Commit 814dd948 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull perf fixes from Ingo Molnar:
 "x86 PMU driver fixes plus a core code race fix"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Fix incorrect lbr_sel_mask value
  perf/x86/intel/pt: Don't die on VMXON
  perf/core: Fix perf_event_open() vs. execve() race
  perf/x86/amd: Set the size of event map array to PERF_COUNT_HW_MAX
  perf/core: Make sysctl_perf_cpu_time_max_percent conform to documentation
  perf/x86/intel/rapl: Add missing Haswell model
  perf/x86/intel: Add model number for Skylake Server to perf
parents 2113caed cf3beb7c

arch/x86/events/amd/core.c

+1 −1
Original line number Diff line number Diff line
@@ -115,7 +115,7 @@ static __initconst const u64 amd_hw_cache_event_ids 
/*

 * AMD Performance Monitor K7 and later.

 */

static const u64 amd_perfmon_event_map[] =

static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =

{

  [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,

  [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,

arch/x86/events/intel/core.c

+1 −0
Original line number Diff line number Diff line
@@ -3639,6 +3639,7 @@ __init int intel_pmu_init(void) 


	case 78: /* 14nm Skylake Mobile */

	case 94: /* 14nm Skylake Desktop */

	case 85: /* 14nm Skylake Server */

		x86_pmu.late_ack = true;

		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));

		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));

arch/x86/events/intel/lbr.c

+4 −2
Original line number Diff line number Diff line
@@ -63,7 +63,7 @@ static enum { 


#define LBR_PLM (LBR_KERNEL | LBR_USER)



#define LBR_SEL_MASK	0x1ff	/* valid bits in LBR_SELECT */

#define LBR_SEL_MASK	0x3ff	/* valid bits in LBR_SELECT */

#define LBR_NOT_SUPP	-1	/* LBR filter not supported */

#define LBR_IGN		0	/* ignored */
@@ -610,8 +610,10 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) 
	 * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate

	 * in suppress mode. So LBR_SELECT should be set to

	 * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK)

	 * But the 10th bit LBR_CALL_STACK does not operate

	 * in suppress mode.

	 */

	reg->config = mask ^ x86_pmu.lbr_sel_mask;

	reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK);



	if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) &&

	    (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) &&

arch/x86/events/intel/pt.c

+64 −11
Original line number Diff line number Diff line
@@ -136,9 +136,21 @@ static int __init pt_pmu_hw_init(void) 
	struct dev_ext_attribute *de_attrs;

	struct attribute **attrs;

	size_t size;

	u64 reg;

	int ret;

	long i;



	if (boot_cpu_has(X86_FEATURE_VMX)) {

		/*

		 * Intel SDM, 36.5 "Tracing post-VMXON" says that

		 * "IA32_VMX_MISC[bit 14]" being 1 means PT can trace

		 * post-VMXON.

		 */

		rdmsrl(MSR_IA32_VMX_MISC, reg);

		if (reg & BIT(14))

			pt_pmu.vmx = true;

	}



	attrs = NULL;



	for (i = 0; i < PT_CPUID_LEAVES; i++) {
@@ -269,20 +281,23 @@ static void pt_config(struct perf_event *event) 


	reg |= (event->attr.config & PT_CONFIG_MASK);



	event->hw.config = reg;

	wrmsrl(MSR_IA32_RTIT_CTL, reg);

}



static void pt_config_start(bool start)

static void pt_config_stop(struct perf_event *event)

{

	u64 ctl;

	u64 ctl = READ_ONCE(event->hw.config);



	/* may be already stopped by a PMI */

	if (!(ctl & RTIT_CTL_TRACEEN))

		return;



	rdmsrl(MSR_IA32_RTIT_CTL, ctl);

	if (start)

		ctl |= RTIT_CTL_TRACEEN;

	else

	ctl &= ~RTIT_CTL_TRACEEN;

	wrmsrl(MSR_IA32_RTIT_CTL, ctl);



	WRITE_ONCE(event->hw.config, ctl);



	/*

	 * A wrmsr that disables trace generation serializes other PT

	 * registers and causes all data packets to be written to memory,
@@ -291,7 +306,6 @@ static void pt_config_start(bool start) 
	 * The below WMB, separating data store and aux_head store matches

	 * the consumer's RMB that separates aux_head load and data load.

	 */

	if (!start)

	wmb();

}
@@ -942,11 +956,17 @@ void intel_pt_interrupt(void) 
	if (!ACCESS_ONCE(pt->handle_nmi))

		return;



	pt_config_start(false);

	/*

	 * If VMX is on and PT does not support it, don't touch anything.

	 */

	if (READ_ONCE(pt->vmx_on))

		return;



	if (!event)

		return;



	pt_config_stop(event);



	buf = perf_get_aux(&pt->handle);

	if (!buf)

		return;
@@ -983,6 +1003,35 @@ void intel_pt_interrupt(void) 
	}

}



void intel_pt_handle_vmx(int on)

{

	struct pt *pt = this_cpu_ptr(&pt_ctx);

	struct perf_event *event;

	unsigned long flags;



	/* PT plays nice with VMX, do nothing */

	if (pt_pmu.vmx)

		return;



	/*

	 * VMXON will clear RTIT_CTL.TraceEn; we need to make

	 * sure to not try to set it while VMX is on. Disable

	 * interrupts to avoid racing with pmu callbacks;

	 * concurrent PMI should be handled fine.

	 */

	local_irq_save(flags);

	WRITE_ONCE(pt->vmx_on, on);



	if (on) {

		/* prevent pt_config_stop() from writing RTIT_CTL */

		event = pt->handle.event;

		if (event)

			event->hw.config = 0;

	}

	local_irq_restore(flags);

}

EXPORT_SYMBOL_GPL(intel_pt_handle_vmx);



/*

 * PMU callbacks

 */
@@ -992,6 +1041,9 @@ static void pt_event_start(struct perf_event *event, int mode) 
	struct pt *pt = this_cpu_ptr(&pt_ctx);

	struct pt_buffer *buf = perf_get_aux(&pt->handle);



	if (READ_ONCE(pt->vmx_on))

		return;



	if (!buf || pt_buffer_is_full(buf, pt)) {

		event->hw.state = PERF_HES_STOPPED;

		return;
@@ -1014,7 +1066,8 @@ static void pt_event_stop(struct perf_event *event, int mode) 
	 * see comment in intel_pt_interrupt().

	 */

	ACCESS_ONCE(pt->handle_nmi) = 0;

	pt_config_start(false);



	pt_config_stop(event);



	if (event->hw.state == PERF_HES_STOPPED)

		return;

arch/x86/events/intel/pt.h

+3 −0
Original line number Diff line number Diff line
@@ -65,6 +65,7 @@ enum pt_capabilities { 
struct pt_pmu {

	struct pmu		pmu;

	u32			caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES];

	bool			vmx;

};



/**
@@ -107,10 +108,12 @@ struct pt_buffer { 
 * struct pt - per-cpu pt context

 * @handle:	perf output handle

 * @handle_nmi:	do handle PT PMI on this cpu, there's an active event

 * @vmx_on:	1 if VMX is ON on this cpu

 */

struct pt {

	struct perf_output_handle handle;

	int			handle_nmi;

	int			vmx_on;

};



#endif /* __INTEL_PT_H__ */

CRA Git | Maintained and supported by SUSTech CRA and CCSE