[Patch v7 12/24] perf/x86: Enable XMM register sampling for REGS_USER case

[Dapeng Mi]

This patch adds support for XMM register sampling in the REGS_USER case.

To handle simultaneous sampling of XMM registers for both REGS_INTR and
REGS_USER cases, a per-CPU `x86_user_regs` is introduced to store
REGS_USER-specific XMM registers. This prevents REGS_USER-specific XMM
register data from being overwritten by REGS_INTR-specific data if they
share the same `x86_perf_regs` structure.

To sample user-space XMM registers, the `x86_pmu_update_user_ext_regs()`
helper function is added. It checks if the `TIF_NEED_FPU_LOAD` flag is
set. If so, the user-space XMM register data can be directly retrieved
from the cached task FPU state, as the corresponding hardware registers
have been cleared or switched to kernel-space data. Otherwise, the data
must be read from the hardware registers using the `xsaves` instruction.

For PEBS events, `x86_pmu_update_user_ext_regs()` checks if the
PEBS-sampled XMM register data belongs to user-space. If so, no further
action is needed. Otherwise, the user-space XMM register data needs to be
re-sampled using the same method as for non-PEBS events.

Co-developed-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
---
 arch/x86/events/core.c | 95 ++++++++++++++++++++++++++++++++++++------
 1 file changed, 82 insertions(+), 13 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 22965a8a22b3..a5643c875190 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -696,7 +696,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 			return -EINVAL;
 	}
 
-	if (event->attr.sample_type & PERF_SAMPLE_REGS_INTR) {
+	if (event->attr.sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) {
 		/*
 		 * Besides the general purpose registers, XMM registers may
 		 * be collected as well.
@@ -707,15 +707,6 @@ int x86_pmu_hw_config(struct perf_event *event)
 		}
 	}
 
-	if (event->attr.sample_type & PERF_SAMPLE_REGS_USER) {
-		/*
-		 * Currently XMM registers sampling for REGS_USER is not
-		 * supported yet.
-		 */
-		if (event_has_extended_regs(event))
-			return -EINVAL;
-	}
-
 	return x86_setup_perfctr(event);
 }
 
@@ -1745,6 +1736,28 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	static_call_cond(x86_pmu_del)(event);
 }
 
+/*
+ * When both PERF_SAMPLE_REGS_INTR and PERF_SAMPLE_REGS_USER are set,
+ * an additional x86_perf_regs is required to save user-space registers.
+ * Without this, user-space register data may be overwritten by kernel-space
+ * registers.
+ */
+static DEFINE_PER_CPU(struct x86_perf_regs, x86_user_regs);
+static void x86_pmu_perf_get_regs_user(struct perf_sample_data *data,
+				       struct pt_regs *regs)
+{
+	struct x86_perf_regs *x86_regs_user = this_cpu_ptr(&x86_user_regs);
+	struct perf_regs regs_user;
+
+	perf_get_regs_user(&regs_user, regs);
+	data->regs_user.abi = regs_user.abi;
+	if (regs_user.regs) {
+		x86_regs_user->regs = *regs_user.regs;
+		data->regs_user.regs = &x86_regs_user->regs;
+	} else
+		data->regs_user.regs = NULL;
+}
+
 static void x86_pmu_setup_gpregs_data(struct perf_event *event,
 				      struct perf_sample_data *data,
 				      struct pt_regs *regs)
@@ -1757,7 +1770,14 @@ static void x86_pmu_setup_gpregs_data(struct perf_event *event,
 			data->regs_user.abi = perf_reg_abi(current);
 			data->regs_user.regs = regs;
 		} else if (!(current->flags & PF_KTHREAD)) {
-			perf_get_regs_user(&data->regs_user, regs);
+			/*
+			 * It cannot guarantee that the kernel will never
+			 * touch the registers outside of the pt_regs,
+			 * especially when more and more registers
+			 * (e.g., SIMD, eGPR) are added. The live data
+			 * cannot be used.
+			 */
+			x86_pmu_perf_get_regs_user(data, regs);
 		} else {
 			data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
 			data->regs_user.regs = NULL;
@@ -1800,6 +1820,43 @@ static inline void x86_pmu_update_xregs(struct x86_perf_regs *perf_regs,
 		perf_regs->xmm_space = xsave->i387.xmm_space;
 }
 
+/*
+ * This function retrieves cached user-space fpu registers (XMM/YMM/ZMM).
+ * If TIF_NEED_FPU_LOAD is set, it indicates that the user-space FPU state
+ * is cached. Otherwise, the data should be read directly from the hardware
+ * registers.
+ */
+static inline u64 x86_pmu_update_user_xregs(struct perf_sample_data *data,
+					    u64 mask, u64 ignore_mask)
+{
+	struct x86_perf_regs *perf_regs;
+	struct xregs_state *xsave;
+	struct fpu *fpu;
+	struct fpstate *fps;
+
+	if (data->regs_user.abi == PERF_SAMPLE_REGS_ABI_NONE)
+		return 0;
+
+	if (test_thread_flag(TIF_NEED_FPU_LOAD)) {
+		perf_regs = container_of(data->regs_user.regs,
+				 struct x86_perf_regs, regs);
+		fpu = x86_task_fpu(current);
+		/*
+		 * If __task_fpstate is set, it holds the right pointer,
+		 * otherwise fpstate will.
+		 */
+		fps = READ_ONCE(fpu->__task_fpstate);
+		if (!fps)
+			fps = fpu->fpstate;
+		xsave = &fps->regs.xsave;
+
+		x86_pmu_update_xregs(perf_regs, xsave, mask);
+		return 0;
+	}
+
+	return mask & ~ignore_mask;
+}
+
 static void x86_pmu_sample_xregs(struct perf_event *event,
 				 struct perf_sample_data *data,
 				 u64 ignore_mask)
@@ -1807,6 +1864,7 @@ static void x86_pmu_sample_xregs(struct perf_event *event,
 	struct xregs_state *xsave = per_cpu(ext_regs_buf, smp_processor_id());
 	u64 sample_type = event->attr.sample_type;
 	struct x86_perf_regs *perf_regs;
+	u64 user_mask = 0;
 	u64 intr_mask = 0;
 	u64 mask = 0;
 
@@ -1817,15 +1875,26 @@ static void x86_pmu_sample_xregs(struct perf_event *event,
 		mask |= XFEATURE_MASK_SSE;
 
 	mask &= x86_pmu.ext_regs_mask;
+	if ((sample_type & PERF_SAMPLE_REGS_USER) && data->regs_user.abi)
+		user_mask = x86_pmu_update_user_xregs(data, mask, ignore_mask);
 
 	if ((sample_type & PERF_SAMPLE_REGS_INTR) && data->regs_intr.abi)
 		intr_mask = mask & ~ignore_mask;
 
+	if (user_mask | intr_mask) {
+		xsave->header.xfeatures = 0;
+		xsaves_nmi(xsave, user_mask | intr_mask);
+	}
+
+	if (user_mask) {
+		perf_regs = container_of(data->regs_user.regs,
+					 struct x86_perf_regs, regs);
+		x86_pmu_update_xregs(perf_regs, xsave, user_mask);
+	}
+
 	if (intr_mask) {
 		perf_regs = container_of(data->regs_intr.regs,
 					 struct x86_perf_regs, regs);
-		xsave->header.xfeatures = 0;
-		xsaves_nmi(xsave, mask);
 		x86_pmu_update_xregs(perf_regs, xsave, intr_mask);
 	}
 }
-- 
2.34.1