Merge tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:
 "HW support updates:

   - Add uncore support for Intel Comet Lake

   - Add RAPL support for Hygon Fam18h

   - Add Intel "IIO stack to PMON mapping" support on Skylake-SP CPUs,
     which enumerates per device performance counters via sysfs and
     enables the perf stat --iiostat functionality

   - Add support for Intel "Architectural LBRs", which generalized the
     model specific LBR hardware tracing feature into a
     model-independent, architected performance monitoring feature.

     Usage is mostly seamless to tooling, as the pre-existing LBR
     features are kept, but there's a couple of advantages under the
     hood, such as faster context-switching, faster LBR reads, cleaner
     exposure of LBR features to guest kernels, etc.

     ( Since architectural LBRs are supported via XSAVE, there's related
       changes to the x86 FPU code as well. )

  ftrace/perf updates:

   - Add support to add a text poke event to record changes to kernel
     text (i.e. self-modifying code) in order to support tracers like
     Intel PT decoding through jump labels, kprobes and ftrace
     trampolines.

  Misc cleanups, smaller fixes..."

* tag 'perf-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  perf/x86/rapl: Add Hygon Fam18h RAPL support
  kprobes: Remove unnecessary module_mutex locking from kprobe_optimizer()
  x86/perf: Fix a typo
  perf: <linux/perf_event.h>: drop a duplicated word
  perf/x86/intel/lbr: Support XSAVES for arch LBR read
  perf/x86/intel/lbr: Support XSAVES/XRSTORS for LBR context switch
  x86/fpu/xstate: Add helpers for LBR dynamic supervisor feature
  x86/fpu/xstate: Support dynamic supervisor feature for LBR
  x86/fpu: Use proper mask to replace full instruction mask
  perf/x86: Remove task_ctx_size
  perf/x86/intel/lbr: Create kmem_cache for the LBR context data
  perf/core: Use kmem_cache to allocate the PMU specific data
  perf/core: Factor out functions to allocate/free the task_ctx_data
  perf/x86/intel/lbr: Support Architectural LBR
  perf/x86/intel/lbr: Factor out intel_pmu_store_lbr
  perf/x86/intel/lbr: Factor out rdlbr_all() and wrlbr_all()
  perf/x86/intel/lbr: Mark the {rd,wr}lbr_{to,from} wrappers __always_inline
  perf/x86/intel/lbr: Unify the stored format of LBR information
  perf/x86/intel/lbr: Support LBR_CTL
  perf/x86: Expose CPUID enumeration bits for arch LBR
  ...

arch/x86/kernel/alternative.c

@@ -3,6 +3,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/perf_event.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/stringify.h>
@@ -1001,6 +1002,7 @@ struct text_poke_loc {
 	s32 rel32;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	u8 old;
 };
 
 struct bp_patching_desc {
@@ -1168,8 +1170,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	/*
 	 * First step: add a int3 trap to the address that will be patched.
 	 */
-	for (i = 0; i < nr_entries; i++)
+	for (i = 0; i < nr_entries; i++) {
+		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
 		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+	}
 
 	text_poke_sync();
 
@@ -1177,14 +1181,45 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 * Second step: update all but the first byte of the patched range.
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
+		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
 		int len = text_opcode_size(tp[i].opcode);
 
 		if (len - INT3_INSN_SIZE > 0) {
+			memcpy(old + INT3_INSN_SIZE,
+			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+			       len - INT3_INSN_SIZE);
 			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
 				  (const char *)tp[i].text + INT3_INSN_SIZE,
 				  len - INT3_INSN_SIZE);
 			do_sync++;
 		}
+
+		/*
+		 * Emit a perf event to record the text poke, primarily to
+		 * support Intel PT decoding which must walk the executable code
+		 * to reconstruct the trace. The flow up to here is:
+		 *   - write INT3 byte
+		 *   - IPI-SYNC
+		 *   - write instruction tail
+		 * At this point the actual control flow will be through the
+		 * INT3 and handler and not hit the old or new instruction.
+		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
+		 * can still be decoded. Subsequently:
+		 *   - emit RECORD_TEXT_POKE with the new instruction
+		 *   - IPI-SYNC
+		 *   - write first byte
+		 *   - IPI-SYNC
+		 * So before the text poke event timestamp, the decoder will see
+		 * either the old instruction flow or FUP/TIP of INT3. After the
+		 * text poke event timestamp, the decoder will see either the
+		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
+		 * use the timestamp as the point at which to modify the
+		 * executable code.
+		 * The old instruction is recorded so that the event can be
+		 * processed forwards or backwards.
+		 */
+		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
+				     tp[i].text, len);
 	}
 
 	if (do_sync) {

arch/x86/kernel/fpu/core.c

@@ -82,6 +82,45 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact and we can
+ * keep registers active.
+ *
+ * The legacy FNSAVE instruction cleared all FPU state
+ * unconditionally, so registers are essentially destroyed.
+ * Modern FPU state can be kept in registers, if there are
+ * no pending FP exceptions.
+ */
+int copy_fpregs_to_fpstate(struct fpu *fpu)
+{
+	if (likely(use_xsave())) {
+		copy_xregs_to_kernel(&fpu->state.xsave);
+
+		/*
+		 * AVX512 state is tracked here because its use is
+		 * known to slow the max clock speed of the core.
+		 */
+		if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512)
+			fpu->avx512_timestamp = jiffies;
+		return 1;
+	}
+
+	if (likely(use_fxsr())) {
+		copy_fxregs_to_kernel(fpu);
+		return 1;
+	}
+
+	/*
+	 * Legacy FPU register saving, FNSAVE always clears FPU registers,
+	 * so we have to mark them inactive:
+	 */
+	asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave));
+
+	return 0;
+}
+EXPORT_SYMBOL(copy_fpregs_to_fpstate);
+
 void kernel_fpu_begin(void)
 {
 	preempt_disable();

arch/x86/kernel/fpu/xstate.c

@@ -233,8 +233,10 @@ void fpu__init_cpu_xstate(void)
 	/*
 	 * MSR_IA32_XSS sets supervisor states managed by XSAVES.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 static bool xfeature_enabled(enum xfeature xfeature)
@@ -486,7 +488,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
 	return ebx;
 }
 
-static int xfeature_size(int xfeature_nr)
+int xfeature_size(int xfeature_nr)
 {
 	u32 eax, ebx, ecx, edx;
 
@@ -598,7 +600,8 @@ static void check_xstate_against_struct(int nr)
 	 */
 	if ((nr < XFEATURE_YMM) ||
 	    (nr >= XFEATURE_MAX) ||
-	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR)) {
+	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
+	    ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) {
 		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
 		XSTATE_WARN_ON(1);
 	}
@@ -847,8 +850,10 @@ void fpu__resume_cpu(void)
 	 * Restore IA32_XSS. The same CPUID bit enumerates support
 	 * of XSAVES and MSR_IA32_XSS.
 	 */
-	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+	if (boot_cpu_has(X86_FEATURE_XSAVES)) {
+		wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()  |
+				     xfeatures_mask_dynamic());
+	}
 }
 
 /*
@@ -1356,6 +1361,78 @@ void copy_supervisor_to_kernel(struct xregs_state *xstate)
 	}
 }
 
+/**
+ * copy_dynamic_supervisor_to_kernel() - Save dynamic supervisor states to
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features saved into the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are saved into the xsave
+ * area (See the comment in XFEATURE_MASK_DYNAMIC for the details of dynamic
+ * supervisor feature). Besides the dynamic supervisor states, the legacy
+ * region and XSAVE header are also saved into the xsave area. The supervisor
+ * features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not saved.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_dynamic_supervisor_to_kernel(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying to a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
+/**
+ * copy_kernel_to_dynamic_supervisor() - Restore dynamic supervisor states from
+ *                                       an xsave area
+ * @xstate: A pointer to an xsave area
+ * @mask: Represent the dynamic supervisor features restored from the xsave area
+ *
+ * Only the dynamic supervisor states sets in the mask are restored from the
+ * xsave area (See the comment in XFEATURE_MASK_DYNAMIC for the details of
+ * dynamic supervisor feature). Besides the dynamic supervisor states, the
+ * legacy region and XSAVE header are also restored from the xsave area. The
+ * supervisor features in the XFEATURE_MASK_SUPERVISOR_SUPPORTED and
+ * XFEATURE_MASK_SUPERVISOR_UNSUPPORTED are not restored.
+ *
+ * The xsave area must be 64-bytes aligned.
+ */
+void copy_kernel_to_dynamic_supervisor(struct xregs_state *xstate, u64 mask)
+{
+	u64 dynamic_mask = xfeatures_mask_dynamic() & mask;
+	u32 lmask, hmask;
+	int err;
+
+	if (WARN_ON_FPU(!boot_cpu_has(X86_FEATURE_XSAVES)))
+		return;
+
+	if (WARN_ON_FPU(!dynamic_mask))
+		return;
+
+	lmask = dynamic_mask;
+	hmask = dynamic_mask >> 32;
+
+	XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
+
+	/* Should never fault when copying from a kernel buffer */
+	WARN_ON_FPU(err);
+}
+
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
 /*
  * Report the amount of time elapsed in millisecond since last AVX512

arch/x86/kernel/kprobes/core.c

@@ -33,6 +33,7 @@
 #include <linux/hardirq.h>
 #include <linux/preempt.h>
 #include <linux/sched/debug.h>
+#include <linux/perf_event.h>
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
@@ -472,6 +473,9 @@ static int arch_copy_kprobe(struct kprobe *p)
 	/* Also, displacement change doesn't affect the first byte */
 	p->opcode = buf[0];
 
+	p->ainsn.tp_len = len;
+	perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len);
+
 	/* OK, write back the instruction(s) into ROX insn buffer */
 	text_poke(p->ainsn.insn, buf, len);
 
@@ -503,12 +507,18 @@ int arch_prepare_kprobe(struct kprobe *p)
 
 void arch_arm_kprobe(struct kprobe *p)
 {
-	text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1);
+	u8 int3 = INT3_INSN_OPCODE;
+
+	text_poke(p->addr, &int3, 1);
 	text_poke_sync();
+	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
 }
 
 void arch_disarm_kprobe(struct kprobe *p)
 {
+	u8 int3 = INT3_INSN_OPCODE;
+
+	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
 	text_poke(p->addr, &p->opcode, 1);
 	text_poke_sync();
 }
@@ -516,6 +526,9 @@ void arch_disarm_kprobe(struct kprobe *p)
 void arch_remove_kprobe(struct kprobe *p)
 {
 	if (p->ainsn.insn) {
+		/* Record the perf event before freeing the slot */
+		perf_event_text_poke(p->ainsn.insn, p->ainsn.insn,
+				     p->ainsn.tp_len, NULL, 0);
 		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
 		p->ainsn.insn = NULL;
 	}

arch/x86/kernel/kprobes/opt.c

@@ -6,6 +6,7 @@
  * Copyright (C) Hitachi Ltd., 2012
  */
 #include <linux/kprobes.h>
+#include <linux/perf_event.h>
 #include <linux/ptrace.h>
 #include <linux/string.h>
 #include <linux/slab.h>
@@ -352,8 +353,15 @@ int arch_within_optimized_kprobe(struct optimized_kprobe *op,
 static
 void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty)
 {
-	if (op->optinsn.insn) {
-		free_optinsn_slot(op->optinsn.insn, dirty);
+	u8 *slot = op->optinsn.insn;
+	if (slot) {
+		int len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE;
+
+		/* Record the perf event before freeing the slot */
+		if (dirty)
+			perf_event_text_poke(slot, slot, len, NULL, 0);
+
+		free_optinsn_slot(slot, dirty);
 		op->optinsn.insn = NULL;
 		op->optinsn.size = 0;
 	}
@@ -424,8 +432,15 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
 			   (u8 *)op->kp.addr + op->optinsn.size);
 	len += JMP32_INSN_SIZE;
 
+	/*
+	 * Note	len = TMPL_END_IDX + op->optinsn.size + JMP32_INSN_SIZE is also
+	 * used in __arch_remove_optimized_kprobe().
+	 */
+
 	/* We have to use text_poke() for instruction buffer because it is RO */
+	perf_event_text_poke(slot, NULL, 0, buf, len);
 	text_poke(slot, buf, len);
+
 	ret = 0;
 out:
 	kfree(buf);
@@ -477,10 +492,23 @@ void arch_optimize_kprobes(struct list_head *oplist)
  */
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	arch_arm_kprobe(&op->kp);
-	text_poke(op->kp.addr + INT3_INSN_SIZE,
-		  op->optinsn.copied_insn, DISP32_SIZE);
+	u8 new[JMP32_INSN_SIZE] = { INT3_INSN_OPCODE, };
+	u8 old[JMP32_INSN_SIZE];
+	u8 *addr = op->kp.addr;
+
+	memcpy(old, op->kp.addr, JMP32_INSN_SIZE);
+	memcpy(new + INT3_INSN_SIZE,
+	       op->optinsn.copied_insn,
+	       JMP32_INSN_SIZE - INT3_INSN_SIZE);
+
+	text_poke(addr, new, INT3_INSN_SIZE);
 	text_poke_sync();
+	text_poke(addr + INT3_INSN_SIZE,
+		  new + INT3_INSN_SIZE,
+		  JMP32_INSN_SIZE - INT3_INSN_SIZE);
+	text_poke_sync();
+
+	perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
 }
 
 /*