summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/alternative.c54
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/aperture_64.c2
-rw-r--r--arch/x86/kernel/apic/apic.c44
-rw-r--r--arch/x86/kernel/cfi.c86
-rw-r--r--arch/x86/kernel/cpu/acrn.c3
-rw-r--r--arch/x86/kernel/cpu/feat_ctl.c2
-rw-r--r--arch/x86/kernel/cpu/mce/apei.c13
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c10
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c5
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c17
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c117
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c75
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h61
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c232
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c14
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c216
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.c26
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.h2
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c15
-rw-r--r--arch/x86/kernel/dumpstack.c2
-rw-r--r--arch/x86/kernel/early_printk.c14
-rw-r--r--arch/x86/kernel/rtc.c63
-rw-r--r--arch/x86/kernel/traps.c4
-rw-r--r--arch/x86/kernel/x86_init.c2
26 files changed, 685 insertions, 398 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a20a5ebfacd7..1286a73ebdbc 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -139,6 +139,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o
+obj-$(CONFIG_CFI_CLANG) += cfi.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 62f6b8b7c4a5..5cadcea035e0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -453,6 +453,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
return ret;
i += ret;
+ /*
+ * The compiler is supposed to EMIT an INT3 after every unconditional
+ * JMP instruction due to AMD BTC. However, if the compiler is too old
+ * or SLS isn't enabled, we still need an INT3 after indirect JMPs
+ * even on Intel.
+ */
+ if (op == JMP32_INSN_OPCODE && i < insn->length)
+ bytes[i++] = INT3_INSN_OPCODE;
+
for (; i < insn->length;)
bytes[i++] = BYTES_NOP1;
@@ -1319,22 +1328,23 @@ struct bp_patching_desc {
atomic_t refs;
};
-static struct bp_patching_desc *bp_desc;
+static struct bp_patching_desc bp_desc;
static __always_inline
-struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+struct bp_patching_desc *try_get_desc(void)
{
- /* rcu_dereference */
- struct bp_patching_desc *desc = __READ_ONCE(*descp);
+ struct bp_patching_desc *desc = &bp_desc;
- if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
+ if (!arch_atomic_inc_not_zero(&desc->refs))
return NULL;
return desc;
}
-static __always_inline void put_desc(struct bp_patching_desc *desc)
+static __always_inline void put_desc(void)
{
+ struct bp_patching_desc *desc = &bp_desc;
+
smp_mb__before_atomic();
arch_atomic_dec(&desc->refs);
}
@@ -1367,15 +1377,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
/*
* Having observed our INT3 instruction, we now must observe
- * bp_desc:
+ * bp_desc with non-zero refcount:
*
- * bp_desc = desc INT3
+ * bp_desc.refs = 1 INT3
* WMB RMB
- * write INT3 if (desc)
+ * write INT3 if (bp_desc.refs != 0)
*/
smp_rmb();
- desc = try_get_desc(&bp_desc);
+ desc = try_get_desc();
if (!desc)
return 0;
@@ -1429,7 +1439,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
ret = 1;
out_put:
- put_desc(desc);
+ put_desc();
return ret;
}
@@ -1460,18 +1470,20 @@ static int tp_vec_nr;
*/
static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
{
- struct bp_patching_desc desc = {
- .vec = tp,
- .nr_entries = nr_entries,
- .refs = ATOMIC_INIT(1),
- };
unsigned char int3 = INT3_INSN_OPCODE;
unsigned int i;
int do_sync;
lockdep_assert_held(&text_mutex);
- smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
+ bp_desc.vec = tp;
+ bp_desc.nr_entries = nr_entries;
+
+ /*
+ * Corresponds to the implicit memory barrier in try_get_desc() to
+ * ensure reading a non-zero refcount provides up to date bp_desc data.
+ */
+ atomic_set_release(&bp_desc.refs, 1);
/*
* Corresponding read barrier in int3 notifier for making sure the
@@ -1559,12 +1571,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
text_poke_sync();
/*
- * Remove and synchronize_rcu(), except we have a very primitive
- * refcount based completion.
+ * Remove and wait for refs to be zero.
*/
- WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
- if (!atomic_dec_and_test(&desc.refs))
- atomic_cond_read_acquire(&desc.refs, !VAL);
+ if (!atomic_dec_and_test(&bp_desc.refs))
+ atomic_cond_read_acquire(&bp_desc.refs, !VAL);
}
static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 194d54eed537..19a0207e529f 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -53,7 +53,7 @@ static u32 *iommu_gatt_base; /* Remapping table */
* of only flushing when an mapping is reused. With it true the GART is
* flushed for every mapping. Problem is that doing the lazy flush seems
* to trigger bugs with some popular PCI cards, in particular 3ware (but
- * has been also also seen with Qlogic at least).
+ * has been also seen with Qlogic at least).
*/
static int iommu_fullflush = 1;
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 7a5630d904b2..4feaa670d578 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -36,7 +36,7 @@
/*
* Using 512M as goal, in case kexec will load kernel_big
* that will do the on-position decompress, and could overlap with
- * with the gart aperture that is used.
+ * the gart aperture that is used.
* Sequence:
* kernel_small
* ==> kexec (with kdump trigger path or gart still enabled)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 6d303d1d276c..c6876d3ea4b1 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -61,6 +61,7 @@
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
#include <asm/irq_regs.h>
+#include <asm/cpu.h>
unsigned int num_processors;
@@ -1751,11 +1752,26 @@ EXPORT_SYMBOL_GPL(x2apic_mode);
enum {
X2APIC_OFF,
- X2APIC_ON,
X2APIC_DISABLED,
+ /* All states below here have X2APIC enabled */
+ X2APIC_ON,
+ X2APIC_ON_LOCKED
};
static int x2apic_state;
+static bool x2apic_hw_locked(void)
+{
+ u64 ia32_cap;
+ u64 msr;
+
+ ia32_cap = x86_read_arch_cap_msr();
+ if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) {
+ rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
+ return (msr & LEGACY_XAPIC_DISABLED);
+ }
+ return false;
+}
+
static void __x2apic_disable(void)
{
u64 msr;
@@ -1793,6 +1809,10 @@ static int __init setup_nox2apic(char *str)
apicid);
return 0;
}
+ if (x2apic_hw_locked()) {
+ pr_warn("APIC locked in x2apic mode, can't disable\n");
+ return 0;
+ }
pr_warn("x2apic already enabled.\n");
__x2apic_disable();
}
@@ -1807,10 +1827,18 @@ early_param("nox2apic", setup_nox2apic);
void x2apic_setup(void)
{
/*
- * If x2apic is not in ON state, disable it if already enabled
+ * Try to make the AP's APIC state match that of the BSP, but if the
+ * BSP is unlocked and the AP is locked then there is a state mismatch.
+ * Warn about the mismatch in case a GP fault occurs due to a locked AP
+ * trying to be turned off.
+ */
+ if (x2apic_state != X2APIC_ON_LOCKED && x2apic_hw_locked())
+ pr_warn("x2apic lock mismatch between BSP and AP.\n");
+ /*
+ * If x2apic is not in ON or LOCKED state, disable it if already enabled
* from BIOS.
*/
- if (x2apic_state != X2APIC_ON) {
+ if (x2apic_state < X2APIC_ON) {
__x2apic_disable();
return;
}
@@ -1831,6 +1859,11 @@ static __init void x2apic_disable(void)
if (x2apic_id >= 255)
panic("Cannot disable x2apic, id: %08x\n", x2apic_id);
+ if (x2apic_hw_locked()) {
+ pr_warn("Cannot disable locked x2apic, id: %08x\n", x2apic_id);
+ return;
+ }
+
__x2apic_disable();
register_lapic_address(mp_lapic_addr);
}
@@ -1889,7 +1922,10 @@ void __init check_x2apic(void)
if (x2apic_enabled()) {
pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n");
x2apic_mode = 1;
- x2apic_state = X2APIC_ON;
+ if (x2apic_hw_locked())
+ x2apic_state = X2APIC_ON_LOCKED;
+ else
+ x2apic_state = X2APIC_ON;
} else if (!boot_cpu_has(X86_FEATURE_X2APIC)) {
x2apic_state = X2APIC_DISABLED;
}
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
new file mode 100644
index 000000000000..8674a5c0c031
--- /dev/null
+++ b/arch/x86/kernel/cfi.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Clang Control Flow Integrity (CFI) support.
+ *
+ * Copyright (C) 2022 Google LLC
+ */
+#include <asm/cfi.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <linux/string.h>
+
+/*
+ * Returns the target address and the expected type when regs->ip points
+ * to a compiler-generated CFI trap.
+ */
+static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
+ u32 *type)
+{
+ char buffer[MAX_INSN_SIZE];
+ struct insn insn;
+ int offset = 0;
+
+ *target = *type = 0;
+
+ /*
+ * The compiler generates the following instruction sequence
+ * for indirect call checks:
+ *
+ *   movl -<id>, %r10d ; 6 bytes
+ * addl -4(%reg), %r10d ; 4 bytes
+ * je .Ltmp1 ; 2 bytes
+ * ud2 ; <- regs->ip
+ * .Ltmp1:
+ *
+ * We can decode the expected type and the target address from the
+ * movl/addl instructions.
+ */
+ if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 12, MAX_INSN_SIZE))
+ return false;
+ if (insn_decode_kernel(&insn, &buffer[offset]))
+ return false;
+ if (insn.opcode.value != 0xBA)
+ return false;
+
+ *type = -(u32)insn.immediate.value;
+
+ if (copy_from_kernel_nofault(buffer, (void *)regs->ip - 6, MAX_INSN_SIZE))
+ return false;
+ if (insn_decode_kernel(&insn, &buffer[offset]))
+ return false;
+ if (insn.opcode.value != 0x3)
+ return false;
+
+ /* Read the target address from the register. */
+ offset = insn_get_modrm_rm_off(&insn, regs);
+ if (offset < 0)
+ return false;
+
+ *target = *(unsigned long *)((void *)regs + offset);
+
+ return true;
+}
+
+/*
+ * Checks if a ud2 trap is because of a CFI failure, and handles the trap
+ * if needed. Returns a bug_trap_type value similarly to report_bug.
+ */
+enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
+{
+ unsigned long target;
+ u32 type;
+
+ if (!is_cfi_trap(regs->ip))
+ return BUG_TRAP_TYPE_NONE;
+
+ if (!decode_cfi_insn(regs, &target, &type))
+ return report_cfi_failure_noaddr(regs, regs->ip);
+
+ return report_cfi_failure(regs, regs->ip, &target, type);
+}
+
+/*
+ * Ensure that __kcfi_typeid_ symbols are emitted for functions that may
+ * not be indirectly called with all configurations.
+ */
+__ADDRESSABLE(__memcpy)
diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c
index 23f5f27b5a02..485441b7f030 100644
--- a/arch/x86/kernel/cpu/acrn.c
+++ b/arch/x86/kernel/cpu/acrn.c
@@ -28,6 +28,9 @@ static void __init acrn_init_platform(void)
{
/* Setup the IDT for ACRN hypervisor callback */
alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback);
+
+ x86_platform.calibrate_tsc = acrn_get_tsc_khz;
+ x86_platform.calibrate_cpu = acrn_get_tsc_khz;
}
static bool acrn_x2apic_available(void)
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 993697e71854..03851240c3e3 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/tboot.h>
+#include <asm/cpu.h>
#include <asm/cpufeature.h>
#include <asm/msr-index.h>
#include <asm/processor.h>
#include <asm/vmx.h>
-#include "cpu.h"
#undef pr_fmt
#define pr_fmt(fmt) "x86/cpu: " fmt
diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 717192915f28..8ed341714686 100644
--- a/arch/x86/kernel/cpu/mce/apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -29,15 +29,26 @@
void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
{
struct mce m;
+ int lsb;
if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
return;
+ /*
+ * Even if the ->validation_bits are set for address mask,
+ * to be extra safe, check and reject an error radius '0',
+ * and fall back to the default page size.
+ */
+ if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
+ lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT);
+ else
+ lsb = PAGE_SHIFT;
+
mce_setup(&m);
m.bank = -1;
/* Fake a memory read error with unknown channel */
m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f;
- m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT;
+ m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb;
if (severity >= GHES_SEV_RECOVERABLE)
m.status |= MCI_STATUS_UC;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 8b2fcdfa6d31..e7410e98fc1f 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -788,6 +788,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
kfree(patch);
return -EINVAL;
}
+ patch->size = *patch_size;
mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
proc_id = mc_hdr->processor_rev_id;
@@ -869,7 +870,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
return ret;
memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
- memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+ memcpy(amd_ucode_patch, p->data, min_t(u32, p->size, PATCH_MAX_SIZE));
return ret;
}
@@ -924,12 +925,6 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
return ret;
}
-static enum ucode_state
-request_microcode_user(int cpu, const void __user *buf, size_t size)
-{
- return UCODE_ERROR;
-}
-
static void microcode_fini_cpu_amd(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
@@ -938,7 +933,6 @@ static void microcode_fini_cpu_amd(int cpu)
}
static struct microcode_ops microcode_amd_ops = {
- .request_microcode_user = request_microcode_user,
.request_microcode_fw = request_microcode_amd,
.collect_cpu_info = collect_cpu_info_amd,
.apply_microcode = apply_microcode_amd,
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index ad57e0e4d674..6a41cee242f6 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -491,7 +491,7 @@ wait_for_siblings:
*/
static int microcode_reload_late(void)
{
- int ret;
+ int old = boot_cpu_data.microcode, ret;
pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
pr_err("You should switch to early loading, if possible.\n");
@@ -503,7 +503,8 @@ static int microcode_reload_late(void)
if (ret == 0)
microcode_check();
- pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode);
+ pr_info("Reload completed, microcode revision: 0x%x -> 0x%x\n",
+ old, boot_cpu_data.microcode);
return ret;
}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 025c8f0cd948..1fcbd671f1df 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -916,24 +916,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
return ret;
}
-static enum ucode_state
-request_microcode_user(int cpu, const void __user *buf, size_t size)
-{
- struct iov_iter iter;
- struct iovec iov;
-
- if (is_blacklisted(cpu))
- return UCODE_NFOUND;
-
- iov.iov_base = (void __user *)buf;
- iov.iov_len = size;
- iov_iter_init(&iter, WRITE, &iov, 1, size);
-
- return generic_load_microcode(cpu, &iter);
-}
-
static struct microcode_ops microcode_intel_ops = {
- .request_microcode_user = request_microcode_user,
.request_microcode_fw = request_microcode_fw,
.collect_cpu_info = collect_cpu_info,
.apply_microcode = apply_microcode_intel,
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index bb1c3f5f60c8..de62b0b87ced 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -147,7 +147,6 @@ static inline void cache_alloc_hsw_probe(void)
r->cache.shareable_bits = 0xc0000;
r->cache.min_cbm_bits = 2;
r->alloc_capable = true;
- r->alloc_enabled = true;
rdt_alloc_capable = true;
}
@@ -211,7 +210,6 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
thread_throttle_mode_init();
r->alloc_capable = true;
- r->alloc_enabled = true;
return true;
}
@@ -242,7 +240,6 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
r->data_width = 4;
r->alloc_capable = true;
- r->alloc_enabled = true;
return true;
}
@@ -261,7 +258,6 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
r->cache.shareable_bits = ebx & r->default_ctrl;
r->data_width = (r->cache.cbm_len + 3) / 4;
r->alloc_capable = true;
- r->alloc_enabled = true;
}
static void rdt_get_cdp_config(int level)
@@ -300,7 +296,7 @@ mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
* that can be written to QOS_MSRs.
* There are currently no SKUs which support non linear delay values.
*/
-u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
+static u32 delay_bw_map(unsigned long bw, struct rdt_resource *r)
{
if (r->membw.delay_linear)
return MAX_MBA_BW - bw;
@@ -401,7 +397,7 @@ struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
return NULL;
}
-void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
+static void setup_default_ctrlval(struct rdt_resource *r, u32 *dc)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
int i;
@@ -410,12 +406,17 @@ void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm)
* Initialize the Control MSRs to having no control.
* For Cache Allocation: Set all bits in cbm
* For Memory Allocation: Set b/w requested to 100%
- * and the bandwidth in MBps to U32_MAX
*/
- for (i = 0; i < hw_res->num_closid; i++, dc++, dm++) {
+ for (i = 0; i < hw_res->num_closid; i++, dc++)
*dc = r->default_ctrl;
- *dm = MBA_MAX_MBPS;
- }
+}
+
+static void domain_free(struct rdt_hw_domain *hw_dom)
+{
+ kfree(hw_dom->arch_mbm_total);
+ kfree(hw_dom->arch_mbm_local);
+ kfree(hw_dom->ctrl_val);
+ kfree(hw_dom);
}
static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
@@ -423,23 +424,15 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
struct msr_param m;
- u32 *dc, *dm;
+ u32 *dc;
dc = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->ctrl_val),
GFP_KERNEL);
if (!dc)
return -ENOMEM;
- dm = kmalloc_array(hw_res->num_closid, sizeof(*hw_dom->mbps_val),
- GFP_KERNEL);
- if (!dm) {
- kfree(dc);
- return -ENOMEM;
- }
-
hw_dom->ctrl_val = dc;
- hw_dom->mbps_val = dm;
- setup_default_ctrlval(r, dc, dm);
+ setup_default_ctrlval(r, dc);
m.low = 0;
m.high = hw_res->num_closid;
@@ -447,39 +440,31 @@ static int domain_setup_ctrlval(struct rdt_resource *r, struct rdt_domain *d)
return 0;
}
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+/**
+ * arch_domain_mbm_alloc() - Allocate arch private storage for the MBM counters
+ * @num_rmid: The size of the MBM counter array
+ * @hw_dom: The domain that owns the allocated arrays
+ */
+static int arch_domain_mbm_alloc(u32 num_rmid, struct rdt_hw_domain *hw_dom)
{
size_t tsize;
- if (is_llc_occupancy_enabled()) {
- d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
- if (!d->rmid_busy_llc)
- return -ENOMEM;
- INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
- }
if (is_mbm_total_enabled()) {
- tsize = sizeof(*d->mbm_total);
- d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
- if (!d->mbm_total) {
- bitmap_free(d->rmid_busy_llc);
+ tsize = sizeof(*hw_dom->arch_mbm_total);
+ hw_dom->arch_mbm_total = kcalloc(num_rmid, tsize, GFP_KERNEL);
+ if (!hw_dom->arch_mbm_total)
return -ENOMEM;
- }
}
if (is_mbm_local_enabled()) {
- tsize = sizeof(*d->mbm_local);
- d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
- if (!d->mbm_local) {
- bitmap_free(d->rmid_busy_llc);
- kfree(d->mbm_total);
+ tsize = sizeof(*hw_dom->arch_mbm_local);
+ hw_dom->arch_mbm_local = kcalloc(num_rmid, tsize, GFP_KERNEL);
+ if (!hw_dom->arch_mbm_local) {
+ kfree(hw_dom->arch_mbm_total);
+ hw_dom->arch_mbm_total = NULL;
return -ENOMEM;
}
}
- if (is_mbm_enabled()) {
- INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
- mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
- }
-
return 0;
}
@@ -502,6 +487,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
struct list_head *add_pos = NULL;
struct rdt_hw_domain *hw_dom;
struct rdt_domain *d;
+ int err;
d = rdt_find_domain(r, id, &add_pos);
if (IS_ERR(d)) {
@@ -527,25 +513,22 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
rdt_domain_reconfigure_cdp(r);
if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
- kfree(hw_dom);
+ domain_free(hw_dom);
return;
}
- if (r->mon_capable && domain_setup_mon_state(r, d)) {
- kfree(hw_dom->ctrl_val);
- kfree(hw_dom->mbps_val);
- kfree(hw_dom);
+ if (r->mon_capable && arch_domain_mbm_alloc(r->num_rmid, hw_dom)) {
+ domain_free(hw_dom);
return;
}
list_add_tail(&d->list, add_pos);
- /*
- * If resctrl is mounted, add
- * per domain monitor data directories.
- */
- if (static_branch_unlikely(&rdt_mon_enable_key))
- mkdir_mondata_subdir_allrdtgrp(r, d);
+ err = resctrl_online_domain(r, d);
+ if (err) {
+ list_del(&d->list);
+ domain_free(hw_dom);
+ }
}
static void domain_remove_cpu(int cpu, struct rdt_resource *r)
@@ -563,27 +546,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
cpumask_clear_cpu(cpu, &d->cpu_mask);
if (cpumask_empty(&d->cpu_mask)) {
- /*
- * If resctrl is mounted, remove all the
- * per domain monitor data directories.
- */
- if (static_branch_unlikely(&rdt_mon_enable_key))
- rmdir_mondata_subdir_allrdtgrp(r, d->id);
+ resctrl_offline_domain(r, d);
list_del(&d->list);
- if (r->mon_capable && is_mbm_enabled())
- cancel_delayed_work(&d->mbm_over);
- if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
- /*
- * When a package is going down, forcefully
- * decrement rmid->ebusy. There is no way to know
- * that the L3 was flushed and hence may lead to
- * incorrect counts in rare scenarios, but leaving
- * the RMID as busy creates RMID leaks if the
- * package never comes back.
- */
- __check_limbo(d, true);
- cancel_delayed_work(&d->cqm_limbo);
- }
/*
* rdt_domain "d" is going to be freed below, so clear
@@ -591,13 +555,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
*/
if (d->plr)
d->plr->d = NULL;
+ domain_free(hw_dom);
- kfree(hw_dom->ctrl_val);
- kfree(hw_dom->mbps_val);
- bitmap_free(d->rmid_busy_llc);
- kfree(d->mbm_total);
- kfree(d->mbm_local);
- kfree(hw_dom);
return;
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 87666275eed9..1dafbdc5ac31 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -61,6 +61,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
struct rdt_domain *d)
{
struct resctrl_staged_config *cfg;
+ u32 closid = data->rdtgrp->closid;
struct rdt_resource *r = s->res;
unsigned long bw_val;
@@ -72,6 +73,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
if (!bw_validate(data->buf, &bw_val, r))
return -EINVAL;
+
+ if (is_mba_sc(r)) {
+ d->mbps_val[closid] = bw_val;
+ return 0;
+ }
+
cfg->new_ctrl = bw_val;
cfg->have_new_ctrl = true;
@@ -261,14 +268,13 @@ static u32 get_config_index(u32 closid, enum resctrl_conf_type type)
static bool apply_config(struct rdt_hw_domain *hw_dom,
struct resctrl_staged_config *cfg, u32 idx,
- cpumask_var_t cpu_mask, bool mba_sc)
+ cpumask_var_t cpu_mask)
{
struct rdt_domain *dom = &hw_dom->d_resctrl;
- u32 *dc = !mba_sc ? hw_dom->ctrl_val : hw_dom->mbps_val;
- if (cfg->new_ctrl != dc[idx]) {
+ if (cfg->new_ctrl != hw_dom->ctrl_val[idx]) {
cpumask_set_cpu(cpumask_any(&dom->cpu_mask), cpu_mask);
- dc[idx] = cfg->new_ctrl;
+ hw_dom->ctrl_val[idx] = cfg->new_ctrl;
return true;
}
@@ -276,6 +282,27 @@ static bool apply_config(struct rdt_hw_domain *hw_dom,
return false;
}
+int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d,
+ u32 closid, enum resctrl_conf_type t, u32 cfg_val)
+{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ u32 idx = get_config_index(closid, t);
+ struct msr_param msr_param;
+
+ if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+ return -EINVAL;
+
+ hw_dom->ctrl_val[idx] = cfg_val;
+
+ msr_param.res = r;
+ msr_param.low = idx;
+ msr_param.high = idx + 1;
+ hw_res->msr_update(d, &msr_param, r);
+
+ return 0;
+}
+
int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
{
struct resctrl_staged_config *cfg;
@@ -284,14 +311,12 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
enum resctrl_conf_type t;
cpumask_var_t cpu_mask;
struct rdt_domain *d;
- bool mba_sc;
int cpu;
u32 idx;
if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL))
return -ENOMEM;
- mba_sc = is_mba_sc(r);
msr_param.res = NULL;
list_for_each_entry(d, &r->domains, list) {
hw_dom = resctrl_to_arch_dom(d);
@@ -301,7 +326,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
continue;
idx = get_config_index(closid, t);
- if (!apply_config(hw_dom, cfg, idx, cpu_mask, mba_sc))
+ if (!apply_config(hw_dom, cfg, idx, cpu_mask))
continue;
if (!msr_param.res) {
@@ -315,11 +340,7 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
}
}
- /*
- * Avoid writing the control msr with control values when
- * MBA software controller is enabled
- */
- if (cpumask_empty(cpu_mask) || mba_sc)
+ if (cpumask_empty(cpu_mask))
goto done;
cpu = get_cpu();
/* Update resource control msr on this CPU if it's in cpu_mask. */
@@ -406,6 +427,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
+
+ /*
+ * Writes to mba_sc resources update the software controller,
+ * not the control MSR.
+ */
+ if (is_mba_sc(r))
+ continue;
+
ret = resctrl_arch_update_domains(r, rdtgrp->closid);
if (ret)
goto out;
@@ -433,9 +462,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
u32 idx = get_config_index(closid, type);
- if (!is_mba_sc(r))
- return hw_dom->ctrl_val[idx];
- return hw_dom->mbps_val[idx];
+ return hw_dom->ctrl_val[idx];
}
static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
@@ -450,8 +477,12 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo
if (sep)
seq_puts(s, ";");
- ctrl_val = resctrl_arch_get_config(r, dom, closid,
- schema->conf_type);
+ if (is_mba_sc(r))
+ ctrl_val = dom->mbps_val[closid];
+ else
+ ctrl_val = resctrl_arch_get_config(r, dom, closid,
+ schema->conf_type);
+
seq_printf(s, r->format_str, dom->id, max_data_width,
ctrl_val);
sep = true;
@@ -518,7 +549,6 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
int rdtgroup_mondata_show(struct seq_file *m, void *arg)
{
struct kernfs_open_file *of = m->private;
- struct rdt_hw_resource *hw_res;
u32 resid, evtid, domid;
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
@@ -538,8 +568,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
domid = md.u.domid;
evtid = md.u.evtid;
- hw_res = &rdt_resources_all[resid];
- r = &hw_res->r_resctrl;
+ r = &rdt_resources_all[resid].r_resctrl;
d = rdt_find_domain(r, domid, NULL);
if (IS_ERR_OR_NULL(d)) {
ret = -ENOENT;
@@ -548,12 +577,12 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
mon_event_read(&rr, r, d, rdtgrp, evtid, false);
- if (rr.val & RMID_VAL_ERROR)
+ if (rr.err == -EIO)
seq_puts(m, "Error\n");
- else if (rr.val & RMID_VAL_UNAVAIL)
+ else if (rr.err == -EINVAL)
seq_puts(m, "Unavailable\n");
else
- seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale);
+ seq_printf(m, "%llu\n", rr.val);
out:
rdtgroup_kn_unlock(of->kn);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 1d647188a43b..5f7128686cfd 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -22,21 +22,12 @@
#define L2_QOS_CDP_ENABLE 0x01ULL
-/*
- * Event IDs are used to program IA32_QM_EVTSEL before reading event
- * counter from IA32_QM_CTR
- */
-#define QOS_L3_OCCUP_EVENT_ID 0x01
-#define QOS_L3_MBM_TOTAL_EVENT_ID 0x02
-#define QOS_L3_MBM_LOCAL_EVENT_ID 0x03
-
#define CQM_LIMBOCHECK_INTERVAL 1000
#define MBM_CNTR_WIDTH_BASE 24
#define MBM_OVERFLOW_INTERVAL 1000
#define MAX_MBA_BW 100u
#define MBA_IS_LINEAR 0x4
-#define MBA_MAX_MBPS U32_MAX
#define MAX_MBA_BW_AMD 0x800
#define MBM_CNTR_WIDTH_OFFSET_AMD 20
@@ -74,7 +65,7 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);
* @list: entry in &rdt_resource->evt_list
*/
struct mon_evt {
- u32 evtid;
+ enum resctrl_event_id evtid;
char *name;
struct list_head list;
};
@@ -91,9 +82,9 @@ struct mon_evt {
union mon_data_bits {
void *priv;
struct {
- unsigned int rid : 10;
- unsigned int evtid : 8;
- unsigned int domid : 14;
+ unsigned int rid : 10;
+ enum resctrl_event_id evtid : 8;
+ unsigned int domid : 14;
} u;
};
@@ -101,12 +92,12 @@ struct rmid_read {
struct rdtgroup *rgrp;
struct rdt_resource *r;
struct rdt_domain *d;
- int evtid;
+ enum resctrl_event_id evtid;
bool first;
+ int err;
u64 val;
};
-extern unsigned int resctrl_cqm_threshold;
extern bool rdt_alloc_capable;
extern bool rdt_mon_capable;
extern unsigned int rdt_mon_features;
@@ -288,35 +279,45 @@ struct rftype {
/**
* struct mbm_state - status for each MBM counter in each domain
- * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes)
- * @prev_msr: Value of IA32_QM_CTR for this RMID last time we read it
- * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
+ * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
* @prev_bw: The most recent bandwidth in MBps
* @delta_bw: Difference between the current and previous bandwidth
* @delta_comp: Indicates whether to compute the delta_bw
*/
struct mbm_state {
- u64 chunks;
- u64 prev_msr;
- u64 prev_bw_msr;
+ u64 prev_bw_bytes;
u32 prev_bw;
u32 delta_bw;
bool delta_comp;
};
/**
+ * struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s
+ * return value.
+ * @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes)
+ * @prev_msr: Value of IA32_QM_CTR last time it was read for the RMID used to
+ * find this struct.
+ */
+struct arch_mbm_state {
+ u64 chunks;
+ u64 prev_msr;
+};
+
+/**
* struct rdt_hw_domain - Arch private attributes of a set of CPUs that share
* a resource
* @d_resctrl: Properties exposed to the resctrl file system
* @ctrl_val: array of cache or mem ctrl values (indexed by CLOSID)
- * @mbps_val: When mba_sc is enabled, this holds the bandwidth in MBps
+ * @arch_mbm_total: arch private state for MBM total bandwidth
+ * @arch_mbm_local: arch private state for MBM local bandwidth
*
* Members of this structure are accessed via helpers that provide abstraction.
*/
struct rdt_hw_domain {
struct rdt_domain d_resctrl;
u32 *ctrl_val;
- u32 *mbps_val;
+ struct arch_mbm_state *arch_mbm_total;
+ struct arch_mbm_state *arch_mbm_local;
};
static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
@@ -459,14 +460,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
for_each_rdt_resource(r) \
if (r->mon_capable)
-#define for_each_alloc_enabled_rdt_resource(r) \
- for_each_rdt_resource(r) \
- if (r->alloc_enabled)
-
-#define for_each_mon_enabled_rdt_resource(r) \
- for_each_rdt_resource(r) \
- if (r->mon_enabled)
-
/* CPUID.(EAX=10H, ECX=ResID=1).EAX */
union cpuid_0x10_1_eax {
struct {
@@ -530,10 +523,6 @@ void free_rmid(u32 rmid);
int rdt_get_mon_l3_config(struct rdt_resource *r);
void mon_event_count(void *info);
int rdtgroup_mondata_show(struct seq_file *m, void *arg);
-void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- unsigned int dom_id);
-void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_domain *d);
void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
struct rdt_domain *d, struct rdtgroup *rdtgrp,
int evtid, int first);
@@ -542,8 +531,6 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom,
void mbm_handle_overflow(struct work_struct *work);
void __init intel_rdt_mbm_apply_quirk(void);
bool is_mba_sc(struct rdt_resource *r);
-void setup_default_ctrlval(struct rdt_resource *r, u32 *dc, u32 *dm);
-u32 delay_bw_map(unsigned long bw, struct rdt_resource *r);
void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index eaf25a234ff5..efe0c30d3a12 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -16,8 +16,12 @@
*/
#include <linux/module.h>
+#include <linux/sizes.h>
#include <linux/slab.h>
+
#include <asm/cpu_device_id.h>
+#include <asm/resctrl.h>
+
#include "internal.h"
struct rmid_entry {
@@ -37,8 +41,8 @@ static LIST_HEAD(rmid_free_lru);
* @rmid_limbo_count count of currently unused but (potentially)
* dirty RMIDs.
* This counts RMIDs that no one is currently using but that
- * may have a occupancy value > intel_cqm_threshold. User can change
- * the threshold occupancy value.
+ * may have a occupancy value > resctrl_rmid_realloc_threshold. User can
+ * change the threshold occupancy value.
*/
static unsigned int rmid_limbo_count;
@@ -59,10 +63,15 @@ bool rdt_mon_capable;
unsigned int rdt_mon_features;
/*
- * This is the threshold cache occupancy at which we will consider an
+ * This is the threshold cache occupancy in bytes at which we will consider an
* RMID available for re-allocation.
*/
-unsigned int resctrl_cqm_threshold;
+unsigned int resctrl_rmid_realloc_threshold;
+
+/*
+ * This is the maximum value for the reallocation threshold, in bytes.
+ */
+unsigned int resctrl_rmid_realloc_limit;
#define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5))
@@ -137,9 +146,54 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid)
return entry;
}
-static u64 __rmid_read(u32 rmid, u32 eventid)
+static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom,
+ u32 rmid,
+ enum resctrl_event_id eventid)
{
- u64 val;
+ switch (eventid) {
+ case QOS_L3_OCCUP_EVENT_ID:
+ return NULL;
+ case QOS_L3_MBM_TOTAL_EVENT_ID:
+ return &hw_dom->arch_mbm_total[rmid];
+ case QOS_L3_MBM_LOCAL_EVENT_ID:
+ return &hw_dom->arch_mbm_local[rmid];
+ }
+
+ /* Never expect to get here */
+ WARN_ON_ONCE(1);
+
+ return NULL;
+}
+
+void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
+ u32 rmid, enum resctrl_event_id eventid)
+{
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct arch_mbm_state *am;
+
+ am = get_arch_mbm_state(hw_dom, rmid, eventid);
+ if (am)
+ memset(am, 0, sizeof(*am));
+}
+
+static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
+{
+ u64 shift = 64 - width, chunks;
+
+ chunks = (cur_msr << shift) - (prev_msr << shift);
+ return chunks >> shift;
+}
+
+int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
+ u32 rmid, enum resctrl_event_id eventid, u64 *val)
+{
+ struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
+ struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
+ struct arch_mbm_state *am;
+ u64 msr_val, chunks;
+
+ if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask))
+ return -EINVAL;
/*
* As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
@@ -150,16 +204,26 @@ static u64 __rmid_read(u32 rmid, u32 eventid)
* are error bits.
*/
wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
- rdmsrl(MSR_IA32_QM_CTR, val);
-
- return val;
-}
+ rdmsrl(MSR_IA32_QM_CTR, msr_val);
+
+ if (msr_val & RMID_VAL_ERROR)
+ return -EIO;
+ if (msr_val & RMID_VAL_UNAVAIL)
+ return -EINVAL;
+
+ am = get_arch_mbm_state(hw_dom, rmid, eventid);
+ if (am) {
+ am->chunks += mbm_overflow_count(am->prev_msr, msr_val,
+ hw_res->mbm_width);
+ chunks = get_corrected_mbm_count(rmid, am->chunks);
+ am->prev_msr = msr_val;
+ } else {
+ chunks = msr_val;
+ }
-static bool rmid_dirty(struct rmid_entry *entry)
-{
- u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+ *val = chunks * hw_res->mon_scale;
- return val >= resctrl_cqm_threshold;
+ return 0;
}
/*
@@ -170,11 +234,11 @@ static bool rmid_dirty(struct rmid_entry *entry)
*/
void __check_limbo(struct rdt_domain *d, bool force_free)
{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
struct rmid_entry *entry;
- struct rdt_resource *r;
u32 crmid = 1, nrmid;
-
- r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+ bool rmid_dirty;
+ u64 val = 0;
/*
* Skip RMID 0 and start from RMID 1 and check all the RMIDs that
@@ -188,7 +252,15 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
break;
entry = __rmid_entry(nrmid);
- if (force_free || !rmid_dirty(entry)) {
+
+ if (resctrl_arch_rmid_read(r, d, entry->rmid,
+ QOS_L3_OCCUP_EVENT_ID, &val)) {
+ rmid_dirty = true;
+ } else {
+ rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
+ }
+
+ if (force_free || !rmid_dirty) {
clear_bit(entry->rmid, d->rmid_busy_llc);
if (!--entry->busy) {
rmid_limbo_count--;
@@ -227,19 +299,19 @@ int alloc_rmid(void)
static void add_rmid_to_limbo(struct rmid_entry *entry)
{
- struct rdt_resource *r;
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
struct rdt_domain *d;
- int cpu;
- u64 val;
-
- r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
+ int cpu, err;
+ u64 val = 0;
entry->busy = 0;
cpu = get_cpu();
list_for_each_entry(d, &r->domains, list) {
if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
- val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
- if (val <= resctrl_cqm_threshold)
+ err = resctrl_arch_rmid_read(r, d, entry->rmid,
+ QOS_L3_OCCUP_EVENT_ID,
+ &val);
+ if (err || val <= resctrl_rmid_realloc_threshold)
continue;
}
@@ -277,24 +349,18 @@ void free_rmid(u32 rmid)
list_add_tail(&entry->list, &rmid_free_lru);
}
-static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
+static int __mon_event_count(u32 rmid, struct rmid_read *rr)
{
- u64 shift = 64 - width, chunks;
+ struct mbm_state *m;
+ u64 tval = 0;
- chunks = (cur_msr << shift) - (prev_msr << shift);
- return chunks >> shift;
-}
+ if (rr->first)
+ resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
-static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
-{
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
- struct mbm_state *m;
- u64 chunks, tval;
+ rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval);
+ if (rr->err)
+ return rr->err;
- tval = __rmid_read(rmid, rr->evtid);
- if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
- return tval;
- }
switch (rr->evtid) {
case QOS_L3_OCCUP_EVENT_ID:
rr->val += tval;
@@ -308,48 +374,47 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
default:
/*
* Code would never reach here because an invalid
- * event id would fail the __rmid_read.
+ * event id would fail in resctrl_arch_rmid_read().
*/
- return RMID_VAL_ERROR;
+ return -EINVAL;
}
if (rr->first) {
memset(m, 0, sizeof(struct mbm_state));
- m->prev_bw_msr = m->prev_msr = tval;
return 0;
}
- chunks = mbm_overflow_count(m->prev_msr, tval, hw_res->mbm_width);
- m->chunks += chunks;
- m->prev_msr = tval;
-
- rr->val += get_corrected_mbm_count(rmid, m->chunks);
+ rr->val += tval;
return 0;
}
/*
+ * mbm_bw_count() - Update bw count from values previously read by
+ * __mon_event_count().
+ * @rmid: The rmid used to identify the cached mbm_state.
+ * @rr: The struct rmid_read populated by __mon_event_count().
+ *
* Supporting function to calculate the memory bandwidth
- * and delta bandwidth in MBps.
+ * and delta bandwidth in MBps. The chunks value previously read by
+ * __mon_event_count() is compared with the chunks value from the previous
+ * invocation. This must be called once per second to maintain values in MBps.
*/
static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
{
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
struct mbm_state *m = &rr->d->mbm_local[rmid];
- u64 tval, cur_bw, chunks;
+ u64 cur_bw, bytes, cur_bytes;
- tval = __rmid_read(rmid, rr->evtid);
- if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL))
- return;
+ cur_bytes = rr->val;
+ bytes = cur_bytes - m->prev_bw_bytes;
+ m->prev_bw_bytes = cur_bytes;
- chunks = mbm_overflow_count(m->prev_bw_msr, tval, hw_res->mbm_width);
- cur_bw = (get_corrected_mbm_count(rmid, chunks) * hw_res->mon_scale) >> 20;
+ cur_bw = bytes / SZ_1M;
if (m->delta_comp)
m->delta_bw = abs(cur_bw - m->prev_bw);
m->delta_comp = false;
m->prev_bw = cur_bw;
- m->prev_bw_msr = tval;
}
/*
@@ -361,11 +426,11 @@ void mon_event_count(void *info)
struct rdtgroup *rdtgrp, *entry;
struct rmid_read *rr = info;
struct list_head *head;
- u64 ret_val;
+ int ret;
rdtgrp = rr->rgrp;
- ret_val = __mon_event_count(rdtgrp->mon.rmid, rr);
+ ret = __mon_event_count(rdtgrp->mon.rmid, rr);
/*
* For Ctrl groups read data from child monitor groups and
@@ -377,13 +442,17 @@ void mon_event_count(void *info)
if (rdtgrp->type == RDTCTRL_GROUP) {
list_for_each_entry(entry, head, mon.crdtgrp_list) {
if (__mon_event_count(entry->mon.rmid, rr) == 0)
- ret_val = 0;
+ ret = 0;
}
}
- /* Report error if none of rmid_reads are successful */
- if (ret_val)
- rr->val = ret_val;
+ /*
+ * __mon_event_count() calls for newly created monitor groups may
+ * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
+ * Discard error if any of the monitor event reads succeeded.
+ */
+ if (ret == 0)
+ rr->err = 0;
}
/*
@@ -420,10 +489,8 @@ void mon_event_count(void *info)
*/
static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
{
- u32 closid, rmid, cur_msr, cur_msr_val, new_msr_val;
+ u32 closid, rmid, cur_msr_val, new_msr_val;
struct mbm_state *pmbm_data, *cmbm_data;
- struct rdt_hw_resource *hw_r_mba;
- struct rdt_hw_domain *hw_dom_mba;
u32 cur_bw, delta_bw, user_bw;
struct rdt_resource *r_mba;
struct rdt_domain *dom_mba;
@@ -433,8 +500,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
if (!is_mbm_local_enabled())
return;
- hw_r_mba = &rdt_resources_all[RDT_RESOURCE_MBA];
- r_mba = &hw_r_mba->r_resctrl;
+ r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+
closid = rgrp->closid;
rmid = rgrp->mon.rmid;
pmbm_data = &dom_mbm->mbm_local[rmid];
@@ -444,16 +511,13 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
pr_warn_once("Failure to get domain for MBA update\n");
return;
}
- hw_dom_mba = resctrl_to_arch_dom(dom_mba);
cur_bw = pmbm_data->prev_bw;
- user_bw = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
+ user_bw = dom_mba->mbps_val[closid];
delta_bw = pmbm_data->delta_bw;
- /*
- * resctrl_arch_get_config() chooses the mbps/ctrl value to return
- * based on is_mba_sc(). For now, reach into the hw_dom.
- */
- cur_msr_val = hw_dom_mba->ctrl_val[closid];
+
+ /* MBA resource doesn't support CDP */
+ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
/*
* For Ctrl groups read data from child monitor groups.
@@ -488,9 +552,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm)
return;
}
- cur_msr = hw_r_mba->msr_base + closid;
- wrmsrl(cur_msr, delay_bw_map(new_msr_val, r_mba));
- hw_dom_mba->ctrl_val[closid] = new_msr_val;
+ resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
/*
* Delta values are updated dynamically package wise for each
@@ -523,10 +585,12 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
*/
if (is_mbm_total_enabled()) {
rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
+ rr.val = 0;
__mon_event_count(rmid, &rr);
}
if (is_mbm_local_enabled()) {
rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+ rr.val = 0;
__mon_event_count(rmid, &rr);
/*
@@ -686,9 +750,10 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
{
unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
- unsigned int cl_size = boot_cpu_data.x86_cache_size;
+ unsigned int threshold;
int ret;
+ resctrl_rmid_realloc_limit = boot_cpu_data.x86_cache_size * 1024;
hw_res->mon_scale = boot_cpu_data.x86_cache_occ_scale;
r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1;
hw_res->mbm_width = MBM_CNTR_WIDTH_BASE;
@@ -705,10 +770,14 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
*
* For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC.
*/
- resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
+ threshold = resctrl_rmid_realloc_limit / r->num_rmid;
- /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */
- resctrl_cqm_threshold /= hw_res->mon_scale;
+ /*
+ * Because num_rmid may not be a power of two, round the value
+ * to the nearest multiple of hw_res->mon_scale so it matches a
+ * value the hardware will measure. mon_scale may not be a power of 2.
+ */
+ resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(threshold);
ret = dom_data_init(r);
if (ret)
@@ -717,7 +786,6 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)
l3_mon_evt_init(r);
r->mon_capable = true;
- r->mon_enabled = true;
return 0;
}
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index db813f819ad6..d961ae3ed96e 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -420,6 +420,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
struct pseudo_lock_region *plr = rdtgrp->plr;
u32 rmid_p, closid_p;
unsigned long i;
+ u64 saved_msr;
#ifdef CONFIG_KASAN
/*
* The registers used for local register variables are also used
@@ -463,6 +464,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
* the buffer and evict pseudo-locked memory read earlier from the
* cache.
*/
+ saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL);
__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
closid_p = this_cpu_read(pqr_state.cur_closid);
rmid_p = this_cpu_read(pqr_state.cur_rmid);
@@ -514,7 +516,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
/* Re-enable the hardware prefetcher(s) */
- wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr);
local_irq_enable();
plr->thread_done = 1;
@@ -835,7 +837,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
* First determine which cpus have pseudo-locked regions
* associated with them.
*/
- for_each_alloc_enabled_rdt_resource(r) {
+ for_each_alloc_capable_rdt_resource(r) {
list_for_each_entry(d_i, &r->domains, list) {
if (d_i->plr)
cpumask_or(cpu_with_psl, cpu_with_psl,
@@ -871,6 +873,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
static int measure_cycles_lat_fn(void *_plr)
{
struct pseudo_lock_region *plr = _plr;
+ u32 saved_low, saved_high;
unsigned long i;
u64 start, end;
void *mem_r;
@@ -879,6 +882,7 @@ static int measure_cycles_lat_fn(void *_plr)
/*
* Disable hardware prefetchers.
*/
+ rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
mem_r = READ_ONCE(plr->kmem);
/*
@@ -895,7 +899,7 @@ static int measure_cycles_lat_fn(void *_plr)
end = rdtsc_ordered();
trace_pseudo_lock_mem_latency((u32)(end - start));
}
- wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
local_irq_enable();
plr->thread_done = 1;
wake_up_interruptible(&plr->lock_thread_wq);
@@ -940,6 +944,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0;
struct perf_event *miss_event, *hit_event;
int hit_pmcnum, miss_pmcnum;
+ u32 saved_low, saved_high;
unsigned int line_size;
unsigned int size;
unsigned long i;
@@ -973,6 +978,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
/*
* Disable hardware prefetchers.
*/
+ rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
/* Initialize rest of local variables */
@@ -1031,7 +1037,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
*/
rmb();
/* Re-enable hardware prefetchers */
- wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+ wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
local_irq_enable();
out_hit:
perf_event_release_kernel(hit_event);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index f276aff521e8..e5a48f05e787 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1030,10 +1030,7 @@ static int rdt_delay_linear_show(struct kernfs_open_file *of,
static int max_threshold_occ_show(struct kernfs_open_file *of,
struct seq_file *seq, void *v)
{
- struct rdt_resource *r = of->kn->parent->priv;
- struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
-
- seq_printf(seq, "%u\n", resctrl_cqm_threshold * hw_res->mon_scale);
+ seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
return 0;
}
@@ -1055,7 +1052,6 @@ static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
- struct rdt_hw_resource *hw_res;
unsigned int bytes;
int ret;
@@ -1063,11 +1059,10 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
if (ret)
return ret;
- if (bytes > (boot_cpu_data.x86_cache_size * 1024))
+ if (bytes > resctrl_rmid_realloc_limit)
return -EINVAL;
- hw_res = resctrl_to_arch_res(of->kn->parent->priv);
- resctrl_cqm_threshold = bytes / hw_res->mon_scale;
+ resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
return nbytes;
}
@@ -1356,11 +1351,13 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct resctrl_schema *schema;
+ enum resctrl_conf_type type;
struct rdtgroup *rdtgrp;
struct rdt_resource *r;
struct rdt_domain *d;
unsigned int size;
int ret = 0;
+ u32 closid;
bool sep;
u32 ctrl;
@@ -1386,8 +1383,11 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
goto out;
}
+ closid = rdtgrp->closid;
+
list_for_each_entry(schema, &resctrl_schema_all, list) {
r = schema->res;
+ type = schema->conf_type;
sep = false;
seq_printf(s, "%*s:", max_name_width, schema->name);
list_for_each_entry(d, &r->domains, list) {
@@ -1396,9 +1396,12 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
size = 0;
} else {
- ctrl = resctrl_arch_get_config(r, d,
- rdtgrp->closid,
- schema->conf_type);
+ if (is_mba_sc(r))
+ ctrl = d->mbps_val[closid];
+ else
+ ctrl = resctrl_arch_get_config(r, d,
+ closid,
+ type);
if (r->rid == RDT_RESOURCE_MBA)
size = ctrl;
else
@@ -1756,7 +1759,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
if (ret)
goto out_destroy;
- /* loop over enabled controls, these are all alloc_enabled */
+ /* loop over enabled controls, these are all alloc_capable */
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
fflags = r->fflags | RF_CTRL_INFO;
@@ -1765,7 +1768,7 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
goto out_destroy;
}
- for_each_mon_enabled_rdt_resource(r) {
+ for_each_mon_capable_rdt_resource(r) {
fflags = r->fflags | RF_MON_INFO;
sprintf(name, "%s_MON", r->name);
ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
@@ -1889,26 +1892,61 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
l3_qos_cfg_update(&hw_res->cdp_enabled);
}
+static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_domain *d)
+{
+ u32 num_closid = resctrl_arch_get_num_closid(r);
+ int cpu = cpumask_any(&d->cpu_mask);
+ int i;
+
+ d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
+ GFP_KERNEL, cpu_to_node(cpu));
+ if (!d->mbps_val)
+ return -ENOMEM;
+
+ for (i = 0; i < num_closid; i++)
+ d->mbps_val[i] = MBA_MAX_MBPS;
+
+ return 0;
+}
+
+static void mba_sc_domain_destroy(struct rdt_resource *r,
+ struct rdt_domain *d)
+{
+ kfree(d->mbps_val);
+ d->mbps_val = NULL;
+}
+
/*
- * Enable or disable the MBA software controller
- * which helps user specify bandwidth in MBps.
* MBA software controller is supported only if
* MBM is supported and MBA is in linear scale.
*/
+static bool supports_mba_mbps(void)
+{
+ struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
+
+ return (is_mbm_local_enabled() &&
+ r->alloc_capable && is_mba_linear());
+}
+
+/*
+ * Enable or disable the MBA software controller
+ * which helps user specify bandwidth in MBps.
+ */
static int set_mba_sc(bool mba_sc)
{
struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl;
- struct rdt_hw_domain *hw_dom;
+ u32 num_closid = resctrl_arch_get_num_closid(r);
struct rdt_domain *d;
+ int i;
- if (!is_mbm_enabled() || !is_mba_linear() ||
- mba_sc == is_mba_sc(r))
+ if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
return -EINVAL;
r->membw.mba_sc = mba_sc;
+
list_for_each_entry(d, &r->domains, list) {
- hw_dom = resctrl_to_arch_dom(d);
- setup_default_ctrlval(r, hw_dom->ctrl_val, hw_dom->mbps_val);
+ for (i = 0; i < num_closid; i++)
+ d->mbps_val[i] = MBA_MAX_MBPS;
}
return 0;
@@ -2106,7 +2144,7 @@ static int schemata_list_create(void)
struct rdt_resource *r;
int ret = 0;
- for_each_alloc_enabled_rdt_resource(r) {
+ for_each_alloc_capable_rdt_resource(r) {
if (resctrl_arch_get_cdp_enabled(r->rid)) {
ret = schemata_list_add(r, CDP_CODE);
if (ret)
@@ -2261,7 +2299,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
ctx->enable_cdpl2 = true;
return 0;
case Opt_mba_mbps:
- if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ if (!supports_mba_mbps())
return -EINVAL;
ctx->enable_mba_mbps = true;
return 0;
@@ -2452,7 +2490,7 @@ static void rdt_kill_sb(struct super_block *sb)
set_mba_sc(false);
/*Put everything back to default values. */
- for_each_alloc_enabled_rdt_resource(r)
+ for_each_alloc_capable_rdt_resource(r)
reset_all_ctrls(r);
cdp_disable_all();
rmdir_all_sub();
@@ -2499,14 +2537,12 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
* Remove all subdirectories of mon_data of ctrl_mon groups
* and monitor groups with given domain id.
*/
-void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id)
+static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+ unsigned int dom_id)
{
struct rdtgroup *prgrp, *crgrp;
char name[32];
- if (!r->mon_enabled)
- return;
-
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
sprintf(name, "mon_%s_%02d", r->name, dom_id);
kernfs_remove_by_name(prgrp->mon.mon_data_kn, name);
@@ -2565,16 +2601,13 @@ out_destroy:
* Add all subdirectories of mon_data for "ctrl_mon" groups
* and "monitor" groups with given domain id.
*/
-void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_domain *d)
+static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
+ struct rdt_domain *d)
{
struct kernfs_node *parent_kn;
struct rdtgroup *prgrp, *crgrp;
struct list_head *head;
- if (!r->mon_enabled)
- return;
-
list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
parent_kn = prgrp->mon.mon_data_kn;
mkdir_mondata_subdir(parent_kn, d, r, prgrp);
@@ -2642,7 +2675,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
* Create the subdirectories for each domain. Note that all events
* in a domain like L3 are grouped into a resource whose domain is L3
*/
- for_each_mon_enabled_rdt_resource(r) {
+ for_each_mon_capable_rdt_resource(r) {
ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
if (ret)
goto out_destroy;
@@ -2786,14 +2819,19 @@ static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
}
/* Initialize MBA resource with default values. */
-static void rdtgroup_init_mba(struct rdt_resource *r)
+static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
{
struct resctrl_staged_config *cfg;
struct rdt_domain *d;
list_for_each_entry(d, &r->domains, list) {
+ if (is_mba_sc(r)) {
+ d->mbps_val[closid] = MBA_MAX_MBPS;
+ continue;
+ }
+
cfg = &d->staged_config[CDP_NONE];
- cfg->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+ cfg->new_ctrl = r->default_ctrl;
cfg->have_new_ctrl = true;
}
}
@@ -2808,7 +2846,9 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
if (r->rid == RDT_RESOURCE_MBA) {
- rdtgroup_init_mba(r);
+ rdtgroup_init_mba(r, rdtgrp->closid);
+ if (is_mba_sc(r))
+ continue;
} else {
ret = rdtgroup_init_cat(s, rdtgrp->closid);
if (ret < 0)
@@ -3236,6 +3276,110 @@ out:
return ret;
}
+static void domain_destroy_mon_state(struct rdt_domain *d)
+{
+ bitmap_free(d->rmid_busy_llc);
+ kfree(d->mbm_total);
+ kfree(d->mbm_local);
+}
+
+void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+ mba_sc_domain_destroy(r, d);
+
+ if (!r->mon_capable)
+ return;
+
+ /*
+ * If resctrl is mounted, remove all the
+ * per domain monitor data directories.
+ */
+ if (static_branch_unlikely(&rdt_mon_enable_key))
+ rmdir_mondata_subdir_allrdtgrp(r, d->id);
+
+ if (is_mbm_enabled())
+ cancel_delayed_work(&d->mbm_over);
+ if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) {
+ /*
+ * When a package is going down, forcefully
+ * decrement rmid->ebusy. There is no way to know
+ * that the L3 was flushed and hence may lead to
+ * incorrect counts in rare scenarios, but leaving
+ * the RMID as busy creates RMID leaks if the
+ * package never comes back.
+ */
+ __check_limbo(d, true);
+ cancel_delayed_work(&d->cqm_limbo);
+ }
+
+ domain_destroy_mon_state(d);
+}
+
+static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
+{
+ size_t tsize;
+
+ if (is_llc_occupancy_enabled()) {
+ d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL);
+ if (!d->rmid_busy_llc)
+ return -ENOMEM;
+ }
+ if (is_mbm_total_enabled()) {
+ tsize = sizeof(*d->mbm_total);
+ d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+ if (!d->mbm_total) {
+ bitmap_free(d->rmid_busy_llc);
+ return -ENOMEM;
+ }
+ }
+ if (is_mbm_local_enabled()) {
+ tsize = sizeof(*d->mbm_local);
+ d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL);
+ if (!d->mbm_local) {
+ bitmap_free(d->rmid_busy_llc);
+ kfree(d->mbm_total);
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+}
+
+int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
+{
+ int err;
+
+ lockdep_assert_held(&rdtgroup_mutex);
+
+ if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
+ /* RDT_RESOURCE_MBA is never mon_capable */
+ return mba_sc_domain_allocate(r, d);
+
+ if (!r->mon_capable)
+ return 0;
+
+ err = domain_setup_mon_state(r, d);
+ if (err)
+ return err;
+
+ if (is_mbm_enabled()) {
+ INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
+ mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+ }
+
+ if (is_llc_occupancy_enabled())
+ INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
+
+ /* If resctrl is mounted, add per domain monitor data directories. */
+ if (static_branch_unlikely(&rdt_mon_enable_key))
+ mkdir_mondata_subdir_allrdtgrp(r, d);
+
+ return 0;
+}
+
/*
* rdtgroup_init - rdtgroup initialization
*
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 24c1bb8eb196..9f13d724172e 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -12,6 +12,9 @@
#include "encls.h"
#include "sgx.h"
+static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+ struct sgx_backing *backing);
+
#define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd))
/*
* 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to
@@ -344,8 +347,11 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
}
va_page = sgx_encl_grow(encl, false);
- if (IS_ERR(va_page))
+ if (IS_ERR(va_page)) {
+ if (PTR_ERR(va_page) == -EBUSY)
+ vmret = VM_FAULT_NOPAGE;
goto err_out_epc;
+ }
if (va_page)
list_add(&va_page->list, &encl->va_pages);
@@ -914,7 +920,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
}
/**
- * sgx_encl_get_backing() - Pin the backing storage
+ * __sgx_encl_get_backing() - Pin the backing storage
* @encl: an enclave pointer
* @page_index: enclave page index
* @backing: data for accessing backing storage for the page
@@ -926,7 +932,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
* 0 on success,
* -errno otherwise.
*/
-static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+static int __sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing)
{
pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
@@ -1001,7 +1007,7 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
}
/**
- * sgx_encl_alloc_backing() - allocate a new backing storage page
+ * sgx_encl_alloc_backing() - create a new backing storage page
* @encl: an enclave pointer
* @page_index: enclave page index
* @backing: data for accessing backing storage for the page
@@ -1009,7 +1015,9 @@ static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
* When called from ksgxd, sets the active memcg from one of the
* mms in the enclave's mm_list prior to any backing page allocation,
* in order to ensure that shmem page allocations are charged to the
- * enclave.
+ * enclave. Create a backing page for loading data back into an EPC page with
+ * ELDU. This function takes a reference on a new backing page which
+ * must be dropped with a corresponding call to sgx_encl_put_backing().
*
* Return:
* 0 on success,
@@ -1022,7 +1030,7 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
struct mem_cgroup *memcg = set_active_memcg(encl_memcg);
int ret;
- ret = sgx_encl_get_backing(encl, page_index, backing);
+ ret = __sgx_encl_get_backing(encl, page_index, backing);
set_active_memcg(memcg);
mem_cgroup_put(encl_memcg);
@@ -1040,15 +1048,17 @@ int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
* It is the caller's responsibility to ensure that it is appropriate to use
* sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is
* not used correctly, this will cause an allocation which is not accounted for.
+ * This function takes a reference on an existing backing page which must be
+ * dropped with a corresponding call to sgx_encl_put_backing().
*
* Return:
* 0 on success,
* -errno otherwise.
*/
-int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+static int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing)
{
- return sgx_encl_get_backing(encl, page_index, backing);
+ return __sgx_encl_get_backing(encl, page_index, backing);
}
/**
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index a65a952116fd..f94ff14c9486 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -107,8 +107,6 @@ bool current_is_ksgxd(void);
void sgx_encl_release(struct kref *ref);
int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
const cpumask_t *sgx_encl_cpumask(struct sgx_encl *encl);
-int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
- struct sgx_backing *backing);
int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing);
void sgx_encl_put_backing(struct sgx_backing *backing);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 515e2a5f25bb..0aad028f04d4 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -49,9 +49,13 @@ static LIST_HEAD(sgx_dirty_page_list);
* Reset post-kexec EPC pages to the uninitialized state. The pages are removed
* from the input list, and made available for the page allocator. SECS pages
* prepending their children in the input list are left intact.
+ *
+ * Return 0 when sanitization was successful or kthread was stopped, and the
+ * number of unsanitized pages otherwise.
*/
-static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
+static unsigned long __sgx_sanitize_pages(struct list_head *dirty_page_list)
{
+ unsigned long left_dirty = 0;
struct sgx_epc_page *page;
LIST_HEAD(dirty);
int ret;
@@ -59,7 +63,7 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
/* dirty_page_list is thread-local, no need for a lock: */
while (!list_empty(dirty_page_list)) {
if (kthread_should_stop())
- return;
+ return 0;
page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
@@ -92,12 +96,14 @@ static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
} else {
/* The page is not yet clean - move to the dirty list. */
list_move_tail(&page->list, &dirty);
+ left_dirty++;
}
cond_resched();
}
list_splice(&dirty, dirty_page_list);
+ return left_dirty;
}
static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
@@ -395,10 +401,7 @@ static int ksgxd(void *p)
* required for SECS pages, whose child pages blocked EREMOVE.
*/
__sgx_sanitize_pages(&sgx_dirty_page_list);
- __sgx_sanitize_pages(&sgx_dirty_page_list);
-
- /* sanity check: */
- WARN_ON(!list_empty(&sgx_dirty_page_list));
+ WARN_ON(__sgx_sanitize_pages(&sgx_dirty_page_list));
while (!kthread_should_stop()) {
if (try_to_freeze())
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index afae4dd77495..b3dba35f466e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -128,7 +128,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
/* No access to the user space stack of other tasks. Ignore. */
break;
default:
- printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
+ printk("%sCode: Unable to access opcode bytes at 0x%lx.\n",
loglvl, prologue);
break;
}
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 68b38925a74f..44f937015e1e 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -264,11 +264,11 @@ static __init void early_pci_serial_init(char *s)
bar0 = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0);
/*
- * Verify it is a UART type device
+ * Verify it is a 16550-UART type device
*/
if (((classcode >> 16 != PCI_CLASS_COMMUNICATION_MODEM) &&
(classcode >> 16 != PCI_CLASS_COMMUNICATION_SERIAL)) ||
- (((classcode >> 8) & 0xff) != 0x02)) /* 16550 I/F at BAR0 */ {
+ (((classcode >> 8) & 0xff) != PCI_SERIAL_16550_COMPATIBLE)) {
if (!force)
return;
}
@@ -276,22 +276,22 @@ static __init void early_pci_serial_init(char *s)
/*
* Determine if it is IO or memory mapped
*/
- if (bar0 & 0x01) {
+ if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
/* it is IO mapped */
serial_in = io_serial_in;
serial_out = io_serial_out;
- early_serial_base = bar0&0xfffffffc;
+ early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK;
write_pci_config(bus, slot, func, PCI_COMMAND,
- cmdreg|PCI_COMMAND_IO);
+ cmdreg|PCI_COMMAND_IO);
} else {
/* It is memory mapped - assume 32-bit alignment */
serial_in = mem32_serial_in;
serial_out = mem32_serial_out;
/* WARNING! assuming the address is always in the first 4G */
early_serial_base =
- (unsigned long)early_ioremap(bar0 & 0xfffffff0, 0x10);
+ (unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);
write_pci_config(bus, slot, func, PCI_COMMAND,
- cmdreg|PCI_COMMAND_MEMORY);
+ cmdreg|PCI_COMMAND_MEMORY);
}
/*
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 586f718b8e95..349046434513 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -4,11 +4,8 @@
*/
#include <linux/platform_device.h>
#include <linux/mc146818rtc.h>
-#include <linux/acpi.h>
-#include <linux/bcd.h>
#include <linux/export.h>
#include <linux/pnp.h>
-#include <linux/of.h>
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
@@ -20,26 +17,23 @@
/*
* This is a special lock that is owned by the CPU and holds the index
* register we are working with. It is required for NMI access to the
- * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details.
+ * CMOS/RTC registers. See arch/x86/include/asm/mc146818rtc.h for details.
*/
volatile unsigned long cmos_lock;
EXPORT_SYMBOL(cmos_lock);
#endif /* CONFIG_X86_32 */
-/* For two digit years assume time is always after that */
-#define CMOS_YEARS_OFFS 2000
-
DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL(rtc_lock);
/*
- * In order to set the CMOS clock precisely, set_rtc_mmss has to be
+ * In order to set the CMOS clock precisely, mach_set_cmos_time has to be
* called 500 ms after the second nowtime has started, because when
* nowtime is written into the registers of the CMOS clock, it will
* jump to the next second precisely 500 ms later. Check the Motorola
* MC146818A or Dallas DS12887 data sheet for details.
*/
-int mach_set_rtc_mmss(const struct timespec64 *now)
+int mach_set_cmos_time(const struct timespec64 *now)
{
unsigned long long nowtime = now->tv_sec;
struct rtc_time tm;
@@ -62,8 +56,7 @@ int mach_set_rtc_mmss(const struct timespec64 *now)
void mach_get_cmos_time(struct timespec64 *now)
{
- unsigned int status, year, mon, day, hour, min, sec, century = 0;
- unsigned long flags;
+ struct rtc_time tm;
/*
* If pm_trace abused the RTC as storage, set the timespec to 0,
@@ -74,51 +67,13 @@ void mach_get_cmos_time(struct timespec64 *now)
return;
}
- spin_lock_irqsave(&rtc_lock, flags);
-
- /*
- * If UIP is clear, then we have >= 244 microseconds before
- * RTC registers will be updated. Spec sheet says that this
- * is the reliable way to read RTC - registers. If UIP is set
- * then the register access might be invalid.
- */
- while ((CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP))
- cpu_relax();
-
- sec = CMOS_READ(RTC_SECONDS);
- min = CMOS_READ(RTC_MINUTES);
- hour = CMOS_READ(RTC_HOURS);
- day = CMOS_READ(RTC_DAY_OF_MONTH);
- mon = CMOS_READ(RTC_MONTH);
- year = CMOS_READ(RTC_YEAR);
-
-#ifdef CONFIG_ACPI
- if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID &&
- acpi_gbl_FADT.century)
- century = CMOS_READ(acpi_gbl_FADT.century);
-#endif
-
- status = CMOS_READ(RTC_CONTROL);
- WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
-
- spin_unlock_irqrestore(&rtc_lock, flags);
-
- if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
- sec = bcd2bin(sec);
- min = bcd2bin(min);
- hour = bcd2bin(hour);
- day = bcd2bin(day);
- mon = bcd2bin(mon);
- year = bcd2bin(year);
+ if (mc146818_get_time(&tm)) {
+ pr_err("Unable to read current time from RTC\n");
+ now->tv_sec = now->tv_nsec = 0;
+ return;
}
- if (century) {
- century = bcd2bin(century);
- year += century * 100;
- } else
- year += CMOS_YEARS_OFFS;
-
- now->tv_sec = mktime64(year, mon, day, hour, min, sec);
+ now->tv_sec = rtc_tm_to_time64(&tm);
now->tv_nsec = 0;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index d62b2cb85cea..178015a820f0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -63,6 +63,7 @@
#include <asm/insn-eval.h>
#include <asm/vdso.h>
#include <asm/tdx.h>
+#include <asm/cfi.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -313,7 +314,8 @@ static noinstr bool handle_bug(struct pt_regs *regs)
*/
if (regs->flags & X86_EFLAGS_IF)
raw_local_irq_enable();
- if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+ if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
+ handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
regs->ip += LEN_UD2;
handled = true;
}
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e84ee5cdbd8c..57353519bc11 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -138,7 +138,7 @@ struct x86_platform_ops x86_platform __ro_after_init = {
.calibrate_cpu = native_calibrate_cpu_early,
.calibrate_tsc = native_calibrate_tsc,
.get_wallclock = mach_get_cmos_time,
- .set_wallclock = mach_set_rtc_mmss,
+ .set_wallclock = mach_set_cmos_time,
.iommu_shutdown = iommu_shutdown_noop,
.is_untracked_pat_range = is_ISA_range,
.nmi_init = default_nmi_init,