perf/x86: Support outputting XMM registers

Starting from Icelake, XMM registers can be collected in PEBS record.
But current code only output the pt_regs.

Add a new struct x86_perf_regs for both pt_regs and xmm_regs. The
xmm_regs will be used later to keep a pointer to PEBS record which has
XMM information.

XMM registers are 128 bit. To simplify the code, they are handled like
two different registers, which means setting two bits in the register
bitmap. This also allows only sampling the lower 64bit bits in XMM.

The index of XMM registers starts from 32. There are 16 XMM registers.
So all reserved space for regs are used. Remove REG_RESERVED.

Add PERF_REG_X86_XMM_MAX, which stands for the max number of all x86
regs including both GPRs and XMM.

Add REG_NOSUPPORT for 32bit to exclude unsupported registers.

Previous platforms can not collect XMM information in PEBS record.
Adding pebs_no_xmm_regs to indicate the unsupported platforms.

The common code still validates the supported registers. However, it
cannot check model specific registers, e.g. XMM. Add extra check in
x86_pmu_hw_config() to reject invalid config of regs_user and regs_intr.
The regs_user never supports XMM collection.
The regs_intr only supports XMM collection when sampling PEBS event on
icelake and later platforms.

Originally-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: jolsa@kernel.org
Link: https://lkml.kernel.org/r/20190402194509.2832-3-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 38 insertions, 2 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index fdd106267fd2..de1a924a4914 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event)
 			return -EINVAL;
 	}
 
+	/* sample_regs_user never support XMM registers */
+	if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+		return -EINVAL;
+	/*
+	 * Besides the general purpose registers, XMM registers may
+	 * be collected in PEBS on some platforms, e.g. Icelake
+	 */
+	if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
+		if (x86_pmu.pebs_no_xmm_regs)
+			return -EINVAL;
+
+		if (!event->attr.precise_ip)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 10c99ce1fead..f57e6cb7fd99 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1628,8 +1628,10 @@ void __init intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
-	if (x86_pmu.version <= 4)
+	if (x86_pmu.version <= 4) {
 		x86_pmu.pebs_no_isolation = 1;
+		x86_pmu.pebs_no_xmm_regs = 1;
+	}
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9e474a5f3b86..7abfadb4f202 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -115,6 +115,24 @@ struct amd_nb {
 	 (1ULL << PERF_REG_X86_R14)   | \
 	 (1ULL << PERF_REG_X86_R15))
 
+#define PEBS_XMM_REGS                   \
+	((1ULL << PERF_REG_X86_XMM0)  | \
+	 (1ULL << PERF_REG_X86_XMM1)  | \
+	 (1ULL << PERF_REG_X86_XMM2)  | \
+	 (1ULL << PERF_REG_X86_XMM3)  | \
+	 (1ULL << PERF_REG_X86_XMM4)  | \
+	 (1ULL << PERF_REG_X86_XMM5)  | \
+	 (1ULL << PERF_REG_X86_XMM6)  | \
+	 (1ULL << PERF_REG_X86_XMM7)  | \
+	 (1ULL << PERF_REG_X86_XMM8)  | \
+	 (1ULL << PERF_REG_X86_XMM9)  | \
+	 (1ULL << PERF_REG_X86_XMM10) | \
+	 (1ULL << PERF_REG_X86_XMM11) | \
+	 (1ULL << PERF_REG_X86_XMM12) | \
+	 (1ULL << PERF_REG_X86_XMM13) | \
+	 (1ULL << PERF_REG_X86_XMM14) | \
+	 (1ULL << PERF_REG_X86_XMM15))
+
 /*
  * Per register state.
  */
@@ -612,7 +630,8 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1;
+			pebs_no_isolation	:1,
+			pebs_no_xmm_regs	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	void		(*drain_pebs)(struct pt_regs *regs);