x86: Store a per-cpu shadow copy of CR4

Context switches and TLB flushes can change individual bits of CR4.
CR4 reads take several cycles, so store a shadow copy of CR4 in a
per-cpu variable.

To avoid wasting a cache line, I added the CR4 shadow to
cpu_tlbstate, which is already touched in switch_mm.  The heaviest
users of the cr4 shadow will be switch_mm and __switch_to_xtra, and
__switch_to_xtra is called shortly after switch_mm during context
switch, so the cacheline is likely to be hot.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Vince Weaver <vince@deater.net>
Cc: "hillf.zj" <hillf.zj@alibaba-inc.com>
Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/3a54dd3353fffbf84804398e00dfdc5b7c1afd7d.1414190806.git.luto@amacapital.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 46 insertions, 20 deletions

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 32444ae939ca..965c47d254aa 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -80,16 +80,16 @@ static inline void write_cr3(unsigned long x)
 	PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
 }
 
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
 {
 	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
 }
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
 {
 	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
 }
 
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
 {
 	PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
 }
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index e820c080a4e9..6a4b00fafb00 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -137,17 +137,17 @@ static inline void write_cr3(unsigned long x)
 	native_write_cr3(x);
 }
 
-static inline unsigned long read_cr4(void)
+static inline unsigned long __read_cr4(void)
 {
 	return native_read_cr4();
 }
 
-static inline unsigned long read_cr4_safe(void)
+static inline unsigned long __read_cr4_safe(void)
 {
 	return native_read_cr4_safe();
 }
 
-static inline void write_cr4(unsigned long x)
+static inline void __write_cr4(unsigned long x)
 {
 	native_write_cr4(x);
 }
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index fc0c4bc356ce..cd791948b286 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -15,14 +15,37 @@
 #define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
 #endif
 
+struct tlb_state {
+#ifdef CONFIG_SMP
+	struct mm_struct *active_mm;
+	int state;
+#endif
+
+	/*
+	 * Access to this CR4 shadow and to H/W CR4 is protected by
+	 * disabling interrupts when modifying either one.
+	 */
+	unsigned long cr4;
+};
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
+
+/* Initialize cr4 shadow for this CPU. */
+static inline void cr4_init_shadow(void)
+{
+	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
+}
+
 /* Set in this cpu's CR4. */
 static inline void cr4_set_bits(unsigned long mask)
 {
 	unsigned long cr4;
 
-	cr4 = read_cr4();
-	cr4 |= mask;
-	write_cr4(cr4);
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	if ((cr4 | mask) != cr4) {
+		cr4 |= mask;
+		this_cpu_write(cpu_tlbstate.cr4, cr4);
+		__write_cr4(cr4);
+	}
 }
 
 /* Clear in this cpu's CR4. */
@@ -30,9 +53,18 @@ static inline void cr4_clear_bits(unsigned long mask)
 {
 	unsigned long cr4;
 
-	cr4 = read_cr4();
-	cr4 &= ~mask;
-	write_cr4(cr4);
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	if ((cr4 & ~mask) != cr4) {
+		cr4 &= ~mask;
+		this_cpu_write(cpu_tlbstate.cr4, cr4);
+		__write_cr4(cr4);
+	}
+}
+
+/* Read the CR4 shadow. */
+static inline unsigned long cr4_read_shadow(void)
+{
+	return this_cpu_read(cpu_tlbstate.cr4);
 }
 
 /*
@@ -61,7 +93,7 @@ static inline void __native_flush_tlb_global_irq_disabled(void)
 {
 	unsigned long cr4;
 
-	cr4 = native_read_cr4();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
 	/* clear PGE */
 	native_write_cr4(cr4 & ~X86_CR4_PGE);
 	/* write old PGE again and flush TLBs */
@@ -221,12 +253,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 #define TLBSTATE_OK	1
 #define TLBSTATE_LAZY	2
 
-struct tlb_state {
-	struct mm_struct *active_mm;
-	int state;
-};
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
-
 static inline void reset_lazy_tlbstate(void)
 {
 	this_cpu_write(cpu_tlbstate.state, 0);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index f41e19ca717b..cce9ee68e335 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -46,7 +46,7 @@ static inline void cpu_vmxoff(void)
 
 static inline int cpu_vmx_enabled(void)
 {
-	return read_cr4() & X86_CR4_VMXE;
+	return __read_cr4() & X86_CR4_VMXE;
 }
 
 /** Disable VMX if it is enabled on the current CPU