perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch

In the LBR call stack mode, LBR information is used to reconstruct a
call stack. To get the complete call stack, perf has to save/restore
all LBR registers during a context switch. Due to a large number of the
LBR registers, this process causes a high CPU overhead. To reduce the
CPU overhead during a context switch, use the XSAVES/XRSTORS
instructions.

Every XSAVE area must follow a canonical format: the legacy region, an
XSAVE header and the extended region. Although the LBR information is
only kept in the extended region, a space for the legacy region and
XSAVE header is still required. Add a new dedicated structure for LBR
XSAVES support.

Before enabling XSAVES support, the size of the LBR state has to be
sanity checked, because:
- the size of the software structure is calculated from the max number
of the LBR depth, which is enumerated by the CPUID leaf for Arch LBR.
The size of the LBR state is enumerated by the CPUID leaf for XSAVE
support of Arch LBR. If the values from the two CPUID leaves are not
consistent, it may trigger a buffer overflow. For example, a hypervisor
may unconsciously set inconsistent values for the two emulated CPUID.
- unlike other state components, the size of an LBR state depends on the
max number of LBRs, which may vary from generation to generation.

Expose the function xfeature_size() for the sanity check.
The LBR XSAVES support will be disabled if the size of the LBR state
enumerated by CPUID doesn't match with the size of the software
structure.

The XSAVE instruction requires 64-byte alignment for state buffers. A
new macro is added to reflect the alignment requirement. A 64-byte
aligned kmem_cache is created for architecture LBR.

Currently, the structure for each state component is maintained in
fpu/types.h. The structure for the new LBR state component should be
maintained in the same place. Move structure lbr_entry to fpu/types.h as
well for broader sharing.

Add dedicated lbr_save/lbr_restore functions for LBR XSAVES support,
which invokes the corresponding xstate helpers to XSAVES/XRSTORS LBR
information at the context switch when the call stack mode is enabled.
Since the XSAVES/XRSTORS instructions will be eventually invoked, the
dedicated functions is named with '_xsaves'/'_xrstors' postfix.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dave Hansen <dave.hansen@intel.com>
Link: https://lkml.kernel.org/r/1593780569-62993-23-git-send-email-kan.liang@linux.intel.com

1 files changed, 74 insertions, 5 deletions

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 3ad528996d1c..cb1a0495339b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -483,6 +483,17 @@ static void intel_pmu_arch_lbr_restore(void *ctx)
 	}
 }
 
+/*
+ * Restore the Architecture LBR state from the xsave area in the perf
+ * context data for the task via the XRSTORS instruction.
+ */
+static void intel_pmu_arch_lbr_xrstors(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
+
+	copy_kernel_to_dynamic_supervisor(&task_ctx->xsave, XFEATURE_MASK_LBR);
+}
+
 static __always_inline bool lbr_is_reset_in_cstate(void *ctx)
 {
 	if (static_cpu_has(X86_FEATURE_ARCH_LBR))
@@ -557,6 +568,17 @@ static void intel_pmu_arch_lbr_save(void *ctx)
 		entries[x86_pmu.lbr_nr - 1].from = 0;
 }
 
+/*
+ * Save the Architecture LBR state to the xsave area in the perf
+ * context data for the task via the XSAVES instruction.
+ */
+static void intel_pmu_arch_lbr_xsaves(void *ctx)
+{
+	struct x86_perf_task_context_arch_lbr_xsave *task_ctx = ctx;
+
+	copy_dynamic_supervisor_to_kernel(&task_ctx->xsave, XFEATURE_MASK_LBR);
+}
+
 static void __intel_pmu_lbr_save(void *ctx)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1639,12 +1661,40 @@ void intel_pmu_lbr_init_knl(void)
 		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
 
+/*
+ * LBR state size is variable based on the max number of registers.
+ * This calculates the expected state size, which should match
+ * what the hardware enumerates for the size of XFEATURE_LBR.
+ */
+static inline unsigned int get_lbr_state_size(void)
+{
+	return sizeof(struct arch_lbr_state) +
+	       x86_pmu.lbr_nr * sizeof(struct lbr_entry);
+}
+
+static bool is_arch_lbr_xsave_available(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_XSAVES))
+		return false;
+
+	/*
+	 * Check the LBR state with the corresponding software structure.
+	 * Disable LBR XSAVES support if the size doesn't match.
+	 */
+	if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size()))
+		return false;
+
+	return true;
+}
+
 void __init intel_pmu_arch_lbr_init(void)
 {
+	struct pmu *pmu = x86_get_pmu();
 	union cpuid28_eax eax;
 	union cpuid28_ebx ebx;
 	union cpuid28_ecx ecx;
 	unsigned int unused_edx;
+	bool arch_lbr_xsave;
 	size_t size;
 	u64 lbr_nr;
 
@@ -1670,9 +1720,22 @@ void __init intel_pmu_arch_lbr_init(void)
 	x86_pmu.lbr_br_type = ecx.split.lbr_br_type;
 	x86_pmu.lbr_nr = lbr_nr;
 
-	size = sizeof(struct x86_perf_task_context_arch_lbr) +
-	       lbr_nr * sizeof(struct lbr_entry);
-	x86_get_pmu()->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+
+	arch_lbr_xsave = is_arch_lbr_xsave_available();
+	if (arch_lbr_xsave) {
+		size = sizeof(struct x86_perf_task_context_arch_lbr_xsave) +
+		       get_lbr_state_size();
+		pmu->task_ctx_cache = create_lbr_kmem_cache(size,
+							    XSAVE_ALIGNMENT);
+	}
+
+	if (!pmu->task_ctx_cache) {
+		arch_lbr_xsave = false;
+
+		size = sizeof(struct x86_perf_task_context_arch_lbr) +
+		       lbr_nr * sizeof(struct lbr_entry);
+		pmu->task_ctx_cache = create_lbr_kmem_cache(size, 0);
+	}
 
 	x86_pmu.lbr_from = MSR_ARCH_LBR_FROM_0;
 	x86_pmu.lbr_to = MSR_ARCH_LBR_TO_0;
@@ -1705,8 +1768,14 @@ void __init intel_pmu_arch_lbr_init(void)
 
 	x86_pmu.lbr_reset = intel_pmu_arch_lbr_reset;
 	x86_pmu.lbr_read = intel_pmu_arch_lbr_read;
-	x86_pmu.lbr_save = intel_pmu_arch_lbr_save;
-	x86_pmu.lbr_restore = intel_pmu_arch_lbr_restore;
+	if (arch_lbr_xsave) {
+		x86_pmu.lbr_save = intel_pmu_arch_lbr_xsaves;
+		x86_pmu.lbr_restore = intel_pmu_arch_lbr_xrstors;
+		pr_cont("XSAVE ");
+	} else {
+		x86_pmu.lbr_save = intel_pmu_arch_lbr_save;
+		x86_pmu.lbr_restore = intel_pmu_arch_lbr_restore;
+	}
 
 	pr_cont("Architectural LBR, ");