summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/events/amd/core.c21
-rw-r--r--arch/x86/events/amd/ibs.c52
-rw-r--r--arch/x86/events/perf_event.h11
-rw-r--r--arch/x86/include/asm/msr-index.h8
-rw-r--r--arch/x86/include/asm/pmem.h9
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/thread_info.h6
-rw-r--r--arch/x86/include/asm/tlbflush.h6
-rw-r--r--arch/x86/kernel/amd_nb.c6
-rw-r--r--arch/x86/kernel/cpu/amd.c12
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c3
-rw-r--r--arch/x86/kernel/cpu/powerflags.c2
-rw-r--r--arch/x86/kernel/smpboot.c2
-rw-r--r--arch/x86/mm/tlb.c14
-rw-r--r--arch/x86/ras/mce_amd_inj.c3
16 files changed, 108 insertions, 50 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 049ada8d4e9c..86a9bec18dab 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -369,7 +369,7 @@ static int amd_pmu_cpu_prepare(int cpu)
WARN_ON_ONCE(cpuc->amd_nb);
- if (boot_cpu_data.x86_max_cores < 2)
+ if (!x86_pmu.amd_nb_constraints)
return NOTIFY_OK;
cpuc->amd_nb = amd_alloc_nb(cpu);
@@ -388,7 +388,7 @@ static void amd_pmu_cpu_starting(int cpu)
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
- if (boot_cpu_data.x86_max_cores < 2)
+ if (!x86_pmu.amd_nb_constraints)
return;
nb_id = amd_get_nb_id(cpu);
@@ -414,7 +414,7 @@ static void amd_pmu_cpu_dead(int cpu)
{
struct cpu_hw_events *cpuhw;
- if (boot_cpu_data.x86_max_cores < 2)
+ if (!x86_pmu.amd_nb_constraints)
return;
cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -648,6 +648,8 @@ static __initconst const struct x86_pmu amd_pmu = {
.cpu_prepare = amd_pmu_cpu_prepare,
.cpu_starting = amd_pmu_cpu_starting,
.cpu_dead = amd_pmu_cpu_dead,
+
+ .amd_nb_constraints = 1,
};
static int __init amd_core_pmu_init(void)
@@ -674,6 +676,11 @@ static int __init amd_core_pmu_init(void)
x86_pmu.eventsel = MSR_F15H_PERF_CTL;
x86_pmu.perfctr = MSR_F15H_PERF_CTR;
x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE;
+ /*
+ * AMD Core perfctr has separate MSRs for the NB events, see
+ * the amd/uncore.c driver.
+ */
+ x86_pmu.amd_nb_constraints = 0;
pr_cont("core perfctr, ");
return 0;
@@ -693,6 +700,14 @@ __init int amd_pmu_init(void)
if (ret)
return ret;
+ if (num_possible_cpus() == 1) {
+ /*
+ * No point in allocating data structures to serialize
+ * against other CPUs, when there is only the one CPU.
+ */
+ x86_pmu.amd_nb_constraints = 0;
+ }
+
/* Events are common for all AMDs */
memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 3ea25c3917c0..feb90f6730e8 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -28,10 +28,46 @@ static u32 ibs_caps;
#define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
#define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT
+
+/*
+ * IBS states:
+ *
+ * ENABLED; tracks the pmu::add(), pmu::del() state, when set the counter is taken
+ * and any further add()s must fail.
+ *
+ * STARTED/STOPPING/STOPPED; deal with pmu::start(), pmu::stop() state but are
+ * complicated by the fact that the IBS hardware can send late NMIs (ie. after
+ * we've cleared the EN bit).
+ *
+ * In order to consume these late NMIs we have the STOPPED state, any NMI that
+ * happens after we've cleared the EN state will clear this bit and report the
+ * NMI handled (this is fundamentally racy in the face or multiple NMI sources,
+ * someone else can consume our BIT and our NMI will go unhandled).
+ *
+ * And since we cannot set/clear this separate bit together with the EN bit,
+ * there are races; if we cleared STARTED early, an NMI could land in
+ * between clearing STARTED and clearing the EN bit (in fact multiple NMIs
+ * could happen if the period is small enough), and consume our STOPPED bit
+ * and trigger streams of unhandled NMIs.
+ *
+ * If, however, we clear STARTED late, an NMI can hit between clearing the
+ * EN bit and clearing STARTED, still see STARTED set and process the event.
+ * If this event will have the VALID bit clear, we bail properly, but this
+ * is not a given. With VALID set we can end up calling pmu::stop() again
+ * (the throttle logic) and trigger the WARNs in there.
+ *
+ * So what we do is set STOPPING before clearing EN to avoid the pmu::stop()
+ * nesting, and clear STARTED late, so that we have a well defined state over
+ * the clearing of the EN bit.
+ *
+ * XXX: we could probably be using !atomic bitops for all this.
+ */
+
enum ibs_states {
IBS_ENABLED = 0,
IBS_STARTED = 1,
IBS_STOPPING = 2,
+ IBS_STOPPED = 3,
IBS_MAX_STATES,
};
@@ -377,11 +413,10 @@ static void perf_ibs_start(struct perf_event *event, int flags)
perf_ibs_set_period(perf_ibs, hwc, &period);
/*
- * Set STARTED before enabling the hardware, such that
- * a subsequent NMI must observe it. Then clear STOPPING
- * such that we don't consume NMIs by accident.
+ * Set STARTED before enabling the hardware, such that a subsequent NMI
+ * must observe it.
*/
- set_bit(IBS_STARTED, pcpu->state);
+ set_bit(IBS_STARTED, pcpu->state);
clear_bit(IBS_STOPPING, pcpu->state);
perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
@@ -396,6 +431,9 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
u64 config;
int stopping;
+ if (test_and_set_bit(IBS_STOPPING, pcpu->state))
+ return;
+
stopping = test_bit(IBS_STARTED, pcpu->state);
if (!stopping && (hwc->state & PERF_HES_UPTODATE))
@@ -405,12 +443,12 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
if (stopping) {
/*
- * Set STOPPING before disabling the hardware, such that it
+ * Set STOPPED before disabling the hardware, such that it
* must be visible to NMIs the moment we clear the EN bit,
* at which point we can generate an !VALID sample which
* we need to consume.
*/
- set_bit(IBS_STOPPING, pcpu->state);
+ set_bit(IBS_STOPPED, pcpu->state);
perf_ibs_disable_event(perf_ibs, hwc, config);
/*
* Clear STARTED after disabling the hardware; if it were
@@ -556,7 +594,7 @@ fail:
* with samples that even have the valid bit cleared.
* Mark all this NMIs as handled.
*/
- if (test_and_clear_bit(IBS_STOPPING, pcpu->state))
+ if (test_and_clear_bit(IBS_STOPPED, pcpu->state))
return 1;
return 0;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba6ef18528c9..ad4dc7ffffb5 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -608,6 +608,11 @@ struct x86_pmu {
atomic_t lbr_exclusive[x86_lbr_exclusive_max];
/*
+ * AMD bits
+ */
+ unsigned int amd_nb_constraints : 1;
+
+ /*
* Extra registers for events
*/
struct extra_reg *extra_regs;
@@ -795,6 +800,9 @@ ssize_t intel_event_sysfs_show(char *page, u64 config);
struct attribute **merge_attr(struct attribute **a, struct attribute **b);
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page);
+
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
@@ -925,9 +933,6 @@ int p6_pmu_init(void);
int knc_pmu_init(void);
-ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
- char *page);
-
static inline int is_ht_workaround_enabled(void)
{
return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2da46ac16e37..426e946ed0c0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -190,6 +190,7 @@
#define MSR_PP1_ENERGY_STATUS 0x00000641
#define MSR_PP1_POLICY 0x00000642
+/* Config TDP MSRs */
#define MSR_CONFIG_TDP_NOMINAL 0x00000648
#define MSR_CONFIG_TDP_LEVEL_1 0x00000649
#define MSR_CONFIG_TDP_LEVEL_2 0x0000064A
@@ -210,13 +211,6 @@
#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0
#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1
-/* Config TDP MSRs */
-#define MSR_CONFIG_TDP_NOMINAL 0x00000648
-#define MSR_CONFIG_TDP_LEVEL1 0x00000649
-#define MSR_CONFIG_TDP_LEVEL2 0x0000064A
-#define MSR_CONFIG_TDP_CONTROL 0x0000064B
-#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C
-
/* Hardware P state interface */
#define MSR_PPERF 0x0000064e
#define MSR_PERF_LIMIT_REASONS 0x0000064f
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index bf8b35d2035a..fbc5e92e1ecc 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -47,6 +47,15 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
BUG();
}
+static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src,
+ size_t n)
+{
+ if (static_cpu_has(X86_FEATURE_MCE_RECOVERY))
+ return memcpy_mcsafe(dst, (void __force *) src, n);
+ memcpy(dst, (void __force *) src, n);
+ return 0;
+}
+
/**
* arch_wmb_pmem - synchronize writes to persistent memory
*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 983738ac014c..9264476f3d57 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -132,8 +132,6 @@ struct cpuinfo_x86 {
u16 logical_proc_id;
/* Core id: */
u16 cpu_core_id;
- /* Compute unit id */
- u8 compute_unit_id;
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 20a3de5cb3b0..66b057306f40 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -155,6 +155,7 @@ static inline int wbinvd_on_all_cpus(void)
wbinvd();
return 0;
}
+#define smp_num_siblings 1
#endif /* CONFIG_SMP */
extern unsigned disabled_cpus;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 82866697fcf1..ffae84df8a93 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -276,11 +276,9 @@ static inline bool is_ia32_task(void)
*/
#define force_iret() set_thread_flag(TIF_NOTIFY_RESUME)
-#endif /* !__ASSEMBLY__ */
-
-#ifndef __ASSEMBLY__
extern void arch_task_cache_init(void);
extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
extern void arch_release_task_struct(struct task_struct *tsk);
-#endif
+#endif /* !__ASSEMBLY__ */
+
#endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index c24b4224d439..1fde8d580a5b 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -319,12 +319,6 @@ static inline void reset_lazy_tlbstate(void)
#endif /* SMP */
-/* Not inlined due to inc_irq_stat not being defined yet */
-#define flush_tlb_local() { \
- inc_irq_stat(irq_tlb_count); \
- local_flush_tlb(); \
-}
-
#ifndef CONFIG_PARAVIRT
#define flush_tlb_others(mask, mm, start, end) \
native_flush_tlb_others(mask, mm, start, end)
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 29fa475ec518..a147e676fc7b 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -170,15 +170,13 @@ int amd_get_subcaches(int cpu)
{
struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
unsigned int mask;
- int cuid;
if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
return 0;
pci_read_config_dword(link, 0x1d4, &mask);
- cuid = cpu_data(cpu).compute_unit_id;
- return (mask >> (4 * cuid)) & 0xf;
+ return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf;
}
int amd_set_subcaches(int cpu, unsigned long mask)
@@ -204,7 +202,7 @@ int amd_set_subcaches(int cpu, unsigned long mask)
pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
}
- cuid = cpu_data(cpu).compute_unit_id;
+ cuid = cpu_data(cpu).cpu_core_id;
mask <<= 4 * cuid;
mask |= (0xf ^ (1 << cuid)) << 26;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6e47e3a916f1..7b76eb67a9b3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -300,7 +300,6 @@ static int nearby_node(int apicid)
#ifdef CONFIG_SMP
static void amd_get_topology(struct cpuinfo_x86 *c)
{
- u32 cores_per_cu = 1;
u8 node_id;
int cpu = smp_processor_id();
@@ -313,8 +312,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
/* get compute unit information */
smp_num_siblings = ((ebx >> 8) & 3) + 1;
- c->compute_unit_id = ebx & 0xff;
- cores_per_cu += ((ebx >> 8) & 3);
+ c->x86_max_cores /= smp_num_siblings;
+ c->cpu_core_id = ebx & 0xff;
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
@@ -325,19 +324,16 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
/* fixup multi-node processor information */
if (nodes_per_socket > 1) {
- u32 cores_per_node;
u32 cus_per_node;
set_cpu_cap(c, X86_FEATURE_AMD_DCM);
- cores_per_node = c->x86_max_cores / nodes_per_socket;
- cus_per_node = cores_per_node / cores_per_cu;
+ cus_per_node = c->x86_max_cores / nodes_per_socket;
/* store NodeID, use llc_shared_map to store sibling info */
per_cpu(cpu_llc_id, cpu) = node_id;
/* core id has to be in the [0 .. cores_per_node - 1] range */
- c->cpu_core_id %= cores_per_node;
- c->compute_unit_id %= cus_per_node;
+ c->cpu_core_id %= cus_per_node;
}
}
#endif
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 0b445c2ff735..ac780cad3b86 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -384,6 +384,9 @@ static void intel_thermal_interrupt(void)
{
__u64 msr_val;
+ if (static_cpu_has(X86_FEATURE_HWP))
+ wrmsrl_safe(MSR_HWP_STATUS, 0);
+
rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
/* Check for violation of core thermal thresholds*/
diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c
index 31f0f335ed22..1dd8294fd730 100644
--- a/arch/x86/kernel/cpu/powerflags.c
+++ b/arch/x86/kernel/cpu/powerflags.c
@@ -18,4 +18,6 @@ const char *const x86_power_flags[32] = {
"", /* tsc invariant mapped to constant_tsc */
"cpb", /* core performance boost */
"eff_freq_ro", /* Readonly aperf/mperf */
+ "proc_feedback", /* processor feedback interface */
+ "acc_power", /* accumulated power mechanism */
};
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b2c99f811c3f..a2065d3b3b39 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -422,7 +422,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
if (c->phys_proc_id == o->phys_proc_id &&
per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
- c->compute_unit_id == o->compute_unit_id)
+ c->cpu_core_id == o->cpu_core_id)
return topology_sane(c, o, "smt");
} else if (c->phys_proc_id == o->phys_proc_id &&
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 8f4cc3dfac32..fe9b9f776361 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -104,10 +104,8 @@ static void flush_tlb_func(void *info)
inc_irq_stat(irq_tlb_count);
- if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+ if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
return;
- if (!f->flush_end)
- f->flush_end = f->flush_start + PAGE_SIZE;
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
@@ -135,12 +133,20 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
unsigned long end)
{
struct flush_tlb_info info;
+
+ if (end == 0)
+ end = start + PAGE_SIZE;
info.flush_mm = mm;
info.flush_start = start;
info.flush_end = end;
count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
- trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start);
+ if (end == TLB_FLUSH_ALL)
+ trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
+ else
+ trace_tlb_flush(TLB_REMOTE_SEND_IPI,
+ (end - start) >> PAGE_SHIFT);
+
if (is_uv_system()) {
unsigned int cpu;
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 55d38cfa46c2..9e02dcaef683 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -20,6 +20,7 @@
#include <linux/pci.h>
#include <asm/mce.h>
+#include <asm/smp.h>
#include <asm/amd_nb.h>
#include <asm/irq_vectors.h>
@@ -206,7 +207,7 @@ static u32 get_nbc_for_node(int node_id)
struct cpuinfo_x86 *c = &boot_cpu_data;
u32 cores_per_node;
- cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket();
+ cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket();
return cores_per_node * node_id;
}
generated by cgit (git 2.34.1) at 2024-06-10 23:02:23 +0000