclock_page, + __pa(pvti) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + } + up_fail: if (ret) current->mm->context.vdso = NULL; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316bf801a..c80f6b6f3da2 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -23,6 +23,11 @@ #define APIC_VERBOSE 1 #define APIC_DEBUG 2 +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + /* * Define the default level of output to be very little * This can be turned up by using apic=verbose for more @@ -303,6 +308,7 @@ struct apic { unsigned int *apicid); /* ipi */ + void (*send_IPI)(int cpu, int vector); void (*send_IPI_mask)(const struct cpumask *mask, int vector); void (*send_IPI_mask_allbutself)(const struct cpumask *mask, int vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index ae5fb83e6d91..3e8674288198 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index a11c30b77fb5..a984111135b1 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> //#include <asm/cmpxchg.h> /* An 64bit atomic type */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 43e144474043..7ad8c9464297 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -202,6 +202,7 @@ #define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index f80d70009ff8..6d7d0e52ed5a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,7 +19,6 @@ #include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> -#include <asm/pvclock.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> @@ -72,10 +71,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #endif -#ifdef CONFIG_PARAVIRT_CLOCK - PVCLOCK_FIXMAP_BEGIN, - PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, -#endif #endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 000000000000..e1a411786bf5 --- /dev/null +++ b/arch/x86/include/asm/intel_pt.h @@ -0,0 +1,10 @@ +#ifndef _ASM_X86_INTEL_PT_H +#define _ASM_X86_INTEL_PT_H + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +void cpu_emergency_stop_pt(void); +#else +static inline void cpu_emergency_stop_pt(void) {} +#endif + +#endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 615fa9061b57..cfc9a0d2d07c 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -119,6 +119,8 @@ static inline void native_apic_mem_write(APIC_ICR, cfg); } +extern void default_send_IPI_single(int cpu, int vector); +extern void default_send_IPI_single_phys(int cpu, int vector); extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 5daeca3d0f9e..adc54c12cbd1 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,12 +1,18 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef __ASSEMBLY__ - -#include <linux/stringify.h> -#include <linux/types.h> -#include <asm/nops.h> -#include <asm/asm.h> +#ifndef HAVE_JUMP_LABEL +/* + * For better or for worse, if jump labels (the gcc extension) are missing, + * then the entire static branch patching infrastructure is compiled out. + * If that happens, the code in here will malfunction. Raise a compiler + * error instead. + * + * In theory, jump labels and the static branch patching infrastructure + * could be decoupled to fix this. + */ +#error asm/jump_label.h included on a non-jump-label kernel +#endif #define JUMP_LABEL_NOP_SIZE 5 @@ -16,6 +22,14 @@ # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif +#include <asm/asm.h> +#include <asm/nops.h> + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> +#include <linux/types.h> + static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" @@ -59,5 +73,40 @@ struct jump_entry { jump_label_t key; }; -#endif /* __ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +.macro STATIC_JUMP_IF_TRUE target, key, def +.Lstatic_jump_\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + .popsection +.endm + +.macro STATIC_JUMP_IF_FALSE target, key, def +.Lstatic_jump_\@: + .if \def + .byte STATIC_KEY_INIT_NOP + .else + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + 1 + .popsection +.endm + +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 93724cc62177..eb4b09b41df5 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -1,7 +1,13 @@ #ifndef _ASM_X86_MSI_H #define _ASM_X86_MSI_H #include <asm/hw_irq.h> +#include <asm/irqdomain.h> typedef struct irq_alloc_info msi_alloc_info_t; +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg); + +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc); + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 000000000000..7567225747d8 --- /dev/null +++ b/arch/x86/include/asm/msr-trace.h @@ -0,0 +1,57 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM msr + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE msr-trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/ + +#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MSR_H + +#include <linux/tracepoint.h> + +/* + * Tracing for x86 model specific registers. Directly maps to the + * RDMSR/WRMSR instructions. + */ + +DECLARE_EVENT_CLASS(msr_trace_class, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed), + TP_STRUCT__entry( + __field( unsigned, msr ) + __field( u64, val ) + __field( int, failed ) + ), + TP_fast_assign( + __entry->msr = msr; + __entry->val = val; + __entry->failed = failed; + ), + TP_printk("%x, value %llx%s", + __entry->msr, + __entry->val, + __entry->failed ? " #GP" : "") +); + +DEFINE_EVENT(msr_trace_class, read_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, write_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, rdpmc, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +#endif /* _TRACE_MSR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 77d8b284e4a7..fedd6e6d1e43 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -57,11 +57,34 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif +#ifdef CONFIG_TRACEPOINTS +/* + * Be very careful with includes. This header is prone to include loops. + */ +#include <asm/atomic.h> +#include <linux/tracepoint-defs.h> + +extern struct tracepoint __tracepoint_read_msr; +extern struct tracepoint __tracepoint_write_msr; +extern struct tracepoint __tracepoint_rdpmc; +#define msr_tracepoint_active(t) static_key_false(&(t).key) +extern void do_trace_write_msr(unsigned msr, u64 val, int failed); +extern void do_trace_read_msr(unsigned msr, u64 val, int failed); +extern void do_trace_rdpmc(unsigned msr, u64 val, int failed); +#else +#define msr_tracepoint_active(t) false +static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {} +#endif + static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -78,6 +101,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) : "c" (msr), [fault] "i" (-EIO)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err); return EAX_EDX_VAL(val, low, high); } @@ -85,6 +110,8 @@ static inline void native_write_msr(unsigned int msr, unsigned low, unsigned high) { asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } /* Can be uninlined because referenced by paravirt */ @@ -102,6 +129,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr, : "c" (msr), "0" (low), "d" (high), [fault] "i" (-EIO) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } @@ -160,6 +189,8 @@ static inline unsigned long long native_read_pmc(int counter) DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); + if (msr_tracepoint_active(__tracepoint_rdpmc)) + do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cbbf41c0a328..f6192502149e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -19,6 +19,12 @@ static inline int paravirt_enabled(void) return pv_info.paravirt_enabled; } +static inline int paravirt_has_feature(unsigned int feature) +{ + WARN_ON_ONCE(!pv_info.paravirt_enabled); + return (pv_info.features & feature); +} + static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -896,23 +902,11 @@ extern void default_banner(void); call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) -#define USERGS_SYSRET32 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32)) - #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx - -#define ENABLE_INTERRUPTS_SYSEXIT \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) - - #else /* !CONFIG_X86_32 */ /* diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 0451503e1716..77db5616a473 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -70,9 +70,14 @@ struct pv_info { #endif int paravirt_enabled; + unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; +#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) +/* Supported features */ +#define PV_SUPPORTED_RTC (1<<0) + struct pv_init_ops { /* * Patch may replace one of the defined code sequences with @@ -157,15 +162,6 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); -#ifdef CONFIG_X86_32 - /* - * Atomically enable interrupts and return to userspace. This - * is only used in 32-bit kernels. 64-bit kernels use - * usergs_sysret32 instead. - */ - void (*irq_enable_sysexit)(void); -#endif - /* * Switch to usermode gs and return to 64-bit usermode using * sysret. Only used in 64-bit kernels to return to 64-bit @@ -174,14 +170,6 @@ struct pv_cpu_ops { */ void (*usergs_sysret64)(void); - /* - * Switch to usermode gs and return to 32-bit usermode using - * sysret. Used to return to 32-on-64 compat processes. - * Other usermode register state, including %esp, must already - * be restored. - */ - void (*usergs_sysret32)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 67522256c7ff..2d5a50cb61a2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -472,6 +472,7 @@ static inline unsigned long current_top_of_stack(void) #else #define __cpuid native_cpuid #define paravirt_enabled() 0 +#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5c08bc..fdcc04020636 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -4,6 +4,15 @@ #include <linux/clocksource.h> #include <asm/pvclock-abi.h> +#ifdef CONFIG_KVM_GUEST +extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); @@ -91,10 +100,5 @@ struct pvclock_vsyscall_time_info { } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) -#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size); -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index b002e711ba88..9f92c180ed2f 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -1,6 +1,65 @@ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H +/* + * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit + * registers. For i386, however, only 1 32-bit register needs to be saved + * and restored. So an optimized version of __pv_queued_spin_unlock() is + * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit. + */ +#ifdef CONFIG_64BIT + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); +#define __pv_queued_spin_unlock __pv_queued_spin_unlock +#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" +#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" + +/* + * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock + * which combines the registers saving trunk and the body of the following + * C code: + * + * void __pv_queued_spin_unlock(struct qspinlock *lock) + * { + * struct __qspinlock *l = (void *)lock; + * u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + * + * if (likely(lockval == _Q_LOCKED_VAL)) + * return; + * pv_queued_spin_unlock_slowpath(lock, lockval); + * } + * + * For x86-64, + * rdi = lock (first argument) + * rsi = lockval (second argument) + * rdx = internal variable (set to 0) + */ +asm (".pushsection .text;" + ".globl " PV_UNLOCK ";" + ".align 4,0x90;" + PV_UNLOCK ": " + "push %rdx;" + "mov $0x1,%eax;" + "xor %edx,%edx;" + "lock cmpxchg %dl,(%rdi);" + "cmp $0x1,%al;" + "jne .slowpath;" + "pop %rdx;" + "ret;" + ".slowpath: " + "push %rsi;" + "movzbl %al,%esi;" + "call " PV_UNLOCK_SLOWPATH ";" + "pop %rsi;" + "pop %rdx;" + "ret;" + ".size " PV_UNLOCK ", .-" PV_UNLOCK ";" + ".popsection"); + +#else /* CONFIG_64BIT */ + +extern void __pv_queued_spin_unlock(struct qspinlock *lock); PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); +#endif /* CONFIG_64BIT */ #endif diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a82c4f1b4d83..2cb1cc253d51 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,5 +25,6 @@ void __noreturn machine_real_restart(unsigned int type); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); +void run_crash_ipi_callback(struct pt_regs *regs); #endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 09b1b0ab94b7..660458af425d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -745,5 +745,14 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #undef __copy_from_user_overflow #undef __copy_to_user_overflow +/* + * We rely on the nested NMI work to allow atomic faults from the NMI path; the + * nested NMI paths are careful to preserve CR2. + * + * Caller must use pagefault_enable/disable, or run in interrupt context, + * and also do a uaccess_ok() check + */ +#define __copy_from_user_nmi __copy_from_user_inatomic + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 756de9190aec..deabaf9759b6 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -22,6 +22,7 @@ struct vdso_image { long sym_vvar_page; long sym_hpet_page; + long sym_pvclock_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 03429da2fa80..2184943341bf 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -16,7 +16,7 @@ struct mce { __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ __u8 severity; - __u8 usable_addr; + __u8 pad; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2f69e3b184f6..8a5cddac7d44 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -82,6 +82,12 @@ physid_mask_t phys_cpu_present_map; static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; /* + * This variable controls which CPUs receive external NMIs. By default, + * external NMIs are delivered only to the BSP. + */ +static int apic_extnmi = APIC_EXTNMI_BSP; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -1161,6 +1167,8 @@ void __init init_bsp_APIC(void) value = APIC_DM_NMI; if (!lapic_is_integrated()) /* 82489DX */ value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; apic_write(APIC_LVT1, value); } @@ -1378,9 +1386,11 @@ void setup_local_APIC(void) apic_write(APIC_LVT0, value); /* - * only the BP should see the LINT1 NMI signal, obviously. + * Only the BSP sees the LINT1 NMI signal by default. This can be + * modified by apic_extnmi= boot option. */ - if (!cpu) + if ((!cpu && apic_extnmi != APIC_EXTNMI_NONE) || + apic_extnmi == APIC_EXTNMI_ALL) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; @@ -2270,6 +2280,7 @@ static struct { unsigned int apic_tmict; unsigned int apic_tdcr; unsigned int apic_thmr; + unsigned int apic_cmci; } apic_pm_state; static int lapic_suspend(void) @@ -2299,6 +2310,10 @@ static int lapic_suspend(void) if (maxlvt >= 5) apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_pm_state.apic_cmci = apic_read(APIC_LVTCMCI); +#endif local_irq_save(flags); disable_local_APIC(); @@ -2355,10 +2370,14 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_INTEL) +#ifdef CONFIG_X86_THERMAL_VECTOR if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_write(APIC_LVTCMCI, apic_pm_state.apic_cmci); +#endif if (maxlvt >= 4) apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc); apic_write(APIC_LVTT, apic_pm_state.apic_lvtt); @@ -2548,3 +2567,23 @@ static int __init apic_set_disabled_cpu_apicid(char *arg) return 0; } early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); + +static int __init apic_set_extnmi(char *arg) +{ + if (!arg) + return -EINVAL; + + if (!strncmp("all", arg, 3)) + apic_extnmi = APIC_EXTNMI_ALL; + else if (!strncmp("none", arg, 4)) + apic_extnmi = APIC_EXTNMI_NONE; + else if (!strncmp("bsp", arg, 3)) + apic_extnmi = APIC_EXTNMI_BSP; + else { + pr_warn("Unknown external NMI delivery mode `%s' ignored\n", arg); + return -EINVAL; + } + + return 0; +} +early_param("apic_extnmi", apic_set_extnmi); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f92ab36979a2..9968f30cca3e 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -185,6 +185,7 @@ static struct apic apic_flat = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, .send_IPI_allbutself = flat_send_IPI_allbutself, @@ -230,17 +231,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) -{ - default_send_IPI_mask_sequence_phys(cpumask, vector); -} - -static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask, - int vector) -{ - default_send_IPI_mask_allbutself_phys(cpumask, vector); -} - static void physflat_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -248,7 +238,7 @@ static void physflat_send_IPI_allbutself(int vector) static void physflat_send_IPI_all(int vector) { - physflat_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int physflat_probe(void) @@ -292,8 +282,9 @@ static struct apic apic_physflat = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = physflat_send_IPI_mask, - .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, + .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys, .send_IPI_allbutself = physflat_send_IPI_allbutself, .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 0d96749cfcac..331a7a07c48f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -30,6 +30,7 @@ #include <asm/e820.h> static void noop_init_apic_ldr(void) { } +static void noop_send_IPI(int cpu, int vector) { } static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_allbutself(int vector) { } @@ -144,6 +145,7 @@ struct apic apic_noop = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, .send_IPI_allbutself = noop_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 38dd5efdd04c..c80c02c6ec49 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -193,20 +193,17 @@ static int __init numachip_system_init(void) case 1: init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); numachip_apic_icr_write = numachip1_apic_icr_write; - x86_init.pci.arch_init = pci_numachip_init; break; case 2: init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); numachip_apic_icr_write = numachip2_apic_icr_write; - - /* Use MCFG config cycles rather than locked CF8 cycles */ - raw_pci_ops = &pci_mmcfg; break; default: return 0; } x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; return 0; } @@ -276,6 +273,7 @@ static const struct apic apic_numachip1 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, @@ -327,6 +325,7 @@ static const struct apic apic_numachip2 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 971cf8875939..cf9bd896c12d 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -96,11 +96,6 @@ static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) -{ - default_send_IPI_mask_sequence_phys(mask, vector); -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -108,7 +103,7 @@ static void bigsmp_send_IPI_allbutself(int vector) static void bigsmp_send_IPI_all(int vector) { - bigsmp_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int dmi_bigsmp; /* can be set by dmi scanners */ @@ -180,7 +175,8 @@ static struct apic apic_bigsmp = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = bigsmp_send_IPI_mask, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, .send_IPI_mask_allbutself = NULL, .send_IPI_allbutself = bigsmp_send_IPI_allbutself, .send_IPI_all = bigsmp_send_IPI_all, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 62071569bd50..eb45fc9b6124 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -18,6 +18,16 @@ #include <asm/proto.h> #include <asm/ipi.h> +void default_send_IPI_single_phys(int cpu, int vector) +{ + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu), + vector, APIC_DEST_PHYSICAL); + local_irq_restore(flags); +} + void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector) { unsigned long query_cpu; @@ -55,6 +65,14 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, local_irq_restore(flags); } +/* + * Helper function for APICs which insist on cpumasks + */ +void default_send_IPI_single(int cpu, int vector) +{ + apic->send_IPI_mask(cpumask_of(cpu), vector); +} + #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 5f1feb6854af..ade25320df96 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -96,8 +96,8 @@ static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, return arg->msi_hwirq; } -static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { struct pci_dev *pdev = to_pci_dev(dev); struct msi_desc *desc = first_pci_msi_entry(pdev); @@ -113,11 +113,13 @@ static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, return 0; } +EXPORT_SYMBOL_GPL(pci_msi_prepare); -static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); } +EXPORT_SYMBOL_GPL(pci_msi_set_desc); static struct msi_domain_ops pci_msi_domain_ops = { .get_hwirq = pci_msi_get_hwirq, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7694ae6c1199..f316e34abb42 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,6 +105,7 @@ static struct apic apic_default = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, .send_IPI_allbutself = default_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59c8f25..908cb37da171 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -29,6 +29,7 @@ struct apic_chip_data { }; struct irq_domain *x86_vector_domain; +EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); static cpumask_var_t vector_cpumask; static struct irq_chip lapic_controller; @@ -66,6 +67,7 @@ struct irq_cfg *irqd_cfg(struct irq_data *irq_data) return data ? &data->cfg : NULL; } +EXPORT_SYMBOL_GPL(irqd_cfg); struct irq_cfg *irq_cfg(unsigned int irq) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cc8311c4d298..aca8b75c1552 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -23,6 +23,14 @@ static inline u32 x2apic_cluster(int cpu) return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -266,6 +274,7 @@ static struct apic apic_x2apic_cluster = { .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 662e9150ea6f..a1242e2c12e6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -36,6 +36,14 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -122,6 +130,7 @@ static struct apic apic_x2apic_phys = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 4a139465f1d4..d760c6bb37b5 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -406,6 +406,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, .send_IPI_allbutself = uv_send_IPI_allbutself, diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 439df975bc7a..84a7524b202c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -65,9 +65,6 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); -#ifdef CONFIG_X86_32 - OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); -#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d8f42f902a0f..f2edafb5f24e 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,7 +23,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); - OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c5b0d562dbf5..a006f4cd792b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -114,7 +114,6 @@ static struct work_struct mce_work; static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); -static int mce_usable_address(struct mce *m); /* * CPU/chipset specific EDAC code can register a notifier call here to print @@ -475,6 +474,28 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&mce_irq_work); } +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granuality for now. + */ +static int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + return 1; +} + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -484,7 +505,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (!mce) return NOTIFY_DONE; - if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) { + if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; memory_failure(pfn, MCE_VECTOR, 0); } @@ -522,10 +543,10 @@ static bool memory_error(struct mce *m) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor == X86_VENDOR_AMD) { - /* - * coming soon - */ - return false; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); } else if (c->x86_vendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -567,7 +588,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); */ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { - bool error_logged = false; + bool error_seen = false; struct mce m; int severity; int i; @@ -601,6 +622,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; + error_seen = true; + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) @@ -608,27 +631,24 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* - * In the cases where we don't have a valid address after all, - * do not add it into the ring buffer. - */ - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { - if (m.status & MCI_STATUS_ADDRV) { + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) + if (m.status & MCI_STATUS_ADDRV) m.severity = severity; - m.usable_addr = mce_usable_address(&m); - - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } - } /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { - error_logged = true; + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); + else if (mce_usable_address(&m)) { + /* + * Although we skipped logging this, we still want + * to take action. Add to the pool so the registered + * notifiers will see it. + */ + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } /* @@ -644,7 +664,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) sync_core(); - return error_logged; + return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -931,23 +951,6 @@ reset: return ret; } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. - */ -static int mce_usable_address(struct mce *m) -{ - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) - return 0; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; - return 1; -} - static void mce_clear_state(unsigned long *toclear) { int i; @@ -999,6 +1002,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) int flags = MF_ACTION_REQUIRED; int lmce = 0; + /* If this CPU is offline, just bail out. */ + if (cpu_is_offline(smp_processor_id())) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return; + } + } + ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1089,7 +1103,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* assuming valid severity level != 0 */ m.severity = severity; - m.usable_addr = mce_usable_address(&m); mce_log(&m); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7c97df..1b443db2db50 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -482,6 +482,9 @@ int x86_pmu_hw_config(struct perf_event *event) /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; + + if (x86_pmu.pebs_prec_dist) + precise++; } if (event->attr.precise_ip > precise) @@ -1531,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs) { struct device_attribute *d; struct perf_pmu_events_attr *pmu_attr; + int offset = 0; int i, j; for (i = 0; attrs[i]; i++) { @@ -1539,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs) /* str trumps id */ if (pmu_attr->event_str) continue; - if (x86_pmu.event_map(i)) + if (x86_pmu.event_map(i + offset)) continue; for (j = i; attrs[j]; j++) @@ -1547,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs) /* Check the shifted attr. */ i--; + + /* + * event_map() is index based, the attrs array is organized + * by increasing event index. If we shift the events, then + * we need to compensate for the event_map(), otherwise + * we are looking up the wrong event in the map + */ + offset++; } } @@ -2250,12 +2262,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 8)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); if (bytes != 0) break; @@ -2265,6 +2284,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } + pagefault_enable(); return 1; } #else @@ -2302,12 +2322,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) if (perf_callchain_user32(regs, entry)) return; + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 16)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); if (bytes != 0) break; @@ -2315,8 +2342,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) break; perf_callchain_store(entry, frame.return_address); - fp = frame.next_frame; + fp = (void __user *)frame.next_frame; } + pagefault_enable(); } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index d0e35ebb2adb..7bb61e32fb29 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -14,17 +14,7 @@ #include <linux/perf_event.h> -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - unsigned int _msr = (msr); \ - u64 _val = (val); \ - trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ - (unsigned long long)(_val)); \ - native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ -} while (0) -#endif +/* To enable MSR tracing please use the generic trace points. */ /* * | NHM/WSM | SNB | @@ -318,6 +308,10 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Constraint on specific umask bit only + event */ +#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c)) + /* Like UEVENT_CONSTRAINT, but match flags too */ #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) @@ -589,7 +583,8 @@ struct x86_pmu { bts_active :1, pebs :1, pebs_active :1, - pebs_broken :1; + pebs_broken :1, + pebs_prec_dist :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; @@ -907,6 +902,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_lbr_init_knl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 3ea177cb7366..58610539b048 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -18,7 +18,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ + [ C(RESULT_ACCESS) ] = 0, [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a430021e46..a667078a5180 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -185,6 +185,14 @@ struct event_constraint intel_skl_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_knl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, + MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, + MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1), + EVENT_EXTRA_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), @@ -255,7 +263,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -1457,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ +#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ +#define KNL_MCDRAM_LOCAL BIT_ULL(21) +#define KNL_MCDRAM_FAR BIT_ULL(22) +#define KNL_DDR_LOCAL BIT_ULL(23) +#define KNL_DDR_FAR BIT_ULL(24) +#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \ + KNL_DDR_LOCAL | KNL_DDR_FAR) +#define KNL_L2_READ SLM_DMND_READ +#define KNL_L2_WRITE SLM_DMND_WRITE +#define KNL_L2_PREFETCH SLM_DMND_PREFETCH +#define KNL_L2_ACCESS SLM_LLC_ACCESS +#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \ + KNL_DRAM_ANY | SNB_SNP_ANY | \ + SNB_NON_DRAM) + +static __initconst const u64 knl_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS, + }, + }, +}; + /* * Use from PMIs where the LBRs are already disabled. */ @@ -2475,6 +2519,44 @@ static void intel_pebs_aliases_snb(struct perf_event *event) } } +static void intel_pebs_aliases_precdist(struct perf_event *event) +{ + if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.PREC_DIST + * (0x01c0), which is a PEBS capable event, to get the same + * count. + * + * The PREC_DIST event has special support to minimize sample + * shadowing effects. One drawback is that it can be + * only programmed on counter 1, but that seems like an + * acceptable trade off. + */ + u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16); + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } +} + +static void intel_pebs_aliases_ivb(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_snb(event); + return intel_pebs_aliases_precdist(event); +} + +static void intel_pebs_aliases_skl(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_core2(event); + return intel_pebs_aliases_precdist(event); +} + static unsigned long intel_pmu_free_running_flags(struct perf_event *event) { unsigned long flags = x86_pmu.free_running_flags; @@ -3332,6 +3414,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_gen_event_constraints; x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); break; @@ -3431,7 +3514,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; if (boot_cpu_data.x86_model == 62) x86_pmu.extra_regs = intel_snbep_extra_regs; else @@ -3464,7 +3548,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3499,7 +3584,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_bdw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3511,6 +3597,24 @@ __init int intel_pmu_init(void) pr_cont("Broadwell events, "); break; + case 87: /* Knights Landing Xeon Phi */ + memcpy(hw_cache_event_ids, + slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, + knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_knl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_knl_extra_regs; + + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + pr_cont("Knights Landing events, "); + break; + case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ x86_pmu.late_ack = true; @@ -3521,7 +3625,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_skl_event_constraints; x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints; x86_pmu.extra_regs = intel_skl_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_skl; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c7755548..10602f0a438f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -620,6 +620,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -686,6 +688,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -700,6 +704,8 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -718,9 +724,10 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ @@ -1101,6 +1108,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1186,7 +1200,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; @@ -1230,12 +1244,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) pebs_status = p->status & cpuc->pebs_enabled; pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + /* + * On some CPUs the PEBS status can be zero when PEBS is + * racing with clearing of GLOBAL_STATUS. + * + * Normally we would drop that record, but in the + * case when there is only a single active PEBS event + * we can assume it's for that event. + */ + if (!pebs_status && cpuc->pebs_enabled && + !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) + pebs_status = cpuc->pebs_enabled; + bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); - if (WARN(bit >= x86_pmu.max_pebs_events, - "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx", - (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled, - *(unsigned long long *)cpuc->active_mask)) + if (bit >= x86_pmu.max_pebs_events) continue; /* diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 659f01e165d5..653f88d25987 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -42,6 +42,13 @@ static enum { #define LBR_FAR_BIT 8 /* do not capture far branches */ #define LBR_CALL_STACK_BIT 9 /* enable call stack */ +/* + * Following bit only exists in Linux; we mask it out before writing it to + * the actual MSR. But it helps the constraint perf code to understand + * that this is a separate configuration. + */ +#define LBR_NO_INFO_BIT 63 /* don't read LBR_INFO. */ + #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) #define LBR_JCC (1 << LBR_JCC_BIT) @@ -52,6 +59,7 @@ static enum { #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) #define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) +#define LBR_NO_INFO (1ULL << LBR_NO_INFO_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -152,8 +160,8 @@ static void __intel_pmu_lbr_enable(bool pmi) * did not change. */ if (cpuc->lbr_sel) - lbr_select = cpuc->lbr_sel->config; - if (!pmi) + lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask; + if (!pmi && cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, lbr_select); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); @@ -422,6 +430,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { + bool need_info = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -429,8 +438,11 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int out = 0; int num = x86_pmu.lbr_nr; - if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + if (cpuc->lbr_sel) { + need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + } for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; @@ -442,7 +454,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_INFO) { + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info); @@ -590,6 +602,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (v != LBR_IGN) mask |= v; } + reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; @@ -600,6 +613,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) */ reg->config = mask ^ x86_pmu.lbr_sel_mask; + if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && + (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && + (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + reg->config |= LBR_NO_INFO; + return 0; } @@ -1028,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void) */ pr_cont("8-deep LBR, "); } + +/* Knights Landing */ +void intel_pmu_lbr_init_knl(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + pr_cont("8-deep LBR, "); +} diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 868e1194337f..c0bbd1033b7c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -27,6 +27,7 @@ #include <asm/perf_event.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/intel_pt.h> #include "perf_event.h" #include "intel_pt.h" @@ -1122,6 +1123,14 @@ static int pt_event_init(struct perf_event *event) return 0; } +void cpu_emergency_stop_pt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + if (pt->handle.event) + pt_event_stop(pt->handle.event, PERF_EF_UPDATE); +} + static __init int pt_init(void) { int ret, cpu, prior_warn = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index ed446bdcbf31..24a351ad628d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -63,7 +63,7 @@ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ #define NR_RAPL_DOMAINS 0x4 -static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -109,11 +109,11 @@ static struct kobj_attribute format_attr_##_var = \ #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ -#define RAPL_EVENT_ATTR_STR(_name, v, str) \ -static struct perf_pmu_events_attr event_attr_##v = { \ - .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \ - .id = 0, \ - .event_str = str, \ +#define RAPL_EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ }; struct rapl_pmu { @@ -405,19 +405,6 @@ static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; -static ssize_t rapl_sysfs_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct perf_pmu_events_attr *pmu_attr = \ - container_of(attr, struct perf_pmu_events_attr, attr); - - if (pmu_attr->event_str) - return sprintf(page, "%s", pmu_attr->event_str); - - return 0; -} - RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 61215a69b03d..f97f8075bf04 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -884,6 +884,15 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * each box has a different function id. */ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + /* Knights Landing uses a common PCI device ID for multiple instances of + * an uncore PMU device type. There is only one entry per device type in + * the knl_uncore_pci_ids table inspite of multiple devices present for + * some device types. Hence PCI device idx would be 0 for all devices. + * So increment pmu pointer to point to an unused array element. + */ + if (boot_cpu_data.x86_model == 87) + while (pmu->func_id >= 0) + pmu++; if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else @@ -966,6 +975,7 @@ static int __init uncore_pci_init(void) case 63: /* Haswell-EP */ ret = hswep_uncore_pci_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ ret = bdx_uncore_pci_init(); break; @@ -982,6 +992,9 @@ static int __init uncore_pci_init(void) case 61: /* Broadwell */ ret = bdw_uncore_pci_init(); break; + case 87: /* Knights Landing */ + ret = knl_uncore_pci_init(); + break; default: return 0; } @@ -1287,9 +1300,13 @@ static int __init uncore_cpu_init(void) case 63: /* Haswell-EP */ hswep_uncore_cpu_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ bdx_uncore_cpu_init(); break; + case 87: /* Knights Landing */ + knl_uncore_cpu_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 2f0a4a98e16b..07aa2d6bd710 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -338,6 +338,7 @@ int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); +int snb_pci2phy_map_init(int devid); /* perf_event_intel_uncore_snbep.c */ int snbep_uncore_pci_init(void); @@ -348,6 +349,8 @@ int hswep_uncore_pci_init(void); void hswep_uncore_cpu_init(void); int bdx_uncore_pci_init(void); void bdx_uncore_cpu_init(void); +int knl_uncore_pci_init(void); +void knl_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 845256158a10..0b934820fafd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -417,7 +417,7 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags) } } -static int snb_pci2phy_map_init(int devid) +int snb_pci2phy_map_init(int devid) { struct pci_dev *dev = NULL; struct pci2phy_map *map; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index f0f4fcba252e..33acb884ccf1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -209,31 +209,98 @@ #define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 #define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 +/* KNL Ubox */ +#define KNL_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) +/* KNL CHA */ +#define KNL_CHA_MSR_OFFSET 0xc +#define KNL_CHA_MSR_PMON_CTL_QOR (1 << 16) +#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +#define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff +#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) +#define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) + +/* KNL EDC/MC UCLK */ +#define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 +#define KNL_UCLK_MSR_PMON_CTL0 0x420 +#define KNL_UCLK_MSR_PMON_BOX_CTL 0x430 +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW 0x44c +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL 0x454 +#define KNL_PMON_FIXED_CTL_EN 0x1 + +/* KNL EDC */ +#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW 0xa00 +#define KNL_EDC0_ECLK_MSR_PMON_CTL0 0xa20 +#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL 0xa30 +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW 0xa3c +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL 0xa44 + +/* KNL MC */ +#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW 0xb00 +#define KNL_MC0_CH0_MSR_PMON_CTL0 0xb20 +#define KNL_MC0_CH0_MSR_PMON_BOX_CTL 0xb30 +#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW 0xb3c +#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL 0xb44 + +/* KNL IRP */ +#define KNL_IRP_PCI_PMON_BOX_CTL 0xf0 +#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +/* KNL PCU */ +#define KNL_PCU_PMON_CTL_EV_SEL_MASK 0x0000007f +#define KNL_PCU_PMON_CTL_USE_OCC_CTR (1 << 7) +#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK 0x3f000000 +#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK \ + (KNL_PCU_PMON_CTL_EV_SEL_MASK | \ + KNL_PCU_PMON_CTL_USE_OCC_CTR | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_CBO_PMON_CTL_TID_EN | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29"); DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20"); +DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); @@ -315,8 +382,9 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); + pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT); } static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) @@ -1728,6 +1796,419 @@ int ivbep_uncore_pci_init(void) } /* end of IvyTown uncore support */ +/* KNL uncore support */ +static struct attribute *knl_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute_group knl_uncore_ubox_format_group = { + .name = "format", + .attrs = knl_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = KNL_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_ubox_format_group, +}; + +static struct attribute *knl_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid4.attr, + &format_attr_filter_link3.attr, + &format_attr_filter_state4.attr, + &format_attr_filter_local.attr, + &format_attr_filter_all_op.attr, + &format_attr_filter_nnm.attr, + &format_attr_filter_opc3.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group knl_uncore_cha_format_group = { + .name = "format", + .attrs = knl_uncore_cha_formats_attr, +}; + +static struct event_constraint knl_uncore_cha_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg knl_uncore_cha_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4), + EVENT_EXTRA_END +}; + +static u64 knl_cha_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x4) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP; + return mask; +} + +static struct event_constraint * +knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask); +} + +static int knl_cha_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = knl_uncore_cha_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event); + +static struct intel_uncore_ops knl_uncore_cha_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = knl_cha_hw_config, + .get_constraint = knl_cha_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type knl_uncore_cha = { + .name = "cha", + .num_counters = 4, + .num_boxes = 38, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = KNL_CHA_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = KNL_CHA_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = knl_uncore_cha_constraints, + .ops = &knl_uncore_cha_ops, + .format_group = &knl_uncore_cha_format_group, +}; + +static struct attribute *knl_uncore_pcu_formats_attr[] = { + &format_attr_event2.attr, + &format_attr_use_occ_ctr.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh6.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + NULL, +}; + +static struct attribute_group knl_uncore_pcu_format_group = { + .name = "format", + .attrs = knl_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = KNL_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *knl_msr_uncores[] = { + &knl_uncore_ubox, + &knl_uncore_cha, + &knl_uncore_pcu, + NULL, +}; + +void knl_uncore_cpu_init(void) +{ + uncore_msr_uncores = knl_msr_uncores; +} + +static void knl_uncore_imc_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + + pci_write_config_dword(pdev, box_ctl, 0); +} + +static void knl_uncore_imc_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK) + == UNCORE_FIXED_EVENT) + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | KNL_PMON_FIXED_CTL_EN); + else + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops knl_uncore_imc_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = knl_uncore_imc_enable_box, + .read_counter = snbep_uncore_pci_read_counter, + .enable_event = knl_uncore_imc_enable_event, + .disable_event = snbep_uncore_pci_disable_event, +}; + +static struct intel_uncore_type knl_uncore_imc_uclk = { + .name = "imc_uclk", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_imc_dclk = { + .name = "imc", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_MC0_CH0_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_MC0_CH0_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_MC0_CH0_MSR_PMON_FIXED_LOW, + .fixed_ctl = KNL_MC0_CH0_MSR_PMON_FIXED_CTL, + .box_ctl = KNL_MC0_CH0_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_uclk = { + .name = "edc_uclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_eclk = { + .name = "edc_eclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_EDC0_ECLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW, + .fixed_ctl = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL, + .box_ctl = KNL_EDC0_ECLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct event_constraint knl_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type knl_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = knl_uncore_m2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct attribute *knl_uncore_irp_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group knl_uncore_irp_format_group = { + .name = "format", + .attrs = knl_uncore_irp_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = KNL_IRP_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = KNL_IRP_PCI_PMON_BOX_CTL, + .ops = &snbep_uncore_pci_ops, + .format_group = &knl_uncore_irp_format_group, +}; + +enum { + KNL_PCI_UNCORE_MC_UCLK, + KNL_PCI_UNCORE_MC_DCLK, + KNL_PCI_UNCORE_EDC_UCLK, + KNL_PCI_UNCORE_EDC_ECLK, + KNL_PCI_UNCORE_M2PCIE, + KNL_PCI_UNCORE_IRP, +}; + +static struct intel_uncore_type *knl_pci_uncores[] = { + [KNL_PCI_UNCORE_MC_UCLK] = &knl_uncore_imc_uclk, + [KNL_PCI_UNCORE_MC_DCLK] = &knl_uncore_imc_dclk, + [KNL_PCI_UNCORE_EDC_UCLK] = &knl_uncore_edc_uclk, + [KNL_PCI_UNCORE_EDC_ECLK] = &knl_uncore_edc_eclk, + [KNL_PCI_UNCORE_M2PCIE] = &knl_uncore_m2pcie, + [KNL_PCI_UNCORE_IRP] = &knl_uncore_irp, + NULL, +}; + +/* + * KNL uses a common PCI device ID for multiple instances of an Uncore PMU + * device type. prior to KNL, each instance of a PMU device type had a unique + * device ID. + * + * PCI Device ID Uncore PMU Devices + * ---------------------------------- + * 0x7841 MC0 UClk, MC1 UClk + * 0x7843 MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2, + * MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2 + * 0x7833 EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk, + * EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk + * 0x7835 EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk, + * EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk + * 0x7817 M2PCIe + * 0x7814 IRP +*/ + +static const struct pci_device_id knl_uncore_pci_ids[] = { + { /* MC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0), + }, + { /* MC DClk Channel */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0), + }, + { /* EDC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0), + }, + { /* EDC EClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0), + }, + { /* M2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver knl_uncore_pci_driver = { + .name = "knl_uncore", + .id_table = knl_uncore_pci_ids, +}; + +int knl_uncore_pci_init(void) +{ + int ret; + + /* All KNL PCI based PMON units are on the same PCI bus except IRP */ + ret = snb_pci2phy_map_init(0x7814); /* IRP */ + if (ret) + return ret; + ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */ + if (ret) + return ret; + uncore_pci_uncores = knl_pci_uncores; + uncore_pci_driver = &knl_uncore_pci_driver; + return 0; +} + +/* end of KNL uncore support */ + /* Haswell-EP uncore support */ static struct attribute *hswep_uncore_ubox_formats_attr[] = { &format_attr_event.attr, @@ -2338,7 +2819,7 @@ int hswep_uncore_pci_init(void) } /* end of Haswell-EP uncore support */ -/* BDX-DE uncore support */ +/* BDX uncore support */ static struct intel_uncore_type bdx_uncore_ubox = { .name = "ubox", @@ -2360,13 +2841,14 @@ static struct event_constraint bdx_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x09, 0x3), UNCORE_EVENT_CONSTRAINT(0x11, 0x1), UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), EVENT_CONSTRAINT_END }; static struct intel_uncore_type bdx_uncore_cbox = { .name = "cbox", .num_counters = 4, - .num_boxes = 8, + .num_boxes = 24, .perf_ctr_bits = 48, .event_ctl = HSWEP_C0_MSR_PMON_CTL0, .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, @@ -2379,9 +2861,24 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, + &bdx_uncore_sbox, &hswep_uncore_pcu, NULL, }; @@ -2396,7 +2893,7 @@ void bdx_uncore_cpu_init(void) static struct intel_uncore_type bdx_uncore_ha = { .name = "ha", .num_counters = 4, - .num_boxes = 1, + .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), }; @@ -2404,7 +2901,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", .num_counters = 5, - .num_boxes = 2, + .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, @@ -2424,6 +2921,19 @@ static struct intel_uncore_type bdx_uncore_irp = { .format_group = &snbep_uncore_format_group, }; +static struct intel_uncore_type bdx_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x10, 0x3), @@ -2432,6 +2942,8 @@ static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x23, 0x1), UNCORE_EVENT_CONSTRAINT(0x25, 0x1), UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), EVENT_CONSTRAINT_END }; @@ -2445,18 +2957,65 @@ static struct intel_uncore_type bdx_uncore_r2pcie = { SNBEP_UNCORE_PCI_COMMON_INIT(), }; +static struct event_constraint bdx_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x7), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 3, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + enum { BDX_PCI_UNCORE_HA, BDX_PCI_UNCORE_IMC, BDX_PCI_UNCORE_IRP, + BDX_PCI_UNCORE_QPI, BDX_PCI_UNCORE_R2PCIE, + BDX_PCI_UNCORE_R3QPI, }; static struct intel_uncore_type *bdx_pci_uncores[] = { [BDX_PCI_UNCORE_HA] = &bdx_uncore_ha, [BDX_PCI_UNCORE_IMC] = &bdx_uncore_imc, [BDX_PCI_UNCORE_IRP] = &bdx_uncore_irp, + [BDX_PCI_UNCORE_QPI] = &bdx_uncore_qpi, [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie, + [BDX_PCI_UNCORE_R3QPI] = &bdx_uncore_r3qpi, NULL, }; @@ -2465,6 +3024,10 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0), }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1), + }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0), @@ -2473,14 +3036,74 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1), }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7), + }, { /* IRP */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0), }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2), + }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0), }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + }, + { /* QPI Port 2 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + }, { /* end: all zeroes */ } }; @@ -2500,4 +3123,4 @@ int bdx_uncore_pci_init(void) return 0; } -/* end of BDX-DE uncore support */ +/* end of BDX uncore support */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2c1910f6717e..58f34319b29a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -35,6 +35,7 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> +#include <asm/intel_pt.h> /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -125,6 +126,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + disable_local_APIC(); } @@ -169,6 +175,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 22abea04731e..0d4e092ae1bf 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -143,9 +143,18 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +/* Get alignment of the TYPE. */ +#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) + +/* + * Enforce that 'MEMBER' is the last field of 'TYPE'. + * + * Align the computed size with alignment of the TYPE, + * because that's how C aligns structs. + */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ + TYPE_ALIGN(TYPE))) /* * We append the 'struct fpu' to the task_struct: diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2bd81e302427..72cef58693c7 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock); static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; +struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return hv_clock; +} + /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -305,7 +310,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 int cpu; - int ret; u8 flags; struct pvclock_vcpu_time_info *vcpu_time; unsigned int size; @@ -325,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } - if ((ret = pvclock_init_vsyscall(hv_clock, size))) { - put_cpu(); - return ret; - } - put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 697f90db0e37..8a2cdd736fa4 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -29,6 +29,7 @@ #include <asm/mach_traps.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/reboot.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -231,7 +232,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) #endif if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); @@ -255,8 +256,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); show_regs(regs); - if (panic_on_io_nmi) - panic("NMI IOCK error: Not continuing"); + if (panic_on_io_nmi) { + nmi_panic(regs, "NMI IOCK error: Not continuing"); + + /* + * If we end up here, it means we have received an NMI while + * processing panic(). Simply return without delaying and + * re-enabling NMIs. + */ + return; + } /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; @@ -297,7 +306,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Do you have a strange power saving mode enabled?\n"); if (unknown_nmi_panic || panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); } @@ -348,8 +357,19 @@ static void default_do_nmi(struct pt_regs *regs) return; } - /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ - raw_spin_lock(&nmi_reason_lock); + /* + * Non-CPU-specific NMI: NMI sources can be processed on any CPU. + * + * Another CPU may be processing panic routines while holding + * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping, + * and if so, call its callback directly. If there is no CPU preparing + * crash dump, we simply loop here. + */ + while (!raw_spin_trylock(&nmi_reason_lock)) { + run_crash_ipi_callback(regs); + cpu_relax(); + } + reason = x86_platform.get_nmi_reason(); if (reason & NMI_REASON_MASK) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 3265ea0fceeb..f08ac28b8136 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -150,10 +150,6 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || -#ifdef CONFIG_X86_32 - type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || -#endif - type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); @@ -208,8 +204,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_irq_enable_sysexit(void); -extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { @@ -367,13 +361,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) - .irq_enable_sysexit = native_irq_enable_sysexit, -#endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_IA32_EMULATION - .usergs_sysret32 = native_usergs_sysret32, -#endif .usergs_sysret64 = native_usergs_sysret64, #endif .iret = native_iret, diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index c89f50a76e97..158dc0650d5d 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -5,7 +5,6 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); @@ -46,7 +45,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, restore_fl); PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa05583bc42..e70087a04cc8 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); -DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); @@ -55,7 +53,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); PATCH_SITE(pv_mmu_ops, read_cr2); diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..99bfc025111d 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } - -#ifdef CONFIG_X86_64 -/* - * Initialize the generic pvclock vsyscall state. This will allocate - * a/some page(s) for the per-vcpu pvclock information, set up a - * fixmap mapping for the page(s) - */ - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size) -{ - int idx; - - WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { - __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, - __pa(i) + (idx*PAGE_SIZE), - PAGE_KERNEL_VVAR); - } - - return 0; -} -#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..d64889aa2d46 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -718,6 +718,7 @@ static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; +static int crash_ipi_issued; static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) { @@ -780,6 +781,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) smp_send_nmi_allbutself(); + /* Kick CPUs looping in NMI context. */ + WRITE_ONCE(crash_ipi_issued, 1); + msecs = 1000; /* Wait at most a second for the other cpus to stop */ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { mdelay(1); @@ -788,9 +792,35 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* Leave the nmi callback set */ } + +/* + * Check if the crash dumping IPI got issued and if so, call its callback + * directly. This function is used when we have already been in NMI handler. + * It doesn't return. + */ +void run_crash_ipi_callback(struct pt_regs *regs) +{ + if (crash_ipi_issued) + crash_nmi_callback(0, regs); +} + +/* Override the weak function in kernel/panic.c */ +void nmi_panic_self_stop(struct pt_regs *regs) +{ + while (1) { + /* If no CPU is preparing crash dump, we simply loop here. */ + run_crash_ipi_callback(regs); + cpu_relax(); + } +} + #else /* !CONFIG_SMP */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { /* No other CPUs to shoot down */ } + +void run_crash_ipi_callback(struct pt_regs *regs) +{ +} #endif diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index cd9685235df9..4af8d063fb36 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -200,6 +200,9 @@ static __init int add_rtc_cmos(void) } #endif + if (paravirt_enabled() && !paravirt_has(RTC)) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 12c8286206ce..658777cf3851 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -125,12 +125,12 @@ static void native_smp_send_reschedule(int cpu) WARN_ON(1); return; } - apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); + apic->send_IPI(cpu, RESCHEDULE_VECTOR); } void native_send_call_func_single_ipi(int cpu) { - apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); + apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); } void native_send_call_func_ipi(const struct cpumask *mask) diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 06332cb7e7d1..3f5c48ddba45 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -38,6 +38,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->edx & bit(X86_FEATURE_MTRR)); +} + static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 08116ff227cc..b0ea42b78ccd 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -420,6 +420,7 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_s u8 saved_mode; if (hpet_legacy_start) { /* save existing mode for later reenablement */ + WARN_ON(channel != 0); saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ pit_load_count(kvm, channel, val); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 9e8bf13572e6..3f8c732117ec 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,14 +120,22 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; } -static u8 mtrr_disabled_type(void) +static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) { /* * Intel SDM 11.11.2.2: all MTRRs are disabled when * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC * memory type is applied to all of physical memory. + * + * However, virtual machines can be run with CPUID such that + * there are no MTRRs. In that case, the firmware will never + * enable MTRRs and it is obviously undesirable to run the + * guest entirely with UC memory and we use WB. */ - return MTRR_TYPE_UNCACHABLE; + if (guest_cpuid_has_mtrr(vcpu)) + return MTRR_TYPE_UNCACHABLE; + else + return MTRR_TYPE_WRBACK; } /* @@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr) for (seg = 0; seg < seg_num; seg++) { mtrr_seg = &fixed_seg_table[seg]; - if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + if (mtrr_seg->start <= addr && addr < mtrr_seg->end) return seg; } @@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) *start = range->base & PAGE_MASK; mask = range->mask & PAGE_MASK; - mask |= ~0ULL << boot_cpu_data.x86_phys_bits; /* This cannot overflow because writing to the reserved bits of * variable MTRRs causes a #GP. @@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (var_mtrr_range_is_valid(cur)) list_del(&mtrr_state->var_ranges[index].node); + /* Extend the mask with all 1 bits to the left, since those + * bits must implicitly be 0. The bits are then cleared + * when reading them. + */ if (!is_mtrr_mask) cur->base = data; else - cur->mask = data; + cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); /* add it to the list if it's enabled. */ if (var_mtrr_range_is_valid(cur)) { @@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; else *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + + *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; } return 0; @@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } if (iter.mtrr_disabled) - return mtrr_disabled_type(); + return mtrr_disabled_type(vcpu); /* not contained in any MTRRs. */ if (type == -1) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 83a1c643f9a5..899c40f826dd 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3422,6 +3422,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; + trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3892,8 +3894,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); - if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index af823a388c19..44976a596fa6 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2803,7 +2803,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: @@ -2909,7 +2909,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -8042,6 +8042,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -8668,7 +8670,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eed32283d22c..97592e190413 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3572,9 +3572,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -3593,6 +3595,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { int start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3602,7 +3605,9 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + start && i == 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -6515,6 +6520,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); + trace_kvm_entry(vcpu->vcpu_id); + wait_lapic_expire(vcpu); __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -6527,8 +6534,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); kvm_x86_ops->run(vcpu); /* diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a1900d4682c0..4ba229ac3f4f 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1414,6 +1414,7 @@ __init void lguest_init(void) pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; + pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 43623739c7cf..004c861b1648 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,6 +1,8 @@ #include <linux/module.h> #include <linux/preempt.h> #include <asm/msr.h> +#define CREATE_TRACE_POINTS +#include <asm/msr-trace.h> struct msr *msrs_alloc(void) { @@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, false); } + +#ifdef CONFIG_TRACEPOINTS +void do_trace_write_msr(unsigned msr, u64 val, int failed) +{ + trace_write_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_write_msr); +EXPORT_TRACEPOINT_SYMBOL(write_msr); + +void do_trace_read_msr(unsigned msr, u64 val, int failed) +{ + trace_read_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_read_msr); +EXPORT_TRACEPOINT_SYMBOL(read_msr); + +void do_trace_rdpmc(unsigned counter, u64 val, int failed) +{ + trace_rdpmc(counter, val, failed); +} +EXPORT_SYMBOL(do_trace_rdpmc); +EXPORT_TRACEPOINT_SYMBOL(rdpmc); + +#endif diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 327f21c3bde1..8dd80050d705 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -28,6 +28,7 @@ #include <linux/nmi.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/clocksource.h> #include <asm/apic.h> #include <asm/current.h> diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index e5f854ce2d72..14fcd01ed992 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -470,7 +470,7 @@ long sys_sigreturn(void) struct sigcontext __user *sc = &frame->sc; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], (void *)sc->oldmask, sizeof(set.sig[0])) || + if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) || copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 4334e511cfc8..23063923e364 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1192,7 +1192,7 @@ static const struct pv_info xen_info __initconst = { #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - + .features = 0, .name = "Xen", }; @@ -1229,10 +1229,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .iret = xen_iret, #ifdef CONFIG_X86_64 - .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, -#else - .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1529,6 +1526,8 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; + if (xen_initial_domain()) + pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1879,8 +1878,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) + if (xen_pv_domain()) { clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + set_cpu_cap(c, X86_FEATURE_XENPV); + } } const struct hypervisor_x86 x86_hyper_xen = { diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 3705eabd7e22..df0c40559583 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include <linux/tick.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index fd92a64d748e..feb6d40a0860 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -35,20 +35,6 @@ check_events: ret /* - * We can't use sysexit directly, because we're not running in ring0. - * But we can easily fake it up using iret. Assuming xen_sysexit is - * jumped to with a standard stack frame, we can just strip it back to - * a standard iret frame and use iret. - */ -ENTRY(xen_sysexit) - movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ - orl $X86_EFLAGS_IF, PT_EFLAGS(%esp) - lea PT_EIP(%esp), %esp - - jmp xen_iret -ENDPROC(xen_sysexit) - -/* * This is run where a normal iret would be run, with the same stack setup: * 8: eflags * 4: cs diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index f22667abf7b9..cc8acc410ddb 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -68,25 +68,6 @@ ENTRY(xen_sysret64) ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) -ENTRY(xen_sysret32) - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back - */ - movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER32_DS - pushq PER_CPU_VAR(rsp_scratch) - pushq %r11 - pushq $__USER32_CS - pushq %rcx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysret32) -RELOC(xen_sysret32, 1b+1) - /* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1399423f3418..4140b070f2e9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -139,9 +139,6 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); -#ifdef CONFIG_X86_32 -__visible void xen_sysexit(void); -#endif __visible void xen_sysret32(void); __visible void xen_sysret64(void); __visible void xen_adjust_exception_frame(void); diff --git a/block/blk-core.c b/block/blk-core.c index 3636be469fa2..33e2f62d5062 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -207,6 +207,22 @@ void blk_delay_queue(struct request_queue *q, unsigned long msecs) EXPORT_SYMBOL(blk_delay_queue); /** + * blk_start_queue_async - asynchronously restart a previously stopped queue + * @q: The &struct request_queue in question + * + * Description: + * blk_start_queue_async() will clear the stop flag on the queue, and + * ensure that the request_fn for the queue is run from an async + * context. + **/ +void blk_start_queue_async(struct request_queue *q) +{ + queue_flag_clear(QUEUE_FLAG_STOPPED, q); + blk_run_queue_async(q); +} +EXPORT_SYMBOL(blk_start_queue_async); + +/** * blk_start_queue - restart a previously stopped queue * @q: The &struct request_queue in question * @@ -1689,8 +1705,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) struct request *req; unsigned int request_count = 0; - blk_queue_split(q, &bio, q->bio_split); - /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1698,6 +1712,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); + blk_queue_split(q, &bio, q->bio_split); + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio->bi_error = -EIO; bio_endio(bio); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index ca9efe17db1a..634b4d1ab681 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -47,7 +47,7 @@ struct skcipher_ctx { bool merge; bool enc; - struct ablkcipher_request req; + struct skcipher_request req; }; struct skcipher_async_rsgl { @@ -64,13 +64,13 @@ struct skcipher_async_req { }; #define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \ - crypto_ablkcipher_reqsize(crypto_ablkcipher_reqtfm(&ctx->req))) + crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))) #define GET_REQ_SIZE(ctx) \ - crypto_ablkcipher_reqsize(crypto_ablkcipher_reqtfm(&ctx->req)) + crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)) #define GET_IV_SIZE(ctx) \ - crypto_ablkcipher_ivsize(crypto_ablkcipher_reqtfm(&ctx->req)) + crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req)) #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) @@ -302,8 +302,8 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req); - unsigned ivsize = crypto_ablkcipher_ivsize(tfm); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); + unsigned ivsize = crypto_skcipher_ivsize(tfm); struct skcipher_sg_list *sgl; struct af_alg_control con = {}; long copied = 0; @@ -507,7 +507,7 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, struct skcipher_sg_list *sgl; struct scatterlist *sg; struct skcipher_async_req *sreq; - struct ablkcipher_request *req; + struct skcipher_request *req; struct skcipher_async_rsgl *last_rsgl = NULL; unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx); unsigned int reqlen = sizeof(struct skcipher_async_req) + @@ -531,9 +531,9 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, } sg_init_table(sreq->tsg, tx_nents); memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx)); - ablkcipher_request_set_tfm(req, crypto_ablkcipher_reqtfm(&ctx->req)); - ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - skcipher_async_cb, sk); + skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req)); + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_async_cb, sk); while (iov_iter_count(&msg->msg_iter)) { struct skcipher_async_rsgl *rsgl; @@ -608,10 +608,10 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, if (mark) sg_mark_end(sreq->tsg + txbufs - 1); - ablkcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, - len, sreq->iv); - err = ctx->enc ? crypto_ablkcipher_encrypt(req) : - crypto_ablkcipher_decrypt(req); + skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, + len, sreq->iv); + err = ctx->enc ? crypto_skcipher_encrypt(req) : + crypto_skcipher_decrypt(req); if (err == -EINPROGRESS) { atomic_inc(&ctx->inflight); err = -EIOCBQUEUED; @@ -632,7 +632,7 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - unsigned bs = crypto_ablkcipher_blocksize(crypto_ablkcipher_reqtfm( + unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm( &ctx->req)); struct skcipher_sg_list *sgl; struct scatterlist *sg; @@ -669,14 +669,13 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, if (!used) goto free; - ablkcipher_request_set_crypt(&ctx->req, sg, - ctx->rsgl.sg, used, - ctx->iv); + skcipher_request_set_crypt(&ctx->req, sg, ctx->rsgl.sg, used, + ctx->iv); err = af_alg_wait_for_completion( ctx->enc ? - crypto_ablkcipher_encrypt(&ctx->req) : - crypto_ablkcipher_decrypt(&ctx->req), + crypto_skcipher_encrypt(&ctx->req) : + crypto_skcipher_decrypt(&ctx->req), &ctx->completion); free: @@ -751,17 +750,17 @@ static struct proto_ops algif_skcipher_ops = { static void *skcipher_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_ablkcipher(name, type, mask); + return crypto_alloc_skcipher(name, type, mask); } static void skcipher_release(void *private) { - crypto_free_ablkcipher(private); + crypto_free_skcipher(private); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_ablkcipher_setkey(private, key, keylen); + return crypto_skcipher_setkey(private, key, keylen); } static void skcipher_wait(struct sock *sk) @@ -778,13 +777,13 @@ static void skcipher_sock_destruct(struct sock *sk) { struct alg_sock *ask = alg_sk(sk); struct skcipher_ctx *ctx = ask->private; - struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); if (atomic_read(&ctx->inflight)) skcipher_wait(sk); skcipher_free_sgl(sk); - sock_kzfree_s(sk, ctx->iv, crypto_ablkcipher_ivsize(tfm)); + sock_kzfree_s(sk, ctx->iv, crypto_skcipher_ivsize(tfm)); sock_kfree_s(sk, ctx, ctx->len); af_alg_release_parent(sk); } @@ -793,20 +792,20 @@ static int skcipher_accept_parent(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(private); + unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(private); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; - ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(private), + ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(private), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_ablkcipher_ivsize(private)); + memset(ctx->iv, 0, crypto_skcipher_ivsize(private)); INIT_LIST_HEAD(&ctx->tsgl); ctx->len = len; @@ -819,9 +818,9 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ask->private = ctx; - ablkcipher_request_set_tfm(&ctx->req, private); - ablkcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, - af_alg_complete, &ctx->completion); + skcipher_request_set_tfm(&ctx->req, private); + skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, + af_alg_complete, &ctx->completion); sk->sk_destruct = skcipher_sock_destruct; diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c index f8c0b8dbeb75..88bc8e6b2a54 100644 --- a/crypto/async_tx/async_memcpy.c +++ b/crypto/async_tx/async_memcpy.c @@ -53,7 +53,7 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, struct dmaengine_unmap_data *unmap = NULL; if (device) - unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT); if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) { unsigned long dma_prep_flags = 0; diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c index 5d355e0c2633..c0748bbd4c08 100644 --- a/crypto/async_tx/async_pq.c +++ b/crypto/async_tx/async_pq.c @@ -188,7 +188,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks, BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks))); if (device) - unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT); /* XORing P/Q is only implemented in software */ if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) && @@ -307,7 +307,7 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks, BUG_ON(disks < 4); if (device) - unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT); if (unmap && disks <= dma_maxpq(device, 0) && is_dma_pq_aligned(device, offset, 0, len)) { diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c index 934a84981495..8fab6275ea1f 100644 --- a/crypto/async_tx/async_raid6_recov.c +++ b/crypto/async_tx/async_raid6_recov.c @@ -41,7 +41,7 @@ async_sum_product(struct page *dest, struct page **srcs, unsigned char *coef, u8 *a, *b, *c; if (dma) - unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO); + unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT); if (unmap) { struct device *dev = dma->dev; @@ -105,7 +105,7 @@ async_mult(struct page *dest, struct page *src, u8 coef, size_t len, u8 *d, *s; if (dma) - unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOIO); + unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT); if (unmap) { dma_addr_t dma_dest[2]; diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c index e1bce26cd4f9..da75777f2b3f 100644 --- a/crypto/async_tx/async_xor.c +++ b/crypto/async_tx/async_xor.c @@ -182,7 +182,7 @@ async_xor(struct page *dest, struct page **src_list, unsigned int offset, BUG_ON(src_cnt <= 1); if (device) - unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT); if (unmap && is_dma_xor_aligned(device, offset, 0, len)) { struct dma_async_tx_descriptor *tx; @@ -278,7 +278,7 @@ async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, BUG_ON(src_cnt <= 1); if (device) - unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOIO); + unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT); if (unmap && src_cnt <= device->max_xor && is_dma_xor_aligned(device, offset, 0, len)) { diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index 707cf6213bc2..b9afb47db7ed 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -104,7 +104,7 @@ static void acpi_expose_nondev_subnodes(struct kobject *kobj, init_completion(&dn->kobj_done); ret = kobject_init_and_add(&dn->kobj, &acpi_data_node_ktype, - kobj, dn->name); + kobj, "%s", dn->name); if (ret) acpi_handle_err(dn->handle, "Failed to expose (%d)\n", ret); else diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index f4e02ae93f58..11154a330f07 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -200,7 +200,8 @@ static int acpi_pss_perf_init(struct acpi_processor *pr, goto err_remove_sysfs_thermal; } - sysfs_remove_link(&pr->cdev->device.kobj, "device"); + return 0; + err_remove_sysfs_thermal: sysfs_remove_link(&device->dev.kobj, "thermal_cooling"); err_thermal_unregister: diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 8162475d96b5..09e3c0d87ecc 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -219,6 +219,9 @@ static void end_cmd(struct nullb_cmd *cmd) { struct request_queue *q = NULL; + if (cmd->rq) + q = cmd->rq->q; + switch (queue_mode) { case NULL_Q_MQ: blk_mq_end_request(cmd->rq, 0); @@ -229,23 +232,19 @@ static void end_cmd(struct nullb_cmd *cmd) break; case NULL_Q_BIO: bio_endio(cmd->bio); - goto free_cmd; + break; } - if (cmd->rq) - q = cmd->rq->q; + free_cmd(cmd); /* Restart queue if needed, as we are freeing a tag */ - if (q && !q->mq_ops && blk_queue_stopped(q)) { + if (queue_mode == NULL_Q_RQ && blk_queue_stopped(q)) { unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); - if (blk_queue_stopped(q)) - blk_start_queue(q); + blk_start_queue_async(q); spin_unlock_irqrestore(q->queue_lock, flags); } -free_cmd: - free_cmd(cmd); } static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 846bc29c157d..25996e256110 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -342,13 +342,13 @@ static int sunxi_rsb_read(struct sunxi_rsb *rsb, u8 rtaddr, u8 addr, ret = _sunxi_rsb_run_xfer(rsb); if (ret) - goto out; + goto unlock; *buf = readl(rsb->regs + RSB_DATA); +unlock: mutex_unlock(&rsb->lock); -out: return ret; } @@ -527,9 +527,9 @@ static int sunxi_rsb_init_device_mode(struct sunxi_rsb *rsb) */ static const struct sunxi_rsb_addr_map sunxi_rsb_addr_maps[] = { - { 0x3e3, 0x2d }, /* Primary PMIC: AXP223, AXP809, AXP81X, ... */ + { 0x3a3, 0x2d }, /* Primary PMIC: AXP223, AXP809, AXP81X, ... */ { 0x745, 0x3a }, /* Secondary PMIC: AXP806, ... */ - { 0xe89, 0x45 }, /* Peripheral IC: AC100, ... */ + { 0xe89, 0x4e }, /* Peripheral IC: AC100, ... */ }; static u8 sunxi_rsb_get_rtaddr(u16 hwaddr) diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index d7373ca69c99..25693b045371 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -179,26 +179,21 @@ static int cn_call_callback(struct sk_buff *skb) * * It checks skb, netlink header and msg sizes, and calls callback helper. */ -static void cn_rx_skb(struct sk_buff *__skb) +static void cn_rx_skb(struct sk_buff *skb) { struct nlmsghdr *nlh; - struct sk_buff *skb; int len, err; - skb = skb_get(__skb); - if (skb->len >= NLMSG_HDRLEN) { nlh = nlmsg_hdr(skb); len = nlmsg_len(nlh); if (len < (int)sizeof(struct cn_msg) || skb->len < nlh->nlmsg_len || - len > CONNECTOR_MAX_MSG_SIZE) { - kfree_skb(skb); + len > CONNECTOR_MAX_MSG_SIZE) return; - } - err = cn_call_callback(skb); + err = cn_call_callback(skb_get(skb)); if (err < 0) kfree_skb(skb); } diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c index 2c3b16fd3a01..de5e89b2eaaa 100644 --- a/drivers/cpufreq/scpi-cpufreq.c +++ b/drivers/cpufreq/scpi-cpufreq.c @@ -31,7 +31,7 @@ static struct scpi_ops *scpi_ops; static struct scpi_dvfs_info *scpi_get_dvfs_info(struct device *cpu_dev) { - u8 domain = topology_physical_package_id(cpu_dev->id); + int domain = topology_physical_package_id(cpu_dev->id); if (domain < 0) return ERR_PTR(-EINVAL); diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index cddfa8dbf4bd..068e920ecb68 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -317,7 +317,6 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); struct device *dev = mic_dma_ch_to_device(mic_ch); int result; - struct dma_async_tx_descriptor *tx = NULL; if (!len && !flags) return NULL; @@ -325,13 +324,10 @@ mic_dma_prep_memcpy_lock(struct dma_chan *ch, dma_addr_t dma_dest, spin_lock(&mic_ch->prep_lock); result = mic_dma_do_dma(mic_ch, flags, dma_src, dma_dest, len); if (result >= 0) - tx = allocate_tx(mic_ch); - - if (!tx) - dev_err(dev, "Error enqueueing dma, error=%d\n", result); - + return allocate_tx(mic_ch); + dev_err(dev, "Error enqueueing dma, error=%d\n", result); spin_unlock(&mic_ch->prep_lock); - return tx; + return NULL; } static struct dma_async_tx_descriptor * @@ -339,14 +335,13 @@ mic_dma_prep_interrupt_lock(struct dma_chan *ch, unsigned long flags) { struct mic_dma_chan *mic_ch = to_mic_dma_chan(ch); int ret; - struct dma_async_tx_descriptor *tx = NULL; spin_lock(&mic_ch->prep_lock); ret = mic_dma_do_dma(mic_ch, flags, 0, 0, 0); if (!ret) - tx = allocate_tx(mic_ch); + return allocate_tx(mic_ch); spin_unlock(&mic_ch->prep_lock); - return tx; + return NULL; } /* Return the status of the transaction */ diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c index 9dfa2b0fa5da..9cb93c5b655d 100644 --- a/drivers/dma/xgene-dma.c +++ b/drivers/dma/xgene-dma.c @@ -29,6 +29,7 @@ #include <linux/dmapool.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/irq.h> #include <linux/module.h> #include <linux/of_device.h> @@ -1610,6 +1611,7 @@ static int xgene_dma_request_irqs(struct xgene_dma *pdma) /* Register DMA channel rx irq */ for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { chan = &pdma->chan[i]; + irq_set_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY); ret = devm_request_irq(chan->dev, chan->rx_irq, xgene_dma_chan_ring_isr, 0, chan->name, chan); @@ -1620,6 +1622,7 @@ static int xgene_dma_request_irqs(struct xgene_dma *pdma) for (j = 0; j < i; j++) { chan = &pdma->chan[i]; + irq_clear_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY); devm_free_irq(chan->dev, chan->rx_irq, chan); } @@ -1640,6 +1643,7 @@ static void xgene_dma_free_irqs(struct xgene_dma *pdma) for (i = 0; i < XGENE_DMA_MAX_CHANNEL; i++) { chan = &pdma->chan[i]; + irq_clear_status_flags(chan->rx_irq, IRQ_DISABLE_UNLAZY); devm_free_irq(chan->dev, chan->rx_irq, chan); } } diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index ac1ce4a73edf..0e08e665f715 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -521,6 +521,7 @@ static int __init dmi_present(const u8 *buf) dmi_ver = smbios_ver; else dmi_ver = (buf[14] & 0xF0) << 4 | (buf[14] & 0x0F); + dmi_ver <<= 8; dmi_num = get_unaligned_le16(buf + 12); dmi_len = get_unaligned_le16(buf + 6); dmi_base = get_unaligned_le32(buf + 8); @@ -528,15 +529,14 @@ static int __init dmi_present(const u8 *buf) if (dmi_walk_early(dmi_decode) == 0) { if (smbios_ver) { pr_info("SMBIOS %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); + dmi_ver >> 16, (dmi_ver >> 8) & 0xFF); } else { smbios_entry_point_size = 15; memcpy(smbios_entry_point, buf, smbios_entry_point_size); pr_info("Legacy DMI %d.%d present.\n", - dmi_ver >> 8, dmi_ver & 0xFF); + dmi_ver >> 16, (dmi_ver >> 8) & 0xFF); } - dmi_ver <<= 8; dmi_format_ids(dmi_ids_string, sizeof(dmi_ids_string)); printk(KERN_DEBUG "DMI: %s\n", dmi_ids_string); return 0; diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c index e5827a56ff3b..5eaea8b812cf 100644 --- a/drivers/gpio/gpio-ath79.c +++ b/drivers/gpio/gpio-ath79.c @@ -113,7 +113,7 @@ static int ar934x_gpio_direction_output(struct gpio_chip *chip, unsigned offset, __raw_writel(BIT(offset), ctrl->base + AR71XX_GPIO_REG_CLEAR); __raw_writel( - __raw_readl(ctrl->base + AR71XX_GPIO_REG_OE) & BIT(offset), + __raw_readl(ctrl->base + AR71XX_GPIO_REG_OE) & ~BIT(offset), ctrl->base + AR71XX_GPIO_REG_OE); spin_unlock_irqrestore(&ctrl->lock, flags); diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c index bd5193c67a9c..88ae70ddb127 100644 --- a/drivers/gpio/gpio-generic.c +++ b/drivers/gpio/gpio-generic.c @@ -141,9 +141,9 @@ static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio) unsigned long pinmask = bgc->pin2mask(bgc, gpio); if (bgc->dir & pinmask) - return bgc->read_reg(bgc->reg_set) & pinmask; + return !!(bgc->read_reg(bgc->reg_set) & pinmask); else - return bgc->read_reg(bgc->reg_dat) & pinmask; + return !!(bgc->read_reg(bgc->reg_dat) & pinmask); } static int bgpio_get(struct gpio_chip *gc, unsigned int gpio) diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 2a91f3287e3b..4e4c3083ae56 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1279,7 +1279,13 @@ static int _gpiod_get_raw_value(const struct gpio_desc *desc) chip = desc->chip; offset = gpio_chip_hwgpio(desc); value = chip->get ? chip->get(chip, offset) : -EIO; - value = value < 0 ? value : !!value; + /* + * FIXME: fix all drivers to clamp to [0,1] or return negative, + * then change this to: + * value = value < 0 ? value : !!value; + * so we can properly propagate error codes. + */ + value = !!value; trace_gpio_value(desc_to_gpio(desc), 1, value); return value; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 5a5f04d0902d..048cfe073dae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1264,7 +1264,8 @@ struct amdgpu_cs_parser { struct ww_acquire_ctx ticket; /* user fence */ - struct amdgpu_user_fence uf; + struct amdgpu_user_fence uf; + struct amdgpu_bo_list_entry uf_entry; }; struct amdgpu_job { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 4f352ec9dec4..25a3e2485cc2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -127,6 +127,37 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, return 0; } +static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, + struct drm_amdgpu_cs_chunk_fence *fence_data) +{ + struct drm_gem_object *gobj; + uint32_t handle; + + handle = fence_data->handle; + gobj = drm_gem_object_lookup(p->adev->ddev, p->filp, + fence_data->handle); + if (gobj == NULL) + return -EINVAL; + + p->uf.bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj)); + p->uf.offset = fence_data->offset; + + if (amdgpu_ttm_tt_has_userptr(p->uf.bo->tbo.ttm)) { + drm_gem_object_unreference_unlocked(gobj); + return -EINVAL; + } + + p->uf_entry.robj = amdgpu_bo_ref(p->uf.bo); + p->uf_entry.prefered_domains = AMDGPU_GEM_DOMAIN_GTT; + p->uf_entry.allowed_domains = AMDGPU_GEM_DOMAIN_GTT; + p->uf_entry.priority = 0; + p->uf_entry.tv.bo = &p->uf_entry.robj->tbo; + p->uf_entry.tv.shared = true; + + drm_gem_object_unreference_unlocked(gobj); + return 0; +} + int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) { union drm_amdgpu_cs *cs = data; @@ -207,28 +238,15 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) case AMDGPU_CHUNK_ID_FENCE: size = sizeof(struct drm_amdgpu_cs_chunk_fence); - if (p->chunks[i].length_dw * sizeof(uint32_t) >= size) { - uint32_t handle; - struct drm_gem_object *gobj; - struct drm_amdgpu_cs_chunk_fence *fence_data; - - fence_data = (void *)p->chunks[i].kdata; - handle = fence_data->handle; - gobj = drm_gem_object_lookup(p->adev->ddev, - p->filp, handle); - if (gobj == NULL) { - ret = -EINVAL; - goto free_partial_kdata; - } - - p->uf.bo = gem_to_amdgpu_bo(gobj); - amdgpu_bo_ref(p->uf.bo); - drm_gem_object_unreference_unlocked(gobj); - p->uf.offset = fence_data->offset; - } else { + if (p->chunks[i].length_dw * sizeof(uint32_t) < size) { ret = -EINVAL; goto free_partial_kdata; } + + ret = amdgpu_cs_user_fence_chunk(p, (void *)p->chunks[i].kdata); + if (ret) + goto free_partial_kdata; + break; case AMDGPU_CHUNK_ID_DEPENDENCIES: @@ -391,6 +409,9 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p) p->vm_bos = amdgpu_vm_get_bos(p->adev, &fpriv->vm, &p->validated); + if (p->uf.bo) + list_add(&p->uf_entry.tv.head, &p->validated); + if (need_mmap_lock) down_read(¤t->mm->mmap_sem); @@ -488,8 +509,8 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bo for (i = 0; i < parser->num_ibs; i++) amdgpu_ib_free(parser->adev, &parser->ibs[i]); kfree(parser->ibs); - if (parser->uf.bo) - amdgpu_bo_unref(&parser->uf.bo); + amdgpu_bo_unref(&parser->uf.bo); + amdgpu_bo_unref(&parser->uf_entry.robj); } static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p, diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index b3ba27fd9a6b..e69357172ffb 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -55,6 +55,9 @@ static int exynos_crtc_atomic_check(struct drm_crtc *crtc, { struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); + if (!state->enable) + return 0; + if (exynos_crtc->ops->atomic_check) return exynos_crtc->ops->atomic_check(exynos_crtc, state); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index a01e51581c4c..f4af19a0d569 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2193,8 +2193,17 @@ struct drm_i915_gem_request { struct drm_i915_private *i915; struct intel_engine_cs *ring; - /** GEM sequence number associated with this request. */ - uint32_t seqno; + /** GEM sequence number associated with the previous request, + * when the HWS breadcrumb is equal to this the GPU is processing + * this request. + */ + u32 previous_seqno; + + /** GEM sequence number associated with this request, + * when the HWS breadcrumb is equal or greater than this the GPU + * has finished processing this request. + */ + u32 seqno; /** Position in the ringbuffer of the start of the request */ u32 head; @@ -2839,6 +2848,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level, u32 flags); +void __i915_vma_set_map_and_fenceable(struct i915_vma *vma); int __must_check i915_vma_unbind(struct i915_vma *vma); /* * BEWARE: Do not use the function below unless you can _absolutely_ @@ -2910,15 +2920,17 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2) return (int32_t)(seq1 - seq2) >= 0; } +static inline bool i915_gem_request_started(struct drm_i915_gem_request *req, + bool lazy_coherency) +{ + u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency); + return i915_seqno_passed(seqno, req->previous_seqno); +} + static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req, bool lazy_coherency) { - u32 seqno; - - BUG_ON(req == NULL); - - seqno = req->ring->get_seqno(req->ring, lazy_coherency); - + u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency); return i915_seqno_passed(seqno, req->seqno); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 32e6aade6223..f56af0aaafde 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1146,23 +1146,74 @@ static bool missed_irq(struct drm_i915_private *dev_priv, return test_bit(ring->id, &dev_priv->gpu_error.missed_irq_rings); } -static int __i915_spin_request(struct drm_i915_gem_request *req) +static unsigned long local_clock_us(unsigned *cpu) +{ + unsigned long t; + + /* Cheaply and approximately convert from nanoseconds to microseconds. + * The result and subsequent calculations are also defined in the same + * approximate microseconds units. The principal source of timing + * error here is from the simple truncation. + * + * Note that local_clock() is only defined wrt to the current CPU; + * the comparisons are no longer valid if we switch CPUs. Instead of + * blocking preemption for the entire busywait, we can detect the CPU + * switch and use that as indicator of system load and a reason to + * stop busywaiting, see busywait_stop(). + */ + *cpu = get_cpu(); + t = local_clock() >> 10; + put_cpu(); + + return t; +} + +static bool busywait_stop(unsigned long timeout, unsigned cpu) +{ + unsigned this_cpu; + + if (time_after(local_clock_us(&this_cpu), timeout)) + return true; + + return this_cpu != cpu; +} + +static int __i915_spin_request(struct drm_i915_gem_request *req, int state) { unsigned long timeout; + unsigned cpu; + + /* When waiting for high frequency requests, e.g. during synchronous + * rendering split between the CPU and GPU, the finite amount of time + * required to set up the irq and wait upon it limits the response + * rate. By busywaiting on the request completion for a short while we + * can service the high frequency waits as quick as possible. However, + * if it is a slow request, we want to sleep as quickly as possible. + * The tradeoff between waiting and sleeping is roughly the time it + * takes to sleep on a request, on the order of a microsecond. + */ - if (i915_gem_request_get_ring(req)->irq_refcount) + if (req->ring->irq_refcount) return -EBUSY; - timeout = jiffies + 1; + /* Only spin if we know the GPU is processing this request */ + if (!i915_gem_request_started(req, true)) + return -EAGAIN; + + timeout = local_clock_us(&cpu) + 5; while (!need_resched()) { if (i915_gem_request_completed(req, true)) return 0; - if (time_after_eq(jiffies, timeout)) + if (signal_pending_state(state, current)) + break; + + if (busywait_stop(timeout, cpu)) break; cpu_relax_lowlatency(); } + if (i915_gem_request_completed(req, false)) return 0; @@ -1197,6 +1248,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, struct drm_i915_private *dev_priv = dev->dev_private; const bool irq_test_in_progress = ACCESS_ONCE(dev_priv->gpu_error.test_irq_rings) & intel_ring_flag(ring); + int state = interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE; DEFINE_WAIT(wait); unsigned long timeout_expire; s64 before, now; @@ -1229,7 +1281,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, before = ktime_get_raw_ns(); /* Optimistic spin for the next jiffie before touching IRQs */ - ret = __i915_spin_request(req); + ret = __i915_spin_request(req, state); if (ret == 0) goto out; @@ -1241,8 +1293,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, for (;;) { struct timer_list timer; - prepare_to_wait(&ring->irq_queue, &wait, - interruptible ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE); + prepare_to_wait(&ring->irq_queue, &wait, state); /* We need to check whether any gpu reset happened in between * the caller grabbing the seqno and now ... */ @@ -1260,7 +1311,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req, break; } - if (interruptible && signal_pending(current)) { + if (signal_pending_state(state, current)) { ret = -ERESTARTSYS; break; } @@ -2554,6 +2605,7 @@ void __i915_add_request(struct drm_i915_gem_request *request, request->batch_obj = obj; request->emitted_jiffies = jiffies; + request->previous_seqno = ring->last_submitted_seqno; ring->last_submitted_seqno = request->seqno; list_add_tail(&request->list, &ring->request_list); @@ -4080,6 +4132,29 @@ i915_vma_misplaced(struct i915_vma *vma, uint32_t alignment, uint64_t flags) return false; } +void __i915_vma_set_map_and_fenceable(struct i915_vma *vma) +{ + struct drm_i915_gem_object *obj = vma->obj; + bool mappable, fenceable; + u32 fence_size, fence_alignment; + + fence_size = i915_gem_get_gtt_size(obj->base.dev, + obj->base.size, + obj->tiling_mode); + fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev, + obj->base.size, + obj->tiling_mode, + true); + + fenceable = (vma->node.size == fence_size && + (vma->node.start & (fence_alignment - 1)) == 0); + + mappable = (vma->node.start + fence_size <= + to_i915(obj->base.dev)->gtt.mappable_end); + + obj->map_and_fenceable = mappable && fenceable; +} + static int i915_gem_object_do_pin(struct drm_i915_gem_object *obj, struct i915_address_space *vm, @@ -4147,25 +4222,7 @@ i915_gem_object_do_pin(struct drm_i915_gem_object *obj, if (ggtt_view && ggtt_view->type == I915_GGTT_VIEW_NORMAL && (bound ^ vma->bound) & GLOBAL_BIND) { - bool mappable, fenceable; - u32 fence_size, fence_alignment; - - fence_size = i915_gem_get_gtt_size(obj->base.dev, - obj->base.size, - obj->tiling_mode); - fence_alignment = i915_gem_get_gtt_alignment(obj->base.dev, - obj->base.size, - obj->tiling_mode, - true); - - fenceable = (vma->node.size == fence_size && - (vma->node.start & (fence_alignment - 1)) == 0); - - mappable = (vma->node.start + fence_size <= - dev_priv->gtt.mappable_end); - - obj->map_and_fenceable = mappable && fenceable; - + __i915_vma_set_map_and_fenceable(vma); WARN_ON(flags & PIN_MAPPABLE && !obj->map_and_fenceable); } diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 43f35d12b677..86c7500454b4 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2676,6 +2676,7 @@ static int i915_gem_setup_global_gtt(struct drm_device *dev, return ret; } vma->bound |= GLOBAL_BIND; + __i915_vma_set_map_and_fenceable(vma); list_add_tail(&vma->mm_list, &ggtt_vm->inactive_list); } diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index cdacf3f5b77a..87e919a06b27 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -687,6 +687,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, } vma->bound |= GLOBAL_BIND; + __i915_vma_set_map_and_fenceable(vma); list_add_tail(&vma->mm_list, &ggtt->inactive_list); } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 62211abe4922..32cf97346978 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -116,6 +116,7 @@ static void skylake_pfit_enable(struct intel_crtc *crtc); static void ironlake_pfit_disable(struct intel_crtc *crtc, bool force); static void ironlake_pfit_enable(struct intel_crtc *crtc); static void intel_modeset_setup_hw_state(struct drm_device *dev); +static void intel_pre_disable_primary(struct drm_crtc *crtc); typedef struct { int min, max; @@ -2607,6 +2608,8 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, struct drm_i915_gem_object *obj; struct drm_plane *primary = intel_crtc->base.primary; struct drm_plane_state *plane_state = primary->state; + struct drm_crtc_state *crtc_state = intel_crtc->base.state; + struct intel_plane *intel_plane = to_intel_plane(primary); struct drm_framebuffer *fb; if (!plane_config->fb) @@ -2643,6 +2646,18 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc, } } + /* + * We've failed to reconstruct the BIOS FB. Current display state + * indicates that the primary plane is visible, but has a NULL FB, + * which will lead to problems later if we don't fix it up. The + * simplest solution is to just disable the primary plane now and + * pretend the BIOS never had it enabled. + */ + to_intel_plane_state(plane_state)->visible = false; + crtc_state->plane_mask &= ~(1 << drm_plane_index(primary)); + intel_pre_disable_primary(&intel_crtc->base); + intel_plane->disable_plane(primary, &intel_crtc->base); + return; valid_fb: @@ -9910,14 +9925,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, return true; } -static void i845_update_cursor(struct drm_crtc *crtc, u32 base) +static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); uint32_t cntl = 0, size = 0; - if (base) { + if (on) { unsigned int width = intel_crtc->base.cursor->state->crtc_w; unsigned int height = intel_crtc->base.cursor->state->crtc_h; unsigned int stride = roundup_pow_of_two(width) * 4; @@ -9972,16 +9987,15 @@ static void i845_update_cursor(struct drm_crtc *crtc, u32 base) } } -static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base) +static void i9xx_update_cursor(struct drm_crtc *crtc, u32 base, bool on) { struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = dev->dev_private; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); int pipe = intel_crtc->pipe; - uint32_t cntl; + uint32_t cntl = 0; - cntl = 0; - if (base) { + if (on) { cntl = MCURSOR_GAMMA_ENABLE; switch (intel_crtc->base.cursor->state->crtc_w) { case 64: @@ -10032,18 +10046,17 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, int y = cursor_state->crtc_y; u32 base = 0, pos = 0; - if (on) - base = intel_crtc->cursor_addr; + base = intel_crtc->cursor_addr; if (x >= intel_crtc->config->pipe_src_w) - base = 0; + on = false; if (y >= intel_crtc->config->pipe_src_h) - base = 0; + on = false; if (x < 0) { if (x + cursor_state->crtc_w <= 0) - base = 0; + on = false; pos |= CURSOR_POS_SIGN << CURSOR_X_SHIFT; x = -x; @@ -10052,16 +10065,13 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, if (y < 0) { if (y + cursor_state->crtc_h <= 0) - base = 0; + on = false; pos |= CURSOR_POS_SIGN << CURSOR_Y_SHIFT; y = -y; } pos |= y << CURSOR_Y_SHIFT; - if (base == 0 && intel_crtc->cursor_base == 0) - return; - I915_WRITE(CURPOS(pipe), pos); /* ILK+ do this automagically */ @@ -10072,9 +10082,9 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc, } if (IS_845G(dev) || IS_I865G(dev)) - i845_update_cursor(crtc, base); + i845_update_cursor(crtc, base, on); else - i9xx_update_cursor(crtc, base); + i9xx_update_cursor(crtc, base, on); } static bool cursor_size_ok(struct drm_device *dev, @@ -12113,18 +12123,22 @@ static void intel_dump_pipe_config(struct intel_crtc *crtc, static bool check_digital_port_conflicts(struct drm_atomic_state *state) { struct drm_device *dev = state->dev; - struct intel_encoder *encoder; struct drm_connector *connector; - struct drm_connector_state *connector_state; unsigned int used_ports = 0; - int i; /* * Walk the connector list instead of the encoder * list to detect the problem on ddi platforms * where there's just one encoder per digital port. */ - for_each_connector_in_state(state, connector, connector_state, i) { + drm_for_each_connector(connector, dev) { + struct drm_connector_state *connector_state; + struct intel_encoder *encoder; + + connector_state = drm_atomic_get_existing_connector_state(state, connector); + if (!connector_state) + connector_state = connector->state; + if (!connector_state->best_encoder) continue; @@ -13718,6 +13732,7 @@ intel_check_cursor_plane(struct drm_plane *plane, struct drm_crtc *crtc = crtc_state->base.crtc; struct drm_framebuffer *fb = state->base.fb; struct drm_i915_gem_object *obj = intel_fb_obj(fb); + enum pipe pipe = to_intel_plane(plane)->pipe; unsigned stride; int ret; @@ -13751,6 +13766,22 @@ intel_check_cursor_plane(struct drm_plane *plane, return -EINVAL; } + /* + * There's something wrong with the cursor on CHV pipe C. + * If it straddles the left edge of the screen then + * moving it away from the edge or disabling it often + * results in a pipe underrun, and often that can lead to + * dead pipe (constant underrun reported, and it scans + * out just a solid color). To recover from that, the + * display power well must be turned off and on again. + * Refuse the put the cursor into that compromised position. + */ + if (IS_CHERRYVIEW(plane->dev) && pipe == PIPE_C && + state->visible && state->base.crtc_x < 0) { + DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n"); + return -EINVAL; + } + return 0; } @@ -13774,9 +13805,6 @@ intel_commit_cursor_plane(struct drm_plane *plane, crtc = crtc ? crtc : plane->crtc; intel_crtc = to_intel_crtc(crtc); - if (intel_crtc->cursor_bo == obj) - goto update; - if (!obj) addr = 0; else if (!INTEL_INFO(dev)->cursor_needs_physical) @@ -13785,9 +13813,7 @@ intel_commit_cursor_plane(struct drm_plane *plane, addr = obj->phys_handle->busaddr; intel_crtc->cursor_addr = addr; - intel_crtc->cursor_bo = obj; -update: if (crtc->state->active) intel_crtc_update_cursor(crtc, state->visible); } diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index f2a1142bff34..0d00f07b7163 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -550,7 +550,6 @@ struct intel_crtc { int adjusted_x; int adjusted_y; - struct drm_i915_gem_object *cursor_bo; uint32_t cursor_addr; uint32_t cursor_cntl; uint32_t cursor_size; diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 81cdd9ff3892..e6c035b0fc1c 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1374,17 +1374,18 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector); struct drm_i915_private *dev_priv = to_i915(connector->dev); bool live_status = false; - unsigned int retry = 3; + unsigned int try; DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n", connector->base.id, connector->name); intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); - while (!live_status && --retry) { + for (try = 0; !live_status && try < 9; try++) { + if (try) + msleep(10); live_status = intel_digital_port_connected(dev_priv, hdmi_to_dig_port(intel_hdmi)); - mdelay(10); } if (!live_status) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c index ffa902ece872..05a895496fc6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/nv40.c @@ -156,6 +156,7 @@ nv40_gr_chan_new(struct nvkm_gr *base, struct nvkm_fifo_chan *fifoch, return -ENOMEM; nvkm_object_ctor(&nv40_gr_chan, oclass, &chan->object); chan->gr = gr; + chan->fifo = fifoch; *pobject = &chan->object; spin_lock_irqsave(&chan->gr->base.engine.lock, flags); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c index 43006db6fd58..80fed7e78dcb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/fan.c @@ -83,6 +83,7 @@ nvbios_fan_parse(struct nvkm_bios *bios, struct nvbios_therm_fan *fan) fan->type = NVBIOS_THERM_FAN_UNK; } + fan->fan_mode = NVBIOS_THERM_FAN_LINEAR; fan->min_duty = nvbios_rd08(bios, data + 0x02); fan->max_duty = nvbios_rd08(bios, data + 0x03); diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index c5628a42170a..a8bdcb5292f5 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -202,8 +202,15 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) * d is always 6 on Keystone I2C controller */ - /* get minimum of 7 MHz clock, but max of 12 MHz */ - psc = (input_clock / 7000000) - 1; + /* + * Both Davinci and current Keystone User Guides recommend a value + * between 7MHz and 12MHz. In reality 7MHz module clock doesn't + * always produce enough margin between SDA and SCL transitions. + * Measurements show that the higher the module clock is, the + * bigger is the margin, providing more reliable communication. + * So we better target for 12MHz. + */ + psc = (input_clock / 12000000) - 1; if ((input_clock / (psc + 1)) > 12000000) psc++; /* better to run under spec than over */ d = (psc >= 2) ? 5 : 7 - psc; diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c index 8c48b27ba059..de7fbbb374cd 100644 --- a/drivers/i2c/busses/i2c-designware-core.c +++ b/drivers/i2c/busses/i2c-designware-core.c @@ -813,6 +813,12 @@ static irqreturn_t i2c_dw_isr(int this_irq, void *dev_id) tx_aborted: if ((stat & (DW_IC_INTR_TX_ABRT | DW_IC_INTR_STOP_DET)) || dev->msg_err) complete(&dev->cmd_complete); + else if (unlikely(dev->accessor_flags & ACCESS_INTR_MASK)) { + /* workaround to trigger pending interrupt */ + stat = dw_readl(dev, DW_IC_INTR_MASK); + i2c_dw_disable_int(dev); + dw_writel(dev, stat, DW_IC_INTR_MASK); + } return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h index 1d50898e7b24..9ffb63a60f95 100644 --- a/drivers/i2c/busses/i2c-designware-core.h +++ b/drivers/i2c/busses/i2c-designware-core.h @@ -111,6 +111,7 @@ struct dw_i2c_dev { #define ACCESS_SWAP 0x00000001 #define ACCESS_16BIT 0x00000002 +#define ACCESS_INTR_MASK 0x00000004 extern int i2c_dw_init(struct dw_i2c_dev *dev); extern void i2c_dw_disable(struct dw_i2c_dev *dev); diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 809579ecb5a4..6b00061c3746 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -93,6 +93,7 @@ static void dw_i2c_acpi_params(struct platform_device *pdev, char method[], static int dw_i2c_acpi_configure(struct platform_device *pdev) { struct dw_i2c_dev *dev = platform_get_drvdata(pdev); + const struct acpi_device_id *id; dev->adapter.nr = -1; dev->tx_fifo_depth = 32; @@ -106,6 +107,10 @@ static int dw_i2c_acpi_configure(struct platform_device *pdev) dw_i2c_acpi_params(pdev, "FMCN", &dev->fs_hcnt, &dev->fs_lcnt, &dev->sda_hold_time); + id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev); + if (id && id->driver_data) + dev->accessor_flags |= (u32)id->driver_data; + return 0; } @@ -116,7 +121,7 @@ static const struct acpi_device_id dw_i2c_acpi_match[] = { { "INT3433", 0 }, { "80860F41", 0 }, { "808622C1", 0 }, - { "AMD0010", 0 }, + { "AMD0010", ACCESS_INTR_MASK }, { } }; MODULE_DEVICE_TABLE(acpi, dw_i2c_acpi_match); @@ -240,12 +245,10 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) } r = i2c_dw_probe(dev); - if (r) { + if (r && !dev->pm_runtime_disabled) pm_runtime_disable(&pdev->dev); - return r; - } - return 0; + return r; } static int dw_i2c_plat_remove(struct platform_device *pdev) @@ -260,7 +263,8 @@ static int dw_i2c_plat_remove(struct platform_device *pdev) pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_sync(&pdev->dev); - pm_runtime_disable(&pdev->dev); + if (!dev->pm_runtime_disabled) + pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 9bb0b056b25f..d4d853680ae4 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -1119,6 +1119,8 @@ static int i2c_imx_probe(struct platform_device *pdev) i2c_imx, IMX_I2C_I2CR); imx_i2c_write_reg(i2c_imx->hwdata->i2sr_clr_opcode, i2c_imx, IMX_I2C_I2SR); + i2c_imx_init_recovery_info(i2c_imx, pdev); + /* Add I2C adapter */ ret = i2c_add_numbered_adapter(&i2c_imx->adapter); if (ret < 0) { @@ -1126,8 +1128,6 @@ static int i2c_imx_probe(struct platform_device *pdev) goto clk_disable; } - i2c_imx_init_recovery_info(i2c_imx, pdev); - /* Set up platform driver data */ platform_set_drvdata(pdev, i2c_imx); clk_disable_unprepare(i2c_imx->clk); diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index 5801227b97ab..43207f52e5a3 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -146,6 +146,8 @@ struct mv64xxx_i2c_data { bool errata_delay; struct reset_control *rstc; bool irq_clear_inverted; + /* Clk div is 2 to the power n, not 2 to the power n + 1 */ + bool clk_n_base_0; }; static struct mv64xxx_i2c_regs mv64xxx_i2c_regs_mv64xxx = { @@ -757,25 +759,29 @@ MODULE_DEVICE_TABLE(of, mv64xxx_i2c_of_match_table); #ifdef CONFIG_OF #ifdef CONFIG_HAVE_CLK static int -mv64xxx_calc_freq(const int tclk, const int n, const int m) +mv64xxx_calc_freq(struct mv64xxx_i2c_data *drv_data, + const int tclk, const int n, const int m) { - return tclk / (10 * (m + 1) * (2 << n)); + if (drv_data->clk_n_base_0) + return tclk / (10 * (m + 1) * (1 << n)); + else + return tclk / (10 * (m + 1) * (2 << n)); } static bool -mv64xxx_find_baud_factors(const u32 req_freq, const u32 tclk, u32 *best_n, - u32 *best_m) +mv64xxx_find_baud_factors(struct mv64xxx_i2c_data *drv_data, + const u32 req_freq, const u32 tclk) { int freq, delta, best_delta = INT_MAX; int m, n; for (n = 0; n <= 7; n++) for (m = 0; m <= 15; m++) { - freq = mv64xxx_calc_freq(tclk, n, m); + freq = mv64xxx_calc_freq(drv_data, tclk, n, m); delta = req_freq - freq; if (delta >= 0 && delta < best_delta) { - *best_m = m; - *best_n = n; + drv_data->freq_m = m; + drv_data->freq_n = n; best_delta = delta; } if (best_delta == 0) @@ -813,8 +819,11 @@ mv64xxx_of_config(struct mv64xxx_i2c_data *drv_data, if (of_property_read_u32(np, "clock-frequency", &bus_freq)) bus_freq = 100000; /* 100kHz by default */ - if (!mv64xxx_find_baud_factors(bus_freq, tclk, - &drv_data->freq_n, &drv_data->freq_m)) { + if (of_device_is_compatible(np, "allwinner,sun4i-a10-i2c") || + of_device_is_compatible(np, "allwinner,sun6i-a31-i2c")) + drv_data->clk_n_base_0 = true; + + if (!mv64xxx_find_baud_factors(drv_data, bus_freq, tclk)) { rc = -EINVAL; goto out; } diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index b0ae560b38c3..599c0d7bd906 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -576,7 +576,7 @@ static int rcar_reg_slave(struct i2c_client *slave) if (slave->flags & I2C_CLIENT_TEN) return -EAFNOSUPPORT; - pm_runtime_forbid(rcar_i2c_priv_to_dev(priv)); + pm_runtime_get_sync(rcar_i2c_priv_to_dev(priv)); priv->slave = slave; rcar_i2c_write(priv, ICSAR, slave->addr); @@ -598,7 +598,7 @@ static int rcar_unreg_slave(struct i2c_client *slave) priv->slave = NULL; - pm_runtime_allow(rcar_i2c_priv_to_dev(priv)); + pm_runtime_put(rcar_i2c_priv_to_dev(priv)); return 0; } diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index c1935ebd6a9c..9096d17beb5b 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -908,7 +908,7 @@ static int rk3x_i2c_probe(struct platform_device *pdev) &i2c->scl_fall_ns)) i2c->scl_fall_ns = 300; if (of_property_read_u32(pdev->dev.of_node, "i2c-sda-falling-time-ns", - &i2c->scl_fall_ns)) + &i2c->sda_fall_ns)) i2c->sda_fall_ns = i2c->scl_fall_ns; strlcpy(i2c->adap.name, "rk3x-i2c", sizeof(i2c->adap.name)); diff --git a/drivers/i2c/busses/i2c-st.c b/drivers/i2c/busses/i2c-st.c index ea72dca32fdf..25020ec777c9 100644 --- a/drivers/i2c/busses/i2c-st.c +++ b/drivers/i2c/busses/i2c-st.c @@ -822,7 +822,7 @@ static int st_i2c_probe(struct platform_device *pdev) adap = &i2c_dev->adap; i2c_set_adapdata(adap, i2c_dev); - snprintf(adap->name, sizeof(adap->name), "ST I2C(0x%pa)", &res->start); + snprintf(adap->name, sizeof(adap->name), "ST I2C(%pa)", &res->start); adap->owner = THIS_MODULE; adap->timeout = 2 * HZ; adap->retries = 0; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index d2d5d004f16d..2d762a2ecd81 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1265,15 +1265,17 @@ static bool cma_protocol_roce(const struct rdma_cm_id *id) return cma_protocol_roce_dev_port(device, port_num); } -static bool cma_match_net_dev(const struct rdma_id_private *id_priv, - const struct net_device *net_dev) +static bool cma_match_net_dev(const struct rdma_cm_id *id, + const struct net_device *net_dev, + u8 port_num) { - const struct rdma_addr *addr = &id_priv->id.route.addr; + const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request or a RoCE request */ - return addr->src_addr.ss_family == AF_IB || - cma_protocol_roce(&id_priv->id); + return (!id->port_num || id->port_num == port_num) && + (addr->src_addr.ss_family == AF_IB || + cma_protocol_roce_dev_port(id->device, port_num)); return !addr->dev_addr.bound_dev_if || (net_eq(dev_net(net_dev), addr->dev_addr.net) && @@ -1295,13 +1297,13 @@ static struct rdma_id_private *cma_find_listener( hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && - cma_match_net_dev(id_priv, net_dev)) + cma_match_net_dev(&id_priv->id, net_dev, req->port)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_list) { if (id_priv_dev->id.device == cm_id->device && - cma_match_net_dev(id_priv_dev, net_dev)) + cma_match_net_dev(&id_priv_dev->id, net_dev, req->port)) return id_priv_dev; } } diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c index 8d133c40fa0e..c394376ebe06 100644 --- a/drivers/infiniband/hw/mlx4/srq.c +++ b/drivers/infiniband/hw/mlx4/srq.c @@ -286,7 +286,7 @@ int mlx4_ib_destroy_srq(struct ib_srq *srq) mlx4_ib_db_unmap_user(to_mucontext(srq->uobject->context), &msrq->db); ib_umem_release(msrq->umem); } else { - kfree(msrq->wrid); + kvfree(msrq->wrid); mlx4_buf_free(dev->dev, msrq->msrq.max << msrq->msrq.wqe_shift, &msrq->buf); mlx4_db_free(dev->dev, &msrq->db); diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h index ae80590aabdf..040bb8b5cb15 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma.h @@ -232,6 +232,10 @@ struct phy_info { u16 interface_type; }; +enum ocrdma_flags { + OCRDMA_FLAGS_LINK_STATUS_INIT = 0x01 +}; + struct ocrdma_dev { struct ib_device ibdev; struct ocrdma_dev_attr attr; @@ -287,6 +291,7 @@ struct ocrdma_dev { atomic_t update_sl; u16 pvid; u32 asic_id; + u32 flags; ulong last_stats_time; struct mutex stats_lock; /* provide synch for debugfs operations */ @@ -591,4 +596,9 @@ static inline u8 ocrdma_is_enabled_and_synced(u32 state) (state & OCRDMA_STATE_FLAG_SYNC); } +static inline u8 ocrdma_get_ae_link_state(u32 ae_state) +{ + return ((ae_state & OCRDMA_AE_LSC_LS_MASK) >> OCRDMA_AE_LSC_LS_SHIFT); +} + #endif diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 30f67bebffa3..283ca842ff74 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -579,6 +579,8 @@ static int ocrdma_mbx_create_mq(struct ocrdma_dev *dev, cmd->async_event_bitmap = BIT(OCRDMA_ASYNC_GRP5_EVE_CODE); cmd->async_event_bitmap |= BIT(OCRDMA_ASYNC_RDMA_EVE_CODE); + /* Request link events on this MQ. */ + cmd->async_event_bitmap |= BIT(OCRDMA_ASYNC_LINK_EVE_CODE); cmd->async_cqid_ringsize = cq->id; cmd->async_cqid_ringsize |= (ocrdma_encoded_q_len(mq->len) << @@ -819,20 +821,42 @@ static void ocrdma_process_grp5_aync(struct ocrdma_dev *dev, } } +static void ocrdma_process_link_state(struct ocrdma_dev *dev, + struct ocrdma_ae_mcqe *cqe) +{ + struct ocrdma_ae_lnkst_mcqe *evt; + u8 lstate; + + evt = (struct ocrdma_ae_lnkst_mcqe *)cqe; + lstate = ocrdma_get_ae_link_state(evt->speed_state_ptn); + + if (!(lstate & OCRDMA_AE_LSC_LLINK_MASK)) + return; + + if (dev->flags & OCRDMA_FLAGS_LINK_STATUS_INIT) + ocrdma_update_link_state(dev, (lstate & OCRDMA_LINK_ST_MASK)); +} + static void ocrdma_process_acqe(struct ocrdma_dev *dev, void *ae_cqe) { /* async CQE processing */ struct ocrdma_ae_mcqe *cqe = ae_cqe; u32 evt_code = (cqe->valid_ae_event & OCRDMA_AE_MCQE_EVENT_CODE_MASK) >> OCRDMA_AE_MCQE_EVENT_CODE_SHIFT; - - if (evt_code == OCRDMA_ASYNC_RDMA_EVE_CODE) + switch (evt_code) { + case OCRDMA_ASYNC_LINK_EVE_CODE: + ocrdma_process_link_state(dev, cqe); + break; + case OCRDMA_ASYNC_RDMA_EVE_CODE: ocrdma_dispatch_ibevent(dev, cqe); - else if (evt_code == OCRDMA_ASYNC_GRP5_EVE_CODE) + break; + case OCRDMA_ASYNC_GRP5_EVE_CODE: ocrdma_process_grp5_aync(dev, cqe); - else + break; + default: pr_err("%s(%d) invalid evt code=0x%x\n", __func__, dev->id, evt_code); + } } static void ocrdma_process_mcqe(struct ocrdma_dev *dev, struct ocrdma_mcqe *cqe) @@ -1363,7 +1387,8 @@ mbx_err: return status; } -int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed) +int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed, + u8 *lnk_state) { int status = -ENOMEM; struct ocrdma_get_link_speed_rsp *rsp; @@ -1384,8 +1409,11 @@ int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed) goto mbx_err; rsp = (struct ocrdma_get_link_speed_rsp *)cmd; - *lnk_speed = (rsp->pflt_pps_ld_pnum & OCRDMA_PHY_PS_MASK) - >> OCRDMA_PHY_PS_SHIFT; + if (lnk_speed) + *lnk_speed = (rsp->pflt_pps_ld_pnum & OCRDMA_PHY_PS_MASK) + >> OCRDMA_PHY_PS_SHIFT; + if (lnk_state) + *lnk_state = (rsp->res_lnk_st & OCRDMA_LINK_ST_MASK); mbx_err: kfree(cmd); @@ -2515,9 +2543,10 @@ static int ocrdma_set_av_params(struct ocrdma_qp *qp, ocrdma_cpu_to_le32(&cmd->params.sgid[0], sizeof(cmd->params.sgid)); cmd->params.vlan_dmac_b4_to_b5 = mac_addr[4] | (mac_addr[5] << 8); - if (vlan_id < 0x1000) { - if (dev->pfc_state) { - vlan_id = 0; + if (vlan_id == 0xFFFF) + vlan_id = 0; + if (vlan_id || dev->pfc_state) { + if (!vlan_id) { pr_err("ocrdma%d:Using VLAN with PFC is recommended\n", dev->id); pr_err("ocrdma%d:Using VLAN 0 for this connection\n", diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h index 7ed885c1851e..ebc1f442aec3 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h @@ -106,7 +106,8 @@ void ocrdma_ring_cq_db(struct ocrdma_dev *, u16 cq_id, bool armed, bool solicited, u16 cqe_popped); /* verbs specific mailbox commands */ -int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed); +int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed, + u8 *lnk_st); int ocrdma_query_config(struct ocrdma_dev *, struct ocrdma_mbx_query_config *config); @@ -153,5 +154,6 @@ char *port_speed_string(struct ocrdma_dev *dev); void ocrdma_init_service_level(struct ocrdma_dev *); void ocrdma_alloc_pd_pool(struct ocrdma_dev *dev); void ocrdma_free_pd_range(struct ocrdma_dev *dev); +void ocrdma_update_link_state(struct ocrdma_dev *dev, u8 lstate); #endif /* __OCRDMA_HW_H__ */ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 62b7009daa6c..3afb40b85159 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -290,6 +290,7 @@ static void ocrdma_remove_sysfiles(struct ocrdma_dev *dev) static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info) { int status = 0, i; + u8 lstate = 0; struct ocrdma_dev *dev; dev = (struct ocrdma_dev *)ib_alloc_device(sizeof(struct ocrdma_dev)); @@ -319,6 +320,11 @@ static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info) if (status) goto alloc_err; + /* Query Link state and update */ + status = ocrdma_mbx_get_link_speed(dev, NULL, &lstate); + if (!status) + ocrdma_update_link_state(dev, lstate); + for (i = 0; i < ARRAY_SIZE(ocrdma_attributes); i++) if (device_create_file(&dev->ibdev.dev, ocrdma_attributes[i])) goto sysfs_err; @@ -373,7 +379,7 @@ static void ocrdma_remove(struct ocrdma_dev *dev) ocrdma_remove_free(dev); } -static int ocrdma_open(struct ocrdma_dev *dev) +static int ocrdma_dispatch_port_active(struct ocrdma_dev *dev) { struct ib_event port_event; @@ -384,32 +390,9 @@ static int ocrdma_open(struct ocrdma_dev *dev) return 0; } -static int ocrdma_close(struct ocrdma_dev *dev) +static int ocrdma_dispatch_port_error(struct ocrdma_dev *dev) { - int i; - struct ocrdma_qp *qp, **cur_qp; struct ib_event err_event; - struct ib_qp_attr attrs; - int attr_mask = IB_QP_STATE; - - attrs.qp_state = IB_QPS_ERR; - mutex_lock(&dev->dev_lock); - if (dev->qp_tbl) { - cur_qp = dev->qp_tbl; - for (i = 0; i < OCRDMA_MAX_QP; i++) { - qp = cur_qp[i]; - if (qp && qp->ibqp.qp_type != IB_QPT_GSI) { - /* change the QP state to ERROR */ - _ocrdma_modify_qp(&qp->ibqp, &attrs, attr_mask); - - err_event.event = IB_EVENT_QP_FATAL; - err_event.element.qp = &qp->ibqp; - err_event.device = &dev->ibdev; - ib_dispatch_event(&err_event); - } - } - } - mutex_unlock(&dev->dev_lock); err_event.event = IB_EVENT_PORT_ERR; err_event.element.port_num = 1; @@ -420,7 +403,7 @@ static int ocrdma_close(struct ocrdma_dev *dev) static void ocrdma_shutdown(struct ocrdma_dev *dev) { - ocrdma_close(dev); + ocrdma_dispatch_port_error(dev); ocrdma_remove(dev); } @@ -431,18 +414,28 @@ static void ocrdma_shutdown(struct ocrdma_dev *dev) static void ocrdma_event_handler(struct ocrdma_dev *dev, u32 event) { switch (event) { - case BE_DEV_UP: - ocrdma_open(dev); - break; - case BE_DEV_DOWN: - ocrdma_close(dev); - break; case BE_DEV_SHUTDOWN: ocrdma_shutdown(dev); break; + default: + break; } } +void ocrdma_update_link_state(struct ocrdma_dev *dev, u8 lstate) +{ + if (!(dev->flags & OCRDMA_FLAGS_LINK_STATUS_INIT)) { + dev->flags |= OCRDMA_FLAGS_LINK_STATUS_INIT; + if (!lstate) + return; + } + + if (!lstate) + ocrdma_dispatch_port_error(dev); + else + ocrdma_dispatch_port_active(dev); +} + static struct ocrdma_driver ocrdma_drv = { .name = "ocrdma_driver", .add = ocrdma_add, diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 6a38268bbe9f..99dd6fdf06d7 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -465,8 +465,11 @@ struct ocrdma_ae_qp_mcqe { u32 valid_ae_event; }; -#define OCRDMA_ASYNC_RDMA_EVE_CODE 0x14 -#define OCRDMA_ASYNC_GRP5_EVE_CODE 0x5 +enum ocrdma_async_event_code { + OCRDMA_ASYNC_LINK_EVE_CODE = 0x01, + OCRDMA_ASYNC_GRP5_EVE_CODE = 0x05, + OCRDMA_ASYNC_RDMA_EVE_CODE = 0x14 +}; enum ocrdma_async_grp5_events { OCRDMA_ASYNC_EVENT_QOS_VALUE = 0x01, @@ -489,6 +492,44 @@ enum OCRDMA_ASYNC_EVENT_TYPE { OCRDMA_MAX_ASYNC_ERRORS }; +struct ocrdma_ae_lnkst_mcqe { + u32 speed_state_ptn; + u32 qos_reason_falut; + u32 evt_tag; + u32 valid_ae_event; +}; + +enum { + OCRDMA_AE_LSC_PORT_NUM_MASK = 0x3F, + OCRDMA_AE_LSC_PT_SHIFT = 0x06, + OCRDMA_AE_LSC_PT_MASK = (0x03 << + OCRDMA_AE_LSC_PT_SHIFT), + OCRDMA_AE_LSC_LS_SHIFT = 0x08, + OCRDMA_AE_LSC_LS_MASK = (0xFF << + OCRDMA_AE_LSC_LS_SHIFT), + OCRDMA_AE_LSC_LD_SHIFT = 0x10, + OCRDMA_AE_LSC_LD_MASK = (0xFF << + OCRDMA_AE_LSC_LD_SHIFT), + OCRDMA_AE_LSC_PPS_SHIFT = 0x18, + OCRDMA_AE_LSC_PPS_MASK = (0xFF << + OCRDMA_AE_LSC_PPS_SHIFT), + OCRDMA_AE_LSC_PPF_MASK = 0xFF, + OCRDMA_AE_LSC_ER_SHIFT = 0x08, + OCRDMA_AE_LSC_ER_MASK = (0xFF << + OCRDMA_AE_LSC_ER_SHIFT), + OCRDMA_AE_LSC_QOS_SHIFT = 0x10, + OCRDMA_AE_LSC_QOS_MASK = (0xFFFF << + OCRDMA_AE_LSC_QOS_SHIFT) +}; + +enum { + OCRDMA_AE_LSC_PLINK_DOWN = 0x00, + OCRDMA_AE_LSC_PLINK_UP = 0x01, + OCRDMA_AE_LSC_LLINK_DOWN = 0x02, + OCRDMA_AE_LSC_LLINK_MASK = 0x02, + OCRDMA_AE_LSC_LLINK_UP = 0x03 +}; + /* mailbox command request and responses */ enum { OCRDMA_MBX_QUERY_CFG_CQ_OVERFLOW_SHIFT = 2, @@ -676,7 +717,7 @@ enum { OCRDMA_PHY_PFLT_SHIFT = 0x18, OCRDMA_QOS_LNKSP_MASK = 0xFFFF0000, OCRDMA_QOS_LNKSP_SHIFT = 0x10, - OCRDMA_LLST_MASK = 0xFF, + OCRDMA_LINK_ST_MASK = 0x01, OCRDMA_PLFC_MASK = 0x00000400, OCRDMA_PLFC_SHIFT = 0x8, OCRDMA_PLRFC_MASK = 0x00000200, @@ -691,7 +732,7 @@ struct ocrdma_get_link_speed_rsp { u32 pflt_pps_ld_pnum; u32 qos_lsp; - u32 res_lls; + u32 res_lnk_st; }; enum { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 583001bcfb8f..76e96f97b3f6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -171,7 +171,7 @@ static inline void get_link_speed_and_width(struct ocrdma_dev *dev, int status; u8 speed; - status = ocrdma_mbx_get_link_speed(dev, &speed); + status = ocrdma_mbx_get_link_speed(dev, &speed, NULL); if (status) speed = OCRDMA_PHYS_LINK_SPEED_ZERO; diff --git a/drivers/input/joystick/db9.c b/drivers/input/joystick/db9.c index 932d07307454..da326090c2b0 100644 --- a/drivers/input/joystick/db9.c +++ b/drivers/input/joystick/db9.c @@ -592,6 +592,7 @@ static void db9_attach(struct parport *pp) return; } + memset(&db9_parport_cb, 0, sizeof(db9_parport_cb)); db9_parport_cb.flags = PARPORT_FLAG_EXCL; pd = parport_register_dev_model(pp, "db9", &db9_parport_cb, port_idx); diff --git a/drivers/input/joystick/gamecon.c b/drivers/input/joystick/gamecon.c index 5a672dcac0d8..eae14d512353 100644 --- a/drivers/input/joystick/gamecon.c +++ b/drivers/input/joystick/gamecon.c @@ -951,6 +951,7 @@ static void gc_attach(struct parport *pp) pads = gc_cfg[port_idx].args + 1; n_pads = gc_cfg[port_idx].nargs - 1; + memset(&gc_parport_cb, 0, sizeof(gc_parport_cb)); gc_parport_cb.flags = PARPORT_FLAG_EXCL; pd = parport_register_dev_model(pp, "gamecon", &gc_parport_cb, diff --git a/drivers/input/joystick/turbografx.c b/drivers/input/joystick/turbografx.c index 9f5bca26bd2f..77f575dd0901 100644 --- a/drivers/input/joystick/turbografx.c +++ b/drivers/input/joystick/turbografx.c @@ -181,6 +181,7 @@ static void tgfx_attach(struct parport *pp) n_buttons = tgfx_cfg[port_idx].args + 1; n_devs = tgfx_cfg[port_idx].nargs - 1; + memset(&tgfx_parport_cb, 0, sizeof(tgfx_parport_cb)); tgfx_parport_cb.flags = PARPORT_FLAG_EXCL; pd = parport_register_dev_model(pp, "turbografx", &tgfx_parport_cb, diff --git a/drivers/input/joystick/walkera0701.c b/drivers/input/joystick/walkera0701.c index 9c07fe911075..70a893a17467 100644 --- a/drivers/input/joystick/walkera0701.c +++ b/drivers/input/joystick/walkera0701.c @@ -218,6 +218,7 @@ static void walkera0701_attach(struct parport *pp) w->parport = pp; + memset(&walkera0701_parport_cb, 0, sizeof(walkera0701_parport_cb)); walkera0701_parport_cb.flags = PARPORT_FLAG_EXCL; walkera0701_parport_cb.irq_func = walkera0701_irq_handler; walkera0701_parport_cb.private = w; diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c index 4bf678541496..d5994a745ffa 100644 --- a/drivers/input/misc/arizona-haptics.c +++ b/drivers/input/misc/arizona-haptics.c @@ -97,8 +97,7 @@ static void arizona_haptics_work(struct work_struct *work) ret = regmap_update_bits(arizona->regmap, ARIZONA_HAPTICS_CONTROL_1, - ARIZONA_HAP_CTRL_MASK, - 1 << ARIZONA_HAP_CTRL_SHIFT); + ARIZONA_HAP_CTRL_MASK, 0); if (ret != 0) { dev_err(arizona->dev, "Failed to stop haptics: %d\n", ret); diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 5e1665bbaa0b..2f589857a039 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -41,6 +41,7 @@ #define DRIVER_NAME "elan_i2c" #define ELAN_DRIVER_VERSION "1.6.1" +#define ELAN_VENDOR_ID 0x04f3 #define ETP_MAX_PRESSURE 255 #define ETP_FWIDTH_REDUCE 90 #define ETP_FINGER_WIDTH 15 @@ -914,6 +915,8 @@ static int elan_setup_input_device(struct elan_tp_data *data) input->name = "Elan Touchpad"; input->id.bustype = BUS_I2C; + input->id.vendor = ELAN_VENDOR_ID; + input->id.product = data->product_id; input_set_drvdata(input, data); error = input_mt_init_slots(input, ETP_MAX_FINGERS, diff --git a/drivers/input/serio/parkbd.c b/drivers/input/serio/parkbd.c index 92c31b8f8fb4..1edfac78d4ac 100644 --- a/drivers/input/serio/parkbd.c +++ b/drivers/input/serio/parkbd.c @@ -145,6 +145,7 @@ static int parkbd_getport(struct parport *pp) { struct pardev_cb parkbd_parport_cb; + memset(&parkbd_parport_cb, 0, sizeof(parkbd_parport_cb)); parkbd_parport_cb.irq_func = parkbd_interrupt; parkbd_parport_cb.flags = PARPORT_FLAG_EXCL; diff --git a/drivers/input/tablet/aiptek.c b/drivers/input/tablet/aiptek.c index e7f966da6efa..78ca44840d60 100644 --- a/drivers/input/tablet/aiptek.c +++ b/drivers/input/tablet/aiptek.c @@ -1819,6 +1819,14 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) input_set_abs_params(inputdev, ABS_TILT_Y, AIPTEK_TILT_MIN, AIPTEK_TILT_MAX, 0, 0); input_set_abs_params(inputdev, ABS_WHEEL, AIPTEK_WHEEL_MIN, AIPTEK_WHEEL_MAX - 1, 0, 0); + /* Verify that a device really has an endpoint */ + if (intf->altsetting[0].desc.bNumEndpoints < 1) { + dev_err(&intf->dev, + "interface has %d endpoints, but must have minimum 1\n", + intf->altsetting[0].desc.bNumEndpoints); + err = -EINVAL; + goto fail3; + } endpoint = &intf->altsetting[0].endpoint[0].desc; /* Go set up our URB, which is called when the tablet receives @@ -1861,6 +1869,7 @@ aiptek_probe(struct usb_interface *intf, const struct usb_device_id *id) if (i == ARRAY_SIZE(speeds)) { dev_info(&intf->dev, "Aiptek tried all speeds, no sane response\n"); + err = -EINVAL; goto fail3; } diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index c5622058c22b..2d5794ec338b 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -2487,6 +2487,31 @@ static struct mxt_acpi_platform_data samus_platform_data[] = { { } }; +static unsigned int chromebook_tp_buttons[] = { + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + KEY_RESERVED, + BTN_LEFT +}; + +static struct mxt_acpi_platform_data chromebook_platform_data[] = { + { + /* Touchpad */ + .hid = "ATML0000", + .pdata = { + .t19_num_keys = ARRAY_SIZE(chromebook_tp_buttons), + .t19_keymap = chromebook_tp_buttons, + }, + }, + { + /* Touchscreen */ + .hid = "ATML0001", + }, + { } +}; + static const struct dmi_system_id mxt_dmi_table[] = { { /* 2015 Google Pixel */ @@ -2497,6 +2522,14 @@ static const struct dmi_system_id mxt_dmi_table[] = { }, .driver_data = samus_platform_data, }, + { + /* Other Google Chromebooks */ + .ident = "Chromebook", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), + }, + .driver_data = chromebook_platform_data, + }, { } }; @@ -2701,6 +2734,7 @@ static const struct i2c_device_id mxt_id[] = { { "qt602240_ts", 0 }, { "atmel_mxt_ts", 0 }, { "atmel_mxt_tp", 0 }, + { "maxtouch", 0 }, { "mXT224", 0 }, { } }; diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 17cc20ef4923..ac09855fa435 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -1316,7 +1316,13 @@ static int __maybe_unused elants_i2c_suspend(struct device *dev) disable_irq(client->irq); - if (device_may_wakeup(dev) || ts->keep_power_in_suspend) { + if (device_may_wakeup(dev)) { + /* + * The device will automatically enter idle mode + * that has reduced power consumption. + */ + ts->wake_irq_enabled = (enable_irq_wake(client->irq) == 0); + } else if (ts->keep_power_in_suspend) { for (retry_cnt = 0; retry_cnt < MAX_RETRIES; retry_cnt++) { error = elants_i2c_send(client, set_sleep_cmd, sizeof(set_sleep_cmd)); @@ -1326,10 +1332,6 @@ static int __maybe_unused elants_i2c_suspend(struct device *dev) dev_err(&client->dev, "suspend command failed: %d\n", error); } - - if (device_may_wakeup(dev)) - ts->wake_irq_enabled = - (enable_irq_wake(client->irq) == 0); } else { elants_i2c_power_off(ts); } @@ -1345,10 +1347,11 @@ static int __maybe_unused elants_i2c_resume(struct device *dev) int retry_cnt; int error; - if (device_may_wakeup(dev) && ts->wake_irq_enabled) - disable_irq_wake(client->irq); - - if (ts->keep_power_in_suspend) { + if (device_may_wakeup(dev)) { + if (ts->wake_irq_enabled) + disable_irq_wake(client->irq); + elants_i2c_sw_reset(client); + } else if (ts->keep_power_in_suspend) { for (retry_cnt = 0; retry_cnt < MAX_RETRIES; retry_cnt++) { error = elants_i2c_send(client, set_active_cmd, sizeof(set_active_cmd)); diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 3a20db4f8604..72d6182666cb 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -21,10 +21,13 @@ #include <linux/device.h> #include <linux/dma-iommu.h> +#include <linux/gfp.h> #include <linux/huge_mm.h> #include <linux/iommu.h> #include <linux/iova.h> #include <linux/mm.h> +#include <linux/scatterlist.h> +#include <linux/vmalloc.h> int iommu_dma_init(void) { @@ -191,6 +194,7 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp) { struct page **pages; unsigned int i = 0, array_size = count * sizeof(*pages); + unsigned int order = MAX_ORDER; if (array_size <= PAGE_SIZE) pages = kzalloc(array_size, GFP_KERNEL); @@ -204,14 +208,15 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, gfp_t gfp) while (count) { struct page *page = NULL; - int j, order = __fls(count); + int j; /* * Higher-order allocations are a convenience rather * than a necessity, hence using __GFP_NORETRY until * falling back to single-page allocations. */ - for (order = min(order, MAX_ORDER); order > 0; order--) { + for (order = min_t(unsigned int, order, __fls(count)); + order > 0; order--) { page = alloc_pages(gfp | __GFP_NORETRY, order); if (!page) continue; @@ -453,7 +458,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, size_t s_offset = iova_offset(iovad, s->offset); size_t s_length = s->length; - sg_dma_address(s) = s->offset; + sg_dma_address(s) = s_offset; sg_dma_len(s) = s_length; s->offset -= s_offset; s_length = iova_align(iovad, s_length + s_offset); diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 8cf605fa9946..dfb868e2d129 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -295,7 +295,7 @@ static struct iommu_gather_ops ipmmu_gather_ops = { static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain) { - phys_addr_t ttbr; + u64 ttbr; /* * Allocate the page table operations. diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c index f434e89e1c7a..a54b339951a3 100644 --- a/drivers/lightnvm/gennvm.c +++ b/drivers/lightnvm/gennvm.c @@ -75,7 +75,7 @@ static int gennvm_block_bb(struct ppa_addr ppa, int nr_blocks, u8 *blks, struct nvm_block *blk; int i; - lun = &gn->luns[(dev->nr_luns * ppa.g.ch) + ppa.g.lun]; + lun = &gn->luns[(dev->luns_per_chnl * ppa.g.ch) + ppa.g.lun]; for (i = 0; i < nr_blocks; i++) { if (blks[i] == 0) diff --git a/drivers/md/md.c b/drivers/md/md.c index 807095f4c793..61aacab424cf 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -314,8 +314,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) */ void mddev_suspend(struct mddev *mddev) { - BUG_ON(mddev->suspended); - mddev->suspended = 1; + if (mddev->suspended++) + return; synchronize_rcu(); wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0); mddev->pers->quiesce(mddev, 1); @@ -326,7 +326,8 @@ EXPORT_SYMBOL_GPL(mddev_suspend); void mddev_resume(struct mddev *mddev) { - mddev->suspended = 0; + if (--mddev->suspended) + return; wake_up(&mddev->sb_wait); mddev->pers->quiesce(mddev, 0); @@ -1652,7 +1653,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->journal_tail = le64_to_cpu(sb->journal_tail); if (mddev->recovery_cp == MaxSector) set_bit(MD_JOURNAL_CLEAN, &mddev->flags); - rdev->raid_disk = mddev->raid_disks; + rdev->raid_disk = 0; break; default: rdev->saved_raid_disk = role; @@ -2773,6 +2774,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) /* Activating a spare .. or possibly reactivating * if we ever get bitmaps working here. */ + int err; if (rdev->raid_disk != -1) return -EBUSY; @@ -2794,9 +2796,15 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) rdev->saved_raid_disk = -1; clear_bit(In_sync, &rdev->flags); clear_bit(Bitmap_sync, &rdev->flags); - remove_and_add_spares(rdev->mddev, rdev); - if (rdev->raid_disk == -1) - return -EBUSY; + err = rdev->mddev->pers-> + hot_add_disk(rdev->mddev, rdev); + if (err) { + rdev->raid_disk = -1; + return err; + } else + sysfs_notify_dirent_safe(rdev->sysfs_state); + if (sysfs_link_rdev(rdev->mddev, rdev)) + /* failure here is OK */; /* don't wakeup anyone, leave that to userspace. */ } else { if (slot >= rdev->mddev->raid_disks && @@ -4318,8 +4326,7 @@ action_store(struct mddev *mddev, const char *page, size_t len) } mddev_unlock(mddev); } - } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) || - test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) + } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; else if (cmd_match(page, "resync")) clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); @@ -4332,8 +4339,12 @@ action_store(struct mddev *mddev, const char *page, size_t len) return -EINVAL; err = mddev_lock(mddev); if (!err) { - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - err = mddev->pers->start_reshape(mddev); + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + err = -EBUSY; + else { + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + err = mddev->pers->start_reshape(mddev); + } mddev_unlock(mddev); } if (err) diff --git a/drivers/md/md.h b/drivers/md/md.h index 2bea51edfab7..ca0b643fe3c1 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -566,7 +566,9 @@ static inline char * mdname (struct mddev * mddev) static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + if (!test_bit(Replacement, &rdev->flags) && + !test_bit(Journal, &rdev->flags) && + mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } else @@ -576,7 +578,9 @@ static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - if (!test_bit(Replacement, &rdev->flags) && mddev->kobj.sd) { + if (!test_bit(Replacement, &rdev->flags) && + !test_bit(Journal, &rdev->flags) && + mddev->kobj.sd) { sprintf(nm, "rd%d", rdev->raid_disk); sysfs_remove_link(&mddev->kobj, nm); } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 41d70bc9ba2f..84e597e1c489 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1946,6 +1946,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) first = i; fbio = r10_bio->devs[i].bio; + fbio->bi_iter.bi_size = r10_bio->sectors << 9; + fbio->bi_iter.bi_idx = 0; vcnt = (r10_bio->sectors + (PAGE_SIZE >> 9) - 1) >> (PAGE_SHIFT - 9); /* now find blocks with errors */ @@ -1989,7 +1991,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) bio_reset(tbio); tbio->bi_vcnt = vcnt; - tbio->bi_iter.bi_size = r10_bio->sectors << 9; + tbio->bi_iter.bi_size = fbio->bi_iter.bi_size; tbio->bi_rw = WRITE; tbio->bi_private = r10_bio; tbio->bi_iter.bi_sector = r10_bio->devs[i].addr; diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c index e87459f6d686..acd1460cf787 100644 --- a/drivers/memory/fsl_ifc.c +++ b/drivers/memory/fsl_ifc.c @@ -22,6 +22,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/compiler.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/slab.h> diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 95c13b2ffa79..ffa288474820 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -426,15 +426,6 @@ int add_mtd_device(struct mtd_info *mtd) mtd->erasesize_mask = (1 << mtd->erasesize_shift) - 1; mtd->writesize_mask = (1 << mtd->writesize_shift) - 1; - if (mtd->dev.parent) { - if (!mtd->owner && mtd->dev.parent->driver) - mtd->owner = mtd->dev.parent->driver->owner; - if (!mtd->name) - mtd->name = dev_name(mtd->dev.parent); - } else { - pr_debug("mtd device won't show a device symlink in sysfs\n"); - } - /* Some chips always power up locked. Unlock them now */ if ((mtd->flags & MTD_WRITEABLE) && (mtd->flags & MTD_POWERUP_LOCK)) { error = mtd_unlock(mtd, 0, mtd->size); @@ -549,6 +540,21 @@ static int mtd_add_device_partitions(struct mtd_info *mtd, return 0; } +/* + * Set a few defaults based on the parent devices, if not provided by the + * driver + */ +static void mtd_set_dev_defaults(struct mtd_info *mtd) +{ + if (mtd->dev.parent) { + if (!mtd->owner && mtd->dev.parent->driver) + mtd->owner = mtd->dev.parent->driver->owner; + if (!mtd->name) + mtd->name = dev_name(mtd->dev.parent); + } else { + pr_debug("mtd device won't show a device symlink in sysfs\n"); + } +} /** * mtd_device_parse_register - parse partitions and register an MTD device. @@ -587,6 +593,8 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, int ret; struct mtd_partition *real_parts = NULL; + mtd_set_dev_defaults(mtd); + ret = parse_mtd_partitions(mtd, types, &real_parts, parser_data); if (ret <= 0 && nr_parts && parts) { real_parts = kmemdup(parts, sizeof(*parts) * nr_parts, diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 49883905a434..32477c4eb421 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -516,8 +516,8 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len) status_old = read_sr(nor); /* Cannot unlock; would unlock larger region than requested */ - if (stm_is_locked_sr(nor, status_old, ofs - mtd->erasesize, - mtd->erasesize)) + if (stm_is_locked_sr(nor, ofs - mtd->erasesize, mtd->erasesize, + status_old)) return -EINVAL; /* @@ -1200,8 +1200,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) if (JEDEC_MFR(info) == SNOR_MFR_ATMEL || JEDEC_MFR(info) == SNOR_MFR_INTEL || - JEDEC_MFR(info) == SNOR_MFR_SST || - JEDEC_MFR(info) == SNOR_MFR_WINBOND) { + JEDEC_MFR(info) == SNOR_MFR_SST) { write_enable(nor); write_sr(nor, 0); } @@ -1217,8 +1216,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode) mtd->_read = spi_nor_read; /* NOR protection support for STmicro/Micron chips and similar */ - if (JEDEC_MFR(info) == SNOR_MFR_MICRON || - JEDEC_MFR(info) == SNOR_MFR_WINBOND) { + if (JEDEC_MFR(info) == SNOR_MFR_MICRON) { nor->flash_lock = stm_lock; nor->flash_unlock = stm_unlock; nor->flash_is_locked = stm_is_locked; diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index b077e43b5ba9..c4cb15a3098c 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -236,7 +236,7 @@ int ubi_debugfs_init(void) dfs_rootdir = debugfs_create_dir("ubi", NULL); if (IS_ERR_OR_NULL(dfs_rootdir)) { - int err = dfs_rootdir ? -ENODEV : PTR_ERR(dfs_rootdir); + int err = dfs_rootdir ? PTR_ERR(dfs_rootdir) : -ENODEV; pr_err("UBI error: cannot create \"ubi\" debugfs directory, error %d\n", err); diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index 1fc23e48fe8e..10cf3b549959 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -1299,7 +1299,7 @@ static int self_check_peb_vid_hdr(const struct ubi_device *ubi, int pnum) if (err && err != UBI_IO_BITFLIPS && !mtd_is_eccerr(err)) goto exit; - crc = crc32(UBI_CRC32_INIT, vid_hdr, UBI_EC_HDR_SIZE_CRC); + crc = crc32(UBI_CRC32_INIT, vid_hdr, UBI_VID_HDR_SIZE_CRC); hdr_crc = be32_to_cpu(vid_hdr->hdr_crc); if (hdr_crc != crc) { ubi_err(ubi, "bad VID header CRC at PEB %d, calculated %#08x, read %#08x", diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index eb4489f9082f..56065632a5b8 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -603,6 +603,7 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, return 0; } +static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk); /** * do_sync_erase - run the erase worker synchronously. * @ubi: UBI device description object @@ -615,20 +616,16 @@ static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, static int do_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e, int vol_id, int lnum, int torture) { - struct ubi_work *wl_wrk; + struct ubi_work wl_wrk; dbg_wl("sync erase of PEB %i", e->pnum); - wl_wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS); - if (!wl_wrk) - return -ENOMEM; - - wl_wrk->e = e; - wl_wrk->vol_id = vol_id; - wl_wrk->lnum = lnum; - wl_wrk->torture = torture; + wl_wrk.e = e; + wl_wrk.vol_id = vol_id; + wl_wrk.lnum = lnum; + wl_wrk.torture = torture; - return erase_worker(ubi, wl_wrk, 0); + return __erase_worker(ubi, &wl_wrk); } /** @@ -1014,7 +1011,7 @@ out_unlock: } /** - * erase_worker - physical eraseblock erase worker function. + * __erase_worker - physical eraseblock erase worker function. * @ubi: UBI device description object * @wl_wrk: the work object * @shutdown: non-zero if the worker has to free memory and exit @@ -1025,8 +1022,7 @@ out_unlock: * needed. Returns zero in case of success and a negative error code in case of * failure. */ -static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, - int shutdown) +static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) { struct ubi_wl_entry *e = wl_wrk->e; int pnum = e->pnum; @@ -1034,21 +1030,11 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, int lnum = wl_wrk->lnum; int err, available_consumed = 0; - if (shutdown) { - dbg_wl("cancel erasure of PEB %d EC %d", pnum, e->ec); - kfree(wl_wrk); - wl_entry_destroy(ubi, e); - return 0; - } - dbg_wl("erase PEB %d EC %d LEB %d:%d", pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum); err = sync_erase(ubi, e, wl_wrk->torture); if (!err) { - /* Fine, we've erased it successfully */ - kfree(wl_wrk); - spin_lock(&ubi->wl_lock); wl_tree_add(e, &ubi->free); ubi->free_count++; @@ -1066,7 +1052,6 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, } ubi_err(ubi, "failed to erase PEB %d, error %d", pnum, err); - kfree(wl_wrk); if (err == -EINTR || err == -ENOMEM || err == -EAGAIN || err == -EBUSY) { @@ -1075,6 +1060,7 @@ static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, /* Re-schedule the LEB for erasure */ err1 = schedule_erase(ubi, e, vol_id, lnum, 0); if (err1) { + wl_entry_destroy(ubi, e); err = err1; goto out_ro; } @@ -1150,6 +1136,25 @@ out_ro: return err; } +static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk, + int shutdown) +{ + int ret; + + if (shutdown) { + struct ubi_wl_entry *e = wl_wrk->e; + + dbg_wl("cancel erasure of PEB %d EC %d", e->pnum, e->ec); + kfree(wl_wrk); + wl_entry_destroy(ubi, e); + return 0; + } + + ret = __erase_worker(ubi, wl_wrk); + kfree(wl_wrk); + return ret; +} + /** * ubi_wl_put_peb - return a PEB to the wear-leveling sub-system. * @ubi: UBI device description object diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index f8d7a2f06950..c82ab87fcbe8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3430,25 +3430,29 @@ static u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb) return rc; } -#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - 3) +/* VXLAN: 4 = 1 (for linear data BD) + 3 (2 for PBD and last BD) */ +#define BNX2X_NUM_VXLAN_TSO_WIN_SUB_BDS 4 + +/* Regular: 3 = 1 (for linear data BD) + 2 (for PBD and last BD) */ +#define BNX2X_NUM_TSO_WIN_SUB_BDS 3 + +#if (MAX_SKB_FRAGS >= MAX_FETCH_BD - BDS_PER_TX_PKT) /* check if packet requires linearization (packet is too fragmented) no need to check fragmentation if page size > 8K (there will be no violation to FW restrictions) */ static int bnx2x_pkt_req_lin(struct bnx2x *bp, struct sk_buff *skb, u32 xmit_type) { - int to_copy = 0; - int hlen = 0; - int first_bd_sz = 0; + int first_bd_sz = 0, num_tso_win_sub = BNX2X_NUM_TSO_WIN_SUB_BDS; + int to_copy = 0, hlen = 0; - /* 3 = 1 (for linear data BD) + 2 (for PBD and last BD) */ - if (skb_shinfo(skb)->nr_frags >= (MAX_FETCH_BD - 3)) { + if (xmit_type & XMIT_GSO_ENC) + num_tso_win_sub = BNX2X_NUM_VXLAN_TSO_WIN_SUB_BDS; + if (skb_shinfo(skb)->nr_frags >= (MAX_FETCH_BD - num_tso_win_sub)) { if (xmit_type & XMIT_GSO) { unsigned short lso_mss = skb_shinfo(skb)->gso_size; - /* Check if LSO packet needs to be copied: - 3 = 1 (for headers BD) + 2 (for PBD and last BD) */ - int wnd_size = MAX_FETCH_BD - 3; + int wnd_size = MAX_FETCH_BD - num_tso_win_sub; /* Number of windows to check */ int num_wnds = skb_shinfo(skb)->nr_frags - wnd_size; int wnd_idx = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c index c308429dd9c7..11dd91e4db56 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c @@ -295,6 +295,10 @@ struct clip_tbl *t4_init_clip_tbl(unsigned int clipt_start, INIT_LIST_HEAD(&ctbl->hash_list[i]); cl_list = t4_alloc_mem(clipt_size*sizeof(struct clip_entry)); + if (!cl_list) { + t4_free_mem(ctbl); + return NULL; + } ctbl->cl_list = (void *)cl_list; for (i = 0; i < clipt_size; i++) { diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index d463563e1f70..6ee78c203eca 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -848,8 +848,6 @@ void be_roce_dev_remove(struct be_adapter *); /* * internal function to open-close roce device during ifup-ifdown. */ -void be_roce_dev_open(struct be_adapter *); -void be_roce_dev_close(struct be_adapter *); void be_roce_dev_shutdown(struct be_adapter *); #endif /* BE_H */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b6ad02909d6b..8a1d9fffd7d6 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -3299,8 +3299,10 @@ static int be_msix_register(struct be_adapter *adapter) return 0; err_msix: - for (i--, eqo = &adapter->eq_obj[i]; i >= 0; i--, eqo--) + for (i--; i >= 0; i--) { + eqo = &adapter->eq_obj[i]; free_irq(be_msix_vec_get(adapter, eqo), eqo); + } dev_warn(&adapter->pdev->dev, "MSIX Request IRQ failed - err %d\n", status); be_msix_disable(adapter); @@ -3432,8 +3434,6 @@ static int be_close(struct net_device *netdev) be_disable_if_filters(adapter); - be_roce_dev_close(adapter); - if (adapter->flags & BE_FLAGS_NAPI_ENABLED) { for_all_evt_queues(adapter, eqo, i) { napi_disable(&eqo->napi); @@ -3601,8 +3601,6 @@ static int be_open(struct net_device *netdev) be_link_status_update(adapter, link_status); netif_tx_start_all_queues(netdev); - be_roce_dev_open(adapter); - #ifdef CONFIG_BE2NET_VXLAN if (skyhawk_chip(adapter)) vxlan_get_rx_port(netdev); diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c index 60368207bf58..4089156a7f5e 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.c +++ b/drivers/net/ethernet/emulex/benet/be_roce.c @@ -116,40 +116,6 @@ void be_roce_dev_remove(struct be_adapter *adapter) } } -static void _be_roce_dev_open(struct be_adapter *adapter) -{ - if (ocrdma_drv && adapter->ocrdma_dev && - ocrdma_drv->state_change_handler) - ocrdma_drv->state_change_handler(adapter->ocrdma_dev, - BE_DEV_UP); -} - -void be_roce_dev_open(struct be_adapter *adapter) -{ - if (be_roce_supported(adapter)) { - mutex_lock(&be_adapter_list_lock); - _be_roce_dev_open(adapter); - mutex_unlock(&be_adapter_list_lock); - } -} - -static void _be_roce_dev_close(struct be_adapter *adapter) -{ - if (ocrdma_drv && adapter->ocrdma_dev && - ocrdma_drv->state_change_handler) - ocrdma_drv->state_change_handler(adapter->ocrdma_dev, - BE_DEV_DOWN); -} - -void be_roce_dev_close(struct be_adapter *adapter) -{ - if (be_roce_supported(adapter)) { - mutex_lock(&be_adapter_list_lock); - _be_roce_dev_close(adapter); - mutex_unlock(&be_adapter_list_lock); - } -} - void be_roce_dev_shutdown(struct be_adapter *adapter) { if (be_roce_supported(adapter)) { @@ -177,8 +143,6 @@ int be_roce_register_driver(struct ocrdma_driver *drv) _be_roce_dev_add(dev); netdev = dev->netdev; - if (netif_running(netdev) && netif_oper_up(netdev)) - _be_roce_dev_open(dev); } mutex_unlock(&be_adapter_list_lock); return 0; diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h index cde6ef905ec4..fde609789483 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.h +++ b/drivers/net/ethernet/emulex/benet/be_roce.h @@ -60,9 +60,7 @@ struct ocrdma_driver { void (*state_change_handler) (struct ocrdma_dev *, u32 new_state); }; -enum { - BE_DEV_UP = 0, - BE_DEV_DOWN = 1, +enum be_roce_event { BE_DEV_SHUTDOWN = 2 }; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 8a083d73efdb..038f9ce391e6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -242,6 +242,13 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) unsigned long flags; u64 ns, zero = 0; + /* mlx4_en_init_timestamp is called for each netdev. + * mdev->ptp_clock is common for all ports, skip initialization if + * was done for other port. + */ + if (mdev->ptp_clock) + return; + rwlock_init(&mdev->clock_lock); memset(&mdev->cycles, 0, sizeof(mdev->cycles)); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 005f910ec955..e0ec280a7fa1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -232,9 +232,6 @@ static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr) if (mdev->pndev[i]) mlx4_en_destroy_netdev(mdev->pndev[i]); - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - mlx4_en_remove_timestamp(mdev); - flush_workqueue(mdev->workqueue); destroy_workqueue(mdev->workqueue); (void) mlx4_mr_free(dev, &mdev->mr); @@ -320,10 +317,6 @@ static void *mlx4_en_add(struct mlx4_dev *dev) mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) mdev->port_cnt++; - /* Initialize time stamp mechanism */ - if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - mlx4_en_init_timestamp(mdev); - /* Set default number of RX rings*/ mlx4_en_set_num_rx_rings(mdev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 886e1bc86374..7869f97de5da 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2072,6 +2072,9 @@ void mlx4_en_destroy_netdev(struct net_device *dev) /* flush any pending task for this netdev */ flush_workqueue(mdev->workqueue); + if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) + mlx4_en_remove_timestamp(mdev); + /* Detach the netdev so tasks would not attempt to access it */ mutex_lock(&mdev->state_lock); mdev->pndev[priv->port] = NULL; @@ -3058,9 +3061,12 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } queue_delayed_work(mdev->workqueue, &priv->stats_task, STATS_DELAY); + /* Initialize time stamp mechanism */ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) - queue_delayed_work(mdev->workqueue, &priv->service_task, - SERVICE_TASK_DELAY); + mlx4_en_init_timestamp(mdev); + + queue_delayed_work(mdev->workqueue, &priv->service_task, + SERVICE_TASK_DELAY); mlx4_en_set_stats_bitmap(mdev->dev, &priv->stats_bitmap, mdev->profile.prof[priv->port].rx_ppp, diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index b83f7c0fcf99..122c2ee3dfe2 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -1937,6 +1937,12 @@ static void refill_rx(struct net_device *dev) break; /* Better luck next round. */ np->rx_dma[entry] = pci_map_single(np->pci_dev, skb->data, buflen, PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(np->pci_dev, + np->rx_dma[entry])) { + dev_kfree_skb_any(skb); + np->rx_skbuff[entry] = NULL; + break; /* Better luck next round. */ + } np->rx_ring[entry].addr = cpu_to_le32(np->rx_dma[entry]); } np->rx_ring[entry].cmd_status = cpu_to_le32(np->rx_buf_sz); @@ -2093,6 +2099,12 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev) np->tx_skbuff[entry] = skb; np->tx_dma[entry] = pci_map_single(np->pci_dev, skb->data,skb->len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(np->pci_dev, np->tx_dma[entry])) { + np->tx_skbuff[entry] = NULL; + dev_kfree_skb_irq(skb); + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } np->tx_ring[entry].addr = cpu_to_le32(np->tx_dma[entry]); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c index b1a452f291ee..34906750b7e7 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c @@ -252,7 +252,7 @@ int qlcnic_83xx_check_vnic_state(struct qlcnic_adapter *adapter) state = QLCRDX(ahw, QLC_83XX_VNIC_STATE); } - if (!idc->vnic_wait_limit) { + if (state != QLCNIC_DEV_NPAR_OPER) { dev_err(&adapter->pdev->dev, "vNIC mode not operational, state check timed out.\n"); return -EIO; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index a5f422f26cb4..daf05155b732 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -772,8 +772,10 @@ int qlcnic_82xx_config_intrpt(struct qlcnic_adapter *adapter, u8 op_type) int i, err = 0; for (i = 0; i < ahw->num_msix; i++) { - qlcnic_alloc_mbx_args(&cmd, adapter, - QLCNIC_CMD_MQ_TX_CONFIG_INTR); + err = qlcnic_alloc_mbx_args(&cmd, adapter, + QLCNIC_CMD_MQ_TX_CONFIG_INTR); + if (err) + return err; type = op_type ? QLCNIC_INTRPT_ADD : QLCNIC_INTRPT_DEL; val = type | (ahw->intr_tbl[i].type << 4); if (ahw->intr_tbl[i].type == QLCNIC_INTRPT_MSIX) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index a0eaf50499a2..6a8fc0f341ff 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1167,6 +1167,7 @@ static void sh_eth_ring_format(struct net_device *ndev) int tx_ringsize = sizeof(*txdesc) * mdp->num_tx_ring; int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; + u32 buf_len; mdp->cur_rx = 0; mdp->cur_tx = 0; @@ -1187,9 +1188,9 @@ static void sh_eth_ring_format(struct net_device *ndev) /* RX descriptor */ rxdesc = &mdp->rx_ring[i]; /* The size of the buffer is a multiple of 32 bytes. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); - dma_addr = dma_map_single(&ndev->dev, skb->data, - rxdesc->buffer_length, + buf_len = ALIGN(mdp->rx_buf_sz, 32); + rxdesc->len = cpu_to_edmac(mdp, buf_len << 16); + dma_addr = dma_map_single(&ndev->dev, skb->data, buf_len, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, dma_addr)) { kfree_skb(skb); @@ -1220,7 +1221,7 @@ static void sh_eth_ring_format(struct net_device *ndev) mdp->tx_skbuff[i] = NULL; txdesc = &mdp->tx_ring[i]; txdesc->status = cpu_to_edmac(mdp, TD_TFP); - txdesc->buffer_length = 0; + txdesc->len = cpu_to_edmac(mdp, 0); if (i == 0) { /* Tx descriptor address set */ sh_eth_write(ndev, mdp->tx_desc_dma, TDLAR); @@ -1429,7 +1430,8 @@ static int sh_eth_txfree(struct net_device *ndev) if (mdp->tx_skbuff[entry]) { dma_unmap_single(&ndev->dev, edmac_to_cpu(mdp, txdesc->addr), - txdesc->buffer_length, DMA_TO_DEVICE); + edmac_to_cpu(mdp, txdesc->len) >> 16, + DMA_TO_DEVICE); dev_kfree_skb_irq(mdp->tx_skbuff[entry]); mdp->tx_skbuff[entry] = NULL; free_num++; @@ -1439,7 +1441,7 @@ static int sh_eth_txfree(struct net_device *ndev) txdesc->status |= cpu_to_edmac(mdp, TD_TDLE); ndev->stats.tx_packets++; - ndev->stats.tx_bytes += txdesc->buffer_length; + ndev->stats.tx_bytes += edmac_to_cpu(mdp, txdesc->len) >> 16; } return free_num; } @@ -1458,6 +1460,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) u32 desc_status; int skbuff_size = mdp->rx_buf_sz + SH_ETH_RX_ALIGN + 32 - 1; dma_addr_t dma_addr; + u32 buf_len; boguscnt = min(boguscnt, *quota); limit = boguscnt; @@ -1466,7 +1469,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) /* RACT bit must be checked before all the following reads */ dma_rmb(); desc_status = edmac_to_cpu(mdp, rxdesc->status); - pkt_len = rxdesc->frame_length; + pkt_len = edmac_to_cpu(mdp, rxdesc->len) & RD_RFL; if (--boguscnt < 0) break; @@ -1532,7 +1535,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) entry = mdp->dirty_rx % mdp->num_rx_ring; rxdesc = &mdp->rx_ring[entry]; /* The size of the buffer is 32 byte boundary. */ - rxdesc->buffer_length = ALIGN(mdp->rx_buf_sz, 32); + buf_len = ALIGN(mdp->rx_buf_sz, 32); + rxdesc->len = cpu_to_edmac(mdp, buf_len << 16); if (mdp->rx_skbuff[entry] == NULL) { skb = netdev_alloc_skb(ndev, skbuff_size); @@ -1540,8 +1544,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) break; /* Better luck next round. */ sh_eth_set_receive_align(skb); dma_addr = dma_map_single(&ndev->dev, skb->data, - rxdesc->buffer_length, - DMA_FROM_DEVICE); + buf_len, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, dma_addr)) { kfree_skb(skb); break; @@ -2407,7 +2410,7 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } txdesc->addr = cpu_to_edmac(mdp, dma_addr); - txdesc->buffer_length = skb->len; + txdesc->len = cpu_to_edmac(mdp, skb->len << 16); dma_wmb(); /* TACT bit must be set after all the above writes */ if (entry >= mdp->num_tx_ring - 1) diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 26ad1cf0bcf1..72fcfc924589 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -283,7 +283,7 @@ enum DMAC_IM_BIT { DMAC_M_RINT1 = 0x00000001, }; -/* Receive descriptor bit */ +/* Receive descriptor 0 bits */ enum RD_STS_BIT { RD_RACT = 0x80000000, RD_RDLE = 0x40000000, RD_RFP1 = 0x20000000, RD_RFP0 = 0x10000000, @@ -298,6 +298,12 @@ enum RD_STS_BIT { #define RDFEND RD_RFP0 #define RD_RFP (RD_RFP1|RD_RFP0) +/* Receive descriptor 1 bits */ +enum RD_LEN_BIT { + RD_RFL = 0x0000ffff, /* receive frame length */ + RD_RBL = 0xffff0000, /* receive buffer length */ +}; + /* FCFTR */ enum FCFTR_BIT { FCFTR_RFF2 = 0x00040000, FCFTR_RFF1 = 0x00020000, @@ -307,7 +313,7 @@ enum FCFTR_BIT { #define DEFAULT_FIFO_F_D_RFF (FCFTR_RFF2 | FCFTR_RFF1 | FCFTR_RFF0) #define DEFAULT_FIFO_F_D_RFD (FCFTR_RFD2 | FCFTR_RFD1 | FCFTR_RFD0) -/* Transmit descriptor bit */ +/* Transmit descriptor 0 bits */ enum TD_STS_BIT { TD_TACT = 0x80000000, TD_TDLE = 0x40000000, TD_TFP1 = 0x20000000, TD_TFP0 = 0x10000000, @@ -317,6 +323,11 @@ enum TD_STS_BIT { #define TDFEND TD_TFP0 #define TD_TFP (TD_TFP1|TD_TFP0) +/* Transmit descriptor 1 bits */ +enum TD_LEN_BIT { + TD_TBL = 0xffff0000, /* transmit buffer length */ +}; + /* RMCR */ enum RMCR_BIT { RMCR_RNC = 0x00000001, @@ -425,15 +436,9 @@ enum TSU_FWSLC_BIT { */ struct sh_eth_txdesc { u32 status; /* TD0 */ -#if defined(__LITTLE_ENDIAN) - u16 pad0; /* TD1 */ - u16 buffer_length; /* TD1 */ -#else - u16 buffer_length; /* TD1 */ - u16 pad0; /* TD1 */ -#endif + u32 len; /* TD1 */ u32 addr; /* TD2 */ - u32 pad1; /* padding data */ + u32 pad0; /* padding data */ } __aligned(2) __packed; /* The sh ether Rx buffer descriptors. @@ -441,13 +446,7 @@ struct sh_eth_txdesc { */ struct sh_eth_rxdesc { u32 status; /* RD0 */ -#if defined(__LITTLE_ENDIAN) - u16 frame_length; /* RD1 */ - u16 buffer_length; /* RD1 */ -#else - u16 buffer_length; /* RD1 */ - u16 frame_length; /* RD1 */ -#endif + u32 len; /* RD1 */ u32 addr; /* RD2 */ u32 pad0; /* padding data */ } __aligned(2) __packed; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 48b92c9de12a..fc958067d10a 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2026,45 +2026,54 @@ static int cpsw_probe_dt(struct cpsw_priv *priv, for_each_child_of_node(node, slave_node) { struct cpsw_slave_data *slave_data = data->slave_data + i; const void *mac_addr = NULL; - u32 phyid; int lenp; const __be32 *parp; - struct device_node *mdio_node; - struct platform_device *mdio; /* This is no slave child node, continue */ if (strcmp(slave_node->name, "slave")) continue; priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); + parp = of_get_property(slave_node, "phy_id", &lenp); if (of_phy_is_fixed_link(slave_node)) { - struct phy_device *pd; + struct device_node *phy_node; + struct phy_device *phy_dev; + /* In the case of a fixed PHY, the DT node associated + * to the PHY is the Ethernet MAC DT node. + */ ret = of_phy_register_fixed_link(slave_node); if (ret) return ret; - pd = of_phy_find_device(slave_node); - if (!pd) + phy_node = of_node_get(slave_node); + phy_dev = of_phy_find_device(phy_node); + if (!phy_dev) return -ENODEV; snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, pd->bus->id, pd->phy_id); - goto no_phy_slave; - } - parp = of_get_property(slave_node, "phy_id", &lenp); - if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) { - dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i); + PHY_ID_FMT, phy_dev->bus->id, phy_dev->addr); + } else if (parp) { + u32 phyid; + struct device_node *mdio_node; + struct platform_device *mdio; + + if (lenp != (sizeof(__be32) * 2)) { + dev_err(&pdev->dev, "Invalid slave[%d] phy_id property\n", i); + goto no_phy_slave; + } + mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); + phyid = be32_to_cpup(parp+1); + mdio = of_find_device_by_node(mdio_node); + of_node_put(mdio_node); + if (!mdio) { + dev_err(&pdev->dev, "Missing mdio platform device\n"); + return -EINVAL; + } + snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), + PHY_ID_FMT, mdio->name, phyid); + } else { + dev_err(&pdev->dev, "No slave[%d] phy_id or fixed-link property\n", i); goto no_phy_slave; } - mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); - phyid = be32_to_cpup(parp+1); - mdio = of_find_device_by_node(mdio_node); - of_node_put(mdio_node); - if (!mdio) { - dev_err(&pdev->dev, "Missing mdio platform device\n"); - return -EINVAL; - } - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, mdio->name, phyid); slave_data->phy_if = of_get_phy_mode(slave_node); if (slave_data->phy_if < 0) { dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", @@ -2418,7 +2427,7 @@ static int cpsw_probe(struct platform_device *pdev) ndev->irq = platform_get_irq(pdev, 1); if (ndev->irq < 0) { dev_err(priv->dev, "error getting irq resource\n"); - ret = -ENOENT; + ret = ndev->irq; goto clean_ale_ret; } @@ -2439,8 +2448,10 @@ static int cpsw_probe(struct platform_device *pdev) /* RX IRQ */ irq = platform_get_irq(pdev, 1); - if (irq < 0) + if (irq < 0) { + ret = irq; goto clean_ale_ret; + } priv->irqs_table[0] = irq; ret = devm_request_irq(&pdev->dev, irq, cpsw_rx_interrupt, @@ -2452,8 +2463,10 @@ static int cpsw_probe(struct platform_device *pdev) /* TX IRQ */ irq = platform_get_irq(pdev, 2); - if (irq < 0) + if (irq < 0) { + ret = irq; goto clean_ale_ret; + } priv->irqs_table[1] = irq; ret = devm_request_irq(&pdev->dev, irq, cpsw_tx_interrupt, diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index c2b79f5d1c89..58efdec12f30 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1155,7 +1155,7 @@ static int geneve_configure(struct net *net, struct net_device *dev, struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); bool tun_collect_md, tun_on_same_port; - int err; + int err, encap_len; if (!remote) return -EINVAL; @@ -1187,6 +1187,14 @@ static int geneve_configure(struct net *net, struct net_device *dev, if (t) return -EBUSY; + /* make enough headroom for basic scenario */ + encap_len = GENEVE_BASE_HLEN + ETH_HLEN; + if (remote->sa.sa_family == AF_INET) + encap_len += sizeof(struct iphdr); + else + encap_len += sizeof(struct ipv6hdr); + dev->needed_headroom = encap_len + ETH_HLEN; + if (metadata) { if (tun_on_same_port) return -EPERM; diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 7c4a4151ef0f..5a1e98547031 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -683,14 +683,20 @@ static void sixpack_close(struct tty_struct *tty) if (!atomic_dec_and_test(&sp->refcnt)) down(&sp->dead_sem); - unregister_netdev(sp->dev); + /* We must stop the queue to avoid potentially scribbling + * on the free buffers. The sp->dead_sem is not sufficient + * to protect us from sp->xbuff access. + */ + netif_stop_queue(sp->dev); - del_timer(&sp->tx_t); - del_timer(&sp->resync_t); + del_timer_sync(&sp->tx_t); + del_timer_sync(&sp->resync_t); /* Free all 6pack frame buffers. */ kfree(sp->rbuff); kfree(sp->xbuff); + + unregister_netdev(sp->dev); } /* Perform I/O control on an active 6pack channel. */ diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 216bfd350169..85828f153445 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -797,14 +797,19 @@ static void mkiss_close(struct tty_struct *tty) */ if (!atomic_dec_and_test(&ax->refcnt)) down(&ax->dead_sem); - - unregister_netdev(ax->dev); + /* + * Halt the transmit queue so that a new transmit cannot scribble + * on our buffers + */ + netif_stop_queue(ax->dev); /* Free all AX25 frame buffers. */ kfree(ax->rbuff); kfree(ax->xbuff); ax->tty = NULL; + + unregister_netdev(ax->dev); } /* Perform I/O control on an active ax25 channel. */ diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 8973abdec9f6..bdd83d95ec0a 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -100,7 +100,7 @@ static const struct net_device_ops cdc_mbim_netdev_ops = { .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, - .ndo_change_mtu = usbnet_change_mtu, + .ndo_change_mtu = cdc_ncm_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = cdc_mbim_rx_add_vid, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 1e9843a41168..e8a1144c5a8b 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -41,6 +41,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ctype.h> +#include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/workqueue.h> #include <linux/mii.h> @@ -689,6 +690,33 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx) kfree(ctx); } +/* we need to override the usbnet change_mtu ndo for two reasons: + * - respect the negotiated maximum datagram size + * - avoid unwanted changes to rx and tx buffers + */ +int cdc_ncm_change_mtu(struct net_device *net, int new_mtu) +{ + struct usbnet *dev = netdev_priv(net); + struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; + int maxmtu = ctx->max_datagram_size - cdc_ncm_eth_hlen(dev); + + if (new_mtu <= 0 || new_mtu > maxmtu) + return -EINVAL; + net->mtu = new_mtu; + return 0; +} +EXPORT_SYMBOL_GPL(cdc_ncm_change_mtu); + +static const struct net_device_ops cdc_ncm_netdev_ops = { + .ndo_open = usbnet_open, + .ndo_stop = usbnet_stop, + .ndo_start_xmit = usbnet_start_xmit, + .ndo_tx_timeout = usbnet_tx_timeout, + .ndo_change_mtu = cdc_ncm_change_mtu, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags) { struct cdc_ncm_ctx *ctx; @@ -823,6 +851,9 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ /* add our sysfs attrs */ dev->net->sysfs_groups[0] = &cdc_ncm_sysfs_attr_group; + /* must handle MTU changes */ + dev->net->netdev_ops = &cdc_ncm_netdev_ops; + return 0; error2: @@ -1558,6 +1589,24 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long) &wwan_info, }, + /* DW5812 LTE Verizon Mobile Broadband Card + * Unlike DW5550 this device requires FLAG_NOARP + */ + { USB_DEVICE_AND_INTERFACE_INFO(0x413c, 0x81bb, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, + + /* DW5813 LTE AT&T Mobile Broadband Card + * Unlike DW5550 this device requires FLAG_NOARP + */ + { USB_DEVICE_AND_INTERFACE_INFO(0x413c, 0x81bc, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_noarp_info, + }, + /* Dell branded MBM devices like DW5550 */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_VENDOR, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 9a5be8b85186..5fccc5a8153f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -742,6 +742,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81a9, 8)}, /* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x413c, 0x81b1, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ + {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 2e32c41536ae..2fb637ad594a 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -3525,6 +3525,14 @@ static int rtl8152_resume(struct usb_interface *intf) return 0; } +static int rtl8152_reset_resume(struct usb_interface *intf) +{ + struct r8152 *tp = usb_get_intfdata(intf); + + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + return rtl8152_resume(intf); +} + static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct r8152 *tp = netdev_priv(dev); @@ -4276,7 +4284,7 @@ static struct usb_driver rtl8152_driver = { .disconnect = rtl8152_disconnect, .suspend = rtl8152_suspend, .resume = rtl8152_resume, - .reset_resume = rtl8152_resume, + .reset_resume = rtl8152_reset_resume, .pre_reset = rtl8152_pre_reset, .post_reset = rtl8152_post_reset, .supports_autosuspend = 1, diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0ef4a5ad5557..ba21d072be31 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -117,12 +117,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) kfree_skb(skb); goto drop; } - /* don't change ip_summed == CHECKSUM_PARTIAL, as that - * will cause bad checksum on forwarded packets - */ - if (skb->ip_summed == CHECKSUM_NONE && - rcv->features & NETIF_F_RXCSUM) - skb->ip_summed = CHECKSUM_UNNECESSARY; if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) { struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 417903715437..0cbf520cea77 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1380,10 +1380,10 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, skip_page_frags = true; goto rcd_done; } - new_dma_addr = dma_map_page(&adapter->pdev->dev - , rbi->page, - 0, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + new_dma_addr = dma_map_page(&adapter->pdev->dev, + new_page, + 0, PAGE_SIZE, + PCI_DMA_FROMDEVICE); if (dma_mapping_error(&adapter->pdev->dev, new_dma_addr)) { put_page(new_page); diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 4c58c83dc225..bdb8a6c0f8aa 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.4.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.5.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040400 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040500 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 4f9748457f5a..0a242b200df4 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -800,7 +800,7 @@ static struct rtable *vrf_get_rtable(const struct net_device *dev, } /* called under rcu_read_lock */ -static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) +static int vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) { struct fib_result res = { .tclassid = 0 }; struct net *net = dev_net(dev); @@ -808,9 +808,10 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) u8 flags = fl4->flowi4_flags; u8 scope = fl4->flowi4_scope; u8 tos = RT_FL_TOS(fl4); + int rc; if (unlikely(!fl4->daddr)) - return; + return 0; fl4->flowi4_flags |= FLOWI_FLAG_SKIP_NH_OIF; fl4->flowi4_iif = LOOPBACK_IFINDEX; @@ -818,7 +819,8 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); - if (!fib_lookup(net, fl4, &res, 0)) { + rc = fib_lookup(net, fl4, &res, 0); + if (!rc) { if (res.type == RTN_LOCAL) fl4->saddr = res.fi->fib_prefsrc ? : fl4->daddr; else @@ -828,6 +830,8 @@ static void vrf_get_saddr(struct net_device *dev, struct flowi4 *fl4) fl4->flowi4_flags = flags; fl4->flowi4_tos = orig_tos; fl4->flowi4_scope = scope; + + return rc; } #if IS_ENABLED(CONFIG_IPV6) diff --git a/drivers/net/wireless/iwlwifi/iwl-7000.c b/drivers/net/wireless/iwlwifi/iwl-7000.c index bf88ec3a65fa..d9a4aee246a6 100644 --- a/drivers/net/wireless/iwlwifi/iwl-7000.c +++ b/drivers/net/wireless/iwlwifi/iwl-7000.c @@ -69,13 +69,19 @@ #include "iwl-agn-hw.h" /* Highest firmware API version supported */ -#define IWL7260_UCODE_API_MAX 19 +#define IWL7260_UCODE_API_MAX 17 +#define IWL7265_UCODE_API_MAX 19 +#define IWL7265D_UCODE_API_MAX 19 /* Oldest version we won't warn about */ #define IWL7260_UCODE_API_OK 13 +#define IWL7265_UCODE_API_OK 13 +#define IWL7265D_UCODE_API_OK 13 /* Lowest firmware API version supported */ #define IWL7260_UCODE_API_MIN 13 +#define IWL7265_UCODE_API_MIN 13 +#define IWL7265D_UCODE_API_MIN 13 /* NVM versions */ #define IWL7260_NVM_VERSION 0x0a1d @@ -149,10 +155,7 @@ static const struct iwl_ht_params iwl7000_ht_params = { .ht40_bands = BIT(IEEE80211_BAND_2GHZ) | BIT(IEEE80211_BAND_5GHZ), }; -#define IWL_DEVICE_7000 \ - .ucode_api_max = IWL7260_UCODE_API_MAX, \ - .ucode_api_ok = IWL7260_UCODE_API_OK, \ - .ucode_api_min = IWL7260_UCODE_API_MIN, \ +#define IWL_DEVICE_7000_COMMON \ .device_family = IWL_DEVICE_FAMILY_7000, \ .max_inst_size = IWL60_RTC_INST_SIZE, \ .max_data_size = IWL60_RTC_DATA_SIZE, \ @@ -163,6 +166,24 @@ static const struct iwl_ht_params iwl7000_ht_params = { .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, \ .dccm_offset = IWL7000_DCCM_OFFSET +#define IWL_DEVICE_7000 \ + IWL_DEVICE_7000_COMMON, \ + .ucode_api_max = IWL7260_UCODE_API_MAX, \ + .ucode_api_ok = IWL7260_UCODE_API_OK, \ + .ucode_api_min = IWL7260_UCODE_API_MIN + +#define IWL_DEVICE_7005 \ + IWL_DEVICE_7000_COMMON, \ + .ucode_api_max = IWL7265_UCODE_API_MAX, \ + .ucode_api_ok = IWL7265_UCODE_API_OK, \ + .ucode_api_min = IWL7265_UCODE_API_MIN + +#define IWL_DEVICE_7005D \ + IWL_DEVICE_7000_COMMON, \ + .ucode_api_max = IWL7265D_UCODE_API_MAX, \ + .ucode_api_ok = IWL7265D_UCODE_API_OK, \ + .ucode_api_min = IWL7265D_UCODE_API_MIN + const struct iwl_cfg iwl7260_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 7260", .fw_name_pre = IWL7260_FW_PRE, @@ -266,7 +287,7 @@ static const struct iwl_ht_params iwl7265_ht_params = { const struct iwl_cfg iwl3165_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 3165", .fw_name_pre = IWL7265D_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005D, .ht_params = &iwl7000_ht_params, .nvm_ver = IWL3165_NVM_VERSION, .nvm_calib_ver = IWL3165_TX_POWER_VERSION, @@ -277,7 +298,7 @@ const struct iwl_cfg iwl3165_2ac_cfg = { const struct iwl_cfg iwl7265_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 7265", .fw_name_pre = IWL7265_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005, .ht_params = &iwl7265_ht_params, .nvm_ver = IWL7265_NVM_VERSION, .nvm_calib_ver = IWL7265_TX_POWER_VERSION, @@ -288,7 +309,7 @@ const struct iwl_cfg iwl7265_2ac_cfg = { const struct iwl_cfg iwl7265_2n_cfg = { .name = "Intel(R) Dual Band Wireless N 7265", .fw_name_pre = IWL7265_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005, .ht_params = &iwl7265_ht_params, .nvm_ver = IWL7265_NVM_VERSION, .nvm_calib_ver = IWL7265_TX_POWER_VERSION, @@ -299,7 +320,7 @@ const struct iwl_cfg iwl7265_2n_cfg = { const struct iwl_cfg iwl7265_n_cfg = { .name = "Intel(R) Wireless N 7265", .fw_name_pre = IWL7265_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005, .ht_params = &iwl7265_ht_params, .nvm_ver = IWL7265_NVM_VERSION, .nvm_calib_ver = IWL7265_TX_POWER_VERSION, @@ -310,7 +331,7 @@ const struct iwl_cfg iwl7265_n_cfg = { const struct iwl_cfg iwl7265d_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 7265", .fw_name_pre = IWL7265D_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005D, .ht_params = &iwl7265_ht_params, .nvm_ver = IWL7265D_NVM_VERSION, .nvm_calib_ver = IWL7265_TX_POWER_VERSION, @@ -321,7 +342,7 @@ const struct iwl_cfg iwl7265d_2ac_cfg = { const struct iwl_cfg iwl7265d_2n_cfg = { .name = "Intel(R) Dual Band Wireless N 7265", .fw_name_pre = IWL7265D_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005D, .ht_params = &iwl7265_ht_params, .nvm_ver = IWL7265D_NVM_VERSION, .nvm_calib_ver = IWL7265_TX_POWER_VERSION, @@ -332,7 +353,7 @@ const struct iwl_cfg iwl7265d_2n_cfg = { const struct iwl_cfg iwl7265d_n_cfg = { .name = "Intel(R) Wireless N 7265", .fw_name_pre = IWL7265D_FW_PRE, - IWL_DEVICE_7000, + IWL_DEVICE_7005D, .ht_params = &iwl7265_ht_params, .nvm_ver = IWL7265D_NVM_VERSION, .nvm_calib_ver = IWL7265_TX_POWER_VERSION, @@ -342,5 +363,5 @@ const struct iwl_cfg iwl7265d_n_cfg = { MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); -MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); -MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7260_UCODE_API_OK)); +MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7265_UCODE_API_OK)); +MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7265D_UCODE_API_OK)); diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c index 354acbde088e..2b976b110207 100644 --- a/drivers/net/wireless/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/iwlwifi/mvm/sta.c @@ -1222,8 +1222,8 @@ static u8 iwl_mvm_get_key_sta_id(struct iwl_mvm *mvm, mvmvif->ap_sta_id != IWL_MVM_STATION_COUNT) { u8 sta_id = mvmvif->ap_sta_id; - sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id], - lockdep_is_held(&mvm->mutex)); + sta = rcu_dereference_check(mvm->fw_id_to_mac_id[sta_id], + lockdep_is_held(&mvm->mutex)); /* * It is possible that the 'sta' parameter is NULL, * for example when a GTK is removed - the sta_id will then @@ -1590,14 +1590,15 @@ void iwl_mvm_update_tkip_key(struct iwl_mvm *mvm, u16 *phase1key) { struct iwl_mvm_sta *mvm_sta; - u8 sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta); + u8 sta_id; bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE); - if (WARN_ON_ONCE(sta_id == IWL_MVM_STATION_COUNT)) - return; - rcu_read_lock(); + sta_id = iwl_mvm_get_key_sta_id(mvm, vif, sta); + if (WARN_ON_ONCE(sta_id == IWL_MVM_STATION_COUNT)) + goto unlock; + if (!sta) { sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); if (WARN_ON(IS_ERR_OR_NULL(sta))) { @@ -1609,6 +1610,8 @@ void iwl_mvm_update_tkip_key(struct iwl_mvm *mvm, mvm_sta = iwl_mvm_sta_from_mac80211(sta); iwl_mvm_send_sta_key(mvm, mvm_sta, keyconf, mcast, iv32, phase1key, CMD_ASYNC, keyconf->hw_key_idx); + + unlock: rcu_read_unlock(); } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9e294ff4e652..0c67b57be83c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2540,8 +2540,17 @@ static void nvme_ns_remove(struct nvme_ns *ns) { bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue); - if (kill) + if (kill) { blk_set_queue_dying(ns->queue); + + /* + * The controller was shutdown first if we got here through + * device removal. The shutdown may requeue outstanding + * requests. These need to be aborted immediately so + * del_gendisk doesn't block indefinitely for their completion. + */ + blk_mq_abort_requeue_list(ns->queue); + } if (ns->disk->flags & GENHD_FL_UP) del_gendisk(ns->disk); if (kill || !blk_queue_dying(ns->queue)) { @@ -2977,6 +2986,15 @@ static void nvme_dev_remove(struct nvme_dev *dev) { struct nvme_ns *ns, *next; + if (nvme_io_incapable(dev)) { + /* + * If the device is not capable of IO (surprise hot-removal, + * for example), we need to quiesce prior to deleting the + * namespaces. This will end outstanding requests and prevent + * attempts to sync dirty data. + */ + nvme_dev_shutdown(dev); + } list_for_each_entry_safe(ns, next, &dev->namespaces, list) nvme_ns_remove(ns); } diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index f131ba947dc6..c0ad9aaa16a7 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -5,6 +5,7 @@ config PCI_DRA7XX bool "TI DRA7xx PCIe controller" select PCIE_DW depends on OF && HAS_IOMEM && TI_PIPE3 + depends on BROKEN help Enables support for the PCIe controller in the DRA7xx SoC. There are two instances of PCIe controller in DRA7xx. This controller can diff --git a/drivers/pci/host/pcie-hisi.c b/drivers/pci/host/pcie-hisi.c index 163671a4f798..77f7c669a1b9 100644 --- a/drivers/pci/host/pcie-hisi.c +++ b/drivers/pci/host/pcie-hisi.c @@ -61,7 +61,9 @@ static int hisi_pcie_cfg_read(struct pcie_port *pp, int where, int size, *val = *(u8 __force *) walker; else if (size == 2) *val = *(u16 __force *) walker; - else if (size != 4) + else if (size == 4) + *val = reg_val; + else return PCIBIOS_BAD_REGISTER_NUMBER; return PCIBIOS_SUCCESSFUL; diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index 7eb5859dd035..03cb3ea2d2c0 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -233,6 +233,7 @@ config PHY_SUN9I_USB tristate "Allwinner sun9i SoC USB PHY driver" depends on ARCH_SUNXI && HAS_IOMEM && OF depends on RESET_CONTROLLER + depends on USB_COMMON select GENERIC_PHY help Enable this to support the transceiver that is part of Allwinner diff --git a/drivers/phy/phy-bcm-cygnus-pcie.c b/drivers/phy/phy-bcm-cygnus-pcie.c index 7ad72b7d2b98..082c03f6438f 100644 --- a/drivers/phy/phy-bcm-cygnus-pcie.c +++ b/drivers/phy/phy-bcm-cygnus-pcie.c @@ -128,6 +128,7 @@ static int cygnus_pcie_phy_probe(struct platform_device *pdev) struct phy_provider *provider; struct resource *res; unsigned cnt = 0; + int ret; if (of_get_child_count(node) == 0) { dev_err(dev, "PHY no child node\n"); @@ -154,24 +155,28 @@ static int cygnus_pcie_phy_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &id)) { dev_err(dev, "missing reg property for %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (id >= MAX_NUM_PHYS) { dev_err(dev, "invalid PHY id: %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (core->phys[id].phy) { dev_err(dev, "duplicated PHY id: %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } p = &core->phys[id]; p->phy = devm_phy_create(dev, child, &cygnus_pcie_phy_ops); if (IS_ERR(p->phy)) { dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(p->phy); + ret = PTR_ERR(p->phy); + goto put_child; } p->core = core; @@ -191,6 +196,9 @@ static int cygnus_pcie_phy_probe(struct platform_device *pdev) dev_dbg(dev, "registered %u PCIe PHY(s)\n", cnt); return 0; +put_child: + of_node_put(child); + return ret; } static const struct of_device_id cygnus_pcie_phy_match_table[] = { diff --git a/drivers/phy/phy-berlin-sata.c b/drivers/phy/phy-berlin-sata.c index 77a2e054fdea..f84a33a1bdd9 100644 --- a/drivers/phy/phy-berlin-sata.c +++ b/drivers/phy/phy-berlin-sata.c @@ -195,7 +195,7 @@ static int phy_berlin_sata_probe(struct platform_device *pdev) struct phy_provider *phy_provider; struct phy_berlin_priv *priv; struct resource *res; - int i = 0; + int ret, i = 0; u32 phy_id; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -237,22 +237,27 @@ static int phy_berlin_sata_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &phy_id)) { dev_err(dev, "missing reg property in node %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (phy_id >= ARRAY_SIZE(phy_berlin_power_down_bits)) { dev_err(dev, "invalid reg in node %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } phy_desc = devm_kzalloc(dev, sizeof(*phy_desc), GFP_KERNEL); - if (!phy_desc) - return -ENOMEM; + if (!phy_desc) { + ret = -ENOMEM; + goto put_child; + } phy = devm_phy_create(dev, NULL, &phy_berlin_sata_ops); if (IS_ERR(phy)) { dev_err(dev, "failed to create PHY %d\n", phy_id); - return PTR_ERR(phy); + ret = PTR_ERR(phy); + goto put_child; } phy_desc->phy = phy; @@ -269,6 +274,9 @@ static int phy_berlin_sata_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, phy_berlin_sata_phy_xlate); return PTR_ERR_OR_ZERO(phy_provider); +put_child: + of_node_put(child); + return ret; } static const struct of_device_id phy_berlin_sata_of_match[] = { diff --git a/drivers/phy/phy-brcmstb-sata.c b/drivers/phy/phy-brcmstb-sata.c index 8a2cb16a1937..cd9dba820566 100644 --- a/drivers/phy/phy-brcmstb-sata.c +++ b/drivers/phy/phy-brcmstb-sata.c @@ -140,7 +140,7 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) struct brcm_sata_phy *priv; struct resource *res; struct phy_provider *provider; - int count = 0; + int ret, count = 0; if (of_get_child_count(dn) == 0) return -ENODEV; @@ -163,16 +163,19 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) if (of_property_read_u32(child, "reg", &id)) { dev_err(dev, "missing reg property in node %s\n", child->name); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (id >= MAX_PORTS) { dev_err(dev, "invalid reg: %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } if (priv->phys[id].phy) { dev_err(dev, "already registered port %u\n", id); - return -EINVAL; + ret = -EINVAL; + goto put_child; } port = &priv->phys[id]; @@ -182,7 +185,8 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) port->ssc_en = of_property_read_bool(child, "brcm,enable-ssc"); if (IS_ERR(port->phy)) { dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(port->phy); + ret = PTR_ERR(port->phy); + goto put_child; } phy_set_drvdata(port->phy, port); @@ -198,6 +202,9 @@ static int brcm_sata_phy_probe(struct platform_device *pdev) dev_info(dev, "registered %d port(s)\n", count); return 0; +put_child: + of_node_put(child); + return ret; } static struct platform_driver brcm_sata_phy_driver = { diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index fc48fac003a6..8c7f27db6ad3 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -636,8 +636,9 @@ EXPORT_SYMBOL_GPL(devm_of_phy_get); * @np: node containing the phy * @index: index of the phy * - * Gets the phy using _of_phy_get(), and associates a device with it using - * devres. On driver detach, release function is invoked on the devres data, + * Gets the phy using _of_phy_get(), then gets a refcount to it, + * and associates a device with it using devres. On driver detach, + * release function is invoked on the devres data, * then, devres data is freed. * */ @@ -651,13 +652,21 @@ struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np, return ERR_PTR(-ENOMEM); phy = _of_phy_get(np, index); - if (!IS_ERR(phy)) { - *ptr = phy; - devres_add(dev, ptr); - } else { + if (IS_ERR(phy)) { devres_free(ptr); + return phy; } + if (!try_module_get(phy->ops->owner)) { + devres_free(ptr); + return ERR_PTR(-EPROBE_DEFER); + } + + get_device(&phy->dev); + + *ptr = phy; + devres_add(dev, ptr); + return phy; } EXPORT_SYMBOL_GPL(devm_of_phy_get_by_index); diff --git a/drivers/phy/phy-miphy28lp.c b/drivers/phy/phy-miphy28lp.c index c47b56b4a2b8..3acd2a1808df 100644 --- a/drivers/phy/phy-miphy28lp.c +++ b/drivers/phy/phy-miphy28lp.c @@ -1226,15 +1226,18 @@ static int miphy28lp_probe(struct platform_device *pdev) miphy_phy = devm_kzalloc(&pdev->dev, sizeof(*miphy_phy), GFP_KERNEL); - if (!miphy_phy) - return -ENOMEM; + if (!miphy_phy) { + ret = -ENOMEM; + goto put_child; + } miphy_dev->phys[port] = miphy_phy; phy = devm_phy_create(&pdev->dev, child, &miphy28lp_ops); if (IS_ERR(phy)) { dev_err(&pdev->dev, "failed to create PHY\n"); - return PTR_ERR(phy); + ret = PTR_ERR(phy); + goto put_child; } miphy_dev->phys[port]->phy = phy; @@ -1242,11 +1245,11 @@ static int miphy28lp_probe(struct platform_device *pdev) ret = miphy28lp_of_probe(child, miphy_phy); if (ret) - return ret; + goto put_child; ret = miphy28lp_probe_resets(child, miphy_dev->phys[port]); if (ret) - return ret; + goto put_child; phy_set_drvdata(phy, miphy_dev->phys[port]); port++; @@ -1255,6 +1258,9 @@ static int miphy28lp_probe(struct platform_device *pdev) provider = devm_of_phy_provider_register(&pdev->dev, miphy28lp_xlate); return PTR_ERR_OR_ZERO(provider); +put_child: + of_node_put(child); + return ret; } static const struct of_device_id miphy28lp_of_match[] = { diff --git a/drivers/phy/phy-miphy365x.c b/drivers/phy/phy-miphy365x.c index 00a686a073ed..e661f3b36eaa 100644 --- a/drivers/phy/phy-miphy365x.c +++ b/drivers/phy/phy-miphy365x.c @@ -566,22 +566,25 @@ static int miphy365x_probe(struct platform_device *pdev) miphy_phy = devm_kzalloc(&pdev->dev, sizeof(*miphy_phy), GFP_KERNEL); - if (!miphy_phy) - return -ENOMEM; + if (!miphy_phy) { + ret = -ENOMEM; + goto put_child; + } miphy_dev->phys[port] = miphy_phy; phy = devm_phy_create(&pdev->dev, child, &miphy365x_ops); if (IS_ERR(phy)) { dev_err(&pdev->dev, "failed to create PHY\n"); - return PTR_ERR(phy); + ret = PTR_ERR(phy); + goto put_child; } miphy_dev->phys[port]->phy = phy; ret = miphy365x_of_probe(child, miphy_phy); if (ret) - return ret; + goto put_child; phy_set_drvdata(phy, miphy_dev->phys[port]); @@ -591,12 +594,15 @@ static int miphy365x_probe(struct platform_device *pdev) &miphy_phy->ctrlreg); if (ret) { dev_err(&pdev->dev, "No sysconfig offset found\n"); - return ret; + goto put_child; } } provider = devm_of_phy_provider_register(&pdev->dev, miphy365x_xlate); return PTR_ERR_OR_ZERO(provider); +put_child: + of_node_put(child); + return ret; } static const struct of_device_id miphy365x_of_match[] = { diff --git a/drivers/phy/phy-mt65xx-usb3.c b/drivers/phy/phy-mt65xx-usb3.c index f30b28bd41fe..e427c3b788ff 100644 --- a/drivers/phy/phy-mt65xx-usb3.c +++ b/drivers/phy/phy-mt65xx-usb3.c @@ -415,7 +415,7 @@ static int mt65xx_u3phy_probe(struct platform_device *pdev) struct resource *sif_res; struct mt65xx_u3phy *u3phy; struct resource res; - int port; + int port, retval; u3phy = devm_kzalloc(dev, sizeof(*u3phy), GFP_KERNEL); if (!u3phy) @@ -447,31 +447,34 @@ static int mt65xx_u3phy_probe(struct platform_device *pdev) for_each_child_of_node(np, child_np) { struct mt65xx_phy_instance *instance; struct phy *phy; - int retval; instance = devm_kzalloc(dev, sizeof(*instance), GFP_KERNEL); - if (!instance) - return -ENOMEM; + if (!instance) { + retval = -ENOMEM; + goto put_child; + } u3phy->phys[port] = instance; phy = devm_phy_create(dev, child_np, &mt65xx_u3phy_ops); if (IS_ERR(phy)) { dev_err(dev, "failed to create phy\n"); - return PTR_ERR(phy); + retval = PTR_ERR(phy); + goto put_child; } retval = of_address_to_resource(child_np, 0, &res); if (retval) { dev_err(dev, "failed to get address resource(id-%d)\n", port); - return retval; + goto put_child; } instance->port_base = devm_ioremap_resource(&phy->dev, &res); if (IS_ERR(instance->port_base)) { dev_err(dev, "failed to remap phy regs\n"); - return PTR_ERR(instance->port_base); + retval = PTR_ERR(instance->port_base); + goto put_child; } instance->phy = phy; @@ -483,6 +486,9 @@ static int mt65xx_u3phy_probe(struct platform_device *pdev) provider = devm_of_phy_provider_register(dev, mt65xx_phy_xlate); return PTR_ERR_OR_ZERO(provider); +put_child: + of_node_put(child_np); + return retval; } static const struct of_device_id mt65xx_u3phy_id_table[] = { diff --git a/drivers/phy/phy-rockchip-usb.c b/drivers/phy/phy-rockchip-usb.c index 91d6f342c565..62c43c435194 100644 --- a/drivers/phy/phy-rockchip-usb.c +++ b/drivers/phy/phy-rockchip-usb.c @@ -108,13 +108,16 @@ static int rockchip_usb_phy_probe(struct platform_device *pdev) for_each_available_child_of_node(dev->of_node, child) { rk_phy = devm_kzalloc(dev, sizeof(*rk_phy), GFP_KERNEL); - if (!rk_phy) - return -ENOMEM; + if (!rk_phy) { + err = -ENOMEM; + goto put_child; + } if (of_property_read_u32(child, "reg", ®_offset)) { dev_err(dev, "missing reg property in node %s\n", child->name); - return -EINVAL; + err = -EINVAL; + goto put_child; } rk_phy->reg_offset = reg_offset; @@ -127,18 +130,22 @@ static int rockchip_usb_phy_probe(struct platform_device *pdev) rk_phy->phy = devm_phy_create(dev, child, &ops); if (IS_ERR(rk_phy->phy)) { dev_err(dev, "failed to create PHY\n"); - return PTR_ERR(rk_phy->phy); + err = PTR_ERR(rk_phy->phy); + goto put_child; } phy_set_drvdata(rk_phy->phy, rk_phy); /* only power up usb phy when it use, so disable it when init*/ err = rockchip_usb_phy_power(rk_phy, 1); if (err) - return err; + goto put_child; } phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); return PTR_ERR_OR_ZERO(phy_provider); +put_child: + of_node_put(child); + return err; } static const struct of_device_id rockchip_usb_phy_dt_ids[] = { diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index a1ea565fcd46..2e6ca69635aa 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -342,12 +342,6 @@ static int bcm2835_gpio_get(struct gpio_chip *chip, unsigned offset) return bcm2835_gpio_get_bit(pc, GPLEV0, offset); } -static int bcm2835_gpio_direction_output(struct gpio_chip *chip, - unsigned offset, int value) -{ - return pinctrl_gpio_direction_output(chip->base + offset); -} - static void bcm2835_gpio_set(struct gpio_chip *chip, unsigned offset, int value) { struct bcm2835_pinctrl *pc = dev_get_drvdata(chip->dev); @@ -355,6 +349,13 @@ static void bcm2835_gpio_set(struct gpio_chip *chip, unsigned offset, int value) bcm2835_gpio_set_bit(pc, value ? GPSET0 : GPCLR0, offset); } +static int bcm2835_gpio_direction_output(struct gpio_chip *chip, + unsigned offset, int value) +{ + bcm2835_gpio_set(chip, offset, value); + return pinctrl_gpio_direction_output(chip->base + offset); +} + static int bcm2835_gpio_to_irq(struct gpio_chip *chip, unsigned offset) { struct bcm2835_pinctrl *pc = dev_get_drvdata(chip->dev); diff --git a/drivers/pinctrl/freescale/pinctrl-vf610.c b/drivers/pinctrl/freescale/pinctrl-vf610.c index 37a037543d29..587d1ff6210e 100644 --- a/drivers/pinctrl/freescale/pinctrl-vf610.c +++ b/drivers/pinctrl/freescale/pinctrl-vf610.c @@ -299,7 +299,7 @@ static const struct pinctrl_pin_desc vf610_pinctrl_pads[] = { static struct imx_pinctrl_soc_info vf610_pinctrl_info = { .pins = vf610_pinctrl_pads, .npins = ARRAY_SIZE(vf610_pinctrl_pads), - .flags = SHARE_MUX_CONF_REG, + .flags = SHARE_MUX_CONF_REG | ZERO_OFFSET_VALID, }; static const struct of_device_id vf610_pinctrl_of_match[] = { diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c index e42d5d4183f5..5979d38c46b2 100644 --- a/drivers/pinctrl/intel/pinctrl-broxton.c +++ b/drivers/pinctrl/intel/pinctrl-broxton.c @@ -28,6 +28,7 @@ .padcfglock_offset = BXT_PADCFGLOCK, \ .hostown_offset = BXT_HOSTSW_OWN, \ .ie_offset = BXT_GPI_IE, \ + .gpp_size = 32, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ } diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 392e28d3f48d..26f6b6ffea5b 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -25,9 +25,6 @@ #include "pinctrl-intel.h" -/* Maximum number of pads in each group */ -#define NPADS_IN_GPP 24 - /* Offset from regs */ #define PADBAR 0x00c #define GPI_IS 0x100 @@ -37,6 +34,7 @@ #define PADOWN_BITS 4 #define PADOWN_SHIFT(p) ((p) % 8 * PADOWN_BITS) #define PADOWN_MASK(p) (0xf << PADOWN_SHIFT(p)) +#define PADOWN_GPP(p) ((p) / 8) /* Offset from pad_regs */ #define PADCFG0 0x000 @@ -142,7 +140,7 @@ static void __iomem *intel_get_padcfg(struct intel_pinctrl *pctrl, unsigned pin, static bool intel_pad_owned_by_host(struct intel_pinctrl *pctrl, unsigned pin) { const struct intel_community *community; - unsigned padno, gpp, gpp_offset, offset; + unsigned padno, gpp, offset, group; void __iomem *padown; community = intel_get_community(pctrl, pin); @@ -152,9 +150,9 @@ static bool intel_pad_owned_by_host(struct intel_pinctrl *pctrl, unsigned pin) return true; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; - gpp_offset = padno % NPADS_IN_GPP; - offset = community->padown_offset + gpp * 16 + (gpp_offset / 8) * 4; + group = padno / community->gpp_size; + gpp = PADOWN_GPP(padno % community->gpp_size); + offset = community->padown_offset + 0x10 * group + gpp * 4; padown = community->regs + offset; return !(readl(padown) & PADOWN_MASK(padno)); @@ -173,11 +171,11 @@ static bool intel_pad_acpi_mode(struct intel_pinctrl *pctrl, unsigned pin) return false; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; + gpp = padno / community->gpp_size; offset = community->hostown_offset + gpp * 4; hostown = community->regs + offset; - return !(readl(hostown) & BIT(padno % NPADS_IN_GPP)); + return !(readl(hostown) & BIT(padno % community->gpp_size)); } static bool intel_pad_locked(struct intel_pinctrl *pctrl, unsigned pin) @@ -193,7 +191,7 @@ static bool intel_pad_locked(struct intel_pinctrl *pctrl, unsigned pin) return false; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; + gpp = padno / community->gpp_size; /* * If PADCFGLOCK and PADCFGLOCKTX bits are both clear for this pad, @@ -202,12 +200,12 @@ static bool intel_pad_locked(struct intel_pinctrl *pctrl, unsigned pin) */ offset = community->padcfglock_offset + gpp * 8; value = readl(community->regs + offset); - if (value & BIT(pin % NPADS_IN_GPP)) + if (value & BIT(pin % community->gpp_size)) return true; offset = community->padcfglock_offset + 4 + gpp * 8; value = readl(community->regs + offset); - if (value & BIT(pin % NPADS_IN_GPP)) + if (value & BIT(pin % community->gpp_size)) return true; return false; @@ -663,8 +661,8 @@ static void intel_gpio_irq_ack(struct irq_data *d) community = intel_get_community(pctrl, pin); if (community) { unsigned padno = pin_to_padno(community, pin); - unsigned gpp_offset = padno % NPADS_IN_GPP; - unsigned gpp = padno / NPADS_IN_GPP; + unsigned gpp_offset = padno % community->gpp_size; + unsigned gpp = padno / community->gpp_size; writel(BIT(gpp_offset), community->regs + GPI_IS + gpp * 4); } @@ -685,8 +683,8 @@ static void intel_gpio_irq_mask_unmask(struct irq_data *d, bool mask) community = intel_get_community(pctrl, pin); if (community) { unsigned padno = pin_to_padno(community, pin); - unsigned gpp_offset = padno % NPADS_IN_GPP; - unsigned gpp = padno / NPADS_IN_GPP; + unsigned gpp_offset = padno % community->gpp_size; + unsigned gpp = padno / community->gpp_size; void __iomem *reg; u32 value; @@ -780,8 +778,8 @@ static int intel_gpio_irq_wake(struct irq_data *d, unsigned int on) return -EINVAL; padno = pin_to_padno(community, pin); - gpp = padno / NPADS_IN_GPP; - gpp_offset = padno % NPADS_IN_GPP; + gpp = padno / community->gpp_size; + gpp_offset = padno % community->gpp_size; /* Clear the existing wake status */ writel(BIT(gpp_offset), community->regs + GPI_GPE_STS + gpp * 4); @@ -819,14 +817,14 @@ static irqreturn_t intel_gpio_community_irq_handler(struct intel_pinctrl *pctrl, /* Only interrupts that are enabled */ pending &= enabled; - for_each_set_bit(gpp_offset, &pending, NPADS_IN_GPP) { + for_each_set_bit(gpp_offset, &pending, community->gpp_size) { unsigned padno, irq; /* * The last group in community can have less pins * than NPADS_IN_GPP. */ - padno = gpp_offset + gpp * NPADS_IN_GPP; + padno = gpp_offset + gpp * community->gpp_size; if (padno >= community->npins) break; @@ -1002,7 +1000,8 @@ int intel_pinctrl_probe(struct platform_device *pdev, community->regs = regs; community->pad_regs = regs + padbar; - community->ngpps = DIV_ROUND_UP(community->npins, NPADS_IN_GPP); + community->ngpps = DIV_ROUND_UP(community->npins, + community->gpp_size); } irq = platform_get_irq(pdev, 0); diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h index 4ec8b572a288..b60215793017 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.h +++ b/drivers/pinctrl/intel/pinctrl-intel.h @@ -55,6 +55,8 @@ struct intel_function { * ACPI). * @ie_offset: Register offset of GPI_IE from @regs. * @pin_base: Starting pin of pins in this community + * @gpp_size: Maximum number of pads in each group, such as PADCFGLOCK, + * HOSTSW_OWN, GPI_IS, GPI_IE, etc. * @npins: Number of pins in this community * @regs: Community specific common registers (reserved for core driver) * @pad_regs: Community specific pad registers (reserved for core driver) @@ -68,6 +70,7 @@ struct intel_community { unsigned hostown_offset; unsigned ie_offset; unsigned pin_base; + unsigned gpp_size; size_t npins; void __iomem *regs; void __iomem *pad_regs; diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 1de9ae5010db..c725a5313b4e 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -30,6 +30,7 @@ .padcfglock_offset = SPT_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ .ie_offset = SPT_GPI_IE, \ + .gpp_size = 24, \ .pin_base = (s), \ .npins = ((e) - (s) + 1), \ } diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c index 284b587da65c..d6c853bbfa9f 100644 --- a/drivers/rtc/rtc-da9063.c +++ b/drivers/rtc/rtc-da9063.c @@ -483,24 +483,23 @@ static int da9063_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); + rtc->rtc_dev = devm_rtc_device_register(&pdev->dev, DA9063_DRVNAME_RTC, + &da9063_rtc_ops, THIS_MODULE); + if (IS_ERR(rtc->rtc_dev)) + return PTR_ERR(rtc->rtc_dev); + + da9063_data_to_tm(data, &rtc->alarm_time, rtc); + rtc->rtc_sync = false; + irq_alarm = platform_get_irq_byname(pdev, "ALARM"); ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL, da9063_alarm_event, IRQF_TRIGGER_LOW | IRQF_ONESHOT, "ALARM", rtc); - if (ret) { + if (ret) dev_err(&pdev->dev, "Failed to request ALARM IRQ %d: %d\n", irq_alarm, ret); - return ret; - } - - rtc->rtc_dev = devm_rtc_device_register(&pdev->dev, DA9063_DRVNAME_RTC, - &da9063_rtc_ops, THIS_MODULE); - if (IS_ERR(rtc->rtc_dev)) - return PTR_ERR(rtc->rtc_dev); - da9063_data_to_tm(data, &rtc->alarm_time, rtc); - rtc->rtc_sync = false; return ret; } diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c index 91ca0bc1b484..35c9aada07c8 100644 --- a/drivers/rtc/rtc-rk808.c +++ b/drivers/rtc/rtc-rk808.c @@ -56,6 +56,42 @@ struct rk808_rtc { int irq; }; +/* + * The Rockchip calendar used by the RK808 counts November with 31 days. We use + * these translation functions to convert its dates to/from the Gregorian + * calendar used by the rest of the world. We arbitrarily define Jan 1st, 2016 + * as the day when both calendars were in sync, and treat all other dates + * relative to that. + * NOTE: Other system software (e.g. firmware) that reads the same hardware must + * implement this exact same conversion algorithm, with the same anchor date. + */ +static time64_t nov2dec_transitions(struct rtc_time *tm) +{ + return (tm->tm_year + 1900) - 2016 + (tm->tm_mon + 1 > 11 ? 1 : 0); +} + +static void rockchip_to_gregorian(struct rtc_time *tm) +{ + /* If it's Nov 31st, rtc_tm_to_time64() will count that like Dec 1st */ + time64_t time = rtc_tm_to_time64(tm); + rtc_time64_to_tm(time + nov2dec_transitions(tm) * 86400, tm); +} + +static void gregorian_to_rockchip(struct rtc_time *tm) +{ + time64_t extra_days = nov2dec_transitions(tm); + time64_t time = rtc_tm_to_time64(tm); + rtc_time64_to_tm(time - extra_days * 86400, tm); + + /* Compensate if we went back over Nov 31st (will work up to 2381) */ + if (nov2dec_transitions(tm) < extra_days) { + if (tm->tm_mon + 1 == 11) + tm->tm_mday++; /* This may result in 31! */ + else + rtc_time64_to_tm(time - (extra_days - 1) * 86400, tm); + } +} + /* Read current time and date in RTC */ static int rk808_rtc_readtime(struct device *dev, struct rtc_time *tm) { @@ -101,9 +137,10 @@ static int rk808_rtc_readtime(struct device *dev, struct rtc_time *tm) tm->tm_mon = (bcd2bin(rtc_data[4] & MONTHS_REG_MSK)) - 1; tm->tm_year = (bcd2bin(rtc_data[5] & YEARS_REG_MSK)) + 100; tm->tm_wday = bcd2bin(rtc_data[6] & WEEKS_REG_MSK); + rockchip_to_gregorian(tm); dev_dbg(dev, "RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n", 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, - tm->tm_wday, tm->tm_hour , tm->tm_min, tm->tm_sec); + tm->tm_wday, tm->tm_hour, tm->tm_min, tm->tm_sec); return ret; } @@ -116,6 +153,10 @@ static int rk808_rtc_set_time(struct device *dev, struct rtc_time *tm) u8 rtc_data[NUM_TIME_REGS]; int ret; + dev_dbg(dev, "set RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n", + 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, + tm->tm_wday, tm->tm_hour, tm->tm_min, tm->tm_sec); + gregorian_to_rockchip(tm); rtc_data[0] = bin2bcd(tm->tm_sec); rtc_data[1] = bin2bcd(tm->tm_min); rtc_data[2] = bin2bcd(tm->tm_hour); @@ -123,9 +164,6 @@ static int rk808_rtc_set_time(struct device *dev, struct rtc_time *tm) rtc_data[4] = bin2bcd(tm->tm_mon + 1); rtc_data[5] = bin2bcd(tm->tm_year - 100); rtc_data[6] = bin2bcd(tm->tm_wday); - dev_dbg(dev, "set RTC date/time %4d-%02d-%02d(%d) %02d:%02d:%02d\n", - 1900 + tm->tm_year, tm->tm_mon + 1, tm->tm_mday, - tm->tm_wday, tm->tm_hour , tm->tm_min, tm->tm_sec); /* Stop RTC while updating the RTC registers */ ret = regmap_update_bits(rk808->regmap, RK808_RTC_CTRL_REG, @@ -170,6 +208,7 @@ static int rk808_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm) alrm->time.tm_mday = bcd2bin(alrm_data[3] & DAYS_REG_MSK); alrm->time.tm_mon = (bcd2bin(alrm_data[4] & MONTHS_REG_MSK)) - 1; alrm->time.tm_year = (bcd2bin(alrm_data[5] & YEARS_REG_MSK)) + 100; + rockchip_to_gregorian(&alrm->time); ret = regmap_read(rk808->regmap, RK808_RTC_INT_REG, &int_reg); if (ret) { @@ -227,6 +266,7 @@ static int rk808_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm) alrm->time.tm_mday, alrm->time.tm_wday, alrm->time.tm_hour, alrm->time.tm_min, alrm->time.tm_sec); + gregorian_to_rockchip(&alrm->time); alrm_data[0] = bin2bcd(alrm->time.tm_sec); alrm_data[1] = bin2bcd(alrm->time.tm_min); alrm_data[2] = bin2bcd(alrm->time.tm_hour); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 61f768518a34..24ec282e15d8 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -599,8 +599,10 @@ static enum ap_wait ap_sm_read(struct ap_device *ap_dev) status = ap_sm_recv(ap_dev); switch (status.response_code) { case AP_RESPONSE_NORMAL: - if (ap_dev->queue_count > 0) + if (ap_dev->queue_count > 0) { + ap_dev->state = AP_STATE_WORKING; return AP_WAIT_AGAIN; + } ap_dev->state = AP_STATE_IDLE; return AP_WAIT_NONE; case AP_RESPONSE_NO_PENDING_REPLY: diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index b2a1a81e6fc8..1b831598df7c 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -984,6 +984,36 @@ static struct virtqueue *virtio_ccw_vq_by_ind(struct virtio_ccw_device *vcdev, return vq; } +static void virtio_ccw_check_activity(struct virtio_ccw_device *vcdev, + __u32 activity) +{ + if (vcdev->curr_io & activity) { + switch (activity) { + case VIRTIO_CCW_DOING_READ_FEAT: + case VIRTIO_CCW_DOING_WRITE_FEAT: + case VIRTIO_CCW_DOING_READ_CONFIG: + case VIRTIO_CCW_DOING_WRITE_CONFIG: + case VIRTIO_CCW_DOING_WRITE_STATUS: + case VIRTIO_CCW_DOING_SET_VQ: + case VIRTIO_CCW_DOING_SET_IND: + case VIRTIO_CCW_DOING_SET_CONF_IND: + case VIRTIO_CCW_DOING_RESET: + case VIRTIO_CCW_DOING_READ_VQ_CONF: + case VIRTIO_CCW_DOING_SET_IND_ADAPTER: + case VIRTIO_CCW_DOING_SET_VIRTIO_REV: + vcdev->curr_io &= ~activity; + wake_up(&vcdev->wait_q); + break; + default: + /* don't know what to do... */ + dev_warn(&vcdev->cdev->dev, + "Suspicious activity '%08x'\n", activity); + WARN_ON(1); + break; + } + } +} + static void virtio_ccw_int_handler(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) @@ -995,6 +1025,12 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev, if (!vcdev) return; + if (IS_ERR(irb)) { + vcdev->err = PTR_ERR(irb); + virtio_ccw_check_activity(vcdev, activity); + /* Don't poke around indicators, something's wrong. */ + return; + } /* Check if it's a notification from the host. */ if ((intparm == 0) && (scsw_stctl(&irb->scsw) == @@ -1010,31 +1046,7 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev, /* Map everything else to -EIO. */ vcdev->err = -EIO; } - if (vcdev->curr_io & activity) { - switch (activity) { - case VIRTIO_CCW_DOING_READ_FEAT: - case VIRTIO_CCW_DOING_WRITE_FEAT: - case VIRTIO_CCW_DOING_READ_CONFIG: - case VIRTIO_CCW_DOING_WRITE_CONFIG: - case VIRTIO_CCW_DOING_WRITE_STATUS: - case VIRTIO_CCW_DOING_SET_VQ: - case VIRTIO_CCW_DOING_SET_IND: - case VIRTIO_CCW_DOING_SET_CONF_IND: - case VIRTIO_CCW_DOING_RESET: - case VIRTIO_CCW_DOING_READ_VQ_CONF: - case VIRTIO_CCW_DOING_SET_IND_ADAPTER: - case VIRTIO_CCW_DOING_SET_VIRTIO_REV: - vcdev->curr_io &= ~activity; - wake_up(&vcdev->wait_q); - break; - default: - /* don't know what to do... */ - dev_warn(&cdev->dev, "Suspicious activity '%08x'\n", - activity); - WARN_ON(1); - break; - } - } + virtio_ccw_check_activity(vcdev, activity); for_each_set_bit(i, &vcdev->indicators, sizeof(vcdev->indicators) * BITS_PER_BYTE) { /* The bit clear must happen before the vring kick. */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3d22fc3e3c1a..4e08d1cd704d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2885,10 +2885,13 @@ static int sd_revalidate_disk(struct gendisk *disk) /* * Use the device's preferred I/O size for reads and writes - * unless the reported value is unreasonably large (or garbage). + * unless the reported value is unreasonably small, large, or + * garbage. */ - if (sdkp->opt_xfer_blocks && sdkp->opt_xfer_blocks <= dev_max && - sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS) + if (sdkp->opt_xfer_blocks && + sdkp->opt_xfer_blocks <= dev_max && + sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && + sdkp->opt_xfer_blocks * sdp->sector_size >= PAGE_CACHE_SIZE) rw_max = q->limits.io_opt = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); else diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 59a11437db70..39412c9097c6 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -167,7 +167,7 @@ static inline int is_double_byte_mode(struct fsl_dspi *dspi) { unsigned int val; - regmap_read(dspi->regmap, SPI_CTAR(dspi->cs), &val); + regmap_read(dspi->regmap, SPI_CTAR(0), &val); return ((val & SPI_FRAME_BITS_MASK) == SPI_FRAME_BITS(8)) ? 0 : 1; } @@ -257,7 +257,7 @@ static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word) return SPI_PUSHR_TXDATA(d16) | SPI_PUSHR_PCS(dspi->cs) | - SPI_PUSHR_CTAS(dspi->cs) | + SPI_PUSHR_CTAS(0) | SPI_PUSHR_CONT; } @@ -290,7 +290,7 @@ static int dspi_eoq_write(struct fsl_dspi *dspi) */ if (tx_word && (dspi->len == 1)) { dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM; - regmap_update_bits(dspi->regmap, SPI_CTAR(dspi->cs), + regmap_update_bits(dspi->regmap, SPI_CTAR(0), SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8)); tx_word = 0; } @@ -339,7 +339,7 @@ static int dspi_tcfq_write(struct fsl_dspi *dspi) if (tx_word && (dspi->len == 1)) { dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM; - regmap_update_bits(dspi->regmap, SPI_CTAR(dspi->cs), + regmap_update_bits(dspi->regmap, SPI_CTAR(0), SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8)); tx_word = 0; } @@ -407,7 +407,7 @@ static int dspi_transfer_one_message(struct spi_master *master, regmap_update_bits(dspi->regmap, SPI_MCR, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF, SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF); - regmap_write(dspi->regmap, SPI_CTAR(dspi->cs), + regmap_write(dspi->regmap, SPI_CTAR(0), dspi->cur_chip->ctar_val); trans_mode = dspi->devtype_data->trans_mode; @@ -566,7 +566,7 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id) if (!dspi->len) { if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM) { regmap_update_bits(dspi->regmap, - SPI_CTAR(dspi->cs), + SPI_CTAR(0), SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(16)); dspi->dataflags &= ~TRAN_STATE_WORD_ODD_NUM; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 2b0a8ec3affb..dee1cb87d24f 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1705,7 +1705,7 @@ struct spi_master *spi_alloc_master(struct device *dev, unsigned size) master->bus_num = -1; master->num_chipselect = 1; master->dev.class = &spi_master_class; - master->dev.parent = get_device(dev); + master->dev.parent = dev; spi_master_set_devdata(master, &master[1]); return master; diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 91a0fcd72423..d0e7dfc647cf 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -651,11 +651,11 @@ static int spidev_release(struct inode *inode, struct file *filp) kfree(spidev->rx_buffer); spidev->rx_buffer = NULL; + spin_lock_irq(&spidev->spi_lock); if (spidev->spi) spidev->speed_hz = spidev->spi->max_speed_hz; /* ... after we unbound from the underlying device? */ - spin_lock_irq(&spidev->spi_lock); dofree = (spidev->spi == NULL); spin_unlock_irq(&spidev->spi_lock); diff --git a/drivers/staging/lustre/lustre/llite/symlink.c b/drivers/staging/lustre/lustre/llite/symlink.c index 69b203651905..e489a3271f06 100644 --- a/drivers/staging/lustre/lustre/llite/symlink.c +++ b/drivers/staging/lustre/lustre/llite/symlink.c @@ -118,12 +118,20 @@ failed: return rc; } -static const char *ll_follow_link(struct dentry *dentry, void **cookie) +static void ll_put_link(void *p) +{ + ptlrpc_req_finished(p); +} + +static const char *ll_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct ptlrpc_request *request = NULL; int rc; char *symname = NULL; + if (!dentry) + return ERR_PTR(-ECHILD); CDEBUG(D_VFSTRACE, "VFS Op\n"); ll_inode_size_lock(inode); @@ -135,22 +143,16 @@ static const char *ll_follow_link(struct dentry *dentry, void **cookie) } /* symname may contain a pointer to the request message buffer, - * we delay request releasing until ll_put_link then. + * we delay request releasing then. */ - *cookie = request; + set_delayed_call(done, ll_put_link, request); return symname; } -static void ll_put_link(struct inode *unused, void *cookie) -{ - ptlrpc_req_finished(cookie); -} - struct inode_operations ll_fast_symlink_inode_operations = { .readlink = generic_readlink, .setattr = ll_setattr, - .follow_link = ll_follow_link, - .put_link = ll_put_link, + .get_link = ll_get_link, .getattr = ll_getattr, .permission = ll_inode_permission, .setxattr = ll_setxattr, diff --git a/drivers/staging/lustre/lustre/llite/xattr.c b/drivers/staging/lustre/lustre/llite/xattr.c index 4b7eb33f7d01..660b8ac37ae0 100644 --- a/drivers/staging/lustre/lustre/llite/xattr.c +++ b/drivers/staging/lustre/lustre/llite/xattr.c @@ -60,10 +60,10 @@ static int get_xattr_type(const char *name) { - if (!strcmp(name, POSIX_ACL_XATTR_ACCESS)) + if (!strcmp(name, XATTR_NAME_POSIX_ACL_ACCESS)) return XATTR_ACL_ACCESS_T; - if (!strcmp(name, POSIX_ACL_XATTR_DEFAULT)) + if (!strcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT)) return XATTR_ACL_DEFAULT_T; if (!strncmp(name, XATTR_USER_PREFIX, diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index ed776149261e..e49c2bce551d 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2054,13 +2054,13 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, size_t eol; size_t tail; int ret, found = 0; - bool eof_push = 0; /* N.B. avoid overrun if nr == 0 */ - n = min(*nr, smp_load_acquire(&ldata->canon_head) - ldata->read_tail); - if (!n) + if (!*nr) return 0; + n = min(*nr + 1, smp_load_acquire(&ldata->canon_head) - ldata->read_tail); + tail = ldata->read_tail & (N_TTY_BUF_SIZE - 1); size = min_t(size_t, tail + n, N_TTY_BUF_SIZE); @@ -2081,12 +2081,11 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, n = eol - tail; if (n > N_TTY_BUF_SIZE) n += N_TTY_BUF_SIZE; - n += found; - c = n; + c = n + found; - if (found && !ldata->push && read_buf(ldata, eol) == __DISABLED_CHAR) { - n--; - eof_push = !n && ldata->read_tail != ldata->line_start; + if (!found || read_buf(ldata, eol) != __DISABLED_CHAR) { + c = min(*nr, c); + n = c; } n_tty_trace("%s: eol:%zu found:%d n:%zu c:%zu size:%zu more:%zu\n", @@ -2116,7 +2115,7 @@ static int canon_copy_from_read_buf(struct tty_struct *tty, ldata->push = 0; tty_audit_push(tty); } - return eof_push ? -EAGAIN : 0; + return 0; } extern ssize_t redirected_tty_write(struct file *, const char __user *, @@ -2273,10 +2272,7 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file, if (ldata->icanon && !L_EXTPROC(tty)) { retval = canon_copy_from_read_buf(tty, &b, &nr); - if (retval == -EAGAIN) { - retval = 0; - continue; - } else if (retval) + if (retval) break; } else { int uncopied; diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c index d11621e2cf1d..245edbb68d4b 100644 --- a/drivers/tty/serial/8250/8250_uniphier.c +++ b/drivers/tty/serial/8250/8250_uniphier.c @@ -115,12 +115,16 @@ static void uniphier_serial_out(struct uart_port *p, int offset, int value) */ static int uniphier_serial_dl_read(struct uart_8250_port *up) { - return readl(up->port.membase + UNIPHIER_UART_DLR); + int offset = UNIPHIER_UART_DLR << up->port.regshift; + + return readl(up->port.membase + offset); } static void uniphier_serial_dl_write(struct uart_8250_port *up, int value) { - writel(value, up->port.membase + UNIPHIER_UART_DLR); + int offset = UNIPHIER_UART_DLR << up->port.regshift; + + writel(value, up->port.membase + offset); } static int uniphier_of_serial_setup(struct device *dev, struct uart_port *port, diff --git a/drivers/tty/serial/earlycon.c b/drivers/tty/serial/earlycon.c index f09636083426..b5b2f2be6be7 100644 --- a/drivers/tty/serial/earlycon.c +++ b/drivers/tty/serial/earlycon.c @@ -115,6 +115,7 @@ static int __init register_earlycon(char *buf, const struct earlycon_id *match) if (buf && !parse_options(&early_console_dev, buf)) buf = NULL; + spin_lock_init(&port->lock); port->uartclk = BASE_BAUD * 16; if (port->mapbase) port->membase = earlycon_map(port->mapbase, 64); @@ -202,6 +203,7 @@ int __init of_setup_earlycon(unsigned long addr, int err; struct uart_port *port = &early_console_dev.port; + spin_lock_init(&port->lock); port->iotype = UPIO_MEM; port->mapbase = addr; port->uartclk = BASE_BAUD * 16; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 960e50a97558..51c7507b0444 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1437,7 +1437,7 @@ static void sci_request_dma(struct uart_port *port) sg_init_table(sg, 1); s->rx_buf[i] = buf; sg_dma_address(sg) = dma; - sg->length = s->buf_len_rx; + sg_dma_len(sg) = s->buf_len_rx; buf += s->buf_len_rx; dma += s->buf_len_rx; diff --git a/drivers/tty/serial/sunhv.c b/drivers/tty/serial/sunhv.c index 064031870ba0..ca0d3802f2af 100644 --- a/drivers/tty/serial/sunhv.c +++ b/drivers/tty/serial/sunhv.c @@ -148,8 +148,10 @@ static int receive_chars_read(struct uart_port *port) uart_handle_dcd_change(port, 1); } - for (i = 0; i < bytes_read; i++) - uart_handle_sysrq_char(port, con_read_page[i]); + if (port->sysrq != 0 && *con_read_page) { + for (i = 0; i < bytes_read; i++) + uart_handle_sysrq_char(port, con_read_page[i]); + } if (port->state == NULL) continue; @@ -168,17 +170,17 @@ struct sunhv_ops { int (*receive_chars)(struct uart_port *port); }; -static struct sunhv_ops bychar_ops = { +static const struct sunhv_ops bychar_ops = { .transmit_chars = transmit_chars_putchar, .receive_chars = receive_chars_getchar, }; -static struct sunhv_ops bywrite_ops = { +static const struct sunhv_ops bywrite_ops = { .transmit_chars = transmit_chars_write, .receive_chars = receive_chars_read, }; -static struct sunhv_ops *sunhv_ops = &bychar_ops; +static const struct sunhv_ops *sunhv_ops = &bychar_ops; static struct tty_port *receive_chars(struct uart_port *port) { diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 5381a728d23e..e5139402e7f8 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -133,6 +133,12 @@ static void sysrq_handle_crash(int key) { char *killer = NULL; + /* we need to release the RCU read lock here, + * otherwise we get an annoying + * 'BUG: sleeping function called from invalid context' + * complaint from the kernel before the panic. + */ + rcu_read_unlock(); panic_on_oops = 1; /* force panic */ wmb(); *killer = 1; diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 9a479e61791a..3cd31e0d4bd9 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -450,7 +450,7 @@ receive_buf(struct tty_struct *tty, struct tty_buffer *head, int count) count = disc->ops->receive_buf2(tty, p, f, count); else { count = min_t(int, count, tty->receive_room); - if (count) + if (count && disc->ops->receive_buf) disc->ops->receive_buf(tty, p, f, count); } return count; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index a5cc032ef77a..ddbf32d599cb 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1035,10 +1035,20 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) unsigned delay; /* Continue a partial initialization */ - if (type == HUB_INIT2) - goto init2; - if (type == HUB_INIT3) + if (type == HUB_INIT2 || type == HUB_INIT3) { + device_lock(hub->intfdev); + + /* Was the hub disconnected while we were waiting? */ + if (hub->disconnected) { + device_unlock(hub->intfdev); + kref_put(&hub->kref, hub_release); + return; + } + if (type == HUB_INIT2) + goto init2; goto init3; + } + kref_get(&hub->kref); /* The superspeed hub except for root hub has to use Hub Depth * value as an offset into the route string to locate the bits @@ -1236,6 +1246,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) queue_delayed_work(system_power_efficient_wq, &hub->init_work, msecs_to_jiffies(delay)); + device_unlock(hub->intfdev); return; /* Continues at init3: below */ } else { msleep(delay); @@ -1257,6 +1268,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Allow autosuspend if it was suppressed */ if (type <= HUB_INIT3) usb_autopm_put_interface_async(to_usb_interface(hub->intfdev)); + + if (type == HUB_INIT2 || type == HUB_INIT3) + device_unlock(hub->intfdev); + + kref_put(&hub->kref, hub_release); } /* Implement the continuations for the delays above */ diff --git a/drivers/usb/serial/ipaq.c b/drivers/usb/serial/ipaq.c index f51a5d52c0ed..ec1b8f2c1183 100644 --- a/drivers/usb/serial/ipaq.c +++ b/drivers/usb/serial/ipaq.c @@ -531,7 +531,8 @@ static int ipaq_open(struct tty_struct *tty, * through. Since this has a reasonably high failure rate, we retry * several times. */ - while (retries--) { + while (retries) { + retries--; result = usb_control_msg(serial->dev, usb_sndctrlpipe(serial->dev, 0), 0x22, 0x21, 0x1, 0, NULL, 0, 100); diff --git a/fs/9p/acl.c b/fs/9p/acl.c index a7e28890f5ef..9da967f38387 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -67,8 +67,8 @@ int v9fs_get_acl(struct inode *inode, struct p9_fid *fid) return 0; } /* get the default/access acl values and cache them */ - dacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_DEFAULT); - pacl = __v9fs_get_acl(fid, POSIX_ACL_XATTR_ACCESS); + dacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_DEFAULT); + pacl = __v9fs_get_acl(fid, XATTR_NAME_POSIX_ACL_ACCESS); if (!IS_ERR(dacl) && !IS_ERR(pacl)) { set_cached_acl(inode, ACL_TYPE_DEFAULT, dacl); @@ -133,10 +133,10 @@ static int v9fs_set_acl(struct p9_fid *fid, int type, struct posix_acl *acl) goto err_free_out; switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -220,15 +220,12 @@ static int v9fs_xattr_get_acl(const struct xattr_handler *handler, struct posix_acl *acl; int error; - if (strcmp(name, "") != 0) - return -EINVAL; - v9ses = v9fs_dentry2v9ses(dentry); /* * We allow set/get/list of acl when access=client is not specified */ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) - return v9fs_xattr_get(dentry, handler->prefix, buffer, size); + return v9fs_xattr_get(dentry, handler->name, buffer, size); acl = v9fs_get_cached_acl(d_inode(dentry), handler->flags); if (IS_ERR(acl)) @@ -250,16 +247,13 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, struct v9fs_session_info *v9ses; struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; - v9ses = v9fs_dentry2v9ses(dentry); /* * set the attribute on the remote. Without even looking at the * xattr value. We leave it to the server to validate */ if ((v9ses->flags & V9FS_ACCESS_MASK) != V9FS_ACCESS_CLIENT) - return v9fs_xattr_set(dentry, handler->prefix, value, size, + return v9fs_xattr_set(dentry, handler->name, value, size, flags); if (S_ISLNK(inode->i_mode)) @@ -319,7 +313,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, default: BUG(); } - retval = v9fs_xattr_set(dentry, handler->prefix, value, size, flags); + retval = v9fs_xattr_set(dentry, handler->name, value, size, flags); if (!retval) set_cached_acl(inode, handler->flags, acl); err_out: @@ -328,14 +322,14 @@ err_out: } const struct xattr_handler v9fs_xattr_acl_access_handler = { - .prefix = POSIX_ACL_XATTR_ACCESS, + .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .get = v9fs_xattr_get_acl, .set = v9fs_xattr_set_acl, }; const struct xattr_handler v9fs_xattr_acl_default_handler = { - .prefix = POSIX_ACL_XATTR_DEFAULT, + .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .get = v9fs_xattr_get_acl, .set = v9fs_xattr_set_acl, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 511078586fa1..c7cc7c30f0c8 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1223,18 +1223,26 @@ ino_t v9fs_qid2ino(struct p9_qid *qid) } /** - * v9fs_vfs_follow_link - follow a symlink path + * v9fs_vfs_get_link - follow a symlink path * @dentry: dentry for symlink - * @cookie: place to pass the data to put_link() + * @inode: inode for symlink + * @done: delayed call for when we are done with the return value */ -static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie) +static const char *v9fs_vfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); - struct p9_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_session_info *v9ses; + struct p9_fid *fid; struct p9_wstat *st; char *res; + if (!dentry) + return ERR_PTR(-ECHILD); + + v9ses = v9fs_dentry2v9ses(dentry); + fid = v9fs_fid_lookup(dentry); p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); if (IS_ERR(fid)) @@ -1259,7 +1267,8 @@ static const char *v9fs_vfs_follow_link(struct dentry *dentry, void **cookie) p9stat_free(st); kfree(st); - return *cookie = res; + set_delayed_call(done, kfree_link, res); + return res; } /** @@ -1452,8 +1461,7 @@ static const struct inode_operations v9fs_file_inode_operations = { static const struct inode_operations v9fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link, - .put_link = kfree_put_link, + .get_link = v9fs_vfs_get_link, .getattr = v9fs_vfs_getattr, .setattr = v9fs_vfs_setattr, }; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index cb899af1babc..a34702c998f5 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -899,26 +899,34 @@ error: } /** - * v9fs_vfs_follow_link_dotl - follow a symlink path + * v9fs_vfs_get_link_dotl - follow a symlink path * @dentry: dentry for symlink - * @cookie: place to pass the data to put_link() + * @inode: inode for symlink + * @done: destructor for return value */ static const char * -v9fs_vfs_follow_link_dotl(struct dentry *dentry, void **cookie) +v9fs_vfs_get_link_dotl(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct p9_fid *fid = v9fs_fid_lookup(dentry); + struct p9_fid *fid; char *target; int retval; + if (!dentry) + return ERR_PTR(-ECHILD); + p9_debug(P9_DEBUG_VFS, "%pd\n", dentry); + fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) return ERR_CAST(fid); retval = p9_client_readlink(fid, &target); if (retval) return ERR_PTR(retval); - return *cookie = target; + set_delayed_call(done, kfree_link, target); + return target; } int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) @@ -984,8 +992,7 @@ const struct inode_operations v9fs_file_inode_operations_dotl = { const struct inode_operations v9fs_symlink_inode_operations_dotl = { .readlink = generic_readlink, - .follow_link = v9fs_vfs_follow_link_dotl, - .put_link = kfree_put_link, + .get_link = v9fs_vfs_get_link_dotl, .getattr = v9fs_vfs_getattr_dotl, .setattr = v9fs_vfs_setattr_dotl, .setxattr = generic_setxattr, diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index e3d026ac382e..9dd9b47a6c1a 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -143,8 +143,6 @@ static int v9fs_xattr_handler_get(const struct xattr_handler *handler, { const char *full_name = xattr_full_name(handler, name); - if (strcmp(name, "") == 0) - return -EINVAL; return v9fs_xattr_get(dentry, full_name, buffer, size); } @@ -154,8 +152,6 @@ static int v9fs_xattr_handler_set(const struct xattr_handler *handler, { const char *full_name = xattr_full_name(handler, name); - if (strcmp(name, "") == 0) - return -EINVAL; return v9fs_xattr_set(dentry, full_name, value, size, flags); } diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 17349500592d..0fdb0f5b2239 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -140,6 +140,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) break; case ST_SOFTLINK: inode->i_mode |= S_IFLNK; + inode_nohighmem(inode); inode->i_op = &affs_symlink_inode_operations; inode->i_data.a_ops = &affs_symlink_aops; break; diff --git a/fs/affs/namei.c b/fs/affs/namei.c index 181e05b46e72..00d3002a6780 100644 --- a/fs/affs/namei.c +++ b/fs/affs/namei.c @@ -344,6 +344,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) return -ENOSPC; inode->i_op = &affs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &affs_symlink_aops; inode->i_mode = S_IFLNK | 0777; mode_to_prot(inode); diff --git a/fs/affs/symlink.c b/fs/affs/symlink.c index ea5b69a18ba9..69b03dbb792f 100644 --- a/fs/affs/symlink.c +++ b/fs/affs/symlink.c @@ -14,13 +14,13 @@ static int affs_symlink_readpage(struct file *file, struct page *page) { struct buffer_head *bh; struct inode *inode = page->mapping->host; - char *link = kmap(page); + char *link = page_address(page); struct slink_front *lf; int i, j; char c; char lc; - pr_debug("follow_link(ino=%lu)\n", inode->i_ino); + pr_debug("get_link(ino=%lu)\n", inode->i_ino); bh = affs_bread(inode->i_sb, inode->i_ino); if (!bh) @@ -57,12 +57,10 @@ static int affs_symlink_readpage(struct file *file, struct page *page) link[i] = '\0'; affs_brelse(bh); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return -EIO; } @@ -73,7 +71,6 @@ const struct address_space_operations affs_symlink_aops = { const struct inode_operations affs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = affs_notify_change, }; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index e06f5a23352a..86cc7264c21c 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -56,6 +56,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) case AFS_FTYPE_SYMLINK: inode->i_mode = S_IFLNK | vnode->status.mode; inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; default: printk("kAFS: AFS vnode with undefined type\n"); diff --git a/fs/autofs4/symlink.c b/fs/autofs4/symlink.c index da0c33481bc0..84e037d1d129 100644 --- a/fs/autofs4/symlink.c +++ b/fs/autofs4/symlink.c @@ -12,10 +12,16 @@ #include "autofs_i.h" -static const char *autofs4_follow_link(struct dentry *dentry, void **cookie) +static const char *autofs4_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi; + struct autofs_info *ino; + if (!dentry) + return ERR_PTR(-ECHILD); + sbi = autofs4_sbi(dentry->d_sb); + ino = autofs4_dentry_ino(dentry); if (ino && !autofs4_oz_mode(sbi)) ino->last_used = jiffies; return d_inode(dentry)->i_private; @@ -23,5 +29,5 @@ static const char *autofs4_follow_link(struct dentry *dentry, void **cookie) const struct inode_operations autofs4_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = autofs4_follow_link + .get_link = autofs4_get_link }; diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 46aedacfa6a8..25250fa87086 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -42,7 +42,7 @@ static struct inode *befs_iget(struct super_block *, unsigned long); static struct inode *befs_alloc_inode(struct super_block *sb); static void befs_destroy_inode(struct inode *inode); static void befs_destroy_inodecache(void); -static const char *befs_follow_link(struct dentry *, void **); +static int befs_symlink_readpage(struct file *, struct page *); static int befs_utf2nls(struct super_block *sb, const char *in, int in_len, char **out, int *out_len); static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, @@ -79,10 +79,8 @@ static const struct address_space_operations befs_aops = { .bmap = befs_bmap, }; -static const struct inode_operations befs_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = befs_follow_link, - .put_link = kfree_put_link, +static const struct address_space_operations befs_symlink_aops = { + .readpage = befs_symlink_readpage, }; /* @@ -398,7 +396,9 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &befs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { if (befs_ino->i_flags & BEFS_LONG_SYMLINK) { - inode->i_op = &befs_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); + inode->i_mapping->a_ops = &befs_symlink_aops; } else { inode->i_link = befs_ino->i_data.symlink; inode->i_op = &simple_symlink_inode_operations; @@ -463,31 +463,33 @@ befs_destroy_inodecache(void) * The data stream become link name. Unless the LONG_SYMLINK * flag is set. */ -static const char * -befs_follow_link(struct dentry *dentry, void **cookie) +static int befs_symlink_readpage(struct file *unused, struct page *page) { - struct super_block *sb = dentry->d_sb; - struct befs_inode_info *befs_ino = BEFS_I(d_inode(dentry)); + struct inode *inode = page->mapping->host; + struct super_block *sb = inode->i_sb; + struct befs_inode_info *befs_ino = BEFS_I(inode); befs_data_stream *data = &befs_ino->i_data.ds; befs_off_t len = data->size; - char *link; + char *link = page_address(page); - if (len == 0) { + if (len == 0 || len > PAGE_SIZE) { befs_error(sb, "Long symlink with illegal length"); - return ERR_PTR(-EIO); + goto fail; } befs_debug(sb, "Follow long symlink"); - link = kmalloc(len, GFP_NOFS); - if (!link) - return ERR_PTR(-ENOMEM); if (befs_read_lsymlink(sb, data, link, len) != len) { - kfree(link); befs_error(sb, "Failed to read entire long symlink"); - return ERR_PTR(-EIO); + goto fail; } link[len - 1] = '\0'; - return *cookie = link; + SetPageUptodate(page); + unlock_page(page); + return 0; +fail: + SetPageError(page); + unlock_page(page); + return -EIO; } /* diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 9a0124a95851..f89db0c21b51 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -37,10 +37,10 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -81,7 +81,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { ret = posix_acl_equiv_mode(acl, &inode->i_mode); if (ret < 0) @@ -94,7 +94,7 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) return acl ? -EINVAL : 0; - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return -EINVAL; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a70c5790f8f5..3b8856e182ae 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3550,10 +3550,10 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, int scanned = 0; if (!xattr_access) { - xattr_access = btrfs_name_hash(POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)); - xattr_default = btrfs_name_hash(POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)); + xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)); + xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)); } slot++; @@ -3774,6 +3774,7 @@ cache_acl: break; case S_IFLNK: inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; break; default: @@ -9705,6 +9706,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, btrfs_free_path(path); inode->i_op = &btrfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &btrfs_symlink_aops; inode_set_bytes(inode, name_len); btrfs_i_size_write(inode, name_len); @@ -9994,7 +9996,7 @@ static const struct inode_operations btrfs_dir_inode_operations = { .setattr = btrfs_setattr, .mknod = btrfs_mknod, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .permission = btrfs_permission, @@ -10071,7 +10073,7 @@ static const struct inode_operations btrfs_file_inode_operations = { .getattr = btrfs_getattr, .setattr = btrfs_setattr, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .permission = btrfs_permission, @@ -10085,7 +10087,7 @@ static const struct inode_operations btrfs_special_inode_operations = { .setattr = btrfs_setattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .get_acl = btrfs_get_acl, @@ -10094,13 +10096,12 @@ static const struct inode_operations btrfs_special_inode_operations = { }; static const struct inode_operations btrfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = btrfs_getattr, .setattr = btrfs_setattr, .permission = btrfs_permission, .setxattr = btrfs_setxattr, - .getxattr = btrfs_getxattr, + .getxattr = generic_getxattr, .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .update_time = btrfs_update_time, diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 1fcd7b6e7564..7cbef1a14fe1 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -351,137 +351,89 @@ err: return ret; } -/* - * List of handlers for synthetic system.* attributes. All real ondisk - * attributes are handled directly. - */ -const struct xattr_handler *btrfs_xattr_handlers[] = { -#ifdef CONFIG_BTRFS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif - NULL, -}; - -/* - * Check if the attribute is in a supported namespace. - * - * This is applied after the check for the synthetic attributes in the system - * namespace. - */ -static int btrfs_is_valid_xattr(const char *name) +static int btrfs_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { - int len = strlen(name); - int prefixlen = 0; - - if (!strncmp(name, XATTR_SECURITY_PREFIX, - XATTR_SECURITY_PREFIX_LEN)) - prefixlen = XATTR_SECURITY_PREFIX_LEN; - else if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - prefixlen = XATTR_SYSTEM_PREFIX_LEN; - else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) - prefixlen = XATTR_TRUSTED_PREFIX_LEN; - else if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) - prefixlen = XATTR_USER_PREFIX_LEN; - else if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - prefixlen = XATTR_BTRFS_PREFIX_LEN; - else - return -EOPNOTSUPP; - - /* - * The name cannot consist of just prefix - */ - if (len <= prefixlen) - return -EINVAL; + struct inode *inode = d_inode(dentry); - return 0; + name = xattr_full_name(handler, name); + return __btrfs_getxattr(inode, name, buffer, size); } -ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size) +static int btrfs_xattr_handler_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *buffer, size_t size, + int flags) { - int ret; + struct inode *inode = d_inode(dentry); - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_getxattr(dentry, name, buffer, size); + name = xattr_full_name(handler, name); + return __btrfs_setxattr(NULL, inode, name, buffer, size, flags); +} - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - return __btrfs_getxattr(d_inode(dentry), name, buffer, size); +static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, + struct dentry *dentry, + const char *name, const void *value, + size_t size, int flags) +{ + name = xattr_full_name(handler, name); + return btrfs_set_prop(d_inode(dentry), name, value, size, flags); } +static const struct xattr_handler btrfs_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_user_xattr_handler = { + .prefix = XATTR_USER_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set, +}; + +static const struct xattr_handler btrfs_btrfs_xattr_handler = { + .prefix = XATTR_BTRFS_PREFIX, + .get = btrfs_xattr_handler_get, + .set = btrfs_xattr_handler_set_prop, +}; + +const struct xattr_handler *btrfs_xattr_handlers[] = { + &btrfs_security_xattr_handler, +#ifdef CONFIG_BTRFS_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &btrfs_trusted_xattr_handler, + &btrfs_user_xattr_handler, + &btrfs_btrfs_xattr_handler, + NULL, +}; + int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - int ret; - /* - * The permission on security.* and system.* is not checked - * in permission(). - */ if (btrfs_root_readonly(root)) return -EROFS; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_setxattr(dentry, name, value, size, flags); - - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(d_inode(dentry), name, - value, size, flags); - - if (size == 0) - value = ""; /* empty EA, do not remove */ - - return __btrfs_setxattr(NULL, d_inode(dentry), name, value, size, - flags); + return generic_setxattr(dentry, name, value, size, flags); } int btrfs_removexattr(struct dentry *dentry, const char *name) { struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root; - int ret; - /* - * The permission on security.* and system.* is not checked - * in permission(). - */ if (btrfs_root_readonly(root)) return -EROFS; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_removexattr(dentry, name); - - ret = btrfs_is_valid_xattr(name); - if (ret) - return ret; - - if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN)) - return btrfs_set_prop(d_inode(dentry), name, - NULL, 0, XATTR_REPLACE); - - return __btrfs_setxattr(NULL, d_inode(dentry), name, NULL, 0, - XATTR_REPLACE); + return generic_removexattr(dentry, name); } static int btrfs_initxattrs(struct inode *inode, diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h index 5049608d1388..96807b3d22f5 100644 --- a/fs/btrfs/xattr.h +++ b/fs/btrfs/xattr.h @@ -28,8 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name, extern int __btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags); -extern ssize_t btrfs_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size); extern int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int btrfs_removexattr(struct dentry *dentry, const char *name); diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 8f84646f10e9..f19708487e2f 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -49,10 +49,10 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -92,7 +92,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { ret = posix_acl_equiv_mode(acl, &new_mode); if (ret < 0) @@ -106,7 +106,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) ret = acl ? -EINVAL : 0; goto out; } - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: ret = -EINVAL; @@ -202,11 +202,11 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1); if (acl) { - size_t len = strlen(POSIX_ACL_XATTR_ACCESS); + size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS); err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8); if (err) goto out_err; - ceph_pagelist_encode_string(pagelist, POSIX_ACL_XATTR_ACCESS, + ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS, len); err = posix_acl_to_xattr(&init_user_ns, acl, tmp_buf, val_size1); @@ -216,12 +216,12 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode, ceph_pagelist_append(pagelist, tmp_buf, val_size1); } if (default_acl) { - size_t len = strlen(POSIX_ACL_XATTR_DEFAULT); + size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT); err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8); if (err) goto out_err; err = ceph_pagelist_encode_string(pagelist, - POSIX_ACL_XATTR_DEFAULT, len); + XATTR_NAME_POSIX_ACL_DEFAULT, len); err = posix_acl_to_xattr(&init_user_ns, default_acl, tmp_buf, val_size2); if (err < 0) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 498dcfa2dcdb..da55eb8bcffa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1756,7 +1756,7 @@ retry: */ static const struct inode_operations ceph_symlink_iops = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ceph_setattr, .getattr = ceph_getattr, .setxattr = ceph_setxattr, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index cbc0f4bca0c0..90e4e2b398b6 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -900,8 +900,7 @@ const struct inode_operations cifs_file_inode_ops = { const struct inode_operations cifs_symlink_inode_ops = { .readlink = generic_readlink, - .follow_link = cifs_follow_link, - .put_link = kfree_put_link, + .get_link = cifs_get_link, .permission = cifs_permission, /* BB add the following two eventually */ /* revalidate: cifs_revalidate, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c3cc1609025f..26a1187d4323 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -120,9 +120,8 @@ extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #endif /* Functions related to symlinks */ -extern const char *cifs_follow_link(struct dentry *direntry, void **cookie); -extern int cifs_readlink(struct dentry *direntry, char __user *buffer, - int buflen); +extern const char *cifs_get_link(struct dentry *, struct inode *, + struct delayed_call *); extern int cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname); extern int cifs_removexattr(struct dentry *, const char *); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index e3548f73bdea..062c2375549a 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -627,9 +627,9 @@ cifs_hl_exit: } const char * -cifs_follow_link(struct dentry *direntry, void **cookie) +cifs_get_link(struct dentry *direntry, struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(direntry); int rc = -ENOMEM; unsigned int xid; char *full_path = NULL; @@ -639,6 +639,9 @@ cifs_follow_link(struct dentry *direntry, void **cookie) struct cifs_tcon *tcon; struct TCP_Server_Info *server; + if (!direntry) + return ERR_PTR(-ECHILD); + xid = get_xid(); tlink = cifs_sb_tlink(cifs_sb); @@ -678,7 +681,8 @@ cifs_follow_link(struct dentry *direntry, void **cookie) kfree(target_path); return ERR_PTR(rc); } - return *cookie = target_path; + set_delayed_call(done, kfree_link, target_path); + return target_path; } int diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index ff9e1f8b16a4..f5dc2f0df4ad 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -190,8 +190,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #endif /* CONFIG_CIFS_ACL */ } else { int temp; - temp = strncmp(ea_name, POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)); + temp = strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)); if (temp == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) @@ -203,8 +203,8 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, #else cifs_dbg(FYI, "set POSIX ACL not supported\n"); #endif - } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBSetPosixACL(xid, pTcon, full_path, @@ -292,8 +292,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon, full_path, ea_name, ea_value, buf_size, cifs_sb->local_nls, cifs_remap(cifs_sb)); - } else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_ACCESS, + strlen(XATTR_NAME_POSIX_ACL_ACCESS)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, @@ -303,8 +303,8 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, #else cifs_dbg(FYI, "Query POSIX ACL not supported yet\n"); #endif /* CONFIG_CIFS_POSIX */ - } else if (strncmp(ea_name, POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT)) == 0) { + } else if (strncmp(ea_name, XATTR_NAME_POSIX_ACL_DEFAULT, + strlen(XATTR_NAME_POSIX_ACL_DEFAULT)) == 0) { #ifdef CONFIG_CIFS_POSIX if (sb->s_flags & MS_POSIXACL) rc = CIFSSMBGetPosixACL(xid, pTcon, full_path, diff --git a/fs/coda/cnode.c b/fs/coda/cnode.c index 7740b1c871c1..1bfb7ba4e85e 100644 --- a/fs/coda/cnode.c +++ b/fs/coda/cnode.c @@ -8,6 +8,7 @@ #include <linux/coda.h> #include <linux/coda_psdev.h> +#include <linux/pagemap.h> #include "coda_linux.h" static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) @@ -17,8 +18,7 @@ static inline int coda_fideq(struct CodaFid *fid1, struct CodaFid *fid2) static const struct inode_operations coda_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = coda_setattr, }; @@ -35,6 +35,7 @@ static void coda_fill_inode(struct inode *inode, struct coda_vattr *attr) inode->i_fop = &coda_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &coda_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &coda_symlink_aops; inode->i_mapping = &inode->i_data; } else diff --git a/fs/coda/symlink.c b/fs/coda/symlink.c index ab94ef63caef..03736e20d720 100644 --- a/fs/coda/symlink.c +++ b/fs/coda/symlink.c @@ -26,7 +26,7 @@ static int coda_symlink_filler(struct file *file, struct page *page) int error; struct coda_inode_info *cii; unsigned int len = PAGE_SIZE; - char *p = kmap(page); + char *p = page_address(page); cii = ITOC(inode); @@ -34,13 +34,11 @@ static int coda_symlink_filler(struct file *file, struct page *page) if (error) goto fail; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return error; } diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index dcf26537c935..9144b779d10e 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -58,6 +58,8 @@ #include <linux/atalk.h> #include <linux/gfp.h> +#include "internal.h" + #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_sock.h> #include <net/bluetooth/rfcomm.h> @@ -115,19 +117,38 @@ #include <asm/fbio.h> #endif -static int w_long(unsigned int fd, unsigned int cmd, - compat_ulong_t __user *argp) +#define convert_in_user(srcptr, dstptr) \ +({ \ + typeof(*srcptr) val; \ + \ + get_user(val, srcptr) || put_user(val, dstptr); \ +}) + +static int do_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + int err; + + err = security_file_ioctl(file, cmd, arg); + if (err) + return err; + + return vfs_ioctl(file, cmd, arg); +} + +static int w_long(struct file *file, + unsigned int cmd, compat_ulong_t __user *argp) { - mm_segment_t old_fs = get_fs(); int err; - unsigned long val; + unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp)); - set_fs (KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long)&val); - set_fs (old_fs); - if (!err && put_user(val, argp)) + if (valp == NULL) return -EFAULT; - return err; + err = do_ioctl(file, cmd, (unsigned long)valp); + if (err) + return err; + if (convert_in_user(valp, argp)) + return -EFAULT; + return 0; } struct compat_video_event { @@ -139,23 +160,23 @@ struct compat_video_event { } u; }; -static int do_video_get_event(unsigned int fd, unsigned int cmd, - struct compat_video_event __user *up) +static int do_video_get_event(struct file *file, + unsigned int cmd, struct compat_video_event __user *up) { - struct video_event kevent; - mm_segment_t old_fs = get_fs(); + struct video_event __user *kevent = + compat_alloc_user_space(sizeof(*kevent)); int err; - set_fs(KERNEL_DS); - err = sys_ioctl(fd, cmd, (unsigned long) &kevent); - set_fs(old_fs); + if (kevent == NULL) + return -EFAULT; + err = do_ioctl(file, cmd, (unsigned long)kevent); if (!err) { - err = put_user(kevent.type, &up->type); - err |= put_user(kevent.timestamp, &up->timestamp); - err |= put_user(kevent.u.size.w, &up->u.size.w); - err |= put_user(kevent.u.size.h, &up->u.size.h); - err |= put_user(kevent.u.size.aspect_ratio, + err = convert_in_user(&kevent->type, &up->type); + err |= convert_in_user(&kevent->timestamp, &up->timestamp); + err |= convert_in_user(&kevent->u.size.w, &up->u.size.w); + err |= convert_in_user(&kevent->u.size.h, &up->u.size.h); + err |= convert_in_user(&kevent->u.size.aspect_ratio, &up->u.size.aspect_ratio); if (err) err = -EFAULT; @@ -169,8 +190,8 @@ struct compat_video_still_picture { int32_t size; }; -static int do_video_stillpicture(unsigned int fd, unsigned int cmd, - struct compat_video_still_picture __user *up) +static int do_video_stillpicture(struct file *file, + unsigned int cmd, struct compat_video_still_picture __user *up) { struct video_still_picture __user *up_native; compat_uptr_t fp; @@ -190,7 +211,7 @@ static int do_video_stillpicture(unsigned int fd, unsigned int cmd, if (err) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) up_native); + err = do_ioctl(file, cmd, (unsigned long) up_native); return err; } @@ -200,8 +221,8 @@ struct compat_video_spu_palette { compat_uptr_t palette; }; -static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, - struct compat_video_spu_palette __user *up) +static int do_video_set_spu_palette(struct file *file, + unsigned int cmd, struct compat_video_spu_palette __user *up) { struct video_spu_palette __user *up_native; compat_uptr_t palp; @@ -218,7 +239,7 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, if (err) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) up_native); + err = do_ioctl(file, cmd, (unsigned long) up_native); return err; } @@ -276,7 +297,7 @@ static int sg_build_iovec(sg_io_hdr_t __user *sgio, void __user *dxferp, u16 iov return 0; } -static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, +static int sg_ioctl_trans(struct file *file, unsigned int cmd, sg_io_hdr32_t __user *sgio32) { sg_io_hdr_t __user *sgio; @@ -289,7 +310,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, if (get_user(interface_id, &sgio32->interface_id)) return -EFAULT; if (interface_id != 'S') - return sys_ioctl(fd, cmd, (unsigned long)sgio32); + return do_ioctl(file, cmd, (unsigned long)sgio32); if (get_user(iovec_count, &sgio32->iovec_count)) return -EFAULT; @@ -349,7 +370,7 @@ static int sg_ioctl_trans(unsigned int fd, unsigned int cmd, if (put_user(compat_ptr(data), &sgio->usr_ptr)) return -EFAULT; - err = sys_ioctl(fd, cmd, (unsigned long) sgio); + err = do_ioctl(file, cmd, (unsigned long) sgio); if (err >= 0) { void __user *datap; @@ -380,13 +401,13 @@ struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ int unused; }; -static int sg_grt_trans(unsigned int fd, unsigned int cmd, struct - compat_sg_req_info __user *o) +static int sg_grt_trans(struct file *file, + unsigned int cmd, struct compat_sg_req_info __user *o) { int err, i; sg_req_info_t __user *r; r = compat_alloc_user_space(sizeof(sg_req_info_t)*SG_MAX_QUEUE); - err = sys_ioctl(fd,cmd,(unsigned long)r); + err = do_ioctl(file, cmd, (unsigned long)r); if (err < 0) return err; for (i = 0; i < SG_MAX_QUEUE; i++) { @@ -412,8 +433,8 @@ struct sock_fprog32 { #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) -static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd, - struct sock_fprog32 __user *u_fprog32) +static int ppp_sock_fprog_ioctl_trans(struct file *file, + unsigned int cmd, struct sock_fprog32 __user *u_fprog32) { struct sock_fprog __user *u_fprog64 = compat_alloc_user_space(sizeof(struct sock_fprog)); void __user *fptr64; @@ -435,7 +456,7 @@ static int ppp_sock_fprog_ioctl_trans(unsigned int fd, unsigned int cmd, else cmd = PPPIOCSACTIVE; - return sys_ioctl(fd, cmd, (unsigned long) u_fprog64); + return do_ioctl(file, cmd, (unsigned long) u_fprog64); } struct ppp_option_data32 { @@ -451,7 +472,7 @@ struct ppp_idle32 { }; #define PPPIOCGIDLE32 _IOR('t', 63, struct ppp_idle32) -static int ppp_gidle(unsigned int fd, unsigned int cmd, +static int ppp_gidle(struct file *file, unsigned int cmd, struct ppp_idle32 __user *idle32) { struct ppp_idle __user *idle; @@ -460,7 +481,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd, idle = compat_alloc_user_space(sizeof(*idle)); - err = sys_ioctl(fd, PPPIOCGIDLE, (unsigned long) idle); + err = do_ioctl(file, PPPIOCGIDLE, (unsigned long) idle); if (!err) { if (get_user(xmit, &idle->xmit_idle) || @@ -472,7 +493,7 @@ static int ppp_gidle(unsigned int fd, unsigned int cmd, return err; } -static int ppp_scompress(unsigned int fd, unsigned int cmd, +static int ppp_scompress(struct file *file, unsigned int cmd, struct ppp_option_data32 __user *odata32) { struct ppp_option_data __user *odata; @@ -492,7 +513,7 @@ static int ppp_scompress(unsigned int fd, unsigned int cmd, sizeof(__u32) + sizeof(int))) return -EFAULT; - return sys_ioctl(fd, PPPIOCSCOMPRESS, (unsigned long) odata); + return do_ioctl(file, PPPIOCSCOMPRESS, (unsigned long) odata); } #ifdef CONFIG_BLOCK @@ -512,12 +533,13 @@ struct mtpos32 { }; #define MTIOCPOS32 _IOR('m', 3, struct mtpos32) -static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) +static int mt_ioctl_trans(struct file *file, + unsigned int cmd, void __user *argp) { - mm_segment_t old_fs = get_fs(); - struct mtget get; + /* NULL initialization to make gcc shut up */ + struct mtget __user *get = NULL; struct mtget32 __user *umget32; - struct mtpos pos; + struct mtpos __user *pos = NULL; struct mtpos32 __user *upos32; unsigned long kcmd; void *karg; @@ -526,32 +548,34 @@ static int mt_ioctl_trans(unsigned int fd, unsigned int cmd, void __user *argp) switch(cmd) { case MTIOCPOS32: kcmd = MTIOCPOS; - karg = &pos; + pos = compat_alloc_user_space(sizeof(*pos)); + karg = pos; break; default: /* MTIOCGET32 */ kcmd = MTIOCGET; - karg = &get; + get = compat_alloc_user_space(sizeof(*get)); + karg = get; break; } - set_fs (KERNEL_DS); - err = sys_ioctl (fd, kcmd, (unsigned long)karg); - set_fs (old_fs); + if (karg == NULL) + return -EFAULT; + err = do_ioctl(file, kcmd, (unsigned long)karg); if (err) return err; switch (cmd) { case MTIOCPOS32: upos32 = argp; - err = __put_user(pos.mt_blkno, &upos32->mt_blkno); + err = convert_in_user(&pos->mt_blkno, &upos32->mt_blkno); break; case MTIOCGET32: umget32 = argp; - err = __put_user(get.mt_type, &umget32->mt_type); - err |= __put_user(get.mt_resid, &umget32->mt_resid); - err |= __put_user(get.mt_dsreg, &umget32->mt_dsreg); - err |= __put_user(get.mt_gstat, &umget32->mt_gstat); - err |= __put_user(get.mt_erreg, &umget32->mt_erreg); - err |= __put_user(get.mt_fileno, &umget32->mt_fileno); - err |= __put_user(get.mt_blkno, &umget32->mt_blkno); + err = convert_in_user(&get->mt_type, &umget32->mt_type); + err |= convert_in_user(&get->mt_resid, &umget32->mt_resid); + err |= convert_in_user(&get->mt_dsreg, &umget32->mt_dsreg); + err |= convert_in_user(&get->mt_gstat, &umget32->mt_gstat); + err |= convert_in_user(&get->mt_erreg, &umget32->mt_erreg); + err |= convert_in_user(&get->mt_fileno, &umget32->mt_fileno); + err |= convert_in_user(&get->mt_blkno, &umget32->mt_blkno); break; } return err ? -EFAULT: 0; @@ -605,42 +629,41 @@ struct serial_struct32 { compat_int_t reserved[1]; }; -static int serial_struct_ioctl(unsigned fd, unsigned cmd, - struct serial_struct32 __user *ss32) +static int serial_struct_ioctl(struct file *file, + unsigned cmd, struct serial_struct32 __user *ss32) { typedef struct serial_struct32 SS32; int err; - struct serial_struct ss; - mm_segment_t oldseg = get_fs(); + struct serial_struct __user *ss = compat_alloc_user_space(sizeof(*ss)); __u32 udata; unsigned int base; + unsigned char *iomem_base; + if (ss == NULL) + return -EFAULT; if (cmd == TIOCSSERIAL) { - if (!access_ok(VERIFY_READ, ss32, sizeof(SS32))) - return -EFAULT; - if (__copy_from_user(&ss, ss32, offsetof(SS32, iomem_base))) + if (copy_in_user(ss, ss32, offsetof(SS32, iomem_base)) || + get_user(udata, &ss32->iomem_base)) return -EFAULT; - if (__get_user(udata, &ss32->iomem_base)) + iomem_base = compat_ptr(udata); + if (put_user(iomem_base, &ss->iomem_base) || + convert_in_user(&ss32->iomem_reg_shift, + &ss->iomem_reg_shift) || + convert_in_user(&ss32->port_high, &ss->port_high) || + put_user(0UL, &ss->iomap_base)) return -EFAULT; - ss.iomem_base = compat_ptr(udata); - if (__get_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) || - __get_user(ss.port_high, &ss32->port_high)) - return -EFAULT; - ss.iomap_base = 0UL; } - set_fs(KERNEL_DS); - err = sys_ioctl(fd,cmd,(unsigned long)(&ss)); - set_fs(oldseg); + err = do_ioctl(file, cmd, (unsigned long)ss); if (cmd == TIOCGSERIAL && err >= 0) { - if (!access_ok(VERIFY_WRITE, ss32, sizeof(SS32))) - return -EFAULT; - if (__copy_to_user(ss32,&ss,offsetof(SS32,iomem_base))) + if (copy_in_user(ss32, ss, offsetof(SS32, iomem_base)) || + get_user(iomem_base, &ss->iomem_base)) return -EFAULT; - base = (unsigned long)ss.iomem_base >> 32 ? - 0xffffffff : (unsigned)(unsigned long)ss.iomem_base; - if (__put_user(base, &ss32->iomem_base) || - __put_user(ss.iomem_reg_shift, &ss32->iomem_reg_shift) || - __put_user(ss.port_high, &ss32->port_high)) + base = (unsigned long)iomem_base >> 32 ? + 0xffffffff : (unsigned)(unsigned long)iomem_base; + if (put_user(base, &ss32->iomem_base) || + convert_in_user(&ss->iomem_reg_shift, + &ss32->iomem_reg_shift) || + convert_in_user(&ss->port_high, &ss32->port_high)) return -EFAULT; } return err; @@ -674,8 +697,8 @@ struct i2c_rdwr_aligned { struct i2c_msg msgs[0]; }; -static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, - struct i2c_rdwr_ioctl_data32 __user *udata) +static int do_i2c_rdwr_ioctl(struct file *file, + unsigned int cmd, struct i2c_rdwr_ioctl_data32 __user *udata) { struct i2c_rdwr_aligned __user *tdata; struct i2c_msg __user *tmsgs; @@ -708,11 +731,11 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, put_user(compat_ptr(datap), &tmsgs[i].buf)) return -EFAULT; } - return sys_ioctl(fd, cmd, (unsigned long)tdata); + return do_ioctl(file, cmd, (unsigned long)tdata); } -static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, - struct i2c_smbus_ioctl_data32 __user *udata) +static int do_i2c_smbus_ioctl(struct file *file, + unsigned int cmd, struct i2c_smbus_ioctl_data32 __user *udata) { struct i2c_smbus_ioctl_data __user *tdata; compat_caddr_t datap; @@ -734,7 +757,7 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, __put_user(compat_ptr(datap), &tdata->data)) return -EFAULT; - return sys_ioctl(fd, cmd, (unsigned long)tdata); + return do_ioctl(file, cmd, (unsigned long)tdata); } #define RTC_IRQP_READ32 _IOR('p', 0x0b, compat_ulong_t) @@ -742,29 +765,27 @@ static int do_i2c_smbus_ioctl(unsigned int fd, unsigned int cmd, #define RTC_EPOCH_READ32 _IOR('p', 0x0d, compat_ulong_t) #define RTC_EPOCH_SET32 _IOW('p', 0x0e, compat_ulong_t) -static int rtc_ioctl(unsigned fd, unsigned cmd, void __user *argp) +static int rtc_ioctl(struct file *file, + unsigned cmd, void __user *argp) { - mm_segment_t oldfs = get_fs(); - compat_ulong_t val32; - unsigned long kval; + unsigned long __user *valp = compat_alloc_user_space(sizeof(*valp)); int ret; + if (valp == NULL) + return -EFAULT; switch (cmd) { case RTC_IRQP_READ32: case RTC_EPOCH_READ32: - set_fs(KERNEL_DS); - ret = sys_ioctl(fd, (cmd == RTC_IRQP_READ32) ? + ret = do_ioctl(file, (cmd == RTC_IRQP_READ32) ? RTC_IRQP_READ : RTC_EPOCH_READ, - (unsigned long)&kval); - set_fs(oldfs); + (unsigned long)valp); if (ret) return ret; - val32 = kval; - return put_user(val32, (unsigned int __user *)argp); + return convert_in_user(valp, (unsigned int __user *)argp); case RTC_IRQP_SET32: - return sys_ioctl(fd, RTC_IRQP_SET, (unsigned long)argp); + return do_ioctl(file, RTC_IRQP_SET, (unsigned long)argp); case RTC_EPOCH_SET32: - return sys_ioctl(fd, RTC_EPOCH_SET, (unsigned long)argp); + return do_ioctl(file, RTC_EPOCH_SET, (unsigned long)argp); } return -ENOIOCTLCMD; @@ -1436,53 +1457,53 @@ IGNORE_IOCTL(FBIOGCURSOR32) * a compat_ioctl operation in the place that handleÑ• the * ioctl for the native case. */ -static long do_ioctl_trans(int fd, unsigned int cmd, +static long do_ioctl_trans(unsigned int cmd, unsigned long arg, struct file *file) { void __user *argp = compat_ptr(arg); switch (cmd) { case PPPIOCGIDLE32: - return ppp_gidle(fd, cmd, argp); + return ppp_gidle(file, cmd, argp); case PPPIOCSCOMPRESS32: - return ppp_scompress(fd, cmd, argp); + return ppp_scompress(file, cmd, argp); case PPPIOCSPASS32: case PPPIOCSACTIVE32: - return ppp_sock_fprog_ioctl_trans(fd, cmd, argp); + return ppp_sock_fprog_ioctl_trans(file, cmd, argp); #ifdef CONFIG_BLOCK case SG_IO: - return sg_ioctl_trans(fd, cmd, argp); + return sg_ioctl_trans(file, cmd, argp); case SG_GET_REQUEST_TABLE: - return sg_grt_trans(fd, cmd, argp); + return sg_grt_trans(file, cmd, argp); case MTIOCGET32: case MTIOCPOS32: - return mt_ioctl_trans(fd, cmd, argp); + return mt_ioctl_trans(file, cmd, argp); #endif /* Serial */ case TIOCGSERIAL: case TIOCSSERIAL: - return serial_struct_ioctl(fd, cmd, argp); + return serial_struct_ioctl(file, cmd, argp); /* i2c */ case I2C_FUNCS: - return w_long(fd, cmd, argp); + return w_long(file, cmd, argp); case I2C_RDWR: - return do_i2c_rdwr_ioctl(fd, cmd, argp); + return do_i2c_rdwr_ioctl(file, cmd, argp); case I2C_SMBUS: - return do_i2c_smbus_ioctl(fd, cmd, argp); + return do_i2c_smbus_ioctl(file, cmd, argp); /* Not implemented in the native kernel */ case RTC_IRQP_READ32: case RTC_IRQP_SET32: case RTC_EPOCH_READ32: case RTC_EPOCH_SET32: - return rtc_ioctl(fd, cmd, argp); + return rtc_ioctl(file, cmd, argp); /* dvb */ case VIDEO_GET_EVENT: - return do_video_get_event(fd, cmd, argp); + return do_video_get_event(file, cmd, argp); case VIDEO_STILLPICTURE: - return do_video_stillpicture(fd, cmd, argp); + return do_video_stillpicture(file, cmd, argp); case VIDEO_SET_SPU_PALETTE: - return do_video_set_spu_palette(fd, cmd, argp); + return do_video_set_spu_palette(file, cmd, argp); } /* @@ -1513,7 +1534,7 @@ static long do_ioctl_trans(int fd, unsigned int cmd, case NBD_SET_BLKSIZE: case NBD_SET_SIZE: case NBD_SET_SIZE_BLOCKS: - return do_vfs_ioctl(file, fd, cmd, arg); + return vfs_ioctl(file, cmd, arg); } return -ENOIOCTLCMD; @@ -1602,7 +1623,7 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, if (compat_ioctl_check_table(XFORM(cmd))) goto found_handler; - error = do_ioctl_trans(fd, cmd, arg, f.file); + error = do_ioctl_trans(cmd, arg, f.file); if (error == -ENOIOCTLCMD) error = -ENOTTY; diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index ec5c8325b503..db6d69289608 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -279,27 +279,33 @@ static int configfs_getlink(struct dentry *dentry, char * path) } -static const char *configfs_follow_link(struct dentry *dentry, void **cookie) +static const char *configfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - unsigned long page = get_zeroed_page(GFP_KERNEL); + char *body; int error; - if (!page) + if (!dentry) + return ERR_PTR(-ECHILD); + + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) return ERR_PTR(-ENOMEM); - error = configfs_getlink(dentry, (char *)page); + error = configfs_getlink(dentry, body); if (!error) { - return *cookie = (void *)page; + set_delayed_call(done, kfree_link, body); + return body; } - free_page(page); + kfree(body); return ERR_PTR(error); } const struct inode_operations configfs_symlink_inode_operations = { - .follow_link = configfs_follow_link, + .get_link = configfs_get_link, .readlink = generic_readlink, - .put_link = free_page_put_link, .setattr = configfs_setattr, }; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 355c522f3585..b862bc219cd7 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -100,6 +100,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &cramfs_aops; break; default: diff --git a/fs/dcache.c b/fs/dcache.c index 5c33aeb0f68f..d27f0909d9f6 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1734,7 +1734,7 @@ static unsigned d_flags_for_inode(struct inode *inode) } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { - if (unlikely(inode->i_op->follow_link)) { + if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e2e47ba5d313..a4dddc61594c 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -674,16 +674,24 @@ out: return rc ? ERR_PTR(rc) : buf; } -static const char *ecryptfs_follow_link(struct dentry *dentry, void **cookie) +static const char *ecryptfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { size_t len; - char *buf = ecryptfs_readlink_lower(dentry, &len); + char *buf; + + if (!dentry) + return ERR_PTR(-ECHILD); + + buf = ecryptfs_readlink_lower(dentry, &len); if (IS_ERR(buf)) return buf; fsstack_copy_attr_atime(d_inode(dentry), d_inode(ecryptfs_dentry_to_lower(dentry))); buf[len] = '\0'; - return *cookie = buf; + set_delayed_call(done, kfree_link, buf); + return buf; } /** @@ -1095,8 +1103,7 @@ out: const struct inode_operations ecryptfs_symlink_iops = { .readlink = generic_readlink, - .follow_link = ecryptfs_follow_link, - .put_link = kfree_put_link, + .get_link = ecryptfs_get_link, .permission = ecryptfs_permission, .setattr = ecryptfs_setattr, .getattr = ecryptfs_getattr_link, diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 079d20306ee1..cdf0872382af 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -151,6 +151,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &efs_symlink_aops; break; case S_IFCHR: diff --git a/fs/efs/symlink.c b/fs/efs/symlink.c index 75117d0dac2b..4870cc82deb0 100644 --- a/fs/efs/symlink.c +++ b/fs/efs/symlink.c @@ -13,7 +13,7 @@ static int efs_symlink_readpage(struct file *file, struct page *page) { - char *link = kmap(page); + char *link = page_address(page); struct buffer_head * bh; struct inode * inode = page->mapping->host; efs_block_t size = inode->i_size; @@ -39,12 +39,10 @@ static int efs_symlink_readpage(struct file *file, struct page *page) } link[size] = '\0'; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: SetPageError(page); - kunmap(page); unlock_page(page); return err; } diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 60f03b78914e..9eaf595aeaf8 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1224,6 +1224,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) inode->i_link = (char *)oi->i_data; } else { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &exofs_aops; } } else { diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c index 994e078da4bb..c20d77df2679 100644 --- a/fs/exofs/namei.c +++ b/fs/exofs/namei.c @@ -111,6 +111,7 @@ static int exofs_symlink(struct inode *dir, struct dentry *dentry, if (l > sizeof(oi->i_data)) { /* slow symlink */ inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &exofs_aops; memset(oi->i_data, 0, sizeof(oi->i_data)); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 0aa9bf6e6e53..338eefda70c6 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1420,6 +1420,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) sizeof(ei->i_data) - 1); } else { inode->i_op = &ext2_symlink_inode_operations; + inode_nohighmem(inode); if (test_opt(inode->i_sb, NOBH)) inode->i_mapping->a_ops = &ext2_nobh_aops; else diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index 3267a80dbbe2..7a2be8f7f3c3 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -183,6 +183,7 @@ static int ext2_symlink (struct inode * dir, struct dentry * dentry, if (l > sizeof (EXT2_I(inode)->i_data)) { /* slow symlink */ inode->i_op = &ext2_symlink_inode_operations; + inode_nohighmem(inode); if (test_opt(inode->i_sb, NOBH)) inode->i_mapping->a_ops = &ext2_nobh_aops; else diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c index ae17179f3810..3495d8ae4b33 100644 --- a/fs/ext2/symlink.c +++ b/fs/ext2/symlink.c @@ -22,8 +22,7 @@ const struct inode_operations ext2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, @@ -35,7 +34,7 @@ const struct inode_operations ext2_symlink_inode_operations = { const struct inode_operations ext2_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ext2_setattr, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index fa70848afa8f..cd95d14f9cc2 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -292,16 +292,21 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", const struct xattr_handler *handler = ext2_xattr_handler(entry->e_name_index); - if (handler) { - size_t size = handler->list(handler, dentry, buffer, - rest, entry->e_name, - entry->e_name_len); + if (handler && (!handler->list || handler->list(dentry))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_len = strlen(prefix); + size_t size = prefix_len + entry->e_name_len + 1; + if (buffer) { if (size > rest) { error = -ERANGE; goto cleanup; } - buffer += size; + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } rest -= size; } diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c index dfb08750370d..ba97f243b050 100644 --- a/fs/ext2/xattr_security.c +++ b/fs/ext2/xattr_security.c @@ -7,29 +7,11 @@ #include <linux/security.h> #include "xattr.h" -static size_t -ext2_xattr_security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) -{ - const int prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ext2_xattr_security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -39,8 +21,6 @@ ext2_xattr_security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -71,7 +51,6 @@ ext2_init_security(struct inode *inode, struct inode *dir, const struct xattr_handler ext2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ext2_xattr_security_list, .get = ext2_xattr_security_get, .set = ext2_xattr_security_set, }; diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c index 3150dd3a7859..2c94d1930626 100644 --- a/fs/ext2/xattr_trusted.c +++ b/fs/ext2/xattr_trusted.c @@ -8,23 +8,10 @@ #include "ext2.h" #include "xattr.h" -static size_t -ext2_xattr_trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext2_xattr_trusted_list(struct dentry *dentry) { - const int prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return capable(CAP_SYS_ADMIN); } static int @@ -32,8 +19,6 @@ ext2_xattr_trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -43,8 +28,6 @@ ext2_xattr_trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext2_xattr_set(d_inode(dentry), EXT2_XATTR_INDEX_TRUSTED, name, value, size, flags); } diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c index 339a49bbb8ef..72a2a96d677f 100644 --- a/fs/ext2/xattr_user.c +++ b/fs/ext2/xattr_user.c @@ -10,23 +10,10 @@ #include "ext2.h" #include "xattr.h" -static size_t -ext2_xattr_user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext2_xattr_user_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!test_opt(dentry->d_sb, XATTR_USER)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return test_opt(dentry->d_sb, XATTR_USER); } static int @@ -34,8 +21,6 @@ ext2_xattr_user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext2_xattr_get(d_inode(dentry), EXT2_XATTR_INDEX_USER, @@ -47,8 +32,6 @@ ext2_xattr_user_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ea433a7f4bca..b3bd912df6bf 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4283,6 +4283,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_symlink_inode_operations; ext4_set_aops(inode); } + inode_nohighmem(inode); } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a969ab39f302..f27e0c2598c5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3132,6 +3132,7 @@ static int ext4_symlink(struct inode *dir, if ((disk_link.len > EXT4_N_BLOCKS * 4)) { if (!encryption_required) inode->i_op = &ext4_symlink_inode_operations; + inode_nohighmem(inode); ext4_set_aops(inode); /* * We cannot call page_symlink() with transaction started diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index e8e7af62ac95..6f7ee30a89ce 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -23,17 +23,21 @@ #include "xattr.h" #ifdef CONFIG_EXT4_FS_ENCRYPTION -static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cookie) +static const char *ext4_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct page *cpage = NULL; char *caddr, *paddr = NULL; struct ext4_str cstr, pstr; - struct inode *inode = d_inode(dentry); struct ext4_encrypted_symlink_data *sd; loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); int res; u32 plen, max_size = inode->i_sb->s_blocksize; + if (!dentry) + return ERR_PTR(-ECHILD); + res = ext4_get_encryption_info(inode); if (res) return ERR_PTR(res); @@ -45,7 +49,7 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; } @@ -75,24 +79,20 @@ static const char *ext4_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ if (res <= plen) paddr[res] = '\0'; - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } - return *cookie = paddr; + set_delayed_call(done, kfree_link, paddr); + return paddr; errout: - if (cpage) { - kunmap(cpage); + if (cpage) page_cache_release(cpage); - } kfree(paddr); return ERR_PTR(res); } const struct inode_operations ext4_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = ext4_encrypted_follow_link, - .put_link = kfree_put_link, + .get_link = ext4_encrypted_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -103,8 +103,7 @@ const struct inode_operations ext4_encrypted_symlink_inode_operations = { const struct inode_operations ext4_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, @@ -114,7 +113,7 @@ const struct inode_operations ext4_symlink_inode_operations = { const struct inode_operations ext4_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ext4_setattr, .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 6b6b3e751f8c..e9b9afdd1d96 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -404,19 +404,24 @@ ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, const struct xattr_handler *handler = ext4_xattr_handler(entry->e_name_index); - if (handler) { - size_t size = handler->list(handler, dentry, buffer, - rest, entry->e_name, - entry->e_name_len); + if (handler && (!handler->list || handler->list(dentry))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_len = strlen(prefix); + size_t size = prefix_len + entry->e_name_len + 1; + if (buffer) { if (size > rest) return -ERANGE; - buffer += size; + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } rest -= size; } } - return buffer_size - rest; + return buffer_size - rest; /* total size */ } static int diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c index 36f4c1a84c21..3e81bdca071a 100644 --- a/fs/ext4/xattr_security.c +++ b/fs/ext4/xattr_security.c @@ -11,30 +11,11 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) -{ - const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1; - const size_t total_len = prefix_len + name_len + 1; - - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ext4_xattr_security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -44,8 +25,6 @@ ext4_xattr_security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -79,7 +58,6 @@ ext4_init_security(handle_t *handle, struct inode *inode, struct inode *dir, const struct xattr_handler ext4_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ext4_xattr_security_list, .get = ext4_xattr_security_get, .set = ext4_xattr_security_set, }; diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c index 488089053342..2a3c6f9b8cb8 100644 --- a/fs/ext4/xattr_trusted.c +++ b/fs/ext4/xattr_trusted.c @@ -12,23 +12,10 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext4_xattr_trusted_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return capable(CAP_SYS_ADMIN); } static int @@ -36,8 +23,6 @@ ext4_xattr_trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -47,8 +32,6 @@ ext4_xattr_trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_TRUSTED, name, value, size, flags); } diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c index d2dec3364062..d152f431e432 100644 --- a/fs/ext4/xattr_user.c +++ b/fs/ext4/xattr_user.c @@ -11,23 +11,10 @@ #include "ext4.h" #include "xattr.h" -static size_t -ext4_xattr_user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +ext4_xattr_user_list(struct dentry *dentry) { - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!test_opt(dentry->d_sb, XATTR_USER)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list+prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; + return test_opt(dentry->d_sb, XATTR_USER); } static int @@ -35,8 +22,6 @@ ext4_xattr_user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext4_xattr_get(d_inode(dentry), EXT4_XATTR_INDEX_USER, @@ -48,8 +33,6 @@ ext4_xattr_user_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; if (!test_opt(dentry->d_sb, XATTR_USER)) return -EOPNOTSUPP; return ext4_xattr_set(d_inode(dentry), EXT4_XATTR_INDEX_USER, diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 97e20decacb4..5528801a5baf 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -202,6 +202,7 @@ make_now: inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 2c32110f9fc0..e7587fce1b80 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -315,12 +315,15 @@ fail: return err; } -static const char *f2fs_follow_link(struct dentry *dentry, void **cookie) +static const char *f2fs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - const char *link = page_follow_link_light(dentry, cookie); + const char *link = page_get_link(dentry, inode, done); if (!IS_ERR(link) && !*link) { /* this is broken symlink case */ - page_put_link(NULL, *cookie); + do_delayed_call(done); + clear_delayed_call(done); link = ERR_PTR(-ENOENT); } return link; @@ -351,6 +354,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &f2fs_dblock_aops; f2fs_lock_op(sbi); @@ -923,18 +927,22 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, } #ifdef CONFIG_F2FS_FS_ENCRYPTION -static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cookie) +static const char *f2fs_encrypted_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct page *cpage = NULL; char *caddr, *paddr = NULL; struct f2fs_str cstr; struct f2fs_str pstr = FSTR_INIT(NULL, 0); - struct inode *inode = d_inode(dentry); struct f2fs_encrypted_symlink_data *sd; loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1); u32 max_size = inode->i_sb->s_blocksize; int res; + if (!dentry) + return ERR_PTR(-ECHILD); + res = f2fs_get_encryption_info(inode); if (res) return ERR_PTR(res); @@ -942,7 +950,7 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); - caddr = kmap(cpage); + caddr = page_address(cpage); caddr[size] = 0; /* Symlink is encrypted */ @@ -982,21 +990,19 @@ static const char *f2fs_encrypted_follow_link(struct dentry *dentry, void **cook /* Null-terminate the name */ paddr[res] = '\0'; - kunmap(cpage); page_cache_release(cpage); - return *cookie = paddr; + set_delayed_call(done, kfree_link, paddr); + return paddr; errout: kfree(cstr.name); f2fs_fname_crypto_free_buffer(&pstr); - kunmap(cpage); page_cache_release(cpage); return ERR_PTR(res); } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_encrypted_follow_link, - .put_link = kfree_put_link, + .get_link = f2fs_encrypted_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, .setxattr = generic_setxattr, @@ -1031,8 +1037,7 @@ const struct inode_operations f2fs_dir_inode_operations = { const struct inode_operations f2fs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = f2fs_follow_link, - .put_link = page_put_link, + .get_link = f2fs_get_link, .getattr = f2fs_getattr, .setattr = f2fs_setattr, #ifdef CONFIG_F2FS_FS_XATTR diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 862368a32e53..036952a945fa 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -25,38 +25,6 @@ #include "f2fs.h" #include "xattr.h" -static size_t f2fs_xattr_generic_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t len) -{ - struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - int total_len, prefix_len; - - switch (handler->flags) { - case F2FS_XATTR_INDEX_USER: - if (!test_opt(sbi, XATTR_USER)) - return -EOPNOTSUPP; - break; - case F2FS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - break; - case F2FS_XATTR_INDEX_SECURITY: - break; - default: - return -EINVAL; - } - - prefix_len = strlen(handler->prefix); - total_len = prefix_len + len + 1; - if (list && total_len <= list_size) { - memcpy(list, handler->prefix, prefix_len); - memcpy(list + prefix_len, name, len); - list[prefix_len + len] = '\0'; - } - return total_len; -} - static int f2fs_xattr_generic_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) @@ -77,8 +45,6 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler, default: return -EINVAL; } - if (strcmp(name, "") == 0) - return -EINVAL; return f2fs_getxattr(d_inode(dentry), handler->flags, name, buffer, size, NULL); } @@ -103,24 +69,20 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler, default: return -EINVAL; } - if (strcmp(name, "") == 0) - return -EINVAL; - return f2fs_setxattr(d_inode(dentry), handler->flags, name, value, size, NULL, flags); } -static size_t f2fs_xattr_advise_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t len) +static bool f2fs_xattr_user_list(struct dentry *dentry) { - const char *xname = F2FS_SYSTEM_ADVISE_PREFIX; - size_t size; + struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb); - size = strlen(xname) + 1; - if (list && size <= list_size) - memcpy(list, xname, size); - return size; + return test_opt(sbi, XATTR_USER); +} + +static bool f2fs_xattr_trusted_list(struct dentry *dentry) +{ + return capable(CAP_SYS_ADMIN); } static int f2fs_xattr_advise_get(const struct xattr_handler *handler, @@ -129,9 +91,6 @@ static int f2fs_xattr_advise_get(const struct xattr_handler *handler, { struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; - if (buffer) *((char *)buffer) = F2FS_I(inode)->i_advise; return sizeof(char); @@ -143,8 +102,6 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, { struct inode *inode = d_inode(dentry); - if (strcmp(name, "") != 0) - return -EINVAL; if (!inode_owner_or_capable(inode)) return -EPERM; if (value == NULL) @@ -183,7 +140,7 @@ int f2fs_init_security(struct inode *inode, struct inode *dir, const struct xattr_handler f2fs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .flags = F2FS_XATTR_INDEX_USER, - .list = f2fs_xattr_generic_list, + .list = f2fs_xattr_user_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; @@ -191,15 +148,14 @@ const struct xattr_handler f2fs_xattr_user_handler = { const struct xattr_handler f2fs_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, .flags = F2FS_XATTR_INDEX_TRUSTED, - .list = f2fs_xattr_generic_list, + .list = f2fs_xattr_trusted_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; const struct xattr_handler f2fs_xattr_advise_handler = { - .prefix = F2FS_SYSTEM_ADVISE_PREFIX, + .name = F2FS_SYSTEM_ADVISE_NAME, .flags = F2FS_XATTR_INDEX_ADVISE, - .list = f2fs_xattr_advise_list, .get = f2fs_xattr_advise_get, .set = f2fs_xattr_advise_set, }; @@ -207,7 +163,6 @@ const struct xattr_handler f2fs_xattr_advise_handler = { const struct xattr_handler f2fs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .flags = F2FS_XATTR_INDEX_SECURITY, - .list = f2fs_xattr_generic_list, .get = f2fs_xattr_generic_get, .set = f2fs_xattr_generic_set, }; @@ -455,20 +410,27 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) list_for_each_xattr(entry, base_addr) { const struct xattr_handler *handler = f2fs_xattr_handler(entry->e_name_index); + const char *prefix; + size_t prefix_len; size_t size; - if (!handler) + if (!handler || (handler->list && !handler->list(dentry))) continue; - size = handler->list(handler, dentry, buffer, rest, - entry->e_name, entry->e_name_len); - if (buffer && size > rest) { - error = -ERANGE; - goto cleanup; + prefix = handler->prefix ?: handler->name; + prefix_len = strlen(prefix); + size = prefix_len + entry->e_name_len + 1; + if (buffer) { + if (size > rest) { + error = -ERANGE; + goto cleanup; + } + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, entry->e_name, entry->e_name_len); + buffer += entry->e_name_len; + *buffer++ = 0; } - - if (buffer) - buffer += size; rest -= size; } error = buffer_size - rest; diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 71a7100d5492..79dccc8252dd 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -27,7 +27,7 @@ #define F2FS_XATTR_REFCOUNT_MAX 1024 /* Name indexes */ -#define F2FS_SYSTEM_ADVISE_PREFIX "system.advise" +#define F2FS_SYSTEM_ADVISE_NAME "system.advise" #define F2FS_XATTR_INDEX_USER 1 #define F2FS_XATTR_INDEX_POSIX_ACL_ACCESS 2 #define F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT 3 diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index ef73ed674a27..3e2ccade61ed 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -326,6 +326,7 @@ vxfs_iget(struct super_block *sbp, ino_t ino) } else if (S_ISLNK(ip->i_mode)) { if (!VXFS_ISIMMED(vip)) { ip->i_op = &page_symlink_inode_operations; + inode_nohighmem(ip); ip->i_mapping->a_ops = &vxfs_aops; } else { ip->i_op = &simple_symlink_inode_operations; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 5e2e08712d3b..712601f299b8 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1365,15 +1365,19 @@ static int fuse_readdir(struct file *file, struct dir_context *ctx) return err; } -static const char *fuse_follow_link(struct dentry *dentry, void **cookie) +static const char *fuse_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct fuse_conn *fc = get_fuse_conn(inode); FUSE_ARGS(args); char *link; ssize_t ret; - link = (char *) __get_free_page(GFP_KERNEL); + if (!dentry) + return ERR_PTR(-ECHILD); + + link = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); @@ -1385,11 +1389,11 @@ static const char *fuse_follow_link(struct dentry *dentry, void **cookie) args.out.args[0].value = link; ret = fuse_simple_request(fc, &args); if (ret < 0) { - free_page((unsigned long) link); + kfree(link); link = ERR_PTR(ret); } else { link[ret] = '\0'; - *cookie = link; + set_delayed_call(done, kfree_link, link); } fuse_invalidate_atime(inode); return link; @@ -1909,8 +1913,7 @@ static const struct inode_operations fuse_common_inode_operations = { static const struct inode_operations fuse_symlink_inode_operations = { .setattr = fuse_setattr, - .follow_link = fuse_follow_link, - .put_link = free_page_put_link, + .get_link = fuse_get_link, .readlink = generic_readlink, .getattr = fuse_getattr, .setxattr = fuse_setxattr, diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 1be3b061c05c..791932617d1a 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -31,9 +31,9 @@ static const char *gfs2_acl_name(int type) { switch (type) { case ACL_TYPE_ACCESS: - return GFS2_POSIX_ACL_ACCESS; + return XATTR_POSIX_ACL_ACCESS; case ACL_TYPE_DEFAULT: - return GFS2_POSIX_ACL_DEFAULT; + return XATTR_POSIX_ACL_DEFAULT; } return NULL; } diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index 2d65ec4cd4be..3af4f407a483 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -12,8 +12,6 @@ #include "incore.h" -#define GFS2_POSIX_ACL_ACCESS "posix_acl_access" -#define GFS2_POSIX_ACL_DEFAULT "posix_acl_default" #define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12) extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 063fdfcf8275..1bae189f3245 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1712,24 +1712,30 @@ static int gfs2_rename2(struct inode *odir, struct dentry *odentry, } /** - * gfs2_follow_link - Follow a symbolic link + * gfs2_get_link - Follow a symbolic link * @dentry: The dentry of the link - * @nd: Data that we pass to vfs_follow_link() + * @inode: The inode of the link + * @done: destructor for return value * * This can handle symlinks of any size. * * Returns: 0 on success or error code */ -static const char *gfs2_follow_link(struct dentry *dentry, void **cookie) +static const char *gfs2_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct gfs2_inode *ip = GFS2_I(d_inode(dentry)); + struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder i_gh; struct buffer_head *dibh; unsigned int size; char *buf; int error; + if (!dentry) + return ERR_PTR(-ECHILD); + gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh); error = gfs2_glock_nq(&i_gh); if (error) { @@ -1759,7 +1765,7 @@ static const char *gfs2_follow_link(struct dentry *dentry, void **cookie) out: gfs2_glock_dq_uninit(&i_gh); if (!IS_ERR(buf)) - *cookie = buf; + set_delayed_call(done, kfree_link, buf); return buf; } @@ -2132,8 +2138,7 @@ const struct inode_operations gfs2_dir_iops = { const struct inode_operations gfs2_symlink_iops = { .readlink = generic_readlink, - .follow_link = gfs2_follow_link, - .put_link = kfree_put_link, + .get_link = gfs2_get_link, .permission = gfs2_permission, .setattr = gfs2_setattr, .getattr = gfs2_getattr, diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 53ce76a374fe..84f2d81fe451 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1237,56 +1237,6 @@ static int gfs2_xattr_set(const struct xattr_handler *handler, size, flags, handler->flags); } - -static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip, - struct gfs2_ea_header *ea, char *data) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - unsigned int amount = GFS2_EA_DATA_LEN(ea); - unsigned int nptrs = DIV_ROUND_UP(amount, sdp->sd_jbsize); - int ret; - - ret = gfs2_trans_begin(sdp, nptrs + RES_DINODE, 0); - if (ret) - return ret; - - ret = gfs2_iter_unstuffed(ip, ea, data, NULL); - gfs2_trans_end(sdp); - - return ret; -} - -int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data) -{ - struct inode *inode = &ip->i_inode; - struct gfs2_sbd *sdp = GFS2_SB(inode); - struct gfs2_ea_location el; - int error; - - error = gfs2_ea_find(ip, GFS2_EATYPE_SYS, GFS2_POSIX_ACL_ACCESS, &el); - if (error) - return error; - - if (GFS2_EA_IS_STUFFED(el.el_ea)) { - error = gfs2_trans_begin(sdp, RES_DINODE + RES_EATTR, 0); - if (error == 0) { - gfs2_trans_add_meta(ip->i_gl, el.el_bh); - memcpy(GFS2_EA2DATA(el.el_ea), data, - GFS2_EA_DATA_LEN(el.el_ea)); - } - } else { - error = ea_acl_chmod_unstuffed(ip, el.el_ea, data); - } - - brelse(el.el_bh); - if (error) - return error; - - error = gfs2_setattr_simple(inode, attr); - gfs2_trans_end(sdp); - return error; -} - static int ea_dealloc_indirect(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h index d392f8358f2f..2d887c88eb49 100644 --- a/fs/gfs2/xattr.h +++ b/fs/gfs2/xattr.h @@ -62,6 +62,5 @@ extern int gfs2_ea_dealloc(struct gfs2_inode *ip); /* Exported to acl.c */ extern int gfs2_xattr_acl_get(struct gfs2_inode *ip, const char *name, char **data); -extern int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data); #endif /* __EATTR_DOT_H__ */ diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 6dd107d7421e..19b33f8151f1 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -403,6 +403,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode) } else if (S_ISLNK(inode->i_mode)) { sbi->file_count++; inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &hfsplus_aops; hip->clump_blocks = 1; } else @@ -526,6 +527,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) inode->i_mapping->a_ops = &hfsplus_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &hfsplus_aops; } else { init_special_inode(inode, inode->i_mode, diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index df0c9af68d05..afb33eda6d7d 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -21,10 +21,10 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - xattr_name = POSIX_ACL_XATTR_ACCESS; + xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - xattr_name = POSIX_ACL_XATTR_DEFAULT; + xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return ERR_PTR(-EINVAL); @@ -66,7 +66,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, switch (type) { case ACL_TYPE_ACCESS: - xattr_name = POSIX_ACL_XATTR_ACCESS; + xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { err = posix_acl_equiv_mode(acl, &inode->i_mode); if (err < 0) @@ -76,7 +76,7 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, break; case ACL_TYPE_DEFAULT: - xattr_name = POSIX_ACL_XATTR_DEFAULT; + xattr_name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index e41a010cd89c..ab01530b4930 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -431,9 +431,6 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name, char *xattr_name; int res; - if (!strcmp(name, "")) - return -EINVAL; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) @@ -589,9 +586,6 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name, int res; char *xattr_name; - if (!strcmp(name, "")) - return -EINVAL; - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1, GFP_KERNEL); if (!xattr_name) @@ -853,9 +847,6 @@ static int hfsplus_osx_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; - /* * Don't allow retrieving properly prefixed attributes * by prepending them with "osx." @@ -876,9 +867,6 @@ static int hfsplus_osx_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; - /* * Don't allow setting properly prefixed attributes * by prepending them with "osx." diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 2ac99db3750e..7db524cc85b6 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -892,9 +892,14 @@ static const struct inode_operations hostfs_dir_iops = { .setattr = hostfs_setattr, }; -static const char *hostfs_follow_link(struct dentry *dentry, void **cookie) +static const char *hostfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - char *link = __getname(); + char *link; + if (!dentry) + return ERR_PTR(-ECHILD); + link = kmalloc(PATH_MAX, GFP_KERNEL); if (link) { char *path = dentry_name(dentry); int err = -ENOMEM; @@ -905,25 +910,20 @@ static const char *hostfs_follow_link(struct dentry *dentry, void **cookie) __putname(path); } if (err < 0) { - __putname(link); + kfree(link); return ERR_PTR(err); } } else { return ERR_PTR(-ENOMEM); } - return *cookie = link; -} - -static void hostfs_put_link(struct inode *unused, void *cookie) -{ - __putname(cookie); + set_delayed_call(done, kfree_link, link); + return link; } static const struct inode_operations hostfs_link_iops = { .readlink = generic_readlink, - .follow_link = hostfs_follow_link, - .put_link = hostfs_put_link, + .get_link = hostfs_get_link, }; static int hostfs_fill_sb_common(struct super_block *sb, void *d, int silent) diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 933c73780813..1f3c6d76200b 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -77,6 +77,7 @@ void hpfs_read_inode(struct inode *i) kfree(ea); i->i_mode = S_IFLNK | 0777; i->i_op = &page_symlink_inode_operations; + inode_nohighmem(i); i->i_data.a_ops = &hpfs_symlink_aops; set_nlink(i, 1); i->i_size = ea_size; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index ae4d5a1fa4c9..506765afa1a3 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -332,6 +332,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy result->i_blocks = 1; set_nlink(result, 1); result->i_size = strlen(symlink); + inode_nohighmem(result); result->i_op = &page_symlink_inode_operations; result->i_data.a_ops = &hpfs_symlink_aops; @@ -500,7 +501,7 @@ out: static int hpfs_symlink_readpage(struct file *file, struct page *page) { - char *link = kmap(page); + char *link = page_address(page); struct inode *i = page->mapping->host; struct fnode *fnode; struct buffer_head *bh; @@ -516,14 +517,12 @@ static int hpfs_symlink_readpage(struct file *file, struct page *page) goto fail; hpfs_unlock(i->i_sb); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; fail: hpfs_unlock(i->i_sb); SetPageError(page); - kunmap(page); unlock_page(page); return err; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index de4bdfac0cec..d8f51ee8126b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -760,6 +760,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; } lockdep_annotate_inode_mutex_key(inode); diff --git a/fs/inode.c b/fs/inode.c index 1be5f9003eb3..5bb85a064ce7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2028,3 +2028,9 @@ void inode_set_flags(struct inode *inode, unsigned int flags, new_flags) != old_flags)); } EXPORT_SYMBOL(inode_set_flags); + +void inode_nohighmem(struct inode *inode) +{ + mapping_set_gfp_mask(inode->i_mapping, GFP_USER); +} +EXPORT_SYMBOL(inode_nohighmem); diff --git a/fs/internal.h b/fs/internal.h index 71859c4d0b41..e38c08ca437d 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -151,3 +151,10 @@ extern void mnt_pin_kill(struct mount *m); * fs/nsfs.c */ extern struct dentry_operations ns_dentry_operations; + +/* + * fs/ioctl.c + */ +extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd, + unsigned long arg); +extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); diff --git a/fs/ioctl.c b/fs/ioctl.c index 5d01d2638ca5..41c352e81193 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -15,6 +15,7 @@ #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> +#include "internal.h" #include <asm/ioctls.h> @@ -32,8 +33,7 @@ * * Returns 0 on success, -errno on error. */ -static long vfs_ioctl(struct file *filp, unsigned int cmd, - unsigned long arg) +long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d67a16f2a45d..61abdc4920da 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1417,6 +1417,7 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_fop = &isofs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; } else /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 735d7522a3a9..5384ceb35b1c 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -687,7 +687,7 @@ static int rock_ridge_symlink_readpage(struct file *file, struct page *page) struct inode *inode = page->mapping->host; struct iso_inode_info *ei = ISOFS_I(inode); struct isofs_sb_info *sbi = ISOFS_SB(inode->i_sb); - char *link = kmap(page); + char *link = page_address(page); unsigned long bufsize = ISOFS_BUFFER_SIZE(inode); struct buffer_head *bh; char *rpnt = link; @@ -774,7 +774,6 @@ repeat: brelse(bh); *rpnt = '\0'; SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; @@ -791,7 +790,6 @@ fail: brelse(bh); error: SetPageError(page); - kunmap(page); unlock_page(page); return -EIO; } diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c index bf12fe5f83d7..7a28facd7175 100644 --- a/fs/jffs2/security.c +++ b/fs/jffs2/security.c @@ -52,9 +52,6 @@ static int jffs2_security_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; - return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, name, buffer, size); } @@ -63,31 +60,12 @@ static int jffs2_security_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; - return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_SECURITY, name, buffer, size, flags); } -static size_t jffs2_security_listxattr(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - size_t retlen = XATTR_SECURITY_PREFIX_LEN + name_len + 1; - - if (list && retlen <= list_size) { - strcpy(list, XATTR_SECURITY_PREFIX); - strcpy(list + XATTR_SECURITY_PREFIX_LEN, name); - } - - return retlen; -} - const struct xattr_handler jffs2_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = jffs2_security_listxattr, .set = jffs2_security_setxattr, .get = jffs2_security_getxattr }; diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c index 8ce2f240125b..2cabd649d4fb 100644 --- a/fs/jffs2/symlink.c +++ b/fs/jffs2/symlink.c @@ -14,7 +14,7 @@ const struct inode_operations jffs2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = jffs2_setattr, .setxattr = jffs2_setxattr, .getxattr = jffs2_getxattr, diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 4c2c03663533..da3e18503c65 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -967,7 +967,8 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) struct jffs2_xattr_ref *ref, **pref; struct jffs2_xattr_datum *xd; const struct xattr_handler *xhandle; - ssize_t len, rc; + const char *prefix; + ssize_t prefix_len, len, rc; int retry = 0; rc = check_xattr_ref_inode(c, ic); @@ -998,18 +999,23 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) } } xhandle = xprefix_to_handler(xd->xprefix); - if (!xhandle) + if (!xhandle || (xhandle->list && !xhandle->list(dentry))) continue; + prefix = xhandle->prefix ?: xhandle->name; + prefix_len = strlen(prefix); + rc = prefix_len + xd->name_len + 1; + if (buffer) { - rc = xhandle->list(xhandle, dentry, buffer + len, - size - len, xd->xname, - xd->name_len); - } else { - rc = xhandle->list(xhandle, dentry, NULL, 0, - xd->xname, xd->name_len); + if (rc > size - len) { + rc = -ERANGE; + goto out; + } + memcpy(buffer, prefix, prefix_len); + buffer += prefix_len; + memcpy(buffer, xd->xname, xd->name_len); + buffer += xd->name_len; + *buffer++ = 0; } - if (rc < 0) - goto out; len += rc; } rc = len; diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c index a562da0d6a26..b2555ef07a12 100644 --- a/fs/jffs2/xattr_trusted.c +++ b/fs/jffs2/xattr_trusted.c @@ -20,8 +20,6 @@ static int jffs2_trusted_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, name, buffer, size); } @@ -30,28 +28,13 @@ static int jffs2_trusted_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_TRUSTED, name, buffer, size, flags); } -static size_t jffs2_trusted_listxattr(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) +static bool jffs2_trusted_listxattr(struct dentry *dentry) { - size_t retlen = XATTR_TRUSTED_PREFIX_LEN + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && retlen<=list_size) { - strcpy(list, XATTR_TRUSTED_PREFIX); - strcpy(list + XATTR_TRUSTED_PREFIX_LEN, name); - } - - return retlen; + return capable(CAP_SYS_ADMIN); } const struct xattr_handler jffs2_trusted_xattr_handler = { diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c index cbc0472e59a8..539bd630b5e4 100644 --- a/fs/jffs2/xattr_user.c +++ b/fs/jffs2/xattr_user.c @@ -20,8 +20,6 @@ static int jffs2_user_getxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_getxattr(d_inode(dentry), JFFS2_XPREFIX_USER, name, buffer, size); } @@ -30,30 +28,12 @@ static int jffs2_user_setxattr(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *buffer, size_t size, int flags) { - if (!strcmp(name, "")) - return -EINVAL; return do_jffs2_setxattr(d_inode(dentry), JFFS2_XPREFIX_USER, name, buffer, size, flags); } -static size_t jffs2_user_listxattr(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - size_t retlen = XATTR_USER_PREFIX_LEN + name_len + 1; - - if (list && retlen <= list_size) { - strcpy(list, XATTR_USER_PREFIX); - strcpy(list + XATTR_USER_PREFIX_LEN, name); - } - - return retlen; -} - const struct xattr_handler jffs2_user_xattr_handler = { .prefix = XATTR_USER_PREFIX, - .list = jffs2_user_listxattr, .set = jffs2_user_setxattr, .get = jffs2_user_getxattr }; diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 0c8ca830b113..49456853e9de 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -40,10 +40,10 @@ struct posix_acl *jfs_get_acl(struct inode *inode, int type) switch(type) { case ACL_TYPE_ACCESS: - ea_name = POSIX_ACL_XATTR_ACCESS; + ea_name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - ea_name = POSIX_ACL_XATTR_DEFAULT; + ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return ERR_PTR(-EINVAL); @@ -82,7 +82,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: - ea_name = POSIX_ACL_XATTR_ACCESS; + ea_name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { rc = posix_acl_equiv_mode(acl, &inode->i_mode); if (rc < 0) @@ -94,7 +94,7 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, } break; case ACL_TYPE_DEFAULT: - ea_name = POSIX_ACL_XATTR_DEFAULT; + ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: return -EINVAL; diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 41aa3ca6a6a4..9d9bae63ae2a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -60,6 +60,7 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino) } else if (S_ISLNK(inode->i_mode)) { if (inode->i_size >= IDATASIZE) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &jfs_aops; } else { inode->i_op = &jfs_fast_symlink_inode_operations; diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 9d7551f5c32a..701f89370de7 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -983,6 +983,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry, jfs_info("jfs_symlink: allocate extent ip:0x%p", ip); ip->i_op = &jfs_symlink_inode_operations; + inode_nohighmem(ip); ip->i_mapping->a_ops = &jfs_aops; /* diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c index 5929e2363cb8..f8db4fde0b0b 100644 --- a/fs/jfs/symlink.c +++ b/fs/jfs/symlink.c @@ -23,7 +23,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = jfs_setattr, .setxattr = jfs_setxattr, .getxattr = jfs_getxattr, @@ -33,8 +33,7 @@ const struct inode_operations jfs_fast_symlink_inode_operations = { const struct inode_operations jfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = jfs_setattr, .setxattr = jfs_setxattr, .getxattr = jfs_getxattr, diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 756dd56aaf60..16405ae88d2d 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -205,7 +205,7 @@ int kernfs_iop_removexattr(struct dentry *dentry, const char *name) if (!attrs) return -ENOMEM; - return simple_xattr_remove(&attrs->xattrs, name); + return simple_xattr_set(&attrs->xattrs, name, NULL, 0, XATTR_REPLACE); } ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf, @@ -230,7 +230,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) if (!attrs) return -ENOMEM; - return simple_xattr_list(&attrs->xattrs, buf, size); + return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); } static inline void set_default_inode_attr(struct inode *inode, umode_t mode) diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index db272528ab5b..117b8b3416f9 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -112,18 +112,25 @@ static int kernfs_getlink(struct dentry *dentry, char *path) return error; } -static const char *kernfs_iop_follow_link(struct dentry *dentry, void **cookie) +static const char *kernfs_iop_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - int error = -ENOMEM; - unsigned long page = get_zeroed_page(GFP_KERNEL); - if (!page) + char *body; + int error; + + if (!dentry) + return ERR_PTR(-ECHILD); + body = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!body) return ERR_PTR(-ENOMEM); - error = kernfs_getlink(dentry, (char *)page); + error = kernfs_getlink(dentry, body); if (unlikely(error < 0)) { - free_page((unsigned long)page); + kfree(body); return ERR_PTR(error); } - return *cookie = (char *)page; + set_delayed_call(done, kfree_link, body); + return body; } const struct inode_operations kernfs_symlink_iops = { @@ -132,8 +139,7 @@ const struct inode_operations kernfs_symlink_iops = { .getxattr = kernfs_iop_getxattr, .listxattr = kernfs_iop_listxattr, .readlink = generic_readlink, - .follow_link = kernfs_iop_follow_link, - .put_link = free_page_put_link, + .get_link = kernfs_iop_get_link, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .permission = kernfs_iop_permission, diff --git a/fs/libfs.c b/fs/libfs.c index c7cbfb092e94..01491299f348 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1019,17 +1019,12 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(noop_fsync); -void kfree_put_link(struct inode *unused, void *cookie) +/* Because kfree isn't assignment-compatible with void(void*) ;-/ */ +void kfree_link(void *p) { - kfree(cookie); + kfree(p); } -EXPORT_SYMBOL(kfree_put_link); - -void free_page_put_link(struct inode *unused, void *cookie) -{ - free_page((unsigned long) cookie); -} -EXPORT_SYMBOL(free_page_put_link); +EXPORT_SYMBOL(kfree_link); /* * nop .set_page_dirty method so that people can use .page_mkwrite on @@ -1092,14 +1087,15 @@ simple_nosetlease(struct file *filp, long arg, struct file_lock **flp, } EXPORT_SYMBOL(simple_nosetlease); -const char *simple_follow_link(struct dentry *dentry, void **cookie) +const char *simple_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) { - return d_inode(dentry)->i_link; + return inode->i_link; } -EXPORT_SYMBOL(simple_follow_link); +EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { - .follow_link = simple_follow_link, + .get_link = simple_get_link, .readlink = generic_readlink }; EXPORT_SYMBOL(simple_symlink_inode_operations); diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c index f9b45d46d4c4..542468e9bfb4 100644 --- a/fs/logfs/dir.c +++ b/fs/logfs/dir.c @@ -528,7 +528,8 @@ static int logfs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(inode)) return PTR_ERR(inode); - inode->i_op = &logfs_symlink_iops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &logfs_reg_aops; return __logfs_create(dir, dentry, inode, target, destlen); @@ -776,12 +777,6 @@ fail: return -EIO; } -const struct inode_operations logfs_symlink_iops = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, -}; - const struct inode_operations logfs_dir_iops = { .create = logfs_create, .link = logfs_link, diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index af49e2d6941a..0fce46d62b9c 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -64,7 +64,8 @@ static void logfs_inode_setops(struct inode *inode) inode->i_mapping->a_ops = &logfs_reg_aops; break; case S_IFLNK: - inode->i_op = &logfs_symlink_iops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &logfs_reg_aops; break; case S_IFSOCK: /* fall through */ diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h index 5f0937609465..209a26d84c38 100644 --- a/fs/logfs/logfs.h +++ b/fs/logfs/logfs.h @@ -495,7 +495,6 @@ static inline int logfs_get_sb_mtd(struct logfs_super *s, int mtdnr) #endif /* dir.c */ -extern const struct inode_operations logfs_symlink_iops; extern const struct inode_operations logfs_dir_iops; extern const struct file_operations logfs_dir_fops; int logfs_replay_journal(struct super_block *sb); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 086cd0a61e80..cb1789ca1ee6 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -435,8 +435,7 @@ static const struct address_space_operations minix_aops = { static const struct inode_operations minix_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = minix_getattr, }; @@ -452,6 +451,7 @@ void minix_set_inode(struct inode *inode, dev_t rdev) inode->i_mapping->a_ops = &minix_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &minix_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &minix_aops; } else init_special_inode(inode, inode->i_mode, rdev); diff --git a/fs/namei.c b/fs/namei.c index 0c3974cd3ecd..3c909aebef70 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -505,13 +505,13 @@ struct nameidata { int total_link_count; struct saved { struct path link; - void *cookie; + struct delayed_call done; const char *name; - struct inode *inode; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; + struct inode *link_inode; unsigned root_seq; int dfd; }; @@ -592,11 +592,8 @@ static void drop_links(struct nameidata *nd) int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; - struct inode *inode = last->inode; - if (last->cookie && inode->i_op->put_link) { - inode->i_op->put_link(inode, last->cookie); - last->cookie = NULL; - } + do_delayed_call(&last->done); + clear_delayed_call(&last->done); } } @@ -842,7 +839,7 @@ static inline void path_to_nameidata(const struct path *path, } /* - * Helper to directly jump to a known parsed path from ->follow_link, + * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ void nd_jump_link(struct path *path) @@ -858,9 +855,7 @@ void nd_jump_link(struct path *path) static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; - struct inode *inode = last->inode; - if (last->cookie && inode->i_op->put_link) - inode->i_op->put_link(inode, last->cookie); + do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } @@ -892,7 +887,7 @@ static inline int may_follow_link(struct nameidata *nd) return 0; /* Allowed if owner and follower match. */ - inode = nd->stack[0].inode; + inode = nd->link_inode; if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; @@ -983,7 +978,7 @@ const char *get_link(struct nameidata *nd) { struct saved *last = nd->stack + nd->depth - 1; struct dentry *dentry = last->link.dentry; - struct inode *inode = last->inode; + struct inode *inode = nd->link_inode; int error; const char *res; @@ -1004,15 +999,21 @@ const char *get_link(struct nameidata *nd) nd->last_type = LAST_BIND; res = inode->i_link; if (!res) { + const char * (*get)(struct dentry *, struct inode *, + struct delayed_call *); + get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { - if (unlikely(unlazy_walk(nd, NULL, 0))) - return ERR_PTR(-ECHILD); + res = get(NULL, inode, &last->done); + if (res == ERR_PTR(-ECHILD)) { + if (unlikely(unlazy_walk(nd, NULL, 0))) + return ERR_PTR(-ECHILD); + res = get(dentry, inode, &last->done); + } + } else { + res = get(dentry, inode, &last->done); } - res = inode->i_op->follow_link(dentry, &last->cookie); - if (IS_ERR_OR_NULL(res)) { - last->cookie = NULL; + if (IS_ERR_OR_NULL(res)) return res; - } } if (*res == '/') { if (nd->flags & LOOKUP_RCU) { @@ -1691,8 +1692,8 @@ static int pick_link(struct nameidata *nd, struct path *link, last = nd->stack + nd->depth++; last->link = *link; - last->cookie = NULL; - last->inode = inode; + clear_delayed_call(&last->done); + nd->link_inode = inode; last->seq = seq; return 1; } @@ -4495,72 +4496,73 @@ EXPORT_SYMBOL(readlink_copy); /* * A helper for ->readlink(). This should be used *ONLY* for symlinks that - * have ->follow_link() touching nd only in nd_set_link(). Using (or not - * using) it for any given inode is up to filesystem. + * have ->get_link() not calling nd_jump_link(). Using (or not using) it + * for any given inode is up to filesystem. */ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen) { - void *cookie; + DEFINE_DELAYED_CALL(done); struct inode *inode = d_inode(dentry); const char *link = inode->i_link; int res; if (!link) { - link = inode->i_op->follow_link(dentry, &cookie); + link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link); - if (inode->i_op->put_link) - inode->i_op->put_link(inode, cookie); + do_delayed_call(&done); return res; } EXPORT_SYMBOL(generic_readlink); /* get the link contents into pagecache */ -static char *page_getlink(struct dentry * dentry, struct page **ppage) +const char *page_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) { char *kaddr; struct page *page; - struct address_space *mapping = dentry->d_inode->i_mapping; - page = read_mapping_page(mapping, 0, NULL); - if (IS_ERR(page)) - return (char*)page; - *ppage = page; - kaddr = kmap(page); - nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1); + struct address_space *mapping = inode->i_mapping; + + if (!dentry) { + page = find_get_page(mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + page = read_mapping_page(mapping, 0, NULL); + if (IS_ERR(page)) + return (char*)page; + } + set_delayed_call(callback, page_put_link, page); + BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); + kaddr = page_address(page); + nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } -int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) -{ - struct page *page = NULL; - int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page)); - if (page) { - kunmap(page); - page_cache_release(page); - } - return res; -} -EXPORT_SYMBOL(page_readlink); +EXPORT_SYMBOL(page_get_link); -const char *page_follow_link_light(struct dentry *dentry, void **cookie) +void page_put_link(void *arg) { - struct page *page = NULL; - char *res = page_getlink(dentry, &page); - if (!IS_ERR(res)) - *cookie = page; - return res; + put_page(arg); } -EXPORT_SYMBOL(page_follow_link_light); +EXPORT_SYMBOL(page_put_link); -void page_put_link(struct inode *unused, void *cookie) +int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { - struct page *page = cookie; - kunmap(page); - page_cache_release(page); + DEFINE_DELAYED_CALL(done); + int res = readlink_copy(buffer, buflen, + page_get_link(dentry, d_inode(dentry), + &done)); + do_delayed_call(&done); + return res; } -EXPORT_SYMBOL(page_put_link); +EXPORT_SYMBOL(page_readlink); /* * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS @@ -4571,7 +4573,6 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) struct page *page; void *fsdata; int err; - char *kaddr; unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE; if (nofs) flags |= AOP_FLAG_NOFS; @@ -4582,9 +4583,7 @@ retry: if (err) goto fail; - kaddr = kmap_atomic(page); - memcpy(kaddr, symname, len-1); - kunmap_atomic(kaddr); + memcpy(page_address(page), symname, len-1); err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); @@ -4609,7 +4608,6 @@ EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 9605a2f63549..ce1eb3f9dfe8 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -244,8 +244,7 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo) #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) static const struct inode_operations ncp_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = ncp_notify_change, }; #endif @@ -283,6 +282,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info) #if defined(CONFIG_NCPFS_EXTRAS) || defined(CONFIG_NCPFS_NFS_NS) } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &ncp_symlink_inode_operations; + inode_nohighmem(inode); inode->i_data.a_ops = &ncp_symlink_aops; #endif } else { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c7e8b87da5b2..bdb4dc7b4ecd 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -408,9 +408,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } - } else if (S_ISLNK(inode->i_mode)) + } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; - else + inode_nohighmem(inode); + } else init_special_inode(inode, inode->i_mode, fattr->rdev); memset(&inode->i_atime, 0, sizeof(inode->i_atime)); @@ -1086,6 +1087,27 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode) || NFS_STALE(inode); } +int nfs_revalidate_mapping_rcu(struct inode *inode) +{ + struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; + int ret = 0; + + if (IS_SWAPFILE(inode)) + goto out; + if (nfs_mapping_need_revalidate_inode(inode)) { + ret = -ECHILD; + goto out; + } + spin_lock(&inode->i_lock); + if (test_bit(NFS_INO_INVALIDATING, bitlock) || + (nfsi->cache_validity & NFS_INO_INVALID_DATA)) + ret = -ECHILD; + spin_unlock(&inode->i_lock); +out: + return ret; +} + /** * __nfs_revalidate_mapping - Revalidate the pagecache * @inode - pointer to host inode diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 1ebe2fc7cda2..17c0fa1eccfa 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -284,12 +284,12 @@ nfs3_listxattr(struct dentry *dentry, char *data, size_t size) int error; error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, - POSIX_ACL_XATTR_ACCESS, data, size, &result); + XATTR_NAME_POSIX_ACL_ACCESS, data, size, &result); if (error) return error; error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, - POSIX_ACL_XATTR_DEFAULT, data, size, &result); + XATTR_NAME_POSIX_ACL_DEFAULT, data, size, &result); if (error) return error; return result; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 89818036f035..c57d1332c1c8 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6253,9 +6253,6 @@ static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler, const void *buf, size_t buflen, int flags) { - if (strcmp(key, "") != 0) - return -EINVAL; - return nfs4_proc_set_acl(d_inode(dentry), buf, buflen); } @@ -6263,32 +6260,15 @@ static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler, struct dentry *dentry, const char *key, void *buf, size_t buflen) { - if (strcmp(key, "") != 0) - return -EINVAL; - return nfs4_proc_get_acl(d_inode(dentry), buf, buflen); } -static size_t nfs4_xattr_list_nfs4_acl(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_len, const char *name, - size_t name_len) +static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry) { - size_t len = sizeof(XATTR_NAME_NFSV4_ACL); - - if (!nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry)))) - return 0; - - if (list && len <= list_len) - memcpy(list, XATTR_NAME_NFSV4_ACL, len); - return len; + return nfs4_server_supports_acls(NFS_SERVER(d_inode(dentry))); } #ifdef CONFIG_NFS_V4_SECURITY_LABEL -static inline int nfs4_server_supports_labels(struct nfs_server *server) -{ - return server->caps & NFS_CAP_SECURITY_LABEL; -} static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler, struct dentry *dentry, const char *key, @@ -6310,29 +6290,34 @@ static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler, return -EOPNOTSUPP; } -static size_t nfs4_xattr_list_nfs4_label(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_len, const char *name, - size_t name_len) +static ssize_t +nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) { - size_t len = 0; + int len = 0; - if (nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) { - len = security_inode_listsecurity(d_inode(dentry), NULL, 0); - if (list && len <= list_len) - security_inode_listsecurity(d_inode(dentry), list, len); + if (nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) { + len = security_inode_listsecurity(inode, list, list_len); + if (list_len && len > list_len) + return -ERANGE; } return len; } static const struct xattr_handler nfs4_xattr_nfs4_label_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = nfs4_xattr_list_nfs4_label, .get = nfs4_xattr_get_nfs4_label, .set = nfs4_xattr_set_nfs4_label, }; -#endif +#else + +static ssize_t +nfs4_listxattr_nfs4_label(struct inode *inode, char *list, size_t list_len) +{ + return 0; +} + +#endif /* * nfs_fhget will use either the mounted_on_fileid or the fileid @@ -8749,6 +8734,24 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { #endif }; +ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) +{ + ssize_t error, error2; + + error = generic_listxattr(dentry, list, size); + if (error < 0) + return error; + if (list) { + list += error; + size -= error; + } + + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + if (error2 < 0) + return error2; + return error + error2; +} + static const struct inode_operations nfs4_dir_inode_operations = { .create = nfs_create, .lookup = nfs_lookup, @@ -8765,7 +8768,7 @@ static const struct inode_operations nfs4_dir_inode_operations = { .setattr = nfs_setattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, - .listxattr = generic_listxattr, + .listxattr = nfs4_listxattr, .removexattr = generic_removexattr, }; @@ -8775,7 +8778,7 @@ static const struct inode_operations nfs4_file_inode_operations = { .setattr = nfs_setattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, - .listxattr = generic_listxattr, + .listxattr = nfs4_listxattr, .removexattr = generic_removexattr, }; @@ -8834,7 +8837,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { - .prefix = XATTR_NAME_NFSV4_ACL, + .name = XATTR_NAME_NFSV4_ACL, .list = nfs4_xattr_list_nfs4_acl, .get = nfs4_xattr_get_nfs4_acl, .set = nfs4_xattr_set_nfs4_acl, diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index b6de433da5db..4fe3eead3868 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -42,21 +42,35 @@ error: return -EIO; } -static const char *nfs_follow_link(struct dentry *dentry, void **cookie) +static const char *nfs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct page *page; void *err; - err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); - if (err) - return err; - page = read_cache_page(&inode->i_data, 0, - (filler_t *)nfs_symlink_filler, inode); - if (IS_ERR(page)) - return ERR_CAST(page); - *cookie = page; - return kmap(page); + if (!dentry) { + err = ERR_PTR(nfs_revalidate_mapping_rcu(inode)); + if (err) + return err; + page = find_get_page(inode->i_mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); + if (err) + return err; + page = read_cache_page(&inode->i_data, 0, + (filler_t *)nfs_symlink_filler, inode); + if (IS_ERR(page)) + return ERR_CAST(page); + } + set_delayed_call(done, page_put_link, page); + return page_address(page); } /* @@ -64,8 +78,7 @@ static const char *nfs_follow_link(struct dentry *dentry, void **cookie) */ const struct inode_operations nfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = nfs_follow_link, - .put_link = page_put_link, + .get_link = nfs_get_link, .getattr = nfs_getattr, .setattr = nfs_setattr, }; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 9ffef06b30d5..c9d6c715c0fb 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -616,6 +616,7 @@ nfsd4_cb_layout_prepare(struct nfsd4_callback *cb) mutex_lock(&ls->ls_mutex); nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid); + mutex_unlock(&ls->ls_mutex); } static int @@ -659,7 +660,6 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb) trace_layout_recall_release(&ls->ls_stid.sc_stateid); - mutex_unlock(&ls->ls_mutex); nfsd4_return_all_layouts(ls, &reaplist); nfsd4_free_layouts(&reaplist); nfs4_put_stid(&ls->ls_stid); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index ac2f64943ff4..10b22527a617 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -510,6 +510,7 @@ static int __nilfs_read_inode(struct super_block *sb, inode->i_mapping->a_ops = &nilfs_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nilfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; } else { inode->i_op = &nilfs_special_inode_operations; diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index c9a1a491aa91..7ccdb961eea9 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -161,6 +161,7 @@ static int nilfs_symlink(struct inode *dir, struct dentry *dentry, /* slow symlink */ inode->i_op = &nilfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &nilfs_aops; err = page_symlink(inode, symname, l); if (err) @@ -568,8 +569,7 @@ const struct inode_operations nilfs_special_inode_operations = { const struct inode_operations nilfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .permission = nilfs_permission, }; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index ce38b4ccc9ab..84f2f8079466 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2843,6 +2843,8 @@ again: res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY; if (!ret) BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING)); + else + res->migration_pending = 0; spin_unlock(&res->spinlock); /* diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 8f87e05ee25d..97a563bab9a8 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -361,6 +361,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, break; case S_IFLNK: inode->i_op = &ocfs2_symlink_inode_operations; + inode_nohighmem(inode); i_size_write(inode, le64_to_cpu(fe->i_size)); break; default: diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index 652ece4a9d9e..d56f0079b858 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -67,7 +67,10 @@ static int ocfs2_do_flock(struct file *file, struct inode *inode, */ locks_lock_file_wait(file, - &(struct file_lock){.fl_type = F_UNLCK}); + &(struct file_lock) { + .fl_type = F_UNLCK, + .fl_flags = FL_FLOCK + }); ocfs2_file_unlock(file); } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3123408da935..afb81eae2c18 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1958,6 +1958,7 @@ static int ocfs2_symlink(struct inode *dir, inode->i_rdev = 0; newsize = l - 1; inode->i_op = &ocfs2_symlink_inode_operations; + inode_nohighmem(inode); if (l > ocfs2_fast_symlink_chars(sb)) { u32 offset = 0; diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index d5da6f624142..79b8021302b3 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -54,11 +54,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode, struct ocfs2_group_desc *gd, u16 cl_cpg, + u16 old_bg_clusters, int set) { int i; u16 backups = 0; - u32 cluster; + u32 cluster, lgd_cluster; u64 blkno, gd_blkno, lgd_blkno = le64_to_cpu(gd->bg_blkno); for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) { @@ -71,6 +72,12 @@ static u16 ocfs2_calc_new_backup_super(struct inode *inode, else if (gd_blkno > lgd_blkno) break; + /* check if already done backup super */ + lgd_cluster = ocfs2_blocks_to_clusters(inode->i_sb, lgd_blkno); + lgd_cluster += old_bg_clusters; + if (lgd_cluster >= cluster) + continue; + if (set) ocfs2_set_bit(cluster % cl_cpg, (unsigned long *)gd->bg_bitmap); @@ -99,6 +106,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, u16 chain, num_bits, backups = 0; u16 cl_bpc = le16_to_cpu(cl->cl_bpc); u16 cl_cpg = le16_to_cpu(cl->cl_cpg); + u16 old_bg_clusters; trace_ocfs2_update_last_group_and_inode(new_clusters, first_new_cluster); @@ -112,6 +120,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, group = (struct ocfs2_group_desc *)group_bh->b_data; + old_bg_clusters = le16_to_cpu(group->bg_bits) / cl_bpc; /* update the group first. */ num_bits = new_clusters * cl_bpc; le16_add_cpu(&group->bg_bits, num_bits); @@ -125,7 +134,7 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle, OCFS2_FEATURE_COMPAT_BACKUP_SB)) { backups = ocfs2_calc_new_backup_super(bm_inode, group, - cl_cpg, 1); + cl_cpg, old_bg_clusters, 1); le16_add_cpu(&group->bg_free_bits_count, -1 * backups); } @@ -163,7 +172,7 @@ out_rollback: if (ret < 0) { ocfs2_calc_new_backup_super(bm_inode, group, - cl_cpg, 0); + cl_cpg, old_bg_clusters, 0); le16_add_cpu(&group->bg_free_bits_count, backups); le16_add_cpu(&group->bg_bits, -1 * num_bits); le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits); diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index 66edce7ecfd7..6c2a3e3c521c 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -88,8 +88,7 @@ const struct address_space_operations ocfs2_fast_symlink_aops = { const struct inode_operations ocfs2_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = ocfs2_getattr, .setattr = ocfs2_setattr, .setxattr = generic_setxattr, diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index e9164f09841b..f0e241ffd94f 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -544,8 +544,7 @@ static inline const char *ocfs2_xattr_prefix(int name_index) if (name_index > 0 && name_index < OCFS2_XATTR_MAX) handler = ocfs2_xattr_handler_map[name_index]; - - return handler ? handler->prefix : NULL; + return handler ? xattr_prefix(handler) : NULL; } static u32 ocfs2_xattr_name_hash(struct inode *inode, @@ -884,14 +883,39 @@ static int ocfs2_xattr_value_truncate(struct inode *inode, return ret; } -static int ocfs2_xattr_list_entry(char *buffer, size_t size, - size_t *result, const char *prefix, +static int ocfs2_xattr_list_entry(struct super_block *sb, + char *buffer, size_t size, + size_t *result, int type, const char *name, int name_len) { char *p = buffer + *result; - int prefix_len = strlen(prefix); - int total_len = prefix_len + name_len + 1; + const char *prefix; + int prefix_len; + int total_len; + switch(type) { + case OCFS2_XATTR_INDEX_USER: + if (OCFS2_SB(sb)->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) + return 0; + break; + + case OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS: + case OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT: + if (!(sb->s_flags & MS_POSIXACL)) + return 0; + break; + + case OCFS2_XATTR_INDEX_TRUSTED: + if (!capable(CAP_SYS_ADMIN)) + return 0; + break; + } + + prefix = ocfs2_xattr_prefix(type); + if (!prefix) + return 0; + prefix_len = strlen(prefix); + total_len = prefix_len + name_len + 1; *result += total_len; /* we are just looking for how big our buffer needs to be */ @@ -914,23 +938,20 @@ static int ocfs2_xattr_list_entries(struct inode *inode, { size_t result = 0; int i, type, ret; - const char *prefix, *name; + const char *name; for (i = 0 ; i < le16_to_cpu(header->xh_count); i++) { struct ocfs2_xattr_entry *entry = &header->xh_entries[i]; type = ocfs2_xattr_get_type(entry); - prefix = ocfs2_xattr_prefix(type); - - if (prefix) { - name = (const char *)header + - le16_to_cpu(entry->xe_name_offset); + name = (const char *)header + + le16_to_cpu(entry->xe_name_offset); - ret = ocfs2_xattr_list_entry(buffer, buffer_size, - &result, prefix, name, - entry->xe_name_len); - if (ret) - return ret; - } + ret = ocfs2_xattr_list_entry(inode->i_sb, + buffer, buffer_size, + &result, type, name, + entry->xe_name_len); + if (ret) + return ret; } return result; @@ -4033,32 +4054,30 @@ static int ocfs2_list_xattr_bucket(struct inode *inode, int ret = 0, type; struct ocfs2_xattr_tree_list *xl = (struct ocfs2_xattr_tree_list *)para; int i, block_off, new_offset; - const char *prefix, *name; + const char *name; for (i = 0 ; i < le16_to_cpu(bucket_xh(bucket)->xh_count); i++) { struct ocfs2_xattr_entry *entry = &bucket_xh(bucket)->xh_entries[i]; type = ocfs2_xattr_get_type(entry); - prefix = ocfs2_xattr_prefix(type); - if (prefix) { - ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb, - bucket_xh(bucket), - i, - &block_off, - &new_offset); - if (ret) - break; + ret = ocfs2_xattr_bucket_get_name_value(inode->i_sb, + bucket_xh(bucket), + i, + &block_off, + &new_offset); + if (ret) + break; - name = (const char *)bucket_block(bucket, block_off) + - new_offset; - ret = ocfs2_xattr_list_entry(xl->buffer, - xl->buffer_size, - &xl->result, - prefix, name, - entry->xe_name_len); - if (ret) - break; - } + name = (const char *)bucket_block(bucket, block_off) + + new_offset; + ret = ocfs2_xattr_list_entry(inode->i_sb, + xl->buffer, + xl->buffer_size, + &xl->result, + type, name, + entry->xe_name_len); + if (ret) + break; } return ret; @@ -7226,31 +7245,14 @@ int ocfs2_init_security_and_acl(struct inode *dir, leave: return ret; } + /* * 'security' attributes support */ -static size_t ocfs2_xattr_security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_SECURITY_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ocfs2_xattr_security_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, name, buffer, size); } @@ -7259,9 +7261,6 @@ static int ocfs2_xattr_security_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; - return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_SECURITY, name, value, size, flags); } @@ -7314,7 +7313,6 @@ int ocfs2_init_security_set(handle_t *handle, const struct xattr_handler ocfs2_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, - .list = ocfs2_xattr_security_list, .get = ocfs2_xattr_security_get, .set = ocfs2_xattr_security_set, }; @@ -7322,31 +7320,10 @@ const struct xattr_handler ocfs2_xattr_security_handler = { /* * 'trusted' attributes support */ -static size_t ocfs2_xattr_trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - - if (!capable(CAP_SYS_ADMIN)) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ocfs2_xattr_trusted_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { - if (strcmp(name, "") == 0) - return -EINVAL; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, name, buffer, size); } @@ -7355,16 +7332,12 @@ static int ocfs2_xattr_trusted_set(const struct xattr_handler *handler, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (strcmp(name, "") == 0) - return -EINVAL; - return ocfs2_xattr_set(d_inode(dentry), OCFS2_XATTR_INDEX_TRUSTED, name, value, size, flags); } const struct xattr_handler ocfs2_xattr_trusted_handler = { .prefix = XATTR_TRUSTED_PREFIX, - .list = ocfs2_xattr_trusted_list, .get = ocfs2_xattr_trusted_get, .set = ocfs2_xattr_trusted_set, }; @@ -7372,34 +7345,12 @@ const struct xattr_handler ocfs2_xattr_trusted_handler = { /* * 'user' attributes support */ -static size_t ocfs2_xattr_user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - const size_t prefix_len = XATTR_USER_PREFIX_LEN; - const size_t total_len = prefix_len + name_len + 1; - struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - - if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) - return 0; - - if (list && total_len <= list_size) { - memcpy(list, XATTR_USER_PREFIX, prefix_len); - memcpy(list + prefix_len, name, name_len); - list[prefix_len + name_len] = '\0'; - } - return total_len; -} - static int ocfs2_xattr_user_get(const struct xattr_handler *handler, struct dentry *dentry, const char *name, void *buffer, size_t size) { struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (strcmp(name, "") == 0) - return -EINVAL; if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; return ocfs2_xattr_get(d_inode(dentry), OCFS2_XATTR_INDEX_USER, name, @@ -7412,8 +7363,6 @@ static int ocfs2_xattr_user_set(const struct xattr_handler *handler, { struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb); - if (strcmp(name, "") == 0) - return -EINVAL; if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR) return -EOPNOTSUPP; @@ -7423,7 +7372,6 @@ static int ocfs2_xattr_user_set(const struct xattr_handler *handler, const struct xattr_handler ocfs2_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, - .list = ocfs2_xattr_user_list, .get = ocfs2_xattr_user_get, .set = ocfs2_xattr_user_set, }; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 4060ffde8722..964a60fa7afc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -131,57 +131,23 @@ out_dput: return err; } - -struct ovl_link_data { - struct dentry *realdentry; - void *cookie; -}; - -static const char *ovl_follow_link(struct dentry *dentry, void **cookie) +static const char *ovl_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct dentry *realdentry; struct inode *realinode; - struct ovl_link_data *data = NULL; - const char *ret; + + if (!dentry) + return ERR_PTR(-ECHILD); realdentry = ovl_dentry_real(dentry); realinode = realdentry->d_inode; - if (WARN_ON(!realinode->i_op->follow_link)) + if (WARN_ON(!realinode->i_op->get_link)) return ERR_PTR(-EPERM); - if (realinode->i_op->put_link) { - data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); - if (!data) - return ERR_PTR(-ENOMEM); - data->realdentry = realdentry; - } - - ret = realinode->i_op->follow_link(realdentry, cookie); - if (IS_ERR_OR_NULL(ret)) { - kfree(data); - return ret; - } - - if (data) - data->cookie = *cookie; - - *cookie = data; - - return ret; -} - -static void ovl_put_link(struct inode *unused, void *c) -{ - struct inode *realinode; - struct ovl_link_data *data = c; - - if (!data) - return; - - realinode = data->realdentry->d_inode; - realinode->i_op->put_link(realinode, data->cookie); - kfree(data); + return realinode->i_op->get_link(realdentry, realinode, done); } static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) @@ -378,8 +344,7 @@ static const struct inode_operations ovl_file_inode_operations = { static const struct inode_operations ovl_symlink_inode_operations = { .setattr = ovl_setattr, - .follow_link = ovl_follow_link, - .put_link = ovl_put_link, + .get_link = ovl_get_link, .readlink = ovl_readlink, .getattr = ovl_getattr, .setxattr = ovl_setxattr, diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4adde1e2cbec..711dd5170376 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -769,8 +769,6 @@ posix_acl_xattr_get(const struct xattr_handler *handler, struct posix_acl *acl; int error; - if (strcmp(name, "") != 0) - return -EINVAL; if (!IS_POSIXACL(d_backing_inode(dentry))) return -EOPNOTSUPP; if (d_is_symlink(dentry)) @@ -797,8 +795,6 @@ posix_acl_xattr_set(const struct xattr_handler *handler, struct posix_acl *acl = NULL; int ret; - if (strcmp(name, "") != 0) - return -EINVAL; if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) @@ -827,25 +823,14 @@ out: return ret; } -static size_t -posix_acl_xattr_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool +posix_acl_xattr_list(struct dentry *dentry) { - const char *xname = handler->prefix; - size_t size; - - if (!IS_POSIXACL(d_backing_inode(dentry))) - return 0; - - size = strlen(xname) + 1; - if (list && size <= list_size) - memcpy(list, xname, size); - return size; + return IS_POSIXACL(d_backing_inode(dentry)); } const struct xattr_handler posix_acl_access_xattr_handler = { - .prefix = POSIX_ACL_XATTR_ACCESS, + .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, @@ -854,7 +839,7 @@ const struct xattr_handler posix_acl_access_xattr_handler = { EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler); const struct xattr_handler posix_acl_default_xattr_handler = { - .prefix = POSIX_ACL_XATTR_DEFAULT, + .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .list = posix_acl_xattr_list, .get = posix_acl_xattr_get, diff --git a/fs/proc/base.c b/fs/proc/base.c index 4bd5d3118acd..55e01f88eac9 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1564,12 +1564,16 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path) return -ENOENT; } -static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_pid_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); struct path path; int error = -EACCES; + if (!dentry) + return ERR_PTR(-ECHILD); + /* Are we allowed to snoop on the tasks file descriptors? */ if (!proc_fd_access_allowed(inode)) goto out; @@ -1630,7 +1634,7 @@ out: const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_pid_follow_link, + .get_link = proc_pid_get_link, .setattr = proc_setattr, }; @@ -1895,7 +1899,7 @@ static const struct dentry_operations tid_map_files_dentry_operations = { .d_delete = pid_delete_dentry, }; -static int proc_map_files_get_link(struct dentry *dentry, struct path *path) +static int map_files_get_link(struct dentry *dentry, struct path *path) { unsigned long vm_start, vm_end; struct vm_area_struct *vma; @@ -1945,20 +1949,22 @@ struct map_files_info { * path to the file in question. */ static const char * -proc_map_files_follow_link(struct dentry *dentry, void **cookie) +proc_map_files_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - return proc_pid_follow_link(dentry, NULL); + return proc_pid_get_link(dentry, inode, done); } /* - * Identical to proc_pid_link_inode_operations except for follow_link() + * Identical to proc_pid_link_inode_operations except for get_link() */ static const struct inode_operations proc_map_files_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_map_files_follow_link, + .get_link = proc_map_files_get_link, .setattr = proc_setattr, }; @@ -1975,7 +1981,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, return -ENOENT; ei = PROC_I(inode); - ei->op.proc_get_link = proc_map_files_get_link; + ei->op.proc_get_link = map_files_get_link; inode->i_op = &proc_map_files_link_inode_operations; inode->i_size = 64; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index bd95b9fdebb0..d0e9b9b6223e 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -393,24 +393,25 @@ static const struct file_operations proc_reg_file_ops_no_compat = { }; #endif -static const char *proc_follow_link(struct dentry *dentry, void **cookie) +static void proc_put_link(void *p) { - struct proc_dir_entry *pde = PDE(d_inode(dentry)); - if (unlikely(!use_pde(pde))) - return ERR_PTR(-EINVAL); - *cookie = pde; - return pde->data; + unuse_pde(p); } -static void proc_put_link(struct inode *unused, void *p) +static const char *proc_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - unuse_pde(p); + struct proc_dir_entry *pde = PDE(inode); + if (unlikely(!use_pde(pde))) + return ERR_PTR(-EINVAL); + set_delayed_call(done, proc_put_link, pde); + return pde->data; } const struct inode_operations proc_link_inode_operations = { .readlink = generic_readlink, - .follow_link = proc_follow_link, - .put_link = proc_put_link, + .get_link = proc_get_link, }; struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index f6e8354b8cea..1dece8781f91 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -30,14 +30,18 @@ static const struct proc_ns_operations *ns_entries[] = { &mntns_operations, }; -static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_ns_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct inode *inode = d_inode(dentry); const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; struct task_struct *task; struct path ns_path; void *error = ERR_PTR(-EACCES); + if (!dentry) + return ERR_PTR(-ECHILD); + task = get_proc_task(inode); if (!task) return error; @@ -74,7 +78,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl static const struct inode_operations proc_ns_link_inode_operations = { .readlink = proc_ns_readlink, - .follow_link = proc_ns_follow_link, + .get_link = proc_ns_get_link, .setattr = proc_setattr, }; diff --git a/fs/proc/self.c b/fs/proc/self.c index 113b8d061fc0..67e8db442cf0 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -18,26 +18,28 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer, return readlink_copy(buffer, buflen, tmp); } -static const char *proc_self_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_self_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct pid_namespace *ns = dentry->d_sb->s_fs_info; + struct pid_namespace *ns = inode->i_sb->s_fs_info; pid_t tgid = task_tgid_nr_ns(current, ns); char *name; if (!tgid) return ERR_PTR(-ENOENT); /* 11 for max length of signed int in decimal + NULL term */ - name = kmalloc(12, GFP_KERNEL); - if (!name) - return ERR_PTR(-ENOMEM); + name = kmalloc(12, dentry ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!name)) + return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%d", tgid); - return *cookie = name; + set_delayed_call(done, kfree_link, name); + return name; } static const struct inode_operations proc_self_inode_operations = { .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, - .put_link = kfree_put_link, + .get_link = proc_self_get_link, }; static unsigned self_inum; diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index 947b0f4fd0a1..9eacd59e0360 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -19,26 +19,29 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer, return readlink_copy(buffer, buflen, tmp); } -static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie) +static const char *proc_thread_self_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct pid_namespace *ns = dentry->d_sb->s_fs_info; + struct pid_namespace *ns = inode->i_sb->s_fs_info; pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; if (!pid) return ERR_PTR(-ENOENT); - name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL); - if (!name) - return ERR_PTR(-ENOMEM); + name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, + dentry ? GFP_KERNEL : GFP_ATOMIC); + if (unlikely(!name)) + return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%d/task/%d", tgid, pid); - return *cookie = name; + set_delayed_call(done, kfree_link, name); + return name; } static const struct inode_operations proc_thread_self_inode_operations = { .readlink = proc_thread_self_readlink, - .follow_link = proc_thread_self_follow_link, - .put_link = kfree_put_link, + .get_link = proc_thread_self_get_link, }; static unsigned thread_self_inum; diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index c4bcb778886e..f37b3deb01b4 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -316,6 +316,7 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino) inode->i_fop = &qnx4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &qnx4_aops; qnx4_i(inode)->mmu_private = inode->i_size; } else { diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 32d2e1a9774c..9728b5499e1d 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -582,6 +582,7 @@ struct inode *qnx6_iget(struct super_block *sb, unsigned ino) inode->i_mapping->a_ops = &qnx6_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &qnx6_aops; } else init_special_inode(inode, inode->i_mode, 0); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 889d558b4e05..38981b037524 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -79,6 +79,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); break; } } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 3d8e7e671d5b..ae9e5b308cf9 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1361,6 +1361,7 @@ static void init_inode(struct inode *inode, struct treepath *path) inode->i_fop = &reiserfs_dir_operations; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &reiserfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &reiserfs_address_space_operations; } else { inode->i_blocks = 0; diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 47f96988fdd4..2a12d46d7fb4 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1170,6 +1170,7 @@ static int reiserfs_symlink(struct inode *parent_dir, reiserfs_update_inode_transaction(parent_dir); inode->i_op = &reiserfs_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &reiserfs_address_space_operations; retval = reiserfs_add_entry(&th, parent_dir, dentry->d_name.name, @@ -1664,8 +1665,7 @@ const struct inode_operations reiserfs_dir_inode_operations = { */ const struct inode_operations reiserfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .setattr = reiserfs_setattr, .setxattr = reiserfs_setxattr, .getxattr = reiserfs_getxattr, diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 66b26fdfff8d..e5ddb4e5ea94 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -756,7 +756,8 @@ find_xattr_handler_prefix(const struct xattr_handler **handlers, return NULL; for_each_xattr_handler(handlers, xah) { - if (strncmp(xah->prefix, name, strlen(xah->prefix)) == 0) + const char *prefix = xattr_prefix(xah); + if (strncmp(prefix, name, strlen(prefix)) == 0) break; } @@ -839,19 +840,16 @@ static int listxattr_filler(struct dir_context *ctx, const char *name, handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr, name); - if (!handler) /* Unsupported xattr name */ + if (!handler /* Unsupported xattr name */ || + (handler->list && !handler->list(b->dentry))) return 0; + size = namelen + 1; if (b->buf) { - size = handler->list(handler, b->dentry, - b->buf + b->pos, b->size, name, - namelen); if (size > b->size) return -ERANGE; - } else { - size = handler->list(handler, b->dentry, - NULL, 0, name, namelen); + memcpy(b->buf + b->pos, name, namelen); + b->buf[b->pos + namelen] = 0; } - b->pos += size; } return 0; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 4b34b9dc03dd..558a16beaacb 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -186,10 +186,10 @@ struct posix_acl *reiserfs_get_acl(struct inode *inode, int type) switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; break; default: BUG(); @@ -244,7 +244,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: - name = POSIX_ACL_XATTR_ACCESS; + name = XATTR_NAME_POSIX_ACL_ACCESS; if (acl) { error = posix_acl_equiv_mode(acl, &inode->i_mode); if (error < 0) @@ -256,7 +256,7 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, } break; case ACL_TYPE_DEFAULT: - name = POSIX_ACL_XATTR_DEFAULT; + name = XATTR_NAME_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index ac659af431ae..ab0217d32039 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -34,21 +34,9 @@ security_set(const struct xattr_handler *handler, struct dentry *dentry, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t security_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_len, - const char *name, size_t namelen) +static bool security_list(struct dentry *dentry) { - const size_t len = namelen + 1; - - if (IS_PRIVATE(d_inode(dentry))) - return 0; - - if (list && len <= list_len) { - memcpy(list, name, namelen); - list[namelen] = '\0'; - } - - return len; + return !IS_PRIVATE(d_inode(dentry)); } /* Initializes the security context for a new inode and returns the number diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c index a338adf1b8b4..64b67aa643a9 100644 --- a/fs/reiserfs/xattr_trusted.c +++ b/fs/reiserfs/xattr_trusted.c @@ -33,20 +33,9 @@ trusted_set(const struct xattr_handler *handler, struct dentry *dentry, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t trusted_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool trusted_list(struct dentry *dentry) { - const size_t len = name_len + 1; - - if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(d_inode(dentry))) - return 0; - - if (list && len <= list_size) { - memcpy(list, name, name_len); - list[name_len] = '\0'; - } - return len; + return capable(CAP_SYS_ADMIN) && !IS_PRIVATE(d_inode(dentry)); } const struct xattr_handler reiserfs_xattr_trusted_handler = { diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c index 39c9667191c5..12e6306f562a 100644 --- a/fs/reiserfs/xattr_user.c +++ b/fs/reiserfs/xattr_user.c @@ -30,19 +30,9 @@ user_set(const struct xattr_handler *handler, struct dentry *dentry, return reiserfs_xattr_set(d_inode(dentry), name, buffer, size, flags); } -static size_t user_list(const struct xattr_handler *handler, - struct dentry *dentry, char *list, size_t list_size, - const char *name, size_t name_len) +static bool user_list(struct dentry *dentry) { - const size_t len = name_len + 1; - - if (!reiserfs_xattrs_user(dentry->d_sb)) - return 0; - if (list && len <= list_size) { - memcpy(list, name, name_len); - list[name_len] = '\0'; - } - return len; + return reiserfs_xattrs_user(dentry->d_sb); } const struct xattr_handler reiserfs_xattr_user_handler = { diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 268733cda397..bb894e78a821 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -360,6 +360,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) break; case ROMFH_SYM: i->i_op = &page_symlink_inode_operations; + inode_nohighmem(i); i->i_data.a_ops = &romfs_aops; mode |= S_IRWXUGO; break; diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index a1ce5ce60632..0927b1e80ab6 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -41,6 +41,7 @@ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/xattr.h> +#include <linux/pagemap.h> #include "squashfs_fs.h" #include "squashfs_fs_sb.h" @@ -291,6 +292,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); inode->i_op = &squashfs_symlink_inode_ops; + inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; inode->i_mode |= S_IFLNK; squashfs_i(inode)->start = block; diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c index 12806dffb345..dbcc2f54bad4 100644 --- a/fs/squashfs/symlink.c +++ b/fs/squashfs/symlink.c @@ -119,8 +119,7 @@ const struct address_space_operations squashfs_symlink_aops = { const struct inode_operations squashfs_symlink_inode_ops = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getxattr = generic_getxattr, .listxattr = squashfs_listxattr }; diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index 6a4cc344085c..1e9de96288d8 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -58,7 +58,7 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer, struct squashfs_xattr_entry entry; struct squashfs_xattr_val val; const struct xattr_handler *handler; - int name_size, prefix_size = 0; + int name_size; err = squashfs_read_metadata(sb, &entry, &start, &offset, sizeof(entry)); @@ -67,15 +67,16 @@ ssize_t squashfs_listxattr(struct dentry *d, char *buffer, name_size = le16_to_cpu(entry.size); handler = squashfs_xattr_handler(le16_to_cpu(entry.type)); - if (handler) - prefix_size = handler->list(handler, d, buffer, rest, - NULL, name_size); - if (prefix_size) { + if (handler && (!handler->list || handler->list(d))) { + const char *prefix = handler->prefix ?: handler->name; + size_t prefix_size = strlen(prefix); + if (buffer) { if (prefix_size + name_size + 1 > rest) { err = -ERANGE; goto failed; } + memcpy(buffer, prefix, prefix_size); buffer += prefix_size; } err = squashfs_read_metadata(sb, buffer, &start, @@ -212,25 +213,10 @@ failed: } -static size_t squashfs_xattr_handler_list(const struct xattr_handler *handler, - struct dentry *d, char *list, - size_t list_size, const char *name, - size_t name_len) -{ - int len = strlen(handler->prefix); - - if (list && len <= list_size) - memcpy(list, handler->prefix, len); - return len; -} - static int squashfs_xattr_handler_get(const struct xattr_handler *handler, struct dentry *d, const char *name, void *buffer, size_t size) { - if (name[0] == '\0') - return -EINVAL; - return squashfs_xattr_get(d_inode(d), handler->flags, name, buffer, size); } @@ -241,22 +227,15 @@ static int squashfs_xattr_handler_get(const struct xattr_handler *handler, static const struct xattr_handler squashfs_xattr_user_handler = { .prefix = XATTR_USER_PREFIX, .flags = SQUASHFS_XATTR_USER, - .list = squashfs_xattr_handler_list, .get = squashfs_xattr_handler_get }; /* * Trusted namespace support */ -static size_t squashfs_trusted_xattr_handler_list(const struct xattr_handler *handler, - struct dentry *d, char *list, - size_t list_size, const char *name, - size_t name_len) +static bool squashfs_trusted_xattr_handler_list(struct dentry *d) { - if (!capable(CAP_SYS_ADMIN)) - return 0; - return squashfs_xattr_handler_list(handler, d, list, list_size, name, - name_len); + return capable(CAP_SYS_ADMIN); } static const struct xattr_handler squashfs_xattr_trusted_handler = { @@ -272,7 +251,6 @@ static const struct xattr_handler squashfs_xattr_trusted_handler = { static const struct xattr_handler squashfs_xattr_security_handler = { .prefix = XATTR_SECURITY_PREFIX, .flags = SQUASHFS_XATTR_SECURITY, - .list = squashfs_xattr_handler_list, .get = squashfs_xattr_handler_get }; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 02fa1dcc5969..07ac18c355e7 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -146,8 +146,7 @@ static inline void write3byte(struct sysv_sb_info *sbi, static const struct inode_operations sysv_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, + .get_link = page_get_link, .getattr = sysv_getattr, }; @@ -163,6 +162,7 @@ void sysv_set_inode(struct inode *inode, dev_t rdev) inode->i_mapping->a_ops = &sysv_aops; } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &sysv_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &sysv_aops; } else init_special_inode(inode, inode->i_mode, rdev); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 0edc12856147..eff62801acbf 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1608,7 +1608,7 @@ const struct inode_operations ubifs_file_inode_operations = { const struct inode_operations ubifs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, .setattr = ubifs_setattr, .getattr = ubifs_getattr, .setxattr = ubifs_setxattr, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 8d0b3ade0ff0..055746350d16 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1540,7 +1540,8 @@ reread: break; case ICBTAG_FILE_TYPE_SYMLINK: inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &udf_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; break; case ICBTAG_FILE_TYPE_MAIN: diff --git a/fs/udf/namei.c b/fs/udf/namei.c index c97b5a8d1e24..42eafb91f7ff 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -921,7 +921,8 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry, } inode->i_data.a_ops = &udf_symlink_aops; - inode->i_op = &udf_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { struct kernel_lb_addr eloc; @@ -1344,8 +1345,3 @@ const struct inode_operations udf_dir_inode_operations = { .rename = udf_rename, .tmpfile = udf_tmpfile, }; -const struct inode_operations udf_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, -}; diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c index 862535b3ba58..8d619773056b 100644 --- a/fs/udf/symlink.c +++ b/fs/udf/symlink.c @@ -107,7 +107,7 @@ static int udf_symlink_filler(struct file *file, struct page *page) struct buffer_head *bh = NULL; unsigned char *symlink; int err; - unsigned char *p = kmap(page); + unsigned char *p = page_address(page); struct udf_inode_info *iinfo; uint32_t pos; @@ -141,7 +141,6 @@ static int udf_symlink_filler(struct file *file, struct page *page) up_read(&iinfo->i_data_sem); SetPageUptodate(page); - kunmap(page); unlock_page(page); return 0; @@ -149,7 +148,6 @@ out_unlock_inode: up_read(&iinfo->i_data_sem); SetPageError(page); out_unmap: - kunmap(page); unlock_page(page); return err; } diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 47bb3f5ca360..ce169b49429d 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -85,7 +85,6 @@ extern const struct inode_operations udf_dir_inode_operations; extern const struct file_operations udf_dir_operations; extern const struct inode_operations udf_file_inode_operations; extern const struct file_operations udf_file_operations; -extern const struct inode_operations udf_symlink_inode_operations; extern const struct address_space_operations udf_aops; extern const struct address_space_operations udf_adinicb_aops; extern const struct address_space_operations udf_symlink_aops; diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile index 392db25c0b56..ec4a6b49fa13 100644 --- a/fs/ufs/Makefile +++ b/fs/ufs/Makefile @@ -5,5 +5,5 @@ obj-$(CONFIG_UFS_FS) += ufs.o ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \ - namei.o super.o symlink.o util.o + namei.o super.o util.o ccflags-$(CONFIG_UFS_DEBUG) += -DDEBUG diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index a064cf44b143..d897e169ab9c 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -528,11 +528,12 @@ static void ufs_set_inode_ops(struct inode *inode) inode->i_mapping->a_ops = &ufs_aops; } else if (S_ISLNK(inode->i_mode)) { if (!inode->i_blocks) { - inode->i_op = &ufs_fast_symlink_inode_operations; inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink; + inode->i_op = &simple_symlink_inode_operations; } else { - inode->i_op = &ufs_symlink_inode_operations; inode->i_mapping->a_ops = &ufs_aops; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); } } else init_special_inode(inode, inode->i_mode, diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 47966554317c..acf4a3b61b81 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -123,14 +123,15 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry, if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) { /* slow symlink */ - inode->i_op = &ufs_symlink_inode_operations; + inode->i_op = &page_symlink_inode_operations; + inode_nohighmem(inode); inode->i_mapping->a_ops = &ufs_aops; err = page_symlink(inode, symname, l); if (err) goto out_fail; } else { /* fast symlink */ - inode->i_op = &ufs_fast_symlink_inode_operations; + inode->i_op = &simple_symlink_inode_operations; inode->i_link = (char *)UFS_I(inode)->i_u1.i_symlink; memcpy(inode->i_link, symname, l); inode->i_size = l-1; diff --git a/fs/ufs/symlink.c b/fs/ufs/symlink.c deleted file mode 100644 index 874480bb43e9..000000000000 --- a/fs/ufs/symlink.c +++ /dev/null @@ -1,42 +0,0 @@ -/* - * linux/fs/ufs/symlink.c - * - * Only fast symlinks left here - the rest is done by generic code. AV, 1999 - * - * Copyright (C) 1998 - * Daniel Pirkl <daniel.pirkl@emai.cz> - * Charles University, Faculty of Mathematics and Physics - * - * from - * - * linux/fs/ext2/symlink.c - * - * Copyright (C) 1992, 1993, 1994, 1995 - * Remy Card (card@masi.ibp.fr) - * Laboratoire MASI - Institut Blaise Pascal - * Universite Pierre et Marie Curie (Paris VI) - * - * from - * - * linux/fs/minix/symlink.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * ext2 symlink handling code - */ - -#include "ufs_fs.h" -#include "ufs.h" - -const struct inode_operations ufs_fast_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = simple_follow_link, - .setattr = ufs_setattr, -}; - -const struct inode_operations ufs_symlink_inode_operations = { - .readlink = generic_readlink, - .follow_link = page_follow_link_light, - .put_link = page_put_link, - .setattr = ufs_setattr, -}; diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h index 7da4aca868c0..c87f4c3fa9dd 100644 --- a/fs/ufs/ufs.h +++ b/fs/ufs/ufs.h @@ -136,10 +136,6 @@ extern __printf(3, 4) void ufs_panic(struct super_block *, const char *, const char *, ...); void ufs_mark_sb_dirty(struct super_block *sb); -/* symlink.c */ -extern const struct inode_operations ufs_fast_symlink_inode_operations; -extern const struct inode_operations ufs_symlink_inode_operations; - static inline struct ufs_sb_info *UFS_SB(struct super_block *sb) { return sb->s_fs_info; diff --git a/fs/xattr.c b/fs/xattr.c index 9b932b95d74e..d7f5037a17b5 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -208,25 +208,6 @@ vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, return error; } -/* Compare an extended attribute value with the given value */ -int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, - const char *value, size_t size, gfp_t flags) -{ - char *xattr_value = NULL; - int rc; - - rc = vfs_getxattr_alloc(dentry, xattr_name, &xattr_value, 0, flags); - if (rc < 0) - return rc; - - if ((rc != size) || (memcmp(xattr_value, value, rc) != 0)) - rc = -EINVAL; - else - rc = 0; - kfree(xattr_value); - return rc; -} - ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { @@ -700,13 +681,20 @@ xattr_resolve_name(const struct xattr_handler **handlers, const char **name) return NULL; for_each_xattr_handler(handlers, handler) { - const char *n = strcmp_prefix(*name, handler->prefix); + const char *n; + + n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { + if (!handler->prefix ^ !*n) { + if (*n) + continue; + return ERR_PTR(-EINVAL); + } *name = n; - break; + return handler; } } - return handler; + return ERR_PTR(-EOPNOTSUPP); } /* @@ -718,8 +706,8 @@ generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t s const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; + if (IS_ERR(handler)) + return PTR_ERR(handler); return handler->get(handler, dentry, name, buffer, size); } @@ -735,19 +723,25 @@ generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!buffer) { for_each_xattr_handler(handlers, handler) { - size += handler->list(handler, dentry, NULL, 0, - NULL, 0); + if (!handler->name || + (handler->list && !handler->list(dentry))) + continue; + size += strlen(handler->name) + 1; } } else { char *buf = buffer; + size_t len; for_each_xattr_handler(handlers, handler) { - size = handler->list(handler, dentry, buf, buffer_size, - NULL, 0); - if (size > buffer_size) + if (!handler->name || + (handler->list && !handler->list(dentry))) + continue; + len = strlen(handler->name); + if (len + 1 > buffer_size) return -ERANGE; - buf += size; - buffer_size -= size; + memcpy(buf, handler->name, len + 1); + buf += len + 1; + buffer_size -= len + 1; } size = buf - buffer; } @@ -765,8 +759,8 @@ generic_setxattr(struct dentry *dentry, const char *name, const void *value, siz if (size == 0) value = ""; /* empty EA, do not remove */ handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; + if (IS_ERR(handler)) + return PTR_ERR(handler); return handler->set(handler, dentry, name, value, size, flags); } @@ -780,8 +774,8 @@ generic_removexattr(struct dentry *dentry, const char *name) const struct xattr_handler *handler; handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name); - if (!handler) - return -EOPNOTSUPP; + if (IS_ERR(handler)) + return PTR_ERR(handler); return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE); } @@ -808,7 +802,7 @@ EXPORT_SYMBOL(generic_removexattr); const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { - size_t prefix_len = strlen(handler->prefix); + size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } @@ -863,8 +857,22 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, return ret; } -static int __simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags) +/** + * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems + * @xattrs: target simple_xattr list + * @name: name of the extended attribute + * @value: value of the xattr. If %NULL, will remove the attribute. + * @size: size of the new xattr + * @flags: %XATTR_{CREATE|REPLACE} + * + * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails + * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; + * otherwise, fails with -ENODATA. + * + * Returns 0 on success, -errno on failure. + */ +int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, + const void *value, size_t size, int flags) { struct simple_xattr *xattr; struct simple_xattr *new_xattr = NULL; @@ -914,73 +922,64 @@ out: } -/** - * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems - * @xattrs: target simple_xattr list - * @name: name of the new extended attribute - * @value: value of the new xattr. If %NULL, will remove the attribute - * @size: size of the new xattr - * @flags: %XATTR_{CREATE|REPLACE} - * - * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails - * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; - * otherwise, fails with -ENODATA. - * - * Returns 0 on success, -errno on failure. - */ -int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, - const void *value, size_t size, int flags) -{ - if (size == 0) - value = ""; /* empty EA, do not remove */ - return __simple_xattr_set(xattrs, name, value, size, flags); -} - -/* - * xattr REMOVE operation for in-memory/pseudo filesystems - */ -int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name) +static bool xattr_is_trusted(const char *name) { - return __simple_xattr_set(xattrs, name, NULL, 0, XATTR_REPLACE); + return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } -static bool xattr_is_trusted(const char *name) +static int xattr_list_one(char **buffer, ssize_t *remaining_size, + const char *name) { - return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); + size_t len = strlen(name) + 1; + if (*buffer) { + if (*remaining_size < len) + return -ERANGE; + memcpy(*buffer, name, len); + *buffer += len; + } + *remaining_size -= len; + return 0; } /* * xattr LIST operation for in-memory/pseudo filesystems */ -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, - size_t size) +ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, + char *buffer, size_t size) { bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; - size_t used = 0; + ssize_t remaining_size = size; + int err; + +#ifdef CONFIG_FS_POSIX_ACL + if (inode->i_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_ACCESS); + if (err) + return err; + } + if (inode->i_default_acl) { + err = xattr_list_one(&buffer, &remaining_size, + XATTR_NAME_POSIX_ACL_DEFAULT); + if (err) + return err; + } +#endif spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { - size_t len; - /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; - len = strlen(xattr->name) + 1; - used += len; - if (buffer) { - if (size < used) { - used = -ERANGE; - break; - } - memcpy(buffer, xattr->name, len); - buffer += len; - } + err = xattr_list_one(&buffer, &remaining_size, xattr->name); + if (err) + return err; } spin_unlock(&xattrs->lock); - return used; + return size - remaining_size; } /* diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 6bb470fbb8e8..2d5df1f23bbc 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -252,29 +252,6 @@ xfs_set_mode(struct inode *inode, umode_t mode) return error; } -static int -xfs_acl_exists(struct inode *inode, unsigned char *name) -{ - int len = XFS_ACL_MAX_SIZE(XFS_M(inode->i_sb)); - - return (xfs_attr_get(XFS_I(inode), name, NULL, &len, - ATTR_ROOT|ATTR_KERNOVAL) == 0); -} - -int -posix_acl_access_exists(struct inode *inode) -{ - return xfs_acl_exists(inode, SGI_ACL_FILE); -} - -int -posix_acl_default_exists(struct inode *inode) -{ - if (!S_ISDIR(inode->i_mode)) - return 0; - return xfs_acl_exists(inode, SGI_ACL_DEFAULT); -} - int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 52f8255d6bdf..286fa89217f5 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -24,16 +24,12 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); -extern int posix_acl_access_exists(struct inode *inode); -extern int posix_acl_default_exists(struct inode *inode); #else static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) { return NULL; } # define xfs_set_acl NULL -# define posix_acl_access_exists(inode) 0 -# define posix_acl_default_exists(inode) 0 #endif /* CONFIG_XFS_POSIX_ACL */ extern void xfs_forget_acl(struct inode *inode, const char *name, int xflags); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 245268a0cdf0..06eafafe636e 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -414,13 +414,17 @@ xfs_vn_rename( * uio is kmalloced for this reason... */ STATIC const char * -xfs_vn_follow_link( +xfs_vn_get_link( struct dentry *dentry, - void **cookie) + struct inode *inode, + struct delayed_call *done) { char *link; int error = -ENOMEM; + if (!dentry) + return ERR_PTR(-ECHILD); + link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); if (!link) goto out_err; @@ -429,7 +433,8 @@ xfs_vn_follow_link( if (unlikely(error)) goto out_kfree; - return *cookie = link; + set_delayed_call(done, kfree_link, link); + return link; out_kfree: kfree(link); @@ -1172,8 +1177,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = { static const struct inode_operations xfs_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = xfs_vn_follow_link, - .put_link = kfree_put_link, + .get_link = xfs_vn_get_link, .getattr = xfs_vn_getattr, .setattr = xfs_vn_setattr, .setxattr = generic_setxattr, diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 839b35ca21c6..110f1d7d86b0 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -39,9 +39,6 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error, asize = size; - if (strcmp(name, "") == 0) - return -EINVAL; - /* Convert Linux syscall to XFS internal ATTR flags */ if (!size) { xflags |= ATTR_KERNOVAL; @@ -84,9 +81,6 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct xfs_inode *ip = XFS_I(d_inode(dentry)); int error; - if (strcmp(name, "") == 0) - return -EINVAL; - /* Convert Linux syscall to XFS internal ATTR flags */ if (flags & XATTR_CREATE) xflags |= ATTR_CREATE; @@ -135,47 +129,19 @@ const struct xattr_handler *xfs_xattr_handlers[] = { NULL }; -static unsigned int xfs_xattr_prefix_len(int flags) -{ - if (flags & XFS_ATTR_SECURE) - return sizeof("security"); - else if (flags & XFS_ATTR_ROOT) - return sizeof("trusted"); - else - return sizeof("user"); -} - -static const char *xfs_xattr_prefix(int flags) -{ - if (flags & XFS_ATTR_SECURE) - return xfs_xattr_security_handler.prefix; - else if (flags & XFS_ATTR_ROOT) - return xfs_xattr_trusted_handler.prefix; - else - return xfs_xattr_user_handler.prefix; -} - static int -xfs_xattr_put_listent( +__xfs_xattr_put_listent( struct xfs_attr_list_context *context, - int flags, - unsigned char *name, - int namelen, - int valuelen, - unsigned char *value) + char *prefix, + int prefix_len, + unsigned char *name, + int namelen) { - unsigned int prefix_len = xfs_xattr_prefix_len(flags); char *offset; int arraytop; - ASSERT(context->count >= 0); - - /* - * Only show root namespace entries if we are actually allowed to - * see them. - */ - if ((flags & XFS_ATTR_ROOT) && !capable(CAP_SYS_ADMIN)) - return 0; + if (!context->alist) + goto compute_size; arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { @@ -183,17 +149,19 @@ xfs_xattr_put_listent( return 1; } offset = (char *)context->alist + context->count; - strncpy(offset, xfs_xattr_prefix(flags), prefix_len); + strncpy(offset, prefix, prefix_len); offset += prefix_len; strncpy(offset, (char *)name, namelen); /* real name */ offset += namelen; *offset = '\0'; + +compute_size: context->count += prefix_len + namelen + 1; return 0; } static int -xfs_xattr_put_listent_sizes( +xfs_xattr_put_listent( struct xfs_attr_list_context *context, int flags, unsigned char *name, @@ -201,24 +169,55 @@ xfs_xattr_put_listent_sizes( int valuelen, unsigned char *value) { - context->count += xfs_xattr_prefix_len(flags) + namelen + 1; - return 0; -} + char *prefix; + int prefix_len; -static int -list_one_attr(const char *name, const size_t len, void *data, - size_t size, ssize_t *result) -{ - char *p = data + *result; + ASSERT(context->count >= 0); - *result += len; - if (!size) - return 0; - if (*result > size) - return -ERANGE; + if (flags & XFS_ATTR_ROOT) { +#ifdef CONFIG_XFS_POSIX_ACL + if (namelen == SGI_ACL_FILE_SIZE && + strncmp(name, SGI_ACL_FILE, + SGI_ACL_FILE_SIZE) == 0) { + int ret = __xfs_xattr_put_listent( + context, XATTR_SYSTEM_PREFIX, + XATTR_SYSTEM_PREFIX_LEN, + XATTR_POSIX_ACL_ACCESS, + strlen(XATTR_POSIX_ACL_ACCESS)); + if (ret) + return ret; + } else if (namelen == SGI_ACL_DEFAULT_SIZE && + strncmp(name, SGI_ACL_DEFAULT, + SGI_ACL_DEFAULT_SIZE) == 0) { + int ret = __xfs_xattr_put_listent( + context, XATTR_SYSTEM_PREFIX, + XATTR_SYSTEM_PREFIX_LEN, + XATTR_POSIX_ACL_DEFAULT, + strlen(XATTR_POSIX_ACL_DEFAULT)); + if (ret) + return ret; + } +#endif - strcpy(p, name); - return 0; + /* + * Only show root namespace entries if we are actually allowed to + * see them. + */ + if (!capable(CAP_SYS_ADMIN)) + return 0; + + prefix = XATTR_TRUSTED_PREFIX; + prefix_len = XATTR_TRUSTED_PREFIX_LEN; + } else if (flags & XFS_ATTR_SECURE) { + prefix = XATTR_SECURITY_PREFIX; + prefix_len = XATTR_SECURITY_PREFIX_LEN; + } else { + prefix = XATTR_USER_PREFIX; + prefix_len = XATTR_USER_PREFIX_LEN; + } + + return __xfs_xattr_put_listent(context, prefix, prefix_len, name, + namelen); } ssize_t @@ -227,7 +226,6 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) struct xfs_attr_list_context context; struct attrlist_cursor_kern cursor = { 0 }; struct inode *inode = d_inode(dentry); - int error; /* * First read the regular on-disk attributes. @@ -236,37 +234,14 @@ xfs_vn_listxattr(struct dentry *dentry, char *data, size_t size) context.dp = XFS_I(inode); context.cursor = &cursor; context.resynch = 1; - context.alist = data; + context.alist = size ? data : NULL; context.bufsize = size; context.firstu = context.bufsize; - - if (size) - context.put_listent = xfs_xattr_put_listent; - else - context.put_listent = xfs_xattr_put_listent_sizes; + context.put_listent = xfs_xattr_put_listent; xfs_attr_list_int(&context); if (context.count < 0) return -ERANGE; - /* - * Then add the two synthetic ACL attributes. - */ - if (posix_acl_access_exists(inode)) { - error = list_one_attr(POSIX_ACL_XATTR_ACCESS, - strlen(POSIX_ACL_XATTR_ACCESS) + 1, - data, size, &context.count); - if (error) - return error; - } - - if (posix_acl_default_exists(inode)) { - error = list_one_attr(POSIX_ACL_XATTR_DEFAULT, - strlen(POSIX_ACL_XATTR_DEFAULT) + 1, - data, size, &context.count); - if (error) - return error; - } - return context.count; } diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index b42afada1280..0f45f93ef692 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -93,7 +93,7 @@ #endif /* CONFIG_SMP */ #ifndef smp_store_mb -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #endif #ifndef smp_mb__before_atomic diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index e2aadbc7151f..39e1cb201b8e 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -12,8 +12,9 @@ * GNU General Public License for more details. * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. + * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * - * Authors: Waiman Long <waiman.long@hp.com> + * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H @@ -62,7 +63,7 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) static __always_inline int queued_spin_trylock(struct qspinlock *lock) { if (!atomic_read(&lock->val) && - (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0)) + (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0)) return 1; return 0; } @@ -77,7 +78,7 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock) { u32 val; - val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL); + val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL); if (likely(val == 0)) return; queued_spin_lock_slowpath(lock, val); @@ -93,7 +94,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock) /* * smp_mb__before_atomic() in order to guarantee release semantics */ - smp_mb__before_atomic_dec(); + smp_mb__before_atomic(); atomic_sub(_Q_LOCKED_VAL, &lock->val); } #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0169ba2e2e64..c70e3588a48c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -797,6 +797,7 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int blk_queue_enter(struct request_queue *q, gfp_t gfp); extern void blk_queue_exit(struct request_queue *q); extern void blk_start_queue(struct request_queue *q); +extern void blk_start_queue_async(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac1036594f..00b042c49ccd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -299,6 +299,23 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __u.__val; \ }) +/** + * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering + * @cond: boolean expression to wait for + * + * Equivalent to using smp_load_acquire() on the condition variable but employs + * the control dependency of the wait to reduce the barrier on many platforms. + * + * The control dependency provides a LOAD->STORE order, the additional RMB + * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, + * aka. ACQUIRE. + */ +#define smp_cond_acquire(cond) do { \ + while (!(cond)) \ + cpu_relax(); \ + smp_rmb(); /* ctrl + rmb := acquire */ \ +} while (0) + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 68b575afe5f5..d259274238db 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -86,7 +86,7 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static inline void guest_enter(void) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -100,7 +100,7 @@ static inline void guest_exit(void) if (context_tracking_is_enabled()) __context_tracking_exit(CONTEXT_GUEST); - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index ee956c528fab..1d34fe68f48a 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -22,12 +22,12 @@ struct context_tracking { }; #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key context_tracking_enabled; +extern struct static_key_false context_tracking_enabled; DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_is_enabled(void) { - return static_key_false(&context_tracking_enabled); + return static_branch_unlikely(&context_tracking_enabled); } static inline bool context_tracking_cpu_is_enabled(void) diff --git a/include/linux/delayed_call.h b/include/linux/delayed_call.h new file mode 100644 index 000000000000..f7fa76ae1a9b --- /dev/null +++ b/include/linux/delayed_call.h @@ -0,0 +1,34 @@ +#ifndef _DELAYED_CALL_H +#define _DELAYED_CALL_H + +/* + * Poor man's closures; I wish we could've done them sanely polymorphic, + * but... + */ + +struct delayed_call { + void (*fn)(void *); + void *arg; +}; + +#define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} + +/* I really wish we had closures with sane typechecking... */ +static inline void set_delayed_call(struct delayed_call *call, + void (*fn)(void *), void *arg) +{ + call->fn = fn; + call->arg = arg; +} + +static inline void do_delayed_call(struct delayed_call *call) +{ + if (call->fn) + call->fn(call->arg); +} + +static inline void clear_delayed_call(struct delayed_call *call) +{ + call->fn = NULL; +} +#endif diff --git a/include/linux/filter.h b/include/linux/filter.h index 4165e9ac9e36..5972ffe5719a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -493,6 +493,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp) #define BPF_ANC BIT(15) +static inline bool bpf_needs_clear_a(const struct sock_filter *first) +{ + switch (first->code) { + case BPF_RET | BPF_K: + case BPF_LD | BPF_W | BPF_LEN: + return false; + + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) + return true; + return false; + + default: + return true; + } +} + static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..ef3cd36689f6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -31,6 +31,7 @@ #include <linux/blk_types.h> #include <linux/workqueue.h> #include <linux/percpu-rwsem.h> +#include <linux/delayed_call.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -1633,12 +1634,11 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - const char * (*follow_link) (struct dentry *, void **); + const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - void (*put_link) (struct inode *, void *); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); @@ -2736,14 +2736,14 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern const char *page_follow_link_light(struct dentry *, void **); -extern void page_put_link(struct inode *, void *); +extern const char *page_get_link(struct dentry *, struct inode *, + struct delayed_call *); +extern void page_put_link(void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; -extern void kfree_put_link(struct inode *, void *); -extern void free_page_put_link(struct inode *, void *); +extern void kfree_link(void *); extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); @@ -2754,7 +2754,8 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); -const char *simple_follow_link(struct dentry *, void **); +const char *simple_get_link(struct dentry *, struct inode *, + struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); @@ -2764,8 +2765,6 @@ extern int vfs_lstat(const char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); extern int vfs_fstatat(int , const char __user *, struct kstat *, int); -extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, - unsigned long arg); extern int __generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, @@ -3025,5 +3024,6 @@ static inline bool dir_relax(struct inode *inode) } extern bool path_noexec(const struct path *path); +extern void inode_nohighmem(struct inode *inode); #endif /* _LINUX_FS_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eae6548efbf0..60048c50404e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -586,6 +586,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1c1ff7e4faa4..f2cb8d45513d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -150,7 +150,7 @@ extern struct task_group root_task_group; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ + .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ .vtime_snap = 0, \ .vtime_snap_whence = VTIME_SYS, #else diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 350dfb08aee3..7311c3294e25 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -255,6 +255,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; +void nmi_panic_self_stop(struct pt_regs *); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); @@ -446,6 +447,33 @@ extern int sysctl_panic_on_stackoverflow; extern bool crash_kexec_post_notifiers; /* + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It + * holds a CPU number which is executing panic() currently. A value of + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). + */ +extern atomic_t panic_cpu; +#define PANIC_CPU_INVALID -1 + +/* + * A variant of panic() called from NMI context. We return if we've already + * panicked on this CPU. If another CPU already panicked, loop in + * nmi_panic_self_stop() which can provide architecture dependent code such + * as saving register state for crash dump. + */ +#define nmi_panic(regs, fmt, ...) \ +do { \ + int old_cpu, cpu; \ + \ + cpu = raw_smp_processor_id(); \ + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \ + \ + if (old_cpu == PANIC_CPU_INVALID) \ + panic(fmt, ##__VA_ARGS__); \ + else if (old_cpu != cpu) \ + nmi_panic_self_stop(regs); \ +} while (0) + +/* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d140b1e9faa7..7b68d2788a56 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -237,6 +237,7 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image, unsigned int size, bool get_value); extern void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); +extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); @@ -332,6 +333,7 @@ int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; +static inline void __crash_kexec(struct pt_regs *regs) { } static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } #define kexec_in_progress false diff --git a/include/linux/list.h b/include/linux/list.h index 993395a2e55c..5356f4d661a7 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -24,7 +24,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { - list->next = list; + WRITE_ONCE(list->next, list); list->prev = list; } @@ -42,7 +42,7 @@ static inline void __list_add(struct list_head *new, next->prev = new; new->next = next; new->prev = prev; - prev->next = new; + WRITE_ONCE(prev->next, new); } #else extern void __list_add(struct list_head *new, @@ -186,7 +186,7 @@ static inline int list_is_last(const struct list_head *list, */ static inline int list_empty(const struct list_head *head) { - return head->next == head; + return READ_ONCE(head->next) == head; } /** @@ -608,7 +608,7 @@ static inline int hlist_unhashed(const struct hlist_node *h) static inline int hlist_empty(const struct hlist_head *h) { - return !h->first; + return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) @@ -642,7 +642,7 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) n->next = first; if (first) first->pprev = &n->next; - h->first = n; + WRITE_ONCE(h->first, n); n->pprev = &h->first; } @@ -653,14 +653,14 @@ static inline void hlist_add_before(struct hlist_node *n, n->pprev = next->pprev; n->next = next; next->pprev = &n->next; - *(n->pprev) = n; + WRITE_ONCE(*(n->pprev), n); } static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; - prev->next = n; + WRITE_ONCE(prev->next, n); n->pprev = &prev->next; if (n->next) diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 8132214e8efd..ee7229a6c06a 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -70,7 +70,7 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h, static inline int hlist_bl_empty(const struct hlist_bl_head *h) { - return !((unsigned long)h->first & ~LIST_BL_LOCKMASK); + return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 444d2b1313bd..b01fe1009084 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -57,7 +57,7 @@ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { - return is_a_nulls(h->first); + return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c8723b62c4cd..bc742dac7d3a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -25,7 +25,7 @@ #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST -#define SNOR_MFR_WINBOND 0xef +#define SNOR_MFR_WINBOND 0xef /* Also used by some Spansion */ /* * Note on opcode nomenclature: some opcodes have a format like diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c0e961474a52..37a3d2981352 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -359,6 +359,7 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); +extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 6f14ee295822..e5e8ec40278d 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -9,16 +9,12 @@ #ifndef _POSIX_ACL_XATTR_H #define _POSIX_ACL_XATTR_H +#include <uapi/linux/xattr.h> #include <linux/posix_acl.h> -/* Extended attribute names */ -#define POSIX_ACL_XATTR_ACCESS "system.posix_acl_access" -#define POSIX_ACL_XATTR_DEFAULT "system.posix_acl_default" - /* Supported ACL a_version fields */ #define POSIX_ACL_XATTR_VERSION 0x0002 - /* An undefined entry e_id value */ #define ACL_UNDEFINED_ID (-1) diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 5ed540986019..14ec1652daf4 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -179,32 +179,31 @@ static inline void list_replace_rcu(struct list_head *old, } /** - * list_splice_init_rcu - splice an RCU-protected list into an existing list. + * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice - * @head: the place in the list to splice the first list into + * @prev: points to the last element of the existing list + * @next: points to the first element of the existing list * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... * - * @head can be RCU-read traversed concurrently with this function. + * The list pointed to by @prev and @next can be RCU-read traversed + * concurrently with this function. * * Note that this function blocks. * - * Important note: the caller must take whatever action is necessary to - * prevent any other updates to @head. In principle, it is possible - * to modify the list as soon as sync() begins execution. - * If this sort of thing becomes necessary, an alternative version - * based on call_rcu() could be created. But only if -really- - * needed -- there is no shortage of RCU API members. + * Important note: the caller must take whatever action is necessary to prevent + * any other updates to the existing list. In principle, it is possible to + * modify the list as soon as sync() begins execution. If this sort of thing + * becomes necessary, an alternative version based on call_rcu() could be + * created. But only if -really- needed -- there is no shortage of RCU API + * members. */ -static inline void list_splice_init_rcu(struct list_head *list, - struct list_head *head, - void (*sync)(void)) +static inline void __list_splice_init_rcu(struct list_head *list, + struct list_head *prev, + struct list_head *next, + void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; - struct list_head *at = head->next; - - if (list_empty(list)) - return; /* * "first" and "last" tracking list, so initialize it. RCU readers @@ -231,10 +230,40 @@ static inline void list_splice_init_rcu(struct list_head *list, * this function. */ - last->next = at; - rcu_assign_pointer(list_next_rcu(head), first); - first->prev = head; - at->prev = last; + last->next = next; + rcu_assign_pointer(list_next_rcu(prev), first); + first->prev = prev; + next->prev = last; +} + +/** + * list_splice_init_rcu - splice an RCU-protected list into an existing list, + * designed for stacks. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head, head->next, sync); +} + +/** + * list_splice_tail_init_rcu - splice an RCU-protected list into an existing + * list, designed for queues. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_tail_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head->prev, head, sync); } /** @@ -305,6 +334,42 @@ static inline void list_splice_init_rcu(struct list_head *list, pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** + * list_entry_lockless - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_entry_lockless(ptr, type, member) \ + container_of((typeof(ptr))lockless_dereference(ptr), type, member) + +/** + * list_for_each_entry_lockless - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_for_each_entry_lockless(pos, head, member) \ + for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) + +/** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a0189ba67fde..14e6f47ee16f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -48,10 +48,17 @@ #include <asm/barrier.h> +#ifndef CONFIG_TINY_RCU extern int rcu_expedited; /* for sysctl */ +extern int rcu_normal; /* also for sysctl */ +#endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_TINY_RCU /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ +static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ +{ + return true; +} static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ { return false; @@ -65,6 +72,7 @@ static inline void rcu_unexpedite_gp(void) { } #else /* #ifdef CONFIG_TINY_RCU */ +bool rcu_gp_is_normal(void); /* Internal RCU use. */ bool rcu_gp_is_expedited(void); /* Internal RCU use. */ void rcu_expedite_gp(void); void rcu_unexpedite_gp(void); @@ -321,7 +329,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -void rcu_end_inkernel_boot(void); void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); @@ -329,6 +336,12 @@ struct notifier_block; int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); +#ifndef CONFIG_TINY_RCU +void rcu_end_inkernel_boot(void); +#else /* #ifndef CONFIG_TINY_RCU */ +static inline void rcu_end_inkernel_boot(void) { } +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); @@ -379,9 +392,9 @@ static inline void rcu_init_nohz(void) */ #define RCU_NONIDLE(a) \ do { \ - rcu_irq_enter(); \ + rcu_irq_enter_irqson(); \ do { a; } while (0); \ - rcu_irq_exit(); \ + rcu_irq_exit_irqson(); \ } while (0) /* @@ -741,7 +754,7 @@ static inline void rcu_preempt_sleep_check(void) * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * - * The tracing version of rcu_dereference_raw() must not call + * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 4c1aaf9cce7b..64809aea661c 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -181,6 +181,14 @@ static inline void rcu_irq_enter(void) { } +static inline void rcu_irq_exit_irqson(void) +{ +} + +static inline void rcu_irq_enter_irqson(void) +{ +} + static inline void rcu_irq_exit(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 60d15a080d7c..ad1eda9fa4da 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,7 +37,7 @@ void rcu_cpu_stall_reset(void); /* * Note a virtualization-based context switch. This is simply a * wrapper around rcu_note_context_switch(), which allows TINY_RCU - * to save a few bytes. + * to save a few bytes. The caller must have disabled interrupts. */ static inline void rcu_virt_note_context_switch(int cpu) { @@ -97,6 +97,8 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_enter_irqson(void); +void rcu_irq_exit_irqson(void); void exit_rcu(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index edad7a43edea..0c0e78102850 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -177,9 +177,9 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void update_cpu_load_nohz(void); +extern void update_cpu_load_nohz(int active); #else -static inline void update_cpu_load_nohz(void) { } +static inline void update_cpu_load_nohz(int active) { } #endif extern unsigned long get_parent_ip(unsigned long addr); @@ -1268,8 +1268,13 @@ struct sched_entity { #endif #ifdef CONFIG_SMP - /* Per entity load average tracking */ - struct sched_avg avg; + /* + * Per entity load average tracking. + * + * Put into separate cache line so it does not + * collide with read-mostly values above. + */ + struct sched_avg avg ____cacheline_aligned_in_smp; #endif }; @@ -1455,14 +1460,15 @@ struct task_struct { /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; - unsigned in_execve:1; /* Tell the LSMs that the process is doing an - * execve */ - unsigned in_iowait:1; - - /* Revert to default priority/policy when forking */ + /* scheduler bits, serialized by scheduler locks */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned :0; /* force alignment to the next boundary */ + + /* unserialized, strictly 'current' */ + unsigned in_execve:1; /* bit to tell LSMs we're in execve */ + unsigned in_iowait:1; #ifdef CONFIG_MEMCG unsigned memcg_may_oom:1; #endif @@ -1519,11 +1525,14 @@ struct task_struct { cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_t vtime_seqlock; + seqcount_t vtime_seqcount; unsigned long long vtime_snap; enum { - VTIME_SLEEPING = 0, + /* Task is sleeping or running in a CPU with VTIME inactive */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active */ VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active */ VTIME_SYS, } vtime_snap_whence; #endif @@ -2002,7 +2011,8 @@ static inline int pid_alive(const struct task_struct *p) } /** - * is_global_init - check if a task structure is init + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. @@ -2011,7 +2021,7 @@ static inline int pid_alive(const struct task_struct *p) */ static inline int is_global_init(struct task_struct *tsk) { - return tsk->pid == 1; + return task_tgid_nr(tsk) == 1; } extern struct pid *cad_pid; diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 0e1b1540597a..3cc9632dcc2a 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -29,7 +29,7 @@ struct cpu_stop_work { int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg); -void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, +bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); @@ -65,7 +65,7 @@ static void stop_one_cpu_nowait_workfn(struct work_struct *work) preempt_enable(); } -static inline void stop_one_cpu_nowait(unsigned int cpu, +static inline bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { @@ -74,7 +74,10 @@ static inline void stop_one_cpu_nowait(unsigned int cpu, work_buf->fn = fn; work_buf->arg = arg; schedule_work(&work_buf->work); + return true; } + + return false; } static inline int stop_cpus(const struct cpumask *cpumask, diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h new file mode 100644 index 000000000000..e1ee97c713bf --- /dev/null +++ b/include/linux/tracepoint-defs.h @@ -0,0 +1,27 @@ +#ifndef TRACEPOINT_DEFS_H +#define TRACEPOINT_DEFS_H 1 + +/* + * File can be included directly by headers who only want to access + * tracepoint->key to guard out of line trace calls. Otherwise + * linux/tracepoint.h should be used. + */ + +#include <linux/atomic.h> +#include <linux/static_key.h> + +struct tracepoint_func { + void *func; + void *data; + int prio; +}; + +struct tracepoint { + const char *name; /* Tracepoint name */ + struct static_key key; + void (*regfunc)(void); + void (*unregfunc)(void); + struct tracepoint_func __rcu *funcs; +}; + +#endif diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..78e8397a1800 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -17,26 +17,12 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/rcupdate.h> -#include <linux/static_key.h> +#include <linux/tracepoint-defs.h> struct module; struct tracepoint; struct notifier_block; -struct tracepoint_func { - void *func; - void *data; - int prio; -}; - -struct tracepoint { - const char *name; /* Tracepoint name */ - struct static_key key; - void (*regfunc)(void); - void (*unregfunc)(void); - struct tracepoint_func __rcu *funcs; -}; - struct trace_enum_map { const char *system; const char *enum_string; @@ -171,8 +157,8 @@ extern void syscall_unregfunc(void); TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), \ - rcu_irq_enter(), \ - rcu_irq_exit()); \ + rcu_irq_enter_irqson(), \ + rcu_irq_exit_irqson()); \ } #else #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 1f6526c76ee8..3a375d07d0dc 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -138,6 +138,7 @@ struct cdc_ncm_ctx { }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); +int cdc_ncm_change_mtu(struct net_device *net, int new_mtu); int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 5dbc8b0ee567..3e5d9075960f 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -176,11 +176,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) #ifdef CONFIG_SMP -void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int); +void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); -void mod_zone_page_state(struct zone *, enum zone_stat_item, int); +void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); @@ -205,7 +205,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, - enum zone_stat_item item, int delta) + enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } diff --git a/include/linux/vtime.h b/include/linux/vtime.h index c5165fd256f9..fa2196990f84 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -10,16 +10,27 @@ struct task_struct; /* - * vtime_accounting_enabled() definitions/declarations + * vtime_accounting_cpu_enabled() definitions/declarations */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -static inline bool vtime_accounting_enabled(void) { return true; } +static inline bool vtime_accounting_cpu_enabled(void) { return true; } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +/* + * Checks if vtime is enabled on some CPU. Cputime readers want to be careful + * in that case and compute the tickless cputime. + * For now vtime state is tied to context tracking. We might want to decouple + * those later if necessary. + */ static inline bool vtime_accounting_enabled(void) { - if (context_tracking_is_enabled()) { + return context_tracking_is_enabled(); +} + +static inline bool vtime_accounting_cpu_enabled(void) +{ + if (vtime_accounting_enabled()) { if (context_tracking_cpu_is_enabled()) return true; } @@ -29,7 +40,7 @@ static inline bool vtime_accounting_enabled(void) #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ #ifndef CONFIG_VIRT_CPU_ACCOUNTING -static inline bool vtime_accounting_enabled(void) { return false; } +static inline bool vtime_accounting_cpu_enabled(void) { return false; } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -44,7 +55,7 @@ extern void vtime_task_switch(struct task_struct *prev); extern void vtime_common_task_switch(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_common_task_switch(prev); } #endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ @@ -59,7 +70,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk); extern void vtime_common_account_irq_enter(struct task_struct *tsk); static inline void vtime_account_irq_enter(struct task_struct *tsk) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_common_account_irq_enter(tsk); } #endif /* __ARCH_HAS_VTIME_ACCOUNT */ @@ -78,7 +89,7 @@ extern void vtime_gen_account_irq_exit(struct task_struct *tsk); static inline void vtime_account_irq_exit(struct task_struct *tsk) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_gen_account_irq_exit(tsk); } diff --git a/include/linux/wait.h b/include/linux/wait.h index 513b36f04dfd..d2f4ec7dba7c 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -102,6 +102,36 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) q->func = func; } +/** + * waitqueue_active -- locklessly test for waiters on the queue + * @q: the waitqueue to test for waiters + * + * returns true if the wait list is not empty + * + * NOTE: this function is lockless and requires care, incorrect usage _will_ + * lead to sporadic and non-obvious failure. + * + * Use either while holding wait_queue_head_t::lock or when used for wakeups + * with an extra smp_mb() like: + * + * CPU0 - waker CPU1 - waiter + * + * for (;;) { + * @cond = true; prepare_to_wait(&wq, &wait, state); + * smp_mb(); // smp_mb() from set_current_state() + * if (waitqueue_active(wq)) if (@cond) + * wake_up(wq); break; + * schedule(); + * } + * finish_wait(&wq, &wait); + * + * Because without the explicit smp_mb() it's possible for the + * waitqueue_active() load to get hoisted over the @cond store such that we'll + * observe an empty wait list while the waiter might not observe @cond. + * + * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), + * which (when the lock is uncontended) are of roughly equal cost. + */ static inline int waitqueue_active(wait_queue_head_t *q) { return !list_empty(&q->task_list); diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 89474b9d260c..4457541de3c9 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -19,12 +19,16 @@ struct inode; struct dentry; +/* + * struct xattr_handler: When @name is set, match attributes with exactly that + * name. When @prefix is set instead, match attributes with that prefix and + * with a non-empty suffix. + */ struct xattr_handler { + const char *name; const char *prefix; int flags; /* fs private flags */ - size_t (*list)(const struct xattr_handler *, struct dentry *dentry, - char *list, size_t list_size, const char *name, - size_t name_len); + bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, @@ -53,8 +57,11 @@ int generic_setxattr(struct dentry *dentry, const char *name, const void *value, int generic_removexattr(struct dentry *dentry, const char *name); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); -int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, - const char *value, size_t size, gfp_t flags); + +static inline const char *xattr_prefix(const struct xattr_handler *handler) +{ + return handler->prefix ?: handler->name; +} struct simple_xattrs { struct list_head head; @@ -95,8 +102,7 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags); -int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name); -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, +ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 774d85b2d5d9..5689a0c749f7 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -29,7 +29,7 @@ struct l3mdev_ops { /* IPv4 ops */ struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, const struct flowi4 *fl4); - void (*l3mdev_get_saddr)(struct net_device *dev, + int (*l3mdev_get_saddr)(struct net_device *dev, struct flowi4 *fl4); /* IPv6 ops */ @@ -112,10 +112,11 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return rc; } -static inline void l3mdev_get_saddr(struct net *net, int ifindex, - struct flowi4 *fl4) +static inline int l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) { struct net_device *dev; + int rc = 0; if (ifindex) { @@ -124,11 +125,13 @@ static inline void l3mdev_get_saddr(struct net *net, int ifindex, dev = dev_get_by_index_rcu(net, ifindex); if (dev && netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_saddr) { - dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); + rc = dev->l3mdev_ops->l3mdev_get_saddr(dev, fl4); } rcu_read_unlock(); } + + return rc; } static inline struct dst_entry *l3mdev_get_rt6_dst(const struct net_device *dev, @@ -200,9 +203,10 @@ static inline bool netif_index_is_l3_master(struct net *net, int ifindex) return false; } -static inline void l3mdev_get_saddr(struct net *net, int ifindex, - struct flowi4 *fl4) +static inline int l3mdev_get_saddr(struct net *net, int ifindex, + struct flowi4 *fl4) { + return 0; } static inline diff --git a/include/net/route.h b/include/net/route.h index ee81307863d5..a3b9ef74a389 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -283,7 +283,12 @@ static inline struct rtable *ip_route_connect(struct flowi4 *fl4, sport, dport, sk); if (!src && oif) { - l3mdev_get_saddr(net, oif, fl4); + int rc; + + rc = l3mdev_get_saddr(net, oif, fl4); + if (rc < 0) + return ERR_PTR(rc); + src = fl4->saddr; } if (!dst || !src) { diff --git a/include/sound/soc.h b/include/sound/soc.h index a8b4b9c8b1d2..fb955e69a78e 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1655,7 +1655,7 @@ extern const struct dev_pm_ops snd_soc_pm_ops; /* Helper functions */ static inline void snd_soc_dapm_mutex_lock(struct snd_soc_dapm_context *dapm) { - mutex_lock(&dapm->card->dapm_mutex); + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); } static inline void snd_soc_dapm_mutex_unlock(struct snd_soc_dapm_context *dapm) diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index d801bb0d9f6d..1afe9623c1a7 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -171,6 +171,9 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ + PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */ + PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -192,6 +195,9 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; diff --git a/init/main.c b/init/main.c index 9e64d7097f1a..c6ebefafa496 100644 --- a/init/main.c +++ b/init/main.c @@ -943,6 +943,8 @@ static int __ref kernel_init(void *unused) flush_delayed_fput(); + rcu_end_inkernel_boot(); + if (ramdisk_execute_command) { ret = run_init_process(ramdisk_execute_command); if (!ret) diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index d8560ee3bab7..9ad37b9e44a7 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -24,7 +24,7 @@ #define CREATE_TRACE_POINTS #include <trace/events/context_tracking.h> -struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE; +DEFINE_STATIC_KEY_FALSE(context_tracking_enabled); EXPORT_SYMBOL_GPL(context_tracking_enabled); DEFINE_PER_CPU(struct context_tracking, context_tracking); @@ -191,7 +191,7 @@ void __init context_tracking_cpu_set(int cpu) if (!per_cpu(context_tracking.active, cpu)) { per_cpu(context_tracking.active, cpu) = true; - static_key_slow_inc(&context_tracking_enabled); + static_branch_inc(&context_tracking_enabled); } if (initialized) diff --git a/kernel/events/core.c b/kernel/events/core.c index ef2d6ea10736..bf8244190d0f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -126,6 +126,37 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info) return data.ret; } +static void event_function_call(struct perf_event *event, + int (*active)(void *), + void (*inactive)(void *), + void *data) +{ + struct perf_event_context *ctx = event->ctx; + struct task_struct *task = ctx->task; + + if (!task) { + cpu_function_call(event->cpu, active, data); + return; + } + +again: + if (!task_function_call(task, active, data)) + return; + + raw_spin_lock_irq(&ctx->lock); + if (ctx->is_active) { + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + inactive(data); + raw_spin_unlock_irq(&ctx->lock); +} + #define EVENT_OWNER_KERNEL ((void *) -1) static bool is_kernel_event(struct perf_event *event) @@ -1629,6 +1660,17 @@ struct remove_event { bool detach_group; }; +static void ___perf_remove_from_context(void *info) +{ + struct remove_event *re = info; + struct perf_event *event = re->event; + struct perf_event_context *ctx = event->ctx; + + if (re->detach_group) + perf_group_detach(event); + list_del_event(event, ctx); +} + /* * Cross CPU call to remove a performance event * @@ -1656,7 +1698,6 @@ static int __perf_remove_from_context(void *info) return 0; } - /* * Remove the event from a task's (or a CPU's) list of events. * @@ -1673,7 +1714,6 @@ static int __perf_remove_from_context(void *info) static void perf_remove_from_context(struct perf_event *event, bool detach_group) { struct perf_event_context *ctx = event->ctx; - struct task_struct *task = ctx->task; struct remove_event re = { .event = event, .detach_group = detach_group, @@ -1681,44 +1721,8 @@ static void perf_remove_from_context(struct perf_event *event, bool detach_group lockdep_assert_held(&ctx->mutex); - if (!task) { - /* - * Per cpu events are removed via an smp call. The removal can - * fail if the CPU is currently offline, but in that case we - * already called __perf_remove_from_context from - * perf_event_exit_cpu. - */ - cpu_function_call(event->cpu, __perf_remove_from_context, &re); - return; - } - -retry: - if (!task_function_call(task, __perf_remove_from_context, &re)) - return; - - raw_spin_lock_irq(&ctx->lock); - /* - * If we failed to find a running task, but find the context active now - * that we've acquired the ctx->lock, retry. - */ - if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); - /* - * Reload the task pointer, it might have been changed by - * a concurrent perf_event_context_sched_out(). - */ - task = ctx->task; - goto retry; - } - - /* - * Since the task isn't running, its safe to remove the event, us - * holding the ctx->lock ensures the task won't get scheduled in. - */ - if (detach_group) - perf_group_detach(event); - list_del_event(event, ctx); - raw_spin_unlock_irq(&ctx->lock); + event_function_call(event, __perf_remove_from_context, + ___perf_remove_from_context, &re); } /* @@ -1762,6 +1766,20 @@ int __perf_event_disable(void *info) return 0; } +void ___perf_event_disable(void *info) +{ + struct perf_event *event = info; + + /* + * Since we have the lock this context can't be scheduled + * in, so we can change the state safely. + */ + if (event->state == PERF_EVENT_STATE_INACTIVE) { + update_group_times(event); + event->state = PERF_EVENT_STATE_OFF; + } +} + /* * Disable a event. * @@ -1778,43 +1796,16 @@ int __perf_event_disable(void *info) static void _perf_event_disable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; - struct task_struct *task = ctx->task; - - if (!task) { - /* - * Disable the event on the cpu that it's on - */ - cpu_function_call(event->cpu, __perf_event_disable, event); - return; - } - -retry: - if (!task_function_call(task, __perf_event_disable, event)) - return; raw_spin_lock_irq(&ctx->lock); - /* - * If the event is still active, we need to retry the cross-call. - */ - if (event->state == PERF_EVENT_STATE_ACTIVE) { + if (event->state <= PERF_EVENT_STATE_OFF) { raw_spin_unlock_irq(&ctx->lock); - /* - * Reload the task pointer, it might have been changed by - * a concurrent perf_event_context_sched_out(). - */ - task = ctx->task; - goto retry; - } - - /* - * Since we have the lock this context can't be scheduled - * in, so we can change the state safely. - */ - if (event->state == PERF_EVENT_STATE_INACTIVE) { - update_group_times(event); - event->state = PERF_EVENT_STATE_OFF; + return; } raw_spin_unlock_irq(&ctx->lock); + + event_function_call(event, __perf_event_disable, + ___perf_event_disable, event); } /* @@ -2067,6 +2058,18 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx, ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); } +static void ___perf_install_in_context(void *info) +{ + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; + + /* + * Since the task isn't running, its safe to add the event, us holding + * the ctx->lock ensures the task won't get scheduled in. + */ + add_event_to_ctx(event, ctx); +} + /* * Cross CPU call to install and enable a performance event * @@ -2143,48 +2146,14 @@ perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { - struct task_struct *task = ctx->task; - lockdep_assert_held(&ctx->mutex); event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; - if (!task) { - /* - * Per cpu events are installed via an smp call and - * the install is always successful. - */ - cpu_function_call(cpu, __perf_install_in_context, event); - return; - } - -retry: - if (!task_function_call(task, __perf_install_in_context, event)) - return; - - raw_spin_lock_irq(&ctx->lock); - /* - * If we failed to find a running task, but find the context active now - * that we've acquired the ctx->lock, retry. - */ - if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); - /* - * Reload the task pointer, it might have been changed by - * a concurrent perf_event_context_sched_out(). - */ - task = ctx->task; - goto retry; - } - - /* - * Since the task isn't running, its safe to add the event, us holding - * the ctx->lock ensures the task won't get scheduled in. - */ - add_event_to_ctx(event, ctx); - raw_spin_unlock_irq(&ctx->lock); + event_function_call(event, __perf_install_in_context, + ___perf_install_in_context, event); } /* @@ -2287,6 +2256,11 @@ unlock: return 0; } +void ___perf_event_enable(void *info) +{ + __perf_event_mark_enabled((struct perf_event *)info); +} + /* * Enable a event. * @@ -2299,58 +2273,26 @@ unlock: static void _perf_event_enable(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; - struct task_struct *task = ctx->task; - if (!task) { - /* - * Enable the event on the cpu that it's on - */ - cpu_function_call(event->cpu, __perf_event_enable, event); + raw_spin_lock_irq(&ctx->lock); + if (event->state >= PERF_EVENT_STATE_INACTIVE) { + raw_spin_unlock_irq(&ctx->lock); return; } - raw_spin_lock_irq(&ctx->lock); - if (event->state >= PERF_EVENT_STATE_INACTIVE) - goto out; - /* * If the event is in error state, clear that first. - * That way, if we see the event in error state below, we - * know that it has gone back into error state, as distinct - * from the task having been scheduled away before the - * cross-call arrived. + * + * That way, if we see the event in error state below, we know that it + * has gone back into error state, as distinct from the task having + * been scheduled away before the cross-call arrived. */ if (event->state == PERF_EVENT_STATE_ERROR) event->state = PERF_EVENT_STATE_OFF; - -retry: - if (!ctx->is_active) { - __perf_event_mark_enabled(event); - goto out; - } - raw_spin_unlock_irq(&ctx->lock); - if (!task_function_call(task, __perf_event_enable, event)) - return; - - raw_spin_lock_irq(&ctx->lock); - - /* - * If the context is active and the event is still off, - * we need to retry the cross-call. - */ - if (ctx->is_active && event->state == PERF_EVENT_STATE_OFF) { - /* - * task could have been flipped by a concurrent - * perf_event_context_sched_out() - */ - task = ctx->task; - goto retry; - } - -out: - raw_spin_unlock_irq(&ctx->lock); + event_function_call(event, __perf_event_enable, + ___perf_event_enable, event); } /* @@ -3154,15 +3096,16 @@ static int event_enable_on_exec(struct perf_event *event, * Enable all of a task's events that have been marked enable-on-exec. * This expects task == current. */ -static void perf_event_enable_on_exec(struct perf_event_context *ctx) +static void perf_event_enable_on_exec(int ctxn) { - struct perf_event_context *clone_ctx = NULL; + struct perf_event_context *ctx, *clone_ctx = NULL; struct perf_event *event; unsigned long flags; int enabled = 0; int ret; local_irq_save(flags); + ctx = current->perf_event_ctxp[ctxn]; if (!ctx || !ctx->nr_events) goto out; @@ -3205,17 +3148,11 @@ out: void perf_event_exec(void) { - struct perf_event_context *ctx; int ctxn; rcu_read_lock(); - for_each_task_context_nr(ctxn) { - ctx = current->perf_event_ctxp[ctxn]; - if (!ctx) - continue; - - perf_event_enable_on_exec(ctx); - } + for_each_task_context_nr(ctxn) + perf_event_enable_on_exec(ctxn); rcu_read_unlock(); } @@ -4154,6 +4091,22 @@ struct period_event { u64 value; }; +static void ___perf_event_period(void *info) +{ + struct period_event *pe = info; + struct perf_event *event = pe->event; + u64 value = pe->value; + + if (event->attr.freq) { + event->attr.sample_freq = value; + } else { + event->attr.sample_period = value; + event->hw.sample_period = value; + } + + local64_set(&event->hw.period_left, 0); +} + static int __perf_event_period(void *info) { struct period_event *pe = info; @@ -4190,8 +4143,6 @@ static int __perf_event_period(void *info) static int perf_event_period(struct perf_event *event, u64 __user *arg) { struct period_event pe = { .event = event, }; - struct perf_event_context *ctx = event->ctx; - struct task_struct *task; u64 value; if (!is_sampling_event(event)) @@ -4206,34 +4157,10 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; - task = ctx->task; pe.value = value; - if (!task) { - cpu_function_call(event->cpu, __perf_event_period, &pe); - return 0; - } - -retry: - if (!task_function_call(task, __perf_event_period, &pe)) - return 0; - - raw_spin_lock_irq(&ctx->lock); - if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); - task = ctx->task; - goto retry; - } - - if (event->attr.freq) { - event->attr.sample_freq = value; - } else { - event->attr.sample_period = value; - event->hw.sample_period = value; - } - - local64_set(&event->hw.period_left, 0); - raw_spin_unlock_irq(&ctx->lock); + event_function_call(event, __perf_event_period, + ___perf_event_period, &pe); return 0; } @@ -6493,9 +6420,6 @@ struct swevent_htable { /* Recursion avoidance in each contexts */ int recursion[PERF_NR_CONTEXTS]; - - /* Keeps track of cpu being initialized/exited */ - bool online; }; static DEFINE_PER_CPU(struct swevent_htable, swevent_htable); @@ -6753,14 +6677,8 @@ static int perf_swevent_add(struct perf_event *event, int flags) hwc->state = !(flags & PERF_EF_START); head = find_swevent_head(swhash, event); - if (!head) { - /* - * We can race with cpu hotplug code. Do not - * WARN if the cpu just got unplugged. - */ - WARN_ON_ONCE(swhash->online); + if (WARN_ON_ONCE(!head)) return -EINVAL; - } hlist_add_head_rcu(&event->hlist_entry, head); perf_event_update_userpage(event); @@ -6828,7 +6746,6 @@ static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) int err = 0; mutex_lock(&swhash->hlist_mutex); - if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) { struct swevent_hlist *hlist; @@ -9291,7 +9208,6 @@ static void perf_event_init_cpu(int cpu) struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); mutex_lock(&swhash->hlist_mutex); - swhash->online = true; if (swhash->hlist_refcount > 0) { struct swevent_hlist *hlist; @@ -9333,14 +9249,7 @@ static void perf_event_exit_cpu_context(int cpu) static void perf_event_exit_cpu(int cpu) { - struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); - perf_event_exit_cpu_context(cpu); - - mutex_lock(&swhash->hlist_mutex); - swhash->online = false; - swevent_hlist_release(swhash); - mutex_unlock(&swhash->hlist_mutex); } #else static inline void perf_event_exit_cpu(int cpu) { } diff --git a/kernel/fork.c b/kernel/fork.c index fce002ee3ddf..291b08cc817b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -380,6 +380,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; + tsk->wake_q.next = NULL; account_kernel_stack(ti, 1); @@ -1348,9 +1349,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_init(&p->vtime_seqlock); + seqcount_init(&p->vtime_seqcount); p->vtime_snap = 0; - p->vtime_snap_whence = VTIME_SLEEPING; + p->vtime_snap_whence = VTIME_INACTIVE; #endif #if defined(SPLIT_RSS_COUNTING) diff --git a/kernel/futex.c b/kernel/futex.c index 684d7549825a..8a310e240cda 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -725,9 +725,12 @@ static struct futex_pi_state * alloc_pi_state(void) } /* + * Drops a reference to the pi_state object and frees or caches it + * when the last reference is gone. + * * Must be called with the hb lock held. */ -static void free_pi_state(struct futex_pi_state *pi_state) +static void put_pi_state(struct futex_pi_state *pi_state) { if (!pi_state) return; @@ -1706,31 +1709,35 @@ retry_private: * exist yet, look it up one more time to ensure we have a * reference to it. If the lock was taken, ret contains the * vpid of the top waiter task. + * If the lock was not taken, we have pi_state and an initial + * refcount on it. In case of an error we have nothing. */ if (ret > 0) { WARN_ON(pi_state); drop_count++; task_count++; /* - * If we acquired the lock, then the user - * space value of uaddr2 should be vpid. It - * cannot be changed by the top waiter as it - * is blocked on hb2 lock if it tries to do - * so. If something fiddled with it behind our - * back the pi state lookup might unearth - * it. So we rather use the known value than - * rereading and handing potential crap to - * lookup_pi_state. + * If we acquired the lock, then the user space value + * of uaddr2 should be vpid. It cannot be changed by + * the top waiter as it is blocked on hb2 lock if it + * tries to do so. If something fiddled with it behind + * our back the pi state lookup might unearth it. So + * we rather use the known value than rereading and + * handing potential crap to lookup_pi_state. + * + * If that call succeeds then we have pi_state and an + * initial refcount on it. */ ret = lookup_pi_state(ret, hb2, &key2, &pi_state); } switch (ret) { case 0: + /* We hold a reference on the pi state. */ break; + + /* If the above failed, then pi_state is NULL */ case -EFAULT: - free_pi_state(pi_state); - pi_state = NULL; double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); put_futex_key(&key2); @@ -1746,8 +1753,6 @@ retry_private: * exit to complete. * - The user space value changed. */ - free_pi_state(pi_state); - pi_state = NULL; double_unlock_hb(hb1, hb2); hb_waiters_dec(hb2); put_futex_key(&key2); @@ -1801,30 +1806,58 @@ retry_private: * of requeue_pi if we couldn't acquire the lock atomically. */ if (requeue_pi) { - /* Prepare the waiter to take the rt_mutex. */ + /* + * Prepare the waiter to take the rt_mutex. Take a + * refcount on the pi_state and store the pointer in + * the futex_q object of the waiter. + */ atomic_inc(&pi_state->refcount); this->pi_state = pi_state; ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex, this->rt_waiter, this->task); if (ret == 1) { - /* We got the lock. */ + /* + * We got the lock. We do neither drop the + * refcount on pi_state nor clear + * this->pi_state because the waiter needs the + * pi_state for cleaning up the user space + * value. It will drop the refcount after + * doing so. + */ requeue_pi_wake_futex(this, &key2, hb2); drop_count++; continue; } else if (ret) { - /* -EDEADLK */ + /* + * rt_mutex_start_proxy_lock() detected a + * potential deadlock when we tried to queue + * that waiter. Drop the pi_state reference + * which we took above and remove the pointer + * to the state from the waiters futex_q + * object. + */ this->pi_state = NULL; - free_pi_state(pi_state); - goto out_unlock; + put_pi_state(pi_state); + /* + * We stop queueing more waiters and let user + * space deal with the mess. + */ + break; } } requeue_futex(this, hb1, hb2, &key2); drop_count++; } + /* + * We took an extra initial reference to the pi_state either + * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We + * need to drop it here again. + */ + put_pi_state(pi_state); + out_unlock: - free_pi_state(pi_state); double_unlock_hb(hb1, hb2); wake_up_q(&wake_q); hb_waiters_dec(hb2); @@ -1973,7 +2006,7 @@ static void unqueue_me_pi(struct futex_q *q) __unqueue_futex(q); BUG_ON(!q->pi_state); - free_pi_state(q->pi_state); + put_pi_state(q->pi_state); q->pi_state = NULL; spin_unlock(q->lock_ptr); @@ -2755,6 +2788,11 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, if (q.pi_state && (q.pi_state->owner != current)) { spin_lock(q.lock_ptr); ret = fixup_pi_state_owner(uaddr2, &q, current); + /* + * Drop the reference to the pi state which + * the requeue_pi() code acquired for us. + */ + put_pi_state(q.pi_state); spin_unlock(q.lock_ptr); } } else { @@ -3046,7 +3084,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, if (op & FUTEX_CLOCK_REALTIME) { flags |= FLAGS_CLOCKRT; - if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI) + if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \ + cmd != FUTEX_WAIT_REQUEUE_PI) return -ENOSYS; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0eebaeef317b..6ead200370da 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1434,6 +1434,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (!desc) return NULL; + chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, flags); /* @@ -1447,7 +1448,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); raw_spin_unlock_irqrestore(&desc->lock, flags); - + chip_bus_sync_unlock(desc); return NULL; } @@ -1475,6 +1476,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif raw_spin_unlock_irqrestore(&desc->lock, flags); + chip_bus_sync_unlock(desc); unregister_handler_proc(irq, action); @@ -1553,9 +1555,7 @@ void free_irq(unsigned int irq, void *dev_id) desc->affinity_notify = NULL; #endif - chip_bus_lock(desc); kfree(__free_irq(irq, dev_id)); - chip_bus_sync_unlock(desc); } EXPORT_SYMBOL(free_irq); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 11b64a63c0f8..c823f3001e12 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -853,7 +853,12 @@ struct kimage *kexec_image; struct kimage *kexec_crash_image; int kexec_load_disabled; -void crash_kexec(struct pt_regs *regs) +/* + * No panic_cpu check version of crash_kexec(). This function is called + * only when panic_cpu holds the current CPU number; this is the only CPU + * which processes crash_kexec routines. + */ +void __crash_kexec(struct pt_regs *regs) { /* Take the kexec_mutex here to prevent sys_kexec_load * running on one cpu from replacing the crash kernel @@ -876,6 +881,29 @@ void crash_kexec(struct pt_regs *regs) } } +void crash_kexec(struct pt_regs *regs) +{ + int old_cpu, this_cpu; + + /* + * Only one CPU is allowed to execute the crash_kexec() code as with + * panic(). Otherwise parallel calls of panic() and crash_kexec() + * may stop each other. To exclude them, we use panic_cpu here too. + */ + this_cpu = raw_smp_processor_id(); + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); + if (old_cpu == PANIC_CPU_INVALID) { + /* This is the 1st CPU which comes here, so go ahead. */ + __crash_kexec(regs); + + /* + * Reset panic_cpu to allow another panic()/crash_kexec() + * call. + */ + atomic_set(&panic_cpu, PANIC_CPU_INVALID); + } +} + size_t crash_get_memory_size(void) { size_t size = 0; diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index e83b26464061..152da4a48867 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -20,7 +20,7 @@ #include <linux/capability.h> #include <linux/compiler.h> -#include <linux/rcupdate.h> /* rcu_expedited */ +#include <linux/rcupdate.h> /* rcu_expedited and rcu_normal */ #define KERNEL_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) @@ -144,11 +144,12 @@ static ssize_t fscaps_show(struct kobject *kobj, } KERNEL_ATTR_RO(fscaps); +#ifndef CONFIG_TINY_RCU int rcu_expedited; static ssize_t rcu_expedited_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return sprintf(buf, "%d\n", rcu_expedited); + return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited)); } static ssize_t rcu_expedited_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -161,6 +162,24 @@ static ssize_t rcu_expedited_store(struct kobject *kobj, } KERNEL_ATTR_RW(rcu_expedited); +int rcu_normal; +static ssize_t rcu_normal_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", READ_ONCE(rcu_normal)); +} +static ssize_t rcu_normal_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (kstrtoint(buf, 0, &rcu_normal)) + return -EINVAL; + + return count; +} +KERNEL_ATTR_RW(rcu_normal); +#endif /* #ifndef CONFIG_TINY_RCU */ + /* * Make /sys/kernel/notes give the raw contents of our kernel .notes section. */ @@ -202,7 +221,10 @@ static struct attribute * kernel_attrs[] = { &kexec_crash_size_attr.attr, &vmcoreinfo_attr.attr, #endif +#ifndef CONFIG_TINY_RCU &rcu_expedited_attr.attr, + &rcu_normal_attr.attr, +#endif NULL }; diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 87e9ce6a63c5..393d1874b9e0 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -14,8 +14,9 @@ * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2013-2014 Red Hat, Inc. * (C) Copyright 2015 Intel Corp. + * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * - * Authors: Waiman Long <waiman.long@hp.com> + * Authors: Waiman Long <waiman.long@hpe.com> * Peter Zijlstra <peterz@infradead.org> */ @@ -176,7 +177,12 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) { struct __qspinlock *l = (void *)lock; - return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; + /* + * Use release semantics to make sure that the MCS node is properly + * initialized before changing the tail code. + */ + return (u32)xchg_release(&l->tail, + tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; } #else /* _Q_PENDING_BITS == 8 */ @@ -208,7 +214,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) for (;;) { new = (val & _Q_LOCKED_PENDING_MASK) | tail; - old = atomic_cmpxchg(&lock->val, val, new); + /* + * Use release semantics to make sure that the MCS node is + * properly initialized before changing the tail code. + */ + old = atomic_cmpxchg_release(&lock->val, val, new); if (old == val) break; @@ -238,18 +248,20 @@ static __always_inline void set_locked(struct qspinlock *lock) */ static __always_inline void __pv_init_node(struct mcs_spinlock *node) { } -static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { } +static __always_inline void __pv_wait_node(struct mcs_spinlock *node, + struct mcs_spinlock *prev) { } static __always_inline void __pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) { } -static __always_inline void __pv_wait_head(struct qspinlock *lock, - struct mcs_spinlock *node) { } +static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock, + struct mcs_spinlock *node) + { return 0; } #define pv_enabled() false #define pv_init_node __pv_init_node #define pv_wait_node __pv_wait_node #define pv_kick_node __pv_kick_node -#define pv_wait_head __pv_wait_head +#define pv_wait_head_or_lock __pv_wait_head_or_lock #ifdef CONFIG_PARAVIRT_SPINLOCKS #define queued_spin_lock_slowpath native_queued_spin_lock_slowpath @@ -319,7 +331,11 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) if (val == new) new |= _Q_PENDING_VAL; - old = atomic_cmpxchg(&lock->val, val, new); + /* + * Acquire semantic is required here as the function may + * return immediately if the lock was free. + */ + old = atomic_cmpxchg_acquire(&lock->val, val, new); if (old == val) break; @@ -382,6 +398,7 @@ queue: * p,*,* -> n,*,* */ old = xchg_tail(lock, tail); + next = NULL; /* * if there was a previous node; link it and wait until reaching the @@ -391,8 +408,18 @@ queue: prev = decode_tail(old); WRITE_ONCE(prev->next, node); - pv_wait_node(node); + pv_wait_node(node, prev); arch_mcs_spin_lock_contended(&node->locked); + + /* + * While waiting for the MCS lock, the next pointer may have + * been set by another lock waiter. We optimistically load + * the next pointer & prefetch the cacheline for writing + * to reduce latency in the upcoming MCS unlock operation. + */ + next = READ_ONCE(node->next); + if (next) + prefetchw(next); } /* @@ -406,11 +433,22 @@ queue: * sequentiality; this is because the set_locked() function below * does not imply a full barrier. * + * The PV pv_wait_head_or_lock function, if active, will acquire + * the lock and return a non-zero value. So we have to skip the + * smp_load_acquire() call. As the next PV queue head hasn't been + * designated yet, there is no way for the locked value to become + * _Q_SLOW_VAL. So both the set_locked() and the + * atomic_cmpxchg_relaxed() calls will be safe. + * + * If PV isn't active, 0 will be returned instead. + * */ - pv_wait_head(lock, node); - while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK) - cpu_relax(); + if ((val = pv_wait_head_or_lock(lock, node))) + goto locked; + smp_cond_acquire(!((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK)); + +locked: /* * claim the lock: * @@ -422,11 +460,17 @@ queue: * to grab the lock. */ for (;;) { - if (val != tail) { + /* In the PV case we might already have _Q_LOCKED_VAL set */ + if ((val & _Q_TAIL_MASK) != tail) { set_locked(lock); break; } - old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL); + /* + * The smp_load_acquire() call above has provided the necessary + * acquire semantics required for locking. At most two + * iterations of this loop may be ran. + */ + old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL); if (old == val) goto release; /* No contention */ @@ -434,10 +478,12 @@ queue: } /* - * contended path; wait for next, release. + * contended path; wait for next if not observed yet, release. */ - while (!(next = READ_ONCE(node->next))) - cpu_relax(); + if (!next) { + while (!(next = READ_ONCE(node->next))) + cpu_relax(); + } arch_mcs_spin_unlock_contended(&next->locked); pv_kick_node(lock, next); @@ -462,7 +508,7 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath); #undef pv_init_node #undef pv_wait_node #undef pv_kick_node -#undef pv_wait_head +#undef pv_wait_head_or_lock #undef queued_spin_lock_slowpath #define queued_spin_lock_slowpath __pv_queued_spin_lock_slowpath diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index f0450ff4829b..87bb235c3448 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -23,6 +23,20 @@ #define _Q_SLOW_VAL (3U << _Q_LOCKED_OFFSET) /* + * Queue Node Adaptive Spinning + * + * A queue node vCPU will stop spinning if the vCPU in the previous node is + * not running. The one lock stealing attempt allowed at slowpath entry + * mitigates the slight slowdown for non-overcommitted guest with this + * aggressive wait-early mechanism. + * + * The status of the previous node will be checked at fixed interval + * controlled by PV_PREV_CHECK_MASK. This is to ensure that we won't + * pound on the cacheline of the previous node too heavily. + */ +#define PV_PREV_CHECK_MASK 0xff + +/* * Queue node uses: vcpu_running & vcpu_halted. * Queue head uses: vcpu_running & vcpu_hashed. */ @@ -41,6 +55,94 @@ struct pv_node { }; /* + * By replacing the regular queued_spin_trylock() with the function below, + * it will be called once when a lock waiter enter the PV slowpath before + * being queued. By allowing one lock stealing attempt here when the pending + * bit is off, it helps to reduce the performance impact of lock waiter + * preemption without the drawback of lock starvation. + */ +#define queued_spin_trylock(l) pv_queued_spin_steal_lock(l) +static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + + return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && + (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0); +} + +/* + * The pending bit is used by the queue head vCPU to indicate that it + * is actively spinning on the lock and no lock stealing is allowed. + */ +#if _Q_PENDING_BITS == 8 +static __always_inline void set_pending(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + + WRITE_ONCE(l->pending, 1); +} + +static __always_inline void clear_pending(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + + WRITE_ONCE(l->pending, 0); +} + +/* + * The pending bit check in pv_queued_spin_steal_lock() isn't a memory + * barrier. Therefore, an atomic cmpxchg() is used to acquire the lock + * just to be sure that it will get it. + */ +static __always_inline int trylock_clear_pending(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + + return !READ_ONCE(l->locked) && + (cmpxchg(&l->locked_pending, _Q_PENDING_VAL, _Q_LOCKED_VAL) + == _Q_PENDING_VAL); +} +#else /* _Q_PENDING_BITS == 8 */ +static __always_inline void set_pending(struct qspinlock *lock) +{ + atomic_set_mask(_Q_PENDING_VAL, &lock->val); +} + +static __always_inline void clear_pending(struct qspinlock *lock) +{ + atomic_clear_mask(_Q_PENDING_VAL, &lock->val); +} + +static __always_inline int trylock_clear_pending(struct qspinlock *lock) +{ + int val = atomic_read(&lock->val); + + for (;;) { + int old, new; + + if (val & _Q_LOCKED_MASK) + break; + + /* + * Try to clear pending bit & set locked bit + */ + old = val; + new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL; + val = atomic_cmpxchg(&lock->val, old, new); + + if (val == old) + return 1; + } + return 0; +} +#endif /* _Q_PENDING_BITS == 8 */ + +/* + * Include queued spinlock statistics code + */ +#include "qspinlock_stat.h" + +/* * Lock and MCS node addresses hash table for fast lookup * * Hashing is done on a per-cacheline basis to minimize the need to access @@ -100,10 +202,13 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node) { unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits); struct pv_hash_entry *he; + int hopcnt = 0; for_each_hash_entry(he, offset, hash) { + hopcnt++; if (!cmpxchg(&he->lock, NULL, lock)) { WRITE_ONCE(he->node, node); + qstat_hop(hopcnt); return &he->lock; } } @@ -144,6 +249,20 @@ static struct pv_node *pv_unhash(struct qspinlock *lock) } /* + * Return true if when it is time to check the previous node which is not + * in a running state. + */ +static inline bool +pv_wait_early(struct pv_node *prev, int loop) +{ + + if ((loop & PV_PREV_CHECK_MASK) != 0) + return false; + + return READ_ONCE(prev->state) != vcpu_running; +} + +/* * Initialize the PV part of the mcs_spinlock node. */ static void pv_init_node(struct mcs_spinlock *node) @@ -161,15 +280,23 @@ static void pv_init_node(struct mcs_spinlock *node) * pv_kick_node() is used to set _Q_SLOW_VAL and fill in hash table on its * behalf. */ -static void pv_wait_node(struct mcs_spinlock *node) +static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) { struct pv_node *pn = (struct pv_node *)node; + struct pv_node *pp = (struct pv_node *)prev; + int waitcnt = 0; int loop; + bool wait_early; - for (;;) { - for (loop = SPIN_THRESHOLD; loop; loop--) { + /* waitcnt processing will be compiled out if !QUEUED_LOCK_STAT */ + for (;; waitcnt++) { + for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) { if (READ_ONCE(node->locked)) return; + if (pv_wait_early(pp, loop)) { + wait_early = true; + break; + } cpu_relax(); } @@ -184,12 +311,17 @@ static void pv_wait_node(struct mcs_spinlock *node) */ smp_store_mb(pn->state, vcpu_halted); - if (!READ_ONCE(node->locked)) + if (!READ_ONCE(node->locked)) { + qstat_inc(qstat_pv_wait_node, true); + qstat_inc(qstat_pv_wait_again, waitcnt); + qstat_inc(qstat_pv_wait_early, wait_early); pv_wait(&pn->state, vcpu_halted); + } /* - * If pv_kick_node() changed us to vcpu_hashed, retain that value - * so that pv_wait_head() knows to not also try to hash this lock. + * If pv_kick_node() changed us to vcpu_hashed, retain that + * value so that pv_wait_head_or_lock() knows to not also try + * to hash this lock. */ cmpxchg(&pn->state, vcpu_halted, vcpu_running); @@ -200,6 +332,7 @@ static void pv_wait_node(struct mcs_spinlock *node) * So it is better to spin for a while in the hope that the * MCS lock will be released soon. */ + qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked)); } /* @@ -212,8 +345,9 @@ static void pv_wait_node(struct mcs_spinlock *node) /* * Called after setting next->locked = 1 when we're the lock owner. * - * Instead of waking the waiters stuck in pv_wait_node() advance their state such - * that they're waiting in pv_wait_head(), this avoids a wake/sleep cycle. + * Instead of waking the waiters stuck in pv_wait_node() advance their state + * such that they're waiting in pv_wait_head_or_lock(), this avoids a + * wake/sleep cycle. */ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) { @@ -242,14 +376,19 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node) } /* - * Wait for l->locked to become clear; halt the vcpu after a short spin. + * Wait for l->locked to become clear and acquire the lock; + * halt the vcpu after a short spin. * __pv_queued_spin_unlock() will wake us. + * + * The current value of the lock will be returned for additional processing. */ -static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) +static u32 +pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) { struct pv_node *pn = (struct pv_node *)node; struct __qspinlock *l = (void *)lock; struct qspinlock **lp = NULL; + int waitcnt = 0; int loop; /* @@ -259,12 +398,25 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) if (READ_ONCE(pn->state) == vcpu_hashed) lp = (struct qspinlock **)1; - for (;;) { + for (;; waitcnt++) { + /* + * Set correct vCPU state to be used by queue node wait-early + * mechanism. + */ + WRITE_ONCE(pn->state, vcpu_running); + + /* + * Set the pending bit in the active lock spinning loop to + * disable lock stealing before attempting to acquire the lock. + */ + set_pending(lock); for (loop = SPIN_THRESHOLD; loop; loop--) { - if (!READ_ONCE(l->locked)) - return; + if (trylock_clear_pending(lock)) + goto gotlock; cpu_relax(); } + clear_pending(lock); + if (!lp) { /* ONCE */ lp = pv_hash(lock, pn); @@ -280,51 +432,50 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) * * Matches the smp_rmb() in __pv_queued_spin_unlock(). */ - if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) { + if (xchg(&l->locked, _Q_SLOW_VAL) == 0) { /* - * The lock is free and _Q_SLOW_VAL has never - * been set. Therefore we need to unhash before - * getting the lock. + * The lock was free and now we own the lock. + * Change the lock value back to _Q_LOCKED_VAL + * and unhash the table. */ + WRITE_ONCE(l->locked, _Q_LOCKED_VAL); WRITE_ONCE(*lp, NULL); - return; + goto gotlock; } } + WRITE_ONCE(pn->state, vcpu_halted); + qstat_inc(qstat_pv_wait_head, true); + qstat_inc(qstat_pv_wait_again, waitcnt); pv_wait(&l->locked, _Q_SLOW_VAL); /* * The unlocker should have freed the lock before kicking the * CPU. So if the lock is still not free, it is a spurious - * wakeup and so the vCPU should wait again after spinning for - * a while. + * wakeup or another vCPU has stolen the lock. The current + * vCPU should spin again. */ + qstat_inc(qstat_pv_spurious_wakeup, READ_ONCE(l->locked)); } /* - * Lock is unlocked now; the caller will acquire it without waiting. - * As with pv_wait_node() we rely on the caller to do a load-acquire - * for us. + * The cmpxchg() or xchg() call before coming here provides the + * acquire semantics for locking. The dummy ORing of _Q_LOCKED_VAL + * here is to indicate to the compiler that the value will always + * be nozero to enable better code optimization. */ +gotlock: + return (u32)(atomic_read(&lock->val) | _Q_LOCKED_VAL); } /* - * PV version of the unlock function to be used in stead of - * queued_spin_unlock(). + * PV versions of the unlock fastpath and slowpath functions to be used + * instead of queued_spin_unlock(). */ -__visible void __pv_queued_spin_unlock(struct qspinlock *lock) +__visible void +__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked) { struct __qspinlock *l = (void *)lock; struct pv_node *node; - u8 locked; - - /* - * We must not unlock if SLOW, because in that case we must first - * unhash. Otherwise it would be possible to have multiple @lock - * entries, which would be BAD. - */ - locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); - if (likely(locked == _Q_LOCKED_VAL)) - return; if (unlikely(locked != _Q_SLOW_VAL)) { WARN(!debug_locks_silent, @@ -338,7 +489,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) * so we need a barrier to order the read of the node data in * pv_unhash *after* we've read the lock being _Q_SLOW_VAL. * - * Matches the cmpxchg() in pv_wait_head() setting _Q_SLOW_VAL. + * Matches the cmpxchg() in pv_wait_head_or_lock() setting _Q_SLOW_VAL. */ smp_rmb(); @@ -361,14 +512,35 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) * vCPU is harmless other than the additional latency in completing * the unlock. */ + qstat_inc(qstat_pv_kick_unlock, true); pv_kick(node->cpu); } + /* * Include the architecture specific callee-save thunk of the * __pv_queued_spin_unlock(). This thunk is put together with - * __pv_queued_spin_unlock() near the top of the file to make sure - * that the callee-save thunk and the real unlock function are close - * to each other sharing consecutive instruction cachelines. + * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock + * function close to each other sharing consecutive instruction cachelines. + * Alternatively, architecture specific version of __pv_queued_spin_unlock() + * can be defined. */ #include <asm/qspinlock_paravirt.h> +#ifndef __pv_queued_spin_unlock +__visible void __pv_queued_spin_unlock(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + u8 locked; + + /* + * We must not unlock if SLOW, because in that case we must first + * unhash. Otherwise it would be possible to have multiple @lock + * entries, which would be BAD. + */ + locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + if (likely(locked == _Q_LOCKED_VAL)) + return; + + __pv_queued_spin_unlock_slowpath(lock, locked); +} +#endif /* __pv_queued_spin_unlock */ diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h new file mode 100644 index 000000000000..640dcecdd1df --- /dev/null +++ b/kernel/locking/qspinlock_stat.h @@ -0,0 +1,300 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Waiman Long <waiman.long@hpe.com> + */ + +/* + * When queued spinlock statistical counters are enabled, the following + * debugfs files will be created for reporting the counter values: + * + * <debugfs>/qlockstat/ + * pv_hash_hops - average # of hops per hashing operation + * pv_kick_unlock - # of vCPU kicks issued at unlock time + * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake + * pv_latency_kick - average latency (ns) of vCPU kick operation + * pv_latency_wake - average latency (ns) from vCPU kick to wakeup + * pv_lock_stealing - # of lock stealing operations + * pv_spurious_wakeup - # of spurious wakeups + * pv_wait_again - # of vCPU wait's that happened after a vCPU kick + * pv_wait_early - # of early vCPU wait's + * pv_wait_head - # of vCPU wait's at the queue head + * pv_wait_node - # of vCPU wait's at a non-head queue node + * + * Writing to the "reset_counters" file will reset all the above counter + * values. + * + * These statistical counters are implemented as per-cpu variables which are + * summed and computed whenever the corresponding debugfs files are read. This + * minimizes added overhead making the counters usable even in a production + * environment. + * + * There may be slight difference between pv_kick_wake and pv_kick_unlock. + */ +enum qlock_stats { + qstat_pv_hash_hops, + qstat_pv_kick_unlock, + qstat_pv_kick_wake, + qstat_pv_latency_kick, + qstat_pv_latency_wake, + qstat_pv_lock_stealing, + qstat_pv_spurious_wakeup, + qstat_pv_wait_again, + qstat_pv_wait_early, + qstat_pv_wait_head, + qstat_pv_wait_node, + qstat_num, /* Total number of statistical counters */ + qstat_reset_cnts = qstat_num, +}; + +#ifdef CONFIG_QUEUED_LOCK_STAT +/* + * Collect pvqspinlock statistics + */ +#include <linux/debugfs.h> +#include <linux/sched.h> +#include <linux/fs.h> + +static const char * const qstat_names[qstat_num + 1] = { + [qstat_pv_hash_hops] = "pv_hash_hops", + [qstat_pv_kick_unlock] = "pv_kick_unlock", + [qstat_pv_kick_wake] = "pv_kick_wake", + [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup", + [qstat_pv_latency_kick] = "pv_latency_kick", + [qstat_pv_latency_wake] = "pv_latency_wake", + [qstat_pv_lock_stealing] = "pv_lock_stealing", + [qstat_pv_wait_again] = "pv_wait_again", + [qstat_pv_wait_early] = "pv_wait_early", + [qstat_pv_wait_head] = "pv_wait_head", + [qstat_pv_wait_node] = "pv_wait_node", + [qstat_reset_cnts] = "reset_counters", +}; + +/* + * Per-cpu counters + */ +static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]); +static DEFINE_PER_CPU(u64, pv_kick_time); + +/* + * Function to read and return the qlock statistical counter values + * + * The following counters are handled specially: + * 1. qstat_pv_latency_kick + * Average kick latency (ns) = pv_latency_kick/pv_kick_unlock + * 2. qstat_pv_latency_wake + * Average wake latency (ns) = pv_latency_wake/pv_kick_wake + * 3. qstat_pv_hash_hops + * Average hops/hash = pv_hash_hops/pv_kick_unlock + */ +static ssize_t qstat_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + char buf[64]; + int cpu, counter, len; + u64 stat = 0, kicks = 0; + + /* + * Get the counter ID stored in file->f_inode->i_private + */ + if (!file->f_inode) { + WARN_ON_ONCE(1); + return -EBADF; + } + counter = (long)(file->f_inode->i_private); + + if (counter >= qstat_num) + return -EBADF; + + for_each_possible_cpu(cpu) { + stat += per_cpu(qstats[counter], cpu); + /* + * Need to sum additional counter for some of them + */ + switch (counter) { + + case qstat_pv_latency_kick: + case qstat_pv_hash_hops: + kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu); + break; + + case qstat_pv_latency_wake: + kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu); + break; + } + } + + if (counter == qstat_pv_hash_hops) { + u64 frac; + + frac = 100ULL * do_div(stat, kicks); + frac = DIV_ROUND_CLOSEST_ULL(frac, kicks); + + /* + * Return a X.XX decimal number + */ + len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac); + } else { + /* + * Round to the nearest ns + */ + if ((counter == qstat_pv_latency_kick) || + (counter == qstat_pv_latency_wake)) { + stat = 0; + if (kicks) + stat = DIV_ROUND_CLOSEST_ULL(stat, kicks); + } + len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat); + } + + return simple_read_from_buffer(user_buf, count, ppos, buf, len); +} + +/* + * Function to handle write request + * + * When counter = reset_cnts, reset all the counter values. + * Since the counter updates aren't atomic, the resetting is done twice + * to make sure that the counters are very likely to be all cleared. + */ +static ssize_t qstat_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + int cpu; + + /* + * Get the counter ID stored in file->f_inode->i_private + */ + if (!file->f_inode) { + WARN_ON_ONCE(1); + return -EBADF; + } + if ((long)(file->f_inode->i_private) != qstat_reset_cnts) + return count; + + for_each_possible_cpu(cpu) { + int i; + unsigned long *ptr = per_cpu_ptr(qstats, cpu); + + for (i = 0 ; i < qstat_num; i++) + WRITE_ONCE(ptr[i], 0); + for (i = 0 ; i < qstat_num; i++) + WRITE_ONCE(ptr[i], 0); + } + return count; +} + +/* + * Debugfs data structures + */ +static const struct file_operations fops_qstat = { + .read = qstat_read, + .write = qstat_write, + .llseek = default_llseek, +}; + +/* + * Initialize debugfs for the qspinlock statistical counters + */ +static int __init init_qspinlock_stat(void) +{ + struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL); + int i; + + if (!d_qstat) { + pr_warn("Could not create 'qlockstat' debugfs directory\n"); + return 0; + } + + /* + * Create the debugfs files + * + * As reading from and writing to the stat files can be slow, only + * root is allowed to do the read/write to limit impact to system + * performance. + */ + for (i = 0; i < qstat_num; i++) + debugfs_create_file(qstat_names[i], 0400, d_qstat, + (void *)(long)i, &fops_qstat); + + debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat, + (void *)(long)qstat_reset_cnts, &fops_qstat); + return 0; +} +fs_initcall(init_qspinlock_stat); + +/* + * Increment the PV qspinlock statistical counters + */ +static inline void qstat_inc(enum qlock_stats stat, bool cond) +{ + if (cond) + this_cpu_inc(qstats[stat]); +} + +/* + * PV hash hop count + */ +static inline void qstat_hop(int hopcnt) +{ + this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt); +} + +/* + * Replacement function for pv_kick() + */ +static inline void __pv_kick(int cpu) +{ + u64 start = sched_clock(); + + per_cpu(pv_kick_time, cpu) = start; + pv_kick(cpu); + this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start); +} + +/* + * Replacement function for pv_wait() + */ +static inline void __pv_wait(u8 *ptr, u8 val) +{ + u64 *pkick_time = this_cpu_ptr(&pv_kick_time); + + *pkick_time = 0; + pv_wait(ptr, val); + if (*pkick_time) { + this_cpu_add(qstats[qstat_pv_latency_wake], + sched_clock() - *pkick_time); + qstat_inc(qstat_pv_kick_wake, true); + } +} + +#define pv_kick(c) __pv_kick(c) +#define pv_wait(p, v) __pv_wait(p, v) + +/* + * PV unfair trylock count tracking function + */ +static inline int qstat_spin_steal_lock(struct qspinlock *lock) +{ + int ret = pv_queued_spin_steal_lock(lock); + + qstat_inc(qstat_pv_lock_stealing, ret); + return ret; +} +#undef queued_spin_trylock +#define queued_spin_trylock(l) qstat_spin_steal_lock(l) + +#else /* CONFIG_QUEUED_LOCK_STAT */ + +static inline void qstat_inc(enum qlock_stats stat, bool cond) { } +static inline void qstat_hop(int hopcnt) { } + +#endif /* CONFIG_QUEUED_LOCK_STAT */ diff --git a/kernel/module.c b/kernel/module.c index 8f051a106676..38c7bd5583ff 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3571,6 +3571,12 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_sched(); mutex_unlock(&module_mutex); free_module: + /* + * Ftrace needs to clean up what it initialized. + * This does nothing if ftrace_module_init() wasn't called, + * but it must be called outside of module_mutex. + */ + ftrace_release_mod(mod); /* Free lock-classes; relies on the preceding sync_rcu() */ lockdep_free_key_range(mod->module_core, mod->core_size); diff --git a/kernel/panic.c b/kernel/panic.c index 4b150bc0c6c1..b333380c6bb2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -61,6 +61,17 @@ void __weak panic_smp_self_stop(void) cpu_relax(); } +/* + * Stop ourselves in NMI context if another CPU has already panicked. Arch code + * may override this to prepare for crash dumping, e.g. save regs info. + */ +void __weak nmi_panic_self_stop(struct pt_regs *regs) +{ + panic_smp_self_stop(); +} + +atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); + /** * panic - halt the system * @fmt: The text string to print @@ -71,17 +82,17 @@ void __weak panic_smp_self_stop(void) */ void panic(const char *fmt, ...) { - static DEFINE_SPINLOCK(panic_lock); static char buf[1024]; va_list args; long i, i_next = 0; int state = 0; + int old_cpu, this_cpu; /* * Disable local interrupts. This will prevent panic_smp_self_stop * from deadlocking the first cpu that invokes the panic, since * there is nothing to prevent an interrupt handler (that runs - * after the panic_lock is acquired) from invoking panic again. + * after setting panic_cpu) from invoking panic() again. */ local_irq_disable(); @@ -94,8 +105,16 @@ void panic(const char *fmt, ...) * multiple parallel invocations of panic, all other CPUs either * stop themself or will wait until they are stopped by the 1st CPU * with smp_send_stop(). + * + * `old_cpu == PANIC_CPU_INVALID' means this is the 1st CPU which + * comes here, so go ahead. + * `old_cpu == this_cpu' means we came from nmi_panic() which sets + * panic_cpu to this CPU. In this case, this is also the 1st CPU. */ - if (!spin_trylock(&panic_lock)) + this_cpu = raw_smp_processor_id(); + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu); + + if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu) panic_smp_self_stop(); console_verbose(); @@ -117,9 +136,11 @@ void panic(const char *fmt, ...) * everything else. * If we want to run this after calling panic_notifiers, pass * the "crash_kexec_post_notifiers" option to the kernel. + * + * Bypass the panic_cpu check and call __crash_kexec directly. */ if (!crash_kexec_post_notifiers) - crash_kexec(NULL); + __crash_kexec(NULL); /* * Note smp_send_stop is the usual smp shutdown function, which @@ -142,9 +163,11 @@ void panic(const char *fmt, ...) * panic_notifiers and dumping kmsg before kdump. * Note: since some panic_notifiers can make crashed kernel * more unstable, it can increase risks of the kdump failure too. + * + * Bypass the panic_cpu check and call __crash_kexec directly. */ if (crash_kexec_post_notifiers) - crash_kexec(NULL); + __crash_kexec(NULL); bust_spinlocks(0); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index d89328e260df..d2988d047d66 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -162,6 +162,27 @@ static int rcu_torture_writer_state; #define RTWS_SYNC 7 #define RTWS_STUTTER 8 #define RTWS_STOPPING 9 +static const char * const rcu_torture_writer_state_names[] = { + "RTWS_FIXED_DELAY", + "RTWS_DELAY", + "RTWS_REPLACE", + "RTWS_DEF_FREE", + "RTWS_EXP_SYNC", + "RTWS_COND_GET", + "RTWS_COND_SYNC", + "RTWS_SYNC", + "RTWS_STUTTER", + "RTWS_STOPPING", +}; + +static const char *rcu_torture_writer_state_getname(void) +{ + unsigned int i = READ_ONCE(rcu_torture_writer_state); + + if (i >= ARRAY_SIZE(rcu_torture_writer_state_names)) + return "???"; + return rcu_torture_writer_state_names[i]; +} #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) #define RCUTORTURE_RUNNABLE_INIT 1 @@ -1307,7 +1328,8 @@ rcu_torture_stats_print(void) rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed); - pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n", + pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x\n", + rcu_torture_writer_state_getname(), rcu_torture_writer_state, gpnum, completed, flags); show_rcu_gp_kthreads(); diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index a63a1ea5a41b..9b9cdd549caa 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -489,7 +489,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) */ void synchronize_srcu(struct srcu_struct *sp) { - __synchronize_srcu(sp, rcu_gp_is_expedited() + __synchronize_srcu(sp, (rcu_gp_is_expedited() && !rcu_gp_is_normal()) ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT : SYNCHRONIZE_SRCU_TRYCOUNT); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index f07343b54fe5..e41dd4131f7a 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -68,10 +68,6 @@ MODULE_ALIAS("rcutree"); /* Data structures. */ -static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; -static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; -static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; - /* * In order to export the rcu_state name to the tracing tools, it * needs to be added in the __tracepoint_string section. @@ -246,24 +242,17 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { - unsigned long flags; - - if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) { - trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gpnum), - TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); - if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) - return; - local_irq_save(flags); - if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) { - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(&rcu_sched_data), - true); - } - local_irq_restore(flags); - } + if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) + return; + trace_rcu_grace_period(TPS("rcu_sched"), + __this_cpu_read(rcu_sched_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); + if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) + return; + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(&rcu_sched_data), true); } void rcu_bh_qs(void) @@ -300,17 +289,16 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr); * We inform the RCU core by emulating a zero-duration dyntick-idle * period, which we in turn do by incrementing the ->dynticks counter * by two. + * + * The caller must have disabled interrupts. */ static void rcu_momentary_dyntick_idle(void) { - unsigned long flags; struct rcu_data *rdp; struct rcu_dynticks *rdtp; int resched_mask; struct rcu_state *rsp; - local_irq_save(flags); - /* * Yes, we can lose flag-setting operations. This is OK, because * the flag will be set again after some delay. @@ -340,13 +328,12 @@ static void rcu_momentary_dyntick_idle(void) smp_mb__after_atomic(); /* Later stuff after QS. */ break; } - local_irq_restore(flags); } /* * Note a context switch. This is a quiescent state for RCU-sched, * and requires special handling for preemptible RCU. - * The caller must have disabled preemption. + * The caller must have disabled interrupts. */ void rcu_note_context_switch(void) { @@ -376,9 +363,14 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); */ void rcu_all_qs(void) { + unsigned long flags; + barrier(); /* Avoid RCU read-side critical sections leaking down. */ - if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) + if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) { + local_irq_save(flags); rcu_momentary_dyntick_idle(); + local_irq_restore(flags); + } this_cpu_inc(rcu_qs_ctr); barrier(); /* Avoid RCU read-side critical sections leaking up. */ } @@ -605,25 +597,25 @@ static int rcu_future_needs_gp(struct rcu_state *rsp) * The caller must have disabled interrupts to prevent races with * normal callback registry. */ -static int +static bool cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { int i; if (rcu_gp_in_progress(rsp)) - return 0; /* No, a grace period is already in progress. */ + return false; /* No, a grace period is already in progress. */ if (rcu_future_needs_gp(rsp)) - return 1; /* Yes, a no-CBs CPU needs one. */ + return true; /* Yes, a no-CBs CPU needs one. */ if (!rdp->nxttail[RCU_NEXT_TAIL]) - return 0; /* No, this is a no-CBs (or offline) CPU. */ + return false; /* No, this is a no-CBs (or offline) CPU. */ if (*rdp->nxttail[RCU_NEXT_READY_TAIL]) - return 1; /* Yes, this CPU has newly registered callbacks. */ + return true; /* Yes, CPU has newly registered callbacks. */ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) if (rdp->nxttail[i - 1] != rdp->nxttail[i] && ULONG_CMP_LT(READ_ONCE(rsp->completed), rdp->nxtcompleted[i])) - return 1; /* Yes, CBs for future grace period. */ - return 0; /* No grace period needed. */ + return true; /* Yes, CBs for future grace period. */ + return false; /* No grace period needed. */ } /* @@ -740,7 +732,7 @@ void rcu_user_enter(void) * * Exit from an interrupt handler, which might possibly result in entering * idle mode, in other words, leaving the mode in which read-side critical - * sections can occur. + * sections can occur. The caller must have disabled interrupts. * * This code assumes that the idle loop never does anything that might * result in unbalanced calls to irq_enter() and irq_exit(). If your @@ -753,11 +745,10 @@ void rcu_user_enter(void) */ void rcu_irq_exit(void) { - unsigned long flags; long long oldval; struct rcu_dynticks *rdtp; - local_irq_save(flags); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting--; @@ -768,6 +759,17 @@ void rcu_irq_exit(void) else rcu_eqs_enter_common(oldval, true); rcu_sysidle_enter(1); +} + +/* + * Wrapper for rcu_irq_exit() where interrupts are enabled. + */ +void rcu_irq_exit_irqson(void) +{ + unsigned long flags; + + local_irq_save(flags); + rcu_irq_exit(); local_irq_restore(flags); } @@ -865,7 +867,7 @@ void rcu_user_exit(void) * * Enter an interrupt handler, which might possibly result in exiting * idle mode, in other words, entering the mode in which read-side critical - * sections can occur. + * sections can occur. The caller must have disabled interrupts. * * Note that the Linux kernel is fully capable of entering an interrupt * handler that it never exits, for example when doing upcalls to @@ -881,11 +883,10 @@ void rcu_user_exit(void) */ void rcu_irq_enter(void) { - unsigned long flags; struct rcu_dynticks *rdtp; long long oldval; - local_irq_save(flags); + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; @@ -896,6 +897,17 @@ void rcu_irq_enter(void) else rcu_eqs_exit_common(oldval, true); rcu_sysidle_exit(1); +} + +/* + * Wrapper for rcu_irq_enter() where interrupts are enabled. + */ +void rcu_irq_enter_irqson(void) +{ + unsigned long flags; + + local_irq_save(flags); + rcu_irq_enter(); local_irq_restore(flags); } @@ -1187,6 +1199,16 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) } /* + * Convert a ->gp_state value to a character string. + */ +static const char *gp_state_getname(short gs) +{ + if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) + return "???"; + return gp_state_names[gs]; +} + +/* * Complain about starvation of grace-period kthread. */ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) @@ -1196,12 +1218,16 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) j = jiffies; gpa = READ_ONCE(rsp->gp_activity); - if (j - gpa > 2 * HZ) - pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x s%d ->state=%#lx\n", + if (j - gpa > 2 * HZ) { + pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx\n", rsp->name, j - gpa, rsp->gpnum, rsp->completed, - rsp->gp_flags, rsp->gp_state, - rsp->gp_kthread ? rsp->gp_kthread->state : 0); + rsp->gp_flags, + gp_state_getname(rsp->gp_state), rsp->gp_state, + rsp->gp_kthread ? rsp->gp_kthread->state : ~0); + if (rsp->gp_kthread) + sched_show_task(rsp->gp_kthread); + } } /* @@ -1214,7 +1240,7 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) struct rcu_node *rnp; rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask != 0) { for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) if (rnp->qsmask & (1UL << cpu)) @@ -1237,7 +1263,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) /* Only let one CPU complain about others per time interval. */ - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); delta = jiffies - READ_ONCE(rsp->jiffies_stall); if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -1256,7 +1282,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) rsp->name); print_cpu_stall_info_begin(); rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); ndetected += rcu_print_task_stall(rnp); if (rnp->qsmask != 0) { for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) @@ -1327,7 +1353,7 @@ static void print_cpu_stall(struct rcu_state *rsp) rcu_dump_cpu_stacks(rsp); - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) WRITE_ONCE(rsp->jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); @@ -1534,10 +1560,8 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, * hold it, acquire the root rcu_node structure's lock in order to * start one (if needed). */ - if (rnp != rnp_root) { - raw_spin_lock(&rnp_root->lock); - smp_mb__after_unlock_lock(); - } + if (rnp != rnp_root) + raw_spin_lock_rcu_node(rnp_root); /* * Get a new grace-period number. If there really is no grace @@ -1786,11 +1810,10 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && rdp->completed == READ_ONCE(rnp->completed) && !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */ - !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */ + !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */ local_irq_restore(flags); return; } - smp_mb__after_unlock_lock(); needwake = __note_gp_changes(rsp, rnp, rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); if (needwake) @@ -1805,21 +1828,20 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay) } /* - * Initialize a new grace period. Return 0 if no grace period required. + * Initialize a new grace period. Return false if no grace period required. */ -static int rcu_gp_init(struct rcu_state *rsp) +static bool rcu_gp_init(struct rcu_state *rsp) { unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_irq_rcu_node(rnp); if (!READ_ONCE(rsp->gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq(&rnp->lock); - return 0; + return false; } WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ @@ -1829,7 +1851,7 @@ static int rcu_gp_init(struct rcu_state *rsp) * Not supposed to be able to happen. */ raw_spin_unlock_irq(&rnp->lock); - return 0; + return false; } /* Advance to a new grace period and initialize state. */ @@ -1847,8 +1869,7 @@ static int rcu_gp_init(struct rcu_state *rsp) */ rcu_for_each_leaf_node(rsp, rnp) { rcu_gp_slow(rsp, gp_preinit_delay); - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_irq_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ @@ -1904,8 +1925,7 @@ static int rcu_gp_init(struct rcu_state *rsp) */ rcu_for_each_node_breadth_first(rsp, rnp) { rcu_gp_slow(rsp, gp_init_delay); - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_irq_rcu_node(rnp); rdp = this_cpu_ptr(rsp->rda); rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; @@ -1923,7 +1943,7 @@ static int rcu_gp_init(struct rcu_state *rsp) WRITE_ONCE(rsp->gp_activity, jiffies); } - return 1; + return true; } /* @@ -1973,8 +1993,7 @@ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) } /* Clear flag to prevent immediate re-entry. */ if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_irq_rcu_node(rnp); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); raw_spin_unlock_irq(&rnp->lock); @@ -1993,8 +2012,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_irq_rcu_node(rnp); gp_duration = jiffies - rsp->gp_start; if (gp_duration > rsp->gp_max) rsp->gp_max = gp_duration; @@ -2019,8 +2037,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) * grace period is recorded in any of the rcu_node structures. */ rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_irq_rcu_node(rnp); WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); WARN_ON_ONCE(rnp->qsmask); WRITE_ONCE(rnp->completed, rsp->gpnum); @@ -2035,8 +2052,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) rcu_gp_slow(rsp, gp_cleanup_delay); } rnp = rcu_get_root(rsp); - raw_spin_lock_irq(&rnp->lock); - smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */ + raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */ rcu_nocb_gp_set(rnp, nocb); /* Declare grace period done. */ @@ -2284,8 +2300,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, raw_spin_unlock_irqrestore(&rnp->lock, flags); rnp_c = rnp; rnp = rnp->parent; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); oldmask = rnp_c->qsmask; } @@ -2332,8 +2347,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp, gps = rnp->gpnum; mask = rnp->grpmask; raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - raw_spin_lock(&rnp_p->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); + raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); } @@ -2355,8 +2369,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) struct rcu_node *rnp; rnp = rdp->mynode; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if ((rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || @@ -2582,8 +2595,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) rnp = rnp->parent; if (!rnp) break; - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); /* GP memory ordering. */ + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rnp->qsmaskinit &= ~mask; rnp->qsmask &= ~mask; if (rnp->qsmaskinit) { @@ -2611,8 +2623,7 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); /* Enforce GP memory-order guarantee. */ + raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ rnp->qsmaskinitnext &= ~mask; raw_spin_unlock_irqrestore(&rnp->lock, flags); } @@ -2809,8 +2820,7 @@ static void force_qs_rnp(struct rcu_state *rsp, rcu_for_each_leaf_node(rsp, rnp) { cond_resched_rcu_qs(); mask = 0; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || @@ -2881,8 +2891,7 @@ static void force_quiescent_state(struct rcu_state *rsp) /* rnp_old == rcu_get_root(rsp), rnp == NULL. */ /* Reached the root of the rcu_node tree, acquire lock. */ - raw_spin_lock_irqsave(&rnp_old->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp_old, flags); raw_spin_unlock(&rnp_old->fqslock); if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { rsp->n_force_qs_lh++; @@ -2914,7 +2923,7 @@ __rcu_process_callbacks(struct rcu_state *rsp) /* Does this CPU require a not-yet-started grace period? */ local_irq_save(flags); if (cpu_needs_another_gp(rsp, rdp)) { - raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */ + raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */ needwake = rcu_start_gp(rsp); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); if (needwake) @@ -3005,8 +3014,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, if (!rcu_gp_in_progress(rsp)) { struct rcu_node *rnp_root = rcu_get_root(rsp); - raw_spin_lock(&rnp_root->lock); - smp_mb__after_unlock_lock(); + raw_spin_lock_rcu_node(rnp_root); needwake = rcu_start_gp(rsp); raw_spin_unlock(&rnp_root->lock); if (needwake) @@ -3365,7 +3373,6 @@ static unsigned long rcu_seq_snap(unsigned long *sp) { unsigned long s; - smp_mb(); /* Caller's modifications seen first by other CPUs. */ s = (READ_ONCE(*sp) + 3) & ~0x1; smp_mb(); /* Above access must not bleed into critical section. */ return s; @@ -3392,6 +3399,7 @@ static void rcu_exp_gp_seq_end(struct rcu_state *rsp) } static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) { + smp_mb(); /* Caller's modifications seen first by other CPUs. */ return rcu_seq_snap(&rsp->expedited_sequence); } static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) @@ -3426,8 +3434,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) * CPUs for the current rcu_node structure up the rcu_node tree. */ rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmaskinit == rnp->expmaskinitnext) { raw_spin_unlock_irqrestore(&rnp->lock, flags); continue; /* No new CPUs, nothing to do. */ @@ -3447,8 +3454,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) rnp_up = rnp->parent; done = false; while (rnp_up) { - raw_spin_lock_irqsave(&rnp_up->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp_up, flags); if (rnp_up->expmaskinit) done = true; rnp_up->expmaskinit |= mask; @@ -3472,8 +3478,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) sync_exp_reset_tree_hotplug(rsp); rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); WARN_ON_ONCE(rnp->expmask); rnp->expmask = rnp->expmaskinit; raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -3531,8 +3536,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, mask = rnp->grpmask; raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ rnp = rnp->parent; - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - smp_mb__after_unlock_lock(); + raw_spin_lock_rcu_node(rnp); /* irqs already disabled */ WARN_ON_ONCE(!(rnp->expmask & mask)); rnp->expmask &= ~mask; } @@ -3549,8 +3553,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, { unsigned long flags; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); __rcu_report_exp_rnp(rsp, rnp, wake, flags); } @@ -3564,8 +3567,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, { unsigned long flags; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!(rnp->expmask & mask)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); return; @@ -3609,7 +3611,7 @@ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, */ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) { - struct rcu_data *rdp; + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); struct rcu_node *rnp0; struct rcu_node *rnp1 = NULL; @@ -3623,7 +3625,7 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) { if (mutex_trylock(&rnp0->exp_funnel_mutex)) { if (sync_exp_work_done(rsp, rnp0, NULL, - &rsp->expedited_workdone0, s)) + &rdp->expedited_workdone0, s)) return NULL; return rnp0; } @@ -3637,14 +3639,13 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) * can be inexact, as it is just promoting locality and is not * strictly needed for correctness. */ - rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); - if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s)) + if (sync_exp_work_done(rsp, NULL, NULL, &rdp->expedited_workdone1, s)) return NULL; mutex_lock(&rdp->exp_funnel_mutex); rnp0 = rdp->mynode; for (; rnp0 != NULL; rnp0 = rnp0->parent) { if (sync_exp_work_done(rsp, rnp1, rdp, - &rsp->expedited_workdone2, s)) + &rdp->expedited_workdone2, s)) return NULL; mutex_lock(&rnp0->exp_funnel_mutex); if (rnp1) @@ -3654,7 +3655,7 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) rnp1 = rnp0; } if (sync_exp_work_done(rsp, rnp1, rdp, - &rsp->expedited_workdone3, s)) + &rdp->expedited_workdone3, s)) return NULL; return rnp1; } @@ -3708,8 +3709,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, sync_exp_reset_tree(rsp); rcu_for_each_leaf_node(rsp, rnp) { - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Each pass checks a CPU for identity, offline, and idle. */ mask_ofl_test = 0; @@ -3741,24 +3741,22 @@ retry_ipi: ret = smp_call_function_single(cpu, func, rsp, 0); if (!ret) { mask_ofl_ipi &= ~mask; - } else { - /* Failed, raced with offline. */ - raw_spin_lock_irqsave(&rnp->lock, flags); - if (cpu_online(cpu) && - (rnp->expmask & mask)) { - raw_spin_unlock_irqrestore(&rnp->lock, - flags); - schedule_timeout_uninterruptible(1); - if (cpu_online(cpu) && - (rnp->expmask & mask)) - goto retry_ipi; - raw_spin_lock_irqsave(&rnp->lock, - flags); - } - if (!(rnp->expmask & mask)) - mask_ofl_ipi &= ~mask; + continue; + } + /* Failed, raced with offline. */ + raw_spin_lock_irqsave_rcu_node(rnp, flags); + if (cpu_online(cpu) && + (rnp->expmask & mask)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); + schedule_timeout_uninterruptible(1); + if (cpu_online(cpu) && + (rnp->expmask & mask)) + goto retry_ipi; + raw_spin_lock_irqsave_rcu_node(rnp, flags); } + if (!(rnp->expmask & mask)) + mask_ofl_ipi &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; @@ -3773,6 +3771,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) unsigned long jiffies_stall; unsigned long jiffies_start; unsigned long mask; + int ndetected; struct rcu_node *rnp; struct rcu_node *rnp_root = rcu_get_root(rsp); int ret; @@ -3785,7 +3784,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); - if (ret > 0) + if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root)) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ @@ -3795,14 +3794,16 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {", rsp->name); + ndetected = 0; rcu_for_each_leaf_node(rsp, rnp) { - (void)rcu_print_task_exp_stall(rnp); + ndetected = rcu_print_task_exp_stall(rnp); mask = 1; for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { struct rcu_data *rdp; if (!(rnp->expmask & mask)) continue; + ndetected++; rdp = per_cpu_ptr(rsp->rda, cpu); pr_cont(" %d-%c%c%c", cpu, "O."[cpu_online(cpu)], @@ -3811,8 +3812,23 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } mask <<= 1; } - pr_cont(" } %lu jiffies s: %lu\n", - jiffies - jiffies_start, rsp->expedited_sequence); + pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", + jiffies - jiffies_start, rsp->expedited_sequence, + rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]); + if (!ndetected) { + pr_err("blocking rcu_node structures:"); + rcu_for_each_node_breadth_first(rsp, rnp) { + if (rnp == rnp_root) + continue; /* printed unconditionally */ + if (sync_rcu_preempt_exp_done(rnp)) + continue; + pr_cont(" l=%u:%d-%d:%#lx/%c", + rnp->level, rnp->grplo, rnp->grphi, + rnp->expmask, + ".T"[!!rnp->exp_tasks]); + } + pr_cont("\n"); + } rcu_for_each_leaf_node(rsp, rnp) { mask = 1; for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { @@ -3847,6 +3863,16 @@ void synchronize_sched_expedited(void) struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; + /* If only one CPU, this is automatically a grace period. */ + if (rcu_blocking_is_gp()) + return; + + /* If expedited grace periods are prohibited, fall back to normal. */ + if (rcu_gp_is_normal()) { + wait_rcu_gp(call_rcu_sched); + return; + } + /* Take a snapshot of the sequence number. */ s = rcu_exp_gp_seq_snap(rsp); @@ -4135,7 +4161,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) rnp = rnp->parent; if (rnp == NULL) return; - raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */ + raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */ rnp->qsmaskinit |= mask; raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */ } @@ -4152,7 +4178,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); @@ -4179,7 +4205,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -4198,8 +4224,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) */ rnp = rdp->mynode; mask = rdp->grpmask; - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ rnp->qsmaskinitnext |= mask; rnp->expmaskinitnext |= mask; if (!rdp->beenonline) @@ -4327,14 +4352,14 @@ static int __init rcu_spawn_gp_kthread(void) t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name); BUG_ON(IS_ERR(t)); rnp = rcu_get_root(rsp); - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rsp->gp_kthread = t; if (kthread_prio) { sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } - wake_up_process(t); raw_spin_unlock_irqrestore(&rnp->lock, flags); + wake_up_process(t); } rcu_spawn_nocb_kthreads(); rcu_spawn_boost_kthreads(); @@ -4385,12 +4410,14 @@ static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt) /* * Helper function for rcu_init() that initializes one rcu_state structure. */ -static void __init rcu_init_one(struct rcu_state *rsp, - struct rcu_data __percpu *rda) +static void __init rcu_init_one(struct rcu_state *rsp) { static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; static const char * const exp[] = RCU_EXP_NAME_INIT; + static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; + static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; + static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -4576,8 +4603,8 @@ void __init rcu_init(void) rcu_bootup_announce(); rcu_init_geometry(); - rcu_init_one(&rcu_bh_state, &rcu_bh_data); - rcu_init_one(&rcu_sched_state, &rcu_sched_data); + rcu_init_one(&rcu_bh_state); + rcu_init_one(&rcu_sched_state); if (dump_tree) rcu_dump_rcu_node_tree(&rcu_sched_state); __rcu_init_preempt(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 9fb4e238d4dc..83360b4f4352 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -178,6 +178,8 @@ struct rcu_node { /* beginning of each expedited GP. */ unsigned long expmaskinitnext; /* Online CPUs for next expedited GP. */ + /* Any CPU that has ever been online will */ + /* have its bit set. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ int grplo; /* lowest-numbered CPU or group here. */ @@ -384,6 +386,10 @@ struct rcu_data { struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ struct mutex exp_funnel_mutex; + atomic_long_t expedited_workdone0; /* # done by others #0. */ + atomic_long_t expedited_workdone1; /* # done by others #1. */ + atomic_long_t expedited_workdone2; /* # done by others #2. */ + atomic_long_t expedited_workdone3; /* # done by others #3. */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -498,10 +504,6 @@ struct rcu_state { /* End of fields guarded by barrier_mutex. */ unsigned long expedited_sequence; /* Take a ticket. */ - atomic_long_t expedited_workdone0; /* # done by others #0. */ - atomic_long_t expedited_workdone1; /* # done by others #1. */ - atomic_long_t expedited_workdone2; /* # done by others #2. */ - atomic_long_t expedited_workdone3; /* # done by others #3. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ wait_queue_head_t expedited_wq; /* Wait for check-ins. */ @@ -545,6 +547,18 @@ struct rcu_state { #define RCU_GP_CLEANUP 5 /* Grace-period cleanup started. */ #define RCU_GP_CLEANED 6 /* Grace-period cleanup complete. */ +#ifndef RCU_TREE_NONCORE +static const char * const gp_state_names[] = { + "RCU_GP_IDLE", + "RCU_GP_WAIT_GPS", + "RCU_GP_DONE_GPS", + "RCU_GP_WAIT_FQS", + "RCU_GP_DOING_FQS", + "RCU_GP_CLEANUP", + "RCU_GP_CLEANED", +}; +#endif /* #ifndef RCU_TREE_NONCORE */ + extern struct list_head rcu_struct_flavors; /* Sequence through rcu_state structures for each RCU flavor. */ @@ -664,3 +678,42 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #else /* #ifdef CONFIG_PPC */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_PPC */ + +/* + * Wrappers for the rcu_node::lock acquire. + * + * Because the rcu_nodes form a tree, the tree traversal locking will observe + * different lock values, this in turn means that an UNLOCK of one level + * followed by a LOCK of another level does not imply a full memory barrier; + * and most importantly transitivity is lost. + * + * In order to restore full ordering between tree levels, augment the regular + * lock acquire functions with smp_mb__after_unlock_lock(). + */ +static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp) +{ + raw_spin_lock(&rnp->lock); + smp_mb__after_unlock_lock(); +} + +static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp) +{ + raw_spin_lock_irq(&rnp->lock); + smp_mb__after_unlock_lock(); +} + +#define raw_spin_lock_irqsave_rcu_node(rnp, flags) \ +do { \ + typecheck(unsigned long, flags); \ + raw_spin_lock_irqsave(&(rnp)->lock, flags); \ + smp_mb__after_unlock_lock(); \ +} while (0) + +static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp) +{ + bool locked = raw_spin_trylock(&rnp->lock); + + if (locked) + smp_mb__after_unlock_lock(); + return locked; +} diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 630c19772630..9467a8b7e756 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -63,8 +63,7 @@ static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ /* * Check the RCU kernel configuration parameters and print informative - * messages about anything out of the ordinary. If you like #ifdef, you - * will love this function. + * messages about anything out of the ordinary. */ static void __init rcu_bootup_announce_oddness(void) { @@ -147,8 +146,8 @@ static void __init rcu_bootup_announce(void) * the corresponding expedited grace period will also be the end of the * normal grace period. */ -static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, - unsigned long flags) __releases(rnp->lock) +static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) + __releases(rnp->lock) /* But leaves rrupts disabled. */ { int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + @@ -236,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, rnp->gp_tasks = &t->rcu_node_entry; if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) rnp->exp_tasks = &t->rcu_node_entry; - raw_spin_unlock(&rnp->lock); + raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */ /* * Report the quiescent state for the expedited GP. This expedited @@ -251,7 +250,6 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, } else { WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); } - local_irq_restore(flags); } /* @@ -286,12 +284,11 @@ static void rcu_preempt_qs(void) * predating the current grace period drain, in other words, until * rnp->gp_tasks becomes NULL. * - * Caller must disable preemption. + * Caller must disable interrupts. */ static void rcu_preempt_note_context_switch(void) { struct task_struct *t = current; - unsigned long flags; struct rcu_data *rdp; struct rcu_node *rnp; @@ -301,8 +298,7 @@ static void rcu_preempt_note_context_switch(void) /* Possibly blocking in an RCU read-side critical section. */ rdp = this_cpu_ptr(rcu_state_p->rda); rnp = rdp->mynode; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_rcu_node(rnp); t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; @@ -318,7 +314,7 @@ static void rcu_preempt_note_context_switch(void) (rnp->qsmask & rdp->grpmask) ? rnp->gpnum : rnp->gpnum + 1); - rcu_preempt_ctxt_queue(rnp, rdp, flags); + rcu_preempt_ctxt_queue(rnp, rdp); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -450,20 +446,13 @@ void rcu_read_unlock_special(struct task_struct *t) /* * Remove this task from the list it blocked on. The task - * now remains queued on the rcu_node corresponding to - * the CPU it first blocked on, so the first attempt to - * acquire the task's rcu_node's ->lock will succeed. - * Keep the loop and add a WARN_ON() out of sheer paranoia. + * now remains queued on the rcu_node corresponding to the + * CPU it first blocked on, so there is no longer any need + * to loop. Retain a WARN_ON_ONCE() out of sheer paranoia. */ - for (;;) { - rnp = t->rcu_blocked_node; - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); - if (rnp == t->rcu_blocked_node) - break; - WARN_ON_ONCE(1); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - } + rnp = t->rcu_blocked_node; + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + WARN_ON_ONCE(rnp != t->rcu_blocked_node); empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ @@ -527,7 +516,7 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) unsigned long flags; struct task_struct *t; - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!rcu_preempt_blocked_readers_cgp(rnp)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); return; @@ -748,6 +737,12 @@ void synchronize_rcu_expedited(void) struct rcu_state *rsp = rcu_state_p; unsigned long s; + /* If expedited grace periods are prohibited, fall back to normal. */ + if (rcu_gp_is_normal()) { + wait_rcu_gp(call_rcu); + return; + } + s = rcu_exp_gp_seq_snap(rsp); rnp_unlock = exp_funnel_lock(rsp, s); @@ -788,7 +783,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier); */ static void __init __rcu_init_preempt(void) { - rcu_init_one(rcu_state_p, rcu_data_p); + rcu_init_one(rcu_state_p); } /* @@ -989,8 +984,7 @@ static int rcu_boost(struct rcu_node *rnp) READ_ONCE(rnp->boost_tasks) == NULL) return 0; /* Nothing left to boost. */ - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); /* * Recheck under the lock: all tasks in need of boosting @@ -1176,8 +1170,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, "rcub/%d", rnp_index); if (IS_ERR(t)) return PTR_ERR(t); - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; raw_spin_unlock_irqrestore(&rnp->lock, flags); sp.sched_priority = kthread_prio; @@ -1524,7 +1517,8 @@ static void rcu_prepare_for_idle(void) struct rcu_state *rsp; int tne; - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || + rcu_is_nocb_cpu(smp_processor_id())) return; /* Handle nohz enablement switches conservatively. */ @@ -1538,10 +1532,6 @@ static void rcu_prepare_for_idle(void) if (!tne) return; - /* If this is a no-CBs CPU, no callbacks, just return. */ - if (rcu_is_nocb_cpu(smp_processor_id())) - return; - /* * If a non-lazy callback arrived at a CPU having only lazy * callbacks, invoke RCU core for the side-effect of recalculating @@ -1567,8 +1557,7 @@ static void rcu_prepare_for_idle(void) if (!*rdp->nxttail[RCU_DONE_TAIL]) continue; rnp = rdp->mynode; - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - smp_mb__after_unlock_lock(); + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ needwake = rcu_accelerate_cbs(rsp, rnp, rdp); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ if (needwake) @@ -2068,8 +2057,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) bool needwake; struct rcu_node *rnp = rdp->mynode; - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); needwake = rcu_start_future_gp(rnp, rdp, &c); raw_spin_unlock_irqrestore(&rnp->lock, flags); if (needwake) diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index ef7093cc9b5c..1088e64f01ad 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -1,5 +1,5 @@ /* - * Read-Copy Update tracing for classic implementation + * Read-Copy Update tracing for hierarchical implementation. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -16,6 +16,7 @@ * http://www.gnu.org/licenses/gpl-2.0.html. * * Copyright IBM Corporation, 2008 + * Author: Paul E. McKenney * * Papers: http://www.rdrop.com/users/paulmck/RCU * @@ -33,9 +34,7 @@ #include <linux/sched.h> #include <linux/atomic.h> #include <linux/bitops.h> -#include <linux/module.h> #include <linux/completion.h> -#include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/cpu.h> @@ -183,14 +182,20 @@ static const struct file_operations rcudata_fops = { static int show_rcuexp(struct seq_file *m, void *v) { + int cpu; struct rcu_state *rsp = (struct rcu_state *)m->private; - + struct rcu_data *rdp; + unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0; + + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(rsp->rda, cpu); + s0 += atomic_long_read(&rdp->expedited_workdone0); + s1 += atomic_long_read(&rdp->expedited_workdone1); + s2 += atomic_long_read(&rdp->expedited_workdone2); + s3 += atomic_long_read(&rdp->expedited_workdone3); + } seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n", - rsp->expedited_sequence, - atomic_long_read(&rsp->expedited_workdone0), - atomic_long_read(&rsp->expedited_workdone1), - atomic_long_read(&rsp->expedited_workdone2), - atomic_long_read(&rsp->expedited_workdone3), + rsp->expedited_sequence, s0, s1, s2, s3, atomic_long_read(&rsp->expedited_normal), atomic_read(&rsp->expedited_need_qs), rsp->expedited_sequence / 2); @@ -319,7 +324,7 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) unsigned long gpmax; struct rcu_node *rnp = &rsp->node[0]; - raw_spin_lock_irqsave(&rnp->lock, flags); + raw_spin_lock_irqsave_rcu_node(rnp, flags); completed = READ_ONCE(rsp->completed); gpnum = READ_ONCE(rsp->gpnum); if (completed == gpnum) @@ -487,16 +492,4 @@ free_out: debugfs_remove_recursive(rcudir); return 1; } - -static void __exit rcutree_trace_cleanup(void) -{ - debugfs_remove_recursive(rcudir); -} - - -module_init(rcutree_trace_init); -module_exit(rcutree_trace_cleanup); - -MODULE_AUTHOR("Paul E. McKenney"); -MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation"); -MODULE_LICENSE("GPL"); +device_initcall(rcutree_trace_init); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5f748c5a40f0..76b94e19430b 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -60,7 +60,12 @@ MODULE_ALIAS("rcupdate"); #endif #define MODULE_PARAM_PREFIX "rcupdate." +#ifndef CONFIG_TINY_RCU module_param(rcu_expedited, int, 0); +module_param(rcu_normal, int, 0); +static int rcu_normal_after_boot; +module_param(rcu_normal_after_boot, int, 0); +#endif /* #ifndef CONFIG_TINY_RCU */ #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT) /** @@ -113,6 +118,17 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held); #ifndef CONFIG_TINY_RCU +/* + * Should expedited grace-period primitives always fall back to their + * non-expedited counterparts? Intended for use within RCU. Note + * that if the user specifies both rcu_expedited and rcu_normal, then + * rcu_normal wins. + */ +bool rcu_gp_is_normal(void) +{ + return READ_ONCE(rcu_normal); +} + static atomic_t rcu_expedited_nesting = ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0); @@ -157,8 +173,6 @@ void rcu_unexpedite_gp(void) } EXPORT_SYMBOL_GPL(rcu_unexpedite_gp); -#endif /* #ifndef CONFIG_TINY_RCU */ - /* * Inform RCU of the end of the in-kernel boot sequence. */ @@ -166,8 +180,12 @@ void rcu_end_inkernel_boot(void) { if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT)) rcu_unexpedite_gp(); + if (rcu_normal_after_boot) + WRITE_ONCE(rcu_normal, 1); } +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_PREEMPT_RCU /* diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index 750ed601ddf7..a5d966cb8891 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -212,7 +212,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) ag = autogroup_task_get(p); down_write(&ag->lock); - err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]); + err = sched_group_set_shares(ag->tg, sched_prio_to_weight[nice + 20]); if (!err) ag->nice = nice; up_write(&ag->lock); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 732e993b564b..77d97a6fc715 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -731,7 +731,7 @@ bool sched_can_stop_tick(void) if (current->policy == SCHED_RR) { struct sched_rt_entity *rt_se = ¤t->rt; - return rt_se->run_list.prev == rt_se->run_list.next; + return list_is_singular(&rt_se->run_list); } /* @@ -823,8 +823,8 @@ static void set_load_weight(struct task_struct *p) return; } - load->weight = scale_load(prio_to_weight[prio]); - load->inv_weight = prio_to_wmult[prio]; + load->weight = scale_load(sched_prio_to_weight[prio]); + load->inv_weight = sched_prio_to_wmult[prio]; } static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) @@ -1071,8 +1071,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new { lockdep_assert_held(&rq->lock); - dequeue_task(rq, p, 0); p->on_rq = TASK_ON_RQ_MIGRATING; + dequeue_task(rq, p, 0); set_task_cpu(p, new_cpu); raw_spin_unlock(&rq->lock); @@ -1080,8 +1080,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new raw_spin_lock(&rq->lock); BUG_ON(task_cpu(p) != new_cpu); - p->on_rq = TASK_ON_RQ_QUEUED; enqueue_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_QUEUED; check_preempt_curr(rq, p, 0); return rq; @@ -1274,6 +1274,15 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && !p->on_rq); + /* + * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING, + * because schedstat_wait_{start,end} rebase migrating task's wait_start + * time relying on p->on_rq. + */ + WARN_ON_ONCE(p->state == TASK_RUNNING && + p->sched_class == &fair_sched_class && + (p->on_rq && !task_on_rq_migrating(p))); + #ifdef CONFIG_LOCKDEP /* * The caller should hold either p->pi_lock or rq->lock, when changing @@ -1310,9 +1319,11 @@ static void __migrate_swap_task(struct task_struct *p, int cpu) src_rq = task_rq(p); dst_rq = cpu_rq(cpu); + p->on_rq = TASK_ON_RQ_MIGRATING; deactivate_task(src_rq, p, 0); set_task_cpu(p, cpu); activate_task(dst_rq, p, 0); + p->on_rq = TASK_ON_RQ_QUEUED; check_preempt_curr(dst_rq, p, 0); } else { /* @@ -1905,6 +1916,97 @@ static void ttwu_queue(struct task_struct *p, int cpu) raw_spin_unlock(&rq->lock); } +/* + * Notes on Program-Order guarantees on SMP systems. + * + * MIGRATION + * + * The basic program-order guarantee on SMP systems is that when a task [t] + * migrates, all its activity on its old cpu [c0] happens-before any subsequent + * execution on its new cpu [c1]. + * + * For migration (of runnable tasks) this is provided by the following means: + * + * A) UNLOCK of the rq(c0)->lock scheduling out task t + * B) migration for t is required to synchronize *both* rq(c0)->lock and + * rq(c1)->lock (if not at the same time, then in that order). + * C) LOCK of the rq(c1)->lock scheduling in task + * + * Transitivity guarantees that B happens after A and C after B. + * Note: we only require RCpc transitivity. + * Note: the cpu doing B need not be c0 or c1 + * + * Example: + * + * CPU0 CPU1 CPU2 + * + * LOCK rq(0)->lock + * sched-out X + * sched-in Y + * UNLOCK rq(0)->lock + * + * LOCK rq(0)->lock // orders against CPU0 + * dequeue X + * UNLOCK rq(0)->lock + * + * LOCK rq(1)->lock + * enqueue X + * UNLOCK rq(1)->lock + * + * LOCK rq(1)->lock // orders against CPU2 + * sched-out Z + * sched-in X + * UNLOCK rq(1)->lock + * + * + * BLOCKING -- aka. SLEEP + WAKEUP + * + * For blocking we (obviously) need to provide the same guarantee as for + * migration. However the means are completely different as there is no lock + * chain to provide order. Instead we do: + * + * 1) smp_store_release(X->on_cpu, 0) + * 2) smp_cond_acquire(!X->on_cpu) + * + * Example: + * + * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule) + * + * LOCK rq(0)->lock LOCK X->pi_lock + * dequeue X + * sched-out X + * smp_store_release(X->on_cpu, 0); + * + * smp_cond_acquire(!X->on_cpu); + * X->state = WAKING + * set_task_cpu(X,2) + * + * LOCK rq(2)->lock + * enqueue X + * X->state = RUNNING + * UNLOCK rq(2)->lock + * + * LOCK rq(2)->lock // orders against CPU1 + * sched-out Z + * sched-in X + * UNLOCK rq(2)->lock + * + * UNLOCK X->pi_lock + * UNLOCK rq(0)->lock + * + * + * However; for wakeups there is a second guarantee we must provide, namely we + * must observe the state that lead to our wakeup. That is, not only must our + * task observe its own prior state, it must also observe the stores prior to + * its wakeup. + * + * This means that any means of doing remote wakeups must order the CPU doing + * the wakeup against the CPU the task is going to end up running on. This, + * however, is already required for the regular Program-Order guarantee above, + * since the waking CPU is the one issueing the ACQUIRE (smp_cond_acquire). + * + */ + /** * try_to_wake_up - wake up a thread * @p: the thread to be awakened @@ -1968,19 +2070,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) /* * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. - */ - while (p->on_cpu) - cpu_relax(); - /* - * Combined with the control dependency above, we have an effective - * smp_load_acquire() without the need for full barriers. * * Pairs with the smp_store_release() in finish_lock_switch(). * * This ensures that tasks getting woken will be fully ordered against * their previous state and preserve Program Order. */ - smp_rmb(); + smp_cond_acquire(!p->on_cpu); p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; @@ -2109,6 +2205,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.vruntime = 0; INIT_LIST_HEAD(&p->se.group_node); +#ifdef CONFIG_FAIR_GROUP_SCHED + p->se.cfs_rq = NULL; +#endif + #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif @@ -3109,7 +3209,6 @@ static void __sched notrace __schedule(bool preempt) cpu = smp_processor_id(); rq = cpu_rq(cpu); - rcu_note_context_switch(); prev = rq->curr; /* @@ -3128,13 +3227,16 @@ static void __sched notrace __schedule(bool preempt) if (sched_feat(HRTICK)) hrtick_clear(rq); + local_irq_disable(); + rcu_note_context_switch(); + /* * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) * done by the caller to avoid the race with signal_wake_up(). */ smp_mb__before_spinlock(); - raw_spin_lock_irq(&rq->lock); + raw_spin_lock(&rq->lock); lockdep_pin_lock(&rq->lock); rq->clock_skip_update <<= 1; /* promote REQ to ACT */ @@ -7355,6 +7457,9 @@ int in_sched_functions(unsigned long addr) */ struct task_group root_task_group; LIST_HEAD(task_groups); + +/* Cacheline aligned slab cache for task_group */ +static struct kmem_cache *task_group_cache __read_mostly; #endif DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); @@ -7412,11 +7517,12 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CGROUP_SCHED + task_group_cache = KMEM_CACHE(task_group, 0); + list_add(&root_task_group.list, &task_groups); INIT_LIST_HEAD(&root_task_group.children); INIT_LIST_HEAD(&root_task_group.siblings); autogroup_init(&init_task); - #endif /* CONFIG_CGROUP_SCHED */ for_each_possible_cpu(i) { @@ -7697,7 +7803,7 @@ static void free_sched_group(struct task_group *tg) free_fair_sched_group(tg); free_rt_sched_group(tg); autogroup_free(tg); - kfree(tg); + kmem_cache_free(task_group_cache, tg); } /* allocate runqueue etc for a new task group */ @@ -7705,7 +7811,7 @@ struct task_group *sched_create_group(struct task_group *parent) { struct task_group *tg; - tg = kzalloc(sizeof(*tg), GFP_KERNEL); + tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO); if (!tg) return ERR_PTR(-ENOMEM); @@ -8610,3 +8716,44 @@ void dump_cpu_task(int cpu) pr_info("Task dump for CPU %d:\n", cpu); sched_show_task(cpu_curr(cpu)); } + +/* + * Nice levels are multiplicative, with a gentle 10% change for every + * nice level changed. I.e. when a CPU-bound task goes from nice 0 to + * nice 1, it will get ~10% less CPU time than another CPU-bound task + * that remained on nice 0. + * + * The "10% effect" is relative and cumulative: from _any_ nice level, + * if you go up 1 level, it's -10% CPU usage, if you go down 1 level + * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. + * If a task goes up by ~10% and another task goes down by ~10% then + * the relative distance between them is ~25%.) + */ +const int sched_prio_to_weight[40] = { + /* -20 */ 88761, 71755, 56483, 46273, 36291, + /* -15 */ 29154, 23254, 18705, 14949, 11916, + /* -10 */ 9548, 7620, 6100, 4904, 3906, + /* -5 */ 3121, 2501, 1991, 1586, 1277, + /* 0 */ 1024, 820, 655, 526, 423, + /* 5 */ 335, 272, 215, 172, 137, + /* 10 */ 110, 87, 70, 56, 45, + /* 15 */ 36, 29, 23, 18, 15, +}; + +/* + * Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated. + * + * In cases where the weight does not change often, we can use the + * precalculated inverse to speed up arithmetics by turning divisions + * into multiplications: + */ +const u32 sched_prio_to_wmult[40] = { + /* -20 */ 48388, 59856, 76040, 92818, 118348, + /* -15 */ 147320, 184698, 229616, 287308, 360437, + /* -10 */ 449829, 563644, 704093, 875809, 1099582, + /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, + /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, + /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, + /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, + /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, +}; diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 05de80b48586..d5ff5c6bf829 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -466,7 +466,7 @@ void account_process_tick(struct task_struct *p, int user_tick) cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) return; if (sched_clock_irqtime) { @@ -680,7 +680,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) { unsigned long long delta = vtime_delta(tsk); - WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING); + WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); tsk->vtime_snap += delta; /* CHECKME: always safe to convert nsecs to cputime? */ @@ -696,37 +696,37 @@ static void __vtime_account_system(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_gen_account_irq_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_account_user(struct task_struct *tsk) { cputime_t delta_cpu; - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); delta_cpu = get_vtime_delta(tsk); tsk->vtime_snap_whence = VTIME_SYS; account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_user_enter(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); tsk->vtime_snap_whence = VTIME_USER; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } void vtime_guest_enter(struct task_struct *tsk) @@ -738,19 +738,19 @@ void vtime_guest_enter(struct task_struct *tsk) * synchronization against the reader (task_gtime()) * that can thus safely catch up with a tickless delta. */ - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); current->flags |= PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_enter); void vtime_guest_exit(struct task_struct *tsk) { - write_seqlock(&tsk->vtime_seqlock); + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); current->flags &= ~PF_VCPU; - write_sequnlock(&tsk->vtime_seqlock); + write_seqcount_end(&tsk->vtime_seqcount); } EXPORT_SYMBOL_GPL(vtime_guest_exit); @@ -763,24 +763,26 @@ void vtime_account_idle(struct task_struct *tsk) void arch_vtime_task_switch(struct task_struct *prev) { - write_seqlock(&prev->vtime_seqlock); - prev->vtime_snap_whence = VTIME_SLEEPING; - write_sequnlock(&prev->vtime_seqlock); + write_seqcount_begin(&prev->vtime_seqcount); + prev->vtime_snap_whence = VTIME_INACTIVE; + write_seqcount_end(&prev->vtime_seqcount); - write_seqlock(¤t->vtime_seqlock); + write_seqcount_begin(¤t->vtime_seqcount); current->vtime_snap_whence = VTIME_SYS; current->vtime_snap = sched_clock_cpu(smp_processor_id()); - write_sequnlock(¤t->vtime_seqlock); + write_seqcount_end(¤t->vtime_seqcount); } void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; - write_seqlock_irqsave(&t->vtime_seqlock, flags); + local_irq_save(flags); + write_seqcount_begin(&t->vtime_seqcount); t->vtime_snap_whence = VTIME_SYS; t->vtime_snap = sched_clock_cpu(cpu); - write_sequnlock_irqrestore(&t->vtime_seqlock, flags); + write_seqcount_end(&t->vtime_seqcount); + local_irq_restore(flags); } cputime_t task_gtime(struct task_struct *t) @@ -788,17 +790,17 @@ cputime_t task_gtime(struct task_struct *t) unsigned int seq; cputime_t gtime; - if (!context_tracking_is_enabled()) + if (!vtime_accounting_enabled()) return t->gtime; do { - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seqcount); gtime = t->gtime; - if (t->flags & PF_VCPU) + if (t->vtime_snap_whence == VTIME_SYS && t->flags & PF_VCPU) gtime += vtime_delta(t); - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seqcount, seq)); return gtime; } @@ -821,7 +823,7 @@ fetch_task_cputime(struct task_struct *t, *udelta = 0; *sdelta = 0; - seq = read_seqbegin(&t->vtime_seqlock); + seq = read_seqcount_begin(&t->vtime_seqcount); if (u_dst) *u_dst = *u_src; @@ -829,7 +831,7 @@ fetch_task_cputime(struct task_struct *t, *s_dst = *s_src; /* Task is sleeping, nothing to add */ - if (t->vtime_snap_whence == VTIME_SLEEPING || + if (t->vtime_snap_whence == VTIME_INACTIVE || is_idle_task(t)) continue; @@ -845,7 +847,7 @@ fetch_task_cputime(struct task_struct *t, if (t->vtime_snap_whence == VTIME_SYS) *sdelta = delta; } - } while (read_seqretry(&t->vtime_seqlock, seq)); + } while (read_seqcount_retry(&t->vtime_seqcount, seq)); } @@ -853,6 +855,14 @@ void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) { cputime_t udelta, sdelta; + if (!vtime_accounting_enabled()) { + if (utime) + *utime = t->utime; + if (stime) + *stime = t->stime; + return; + } + fetch_task_cputime(t, utime, stime, &t->utime, &t->stime, &udelta, &sdelta); if (utime) @@ -866,6 +876,14 @@ void task_cputime_scaled(struct task_struct *t, { cputime_t udelta, sdelta; + if (!vtime_accounting_enabled()) { + if (utimescaled) + *utimescaled = t->utimescaled; + if (stimescaled) + *stimescaled = t->stimescaled; + return; + } + fetch_task_cputime(t, utimescaled, stimescaled, &t->utimescaled, &t->stimescaled, &udelta, &sdelta); if (utimescaled) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 8b0a15e285f9..cd64c979d0e1 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -176,8 +176,10 @@ static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) } } - if (leftmost) + if (leftmost) { dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks; + dl_rq->earliest_dl.next = p->dl.deadline; + } rb_link_node(&p->pushable_dl_tasks, parent, link); rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); @@ -195,6 +197,10 @@ static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) next_node = rb_next(&p->pushable_dl_tasks); dl_rq->pushable_dl_tasks_leftmost = next_node; + if (next_node) { + dl_rq->earliest_dl.next = rb_entry(next_node, + struct task_struct, pushable_dl_tasks)->dl.deadline; + } } rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); @@ -782,42 +788,14 @@ static void update_curr_dl(struct rq *rq) #ifdef CONFIG_SMP -static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu); - -static inline u64 next_deadline(struct rq *rq) -{ - struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu); - - if (next && dl_prio(next->prio)) - return next->dl.deadline; - else - return 0; -} - static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) { struct rq *rq = rq_of_dl_rq(dl_rq); if (dl_rq->earliest_dl.curr == 0 || dl_time_before(deadline, dl_rq->earliest_dl.curr)) { - /* - * If the dl_rq had no -deadline tasks, or if the new task - * has shorter deadline than the current one on dl_rq, we - * know that the previous earliest becomes our next earliest, - * as the new task becomes the earliest itself. - */ - dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr; dl_rq->earliest_dl.curr = deadline; cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1); - } else if (dl_rq->earliest_dl.next == 0 || - dl_time_before(deadline, dl_rq->earliest_dl.next)) { - /* - * On the other hand, if the new -deadline task has a - * a later deadline than the earliest one on dl_rq, but - * it is earlier than the next (if any), we must - * recompute the next-earliest. - */ - dl_rq->earliest_dl.next = next_deadline(rq); } } @@ -839,7 +817,6 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) entry = rb_entry(leftmost, struct sched_dl_entity, rb_node); dl_rq->earliest_dl.curr = entry->deadline; - dl_rq->earliest_dl.next = next_deadline(rq); cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1); } } @@ -1274,28 +1251,6 @@ static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) return 0; } -/* Returns the second earliest -deadline task, NULL otherwise */ -static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu) -{ - struct rb_node *next_node = rq->dl.rb_leftmost; - struct sched_dl_entity *dl_se; - struct task_struct *p = NULL; - -next_node: - next_node = rb_next(next_node); - if (next_node) { - dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); - p = dl_task_of(dl_se); - - if (pick_dl_task(rq, p, cpu)) - return p; - - goto next_node; - } - - return NULL; -} - /* * Return the earliest pushable rq's task, which is suitable to be executed * on the CPU, NULL otherwise: diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 90e26b11deaa..1926606ece80 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -738,12 +738,56 @@ static void update_curr_fair(struct rq *rq) update_curr(cfs_rq_of(&rq->curr->se)); } +#ifdef CONFIG_SCHEDSTATS +static inline void +update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + u64 wait_start = rq_clock(rq_of(cfs_rq)); + + if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) && + likely(wait_start > se->statistics.wait_start)) + wait_start -= se->statistics.wait_start; + + se->statistics.wait_start = wait_start; +} + +static void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct task_struct *p; + u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; + + if (entity_is_task(se)) { + p = task_of(se); + if (task_on_rq_migrating(p)) { + /* + * Preserve migrating task's wait time so wait_start + * time stamp can be adjusted to accumulate wait time + * prior to migration. + */ + se->statistics.wait_start = delta; + return; + } + trace_sched_stat_wait(p, delta); + } + + se->statistics.wait_max = max(se->statistics.wait_max, delta); + se->statistics.wait_count++; + se->statistics.wait_sum += delta; + se->statistics.wait_start = 0; +} +#else static inline void update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) { - schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq))); } +static inline void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} +#endif + /* * Task is being enqueued - update stats: */ @@ -757,23 +801,6 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) update_stats_wait_start(cfs_rq, se); } -static void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max, - rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start)); - schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1); - schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum + - rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); -#ifdef CONFIG_SCHEDSTATS - if (entity_is_task(se)) { - trace_sched_stat_wait(task_of(se), - rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start); - } -#endif - schedstat_set(se->statistics.wait_start, 0); -} - static inline void update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -2155,6 +2182,7 @@ void task_numa_work(struct callback_head *work) unsigned long migrate, next_scan, now = jiffies; struct task_struct *p = current; struct mm_struct *mm = p->mm; + u64 runtime = p->se.sum_exec_runtime; struct vm_area_struct *vma; unsigned long start, end; unsigned long nr_pte_updates = 0; @@ -2277,6 +2305,17 @@ out: else reset_ptenuma_scan(p); up_read(&mm->mmap_sem); + + /* + * Make sure tasks use at least 32x as much time to run other code + * than they used here, to limit NUMA PTE scanning overhead to 3% max. + * Usually update_task_scan_period slows down scanning enough; on an + * overloaded system we need to limit overhead on a per task basis. + */ + if (unlikely(p->se.sum_exec_runtime != runtime)) { + u64 diff = p->se.sum_exec_runtime - runtime; + p->node_stamp += 32 * diff; + } } /* @@ -2670,12 +2709,64 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) { long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib; + /* + * No need to update load_avg for root_task_group as it is not used. + */ + if (cfs_rq->tg == &root_task_group) + return; + if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) { atomic_long_add(delta, &cfs_rq->tg->load_avg); cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg; } } +/* + * Called within set_task_rq() right before setting a task's cpu. The + * caller only guarantees p->pi_lock is held; no other assumptions, + * including the state of rq->lock, should be made. + */ +void set_task_rq_fair(struct sched_entity *se, + struct cfs_rq *prev, struct cfs_rq *next) +{ + if (!sched_feat(ATTACH_AGE_LOAD)) + return; + + /* + * We are supposed to update the task to "current" time, then its up to + * date and ready to go to new CPU/cfs_rq. But we have difficulty in + * getting what current time is, so simply throw away the out-of-date + * time. This will result in the wakee task is less decayed, but giving + * the wakee more load sounds not bad. + */ + if (se->avg.last_update_time && prev) { + u64 p_last_update_time; + u64 n_last_update_time; + +#ifndef CONFIG_64BIT + u64 p_last_update_time_copy; + u64 n_last_update_time_copy; + + do { + p_last_update_time_copy = prev->load_last_update_time_copy; + n_last_update_time_copy = next->load_last_update_time_copy; + + smp_rmb(); + + p_last_update_time = prev->avg.last_update_time; + n_last_update_time = next->avg.last_update_time; + + } while (p_last_update_time != p_last_update_time_copy || + n_last_update_time != n_last_update_time_copy); +#else + p_last_update_time = prev->avg.last_update_time; + n_last_update_time = next->avg.last_update_time; +#endif + __update_load_avg(p_last_update_time, cpu_of(rq_of(prev)), + &se->avg, 0, 0, NULL); + se->avg.last_update_time = n_last_update_time; + } +} #else /* CONFIG_FAIR_GROUP_SCHED */ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -2689,7 +2780,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) int decayed, removed = 0; if (atomic_long_read(&cfs_rq->removed_load_avg)) { - long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); + s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); sa->load_avg = max_t(long, sa->load_avg - r, 0); sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); removed = 1; @@ -2809,48 +2900,48 @@ dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) max_t(s64, cfs_rq->runnable_load_sum - se->avg.load_sum, 0); } -/* - * Task first catches up with cfs_rq, and then subtract - * itself from the cfs_rq (task must be off the queue now). - */ -void remove_entity_load_avg(struct sched_entity *se) -{ - struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 last_update_time; - #ifndef CONFIG_64BIT +static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) +{ u64 last_update_time_copy; + u64 last_update_time; do { last_update_time_copy = cfs_rq->load_last_update_time_copy; smp_rmb(); last_update_time = cfs_rq->avg.last_update_time; } while (last_update_time != last_update_time_copy); -#else - last_update_time = cfs_rq->avg.last_update_time; -#endif - __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL); - atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg); - atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg); + return last_update_time; } - -/* - * Update the rq's load with the elapsed running time before entering - * idle. if the last scheduled task is not a CFS task, idle_enter will - * be the only way to update the runnable statistic. - */ -void idle_enter_fair(struct rq *this_rq) +#else +static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) { + return cfs_rq->avg.last_update_time; } +#endif /* - * Update the rq's load with the elapsed idle time before a task is - * scheduled. if the newly scheduled task is not a CFS task, idle_exit will - * be the only way to update the runnable statistic. + * Task first catches up with cfs_rq, and then subtract + * itself from the cfs_rq (task must be off the queue now). */ -void idle_exit_fair(struct rq *this_rq) +void remove_entity_load_avg(struct sched_entity *se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 last_update_time; + + /* + * Newly created task or never used group entity should not be removed + * from its (source) cfs_rq + */ + if (se->avg.last_update_time == 0) + return; + + last_update_time = cfs_rq_last_update_time(cfs_rq); + + __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL); + atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg); + atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg); } static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq) @@ -4240,42 +4331,37 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) */ /* - * The exact cpuload at various idx values, calculated at every tick would be - * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load + * The exact cpuload calculated at every tick would be: + * + * load' = (1 - 1/2^i) * load + (1/2^i) * cur_load * - * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called - * on nth tick when cpu may be busy, then we have: - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load + * If a cpu misses updates for n ticks (as it was idle) and update gets + * called on the n+1-th tick when cpu may be busy, then we have: + * + * load_n = (1 - 1/2^i)^n * load_0 + * load_n+1 = (1 - 1/2^i) * load_n + (1/2^i) * cur_load * * decay_load_missed() below does efficient calculation of - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load + * + * load' = (1 - 1/2^i)^n * load + * + * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors. + * This allows us to precompute the above in said factors, thereby allowing the + * reduction of an arbitrary n in O(log_2 n) steps. (See also + * fixed_power_int()) * * The calculation is approximated on a 128 point scale. - * degrade_zero_ticks is the number of ticks after which load at any - * particular idx is approximated to be zero. - * degrade_factor is a precomputed table, a row for each load idx. - * Each column corresponds to degradation factor for a power of two ticks, - * based on 128 point scale. - * Example: - * row 2, col 3 (=12) says that the degradation at load idx 2 after - * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). - * - * With this power of 2 load factors, we can degrade the load n times - * by looking at 1 bits in n and doing as many mult/shift instead of - * n mult/shifts needed by the exact degradation. */ #define DEGRADE_SHIFT 7 -static const unsigned char - degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; -static const unsigned char - degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { - {0, 0, 0, 0, 0, 0, 0, 0}, - {64, 32, 8, 0, 0, 0, 0, 0}, - {96, 72, 40, 12, 1, 0, 0}, - {112, 98, 75, 43, 15, 1, 0}, - {120, 112, 98, 76, 45, 16, 2} }; + +static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + { 0, 0, 0, 0, 0, 0, 0, 0 }, + { 64, 32, 8, 0, 0, 0, 0, 0 }, + { 96, 72, 40, 12, 1, 0, 0, 0 }, + { 112, 98, 75, 43, 15, 1, 0, 0 }, + { 120, 112, 98, 76, 45, 16, 2, 0 } +}; /* * Update cpu_load for any missed ticks, due to tickless idle. The backlog @@ -4306,14 +4392,46 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) return load; } -/* +/** + * __update_cpu_load - update the rq->cpu_load[] statistics + * @this_rq: The rq to update statistics for + * @this_load: The current load + * @pending_updates: The number of missed updates + * @active: !0 for NOHZ_FULL + * * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). With tickless idle this will not be called - * every tick. We fix it up based on jiffies. + * scheduler tick (TICK_NSEC). + * + * This function computes a decaying average: + * + * load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load + * + * Because of NOHZ it might not get called on every tick which gives need for + * the @pending_updates argument. + * + * load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1 + * = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load + * = A * (A * load[i]_n-2 + B) + B + * = A * (A * (A * load[i]_n-3 + B) + B) + B + * = A^3 * load[i]_n-3 + (A^2 + A + 1) * B + * = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B + * = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B + * = (1 - 1/2^i)^n * (load[i]_0 - load) + load + * + * In the above we've assumed load_n := load, which is true for NOHZ_FULL as + * any change in load would have resulted in the tick being turned back on. + * + * For regular NOHZ, this reduces to: + * + * load[i]_n = (1 - 1/2^i)^n * load[i]_0 + * + * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra + * term. See the @active paramter. */ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, - unsigned long pending_updates) + unsigned long pending_updates, int active) { + unsigned long tickless_load = active ? this_rq->cpu_load[0] : 0; int i, scale; this_rq->nr_load_updates++; @@ -4325,8 +4443,9 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, /* scale is effectively 1 << i now, and >> i divides by scale */ - old_load = this_rq->cpu_load[i]; + old_load = this_rq->cpu_load[i] - tickless_load; old_load = decay_load_missed(old_load, pending_updates - 1, i); + old_load += tickless_load; new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -4381,16 +4500,17 @@ static void update_idle_cpu_load(struct rq *this_rq) pending_updates = curr_jiffies - this_rq->last_load_update_tick; this_rq->last_load_update_tick = curr_jiffies; - __update_cpu_load(this_rq, load, pending_updates); + __update_cpu_load(this_rq, load, pending_updates, 0); } /* * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed. */ -void update_cpu_load_nohz(void) +void update_cpu_load_nohz(int active) { struct rq *this_rq = this_rq(); unsigned long curr_jiffies = READ_ONCE(jiffies); + unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0; unsigned long pending_updates; if (curr_jiffies == this_rq->last_load_update_tick) @@ -4401,10 +4521,11 @@ void update_cpu_load_nohz(void) if (pending_updates) { this_rq->last_load_update_tick = curr_jiffies; /* - * We were idle, this means load 0, the current load might be - * !0 due to remote wakeups and the sort. + * In the regular NOHZ case, we were idle, this means load 0. + * In the NOHZ_FULL case, we were non-idle, we should consider + * its weighted load. */ - __update_cpu_load(this_rq, 0, pending_updates); + __update_cpu_load(this_rq, load, pending_updates, active); } raw_spin_unlock(&this_rq->lock); } @@ -4420,7 +4541,7 @@ void update_cpu_load_active(struct rq *this_rq) * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). */ this_rq->last_load_update_tick = jiffies; - __update_cpu_load(this_rq, load, 1); + __update_cpu_load(this_rq, load, 1, 1); } /* @@ -5007,8 +5128,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f /* * Called immediately before a task is migrated to a new cpu; task_cpu(p) and * cfs_rq_of(p) references at time of call are still valid and identify the - * previous cpu. However, the caller only guarantees p->pi_lock is held; no - * other assumptions, including the state of rq->lock, should be made. + * previous cpu. The caller guarantees p->pi_lock or task_rq(p)->lock is held. */ static void migrate_task_rq_fair(struct task_struct *p) { @@ -5721,8 +5841,8 @@ static void detach_task(struct task_struct *p, struct lb_env *env) { lockdep_assert_held(&env->src_rq->lock); - deactivate_task(env->src_rq, p, 0); p->on_rq = TASK_ON_RQ_MIGRATING; + deactivate_task(env->src_rq, p, 0); set_task_cpu(p, env->dst_cpu); } @@ -5855,8 +5975,8 @@ static void attach_task(struct rq *rq, struct task_struct *p) lockdep_assert_held(&rq->lock); BUG_ON(task_rq(p) != rq); - p->on_rq = TASK_ON_RQ_QUEUED; activate_task(rq, p, 0); + p->on_rq = TASK_ON_RQ_QUEUED; check_preempt_curr(rq, p, 0); } @@ -6302,7 +6422,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, bool *overload) { unsigned long load; - int i; + int i, nr_running; memset(sgs, 0, sizeof(*sgs)); @@ -6319,7 +6439,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_util += cpu_util(i); sgs->sum_nr_running += rq->cfs.h_nr_running; - if (rq->nr_running > 1) + nr_running = rq->nr_running; + if (nr_running > 1) *overload = true; #ifdef CONFIG_NUMA_BALANCING @@ -6327,7 +6448,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->nr_preferred_running += rq->nr_preferred_running; #endif sgs->sum_weighted_load += weighted_cpuload(i); - if (idle_cpu(i)) + /* + * No need to call idle_cpu() if nr_running is not 0 + */ + if (!nr_running && idle_cpu(i)) sgs->idle_cpus++; } @@ -7248,8 +7372,6 @@ static int idle_balance(struct rq *this_rq) int pulled_task = 0; u64 curr_cost = 0; - idle_enter_fair(this_rq); - /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. @@ -7330,10 +7452,8 @@ out: if (this_rq->nr_running != this_rq->cfs.h_nr_running) pulled_task = -1; - if (pulled_task) { - idle_exit_fair(this_rq); + if (pulled_task) this_rq->idle_stamp = 0; - } return pulled_task; } diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index c4ae0f1fdf9b..47ce94931f1b 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -47,7 +47,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { - idle_exit_fair(rq); rq_last_tick_reset(rq); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b242775bf670..10f16374df7f 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -248,7 +248,12 @@ struct task_group { unsigned long shares; #ifdef CONFIG_SMP - atomic_long_t load_avg; + /* + * load_avg can be heavily contended at clock tick time, so put + * it in its own cacheline separated from the fields above which + * will also be accessed at each tick. + */ + atomic_long_t load_avg ____cacheline_aligned; #endif #endif @@ -335,7 +340,15 @@ extern void sched_move_task(struct task_struct *tsk); #ifdef CONFIG_FAIR_GROUP_SCHED extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); -#endif + +#ifdef CONFIG_SMP +extern void set_task_rq_fair(struct sched_entity *se, + struct cfs_rq *prev, struct cfs_rq *next); +#else /* !CONFIG_SMP */ +static inline void set_task_rq_fair(struct sched_entity *se, + struct cfs_rq *prev, struct cfs_rq *next) { } +#endif /* CONFIG_SMP */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ #else /* CONFIG_CGROUP_SCHED */ @@ -933,6 +946,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #endif #ifdef CONFIG_FAIR_GROUP_SCHED + set_task_rq_fair(&p->se, p->se.cfs_rq, tg->cfs_rq[cpu]); p->se.cfs_rq = tg->cfs_rq[cpu]; p->se.parent = tg->se[cpu]; #endif @@ -1076,7 +1090,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) * In particular, the load of prev->state in finish_task_switch() must * happen before this. * - * Pairs with the control dependency and rmb in try_to_wake_up(). + * Pairs with the smp_cond_acquire() in try_to_wake_up(). */ smp_store_release(&prev->on_cpu, 0); #endif @@ -1113,46 +1127,8 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #define WEIGHT_IDLEPRIO 3 #define WMULT_IDLEPRIO 1431655765 -/* - * Nice levels are multiplicative, with a gentle 10% change for every - * nice level changed. I.e. when a CPU-bound task goes from nice 0 to - * nice 1, it will get ~10% less CPU time than another CPU-bound task - * that remained on nice 0. - * - * The "10% effect" is relative and cumulative: from _any_ nice level, - * if you go up 1 level, it's -10% CPU usage, if you go down 1 level - * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. - * If a task goes up by ~10% and another task goes down by ~10% then - * the relative distance between them is ~25%.) - */ -static const int prio_to_weight[40] = { - /* -20 */ 88761, 71755, 56483, 46273, 36291, - /* -15 */ 29154, 23254, 18705, 14949, 11916, - /* -10 */ 9548, 7620, 6100, 4904, 3906, - /* -5 */ 3121, 2501, 1991, 1586, 1277, - /* 0 */ 1024, 820, 655, 526, 423, - /* 5 */ 335, 272, 215, 172, 137, - /* 10 */ 110, 87, 70, 56, 45, - /* 15 */ 36, 29, 23, 18, 15, -}; - -/* - * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. - * - * In cases where the weight does not change often, we can use the - * precalculated inverse to speed up arithmetics by turning divisions - * into multiplications: - */ -static const u32 prio_to_wmult[40] = { - /* -20 */ 48388, 59856, 76040, 92818, 118348, - /* -15 */ 147320, 184698, 229616, 287308, 360437, - /* -10 */ 449829, 563644, 704093, 875809, 1099582, - /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, - /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, - /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, - /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, - /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, -}; +extern const int sched_prio_to_weight[40]; +extern const u32 sched_prio_to_wmult[40]; #define ENQUEUE_WAKEUP 0x01 #define ENQUEUE_HEAD 0x02 @@ -1252,16 +1228,8 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); -extern void idle_enter_fair(struct rq *this_rq); -extern void idle_exit_fair(struct rq *this_rq); - extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask); -#else - -static inline void idle_enter_fair(struct rq *rq) { } -static inline void idle_exit_fair(struct rq *rq) { } - #endif #ifdef CONFIG_CPU_IDLE diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index a3bbaee77c58..edb6de4f5908 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -28,7 +28,6 @@ */ struct cpu_stop_done { atomic_t nr_todo; /* nr left to execute */ - bool executed; /* actually executed? */ int ret; /* collected return value */ struct completion completion; /* fired if nr_todo reaches 0 */ }; @@ -63,14 +62,10 @@ static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) } /* signal completion unless @done is NULL */ -static void cpu_stop_signal_done(struct cpu_stop_done *done, bool executed) +static void cpu_stop_signal_done(struct cpu_stop_done *done) { - if (done) { - if (executed) - done->executed = true; - if (atomic_dec_and_test(&done->nr_todo)) - complete(&done->completion); - } + if (atomic_dec_and_test(&done->nr_todo)) + complete(&done->completion); } static void __cpu_stop_queue_work(struct cpu_stopper *stopper, @@ -81,17 +76,21 @@ static void __cpu_stop_queue_work(struct cpu_stopper *stopper, } /* queue @work to @stopper. if offline, @work is completed immediately */ -static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) +static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); unsigned long flags; + bool enabled; spin_lock_irqsave(&stopper->lock, flags); - if (stopper->enabled) + enabled = stopper->enabled; + if (enabled) __cpu_stop_queue_work(stopper, work); - else - cpu_stop_signal_done(work->done, false); + else if (work->done) + cpu_stop_signal_done(work->done); spin_unlock_irqrestore(&stopper->lock, flags); + + return enabled; } /** @@ -124,9 +123,10 @@ int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg) struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done }; cpu_stop_init_done(&done, 1); - cpu_stop_queue_work(cpu, &work); + if (!cpu_stop_queue_work(cpu, &work)) + return -ENOENT; wait_for_completion(&done.completion); - return done.executed ? done.ret : -ENOENT; + return done.ret; } /* This controls the threads on each CPU. */ @@ -258,7 +258,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * struct cpu_stop_work work1, work2; struct multi_stop_data msdata; - preempt_disable(); msdata = (struct multi_stop_data){ .fn = fn, .data = arg, @@ -277,16 +276,11 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * if (cpu1 > cpu2) swap(cpu1, cpu2); - if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) { - preempt_enable(); + if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) return -ENOENT; - } - - preempt_enable(); wait_for_completion(&done.completion); - - return done.executed ? done.ret : -ENOENT; + return done.ret; } /** @@ -302,23 +296,28 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * * * CONTEXT: * Don't care. + * + * RETURNS: + * true if cpu_stop_work was queued successfully and @fn will be called, + * false otherwise. */ -void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, +bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, }; - cpu_stop_queue_work(cpu, work_buf); + return cpu_stop_queue_work(cpu, work_buf); } /* static data for stop_cpus */ static DEFINE_MUTEX(stop_cpus_mutex); -static void queue_stop_cpus_work(const struct cpumask *cpumask, +static bool queue_stop_cpus_work(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg, struct cpu_stop_done *done) { struct cpu_stop_work *work; unsigned int cpu; + bool queued = false; /* * Disable preemption while queueing to avoid getting @@ -331,9 +330,12 @@ static void queue_stop_cpus_work(const struct cpumask *cpumask, work->fn = fn; work->arg = arg; work->done = done; - cpu_stop_queue_work(cpu, work); + if (cpu_stop_queue_work(cpu, work)) + queued = true; } lg_global_unlock(&stop_cpus_lock); + + return queued; } static int __stop_cpus(const struct cpumask *cpumask, @@ -342,9 +344,10 @@ static int __stop_cpus(const struct cpumask *cpumask, struct cpu_stop_done done; cpu_stop_init_done(&done, cpumask_weight(cpumask)); - queue_stop_cpus_work(cpumask, fn, arg, &done); + if (!queue_stop_cpus_work(cpumask, fn, arg, &done)) + return -ENOENT; wait_for_completion(&done.completion); - return done.executed ? done.ret : -ENOENT; + return done.ret; } /** @@ -432,7 +435,6 @@ static void cpu_stopper_thread(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); struct cpu_stop_work *work; - int ret; repeat: work = NULL; @@ -448,23 +450,19 @@ repeat: cpu_stop_fn_t fn = work->fn; void *arg = work->arg; struct cpu_stop_done *done = work->done; - char ksym_buf[KSYM_NAME_LEN] __maybe_unused; - - /* cpu stop callbacks are not allowed to sleep */ - preempt_disable(); + int ret; + /* cpu stop callbacks must not sleep, make in_atomic() == T */ + preempt_count_inc(); ret = fn(arg); - if (ret) - done->ret = ret; - - /* restore preemption and check it's still balanced */ - preempt_enable(); + if (done) { + if (ret) + done->ret = ret; + cpu_stop_signal_done(done); + } + preempt_count_dec(); WARN_ONCE(preempt_count(), - "cpu_stop: %s(%p) leaked preempt count\n", - kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL, - ksym_buf), arg); - - cpu_stop_signal_done(done, true); + "cpu_stop: %pf(%p) leaked preempt count\n", fn, arg); goto repeat; } } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 7c7ec4515983..11ce59916c1a 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -694,11 +694,11 @@ out: return tick; } -static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) +static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now, int active) { /* Update jiffies first */ tick_do_update_jiffies64(now); - update_cpu_load_nohz(); + update_cpu_load_nohz(active); calc_load_exit_idle(); touch_softlockup_watchdog(); @@ -725,7 +725,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (can_stop_full_tick()) tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); else if (ts->tick_stopped) - tick_nohz_restart_sched_tick(ts, ktime_get()); + tick_nohz_restart_sched_tick(ts, ktime_get(), 1); #endif } @@ -875,7 +875,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts) #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE unsigned long ticks; - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) return; /* * We stopped the tick in idle. Update process times would miss the @@ -916,7 +916,7 @@ void tick_nohz_idle_exit(void) tick_nohz_stop_idle(ts, now); if (ts->tick_stopped) { - tick_nohz_restart_sched_tick(ts, now); + tick_nohz_restart_sched_tick(ts, now, 0); tick_nohz_account_idle_ticks(ts); } diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 1c2b28536feb..060df67dbdd1 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -273,6 +273,7 @@ static const char **find_next(void *v, loff_t *pos) if (*pos < last_index + start_index) return __start___tracepoint_str + (*pos - last_index); + start_index += last_index; return find_next_mod_format(start_index, v, fmt, pos); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 18f34cf75f74..84b5035cb6a5 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -351,7 +351,7 @@ static void watchdog_overflow_callback(struct perf_event *event, trigger_allbutself_cpu_backtrace(); if (hardlockup_panic) - panic("Hard LOCKUP"); + nmi_panic(regs, "Hard LOCKUP"); __this_cpu_write(hard_watchdog_warn, true); return; diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index 83c33a5bcffb..d62de8bf022d 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -16,6 +16,10 @@ #include <linux/kernel.h> #include <linux/atomic.h> +#ifdef CONFIG_X86 +#include <asm/processor.h> /* for boot_cpu_has below */ +#endif + #define TEST(bit, op, c_op, val) \ do { \ atomic##bit##_set(&v, v0); \ @@ -27,6 +31,65 @@ do { \ (unsigned long long)r); \ } while (0) +/* + * Test for a atomic operation family, + * @test should be a macro accepting parameters (bit, op, ...) + */ + +#define FAMILY_TEST(test, bit, op, args...) \ +do { \ + test(bit, op, ##args); \ + test(bit, op##_acquire, ##args); \ + test(bit, op##_release, ##args); \ + test(bit, op##_relaxed, ##args); \ +} while (0) + +#define TEST_RETURN(bit, op, c_op, val) \ +do { \ + atomic##bit##_set(&v, v0); \ + r = v0; \ + r c_op val; \ + BUG_ON(atomic##bit##_##op(val, &v) != r); \ + BUG_ON(atomic##bit##_read(&v) != r); \ +} while (0) + +#define RETURN_FAMILY_TEST(bit, op, c_op, val) \ +do { \ + FAMILY_TEST(TEST_RETURN, bit, op, c_op, val); \ +} while (0) + +#define TEST_ARGS(bit, op, init, ret, expect, args...) \ +do { \ + atomic##bit##_set(&v, init); \ + BUG_ON(atomic##bit##_##op(&v, ##args) != ret); \ + BUG_ON(atomic##bit##_read(&v) != expect); \ +} while (0) + +#define XCHG_FAMILY_TEST(bit, init, new) \ +do { \ + FAMILY_TEST(TEST_ARGS, bit, xchg, init, init, new, new); \ +} while (0) + +#define CMPXCHG_FAMILY_TEST(bit, init, new, wrong) \ +do { \ + FAMILY_TEST(TEST_ARGS, bit, cmpxchg, \ + init, init, new, init, new); \ + FAMILY_TEST(TEST_ARGS, bit, cmpxchg, \ + init, init, init, wrong, new); \ +} while (0) + +#define INC_RETURN_FAMILY_TEST(bit, i) \ +do { \ + FAMILY_TEST(TEST_ARGS, bit, inc_return, \ + i, (i) + one, (i) + one); \ +} while (0) + +#define DEC_RETURN_FAMILY_TEST(bit, i) \ +do { \ + FAMILY_TEST(TEST_ARGS, bit, dec_return, \ + i, (i) - one, (i) - one); \ +} while (0) + static __init void test_atomic(void) { int v0 = 0xaaa31337; @@ -45,6 +108,18 @@ static __init void test_atomic(void) TEST(, and, &=, v1); TEST(, xor, ^=, v1); TEST(, andnot, &= ~, v1); + + RETURN_FAMILY_TEST(, add_return, +=, onestwos); + RETURN_FAMILY_TEST(, add_return, +=, -one); + RETURN_FAMILY_TEST(, sub_return, -=, onestwos); + RETURN_FAMILY_TEST(, sub_return, -=, -one); + + INC_RETURN_FAMILY_TEST(, v0); + DEC_RETURN_FAMILY_TEST(, v0); + + XCHG_FAMILY_TEST(, v0, v1); + CMPXCHG_FAMILY_TEST(, v0, v1, onestwos); + } #define INIT(c) do { atomic64_set(&v, c); r = c; } while (0) @@ -74,25 +149,10 @@ static __init void test_atomic64(void) TEST(64, xor, ^=, v1); TEST(64, andnot, &= ~, v1); - INIT(v0); - r += onestwos; - BUG_ON(atomic64_add_return(onestwos, &v) != r); - BUG_ON(v.counter != r); - - INIT(v0); - r += -one; - BUG_ON(atomic64_add_return(-one, &v) != r); - BUG_ON(v.counter != r); - - INIT(v0); - r -= onestwos; - BUG_ON(atomic64_sub_return(onestwos, &v) != r); - BUG_ON(v.counter != r); - - INIT(v0); - r -= -one; - BUG_ON(atomic64_sub_return(-one, &v) != r); - BUG_ON(v.counter != r); + RETURN_FAMILY_TEST(64, add_return, +=, onestwos); + RETURN_FAMILY_TEST(64, add_return, +=, -one); + RETURN_FAMILY_TEST(64, sub_return, -=, onestwos); + RETURN_FAMILY_TEST(64, sub_return, -=, -one); INIT(v0); atomic64_inc(&v); @@ -100,33 +160,15 @@ static __init void test_atomic64(void) BUG_ON(v.counter != r); INIT(v0); - r += one; - BUG_ON(atomic64_inc_return(&v) != r); - BUG_ON(v.counter != r); - - INIT(v0); atomic64_dec(&v); r -= one; BUG_ON(v.counter != r); - INIT(v0); - r -= one; - BUG_ON(atomic64_dec_return(&v) != r); - BUG_ON(v.counter != r); + INC_RETURN_FAMILY_TEST(64, v0); + DEC_RETURN_FAMILY_TEST(64, v0); - INIT(v0); - BUG_ON(atomic64_xchg(&v, v1) != v0); - r = v1; - BUG_ON(v.counter != r); - - INIT(v0); - BUG_ON(atomic64_cmpxchg(&v, v0, v1) != v0); - r = v1; - BUG_ON(v.counter != r); - - INIT(v0); - BUG_ON(atomic64_cmpxchg(&v, v2, v1) != v0); - BUG_ON(v.counter != r); + XCHG_FAMILY_TEST(64, v0, v1); + CMPXCHG_FAMILY_TEST(64, v0, v1, v2); INIT(v0); BUG_ON(atomic64_add_unless(&v, one, v0)); diff --git a/lib/list_debug.c b/lib/list_debug.c index c24c2f7e296f..3859bf63561c 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -37,7 +37,7 @@ void __list_add(struct list_head *new, next->prev = new; new->next = next; new->prev = prev; - prev->next = new; + WRITE_ONCE(prev->next, new); } EXPORT_SYMBOL(__list_add); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index eb9240c458fa..51282f579760 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -519,7 +519,8 @@ int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter) return -ENOMEM; spin_lock(&ht->lock); - iter->walker->tbl = rht_dereference(ht->tbl, ht); + iter->walker->tbl = + rcu_dereference_protected(ht->tbl, lockdep_is_held(&ht->lock)); list_add(&iter->walker->list, &iter->walker->tbl->walkers); spin_unlock(&ht->lock); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e234c21a5e6c..fc10620967c7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -903,14 +903,20 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (prev && reclaim->generation != iter->generation) goto out_unlock; - do { + while (1) { pos = READ_ONCE(iter->position); + if (!pos || css_tryget(&pos->css)) + break; /* - * A racing update may change the position and - * put the last reference, hence css_tryget(), - * or retry to see the updated position. + * css reference reached zero, so iter->position will + * be cleared by ->css_released. However, we should not + * rely on this happening soon, because ->css_released + * is called from a work queue, and by busy-waiting we + * might block it. So we clear iter->position right + * away. */ - } while (pos && !css_tryget(&pos->css)); + (void)cmpxchg(&iter->position, pos, NULL); + } } if (pos) @@ -956,17 +962,13 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, } if (reclaim) { - if (cmpxchg(&iter->position, pos, memcg) == pos) { - if (memcg) - css_get(&memcg->css); - if (pos) - css_put(&pos->css); - } - /* - * pairs with css_tryget when dereferencing iter->position - * above. + * The position could have already been updated by a competing + * thread, so check that the value hasn't changed since we read + * it to avoid reclaiming from the same cgroup twice. */ + (void)cmpxchg(&iter->position, pos, memcg); + if (pos) css_put(&pos->css); @@ -999,6 +1001,28 @@ void mem_cgroup_iter_break(struct mem_cgroup *root, css_put(&prev->css); } +static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg) +{ + struct mem_cgroup *memcg = dead_memcg; + struct mem_cgroup_reclaim_iter *iter; + struct mem_cgroup_per_zone *mz; + int nid, zid; + int i; + + while ((memcg = parent_mem_cgroup(memcg))) { + for_each_node(nid) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) { + mz = &memcg->nodeinfo[nid]->zoneinfo[zid]; + for (i = 0; i <= DEF_PRIORITY; i++) { + iter = &mz->iter[i]; + cmpxchg(&iter->position, + dead_memcg, NULL); + } + } + } + } +} + /* * Iteration constructs for visiting all cgroups (under a tree). If * loops are exited prematurely (break), mem_cgroup_iter_break() must @@ -4324,6 +4348,13 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) wb_memcg_offline(memcg); } +static void mem_cgroup_css_released(struct cgroup_subsys_state *css) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + invalidate_reclaim_iterators(memcg); +} + static void mem_cgroup_css_free(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); @@ -5185,6 +5216,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_alloc = mem_cgroup_css_alloc, .css_online = mem_cgroup_css_online, .css_offline = mem_cgroup_css_offline, + .css_released = mem_cgroup_css_released, .css_free = mem_cgroup_css_free, .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 67d488ab495e..a042a9d537bb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1375,23 +1375,30 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) */ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) { - unsigned long pfn; + unsigned long pfn, sec_end_pfn; struct zone *zone = NULL; struct page *page; int i; - for (pfn = start_pfn; + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn); pfn < end_pfn; - pfn += MAX_ORDER_NR_PAGES) { - i = 0; - /* This is just a CONFIG_HOLES_IN_ZONE check.*/ - while ((i < MAX_ORDER_NR_PAGES) && !pfn_valid_within(pfn + i)) - i++; - if (i == MAX_ORDER_NR_PAGES) + pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) { + /* Make sure the memory section is present first */ + if (!present_section_nr(pfn_to_section_nr(pfn))) continue; - page = pfn_to_page(pfn + i); - if (zone && page_zone(page) != zone) - return 0; - zone = page_zone(page); + for (; pfn < sec_end_pfn && pfn < end_pfn; + pfn += MAX_ORDER_NR_PAGES) { + i = 0; + /* This is just a CONFIG_HOLES_IN_ZONE check.*/ + while ((i < MAX_ORDER_NR_PAGES) && + !pfn_valid_within(pfn + i)) + i++; + if (i == MAX_ORDER_NR_PAGES) + continue; + page = pfn_to_page(pfn + i); + if (zone && page_zone(page) != zone) + return 0; + zone = page_zone(page); + } } return 1; } diff --git a/mm/shmem.c b/mm/shmem.c index 2afcdbbdb685..5813b7fa85b6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2438,7 +2438,6 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s int len; struct inode *inode; struct page *page; - char *kaddr; struct shmem_inode_info *info; len = strlen(symname) + 1; @@ -2477,9 +2476,8 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s } inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; - kaddr = kmap_atomic(page); - memcpy(kaddr, symname, len); - kunmap_atomic(kaddr); + inode_nohighmem(inode); + memcpy(page_address(page), symname, len); SetPageUptodate(page); set_page_dirty(page); unlock_page(page); @@ -2492,23 +2490,34 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return 0; } -static const char *shmem_follow_link(struct dentry *dentry, void **cookie) +static void shmem_put_link(void *arg) { - struct page *page = NULL; - int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL); - if (error) - return ERR_PTR(error); - unlock_page(page); - *cookie = page; - return kmap(page); + mark_page_accessed(arg); + put_page(arg); } -static void shmem_put_link(struct inode *unused, void *cookie) +static const char *shmem_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { - struct page *page = cookie; - kunmap(page); - mark_page_accessed(page); - page_cache_release(page); + struct page *page = NULL; + int error; + if (!dentry) { + page = find_get_page(inode->i_mapping, 0); + if (!page) + return ERR_PTR(-ECHILD); + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-ECHILD); + } + } else { + error = shmem_getpage(inode, 0, &page, SGP_READ, NULL); + if (error) + return ERR_PTR(error); + unlock_page(page); + } + set_delayed_call(done, shmem_put_link, page); + return page_address(page); } #ifdef CONFIG_TMPFS_XATTR @@ -2555,122 +2564,74 @@ static int shmem_initxattrs(struct inode *inode, return 0; } -static const struct xattr_handler *shmem_xattr_handlers[] = { -#ifdef CONFIG_TMPFS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif - NULL -}; - -static int shmem_xattr_validate(const char *name) -{ - struct { const char *prefix; size_t len; } arr[] = { - { XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN }, - { XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN } - }; - int i; - - for (i = 0; i < ARRAY_SIZE(arr); i++) { - size_t preflen = arr[i].len; - if (strncmp(name, arr[i].prefix, preflen) == 0) { - if (!name[preflen]) - return -EINVAL; - return 0; - } - } - return -EOPNOTSUPP; -} - -static ssize_t shmem_getxattr(struct dentry *dentry, const char *name, - void *buffer, size_t size) +static int shmem_xattr_handler_get(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + void *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); - int err; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_getxattr(dentry, name, buffer, size); - - err = shmem_xattr_validate(name); - if (err) - return err; + name = xattr_full_name(handler, name); return simple_xattr_get(&info->xattrs, name, buffer, size); } -static int shmem_setxattr(struct dentry *dentry, const char *name, - const void *value, size_t size, int flags) +static int shmem_xattr_handler_set(const struct xattr_handler *handler, + struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); - int err; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_setxattr(dentry, name, value, size, flags); - - err = shmem_xattr_validate(name); - if (err) - return err; + name = xattr_full_name(handler, name); return simple_xattr_set(&info->xattrs, name, value, size, flags); } -static int shmem_removexattr(struct dentry *dentry, const char *name) -{ - struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); - int err; - - /* - * If this is a request for a synthetic attribute in the system.* - * namespace use the generic infrastructure to resolve a handler - * for it via sb->s_xattr. - */ - if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) - return generic_removexattr(dentry, name); +static const struct xattr_handler shmem_security_xattr_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .get = shmem_xattr_handler_get, + .set = shmem_xattr_handler_set, +}; - err = shmem_xattr_validate(name); - if (err) - return err; +static const struct xattr_handler shmem_trusted_xattr_handler = { + .prefix = XATTR_TRUSTED_PREFIX, + .get = shmem_xattr_handler_get, + .set = shmem_xattr_handler_set, +}; - return simple_xattr_remove(&info->xattrs, name); -} +static const struct xattr_handler *shmem_xattr_handlers[] = { +#ifdef CONFIG_TMPFS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &shmem_security_xattr_handler, + &shmem_trusted_xattr_handler, + NULL +}; static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); - return simple_xattr_list(&info->xattrs, buffer, size); + return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size); } #endif /* CONFIG_TMPFS_XATTR */ static const struct inode_operations shmem_short_symlink_operations = { .readlink = generic_readlink, - .follow_link = simple_follow_link, + .get_link = simple_get_link, #ifdef CONFIG_TMPFS_XATTR - .setxattr = shmem_setxattr, - .getxattr = shmem_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = shmem_listxattr, - .removexattr = shmem_removexattr, + .removexattr = generic_removexattr, #endif }; static const struct inode_operations shmem_symlink_inode_operations = { .readlink = generic_readlink, - .follow_link = shmem_follow_link, - .put_link = shmem_put_link, + .get_link = shmem_get_link, #ifdef CONFIG_TMPFS_XATTR - .setxattr = shmem_setxattr, - .getxattr = shmem_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = shmem_listxattr, - .removexattr = shmem_removexattr, + .removexattr = generic_removexattr, #endif }; @@ -3142,10 +3103,10 @@ static const struct inode_operations shmem_inode_operations = { .getattr = shmem_getattr, .setattr = shmem_setattr, #ifdef CONFIG_TMPFS_XATTR - .setxattr = shmem_setxattr, - .getxattr = shmem_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = shmem_listxattr, - .removexattr = shmem_removexattr, + .removexattr = generic_removexattr, .set_acl = simple_set_acl, #endif }; @@ -3164,10 +3125,10 @@ static const struct inode_operations shmem_dir_inode_operations = { .tmpfile = shmem_tmpfile, #endif #ifdef CONFIG_TMPFS_XATTR - .setxattr = shmem_setxattr, - .getxattr = shmem_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = shmem_listxattr, - .removexattr = shmem_removexattr, + .removexattr = generic_removexattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, @@ -3177,10 +3138,10 @@ static const struct inode_operations shmem_dir_inode_operations = { static const struct inode_operations shmem_special_inode_operations = { #ifdef CONFIG_TMPFS_XATTR - .setxattr = shmem_setxattr, - .getxattr = shmem_getxattr, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, .listxattr = shmem_listxattr, - .removexattr = shmem_removexattr, + .removexattr = generic_removexattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, diff --git a/mm/vmstat.c b/mm/vmstat.c index 0d5712b0206c..c54fd2924f25 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -219,7 +219,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, * particular counter cannot be updated from interrupt context. */ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) + long delta) { struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; @@ -318,8 +318,8 @@ EXPORT_SYMBOL(__dec_zone_page_state); * 1 Overstepping half of threshold * -1 Overstepping minus half of threshold */ -static inline void mod_state(struct zone *zone, - enum zone_stat_item item, int delta, int overstep_mode) +static inline void mod_state(struct zone *zone, enum zone_stat_item item, + long delta, int overstep_mode) { struct per_cpu_pageset __percpu *pcp = zone->pageset; s8 __percpu *p = pcp->vm_stat_diff + item; @@ -357,7 +357,7 @@ static inline void mod_state(struct zone *zone, } void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) + long delta) { mod_state(zone, item, delta, 0); } @@ -384,7 +384,7 @@ EXPORT_SYMBOL(dec_zone_page_state); * Use interrupt disable to serialize counter updates */ void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, - int delta) + long delta) { unsigned long flags; @@ -1483,6 +1483,7 @@ static void __init start_shepherd_timer(void) BUG(); cpumask_copy(cpu_stat_off, cpu_online_mask); + vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -1550,7 +1551,6 @@ static int __init setup_vmstat(void) start_shepherd_timer(); cpu_notifier_register_done(); - vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 5396ff08af32..8a7ada8bb947 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -39,7 +39,7 @@ void br_init_port(struct net_bridge_port *p) struct switchdev_attr attr = { .id = SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP | SWITCHDEV_F_DEFER, - .u.ageing_time = p->br->ageing_time, + .u.ageing_time = jiffies_to_clock_t(p->br->ageing_time), }; int err; @@ -142,7 +142,10 @@ static void br_stp_start(struct net_bridge *br) char *envp[] = { NULL }; struct net_bridge_port *p; - r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + if (net_eq(dev_net(br->dev), &init_net)) + r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + else + r = -ENOENT; spin_lock_bh(&br->lock); diff --git a/net/core/dst.c b/net/core/dst.c index e6dc77252fe9..a1656e3b8d72 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -301,12 +301,13 @@ void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; + unsigned short nocache = dst->flags & DST_NOCACHE; newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); - if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE)) + if (!newrefcnt && unlikely(nocache)) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index f34c31defafe..a09fb0dec725 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -253,9 +253,6 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) p.i_key = p.o_key = 0; p.i_flags = p.o_flags = 0; - if (p.iph.ttl) - p.iph.frag_off |= htons(IP_DF); - err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 63e5be0abd86..bc35f1842512 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -601,8 +601,11 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0); - if (!saddr && ipc.oif) - l3mdev_get_saddr(net, ipc.oif, &fl4); + if (!saddr && ipc.oif) { + err = l3mdev_get_saddr(net, ipc.oif, &fl4); + if (err < 0) + goto done; + } if (!inet->hdrincl) { rfv.msg = msg; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d656eef7f8e..d4c51158470f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2478,6 +2478,9 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, int newly_acked_sacked = prior_unsacked - (tp->packets_out - tp->sacked_out); + if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd)) + return; + tp->prr_delivered += newly_acked_sacked; if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0c7b0e61b917..c43890848641 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1025,8 +1025,11 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flow_flags, faddr, saddr, dport, inet->inet_sport); - if (!saddr && ipc.oif) - l3mdev_get_saddr(net, ipc.oif, fl4); + if (!saddr && ipc.oif) { + err = l3mdev_get_saddr(net, ipc.oif, fl4); + if (err < 0) + goto out; + } security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); rt = ip_route_output_flow(net, fl4, sk); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1e0c3c835a63..7b0edb37a115 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -259,7 +259,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xfrm_dst_ifdown(dst, dev); } -static struct dst_ops xfrm4_dst_ops = { +static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, @@ -273,7 +273,7 @@ static struct dst_ops xfrm4_dst_ops = { static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .family = AF_INET, - .dst_ops = &xfrm4_dst_ops, + .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .decode_session = _decode_session4, @@ -295,7 +295,7 @@ static struct ctl_table xfrm4_policy_table[] = { { } }; -static int __net_init xfrm4_net_init(struct net *net) +static int __net_init xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -323,7 +323,7 @@ err_alloc: return -ENOMEM; } -static void __net_exit xfrm4_net_exit(struct net *net) +static void __net_exit xfrm4_net_sysctl_exit(struct net *net) { struct ctl_table *table; @@ -335,12 +335,44 @@ static void __net_exit xfrm4_net_exit(struct net *net) if (!net_eq(net, &init_net)) kfree(table); } +#else /* CONFIG_SYSCTL */ +static int inline xfrm4_net_sysctl_init(struct net *net) +{ + return 0; +} + +static void inline xfrm4_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm4_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, + sizeof(xfrm4_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); + if (ret) + return ret; + + ret = xfrm4_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); + + return ret; +} + +static void __net_exit xfrm4_net_exit(struct net *net) +{ + xfrm4_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); +} static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; -#endif static void __init xfrm4_policy_init(void) { @@ -349,13 +381,9 @@ static void __init xfrm4_policy_init(void) void __init xfrm4_init(void) { - dst_entries_init(&xfrm4_dst_ops); - xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); -#ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm4_net_ops); -#endif } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 17f8e7ea133b..1f21087accab 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5369,13 +5369,10 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, goto out; } - if (!write) { - err = snprintf(str, sizeof(str), "%pI6", - &secret->secret); - if (err >= sizeof(str)) { - err = -EIO; - goto out; - } + err = snprintf(str, sizeof(str), "%pI6", &secret->secret); + if (err >= sizeof(str)) { + err = -EIO; + goto out; } err = proc_dostring(&lctl, write, buffer, lenp, ppos); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 882124ebb438..a8f6986dcbe5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -552,7 +552,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) rcu_read_lock(); p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && ip6addrlbl_hold(p)) + if (p && !ip6addrlbl_hold(p)) p = NULL; lseq = ip6addrlbl_table.seq; rcu_read_unlock(); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d6161e1c48c8..84afb9a77278 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1183,7 +1183,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) */ if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, - NULL, 0)) { + in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); @@ -1337,7 +1337,7 @@ skip_linkparms: #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, - NULL, 0)) { + in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 5643423fe67a..c074771a10f7 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -279,7 +279,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xfrm_dst_ifdown(dst, dev); } -static struct dst_ops xfrm6_dst_ops = { +static struct dst_ops xfrm6_dst_ops_template = { .family = AF_INET6, .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, @@ -293,7 +293,7 @@ static struct dst_ops xfrm6_dst_ops = { static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .family = AF_INET6, - .dst_ops = &xfrm6_dst_ops, + .dst_ops = &xfrm6_dst_ops_template, .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, @@ -325,7 +325,7 @@ static struct ctl_table xfrm6_policy_table[] = { { } }; -static int __net_init xfrm6_net_init(struct net *net) +static int __net_init xfrm6_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -353,7 +353,7 @@ err_alloc: return -ENOMEM; } -static void __net_exit xfrm6_net_exit(struct net *net) +static void __net_exit xfrm6_net_sysctl_exit(struct net *net) { struct ctl_table *table; @@ -365,24 +365,52 @@ static void __net_exit xfrm6_net_exit(struct net *net) if (!net_eq(net, &init_net)) kfree(table); } +#else /* CONFIG_SYSCTL */ +static int inline xfrm6_net_sysctl_init(struct net *net) +{ + return 0; +} + +static void inline xfrm6_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm6_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template, + sizeof(xfrm6_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops); + if (ret) + return ret; + + ret = xfrm6_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); + + return ret; +} + +static void __net_exit xfrm6_net_exit(struct net *net) +{ + xfrm6_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); +} static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, }; -#endif int __init xfrm6_init(void) { int ret; - dst_entries_init(&xfrm6_dst_ops); - ret = xfrm6_policy_init(); - if (ret) { - dst_entries_destroy(&xfrm6_dst_ops); + if (ret) goto out; - } ret = xfrm6_state_init(); if (ret) goto out_policy; @@ -391,9 +419,7 @@ int __init xfrm6_init(void) if (ret) goto out_state; -#ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm6_net_ops); -#endif out: return ret; out_state: @@ -405,11 +431,8 @@ out_policy: void xfrm6_fini(void) { -#ifdef CONFIG_SYSCTL unregister_pernet_subsys(&xfrm6_net_ops); -#endif xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); - dst_entries_destroy(&xfrm6_dst_ops); } diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 7b9c053ba750..edb3502f2016 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -94,7 +94,7 @@ nft_do_chain_netdev(void *priv, struct sk_buff *skb, { struct nft_pktinfo pkt; - switch (eth_hdr(skb)->h_proto) { + switch (skb->protocol) { case htons(ETH_P_IP): nft_netdev_set_pktinfo_ipv4(&pkt, skb, state); break; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 8cbca3432f90..939921532764 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -366,6 +366,7 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; switch (priv->key) { + case NFT_CT_L3PROTOCOL: case NFT_CT_PROTOCOL: case NFT_CT_SRC: case NFT_CT_DST: diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 3e8892216f94..e004067ec24a 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -698,6 +698,10 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, OVS_NLERR(log, "Failed to allocate conntrack template"); return -ENOMEM; } + + __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); + nf_conntrack_get(&ct_info.ct->ct_general); + if (helper) { err = ovs_ct_add_helper(&ct_info, helper, key, log); if (err) @@ -709,8 +713,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (err) goto err_free_ct; - __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 907d6fd28ede..d1bd4a45ca2d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2434,7 +2434,10 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ovs_nla_put_tunnel_info(skb, tun_info); + err = ip_tun_to_nlattr(skb, &tun_info->key, + ip_tunnel_info_opts(tun_info), + tun_info->options_len, + ip_tunnel_info_af(tun_info)); if (err) return err; nla_nest_end(skb, start); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e82a1ad80aa5..16bc83b2842a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -658,8 +658,10 @@ static void qdisc_rcu_free(struct rcu_head *head) { struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) + if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); + free_percpu(qdisc->cpu_qstats); + } kfree((char *) qdisc - qdisc->padded); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index cd34a4a34065..22c2bf367d7e 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort( retval = SCTP_DISPOSITION_CONSUME; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); /* Even if we can't send the ABORT due to low memory delete the * TCB. This is a departure from our typical NOMEM handling. @@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort( SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); retval = SCTP_DISPOSITION_CONSUME; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9b6cc6de80d8..ef1d90fdc773 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1301,8 +1301,9 @@ static int __sctp_setsockopt_connectx(struct sock *sk, int addrs_size, sctp_assoc_t *assoc_id) { - int err = 0; struct sockaddr *kaddrs; + gfp_t gfp = GFP_KERNEL; + int err = 0; pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, addrs, addrs_size); @@ -1315,7 +1316,9 @@ static int __sctp_setsockopt_connectx(struct sock *sk, return -EFAULT; /* Alloc space for the address array in kernel memory. */ - kaddrs = kmalloc(addrs_size, GFP_KERNEL); + if (sk->sk_socket->file) + gfp = GFP_USER | __GFP_NOWARN; + kaddrs = kmalloc(addrs_size, gfp); if (unlikely(!kaddrs)) return -ENOMEM; @@ -1513,8 +1516,7 @@ static void sctp_close(struct sock *sk, long timeout) struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); - if (chunk) - sctp_primitive_ABORT(net, asoc, chunk); + sctp_primitive_ABORT(net, asoc, chunk); } else sctp_primitive_SHUTDOWN(net, asoc, NULL); } @@ -5773,7 +5775,7 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, len = sizeof(struct sctp_assoc_ids) + sizeof(sctp_assoc_t) * num; - ids = kmalloc(len, GFP_KERNEL); + ids = kmalloc(len, GFP_USER | __GFP_NOWARN); if (unlikely(!ids)) return -ENOMEM; @@ -7199,6 +7201,8 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) net_enable_timestamp(); + + security_sk_clone(sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/net/socket.c b/net/socket.c index 29822d6dd91e..d730ef9dfbf0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -257,6 +257,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb) } init_waitqueue_head(&wq->wait); wq->fasync_list = NULL; + wq->flags = 0; RCU_INIT_POINTER(ei->socket.wq, wq); ei->socket.state = SS_UNCONNECTED; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index a4631477cedf..ef05cd9403d4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -953,32 +953,20 @@ fail: return NULL; } -static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode, + struct path *res) { - struct dentry *dentry; - struct path path; - int err = 0; - /* - * Get the parent directory, calculate the hash for last - * component. - */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); - if (IS_ERR(dentry)) - return err; + int err; - /* - * All right, let's create it. - */ - err = security_path_mknod(&path, dentry, mode, 0); + err = security_path_mknod(path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); + err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0); if (!err) { - res->mnt = mntget(path.mnt); + res->mnt = mntget(path->mnt); res->dentry = dget(dentry); } } - done_path_create(&path, dentry); + return err; } @@ -989,10 +977,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - int err; + int err, name_err; unsigned int hash; struct unix_address *addr; struct hlist_head *list; + struct path path; + struct dentry *dentry; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -1008,14 +998,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + name_err = 0; + dentry = NULL; + if (sun_path[0]) { + /* Get the parent directory, calculate the hash for last + * component. + */ + dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + + if (IS_ERR(dentry)) { + /* delay report until after 'already bound' check */ + name_err = PTR_ERR(dentry); + dentry = NULL; + } + } + err = mutex_lock_interruptible(&u->readlock); if (err) - goto out; + goto out_path; err = -EINVAL; if (u->addr) goto out_up; + if (name_err) { + err = name_err == -EEXIST ? -EADDRINUSE : name_err; + goto out_up; + } + err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) @@ -1026,11 +1036,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) addr->hash = hash ^ sk->sk_type; atomic_set(&addr->refcnt, 1); - if (sun_path[0]) { - struct path path; + if (dentry) { + struct path u_path; umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); + err = unix_mknod(dentry, &path, mode, &u_path); if (err) { if (err == -EEXIST) err = -EADDRINUSE; @@ -1038,9 +1048,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1); + hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); - u->path = path; + u->path = u_path; list = &unix_socket_table[hash]; } else { spin_lock(&unix_table_lock); @@ -1063,6 +1073,10 @@ out_unlock: spin_unlock(&unix_table_lock); out_up: mutex_unlock(&u->readlock); +out_path: + if (dentry) + done_path_create(&path, dentry); + out: return err; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 948fa5560de5..b5e665b3cfb0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2826,7 +2826,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { - struct net *net; int err = 0; if (unlikely(afinfo == NULL)) return -EINVAL; @@ -2857,26 +2856,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) } spin_unlock(&xfrm_policy_afinfo_lock); - rtnl_lock(); - for_each_net(net) { - struct dst_ops *xfrm_dst_ops; - - switch (afinfo->family) { - case AF_INET: - xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops; - break; -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops; - break; -#endif - default: - BUG(); - } - *xfrm_dst_ops = *afinfo->dst_ops; - } - rtnl_unlock(); - return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); @@ -2912,22 +2891,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); -static void __net_init xfrm_dst_ops_init(struct net *net) -{ - struct xfrm_policy_afinfo *afinfo; - - rcu_read_lock(); - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]); - if (afinfo) - net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; -#if IS_ENABLED(CONFIG_IPV6) - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]); - if (afinfo) - net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; -#endif - rcu_read_unlock(); -} - static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -3076,7 +3039,6 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; - xfrm_dst_ops_init(net); rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 698768bdc581..e167592793a7 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -48,12 +48,17 @@ static int fd_map; /* File descriptor for file being modified. */ static int mmap_failed; /* Boolean flag. */ -static void *ehdr_curr; /* current ElfXX_Ehdr * for resource cleanup */ static char gpfx; /* prefix for global symbol name (sometimes '_') */ static struct stat sb; /* Remember .st_size, etc. */ static jmp_buf jmpenv; /* setjmp/longjmp per-file error escape */ static const char *altmcount; /* alternate mcount symbol name */ static int warn_on_notrace_sect; /* warn when section has mcount not being recorded */ +static void *file_map; /* pointer of the mapped file */ +static void *file_end; /* pointer to the end of the mapped file */ +static int file_updated; /* flag to state file was changed */ +static void *file_ptr; /* current file pointer location */ +static void *file_append; /* added to the end of the file */ +static size_t file_append_size; /* how much is added to end of file */ /* setjmp() return values */ enum { @@ -67,10 +72,14 @@ static void cleanup(void) { if (!mmap_failed) - munmap(ehdr_curr, sb.st_size); + munmap(file_map, sb.st_size); else - free(ehdr_curr); - close(fd_map); + free(file_map); + file_map = NULL; + free(file_append); + file_append = NULL; + file_append_size = 0; + file_updated = 0; } static void __attribute__((noreturn)) @@ -92,12 +101,22 @@ succeed_file(void) static off_t ulseek(int const fd, off_t const offset, int const whence) { - off_t const w = lseek(fd, offset, whence); - if (w == (off_t)-1) { - perror("lseek"); + switch (whence) { + case SEEK_SET: + file_ptr = file_map + offset; + break; + case SEEK_CUR: + file_ptr += offset; + break; + case SEEK_END: + file_ptr = file_map + (sb.st_size - offset); + break; + } + if (file_ptr < file_map) { + fprintf(stderr, "lseek: seek before file\n"); fail_file(); } - return w; + return file_ptr - file_map; } static size_t @@ -114,12 +133,38 @@ uread(int const fd, void *const buf, size_t const count) static size_t uwrite(int const fd, void const *const buf, size_t const count) { - size_t const n = write(fd, buf, count); - if (n != count) { - perror("write"); - fail_file(); + size_t cnt = count; + off_t idx = 0; + + file_updated = 1; + + if (file_ptr + count >= file_end) { + off_t aoffset = (file_ptr + count) - file_end; + + if (aoffset > file_append_size) { + file_append = realloc(file_append, aoffset); + file_append_size = aoffset; + } + if (!file_append) { + perror("write"); + fail_file(); + } + if (file_ptr < file_end) { + cnt = file_end - file_ptr; + } else { + cnt = 0; + idx = aoffset - count; + } } - return n; + + if (cnt) + memcpy(file_ptr, buf, cnt); + + if (cnt < count) + memcpy(file_append + idx, buf + cnt, count - cnt); + + file_ptr += count; + return count; } static void * @@ -192,9 +237,7 @@ static int make_nop_arm64(void *map, size_t const offset) */ static void *mmap_file(char const *fname) { - void *addr; - - fd_map = open(fname, O_RDWR); + fd_map = open(fname, O_RDONLY); if (fd_map < 0 || fstat(fd_map, &sb) < 0) { perror(fname); fail_file(); @@ -203,15 +246,58 @@ static void *mmap_file(char const *fname) fprintf(stderr, "not a regular file: %s\n", fname); fail_file(); } - addr = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE, - fd_map, 0); + file_map = mmap(0, sb.st_size, PROT_READ|PROT_WRITE, MAP_PRIVATE, + fd_map, 0); mmap_failed = 0; - if (addr == MAP_FAILED) { + if (file_map == MAP_FAILED) { mmap_failed = 1; - addr = umalloc(sb.st_size); - uread(fd_map, addr, sb.st_size); + file_map = umalloc(sb.st_size); + uread(fd_map, file_map, sb.st_size); + } + close(fd_map); + + file_end = file_map + sb.st_size; + + return file_map; +} + +static void write_file(const char *fname) +{ + char tmp_file[strlen(fname) + 4]; + size_t n; + + if (!file_updated) + return; + + sprintf(tmp_file, "%s.rc", fname); + + /* + * After reading the entire file into memory, delete it + * and write it back, to prevent weird side effects of modifying + * an object file in place. + */ + fd_map = open(tmp_file, O_WRONLY | O_TRUNC | O_CREAT, sb.st_mode); + if (fd_map < 0) { + perror(fname); + fail_file(); + } + n = write(fd_map, file_map, sb.st_size); + if (n != sb.st_size) { + perror("write"); + fail_file(); + } + if (file_append_size) { + n = write(fd_map, file_append, file_append_size); + if (n != file_append_size) { + perror("write"); + fail_file(); + } + } + close(fd_map); + if (rename(tmp_file, fname) < 0) { + perror(fname); + fail_file(); } - return addr; } /* w8rev, w8nat, ...: Handle endianness. */ @@ -318,7 +404,6 @@ do_file(char const *const fname) Elf32_Ehdr *const ehdr = mmap_file(fname); unsigned int reltype = 0; - ehdr_curr = ehdr; w = w4nat; w2 = w2nat; w8 = w8nat; @@ -441,6 +526,7 @@ do_file(char const *const fname) } } /* end switch */ + write_file(fname); cleanup(); } @@ -493,11 +579,14 @@ main(int argc, char *argv[]) case SJ_SETJMP: /* normal sequence */ /* Avoid problems if early cleanup() */ fd_map = -1; - ehdr_curr = NULL; mmap_failed = 1; + file_map = NULL; + file_ptr = NULL; + file_updated = 0; do_file(file); break; case SJ_FAIL: /* error in do_file or below */ + fprintf(stderr, "%s: failed\n", file); ++n_error; break; case SJ_SUCCEED: /* premature success */ diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index fb111eafcb89..1c3872aeed14 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -751,16 +751,16 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) /* the key is probably readable - now try to read it */ can_read_key: - ret = key_validate(key); - if (ret == 0) { - ret = -EOPNOTSUPP; - if (key->type->read) { - /* read the data with the semaphore held (since we - * might sleep) */ - down_read(&key->sem); + ret = -EOPNOTSUPP; + if (key->type->read) { + /* Read the data with the semaphore held (since we might sleep) + * to protect against the key being updated or revoked. + */ + down_read(&key->sem); + ret = key_validate(key); + if (ret == 0) ret = key->type->read(key, buffer, buflen); - up_read(&key->sem); - } + up_read(&key->sem); } error2: diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index ff81026f6ddb..37fdd5416a64 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -1519,8 +1519,6 @@ static int smack_inode_getsecurity(const struct inode *inode, * @inode: the object * @buffer: where they go * @buffer_size: size of buffer - * - * Returns 0 on success, -EINVAL otherwise */ static int smack_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index bff5c8b329d1..3b3658297070 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -954,6 +954,36 @@ static int azx_resume(struct device *dev) } #endif /* CONFIG_PM_SLEEP || SUPPORT_VGA_SWITCHEROO */ +#ifdef CONFIG_PM_SLEEP +/* put codec down to D3 at hibernation for Intel SKL+; + * otherwise BIOS may still access the codec and screw up the driver + */ +#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) +#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) +#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) + +static int azx_freeze_noirq(struct device *dev) +{ + struct pci_dev *pci = to_pci_dev(dev); + + if (IS_SKL_PLUS(pci)) + pci_set_power_state(pci, PCI_D3hot); + + return 0; +} + +static int azx_thaw_noirq(struct device *dev) +{ + struct pci_dev *pci = to_pci_dev(dev); + + if (IS_SKL_PLUS(pci)) + pci_set_power_state(pci, PCI_D0); + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + #ifdef CONFIG_PM static int azx_runtime_suspend(struct device *dev) { @@ -1063,6 +1093,10 @@ static int azx_runtime_idle(struct device *dev) static const struct dev_pm_ops azx_pm = { SET_SYSTEM_SLEEP_PM_OPS(azx_suspend, azx_resume) +#ifdef CONFIG_PM_SLEEP + .freeze_noirq = azx_freeze_noirq, + .thaw_noirq = azx_thaw_noirq, +#endif SET_RUNTIME_PM_OPS(azx_runtime_suspend, azx_runtime_resume, azx_runtime_idle) }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6c268dad143f..3a89d82f8057 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -67,6 +67,10 @@ enum { ALC_HEADSET_TYPE_OMTP, }; +enum { + ALC_KEY_MICMUTE_INDEX, +}; + struct alc_customize_define { unsigned int sku_cfg; unsigned char port_connectivity; @@ -123,6 +127,7 @@ struct alc_spec { unsigned int pll_coef_idx, pll_coef_bit; unsigned int coef0; struct input_dev *kb_dev; + u8 alc_mute_keycode_map[1]; }; /* @@ -1775,6 +1780,7 @@ enum { ALC889_FIXUP_MBA11_VREF, ALC889_FIXUP_MBA21_VREF, ALC889_FIXUP_MP11_VREF, + ALC889_FIXUP_MP41_VREF, ALC882_FIXUP_INV_DMIC, ALC882_FIXUP_NO_PRIMARY_HP, ALC887_FIXUP_ASUS_BASS, @@ -1863,7 +1869,7 @@ static void alc889_fixup_mbp_vref(struct hda_codec *codec, const struct hda_fixup *fix, int action) { struct alc_spec *spec = codec->spec; - static hda_nid_t nids[2] = { 0x14, 0x15 }; + static hda_nid_t nids[3] = { 0x14, 0x15, 0x19 }; int i; if (action != HDA_FIXUP_ACT_INIT) @@ -2153,6 +2159,12 @@ static const struct hda_fixup alc882_fixups[] = { .chained = true, .chain_id = ALC885_FIXUP_MACPRO_GPIO, }, + [ALC889_FIXUP_MP41_VREF] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc889_fixup_mbp_vref, + .chained = true, + .chain_id = ALC885_FIXUP_MACPRO_GPIO, + }, [ALC882_FIXUP_INV_DMIC] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_inv_dmic, @@ -2235,7 +2247,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x3f00, "Macbook 5,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4000, "MacbookPro 5,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4100, "Macmini 3,1", ALC889_FIXUP_IMAC91_VREF), - SND_PCI_QUIRK(0x106b, 0x4200, "Mac Pro 5,1", ALC885_FIXUP_MACPRO_GPIO), + SND_PCI_QUIRK(0x106b, 0x4200, "Mac Pro 4,1/5,1", ALC889_FIXUP_MP41_VREF), SND_PCI_QUIRK(0x106b, 0x4300, "iMac 9,1", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4600, "MacbookPro 5,2", ALC889_FIXUP_IMAC91_VREF), SND_PCI_QUIRK(0x106b, 0x4900, "iMac 9,1 Aluminum", ALC889_FIXUP_IMAC91_VREF), @@ -3455,12 +3467,43 @@ static void gpio2_mic_hotkey_event(struct hda_codec *codec, /* GPIO2 just toggles on a keypress/keyrelease cycle. Therefore send both key on and key off event for every interrupt. */ - input_report_key(spec->kb_dev, KEY_MICMUTE, 1); + input_report_key(spec->kb_dev, spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX], 1); input_sync(spec->kb_dev); - input_report_key(spec->kb_dev, KEY_MICMUTE, 0); + input_report_key(spec->kb_dev, spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX], 0); input_sync(spec->kb_dev); } +static int alc_register_micmute_input_device(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + int i; + + spec->kb_dev = input_allocate_device(); + if (!spec->kb_dev) { + codec_err(codec, "Out of memory (input_allocate_device)\n"); + return -ENOMEM; + } + + spec->alc_mute_keycode_map[ALC_KEY_MICMUTE_INDEX] = KEY_MICMUTE; + + spec->kb_dev->name = "Microphone Mute Button"; + spec->kb_dev->evbit[0] = BIT_MASK(EV_KEY); + spec->kb_dev->keycodesize = sizeof(spec->alc_mute_keycode_map[0]); + spec->kb_dev->keycodemax = ARRAY_SIZE(spec->alc_mute_keycode_map); + spec->kb_dev->keycode = spec->alc_mute_keycode_map; + for (i = 0; i < ARRAY_SIZE(spec->alc_mute_keycode_map); i++) + set_bit(spec->alc_mute_keycode_map[i], spec->kb_dev->keybit); + + if (input_register_device(spec->kb_dev)) { + codec_err(codec, "input_register_device failed\n"); + input_free_device(spec->kb_dev); + spec->kb_dev = NULL; + return -ENOMEM; + } + + return 0; +} + static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -3478,20 +3521,8 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec, struct alc_spec *spec = codec->spec; if (action == HDA_FIXUP_ACT_PRE_PROBE) { - spec->kb_dev = input_allocate_device(); - if (!spec->kb_dev) { - codec_err(codec, "Out of memory (input_allocate_device)\n"); - return; - } - spec->kb_dev->name = "Microphone Mute Button"; - spec->kb_dev->evbit[0] = BIT_MASK(EV_KEY); - spec->kb_dev->keybit[BIT_WORD(KEY_MICMUTE)] = BIT_MASK(KEY_MICMUTE); - if (input_register_device(spec->kb_dev)) { - codec_err(codec, "input_register_device failed\n"); - input_free_device(spec->kb_dev); - spec->kb_dev = NULL; + if (alc_register_micmute_input_device(codec) != 0) return; - } snd_hda_add_verbs(codec, gpio_init); snd_hda_codec_write_cache(codec, codec->core.afg, 0, @@ -3521,6 +3552,47 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec, } } +static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + /* Line2 = mic mute hotkey + GPIO2 = mic mute LED */ + static const struct hda_verb gpio_init[] = { + { 0x01, AC_VERB_SET_GPIO_MASK, 0x04 }, + { 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 }, + {} + }; + + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + if (alc_register_micmute_input_device(codec) != 0) + return; + + snd_hda_add_verbs(codec, gpio_init); + snd_hda_jack_detect_enable_callback(codec, 0x1b, + gpio2_mic_hotkey_event); + + spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook; + spec->gpio_led = 0; + spec->mute_led_polarity = 0; + spec->gpio_mic_led_mask = 0x04; + return; + } + + if (!spec->kb_dev) + return; + + switch (action) { + case HDA_FIXUP_ACT_PROBE: + spec->init_amp = ALC_INIT_DEFAULT; + break; + case HDA_FIXUP_ACT_FREE: + input_unregister_device(spec->kb_dev); + spec->kb_dev = NULL; + } +} + static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4621,6 +4693,7 @@ enum { ALC275_FIXUP_DELL_XPS, ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, + ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, }; static const struct hda_fixup alc269_fixups[] = { @@ -5230,6 +5303,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_THINKPAD_ACPI }, + [ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc233_fixup_lenovo_line2_mic_hotkey, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5379,6 +5456,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x2233, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), + SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP), SND_PCI_QUIRK(0x17aa, 0x5013, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index b3ea24d64c50..93b400800905 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -1537,7 +1537,7 @@ static int arizona_hw_params(struct snd_pcm_substream *substream, bool reconfig; unsigned int aif_tx_state, aif_rx_state; - if (params_rate(params) % 8000) + if (params_rate(params) % 4000) rates = &arizona_44k1_bclk_rates[0]; else rates = &arizona_48k_bclk_rates[0]; diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c index 84f5eb07a91b..afa6c5db9dcc 100644 --- a/sound/soc/codecs/es8328.c +++ b/sound/soc/codecs/es8328.c @@ -85,7 +85,15 @@ static const DECLARE_TLV_DB_SCALE(pga_tlv, 0, 300, 0); static const DECLARE_TLV_DB_SCALE(bypass_tlv, -1500, 300, 0); static const DECLARE_TLV_DB_SCALE(mic_tlv, 0, 300, 0); -static const int deemph_settings[] = { 0, 32000, 44100, 48000 }; +static const struct { + int rate; + unsigned int val; +} deemph_settings[] = { + { 0, ES8328_DACCONTROL6_DEEMPH_OFF }, + { 32000, ES8328_DACCONTROL6_DEEMPH_32k }, + { 44100, ES8328_DACCONTROL6_DEEMPH_44_1k }, + { 48000, ES8328_DACCONTROL6_DEEMPH_48k }, +}; static int es8328_set_deemph(struct snd_soc_codec *codec) { @@ -97,21 +105,22 @@ static int es8328_set_deemph(struct snd_soc_codec *codec) * rate. */ if (es8328->deemph) { - best = 1; - for (i = 2; i < ARRAY_SIZE(deemph_settings); i++) { - if (abs(deemph_settings[i] - es8328->playback_fs) < - abs(deemph_settings[best] - es8328->playback_fs)) + best = 0; + for (i = 1; i < ARRAY_SIZE(deemph_settings); i++) { + if (abs(deemph_settings[i].rate - es8328->playback_fs) < + abs(deemph_settings[best].rate - es8328->playback_fs)) best = i; } - val = best << 1; + val = deemph_settings[best].val; } else { - val = 0; + val = ES8328_DACCONTROL6_DEEMPH_OFF; } dev_dbg(codec->dev, "Set deemphasis %d\n", val); - return snd_soc_update_bits(codec, ES8328_DACCONTROL6, 0x6, val); + return snd_soc_update_bits(codec, ES8328_DACCONTROL6, + ES8328_DACCONTROL6_DEEMPH_MASK, val); } static int es8328_get_deemph(struct snd_kcontrol *kcontrol, diff --git a/sound/soc/codecs/es8328.h b/sound/soc/codecs/es8328.h index cb36afe10c0e..156c748c89c7 100644 --- a/sound/soc/codecs/es8328.h +++ b/sound/soc/codecs/es8328.h @@ -153,6 +153,7 @@ int es8328_probe(struct device *dev, struct regmap *regmap); #define ES8328_DACCONTROL6_CLICKFREE (1 << 3) #define ES8328_DACCONTROL6_DAC_INVR (1 << 4) #define ES8328_DACCONTROL6_DAC_INVL (1 << 5) +#define ES8328_DACCONTROL6_DEEMPH_MASK (3 << 6) #define ES8328_DACCONTROL6_DEEMPH_OFF (0 << 6) #define ES8328_DACCONTROL6_DEEMPH_32k (1 << 6) #define ES8328_DACCONTROL6_DEEMPH_44_1k (2 << 6) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index ef76940f9dcb..3e3c7f6be29d 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -1667,9 +1667,13 @@ static int rt5645_spk_event(struct snd_soc_dapm_widget *w, RT5645_PWR_CLS_D_L, RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R | RT5645_PWR_CLS_D_L); + snd_soc_update_bits(codec, RT5645_GEN_CTRL3, + RT5645_DET_CLK_MASK, RT5645_DET_CLK_MODE1); break; case SND_SOC_DAPM_PRE_PMD: + snd_soc_update_bits(codec, RT5645_GEN_CTRL3, + RT5645_DET_CLK_MASK, RT5645_DET_CLK_DIS); snd_soc_write(codec, RT5645_EQ_CTRL2, 0); snd_soc_update_bits(codec, RT5645_PWR_DIG1, RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R | diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h index 093e46d559fb..205e0715c99a 100644 --- a/sound/soc/codecs/rt5645.h +++ b/sound/soc/codecs/rt5645.h @@ -2122,6 +2122,10 @@ enum { /* General Control3 (0xfc) */ #define RT5645_JD_PSV_MODE (0x1 << 12) #define RT5645_IRQ_CLK_GATE_CTRL (0x1 << 11) +#define RT5645_DET_CLK_MASK (0x3 << 9) +#define RT5645_DET_CLK_DIS (0x0 << 9) +#define RT5645_DET_CLK_MODE1 (0x1 << 9) +#define RT5645_DET_CLK_MODE2 (0x2 << 9) #define RT5645_MICINDET_MANU (0x1 << 7) #define RT5645_RING2_SLEEVE_GND (0x1 << 5) diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c index f540f82b1f27..08b40460663c 100644 --- a/sound/soc/codecs/sgtl5000.c +++ b/sound/soc/codecs/sgtl5000.c @@ -189,6 +189,7 @@ static int power_vag_event(struct snd_soc_dapm_widget *w, case SND_SOC_DAPM_POST_PMU: snd_soc_update_bits(codec, SGTL5000_CHIP_ANA_POWER, SGTL5000_VAG_POWERUP, SGTL5000_VAG_POWERUP); + msleep(400); break; case SND_SOC_DAPM_PRE_PMD: diff --git a/sound/soc/codecs/wm8974.c b/sound/soc/codecs/wm8974.c index 0a60677397b3..4c29bd2ae75c 100644 --- a/sound/soc/codecs/wm8974.c +++ b/sound/soc/codecs/wm8974.c @@ -574,6 +574,7 @@ static const struct regmap_config wm8974_regmap = { .max_register = WM8974_MONOMIX, .reg_defaults = wm8974_reg_defaults, .num_reg_defaults = ARRAY_SIZE(wm8974_reg_defaults), + .cache_type = REGCACHE_FLAT, }; static int wm8974_probe(struct snd_soc_codec *codec) diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index c1c9c2e3525b..2ccb8bccc9d4 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -223,8 +223,8 @@ static void mcasp_start_tx(struct davinci_mcasp *mcasp) /* wait for XDATA to be cleared */ cnt = 0; - while (!(mcasp_get_reg(mcasp, DAVINCI_MCASP_TXSTAT_REG) & - ~XRDATA) && (cnt < 100000)) + while ((mcasp_get_reg(mcasp, DAVINCI_MCASP_TXSTAT_REG) & XRDATA) && + (cnt < 100000)) cnt++; /* Release TX state machine */ diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index ffd5f9acc849..08b460ba06ef 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -505,6 +505,24 @@ static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd, FSL_SAI_CSR_FR, FSL_SAI_CSR_FR); regmap_update_bits(sai->regmap, FSL_SAI_RCSR, FSL_SAI_CSR_FR, FSL_SAI_CSR_FR); + + /* + * For sai master mode, after several open/close sai, + * there will be no frame clock, and can't recover + * anymore. Add software reset to fix this issue. + * This is a hardware bug, and will be fix in the + * next sai version. + */ + if (!sai->is_slave_mode) { + /* Software Reset for both Tx and Rx */ + regmap_write(sai->regmap, + FSL_SAI_TCSR, FSL_SAI_CSR_SR); + regmap_write(sai->regmap, + FSL_SAI_RCSR, FSL_SAI_CSR_SR); + /* Clear SR bit to finish the reset */ + regmap_write(sai->regmap, FSL_SAI_TCSR, 0); + regmap_write(sai->regmap, FSL_SAI_RCSR, 0); + } } break; default: diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index ffea427aeca8..ad4d0f82603e 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -1240,7 +1240,6 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus) */ ret = snd_soc_tplg_component_load(&platform->component, &skl_tplg_ops, fw, 0); - release_firmware(fw); if (ret < 0) { dev_err(bus->dev, "tplg component load failed%d\n", ret); return -EINVAL; @@ -1249,5 +1248,7 @@ int skl_tplg_init(struct snd_soc_platform *platform, struct hdac_ext_bus *ebus) skl->resource.max_mcps = SKL_MAX_MCPS; skl->resource.max_mem = SKL_FW_MAX_MEM; + skl->tplg = fw; + return 0; } diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 5319529aedf7..caa69c4598a6 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -25,6 +25,7 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> +#include <linux/firmware.h> #include <sound/pcm.h> #include "skl.h" @@ -520,6 +521,9 @@ static void skl_remove(struct pci_dev *pci) struct hdac_ext_bus *ebus = pci_get_drvdata(pci); struct skl *skl = ebus_to_skl(ebus); + if (skl->tplg) + release_firmware(skl->tplg); + if (pci_dev_run_wake(pci)) pm_runtime_get_noresume(&pci->dev); pci_dev_put(pci); diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h index dd2e79ae45a8..a0709e344d44 100644 --- a/sound/soc/intel/skylake/skl.h +++ b/sound/soc/intel/skylake/skl.h @@ -68,6 +68,8 @@ struct skl { struct skl_dsp_resource resource; struct list_head ppl_list; struct list_head dapm_path_list; + + const struct firmware *tplg; }; #define skl_to_ebus(s) (&(s)->ebus) diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c index ac72ff5055bb..5a806da89f42 100644 --- a/sound/soc/rockchip/rockchip_spdif.c +++ b/sound/soc/rockchip/rockchip_spdif.c @@ -152,8 +152,10 @@ static int rk_spdif_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: ret = regmap_update_bits(spdif->regmap, SPDIF_DMACR, - SPDIF_DMACR_TDE_ENABLE, - SPDIF_DMACR_TDE_ENABLE); + SPDIF_DMACR_TDE_ENABLE | + SPDIF_DMACR_TDL_MASK, + SPDIF_DMACR_TDE_ENABLE | + SPDIF_DMACR_TDL(16)); if (ret != 0) return ret; diff --git a/sound/soc/rockchip/rockchip_spdif.h b/sound/soc/rockchip/rockchip_spdif.h index 921b4095fb92..3ef12770ae12 100644 --- a/sound/soc/rockchip/rockchip_spdif.h +++ b/sound/soc/rockchip/rockchip_spdif.h @@ -42,7 +42,7 @@ #define SPDIF_DMACR_TDL_SHIFT 0 #define SPDIF_DMACR_TDL(x) ((x) << SPDIF_DMACR_TDL_SHIFT) -#define SPDIF_DMACR_TDL_MASK (0x1f << SDPIF_DMACR_TDL_SHIFT) +#define SPDIF_DMACR_TDL_MASK (0x1f << SPDIF_DMACR_TDL_SHIFT) /* * XFER diff --git a/tools/Makefile b/tools/Makefile index 7dc820a8c1f1..0ba0df3b516f 100644 --- a/tools/Makefile +++ b/tools/Makefile @@ -96,7 +96,7 @@ cgroup_install firewire_install hv_install lguest_install perf_install usb_insta $(call descend,$(@:_install=),install) selftests_install: - $(call descend,testing/$(@:_clean=),install) + $(call descend,testing/$(@:_install=),install) turbostat_install x86_energy_perf_policy_install: $(call descend,power/x86/$(@:_install=),install) diff --git a/tools/build/Makefile b/tools/build/Makefile index a93036272d43..0d5a0e3a8fa9 100644 --- a/tools/build/Makefile +++ b/tools/build/Makefile @@ -25,7 +25,7 @@ export Q srctree CC LD MAKEFLAGS := --no-print-directory build := -f $(srctree)/tools/build/Makefile.build dir=. obj -all: fixdep +all: $(OUTPUT)fixdep clean: $(call QUIET_CLEAN, fixdep) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 37ff4c9f92f1..02db3cdff20f 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -7,7 +7,7 @@ endif feature_check = $(eval $(feature_check_code)) define feature_check_code - feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0) + feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0) endef feature_set = $(eval $(feature_set_code)) @@ -101,7 +101,6 @@ ifeq ($(feature-all), 1) # $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat))) else - $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C $(feature_dir) $(addsuffix .bin,$(FEATURE_TESTS)) >/dev/null 2>&1) $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat))) endif @@ -123,13 +122,31 @@ define feature_print_text_code MSG = $(shell printf '...%30s: %s' $(1) $(2)) endef +# +# generates feature value assignment for name, like: +# $(call feature_assign,dwarf) == feature-dwarf=1 +# +feature_assign = feature-$(1)=$(feature-$(1)) + FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER) -FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),feature-$(feat)($(feature-$(feat)))) -FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME)) +FEATURE_DUMP := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME)) -ifeq ($(dwarf-post-unwind),1) - FEATURE_DUMP += dwarf-post-unwind($(dwarf-post-unwind-text)) -endif +feature_dump_check = $(eval $(feature_dump_check_code)) +define feature_dump_check_code + ifeq ($(findstring $(1),$(FEATURE_DUMP)),) + $(2) := 1 + endif +endef + +# +# First check if any test from FEATURE_DISPLAY +# and set feature_display := 1 if it does +$(foreach feat,$(FEATURE_DISPLAY),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_display)) + +# +# Now also check if any other test changed, +# so we force FEATURE-DUMP generation +$(foreach feat,$(FEATURE_TESTS),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_dump_changed)) # The $(feature_display) controls the default detection message # output. It's set if: @@ -138,13 +155,13 @@ endif # - one of the $(FEATURE_DISPLAY) is not detected # - VF is enabled -ifneq ("$(FEATURE_DUMP)","$(FEATURE_DUMP_FILE)") - $(shell echo "$(FEATURE_DUMP)" > $(FEATURE_DUMP_FILENAME)) - feature_display := 1 +ifeq ($(feature_dump_changed),1) + $(shell rm -f $(FEATURE_DUMP_FILENAME)) + $(foreach feat,$(FEATURE_TESTS),$(shell echo "$(call feature_assign,$(feat))" >> $(FEATURE_DUMP_FILENAME))) endif feature_display_check = $(eval $(feature_check_display_code)) -define feature_display_check_code +define feature_check_display_code ifneq ($(feature-$(1)), 1) feature_display := 1 endif @@ -161,11 +178,6 @@ ifeq ($(feature_display),1) $(info ) $(info Auto-detecting system features:) $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),)) - - ifeq ($(dwarf-post-unwind),1) - $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) - endif - ifneq ($(feature_verbose),1) $(info ) endif diff --git a/tools/build/Makefile.include b/tools/build/Makefile.include index 4e09ad617a60..be630bed66d2 100644 --- a/tools/build/Makefile.include +++ b/tools/build/Makefile.include @@ -4,7 +4,7 @@ ifdef CROSS_COMPILE fixdep: else fixdep: - $(Q)$(MAKE) -C $(srctree)/tools/build fixdep + $(Q)$(MAKE) -C $(srctree)/tools/build CFLAGS= LDFLAGS= $(OUTPUT)fixdep endif .PHONY: fixdep diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index cea04ce9f35c..bf8f0352264d 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -1,4 +1,3 @@ - FILES= \ test-all.bin \ test-backtrace.bin \ @@ -38,38 +37,40 @@ FILES= \ test-bpf.bin \ test-get_cpuid.bin +FILES := $(addprefix $(OUTPUT),$(FILES)) + CC := $(CROSS_COMPILE)gcc -MD PKG_CONFIG := $(CROSS_COMPILE)pkg-config all: $(FILES) -__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS) - BUILD = $(__BUILD) > $(OUTPUT)$(@:.bin=.make.output) 2>&1 +__BUILD = $(CC) $(CFLAGS) -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) + BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 ############################### -test-all.bin: +$(OUTPUT)test-all.bin: $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -test-hello.bin: +$(OUTPUT)test-hello.bin: $(BUILD) -test-pthread-attr-setaffinity-np.bin: +$(OUTPUT)test-pthread-attr-setaffinity-np.bin: $(BUILD) -D_GNU_SOURCE -lpthread -test-stackprotector-all.bin: +$(OUTPUT)test-stackprotector-all.bin: $(BUILD) -fstack-protector-all -test-fortify-source.bin: +$(OUTPUT)test-fortify-source.bin: $(BUILD) -O2 -D_FORTIFY_SOURCE=2 -test-bionic.bin: +$(OUTPUT)test-bionic.bin: $(BUILD) -test-libelf.bin: +$(OUTPUT)test-libelf.bin: $(BUILD) -lelf -test-glibc.bin: +$(OUTPUT)test-glibc.bin: $(BUILD) DWARFLIBS := -ldw @@ -77,37 +78,37 @@ ifeq ($(findstring -static,${LDFLAGS}),-static) DWARFLIBS += -lelf -lebl -lz -llzma -lbz2 endif -test-dwarf.bin: +$(OUTPUT)test-dwarf.bin: $(BUILD) $(DWARFLIBS) -test-libelf-mmap.bin: +$(OUTPUT)test-libelf-mmap.bin: $(BUILD) -lelf -test-libelf-getphdrnum.bin: +$(OUTPUT)test-libelf-getphdrnum.bin: $(BUILD) -lelf -test-libnuma.bin: +$(OUTPUT)test-libnuma.bin: $(BUILD) -lnuma -test-numa_num_possible_cpus.bin: +$(OUTPUT)test-numa_num_possible_cpus.bin: $(BUILD) -lnuma -test-libunwind.bin: +$(OUTPUT)test-libunwind.bin: $(BUILD) -lelf -test-libunwind-debug-frame.bin: +$(OUTPUT)test-libunwind-debug-frame.bin: $(BUILD) -lelf -test-libaudit.bin: +$(OUTPUT)test-libaudit.bin: $(BUILD) -laudit -test-libslang.bin: +$(OUTPUT)test-libslang.bin: $(BUILD) -I/usr/include/slang -lslang -test-gtk2.bin: +$(OUTPUT)test-gtk2.bin: $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) -test-gtk2-infobar.bin: +$(OUTPUT)test-gtk2-infobar.bin: $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) grep-libs = $(filter -l%,$(1)) @@ -119,63 +120,63 @@ PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) -test-libperl.bin: +$(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) -test-libpython.bin: +$(OUTPUT)test-libpython.bin: $(BUILD) -test-libpython-version.bin: +$(OUTPUT)test-libpython-version.bin: $(BUILD) -test-libbfd.bin: +$(OUTPUT)test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl -test-liberty.bin: - $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty +$(OUTPUT)test-liberty.bin: + $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -test-liberty-z.bin: - $(CC) $(CFLAGS) -Wall -Werror -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz +$(OUTPUT)test-liberty-z.bin: + $(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz -test-cplus-demangle.bin: +$(OUTPUT)test-cplus-demangle.bin: $(BUILD) -liberty -test-backtrace.bin: +$(OUTPUT)test-backtrace.bin: $(BUILD) -test-timerfd.bin: +$(OUTPUT)test-timerfd.bin: $(BUILD) -test-libdw-dwarf-unwind.bin: +$(OUTPUT)test-libdw-dwarf-unwind.bin: $(BUILD) # -ldw provided by $(FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind) -test-libbabeltrace.bin: +$(OUTPUT)test-libbabeltrace.bin: $(BUILD) # -lbabeltrace provided by $(FEATURE_CHECK_LDFLAGS-libbabeltrace) -test-sync-compare-and-swap.bin: +$(OUTPUT)test-sync-compare-and-swap.bin: $(BUILD) -test-compile-32.bin: - $(CC) -m32 -o $(OUTPUT)$@ test-compile.c +$(OUTPUT)test-compile-32.bin: + $(CC) -m32 -o $@ test-compile.c -test-compile-x32.bin: - $(CC) -mx32 -o $(OUTPUT)$@ test-compile.c +$(OUTPUT)test-compile-x32.bin: + $(CC) -mx32 -o $@ test-compile.c -test-zlib.bin: +$(OUTPUT)test-zlib.bin: $(BUILD) -lz -test-lzma.bin: +$(OUTPUT)test-lzma.bin: $(BUILD) -llzma -test-get_cpuid.bin: +$(OUTPUT)test-get_cpuid.bin: $(BUILD) -test-bpf.bin: +$(OUTPUT)test-bpf.bin: $(BUILD) --include *.d +-include $(OUTPUT)*.d ############################### clean: - rm -f $(FILES) *.d $(FILES:.bin=.make.output) + rm -f $(FILES) $(OUTPUT)*.d $(FILES:.bin=.make.output) diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 40bd21488032..28f5493da491 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -11,6 +11,8 @@ int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); +#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) + #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ ((nbits) % BITS_PER_LONG) ? \ diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h new file mode 100644 index 000000000000..e26223f1f287 --- /dev/null +++ b/tools/include/linux/string.h @@ -0,0 +1,15 @@ +#ifndef _TOOLS_LINUX_STRING_H_ +#define _TOOLS_LINUX_STRING_H_ + + +#include <linux/types.h> /* for size_t */ + +void *memdup(const void *src, size_t len); + +int strtobool(const char *s, bool *res); + +#ifndef __UCLIBC__ +extern size_t strlcpy(char *dest, const char *src, size_t size); +#endif + +#endif /* _LINUX_STRING_H_ */ diff --git a/tools/perf/util/bitmap.c b/tools/lib/bitmap.c index 0a1adc1111fd..0a1adc1111fd 100644 --- a/tools/perf/util/bitmap.c +++ b/tools/lib/bitmap.c diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index a3caaf3eafbd..919b71780710 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -71,7 +71,21 @@ FEATURE_DISPLAY = libelf bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) +check_feat := 1 +NON_CHECK_FEAT_TARGETS := clean TAGS tags cscope help +ifdef MAKECMDGOALS +ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) + check_feat := 0 +endif +endif + +ifeq ($(check_feat),1) +ifeq ($(FEATURES_DUMP),) include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif +endif export prefix libdir src obj diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index a6331050ab79..5bdc6eab6852 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -83,3 +83,17 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns, log_buf[0] = 0; return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } + +int bpf_map_update_elem(int fd, void *key, void *value, + u64 flags) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 854b7361b784..a76465541292 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -20,4 +20,6 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns, u32 kern_version, char *log_buf, size_t log_buf_sz); +int bpf_map_update_elem(int fd, void *key, void *value, + u64 flags); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index e176bad19bcb..8334a5a9d5d7 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -152,29 +152,36 @@ struct bpf_program { } *reloc_desc; int nr_reloc; - int fd; + struct { + int nr; + int *fds; + } instances; + bpf_program_prep_t preprocessor; struct bpf_object *obj; void *priv; bpf_program_clear_priv_t clear_priv; }; +struct bpf_map { + int fd; + char *name; + struct bpf_map_def def; + void *priv; + bpf_map_clear_priv_t clear_priv; +}; + static LIST_HEAD(bpf_objects_list); struct bpf_object { char license[64]; u32 kern_version; - void *maps_buf; - size_t maps_buf_sz; struct bpf_program *programs; size_t nr_programs; - int *map_fds; - /* - * This field is required because maps_buf will be freed and - * maps_buf_sz will be set to 0 after loaded. - */ - size_t nr_map_fds; + struct bpf_map *maps; + size_t nr_maps; + bool loaded; /* @@ -188,6 +195,7 @@ struct bpf_object { Elf *elf; GElf_Ehdr ehdr; Elf_Data *symbols; + size_t strtabidx; struct { GElf_Shdr shdr; Elf_Data *data; @@ -206,10 +214,25 @@ struct bpf_object { static void bpf_program__unload(struct bpf_program *prog) { + int i; + if (!prog) return; - zclose(prog->fd); + /* + * If the object is opened but the program was never loaded, + * it is possible that prog->instances.nr == -1. + */ + if (prog->instances.nr > 0) { + for (i = 0; i < prog->instances.nr; i++) + zclose(prog->instances.fds[i]); + } else if (prog->instances.nr != -1) { + pr_warning("Internal error: instances.nr is %d\n", + prog->instances.nr); + } + + prog->instances.nr = -1; + zfree(&prog->instances.fds); } static void bpf_program__exit(struct bpf_program *prog) @@ -260,7 +283,8 @@ bpf_program__init(void *data, size_t size, char *name, int idx, memcpy(prog->insns, data, prog->insns_cnt * sizeof(struct bpf_insn)); prog->idx = idx; - prog->fd = -1; + prog->instances.fds = NULL; + prog->instances.nr = -1; return 0; errout: @@ -469,21 +493,77 @@ static int bpf_object__init_maps(struct bpf_object *obj, void *data, size_t size) { - if (size == 0) { + size_t nr_maps; + int i; + + nr_maps = size / sizeof(struct bpf_map_def); + if (!data || !nr_maps) { pr_debug("%s doesn't need map definition\n", obj->path); return 0; } - obj->maps_buf = malloc(size); - if (!obj->maps_buf) { - pr_warning("malloc maps failed: %s\n", obj->path); + pr_debug("maps in %s: %zd bytes\n", obj->path, size); + + obj->maps = calloc(nr_maps, sizeof(obj->maps[0])); + if (!obj->maps) { + pr_warning("alloc maps for object failed\n"); return -ENOMEM; } + obj->nr_maps = nr_maps; - obj->maps_buf_sz = size; - memcpy(obj->maps_buf, data, size); - pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size); + for (i = 0; i < nr_maps; i++) { + struct bpf_map_def *def = &obj->maps[i].def; + + /* + * fill all fd with -1 so won't close incorrect + * fd (fd=0 is stdin) when failure (zclose won't close + * negative fd)). + */ + obj->maps[i].fd = -1; + + /* Save map definition into obj->maps */ + *def = ((struct bpf_map_def *)data)[i]; + } + return 0; +} + +static int +bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx) +{ + int i; + Elf_Data *symbols = obj->efile.symbols; + + if (!symbols || maps_shndx < 0) + return -EINVAL; + + for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { + GElf_Sym sym; + size_t map_idx; + const char *map_name; + + if (!gelf_getsym(symbols, i, &sym)) + continue; + if (sym.st_shndx != maps_shndx) + continue; + + map_name = elf_strptr(obj->efile.elf, + obj->efile.strtabidx, + sym.st_name); + map_idx = sym.st_value / sizeof(struct bpf_map_def); + if (map_idx >= obj->nr_maps) { + pr_warning("index of map \"%s\" is buggy: %zu > %zu\n", + map_name, map_idx, obj->nr_maps); + continue; + } + obj->maps[map_idx].name = strdup(map_name); + if (!obj->maps[map_idx].name) { + pr_warning("failed to alloc map name\n"); + return -ENOMEM; + } + pr_debug("map %zu is \"%s\"\n", map_idx, + obj->maps[map_idx].name); + } return 0; } @@ -492,7 +572,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; Elf_Scn *scn = NULL; - int idx = 0, err = 0; + int idx = 0, err = 0, maps_shndx = -1; /* Elf is corrupted/truncated, avoid calling elf_strptr. */ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) { @@ -542,16 +622,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj) err = bpf_object__init_kversion(obj, data->d_buf, data->d_size); - else if (strcmp(name, "maps") == 0) + else if (strcmp(name, "maps") == 0) { err = bpf_object__init_maps(obj, data->d_buf, data->d_size); - else if (sh.sh_type == SHT_SYMTAB) { + maps_shndx = idx; + } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); err = -LIBBPF_ERRNO__FORMAT; - } else + } else { obj->efile.symbols = data; + obj->efile.strtabidx = sh.sh_link; + } } else if ((sh.sh_type == SHT_PROGBITS) && (sh.sh_flags & SHF_EXECINSTR) && (data->d_size > 0)) { @@ -586,6 +669,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj) if (err) goto out; } + + if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) { + pr_warning("Corrupted ELF file: index of strtab invalid\n"); + return LIBBPF_ERRNO__FORMAT; + } + if (maps_shndx >= 0) + err = bpf_object__init_maps_name(obj, maps_shndx); out: return err; } @@ -668,37 +758,15 @@ static int bpf_object__create_maps(struct bpf_object *obj) { unsigned int i; - size_t nr_maps; - int *pfd; - - nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def); - if (!obj->maps_buf || !nr_maps) { - pr_debug("don't need create maps for %s\n", - obj->path); - return 0; - } - - obj->map_fds = malloc(sizeof(int) * nr_maps); - if (!obj->map_fds) { - pr_warning("realloc perf_bpf_map_fds failed\n"); - return -ENOMEM; - } - obj->nr_map_fds = nr_maps; - /* fill all fd with -1 */ - memset(obj->map_fds, -1, sizeof(int) * nr_maps); - - pfd = obj->map_fds; - for (i = 0; i < nr_maps; i++) { - struct bpf_map_def def; + for (i = 0; i < obj->nr_maps; i++) { + struct bpf_map_def *def = &obj->maps[i].def; + int *pfd = &obj->maps[i].fd; - def = *(struct bpf_map_def *)(obj->maps_buf + - i * sizeof(struct bpf_map_def)); - - *pfd = bpf_create_map(def.type, - def.key_size, - def.value_size, - def.max_entries); + *pfd = bpf_create_map(def->type, + def->key_size, + def->value_size, + def->max_entries); if (*pfd < 0) { size_t j; int err = *pfd; @@ -706,22 +774,17 @@ bpf_object__create_maps(struct bpf_object *obj) pr_warning("failed to create map: %s\n", strerror(errno)); for (j = 0; j < i; j++) - zclose(obj->map_fds[j]); - obj->nr_map_fds = 0; - zfree(&obj->map_fds); + zclose(obj->maps[j].fd); return err; } pr_debug("create map: fd=%d\n", *pfd); - pfd++; } - zfree(&obj->maps_buf); - obj->maps_buf_sz = 0; return 0; } static int -bpf_program__relocate(struct bpf_program *prog, int *map_fds) +bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj) { int i; @@ -741,7 +804,7 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds) return -LIBBPF_ERRNO__RELOC; } insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; - insns[insn_idx].imm = map_fds[map_idx]; + insns[insn_idx].imm = obj->maps[map_idx].fd; } zfree(&prog->reloc_desc); @@ -760,7 +823,7 @@ bpf_object__relocate(struct bpf_object *obj) for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_program__relocate(prog, obj->map_fds); + err = bpf_program__relocate(prog, obj); if (err) { pr_warning("failed to relocate '%s'\n", prog->section_name); @@ -784,8 +847,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj) Elf_Data *data = obj->efile.reloc[i].data; int idx = shdr->sh_info; struct bpf_program *prog; - size_t nr_maps = obj->maps_buf_sz / - sizeof(struct bpf_map_def); + size_t nr_maps = obj->nr_maps; if (shdr->sh_type != SHT_REL) { pr_warning("internal error at %d\n", __LINE__); @@ -860,13 +922,73 @@ static int bpf_program__load(struct bpf_program *prog, char *license, u32 kern_version) { - int err, fd; + int err = 0, fd, i; - err = load_program(prog->insns, prog->insns_cnt, - license, kern_version, &fd); - if (!err) - prog->fd = fd; + if (prog->instances.nr < 0 || !prog->instances.fds) { + if (prog->preprocessor) { + pr_warning("Internal error: can't load program '%s'\n", + prog->section_name); + return -LIBBPF_ERRNO__INTERNAL; + } + + prog->instances.fds = malloc(sizeof(int)); + if (!prog->instances.fds) { + pr_warning("Not enough memory for BPF fds\n"); + return -ENOMEM; + } + prog->instances.nr = 1; + prog->instances.fds[0] = -1; + } + + if (!prog->preprocessor) { + if (prog->instances.nr != 1) { + pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n", + prog->section_name, prog->instances.nr); + } + err = load_program(prog->insns, prog->insns_cnt, + license, kern_version, &fd); + if (!err) + prog->instances.fds[0] = fd; + goto out; + } + + for (i = 0; i < prog->instances.nr; i++) { + struct bpf_prog_prep_result result; + bpf_program_prep_t preprocessor = prog->preprocessor; + + bzero(&result, sizeof(result)); + err = preprocessor(prog, i, prog->insns, + prog->insns_cnt, &result); + if (err) { + pr_warning("Preprocessing the %dth instance of program '%s' failed\n", + i, prog->section_name); + goto out; + } + + if (!result.new_insn_ptr || !result.new_insn_cnt) { + pr_debug("Skip loading the %dth instance of program '%s'\n", + i, prog->section_name); + prog->instances.fds[i] = -1; + if (result.pfd) + *result.pfd = -1; + continue; + } + + err = load_program(result.new_insn_ptr, + result.new_insn_cnt, + license, kern_version, &fd); + + if (err) { + pr_warning("Loading the %dth instance of program '%s' failed\n", + i, prog->section_name); + goto out; + } + if (result.pfd) + *result.pfd = fd; + prog->instances.fds[i] = fd; + } +out: if (err) pr_warning("failed to load program '%s'\n", prog->section_name); @@ -970,10 +1092,8 @@ int bpf_object__unload(struct bpf_object *obj) if (!obj) return -EINVAL; - for (i = 0; i < obj->nr_map_fds; i++) - zclose(obj->map_fds[i]); - zfree(&obj->map_fds); - obj->nr_map_fds = 0; + for (i = 0; i < obj->nr_maps; i++) + zclose(obj->maps[i].fd); for (i = 0; i < obj->nr_programs; i++) bpf_program__unload(&obj->programs[i]); @@ -1016,7 +1136,16 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); - zfree(&obj->maps_buf); + for (i = 0; i < obj->nr_maps; i++) { + zfree(&obj->maps[i].name); + if (obj->maps[i].clear_priv) + obj->maps[i].clear_priv(&obj->maps[i], + obj->maps[i].priv); + obj->maps[i].priv = NULL; + obj->maps[i].clear_priv = NULL; + } + zfree(&obj->maps); + obj->nr_maps = 0; if (obj->programs && obj->nr_programs) { for (i = 0; i < obj->nr_programs; i++) @@ -1121,5 +1250,142 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy) int bpf_program__fd(struct bpf_program *prog) { - return prog->fd; + return bpf_program__nth_fd(prog, 0); +} + +int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, + bpf_program_prep_t prep) +{ + int *instances_fds; + + if (nr_instances <= 0 || !prep) + return -EINVAL; + + if (prog->instances.nr > 0 || prog->instances.fds) { + pr_warning("Can't set pre-processor after loading\n"); + return -EINVAL; + } + + instances_fds = malloc(sizeof(int) * nr_instances); + if (!instances_fds) { + pr_warning("alloc memory failed for fds\n"); + return -ENOMEM; + } + + /* fill all fd with -1 */ + memset(instances_fds, -1, sizeof(int) * nr_instances); + + prog->instances.nr = nr_instances; + prog->instances.fds = instances_fds; + prog->preprocessor = prep; + return 0; +} + +int bpf_program__nth_fd(struct bpf_program *prog, int n) +{ + int fd; + + if (n >= prog->instances.nr || n < 0) { + pr_warning("Can't get the %dth fd from program %s: only %d instances\n", + n, prog->section_name, prog->instances.nr); + return -EINVAL; + } + + fd = prog->instances.fds[n]; + if (fd < 0) { + pr_warning("%dth instance of program '%s' is invalid\n", + n, prog->section_name); + return -ENOENT; + } + + return fd; +} + +int bpf_map__get_fd(struct bpf_map *map) +{ + if (!map) + return -EINVAL; + + return map->fd; +} + +int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef) +{ + if (!map || !pdef) + return -EINVAL; + + *pdef = map->def; + return 0; +} + +const char *bpf_map__get_name(struct bpf_map *map) +{ + if (!map) + return NULL; + return map->name; +} + +int bpf_map__set_private(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv) +{ + if (!map) + return -EINVAL; + + if (map->priv) { + if (map->clear_priv) + map->clear_priv(map, map->priv); + } + + map->priv = priv; + map->clear_priv = clear_priv; + return 0; +} + +int bpf_map__get_private(struct bpf_map *map, void **ppriv) +{ + if (!map) + return -EINVAL; + + if (ppriv) + *ppriv = map->priv; + return 0; +} + +struct bpf_map * +bpf_map__next(struct bpf_map *prev, struct bpf_object *obj) +{ + size_t idx; + struct bpf_map *s, *e; + + if (!obj || !obj->maps) + return NULL; + + s = obj->maps; + e = obj->maps + obj->nr_maps; + + if (prev == NULL) + return s; + + if ((prev < s) || (prev >= e)) { + pr_warning("error in %s: map handler doesn't belong to object\n", + __func__); + return NULL; + } + + idx = (prev - obj->maps) + 1; + if (idx >= obj->nr_maps) + return NULL; + return &obj->maps[idx]; +} + +struct bpf_map * +bpf_object__get_map_by_name(struct bpf_object *obj, const char *name) +{ + struct bpf_map *pos; + + bpf_map__for_each(pos, obj) { + if (pos->name && !strcmp(pos->name, name)) + return pos; + } + return NULL; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index c9a9aef2806c..a51594c7b518 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -88,6 +88,70 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); int bpf_program__fd(struct bpf_program *prog); +struct bpf_insn; + +/* + * Libbpf allows callers to adjust BPF programs before being loaded + * into kernel. One program in an object file can be transform into + * multiple variants to be attached to different code. + * + * bpf_program_prep_t, bpf_program__set_prep and bpf_program__nth_fd + * are APIs for this propose. + * + * - bpf_program_prep_t: + * It defines 'preprocessor', which is a caller defined function + * passed to libbpf through bpf_program__set_prep(), and will be + * called before program is loaded. The processor should adjust + * the program one time for each instances according to the number + * passed to it. + * + * - bpf_program__set_prep: + * Attachs a preprocessor to a BPF program. The number of instances + * whould be created is also passed through this function. + * + * - bpf_program__nth_fd: + * After the program is loaded, get resuling fds from bpf program for + * each instances. + * + * If bpf_program__set_prep() is not used, the program whould be loaded + * without adjustment during bpf_object__load(). The program has only + * one instance. In this case bpf_program__fd(prog) is equal to + * bpf_program__nth_fd(prog, 0). + */ + +struct bpf_prog_prep_result { + /* + * If not NULL, load new instruction array. + * If set to NULL, don't load this instance. + */ + struct bpf_insn *new_insn_ptr; + int new_insn_cnt; + + /* If not NULL, result fd is set to it */ + int *pfd; +}; + +/* + * Parameters of bpf_program_prep_t: + * - prog: The bpf_program being loaded. + * - n: Index of instance being generated. + * - insns: BPF instructions array. + * - insns_cnt:Number of instructions in insns. + * - res: Output parameter, result of transformation. + * + * Return value: + * - Zero: pre-processing success. + * - Non-zero: pre-processing, stop loading. + */ +typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, + struct bpf_insn *insns, int insns_cnt, + struct bpf_prog_prep_result *res); + +int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, + bpf_program_prep_t prep); + +int bpf_program__nth_fd(struct bpf_program *prog, int n); + /* * We don't need __attribute__((packed)) now since it is * unnecessary for 'bpf_map_def' because they are all aligned. @@ -101,4 +165,28 @@ struct bpf_map_def { unsigned int max_entries; }; +/* + * There is another 'struct bpf_map' in include/linux/map.h. However, + * it is not a uapi header so no need to consider name clash. + */ +struct bpf_map; +struct bpf_map * +bpf_object__get_map_by_name(struct bpf_object *obj, const char *name); + +struct bpf_map * +bpf_map__next(struct bpf_map *map, struct bpf_object *obj); +#define bpf_map__for_each(pos, obj) \ + for ((pos) = bpf_map__next(NULL, (obj)); \ + (pos) != NULL; \ + (pos) = bpf_map__next((pos), (obj))) + +int bpf_map__get_fd(struct bpf_map *map); +int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef); +const char *bpf_map__get_name(struct bpf_map *map); + +typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); +int bpf_map__set_private(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv); +int bpf_map__get_private(struct bpf_map *map, void **ppriv); + #endif diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c new file mode 100644 index 000000000000..9122a9e80046 --- /dev/null +++ b/tools/lib/find_bit.c @@ -0,0 +1,84 @@ +/* bit search implementation + * + * Copied from lib/find_bit.c to tools/lib/find_bit.c + * + * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * Copyright (C) 2008 IBM Corporation + * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> + * (Inspired by David Howell's find_next_bit implementation) + * + * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease + * size and improve performance, 2015. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/bitops.h> +#include <linux/bitmap.h> +#include <linux/kernel.h> + +#if !defined(find_next_bit) + +/* + * This is a common helper function for find_next_bit and + * find_next_zero_bit. The difference is the "invert" argument, which + * is XORed with each fetched word before searching it for one bits. + */ +static unsigned long _find_next_bit(const unsigned long *addr, + unsigned long nbits, unsigned long start, unsigned long invert) +{ + unsigned long tmp; + + if (!nbits || start >= nbits) + return nbits; + + tmp = addr[start / BITS_PER_LONG] ^ invert; + + /* Handle 1st word. */ + tmp &= BITMAP_FIRST_WORD_MASK(start); + start = round_down(start, BITS_PER_LONG); + + while (!tmp) { + start += BITS_PER_LONG; + if (start >= nbits) + return nbits; + + tmp = addr[start / BITS_PER_LONG] ^ invert; + } + + return min(start + __ffs(tmp), nbits); +} +#endif + +#ifndef find_next_bit +/* + * Find the next set bit in a memory region. + */ +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + return _find_next_bit(addr, size, offset, 0UL); +} +#endif + +#ifndef find_first_bit +/* + * Find the first set bit in a memory region. + */ +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + unsigned long idx; + + for (idx = 0; idx * BITS_PER_LONG < size; idx++) { + if (addr[idx]) + return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); + } + + return size; +} +#endif diff --git a/tools/lib/string.c b/tools/lib/string.c new file mode 100644 index 000000000000..bd239bc1d557 --- /dev/null +++ b/tools/lib/string.c @@ -0,0 +1,89 @@ +/* + * linux/tools/lib/string.c + * + * Copied from linux/lib/string.c, where it is: + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * More specifically, the first copied function was strtobool, which + * was introduced by: + * + * d0f1fed29e6e ("Add a strtobool function matching semantics of existing in kernel equivalents") + * Author: Jonathan Cameron <jic23@cam.ac.uk> + */ + +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <linux/string.h> +#include <linux/compiler.h> + +/** + * memdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + */ +void *memdup(const void *src, size_t len) +{ + void *p = malloc(len); + + if (p) + memcpy(p, src, len); + + return p; +} + +/** + * strtobool - convert common user inputs into boolean values + * @s: input string + * @res: result + * + * This routine returns 0 iff the first character is one of 'Yy1Nn0'. + * Otherwise it will return -EINVAL. Value pointed to by res is + * updated upon finding a match. + */ +int strtobool(const char *s, bool *res) +{ + switch (s[0]) { + case 'y': + case 'Y': + case '1': + *res = true; + break; + case 'n': + case 'N': + case '0': + *res = false; + break; + default: + return -EINVAL; + } + return 0; +} + +/** + * strlcpy - Copy a C-string into a sized buffer + * @dest: Where to copy the string to + * @src: Where to copy the string from + * @size: size of destination buffer + * + * Compatible with *BSD: the result is always a valid + * NUL-terminated string that fits in the buffer (unless, + * of course, the buffer size is zero). It does not pad + * out the result like strncpy() does. + * + * If libc has strlcpy() then that version will override this + * implementation: + */ +size_t __weak strlcpy(char *dest, const char *src, size_t size) +{ + size_t ret = strlen(src); + + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + memcpy(dest, src, len); + dest[len] = '\0'; + } + return ret; +} diff --git a/tools/lib/subcmd/Build b/tools/lib/subcmd/Build new file mode 100644 index 000000000000..ee31288788c1 --- /dev/null +++ b/tools/lib/subcmd/Build @@ -0,0 +1,7 @@ +libsubcmd-y += exec-cmd.o +libsubcmd-y += help.o +libsubcmd-y += pager.o +libsubcmd-y += parse-options.o +libsubcmd-y += run-command.o +libsubcmd-y += sigchain.o +libsubcmd-y += subcmd-config.o diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile new file mode 100644 index 000000000000..629cf8c14e68 --- /dev/null +++ b/tools/lib/subcmd/Makefile @@ -0,0 +1,48 @@ +include ../../scripts/Makefile.include +include ../../perf/config/utilities.mak # QUIET_CLEAN + +ifeq ($(srctree),) +srctree := $(patsubst %/,%,$(dir $(shell pwd))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +srctree := $(patsubst %/,%,$(dir $(srctree))) +#$(info Determined 'srctree' to be $(srctree)) +endif + +CC = $(CROSS_COMPILE)gcc +AR = $(CROSS_COMPILE)ar +RM = rm -f + +MAKEFLAGS += --no-print-directory + +LIBFILE = $(OUTPUT)libsubcmd.a + +CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE + +CFLAGS += -I$(srctree)/tools/include/ +CFLAGS += -I$(srctree)/include/uapi +CFLAGS += -I$(srctree)/include + +SUBCMD_IN := $(OUTPUT)libsubcmd-in.o + +all: + +export srctree OUTPUT CC LD CFLAGS V +include $(srctree)/tools/build/Makefile.include + +all: fixdep $(LIBFILE) + +$(SUBCMD_IN): FORCE + @$(MAKE) $(build)=libsubcmd + +$(LIBFILE): $(SUBCMD_IN) + $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(SUBCMD_IN) + +clean: + $(call QUIET_CLEAN, libsubcmd) $(RM) $(LIBFILE); \ + find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) + +FORCE: + +.PHONY: clean FORCE diff --git a/tools/lib/subcmd/exec-cmd.c b/tools/lib/subcmd/exec-cmd.c new file mode 100644 index 000000000000..1ae833af1a4a --- /dev/null +++ b/tools/lib/subcmd/exec-cmd.c @@ -0,0 +1,209 @@ +#include <linux/compiler.h> +#include <linux/string.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include "subcmd-util.h" +#include "exec-cmd.h" +#include "subcmd-config.h" + +#define MAX_ARGS 32 +#define PATH_MAX 4096 + +static const char *argv_exec_path; +static const char *argv0_path; + +void exec_cmd_init(const char *exec_name, const char *prefix, + const char *exec_path, const char *exec_path_env) +{ + subcmd_config.exec_name = exec_name; + subcmd_config.prefix = prefix; + subcmd_config.exec_path = exec_path; + subcmd_config.exec_path_env = exec_path_env; +} + +#define is_dir_sep(c) ((c) == '/') + +static int is_absolute_path(const char *path) +{ + return path[0] == '/'; +} + +static const char *get_pwd_cwd(void) +{ + static char cwd[PATH_MAX + 1]; + char *pwd; + struct stat cwd_stat, pwd_stat; + if (getcwd(cwd, PATH_MAX) == NULL) + return NULL; + pwd = getenv("PWD"); + if (pwd && strcmp(pwd, cwd)) { + stat(cwd, &cwd_stat); + if (!stat(pwd, &pwd_stat) && + pwd_stat.st_dev == cwd_stat.st_dev && + pwd_stat.st_ino == cwd_stat.st_ino) { + strlcpy(cwd, pwd, PATH_MAX); + } + } + return cwd; +} + +static const char *make_nonrelative_path(const char *path) +{ + static char buf[PATH_MAX + 1]; + + if (is_absolute_path(path)) { + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } else { + const char *cwd = get_pwd_cwd(); + if (!cwd) + die("Cannot determine the current working directory"); + if (snprintf(buf, PATH_MAX, "%s/%s", cwd, path) >= PATH_MAX) + die("Too long path: %.*s", 60, path); + } + return buf; +} + +char *system_path(const char *path) +{ + char *buf = NULL; + + if (is_absolute_path(path)) + return strdup(path); + + astrcatf(&buf, "%s/%s", subcmd_config.prefix, path); + + return buf; +} + +const char *extract_argv0_path(const char *argv0) +{ + const char *slash; + + if (!argv0 || !*argv0) + return NULL; + slash = argv0 + strlen(argv0); + + while (argv0 <= slash && !is_dir_sep(*slash)) + slash--; + + if (slash >= argv0) { + argv0_path = strndup(argv0, slash - argv0); + return argv0_path ? slash + 1 : NULL; + } + + return argv0; +} + +void set_argv_exec_path(const char *exec_path) +{ + argv_exec_path = exec_path; + /* + * Propagate this setting to external programs. + */ + setenv(subcmd_config.exec_path_env, exec_path, 1); +} + + +/* Returns the highest-priority location to look for subprograms. */ +char *get_argv_exec_path(void) +{ + char *env; + + if (argv_exec_path) + return strdup(argv_exec_path); + + env = getenv(subcmd_config.exec_path_env); + if (env && *env) + return strdup(env); + + return system_path(subcmd_config.exec_path); +} + +static void add_path(char **out, const char *path) +{ + if (path && *path) { + if (is_absolute_path(path)) + astrcat(out, path); + else + astrcat(out, make_nonrelative_path(path)); + + astrcat(out, ":"); + } +} + +void setup_path(void) +{ + const char *old_path = getenv("PATH"); + char *new_path = NULL; + char *tmp = get_argv_exec_path(); + + add_path(&new_path, tmp); + add_path(&new_path, argv0_path); + free(tmp); + + if (old_path) + astrcat(&new_path, old_path); + else + astrcat(&new_path, "/usr/local/bin:/usr/bin:/bin"); + + setenv("PATH", new_path, 1); + + free(new_path); +} + +static const char **prepare_exec_cmd(const char **argv) +{ + int argc; + const char **nargv; + + for (argc = 0; argv[argc]; argc++) + ; /* just counting */ + nargv = malloc(sizeof(*nargv) * (argc + 2)); + + nargv[0] = subcmd_config.exec_name; + for (argc = 0; argv[argc]; argc++) + nargv[argc + 1] = argv[argc]; + nargv[argc + 1] = NULL; + return nargv; +} + +int execv_cmd(const char **argv) { + const char **nargv = prepare_exec_cmd(argv); + + /* execvp() can only ever return if it fails */ + execvp(subcmd_config.exec_name, (char **)nargv); + + free(nargv); + return -1; +} + + +int execl_cmd(const char *cmd,...) +{ + int argc; + const char *argv[MAX_ARGS + 1]; + const char *arg; + va_list param; + + va_start(param, cmd); + argv[0] = cmd; + argc = 1; + while (argc < MAX_ARGS) { + arg = argv[argc++] = va_arg(param, char *); + if (!arg) + break; + } + va_end(param); + if (MAX_ARGS <= argc) { + fprintf(stderr, " Error: too many args to run %s\n", cmd); + return -1; + } + + argv[argc] = NULL; + return execv_cmd(argv); +} diff --git a/tools/lib/subcmd/exec-cmd.h b/tools/lib/subcmd/exec-cmd.h new file mode 100644 index 000000000000..5d08bda31d90 --- /dev/null +++ b/tools/lib/subcmd/exec-cmd.h @@ -0,0 +1,16 @@ +#ifndef __SUBCMD_EXEC_CMD_H +#define __SUBCMD_EXEC_CMD_H + +extern void exec_cmd_init(const char *exec_name, const char *prefix, + const char *exec_path, const char *exec_path_env); + +extern void set_argv_exec_path(const char *exec_path); +extern const char *extract_argv0_path(const char *path); +extern void setup_path(void); +extern int execv_cmd(const char **argv); /* NULL terminated */ +extern int execl_cmd(const char *cmd, ...); +/* get_argv_exec_path and system_path return malloc'd string, caller must free it */ +extern char *get_argv_exec_path(void); +extern char *system_path(const char *path); + +#endif /* __SUBCMD_EXEC_CMD_H */ diff --git a/tools/perf/util/help.c b/tools/lib/subcmd/help.c index 86c37c472263..e228c3cb3716 100644 --- a/tools/perf/util/help.c +++ b/tools/lib/subcmd/help.c @@ -1,9 +1,15 @@ -#include "cache.h" -#include "../builtin.h" -#include "exec_cmd.h" -#include "levenshtein.h" -#include "help.h" +#include <stdio.h> +#include <stdlib.h> +#include <string.h> #include <termios.h> +#include <sys/ioctl.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> +#include <dirent.h> +#include "subcmd-util.h" +#include "help.h" +#include "exec-cmd.h" void add_cmdname(struct cmdnames *cmds, const char *name, size_t len) { @@ -17,7 +23,7 @@ void add_cmdname(struct cmdnames *cmds, const char *name, size_t len) cmds->names[cmds->cnt++] = ent; } -static void clean_cmdnames(struct cmdnames *cmds) +void clean_cmdnames(struct cmdnames *cmds) { unsigned int i; @@ -28,14 +34,14 @@ static void clean_cmdnames(struct cmdnames *cmds) cmds->alloc = 0; } -static int cmdname_compare(const void *a_, const void *b_) +int cmdname_compare(const void *a_, const void *b_) { struct cmdname *a = *(struct cmdname **)a_; struct cmdname *b = *(struct cmdname **)b_; return strcmp(a->name, b->name); } -static void uniq(struct cmdnames *cmds) +void uniq(struct cmdnames *cmds) { unsigned int i, j; @@ -71,6 +77,28 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) cmds->cnt = cj; } +static void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} + static void pretty_print_string_list(struct cmdnames *cmds, int longest) { int cols = 1, rows; @@ -114,6 +142,14 @@ static int is_executable(const char *name) return st.st_mode & S_IXUSR; } +static int has_extension(const char *filename, const char *ext) +{ + size_t len = strlen(filename); + size_t extlen = strlen(ext); + + return len > extlen && !memcmp(filename + len - extlen, ext, extlen); +} + static void list_commands_in_dir(struct cmdnames *cmds, const char *path, const char *prefix) @@ -121,8 +157,7 @@ static void list_commands_in_dir(struct cmdnames *cmds, int prefix_len; DIR *dir = opendir(path); struct dirent *de; - struct strbuf buf = STRBUF_INIT; - int len; + char *buf = NULL; if (!dir) return; @@ -130,8 +165,7 @@ static void list_commands_in_dir(struct cmdnames *cmds, prefix = "perf-"; prefix_len = strlen(prefix); - strbuf_addf(&buf, "%s/", path); - len = buf.len; + astrcatf(&buf, "%s/", path); while ((de = readdir(dir)) != NULL) { int entlen; @@ -139,9 +173,8 @@ static void list_commands_in_dir(struct cmdnames *cmds, if (prefixcmp(de->d_name, prefix)) continue; - strbuf_setlen(&buf, len); - strbuf_addstr(&buf, de->d_name); - if (!is_executable(buf.buf)) + astrcat(&buf, de->d_name); + if (!is_executable(buf)) continue; entlen = strlen(de->d_name) - prefix_len; @@ -151,7 +184,7 @@ static void list_commands_in_dir(struct cmdnames *cmds, add_cmdname(cmds, de->d_name + prefix_len, entlen); } closedir(dir); - strbuf_release(&buf); + free(buf); } void load_command_list(const char *prefix, @@ -159,7 +192,7 @@ void load_command_list(const char *prefix, struct cmdnames *other_cmds) { const char *env_path = getenv("PATH"); - const char *exec_path = perf_exec_path(); + char *exec_path = get_argv_exec_path(); if (exec_path) { list_commands_in_dir(main_cmds, exec_path, prefix); @@ -172,7 +205,7 @@ void load_command_list(const char *prefix, char *paths, *path, *colon; path = paths = strdup(env_path); while (1) { - if ((colon = strchr(path, PATH_SEP))) + if ((colon = strchr(path, ':'))) *colon = 0; if (!exec_path || strcmp(path, exec_path)) list_commands_in_dir(other_cmds, path, prefix); @@ -187,6 +220,7 @@ void load_command_list(const char *prefix, sizeof(*other_cmds->names), cmdname_compare); uniq(other_cmds); } + free(exec_path); exclude_cmds(other_cmds, main_cmds); } @@ -203,13 +237,14 @@ void list_commands(const char *title, struct cmdnames *main_cmds, longest = other_cmds->names[i]->len; if (main_cmds->cnt) { - const char *exec_path = perf_exec_path(); + char *exec_path = get_argv_exec_path(); printf("available %s in '%s'\n", title, exec_path); printf("----------------"); mput_char('-', strlen(title) + strlen(exec_path)); putchar('\n'); pretty_print_string_list(main_cmds, longest); putchar('\n'); + free(exec_path); } if (other_cmds->cnt) { @@ -231,109 +266,3 @@ int is_in_cmdlist(struct cmdnames *c, const char *s) return 1; return 0; } - -static int autocorrect; -static struct cmdnames aliases; - -static int perf_unknown_cmd_config(const char *var, const char *value, void *cb) -{ - if (!strcmp(var, "help.autocorrect")) - autocorrect = perf_config_int(var,value); - /* Also use aliases for command lookup */ - if (!prefixcmp(var, "alias.")) - add_cmdname(&aliases, var + 6, strlen(var + 6)); - - return perf_default_config(var, value, cb); -} - -static int levenshtein_compare(const void *p1, const void *p2) -{ - const struct cmdname *const *c1 = p1, *const *c2 = p2; - const char *s1 = (*c1)->name, *s2 = (*c2)->name; - int l1 = (*c1)->len; - int l2 = (*c2)->len; - return l1 != l2 ? l1 - l2 : strcmp(s1, s2); -} - -static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) -{ - unsigned int i; - - ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc); - - for (i = 0; i < old->cnt; i++) - cmds->names[cmds->cnt++] = old->names[i]; - zfree(&old->names); - old->cnt = 0; -} - -const char *help_unknown_cmd(const char *cmd) -{ - unsigned int i, n = 0, best_similarity = 0; - struct cmdnames main_cmds, other_cmds; - - memset(&main_cmds, 0, sizeof(main_cmds)); - memset(&other_cmds, 0, sizeof(main_cmds)); - memset(&aliases, 0, sizeof(aliases)); - - perf_config(perf_unknown_cmd_config, NULL); - - load_command_list("perf-", &main_cmds, &other_cmds); - - add_cmd_list(&main_cmds, &aliases); - add_cmd_list(&main_cmds, &other_cmds); - qsort(main_cmds.names, main_cmds.cnt, - sizeof(main_cmds.names), cmdname_compare); - uniq(&main_cmds); - - if (main_cmds.cnt) { - /* This reuses cmdname->len for similarity index */ - for (i = 0; i < main_cmds.cnt; ++i) - main_cmds.names[i]->len = - levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4); - - qsort(main_cmds.names, main_cmds.cnt, - sizeof(*main_cmds.names), levenshtein_compare); - - best_similarity = main_cmds.names[0]->len; - n = 1; - while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len) - ++n; - } - - if (autocorrect && n == 1) { - const char *assumed = main_cmds.names[0]->name; - - main_cmds.names[0] = NULL; - clean_cmdnames(&main_cmds); - fprintf(stderr, "WARNING: You called a perf program named '%s', " - "which does not exist.\n" - "Continuing under the assumption that you meant '%s'\n", - cmd, assumed); - if (autocorrect > 0) { - fprintf(stderr, "in %0.1f seconds automatically...\n", - (float)autocorrect/10.0); - poll(NULL, 0, autocorrect * 100); - } - return assumed; - } - - fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd); - - if (main_cmds.cnt && best_similarity < 6) { - fprintf(stderr, "\nDid you mean %s?\n", - n < 2 ? "this": "one of these"); - - for (i = 0; i < n; i++) - fprintf(stderr, "\t%s\n", main_cmds.names[i]->name); - } - - exit(1); -} - -int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused, - const char *prefix __maybe_unused) -{ - printf("perf version %s\n", perf_version_string); - return 0; -} diff --git a/tools/perf/util/help.h b/tools/lib/subcmd/help.h index 7f5c6dedd714..e145a020780c 100644 --- a/tools/perf/util/help.h +++ b/tools/lib/subcmd/help.h @@ -1,12 +1,14 @@ -#ifndef __PERF_HELP_H -#define __PERF_HELP_H +#ifndef __SUBCMD_HELP_H +#define __SUBCMD_HELP_H + +#include <sys/types.h> struct cmdnames { size_t alloc; size_t cnt; struct cmdname { size_t len; /* also used for similarity index in help.c */ - char name[FLEX_ARRAY]; + char name[]; } **names; }; @@ -20,10 +22,13 @@ void load_command_list(const char *prefix, struct cmdnames *main_cmds, struct cmdnames *other_cmds); void add_cmdname(struct cmdnames *cmds, const char *name, size_t len); +void clean_cmdnames(struct cmdnames *cmds); +int cmdname_compare(const void *a, const void *b); +void uniq(struct cmdnames *cmds); /* Here we require that excludes is a sorted list. */ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes); int is_in_cmdlist(struct cmdnames *c, const char *s); void list_commands(const char *title, struct cmdnames *main_cmds, struct cmdnames *other_cmds); -#endif /* __PERF_HELP_H */ +#endif /* __SUBCMD_HELP_H */ diff --git a/tools/perf/util/pager.c b/tools/lib/subcmd/pager.c index 53ef006a951c..d50f3b58606b 100644 --- a/tools/perf/util/pager.c +++ b/tools/lib/subcmd/pager.c @@ -1,6 +1,12 @@ -#include "cache.h" +#include <sys/select.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <signal.h> +#include "pager.h" #include "run-command.h" #include "sigchain.h" +#include "subcmd-config.h" /* * This is split up from the rest of git so that we can do @@ -9,6 +15,11 @@ static int spawned_pager; +void pager_init(const char *pager_env) +{ + subcmd_config.pager_env = pager_env; +} + static void pager_preexec(void) { /* @@ -46,7 +57,7 @@ static void wait_for_pager_signal(int signo) void setup_pager(void) { - const char *pager = getenv("PERF_PAGER"); + const char *pager = getenv(subcmd_config.pager_env); if (!isatty(1)) return; @@ -85,11 +96,5 @@ void setup_pager(void) int pager_in_use(void) { - const char *env; - - if (spawned_pager) - return 1; - - env = getenv("PERF_PAGER_IN_USE"); - return env ? perf_config_bool("PERF_PAGER_IN_USE", env) : 0; + return spawned_pager; } diff --git a/tools/lib/subcmd/pager.h b/tools/lib/subcmd/pager.h new file mode 100644 index 000000000000..8b83714ecf73 --- /dev/null +++ b/tools/lib/subcmd/pager.h @@ -0,0 +1,9 @@ +#ifndef __SUBCMD_PAGER_H +#define __SUBCMD_PAGER_H + +extern void pager_init(const char *pager_env); + +extern void setup_pager(void); +extern int pager_in_use(void); + +#endif /* __SUBCMD_PAGER_H */ diff --git a/tools/perf/util/parse-options.c b/tools/lib/subcmd/parse-options.c index 9fca09296eb3..981bb4481fd5 100644 --- a/tools/perf/util/parse-options.c +++ b/tools/lib/subcmd/parse-options.c @@ -1,37 +1,66 @@ -#include "util.h" +#include <linux/compiler.h> +#include <linux/types.h> +#include <stdio.h> +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <ctype.h> +#include "subcmd-util.h" #include "parse-options.h" -#include "cache.h" -#include "header.h" -#include <linux/string.h> +#include "subcmd-config.h" +#include "pager.h" #define OPT_SHORT 1 #define OPT_UNSET 2 -static struct strbuf error_buf = STRBUF_INIT; +char *error_buf; static int opterror(const struct option *opt, const char *reason, int flags) { if (flags & OPT_SHORT) - return error("switch `%c' %s", opt->short_name, reason); - if (flags & OPT_UNSET) - return error("option `no-%s' %s", opt->long_name, reason); - return error("option `%s' %s", opt->long_name, reason); + fprintf(stderr, " Error: switch `%c' %s", opt->short_name, reason); + else if (flags & OPT_UNSET) + fprintf(stderr, " Error: option `no-%s' %s", opt->long_name, reason); + else + fprintf(stderr, " Error: option `%s' %s", opt->long_name, reason); + + return -1; +} + +static const char *skip_prefix(const char *str, const char *prefix) +{ + size_t len = strlen(prefix); + return strncmp(str, prefix, len) ? NULL : str + len; +} + +static void optwarning(const struct option *opt, const char *reason, int flags) +{ + if (flags & OPT_SHORT) + fprintf(stderr, " Warning: switch `%c' %s", opt->short_name, reason); + else if (flags & OPT_UNSET) + fprintf(stderr, " Warning: option `no-%s' %s", opt->long_name, reason); + else + fprintf(stderr, " Warning: option `%s' %s", opt->long_name, reason); } static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt, int flags, const char **arg) { + const char *res; + if (p->opt) { - *arg = p->opt; + res = p->opt; p->opt = NULL; } else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 || **(p->argv + 1) == '-')) { - *arg = (const char *)opt->defval; + res = (const char *)opt->defval; } else if (p->argc > 1) { p->argc--; - *arg = *++p->argv; + res = *++p->argv; } else return opterror(opt, "requires a value", flags); + if (arg) + *arg = res; return 0; } @@ -55,11 +84,11 @@ static int get_value(struct parse_opt_ctx_t *p, if (((flags & OPT_SHORT) && p->excl_opt->short_name) || p->excl_opt->long_name == NULL) { - scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'", - p->excl_opt->short_name); + snprintf(msg, sizeof(msg), "cannot be used with switch `%c'", + p->excl_opt->short_name); } else { - scnprintf(msg, sizeof(msg), "cannot be used with %s", - p->excl_opt->long_name); + snprintf(msg, sizeof(msg), "cannot be used with %s", + p->excl_opt->long_name); } opterror(opt, msg, flags); return -3; @@ -91,6 +120,64 @@ static int get_value(struct parse_opt_ctx_t *p, } } + if (opt->flags & PARSE_OPT_NOBUILD) { + char reason[128]; + bool noarg = false; + + err = snprintf(reason, sizeof(reason), + opt->flags & PARSE_OPT_CANSKIP ? + "is being ignored because %s " : + "is not available because %s", + opt->build_opt); + reason[sizeof(reason) - 1] = '\0'; + + if (err < 0) + strncpy(reason, opt->flags & PARSE_OPT_CANSKIP ? + "is being ignored" : + "is not available", + sizeof(reason)); + + if (!(opt->flags & PARSE_OPT_CANSKIP)) + return opterror(opt, reason, flags); + + err = 0; + if (unset) + noarg = true; + if (opt->flags & PARSE_OPT_NOARG) + noarg = true; + if (opt->flags & PARSE_OPT_OPTARG && !p->opt) + noarg = true; + + switch (opt->type) { + case OPTION_BOOLEAN: + case OPTION_INCR: + case OPTION_BIT: + case OPTION_SET_UINT: + case OPTION_SET_PTR: + case OPTION_END: + case OPTION_ARGUMENT: + case OPTION_GROUP: + noarg = true; + break; + case OPTION_CALLBACK: + case OPTION_STRING: + case OPTION_INTEGER: + case OPTION_UINTEGER: + case OPTION_LONG: + case OPTION_U64: + default: + break; + } + + if (!noarg) + err = get_arg(p, opt, flags, NULL); + if (err) + return err; + + optwarning(opt, reason, flags); + return 0; + } + switch (opt->type) { case OPTION_BIT: if (unset) @@ -327,14 +414,16 @@ match: return get_value(p, options, flags); } - if (ambiguous_option) - return error("Ambiguous option: %s " - "(could be --%s%s or --%s%s)", - arg, - (ambiguous_flags & OPT_UNSET) ? "no-" : "", - ambiguous_option->long_name, - (abbrev_flags & OPT_UNSET) ? "no-" : "", - abbrev_option->long_name); + if (ambiguous_option) { + fprintf(stderr, + " Error: Ambiguous option: %s (could be --%s%s or --%s%s)", + arg, + (ambiguous_flags & OPT_UNSET) ? "no-" : "", + ambiguous_option->long_name, + (abbrev_flags & OPT_UNSET) ? "no-" : "", + abbrev_option->long_name); + return -1; + } if (abbrev_option) return get_value(p, abbrev_option, abbrev_flags); return -2; @@ -346,7 +435,7 @@ static void check_typos(const char *arg, const struct option *options) return; if (!prefixcmp(arg, "no-")) { - error ("did you mean `--%s` (with two dashes ?)", arg); + fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg); exit(129); } @@ -354,14 +443,14 @@ static void check_typos(const char *arg, const struct option *options) if (!options->long_name) continue; if (!prefixcmp(options->long_name, arg)) { - error ("did you mean `--%s` (with two dashes ?)", arg); + fprintf(stderr, " Error: did you mean `--%s` (with two dashes ?)", arg); exit(129); } } } -void parse_options_start(struct parse_opt_ctx_t *ctx, - int argc, const char **argv, int flags) +static void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags) { memset(ctx, 0, sizeof(*ctx)); ctx->argc = argc - 1; @@ -378,9 +467,9 @@ static int usage_with_options_internal(const char * const *, const struct option *, int, struct parse_opt_ctx_t *); -int parse_options_step(struct parse_opt_ctx_t *ctx, - const struct option *options, - const char * const usagestr[]) +static int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]) { int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP); int excl_short_opt = 1; @@ -489,7 +578,7 @@ exclusive: return PARSE_OPT_HELP; } -int parse_options_end(struct parse_opt_ctx_t *ctx) +static int parse_options_end(struct parse_opt_ctx_t *ctx) { memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out)); ctx->out[ctx->cpidx + ctx->argc] = NULL; @@ -501,22 +590,20 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o { struct parse_opt_ctx_t ctx; - perf_env__set_cmdline(&perf_env, argc, argv); - /* build usage string if it's not provided */ if (subcommands && !usagestr[0]) { - struct strbuf buf = STRBUF_INIT; + char *buf = NULL; + + astrcatf(&buf, "%s %s [<options>] {", subcmd_config.exec_name, argv[0]); - strbuf_addf(&buf, "perf %s [<options>] {", argv[0]); for (int i = 0; subcommands[i]; i++) { if (i) - strbuf_addstr(&buf, "|"); - strbuf_addstr(&buf, subcommands[i]); + astrcat(&buf, "|"); + astrcat(&buf, subcommands[i]); } - strbuf_addstr(&buf, "}"); + astrcat(&buf, "}"); - usagestr[0] = strdup(buf.buf); - strbuf_release(&buf); + usagestr[0] = buf; } parse_options_start(&ctx, argc, argv, flags); @@ -541,13 +628,11 @@ int parse_options_subcommand(int argc, const char **argv, const struct option *o putchar('\n'); exit(130); default: /* PARSE_OPT_UNKNOWN */ - if (ctx.argv[0][1] == '-') { - strbuf_addf(&error_buf, "unknown option `%s'", - ctx.argv[0] + 2); - } else { - strbuf_addf(&error_buf, "unknown switch `%c'", - *ctx.opt); - } + if (ctx.argv[0][1] == '-') + astrcatf(&error_buf, "unknown option `%s'", + ctx.argv[0] + 2); + else + astrcatf(&error_buf, "unknown switch `%c'", *ctx.opt); usage_with_options(usagestr, options); } @@ -647,6 +732,10 @@ static void print_option_help(const struct option *opts, int full) pad = USAGE_OPTS_WIDTH; } fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help); + if (opts->flags & PARSE_OPT_NOBUILD) + fprintf(stderr, "%*s(not built-in because %s)\n", + USAGE_OPTS_WIDTH + USAGE_GAP, "", + opts->build_opt); } static int option__cmp(const void *va, const void *vb) @@ -672,16 +761,18 @@ static int option__cmp(const void *va, const void *vb) static struct option *options__order(const struct option *opts) { - int nr_opts = 0; + int nr_opts = 0, len; const struct option *o = opts; struct option *ordered; for (o = opts; o->type != OPTION_END; o++) ++nr_opts; - ordered = memdup(opts, sizeof(*o) * (nr_opts + 1)); - if (ordered == NULL) + len = sizeof(*o) * (nr_opts + 1); + ordered = malloc(len); + if (!ordered) goto out; + memcpy(ordered, opts, len); qsort(ordered, nr_opts, sizeof(*o), option__cmp); out: @@ -719,9 +810,9 @@ static bool option__in_argv(const struct option *opt, const struct parse_opt_ctx return false; } -int usage_with_options_internal(const char * const *usagestr, - const struct option *opts, int full, - struct parse_opt_ctx_t *ctx) +static int usage_with_options_internal(const char * const *usagestr, + const struct option *opts, int full, + struct parse_opt_ctx_t *ctx) { struct option *ordered; @@ -730,9 +821,9 @@ int usage_with_options_internal(const char * const *usagestr, setup_pager(); - if (strbuf_avail(&error_buf)) { - fprintf(stderr, " Error: %s\n", error_buf.buf); - strbuf_release(&error_buf); + if (error_buf) { + fprintf(stderr, " Error: %s\n", error_buf); + zfree(&error_buf); } fprintf(stderr, "\n Usage: %s\n", *usagestr++); @@ -768,7 +859,6 @@ int usage_with_options_internal(const char * const *usagestr, void usage_with_options(const char * const *usagestr, const struct option *opts) { - exit_browser(false); usage_with_options_internal(usagestr, opts, 0, NULL); exit(129); } @@ -777,13 +867,15 @@ void usage_with_options_msg(const char * const *usagestr, const struct option *opts, const char *fmt, ...) { va_list ap; - - exit_browser(false); + char *tmp = error_buf; va_start(ap, fmt); - strbuf_addv(&error_buf, fmt, ap); + if (vasprintf(&error_buf, fmt, ap) == -1) + die("vasprintf failed"); va_end(ap); + free(tmp); + usage_with_options_internal(usagestr, opts, 0, NULL); exit(129); } @@ -853,15 +945,39 @@ int parse_opt_verbosity_cb(const struct option *opt, return 0; } -void set_option_flag(struct option *opts, int shortopt, const char *longopt, - int flag) +static struct option * +find_option(struct option *opts, int shortopt, const char *longopt) { for (; opts->type != OPTION_END; opts++) { if ((shortopt && opts->short_name == shortopt) || (opts->long_name && longopt && - !strcmp(opts->long_name, longopt))) { - opts->flags |= flag; - break; - } + !strcmp(opts->long_name, longopt))) + return opts; } + return NULL; +} + +void set_option_flag(struct option *opts, int shortopt, const char *longopt, + int flag) +{ + struct option *opt = find_option(opts, shortopt, longopt); + + if (opt) + opt->flags |= flag; + return; +} + +void set_option_nobuild(struct option *opts, int shortopt, + const char *longopt, + const char *build_opt, + bool can_skip) +{ + struct option *opt = find_option(opts, shortopt, longopt); + + if (!opt) + return; + + opt->flags |= PARSE_OPT_NOBUILD; + opt->flags |= can_skip ? PARSE_OPT_CANSKIP : 0; + opt->build_opt = build_opt; } diff --git a/tools/perf/util/parse-options.h b/tools/lib/subcmd/parse-options.h index a8e407bc251e..13a2cc1d6140 100644 --- a/tools/perf/util/parse-options.h +++ b/tools/lib/subcmd/parse-options.h @@ -1,8 +1,8 @@ -#ifndef __PERF_PARSE_OPTIONS_H -#define __PERF_PARSE_OPTIONS_H +#ifndef __SUBCMD_PARSE_OPTIONS_H +#define __SUBCMD_PARSE_OPTIONS_H -#include <linux/kernel.h> #include <stdbool.h> +#include <stdint.h> enum parse_opt_type { /* special types */ @@ -41,6 +41,8 @@ enum parse_opt_option_flags { PARSE_OPT_DISABLED = 32, PARSE_OPT_EXCLUSIVE = 64, PARSE_OPT_NOEMPTY = 128, + PARSE_OPT_NOBUILD = 256, + PARSE_OPT_CANSKIP = 512, }; struct option; @@ -96,6 +98,7 @@ struct option { void *value; const char *argh; const char *help; + const char *build_opt; int flags; parse_opt_cb *callback; @@ -149,6 +152,9 @@ struct option { /* parse_options() will filter out the processed options and leave the * non-option argments in argv[]. * Returns the number of arguments left in argv[]. + * + * NOTE: parse_options() and parse_options_subcommand() may call exit() in the + * case of an error (or for 'special' options like --list-cmds or --list-opts). */ extern int parse_options(int argc, const char **argv, const struct option *options, @@ -195,15 +201,6 @@ extern int parse_options_usage(const char * const *usagestr, const char *optstr, bool short_opt); -extern void parse_options_start(struct parse_opt_ctx_t *ctx, - int argc, const char **argv, int flags); - -extern int parse_options_step(struct parse_opt_ctx_t *ctx, - const struct option *options, - const char * const usagestr[]); - -extern int parse_options_end(struct parse_opt_ctx_t *ctx); - /*----- some often used options -----*/ extern int parse_opt_abbrev_cb(const struct option *, const char *, int); @@ -226,4 +223,7 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int); extern const char *parse_options_fix_filename(const char *prefix, const char *file); void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag); -#endif /* __PERF_PARSE_OPTIONS_H */ +void set_option_nobuild(struct option *opts, int shortopt, const char *longopt, + const char *build_opt, bool can_skip); + +#endif /* __SUBCMD_PARSE_OPTIONS_H */ diff --git a/tools/perf/util/run-command.c b/tools/lib/subcmd/run-command.c index 34622b53e733..f4f6c9eb8e59 100644 --- a/tools/perf/util/run-command.c +++ b/tools/lib/subcmd/run-command.c @@ -1,7 +1,15 @@ -#include "cache.h" +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <string.h> +#include <errno.h> +#include <sys/wait.h> +#include "subcmd-util.h" #include "run-command.h" -#include "exec_cmd.h" -#include "debug.h" +#include "exec-cmd.h" + +#define STRERR_BUFSIZE 128 static inline void close_pair(int fd[2]) { @@ -112,8 +120,8 @@ int start_command(struct child_process *cmd) } if (cmd->preexec_cb) cmd->preexec_cb(); - if (cmd->perf_cmd) { - execv_perf_cmd(cmd->argv); + if (cmd->exec_cmd) { + execv_cmd(cmd->argv); } else { execvp(cmd->argv[0], (char *const*) cmd->argv); } @@ -164,8 +172,8 @@ static int wait_or_whine(pid_t pid) if (waiting < 0) { if (errno == EINTR) continue; - error("waitpid failed (%s)", - strerror_r(errno, sbuf, sizeof(sbuf))); + fprintf(stderr, " Error: waitpid failed (%s)", + strerror_r(errno, sbuf, sizeof(sbuf))); return -ERR_RUN_COMMAND_WAITPID; } if (waiting != pid) @@ -207,7 +215,7 @@ static void prepare_run_command_v_opt(struct child_process *cmd, memset(cmd, 0, sizeof(*cmd)); cmd->argv = argv; cmd->no_stdin = opt & RUN_COMMAND_NO_STDIN ? 1 : 0; - cmd->perf_cmd = opt & RUN_PERF_CMD ? 1 : 0; + cmd->exec_cmd = opt & RUN_EXEC_CMD ? 1 : 0; cmd->stdout_to_stderr = opt & RUN_COMMAND_STDOUT_TO_STDERR ? 1 : 0; } diff --git a/tools/perf/util/run-command.h b/tools/lib/subcmd/run-command.h index 1ef264d5069c..fe2befea1e73 100644 --- a/tools/perf/util/run-command.h +++ b/tools/lib/subcmd/run-command.h @@ -1,5 +1,7 @@ -#ifndef __PERF_RUN_COMMAND_H -#define __PERF_RUN_COMMAND_H +#ifndef __SUBCMD_RUN_COMMAND_H +#define __SUBCMD_RUN_COMMAND_H + +#include <unistd.h> enum { ERR_RUN_COMMAND_FORK = 10000, @@ -41,7 +43,7 @@ struct child_process { unsigned no_stdin:1; unsigned no_stdout:1; unsigned no_stderr:1; - unsigned perf_cmd:1; /* if this is to be perf sub-command */ + unsigned exec_cmd:1; /* if this is to be external sub-command */ unsigned stdout_to_stderr:1; void (*preexec_cb)(void); }; @@ -51,8 +53,8 @@ int finish_command(struct child_process *); int run_command(struct child_process *); #define RUN_COMMAND_NO_STDIN 1 -#define RUN_PERF_CMD 2 /*If this is to be perf sub-command */ +#define RUN_EXEC_CMD 2 /*If this is to be external sub-command */ #define RUN_COMMAND_STDOUT_TO_STDERR 4 int run_command_v_opt(const char **argv, int opt); -#endif /* __PERF_RUN_COMMAND_H */ +#endif /* __SUBCMD_RUN_COMMAND_H */ diff --git a/tools/perf/util/sigchain.c b/tools/lib/subcmd/sigchain.c index ba785e9b1841..3537c348a18e 100644 --- a/tools/perf/util/sigchain.c +++ b/tools/lib/subcmd/sigchain.c @@ -1,5 +1,6 @@ +#include <signal.h> +#include "subcmd-util.h" #include "sigchain.h" -#include "cache.h" #define SIGCHAIN_MAX_SIGNALS 32 diff --git a/tools/perf/util/sigchain.h b/tools/lib/subcmd/sigchain.h index 959d64eb5557..0c919f2874ca 100644 --- a/tools/perf/util/sigchain.h +++ b/tools/lib/subcmd/sigchain.h @@ -1,5 +1,5 @@ -#ifndef __PERF_SIGCHAIN_H -#define __PERF_SIGCHAIN_H +#ifndef __SUBCMD_SIGCHAIN_H +#define __SUBCMD_SIGCHAIN_H typedef void (*sigchain_fun)(int); @@ -7,4 +7,4 @@ int sigchain_pop(int sig); void sigchain_push_common(sigchain_fun f); -#endif /* __PERF_SIGCHAIN_H */ +#endif /* __SUBCMD_SIGCHAIN_H */ diff --git a/tools/lib/subcmd/subcmd-config.c b/tools/lib/subcmd/subcmd-config.c new file mode 100644 index 000000000000..d017c728bd1b --- /dev/null +++ b/tools/lib/subcmd/subcmd-config.c @@ -0,0 +1,11 @@ +#include "subcmd-config.h" + +#define UNDEFINED "SUBCMD_HAS_NOT_BEEN_INITIALIZED" + +struct subcmd_config subcmd_config = { + .exec_name = UNDEFINED, + .prefix = UNDEFINED, + .exec_path = UNDEFINED, + .exec_path_env = UNDEFINED, + .pager_env = UNDEFINED, +}; diff --git a/tools/lib/subcmd/subcmd-config.h b/tools/lib/subcmd/subcmd-config.h new file mode 100644 index 000000000000..cc8514030b5c --- /dev/null +++ b/tools/lib/subcmd/subcmd-config.h @@ -0,0 +1,14 @@ +#ifndef __PERF_SUBCMD_CONFIG_H +#define __PERF_SUBCMD_CONFIG_H + +struct subcmd_config { + const char *exec_name; + const char *prefix; + const char *exec_path; + const char *exec_path_env; + const char *pager_env; +}; + +extern struct subcmd_config subcmd_config; + +#endif /* __PERF_SUBCMD_CONFIG_H */ diff --git a/tools/lib/subcmd/subcmd-util.h b/tools/lib/subcmd/subcmd-util.h new file mode 100644 index 000000000000..fc2e45d8aaf1 --- /dev/null +++ b/tools/lib/subcmd/subcmd-util.h @@ -0,0 +1,91 @@ +#ifndef __SUBCMD_UTIL_H +#define __SUBCMD_UTIL_H + +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> + +#define NORETURN __attribute__((__noreturn__)) + +static inline void report(const char *prefix, const char *err, va_list params) +{ + char msg[1024]; + vsnprintf(msg, sizeof(msg), err, params); + fprintf(stderr, " %s%s\n", prefix, msg); +} + +static NORETURN inline void die(const char *err, ...) +{ + va_list params; + + va_start(params, err); + report(" Fatal: ", err, params); + exit(128); + va_end(params); +} + +#define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) + +#define alloc_nr(x) (((x)+16)*3/2) + +/* + * Realloc the buffer pointed at by variable 'x' so that it can hold + * at least 'nr' entries; the number of entries currently allocated + * is 'alloc', using the standard growing factor alloc_nr() macro. + * + * DO NOT USE any expression with side-effect for 'x' or 'alloc'. + */ +#define ALLOC_GROW(x, nr, alloc) \ + do { \ + if ((nr) > alloc) { \ + if (alloc_nr(alloc) < (nr)) \ + alloc = (nr); \ + else \ + alloc = alloc_nr(alloc); \ + x = xrealloc((x), alloc * sizeof(*(x))); \ + } \ + } while(0) + +static inline void *xrealloc(void *ptr, size_t size) +{ + void *ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) { + ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) + die("Out of memory, realloc failed"); + } + return ret; +} + +#define astrcatf(out, fmt, ...) \ +({ \ + char *tmp = *(out); \ + if (asprintf((out), "%s" fmt, tmp ?: "", ## __VA_ARGS__) == -1) \ + die("asprintf failed"); \ + free(tmp); \ +}) + +static inline void astrcat(char **out, const char *add) +{ + char *tmp = *out; + + if (asprintf(out, "%s%s", tmp ?: "", add) == -1) + die("asprintf failed"); + + free(tmp); +} + +static inline int prefixcmp(const char *str, const char *prefix) +{ + for (; ; str++, prefix++) + if (!*prefix) + return 0; + else if (*str != *prefix) + return (unsigned char)*prefix - (unsigned char)*str; +} + +#endif /* __SUBCMD_UTIL_H */ diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 2a912df6771b..ea69ce35e902 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4735,73 +4735,80 @@ static int is_printable_array(char *p, unsigned int len) return 1; } -static void print_event_fields(struct trace_seq *s, void *data, - int size __maybe_unused, - struct event_format *event) +void pevent_print_field(struct trace_seq *s, void *data, + struct format_field *field) { - struct format_field *field; unsigned long long val; unsigned int offset, len, i; - - field = event->format.fields; - while (field) { - trace_seq_printf(s, " %s=", field->name); - if (field->flags & FIELD_IS_ARRAY) { - offset = field->offset; - len = field->size; - if (field->flags & FIELD_IS_DYNAMIC) { - val = pevent_read_number(event->pevent, data + offset, len); - offset = val; - len = offset >> 16; - offset &= 0xffff; - } - if (field->flags & FIELD_IS_STRING && - is_printable_array(data + offset, len)) { - trace_seq_printf(s, "%s", (char *)data + offset); - } else { - trace_seq_puts(s, "ARRAY["); - for (i = 0; i < len; i++) { - if (i) - trace_seq_puts(s, ", "); - trace_seq_printf(s, "%02x", - *((unsigned char *)data + offset + i)); - } - trace_seq_putc(s, ']'); - field->flags &= ~FIELD_IS_STRING; - } + struct pevent *pevent = field->event->pevent; + + if (field->flags & FIELD_IS_ARRAY) { + offset = field->offset; + len = field->size; + if (field->flags & FIELD_IS_DYNAMIC) { + val = pevent_read_number(pevent, data + offset, len); + offset = val; + len = offset >> 16; + offset &= 0xffff; + } + if (field->flags & FIELD_IS_STRING && + is_printable_array(data + offset, len)) { + trace_seq_printf(s, "%s", (char *)data + offset); } else { - val = pevent_read_number(event->pevent, data + field->offset, - field->size); - if (field->flags & FIELD_IS_POINTER) { - trace_seq_printf(s, "0x%llx", val); - } else if (field->flags & FIELD_IS_SIGNED) { - switch (field->size) { - case 4: - /* - * If field is long then print it in hex. - * A long usually stores pointers. - */ - if (field->flags & FIELD_IS_LONG) - trace_seq_printf(s, "0x%x", (int)val); - else - trace_seq_printf(s, "%d", (int)val); - break; - case 2: - trace_seq_printf(s, "%2d", (short)val); - break; - case 1: - trace_seq_printf(s, "%1d", (char)val); - break; - default: - trace_seq_printf(s, "%lld", val); - } - } else { + trace_seq_puts(s, "ARRAY["); + for (i = 0; i < len; i++) { + if (i) + trace_seq_puts(s, ", "); + trace_seq_printf(s, "%02x", + *((unsigned char *)data + offset + i)); + } + trace_seq_putc(s, ']'); + field->flags &= ~FIELD_IS_STRING; + } + } else { + val = pevent_read_number(pevent, data + field->offset, + field->size); + if (field->flags & FIELD_IS_POINTER) { + trace_seq_printf(s, "0x%llx", val); + } else if (field->flags & FIELD_IS_SIGNED) { + switch (field->size) { + case 4: + /* + * If field is long then print it in hex. + * A long usually stores pointers. + */ if (field->flags & FIELD_IS_LONG) - trace_seq_printf(s, "0x%llx", val); + trace_seq_printf(s, "0x%x", (int)val); else - trace_seq_printf(s, "%llu", val); + trace_seq_printf(s, "%d", (int)val); + break; + case 2: + trace_seq_printf(s, "%2d", (short)val); + break; + case 1: + trace_seq_printf(s, "%1d", (char)val); + break; + default: + trace_seq_printf(s, "%lld", val); } + } else { + if (field->flags & FIELD_IS_LONG) + trace_seq_printf(s, "0x%llx", val); + else + trace_seq_printf(s, "%llu", val); } + } +} + +void pevent_print_fields(struct trace_seq *s, void *data, + int size __maybe_unused, struct event_format *event) +{ + struct format_field *field; + + field = event->format.fields; + while (field) { + trace_seq_printf(s, " %s=", field->name); + pevent_print_field(s, data, field); field = field->next; } } @@ -4827,7 +4834,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event if (event->flags & EVENT_FL_FAILED) { trace_seq_printf(s, "[FAILED TO PARSE]"); - print_event_fields(s, data, size, event); + pevent_print_fields(s, data, size, event); return; } @@ -4968,13 +4975,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event sizeof(long) != 8) { char *p; - ls = 2; /* make %l into %ll */ - p = strchr(format, 'l'); - if (p) + if (ls == 1 && (p = strchr(format, 'l'))) memmove(p+1, p, strlen(p)+1); else if (strcmp(format, "%p") == 0) strcpy(format, "0x%llx"); + ls = 2; } switch (ls) { case -2: @@ -5302,7 +5308,7 @@ void pevent_event_info(struct trace_seq *s, struct event_format *event, int print_pretty = 1; if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW)) - print_event_fields(s, record->data, record->size, event); + pevent_print_fields(s, record->data, record->size, event); else { if (event->handler && !(event->flags & EVENT_FL_NOHANDLE)) diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 6fc83c7edbe9..706d9bc24066 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -705,6 +705,10 @@ struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *com struct cmdline *next); int pevent_cmdline_pid(struct pevent *pevent, struct cmdline *cmdline); +void pevent_print_field(struct trace_seq *s, void *data, + struct format_field *field); +void pevent_print_fields(struct trace_seq *s, void *data, + int size __maybe_unused, struct event_format *event); void pevent_event_info(struct trace_seq *s, struct event_format *event, struct pevent_record *record); int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum, diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/util/find_next_bit.c deleted file mode 100644 index 41b44f65a79e..000000000000 --- a/tools/lib/util/find_next_bit.c +++ /dev/null @@ -1,89 +0,0 @@ -/* find_next_bit.c: fallback find next bit implementation - * - * Copied from lib/find_next_bit.c to tools/lib/next_bit.c - * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/bitops.h> -#include <asm/types.h> -#include <asm/byteorder.h> - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) - -#ifndef find_next_bit -/* - * Find the next set bit in a memory region. - */ -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - const unsigned long *p = addr + BITOP_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG-1); - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset %= BITS_PER_LONG; - if (offset) { - tmp = *(p++); - tmp &= (~0UL << offset); - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - } - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found_middle; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __ffs(tmp); -} -#endif - -#ifndef find_first_bit -/* - * Find the first set bit in a memory region. - */ -unsigned long find_first_bit(const unsigned long *addr, unsigned long size) -{ - const unsigned long *p = addr; - unsigned long result = 0; - unsigned long tmp; - - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - - tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found: - return result + __ffs(tmp); -} -#endif diff --git a/tools/perf/Build b/tools/perf/Build index 72237455b400..6b67e6f4179f 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -1,5 +1,6 @@ perf-y += builtin-bench.o perf-y += builtin-annotate.o +perf-y += builtin-config.o perf-y += builtin-diff.o perf-y += builtin-evlist.o perf-y += builtin-help.o @@ -19,6 +20,7 @@ perf-y += builtin-kvm.o perf-y += builtin-inject.o perf-y += builtin-mem.o perf-y += builtin-data.o +perf-y += builtin-version.o perf-$(CONFIG_AUDIT) += builtin-trace.o perf-$(CONFIG_LIBELF) += builtin-probe.o @@ -34,8 +36,12 @@ paths += -DPERF_MAN_PATH="BUILD_STR($(mandir_SQ))" CFLAGS_builtin-help.o += $(paths) CFLAGS_builtin-timechart.o += $(paths) -CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" -include $(OUTPUT)PERF-VERSION-FILE +CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \ + -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" \ + -DPREFIX="BUILD_STR($(prefix_SQ))" \ + -include $(OUTPUT)PERF-VERSION-FILE CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))" +CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))" libperf-y += util/ libperf-y += arch/ diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt new file mode 100644 index 000000000000..b9ca1e304158 --- /dev/null +++ b/tools/perf/Documentation/perf-config.txt @@ -0,0 +1,103 @@ +perf-config(1) +============== + +NAME +---- +perf-config - Get and set variables in a configuration file. + +SYNOPSIS +-------- +[verse] +'perf config' -l | --list + +DESCRIPTION +----------- +You can manage variables in a configuration file with this command. + +OPTIONS +------- + +-l:: +--list:: + Show current config variables, name and value, for all sections. + +CONFIGURATION FILE +------------------ + +The perf configuration file contains many variables to change various +aspects of each of its tools, including output, disk usage, etc. +The '$HOME/.perfconfig' file is used to store a per-user configuration. +The file '$(sysconfdir)/perfconfig' can be used to +store a system-wide default configuration. + +Syntax +~~~~~~ + +The file consist of sections. A section starts with its name +surrounded by square brackets and continues till the next section +begins. Each variable must be in a section, and have the form +'name = value', for example: + + [section] + name1 = value1 + name2 = value2 + +Section names are case sensitive and can contain any characters except +newline (double quote `"` and backslash have to be escaped as `\"` and `\\`, +respectively). Section headers can't span multiple lines. + +Example +~~~~~~~ + +Given a $HOME/.perfconfig like this: + +# +# This is the config file, and +# a '#' and ';' character indicates a comment +# + + [colors] + # Color variables + top = red, default + medium = green, default + normal = lightgray, default + selected = white, lightgray + code = blue, default + addr = magenta, default + root = white, blue + + [tui] + # Defaults if linked with libslang + report = on + annotate = on + top = on + + [buildid] + # Default, disable using /dev/null + dir = ~/.debug + + [annotate] + # Defaults + hide_src_code = false + use_offset = true + jump_arrows = true + show_nr_jumps = false + + [help] + # Format can be man, info, web or html + format = man + autocorrect = 0 + + [ui] + show-headers = true + + [call-graph] + # fp (framepointer), dwarf + record-mode = fp + print-type = graph + order = caller + sort-key = function + +SEE ALSO +-------- +linkperf:perf[1] diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt index 1ceb3700ffbb..6f7200fb85cf 100644 --- a/tools/perf/Documentation/perf-evlist.txt +++ b/tools/perf/Documentation/perf-evlist.txt @@ -32,6 +32,9 @@ OPTIONS --group:: Show event group information. +--trace-fields:: + Show tracepoint field names. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-list[1], diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index e630a7d2c348..3a1a32f5479f 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -207,11 +207,23 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0- In per-thread mode with inheritance mode on (default), samples are captured only when the thread executes on the designated CPUs. Default is to monitor all CPUs. +-B:: +--no-buildid:: +Do not save the build ids of binaries in the perf.data files. This skips +post processing after recording, which sometimes makes the final step in +the recording process to take a long time, as it needs to process all +events looking for mmap records. The downside is that it can misresolve +symbols if the workload binaries used when recording get locally rebuilt +or upgraded, because the only key available in this case is the +pathname. You can also set the "record.build-id" config variable to +'skip to have this behaviour permanently. + -N:: --no-buildid-cache:: Do not update the buildid cache. This saves some overhead in situations where the information in the perf.data file (which includes buildids) -is sufficient. +is sufficient. You can also set the "record.build-id" config variable to +'no-cache' to have the same effect. -G name,...:: --cgroup name,...:: @@ -314,11 +326,17 @@ This option sets the time out limit. The default value is 500 ms. Record context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. ---clang-path:: +--clang-path=PATH:: Path to clang binary to use for compiling BPF scriptlets. +(enabled when BPF support is on) ---clang-opt:: +--clang-opt=OPTIONS:: Options passed to clang when compiling BPF scriptlets. +(enabled when BPF support is on) + +--vmlinux=PATH:: +Specify vmlinux path which has debuginfo. +(enabled when BPF prologue is on) SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 5ce8da1e1256..8a301f6afb37 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,30 @@ OPTIONS And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'. + If the data file has tracepoint event(s), following (dynamic) sort keys + are also available: + trace, trace_fields, [<event>.]<field>[/raw] + + - trace: pretty printed trace output in a single column + - trace_fields: fields in tracepoints in separate columns + - <field name>: optional event and field name for a specific field + + The last form consists of event and field names. If event name is + omitted, it searches all events for matching field name. The matched + field will be shown only for the event has the field. The event name + supports substring match so user doesn't need to specify full subsystem + and event name everytime. For example, 'sched:sched_switch' event can + be shortened to 'switch' as long as it's not ambiguous. Also event can + be specified by its index (starting from 1) preceded by the '%'. + So '%1' is the first event, '%2' is the second, and so on. + + The field name can have '/raw' suffix which disables pretty printing + and shows raw field value like hex numbers. The --raw-trace option + has the same effect for all dynamic sort keys. + + The default sort keys are changed to 'trace' if all events in the data + file are tracepoint. + -F:: --fields=:: Specify output field - multiple keys can be specified in CSV format. @@ -170,17 +194,18 @@ OPTIONS Dump raw trace in ASCII. -g:: ---call-graph=<print_type,threshold[,print_limit],order,sort_key,branch>:: +--call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>:: Display call chains using type, min percent threshold, print limit, - call order, sort key and branch. Note that ordering of parameters is not - fixed so any parement can be given in an arbitraty order. One exception - is the print_limit which should be preceded by threshold. + call order, sort key, optional branch and value. Note that ordering of + parameters is not fixed so any parement can be given in an arbitraty order. + One exception is the print_limit which should be preceded by threshold. print_type can be either: - flat: single column, linear exposure of call chains. - graph: use a graph tree, displaying absolute overhead rates. (default) - fractal: like graph, but displays relative rates. Each branch of the tree is considered as a new profiled object. + - folded: call chains are displayed in a line, separated by semicolons - none: disable call chain display. threshold is a percentage value which specifies a minimum percent to be @@ -204,6 +229,11 @@ OPTIONS - branch: include last branch information in callgraph when available. Usually more convenient to use --branch-history for this. + value can be: + - percent: diplay overhead percent (default) + - period: display event period + - count: display event count + --children:: Accumulate callchain of children to parent entry so that then can show up in the output. The output will have a new "Children" column @@ -365,6 +395,9 @@ include::itrace.txt[] --socket-filter:: Only report the samples on the processor socket that match with this filter +--raw-trace:: + When displaying traceevent output, do not use print fmt or plugins. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 4e074a660826..52ef7a9d50aa 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -10,6 +10,8 @@ SYNOPSIS [verse] 'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command> 'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>] +'perf stat' [-e <EVENT> | --event=EVENT] [-a] record [-o file] -- <command> [<options>] +'perf stat' report [-i file] DESCRIPTION ----------- @@ -22,6 +24,11 @@ OPTIONS <command>...:: Any command you can specify in a shell. +record:: + See STAT RECORD. + +report:: + See STAT REPORT. -e:: --event=:: @@ -159,6 +166,33 @@ filter out the startup phase of the program, which is often very different. Print statistics of transactional execution if supported. +STAT RECORD +----------- +Stores stat data into perf data file. + +-o file:: +--output file:: +Output file name. + +STAT REPORT +----------- +Reads and reports stat data from perf data file. + +-i file:: +--input file:: +Input file name. + +--per-socket:: +Aggregate counts per processor socket for system-wide mode measurements. + +--per-core:: +Aggregate counts per physical processor for system-wide mode measurements. + +-A:: +--no-aggr:: +Do not aggregate counts across all monitored CPUs. + + EXAMPLES -------- diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 556cec09bf50..b0e60e17db38 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -230,6 +230,9 @@ Default is to monitor all CPUS. The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k Note that this feature may not be available on all processors. +--raw-trace:: + When displaying traceevent output, do not use print fmt or plugins. + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt new file mode 100644 index 000000000000..a1c10e360db5 --- /dev/null +++ b/tools/perf/Documentation/tips.txt @@ -0,0 +1,14 @@ +For a higher level overview, try: perf report --sort comm,dso +Sample related events with: perf record -e '{cycles,instructions}:S' +Compare performance results with: perf diff [<old file> <new file>] +Boolean options have negative forms, e.g.: perf report --no-children +Customize output of perf script with: perf script -F event,ip,sym +Generate a script for your data: perf script -g <lang> +Save output of perf stat using: perf stat record <target workload> +Create an archive with symtabs to analyse on other machine: perf archive +Search options using a keyword: perf report -h <keyword> +Use parent filter to see specific call path: perf report -p <regex> +List events using substring match: perf list <keyword> +To see list of saved events and attributes: perf evlist -v +Use --symfs <dir> if your symbol files are in non-standard locations +To see callchains in a more compact form: perf report -g folded diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 39c38cb45b00..ddf922f93aa1 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,6 +1,7 @@ tools/perf tools/arch/alpha/include/asm/barrier.h tools/arch/arm/include/asm/barrier.h +tools/arch/arm64/include/asm/barrier.h tools/arch/ia64/include/asm/barrier.h tools/arch/mips/include/asm/barrier.h tools/arch/powerpc/include/asm/barrier.h @@ -20,14 +21,17 @@ tools/lib/traceevent tools/lib/bpf tools/lib/api tools/lib/bpf +tools/lib/subcmd tools/lib/hweight.c tools/lib/rbtree.c +tools/lib/string.c tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h -tools/lib/util/find_next_bit.c +tools/lib/find_bit.c tools/include/asm/atomic.h tools/include/asm/barrier.h tools/include/asm/bug.h +tools/include/asm-generic/atomic-gcc.h tools/include/asm-generic/barrier.h tools/include/asm-generic/bitops/arch_hweight.h tools/include/asm-generic/bitops/atomic.h @@ -50,6 +54,7 @@ tools/include/linux/log2.h tools/include/linux/poison.h tools/include/linux/rbtree.h tools/include/linux/rbtree_augmented.h +tools/include/linux/string.h tools/include/linux/types.h tools/include/linux/err.h include/asm-generic/bitops/arch_hweight.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 0d19d5447d6c..0a22407e1d7d 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -145,9 +145,10 @@ BISON = bison STRIP = strip AWK = awk -LIB_DIR = $(srctree)/tools/lib/api/ +LIB_DIR = $(srctree)/tools/lib/api/ TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/ -BPF_DIR = $(srctree)/tools/lib/bpf/ +BPF_DIR = $(srctree)/tools/lib/bpf/ +SUBCMD_DIR = $(srctree)/tools/lib/subcmd/ # include config/Makefile by default and rule out # non-config cases @@ -184,15 +185,17 @@ strip-libs = $(filter-out -l%,$(1)) ifneq ($(OUTPUT),) TE_PATH=$(OUTPUT) BPF_PATH=$(OUTPUT) + SUBCMD_PATH=$(OUTPUT) ifneq ($(subdir),) - LIB_PATH=$(OUTPUT)/../lib/api/ + API_PATH=$(OUTPUT)/../lib/api/ else - LIB_PATH=$(OUTPUT) + API_PATH=$(OUTPUT) endif else TE_PATH=$(TRACE_EVENT_DIR) - LIB_PATH=$(LIB_DIR) + API_PATH=$(LIB_DIR) BPF_PATH=$(BPF_DIR) + SUBCMD_PATH=$(SUBCMD_DIR) endif LIBTRACEEVENT = $(TE_PATH)libtraceevent.a @@ -201,11 +204,13 @@ export LIBTRACEEVENT LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST) -LIBAPI = $(LIB_PATH)libapi.a +LIBAPI = $(API_PATH)libapi.a export LIBAPI LIBBPF = $(BPF_PATH)libbpf.a +LIBSUBCMD = $(SUBCMD_PATH)libsubcmd.a + # python extension build directories PYTHON_EXTBUILD := $(OUTPUT)python_ext_build/ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/ @@ -257,7 +262,7 @@ export PERL_PATH LIB_FILE=$(OUTPUT)libperf.a -PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) +PERFLIBS = $(LIB_FILE) $(LIBAPI) $(LIBTRACEEVENT) $(LIBSUBCMD) ifndef NO_LIBBPF PERFLIBS += $(LIBBPF) endif @@ -420,7 +425,7 @@ $(LIBTRACEEVENT)-clean: $(call QUIET_CLEAN, libtraceevent) $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null -install-traceevent-plugins: $(LIBTRACEEVENT) +install-traceevent-plugins: libtraceevent_plugins $(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) install_plugins $(LIBAPI): fixdep FORCE @@ -431,12 +436,19 @@ $(LIBAPI)-clean: $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null $(LIBBPF): fixdep FORCE - $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a + $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP) $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) clean >/dev/null +$(LIBSUBCMD): fixdep FORCE + $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) $(OUTPUT)libsubcmd.a + +$(LIBSUBCMD)-clean: + $(call QUIET_CLEAN, libsubcmd) + $(Q)$(MAKE) -C $(SUBCMD_DIR) O=$(OUTPUT) clean + help: @echo 'Perf make targets:' @echo ' doc - make *all* documentation (see below)' @@ -476,7 +488,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html $(DOC_TARGETS): $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) -TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol ../include ../lib/bpf +TAG_FOLDERS= . ../lib ../include TAG_FILES= ../../include/uapi/linux/perf_event.h TAGS: @@ -555,6 +567,9 @@ endif $(call QUIET_INSTALL, perf_completion-script) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \ $(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf' + $(call QUIET_INSTALL, perf-tip) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \ + $(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)' install-tests: all install-gtk $(call QUIET_INSTALL, tests) \ @@ -582,15 +597,16 @@ $(INSTALL_DOC_TARGETS): # config-clean: $(call QUIET_CLEAN, config) - $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null + $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null -clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean config-clean +clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) - $(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete + $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32 $(call QUIET_CLEAN, core-gen) $(RM) *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \ - $(OUTPUT)util/intel-pt-decoder/inat-tables.c + $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \ + $(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean $(python-clean) diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index 7ed00f4b0908..b48de2f5813c 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -2,10 +2,10 @@ #define ARCH_TESTS_H /* Tests */ -int test__rdpmc(void); -int test__perf_time_to_tsc(void); -int test__insn_x86(void); -int test__intel_cqm_count_nmi_context(void); +int test__rdpmc(int subtest); +int test__perf_time_to_tsc(int subtest); +int test__insn_x86(int subtest); +int test__intel_cqm_count_nmi_context(int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index b6115dfd28f0..08d9b2bc185c 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -171,7 +171,7 @@ static int test_data_set(struct test_data *dat_set, int x86_64) * verbose (-v) option to see all the instructions and whether or not they * decoded successfuly. */ -int test__insn_x86(void) +int test__insn_x86(int subtest __maybe_unused) { int ret = 0; diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index d28c1b6a3b54..3e89ba825f6b 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -33,7 +33,7 @@ static pid_t spawn(void) * the last read counter value to avoid triggering a WARN_ON_ONCE() in * smp_call_function_many() caused by sending IPIs from NMI context. */ -int test__intel_cqm_count_nmi_context(void) +int test__intel_cqm_count_nmi_context(int subtest __maybe_unused) { struct perf_evlist *evlist = NULL; struct perf_evsel *evsel = NULL; @@ -54,7 +54,7 @@ int test__intel_cqm_count_nmi_context(void) ret = parse_events(evlist, "intel_cqm/llc_occupancy/", NULL); if (ret) { - pr_debug("parse_events failed\n"); + pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n"); err = TEST_SKIP; goto out; } diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 658cd200af74..9d29ee283ac5 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -35,13 +35,12 @@ * %0 is returned, otherwise %-1 is returned. If TSC conversion is not * supported then then the test passes but " (not supported)" is printed. */ -int test__perf_time_to_tsc(void) +int test__perf_time_to_tsc(int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, - .freq = 4000, .target = { .uses_mmap = true, }, diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index e7688214c7cf..7bb0d13c235f 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -149,7 +149,7 @@ out_close: return 0; } -int test__rdpmc(void) +int test__rdpmc(int subtest __maybe_unused) { int status = 0; int wret = 0; diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build index ff63649fa9ac..465970370f3e 100644 --- a/tools/perf/arch/x86/util/Build +++ b/tools/perf/arch/x86/util/Build @@ -5,6 +5,7 @@ libperf-y += kvm-stat.o libperf-y += perf_regs.o libperf-$(CONFIG_DWARF) += dwarf-regs.o +libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o libperf-$(CONFIG_LIBUNWIND) += unwind-libunwind.o libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 9b94ce520917..8d8150f1cf9b 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -327,7 +327,7 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr) evlist__for_each(btsr->evlist, evsel) { if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evlist__disable_event(btsr->evlist, evsel); + return perf_evsel__disable(evsel); } return -EINVAL; } @@ -340,7 +340,7 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr) evlist__for_each(btsr->evlist, evsel) { if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evlist__enable_event(btsr->evlist, evsel); + return perf_evsel__enable(evsel); } return -EINVAL; } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index b02af064f0f9..f05daacc9e78 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -26,7 +26,7 @@ #include "../../util/evlist.h" #include "../../util/evsel.h" #include "../../util/cpumap.h" -#include "../../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../../util/parse-events.h" #include "../../util/pmu.h" #include "../../util/debug.h" @@ -725,7 +725,7 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr) evlist__for_each(ptr->evlist, evsel) { if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evlist__disable_event(ptr->evlist, evsel); + return perf_evsel__disable(evsel); } return -EINVAL; } @@ -738,7 +738,7 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr) evlist__for_each(ptr->evlist, evsel) { if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evlist__enable_event(ptr->evlist, evsel); + return perf_evsel__enable(evsel); } return -EINVAL; } diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index fc9bebd2cca0..0999ac536d86 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -11,7 +11,7 @@ #include "../perf.h" #include "../util/util.h" #include "../util/stat.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/header.h" #include "bench.h" #include "futex.h" diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index bc6a16adbca8..6a18ce21f865 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -5,7 +5,7 @@ #include "../perf.h" #include "../util/util.h" #include "../util/stat.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/header.h" #include "bench.h" #include "futex.h" diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index ad0d9b5342fb..718238683013 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -11,7 +11,7 @@ #include "../perf.h" #include "../util/util.h" #include "../util/stat.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/header.h" #include "bench.h" #include "futex.h" diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 6d8c9fa2a16c..91aaf2a1fa90 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -10,7 +10,7 @@ #include "../perf.h" #include "../util/util.h" #include "../util/stat.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/header.h" #include "bench.h" #include "futex.h" diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index e5e41d3bdce7..f416bd705f66 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -11,7 +11,7 @@ #include "../perf.h" #include "../util/util.h" #include "../util/stat.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/header.h" #include "bench.h" #include "futex.h" diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c index 9419b944220f..a91aa85d80ff 100644 --- a/tools/perf/bench/mem-functions.c +++ b/tools/perf/bench/mem-functions.c @@ -8,7 +8,7 @@ #include "../perf.h" #include "../util/util.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/header.h" #include "../util/cloexec.h" #include "bench.h" diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 492df2752a2d..5049d6357a46 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -7,7 +7,7 @@ #include "../perf.h" #include "../builtin.h" #include "../util/util.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../util/cloexec.h" #include "bench.h" diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index d4ff1b539cfd..bfaf9503de8e 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -11,7 +11,7 @@ #include "../perf.h" #include "../util/util.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../builtin.h" #include "bench.h" diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index 005cc283790c..1dc2d13cc272 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -10,7 +10,7 @@ */ #include "../perf.h" #include "../util/util.h" -#include "../util/parse-options.h" +#include <subcmd/parse-options.h> #include "../builtin.h" #include "bench.h" diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index 2bf9b3fd9e61..cc5c1267c738 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -21,7 +21,7 @@ #include "util/evsel.h" #include "util/annotate.h" #include "util/event.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/thread.h" #include "util/sort.h" @@ -47,7 +47,7 @@ struct perf_annotate { }; static int perf_evsel__add_sample(struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct addr_location *al, struct perf_annotate *ann) { @@ -72,7 +72,10 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true); + sample->period = 1; + sample->weight = 1; + + he = __hists__add_entry(hists, al, NULL, NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; @@ -343,18 +346,19 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) return ret; argc = parse_options(argc, argv, options, annotate_usage, 0); + if (argc) { + /* + * Special case: if there's an argument left then assume that + * it's a symbol filter: + */ + if (argc > 1) + usage_with_options(annotate_usage, options); - if (annotate.use_stdio) - use_browser = 0; - else if (annotate.use_tui) - use_browser = 1; - else if (annotate.use_gtk) - use_browser = 2; + annotate.sym_hist_filter = argv[0]; + } file.path = input_name; - setup_browser(true); - annotate.session = perf_session__new(&file, false, &annotate.tool); if (annotate.session == NULL) return -1; @@ -366,19 +370,17 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) goto out_delete; - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) usage_with_options(annotate_usage, options); - if (argc) { - /* - * Special case: if there's an argument left then assume that - * it's a symbol filter: - */ - if (argc > 1) - usage_with_options(annotate_usage, options); + if (annotate.use_stdio) + use_browser = 0; + else if (annotate.use_tui) + use_browser = 1; + else if (annotate.use_gtk) + use_browser = 2; - annotate.sym_hist_filter = argv[0]; - } + setup_browser(true); ret = __cmd_annotate(&annotate); diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c index b17aed36ca16..a1cddc6bbf0f 100644 --- a/tools/perf/builtin-bench.c +++ b/tools/perf/builtin-bench.c @@ -16,7 +16,7 @@ */ #include "perf.h" #include "util/util.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "builtin.h" #include "bench/bench.h" diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index 7b8450cd33c2..d93bff7fc0e4 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -16,7 +16,7 @@ #include "util/cache.h" #include "util/debug.h" #include "util/header.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/strlist.h" #include "util/build-id.h" #include "util/session.h" diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c index 918b4de29de4..5e914ee79eb3 100644 --- a/tools/perf/builtin-buildid-list.c +++ b/tools/perf/builtin-buildid-list.c @@ -12,7 +12,7 @@ #include "util/build-id.h" #include "util/cache.h" #include "util/debug.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/session.h" #include "util/symbol.h" #include "util/data.h" @@ -110,7 +110,7 @@ int cmd_buildid_list(int argc, const char **argv, setup_pager(); if (show_kernel) - return sysfs__fprintf_build_id(stdout); + return !(sysfs__fprintf_build_id(stdout) > 0); return perf_session__list_build_ids(force, with_hits); } diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c new file mode 100644 index 000000000000..f04e804a9fad --- /dev/null +++ b/tools/perf/builtin-config.c @@ -0,0 +1,66 @@ +/* + * builtin-config.c + * + * Copyright (C) 2015, Taeung Song <treeze.taeung@gmail.com> + * + */ +#include "builtin.h" + +#include "perf.h" + +#include "util/cache.h" +#include <subcmd/parse-options.h> +#include "util/util.h" +#include "util/debug.h" + +static const char * const config_usage[] = { + "perf config [options]", + NULL +}; + +enum actions { + ACTION_LIST = 1 +} actions; + +static struct option config_options[] = { + OPT_SET_UINT('l', "list", &actions, + "show current config variables", ACTION_LIST), + OPT_END() +}; + +static int show_config(const char *key, const char *value, + void *cb __maybe_unused) +{ + if (value) + printf("%s=%s\n", key, value); + else + printf("%s\n", key); + + return 0; +} + +int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused) +{ + int ret = 0; + + argc = parse_options(argc, argv, config_options, config_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + switch (actions) { + case ACTION_LIST: + if (argc) { + pr_err("Error: takes no arguments\n"); + parse_options_usage(config_usage, config_options, "l", 1); + } else { + ret = perf_config(show_config, NULL); + if (ret < 0) + pr_err("Nothing configured, " + "please check your ~/.perfconfig file\n"); + } + break; + default: + usage_with_options(config_usage, config_options); + } + + return ret; +} diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c index d6525bc54d13..b97bc1518b44 100644 --- a/tools/perf/builtin-data.c +++ b/tools/perf/builtin-data.c @@ -2,7 +2,7 @@ #include "builtin.h" #include "perf.h" #include "debug.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include "data-convert-bt.h" typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix); diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 0b180a885ba3..36ccc2b8827f 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -311,11 +311,11 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, } static int hists__add_entry(struct hists *hists, - struct addr_location *al, u64 period, - u64 weight, u64 transaction) + struct addr_location *al, + struct perf_sample *sample) { - if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight, - transaction, true) != NULL) + if (__hists__add_entry(hists, al, NULL, NULL, NULL, + sample, true) != NULL) return 0; return -ENOMEM; } @@ -336,8 +336,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (hists__add_entry(hists, &al, sample->period, - sample->weight, sample->transaction)) { + if (hists__add_entry(hists, &al, sample)) { pr_warning("problem incrementing symbol period, skipping event\n"); goto out_put; } @@ -1208,7 +1207,7 @@ static int ui_init(void) BUG_ON(1); } - list_add(&fmt->sort_list, &perf_hpp__sort_list); + perf_hpp__register_sort_field(fmt); return 0; } @@ -1280,7 +1279,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) sort__mode = SORT_MODE__DIFF; - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) usage_with_options(diff_usage, options); setup_pager(); diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index f4d62510acbb..8a31f511e1a0 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -12,7 +12,7 @@ #include "util/evlist.h" #include "util/evsel.h" #include "util/parse-events.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/session.h" #include "util/data.h" #include "util/debug.h" @@ -26,14 +26,22 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details .mode = PERF_DATA_MODE_READ, .force = details->force, }; + bool has_tracepoint = false; session = perf_session__new(&file, 0, NULL); if (session == NULL) return -1; - evlist__for_each(session->evlist, pos) + evlist__for_each(session->evlist, pos) { perf_evsel__fprintf(pos, details, stdout); + if (pos->attr.type == PERF_TYPE_TRACEPOINT) + has_tracepoint = true; + } + + if (has_tracepoint && !details->trace_fields) + printf("# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events\n"); + perf_session__delete(session); return 0; } @@ -49,6 +57,7 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('g', "group", &details.event_group, "Show event group information"), OPT_BOOLEAN('f', "force", &details.force, "don't complain, do it"), + OPT_BOOLEAN(0, "trace-fields", &details.trace_fields, "Show tracepoint fields"), OPT_END() }; const char * const evlist_usage[] = { diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index a7d588bf3cdd..96c1a4cfbbbf 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -6,11 +6,11 @@ #include "perf.h" #include "util/cache.h" #include "builtin.h" -#include "util/exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "common-cmds.h" -#include "util/parse-options.h" -#include "util/run-command.h" -#include "util/help.h" +#include <subcmd/parse-options.h> +#include <subcmd/run-command.h> +#include <subcmd/help.h> #include "util/debug.h" static struct man_viewer_list { @@ -407,7 +407,7 @@ static int get_html_page_path(struct strbuf *page_path, const char *page) #ifndef open_html static void open_html(const char *path) { - execl_perf_cmd("web--browse", "-c", "help.browser", path, NULL); + execl_cmd("web--browse", "-c", "help.browser", path, NULL); } #endif diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 99d127fe9c35..0022e02ed31a 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -18,7 +18,7 @@ #include "util/data.h" #include "util/auxtrace.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include <linux/list.h> diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 93ce665f976f..118010553d0c 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -12,7 +12,7 @@ #include "util/tool.h" #include "util/callchain.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/trace-event.h" #include "util/data.h" #include "util/cpumap.h" diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c index dd94b4ca2213..4418d9214872 100644 --- a/tools/perf/builtin-kvm.c +++ b/tools/perf/builtin-kvm.c @@ -10,7 +10,7 @@ #include "util/header.h" #include "util/session.h" #include "util/intlist.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/trace-event.h" #include "util/debug.h" #include "util/tool.h" @@ -1351,7 +1351,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, disable_buildid_cache(); use_browser = 0; - setup_browser(false); if (argc) { argc = parse_options(argc, argv, live_options, @@ -1409,8 +1408,6 @@ static int kvm_events_live(struct perf_kvm_stat *kvm, err = kvm_events_live_report(kvm); out: - exit_browser(0); - if (kvm->session) perf_session__delete(kvm->session); kvm->session = NULL; diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index bf679e2c978b..5e22db4684b8 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -14,7 +14,7 @@ #include "util/parse-events.h" #include "util/cache.h" #include "util/pmu.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused) { diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index de16aaed516e..ce3bfb48b26f 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -9,7 +9,7 @@ #include "util/thread.h" #include "util/header.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/trace-event.h" #include "util/debug.h" diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index 80170aace5d4..390170041696 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -1,7 +1,7 @@ #include "builtin.h" #include "perf.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/trace-event.h" #include "util/tool.h" #include "util/session.h" diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c index 132afc97676c..9af859b28b15 100644 --- a/tools/perf/builtin-probe.c +++ b/tools/perf/builtin-probe.c @@ -37,7 +37,7 @@ #include "util/strfilter.h" #include "util/symbol.h" #include "util/debug.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/probe-finder.h" #include "util/probe-event.h" #include "util/probe-file.h" @@ -249,6 +249,9 @@ static int opt_show_vars(const struct option *opt, return ret; } +#else +# define opt_show_lines NULL +# define opt_show_vars NULL #endif static int opt_add_probe_event(const struct option *opt, const char *str, int unset __maybe_unused) @@ -473,7 +476,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) opt_add_probe_event), OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events" " with existing name"), -#ifdef HAVE_DWARF_SUPPORT OPT_CALLBACK('L', "line", NULL, "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]", "Show source code lines.", opt_show_lines), @@ -490,7 +492,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) "directory", "path to kernel source"), OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines, "Don't search inlined functions"), -#endif OPT__DRY_RUN(&probe_event_dry_run), OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes, "Set how many probe points can be found for a probe."), @@ -521,6 +522,16 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused) #ifdef HAVE_DWARF_SUPPORT set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE); set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE); +#else +# define set_nobuild(s, l, c) set_option_nobuild(options, s, l, "NO_DWARF=1", c) + set_nobuild('L', "line", false); + set_nobuild('V', "vars", false); + set_nobuild('\0', "externs", false); + set_nobuild('\0', "range", false); + set_nobuild('k', "vmlinux", true); + set_nobuild('s', "source", true); + set_nobuild('\0', "no-inlines", true); +# undef set_nobuild #endif set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE); diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 199fc31e3919..dc4e0adf5c5b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -11,7 +11,7 @@ #include "util/build-id.h" #include "util/util.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/callchain.h" @@ -452,6 +452,8 @@ static void record__init_features(struct record *rec) if (!rec->opts.full_auxtrace) perf_header__clear_feat(&session->header, HEADER_AUXTRACE); + + perf_header__clear_feat(&session->header, HEADER_STAT); } static volatile int workload_exec_errno; @@ -813,8 +815,12 @@ int record_parse_callchain_opt(const struct option *opt, } ret = parse_callchain_record_opt(arg, &callchain_param); - if (!ret) + if (!ret) { + /* Enable data address sampling for DWARF unwind. */ + if (callchain_param.record_mode == CALLCHAIN_DWARF) + record->sample_address = true; callchain_debug(); + } return ret; } @@ -837,6 +843,19 @@ int record_callchain_opt(const struct option *opt, static int perf_record_config(const char *var, const char *value, void *cb) { + struct record *rec = cb; + + if (!strcmp(var, "record.build-id")) { + if (!strcmp(value, "cache")) + rec->no_buildid_cache = false; + else if (!strcmp(value, "no-cache")) + rec->no_buildid_cache = true; + else if (!strcmp(value, "skip")) + rec->no_buildid = true; + else + return -1; + return 0; + } if (!strcmp(var, "record.call-graph")) var = "call-graph.record-mode"; /* fall-through */ @@ -1113,12 +1132,12 @@ struct option __record_options[] = { "per thread proc mmap processing timeout in ms"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), -#ifdef HAVE_LIBBPF_SUPPORT OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path", "clang binary to use for compiling BPF scriptlets"), OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options", "options passed to clang when compiling BPF scriptlets"), -#endif + OPT_STRING(0, "vmlinux", &symbol_conf.vmlinux_name, + "file", "vmlinux pathname"), OPT_END() }; @@ -1130,6 +1149,27 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) struct record *rec = &record; char errbuf[BUFSIZ]; +#ifndef HAVE_LIBBPF_SUPPORT +# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c) + set_nobuild('\0', "clang-path", true); + set_nobuild('\0', "clang-opt", true); +# undef set_nobuild +#endif + +#ifndef HAVE_BPF_PROLOGUE +# if !defined (HAVE_DWARF_SUPPORT) +# define REASON "NO_DWARF=1" +# elif !defined (HAVE_LIBBPF_SUPPORT) +# define REASON "NO_LIBBPF=1" +# else +# define REASON "this architecture doesn't support BPF prologue" +# endif +# define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, REASON, c) + set_nobuild('\0', "vmlinux", true); +# undef set_nobuild +# undef REASON +#endif + rec->evlist = perf_evlist__new(); if (rec->evlist == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f256fac1e722..d5a42ee12529 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -27,7 +27,7 @@ #include "util/session.h" #include "util/tool.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/thread.h" @@ -45,7 +45,6 @@ struct report { struct perf_tool tool; struct perf_session *session; bool use_tui, use_gtk, use_stdio; - bool hide_unresolved; bool dont_use_callchains; bool show_full_info; bool show_threads; @@ -146,7 +145,7 @@ static int process_sample_event(struct perf_tool *tool, struct hist_entry_iter iter = { .evsel = evsel, .sample = sample, - .hide_unresolved = rep->hide_unresolved, + .hide_unresolved = symbol_conf.hide_unresolved, .add_entry_cb = hist_iter__report_callback, }; int ret = 0; @@ -157,7 +156,7 @@ static int process_sample_event(struct perf_tool *tool, return -1; } - if (rep->hide_unresolved && al.sym == NULL) + if (symbol_conf.hide_unresolved && al.sym == NULL) goto out_put; if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap)) @@ -434,7 +433,7 @@ static int report__browse_hists(struct report *rep) int ret; struct perf_session *session = rep->session; struct perf_evlist *evlist = session->evlist; - const char *help = "For a higher level overview, try: perf report --sort comm,dso"; + const char *help = perf_tip(TIPDIR); switch (use_browser) { case 1: @@ -514,20 +513,26 @@ static int __cmd_report(struct report *rep) if (rep->cpu_list) { ret = perf_session__cpu_bitmap(session, rep->cpu_list, rep->cpu_bitmap); - if (ret) + if (ret) { + ui__error("failed to set cpu bitmap\n"); return ret; + } } if (rep->show_threads) perf_read_values_init(&rep->show_threads_values); ret = report__setup_sample_type(rep); - if (ret) + if (ret) { + /* report__setup_sample_type() already showed error message */ return ret; + } ret = perf_session__process_events(session); - if (ret) + if (ret) { + ui__error("failed to process sample\n"); return ret; + } report__warn_kptr_restrict(rep); @@ -625,7 +630,7 @@ parse_percent_limit(const struct option *opt, const char *str, return 0; } -#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function" +#define CALLCHAIN_DEFAULT_OPT "graph,0.5,caller,function,percent" const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n" CALLCHAIN_REPORT_HELP @@ -708,7 +713,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other, "Only display entries with parent-match"), OPT_CALLBACK_DEFAULT('g', "call-graph", &report, - "print_type,threshold[,print_limit],order,sort_key[,branch]", + "print_type,threshold[,print_limit],order,sort_key[,branch],value", report_callchain_help, &report_parse_callchain_opt, callchain_default_opt), OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain, @@ -740,7 +745,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_STRING_NOEMPTY('t', "field-separator", &symbol_conf.field_sep, "separator", "separator for columns, no spaces will be added between " "columns '.' is reserved."), - OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved, + OPT_BOOLEAN('U', "hide-unresolved", &symbol_conf.hide_unresolved, "Only display entries resolved to a symbol"), OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory", "Look for files with symbols relative to this directory"), @@ -783,6 +788,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Show callgraph from reference event"), OPT_INTEGER(0, "socket-filter", &report.socket_filter, "only show processor socket that match with this filter"), + OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, + "Show raw trace event output (do not use print fmt or plugins)"), OPT_END() }; struct perf_data_file file = { @@ -796,6 +803,16 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) perf_config(report__config, &report); argc = parse_options(argc, argv, options, report_usage, 0); + if (argc) { + /* + * Special case: if there's an argument left then assume that + * it's a symbol filter: + */ + if (argc > 1) + usage_with_options(report_usage, options); + + report.symbol_filter_str = argv[0]; + } if (symbol_conf.vmlinux_name && access(symbol_conf.vmlinux_name, R_OK)) { @@ -882,7 +899,7 @@ repeat: symbol_conf.cumulate_callchain = false; } - if (setup_sorting() < 0) { + if (setup_sorting(session->evlist) < 0) { if (sort_order) parse_options_usage(report_usage, options, "s", 1); if (field_order) @@ -941,17 +958,6 @@ repeat: if (symbol__init(&session->header.env) < 0) goto error; - if (argc) { - /* - * Special case: if there's an argument left then assume that - * it's a symbol filter: - */ - if (argc > 1) - usage_with_options(report_usage, options); - - report.symbol_filter_str = argv[0]; - } - sort__setup_elide(stdout); ret = __cmd_report(&report); diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index e3d3e32c0a93..871b55ae22a4 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -12,7 +12,7 @@ #include "util/tool.h" #include "util/cloexec.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/trace-event.h" #include "util/debug.h" diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 72b5deb4bd79..c691214d820f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3,9 +3,9 @@ #include "perf.h" #include "util/cache.h" #include "util/debug.h" -#include "util/exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "util/header.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/perf_regs.h" #include "util/session.h" #include "util/tool.h" @@ -18,7 +18,11 @@ #include "util/sort.h" #include "util/data.h" #include "util/auxtrace.h" +#include "util/cpumap.h" +#include "util/thread_map.h" +#include "util/stat.h" #include <linux/bitmap.h> +#include "asm/bug.h" static char const *script_name; static char const *generate_script_lang; @@ -32,6 +36,7 @@ static bool print_flags; static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +static struct perf_stat_config stat_config; unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; @@ -130,6 +135,18 @@ static struct { .invalid_fields = PERF_OUTPUT_TRACE, }, + + [PERF_TYPE_BREAKPOINT] = { + .user_set = false, + + .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID | + PERF_OUTPUT_CPU | PERF_OUTPUT_TIME | + PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP | + PERF_OUTPUT_SYM | PERF_OUTPUT_DSO | + PERF_OUTPUT_PERIOD, + + .invalid_fields = PERF_OUTPUT_TRACE, + }, }; static bool output_set_by_user(void) @@ -204,6 +221,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, struct perf_event_attr *attr = &evsel->attr; bool allow_user_set; + if (perf_header__has_feat(&session->header, HEADER_STAT)) + return 0; + allow_user_set = perf_header__has_feat(&session->header, HEADER_AUXTRACE); @@ -588,8 +608,35 @@ static void print_sample_flags(u32 flags) printf(" %-4s ", str); } -static void process_event(union perf_event *event, struct perf_sample *sample, - struct perf_evsel *evsel, struct addr_location *al) +struct perf_script { + struct perf_tool tool; + struct perf_session *session; + bool show_task_events; + bool show_mmap_events; + bool show_switch_events; + bool allocated; + struct cpu_map *cpus; + struct thread_map *threads; + int name_width; +}; + +static int perf_evlist__max_name_len(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int max = 0; + + evlist__for_each(evlist, evsel) { + int len = strlen(perf_evsel__name(evsel)); + + max = MAX(len, max); + } + + return max; +} + +static void process_event(struct perf_script *script, union perf_event *event, + struct perf_sample *sample, struct perf_evsel *evsel, + struct addr_location *al) { struct thread *thread = al->thread; struct perf_event_attr *attr = &evsel->attr; @@ -604,7 +651,12 @@ static void process_event(union perf_event *event, struct perf_sample *sample, if (PRINT_FIELD(EVNAME)) { const char *evname = perf_evsel__name(evsel); - printf("%s: ", evname ? evname : "[unknown]"); + + if (!script->name_width) + script->name_width = perf_evlist__max_name_len(script->session->evlist); + + printf("%*s: ", script->name_width, + evname ? evname : "[unknown]"); } if (print_flags) @@ -643,65 +695,81 @@ static void process_event(union perf_event *event, struct perf_sample *sample, printf("\n"); } -static int default_start_script(const char *script __maybe_unused, - int argc __maybe_unused, - const char **argv __maybe_unused) -{ - return 0; -} +static struct scripting_ops *scripting_ops; -static int default_flush_script(void) +static void __process_stat(struct perf_evsel *counter, u64 tstamp) { - return 0; + int nthreads = thread_map__nr(counter->threads); + int ncpus = perf_evsel__nr_cpus(counter); + int cpu, thread; + static int header_printed; + + if (counter->system_wide) + nthreads = 1; + + if (!header_printed) { + printf("%3s %8s %15s %15s %15s %15s %s\n", + "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT"); + header_printed = 1; + } + + for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < ncpus; cpu++) { + struct perf_counts_values *counts; + + counts = perf_counts(counter->counts, cpu, thread); + + printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", + counter->cpus->map[cpu], + thread_map__pid(counter->threads, thread), + counts->val, + counts->ena, + counts->run, + tstamp, + perf_evsel__name(counter)); + } + } } -static int default_stop_script(void) +static void process_stat(struct perf_evsel *counter, u64 tstamp) { - return 0; + if (scripting_ops && scripting_ops->process_stat) + scripting_ops->process_stat(&stat_config, counter, tstamp); + else + __process_stat(counter, tstamp); } -static int default_generate_script(struct pevent *pevent __maybe_unused, - const char *outfile __maybe_unused) +static void process_stat_interval(u64 tstamp) { - return 0; + if (scripting_ops && scripting_ops->process_stat_interval) + scripting_ops->process_stat_interval(tstamp); } -static struct scripting_ops default_scripting_ops = { - .start_script = default_start_script, - .flush_script = default_flush_script, - .stop_script = default_stop_script, - .process_event = process_event, - .generate_script = default_generate_script, -}; - -static struct scripting_ops *scripting_ops; - static void setup_scripting(void) { setup_perl_scripting(); setup_python_scripting(); - - scripting_ops = &default_scripting_ops; } static int flush_scripting(void) { - return scripting_ops->flush_script(); + return scripting_ops ? scripting_ops->flush_script() : 0; } static int cleanup_scripting(void) { pr_debug("\nperf script stopped\n"); - return scripting_ops->stop_script(); + return scripting_ops ? scripting_ops->stop_script() : 0; } -static int process_sample_event(struct perf_tool *tool __maybe_unused, +static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct machine *machine) { + struct perf_script *scr = container_of(tool, struct perf_script, tool); struct addr_location al; if (debug_mode) { @@ -727,20 +795,16 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused, if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) goto out_put; - scripting_ops->process_event(event, sample, evsel, &al); + if (scripting_ops) + scripting_ops->process_event(event, sample, evsel, &al); + else + process_event(scr, event, sample, evsel, &al); + out_put: addr_location__put(&al); return 0; } -struct perf_script { - struct perf_tool tool; - struct perf_session *session; - bool show_task_events; - bool show_mmap_events; - bool show_switch_events; -}; - static int process_attr(struct perf_tool *tool, union perf_event *event, struct perf_evlist **pevlist) { @@ -1156,6 +1220,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused, type = PERF_TYPE_TRACEPOINT; else if (!strcmp(str, "raw")) type = PERF_TYPE_RAW; + else if (!strcmp(str, "break")) + type = PERF_TYPE_BREAKPOINT; else { fprintf(stderr, "Invalid event type in field string.\n"); rc = -EINVAL; @@ -1421,7 +1487,7 @@ static int list_available_scripts(const struct option *opt __maybe_unused, char first_half[BUFSIZ]; char *script_root; - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); if (!scripts_dir) @@ -1542,7 +1608,7 @@ int find_scripts(char **scripts_array, char **scripts_path_array) if (!session) return -1; - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); if (!scripts_dir) { @@ -1600,7 +1666,7 @@ static char *get_script_path(const char *script_root, const char *suffix) char lang_path[MAXPATHLEN]; char *__script_root; - snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path()); + snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); if (!scripts_dir) @@ -1695,6 +1761,87 @@ static void script__setup_sample_type(struct perf_script *script) } } +static int process_stat_round_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session) +{ + struct stat_round_event *round = &event->stat_round; + struct perf_evsel *counter; + + evlist__for_each(session->evlist, counter) { + perf_stat_process_counter(&stat_config, counter); + process_stat(counter, round->time); + } + + process_stat_interval(round->time); + return 0; +} + +static int process_stat_config_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + perf_event__read_stat_config(&stat_config, &event->stat_config); + return 0; +} + +static int set_maps(struct perf_script *script) +{ + struct perf_evlist *evlist = script->session->evlist; + + if (!script->cpus || !script->threads) + return 0; + + if (WARN_ONCE(script->allocated, "stats double allocation\n")) + return -EINVAL; + + perf_evlist__set_maps(evlist, script->cpus, script->threads); + + if (perf_evlist__alloc_stats(evlist, true)) + return -ENOMEM; + + script->allocated = true; + return 0; +} + +static +int process_thread_map_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (script->threads) { + pr_warning("Extra thread map event, ignoring.\n"); + return 0; + } + + script->threads = thread_map__new_event(&event->thread_map); + if (!script->threads) + return -ENOMEM; + + return set_maps(script); +} + +static +int process_cpu_map_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (script->cpus) { + pr_warning("Extra cpu map event, ignoring.\n"); + return 0; + } + + script->cpus = cpu_map__new_data(&event->cpu_map.data); + if (!script->cpus) + return -ENOMEM; + + return set_maps(script); +} + int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) { bool show_full_info = false; @@ -1723,6 +1870,11 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, .auxtrace_error = perf_event__process_auxtrace_error, + .stat = perf_event__process_stat_event, + .stat_round = process_stat_round_event, + .stat_config = process_stat_config_event, + .thread_map = process_thread_map_event, + .cpu_map = process_cpu_map_event, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -1836,7 +1988,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) scripting_max_stack = itrace_synth_opts.callchain_sz; /* make sure PERF_EXEC_PATH is set for scripts */ - perf_set_argv_exec_path(perf_exec_path()); + set_argv_exec_path(get_argv_exec_path()); if (argc && !script_name && !rec_script_path && !rep_script_path) { int live_pipe[2]; @@ -2076,6 +2228,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) flush_scripting(); out_delete: + perf_evlist__free_stats(session->evlist); perf_session__delete(session); if (script_started) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index e77880b5094d..7f568244662b 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -45,7 +45,7 @@ #include "builtin.h" #include "util/cgroup.h" #include "util/util.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/pmu.h" #include "util/event.h" @@ -59,6 +59,9 @@ #include "util/thread.h" #include "util/thread_map.h" #include "util/counts.h" +#include "util/session.h" +#include "util/tool.h" +#include "asm/bug.h" #include <stdlib.h> #include <sys/prctl.h> @@ -126,6 +129,21 @@ static bool append_file; static const char *output_name; static int output_fd; +struct perf_stat { + bool record; + struct perf_data_file file; + struct perf_session *session; + u64 bytes_written; + struct perf_tool tool; + bool maps_allocated; + struct cpu_map *cpus; + struct thread_map *threads; + enum aggr_mode aggr_mode; +}; + +static struct perf_stat perf_stat; +#define STAT_RECORD perf_stat.record + static volatile int done = 0; static struct perf_stat_config stat_config = { @@ -161,15 +179,43 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) attr->inherit = !no_inherit; - if (target__has_cpu(&target)) - return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); + /* + * Some events get initialized with sample_(period/type) set, + * like tracepoints. Clear it up for counting. + */ + attr->sample_period = 0; + + /* + * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless + * while avoiding that older tools show confusing messages. + * + * However for pipe sessions we need to keep it zero, + * because script's perf_evsel__check_attr is triggered + * by attr->sample_type != 0, and we can't run it on + * stat sessions. + */ + if (!(STAT_RECORD && perf_stat.file.is_pipe)) + attr->sample_type = PERF_SAMPLE_IDENTIFIER; - if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) { + /* + * Disabling all counters initially, they will be enabled + * either manually by us or by kernel via enable_on_exec + * set later. + */ + if (perf_evsel__is_group_leader(evsel)) { attr->disabled = 1; - if (!initial_delay) + + /* + * In case of initial_delay we enable tracee + * events manually. + */ + if (target__none(&target) && !initial_delay) attr->enable_on_exec = 1; } + if (target__has_cpu(&target)) + return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel)); + return perf_evsel__open_per_thread(evsel, evsel_list->threads); } @@ -185,6 +231,42 @@ static inline int nsec_counter(struct perf_evsel *evsel) return 0; } +static int process_synthesized_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) { + pr_err("failed to write perf data, error: %m\n"); + return -1; + } + + perf_stat.bytes_written += event->header.size; + return 0; +} + +static int write_stat_round_event(u64 tm, u64 type) +{ + return perf_event__synthesize_stat_round(NULL, tm, type, + process_synthesized_event, + NULL); +} + +#define WRITE_STAT_ROUND_EVENT(time, interval) \ + write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval) + +#define SID(e, x, y) xyarray__entry(e->sample_id, x, y) + +static int +perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread, + struct perf_counts_values *count) +{ + struct perf_sample_id *sid = SID(counter, cpu, thread); + + return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count, + process_synthesized_event, NULL); +} + /* * Read out the results of a single counter: * do not aggregate counts across CPUs in system-wide mode @@ -208,6 +290,13 @@ static int read_counter(struct perf_evsel *counter) count = perf_counts(counter->counts, cpu, thread); if (perf_evsel__read(counter, cpu, thread, count)) return -1; + + if (STAT_RECORD) { + if (perf_evsel__write_stat_event(counter, cpu, thread, count)) { + pr_err("failed to write stat event\n"); + return -1; + } + } } } @@ -241,21 +330,26 @@ static void process_interval(void) clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); + if (STAT_RECORD) { + if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSECS_PER_SEC + rs.tv_nsec, INTERVAL)) + pr_err("failed to write stat round event\n"); + } + print_counters(&rs, 0, NULL); } -static void handle_initial_delay(void) +static void enable_counters(void) { - struct perf_evsel *counter; - - if (initial_delay) { - const int ncpus = cpu_map__nr(evsel_list->cpus), - nthreads = thread_map__nr(evsel_list->threads); - + if (initial_delay) usleep(initial_delay * 1000); - evlist__for_each(evsel_list, counter) - perf_evsel__enable(counter, ncpus, nthreads); - } + + /* + * We need to enable counters only if: + * - we don't have tracee (attaching to task or cpu) + * - we have initial delay configured + */ + if (!target__none(&target) || initial_delay) + perf_evlist__enable(evsel_list); } static volatile int workload_exec_errno; @@ -271,6 +365,135 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf workload_exec_errno = info->si_value.sival_int; } +static bool has_unit(struct perf_evsel *counter) +{ + return counter->unit && *counter->unit; +} + +static bool has_scale(struct perf_evsel *counter) +{ + return counter->scale != 1; +} + +static int perf_stat_synthesize_config(bool is_pipe) +{ + struct perf_evsel *counter; + int err; + + if (is_pipe) { + err = perf_event__synthesize_attrs(NULL, perf_stat.session, + process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize attrs.\n"); + return err; + } + } + + /* + * Synthesize other events stuff not carried within + * attr event - unit, scale, name + */ + evlist__for_each(evsel_list, counter) { + if (!counter->supported) + continue; + + /* + * Synthesize unit and scale only if it's defined. + */ + if (has_unit(counter)) { + err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize evsel unit.\n"); + return err; + } + } + + if (has_scale(counter)) { + err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize evsel scale.\n"); + return err; + } + } + + if (counter->own_cpus) { + err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize evsel scale.\n"); + return err; + } + } + + /* + * Name is needed only for pipe output, + * perf.data carries event names. + */ + if (is_pipe) { + err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event); + if (err < 0) { + pr_err("Couldn't synthesize evsel name.\n"); + return err; + } + } + } + + err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads, + process_synthesized_event, + NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus, + process_synthesized_event, NULL); + if (err < 0) { + pr_err("Couldn't synthesize thread map.\n"); + return err; + } + + err = perf_event__synthesize_stat_config(NULL, &stat_config, + process_synthesized_event, NULL); + if (err < 0) { + pr_err("Couldn't synthesize config.\n"); + return err; + } + + return 0; +} + +#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y)) + +static int __store_counter_ids(struct perf_evsel *counter, + struct cpu_map *cpus, + struct thread_map *threads) +{ + int cpu, thread; + + for (cpu = 0; cpu < cpus->nr; cpu++) { + for (thread = 0; thread < threads->nr; thread++) { + int fd = FD(counter, cpu, thread); + + if (perf_evlist__id_add_fd(evsel_list, counter, + cpu, thread, fd) < 0) + return -1; + } + } + + return 0; +} + +static int store_counter_ids(struct perf_evsel *counter) +{ + struct cpu_map *cpus = counter->cpus; + struct thread_map *threads = counter->threads; + + if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr)) + return -ENOMEM; + + return __store_counter_ids(counter, cpus, threads); +} + static int __run_perf_stat(int argc, const char **argv) { int interval = stat_config.interval; @@ -281,6 +504,7 @@ static int __run_perf_stat(int argc, const char **argv) size_t l; int status = 0; const bool forks = (argc > 0); + bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false; if (interval) { ts.tv_sec = interval / 1000; @@ -291,7 +515,7 @@ static int __run_perf_stat(int argc, const char **argv) } if (forks) { - if (perf_evlist__prepare_workload(evsel_list, &target, argv, false, + if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe, workload_exec_failed_signal) < 0) { perror("failed to prepare workload"); return -1; @@ -335,6 +559,9 @@ static int __run_perf_stat(int argc, const char **argv) l = strlen(counter->unit); if (l > unit_width) unit_width = l; + + if (STAT_RECORD && store_counter_ids(counter)) + return -1; } if (perf_evlist__apply_filters(evsel_list, &counter)) { @@ -344,6 +571,24 @@ static int __run_perf_stat(int argc, const char **argv) return -1; } + if (STAT_RECORD) { + int err, fd = perf_data_file__fd(&perf_stat.file); + + if (is_pipe) { + err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file)); + } else { + err = perf_session__write_header(perf_stat.session, evsel_list, + fd, false); + } + + if (err < 0) + return err; + + err = perf_stat_synthesize_config(is_pipe); + if (err < 0) + return err; + } + /* * Enable counters and exec the command: */ @@ -352,7 +597,7 @@ static int __run_perf_stat(int argc, const char **argv) if (forks) { perf_evlist__start_workload(evsel_list); - handle_initial_delay(); + enable_counters(); if (interval) { while (!waitpid(child_pid, &status, WNOHANG)) { @@ -371,7 +616,7 @@ static int __run_perf_stat(int argc, const char **argv) if (WIFSIGNALED(status)) psignal(WTERMSIG(status), argv[0]); } else { - handle_initial_delay(); + enable_counters(); while (!done) { nanosleep(&ts, NULL); if (interval) @@ -810,8 +1055,8 @@ static void print_header(int argc, const char **argv) else if (target.cpu_list) fprintf(output, "\'CPU(s) %s", target.cpu_list); else if (!target__has_task(&target)) { - fprintf(output, "\'%s", argv[0]); - for (i = 1; i < argc; i++) + fprintf(output, "\'%s", argv ? argv[0] : "pipe"); + for (i = 1; argv && (i < argc); i++) fprintf(output, " %s", argv[i]); } else if (target.pid) fprintf(output, "process id \'%s", target.pid); @@ -847,6 +1092,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) struct perf_evsel *counter; char buf[64], *prefix = NULL; + /* Do not print anything if we record to the pipe. */ + if (STAT_RECORD && perf_stat.file.is_pipe) + return; + if (interval) print_interval(prefix = buf, ts); else @@ -1077,6 +1326,109 @@ static int perf_stat_init_aggr_mode(void) return cpus_aggr_map ? 0 : -ENOMEM; } +static void perf_stat__exit_aggr_mode(void) +{ + cpu_map__put(aggr_map); + cpu_map__put(cpus_aggr_map); + aggr_map = NULL; + cpus_aggr_map = NULL; +} + +static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx) +{ + int cpu; + + if (idx > map->nr) + return -1; + + cpu = map->map[idx]; + + if (cpu >= env->nr_cpus_online) + return -1; + + return cpu; +} + +static int perf_env__get_socket(struct cpu_map *map, int idx, void *data) +{ + struct perf_env *env = data; + int cpu = perf_env__get_cpu(env, map, idx); + + return cpu == -1 ? -1 : env->cpu[cpu].socket_id; +} + +static int perf_env__get_core(struct cpu_map *map, int idx, void *data) +{ + struct perf_env *env = data; + int core = -1, cpu = perf_env__get_cpu(env, map, idx); + + if (cpu != -1) { + int socket_id = env->cpu[cpu].socket_id; + + /* + * Encode socket in upper 16 bits + * core_id is relative to socket, and + * we need a global id. So we combine + * socket + core id. + */ + core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff); + } + + return core; +} + +static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus, + struct cpu_map **sockp) +{ + return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); +} + +static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus, + struct cpu_map **corep) +{ + return cpu_map__build_map(cpus, corep, perf_env__get_core, env); +} + +static int perf_stat__get_socket_file(struct cpu_map *map, int idx) +{ + return perf_env__get_socket(map, idx, &perf_stat.session->header.env); +} + +static int perf_stat__get_core_file(struct cpu_map *map, int idx) +{ + return perf_env__get_core(map, idx, &perf_stat.session->header.env); +} + +static int perf_stat_init_aggr_mode_file(struct perf_stat *st) +{ + struct perf_env *env = &st->session->header.env; + + switch (stat_config.aggr_mode) { + case AGGR_SOCKET: + if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) { + perror("cannot build socket map"); + return -1; + } + aggr_get_id = perf_stat__get_socket_file; + break; + case AGGR_CORE: + if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) { + perror("cannot build core map"); + return -1; + } + aggr_get_id = perf_stat__get_core_file; + break; + case AGGR_NONE: + case AGGR_GLOBAL: + case AGGR_THREAD: + case AGGR_UNSET: + default: + break; + } + + return 0; +} + /* * Add default attributes, if there were no attributes specified or * if -d/--detailed, -d -d or -d -d -d is used: @@ -1236,6 +1588,225 @@ static int add_default_attributes(void) return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs); } +static const char * const recort_usage[] = { + "perf stat record [<options>]", + NULL, +}; + +static void init_features(struct perf_session *session) +{ + int feat; + + for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++) + perf_header__set_feat(&session->header, feat); + + perf_header__clear_feat(&session->header, HEADER_BUILD_ID); + perf_header__clear_feat(&session->header, HEADER_TRACING_DATA); + perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK); + perf_header__clear_feat(&session->header, HEADER_AUXTRACE); +} + +static int __cmd_record(int argc, const char **argv) +{ + struct perf_session *session; + struct perf_data_file *file = &perf_stat.file; + + argc = parse_options(argc, argv, stat_options, record_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (output_name) + file->path = output_name; + + if (run_count != 1 || forever) { + pr_err("Cannot use -r option with perf stat record.\n"); + return -1; + } + + session = perf_session__new(file, false, NULL); + if (session == NULL) { + pr_err("Perf session creation failed.\n"); + return -1; + } + + init_features(session); + + session->evlist = evsel_list; + perf_stat.session = session; + perf_stat.record = true; + return argc; +} + +static int process_stat_round_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session) +{ + struct stat_round_event *round = &event->stat_round; + struct perf_evsel *counter; + struct timespec tsh, *ts = NULL; + const char **argv = session->header.env.cmdline_argv; + int argc = session->header.env.nr_cmdline; + + evlist__for_each(evsel_list, counter) + perf_stat_process_counter(&stat_config, counter); + + if (round->type == PERF_STAT_ROUND_TYPE__FINAL) + update_stats(&walltime_nsecs_stats, round->time); + + if (stat_config.interval && round->time) { + tsh.tv_sec = round->time / NSECS_PER_SEC; + tsh.tv_nsec = round->time % NSECS_PER_SEC; + ts = &tsh; + } + + print_counters(ts, argc, argv); + return 0; +} + +static +int process_stat_config_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_stat *st = container_of(tool, struct perf_stat, tool); + + perf_event__read_stat_config(&stat_config, &event->stat_config); + + if (cpu_map__empty(st->cpus)) { + if (st->aggr_mode != AGGR_UNSET) + pr_warning("warning: processing task data, aggregation mode not set\n"); + return 0; + } + + if (st->aggr_mode != AGGR_UNSET) + stat_config.aggr_mode = st->aggr_mode; + + if (perf_stat.file.is_pipe) + perf_stat_init_aggr_mode(); + else + perf_stat_init_aggr_mode_file(st); + + return 0; +} + +static int set_maps(struct perf_stat *st) +{ + if (!st->cpus || !st->threads) + return 0; + + if (WARN_ONCE(st->maps_allocated, "stats double allocation\n")) + return -EINVAL; + + perf_evlist__set_maps(evsel_list, st->cpus, st->threads); + + if (perf_evlist__alloc_stats(evsel_list, true)) + return -ENOMEM; + + st->maps_allocated = true; + return 0; +} + +static +int process_thread_map_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_stat *st = container_of(tool, struct perf_stat, tool); + + if (st->threads) { + pr_warning("Extra thread map event, ignoring.\n"); + return 0; + } + + st->threads = thread_map__new_event(&event->thread_map); + if (!st->threads) + return -ENOMEM; + + return set_maps(st); +} + +static +int process_cpu_map_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_stat *st = container_of(tool, struct perf_stat, tool); + struct cpu_map *cpus; + + if (st->cpus) { + pr_warning("Extra cpu map event, ignoring.\n"); + return 0; + } + + cpus = cpu_map__new_data(&event->cpu_map.data); + if (!cpus) + return -ENOMEM; + + st->cpus = cpus; + return set_maps(st); +} + +static const char * const report_usage[] = { + "perf stat report [<options>]", + NULL, +}; + +static struct perf_stat perf_stat = { + .tool = { + .attr = perf_event__process_attr, + .event_update = perf_event__process_event_update, + .thread_map = process_thread_map_event, + .cpu_map = process_cpu_map_event, + .stat_config = process_stat_config_event, + .stat = perf_event__process_stat_event, + .stat_round = process_stat_round_event, + }, + .aggr_mode = AGGR_UNSET, +}; + +static int __cmd_report(int argc, const char **argv) +{ + struct perf_session *session; + const struct option options[] = { + OPT_STRING('i', "input", &input_name, "file", "input file name"), + OPT_SET_UINT(0, "per-socket", &perf_stat.aggr_mode, + "aggregate counts per processor socket", AGGR_SOCKET), + OPT_SET_UINT(0, "per-core", &perf_stat.aggr_mode, + "aggregate counts per physical processor core", AGGR_CORE), + OPT_SET_UINT('A', "no-aggr", &perf_stat.aggr_mode, + "disable CPU count aggregation", AGGR_NONE), + OPT_END() + }; + struct stat st; + int ret; + + argc = parse_options(argc, argv, options, report_usage, 0); + + if (!input_name || !strlen(input_name)) { + if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode)) + input_name = "-"; + else + input_name = "perf.data"; + } + + perf_stat.file.path = input_name; + perf_stat.file.mode = PERF_DATA_MODE_READ; + + session = perf_session__new(&perf_stat.file, false, &perf_stat.tool); + if (session == NULL) + return -1; + + perf_stat.session = session; + stat_config.output = stderr; + evsel_list = session->evlist; + + ret = perf_session__process_events(session); + if (ret) + return ret; + + perf_session__delete(session); + return 0; +} + int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) { const char * const stat_usage[] = { @@ -1246,6 +1817,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) const char *mode; FILE *output = stderr; unsigned int interval; + const char * const stat_subcommands[] = { "record", "report" }; setlocale(LC_ALL, ""); @@ -1253,12 +1825,30 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (evsel_list == NULL) return -ENOMEM; - argc = parse_options(argc, argv, stat_options, stat_usage, - PARSE_OPT_STOP_AT_NON_OPTION); + argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands, + (const char **) stat_usage, + PARSE_OPT_STOP_AT_NON_OPTION); + + if (csv_sep) { + csv_output = true; + if (!strcmp(csv_sep, "\\t")) + csv_sep = "\t"; + } else + csv_sep = DEFAULT_SEPARATOR; + + if (argc && !strncmp(argv[0], "rec", 3)) { + argc = __cmd_record(argc, argv); + if (argc < 0) + return -1; + } else if (argc && !strncmp(argv[0], "rep", 3)) + return __cmd_report(argc, argv); interval = stat_config.interval; - if (output_name && strcmp(output_name, "-")) + /* + * For record command the -o is already taken care of. + */ + if (!STAT_RECORD && output_name && strcmp(output_name, "-")) output = NULL; if (output_name && output_fd) { @@ -1296,13 +1886,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) stat_config.output = output; - if (csv_sep) { - csv_output = true; - if (!strcmp(csv_sep, "\\t")) - csv_sep = "\t"; - } else - csv_sep = DEFAULT_SEPARATOR; - /* * let the spreadsheet do the pretty-printing */ @@ -1425,6 +2008,42 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (!forever && status != -1 && !interval) print_counters(NULL, argc, argv); + if (STAT_RECORD) { + /* + * We synthesize the kernel mmap record just so that older tools + * don't emit warnings about not being able to resolve symbols + * due to /proc/sys/kernel/kptr_restrict settings and instear provide + * a saner message about no samples being in the perf.data file. + * + * This also serves to suppress a warning about f_header.data.size == 0 + * in header.c at the moment 'perf stat record' gets introduced, which + * is not really needed once we start adding the stat specific PERF_RECORD_ + * records, but the need to suppress the kptr_restrict messages in older + * tools remain -acme + */ + int fd = perf_data_file__fd(&perf_stat.file); + int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat, + process_synthesized_event, + &perf_stat.session->machines.host); + if (err) { + pr_warning("Couldn't synthesize the kernel mmap record, harmless, " + "older tools may produce warnings about this file\n."); + } + + if (!interval) { + if (WRITE_STAT_ROUND_EVENT(walltime_nsecs_stats.max, FINAL)) + pr_err("failed to write stat round event\n"); + } + + if (!perf_stat.file.is_pipe) { + perf_stat.session->header.data_size += perf_stat.bytes_written; + perf_session__write_header(perf_stat.session, evsel_list, fd, true); + } + + perf_session__delete(perf_stat.session); + } + + perf_stat__exit_aggr_mode(); perf_evlist__free_stats(evsel_list); out: perf_evlist__delete(evsel_list); diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c index 30e59620179d..bd7a7757176f 100644 --- a/tools/perf/builtin-timechart.c +++ b/tools/perf/builtin-timechart.c @@ -30,7 +30,7 @@ #include "perf.h" #include "util/header.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/event.h" #include "util/session.h" diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 7e2e72e6d9d1..bf01cbb0ef23 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -34,7 +34,7 @@ #include "util/top.h" #include "util/util.h" #include <linux/rbtree.h> -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-events.h" #include "util/cpumap.h" #include "util/xyarray.h" @@ -175,42 +175,40 @@ static void perf_top__record_precise_ip(struct perf_top *top, int counter, u64 ip) { struct annotation *notes; - struct symbol *sym; + struct symbol *sym = he->ms.sym; int err = 0; - if (he == NULL || he->ms.sym == NULL || - ((top->sym_filter_entry == NULL || - top->sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1)) + if (sym == NULL || (use_browser == 0 && + (top->sym_filter_entry == NULL || + top->sym_filter_entry->ms.sym != sym))) return; - sym = he->ms.sym; notes = symbol__annotation(sym); if (pthread_mutex_trylock(¬es->lock)) return; - ip = he->ms.map->map_ip(he->ms.map, ip); - - if (ui__has_annotation()) - err = hist_entry__inc_addr_samples(he, counter, ip); + err = hist_entry__inc_addr_samples(he, counter, ip); pthread_mutex_unlock(¬es->lock); - /* - * This function is now called with he->hists->lock held. - * Release it before going to sleep. - */ - pthread_mutex_unlock(&he->hists->lock); + if (unlikely(err)) { + /* + * This function is now called with he->hists->lock held. + * Release it before going to sleep. + */ + pthread_mutex_unlock(&he->hists->lock); + + if (err == -ERANGE && !he->ms.map->erange_warned) + ui__warn_map_erange(he->ms.map, sym, ip); + else if (err == -ENOMEM) { + pr_err("Not enough memory for annotating '%s' symbol!\n", + sym->name); + sleep(1); + } - if (err == -ERANGE && !he->ms.map->erange_warned) - ui__warn_map_erange(he->ms.map, sym, ip); - else if (err == -ENOMEM) { - pr_err("Not enough memory for annotating '%s' symbol!\n", - sym->name); - sleep(1); + pthread_mutex_lock(&he->hists->lock); } - - pthread_mutex_lock(&he->hists->lock); } static void perf_top__show_details(struct perf_top *top) @@ -687,14 +685,8 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter, struct hist_entry *he = iter->he; struct perf_evsel *evsel = iter->evsel; - if (sort__has_sym && single) { - u64 ip = al->addr; - - if (al->map) - ip = al->map->unmap_ip(al->map, ip); - - perf_top__record_precise_ip(top, he, evsel->idx, ip); - } + if (sort__has_sym && single) + perf_top__record_precise_ip(top, he, evsel->idx, al->addr); hist__account_cycles(iter->sample->branch_stack, al, iter->sample, !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY)); @@ -964,7 +956,7 @@ static int __cmd_top(struct perf_top *top) if (ret) goto out_delete; - if (perf_session__register_idle_thread(top->session) == NULL) + if (perf_session__register_idle_thread(top->session) < 0) goto out_delete; machine__synthesize_threads(&top->session->machines.host, &opts->target, @@ -1218,6 +1210,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK('j', "branch-filter", &opts->branch_stack, "branch filter mask", "branch stack filter modes", parse_branch_stack), + OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, + "Show raw trace event output (do not use print fmt or plugins)"), OPT_END() }; const char * const top_usage[] = { @@ -1239,11 +1233,17 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(top_usage, options); + if (!top.evlist->nr_entries && + perf_evlist__add_default(top.evlist) < 0) { + pr_err("Not enough memory for event selector list\n"); + goto out_delete_evlist; + } + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ sort__need_collapse = 1; - if (setup_sorting() < 0) { + if (setup_sorting(top.evlist) < 0) { if (sort_order) parse_options_usage(top_usage, options, "s", 1); if (field_order) @@ -1279,12 +1279,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (target__none(target)) target->system_wide = true; - if (perf_evlist__create_maps(top.evlist, target) < 0) - usage_with_options(top_usage, options); - - if (!top.evlist->nr_entries && - perf_evlist__add_default(top.evlist) < 0) { - ui__error("Not enough memory for event selector list\n"); + if (perf_evlist__create_maps(top.evlist, target) < 0) { + ui__error("Couldn't create thread/CPU maps: %s\n", + errno == ENOENT ? "No such process" : strerror_r(errno, errbuf, sizeof(errbuf))); goto out_delete_evlist; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index c783d8fd3a80..20916dd77aac 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -22,11 +22,11 @@ #include "util/color.h" #include "util/debug.h" #include "util/evlist.h" -#include "util/exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "util/machine.h" #include "util/session.h" #include "util/thread.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/strlist.h" #include "util/intlist.h" #include "util/thread_map.h" diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c new file mode 100644 index 000000000000..9b10cda6b6dc --- /dev/null +++ b/tools/perf/builtin-version.c @@ -0,0 +1,10 @@ +#include "util/util.h" +#include "builtin.h" +#include "perf.h" + +int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused, + const char *prefix __maybe_unused) +{ + printf("perf version %s\n", perf_version_string); + return 0; +} diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h index 3688ad29085f..3f871b54e261 100644 --- a/tools/perf/builtin.h +++ b/tools/perf/builtin.h @@ -17,6 +17,7 @@ extern int cmd_annotate(int argc, const char **argv, const char *prefix); extern int cmd_bench(int argc, const char **argv, const char *prefix); extern int cmd_buildid_cache(int argc, const char **argv, const char *prefix); extern int cmd_buildid_list(int argc, const char **argv, const char *prefix); +extern int cmd_config(int argc, const char **argv, const char *prefix); extern int cmd_diff(int argc, const char **argv, const char *prefix); extern int cmd_evlist(int argc, const char **argv, const char *prefix); extern int cmd_help(int argc, const char **argv, const char *prefix); diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index 00fcaf8a5b8d..ab5cbaa170d0 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -9,6 +9,7 @@ perf-buildid-cache mainporcelain common perf-buildid-list mainporcelain common perf-data mainporcelain common perf-diff mainporcelain common +perf-config mainporcelain common perf-evlist mainporcelain common perf-inject mainporcelain common perf-kmem mainporcelain common @@ -25,4 +26,4 @@ perf-stat mainporcelain common perf-test mainporcelain common perf-timechart mainporcelain common perf-top mainporcelain common -perf-trace mainporcelain common +perf-trace mainporcelain audit diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index de89ec574361..254d06e39bea 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -135,8 +135,6 @@ endif ifeq ($(DEBUG),0) CFLAGS += -O6 -else - CFLAGS += $(call cc-option,-Og,-O0) endif ifdef PARSER_DEBUG @@ -318,6 +316,18 @@ ifndef NO_LIBELF CFLAGS += -DHAVE_LIBBPF_SUPPORT $(call detected,CONFIG_LIBBPF) endif + + ifndef NO_DWARF + ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET + CFLAGS += -DHAVE_BPF_PROLOGUE + $(call detected,CONFIG_BPF_PROLOGUE) + else + msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset()); + endif + else + msg := $(warning DWARF support is off, BPF prologue is disabled); + endif + endif # NO_LIBBPF endif # NO_LIBELF @@ -681,6 +691,7 @@ sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups htmldir = share/doc/perf-doc +tipdir = share/doc/perf-tip ifeq ($(prefix),/usr) sysconfdir = /etc ETC_PERFCONFIG = $(sysconfdir)/perfconfig @@ -707,6 +718,7 @@ infodir_SQ = $(subst ','\'',$(infodir)) perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_SQ = $(subst ','\'',$(htmldir)) +tipdir_SQ = $(subst ','\'',$(tipdir)) prefix_SQ = $(subst ','\'',$(prefix)) sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) libdir_SQ = $(subst ','\'',$(libdir)) @@ -714,12 +726,15 @@ libdir_SQ = $(subst ','\'',$(libdir)) ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR) +tip_instdir = $(tipdir) else perfexec_instdir = $(prefix)/$(perfexecdir) STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR) +tip_instdir = $(prefix)/$(tipdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR)) +tip_instdir_SQ = $(subst ','\'',$(tip_instdir)) # If we install to $(HOME) we keep the traceevent default: # $(HOME)/.traceevent/plugins @@ -741,6 +756,10 @@ ifeq ($(VF),1) $(call print_var,sysconfdir) $(call print_var,LIBUNWIND_DIR) $(call print_var,LIBDW_DIR) + + ifeq ($(dwarf-post-unwind),1) + $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) + endif $(info ) endif @@ -756,6 +775,7 @@ $(call detected_var,ETC_PERFCONFIG_SQ) $(call detected_var,STRACE_GROUPS_DIR_SQ) $(call detected_var,prefix_SQ) $(call detected_var,perfexecdir_SQ) +$(call detected_var,tipdir_SQ) $(call detected_var,LIBDIR) $(call detected_var,GTK_CFLAGS) $(call detected_var,PERL_EMBED_CCOPTS) diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak index 0ebef09c0842..c16ce833079c 100644 --- a/tools/perf/config/utilities.mak +++ b/tools/perf/config/utilities.mak @@ -177,22 +177,3 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2))) endef _ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2))) _gea_err = $(if $(1),$(error Please set '$(1)' appropriately)) - -# try-run -# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise) -# Exit code chooses option. "$$TMP" is can be used as temporary file and -# is automatically cleaned up. -try-run = $(shell set -e; \ - TMP="$(TMPOUT).$$$$.tmp"; \ - TMPO="$(TMPOUT).$$$$.o"; \ - if ($(1)) >/dev/null 2>&1; \ - then echo "$(2)"; \ - else echo "$(3)"; \ - fi; \ - rm -f "$$TMP" "$$TMPO") - -# cc-option -# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586) - -cc-option = $(call try-run,\ - $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 3d4c7c09adea..a929618b8eb6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -9,16 +9,18 @@ #include "builtin.h" #include "util/env.h" -#include "util/exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "util/cache.h" #include "util/quote.h" -#include "util/run-command.h" +#include <subcmd/run-command.h> #include "util/parse-events.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/bpf-loader.h" #include "util/debug.h" #include <api/fs/tracing_path.h> #include <pthread.h> +#include <stdlib.h> +#include <time.h> const char perf_usage_string[] = "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; @@ -39,6 +41,7 @@ struct cmd_struct { static struct cmd_struct commands[] = { { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, + { "config", cmd_config, 0 }, { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, @@ -118,7 +121,7 @@ static void commit_pager_choice(void) { switch (use_pager) { case 0: - setenv("PERF_PAGER", "cat", 1); + setenv(PERF_PAGER_ENVIRONMENT, "cat", 1); break; case 1: /* setup_pager(); */ @@ -182,9 +185,9 @@ static int handle_options(const char ***argv, int *argc, int *envchanged) if (!prefixcmp(cmd, CMD_EXEC_PATH)) { cmd += strlen(CMD_EXEC_PATH); if (*cmd == '=') - perf_set_argv_exec_path(cmd + 1); + set_argv_exec_path(cmd + 1); else { - puts(perf_exec_path()); + puts(get_argv_exec_path()); exit(0); } } else if (!strcmp(cmd, "--html-path")) { @@ -383,6 +386,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv) use_pager = 1; commit_pager_choice(); + perf_env__set_cmdline(&perf_env, argc, argv); status = p->fn(argc, argv, prefix); exit_browser(status); perf_env__exit(&perf_env); @@ -528,14 +532,20 @@ int main(int argc, const char **argv) const char *cmd; char sbuf[STRERR_BUFSIZE]; + /* libsubcmd init */ + exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT); + pager_init(PERF_PAGER_ENVIRONMENT); + /* The page_size is placed in util object. */ page_size = sysconf(_SC_PAGE_SIZE); cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE); - cmd = perf_extract_argv0_path(argv[0]); + cmd = extract_argv0_path(argv[0]); if (!cmd) cmd = "perf-help"; + srandom(time(NULL)); + /* get debugfs/tracefs mount point from /proc/mounts */ tracing_path_mount(); diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py new file mode 100644 index 000000000000..8b60f343dd07 --- /dev/null +++ b/tools/perf/scripts/python/stat-cpi.py @@ -0,0 +1,77 @@ +#!/usr/bin/env python + +data = {} +times = [] +threads = [] +cpus = [] + +def get_key(time, event, cpu, thread): + return "%d-%s-%d-%d" % (time, event, cpu, thread) + +def store_key(time, cpu, thread): + if (time not in times): + times.append(time) + + if (cpu not in cpus): + cpus.append(cpu) + + if (thread not in threads): + threads.append(thread) + +def store(time, event, cpu, thread, val, ena, run): + #print "event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" % \ + # (event, cpu, thread, time, val, ena, run) + + store_key(time, cpu, thread) + key = get_key(time, event, cpu, thread) + data[key] = [ val, ena, run] + +def get(time, event, cpu, thread): + key = get_key(time, event, cpu, thread) + return data[key][0] + +def stat__cycles_k(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions_k(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__cycles_u(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions_u(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__cycles(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__interval(time): + for cpu in cpus: + for thread in threads: + cyc = get(time, "cycles", cpu, thread) + ins = get(time, "instructions", cpu, thread) + cpi = 0 + + if ins != 0: + cpi = cyc/float(ins) + + print "%15f: cpu %d, thread %d -> cpi %f (%d/%d)" % (time/(float(1000000000)), cpu, thread, cpi, cyc, ins) + +def trace_end(): + pass +# XXX trace_end callback could be used as an alternative place +# to compute same values as in the script above: +# +# for time in times: +# for cpu in cpus: +# for thread in threads: +# cyc = get(time, "cycles", cpu, thread) +# ins = get(time, "instructions", cpu, thread) +# +# if ins != 0: +# cpi = cyc/float(ins) +# +# print "time %.9f, cpu %d, thread %d -> cpi %f" % (time/(float(1000000000)), cpu, thread, cpi) diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore index 489fc9ffbcb0..bf016c439fbd 100644 --- a/tools/perf/tests/.gitignore +++ b/tools/perf/tests/.gitignore @@ -1,2 +1,3 @@ llvm-src-base.c llvm-src-kbuild.c +llvm-src-prologue.c diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index f41ebf8849fe..614899b88b37 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -31,24 +31,34 @@ perf-y += sample-parsing.o perf-y += parse-no-sample-id-all.o perf-y += kmod-path.o perf-y += thread-map.o -perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o +perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o perf-y += bpf.o perf-y += topology.o +perf-y += cpumap.o +perf-y += stat.o +perf-y += event_update.o -$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c +$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build $(call rule_mkdir) $(Q)echo '#include <tests/llvm.h>' > $@ $(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@ $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ -$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c +$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c tests/Build $(call rule_mkdir) $(Q)echo '#include <tests/llvm.h>' > $@ $(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@ $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ $(Q)echo ';' >> $@ +$(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build + $(call rule_mkdir) + $(Q)echo '#include <tests/llvm.h>' > $@ + $(Q)echo 'const char test_llvm__bpf_test_prologue_prog[] =' >> $@ + $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@ + $(Q)echo ';' >> $@ + ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o endif diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c index 638875a0960a..28d1605b0338 100644 --- a/tools/perf/tests/attr.c +++ b/tools/perf/tests/attr.c @@ -24,7 +24,7 @@ #include <linux/kernel.h> #include "../perf.h" #include "util.h" -#include "exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "tests.h" #define ENV "PERF_TEST_ATTR" @@ -153,7 +153,7 @@ static int run_dir(const char *d, const char *perf) return system(cmd); } -int test__attr(void) +int test__attr(int subtest __maybe_unused) { struct stat st; char path_perf[PATH_MAX]; @@ -164,7 +164,7 @@ int test__attr(void) return run_dir("./tests", "./perf"); /* Then installed path. */ - snprintf(path_dir, PATH_MAX, "%s/tests", perf_exec_path()); + snprintf(path_dir, PATH_MAX, "%s/tests", get_argv_exec_path()); snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR); if (!lstat(path_dir, &st) && diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c index a02b035fd5aa..fb80c9eb6a95 100644 --- a/tools/perf/tests/bp_signal.c +++ b/tools/perf/tests/bp_signal.c @@ -111,7 +111,7 @@ static long long bp_count(int fd) return count; } -int test__bp_signal(void) +int test__bp_signal(int subtest __maybe_unused) { struct sigaction sa; long long count1, count2; diff --git a/tools/perf/tests/bp_signal_overflow.c b/tools/perf/tests/bp_signal_overflow.c index e76537724491..89f92fa67cc4 100644 --- a/tools/perf/tests/bp_signal_overflow.c +++ b/tools/perf/tests/bp_signal_overflow.c @@ -58,7 +58,7 @@ static long long bp_count(int fd) #define EXECUTIONS 10000 #define THRESHOLD 100 -int test__bp_signal_overflow(void) +int test__bp_signal_overflow(int subtest __maybe_unused) { struct perf_event_attr pe; struct sigaction sa; diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c new file mode 100644 index 000000000000..7230e62c70fc --- /dev/null +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -0,0 +1,35 @@ +/* + * bpf-script-test-prologue.c + * Test BPF prologue + */ +#ifndef LINUX_VERSION_CODE +# error Need LINUX_VERSION_CODE +# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig' +#endif +#define SEC(NAME) __attribute__((section(NAME), used)) + +#include <uapi/linux/fs.h> + +#define FMODE_READ 0x1 +#define FMODE_WRITE 0x2 + +static void (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) = + (void *) 6; + +SEC("func=null_lseek file->f_mode offset orig") +int bpf_func__null_lseek(void *ctx, int err, unsigned long f_mode, + unsigned long offset, unsigned long orig) +{ + if (err) + return 0; + if (f_mode & FMODE_WRITE) + return 0; + if (offset & 1) + return 0; + if (orig == SEEK_CUR) + return 0; + return 1; +} + +char _license[] SEC("license") = "GPL"; +int _version SEC("version") = LINUX_VERSION_CODE; diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index ec16f7812c8b..33689a0cf821 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -19,6 +19,29 @@ static int epoll_pwait_loop(void) return 0; } +#ifdef HAVE_BPF_PROLOGUE + +static int llseek_loop(void) +{ + int fds[2], i; + + fds[0] = open("/dev/null", O_RDONLY); + fds[1] = open("/dev/null", O_RDWR); + + if (fds[0] < 0 || fds[1] < 0) + return -1; + + for (i = 0; i < NR_ITERS; i++) { + lseek(fds[i % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET); + lseek(fds[(i + 1) % 2], i, (i / 2) % 2 ? SEEK_CUR : SEEK_SET); + } + close(fds[0]); + close(fds[1]); + return 0; +} + +#endif + static struct { enum test_llvm__testcase prog_id; const char *desc; @@ -37,6 +60,17 @@ static struct { &epoll_pwait_loop, (NR_ITERS + 1) / 2, }, +#ifdef HAVE_BPF_PROLOGUE + { + LLVM_TESTCASE_BPF_PROLOGUE, + "Test BPF prologue generation", + "[bpf_prologue_test]", + "fix kbuild first", + "check your vmlinux setting?", + &llseek_loop, + (NR_ITERS + 1) / 4, + }, +#endif }; static int do_test(struct bpf_object *obj, int (*func)(void), @@ -68,8 +102,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void), err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj); if (err || list_empty(&parse_evlist.list)) { pr_debug("Failed to add events selected by BPF\n"); - if (!err) - return TEST_FAIL; + return TEST_FAIL; } snprintf(pid, sizeof(pid), "%d", getpid()); @@ -123,8 +156,10 @@ static int do_test(struct bpf_object *obj, int (*func)(void), } } - if (count != expect) + if (count != expect) { pr_debug("BPF filter result incorrect\n"); + goto out_delete_evlist; + } ret = TEST_OK; @@ -146,7 +181,7 @@ prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name) return obj; } -static int __test__bpf(int index) +static int __test__bpf(int idx) { int ret; void *obj_buf; @@ -154,54 +189,72 @@ static int __test__bpf(int index) struct bpf_object *obj; ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - bpf_testcase_table[index].prog_id, + bpf_testcase_table[idx].prog_id, true); if (ret != TEST_OK || !obj_buf || !obj_buf_sz) { pr_debug("Unable to get BPF object, %s\n", - bpf_testcase_table[index].msg_compile_fail); - if (index == 0) + bpf_testcase_table[idx].msg_compile_fail); + if (idx == 0) return TEST_SKIP; else return TEST_FAIL; } obj = prepare_bpf(obj_buf, obj_buf_sz, - bpf_testcase_table[index].name); + bpf_testcase_table[idx].name); if (!obj) { ret = TEST_FAIL; goto out; } ret = do_test(obj, - bpf_testcase_table[index].target_func, - bpf_testcase_table[index].expect_result); + bpf_testcase_table[idx].target_func, + bpf_testcase_table[idx].expect_result); out: bpf__clear(); return ret; } -int test__bpf(void) +int test__bpf_subtest_get_nr(void) +{ + return (int)ARRAY_SIZE(bpf_testcase_table); +} + +const char *test__bpf_subtest_get_desc(int i) +{ + if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table)) + return NULL; + return bpf_testcase_table[i].desc; +} + +int test__bpf(int i) { - unsigned int i; int err; + if (i < 0 || i >= (int)ARRAY_SIZE(bpf_testcase_table)) + return TEST_FAIL; + if (geteuid() != 0) { pr_debug("Only root can run BPF test\n"); return TEST_SKIP; } - for (i = 0; i < ARRAY_SIZE(bpf_testcase_table); i++) { - err = __test__bpf(i); + err = __test__bpf(i); + return err; +} - if (err != TEST_OK) - return err; - } +#else +int test__bpf_subtest_get_nr(void) +{ + return 0; +} - return TEST_OK; +const char *test__bpf_subtest_get_desc(int i __maybe_unused) +{ + return NULL; } -#else -int test__bpf(void) +int test__bpf(int i __maybe_unused) { pr_debug("Skip BPF test because BPF support is not compiled\n"); return TEST_SKIP; diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 80c442eab767..f2b1dcac45d3 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -11,7 +11,7 @@ #include "tests.h" #include "debug.h" #include "color.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include "symbol.h" struct test __weak arch_tests[] = { @@ -160,6 +160,11 @@ static struct test generic_tests[] = { { .desc = "Test LLVM searching and compiling", .func = test__llvm, + .subtest = { + .skip_if_fail = true, + .get_nr = test__llvm_subtest_get_nr, + .get_desc = test__llvm_subtest_get_desc, + }, }, { .desc = "Test topology in session", @@ -168,6 +173,35 @@ static struct test generic_tests[] = { { .desc = "Test BPF filter", .func = test__bpf, + .subtest = { + .skip_if_fail = true, + .get_nr = test__bpf_subtest_get_nr, + .get_desc = test__bpf_subtest_get_desc, + }, + }, + { + .desc = "Test thread map synthesize", + .func = test__thread_map_synthesize, + }, + { + .desc = "Test cpu map synthesize", + .func = test__cpu_map_synthesize, + }, + { + .desc = "Test stat config synthesize", + .func = test__synthesize_stat_config, + }, + { + .desc = "Test stat synthesize", + .func = test__synthesize_stat, + }, + { + .desc = "Test stat round synthesize", + .func = test__synthesize_stat_round, + }, + { + .desc = "Test attr update synthesize", + .func = test__event_update, }, { .func = NULL, @@ -203,7 +237,7 @@ static bool perf_test__matches(struct test *test, int curr, int argc, const char return false; } -static int run_test(struct test *test) +static int run_test(struct test *test, int subtest) { int status, err = -1, child = fork(); char sbuf[STRERR_BUFSIZE]; @@ -216,7 +250,22 @@ static int run_test(struct test *test) if (!child) { pr_debug("test child forked, pid %d\n", getpid()); - err = test->func(); + if (!verbose) { + int nullfd = open("/dev/null", O_WRONLY); + if (nullfd >= 0) { + close(STDERR_FILENO); + close(STDOUT_FILENO); + + dup2(nullfd, STDOUT_FILENO); + dup2(STDOUT_FILENO, STDERR_FILENO); + close(nullfd); + } + } else { + signal(SIGSEGV, sighandler_dump_stack); + signal(SIGFPE, sighandler_dump_stack); + } + + err = test->func(subtest); exit(err); } @@ -237,6 +286,40 @@ static int run_test(struct test *test) for (j = 0; j < ARRAY_SIZE(tests); j++) \ for (t = &tests[j][0]; t->func; t++) +static int test_and_print(struct test *t, bool force_skip, int subtest) +{ + int err; + + if (!force_skip) { + pr_debug("\n--- start ---\n"); + err = run_test(t, subtest); + pr_debug("---- end ----\n"); + } else { + pr_debug("\n--- force skipped ---\n"); + err = TEST_SKIP; + } + + if (!t->subtest.get_nr) + pr_debug("%s:", t->desc); + else + pr_debug("%s subtest %d:", t->desc, subtest); + + switch (err) { + case TEST_OK: + pr_info(" Ok\n"); + break; + case TEST_SKIP: + color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); + break; + case TEST_FAIL: + default: + color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n"); + break; + } + + return err; +} + static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) { struct test *t; @@ -264,21 +347,43 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist) continue; } - pr_debug("\n--- start ---\n"); - err = run_test(t); - pr_debug("---- end ----\n%s:", t->desc); - - switch (err) { - case TEST_OK: - pr_info(" Ok\n"); - break; - case TEST_SKIP: - color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip\n"); - break; - case TEST_FAIL: - default: - color_fprintf(stderr, PERF_COLOR_RED, " FAILED!\n"); - break; + if (!t->subtest.get_nr) { + test_and_print(t, false, -1); + } else { + int subn = t->subtest.get_nr(); + /* + * minus 2 to align with normal testcases. + * For subtest we print additional '.x' in number. + * for example: + * + * 35: Test LLVM searching and compiling : + * 35.1: Basic BPF llvm compiling test : Ok + */ + int subw = width > 2 ? width - 2 : width; + bool skip = false; + int subi; + + if (subn <= 0) { + color_fprintf(stderr, PERF_COLOR_YELLOW, + " Skip (not compiled in)\n"); + continue; + } + pr_info("\n"); + + for (subi = 0; subi < subn; subi++) { + int len = strlen(t->subtest.get_desc(subi)); + + if (subw < len) + subw = len; + } + + for (subi = 0; subi < subn; subi++) { + pr_info("%2d.%1d: %-*s:", i, subi + 1, subw, + t->subtest.get_desc(subi)); + err = test_and_print(t, skip, subi); + if (err != TEST_OK && t->subtest.skip_if_fail) + skip = true; + } } } diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index a767a6400c5c..313a48c6b2bc 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -433,7 +433,6 @@ enum { static int do_test_code_reading(bool try_kcore) { - struct machines machines; struct machine *machine; struct thread *thread; struct record_opts opts = { @@ -459,8 +458,7 @@ static int do_test_code_reading(bool try_kcore) pid = getpid(); - machines__init(&machines); - machine = &machines.host; + machine = machine__new_host(); ret = machine__create_kernel_maps(machine); if (ret < 0) { @@ -549,6 +547,13 @@ static int do_test_code_reading(bool try_kcore) if (ret < 0) { if (!excl_kernel) { excl_kernel = true; + /* + * Both cpus and threads are now owned by evlist + * and will be freed by following perf_evlist__set_maps + * call. Getting refference to keep them alive. + */ + cpu_map__get(cpus); + thread_map__get(threads); perf_evlist__set_maps(evlist, NULL, NULL); perf_evlist__delete(evlist); evlist = NULL; @@ -594,14 +599,13 @@ out_err: cpu_map__put(cpus); thread_map__put(threads); } - machines__destroy_kernel_maps(&machines); machine__delete_threads(machine); - machines__exit(&machines); + machine__delete(machine); return err; } -int test__code_reading(void) +int test__code_reading(int subtest __maybe_unused) { int ret; diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c new file mode 100644 index 000000000000..4cb6418a8ffc --- /dev/null +++ b/tools/perf/tests/cpumap.c @@ -0,0 +1,88 @@ +#include "tests.h" +#include "cpumap.h" + +static int process_event_mask(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct cpu_map_event *map_event = &event->cpu_map; + struct cpu_map_mask *mask; + struct cpu_map_data *data; + struct cpu_map *map; + int i; + + data = &map_event->data; + + TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__MASK); + + mask = (struct cpu_map_mask *)data->data; + + TEST_ASSERT_VAL("wrong nr", mask->nr == 1); + + for (i = 0; i < 20; i++) { + TEST_ASSERT_VAL("wrong cpu", test_bit(i, mask->mask)); + } + + map = cpu_map__new_data(data); + TEST_ASSERT_VAL("wrong nr", map->nr == 20); + + for (i = 0; i < 20; i++) { + TEST_ASSERT_VAL("wrong cpu", map->map[i] == i); + } + + cpu_map__put(map); + return 0; +} + +static int process_event_cpus(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct cpu_map_event *map_event = &event->cpu_map; + struct cpu_map_entries *cpus; + struct cpu_map_data *data; + struct cpu_map *map; + + data = &map_event->data; + + TEST_ASSERT_VAL("wrong type", data->type == PERF_CPU_MAP__CPUS); + + cpus = (struct cpu_map_entries *)data->data; + + TEST_ASSERT_VAL("wrong nr", cpus->nr == 2); + TEST_ASSERT_VAL("wrong cpu", cpus->cpu[0] == 1); + TEST_ASSERT_VAL("wrong cpu", cpus->cpu[1] == 256); + + map = cpu_map__new_data(data); + TEST_ASSERT_VAL("wrong nr", map->nr == 2); + TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1); + TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256); + TEST_ASSERT_VAL("wrong refcnt", atomic_read(&map->refcnt) == 1); + cpu_map__put(map); + return 0; +} + + +int test__cpu_map_synthesize(int subtest __maybe_unused) +{ + struct cpu_map *cpus; + + /* This one is better stores in mask. */ + cpus = cpu_map__new("0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19"); + + TEST_ASSERT_VAL("failed to synthesize map", + !perf_event__synthesize_cpu_map(NULL, cpus, process_event_mask, NULL)); + + cpu_map__put(cpus); + + /* This one is better stores in cpu values. */ + cpus = cpu_map__new("1,256"); + + TEST_ASSERT_VAL("failed to synthesize map", + !perf_event__synthesize_cpu_map(NULL, cpus, process_event_cpus, NULL)); + + cpu_map__put(cpus); + return 0; +} diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c index a218aeaf56a0..dc673ff7c437 100644 --- a/tools/perf/tests/dso-data.c +++ b/tools/perf/tests/dso-data.c @@ -110,7 +110,7 @@ static int dso__data_fd(struct dso *dso, struct machine *machine) return fd; } -int test__dso_data(void) +int test__dso_data(int subtest __maybe_unused) { struct machine machine; struct dso *dso; @@ -245,7 +245,7 @@ static int set_fd_limit(int n) return setrlimit(RLIMIT_NOFILE, &rlim); } -int test__dso_data_cache(void) +int test__dso_data_cache(int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); @@ -302,7 +302,7 @@ int test__dso_data_cache(void) return 0; } -int test__dso_data_reopen(void) +int test__dso_data_reopen(int subtest __maybe_unused) { struct machine machine; long nr_end, nr = open_files_cnt(); diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 07221793a3ac..1c5c0221cea2 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -51,6 +51,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) "krava_1", "test__dwarf_unwind" }; + /* + * The funcs[MAX_STACK] array index, based on the + * callchain order setup. + */ + int idx = callchain_param.order == ORDER_CALLER ? + MAX_STACK - *cnt - 1 : *cnt; if (*cnt >= MAX_STACK) { pr_debug("failed: crossed the max stack value %d\n", MAX_STACK); @@ -63,8 +69,10 @@ static int unwind_entry(struct unwind_entry *entry, void *arg) return -1; } - pr_debug("got: %s 0x%" PRIx64 "\n", symbol, entry->ip); - return strcmp((const char *) symbol, funcs[(*cnt)++]); + (*cnt)++; + pr_debug("got: %s 0x%" PRIx64 ", expecting %s\n", + symbol, entry->ip, funcs[idx]); + return strcmp((const char *) symbol, funcs[idx]); } __attribute__ ((noinline)) @@ -105,8 +113,16 @@ static int compare(void *p1, void *p2) /* Any possible value should be 'thread' */ struct thread *thread = *(struct thread **)p1; - if (global_unwind_retval == -INT_MAX) + if (global_unwind_retval == -INT_MAX) { + /* Call unwinder twice for both callchain orders. */ + callchain_param.order = ORDER_CALLER; + global_unwind_retval = unwind_thread(thread); + if (!global_unwind_retval) { + callchain_param.order = ORDER_CALLEE; + global_unwind_retval = unwind_thread(thread); + } + } return p1 - p2; } @@ -142,21 +158,23 @@ static int krava_1(struct thread *thread) return krava_2(thread); } -int test__dwarf_unwind(void) +int test__dwarf_unwind(int subtest __maybe_unused) { - struct machines machines; struct machine *machine; struct thread *thread; int err = -1; - machines__init(&machines); - - machine = machines__find(&machines, HOST_KERNEL_ID); + machine = machine__new_host(); if (!machine) { pr_err("Could not get machine\n"); return -1; } + if (machine__create_kernel_maps(machine)) { + pr_err("Failed to create kernel maps\n"); + return -1; + } + callchain_param.record_mode = CALLCHAIN_DWARF; if (init_live_machine(machine)) { @@ -178,7 +196,6 @@ int test__dwarf_unwind(void) out: machine__delete_threads(machine); - machine__exit(machine); - machines__exit(&machines); + machine__delete(machine); return err; } diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c new file mode 100644 index 000000000000..012eab5d1df1 --- /dev/null +++ b/tools/perf/tests/event_update.c @@ -0,0 +1,117 @@ +#include <linux/compiler.h> +#include "evlist.h" +#include "evsel.h" +#include "machine.h" +#include "tests.h" +#include "debug.h" + +static int process_event_unit(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct event_update_event *ev = (struct event_update_event *) event; + + TEST_ASSERT_VAL("wrong id", ev->id == 123); + TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__UNIT); + TEST_ASSERT_VAL("wrong unit", !strcmp(ev->data, "KRAVA")); + return 0; +} + +static int process_event_scale(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct event_update_event *ev = (struct event_update_event *) event; + struct event_update_event_scale *ev_data; + + ev_data = (struct event_update_event_scale *) ev->data; + + TEST_ASSERT_VAL("wrong id", ev->id == 123); + TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__SCALE); + TEST_ASSERT_VAL("wrong scale", ev_data->scale = 0.123); + return 0; +} + +struct event_name { + struct perf_tool tool; + const char *name; +}; + +static int process_event_name(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct event_name *tmp = container_of(tool, struct event_name, tool); + struct event_update_event *ev = (struct event_update_event*) event; + + TEST_ASSERT_VAL("wrong id", ev->id == 123); + TEST_ASSERT_VAL("wrong id", ev->type == PERF_EVENT_UPDATE__NAME); + TEST_ASSERT_VAL("wrong name", !strcmp(ev->data, tmp->name)); + return 0; +} + +static int process_event_cpus(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct event_update_event *ev = (struct event_update_event*) event; + struct event_update_event_cpus *ev_data; + struct cpu_map *map; + + ev_data = (struct event_update_event_cpus*) ev->data; + + map = cpu_map__new_data(&ev_data->cpus); + + TEST_ASSERT_VAL("wrong id", ev->id == 123); + TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS); + TEST_ASSERT_VAL("wrong cpus", map->nr == 3); + TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1); + TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2); + TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3); + cpu_map__put(map); + return 0; +} + +int test__event_update(int subtest __maybe_unused) +{ + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct event_name tmp; + + evlist = perf_evlist__new_default(); + TEST_ASSERT_VAL("failed to get evlist", evlist); + + evsel = perf_evlist__first(evlist); + + TEST_ASSERT_VAL("failed to allos ids", + !perf_evsel__alloc_id(evsel, 1, 1)); + + perf_evlist__id_add(evlist, evsel, 0, 0, 123); + + evsel->unit = strdup("KRAVA"); + + TEST_ASSERT_VAL("failed to synthesize attr update unit", + !perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit)); + + evsel->scale = 0.123; + + TEST_ASSERT_VAL("failed to synthesize attr update scale", + !perf_event__synthesize_event_update_scale(NULL, evsel, process_event_scale)); + + tmp.name = perf_evsel__name(evsel); + + TEST_ASSERT_VAL("failed to synthesize attr update name", + !perf_event__synthesize_event_update_name(&tmp.tool, evsel, process_event_name)); + + evsel->own_cpus = cpu_map__new("1,2,3"); + + TEST_ASSERT_VAL("failed to synthesize attr update cpus", + !perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus)); + + cpu_map__put(evsel->own_cpus); + return 0; +} diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c index 3fa715987a5e..2de4a4f2c3ed 100644 --- a/tools/perf/tests/evsel-roundtrip-name.c +++ b/tools/perf/tests/evsel-roundtrip-name.c @@ -95,7 +95,7 @@ out_delete_evlist: #define perf_evsel__name_array_test(names) \ __perf_evsel__name_array_test(names, ARRAY_SIZE(names)) -int test__perf_evsel__roundtrip_name_test(void) +int test__perf_evsel__roundtrip_name_test(int subtest __maybe_unused) { int err = 0, ret = 0; @@ -103,7 +103,8 @@ int test__perf_evsel__roundtrip_name_test(void) if (err) ret = err; - err = perf_evsel__name_array_test(perf_evsel__sw_names); + err = __perf_evsel__name_array_test(perf_evsel__sw_names, + PERF_COUNT_SW_DUMMY + 1); if (err) ret = err; diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 790e413d9a1f..1984b3bbfe15 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -32,7 +32,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return ret; } -int test__perf_evsel__tp_sched_test(void) +int test__perf_evsel__tp_sched_test(int subtest __maybe_unused) { struct perf_evsel *evsel = perf_evsel__newtp("sched", "sched_switch"); int ret = 0; diff --git a/tools/perf/tests/fdarray.c b/tools/perf/tests/fdarray.c index d24b837951d4..c809463edbe5 100644 --- a/tools/perf/tests/fdarray.c +++ b/tools/perf/tests/fdarray.c @@ -25,7 +25,7 @@ static int fdarray__fprintf_prefix(struct fdarray *fda, const char *prefix, FILE return printed + fdarray__fprintf(fda, fp); } -int test__fdarray__filter(void) +int test__fdarray__filter(int subtest __maybe_unused) { int nr_fds, expected_fd[2], fd, err = TEST_FAIL; struct fdarray *fda = fdarray__new(5, 5); @@ -103,7 +103,7 @@ out: return err; } -int test__fdarray__add(void) +int test__fdarray__add(int subtest __maybe_unused) { int err = TEST_FAIL; struct fdarray *fda = fdarray__new(2, 2); diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c index ce80b274b097..bcfd081ee1d2 100644 --- a/tools/perf/tests/hists_common.c +++ b/tools/perf/tests/hists_common.c @@ -87,6 +87,11 @@ struct machine *setup_fake_machine(struct machines *machines) return NULL; } + if (machine__create_kernel_maps(machine)) { + pr_debug("Cannot create kernel maps\n"); + return NULL; + } + for (i = 0; i < ARRAY_SIZE(fake_threads); i++) { struct thread *thread; @@ -150,7 +155,6 @@ struct machine *setup_fake_machine(struct machines *machines) out: pr_debug("Not enough memory for machine setup\n"); machine__delete_threads(machine); - machine__delete(machine); return NULL; } diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 7ed737019de7..e36089212061 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -281,7 +281,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = false; perf_evsel__reset_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -428,7 +428,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = false; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -486,7 +486,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = true; perf_evsel__reset_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -670,7 +670,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = true; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -686,7 +686,7 @@ out: return err; } -int test__hists_cumulate(void) +int test__hists_cumulate(int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index 818acf875dd0..2a784befd9ce 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -104,7 +104,7 @@ out: return TEST_FAIL; } -int test__hists_filter(void) +int test__hists_filter(int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; @@ -122,7 +122,7 @@ int test__hists_filter(void) goto out; /* default sort order (comm,dso,sym) will be used */ - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) goto out; machines__init(&machines); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 8c102b011424..c764d69ac6ef 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) struct perf_evsel *evsel; struct addr_location al; struct hist_entry *he; - struct perf_sample sample = { .period = 1, }; + struct perf_sample sample = { .period = 1, .weight = 1, }; size_t i = 0, k; /* @@ -90,7 +90,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he = __hists__add_entry(hists, &al, NULL, - NULL, NULL, 1, 1, 0, true); + NULL, NULL, &sample, true); if (he == NULL) { addr_location__put(&al); goto out; @@ -116,7 +116,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he = __hists__add_entry(hists, &al, NULL, - NULL, NULL, 1, 1, 0, true); + NULL, NULL, &sample, true); if (he == NULL) { addr_location__put(&al); goto out; @@ -274,7 +274,7 @@ static int validate_link(struct hists *leader, struct hists *other) return __validate_link(leader, 0) || __validate_link(other, 1); } -int test__hists_link(void) +int test__hists_link(int subtest __maybe_unused) { int err = -1; struct hists *hists, *first_hists; @@ -294,7 +294,7 @@ int test__hists_link(void) goto out; /* default sort order (comm,dso,sym) will be used */ - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) goto out; machines__init(&machines); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index adbebc852cc8..ebe6cd485b5d 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -134,7 +134,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) field_order = NULL; sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */ - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -236,7 +236,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) field_order = "overhead,cpu"; sort_order = "pid"; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -292,7 +292,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) field_order = "comm,overhead,dso"; sort_order = NULL; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -366,7 +366,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) field_order = "dso,sym,comm,overhead,dso"; sort_order = "sym"; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -468,7 +468,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) field_order = "cpu,pid,comm,dso,sym"; sort_order = "dso,pid"; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -576,7 +576,7 @@ out: return err; } -int test__hists_output(void) +int test__hists_output(int subtest __maybe_unused) { int err = TEST_FAIL; struct machines machines; diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index a2e2269aa093..ddb78fae064a 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -49,13 +49,12 @@ static int find_comm(struct perf_evlist *evlist, const char *comm) * when an event is disabled but a dummy software event is not disabled. If the * test passes %0 is returned, otherwise %-1 is returned. */ -int test__keep_tracking(void) +int test__keep_tracking(int subtest __maybe_unused) { struct record_opts opts = { .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, - .freq = 4000, .target = { .uses_mmap = true, }, @@ -124,7 +123,7 @@ int test__keep_tracking(void) evsel = perf_evlist__last(evlist); - CHECK__(perf_evlist__disable_event(evlist, evsel)); + CHECK__(perf_evsel__disable(evsel)); comm = "Test COMM 2"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0)); diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c index 08c433b4bf4f..d2af78193153 100644 --- a/tools/perf/tests/kmod-path.c +++ b/tools/perf/tests/kmod-path.c @@ -49,7 +49,7 @@ static int test_is_kernel_module(const char *path, int cpumode, bool expect) #define M(path, c, e) \ TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e)) -int test__kmod_path__parse(void) +int test__kmod_path__parse(int subtest __maybe_unused) { /* path alloc_name alloc_ext kmod comp name ext */ T("/xxxx/xxxx/x-x.ko", true , true , true, false, "[x_x]", NULL); diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c index bc4cf507cde5..06f45c1d4256 100644 --- a/tools/perf/tests/llvm.c +++ b/tools/perf/tests/llvm.c @@ -44,13 +44,17 @@ static struct { .source = test_llvm__bpf_test_kbuild_prog, .desc = "Test kbuild searching", }, + [LLVM_TESTCASE_BPF_PROLOGUE] = { + .source = test_llvm__bpf_test_prologue_prog, + .desc = "Compile source for BPF prologue generation test", + }, }; int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz, - enum test_llvm__testcase index, + enum test_llvm__testcase idx, bool force) { const char *source; @@ -59,11 +63,11 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf, char *tmpl_new = NULL, *clang_opt_new = NULL; int err, old_verbose, ret = TEST_FAIL; - if (index >= __LLVM_TESTCASE_MAX) + if (idx >= __LLVM_TESTCASE_MAX) return TEST_FAIL; - source = bpf_source_table[index].source; - desc = bpf_source_table[index].desc; + source = bpf_source_table[idx].source; + desc = bpf_source_table[idx].desc; perf_config(perf_config_cb, NULL); @@ -127,44 +131,39 @@ out: return ret; } -int test__llvm(void) +int test__llvm(int subtest) { - enum test_llvm__testcase i; + int ret; + void *obj_buf = NULL; + size_t obj_buf_sz = 0; - for (i = 0; i < __LLVM_TESTCASE_MAX; i++) { - int ret; - void *obj_buf = NULL; - size_t obj_buf_sz = 0; + if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) + return TEST_FAIL; - ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, - i, false); + ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz, + subtest, false); - if (ret == TEST_OK) { - ret = test__bpf_parsing(obj_buf, obj_buf_sz); - if (ret != TEST_OK) - pr_debug("Failed to parse test case '%s'\n", - bpf_source_table[i].desc); - } - free(obj_buf); - - switch (ret) { - case TEST_SKIP: - return TEST_SKIP; - case TEST_OK: - break; - default: - /* - * Test 0 is the basic LLVM test. If test 0 - * fail, the basic LLVM support not functional - * so the whole test should fail. If other test - * case fail, it can be fixed by adjusting - * config so don't report error. - */ - if (i == 0) - return TEST_FAIL; - else - return TEST_SKIP; + if (ret == TEST_OK) { + ret = test__bpf_parsing(obj_buf, obj_buf_sz); + if (ret != TEST_OK) { + pr_debug("Failed to parse test case '%s'\n", + bpf_source_table[subtest].desc); } } - return TEST_OK; + free(obj_buf); + + return ret; +} + +int test__llvm_subtest_get_nr(void) +{ + return __LLVM_TESTCASE_MAX; +} + +const char *test__llvm_subtest_get_desc(int subtest) +{ + if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX)) + return NULL; + + return bpf_source_table[subtest].desc; } diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h index d91d8f44efee..5150b4d6ef50 100644 --- a/tools/perf/tests/llvm.h +++ b/tools/perf/tests/llvm.h @@ -6,10 +6,12 @@ extern const char test_llvm__bpf_base_prog[]; extern const char test_llvm__bpf_test_kbuild_prog[]; +extern const char test_llvm__bpf_test_prologue_prog[]; enum test_llvm__testcase { LLVM_TESTCASE_BASE, LLVM_TESTCASE_KBUILD, + LLVM_TESTCASE_BPF_PROLOGUE, __LLVM_TESTCASE_MAX, }; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 8ea3dffc5065..c1fbb8e884c0 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -259,7 +259,8 @@ $(run_O): tarpkg: @cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \ echo "- $@: $$cmd" && echo $$cmd > $@ && \ - ( eval $$cmd ) >> $@ 2>&1 + ( eval $$cmd ) >> $@ 2>&1 && \ + rm -f $@ make_kernelsrc: @echo "- make -C <kernelsrc> tools/perf" diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c index 4495493c9431..359e98fcd94c 100644 --- a/tools/perf/tests/mmap-basic.c +++ b/tools/perf/tests/mmap-basic.c @@ -16,7 +16,7 @@ * Then it checks if the number of syscalls reported as perf events by * the kernel corresponds to the number of syscalls made. */ -int test__basic_mmap(void) +int test__basic_mmap(int subtest __maybe_unused) { int err = -1; union perf_event *event; diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c index 145050e2e544..0c5ce44f723f 100644 --- a/tools/perf/tests/mmap-thread-lookup.c +++ b/tools/perf/tests/mmap-thread-lookup.c @@ -149,7 +149,6 @@ static int synth_process(struct machine *machine) static int mmap_events(synth_cb synth) { - struct machines machines; struct machine *machine; int err, i; @@ -162,8 +161,7 @@ static int mmap_events(synth_cb synth) */ TEST_ASSERT_VAL("failed to create threads", !threads_create()); - machines__init(&machines); - machine = &machines.host; + machine = machine__new_host(); dump_trace = verbose > 1 ? 1 : 0; @@ -203,7 +201,7 @@ static int mmap_events(synth_cb synth) } machine__delete_threads(machine); - machines__exit(&machines); + machine__delete(machine); return err; } @@ -221,7 +219,7 @@ static int mmap_events(synth_cb synth) * * by using all thread objects. */ -int test__mmap_thread_lookup(void) +int test__mmap_thread_lookup(int subtest __maybe_unused) { /* perf_event__synthesize_threads synthesize */ TEST_ASSERT_VAL("failed with sythesizing all", diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index 2006485a2859..53c2273e8859 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -7,7 +7,7 @@ #include "debug.h" #include "stat.h" -int test__openat_syscall_event_on_all_cpus(void) +int test__openat_syscall_event_on_all_cpus(int subtest __maybe_unused) { int err = -1, fd, cpu; struct cpu_map *cpus; diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c index 5e811cd8f1c3..eb99a105f31c 100644 --- a/tools/perf/tests/openat-syscall-tp-fields.c +++ b/tools/perf/tests/openat-syscall-tp-fields.c @@ -6,7 +6,7 @@ #include "tests.h" #include "debug.h" -int test__syscall_openat_tp_fields(void) +int test__syscall_openat_tp_fields(int subtest __maybe_unused) { struct record_opts opts = { .target = { diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index 033b54797b8a..1184f9ba6499 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -5,7 +5,7 @@ #include "debug.h" #include "tests.h" -int test__openat_syscall_event(void) +int test__openat_syscall_event(int subtest __maybe_unused) { int err = -1, fd; struct perf_evsel *evsel; diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index 636d7b42d844..abe8849d1d70 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -1765,7 +1765,7 @@ static void debug_warn(const char *warn, va_list params) fprintf(stderr, " Warning: %s\n", msg); } -int test__parse_events(void) +int test__parse_events(int subtest __maybe_unused) { int ret1, ret2 = 0; diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c index 2c63ea658541..294c76b01b41 100644 --- a/tools/perf/tests/parse-no-sample-id-all.c +++ b/tools/perf/tests/parse-no-sample-id-all.c @@ -67,7 +67,7 @@ struct test_attr_event { * * Return: %0 on success, %-1 if the test fails. */ -int test__parse_no_sample_id_all(void) +int test__parse_no_sample_id_all(int subtest __maybe_unused) { int err; diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 7a228a2a070b..1cc78cefe399 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -32,7 +32,7 @@ realloc: return cpu; } -int test__PERF_RECORD(void) +int test__PERF_RECORD(int subtest __maybe_unused) { struct record_opts opts = { .target = { @@ -40,12 +40,11 @@ int test__PERF_RECORD(void) .uses_mmap = true, }, .no_buffering = true, - .freq = 10, .mmap_pages = 256, }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct perf_evlist *evlist = perf_evlist__new_default(); + struct perf_evlist *evlist = perf_evlist__new_dummy(); struct perf_evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; @@ -61,6 +60,9 @@ int test__PERF_RECORD(void) int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, }; char sbuf[STRERR_BUFSIZE]; + if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ + evlist = perf_evlist__new_default(); + if (evlist == NULL || argv == NULL) { pr_debug("Not enough memory to create evlist\n"); goto out; diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index faa04e9d5d5f..1e2ba2602930 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -133,7 +133,7 @@ static struct list_head *test_terms_list(void) return &terms; } -int test__pmu(void) +int test__pmu(int subtest __maybe_unused) { char *format = test_format_dir_get(); LIST_HEAD(formats); diff --git a/tools/perf/tests/python-use.c b/tools/perf/tests/python-use.c index 7760277c6def..7a52834ee0d0 100644 --- a/tools/perf/tests/python-use.c +++ b/tools/perf/tests/python-use.c @@ -4,11 +4,12 @@ #include <stdio.h> #include <stdlib.h> +#include <linux/compiler.h> #include "tests.h" extern int verbose; -int test__python_use(void) +int test__python_use(int subtest __maybe_unused) { char *cmd; int ret; diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c index 30c02181e78b..5f23710b9fee 100644 --- a/tools/perf/tests/sample-parsing.c +++ b/tools/perf/tests/sample-parsing.c @@ -290,7 +290,7 @@ out_free: * checks sample format bits separately and together. If the test passes %0 is * returned, otherwise %-1 is returned. */ -int test__sample_parsing(void) +int test__sample_parsing(int subtest __maybe_unused) { const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15}; u64 sample_type; diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c new file mode 100644 index 000000000000..6a20ff2326bb --- /dev/null +++ b/tools/perf/tests/stat.c @@ -0,0 +1,111 @@ +#include <linux/compiler.h> +#include "event.h" +#include "tests.h" +#include "stat.h" +#include "counts.h" +#include "debug.h" + +static bool has_term(struct stat_config_event *config, + u64 tag, u64 val) +{ + unsigned i; + + for (i = 0; i < config->nr; i++) { + if ((config->data[i].tag == tag) && + (config->data[i].val == val)) + return true; + } + + return false; +} + +static int process_stat_config_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct stat_config_event *config = &event->stat_config; + struct perf_stat_config stat_config; + +#define HAS(term, val) \ + has_term(config, PERF_STAT_CONFIG_TERM__##term, val) + + TEST_ASSERT_VAL("wrong nr", config->nr == PERF_STAT_CONFIG_TERM__MAX); + TEST_ASSERT_VAL("wrong aggr_mode", HAS(AGGR_MODE, AGGR_CORE)); + TEST_ASSERT_VAL("wrong scale", HAS(SCALE, 1)); + TEST_ASSERT_VAL("wrong interval", HAS(INTERVAL, 1)); + +#undef HAS + + perf_event__read_stat_config(&stat_config, config); + + TEST_ASSERT_VAL("wrong aggr_mode", stat_config.aggr_mode == AGGR_CORE); + TEST_ASSERT_VAL("wrong scale", stat_config.scale == 1); + TEST_ASSERT_VAL("wrong interval", stat_config.interval == 1); + return 0; +} + +int test__synthesize_stat_config(int subtest __maybe_unused) +{ + struct perf_stat_config stat_config = { + .aggr_mode = AGGR_CORE, + .scale = 1, + .interval = 1, + }; + + TEST_ASSERT_VAL("failed to synthesize stat_config", + !perf_event__synthesize_stat_config(NULL, &stat_config, process_stat_config_event, NULL)); + + return 0; +} + +static int process_stat_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct stat_event *st = &event->stat; + + TEST_ASSERT_VAL("wrong cpu", st->cpu == 1); + TEST_ASSERT_VAL("wrong thread", st->thread == 2); + TEST_ASSERT_VAL("wrong id", st->id == 3); + TEST_ASSERT_VAL("wrong val", st->val == 100); + TEST_ASSERT_VAL("wrong run", st->ena == 200); + TEST_ASSERT_VAL("wrong ena", st->run == 300); + return 0; +} + +int test__synthesize_stat(int subtest __maybe_unused) +{ + struct perf_counts_values count; + + count.val = 100; + count.ena = 200; + count.run = 300; + + TEST_ASSERT_VAL("failed to synthesize stat_config", + !perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL)); + + return 0; +} + +static int process_stat_round_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct stat_round_event *stat_round = &event->stat_round; + + TEST_ASSERT_VAL("wrong time", stat_round->time == 0xdeadbeef); + TEST_ASSERT_VAL("wrong type", stat_round->type == PERF_STAT_ROUND_TYPE__INTERVAL); + return 0; +} + +int test__synthesize_stat_round(int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("failed to synthesize stat_config", + !perf_event__synthesize_stat_round(NULL, 0xdeadbeef, PERF_STAT_ROUND_TYPE__INTERVAL, + process_stat_round_event, NULL)); + + return 0; +} diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c index 5b83f56a3b6f..36e8ce1550e3 100644 --- a/tools/perf/tests/sw-clock.c +++ b/tools/perf/tests/sw-clock.c @@ -122,7 +122,7 @@ out_delete_evlist: return err; } -int test__sw_clock_freq(void) +int test__sw_clock_freq(int subtest __maybe_unused) { int ret; diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index a02af503100c..ebd80168d51e 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -305,7 +305,7 @@ out_free_nodes: * evsel->system_wide and evsel->tracking flags (respectively) with other events * sometimes enabled or disabled. */ -int test__switch_tracking(void) +int test__switch_tracking(int subtest __maybe_unused) { const char *sched_switch = "sched:sched_switch"; struct switch_tracking switch_tracking = { .tids = NULL, }; @@ -455,7 +455,7 @@ int test__switch_tracking(void) perf_evlist__enable(evlist); - err = perf_evlist__disable_event(evlist, cpu_clocks_evsel); + err = perf_evsel__disable(cpu_clocks_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -474,7 +474,7 @@ int test__switch_tracking(void) goto out_err; } - err = perf_evlist__disable_event(evlist, cycles_evsel); + err = perf_evsel__disable(cycles_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -500,7 +500,7 @@ int test__switch_tracking(void) goto out_err; } - err = perf_evlist__enable_event(evlist, cycles_evsel); + err = perf_evsel__enable(cycles_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index add16385f13e..2dfff7ac8ef3 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -31,7 +31,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused, * if the number of exit event reported by the kernel is 1 or not * in order to check the kernel returns correct number of event. */ -int test__task_exit(void) +int test__task_exit(int subtest __maybe_unused) { int err = -1; union perf_event *event; diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index 3c8734a3abbc..82b2b5e6ba7c 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -1,6 +1,8 @@ #ifndef TESTS_H #define TESTS_H +#include <stdbool.h> + #define TEST_ASSERT_VAL(text, cond) \ do { \ if (!(cond)) { \ @@ -26,48 +28,63 @@ enum { struct test { const char *desc; - int (*func)(void); + int (*func)(int subtest); + struct { + bool skip_if_fail; + int (*get_nr)(void); + const char *(*get_desc)(int subtest); + } subtest; }; /* Tests */ -int test__vmlinux_matches_kallsyms(void); -int test__openat_syscall_event(void); -int test__openat_syscall_event_on_all_cpus(void); -int test__basic_mmap(void); -int test__PERF_RECORD(void); -int test__perf_evsel__roundtrip_name_test(void); -int test__perf_evsel__tp_sched_test(void); -int test__syscall_openat_tp_fields(void); -int test__pmu(void); -int test__attr(void); -int test__dso_data(void); -int test__dso_data_cache(void); -int test__dso_data_reopen(void); -int test__parse_events(void); -int test__hists_link(void); -int test__python_use(void); -int test__bp_signal(void); -int test__bp_signal_overflow(void); -int test__task_exit(void); -int test__sw_clock_freq(void); -int test__code_reading(void); -int test__sample_parsing(void); -int test__keep_tracking(void); -int test__parse_no_sample_id_all(void); -int test__dwarf_unwind(void); -int test__hists_filter(void); -int test__mmap_thread_lookup(void); -int test__thread_mg_share(void); -int test__hists_output(void); -int test__hists_cumulate(void); -int test__switch_tracking(void); -int test__fdarray__filter(void); -int test__fdarray__add(void); -int test__kmod_path__parse(void); -int test__thread_map(void); -int test__llvm(void); -int test__bpf(void); -int test_session_topology(void); +int test__vmlinux_matches_kallsyms(int subtest); +int test__openat_syscall_event(int subtest); +int test__openat_syscall_event_on_all_cpus(int subtest); +int test__basic_mmap(int subtest); +int test__PERF_RECORD(int subtest); +int test__perf_evsel__roundtrip_name_test(int subtest); +int test__perf_evsel__tp_sched_test(int subtest); +int test__syscall_openat_tp_fields(int subtest); +int test__pmu(int subtest); +int test__attr(int subtest); +int test__dso_data(int subtest); +int test__dso_data_cache(int subtest); +int test__dso_data_reopen(int subtest); +int test__parse_events(int subtest); +int test__hists_link(int subtest); +int test__python_use(int subtest); +int test__bp_signal(int subtest); +int test__bp_signal_overflow(int subtest); +int test__task_exit(int subtest); +int test__sw_clock_freq(int subtest); +int test__code_reading(int subtest); +int test__sample_parsing(int subtest); +int test__keep_tracking(int subtest); +int test__parse_no_sample_id_all(int subtest); +int test__dwarf_unwind(int subtest); +int test__hists_filter(int subtest); +int test__mmap_thread_lookup(int subtest); +int test__thread_mg_share(int subtest); +int test__hists_output(int subtest); +int test__hists_cumulate(int subtest); +int test__switch_tracking(int subtest); +int test__fdarray__filter(int subtest); +int test__fdarray__add(int subtest); +int test__kmod_path__parse(int subtest); +int test__thread_map(int subtest); +int test__llvm(int subtest); +const char *test__llvm_subtest_get_desc(int subtest); +int test__llvm_subtest_get_nr(void); +int test__bpf(int subtest); +const char *test__bpf_subtest_get_desc(int subtest); +int test__bpf_subtest_get_nr(void); +int test_session_topology(int subtest); +int test__thread_map_synthesize(int subtest); +int test__cpu_map_synthesize(int subtest); +int test__synthesize_stat_config(int subtest); +int test__synthesize_stat(int subtest); +int test__synthesize_stat_round(int subtest); +int test__event_update(int subtest); #if defined(__arm__) || defined(__aarch64__) #ifdef HAVE_DWARF_UNWIND_SUPPORT diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c index 138a0e3431fa..fccde848fe9c 100644 --- a/tools/perf/tests/thread-map.c +++ b/tools/perf/tests/thread-map.c @@ -4,7 +4,7 @@ #include "thread_map.h" #include "debug.h" -int test__thread_map(void) +int test__thread_map(int subtest __maybe_unused) { struct thread_map *map; @@ -40,3 +40,46 @@ int test__thread_map(void) thread_map__put(map); return 0; } + +static int process_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_sample *sample __maybe_unused, + struct machine *machine __maybe_unused) +{ + struct thread_map_event *map = &event->thread_map; + struct thread_map *threads; + + TEST_ASSERT_VAL("wrong nr", map->nr == 1); + TEST_ASSERT_VAL("wrong pid", map->entries[0].pid == (u64) getpid()); + TEST_ASSERT_VAL("wrong comm", !strcmp(map->entries[0].comm, "perf")); + + threads = thread_map__new_event(&event->thread_map); + TEST_ASSERT_VAL("failed to alloc map", threads); + + TEST_ASSERT_VAL("wrong nr", threads->nr == 1); + TEST_ASSERT_VAL("wrong pid", + thread_map__pid(threads, 0) == getpid()); + TEST_ASSERT_VAL("wrong comm", + thread_map__comm(threads, 0) && + !strcmp(thread_map__comm(threads, 0), "perf")); + TEST_ASSERT_VAL("wrong refcnt", + atomic_read(&threads->refcnt) == 1); + thread_map__put(threads); + return 0; +} + +int test__thread_map_synthesize(int subtest __maybe_unused) +{ + struct thread_map *threads; + + /* test map on current pid */ + threads = thread_map__new_by_pid(getpid()); + TEST_ASSERT_VAL("failed to alloc map", threads); + + thread_map__read_comms(threads); + + TEST_ASSERT_VAL("failed to synthesize map", + !perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL)); + + return 0; +} diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c index 01fabb19d746..188b63140fc8 100644 --- a/tools/perf/tests/thread-mg-share.c +++ b/tools/perf/tests/thread-mg-share.c @@ -4,7 +4,7 @@ #include "map.h" #include "debug.h" -int test__thread_mg_share(void) +int test__thread_mg_share(int subtest __maybe_unused) { struct machines machines; struct machine *machine; diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c index f5bb096c3bd9..98fe69ac553c 100644 --- a/tools/perf/tests/topology.c +++ b/tools/perf/tests/topology.c @@ -84,7 +84,7 @@ static int check_cpu_topology(char *path, struct cpu_map *map) return 0; } -int test_session_topology(void) +int test_session_topology(int subtest __maybe_unused) { char path[PATH_MAX]; struct cpu_map *map; diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c index d677e018e504..f0bfc9e8fd9f 100644 --- a/tools/perf/tests/vmlinux-kallsyms.c +++ b/tools/perf/tests/vmlinux-kallsyms.c @@ -18,7 +18,7 @@ static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused, #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x)) -int test__vmlinux_matches_kallsyms(void) +int test__vmlinux_matches_kallsyms(int subtest __maybe_unused) { int err = -1; struct rb_node *nd; diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c index e9703c0829f1..d37202121689 100644 --- a/tools/perf/ui/browser.c +++ b/tools/perf/ui/browser.c @@ -528,7 +528,7 @@ static struct ui_browser_colorset { .colorset = HE_COLORSET_SELECTED, .name = "selected", .fg = "black", - .bg = "lightgray", + .bg = "yellow", }, { .colorset = HE_COLORSET_CODE, diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index fa9eb92c9e24..901d481e6cea 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -178,12 +178,51 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node) return n; } +static int callchain_node__count_flat_rows(struct callchain_node *node) +{ + struct callchain_list *chain; + char folded_sign = 0; + int n = 0; + + list_for_each_entry(chain, &node->parent_val, list) { + if (!folded_sign) { + /* only check first chain list entry */ + folded_sign = callchain_list__folded(chain); + if (folded_sign == '+') + return 1; + } + n++; + } + + list_for_each_entry(chain, &node->val, list) { + if (!folded_sign) { + /* node->parent_val list might be empty */ + folded_sign = callchain_list__folded(chain); + if (folded_sign == '+') + return 1; + } + n++; + } + + return n; +} + +static int callchain_node__count_folded_rows(struct callchain_node *node __maybe_unused) +{ + return 1; +} + static int callchain_node__count_rows(struct callchain_node *node) { struct callchain_list *chain; bool unfolded = false; int n = 0; + if (callchain_param.mode == CHAIN_FLAT) + return callchain_node__count_flat_rows(node); + else if (callchain_param.mode == CHAIN_FOLDED) + return callchain_node__count_folded_rows(node); + list_for_each_entry(chain, &node->val, list) { ++n; unfolded = chain->unfolded; @@ -263,7 +302,7 @@ static void callchain_node__init_have_children(struct callchain_node *node, chain = list_entry(node->val.next, struct callchain_list, list); chain->has_children = has_sibling; - if (!list_empty(&node->val)) { + if (node->val.next != node->val.prev) { chain = list_entry(node->val.prev, struct callchain_list, list); chain->has_children = !RB_EMPTY_ROOT(&node->rb_root); } @@ -279,6 +318,9 @@ static void callchain__init_have_children(struct rb_root *root) for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node); callchain_node__init_have_children(node, has_sibling); + if (callchain_param.mode == CHAIN_FLAT || + callchain_param.mode == CHAIN_FOLDED) + callchain_node__make_parent_list(node); } } @@ -298,6 +340,9 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser) struct callchain_list *cl = container_of(ms, struct callchain_list, ms); bool has_children; + if (!he || !ms) + return false; + if (ms == &he->ms) has_children = hist_entry__toggle_fold(he); else @@ -574,6 +619,231 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u #define LEVEL_OFFSET_STEP 3 +static int hist_browser__show_callchain_list(struct hist_browser *browser, + struct callchain_node *node, + struct callchain_list *chain, + unsigned short row, u64 total, + bool need_percent, int offset, + print_callchain_entry_fn print, + struct callchain_print_arg *arg) +{ + char bf[1024], *alloc_str; + const char *str; + + if (arg->row_offset != 0) { + arg->row_offset--; + return 0; + } + + alloc_str = NULL; + str = callchain_list__sym_name(chain, bf, sizeof(bf), + browser->show_dso); + + if (need_percent) { + char buf[64]; + + callchain_node__scnprintf_value(node, buf, sizeof(buf), + total); + + if (asprintf(&alloc_str, "%s %s", buf, str) < 0) + str = "Not enough memory!"; + else + str = alloc_str; + } + + print(browser, chain, str, offset, row, arg); + + free(alloc_str); + return 1; +} + +static int hist_browser__show_callchain_flat(struct hist_browser *browser, + struct rb_root *root, + unsigned short row, u64 total, + print_callchain_entry_fn print, + struct callchain_print_arg *arg, + check_output_full_fn is_output_full) +{ + struct rb_node *node; + int first_row = row, offset = LEVEL_OFFSET_STEP; + bool need_percent; + + node = rb_first(root); + need_percent = node && rb_next(node); + + while (node) { + struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); + struct rb_node *next = rb_next(node); + struct callchain_list *chain; + char folded_sign = ' '; + int first = true; + int extra_offset = 0; + + list_for_each_entry(chain, &child->parent_val, list) { + bool was_first = first; + + if (first) + first = false; + else if (need_percent) + extra_offset = LEVEL_OFFSET_STEP; + + folded_sign = callchain_list__folded(chain); + + row += hist_browser__show_callchain_list(browser, child, + chain, row, total, + was_first && need_percent, + offset + extra_offset, + print, arg); + + if (is_output_full(browser, row)) + goto out; + + if (folded_sign == '+') + goto next; + } + + list_for_each_entry(chain, &child->val, list) { + bool was_first = first; + + if (first) + first = false; + else if (need_percent) + extra_offset = LEVEL_OFFSET_STEP; + + folded_sign = callchain_list__folded(chain); + + row += hist_browser__show_callchain_list(browser, child, + chain, row, total, + was_first && need_percent, + offset + extra_offset, + print, arg); + + if (is_output_full(browser, row)) + goto out; + + if (folded_sign == '+') + break; + } + +next: + if (is_output_full(browser, row)) + break; + node = next; + } +out: + return row - first_row; +} + +static char *hist_browser__folded_callchain_str(struct hist_browser *browser, + struct callchain_list *chain, + char *value_str, char *old_str) +{ + char bf[1024]; + const char *str; + char *new; + + str = callchain_list__sym_name(chain, bf, sizeof(bf), + browser->show_dso); + if (old_str) { + if (asprintf(&new, "%s%s%s", old_str, + symbol_conf.field_sep ?: ";", str) < 0) + new = NULL; + } else { + if (value_str) { + if (asprintf(&new, "%s %s", value_str, str) < 0) + new = NULL; + } else { + if (asprintf(&new, "%s", str) < 0) + new = NULL; + } + } + return new; +} + +static int hist_browser__show_callchain_folded(struct hist_browser *browser, + struct rb_root *root, + unsigned short row, u64 total, + print_callchain_entry_fn print, + struct callchain_print_arg *arg, + check_output_full_fn is_output_full) +{ + struct rb_node *node; + int first_row = row, offset = LEVEL_OFFSET_STEP; + bool need_percent; + + node = rb_first(root); + need_percent = node && rb_next(node); + + while (node) { + struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); + struct rb_node *next = rb_next(node); + struct callchain_list *chain, *first_chain = NULL; + int first = true; + char *value_str = NULL, *value_str_alloc = NULL; + char *chain_str = NULL, *chain_str_alloc = NULL; + + if (arg->row_offset != 0) { + arg->row_offset--; + goto next; + } + + if (need_percent) { + char buf[64]; + + callchain_node__scnprintf_value(child, buf, sizeof(buf), total); + if (asprintf(&value_str, "%s", buf) < 0) { + value_str = (char *)"<...>"; + goto do_print; + } + value_str_alloc = value_str; + } + + list_for_each_entry(chain, &child->parent_val, list) { + chain_str = hist_browser__folded_callchain_str(browser, + chain, value_str, chain_str); + if (first) { + first = false; + first_chain = chain; + } + + if (chain_str == NULL) { + chain_str = (char *)"Not enough memory!"; + goto do_print; + } + + chain_str_alloc = chain_str; + } + + list_for_each_entry(chain, &child->val, list) { + chain_str = hist_browser__folded_callchain_str(browser, + chain, value_str, chain_str); + if (first) { + first = false; + first_chain = chain; + } + + if (chain_str == NULL) { + chain_str = (char *)"Not enough memory!"; + goto do_print; + } + + chain_str_alloc = chain_str; + } + +do_print: + print(browser, first_chain, chain_str, offset, row++, arg); + free(value_str_alloc); + free(chain_str_alloc); + +next: + if (is_output_full(browser, row)) + break; + node = next; + } + + return row - first_row; +} + static int hist_browser__show_callchain(struct hist_browser *browser, struct rb_root *root, int level, unsigned short row, u64 total, @@ -592,15 +862,12 @@ static int hist_browser__show_callchain(struct hist_browser *browser, while (node) { struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node); struct rb_node *next = rb_next(node); - u64 cumul = callchain_cumul_hits(child); struct callchain_list *chain; char folded_sign = ' '; int first = true; int extra_offset = 0; list_for_each_entry(chain, &child->val, list) { - char bf[1024], *alloc_str; - const char *str; bool was_first = first; if (first) @@ -609,31 +876,16 @@ static int hist_browser__show_callchain(struct hist_browser *browser, extra_offset = LEVEL_OFFSET_STEP; folded_sign = callchain_list__folded(chain); - if (arg->row_offset != 0) { - arg->row_offset--; - goto do_next; - } - - alloc_str = NULL; - str = callchain_list__sym_name(chain, bf, sizeof(bf), - browser->show_dso); - - if (was_first && need_percent) { - double percent = cumul * 100.0 / total; - if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0) - str = "Not enough memory!"; - else - str = alloc_str; - } - - print(browser, chain, str, offset + extra_offset, row, arg); + row += hist_browser__show_callchain_list(browser, child, + chain, row, total, + was_first && need_percent, + offset + extra_offset, + print, arg); - free(alloc_str); - - if (is_output_full(browser, ++row)) + if (is_output_full(browser, row)) goto out; -do_next: + if (folded_sign == '+') break; } @@ -789,7 +1041,8 @@ static int hist_browser__show_entry(struct hist_browser *browser, hist_browser__gotorc(browser, row, 0); perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll) + if (perf_hpp__should_skip(fmt, entry->hists) || + column++ < browser->b.horiz_scroll) continue; if (current_entry && browser->b.navkeypressed) { @@ -844,10 +1097,22 @@ static int hist_browser__show_entry(struct hist_browser *browser, total = entry->stat.period; } - printed += hist_browser__show_callchain(browser, + if (callchain_param.mode == CHAIN_FLAT) { + printed += hist_browser__show_callchain_flat(browser, + &entry->sorted_chain, row, total, + hist_browser__show_callchain_entry, &arg, + hist_browser__check_output_full); + } else if (callchain_param.mode == CHAIN_FOLDED) { + printed += hist_browser__show_callchain_folded(browser, + &entry->sorted_chain, row, total, + hist_browser__show_callchain_entry, &arg, + hist_browser__check_output_full); + } else { + printed += hist_browser__show_callchain(browser, &entry->sorted_chain, 1, row, total, hist_browser__show_callchain_entry, &arg, hist_browser__check_output_full); + } if (arg.is_current_entry) browser->he_selection = entry; @@ -880,7 +1145,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char * } perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll) + if (perf_hpp__should_skip(fmt, hists) || column++ < browser->b.horiz_scroll) continue; ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); @@ -928,6 +1193,8 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser) } ui_browser__hists_init_top(browser); + hb->he_selection = NULL; + hb->selection = NULL; for (nd = browser->top; nd; nd = rb_next(nd)) { struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node); @@ -1033,6 +1300,9 @@ static void ui_browser__hists_seek(struct ui_browser *browser, * and stop when we printed enough lines to fill the screen. */ do_offset: + if (!nd) + return; + if (offset > 0) { do { h = rb_entry(nd, struct hist_entry, rb_node); @@ -1145,7 +1415,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, printed += fprintf(fp, "%c ", folded_sign); perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, he->hists)) continue; if (!first) { @@ -1794,10 +2064,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, SLang_reset_tty(); SLang_init_tty(0, 0, 0); - if (min_pcnt) { + if (min_pcnt) browser->min_pcnt = min_pcnt; - hist_browser__update_nr_entries(browser); - } + hist_browser__update_nr_entries(browser); browser->pstack = pstack__new(3); if (browser->pstack == NULL) diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 4b3585eed1e8..0f8dcfdfb10f 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -89,8 +89,8 @@ void perf_gtk__init_hpp(void) perf_gtk__hpp_color_overhead_acc; } -static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, - GtkTreeIter *parent, int col, u64 total) +static void perf_gtk__add_callchain_flat(struct rb_root *root, GtkTreeStore *store, + GtkTreeIter *parent, int col, u64 total) { struct rb_node *nd; bool has_single_node = (rb_first(root) == rb_last(root)); @@ -100,13 +100,132 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, struct callchain_list *chain; GtkTreeIter iter, new_parent; bool need_new_parent; - double percent; - u64 hits, child_total; node = rb_entry(nd, struct callchain_node, rb_node); - hits = callchain_cumul_hits(node); - percent = 100.0 * hits / total; + new_parent = *parent; + need_new_parent = !has_single_node; + + callchain_node__make_parent_list(node); + + list_for_each_entry(chain, &node->parent_val, list) { + char buf[128]; + + gtk_tree_store_append(store, &iter, &new_parent); + + callchain_node__scnprintf_value(node, buf, sizeof(buf), total); + gtk_tree_store_set(store, &iter, 0, buf, -1); + + callchain_list__sym_name(chain, buf, sizeof(buf), false); + gtk_tree_store_set(store, &iter, col, buf, -1); + + if (need_new_parent) { + /* + * Only show the top-most symbol in a callchain + * if it's not the only callchain. + */ + new_parent = iter; + need_new_parent = false; + } + } + + list_for_each_entry(chain, &node->val, list) { + char buf[128]; + + gtk_tree_store_append(store, &iter, &new_parent); + + callchain_node__scnprintf_value(node, buf, sizeof(buf), total); + gtk_tree_store_set(store, &iter, 0, buf, -1); + + callchain_list__sym_name(chain, buf, sizeof(buf), false); + gtk_tree_store_set(store, &iter, col, buf, -1); + + if (need_new_parent) { + /* + * Only show the top-most symbol in a callchain + * if it's not the only callchain. + */ + new_parent = iter; + need_new_parent = false; + } + } + } +} + +static void perf_gtk__add_callchain_folded(struct rb_root *root, GtkTreeStore *store, + GtkTreeIter *parent, int col, u64 total) +{ + struct rb_node *nd; + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct callchain_node *node; + struct callchain_list *chain; + GtkTreeIter iter; + char buf[64]; + char *str, *str_alloc = NULL; + bool first = true; + + node = rb_entry(nd, struct callchain_node, rb_node); + + callchain_node__make_parent_list(node); + + list_for_each_entry(chain, &node->parent_val, list) { + char name[1024]; + + callchain_list__sym_name(chain, name, sizeof(name), false); + + if (asprintf(&str, "%s%s%s", + first ? "" : str_alloc, + first ? "" : symbol_conf.field_sep ?: "; ", + name) < 0) + return; + + first = false; + free(str_alloc); + str_alloc = str; + } + + list_for_each_entry(chain, &node->val, list) { + char name[1024]; + + callchain_list__sym_name(chain, name, sizeof(name), false); + + if (asprintf(&str, "%s%s%s", + first ? "" : str_alloc, + first ? "" : symbol_conf.field_sep ?: "; ", + name) < 0) + return; + + first = false; + free(str_alloc); + str_alloc = str; + } + + gtk_tree_store_append(store, &iter, parent); + + callchain_node__scnprintf_value(node, buf, sizeof(buf), total); + gtk_tree_store_set(store, &iter, 0, buf, -1); + + gtk_tree_store_set(store, &iter, col, str, -1); + + free(str_alloc); + } +} + +static void perf_gtk__add_callchain_graph(struct rb_root *root, GtkTreeStore *store, + GtkTreeIter *parent, int col, u64 total) +{ + struct rb_node *nd; + bool has_single_node = (rb_first(root) == rb_last(root)); + + for (nd = rb_first(root); nd; nd = rb_next(nd)) { + struct callchain_node *node; + struct callchain_list *chain; + GtkTreeIter iter, new_parent; + bool need_new_parent; + u64 child_total; + + node = rb_entry(nd, struct callchain_node, rb_node); new_parent = *parent; need_new_parent = !has_single_node && (node->val_nr > 1); @@ -116,7 +235,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, gtk_tree_store_append(store, &iter, &new_parent); - scnprintf(buf, sizeof(buf), "%5.2f%%", percent); + callchain_node__scnprintf_value(node, buf, sizeof(buf), total); gtk_tree_store_set(store, &iter, 0, buf, -1); callchain_list__sym_name(chain, buf, sizeof(buf), false); @@ -138,11 +257,22 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, child_total = total; /* Now 'iter' contains info of the last callchain_list */ - perf_gtk__add_callchain(&node->rb_root, store, &iter, col, - child_total); + perf_gtk__add_callchain_graph(&node->rb_root, store, &iter, col, + child_total); } } +static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store, + GtkTreeIter *parent, int col, u64 total) +{ + if (callchain_param.mode == CHAIN_FLAT) + perf_gtk__add_callchain_flat(root, store, parent, col, total); + else if (callchain_param.mode == CHAIN_FOLDED) + perf_gtk__add_callchain_folded(root, store, parent, col, total); + else + perf_gtk__add_callchain_graph(root, store, parent, col, total); +} + static void on_row_activated(GtkTreeView *view, GtkTreePath *path, GtkTreeViewColumn *col __maybe_unused, gpointer user_data __maybe_unused) @@ -188,7 +318,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; /* @@ -238,7 +368,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, h->hists)) continue; if (fmt->color) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 5029ba2b55af..bf2a66e254ea 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -443,7 +443,6 @@ LIST_HEAD(perf_hpp__sort_list); void perf_hpp__init(void) { - struct list_head *list; int i; for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { @@ -484,17 +483,6 @@ void perf_hpp__init(void) if (symbol_conf.show_total_period) hpp_dimension__add_output(PERF_HPP__PERIOD); - - /* prepend overhead field for backward compatiblity. */ - list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list; - if (list_empty(list)) - list_add(list, &perf_hpp__sort_list); - - if (symbol_conf.cumulate_callchain) { - list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list; - if (list_empty(list)) - list_add(list, &perf_hpp__sort_list); - } } void perf_hpp__column_register(struct perf_hpp_fmt *format) @@ -619,7 +607,7 @@ unsigned int hists__sort_list_width(struct hists *hists) struct perf_hpp dummy_hpp; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; if (first) diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index dfcbc90146ef..387110d50b00 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -34,10 +34,10 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask, return ret; } -static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, +static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node, + struct callchain_list *chain, int depth, int depth_mask, int period, - u64 total_samples, u64 hits, - int left_margin) + u64 total_samples, int left_margin) { int i; size_t ret = 0; @@ -50,10 +50,9 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, else ret += fprintf(fp, " "); if (!period && i == depth - 1) { - double percent; - - percent = hits * 100.0 / total_samples; - ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent); + ret += fprintf(fp, "--"); + ret += callchain_node__fprintf_value(node, fp, total_samples); + ret += fprintf(fp, "--"); } else ret += fprintf(fp, "%s", " "); } @@ -82,13 +81,14 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, int depth_mask, int left_margin) { struct rb_node *node, *next; - struct callchain_node *child; + struct callchain_node *child = NULL; struct callchain_list *chain; int new_depth_mask = depth_mask; u64 remaining; size_t ret = 0; int i; uint entries_printed = 0; + int cumul_count = 0; remaining = total_samples; @@ -100,6 +100,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, child = rb_entry(node, struct callchain_node, rb_node); cumul = callchain_cumul_hits(child); remaining -= cumul; + cumul_count += callchain_cumul_counts(child); /* * The depth mask manages the output of pipes that show @@ -120,10 +121,9 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, left_margin); i = 0; list_for_each_entry(chain, &child->val, list) { - ret += ipchain__fprintf_graph(fp, chain, depth, + ret += ipchain__fprintf_graph(fp, child, chain, depth, new_depth_mask, i++, total_samples, - cumul, left_margin); } @@ -143,14 +143,23 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root, if (callchain_param.mode == CHAIN_GRAPH_REL && remaining && remaining != total_samples) { + struct callchain_node rem_node = { + .hit = remaining, + }; if (!rem_sq_bracket) return ret; + if (callchain_param.value == CCVAL_COUNT && child && child->parent) { + rem_node.count = child->parent->children_count - cumul_count; + if (rem_node.count <= 0) + return ret; + } + new_depth_mask &= ~(1 << (depth - 1)); - ret += ipchain__fprintf_graph(fp, &rem_hits, depth, + ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth, new_depth_mask, 0, total_samples, - remaining, left_margin); + left_margin); } return ret; @@ -243,12 +252,11 @@ static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree, struct rb_node *rb_node = rb_first(tree); while (rb_node) { - double percent; - chain = rb_entry(rb_node, struct callchain_node, rb_node); - percent = chain->hit * 100.0 / total_samples; - ret = percent_color_fprintf(fp, " %6.2f%%\n", percent); + ret += fprintf(fp, " "); + ret += callchain_node__fprintf_value(chain, fp, total_samples); + ret += fprintf(fp, "\n"); ret += __callchain__fprintf_flat(fp, chain, total_samples); ret += fprintf(fp, "\n"); if (++entries_printed == callchain_param.print_limit) @@ -260,6 +268,57 @@ static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree, return ret; } +static size_t __callchain__fprintf_folded(FILE *fp, struct callchain_node *node) +{ + const char *sep = symbol_conf.field_sep ?: ";"; + struct callchain_list *chain; + size_t ret = 0; + char bf[1024]; + bool first; + + if (!node) + return 0; + + ret += __callchain__fprintf_folded(fp, node->parent); + + first = (ret == 0); + list_for_each_entry(chain, &node->val, list) { + if (chain->ip >= PERF_CONTEXT_MAX) + continue; + ret += fprintf(fp, "%s%s", first ? "" : sep, + callchain_list__sym_name(chain, + bf, sizeof(bf), false)); + first = false; + } + + return ret; +} + +static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree, + u64 total_samples) +{ + size_t ret = 0; + u32 entries_printed = 0; + struct callchain_node *chain; + struct rb_node *rb_node = rb_first(tree); + + while (rb_node) { + + chain = rb_entry(rb_node, struct callchain_node, rb_node); + + ret += callchain_node__fprintf_value(chain, fp, total_samples); + ret += fprintf(fp, " "); + ret += __callchain__fprintf_folded(fp, chain); + ret += fprintf(fp, "\n"); + if (++entries_printed == callchain_param.print_limit) + break; + + rb_node = rb_next(rb_node); + } + + return ret; +} + static size_t hist_entry_callchain__fprintf(struct hist_entry *he, u64 total_samples, int left_margin, FILE *fp) @@ -278,6 +337,9 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he, case CHAIN_FLAT: return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples); break; + case CHAIN_FOLDED: + return callchain__fprintf_folded(fp, &he->sorted_chain, total_samples); + break; case CHAIN_NONE: break; default: @@ -323,7 +385,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) return 0; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, he->hists)) continue; /* @@ -402,7 +464,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, fprintf(fp, "# "); perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; if (!first) @@ -428,7 +490,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, perf_hpp__for_each_format(fmt) { unsigned int i; - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; if (!first) diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 591b3fe3ed49..5eec53a3f4ac 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -6,24 +6,20 @@ libperf-y += config.o libperf-y += ctype.o libperf-y += db-export.o libperf-y += env.o -libperf-y += environment.o libperf-y += event.o libperf-y += evlist.o libperf-y += evsel.o -libperf-y += exec_cmd.o -libperf-y += find_next_bit.o -libperf-y += help.o +libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o -libperf-y += parse-options.o libperf-y += parse-events.o libperf-y += perf_regs.o libperf-y += path.o libperf-y += rbtree.o +libperf-y += libstring.o libperf-y += bitmap.o libperf-y += hweight.o -libperf-y += run-command.o libperf-y += quote.o libperf-y += strbuf.o libperf-y += string.o @@ -32,11 +28,9 @@ libperf-y += strfilter.o libperf-y += top.o libperf-y += usage.o libperf-y += wrapper.o -libperf-y += sigchain.o libperf-y += dso.o libperf-y += symbol.o libperf-y += color.o -libperf-y += pager.o libperf-y += header.o libperf-y += callchain.o libperf-y += values.o @@ -86,8 +80,11 @@ libperf-$(CONFIG_AUXTRACE) += intel-pt.o libperf-$(CONFIG_AUXTRACE) += intel-bts.o libperf-y += parse-branch-options.o libperf-y += parse-regs-options.o +libperf-y += term.o +libperf-y += help-unknown-cmd.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o +libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o libperf-$(CONFIG_LIBELF) += symbol-elf.o libperf-$(CONFIG_LIBELF) += probe-file.o libperf-$(CONFIG_LIBELF) += probe-event.o @@ -110,7 +107,6 @@ libperf-$(CONFIG_ZLIB) += zlib.o libperf-$(CONFIG_LZMA) += lzma.o CFLAGS_config.o += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" -CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="BUILD_STR($(prefix_SQ))" $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c $(call rule_mkdir) @@ -136,8 +132,10 @@ CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c -CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_bitmap.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_parse-events.o += -Wno-redundant-decls @@ -145,7 +143,11 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE +$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) @@ -153,6 +155,10 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) +$(OUTPUT)util/libstring.o: ../lib/string.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 1dd1949b0e79..b795b6994144 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -65,6 +65,11 @@ static int call__parse(struct ins_operands *ops) name++; +#ifdef __arm__ + if (strchr(name, '+')) + return -1; +#endif + tok = strchr(name, '>'); if (tok == NULL) return -1; @@ -246,7 +251,11 @@ static int mov__parse(struct ins_operands *ops) return -1; target = ++s; +#ifdef __arm__ + comment = strchr(s, ';'); +#else comment = strchr(s, '#'); +#endif if (comment != NULL) s = comment - 1; @@ -354,6 +363,20 @@ static struct ins instructions[] = { { .name = "addq", .ops = &mov_ops, }, { .name = "addw", .ops = &mov_ops, }, { .name = "and", .ops = &mov_ops, }, +#ifdef __arm__ + { .name = "b", .ops = &jump_ops, }, // might also be a call + { .name = "bcc", .ops = &jump_ops, }, + { .name = "bcs", .ops = &jump_ops, }, + { .name = "beq", .ops = &jump_ops, }, + { .name = "bge", .ops = &jump_ops, }, + { .name = "bgt", .ops = &jump_ops, }, + { .name = "bhi", .ops = &jump_ops, }, + { .name = "bl", .ops = &call_ops, }, + { .name = "blt", .ops = &jump_ops, }, + { .name = "bls", .ops = &jump_ops, }, + { .name = "blx", .ops = &call_ops, }, + { .name = "bne", .ops = &jump_ops, }, +#endif { .name = "bts", .ops = &mov_ops, }, { .name = "call", .ops = &call_ops, }, { .name = "callq", .ops = &call_ops, }, diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 7f10430af39c..360fda01f3b0 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -45,7 +45,7 @@ #include "event.h" #include "session.h" #include "debug.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include "intel-pt.h" #include "intel-bts.h" diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 4c50411371db..540a7efa657e 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -5,11 +5,15 @@ * Copyright (C) 2015 Huawei Inc. */ +#include <linux/bpf.h> #include <bpf/libbpf.h> #include <linux/err.h> +#include <linux/string.h> #include "perf.h" #include "debug.h" #include "bpf-loader.h" +#include "bpf-prologue.h" +#include "llvm-utils.h" #include "probe-event.h" #include "probe-finder.h" // for MAX_PROBES #include "llvm-utils.h" @@ -32,6 +36,10 @@ DEFINE_PRINT_FN(debug, 1) struct bpf_prog_priv { struct perf_probe_event pev; + bool need_prologue; + struct bpf_insn *insns_buf; + int nr_types; + int *type_mapping; }; static bool libbpf_initialized; @@ -106,10 +114,178 @@ bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused, struct bpf_prog_priv *priv = _priv; cleanup_perf_probe_events(&priv->pev, 1); + zfree(&priv->insns_buf); + zfree(&priv->type_mapping); free(priv); } static int +prog_config__exec(const char *value, struct perf_probe_event *pev) +{ + pev->uprobes = true; + pev->target = strdup(value); + if (!pev->target) + return -ENOMEM; + return 0; +} + +static int +prog_config__module(const char *value, struct perf_probe_event *pev) +{ + pev->uprobes = false; + pev->target = strdup(value); + if (!pev->target) + return -ENOMEM; + return 0; +} + +static int +prog_config__bool(const char *value, bool *pbool, bool invert) +{ + int err; + bool bool_value; + + if (!pbool) + return -EINVAL; + + err = strtobool(value, &bool_value); + if (err) + return err; + + *pbool = invert ? !bool_value : bool_value; + return 0; +} + +static int +prog_config__inlines(const char *value, + struct perf_probe_event *pev __maybe_unused) +{ + return prog_config__bool(value, &probe_conf.no_inlines, true); +} + +static int +prog_config__force(const char *value, + struct perf_probe_event *pev __maybe_unused) +{ + return prog_config__bool(value, &probe_conf.force_add, false); +} + +static struct { + const char *key; + const char *usage; + const char *desc; + int (*func)(const char *, struct perf_probe_event *); +} bpf_prog_config_terms[] = { + { + .key = "exec", + .usage = "exec=<full path of file>", + .desc = "Set uprobe target", + .func = prog_config__exec, + }, + { + .key = "module", + .usage = "module=<module name> ", + .desc = "Set kprobe module", + .func = prog_config__module, + }, + { + .key = "inlines", + .usage = "inlines=[yes|no] ", + .desc = "Probe at inline symbol", + .func = prog_config__inlines, + }, + { + .key = "force", + .usage = "force=[yes|no] ", + .desc = "Forcibly add events with existing name", + .func = prog_config__force, + }, +}; + +static int +do_prog_config(const char *key, const char *value, + struct perf_probe_event *pev) +{ + unsigned int i; + + pr_debug("config bpf program: %s=%s\n", key, value); + for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++) + if (strcmp(key, bpf_prog_config_terms[i].key) == 0) + return bpf_prog_config_terms[i].func(value, pev); + + pr_debug("BPF: ERROR: invalid program config option: %s=%s\n", + key, value); + + pr_debug("\nHint: Valid options are:\n"); + for (i = 0; i < ARRAY_SIZE(bpf_prog_config_terms); i++) + pr_debug("\t%s:\t%s\n", bpf_prog_config_terms[i].usage, + bpf_prog_config_terms[i].desc); + pr_debug("\n"); + + return -BPF_LOADER_ERRNO__PROGCONF_TERM; +} + +static const char * +parse_prog_config_kvpair(const char *config_str, struct perf_probe_event *pev) +{ + char *text = strdup(config_str); + char *sep, *line; + const char *main_str = NULL; + int err = 0; + + if (!text) { + pr_debug("No enough memory: dup config_str failed\n"); + return ERR_PTR(-ENOMEM); + } + + line = text; + while ((sep = strchr(line, ';'))) { + char *equ; + + *sep = '\0'; + equ = strchr(line, '='); + if (!equ) { + pr_warning("WARNING: invalid config in BPF object: %s\n", + line); + pr_warning("\tShould be 'key=value'.\n"); + goto nextline; + } + *equ = '\0'; + + err = do_prog_config(line, equ + 1, pev); + if (err) + break; +nextline: + line = sep + 1; + } + + if (!err) + main_str = config_str + (line - text); + free(text); + + return err ? ERR_PTR(err) : main_str; +} + +static int +parse_prog_config(const char *config_str, struct perf_probe_event *pev) +{ + int err; + const char *main_str = parse_prog_config_kvpair(config_str, pev); + + if (IS_ERR(main_str)) + return PTR_ERR(main_str); + + err = parse_perf_probe_command(main_str, pev); + if (err < 0) { + pr_debug("bpf: '%s' is not a valid config string\n", + config_str); + /* parse failed, don't need clear pev. */ + return -BPF_LOADER_ERRNO__CONFIG; + } + return 0; +} + +static int config_bpf_program(struct bpf_program *prog) { struct perf_probe_event *pev = NULL; @@ -117,6 +293,10 @@ config_bpf_program(struct bpf_program *prog) const char *config_str; int err; + /* Initialize per-program probing setting */ + probe_conf.no_inlines = false; + probe_conf.force_add = false; + config_str = bpf_program__title(prog, false); if (IS_ERR(config_str)) { pr_debug("bpf: unable to get title for program\n"); @@ -131,13 +311,9 @@ config_bpf_program(struct bpf_program *prog) pev = &priv->pev; pr_debug("bpf: config program '%s'\n", config_str); - err = parse_perf_probe_command(config_str, pev); - if (err < 0) { - pr_debug("bpf: '%s' is not a valid config string\n", - config_str); - err = -BPF_LOADER_ERRNO__CONFIG; + err = parse_prog_config(config_str, pev); + if (err) goto errout; - } if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) { pr_debug("bpf: '%s': group for event is set and not '%s'.\n", @@ -197,6 +373,220 @@ static int bpf__prepare_probe(void) return err; } +static int +preproc_gen_prologue(struct bpf_program *prog, int n, + struct bpf_insn *orig_insns, int orig_insns_cnt, + struct bpf_prog_prep_result *res) +{ + struct probe_trace_event *tev; + struct perf_probe_event *pev; + struct bpf_prog_priv *priv; + struct bpf_insn *buf; + size_t prologue_cnt = 0; + int i, err; + + err = bpf_program__get_private(prog, (void **)&priv); + if (err || !priv) + goto errout; + + pev = &priv->pev; + + if (n < 0 || n >= priv->nr_types) + goto errout; + + /* Find a tev belongs to that type */ + for (i = 0; i < pev->ntevs; i++) { + if (priv->type_mapping[i] == n) + break; + } + + if (i >= pev->ntevs) { + pr_debug("Internal error: prologue type %d not found\n", n); + return -BPF_LOADER_ERRNO__PROLOGUE; + } + + tev = &pev->tevs[i]; + + buf = priv->insns_buf; + err = bpf__gen_prologue(tev->args, tev->nargs, + buf, &prologue_cnt, + BPF_MAXINSNS - orig_insns_cnt); + if (err) { + const char *title; + + title = bpf_program__title(prog, false); + if (!title) + title = "[unknown]"; + + pr_debug("Failed to generate prologue for program %s\n", + title); + return err; + } + + memcpy(&buf[prologue_cnt], orig_insns, + sizeof(struct bpf_insn) * orig_insns_cnt); + + res->new_insn_ptr = buf; + res->new_insn_cnt = prologue_cnt + orig_insns_cnt; + res->pfd = NULL; + return 0; + +errout: + pr_debug("Internal error in preproc_gen_prologue\n"); + return -BPF_LOADER_ERRNO__PROLOGUE; +} + +/* + * compare_tev_args is reflexive, transitive and antisymmetric. + * I can proof it but this margin is too narrow to contain. + */ +static int compare_tev_args(const void *ptev1, const void *ptev2) +{ + int i, ret; + const struct probe_trace_event *tev1 = + *(const struct probe_trace_event **)ptev1; + const struct probe_trace_event *tev2 = + *(const struct probe_trace_event **)ptev2; + + ret = tev2->nargs - tev1->nargs; + if (ret) + return ret; + + for (i = 0; i < tev1->nargs; i++) { + struct probe_trace_arg *arg1, *arg2; + struct probe_trace_arg_ref *ref1, *ref2; + + arg1 = &tev1->args[i]; + arg2 = &tev2->args[i]; + + ret = strcmp(arg1->value, arg2->value); + if (ret) + return ret; + + ref1 = arg1->ref; + ref2 = arg2->ref; + + while (ref1 && ref2) { + ret = ref2->offset - ref1->offset; + if (ret) + return ret; + + ref1 = ref1->next; + ref2 = ref2->next; + } + + if (ref1 || ref2) + return ref2 ? 1 : -1; + } + + return 0; +} + +/* + * Assign a type number to each tevs in a pev. + * mapping is an array with same slots as tevs in that pev. + * nr_types will be set to number of types. + */ +static int map_prologue(struct perf_probe_event *pev, int *mapping, + int *nr_types) +{ + int i, type = 0; + struct probe_trace_event **ptevs; + + size_t array_sz = sizeof(*ptevs) * pev->ntevs; + + ptevs = malloc(array_sz); + if (!ptevs) { + pr_debug("No ehough memory: alloc ptevs failed\n"); + return -ENOMEM; + } + + pr_debug("In map_prologue, ntevs=%d\n", pev->ntevs); + for (i = 0; i < pev->ntevs; i++) + ptevs[i] = &pev->tevs[i]; + + qsort(ptevs, pev->ntevs, sizeof(*ptevs), + compare_tev_args); + + for (i = 0; i < pev->ntevs; i++) { + int n; + + n = ptevs[i] - pev->tevs; + if (i == 0) { + mapping[n] = type; + pr_debug("mapping[%d]=%d\n", n, type); + continue; + } + + if (compare_tev_args(ptevs + i, ptevs + i - 1) == 0) + mapping[n] = type; + else + mapping[n] = ++type; + + pr_debug("mapping[%d]=%d\n", n, mapping[n]); + } + free(ptevs); + *nr_types = type + 1; + + return 0; +} + +static int hook_load_preprocessor(struct bpf_program *prog) +{ + struct perf_probe_event *pev; + struct bpf_prog_priv *priv; + bool need_prologue = false; + int err, i; + + err = bpf_program__get_private(prog, (void **)&priv); + if (err || !priv) { + pr_debug("Internal error when hook preprocessor\n"); + return -BPF_LOADER_ERRNO__INTERNAL; + } + + pev = &priv->pev; + for (i = 0; i < pev->ntevs; i++) { + struct probe_trace_event *tev = &pev->tevs[i]; + + if (tev->nargs > 0) { + need_prologue = true; + break; + } + } + + /* + * Since all tevs don't have argument, we don't need generate + * prologue. + */ + if (!need_prologue) { + priv->need_prologue = false; + return 0; + } + + priv->need_prologue = true; + priv->insns_buf = malloc(sizeof(struct bpf_insn) * BPF_MAXINSNS); + if (!priv->insns_buf) { + pr_debug("No enough memory: alloc insns_buf failed\n"); + return -ENOMEM; + } + + priv->type_mapping = malloc(sizeof(int) * pev->ntevs); + if (!priv->type_mapping) { + pr_debug("No enough memory: alloc type_mapping failed\n"); + return -ENOMEM; + } + memset(priv->type_mapping, -1, + sizeof(int) * pev->ntevs); + + err = map_prologue(pev, priv->type_mapping, &priv->nr_types); + if (err) + return err; + + err = bpf_program__set_prep(prog, priv->nr_types, + preproc_gen_prologue); + return err; +} + int bpf__probe(struct bpf_object *obj) { int err = 0; @@ -231,6 +621,18 @@ int bpf__probe(struct bpf_object *obj) pr_debug("bpf_probe: failed to apply perf probe events"); goto out; } + + /* + * After probing, let's consider prologue, which + * adds program fetcher to BPF programs. + * + * hook_load_preprocessorr() hooks pre-processor + * to bpf_program, let it generate prologue + * dynamically during loading. + */ + err = hook_load_preprocessor(prog); + if (err) + goto out; } out: return err < 0 ? err : 0; @@ -314,7 +716,14 @@ int bpf__foreach_tev(struct bpf_object *obj, for (i = 0; i < pev->ntevs; i++) { tev = &pev->tevs[i]; - fd = bpf_program__fd(prog); + if (priv->need_prologue) { + int type = priv->type_mapping[i]; + + fd = bpf_program__nth_fd(prog, type); + } else { + fd = bpf_program__fd(prog); + } + if (fd < 0) { pr_debug("bpf: failed to get file descriptor\n"); return fd; @@ -340,6 +749,10 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = { [ERRCODE_OFFSET(EVENTNAME)] = "No event name found in config string", [ERRCODE_OFFSET(INTERNAL)] = "BPF loader internal error", [ERRCODE_OFFSET(COMPILE)] = "Error when compiling BPF scriptlet", + [ERRCODE_OFFSET(PROGCONF_TERM)] = "Invalid program config term in config string", + [ERRCODE_OFFSET(PROLOGUE)] = "Failed to generate prologue", + [ERRCODE_OFFSET(PROLOGUE2BIG)] = "Prologue too big for program", + [ERRCODE_OFFSET(PROLOGUEOOB)] = "Offset out of bound for prologue", }; static int @@ -420,7 +833,11 @@ int bpf__strerror_probe(struct bpf_object *obj __maybe_unused, int err, char *buf, size_t size) { bpf__strerror_head(err, buf, size); - bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'"); + case BPF_LOADER_ERRNO__PROGCONF_TERM: { + scnprintf(buf, size, "%s (add -v to see detail)", emsg); + break; + } + bpf__strerror_entry(EEXIST, "Probe point exist. Try 'perf probe -d \"*\"' and set 'force=yes'"); bpf__strerror_entry(EACCES, "You need to be root"); bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0"); bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file"); diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h index 9caf3ae4acf3..6fdc0457e2b6 100644 --- a/tools/perf/util/bpf-loader.h +++ b/tools/perf/util/bpf-loader.h @@ -20,6 +20,10 @@ enum bpf_loader_errno { BPF_LOADER_ERRNO__EVENTNAME, /* Event name is missing */ BPF_LOADER_ERRNO__INTERNAL, /* BPF loader internal error */ BPF_LOADER_ERRNO__COMPILE, /* Error when compiling BPF scriptlet */ + BPF_LOADER_ERRNO__PROGCONF_TERM,/* Invalid program config term in config string */ + BPF_LOADER_ERRNO__PROLOGUE, /* Failed to generate prologue */ + BPF_LOADER_ERRNO__PROLOGUE2BIG, /* Prologue too big for program */ + BPF_LOADER_ERRNO__PROLOGUEOOB, /* Offset out of bound for prologue */ __BPF_LOADER_ERRNO__END, }; diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c new file mode 100644 index 000000000000..6cdbee119ceb --- /dev/null +++ b/tools/perf/util/bpf-prologue.c @@ -0,0 +1,455 @@ +/* + * bpf-prologue.c + * + * Copyright (C) 2015 He Kuang <hekuang@huawei.com> + * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com> + * Copyright (C) 2015 Huawei Inc. + */ + +#include <bpf/libbpf.h> +#include "perf.h" +#include "debug.h" +#include "bpf-loader.h" +#include "bpf-prologue.h" +#include "probe-finder.h" +#include <dwarf-regs.h> +#include <linux/filter.h> + +#define BPF_REG_SIZE 8 + +#define JMP_TO_ERROR_CODE -1 +#define JMP_TO_SUCCESS_CODE -2 +#define JMP_TO_USER_CODE -3 + +struct bpf_insn_pos { + struct bpf_insn *begin; + struct bpf_insn *end; + struct bpf_insn *pos; +}; + +static inline int +pos_get_cnt(struct bpf_insn_pos *pos) +{ + return pos->pos - pos->begin; +} + +static int +append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos) +{ + if (!pos->pos) + return -BPF_LOADER_ERRNO__PROLOGUE2BIG; + + if (pos->pos + 1 >= pos->end) { + pr_err("bpf prologue: prologue too long\n"); + pos->pos = NULL; + return -BPF_LOADER_ERRNO__PROLOGUE2BIG; + } + + *(pos->pos)++ = new_insn; + return 0; +} + +static int +check_pos(struct bpf_insn_pos *pos) +{ + if (!pos->pos || pos->pos >= pos->end) + return -BPF_LOADER_ERRNO__PROLOGUE2BIG; + return 0; +} + +/* Give it a shorter name */ +#define ins(i, p) append_insn((i), (p)) + +/* + * Give a register name (in 'reg'), generate instruction to + * load register into an eBPF register rd: + * 'ldd target_reg, offset(ctx_reg)', where: + * ctx_reg is pre initialized to pointer of 'struct pt_regs'. + */ +static int +gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg, + const char *reg, int target_reg) +{ + int offset = regs_query_register_offset(reg); + + if (offset < 0) { + pr_err("bpf: prologue: failed to get register %s\n", + reg); + return offset; + } + ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos); + + return check_pos(pos); +} + +/* + * Generate a BPF_FUNC_probe_read function call. + * + * src_base_addr_reg is a register holding base address, + * dst_addr_reg is a register holding dest address (on stack), + * result is: + * + * *[dst_addr_reg] = *([src_base_addr_reg] + offset) + * + * Arguments of BPF_FUNC_probe_read: + * ARG1: ptr to stack (dest) + * ARG2: size (8) + * ARG3: unsafe ptr (src) + */ +static int +gen_read_mem(struct bpf_insn_pos *pos, + int src_base_addr_reg, + int dst_addr_reg, + long offset) +{ + /* mov arg3, src_base_addr_reg */ + if (src_base_addr_reg != BPF_REG_ARG3) + ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos); + /* add arg3, #offset */ + if (offset) + ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos); + + /* mov arg2, #reg_size */ + ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos); + + /* mov arg1, dst_addr_reg */ + if (dst_addr_reg != BPF_REG_ARG1) + ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos); + + /* Call probe_read */ + ins(BPF_EMIT_CALL(BPF_FUNC_probe_read), pos); + /* + * Error processing: if read fail, goto error code, + * will be relocated. Target should be the start of + * error processing code. + */ + ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE), + pos); + + return check_pos(pos); +} + +/* + * Each arg should be bare register. Fetch and save them into argument + * registers (r3 - r5). + * + * BPF_REG_1 should have been initialized with pointer to + * 'struct pt_regs'. + */ +static int +gen_prologue_fastpath(struct bpf_insn_pos *pos, + struct probe_trace_arg *args, int nargs) +{ + int i, err = 0; + + for (i = 0; i < nargs; i++) { + err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value, + BPF_PROLOGUE_START_ARG_REG + i); + if (err) + goto errout; + } + + return check_pos(pos); +errout: + return err; +} + +/* + * Slow path: + * At least one argument has the form of 'offset($rx)'. + * + * Following code first stores them into stack, then loads all of then + * to r2 - r5. + * Before final loading, the final result should be: + * + * low address + * BPF_REG_FP - 24 ARG3 + * BPF_REG_FP - 16 ARG2 + * BPF_REG_FP - 8 ARG1 + * BPF_REG_FP + * high address + * + * For each argument (described as: offn(...off2(off1(reg)))), + * generates following code: + * + * r7 <- fp + * r7 <- r7 - stack_offset // Ideal code should initialize r7 using + * // fp before generating args. However, + * // eBPF won't regard r7 as stack pointer + * // if it is generated by minus 8 from + * // another stack pointer except fp. + * // This is why we have to set r7 + * // to fp for each variable. + * r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx() + * (r7) <- r3 // skip following instructions for bare reg + * r3 <- r3 + off1 . // skip if off1 == 0 + * r2 <- 8 \ + * r1 <- r7 |-> generated by gen_read_mem() + * call probe_read / + * jnei r0, 0, err ./ + * r3 <- (r7) + * r3 <- r3 + off2 . // skip if off2 == 0 + * r2 <- 8 \ // r2 may be broken by probe_read, so set again + * r1 <- r7 |-> generated by gen_read_mem() + * call probe_read / + * jnei r0, 0, err ./ + * ... + */ +static int +gen_prologue_slowpath(struct bpf_insn_pos *pos, + struct probe_trace_arg *args, int nargs) +{ + int err, i; + + for (i = 0; i < nargs; i++) { + struct probe_trace_arg *arg = &args[i]; + const char *reg = arg->value; + struct probe_trace_arg_ref *ref = NULL; + int stack_offset = (i + 1) * -8; + + pr_debug("prologue: fetch arg %d, base reg is %s\n", + i, reg); + + /* value of base register is stored into ARG3 */ + err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg, + BPF_REG_ARG3); + if (err) { + pr_err("prologue: failed to get offset of register %s\n", + reg); + goto errout; + } + + /* Make r7 the stack pointer. */ + ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos); + /* r7 += -8 */ + ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos); + /* + * Store r3 (base register) onto stack + * Ensure fp[offset] is set. + * fp is the only valid base register when storing + * into stack. We are not allowed to use r7 as base + * register here. + */ + ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3, + stack_offset), pos); + + ref = arg->ref; + while (ref) { + pr_debug("prologue: arg %d: offset %ld\n", + i, ref->offset); + err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7, + ref->offset); + if (err) { + pr_err("prologue: failed to generate probe_read function call\n"); + goto errout; + } + + ref = ref->next; + /* + * Load previous result into ARG3. Use + * BPF_REG_FP instead of r7 because verifier + * allows FP based addressing only. + */ + if (ref) + ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3, + BPF_REG_FP, stack_offset), pos); + } + } + + /* Final pass: read to registers */ + for (i = 0; i < nargs; i++) + ins(BPF_LDX_MEM(BPF_DW, BPF_PROLOGUE_START_ARG_REG + i, + BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); + + ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); + + return check_pos(pos); +errout: + return err; +} + +static int +prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code, + struct bpf_insn *success_code, struct bpf_insn *user_code) +{ + struct bpf_insn *insn; + + if (check_pos(pos)) + return -BPF_LOADER_ERRNO__PROLOGUE2BIG; + + for (insn = pos->begin; insn < pos->pos; insn++) { + struct bpf_insn *target; + u8 class = BPF_CLASS(insn->code); + u8 opcode; + + if (class != BPF_JMP) + continue; + opcode = BPF_OP(insn->code); + if (opcode == BPF_CALL) + continue; + + switch (insn->off) { + case JMP_TO_ERROR_CODE: + target = error_code; + break; + case JMP_TO_SUCCESS_CODE: + target = success_code; + break; + case JMP_TO_USER_CODE: + target = user_code; + break; + default: + pr_err("bpf prologue: internal error: relocation failed\n"); + return -BPF_LOADER_ERRNO__PROLOGUE; + } + + insn->off = target - (insn + 1); + } + return 0; +} + +int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, + struct bpf_insn *new_prog, size_t *new_cnt, + size_t cnt_space) +{ + struct bpf_insn *success_code = NULL; + struct bpf_insn *error_code = NULL; + struct bpf_insn *user_code = NULL; + struct bpf_insn_pos pos; + bool fastpath = true; + int err = 0, i; + + if (!new_prog || !new_cnt) + return -EINVAL; + + if (cnt_space > BPF_MAXINSNS) + cnt_space = BPF_MAXINSNS; + + pos.begin = new_prog; + pos.end = new_prog + cnt_space; + pos.pos = new_prog; + + if (!nargs) { + ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), + &pos); + + if (check_pos(&pos)) + goto errout; + + *new_cnt = pos_get_cnt(&pos); + return 0; + } + + if (nargs > BPF_PROLOGUE_MAX_ARGS) { + pr_warning("bpf: prologue: %d arguments are dropped\n", + nargs - BPF_PROLOGUE_MAX_ARGS); + nargs = BPF_PROLOGUE_MAX_ARGS; + } + + /* First pass: validation */ + for (i = 0; i < nargs; i++) { + struct probe_trace_arg_ref *ref = args[i].ref; + + if (args[i].value[0] == '@') { + /* TODO: fetch global variable */ + pr_err("bpf: prologue: global %s%+ld not support\n", + args[i].value, ref ? ref->offset : 0); + return -ENOTSUP; + } + + while (ref) { + /* fastpath is true if all args has ref == NULL */ + fastpath = false; + + /* + * Instruction encodes immediate value using + * s32, ref->offset is long. On systems which + * can't fill long in s32, refuse to process if + * ref->offset too large (or small). + */ +#ifdef __LP64__ +#define OFFSET_MAX ((1LL << 31) - 1) +#define OFFSET_MIN ((1LL << 31) * -1) + if (ref->offset > OFFSET_MAX || + ref->offset < OFFSET_MIN) { + pr_err("bpf: prologue: offset out of bound: %ld\n", + ref->offset); + return -BPF_LOADER_ERRNO__PROLOGUEOOB; + } +#endif + ref = ref->next; + } + } + pr_debug("prologue: pass validation\n"); + + if (fastpath) { + /* If all variables are registers... */ + pr_debug("prologue: fast path\n"); + err = gen_prologue_fastpath(&pos, args, nargs); + if (err) + goto errout; + } else { + pr_debug("prologue: slow path\n"); + + /* Initialization: move ctx to a callee saved register. */ + ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos); + + err = gen_prologue_slowpath(&pos, args, nargs); + if (err) + goto errout; + /* + * start of ERROR_CODE (only slow pass needs error code) + * mov r2 <- 1 // r2 is error number + * mov r3 <- 0 // r3, r4... should be touched or + * // verifier would complain + * mov r4 <- 0 + * ... + * goto usercode + */ + error_code = pos.pos; + ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1), + &pos); + + for (i = 0; i < nargs; i++) + ins(BPF_ALU64_IMM(BPF_MOV, + BPF_PROLOGUE_START_ARG_REG + i, + 0), + &pos); + ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE), + &pos); + } + + /* + * start of SUCCESS_CODE: + * mov r2 <- 0 + * goto usercode // skip + */ + success_code = pos.pos; + ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos); + + /* + * start of USER_CODE: + * Restore ctx to r1 + */ + user_code = pos.pos; + if (!fastpath) { + /* + * Only slow path needs restoring of ctx. In fast path, + * register are loaded directly from r1. + */ + ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos); + err = prologue_relocate(&pos, error_code, success_code, + user_code); + if (err) + goto errout; + } + + err = check_pos(&pos); + if (err) + goto errout; + + *new_cnt = pos_get_cnt(&pos); + return 0; +errout: + return err; +} diff --git a/tools/perf/util/bpf-prologue.h b/tools/perf/util/bpf-prologue.h new file mode 100644 index 000000000000..d94cbea12899 --- /dev/null +++ b/tools/perf/util/bpf-prologue.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) 2015, He Kuang <hekuang@huawei.com> + * Copyright (C) 2015, Huawei Inc. + */ +#ifndef __BPF_PROLOGUE_H +#define __BPF_PROLOGUE_H + +#include <linux/compiler.h> +#include <linux/filter.h> +#include "probe-event.h" + +#define BPF_PROLOGUE_MAX_ARGS 3 +#define BPF_PROLOGUE_START_ARG_REG BPF_REG_3 +#define BPF_PROLOGUE_FETCH_RESULT_REG BPF_REG_2 + +#ifdef HAVE_BPF_PROLOGUE +int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, + struct bpf_insn *new_prog, size_t *new_cnt, + size_t cnt_space); +#else +static inline int +bpf__gen_prologue(struct probe_trace_arg *args __maybe_unused, + int nargs __maybe_unused, + struct bpf_insn *new_prog __maybe_unused, + size_t *new_cnt, + size_t cnt_space __maybe_unused) +{ + if (!new_cnt) + return -EINVAL; + *new_cnt = 0; + return -ENOTSUP; +} +#endif +#endif /* __BPF_PROLOGUE_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 217b5a60e2ab..6a7e273a514a 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -91,7 +91,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf) bid += 2; } - return raw - build_id; + return (bid - bf) + 1; } int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id) diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h index c861373aaed3..07b5d63947b1 100644 --- a/tools/perf/util/cache.h +++ b/tools/perf/util/cache.h @@ -4,9 +4,12 @@ #include <stdbool.h> #include "util.h" #include "strbuf.h" +#include <subcmd/pager.h> #include "../perf.h" #include "../ui/ui.h" +#include <linux/string.h> + #define CMD_EXEC_PATH "--exec-path" #define CMD_PERF_DIR "--perf-dir=" #define CMD_WORK_TREE "--work-tree=" @@ -18,6 +21,7 @@ #define DEFAULT_PERF_DIR_ENVIRONMENT ".perf" #define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR" #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR" +#define PERF_PAGER_ENVIRONMENT "PERF_PAGER" typedef int (*config_fn_t)(const char *, const char *, void *); extern int perf_default_config(const char *, const char *, void *); @@ -28,11 +32,6 @@ extern int perf_config_bool(const char *, const char *); extern int config_error_nonbool(const char *); extern const char *perf_config_dirname(const char *, const char *); -/* pager.c */ -extern void setup_pager(void); -extern int pager_in_use(void); -extern int pager_use_color; - char *alias_lookup(const char *alias); int split_cmdline(char *cmdline, const char ***argv); @@ -71,9 +70,4 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2 extern char *perf_pathdup(const char *fmt, ...) __attribute__((format (printf, 1, 2))); -#ifndef __UCLIBC__ -/* Matches the libc/libbsd function attribute so we declare this unconditionally: */ -extern size_t strlcpy(char *dest, const char *src, size_t size); -#endif - #endif /* __PERF_CACHE_H */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 735ad48e1858..53c43eb9489e 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -44,6 +44,10 @@ static int parse_callchain_mode(const char *value) callchain_param.mode = CHAIN_GRAPH_REL; return 0; } + if (!strncmp(value, "folded", strlen(value))) { + callchain_param.mode = CHAIN_FOLDED; + return 0; + } return -1; } @@ -79,6 +83,23 @@ static int parse_callchain_sort_key(const char *value) return -1; } +static int parse_callchain_value(const char *value) +{ + if (!strncmp(value, "percent", strlen(value))) { + callchain_param.value = CCVAL_PERCENT; + return 0; + } + if (!strncmp(value, "period", strlen(value))) { + callchain_param.value = CCVAL_PERIOD; + return 0; + } + if (!strncmp(value, "count", strlen(value))) { + callchain_param.value = CCVAL_COUNT; + return 0; + } + return -1; +} + static int __parse_callchain_report_opt(const char *arg, bool allow_record_opt) { @@ -102,7 +123,8 @@ __parse_callchain_report_opt(const char *arg, bool allow_record_opt) if (!parse_callchain_mode(tok) || !parse_callchain_order(tok) || - !parse_callchain_sort_key(tok)) { + !parse_callchain_sort_key(tok) || + !parse_callchain_value(tok)) { /* parsing ok - move on to the next */ try_stack_size = false; goto next; @@ -218,6 +240,7 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, switch (mode) { case CHAIN_FLAT: + case CHAIN_FOLDED: if (rnode->hit < chain->hit) p = &(*p)->rb_left; else @@ -267,6 +290,7 @@ static void sort_chain_flat(struct rb_root *rb_root, struct callchain_root *root, u64 min_hit, struct callchain_param *param __maybe_unused) { + *rb_root = RB_ROOT; __sort_chain_flat(rb_root, &root->node, min_hit); } @@ -338,6 +362,7 @@ int callchain_register_param(struct callchain_param *param) param->sort = sort_chain_graph_rel; break; case CHAIN_FLAT: + case CHAIN_FOLDED: param->sort = sort_chain_flat; break; case CHAIN_NONE: @@ -363,6 +388,7 @@ create_child(struct callchain_node *parent, bool inherit_children) } new->parent = parent; INIT_LIST_HEAD(&new->val); + INIT_LIST_HEAD(&new->parent_val); if (inherit_children) { struct rb_node *n; @@ -431,6 +457,8 @@ add_child(struct callchain_node *parent, new->children_hit = 0; new->hit = period; + new->children_count = 0; + new->count = 1; return new; } @@ -478,6 +506,9 @@ split_add_child(struct callchain_node *parent, parent->children_hit = callchain_cumul_hits(new); new->val_nr = parent->val_nr - idx_local; parent->val_nr = idx_local; + new->count = parent->count; + new->children_count = parent->children_count; + parent->children_count = callchain_cumul_counts(new); /* create a new child for the new branch if any */ if (idx_total < cursor->nr) { @@ -488,6 +519,8 @@ split_add_child(struct callchain_node *parent, parent->hit = 0; parent->children_hit += period; + parent->count = 0; + parent->children_count += 1; node = callchain_cursor_current(cursor); new = add_child(parent, cursor, period); @@ -510,6 +543,7 @@ split_add_child(struct callchain_node *parent, rb_insert_color(&new->rb_node_in, &parent->rb_root_in); } else { parent->hit = period; + parent->count = 1; } } @@ -556,6 +590,7 @@ append_chain_children(struct callchain_node *root, inc_children_hit: root->children_hit += period; + root->children_count++; } static int @@ -608,6 +643,7 @@ append_chain(struct callchain_node *root, /* we match 100% of the path, increment the hit */ if (matches == root->val_nr && cursor->pos == cursor->nr) { root->hit += period; + root->count++; return 0; } @@ -799,12 +835,72 @@ char *callchain_list__sym_name(struct callchain_list *cl, return bf; } +char *callchain_node__scnprintf_value(struct callchain_node *node, + char *bf, size_t bfsize, u64 total) +{ + double percent = 0.0; + u64 period = callchain_cumul_hits(node); + unsigned count = callchain_cumul_counts(node); + + if (callchain_param.mode == CHAIN_FOLDED) { + period = node->hit; + count = node->count; + } + + switch (callchain_param.value) { + case CCVAL_PERIOD: + scnprintf(bf, bfsize, "%"PRIu64, period); + break; + case CCVAL_COUNT: + scnprintf(bf, bfsize, "%u", count); + break; + case CCVAL_PERCENT: + default: + if (total) + percent = period * 100.0 / total; + scnprintf(bf, bfsize, "%.2f%%", percent); + break; + } + return bf; +} + +int callchain_node__fprintf_value(struct callchain_node *node, + FILE *fp, u64 total) +{ + double percent = 0.0; + u64 period = callchain_cumul_hits(node); + unsigned count = callchain_cumul_counts(node); + + if (callchain_param.mode == CHAIN_FOLDED) { + period = node->hit; + count = node->count; + } + + switch (callchain_param.value) { + case CCVAL_PERIOD: + return fprintf(fp, "%"PRIu64, period); + case CCVAL_COUNT: + return fprintf(fp, "%u", count); + case CCVAL_PERCENT: + default: + if (total) + percent = period * 100.0 / total; + return percent_color_fprintf(fp, "%.2f%%", percent); + } + return 0; +} + static void free_callchain_node(struct callchain_node *node) { struct callchain_list *list, *tmp; struct callchain_node *child; struct rb_node *n; + list_for_each_entry_safe(list, tmp, &node->parent_val, list) { + list_del(&list->list); + free(list); + } + list_for_each_entry_safe(list, tmp, &node->val, list) { list_del(&list->list); free(list); @@ -828,3 +924,69 @@ void free_callchain(struct callchain_root *root) free_callchain_node(&root->node); } + +static u64 decay_callchain_node(struct callchain_node *node) +{ + struct callchain_node *child; + struct rb_node *n; + u64 child_hits = 0; + + n = rb_first(&node->rb_root_in); + while (n) { + child = container_of(n, struct callchain_node, rb_node_in); + + child_hits += decay_callchain_node(child); + n = rb_next(n); + } + + node->hit = (node->hit * 7) / 8; + node->children_hit = child_hits; + + return node->hit; +} + +void decay_callchain(struct callchain_root *root) +{ + if (!symbol_conf.use_callchain) + return; + + decay_callchain_node(&root->node); +} + +int callchain_node__make_parent_list(struct callchain_node *node) +{ + struct callchain_node *parent = node->parent; + struct callchain_list *chain, *new; + LIST_HEAD(head); + + while (parent) { + list_for_each_entry_reverse(chain, &parent->val, list) { + new = malloc(sizeof(*new)); + if (new == NULL) + goto out; + *new = *chain; + new->has_children = false; + list_add_tail(&new->list, &head); + } + parent = parent->parent; + } + + list_for_each_entry_safe_reverse(chain, new, &head, list) + list_move_tail(&chain->list, &node->parent_val); + + if (!list_empty(&node->parent_val)) { + chain = list_first_entry(&node->parent_val, struct callchain_list, list); + chain->has_children = rb_prev(&node->rb_node) || rb_next(&node->rb_node); + + chain = list_first_entry(&node->val, struct callchain_list, list); + chain->has_children = false; + } + return 0; + +out: + list_for_each_entry_safe(chain, new, &head, list) { + list_del(&chain->list); + free(chain); + } + return -ENOMEM; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index fce8161e54db..18dd22269764 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -24,12 +24,13 @@ #define CALLCHAIN_RECORD_HELP CALLCHAIN_HELP RECORD_MODE_HELP RECORD_SIZE_HELP #define CALLCHAIN_REPORT_HELP \ - HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|none)\n" \ + HELP_PAD "print_type:\tcall graph printing style (graph|flat|fractal|folded|none)\n" \ HELP_PAD "threshold:\tminimum call graph inclusion threshold (<percent>)\n" \ HELP_PAD "print_limit:\tmaximum number of call graph entry (<number>)\n" \ HELP_PAD "order:\t\tcall graph order (caller|callee)\n" \ HELP_PAD "sort_key:\tcall graph sort key (function|address)\n" \ - HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" + HELP_PAD "branch:\t\tinclude last branch info to call graph (branch)\n" \ + HELP_PAD "value:\t\tcall graph value (percent|period|count)\n" enum perf_call_graph_mode { CALLCHAIN_NONE, @@ -43,7 +44,8 @@ enum chain_mode { CHAIN_NONE, CHAIN_FLAT, CHAIN_GRAPH_ABS, - CHAIN_GRAPH_REL + CHAIN_GRAPH_REL, + CHAIN_FOLDED, }; enum chain_order { @@ -54,11 +56,14 @@ enum chain_order { struct callchain_node { struct callchain_node *parent; struct list_head val; + struct list_head parent_val; struct rb_node rb_node_in; /* to insert nodes in an rbtree */ struct rb_node rb_node; /* to sort nodes in an output tree */ struct rb_root rb_root_in; /* input tree of children */ struct rb_root rb_root; /* sorted output tree of children */ unsigned int val_nr; + unsigned int count; + unsigned int children_count; u64 hit; u64 children_hit; }; @@ -78,6 +83,12 @@ enum chain_key { CCKEY_ADDRESS }; +enum chain_value { + CCVAL_PERCENT, + CCVAL_PERIOD, + CCVAL_COUNT, +}; + struct callchain_param { bool enabled; enum perf_call_graph_mode record_mode; @@ -90,6 +101,7 @@ struct callchain_param { bool order_set; enum chain_key key; bool branch_callstack; + enum chain_value value; }; extern struct callchain_param callchain_param; @@ -131,6 +143,7 @@ extern __thread struct callchain_cursor callchain_cursor; static inline void callchain_init(struct callchain_root *root) { INIT_LIST_HEAD(&root->node.val); + INIT_LIST_HEAD(&root->node.parent_val); root->node.parent = NULL; root->node.hit = 0; @@ -144,6 +157,11 @@ static inline u64 callchain_cumul_hits(struct callchain_node *node) return node->hit + node->children_hit; } +static inline unsigned callchain_cumul_counts(struct callchain_node *node) +{ + return node->count + node->children_count; +} + int callchain_register_param(struct callchain_param *param); int callchain_append(struct callchain_root *root, struct callchain_cursor *cursor, @@ -229,7 +247,13 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused, char *callchain_list__sym_name(struct callchain_list *cl, char *bf, size_t bfsize, bool show_dso); +char *callchain_node__scnprintf_value(struct callchain_node *node, + char *bf, size_t bfsize, u64 total); +int callchain_node__fprintf_value(struct callchain_node *node, + FILE *fp, u64 total); void free_callchain(struct callchain_root *root); +void decay_callchain(struct callchain_root *root); +int callchain_node__make_parent_list(struct callchain_node *node); #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 32e12ecfe9c5..90aa1b46b2e5 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -1,6 +1,6 @@ #include "util.h" #include "../perf.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include "evsel.h" #include "cgroup.h" #include "evlist.h" diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 9b9565416f90..e5fb88bab9e1 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -24,7 +24,7 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty) auto_color: if (stdout_is_tty < 0) stdout_is_tty = isatty(1); - if (stdout_is_tty || (pager_in_use() && pager_use_color)) { + if (stdout_is_tty || pager_in_use()) { char *term = getenv("TERM"); if (term && strcmp(term, "dumb")) return 1; diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c index 2e452ac1353d..d3e12e30e1d5 100644 --- a/tools/perf/util/config.c +++ b/tools/perf/util/config.c @@ -10,7 +10,7 @@ */ #include "util.h" #include "cache.h" -#include "exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "util/hist.h" /* perf_hist_config */ #include "util/llvm-utils.h" /* perf_llvm_config */ diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 10af1e7524fb..fa935093a599 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -5,6 +5,7 @@ #include <assert.h> #include <stdio.h> #include <stdlib.h> +#include <linux/bitmap.h> #include "asm/bug.h" static struct cpu_map *cpu_map__default_new(void) @@ -179,6 +180,56 @@ out: return cpus; } +static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) +{ + struct cpu_map *map; + + map = cpu_map__empty_new(cpus->nr); + if (map) { + unsigned i; + + for (i = 0; i < cpus->nr; i++) { + /* + * Special treatment for -1, which is not real cpu number, + * and we need to use (int) -1 to initialize map[i], + * otherwise it would become 65535. + */ + if (cpus->cpu[i] == (u16) -1) + map->map[i] = -1; + else + map->map[i] = (int) cpus->cpu[i]; + } + } + + return map; +} + +static struct cpu_map *cpu_map__from_mask(struct cpu_map_mask *mask) +{ + struct cpu_map *map; + int nr, nbits = mask->nr * mask->long_size * BITS_PER_BYTE; + + nr = bitmap_weight(mask->mask, nbits); + + map = cpu_map__empty_new(nr); + if (map) { + int cpu, i = 0; + + for_each_set_bit(cpu, mask->mask, nbits) + map->map[i++] = cpu; + } + return map; + +} + +struct cpu_map *cpu_map__new_data(struct cpu_map_data *data) +{ + if (data->type == PERF_CPU_MAP__CPUS) + return cpu_map__from_entries((struct cpu_map_entries *)data->data); + else + return cpu_map__from_mask((struct cpu_map_mask *)data->data); +} + size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp) { int i; diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h index 85f7772457fa..71c41b9efabb 100644 --- a/tools/perf/util/cpumap.h +++ b/tools/perf/util/cpumap.h @@ -17,6 +17,7 @@ struct cpu_map { struct cpu_map *cpu_map__new(const char *cpu_list); struct cpu_map *cpu_map__empty_new(int nr); struct cpu_map *cpu_map__dummy_new(void); +struct cpu_map *cpu_map__new_data(struct cpu_map_data *data); struct cpu_map *cpu_map__read(FILE *file); size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp); int cpu_map__get_socket_id(int cpu); diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c index 5bfc1198ab46..34cd1e4039d3 100644 --- a/tools/perf/util/data-convert-bt.c +++ b/tools/perf/util/data-convert-bt.c @@ -63,6 +63,7 @@ struct ctf_writer { struct bt_ctf_field_type *s32; struct bt_ctf_field_type *u32; struct bt_ctf_field_type *string; + struct bt_ctf_field_type *u32_hex; struct bt_ctf_field_type *u64_hex; }; struct bt_ctf_field_type *array[6]; @@ -982,6 +983,7 @@ do { \ CREATE_INT_TYPE(cw->data.u64, 64, false, false); CREATE_INT_TYPE(cw->data.s32, 32, true, false); CREATE_INT_TYPE(cw->data.u32, 32, false, false); + CREATE_INT_TYPE(cw->data.u32_hex, 32, false, true); CREATE_INT_TYPE(cw->data.u64_hex, 64, false, true); cw->data.string = bt_ctf_field_type_string_create(); diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index 425df5c86c9c..e8e9a9dbf5e3 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -1243,6 +1243,8 @@ struct dso *__dsos__addnew(struct dsos *dsos, const char *name) if (dso != NULL) { __dsos__add(dsos, dso); dso__set_basename(dso); + /* Put dso here because __dsos_add already got it */ + dso__put(dso); } return dso; } diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 6af4f7c36820..7dd5939dea2e 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -25,15 +25,6 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]) { int i; - /* - * If env->cmdline_argv has already been set, do not override it. This allows - * a command to set the cmdline, parse args and then call another - * builtin function that implements a command -- e.g, cmd_kvm calling - * cmd_record. - */ - if (env->cmdline_argv != NULL) - return 0; - /* do not include NULL termination */ env->cmdline_argv = calloc(argc, sizeof(char *)); if (env->cmdline_argv == NULL) diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c deleted file mode 100644 index 7405123692f1..000000000000 --- a/tools/perf/util/environment.c +++ /dev/null @@ -1,8 +0,0 @@ -/* - * We put all the perf config variables in this same object - * file, so that programs can link against the config parser - * without having to link against all the rest of perf. - */ -#include "cache.h" - -int pager_use_color = 1; diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c index 8b10621b415c..cd61bb1f3917 100644 --- a/tools/perf/util/event.c +++ b/tools/perf/util/event.c @@ -10,6 +10,8 @@ #include "thread.h" #include "thread_map.h" #include "symbol/kallsyms.h" +#include "asm/bug.h" +#include "stat.h" static const char *perf_event__names[] = { [0] = "TOTAL", @@ -37,6 +39,12 @@ static const char *perf_event__names[] = { [PERF_RECORD_AUXTRACE_INFO] = "AUXTRACE_INFO", [PERF_RECORD_AUXTRACE] = "AUXTRACE", [PERF_RECORD_AUXTRACE_ERROR] = "AUXTRACE_ERROR", + [PERF_RECORD_THREAD_MAP] = "THREAD_MAP", + [PERF_RECORD_CPU_MAP] = "CPU_MAP", + [PERF_RECORD_STAT_CONFIG] = "STAT_CONFIG", + [PERF_RECORD_STAT] = "STAT", + [PERF_RECORD_STAT_ROUND] = "STAT_ROUND", + [PERF_RECORD_EVENT_UPDATE] = "EVENT_UPDATE", }; const char *perf_event__name(unsigned int id) @@ -699,6 +707,274 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, return err; } +int perf_event__synthesize_thread_map2(struct perf_tool *tool, + struct thread_map *threads, + perf_event__handler_t process, + struct machine *machine) +{ + union perf_event *event; + int i, err, size; + + size = sizeof(event->thread_map); + size += threads->nr * sizeof(event->thread_map.entries[0]); + + event = zalloc(size); + if (!event) + return -ENOMEM; + + event->header.type = PERF_RECORD_THREAD_MAP; + event->header.size = size; + event->thread_map.nr = threads->nr; + + for (i = 0; i < threads->nr; i++) { + struct thread_map_event_entry *entry = &event->thread_map.entries[i]; + char *comm = thread_map__comm(threads, i); + + if (!comm) + comm = (char *) ""; + + entry->pid = thread_map__pid(threads, i); + strncpy((char *) &entry->comm, comm, sizeof(entry->comm)); + } + + err = process(tool, event, NULL, machine); + + free(event); + return err; +} + +static void synthesize_cpus(struct cpu_map_entries *cpus, + struct cpu_map *map) +{ + int i; + + cpus->nr = map->nr; + + for (i = 0; i < map->nr; i++) + cpus->cpu[i] = map->map[i]; +} + +static void synthesize_mask(struct cpu_map_mask *mask, + struct cpu_map *map, int max) +{ + int i; + + mask->nr = BITS_TO_LONGS(max); + mask->long_size = sizeof(long); + + for (i = 0; i < map->nr; i++) + set_bit(map->map[i], mask->mask); +} + +static size_t cpus_size(struct cpu_map *map) +{ + return sizeof(struct cpu_map_entries) + map->nr * sizeof(u16); +} + +static size_t mask_size(struct cpu_map *map, int *max) +{ + int i; + + *max = 0; + + for (i = 0; i < map->nr; i++) { + /* bit possition of the cpu is + 1 */ + int bit = map->map[i] + 1; + + if (bit > *max) + *max = bit; + } + + return sizeof(struct cpu_map_mask) + BITS_TO_LONGS(*max) * sizeof(long); +} + +void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max) +{ + size_t size_cpus, size_mask; + bool is_dummy = cpu_map__empty(map); + + /* + * Both array and mask data have variable size based + * on the number of cpus and their actual values. + * The size of the 'struct cpu_map_data' is: + * + * array = size of 'struct cpu_map_entries' + + * number of cpus * sizeof(u64) + * + * mask = size of 'struct cpu_map_mask' + + * maximum cpu bit converted to size of longs + * + * and finaly + the size of 'struct cpu_map_data'. + */ + size_cpus = cpus_size(map); + size_mask = mask_size(map, max); + + if (is_dummy || (size_cpus < size_mask)) { + *size += size_cpus; + *type = PERF_CPU_MAP__CPUS; + } else { + *size += size_mask; + *type = PERF_CPU_MAP__MASK; + } + + *size += sizeof(struct cpu_map_data); + return zalloc(*size); +} + +void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, + u16 type, int max) +{ + data->type = type; + + switch (type) { + case PERF_CPU_MAP__CPUS: + synthesize_cpus((struct cpu_map_entries *) data->data, map); + break; + case PERF_CPU_MAP__MASK: + synthesize_mask((struct cpu_map_mask *) data->data, map, max); + default: + break; + }; +} + +static struct cpu_map_event* cpu_map_event__new(struct cpu_map *map) +{ + size_t size = sizeof(struct cpu_map_event); + struct cpu_map_event *event; + int max; + u16 type; + + event = cpu_map_data__alloc(map, &size, &type, &max); + if (!event) + return NULL; + + event->header.type = PERF_RECORD_CPU_MAP; + event->header.size = size; + event->data.type = type; + + cpu_map_data__synthesize(&event->data, map, type, max); + return event; +} + +int perf_event__synthesize_cpu_map(struct perf_tool *tool, + struct cpu_map *map, + perf_event__handler_t process, + struct machine *machine) +{ + struct cpu_map_event *event; + int err; + + event = cpu_map_event__new(map); + if (!event) + return -ENOMEM; + + err = process(tool, (union perf_event *) event, NULL, machine); + + free(event); + return err; +} + +int perf_event__synthesize_stat_config(struct perf_tool *tool, + struct perf_stat_config *config, + perf_event__handler_t process, + struct machine *machine) +{ + struct stat_config_event *event; + int size, i = 0, err; + + size = sizeof(*event); + size += (PERF_STAT_CONFIG_TERM__MAX * sizeof(event->data[0])); + + event = zalloc(size); + if (!event) + return -ENOMEM; + + event->header.type = PERF_RECORD_STAT_CONFIG; + event->header.size = size; + event->nr = PERF_STAT_CONFIG_TERM__MAX; + +#define ADD(__term, __val) \ + event->data[i].tag = PERF_STAT_CONFIG_TERM__##__term; \ + event->data[i].val = __val; \ + i++; + + ADD(AGGR_MODE, config->aggr_mode) + ADD(INTERVAL, config->interval) + ADD(SCALE, config->scale) + + WARN_ONCE(i != PERF_STAT_CONFIG_TERM__MAX, + "stat config terms unbalanced\n"); +#undef ADD + + err = process(tool, (union perf_event *) event, NULL, machine); + + free(event); + return err; +} + +int perf_event__synthesize_stat(struct perf_tool *tool, + u32 cpu, u32 thread, u64 id, + struct perf_counts_values *count, + perf_event__handler_t process, + struct machine *machine) +{ + struct stat_event event; + + event.header.type = PERF_RECORD_STAT; + event.header.size = sizeof(event); + event.header.misc = 0; + + event.id = id; + event.cpu = cpu; + event.thread = thread; + event.val = count->val; + event.ena = count->ena; + event.run = count->run; + + return process(tool, (union perf_event *) &event, NULL, machine); +} + +int perf_event__synthesize_stat_round(struct perf_tool *tool, + u64 evtime, u64 type, + perf_event__handler_t process, + struct machine *machine) +{ + struct stat_round_event event; + + event.header.type = PERF_RECORD_STAT_ROUND; + event.header.size = sizeof(event); + event.header.misc = 0; + + event.time = evtime; + event.type = type; + + return process(tool, (union perf_event *) &event, NULL, machine); +} + +void perf_event__read_stat_config(struct perf_stat_config *config, + struct stat_config_event *event) +{ + unsigned i; + + for (i = 0; i < event->nr; i++) { + + switch (event->data[i].tag) { +#define CASE(__term, __val) \ + case PERF_STAT_CONFIG_TERM__##__term: \ + config->__val = event->data[i].val; \ + break; + + CASE(AGGR_MODE, aggr_mode) + CASE(SCALE, scale) + CASE(INTERVAL, interval) +#undef CASE + default: + pr_warning("unknown stat config term %" PRIu64 "\n", + event->data[i].tag); + } + } +} + size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp) { const char *s; @@ -783,6 +1059,38 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp) event->mmap2.filename); } +size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp) +{ + struct thread_map *threads = thread_map__new_event(&event->thread_map); + size_t ret; + + ret = fprintf(fp, " nr: "); + + if (threads) + ret += thread_map__fprintf(threads, fp); + else + ret += fprintf(fp, "failed to get threads from event\n"); + + thread_map__put(threads); + return ret; +} + +size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp) +{ + struct cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data); + size_t ret; + + ret = fprintf(fp, " nr: "); + + if (cpus) + ret += cpu_map__fprintf(cpus, fp); + else + ret += fprintf(fp, "failed to get cpumap from event\n"); + + cpu_map__put(cpus); + return ret; +} + int perf_event__process_mmap(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_sample *sample, diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index a0dbcbd4f6d8..b7ffb7ee9971 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -226,6 +226,12 @@ enum perf_user_event_type { /* above any possible kernel type */ PERF_RECORD_AUXTRACE_INFO = 70, PERF_RECORD_AUXTRACE = 71, PERF_RECORD_AUXTRACE_ERROR = 72, + PERF_RECORD_THREAD_MAP = 73, + PERF_RECORD_CPU_MAP = 74, + PERF_RECORD_STAT_CONFIG = 75, + PERF_RECORD_STAT = 76, + PERF_RECORD_STAT_ROUND = 77, + PERF_RECORD_EVENT_UPDATE = 78, PERF_RECORD_HEADER_MAX }; @@ -270,12 +276,61 @@ struct events_stats { u32 nr_proc_map_timeout; }; +enum { + PERF_CPU_MAP__CPUS = 0, + PERF_CPU_MAP__MASK = 1, +}; + +struct cpu_map_entries { + u16 nr; + u16 cpu[]; +}; + +struct cpu_map_mask { + u16 nr; + u16 long_size; + unsigned long mask[]; +}; + +struct cpu_map_data { + u16 type; + char data[]; +}; + +struct cpu_map_event { + struct perf_event_header header; + struct cpu_map_data data; +}; + struct attr_event { struct perf_event_header header; struct perf_event_attr attr; u64 id[]; }; +enum { + PERF_EVENT_UPDATE__UNIT = 0, + PERF_EVENT_UPDATE__SCALE = 1, + PERF_EVENT_UPDATE__NAME = 2, + PERF_EVENT_UPDATE__CPUS = 3, +}; + +struct event_update_event_cpus { + struct cpu_map_data cpus; +}; + +struct event_update_event_scale { + double scale; +}; + +struct event_update_event { + struct perf_event_header header; + u64 type; + u64 id; + + char data[]; +}; + #define MAX_EVENT_NAME 64 struct perf_trace_event_type { @@ -356,6 +411,63 @@ struct context_switch_event { u32 next_prev_tid; }; +struct thread_map_event_entry { + u64 pid; + char comm[16]; +}; + +struct thread_map_event { + struct perf_event_header header; + u64 nr; + struct thread_map_event_entry entries[]; +}; + +enum { + PERF_STAT_CONFIG_TERM__AGGR_MODE = 0, + PERF_STAT_CONFIG_TERM__INTERVAL = 1, + PERF_STAT_CONFIG_TERM__SCALE = 2, + PERF_STAT_CONFIG_TERM__MAX = 3, +}; + +struct stat_config_event_entry { + u64 tag; + u64 val; +}; + +struct stat_config_event { + struct perf_event_header header; + u64 nr; + struct stat_config_event_entry data[]; +}; + +struct stat_event { + struct perf_event_header header; + + u64 id; + u32 cpu; + u32 thread; + + union { + struct { + u64 val; + u64 ena; + u64 run; + }; + u64 values[3]; + }; +}; + +enum { + PERF_STAT_ROUND_TYPE__INTERVAL = 0, + PERF_STAT_ROUND_TYPE__FINAL = 1, +}; + +struct stat_round_event { + struct perf_event_header header; + u64 type; + u64 time; +}; + union perf_event { struct perf_event_header header; struct mmap_event mmap; @@ -368,6 +480,7 @@ union perf_event { struct throttle_event throttle; struct sample_event sample; struct attr_event attr; + struct event_update_event event_update; struct event_type_event event_type; struct tracing_data_event tracing_data; struct build_id_event build_id; @@ -378,12 +491,20 @@ union perf_event { struct aux_event aux; struct itrace_start_event itrace_start; struct context_switch_event context_switch; + struct thread_map_event thread_map; + struct cpu_map_event cpu_map; + struct stat_config_event stat_config; + struct stat_event stat; + struct stat_round_event stat_round; }; void perf_event__print_totals(void); struct perf_tool; struct thread_map; +struct cpu_map; +struct perf_stat_config; +struct perf_counts_values; typedef int (*perf_event__handler_t)(struct perf_tool *tool, union perf_event *event, @@ -395,6 +516,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, unsigned int proc_map_timeout); +int perf_event__synthesize_thread_map2(struct perf_tool *tool, + struct thread_map *threads, + perf_event__handler_t process, + struct machine *machine); +int perf_event__synthesize_cpu_map(struct perf_tool *tool, + struct cpu_map *cpus, + perf_event__handler_t process, + struct machine *machine); int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool mmap_data, @@ -402,7 +531,21 @@ int perf_event__synthesize_threads(struct perf_tool *tool, int perf_event__synthesize_kernel_mmap(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); - +int perf_event__synthesize_stat_config(struct perf_tool *tool, + struct perf_stat_config *config, + perf_event__handler_t process, + struct machine *machine); +void perf_event__read_stat_config(struct perf_stat_config *config, + struct stat_config_event *event); +int perf_event__synthesize_stat(struct perf_tool *tool, + u32 cpu, u32 thread, u64 id, + struct perf_counts_values *count, + perf_event__handler_t process, + struct machine *machine); +int perf_event__synthesize_stat_round(struct perf_tool *tool, + u64 time, u64 type, + perf_event__handler_t process, + struct machine *machine); int perf_event__synthesize_modules(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine); @@ -499,9 +642,14 @@ size_t perf_event__fprintf_task(union perf_event *event, FILE *fp); size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp); size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp); size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp); size_t perf_event__fprintf(union perf_event *event, FILE *fp); u64 kallsyms__get_function_start(const char *kallsyms_filename, const char *symbol_name); +void *cpu_map_data__alloc(struct cpu_map *map, size_t *size, u16 *type, int *max); +void cpu_map_data__synthesize(struct cpu_map_data *data, struct cpu_map *map, + u16 type, int max); #endif /* __PERF_RECORD_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index d1392194a9a9..d81f13de2476 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -18,7 +18,7 @@ #include <unistd.h> #include "parse-events.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include <sys/mman.h> @@ -68,6 +68,18 @@ struct perf_evlist *perf_evlist__new_default(void) return evlist; } +struct perf_evlist *perf_evlist__new_dummy(void) +{ + struct perf_evlist *evlist = perf_evlist__new(); + + if (evlist && perf_evlist__add_dummy(evlist)) { + perf_evlist__delete(evlist); + evlist = NULL; + } + + return evlist; +} + /** * perf_evlist__set_id_pos - set the positions of event ids. * @evlist: selected event list @@ -248,6 +260,22 @@ error: return -ENOMEM; } +int perf_evlist__add_dummy(struct perf_evlist *evlist) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_DUMMY, + .size = sizeof(attr), /* to capture ABI version */ + }; + struct perf_evsel *evsel = perf_evsel__new(&attr); + + if (evsel == NULL) + return -ENOMEM; + + perf_evlist__add(evlist, evsel); + return 0; +} + static int perf_evlist__add_attrs(struct perf_evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { @@ -336,20 +364,12 @@ static int perf_evlist__nr_threads(struct perf_evlist *evlist, void perf_evlist__disable(struct perf_evlist *evlist) { - int cpu, thread; struct perf_evsel *pos; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads; - for (cpu = 0; cpu < nr_cpus; cpu++) { - evlist__for_each(evlist, pos) { - if (!perf_evsel__is_group_leader(pos) || !pos->fd) - continue; - nr_threads = perf_evlist__nr_threads(evlist, pos); - for (thread = 0; thread < nr_threads; thread++) - ioctl(FD(pos, cpu, thread), - PERF_EVENT_IOC_DISABLE, 0); - } + evlist__for_each(evlist, pos) { + if (!perf_evsel__is_group_leader(pos) || !pos->fd) + continue; + perf_evsel__disable(pos); } evlist->enabled = false; @@ -357,20 +377,12 @@ void perf_evlist__disable(struct perf_evlist *evlist) void perf_evlist__enable(struct perf_evlist *evlist) { - int cpu, thread; struct perf_evsel *pos; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads; - for (cpu = 0; cpu < nr_cpus; cpu++) { - evlist__for_each(evlist, pos) { - if (!perf_evsel__is_group_leader(pos) || !pos->fd) - continue; - nr_threads = perf_evlist__nr_threads(evlist, pos); - for (thread = 0; thread < nr_threads; thread++) - ioctl(FD(pos, cpu, thread), - PERF_EVENT_IOC_ENABLE, 0); - } + evlist__for_each(evlist, pos) { + if (!perf_evsel__is_group_leader(pos) || !pos->fd) + continue; + perf_evsel__enable(pos); } evlist->enabled = true; @@ -381,48 +393,6 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist) (evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist); } -int perf_evlist__disable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel) -{ - int cpu, thread, err; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = perf_evlist__nr_threads(evlist, evsel); - - if (!evsel->fd) - return 0; - - for (cpu = 0; cpu < nr_cpus; cpu++) { - for (thread = 0; thread < nr_threads; thread++) { - err = ioctl(FD(evsel, cpu, thread), - PERF_EVENT_IOC_DISABLE, 0); - if (err) - return err; - } - } - return 0; -} - -int perf_evlist__enable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel) -{ - int cpu, thread, err; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = perf_evlist__nr_threads(evlist, evsel); - - if (!evsel->fd) - return -EINVAL; - - for (cpu = 0; cpu < nr_cpus; cpu++) { - for (thread = 0; thread < nr_threads; thread++) { - err = ioctl(FD(evsel, cpu, thread), - PERF_EVENT_IOC_ENABLE, 0); - if (err) - return err; - } - } - return 0; -} - static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu) { @@ -550,9 +520,9 @@ void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, evsel->id[evsel->ids++] = id; } -static int perf_evlist__id_add_fd(struct perf_evlist *evlist, - struct perf_evsel *evsel, - int cpu, int thread, int fd) +int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd) { u64 read_data[4] = { 0, }; int id_idx = 1; /* The first entry is the counter value */ @@ -1486,7 +1456,7 @@ int perf_evlist__open(struct perf_evlist *evlist) perf_evlist__update_id_pos(evlist); evlist__for_each(evlist, evsel) { - err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); + err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); if (err < 0) goto out_err; } diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a459fe71b452..7c4d9a206776 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -67,6 +67,7 @@ struct perf_evsel_str_handler { struct perf_evlist *perf_evlist__new(void); struct perf_evlist *perf_evlist__new_default(void); +struct perf_evlist *perf_evlist__new_dummy(void); void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads); void perf_evlist__exit(struct perf_evlist *evlist); @@ -81,6 +82,8 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, #define perf_evlist__add_default_attrs(evlist, array) \ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) +int perf_evlist__add_dummy(struct perf_evlist *evlist); + int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); @@ -97,6 +100,9 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist, void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu, int thread, u64 id); +int perf_evlist__id_add_fd(struct perf_evlist *evlist, + struct perf_evsel *evsel, + int cpu, int thread, int fd); int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd); int perf_evlist__alloc_pollfd(struct perf_evlist *evlist); @@ -149,10 +155,6 @@ void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); void perf_evlist__toggle_enable(struct perf_evlist *evlist); -int perf_evlist__disable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel); -int perf_evlist__enable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel); int perf_evlist__enable_event_idx(struct perf_evlist *evlist, struct perf_evsel *evsel, int idx); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 397fb4ed3c97..cdbaf9b51e42 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -36,6 +36,7 @@ static struct { bool cloexec; bool clockid; bool clockid_wrong; + bool lbr_flags; } perf_missing_features; static clockid_t clockid; @@ -574,7 +575,9 @@ perf_evsel__config_callgraph(struct perf_evsel *evsel, } else { perf_evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER | - PERF_SAMPLE_BRANCH_CALL_STACK; + PERF_SAMPLE_BRANCH_CALL_STACK | + PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_NO_FLAGS; } } else pr_warning("Cannot use LBR callstack with branch stack. " @@ -981,13 +984,26 @@ int perf_evsel__append_filter(struct perf_evsel *evsel, return -1; } -int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads) +int perf_evsel__enable(struct perf_evsel *evsel) { + int nthreads = thread_map__nr(evsel->threads); + int ncpus = cpu_map__nr(evsel->cpus); + return perf_evsel__run_ioctl(evsel, ncpus, nthreads, PERF_EVENT_IOC_ENABLE, 0); } +int perf_evsel__disable(struct perf_evsel *evsel) +{ + int nthreads = thread_map__nr(evsel->threads); + int ncpus = cpu_map__nr(evsel->cpus); + + return perf_evsel__run_ioctl(evsel, ncpus, nthreads, + PERF_EVENT_IOC_DISABLE, + 0); +} + int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads) { if (ncpus == 0 || nthreads == 0) @@ -1192,6 +1208,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value) bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW), bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER), bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC), + bit_name(WEIGHT), { .name = NULL, } }; #undef bit_name @@ -1323,6 +1340,9 @@ fallback_missing_features: evsel->attr.mmap2 = 0; if (perf_missing_features.exclude_guest) evsel->attr.exclude_guest = evsel->attr.exclude_host = 0; + if (perf_missing_features.lbr_flags) + evsel->attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | + PERF_SAMPLE_BRANCH_NO_CYCLES); retry_sample_id: if (perf_missing_features.sample_id_all) evsel->attr.sample_id_all = 0; @@ -1441,6 +1461,12 @@ try_fallback: } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; goto retry_sample_id; + } else if (!perf_missing_features.lbr_flags && + (evsel->attr.branch_sample_type & + (PERF_SAMPLE_BRANCH_NO_CYCLES | + PERF_SAMPLE_BRANCH_NO_FLAGS))) { + perf_missing_features.lbr_flags = true; + goto fallback_missing_features; } out_close: @@ -2272,6 +2298,29 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += comma_fprintf(fp, &first, " %s=%" PRIu64, term, (u64)evsel->attr.sample_freq); } + + if (details->trace_fields) { + struct format_field *field; + + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + printed += comma_fprintf(fp, &first, " (not a tracepoint)"); + goto out; + } + + field = evsel->tp_format->format.fields; + if (field == NULL) { + printed += comma_fprintf(fp, &first, " (no trace field)"); + goto out; + } + + printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name); + + field = field->next; + while (field) { + printed += comma_fprintf(fp, &first, "%s", field->name); + field = field->next; + } + } out: fputc('\n', fp); return ++printed; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 0e49bd742c63..8e75434bd01c 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -227,7 +227,8 @@ int perf_evsel__append_filter(struct perf_evsel *evsel, const char *op, const char *filter); int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads, const char *filter); -int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads); +int perf_evsel__enable(struct perf_evsel *evsel); +int perf_evsel__disable(struct perf_evsel *evsel); int perf_evsel__open_per_cpu(struct perf_evsel *evsel, struct cpu_map *cpus); @@ -368,6 +369,7 @@ struct perf_attr_details { bool verbose; bool event_group; bool force; + bool trace_fields; }; int perf_evsel__fprintf(struct perf_evsel *evsel, diff --git a/tools/perf/util/exec_cmd.c b/tools/perf/util/exec_cmd.c deleted file mode 100644 index 7adf4ad15d8f..000000000000 --- a/tools/perf/util/exec_cmd.c +++ /dev/null @@ -1,148 +0,0 @@ -#include "cache.h" -#include "exec_cmd.h" -#include "quote.h" - -#include <string.h> - -#define MAX_ARGS 32 - -static const char *argv_exec_path; -static const char *argv0_path; - -const char *system_path(const char *path) -{ - static const char *prefix = PREFIX; - struct strbuf d = STRBUF_INIT; - - if (is_absolute_path(path)) - return path; - - strbuf_addf(&d, "%s/%s", prefix, path); - path = strbuf_detach(&d, NULL); - return path; -} - -const char *perf_extract_argv0_path(const char *argv0) -{ - const char *slash; - - if (!argv0 || !*argv0) - return NULL; - slash = argv0 + strlen(argv0); - - while (argv0 <= slash && !is_dir_sep(*slash)) - slash--; - - if (slash >= argv0) { - argv0_path = strndup(argv0, slash - argv0); - return argv0_path ? slash + 1 : NULL; - } - - return argv0; -} - -void perf_set_argv_exec_path(const char *exec_path) -{ - argv_exec_path = exec_path; - /* - * Propagate this setting to external programs. - */ - setenv(EXEC_PATH_ENVIRONMENT, exec_path, 1); -} - - -/* Returns the highest-priority, location to look for perf programs. */ -const char *perf_exec_path(void) -{ - const char *env; - - if (argv_exec_path) - return argv_exec_path; - - env = getenv(EXEC_PATH_ENVIRONMENT); - if (env && *env) { - return env; - } - - return system_path(PERF_EXEC_PATH); -} - -static void add_path(struct strbuf *out, const char *path) -{ - if (path && *path) { - if (is_absolute_path(path)) - strbuf_addstr(out, path); - else - strbuf_addstr(out, make_nonrelative_path(path)); - - strbuf_addch(out, PATH_SEP); - } -} - -void setup_path(void) -{ - const char *old_path = getenv("PATH"); - struct strbuf new_path = STRBUF_INIT; - - add_path(&new_path, perf_exec_path()); - add_path(&new_path, argv0_path); - - if (old_path) - strbuf_addstr(&new_path, old_path); - else - strbuf_addstr(&new_path, "/usr/local/bin:/usr/bin:/bin"); - - setenv("PATH", new_path.buf, 1); - - strbuf_release(&new_path); -} - -static const char **prepare_perf_cmd(const char **argv) -{ - int argc; - const char **nargv; - - for (argc = 0; argv[argc]; argc++) - ; /* just counting */ - nargv = malloc(sizeof(*nargv) * (argc + 2)); - - nargv[0] = "perf"; - for (argc = 0; argv[argc]; argc++) - nargv[argc + 1] = argv[argc]; - nargv[argc + 1] = NULL; - return nargv; -} - -int execv_perf_cmd(const char **argv) { - const char **nargv = prepare_perf_cmd(argv); - - /* execvp() can only ever return if it fails */ - execvp("perf", (char **)nargv); - - free(nargv); - return -1; -} - - -int execl_perf_cmd(const char *cmd,...) -{ - int argc; - const char *argv[MAX_ARGS + 1]; - const char *arg; - va_list param; - - va_start(param, cmd); - argv[0] = cmd; - argc = 1; - while (argc < MAX_ARGS) { - arg = argv[argc++] = va_arg(param, char *); - if (!arg) - break; - } - va_end(param); - if (MAX_ARGS <= argc) - return error("too many args to run %s", cmd); - - argv[argc] = NULL; - return execv_perf_cmd(argv); -} diff --git a/tools/perf/util/exec_cmd.h b/tools/perf/util/exec_cmd.h deleted file mode 100644 index bc4b915963f5..000000000000 --- a/tools/perf/util/exec_cmd.h +++ /dev/null @@ -1,12 +0,0 @@ -#ifndef __PERF_EXEC_CMD_H -#define __PERF_EXEC_CMD_H - -extern void perf_set_argv_exec_path(const char *exec_path); -extern const char *perf_extract_argv0_path(const char *path); -extern const char *perf_exec_path(void); -extern void setup_path(void); -extern int execv_perf_cmd(const char **argv); /* NULL terminated */ -extern int execl_perf_cmd(const char *cmd, ...); -extern const char *system_path(const char *path); - -#endif /* __PERF_EXEC_CMD_H */ diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 36a885d2cd22..0ac2037c970c 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -36,4 +36,19 @@ do }' "Documentation/perf-$cmd.txt" done echo "#endif /* HAVE_LIBELF_SUPPORT */" + +echo "#ifdef HAVE_LIBAUDIT_SUPPORT" +sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "#endif /* HAVE_LIBELF_SUPPORT */" echo "};" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 43838003c1a1..f50b7235ecb6 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -724,7 +724,7 @@ static int write_numa_topology(int fd, struct perf_header *h __maybe_unused, done: free(buf); fclose(fp); - free(node_map); + cpu_map__put(node_map); return ret; } @@ -868,6 +868,13 @@ static int write_auxtrace(int fd, struct perf_header *h, return err; } +static int write_stat(int fd __maybe_unused, + struct perf_header *h __maybe_unused, + struct perf_evlist *evlist __maybe_unused) +{ + return 0; +} + static void print_hostname(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { @@ -1159,6 +1166,12 @@ static void print_auxtrace(struct perf_header *ph __maybe_unused, fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n"); } +static void print_stat(struct perf_header *ph __maybe_unused, + int fd __maybe_unused, FILE *fp) +{ + fprintf(fp, "# contains stat data\n"); +} + static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused, FILE *fp) { @@ -1948,6 +1961,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = { FEAT_OPP(HEADER_PMU_MAPPINGS, pmu_mappings), FEAT_OPP(HEADER_GROUP_DESC, group_desc), FEAT_OPP(HEADER_AUXTRACE, auxtrace), + FEAT_OPA(HEADER_STAT, stat), }; struct header_print_data { @@ -2686,6 +2700,152 @@ int perf_event__synthesize_attr(struct perf_tool *tool, return err; } +static struct event_update_event * +event_update_event__new(size_t size, u64 type, u64 id) +{ + struct event_update_event *ev; + + size += sizeof(*ev); + size = PERF_ALIGN(size, sizeof(u64)); + + ev = zalloc(size); + if (ev) { + ev->header.type = PERF_RECORD_EVENT_UPDATE; + ev->header.size = (u16)size; + ev->type = type; + ev->id = id; + } + return ev; +} + +int +perf_event__synthesize_event_update_unit(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process) +{ + struct event_update_event *ev; + size_t size = strlen(evsel->unit); + int err; + + ev = event_update_event__new(size + 1, PERF_EVENT_UPDATE__UNIT, evsel->id[0]); + if (ev == NULL) + return -ENOMEM; + + strncpy(ev->data, evsel->unit, size); + err = process(tool, (union perf_event *)ev, NULL, NULL); + free(ev); + return err; +} + +int +perf_event__synthesize_event_update_scale(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process) +{ + struct event_update_event *ev; + struct event_update_event_scale *ev_data; + int err; + + ev = event_update_event__new(sizeof(*ev_data), PERF_EVENT_UPDATE__SCALE, evsel->id[0]); + if (ev == NULL) + return -ENOMEM; + + ev_data = (struct event_update_event_scale *) ev->data; + ev_data->scale = evsel->scale; + err = process(tool, (union perf_event*) ev, NULL, NULL); + free(ev); + return err; +} + +int +perf_event__synthesize_event_update_name(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process) +{ + struct event_update_event *ev; + size_t len = strlen(evsel->name); + int err; + + ev = event_update_event__new(len + 1, PERF_EVENT_UPDATE__NAME, evsel->id[0]); + if (ev == NULL) + return -ENOMEM; + + strncpy(ev->data, evsel->name, len); + err = process(tool, (union perf_event*) ev, NULL, NULL); + free(ev); + return err; +} + +int +perf_event__synthesize_event_update_cpus(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process) +{ + size_t size = sizeof(struct event_update_event); + struct event_update_event *ev; + int max, err; + u16 type; + + if (!evsel->own_cpus) + return 0; + + ev = cpu_map_data__alloc(evsel->own_cpus, &size, &type, &max); + if (!ev) + return -ENOMEM; + + ev->header.type = PERF_RECORD_EVENT_UPDATE; + ev->header.size = (u16)size; + ev->type = PERF_EVENT_UPDATE__CPUS; + ev->id = evsel->id[0]; + + cpu_map_data__synthesize((struct cpu_map_data *) ev->data, + evsel->own_cpus, + type, max); + + err = process(tool, (union perf_event*) ev, NULL, NULL); + free(ev); + return err; +} + +size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) +{ + struct event_update_event *ev = &event->event_update; + struct event_update_event_scale *ev_scale; + struct event_update_event_cpus *ev_cpus; + struct cpu_map *map; + size_t ret; + + ret = fprintf(fp, "\n... id: %" PRIu64 "\n", ev->id); + + switch (ev->type) { + case PERF_EVENT_UPDATE__SCALE: + ev_scale = (struct event_update_event_scale *) ev->data; + ret += fprintf(fp, "... scale: %f\n", ev_scale->scale); + break; + case PERF_EVENT_UPDATE__UNIT: + ret += fprintf(fp, "... unit: %s\n", ev->data); + break; + case PERF_EVENT_UPDATE__NAME: + ret += fprintf(fp, "... name: %s\n", ev->data); + break; + case PERF_EVENT_UPDATE__CPUS: + ev_cpus = (struct event_update_event_cpus *) ev->data; + ret += fprintf(fp, "... "); + + map = cpu_map__new_data(&ev_cpus->cpus); + if (map) + ret += cpu_map__fprintf(map, fp); + else + ret += fprintf(fp, "failed to get cpus\n"); + break; + default: + ret += fprintf(fp, "... unknown type\n"); + break; + } + + return ret; +} + int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process) @@ -2745,6 +2905,51 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused, return 0; } +int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_evlist **pevlist) +{ + struct event_update_event *ev = &event->event_update; + struct event_update_event_scale *ev_scale; + struct event_update_event_cpus *ev_cpus; + struct perf_evlist *evlist; + struct perf_evsel *evsel; + struct cpu_map *map; + + if (!pevlist || *pevlist == NULL) + return -EINVAL; + + evlist = *pevlist; + + evsel = perf_evlist__id2evsel(evlist, ev->id); + if (evsel == NULL) + return -EINVAL; + + switch (ev->type) { + case PERF_EVENT_UPDATE__UNIT: + evsel->unit = strdup(ev->data); + break; + case PERF_EVENT_UPDATE__NAME: + evsel->name = strdup(ev->data); + break; + case PERF_EVENT_UPDATE__SCALE: + ev_scale = (struct event_update_event_scale *) ev->data; + evsel->scale = ev_scale->scale; + case PERF_EVENT_UPDATE__CPUS: + ev_cpus = (struct event_update_event_cpus *) ev->data; + + map = cpu_map__new_data(&ev_cpus->cpus); + if (map) + evsel->own_cpus = map; + else + pr_err("failed to get event_update cpus\n"); + default: + break; + } + + return 0; +} + int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, perf_event__handler_t process) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 05f27cb6b7e3..cff9892452ee 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -31,6 +31,7 @@ enum { HEADER_PMU_MAPPINGS, HEADER_GROUP_DESC, HEADER_AUXTRACE, + HEADER_STAT, HEADER_LAST_FEATURE, HEADER_FEAT_BITS = 256, }; @@ -105,8 +106,24 @@ int perf_event__synthesize_attr(struct perf_tool *tool, int perf_event__synthesize_attrs(struct perf_tool *tool, struct perf_session *session, perf_event__handler_t process); +int perf_event__synthesize_event_update_unit(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process); +int perf_event__synthesize_event_update_scale(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process); +int perf_event__synthesize_event_update_name(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process); +int perf_event__synthesize_event_update_cpus(struct perf_tool *tool, + struct perf_evsel *evsel, + perf_event__handler_t process); int perf_event__process_attr(struct perf_tool *tool, union perf_event *event, struct perf_evlist **pevlist); +int perf_event__process_event_update(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_evlist **pevlist); +size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp); int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd, struct perf_evlist *evlist, diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c new file mode 100644 index 000000000000..dc1e41c9b054 --- /dev/null +++ b/tools/perf/util/help-unknown-cmd.c @@ -0,0 +1,103 @@ +#include "cache.h" +#include <subcmd/help.h> +#include "../builtin.h" +#include "levenshtein.h" + +static int autocorrect; +static struct cmdnames aliases; + +static int perf_unknown_cmd_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, "help.autocorrect")) + autocorrect = perf_config_int(var,value); + /* Also use aliases for command lookup */ + if (!prefixcmp(var, "alias.")) + add_cmdname(&aliases, var + 6, strlen(var + 6)); + + return perf_default_config(var, value, cb); +} + +static int levenshtein_compare(const void *p1, const void *p2) +{ + const struct cmdname *const *c1 = p1, *const *c2 = p2; + const char *s1 = (*c1)->name, *s2 = (*c2)->name; + int l1 = (*c1)->len; + int l2 = (*c2)->len; + return l1 != l2 ? l1 - l2 : strcmp(s1, s2); +} + +static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old) +{ + unsigned int i; + + ALLOC_GROW(cmds->names, cmds->cnt + old->cnt, cmds->alloc); + + for (i = 0; i < old->cnt; i++) + cmds->names[cmds->cnt++] = old->names[i]; + zfree(&old->names); + old->cnt = 0; +} + +const char *help_unknown_cmd(const char *cmd) +{ + unsigned int i, n = 0, best_similarity = 0; + struct cmdnames main_cmds, other_cmds; + + memset(&main_cmds, 0, sizeof(main_cmds)); + memset(&other_cmds, 0, sizeof(main_cmds)); + memset(&aliases, 0, sizeof(aliases)); + + perf_config(perf_unknown_cmd_config, NULL); + + load_command_list("perf-", &main_cmds, &other_cmds); + + add_cmd_list(&main_cmds, &aliases); + add_cmd_list(&main_cmds, &other_cmds); + qsort(main_cmds.names, main_cmds.cnt, + sizeof(main_cmds.names), cmdname_compare); + uniq(&main_cmds); + + if (main_cmds.cnt) { + /* This reuses cmdname->len for similarity index */ + for (i = 0; i < main_cmds.cnt; ++i) + main_cmds.names[i]->len = + levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4); + + qsort(main_cmds.names, main_cmds.cnt, + sizeof(*main_cmds.names), levenshtein_compare); + + best_similarity = main_cmds.names[0]->len; + n = 1; + while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len) + ++n; + } + + if (autocorrect && n == 1) { + const char *assumed = main_cmds.names[0]->name; + + main_cmds.names[0] = NULL; + clean_cmdnames(&main_cmds); + fprintf(stderr, "WARNING: You called a perf program named '%s', " + "which does not exist.\n" + "Continuing under the assumption that you meant '%s'\n", + cmd, assumed); + if (autocorrect > 0) { + fprintf(stderr, "in %0.1f seconds automatically...\n", + (float)autocorrect/10.0); + poll(NULL, 0, autocorrect * 100); + } + return assumed; + } + + fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd); + + if (main_cmds.cnt && best_similarity < 6) { + fprintf(stderr, "\nDid you mean %s?\n", + n < 2 ? "this": "one of these"); + + for (i = 0; i < n; i++) + fprintf(stderr, "\t%s\n", main_cmds.names[i]->name); + } + + exit(1); +} diff --git a/tools/perf/util/help-unknown-cmd.h b/tools/perf/util/help-unknown-cmd.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/perf/util/help-unknown-cmd.h diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 4fd37d6708cb..c226303e3da0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -254,6 +254,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) he_stat__decay(&he->stat); if (symbol_conf.cumulate_callchain) he_stat__decay(he->stat_acc); + decay_callchain(he->callchain); diff = prev_period - he->stat.period; @@ -270,6 +271,8 @@ static void hists__delete_entry(struct hists *hists, struct hist_entry *he) if (sort__need_collapse) rb_erase(&he->rb_node_in, &hists->entries_collapsed); + else + rb_erase(&he->rb_node_in, hists->entries_in); --hists->nr_entries; if (!he->filtered) @@ -367,6 +370,25 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, if (symbol_conf.use_callchain) callchain_init(he->callchain); + if (he->raw_data) { + he->raw_data = memdup(he->raw_data, he->raw_size); + + if (he->raw_data == NULL) { + map__put(he->ms.map); + if (he->branch_info) { + map__put(he->branch_info->from.map); + map__put(he->branch_info->to.map); + free(he->branch_info); + } + if (he->mem_info) { + map__put(he->mem_info->iaddr.map); + map__put(he->mem_info->daddr.map); + } + free(he->stat_acc); + free(he); + return NULL; + } + } INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); } @@ -459,7 +481,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, - u64 period, u64 weight, u64 transaction, + struct perf_sample *sample, bool sample_self) { struct hist_entry entry = { @@ -476,15 +498,17 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .level = al->level, .stat = { .nr_events = 1, - .period = period, - .weight = weight, + .period = sample->period, + .weight = sample->weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, .hists = hists, .branch_info = bi, .mem_info = mi, - .transaction = transaction, + .transaction = sample->transaction, + .raw_data = sample->raw_data, + .raw_size = sample->raw_size, }; return hists__findnew_entry(hists, &entry, al, sample_self); @@ -524,12 +548,13 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al u64 cost; struct mem_info *mi = iter->priv; struct hists *hists = evsel__hists(iter->evsel); + struct perf_sample *sample = iter->sample; struct hist_entry *he; if (mi == NULL) return -EINVAL; - cost = iter->sample->weight; + cost = sample->weight; if (!cost) cost = 1; @@ -540,8 +565,10 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al * and this is indirectly achieved by passing period=weight here * and the he_stat__add_period() function. */ + sample->period = cost; + he = __hists__add_entry(hists, al, iter->parent, NULL, mi, - cost, cost, 0, true); + sample, true); if (!he) return -ENOMEM; @@ -628,6 +655,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a struct branch_info *bi; struct perf_evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); + struct perf_sample *sample = iter->sample; struct hist_entry *he = NULL; int i = iter->curr; int err = 0; @@ -641,9 +669,11 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a * The report shows the percentage of total branches captured * and not events sampled. Thus we use a pseudo period of 1. */ + sample->period = 1; + sample->weight = bi->flags.cycles ? bi->flags.cycles : 1; + he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL, - 1, bi->flags.cycles ? bi->flags.cycles : 1, - 0, true); + sample, true); if (he == NULL) return -ENOMEM; @@ -680,8 +710,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location struct hist_entry *he; he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction, true); + sample, true); if (he == NULL) return -ENOMEM; @@ -742,8 +771,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, int err = 0; he = __hists__add_entry(hists, al, iter->parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction, true); + sample, true); if (he == NULL) return -ENOMEM; @@ -795,6 +823,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .sym = al->sym, }, .parent = iter->parent, + .raw_data = sample->raw_data, + .raw_size = sample->raw_size, }; int i; struct callchain_cursor cursor; @@ -816,8 +846,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, } he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction, false); + sample, false); if (he == NULL) return -ENOMEM; @@ -924,9 +953,6 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right) int64_t cmp = 0; perf_hpp__for_each_sort_list(fmt) { - if (perf_hpp__should_skip(fmt)) - continue; - cmp = fmt->cmp(fmt, left, right); if (cmp) break; @@ -942,9 +968,6 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right) int64_t cmp = 0; perf_hpp__for_each_sort_list(fmt) { - if (perf_hpp__should_skip(fmt)) - continue; - cmp = fmt->collapse(fmt, left, right); if (cmp) break; @@ -975,6 +998,8 @@ void hist_entry__delete(struct hist_entry *he) if (he->srcfile && he->srcfile[0]) free(he->srcfile); free_callchain(he->callchain); + free(he->trace_output); + free(he->raw_data); free(he); } @@ -982,9 +1007,8 @@ void hist_entry__delete(struct hist_entry *he) * collapse the histogram */ -static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, - struct rb_root *root, - struct hist_entry *he) +bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, + struct rb_root *root, struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -1024,7 +1048,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, return true; } -static struct rb_root *hists__get_rotate_entries_in(struct hists *hists) +struct rb_root *hists__get_rotate_entries_in(struct hists *hists) { struct rb_root *root; @@ -1088,7 +1112,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) int64_t cmp = 0; perf_hpp__for_each_sort_list(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, a->hists)) continue; cmp = fmt->sort(fmt, a, b); @@ -1559,10 +1583,8 @@ int perf_hist_config(const char *var, const char *value) return 0; } -static int hists_evsel__init(struct perf_evsel *evsel) +int __hists__init(struct hists *hists) { - struct hists *hists = evsel__hists(evsel); - memset(hists, 0, sizeof(*hists)); hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; hists->entries_in = &hists->entries_in_array[0]; @@ -1573,6 +1595,43 @@ static int hists_evsel__init(struct perf_evsel *evsel) return 0; } +static void hists__delete_remaining_entries(struct rb_root *root) +{ + struct rb_node *node; + struct hist_entry *he; + + while (!RB_EMPTY_ROOT(root)) { + node = rb_first(root); + rb_erase(node, root); + + he = rb_entry(node, struct hist_entry, rb_node_in); + hist_entry__delete(he); + } +} + +static void hists__delete_all_entries(struct hists *hists) +{ + hists__delete_entries(hists); + hists__delete_remaining_entries(&hists->entries_in_array[0]); + hists__delete_remaining_entries(&hists->entries_in_array[1]); + hists__delete_remaining_entries(&hists->entries_collapsed); +} + +static void hists_evsel__exit(struct perf_evsel *evsel) +{ + struct hists *hists = evsel__hists(evsel); + + hists__delete_all_entries(hists); +} + +static int hists_evsel__init(struct perf_evsel *evsel) +{ + struct hists *hists = evsel__hists(evsel); + + __hists__init(hists); + return 0; +} + /* * XXX We probably need a hists_evsel__exit() to free the hist_entries * stored in the rbtree... @@ -1581,7 +1640,8 @@ static int hists_evsel__init(struct perf_evsel *evsel) int hists__init(void) { int err = perf_evsel__object_config(sizeof(struct hists_evsel), - hists_evsel__init, NULL); + hists_evsel__init, + hists_evsel__exit); if (err) fputs("FATAL ERROR: Couldn't setup hists class\n", stderr); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a48a2078d288..d4ec4822a103 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -52,6 +52,7 @@ enum hist_column { HISTC_MEM_IADDR_SYMBOL, HISTC_TRANSACTION, HISTC_CYCLES, + HISTC_TRACE, HISTC_NR_COLS, /* Last entry */ }; @@ -114,8 +115,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, struct symbol *parent, struct branch_info *bi, - struct mem_info *mi, u64 period, - u64 weight, u64 transaction, + struct mem_info *mi, + struct perf_sample *sample, bool sample_self); int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int max_stack_depth, void *arg); @@ -184,6 +185,11 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) } int hists__init(void); +int __hists__init(struct hists *hists); + +struct rb_root *hists__get_rotate_entries_in(struct hists *hists); +bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, + struct rb_root *root, struct hist_entry *he); struct perf_hpp { char *buf; @@ -261,10 +267,20 @@ void perf_hpp__append_sort_keys(void); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); +bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format); +bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists); -static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format, + struct hists *hists) { - return format->elide; + if (format->elide) + return true; + + if (perf_hpp__is_dynamic_entry(format) && + !perf_hpp__defined_dynamic_entry(format, hists)) + return true; + + return false; } void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h deleted file mode 100644 index 6f19c548ecc0..000000000000 --- a/tools/perf/util/include/linux/string.h +++ /dev/null @@ -1,3 +0,0 @@ -#include <string.h> - -void *memdup(const void *src, size_t len); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 97f963a3dcb9..81a2eb77ba7f 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1744,7 +1744,7 @@ static void intel_pt_free(struct perf_session *session) auxtrace_heap__free(&pt->heap); intel_pt_free_events(session); session->auxtrace = NULL; - thread__delete(pt->unknown_thread); + thread__put(pt->unknown_thread); free(pt); } @@ -2153,7 +2153,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event, return 0; err_delete_thread: - thread__delete(pt->unknown_thread); + thread__zput(pt->unknown_thread); err_free_queues: intel_pt_log_disable(); auxtrace_queues__free(&pt->queues); diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 8b303ff20289..ad79297c76c8 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -25,6 +25,7 @@ static void dsos__init(struct dsos *dsos) int machine__init(struct machine *machine, const char *root_dir, pid_t pid) { + memset(machine, 0, sizeof(*machine)); map_groups__init(&machine->kmaps, machine); RB_CLEAR_NODE(&machine->rb_node); dsos__init(&machine->dsos); @@ -44,6 +45,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid) machine->comm_exec = false; machine->kernel_start = 0; + memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps)); + machine->root_dir = strdup(root_dir); if (machine->root_dir == NULL) return -ENOMEM; @@ -122,6 +125,7 @@ void machine__delete_threads(struct machine *machine) void machine__exit(struct machine *machine) { + machine__destroy_kernel_maps(machine); map_groups__exit(&machine->kmaps); dsos__exit(&machine->dsos); machine__exit_vdso(machine); @@ -348,13 +352,18 @@ static void machine__update_thread_pid(struct machine *machine, } th->mg = map_groups__get(leader->mg); - +out_put: + thread__put(leader); return; - out_err: pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid); + goto out_put; } +/* + * Caller must eventually drop thread->refcnt returned with a successfull + * lookup/new thread inserted. + */ static struct thread *____machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid, bool create) @@ -372,7 +381,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, if (th != NULL) { if (th->tid == tid) { machine__update_thread_pid(machine, th, pid); - return th; + return thread__get(th); } machine->last_match = NULL; @@ -385,7 +394,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, if (th->tid == tid) { machine->last_match = th; machine__update_thread_pid(machine, th, pid); - return th; + return thread__get(th); } if (tid < th->tid) @@ -413,7 +422,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine, if (thread__init_map_groups(th, machine)) { rb_erase_init(&th->rb_node, &machine->threads); RB_CLEAR_NODE(&th->rb_node); - thread__delete(th); + thread__put(th); return NULL; } /* @@ -437,7 +446,7 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, struct thread *th; pthread_rwlock_wrlock(&machine->threads_lock); - th = thread__get(__machine__findnew_thread(machine, pid, tid)); + th = __machine__findnew_thread(machine, pid, tid); pthread_rwlock_unlock(&machine->threads_lock); return th; } @@ -447,7 +456,7 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid, { struct thread *th; pthread_rwlock_rdlock(&machine->threads_lock); - th = thread__get(____machine__findnew_thread(machine, pid, tid, false)); + th = ____machine__findnew_thread(machine, pid, tid, false); pthread_rwlock_unlock(&machine->threads_lock); return th; } @@ -560,11 +569,29 @@ int machine__process_switch_event(struct machine *machine __maybe_unused, return 0; } +static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename) +{ + const char *dup_filename; + + if (!filename || !dso || !dso->long_name) + return; + if (dso->long_name[0] != '[') + return; + if (!strchr(filename, '/')) + return; + + dup_filename = strdup(filename); + if (!dup_filename) + return; + + dso__set_long_name(dso, dup_filename, true); +} + struct map *machine__findnew_module_map(struct machine *machine, u64 start, const char *filename) { struct map *map = NULL; - struct dso *dso; + struct dso *dso = NULL; struct kmod_path m; if (kmod_path__parse_name(&m, filename)) @@ -572,8 +599,15 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION, m.name); - if (map) + if (map) { + /* + * If the map's dso is an offline module, give dso__load() + * a chance to find the file path of that module by fixing + * long_name. + */ + dso__adjust_kmod_long_name(map->dso, filename); goto out; + } dso = machine__findnew_module_dso(machine, &m, filename); if (dso == NULL) @@ -585,7 +619,11 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start, map_groups__insert(&machine->kmaps, map); + /* Put the map here because map_groups__insert alread got it */ + map__put(map); out: + /* put the dso here, corresponding to machine__findnew_module_dso */ + dso__put(dso); free(m.name); return map; } @@ -740,6 +778,9 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel) enum map_type type; u64 start = machine__get_running_kernel_start(machine, NULL); + /* In case of renewal the kernel map, destroy previous one */ + machine__destroy_kernel_maps(machine); + for (type = 0; type < MAP__NR_TYPES; ++type) { struct kmap *kmap; struct map *map; @@ -788,6 +829,7 @@ void machine__destroy_kernel_maps(struct machine *machine) kmap->ref_reloc_sym = NULL; } + map__put(machine->vmlinux_maps[type]); machine->vmlinux_maps[type] = NULL; } } @@ -1084,11 +1126,14 @@ int machine__create_kernel_maps(struct machine *machine) struct dso *kernel = machine__get_kernel(machine); const char *name; u64 addr = machine__get_running_kernel_start(machine, &name); - if (!addr) + int ret; + + if (!addr || kernel == NULL) return -1; - if (kernel == NULL || - __machine__create_kernel_maps(machine, kernel) < 0) + ret = __machine__create_kernel_maps(machine, kernel); + dso__put(kernel); + if (ret < 0) return -1; if (symbol_conf.use_modules && machine__create_modules(machine) < 0) { @@ -1609,6 +1654,8 @@ static int add_callchain_ip(struct thread *thread, } } + if (symbol_conf.hide_unresolved && al.sym == NULL) + return 0; return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym); } @@ -1863,6 +1910,9 @@ check_calls: static int unwind_entry(struct unwind_entry *entry, void *arg) { struct callchain_cursor *cursor = arg; + + if (symbol_conf.hide_unresolved && entry->sym == NULL) + return 0; return callchain_cursor_append(cursor, entry->ip, entry->map, entry->sym); } diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index afc6b56cf749..171b6d10a04b 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -26,8 +26,8 @@ const char *map_type__name[MAP__NR_TYPES] = { static inline int is_anon_memory(const char *filename) { return !strcmp(filename, "//anon") || - !strcmp(filename, "/dev/zero (deleted)") || - !strcmp(filename, "/anon_hugepage (deleted)"); + !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) || + !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1); } static inline int is_no_dso_memory(const char *filename) @@ -691,6 +691,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp __map_groups__insert(pos->groups, before); if (verbose >= 2) map__fprintf(before, fp); + map__put(before); } if (map->end < pos->end) { @@ -705,6 +706,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp __map_groups__insert(pos->groups, after); if (verbose >= 2) map__fprintf(after, fp); + map__put(after); } put_map: map__put(pos); @@ -742,6 +744,7 @@ int map_groups__clone(struct map_groups *mg, if (new == NULL) goto out_unlock; map_groups__insert(mg, new); + map__put(new); } err = 0; diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c index 355eecf6bf59..afc088dd7d20 100644 --- a/tools/perf/util/parse-branch-options.c +++ b/tools/perf/util/parse-branch-options.c @@ -1,7 +1,7 @@ #include "perf.h" #include "util/util.h" #include "util/debug.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-branch-options.h" #define BRANCH_OPT(n, m) \ diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index e48d9da75707..4f7b0efdde2f 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -4,9 +4,9 @@ #include "../perf.h" #include "evlist.h" #include "evsel.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include "parse-events.h" -#include "exec_cmd.h" +#include <subcmd/exec-cmd.h> #include "string.h" #include "symbol.h" #include "cache.h" @@ -124,6 +124,10 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = { .symbol = "dummy", .alias = "", }, + [PERF_COUNT_SW_BPF_OUTPUT] = { + .symbol = "bpf-output", + .alias = "", + }, }; #define __PERF_EVENT_FIELD(config, name) \ @@ -1879,7 +1883,7 @@ restart: for (i = 0; i < max; i++, syms++) { - if (event_glob != NULL && + if (event_glob != NULL && syms->symbol != NULL && !(strglobmatch(syms->symbol, event_glob) || (syms->alias && strglobmatch(syms->alias, event_glob)))) continue; diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c index 4f2c1c255d81..646ecf736aad 100644 --- a/tools/perf/util/parse-regs-options.c +++ b/tools/perf/util/parse-regs-options.c @@ -1,7 +1,7 @@ #include "perf.h" #include "util/util.h" #include "util/debug.h" -#include "util/parse-options.h" +#include <subcmd/parse-options.h> #include "util/parse-regs-options.h" int diff --git a/tools/perf/util/path.c b/tools/perf/util/path.c index 5d13cb45b317..3654d964e49d 100644 --- a/tools/perf/util/path.c +++ b/tools/perf/util/path.c @@ -22,24 +22,6 @@ static const char *get_perf_dir(void) return "."; } -/* - * If libc has strlcpy() then that version will override this - * implementation: - */ -size_t __weak strlcpy(char *dest, const char *src, size_t size) -{ - size_t ret = strlen(src); - - if (size) { - size_t len = (ret >= size) ? size - 1 : ret; - - memcpy(dest, src, len); - dest[len] = '\0'; - } - - return ret; -} - static char *get_pathname(void) { static char pathname_array[4][PATH_MAX]; diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index e4b173dec4b9..b597bcc8fc78 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -220,6 +220,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->scale = 1.0; alias->unit[0] = '\0'; alias->per_pkg = false; + alias->snapshot = false; ret = parse_events_terms(&alias->terms, val); if (ret) { diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 03875f9154e7..93996ec4bbe3 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -2326,8 +2326,11 @@ static int get_new_event_name(char *buf, size_t len, const char *base, goto out; if (!allow_suffix) { - pr_warning("Error: event \"%s\" already exists. " - "(Use -f to force duplicates.)\n", buf); + pr_warning("Error: event \"%s\" already exists.\n" + " Hint: Remove existing event by 'perf probe -d'\n" + " or force duplicates by 'perf probe -f'\n" + " or set 'force=yes' in BPF source.\n", + buf); ret = -EEXIST; goto out; } diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 05012bb178d7..2be10fb27172 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -654,6 +654,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod, static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) { Dwarf_Attribute fb_attr; + Dwarf_Frame *frame = NULL; size_t nops; int ret; @@ -686,11 +687,11 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) #if _ELFUTILS_PREREQ(0, 142) } else if (nops == 1 && pf->fb_ops[0].atom == DW_OP_call_frame_cfa && pf->cfi != NULL) { - Dwarf_Frame *frame; if (dwarf_cfi_addrframe(pf->cfi, pf->addr, &frame) != 0 || dwarf_frame_cfa(frame, &pf->fb_ops, &nops) != 0) { pr_warning("Failed to get call frame on 0x%jx\n", (uintmax_t)pf->addr); + free(frame); return -ENOENT; } #endif @@ -699,7 +700,8 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf) /* Call finder's callback handler */ ret = pf->callback(sc_die, pf); - /* *pf->fb_ops will be cached in libdw. Don't free it. */ + /* Since *pf->fb_ops can be a part of frame. we should free it here. */ + free(frame); pf->fb_ops = NULL; return ret; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 51be28b1bca2..8162ba0e2e57 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,8 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c +../lib/bitmap.c +../lib/find_bit.c ../lib/hweight.c util/thread_map.c util/util.c diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index a8e825fca42a..d72fafc1c800 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -41,6 +41,9 @@ #include "../thread-stack.h" #include "../trace-event.h" #include "../machine.h" +#include "thread_map.h" +#include "cpumap.h" +#include "stat.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -859,6 +862,104 @@ static void python_process_event(union perf_event *event, } } +static void get_handler_name(char *str, size_t size, + struct perf_evsel *evsel) +{ + char *p = str; + + scnprintf(str, size, "stat__%s", perf_evsel__name(evsel)); + + while ((p = strchr(p, ':'))) { + *p = '_'; + p++; + } +} + +static void +process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, + struct perf_counts_values *count) +{ + PyObject *handler, *t; + static char handler_name[256]; + int n = 0; + + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + get_handler_name(handler_name, sizeof(handler_name), + counter); + + handler = get_handler(handler_name); + if (!handler) { + pr_debug("can't find python handler %s\n", handler_name); + return; + } + + PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); + PyTuple_SetItem(t, n++, PyInt_FromLong(thread)); + + tuple_set_u64(t, n++, tstamp); + tuple_set_u64(t, n++, count->val); + tuple_set_u64(t, n++, count->ena); + tuple_set_u64(t, n++, count->run); + + if (_PyTuple_Resize(&t, n) == -1) + Py_FatalError("error resizing Python tuple"); + + call_object(handler, t, handler_name); + + Py_DECREF(t); +} + +static void python_process_stat(struct perf_stat_config *config, + struct perf_evsel *counter, u64 tstamp) +{ + struct thread_map *threads = counter->threads; + struct cpu_map *cpus = counter->cpus; + int cpu, thread; + + if (config->aggr_mode == AGGR_GLOBAL) { + process_stat(counter, -1, -1, tstamp, + &counter->counts->aggr); + return; + } + + for (thread = 0; thread < threads->nr; thread++) { + for (cpu = 0; cpu < cpus->nr; cpu++) { + process_stat(counter, cpus->map[cpu], + thread_map__pid(threads, thread), tstamp, + perf_counts(counter->counts, cpu, thread)); + } + } +} + +static void python_process_stat_interval(u64 tstamp) +{ + PyObject *handler, *t; + static const char handler_name[] = "stat__interval"; + int n = 0; + + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + handler = get_handler(handler_name); + if (!handler) { + pr_debug("can't find python handler %s\n", handler_name); + return; + } + + tuple_set_u64(t, n++, tstamp); + + if (_PyTuple_Resize(&t, n) == -1) + Py_FatalError("error resizing Python tuple"); + + call_object(handler, t, handler_name); + + Py_DECREF(t); +} + static int run_start_sub(void) { main_module = PyImport_AddModule("__main__"); @@ -1201,10 +1302,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) } struct scripting_ops python_scripting_ops = { - .name = "Python", - .start_script = python_start_script, - .flush_script = python_flush_script, - .stop_script = python_stop_script, - .process_event = python_process_event, - .generate_script = python_generate_script, + .name = "Python", + .start_script = python_start_script, + .flush_script = python_flush_script, + .stop_script = python_stop_script, + .process_event = python_process_event, + .process_stat = python_process_stat, + .process_stat_interval = python_process_stat_interval, + .generate_script = python_generate_script, }; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index c35ffdd360fe..d5636ba94b20 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -17,6 +17,7 @@ #include "asm/bug.h" #include "auxtrace.h" #include "thread-stack.h" +#include "stat.h" static int perf_session__deliver_event(struct perf_session *session, union perf_event *event, @@ -36,6 +37,9 @@ static int perf_session__open(struct perf_session *session) if (perf_data_file__is_pipe(file)) return 0; + if (perf_header__has_feat(&session->header, HEADER_STAT)) + return 0; + if (!perf_evlist__valid_sample_type(session->evlist)) { pr_err("non matching sample_type\n"); return -1; @@ -205,6 +209,18 @@ static int process_event_synth_attr_stub(struct perf_tool *tool __maybe_unused, return 0; } +static int process_event_synth_event_update_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_evlist **pevlist + __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_event_update(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + static int process_event_sample_stub(struct perf_tool *tool __maybe_unused, union perf_event *event __maybe_unused, struct perf_sample *sample __maybe_unused, @@ -296,6 +312,67 @@ int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused, return 0; } + +static +int process_event_thread_map_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_thread_map(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + +static +int process_event_cpu_map_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_cpu_map(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + +static +int process_event_stat_config_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *session __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_stat_config(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + +static int process_stat_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *perf_session + __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_stat(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + +static int process_stat_round_stub(struct perf_tool *tool __maybe_unused, + union perf_event *event __maybe_unused, + struct perf_session *perf_session + __maybe_unused) +{ + if (dump_trace) + perf_event__fprintf_stat_round(event, stdout); + + dump_printf(": unhandled!\n"); + return 0; +} + void perf_tool__fill_defaults(struct perf_tool *tool) { if (tool->sample == NULL) @@ -328,6 +405,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->unthrottle = process_event_stub; if (tool->attr == NULL) tool->attr = process_event_synth_attr_stub; + if (tool->event_update == NULL) + tool->event_update = process_event_synth_event_update_stub; if (tool->tracing_data == NULL) tool->tracing_data = process_event_synth_tracing_data_stub; if (tool->build_id == NULL) @@ -346,6 +425,16 @@ void perf_tool__fill_defaults(struct perf_tool *tool) tool->auxtrace = process_event_auxtrace_stub; if (tool->auxtrace_error == NULL) tool->auxtrace_error = process_event_auxtrace_error_stub; + if (tool->thread_map == NULL) + tool->thread_map = process_event_thread_map_stub; + if (tool->cpu_map == NULL) + tool->cpu_map = process_event_cpu_map_stub; + if (tool->stat_config == NULL) + tool->stat_config = process_event_stat_config_stub; + if (tool->stat == NULL) + tool->stat = process_stat_stub; + if (tool->stat_round == NULL) + tool->stat_round = process_stat_round_stub; } static void swap_sample_id_all(union perf_event *event, void *data) @@ -569,6 +658,13 @@ static void perf_event__hdr_attr_swap(union perf_event *event, mem_bswap_64(event->attr.id, size); } +static void perf_event__event_update_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->event_update.type = bswap_64(event->event_update.type); + event->event_update.id = bswap_64(event->event_update.id); +} + static void perf_event__event_type_swap(union perf_event *event, bool sample_id_all __maybe_unused) { @@ -616,6 +712,81 @@ static void perf_event__auxtrace_error_swap(union perf_event *event, event->auxtrace_error.ip = bswap_64(event->auxtrace_error.ip); } +static void perf_event__thread_map_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + unsigned i; + + event->thread_map.nr = bswap_64(event->thread_map.nr); + + for (i = 0; i < event->thread_map.nr; i++) + event->thread_map.entries[i].pid = bswap_64(event->thread_map.entries[i].pid); +} + +static void perf_event__cpu_map_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + struct cpu_map_data *data = &event->cpu_map.data; + struct cpu_map_entries *cpus; + struct cpu_map_mask *mask; + unsigned i; + + data->type = bswap_64(data->type); + + switch (data->type) { + case PERF_CPU_MAP__CPUS: + cpus = (struct cpu_map_entries *)data->data; + + cpus->nr = bswap_16(cpus->nr); + + for (i = 0; i < cpus->nr; i++) + cpus->cpu[i] = bswap_16(cpus->cpu[i]); + break; + case PERF_CPU_MAP__MASK: + mask = (struct cpu_map_mask *) data->data; + + mask->nr = bswap_16(mask->nr); + mask->long_size = bswap_16(mask->long_size); + + switch (mask->long_size) { + case 4: mem_bswap_32(&mask->mask, mask->nr); break; + case 8: mem_bswap_64(&mask->mask, mask->nr); break; + default: + pr_err("cpu_map swap: unsupported long size\n"); + } + default: + break; + } +} + +static void perf_event__stat_config_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + u64 size; + + size = event->stat_config.nr * sizeof(event->stat_config.data[0]); + size += 1; /* nr item itself */ + mem_bswap_64(&event->stat_config.nr, size); +} + +static void perf_event__stat_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->stat.id = bswap_64(event->stat.id); + event->stat.thread = bswap_32(event->stat.thread); + event->stat.cpu = bswap_32(event->stat.cpu); + event->stat.val = bswap_64(event->stat.val); + event->stat.ena = bswap_64(event->stat.ena); + event->stat.run = bswap_64(event->stat.run); +} + +static void perf_event__stat_round_swap(union perf_event *event, + bool sample_id_all __maybe_unused) +{ + event->stat_round.type = bswap_64(event->stat_round.type); + event->stat_round.time = bswap_64(event->stat_round.time); +} + typedef void (*perf_event__swap_op)(union perf_event *event, bool sample_id_all); @@ -643,6 +814,12 @@ static perf_event__swap_op perf_event__swap_ops[] = { [PERF_RECORD_AUXTRACE_INFO] = perf_event__auxtrace_info_swap, [PERF_RECORD_AUXTRACE] = perf_event__auxtrace_swap, [PERF_RECORD_AUXTRACE_ERROR] = perf_event__auxtrace_error_swap, + [PERF_RECORD_THREAD_MAP] = perf_event__thread_map_swap, + [PERF_RECORD_CPU_MAP] = perf_event__cpu_map_swap, + [PERF_RECORD_STAT_CONFIG] = perf_event__stat_config_swap, + [PERF_RECORD_STAT] = perf_event__stat_swap, + [PERF_RECORD_STAT_ROUND] = perf_event__stat_round_swap, + [PERF_RECORD_EVENT_UPDATE] = perf_event__event_update_swap, [PERF_RECORD_HEADER_MAX] = NULL, }; @@ -1154,6 +1331,8 @@ static s64 perf_session__process_user_event(struct perf_session *session, perf_session__set_comm_exec(session); } return err; + case PERF_RECORD_EVENT_UPDATE: + return tool->event_update(tool, event, &session->evlist); case PERF_RECORD_HEADER_EVENT_TYPE: /* * Depreceated, but we need to handle it for sake @@ -1179,6 +1358,16 @@ static s64 perf_session__process_user_event(struct perf_session *session, case PERF_RECORD_AUXTRACE_ERROR: perf_session__auxtrace_error_inc(session, event); return tool->auxtrace_error(tool, event, session); + case PERF_RECORD_THREAD_MAP: + return tool->thread_map(tool, event, session); + case PERF_RECORD_CPU_MAP: + return tool->cpu_map(tool, event, session); + case PERF_RECORD_STAT_CONFIG: + return tool->stat_config(tool, event, session); + case PERF_RECORD_STAT: + return tool->stat(tool, event, session); + case PERF_RECORD_STAT_ROUND: + return tool->stat_round(tool, event, session); default: return -EINVAL; } @@ -1311,17 +1500,20 @@ struct thread *perf_session__findnew(struct perf_session *session, pid_t pid) return machine__findnew_thread(&session->machines.host, -1, pid); } -struct thread *perf_session__register_idle_thread(struct perf_session *session) +int perf_session__register_idle_thread(struct perf_session *session) { struct thread *thread; + int err = 0; thread = machine__findnew_thread(&session->machines.host, 0, 0); if (thread == NULL || thread__set_comm(thread, "swapper", 0)) { pr_err("problem inserting idle task.\n"); - thread = NULL; + err = -1; } - return thread; + /* machine__findnew_thread() got the thread, so put it */ + thread__put(thread); + return err; } static void perf_session__warn_about_errors(const struct perf_session *session) @@ -1676,7 +1868,7 @@ int perf_session__process_events(struct perf_session *session) u64 size = perf_data_file__size(session->file); int err; - if (perf_session__register_idle_thread(session) == NULL) + if (perf_session__register_idle_thread(session) < 0) return -ENOMEM; if (!perf_data_file__is_pipe(session->file)) diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index 3e900c0efc73..5f792e35d4c1 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -89,7 +89,7 @@ struct machine *perf_session__findnew_machine(struct perf_session *session, pid_ } struct thread *perf_session__findnew(struct perf_session *session, pid_t pid); -struct thread *perf_session__register_idle_thread(struct perf_session *session); +int perf_session__register_idle_thread(struct perf_session *session); size_t perf_session__fprintf(struct perf_session *session, FILE *fp); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2d8ccd4d9e1b..ec722346e6ff 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -4,6 +4,8 @@ #include "comm.h" #include "symbol.h" #include "evsel.h" +#include "evlist.h" +#include <traceevent/event-parse.h> regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -13,6 +15,7 @@ const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cy const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; const char default_top_sort_order[] = "dso,symbol"; const char default_diff_sort_order[] = "dso,symbol"; +const char default_tracepoint_sort_order[] = "trace"; const char *sort_order; const char *field_order; regex_t ignore_callees_regex; @@ -443,6 +446,70 @@ struct sort_entry sort_socket = { .se_width_idx = HISTC_SOCKET, }; +/* --sort trace */ + +static char *get_trace_output(struct hist_entry *he) +{ + struct trace_seq seq; + struct perf_evsel *evsel; + struct pevent_record rec = { + .data = he->raw_data, + .size = he->raw_size, + }; + + evsel = hists_to_evsel(he->hists); + + trace_seq_init(&seq); + if (symbol_conf.raw_trace) { + pevent_print_fields(&seq, he->raw_data, he->raw_size, + evsel->tp_format); + } else { + pevent_event_info(&seq, evsel->tp_format, &rec); + } + return seq.buffer; +} + +static int64_t +sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct perf_evsel *evsel; + + evsel = hists_to_evsel(left->hists); + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + return 0; + + if (left->trace_output == NULL) + left->trace_output = get_trace_output(left); + if (right->trace_output == NULL) + right->trace_output = get_trace_output(right); + + hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output)); + hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output)); + + return strcmp(right->trace_output, left->trace_output); +} + +static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + struct perf_evsel *evsel; + + evsel = hists_to_evsel(he->hists); + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + return scnprintf(bf, size, "%-*.*s", width, width, "N/A"); + + if (he->trace_output == NULL) + he->trace_output = get_trace_output(he); + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output); +} + +struct sort_entry sort_trace = { + .se_header = "Trace output", + .se_cmp = sort__trace_cmp, + .se_snprintf = hist_entry__trace_snprintf, + .se_width_idx = HISTC_TRACE, +}; + /* sort keys for branch stacks */ static int64_t @@ -1312,6 +1379,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), + DIM(SORT_TRACE, "trace", sort_trace), }; #undef DIM @@ -1529,6 +1597,455 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) return 0; } +struct hpp_dynamic_entry { + struct perf_hpp_fmt hpp; + struct perf_evsel *evsel; + struct format_field *field; + unsigned dynamic_len; + bool raw_trace; +}; + +static int hde_width(struct hpp_dynamic_entry *hde) +{ + if (!hde->hpp.len) { + int len = hde->dynamic_len; + int namelen = strlen(hde->field->name); + int fieldlen = hde->field->size; + + if (namelen > len) + len = namelen; + + if (!(hde->field->flags & FIELD_IS_STRING)) { + /* length for print hex numbers */ + fieldlen = hde->field->size * 2 + 2; + } + if (fieldlen > len) + len = fieldlen; + + hde->hpp.len = len; + } + return hde->hpp.len; +} + +static void update_dynamic_len(struct hpp_dynamic_entry *hde, + struct hist_entry *he) +{ + char *str, *pos; + struct format_field *field = hde->field; + size_t namelen; + bool last = false; + + if (hde->raw_trace) + return; + + /* parse pretty print result and update max length */ + if (!he->trace_output) + he->trace_output = get_trace_output(he); + + namelen = strlen(field->name); + str = he->trace_output; + + while (str) { + pos = strchr(str, ' '); + if (pos == NULL) { + last = true; + pos = str + strlen(str); + } + + if (!strncmp(str, field->name, namelen)) { + size_t len; + + str += namelen + 1; + len = pos - str; + + if (len > hde->dynamic_len) + hde->dynamic_len = len; + break; + } + + if (last) + str = NULL; + else + str = pos + 1; + } +} + +static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel __maybe_unused) +{ + struct hpp_dynamic_entry *hde; + size_t len = fmt->user_len; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (!len) + len = hde_width(hde); + + return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, hde->field->name); +} + +static int __sort__hde_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel __maybe_unused) +{ + struct hpp_dynamic_entry *hde; + size_t len = fmt->user_len; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (!len) + len = hde_width(hde); + + return len; +} + +bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists) +{ + struct hpp_dynamic_entry *hde; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + return hists_to_evsel(hists) == hde->evsel; +} + +static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct hpp_dynamic_entry *hde; + size_t len = fmt->user_len; + char *str, *pos; + struct format_field *field; + size_t namelen; + bool last = false; + int ret; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (!len) + len = hde_width(hde); + + if (hde->raw_trace) + goto raw_field; + + field = hde->field; + namelen = strlen(field->name); + str = he->trace_output; + + while (str) { + pos = strchr(str, ' '); + if (pos == NULL) { + last = true; + pos = str + strlen(str); + } + + if (!strncmp(str, field->name, namelen)) { + str += namelen + 1; + str = strndup(str, pos - str); + + if (str == NULL) + return scnprintf(hpp->buf, hpp->size, + "%*.*s", len, len, "ERROR"); + break; + } + + if (last) + str = NULL; + else + str = pos + 1; + } + + if (str == NULL) { + struct trace_seq seq; +raw_field: + trace_seq_init(&seq); + pevent_print_field(&seq, he->raw_data, hde->field); + str = seq.buffer; + } + + ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, str); + free(str); + return ret; +} + +static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_dynamic_entry *hde; + struct format_field *field; + unsigned offset, size; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + field = hde->field; + if (field->flags & FIELD_IS_DYNAMIC) { + unsigned long long dyn; + + pevent_read_number_field(field, a->raw_data, &dyn); + offset = dyn & 0xffff; + size = (dyn >> 16) & 0xffff; + + /* record max width for output */ + if (size > hde->dynamic_len) + hde->dynamic_len = size; + } else { + offset = field->offset; + size = field->size; + + update_dynamic_len(hde, a); + update_dynamic_len(hde, b); + } + + return memcmp(a->raw_data + offset, b->raw_data + offset, size); +} + +bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt) +{ + return fmt->cmp == __sort__hde_cmp; +} + +static struct hpp_dynamic_entry * +__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) +{ + struct hpp_dynamic_entry *hde; + + hde = malloc(sizeof(*hde)); + if (hde == NULL) { + pr_debug("Memory allocation failed\n"); + return NULL; + } + + hde->evsel = evsel; + hde->field = field; + hde->dynamic_len = 0; + + hde->hpp.name = field->name; + hde->hpp.header = __sort__hde_header; + hde->hpp.width = __sort__hde_width; + hde->hpp.entry = __sort__hde_entry; + hde->hpp.color = NULL; + + hde->hpp.cmp = __sort__hde_cmp; + hde->hpp.collapse = __sort__hde_cmp; + hde->hpp.sort = __sort__hde_cmp; + + INIT_LIST_HEAD(&hde->hpp.list); + INIT_LIST_HEAD(&hde->hpp.sort_list); + hde->hpp.elide = false; + hde->hpp.len = 0; + hde->hpp.user_len = 0; + + return hde; +} + +static int parse_field_name(char *str, char **event, char **field, char **opt) +{ + char *event_name, *field_name, *opt_name; + + event_name = str; + field_name = strchr(str, '.'); + + if (field_name) { + *field_name++ = '\0'; + } else { + event_name = NULL; + field_name = str; + } + + opt_name = strchr(field_name, '/'); + if (opt_name) + *opt_name++ = '\0'; + + *event = event_name; + *field = field_name; + *opt = opt_name; + + return 0; +} + +/* find match evsel using a given event name. The event name can be: + * 1. '%' + event index (e.g. '%1' for first event) + * 2. full event name (e.g. sched:sched_switch) + * 3. partial event name (should not contain ':') + */ +static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name) +{ + struct perf_evsel *evsel = NULL; + struct perf_evsel *pos; + bool full_name; + + /* case 1 */ + if (event_name[0] == '%') { + int nr = strtol(event_name+1, NULL, 0); + + if (nr > evlist->nr_entries) + return NULL; + + evsel = perf_evlist__first(evlist); + while (--nr > 0) + evsel = perf_evsel__next(evsel); + + return evsel; + } + + full_name = !!strchr(event_name, ':'); + evlist__for_each(evlist, pos) { + /* case 2 */ + if (full_name && !strcmp(pos->name, event_name)) + return pos; + /* case 3 */ + if (!full_name && strstr(pos->name, event_name)) { + if (evsel) { + pr_debug("'%s' event is ambiguous: it can be %s or %s\n", + event_name, evsel->name, pos->name); + return NULL; + } + evsel = pos; + } + } + + return evsel; +} + +static int __dynamic_dimension__add(struct perf_evsel *evsel, + struct format_field *field, + bool raw_trace) +{ + struct hpp_dynamic_entry *hde; + + hde = __alloc_dynamic_entry(evsel, field); + if (hde == NULL) + return -ENOMEM; + + hde->raw_trace = raw_trace; + + perf_hpp__register_sort_field(&hde->hpp); + return 0; +} + +static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace) +{ + int ret; + struct format_field *field; + + field = evsel->tp_format->format.fields; + while (field) { + ret = __dynamic_dimension__add(evsel, field, raw_trace); + if (ret < 0) + return ret; + + field = field->next; + } + return 0; +} + +static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace) +{ + int ret; + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + continue; + + ret = add_evsel_fields(evsel, raw_trace); + if (ret < 0) + return ret; + } + return 0; +} + +static int add_all_matching_fields(struct perf_evlist *evlist, + char *field_name, bool raw_trace) +{ + int ret = -ESRCH; + struct perf_evsel *evsel; + struct format_field *field; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + continue; + + field = pevent_find_any_field(evsel->tp_format, field_name); + if (field == NULL) + continue; + + ret = __dynamic_dimension__add(evsel, field, raw_trace); + if (ret < 0) + break; + } + return ret; +} + +static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) +{ + char *str, *event_name, *field_name, *opt_name; + struct perf_evsel *evsel; + struct format_field *field; + bool raw_trace = symbol_conf.raw_trace; + int ret = 0; + + if (evlist == NULL) + return -ENOENT; + + str = strdup(tok); + if (str == NULL) + return -ENOMEM; + + if (parse_field_name(str, &event_name, &field_name, &opt_name) < 0) { + ret = -EINVAL; + goto out; + } + + if (opt_name) { + if (strcmp(opt_name, "raw")) { + pr_debug("unsupported field option %s\n", opt_name); + ret = -EINVAL; + goto out; + } + raw_trace = true; + } + + if (!strcmp(field_name, "trace_fields")) { + ret = add_all_dynamic_fields(evlist, raw_trace); + goto out; + } + + if (event_name == NULL) { + ret = add_all_matching_fields(evlist, field_name, raw_trace); + goto out; + } + + evsel = find_evsel(evlist, event_name); + if (evsel == NULL) { + pr_debug("Cannot find event: %s\n", event_name); + ret = -ENOENT; + goto out; + } + + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + pr_debug("%s is not a tracepoint event\n", event_name); + ret = -EINVAL; + goto out; + } + + if (!strcmp(field_name, "*")) { + ret = add_evsel_fields(evsel, raw_trace); + } else { + field = pevent_find_any_field(evsel->tp_format, field_name); + if (field == NULL) { + pr_debug("Cannot find event field for %s.%s\n", + event_name, field_name); + return -ENOENT; + } + + ret = __dynamic_dimension__add(evsel, field, raw_trace); + } + +out: + free(str); + return ret; +} + static int __sort_dimension__add(struct sort_dimension *sd) { if (sd->taken) @@ -1583,7 +2100,8 @@ int hpp_dimension__add_output(unsigned col) return __hpp_dimension__add_output(&hpp_sort_dimensions[col]); } -int sort_dimension__add(const char *tok) +static int sort_dimension__add(const char *tok, + struct perf_evlist *evlist __maybe_unused) { unsigned int i; @@ -1664,10 +2182,13 @@ int sort_dimension__add(const char *tok) return 0; } + if (!add_dynamic_entry(evlist, tok)) + return 0; + return -ESRCH; } -static const char *get_default_sort_order(void) +static const char *get_default_sort_order(struct perf_evlist *evlist) { const char *default_sort_orders[] = { default_sort_order, @@ -1675,14 +2196,33 @@ static const char *get_default_sort_order(void) default_mem_sort_order, default_top_sort_order, default_diff_sort_order, + default_tracepoint_sort_order, }; + bool use_trace = true; + struct perf_evsel *evsel; BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); + if (evlist == NULL) + goto out_no_evlist; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + use_trace = false; + break; + } + } + + if (use_trace) { + sort__mode = SORT_MODE__TRACEPOINT; + if (symbol_conf.raw_trace) + return "trace_fields"; + } +out_no_evlist: return default_sort_orders[sort__mode]; } -static int setup_sort_order(void) +static int setup_sort_order(struct perf_evlist *evlist) { char *new_sort_order; @@ -1703,7 +2243,7 @@ static int setup_sort_order(void) * because it's checked over the rest of the code. */ if (asprintf(&new_sort_order, "%s,%s", - get_default_sort_order(), sort_order + 1) < 0) { + get_default_sort_order(evlist), sort_order + 1) < 0) { error("Not enough memory to set up --sort"); return -ENOMEM; } @@ -1712,13 +2252,41 @@ static int setup_sort_order(void) return 0; } -static int __setup_sorting(void) +/* + * Adds 'pre,' prefix into 'str' is 'pre' is + * not already part of 'str'. + */ +static char *prefix_if_not_in(const char *pre, char *str) +{ + char *n; + + if (!str || strstr(str, pre)) + return str; + + if (asprintf(&n, "%s,%s", pre, str) < 0) + return NULL; + + free(str); + return n; +} + +static char *setup_overhead(char *keys) +{ + keys = prefix_if_not_in("overhead", keys); + + if (symbol_conf.cumulate_callchain) + keys = prefix_if_not_in("overhead_children", keys); + + return keys; +} + +static int __setup_sorting(struct perf_evlist *evlist) { char *tmp, *tok, *str; const char *sort_keys; int ret = 0; - ret = setup_sort_order(); + ret = setup_sort_order(evlist); if (ret) return ret; @@ -1732,7 +2300,7 @@ static int __setup_sorting(void) return 0; } - sort_keys = get_default_sort_order(); + sort_keys = get_default_sort_order(evlist); } str = strdup(sort_keys); @@ -1741,9 +2309,20 @@ static int __setup_sorting(void) return -ENOMEM; } + /* + * Prepend overhead fields for backward compatibility. + */ + if (!is_strict_order(field_order)) { + str = setup_overhead(str); + if (str == NULL) { + error("Not enough memory to setup overhead keys"); + return -ENOMEM; + } + } + for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = sort_dimension__add(tok); + ret = sort_dimension__add(tok, evlist); if (ret == -EINVAL) { error("Invalid --sort key: `%s'", tok); break; @@ -1954,16 +2533,16 @@ out: return ret; } -int setup_sorting(void) +int setup_sorting(struct perf_evlist *evlist) { int err; - err = __setup_sorting(); + err = __setup_sorting(evlist); if (err < 0) return err; if (parent_pattern != default_parent_pattern) { - err = sort_dimension__add("parent"); + err = sort_dimension__add("parent", evlist); if (err < 0) return err; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 31228851e397..687bbb124428 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -18,7 +18,7 @@ #include "debug.h" #include "header.h" -#include "parse-options.h" +#include <subcmd/parse-options.h> #include "parse-events.h" #include "hist.h" #include "thread.h" @@ -122,6 +122,9 @@ struct hist_entry { struct branch_info *branch_info; struct hists *hists; struct mem_info *mem_info; + void *raw_data; + u32 raw_size; + void *trace_output; struct callchain_root callchain[0]; /* must be last member */ }; @@ -164,6 +167,7 @@ enum sort_mode { SORT_MODE__MEMORY, SORT_MODE__TOP, SORT_MODE__DIFF, + SORT_MODE__TRACEPOINT, }; enum sort_type { @@ -180,6 +184,7 @@ enum sort_type { SORT_LOCAL_WEIGHT, SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, + SORT_TRACE, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, @@ -209,8 +214,6 @@ enum sort_type { */ struct sort_entry { - struct list_head list; - const char *se_header; int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); @@ -224,10 +227,11 @@ struct sort_entry { extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -int setup_sorting(void); +struct perf_evlist; +struct pevent; +int setup_sorting(struct perf_evlist *evlist); int setup_output_field(void); void reset_output_field(void); -extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 2d9d8306dbd3..2f901d15e063 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -341,3 +341,65 @@ int perf_stat_process_counter(struct perf_stat_config *config, return 0; } + +int perf_event__process_stat_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session) +{ + struct perf_counts_values count; + struct stat_event *st = &event->stat; + struct perf_evsel *counter; + + count.val = st->val; + count.ena = st->ena; + count.run = st->run; + + counter = perf_evlist__id2evsel(session->evlist, st->id); + if (!counter) { + pr_err("Failed to resolve counter for stat event.\n"); + return -EINVAL; + } + + *perf_counts(counter->counts, st->cpu, st->thread) = count; + counter->supported = true; + return 0; +} + +size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp) +{ + struct stat_event *st = (struct stat_event *) event; + size_t ret; + + ret = fprintf(fp, "\n... id %" PRIu64 ", cpu %d, thread %d\n", + st->id, st->cpu, st->thread); + ret += fprintf(fp, "... value %" PRIu64 ", enabled %" PRIu64 ", running %" PRIu64 "\n", + st->val, st->ena, st->run); + + return ret; +} + +size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp) +{ + struct stat_round_event *rd = (struct stat_round_event *)event; + size_t ret; + + ret = fprintf(fp, "\n... time %" PRIu64 ", type %s\n", rd->time, + rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL"); + + return ret; +} + +size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp) +{ + struct perf_stat_config sc; + size_t ret; + + perf_event__read_stat_config(&sc, &event->stat_config); + + ret = fprintf(fp, "\n"); + ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode); + ret += fprintf(fp, "... scale %d\n", sc.scale); + ret += fprintf(fp, "... interval %u\n", sc.interval); + + return ret; +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index da1d11c4f8c1..086f4e128d63 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -90,4 +90,14 @@ void perf_evlist__reset_stats(struct perf_evlist *evlist); int perf_stat_process_counter(struct perf_stat_config *config, struct perf_evsel *counter); +struct perf_tool; +union perf_event; +struct perf_session; +int perf_event__process_stat_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session); + +size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp); +size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp); #endif diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index fc8781de62db..7f7e072be746 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -342,22 +342,6 @@ char *rtrim(char *s) return s; } -/** - * memdup - duplicate region of memory - * @src: memory region to duplicate - * @len: memory region length - */ -void *memdup(const void *src, size_t len) -{ - void *p; - - p = malloc(len); - if (p) - memcpy(p, src, len); - - return p; -} - char *asprintf_expr_inout_ints(const char *var, bool in, size_t nints, int *ints) { /* diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 475d88d0a1c9..562b8ebeae5b 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1026,8 +1026,8 @@ int dso__load_sym(struct dso *dso, struct map *map, curr_dso->long_name_len = dso->long_name_len; curr_map = map__new2(start, curr_dso, map->type); + dso__put(curr_dso); if (curr_map == NULL) { - dso__put(curr_dso); goto out_elf_end; } if (adjust_kernel_syms) { @@ -1042,7 +1042,14 @@ int dso__load_sym(struct dso *dso, struct map *map, } curr_dso->symtab_type = dso->symtab_type; map_groups__insert(kmaps, curr_map); + /* + * Add it before we drop the referece to curr_map, + * i.e. while we still are sure to have a reference + * to this DSO via curr_map->dso. + */ dsos__add(&map->groups->machine->dsos, curr_dso); + /* kmaps already got it */ + map__put(curr_map); dso__set_loaded(curr_dso, map->type); } else curr_dso = curr_map->dso; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index cd08027a6d2c..3b2de6eb3376 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -39,6 +39,7 @@ struct symbol_conf symbol_conf = { .cumulate_callchain = true, .show_hist_headers = true, .symfs = "", + .event_group = true, }; static enum dso_binary_type binary_type_symtab[] = { @@ -1860,24 +1861,44 @@ static void vmlinux_path__exit(void) zfree(&vmlinux_path); } +static const char * const vmlinux_paths[] = { + "vmlinux", + "/boot/vmlinux" +}; + +static const char * const vmlinux_paths_upd[] = { + "/boot/vmlinux-%s", + "/usr/lib/debug/boot/vmlinux-%s", + "/lib/modules/%s/build/vmlinux", + "/usr/lib/debug/lib/modules/%s/vmlinux", + "/usr/lib/debug/boot/vmlinux-%s.debug" +}; + +static int vmlinux_path__add(const char *new_entry) +{ + vmlinux_path[vmlinux_path__nr_entries] = strdup(new_entry); + if (vmlinux_path[vmlinux_path__nr_entries] == NULL) + return -1; + ++vmlinux_path__nr_entries; + + return 0; +} + static int vmlinux_path__init(struct perf_env *env) { struct utsname uts; char bf[PATH_MAX]; char *kernel_version; + unsigned int i; - vmlinux_path = malloc(sizeof(char *) * 6); + vmlinux_path = malloc(sizeof(char *) * (ARRAY_SIZE(vmlinux_paths) + + ARRAY_SIZE(vmlinux_paths_upd))); if (vmlinux_path == NULL) return -1; - vmlinux_path[vmlinux_path__nr_entries] = strdup("vmlinux"); - if (vmlinux_path[vmlinux_path__nr_entries] == NULL) - goto out_fail; - ++vmlinux_path__nr_entries; - vmlinux_path[vmlinux_path__nr_entries] = strdup("/boot/vmlinux"); - if (vmlinux_path[vmlinux_path__nr_entries] == NULL) - goto out_fail; - ++vmlinux_path__nr_entries; + for (i = 0; i < ARRAY_SIZE(vmlinux_paths); i++) + if (vmlinux_path__add(vmlinux_paths[i]) < 0) + goto out_fail; /* only try kernel version if no symfs was given */ if (symbol_conf.symfs[0] != 0) @@ -1892,28 +1913,11 @@ static int vmlinux_path__init(struct perf_env *env) kernel_version = uts.release; } - snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version); - vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); - if (vmlinux_path[vmlinux_path__nr_entries] == NULL) - goto out_fail; - ++vmlinux_path__nr_entries; - snprintf(bf, sizeof(bf), "/usr/lib/debug/boot/vmlinux-%s", - kernel_version); - vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); - if (vmlinux_path[vmlinux_path__nr_entries] == NULL) - goto out_fail; - ++vmlinux_path__nr_entries; - snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version); - vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); - if (vmlinux_path[vmlinux_path__nr_entries] == NULL) - goto out_fail; - ++vmlinux_path__nr_entries; - snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux", - kernel_version); - vmlinux_path[vmlinux_path__nr_entries] = strdup(bf); - if (vmlinux_path[vmlinux_path__nr_entries] == NULL) - goto out_fail; - ++vmlinux_path__nr_entries; + for (i = 0; i < ARRAY_SIZE(vmlinux_paths_upd); i++) { + snprintf(bf, sizeof(bf), vmlinux_paths_upd[i], kernel_version); + if (vmlinux_path__add(bf) < 0) + goto out_fail; + } return 0; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index dcd786e364f2..ccd1caa40e11 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -108,7 +108,9 @@ struct symbol_conf { show_hist_headers, branch_callstack, has_filter, - show_ref_callgraph; + show_ref_callgraph, + hide_unresolved, + raw_trace; const char *vmlinux_name, *kallsyms_name, *source_prefix, diff --git a/tools/perf/util/term.c b/tools/perf/util/term.c new file mode 100644 index 000000000000..90b47d8aa19c --- /dev/null +++ b/tools/perf/util/term.c @@ -0,0 +1,35 @@ +#include "util.h" + +void get_term_dimensions(struct winsize *ws) +{ + char *s = getenv("LINES"); + + if (s != NULL) { + ws->ws_row = atoi(s); + s = getenv("COLUMNS"); + if (s != NULL) { + ws->ws_col = atoi(s); + if (ws->ws_row && ws->ws_col) + return; + } + } +#ifdef TIOCGWINSZ + if (ioctl(1, TIOCGWINSZ, ws) == 0 && + ws->ws_row && ws->ws_col) + return; +#endif + ws->ws_row = 25; + ws->ws_col = 80; +} + +void set_term_quiet_input(struct termios *old) +{ + struct termios tc; + + tcgetattr(0, old); + tc = *old; + tc.c_lflag &= ~(ICANON | ECHO); + tc.c_cc[VMIN] = 0; + tc.c_cc[VTIME] = 0; + tcsetattr(0, TCSANOW, &tc); +} diff --git a/tools/perf/util/term.h b/tools/perf/util/term.h new file mode 100644 index 000000000000..2c06a61846a1 --- /dev/null +++ b/tools/perf/util/term.h @@ -0,0 +1,10 @@ +#ifndef __PERF_TERM_H +#define __PERF_TERM_H + +struct termios; +struct winsize; + +void get_term_dimensions(struct winsize *ws); +void set_term_quiet_input(struct termios *old); + +#endif /* __PERF_TERM_H */ diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c index 0a9ae8014729..dfd00c6dad6e 100644 --- a/tools/perf/util/thread.c +++ b/tools/perf/util/thread.c @@ -19,8 +19,10 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine) thread->mg = map_groups__new(machine); } else { leader = __machine__findnew_thread(machine, pid, pid); - if (leader) + if (leader) { thread->mg = map_groups__get(leader->mg); + thread__put(leader); + } } return thread->mg ? 0 : -1; @@ -53,7 +55,7 @@ struct thread *thread__new(pid_t pid, pid_t tid) goto err_thread; list_add(&comm->list, &thread->comm_list); - atomic_set(&thread->refcnt, 0); + atomic_set(&thread->refcnt, 1); RB_CLEAR_NODE(&thread->rb_node); } @@ -95,6 +97,10 @@ struct thread *thread__get(struct thread *thread) void thread__put(struct thread *thread) { if (thread && atomic_dec_and_test(&thread->refcnt)) { + /* + * Remove it from the dead_threads list, as last reference + * is gone. + */ list_del_init(&thread->node); thread__delete(thread); } diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c index 6ec3c5ca438f..08afc6909953 100644 --- a/tools/perf/util/thread_map.c +++ b/tools/perf/util/thread_map.c @@ -13,6 +13,7 @@ #include "thread_map.h" #include "util.h" #include "debug.h" +#include "event.h" /* Skip "." and ".." directories */ static int filter(const struct dirent *dir) @@ -304,6 +305,7 @@ out: out_free_threads: zfree(&threads); + strlist__delete(slist); goto out; } @@ -408,3 +410,29 @@ void thread_map__read_comms(struct thread_map *threads) for (i = 0; i < threads->nr; ++i) comm_init(threads, i); } + +static void thread_map__copy_event(struct thread_map *threads, + struct thread_map_event *event) +{ + unsigned i; + + threads->nr = (int) event->nr; + + for (i = 0; i < event->nr; i++) { + thread_map__set_pid(threads, i, (pid_t) event->entries[i].pid); + threads->map[i].comm = strndup(event->entries[i].comm, 16); + } + + atomic_set(&threads->refcnt, 1); +} + +struct thread_map *thread_map__new_event(struct thread_map_event *event) +{ + struct thread_map *threads; + + threads = thread_map__alloc(event->nr); + if (threads) + thread_map__copy_event(threads, event); + + return threads; +} diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h index af679d8a50f8..85e4c7c4fbde 100644 --- a/tools/perf/util/thread_map.h +++ b/tools/perf/util/thread_map.h @@ -16,11 +16,14 @@ struct thread_map { struct thread_map_data map[]; }; +struct thread_map_event; + struct thread_map *thread_map__new_dummy(void); struct thread_map *thread_map__new_by_pid(pid_t pid); struct thread_map *thread_map__new_by_tid(pid_t tid); struct thread_map *thread_map__new_by_uid(uid_t uid); struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid); +struct thread_map *thread_map__new_event(struct thread_map_event *event); struct thread_map *thread_map__get(struct thread_map *map); void thread_map__put(struct thread_map *map); diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index cab8cc24831b..55de4cffcd4e 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -50,12 +50,18 @@ struct perf_tool { throttle, unthrottle; event_attr_op attr; + event_attr_op event_update; event_op2 tracing_data; event_oe finished_round; event_op2 build_id, id_index, auxtrace_info, - auxtrace_error; + auxtrace_error, + thread_map, + cpu_map, + stat_config, + stat, + stat_round; event_op3 auxtrace; bool ordered_events; bool ordering_requires_timestamps; diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index b85ee55cca0c..bce5b1dac268 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -65,6 +65,7 @@ int tracing_data_put(struct tracing_data *tdata); struct addr_location; struct perf_session; +struct perf_stat_config; struct scripting_ops { const char *name; @@ -75,6 +76,9 @@ struct scripting_ops { struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al); + void (*process_stat)(struct perf_stat_config *config, + struct perf_evsel *evsel, u64 tstamp); + void (*process_stat_interval)(u64 tstamp); int (*generate_script) (struct pevent *pevent, const char *outfile); }; diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index 2dcfe9a7c8d0..cf5e250bc78e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include "event.h" #include "perf_regs.h" +#include "callchain.h" static char *debuginfo_path; @@ -52,25 +53,28 @@ static int report_module(u64 ip, struct unwind_info *ui) return __report_module(&al, ip, ui); } +/* + * Store all entries within entries array, + * we will process it after we finish unwind. + */ static int entry(u64 ip, struct unwind_info *ui) { - struct unwind_entry e; + struct unwind_entry *e = &ui->entries[ui->idx++]; struct addr_location al; if (__report_module(&al, ip, ui)) return -1; - e.ip = ip; - e.map = al.map; - e.sym = al.sym; + e->ip = ip; + e->map = al.map; + e->sym = al.sym; pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n", al.sym ? al.sym->name : "''", ip, al.map ? al.map->map_ip(al.map, ip) : (u64) 0); - - return ui->cb(&e, ui->arg); + return 0; } static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp) @@ -92,6 +96,16 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, addr, &al); if (!al.map) { + /* + * We've seen cases (softice) where DWARF unwinder went + * through non executable mmaps, which we need to lookup + * in MAP__VARIABLE tree. + */ + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, + MAP__VARIABLE, addr, &al); + } + + if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } @@ -168,7 +182,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct perf_sample *data, int max_stack) { - struct unwind_info ui = { + struct unwind_info *ui, ui_buf = { .sample = data, .thread = thread, .machine = thread->mg->machine, @@ -177,35 +191,54 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .max_stack = max_stack, }; Dwarf_Word ip; - int err = -EINVAL; + int err = -EINVAL, i; if (!data->user_regs.regs) return -EINVAL; - ui.dwfl = dwfl_begin(&offline_callbacks); - if (!ui.dwfl) + ui = zalloc(sizeof(ui_buf) + sizeof(ui_buf.entries[0]) * max_stack); + if (!ui) + return -ENOMEM; + + *ui = ui_buf; + + ui->dwfl = dwfl_begin(&offline_callbacks); + if (!ui->dwfl) goto out; err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); if (err) goto out; - err = report_module(ip, &ui); + err = report_module(ip, ui); if (err) goto out; - if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui)) + if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui)) goto out; - err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui); + err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui); - if (err && !ui.max_stack) + if (err && !ui->max_stack) err = 0; + /* + * Display what we got based on the order setup. + */ + for (i = 0; i < ui->idx && !err; i++) { + int j = i; + + if (callchain_param.order == ORDER_CALLER) + j = ui->idx - i - 1; + + err = ui->entries[j].ip ? ui->cb(&ui->entries[j], ui->arg) : 0; + } + out: if (err) pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1)); - dwfl_end(ui.dwfl); + dwfl_end(ui->dwfl); + free(ui); return 0; } diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 417a1426f3ad..58328669ed16 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -16,6 +16,8 @@ struct unwind_info { unwind_entry_cb_t cb; void *arg; int max_stack; + int idx; + struct unwind_entry entries[]; }; #endif /* __PERF_UNWIND_LIBDW_H */ diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index c83832b555e5..ee7e372297e5 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -319,6 +319,15 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui) thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); + if (!al.map) { + /* + * We've seen cases (softice) where DWARF unwinder went + * through non executable mmaps, which we need to lookup + * in MAP__VARIABLE tree. + */ + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, + MAP__VARIABLE, ip, &al); + } return al.map; } @@ -416,20 +425,19 @@ get_proc_name(unw_addr_space_t __maybe_unused as, static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, unw_word_t *data) { - struct addr_location al; + struct map *map; ssize_t size; - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, addr, &al); - if (!al.map) { + map = find_map(addr, ui); + if (!map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } - if (!al.map->dso) + if (!map->dso) return -1; - size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + size = dso__data_read_addr(map->dso, map, ui->machine, addr, (u8 *) data, sizeof(*data)); return !(size == sizeof(*data)); @@ -614,23 +622,48 @@ void unwind__finish_access(struct thread *thread) static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, void *arg, int max_stack) { + u64 val; + unw_word_t ips[max_stack]; unw_addr_space_t addr_space; unw_cursor_t c; - int ret; - - addr_space = thread__priv(ui->thread); - if (addr_space == NULL) - return -1; + int ret, i = 0; - ret = unw_init_remote(&c, addr_space, ui); + ret = perf_reg_value(&val, &ui->sample->user_regs, PERF_REG_IP); if (ret) - display_error(ret); + return ret; - while (!ret && (unw_step(&c) > 0) && max_stack--) { - unw_word_t ip; + ips[i++] = (unw_word_t) val; - unw_get_reg(&c, UNW_REG_IP, &ip); - ret = ip ? entry(ip, ui->thread, cb, arg) : 0; + /* + * If we need more than one entry, do the DWARF + * unwind itself. + */ + if (max_stack - 1 > 0) { + addr_space = thread__priv(ui->thread); + if (addr_space == NULL) + return -1; + + ret = unw_init_remote(&c, addr_space, ui); + if (ret) + display_error(ret); + + while (!ret && (unw_step(&c) > 0) && i < max_stack) { + unw_get_reg(&c, UNW_REG_IP, &ips[i]); + ++i; + } + + max_stack = i; + } + + /* + * Display what we got based on the order setup. + */ + for (i = 0; i < max_stack && !ret; i++) { + int j = i; + + if (callchain_param.order == ORDER_CALLER) + j = max_stack - i - 1; + ret = ips[j] ? entry(ips[j], ui->thread, cb, arg) : 0; } return ret; @@ -640,24 +673,17 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, int max_stack) { - u64 ip; struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->mg->machine, }; - int ret; if (!data->user_regs.regs) return -EINVAL; - ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP); - if (ret) - return ret; - - ret = entry(ip, thread, cb, arg); - if (ret) - return -ENOMEM; + if (max_stack <= 0) + return -EINVAL; - return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0; + return get_entries(&ui, cb, arg, max_stack); } diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 47b1e36c7ea0..88b8f8d21f58 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -16,12 +16,15 @@ #include <linux/kernel.h> #include <unistd.h> #include "callchain.h" +#include "strlist.h" +#include <subcmd/exec-cmd.h> struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_ABS, .min_percent = 0.5, .order = ORDER_CALLEE, - .key = CCKEY_FUNCTION + .key = CCKEY_FUNCTION, + .value = CCVAL_PERCENT, }; /* @@ -351,41 +354,8 @@ void sighandler_dump_stack(int sig) { psignal(sig, "perf"); dump_stack(); - exit(sig); -} - -void get_term_dimensions(struct winsize *ws) -{ - char *s = getenv("LINES"); - - if (s != NULL) { - ws->ws_row = atoi(s); - s = getenv("COLUMNS"); - if (s != NULL) { - ws->ws_col = atoi(s); - if (ws->ws_row && ws->ws_col) - return; - } - } -#ifdef TIOCGWINSZ - if (ioctl(1, TIOCGWINSZ, ws) == 0 && - ws->ws_row && ws->ws_col) - return; -#endif - ws->ws_row = 25; - ws->ws_col = 80; -} - -void set_term_quiet_input(struct termios *old) -{ - struct termios tc; - - tcgetattr(0, old); - tc = *old; - tc.c_lflag &= ~(ICANON | ECHO); - tc.c_cc[VMIN] = 0; - tc.c_cc[VTIME] = 0; - tcsetattr(0, TCSANOW, &tc); + signal(sig, SIG_DFL); + raise(sig); } int parse_nsec_time(const char *str, u64 *ptime) @@ -695,3 +665,28 @@ fetch_kernel_version(unsigned int *puint, char *str, *puint = (version << 16) + (patchlevel << 8) + sublevel; return 0; } + +const char *perf_tip(const char *dirpath) +{ + struct strlist *tips; + struct str_node *node; + char *tip = NULL; + struct strlist_config conf = { + .dirname = system_path(dirpath) , + }; + + tips = strlist__new("tips.txt", &conf); + if (tips == NULL || strlist__nr_entries(tips) == 1) { + tip = (char *)"Cannot find tips.txt file"; + goto out; + } + + node = strlist__entry(tips, random() % strlist__nr_entries(tips)); + if (asprintf(&tip, "Tip: %s", node->s) < 0) + tip = (char *)"Tip: get more memory! ;-)"; + +out: + strlist__delete(tips); + + return tip; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index dcc659017976..fe915e616f9b 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -53,6 +53,7 @@ #include <stdlib.h> #include <stdarg.h> #include <string.h> +#include <term.h> #include <errno.h> #include <limits.h> #include <sys/param.h> @@ -150,12 +151,6 @@ extern void set_warning_routine(void (*routine)(const char *err, va_list params) extern int prefixcmp(const char *str, const char *prefix); extern void set_buildid_dir(const char *dir); -static inline const char *skip_prefix(const char *str, const char *prefix) -{ - size_t len = strlen(prefix); - return strncmp(str, prefix, len) ? NULL : str + len; -} - #ifdef __GLIBC_PREREQ #if __GLIBC_PREREQ(2, 1) #define HAVE_STRCHRNUL @@ -186,14 +181,6 @@ static inline void *zalloc(size_t size) #define zfree(ptr) ({ free(*ptr); *ptr = NULL; }) -static inline int has_extension(const char *filename, const char *ext) -{ - size_t len = strlen(filename); - size_t extlen = strlen(ext); - - return len > extlen && !memcmp(filename + len - extlen, ext, extlen); -} - /* Sane ctype - no locale, and works with signed chars */ #undef isascii #undef isspace @@ -282,9 +269,6 @@ void sighandler_dump_stack(int sig); extern unsigned int page_size; extern int cacheline_size; -void get_term_dimensions(struct winsize *ws); -void set_term_quiet_input(struct termios *old); - struct parse_tag { char tag; int mult; @@ -358,4 +342,6 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_FMT "%d.%d.%d" #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) +const char *perf_tip(const char *dirpath); + #endif /* GIT_COMPAT_UTIL_H */ diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 5236e073919d..0f80eefb0bfd 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -38,8 +38,6 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -grace=120 - T=/tmp/kvm-test-1-run.sh.$$ trap 'rm -rf $T' 0 touch $T @@ -152,7 +150,7 @@ fi qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`" # Generate architecture-specific and interaction-specific qemu arguments -qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$builddir/console.log"`" +qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$resdir/console.log"`" # Generate qemu -append arguments qemu_append="`identify_qemu_append "$QEMU"`" @@ -168,7 +166,7 @@ then touch $resdir/buildonly exit 0 fi -echo "NOTE: $QEMU either did not run or was interactive" > $builddir/console.log +echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log echo $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd ( $QEMU $qemu_args -m 512 -kernel $resdir/bzImage -append "$qemu_append $boot_args"; echo $? > $resdir/qemu-retval ) & qemu_pid=$! @@ -214,7 +212,7 @@ then else break fi - if test $kruntime -ge $((seconds + grace)) + if test $kruntime -ge $((seconds + $TORTURE_SHUTDOWN_GRACE)) then echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid @@ -224,6 +222,5 @@ then done fi -cp $builddir/console.log $resdir parse-torture.sh $resdir/console.log $title parse-console.sh $resdir/console.log $title diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index f6483609ebc2..4a431767f77a 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -42,6 +42,7 @@ TORTURE_DEFCONFIG=defconfig TORTURE_BOOT_IMAGE="" TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD TORTURE_KMAKE_ARG="" +TORTURE_SHUTDOWN_GRACE=180 TORTURE_SUITE=rcu resdir="" configs="" @@ -149,6 +150,11 @@ do resdir=$2 shift ;; + --shutdown-grace) + checkarg --shutdown-grace "(seconds)" "$#" "$2" '^[0-9]*$' '^error' + TORTURE_SHUTDOWN_GRACE=$2 + shift + ;; --torture) checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\)$' '^--' TORTURE_SUITE=$2 @@ -266,6 +272,7 @@ TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC +TORTURE_SHUTDOWN_GRACE="$TORTURE_SHUTDOWN_GRACE"; export TORTURE_SHUTDOWN_GRACE TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE if ! test -e $resdir then @@ -307,10 +314,10 @@ awk < $T/cfgcpu.pack \ } # Dump out the scripting required to run one test batch. -function dump(first, pastlast) +function dump(first, pastlast, batchnum) { - print "echo ----Start batch: `date`"; - print "echo ----Start batch: `date` >> " rd "/log"; + print "echo ----Start batch " batchnum ": `date`"; + print "echo ----Start batch " batchnum ": `date` >> " rd "/log"; jn=1 for (j = first; j < pastlast; j++) { builddir=KVM "/b" jn @@ -371,25 +378,28 @@ END { njobs = i; nc = ncpus; first = 0; + batchnum = 1; # Each pass through the following loop considers one test. for (i = 0; i < njobs; i++) { if (ncpus == 0) { # Sequential test specified, each test its own batch. - dump(i, i + 1); + dump(i, i + 1, batchnum); first = i; + batchnum++; } else if (nc < cpus[i] && i != 0) { # Out of CPUs, dump out a batch. - dump(first, i); + dump(first, i, batchnum); first = i; nc = ncpus; + batchnum++; } # Account for the CPUs needed by the current test. nc -= cpus[i]; } # Dump the last batch. if (ncpus != 0) - dump(first, i); + dump(first, i, batchnum); }' >> $T/script cat << ___EOF___ >> $T/script diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index d8f35cf116be..844787a0d7be 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -24,9 +24,6 @@ # # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com> -T=/tmp/abat-chk-badness.sh.$$ -trap 'rm -f $T' 0 - file="$1" title="$2" @@ -36,9 +33,41 @@ if grep -Pq '\x00' < $file then print_warning Console output contains nul bytes, old qemu still running? fi -egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T -if test -s $T +egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags +if test -s $1.diags then print_warning Assertion failure in $file $title - cat $T + # cat $1.diags + summary="" + n_badness=`grep -c Badness $1` + if test "$n_badness" -ne 0 + then + summary="$summary Badness: $n_badness" + fi + n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'` + if test "$n_warn" -ne 0 + then + summary="$summary Warnings: $n_warn" + fi + n_bugs=`egrep -c 'BUG|Oops:' $1` + if test "$n_bugs" -ne 0 + then + summary="$summary Bugs: $n_bugs" + fi + n_calltrace=`grep -c 'Call Trace:' $1` + if test "$n_calltrace" -ne 0 + then + summary="$summary Call Traces: $n_calltrace" + fi + n_lockdep=`grep -c =========== $1` + if test "$n_badness" -ne 0 + then + summary="$summary lockdep: $n_badness" + fi + n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1` + if test "$n_stalls" -ne 0 + then + summary="$summary Stalls: $n_stalls" + fi + print_warning Summary: $summary fi diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt index 9ef33a743b73..24396ae8355b 100644 --- a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt +++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt @@ -20,7 +20,6 @@ CONFIG_PROVE_RCU CONFIG_NO_HZ_FULL_SYSIDLE CONFIG_RCU_NOCB_CPU -CONFIG_RCU_USER_QS Meaningless for TINY_RCU. diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt index 657f3a035488..4e2b1893d40d 100644 --- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt +++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt @@ -72,10 +72,6 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE Always used in KVM testing. -CONFIG_RCU_USER_QS - - Redundant with CONFIG_NO_HZ_FULL. - CONFIG_PREEMPT_RCU CONFIG_TREE_RCU diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 65461f821a75..7a2f449bd85d 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1114,7 +1114,7 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map) return true; } - return dist_active_irq(vcpu); + return vgic_irq_is_active(vcpu, map->virt_irq); } /* |
