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

Pull perf fixes from Ingo Molnar:
 "A bit larger than what I'd wish for - half of it is due to hw driver
  updates to Intel Ivy-Bridge which info got recently released,
  cycles:pp should work there now too, amongst other things.  (but we
  are generally making exceptions for hardware enablement of this type.)

  There are also callchain fixes in it - responding to mostly
  theoretical (but valid) concerns.  The tooling side sports perf.data
  endianness/portability fixes which did not make it for the merge
  window - and various other fixes as well."

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  perf/x86: Check user address explicitly in copy_from_user_nmi()
  perf/x86: Check if user fp is valid
  perf: Limit callchains to 127
  perf/x86: Allow multiple stacks
  perf/x86: Update SNB PEBS constraints
  perf/x86: Enable/Add IvyBridge hardware support
  perf/x86: Implement cycles:p for SNB/IVB
  perf/x86: Fix Intel shared extra MSR allocation
  x86/decoder: Fix bsr/bsf/jmpe decoding with operand-size prefix
  perf: Remove duplicate invocation on perf_event_for_each
  perf uprobes: Remove unnecessary check before strlist__delete
  perf symbols: Check for valid dso before creating map
  perf evsel: Fix 32 bit values endianity swap for sample_id_all header
  perf session: Handle endianity swap on sample_id_all header data
  perf symbols: Handle different endians properly during symbol load
  perf evlist: Pass third argument to ioctl explicitly
  perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP
  perf tools: Make --version show kernel version instead of pull req tag
  perf tools: Check if callchain is corrupted
  perf callchain: Make callchain cursors TLS
  ...

8 files changed, 143 insertions, 62 deletions

diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 04cd6882308..e1f3a17034f 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,9 +33,8 @@
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
 #define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) 	\
+	((unsigned long __force)(addr) < user_addr_max())
 
 /*
  * Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
  * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
 
-#define __range_not_ok(addr, size)					\
+#define __range_not_ok(addr, size, limit)				\
 ({									\
 	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
 	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
 	    : "=&r" (flag), "=r" (roksum)				\
 	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
+	      "rm" (limit));						\
 	flag;								\
 })
 
@@ -77,7 +76,8 @@
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
 
 /*
  * The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6da018..c4706cf9c01 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
 		if (!cpuc->shared_regs)
 			goto error;
 	}
+	cpuc->is_fake = 1;
 	return cpuc;
 error:
 	free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
 }
 
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+	return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		if (bytes != sizeof(frame))
 			break;
 
-		if (fp < compat_ptr(regs->sp))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 		if (bytes != sizeof(frame))
 			break;
 
-		if ((unsigned long)fp < regs->sp)
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf5449..7241e2fc3c1 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -117,6 +117,7 @@ struct cpu_hw_events {
 	struct perf_event	*event_list[X86_PMC_IDX_MAX]; /* in enabled order */
 
 	unsigned int		group_flag;
+	int			is_fake;
 
 	/*
 	 * Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
 	int		pebs_record_size;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
+	void		(*pebs_aliases)(struct perf_event *event);
 
 	/*
 	 * Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546ec6ae..187c294bc65 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
 {
 	if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
-		return false;
+		return idx;
 
-	if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
-		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= 0x01bb;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
-		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
-	} else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+	if (idx == EXTRA_REG_RSP_0)
+		return EXTRA_REG_RSP_1;
+
+	if (idx == EXTRA_REG_RSP_1)
+		return EXTRA_REG_RSP_0;
+
+	return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+	event->hw.extra_reg.idx = idx;
+
+	if (idx == EXTRA_REG_RSP_0) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
 		event->hw.config |= 0x01b7;
-		event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+	} else if (idx == EXTRA_REG_RSP_1) {
+		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+		event->hw.config |= 0x01bb;
+		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
 	}
-
-	if (event->hw.extra_reg.idx == orig_idx)
-		return false;
-
-	return true;
 }
 
 /*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
 	struct event_constraint *c = &emptyconstraint;
 	struct er_account *era;
 	unsigned long flags;
-	int orig_idx = reg->idx;
+	int idx = reg->idx;
 
-	/* already allocated shared msr */
-	if (reg->alloc)
+	/*
+	 * reg->alloc can be set due to existing state, so for fake cpuc we
+	 * need to ignore this, otherwise we might fail to allocate proper fake
+	 * state for this extra reg constraint. Also see the comment below.
+	 */
+	if (reg->alloc && !cpuc->is_fake)
 		return NULL; /* call x86_get_event_constraint() */
 
 again:
-	era = &cpuc->shared_regs->regs[reg->idx];
+	era = &cpuc->shared_regs->regs[idx];
 	/*
 	 * we use spin_lock_irqsave() to avoid lockdep issues when
 	 * passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
 
 	if (!atomic_read(&era->ref) || era->config == reg->config) {
 
+		/*
+		 * If its a fake cpuc -- as per validate_{group,event}() we
+		 * shouldn't touch event state and we can avoid doing so
+		 * since both will only call get_event_constraints() once
+		 * on each event, this avoids the need for reg->alloc.
+		 *
+		 * Not doing the ER fixup will only result in era->reg being
+		 * wrong, but since we won't actually try and program hardware
+		 * this isn't a problem either.
+		 */
+		if (!cpuc->is_fake) {
+			if (idx != reg->idx)
+				intel_fixup_er(event, idx);
+
+			/*
+			 * x86_schedule_events() can call get_event_constraints()
+			 * multiple times on events in the case of incremental
+			 * scheduling(). reg->alloc ensures we only do the ER
+			 * allocation once.
+			 */
+			reg->alloc = 1;
+		}
+
 		/* lock in msr value */
 		era->config = reg->config;
 		era->reg = reg->reg;
@@ -1180,17 +1213,17 @@ again:
 		/* one more user */
 		atomic_inc(&era->ref);
 
-		/* no need to reallocate during incremental event scheduling */
-		reg->alloc = 1;
-
 		/*
 		 * need to call x86_get_event_constraint()
 		 * to check if associated event has constraints
 		 */
 		c = NULL;
-	} else if (intel_try_alt_er(event, orig_idx)) {
-		raw_spin_unlock_irqrestore(&era->lock, flags);
-		goto again;
+	} else {
+		idx = intel_alt_er(idx);
+		if (idx != reg->idx) {
+			raw_spin_unlock_irqrestore(&era->lock, flags);
+			goto again;
+		}
 	}
 	raw_spin_unlock_irqrestore(&era->lock, flags);
 
@@ -1204,11 +1237,14 @@ __intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
 	struct er_account *era;
 
 	/*
-	 * only put constraint if extra reg was actually
-	 * allocated. Also takes care of event which do
-	 * not use an extra shared reg
+	 * Only put constraint if extra reg was actually allocated. Also takes
+	 * care of event which do not use an extra shared reg.
+	 *
+	 * Also, if this is a fake cpuc we shouldn't touch any event state
+	 * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+	 * either since it'll be thrown out.
 	 */
-	if (!reg->alloc)
+	if (!reg->alloc || cpuc->is_fake)
 		return;
 
 	era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
 {
-	int ret = x86_pmu_hw_config(event);
-
-	if (ret)
-		return ret;
-
-	if (event->attr.precise_ip &&
-	    (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
 		/*
 		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
 		 * (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		 */
 		u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
 
+		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+		event->hw.config = alt_config;
+	}
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+		/*
+		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+		 * (0x003c) so that we can use it with PEBS.
+		 *
+		 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+		 * PEBS capable. However we can use UOPS_RETIRED.ALL
+		 * (0x01c2), which is a PEBS capable event, to get the same
+		 * count.
+		 *
+		 * UOPS_RETIRED.ALL counts the number of cycles that retires
+		 * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+		 * larger than the maximum number of micro-ops that can be
+		 * retired per cycle (4) and then inverting the condition, we
+		 * count all cycles that retire 16 or less micro-ops, which
+		 * is every cycle.
+		 *
+		 * Thereby we gain a PEBS capable cycle counter.
+		 */
+		u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
 
 		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
 		event->hw.config = alt_config;
 	}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+	int ret = x86_pmu_hw_config(event);
+
+	if (ret)
+		return ret;
+
+	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+		x86_pmu.pebs_aliases(event);
 
 	if (intel_pmu_needs_lbr_smpl(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.max_period		= (1ULL << 31) - 1,
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
+	.pebs_aliases		= intel_pebs_aliases_core2,
 
 	.format_attrs		= intel_arch3_formats_attr,
 
@@ -1840,8 +1909,9 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
-		x86_add_quirk(intel_sandybridge_quirk);
 	case 45: /* SandyBridge, "Romely-EP" */
+		x86_add_quirk(intel_sandybridge_quirk);
+	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -1849,6 +1919,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
 		x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5a3edc27f6e..35e2192df9f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index f61ee67ec00..677b1ed184c 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 
 #include <asm/word-at-a-time.h>
+#include <linux/sched.h>
 
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	void *map;
 	int ret;
 
+	if (__range_not_ok(from, n, TASK_SIZE) == 0)
+		return len;
+
 	do {
 		ret = __get_user_pages_fast(addr, 1, 0, &page);
 		if (!ret)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 81913790442..5d7e51f3fd2 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -28,7 +28,7 @@
 #  - (66): the last prefix is 0x66
 #  - (F3): the last prefix is 0xF3
 #  - (F2): the last prefix is 0xF2
-#
+#  - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
 
 Table: one byte opcode
 Referrer:
@@ -515,12 +515,12 @@ b4: LFS Gv,Mp
 b5: LGS Gv,Mp
 b6: MOVZX Gv,Eb
 b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
 b9: Grp10 (1A)
 ba: Grp8 Ev,Ib (1A)
 bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
 be: MOVSX Gv,Eb
 bf: MOVSX Gv,Ew
 # 0x0f 0xc0-0xcf
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5f6a5b6c3a1..ddcf39b1a18 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -66,9 +66,10 @@ BEGIN {
 	rex_expr = "^REX(\\.[XRWB]+)*"
 	fpu_expr = "^ESC" # TODO
 
-	lprefix1_expr = "\\(66\\)"
+	lprefix1_expr = "\\((66|!F3)\\)"
 	lprefix2_expr = "\\(F3\\)"
-	lprefix3_expr = "\\(F2\\)"
+	lprefix3_expr = "\\((F2|!F3)\\)"
+	lprefix_expr = "\\((66|F2|F3)\\)"
 	max_lprefix = 4
 
 	# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@ function convert_operands(count,opnd,       i,j,imm,mod)
 		if (match(ext, lprefix1_expr)) {
 			lptable1[idx] = add_flags(lptable1[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix2_expr)) {
+		}
+		if (match(ext, lprefix2_expr)) {
 			lptable2[idx] = add_flags(lptable2[idx],flags)
 			variant = "INAT_VARIANT"
-		} else if (match(ext, lprefix3_expr)) {
+		}
+		if (match(ext, lprefix3_expr)) {
 			lptable3[idx] = add_flags(lptable3[idx],flags)
 			variant = "INAT_VARIANT"
-		} else {
+		}
+		if (!match(ext, lprefix_expr)){
 			table[idx] = add_flags(table[idx],flags)
 		}
 	}