Merge branch 'perfcounters-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (60 commits)
  perf tools: Avoid unnecessary work in directory lookups
  perf stat: Clean up statistics calculations a bit more
  perf stat: More advanced variance computation
  perf stat: Use stddev_mean in stead of stddev
  perf stat: Remove the limit on repeat
  perf stat: Change noise calculation to use stddev
  x86, perf_counter, bts: Do not allow kernel BTS tracing for now
  x86, perf_counter, bts: Correct pointer-to-u64 casts
  x86, perf_counter, bts: Fail if BTS is not available
  perf_counter: Fix output-sharing error path
  perf trace: Fix read_string()
  perf trace: Print out in nanoseconds
  perf tools: Seek to the end of the header area
  perf trace: Fix parsing of perf.data
  perf trace: Sample timestamps as well
  perf_counter: Introduce new (non-)paranoia level to allow raw tracepoint access
  perf trace: Sample the CPU too
  perf tools: Work around strict aliasing related warnings
  perf tools: Clean up warnings list in the Makefile
  perf tools: Complete support for dynamic strings
  ...

9 files changed, 921 insertions, 22 deletions

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index eb17da7..2a5da06 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -104,8 +104,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	else
 		pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte));
 
-#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) && defined(CONFIG_SMP)
-	/* Second case is 32-bit with 64-bit PTE in SMP mode. In this case, we
+#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT)
+	/* Second case is 32-bit with 64-bit PTE.  In this case, we
 	 * can just store as long as we do the two halves in the right order
 	 * with a barrier in between. This is possible because we take care,
 	 * in the hash code, to pre-invalidate if the PTE was already hashed,
@@ -140,7 +140,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #else
 	/* Anything else just stores the PTE normally. That covers all 64-bit
-	 * cases, and 32-bit non-hash with 64-bit PTEs in UP mode
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
 	 */
 	*ptep = pte;
 #endif
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b73396b..9619285 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -97,7 +97,7 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
-obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_counter.o
+obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_counter.o perf_callchain.o
 obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
 				   power5+-pmu.o power6-pmu.o power7-pmu.o
 obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 561b646..197b156 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -67,6 +67,8 @@ int main(void)
 	DEFINE(MMCONTEXTID, offsetof(struct mm_struct, context.id));
 #ifdef CONFIG_PPC64
 	DEFINE(AUDITCONTEXT, offsetof(struct task_struct, audit_context));
+	DEFINE(SIGSEGV, SIGSEGV);
+	DEFINE(NMI_MASK, NMI_MASK);
 #else
 	DEFINE(THREAD_INFO, offsetof(struct task_struct, stack));
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index eb89811..8ac85e0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -729,6 +729,11 @@ BEGIN_FTR_SECTION
 	bne-	do_ste_alloc		/* If so handle it */
 END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
 
+	clrrdi	r11,r1,THREAD_SHIFT
+	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
+	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
+	bne	77f			/* then don't call hash_page now */
+
 	/*
 	 * On iSeries, we soft-disable interrupts here, then
 	 * hard-enable interrupts so that the hash_page code can spin on
@@ -833,6 +838,20 @@ handle_page_fault:
 	bl	.low_hash_fault
 	b	.ret_from_except
 
+/*
+ * We come here as a result of a DSI at a point where we don't want
+ * to call hash_page, such as when we are accessing memory (possibly
+ * user memory) inside a PMU interrupt that occurred while interrupts
+ * were soft-disabled.  We want to invoke the exception handler for
+ * the access, or panic if there isn't a handler.
+ */
+77:	bl	.save_nvgprs
+	mr	r4,r3
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	li	r5,SIGSEGV
+	bl	.bad_page_fault
+	b	.ret_from_except
+
 	/* here we have a segment miss */
 do_ste_alloc:
 	bl	.ste_allocate		/* try to insert stab entry */
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
new file mode 100644
index 0000000..f74b62c
--- /dev/null
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -0,0 +1,527 @@
+/*
+ * Performance counter callchain support - powerpc architecture code
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_counter.h>
+#include <linux/percpu.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+#include <asm/ptrace.h>
+#include <asm/pgtable.h>
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+#include <asm/vdso.h>
+#ifdef CONFIG_PPC64
+#include "ppc32.h"
+#endif
+
+/*
+ * Store another value in a callchain_entry.
+ */
+static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+	unsigned int nr = entry->nr;
+
+	if (nr < PERF_MAX_STACK_DEPTH) {
+		entry->ip[nr] = ip;
+		entry->nr = nr + 1;
+	}
+}
+
+/*
+ * Is sp valid as the address of the next kernel stack frame after prev_sp?
+ * The next frame may be in a different stack area but should not go
+ * back down in the same stack area.
+ */
+static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
+{
+	if (sp & 0xf)
+		return 0;		/* must be 16-byte aligned */
+	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
+		return 0;
+	if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+		return 1;
+	/*
+	 * sp could decrease when we jump off an interrupt stack
+	 * back to the regular process stack.
+	 */
+	if ((sp & ~(THREAD_SIZE - 1)) != (prev_sp & ~(THREAD_SIZE - 1)))
+		return 1;
+	return 0;
+}
+
+static void perf_callchain_kernel(struct pt_regs *regs,
+				  struct perf_callchain_entry *entry)
+{
+	unsigned long sp, next_sp;
+	unsigned long next_ip;
+	unsigned long lr;
+	long level = 0;
+	unsigned long *fp;
+
+	lr = regs->link;
+	sp = regs->gpr[1];
+	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	callchain_store(entry, regs->nip);
+
+	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
+		return;
+
+	for (;;) {
+		fp = (unsigned long *) sp;
+		next_sp = fp[0];
+
+		if (next_sp == sp + STACK_INT_FRAME_SIZE &&
+		    fp[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
+			/*
+			 * This looks like an interrupt frame for an
+			 * interrupt that occurred in the kernel
+			 */
+			regs = (struct pt_regs *)(sp + STACK_FRAME_OVERHEAD);
+			next_ip = regs->nip;
+			lr = regs->link;
+			level = 0;
+			callchain_store(entry, PERF_CONTEXT_KERNEL);
+
+		} else {
+			if (level == 0)
+				next_ip = lr;
+			else
+				next_ip = fp[STACK_FRAME_LR_SAVE];
+
+			/*
+			 * We can't tell which of the first two addresses
+			 * we get are valid, but we can filter out the
+			 * obviously bogus ones here.  We replace them
+			 * with 0 rather than removing them entirely so
+			 * that userspace can tell which is which.
+			 */
+			if ((level == 1 && next_ip == lr) ||
+			    (level <= 1 && !kernel_text_address(next_ip)))
+				next_ip = 0;
+
+			++level;
+		}
+
+		callchain_store(entry, next_ip);
+		if (!valid_next_sp(next_sp, sp))
+			return;
+		sp = next_sp;
+	}
+}
+
+#ifdef CONFIG_PPC64
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define is_huge_psize(pagesize)	(HPAGE_SHIFT && mmu_huge_psizes[pagesize])
+#else
+#define is_huge_psize(pagesize)	0
+#endif
+
+/*
+ * On 64-bit we don't want to invoke hash_page on user addresses from
+ * interrupt context, so if the access faults, we read the page tables
+ * to find which page (if any) is mapped and access it directly.
+ */
+static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
+{
+	pgd_t *pgdir;
+	pte_t *ptep, pte;
+	int pagesize;
+	unsigned long addr = (unsigned long) ptr;
+	unsigned long offset;
+	unsigned long pfn;
+	void *kaddr;
+
+	pgdir = current->mm->pgd;
+	if (!pgdir)
+		return -EFAULT;
+
+	pagesize = get_slice_psize(current->mm, addr);
+
+	/* align address to page boundary */
+	offset = addr & ((1ul << mmu_psize_defs[pagesize].shift) - 1);
+	addr -= offset;
+
+	if (is_huge_psize(pagesize))
+		ptep = huge_pte_offset(current->mm, addr);
+	else
+		ptep = find_linux_pte(pgdir, addr);
+
+	if (ptep == NULL)
+		return -EFAULT;
+	pte = *ptep;
+	if (!pte_present(pte) || !(pte_val(pte) & _PAGE_USER))
+		return -EFAULT;
+	pfn = pte_pfn(pte);
+	if (!page_is_ram(pfn))
+		return -EFAULT;
+
+	/* no highmem to worry about here */
+	kaddr = pfn_to_kaddr(pfn);
+	memcpy(ret, kaddr + offset, nb);
+	return 0;
+}
+
+static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
+{
+	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned long) ||
+	    ((unsigned long)ptr & 7))
+		return -EFAULT;
+
+	if (!__get_user_inatomic(*ret, ptr))
+		return 0;
+
+	return read_user_stack_slow(ptr, ret, 8);
+}
+
+static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
+{
+	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
+	    ((unsigned long)ptr & 3))
+		return -EFAULT;
+
+	if (!__get_user_inatomic(*ret, ptr))
+		return 0;
+
+	return read_user_stack_slow(ptr, ret, 4);
+}
+
+static inline int valid_user_sp(unsigned long sp, int is_64)
+{
+	if (!sp || (sp & 7) || sp > (is_64 ? TASK_SIZE : 0x100000000UL) - 32)
+		return 0;
+	return 1;
+}
+
+/*
+ * 64-bit user processes use the same stack frame for RT and non-RT signals.
+ */
+struct signal_frame_64 {
+	char		dummy[__SIGNAL_FRAMESIZE];
+	struct ucontext	uc;
+	unsigned long	unused[2];
+	unsigned int	tramp[6];
+	struct siginfo	*pinfo;
+	void		*puc;
+	struct siginfo	info;
+	char		abigap[288];
+};
+
+static int is_sigreturn_64_address(unsigned long nip, unsigned long fp)
+{
+	if (nip == fp + offsetof(struct signal_frame_64, tramp))
+		return 1;
+	if (vdso64_rt_sigtramp && current->mm->context.vdso_base &&
+	    nip == current->mm->context.vdso_base + vdso64_rt_sigtramp)
+		return 1;
+	return 0;
+}
+
+/*
+ * Do some sanity checking on the signal frame pointed to by sp.
+ * We check the pinfo and puc pointers in the frame.
+ */
+static int sane_signal_64_frame(unsigned long sp)
+{
+	struct signal_frame_64 __user *sf;
+	unsigned long pinfo, puc;
+
+	sf = (struct signal_frame_64 __user *) sp;
+	if (read_user_stack_64((unsigned long __user *) &sf->pinfo, &pinfo) ||
+	    read_user_stack_64((unsigned long __user *) &sf->puc, &puc))
+		return 0;
+	return pinfo == (unsigned long) &sf->info &&
+		puc == (unsigned long) &sf->uc;
+}
+
+static void perf_callchain_user_64(struct pt_regs *regs,
+				   struct perf_callchain_entry *entry)
+{
+	unsigned long sp, next_sp;
+	unsigned long next_ip;
+	unsigned long lr;
+	long level = 0;
+	struct signal_frame_64 __user *sigframe;
+	unsigned long __user *fp, *uregs;
+
+	next_ip = regs->nip;
+	lr = regs->link;
+	sp = regs->gpr[1];
+	callchain_store(entry, PERF_CONTEXT_USER);
+	callchain_store(entry, next_ip);
+
+	for (;;) {
+		fp = (unsigned long __user *) sp;
+		if (!valid_user_sp(sp, 1) || read_user_stack_64(fp, &next_sp))
+			return;
+		if (level > 0 && read_user_stack_64(&fp[2], &next_ip))
+			return;
+
+		/*
+		 * Note: the next_sp - sp >= signal frame size check
+		 * is true when next_sp < sp, which can happen when
+		 * transitioning from an alternate signal stack to the
+		 * normal stack.
+		 */
+		if (next_sp - sp >= sizeof(struct signal_frame_64) &&
+		    (is_sigreturn_64_address(next_ip, sp) ||
+		     (level <= 1 && is_sigreturn_64_address(lr, sp))) &&
+		    sane_signal_64_frame(sp)) {
+			/*
+			 * This looks like an signal frame
+			 */
+			sigframe = (struct signal_frame_64 __user *) sp;
+			uregs = sigframe->uc.uc_mcontext.gp_regs;
+			if (read_user_stack_64(&uregs[PT_NIP], &next_ip) ||
+			    read_user_stack_64(&uregs[PT_LNK], &lr) ||
+			    read_user_stack_64(&uregs[PT_R1], &sp))
+				return;
+			level = 0;
+			callchain_store(entry, PERF_CONTEXT_USER);
+			callchain_store(entry, next_ip);
+			continue;
+		}
+
+		if (level == 0)
+			next_ip = lr;
+		callchain_store(entry, next_ip);
+		++level;
+		sp = next_sp;
+	}
+}
+
+static inline int current_is_64bit(void)
+{
+	/*
+	 * We can't use test_thread_flag() here because we may be on an
+	 * interrupt stack, and the thread flags don't get copied over
+	 * from the thread_info on the main stack to the interrupt stack.
+	 */
+	return !test_ti_thread_flag(task_thread_info(current), TIF_32BIT);
+}
+
+#else  /* CONFIG_PPC64 */
+/*
+ * On 32-bit we just access the address and let hash_page create a
+ * HPTE if necessary, so there is no need to fall back to reading
+ * the page tables.  Since this is called at interrupt level,
+ * do_page_fault() won't treat a DSI as a page fault.
+ */
+static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
+{
+	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
+	    ((unsigned long)ptr & 3))
+		return -EFAULT;
+
+	return __get_user_inatomic(*ret, ptr);
+}
+
+static inline void perf_callchain_user_64(struct pt_regs *regs,
+					  struct perf_callchain_entry *entry)
+{
+}
+
+static inline int current_is_64bit(void)
+{
+	return 0;
+}
+
+static inline int valid_user_sp(unsigned long sp, int is_64)
+{
+	if (!sp || (sp & 7) || sp > TASK_SIZE - 32)
+		return 0;
+	return 1;
+}
+
+#define __SIGNAL_FRAMESIZE32	__SIGNAL_FRAMESIZE
+#define sigcontext32		sigcontext
+#define mcontext32		mcontext
+#define ucontext32		ucontext
+#define compat_siginfo_t	struct siginfo
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * Layout for non-RT signal frames
+ */
+struct signal_frame_32 {
+	char			dummy[__SIGNAL_FRAMESIZE32];
+	struct sigcontext32	sctx;
+	struct mcontext32	mctx;
+	int			abigap[56];
+};
+
+/*
+ * Layout for RT signal frames
+ */
+struct rt_signal_frame_32 {
+	char			dummy[__SIGNAL_FRAMESIZE32 + 16];
+	compat_siginfo_t	info;
+	struct ucontext32	uc;
+	int			abigap[56];
+};
+
+static int is_sigreturn_32_address(unsigned int nip, unsigned int fp)
+{
+	if (nip == fp + offsetof(struct signal_frame_32, mctx.mc_pad))
+		return 1;
+	if (vdso32_sigtramp && current->mm->context.vdso_base &&
+	    nip == current->mm->context.vdso_base + vdso32_sigtramp)
+		return 1;
+	return 0;
+}
+
+static int is_rt_sigreturn_32_address(unsigned int nip, unsigned int fp)
+{
+	if (nip == fp + offsetof(struct rt_signal_frame_32,
+				 uc.uc_mcontext.mc_pad))
+		return 1;
+	if (vdso32_rt_sigtramp && current->mm->context.vdso_base &&
+	    nip == current->mm->context.vdso_base + vdso32_rt_sigtramp)
+		return 1;
+	return 0;
+}
+
+static int sane_signal_32_frame(unsigned int sp)
+{
+	struct signal_frame_32 __user *sf;
+	unsigned int regs;
+
+	sf = (struct signal_frame_32 __user *) (unsigned long) sp;
+	if (read_user_stack_32((unsigned int __user *) &sf->sctx.regs, &regs))
+		return 0;
+	return regs == (unsigned long) &sf->mctx;
+}
+
+static int sane_rt_signal_32_frame(unsigned int sp)
+{
+	struct rt_signal_frame_32 __user *sf;
+	unsigned int regs;
+
+	sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
+	if (read_user_stack_32((unsigned int __user *) &sf->uc.uc_regs, &regs))
+		return 0;
+	return regs == (unsigned long) &sf->uc.uc_mcontext;
+}
+
+static unsigned int __user *signal_frame_32_regs(unsigned int sp,
+				unsigned int next_sp, unsigned int next_ip)
+{
+	struct mcontext32 __user *mctx = NULL;
+	struct signal_frame_32 __user *sf;
+	struct rt_signal_frame_32 __user *rt_sf;
+
+	/*
+	 * Note: the next_sp - sp >= signal frame size check
+	 * is true when next_sp < sp, for example, when
+	 * transitioning from an alternate signal stack to the
+	 * normal stack.
+	 */
+	if (next_sp - sp >= sizeof(struct signal_frame_32) &&
+	    is_sigreturn_32_address(next_ip, sp) &&
+	    sane_signal_32_frame(sp)) {
+		sf = (struct signal_frame_32 __user *) (unsigned long) sp;
+		mctx = &sf->mctx;
+	}
+
+	if (!mctx && next_sp - sp >= sizeof(struct rt_signal_frame_32) &&
+	    is_rt_sigreturn_32_address(next_ip, sp) &&
+	    sane_rt_signal_32_frame(sp)) {
+		rt_sf = (struct rt_signal_frame_32 __user *) (unsigned long) sp;
+		mctx = &rt_sf->uc.uc_mcontext;
+	}
+
+	if (!mctx)
+		return NULL;
+	return mctx->mc_gregs;
+}
+
+static void perf_callchain_user_32(struct pt_regs *regs,
+				   struct perf_callchain_entry *entry)
+{
+	unsigned int sp, next_sp;
+	unsigned int next_ip;
+	unsigned int lr;
+	long level = 0;
+	unsigned int __user *fp, *uregs;
+
+	next_ip = regs->nip;
+	lr = regs->link;
+	sp = regs->gpr[1];
+	callchain_store(entry, PERF_CONTEXT_USER);
+	callchain_store(entry, next_ip);
+
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		fp = (unsigned int __user *) (unsigned long) sp;
+		if (!valid_user_sp(sp, 0) || read_user_stack_32(fp, &next_sp))
+			return;
+		if (level > 0 && read_user_stack_32(&fp[1], &next_ip))
+			return;
+
+		uregs = signal_frame_32_regs(sp, next_sp, next_ip);
+		if (!uregs && level <= 1)
+			uregs = signal_frame_32_regs(sp, next_sp, lr);
+		if (uregs) {
+			/*
+			 * This looks like an signal frame, so restart
+			 * the stack trace with the values in it.
+			 */
+			if (read_user_stack_32(&uregs[PT_NIP], &next_ip) ||
+			    read_user_stack_32(&uregs[PT_LNK], &lr) ||
+			    read_user_stack_32(&uregs[PT_R1], &sp))
+				return;
+			level = 0;
+			callchain_store(entry, PERF_CONTEXT_USER);
+			callchain_store(entry, next_ip);
+			continue;
+		}
+
+		if (level == 0)
+			next_ip = lr;
+		callchain_store(entry, next_ip);
+		++level;
+		sp = next_sp;
+	}
+}
+
+/*
+ * Since we can't get PMU interrupts inside a PMU interrupt handler,
+ * we don't need separate irq and nmi entries here.
+ */
+static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+	struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+
+	entry->nr = 0;
+
+	if (current->pid == 0)		/* idle task? */
+		return entry;
+
+	if (!user_mode(regs)) {
+		perf_callchain_kernel(regs, entry);
+		if (current->mm)
+			regs = task_pt_regs(current);
+		else
+			regs = NULL;
+	}
+
+	if (regs) {
+		if (current_is_64bit())
+			perf_callchain_user_64(regs, entry);
+		else
+			perf_callchain_user_32(regs, entry);
+	}
+
+	return entry;
+}
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 5b7038f..a685652 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -92,15 +92,13 @@ static inline void create_shadowed_slbe(unsigned long ea, int ssize,
 		     : "memory" );
 }
 
-void slb_flush_and_rebolt(void)
+static void __slb_flush_and_rebolt(void)
 {
 	/* If you change this make sure you change SLB_NUM_BOLTED
 	 * appropriately too. */
 	unsigned long linear_llp, vmalloc_llp, lflags, vflags;
 	unsigned long ksp_esid_data, ksp_vsid_data;
 
-	WARN_ON(!irqs_disabled());
-
 	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
 	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
 	lflags = SLB_VSID_KERNEL | linear_llp;
@@ -117,12 +115,6 @@ void slb_flush_and_rebolt(void)
 		ksp_vsid_data = get_slb_shadow()->save_area[2].vsid;
 	}
 
-	/*
-	 * We can't take a PMU exception in the following code, so hard
-	 * disable interrupts.
-	 */
-	hard_irq_disable();
-
 	/* We need to do this all in asm, so we're sure we don't touch
 	 * the stack between the slbia and rebolting it. */
 	asm volatile("isync\n"
@@ -139,6 +131,21 @@ void slb_flush_and_rebolt(void)
 		     : "memory");
 }
 
+void slb_flush_and_rebolt(void)
+{
+
+	WARN_ON(!irqs_disabled());
+
+	/*
+	 * We can't take a PMU exception in the following code, so hard
+	 * disable interrupts.
+	 */
+	hard_irq_disable();
+
+	__slb_flush_and_rebolt();
+	get_paca()->slb_cache_ptr = 0;
+}
+
 void slb_vmalloc_update(void)
 {
 	unsigned long vflags;
@@ -180,12 +187,20 @@ static inline int esids_match(unsigned long addr1, unsigned long addr2)
 /* Flush all user entries from the segment table of the current processor. */
 void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 {
-	unsigned long offset = get_paca()->slb_cache_ptr;
+	unsigned long offset;
 	unsigned long slbie_data = 0;
 	unsigned long pc = KSTK_EIP(tsk);
 	unsigned long stack = KSTK_ESP(tsk);
 	unsigned long unmapped_base;
 
+	/*
+	 * We need interrupts hard-disabled here, not just soft-disabled,
+	 * so that a PMU interrupt can't occur, which might try to access
+	 * user memory (to get a stack trace) and possible cause an SLB miss
+	 * which would update the slb_cache/slb_cache_ptr fields in the PACA.
+	 */
+	hard_irq_disable();
+	offset = get_paca()->slb_cache_ptr;
 	if (!cpu_has_feature(CPU_FTR_NO_SLBIE_B) &&
 	    offset <= SLB_CACHE_ENTRIES) {
 		int i;
@@ -200,7 +215,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
 		}
 		asm volatile("isync" : : : "memory");
 	} else {
-		slb_flush_and_rebolt();
+		__slb_flush_and_rebolt();
 	}
 
 	/* Workaround POWER5 < DD2.1 issue */
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 98cd1dc..ab5fb48 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -164,7 +164,7 @@ void switch_stab(struct task_struct *tsk, struct mm_struct *mm)
 {
 	struct stab_entry *stab = (struct stab_entry *) get_paca()->stab_addr;
 	struct stab_entry *ste;
-	unsigned long offset = __get_cpu_var(stab_cache_ptr);
+	unsigned long offset;
 	unsigned long pc = KSTK_EIP(tsk);
 	unsigned long stack = KSTK_ESP(tsk);
 	unsigned long unmapped_base;
@@ -172,6 +172,15 @@ void switch_stab(struct task_struct *tsk, struct mm_struct *mm)
 	/* Force previous translations to complete. DRENG */
 	asm volatile("isync" : : : "memory");
 
+	/*
+	 * We need interrupts hard-disabled here, not just soft-disabled,
+	 * so that a PMU interrupt can't occur, which might try to access
+	 * user memory (to get a stack trace) and possible cause an STAB miss
+	 * which would update the stab_cache/stab_cache_ptr per-cpu variables.
+	 */
+	hard_irq_disable();
+
+	offset = __get_cpu_var(stab_cache_ptr);
 	if (offset <= NR_STAB_CACHE_ENTRIES) {
 		int i;
 
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index fa64e40..e7b7c93 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -84,6 +84,16 @@ union cpuid10_edx {
 #define MSR_ARCH_PERFMON_FIXED_CTR2			0x30b
 #define X86_PMC_IDX_FIXED_BUS_CYCLES			(X86_PMC_IDX_FIXED + 2)
 
+/*
+ * We model BTS tracing as another fixed-mode PMC.
+ *
+ * We choose a value in the middle of the fixed counter range, since lower
+ * values are used by actual fixed counters and higher values are used
+ * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
+ */
+#define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
+
+
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 900332b..f9cd084 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -6,6 +6,7 @@
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
  *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  *  For licencing details see kernel-base/COPYING
  */
@@ -20,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
+#include <linux/cpu.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -27,12 +29,52 @@
 
 static u64 perf_counter_mask __read_mostly;
 
+/* The maximal number of PEBS counters: */
+#define MAX_PEBS_COUNTERS	4
+
+/* The size of a BTS record in bytes: */
+#define BTS_RECORD_SIZE		24
+
+/* The size of a per-cpu BTS buffer in bytes: */
+#define BTS_BUFFER_SIZE		(BTS_RECORD_SIZE * 1024)
+
+/* The BTS overflow threshold in bytes from the end of the buffer: */
+#define BTS_OVFL_TH		(BTS_RECORD_SIZE * 64)
+
+
+/*
+ * Bits in the debugctlmsr controlling branch tracing.
+ */
+#define X86_DEBUGCTL_TR			(1 << 6)
+#define X86_DEBUGCTL_BTS		(1 << 7)
+#define X86_DEBUGCTL_BTINT		(1 << 8)
+#define X86_DEBUGCTL_BTS_OFF_OS		(1 << 9)
+#define X86_DEBUGCTL_BTS_OFF_USR	(1 << 10)
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_counter_reset[MAX_PEBS_COUNTERS];
+};
+
 struct cpu_hw_counters {
 	struct perf_counter	*counters[X86_PMC_IDX_MAX];
 	unsigned long		used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	unsigned long		active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	unsigned long		interrupts;
 	int			enabled;
+	struct debug_store	*ds;
 };
 
 /*
@@ -58,6 +100,8 @@ struct x86_pmu {
 	int		apic;
 	u64		max_period;
 	u64		intel_ctrl;
+	void		(*enable_bts)(u64 config);
+	void		(*disable_bts)(void);
 };
 
 static struct x86_pmu x86_pmu __read_mostly;
@@ -577,6 +621,9 @@ x86_perf_counter_update(struct perf_counter *counter,
 	u64 prev_raw_count, new_raw_count;
 	s64 delta;
 
+	if (idx == X86_PMC_IDX_FIXED_BTS)
+		return 0;
+
 	/*
 	 * Careful: an NMI might modify the previous counter value.
 	 *
@@ -666,10 +713,110 @@ static void release_pmc_hardware(void)
 #endif
 }
 
+static inline bool bts_available(void)
+{
+	return x86_pmu.enable_bts != NULL;
+}
+
+static inline void init_debug_store_on_cpu(int cpu)
+{
+	struct debug_store *ds = per_cpu(cpu_hw_counters, cpu).ds;
+
+	if (!ds)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
+		     (u32)((u64)(unsigned long)ds),
+		     (u32)((u64)(unsigned long)ds >> 32));
+}
+
+static inline void fini_debug_store_on_cpu(int cpu)
+{
+	if (!per_cpu(cpu_hw_counters, cpu).ds)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
+}
+
+static void release_bts_hardware(void)
+{
+	int cpu;
+
+	if (!bts_available())
+		return;
+
+	get_online_cpus();
+
+	for_each_online_cpu(cpu)
+		fini_debug_store_on_cpu(cpu);
+
+	for_each_possible_cpu(cpu) {
+		struct debug_store *ds = per_cpu(cpu_hw_counters, cpu).ds;
+
+		if (!ds)
+			continue;
+
+		per_cpu(cpu_hw_counters, cpu).ds = NULL;
+
+		kfree((void *)(unsigned long)ds->bts_buffer_base);
+		kfree(ds);
+	}
+
+	put_online_cpus();
+}
+
+static int reserve_bts_hardware(void)
+{
+	int cpu, err = 0;
+
+	if (!bts_available())
+		return 0;
+
+	get_online_cpus();
+
+	for_each_possible_cpu(cpu) {
+		struct debug_store *ds;
+		void *buffer;
+
+		err = -ENOMEM;
+		buffer = kzalloc(BTS_BUFFER_SIZE, GFP_KERNEL);
+		if (unlikely(!buffer))
+			break;
+
+		ds = kzalloc(sizeof(*ds), GFP_KERNEL);
+		if (unlikely(!ds)) {
+			kfree(buffer);
+			break;
+		}
+
+		ds->bts_buffer_base = (u64)(unsigned long)buffer;
+		ds->bts_index = ds->bts_buffer_base;
+		ds->bts_absolute_maximum =
+			ds->bts_buffer_base + BTS_BUFFER_SIZE;
+		ds->bts_interrupt_threshold =
+			ds->bts_absolute_maximum - BTS_OVFL_TH;
+
+		per_cpu(cpu_hw_counters, cpu).ds = ds;
+		err = 0;
+	}
+
+	if (err)
+		release_bts_hardware();
+	else {
+		for_each_online_cpu(cpu)
+			init_debug_store_on_cpu(cpu);
+	}
+
+	put_online_cpus();
+
+	return err;
+}
+
 static void hw_perf_counter_destroy(struct perf_counter *counter)
 {
 	if (atomic_dec_and_mutex_lock(&active_counters, &pmc_reserve_mutex)) {
 		release_pmc_hardware();
+		release_bts_hardware();
 		mutex_unlock(&pmc_reserve_mutex);
 	}
 }
@@ -712,6 +859,42 @@ set_ext_hw_attr(struct hw_perf_counter *hwc, struct perf_counter_attr *attr)
 	return 0;
 }
 
+static void intel_pmu_enable_bts(u64 config)
+{
+	unsigned long debugctlmsr;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr |= X86_DEBUGCTL_TR;
+	debugctlmsr |= X86_DEBUGCTL_BTS;
+	debugctlmsr |= X86_DEBUGCTL_BTINT;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_OS))
+		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_OS;
+
+	if (!(config & ARCH_PERFMON_EVENTSEL_USR))
+		debugctlmsr |= X86_DEBUGCTL_BTS_OFF_USR;
+
+	update_debugctlmsr(debugctlmsr);
+}
+
+static void intel_pmu_disable_bts(void)
+{
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+	unsigned long debugctlmsr;
+
+	if (!cpuc->ds)
+		return;
+
+	debugctlmsr = get_debugctlmsr();
+
+	debugctlmsr &=
+		~(X86_DEBUGCTL_TR | X86_DEBUGCTL_BTS | X86_DEBUGCTL_BTINT |
+		  X86_DEBUGCTL_BTS_OFF_OS | X86_DEBUGCTL_BTS_OFF_USR);
+
+	update_debugctlmsr(debugctlmsr);
+}
+
 /*
  * Setup the hardware configuration for a given attr_type
  */
@@ -728,9 +911,13 @@ static int __hw_perf_counter_init(struct perf_counter *counter)
 	err = 0;
 	if (!atomic_inc_not_zero(&active_counters)) {
 		mutex_lock(&pmc_reserve_mutex);
-		if (atomic_read(&active_counters) == 0 && !reserve_pmc_hardware())
-			err = -EBUSY;
-		else
+		if (atomic_read(&active_counters) == 0) {
+			if (!reserve_pmc_hardware())
+				err = -EBUSY;
+			else
+				err = reserve_bts_hardware();
+		}
+		if (!err)
 			atomic_inc(&active_counters);
 		mutex_unlock(&pmc_reserve_mutex);
 	}
@@ -793,6 +980,20 @@ static int __hw_perf_counter_init(struct perf_counter *counter)
 	if (config == -1LL)
 		return -EINVAL;
 
+	/*
+	 * Branch tracing:
+	 */
+	if ((attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+	    (hwc->sample_period == 1)) {
+		/* BTS is not supported by this architecture. */
+		if (!bts_available())
+			return -EOPNOTSUPP;
+
+		/* BTS is currently only allowed for user-mode. */
+		if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+			return -EOPNOTSUPP;
+	}
+
 	hwc->config |= config;
 
 	return 0;
@@ -817,7 +1018,18 @@ static void p6_pmu_disable_all(void)
 
 static void intel_pmu_disable_all(void)
 {
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+	if (!cpuc->enabled)
+		return;
+
+	cpuc->enabled = 0;
+	barrier();
+
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+
+	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+		intel_pmu_disable_bts();
 }
 
 static void amd_pmu_disable_all(void)
@@ -875,7 +1087,25 @@ static void p6_pmu_enable_all(void)
 
 static void intel_pmu_enable_all(void)
 {
+	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+
+	if (cpuc->enabled)
+		return;
+
+	cpuc->enabled = 1;
+	barrier();
+
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+
+	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
+		struct perf_counter *counter =
+			cpuc->counters[X86_PMC_IDX_FIXED_BTS];
+
+		if (WARN_ON_ONCE(!counter))
+			return;
+
+		intel_pmu_enable_bts(counter->hw.config);
+	}
 }
 
 static void amd_pmu_enable_all(void)
@@ -962,6 +1192,11 @@ p6_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
 static inline void
 intel_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
 {
+	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+		intel_pmu_disable_bts();
+		return;
+	}
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc, idx);
 		return;
@@ -990,6 +1225,9 @@ x86_perf_counter_set_period(struct perf_counter *counter,
 	s64 period = hwc->sample_period;
 	int err, ret = 0;
 
+	if (idx == X86_PMC_IDX_FIXED_BTS)
+		return 0;
+
 	/*
 	 * If we are way outside a reasoable range then just skip forward:
 	 */
@@ -1072,6 +1310,14 @@ static void p6_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
 
 static void intel_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
 {
+	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+		if (!__get_cpu_var(cpu_hw_counters).enabled)
+			return;
+
+		intel_pmu_enable_bts(hwc->config);
+		return;
+	}
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_enable_fixed(hwc, idx);
 		return;
@@ -1093,11 +1339,16 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
 {
 	unsigned int event;
 
+	event = hwc->config & ARCH_PERFMON_EVENT_MASK;
+
+	if (unlikely((event ==
+		      x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) &&
+		     (hwc->sample_period == 1)))
+		return X86_PMC_IDX_FIXED_BTS;
+
 	if (!x86_pmu.num_counters_fixed)
 		return -1;
 
-	event = hwc->config & ARCH_PERFMON_EVENT_MASK;
-
 	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
 		return X86_PMC_IDX_FIXED_INSTRUCTIONS;
 	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_CPU_CYCLES)))
@@ -1118,7 +1369,15 @@ static int x86_pmu_enable(struct perf_counter *counter)
 	int idx;
 
 	idx = fixed_mode_idx(counter, hwc);
-	if (idx >= 0) {
+	if (idx == X86_PMC_IDX_FIXED_BTS) {
+		/* BTS is already occupied. */
+		if (test_and_set_bit(idx, cpuc->used_mask))
+			return -EAGAIN;
+
+		hwc->config_base	= 0;
+		hwc->counter_base	= 0;
+		hwc->idx		= idx;
+	} else if (idx >= 0) {
 		/*
 		 * Try to get the fixed counter, if that is already taken
 		 * then try to get a generic counter:
@@ -1229,6 +1488,44 @@ void perf_counter_print_debug(void)
 	local_irq_restore(flags);
 }
 
+static void intel_pmu_drain_bts_buffer(struct cpu_hw_counters *cpuc,
+				       struct perf_sample_data *data)
+{
+	struct debug_store *ds = cpuc->ds;
+	struct bts_record {
+		u64	from;
+		u64	to;
+		u64	flags;
+	};
+	struct perf_counter *counter = cpuc->counters[X86_PMC_IDX_FIXED_BTS];
+	unsigned long orig_ip = data->regs->ip;
+	struct bts_record *at, *top;
+
+	if (!counter)
+		return;
+
+	if (!ds)
+		return;
+
+	at  = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
+	top = (struct bts_record *)(unsigned long)ds->bts_index;
+
+	ds->bts_index = ds->bts_buffer_base;
+
+	for (; at < top; at++) {
+		data->regs->ip	= at->from;
+		data->addr	= at->to;
+
+		perf_counter_output(counter, 1, data);
+	}
+
+	data->regs->ip	= orig_ip;
+	data->addr	= 0;
+
+	/* There's new data available. */
+	counter->pending_kill = POLL_IN;
+}
+
 static void x86_pmu_disable(struct perf_counter *counter)
 {
 	struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
@@ -1253,6 +1550,15 @@ static void x86_pmu_disable(struct perf_counter *counter)
 	 * that we are disabling:
 	 */
 	x86_perf_counter_update(counter, hwc, idx);
+
+	/* Drain the remaining BTS records. */
+	if (unlikely(idx == X86_PMC_IDX_FIXED_BTS)) {
+		struct perf_sample_data data;
+		struct pt_regs regs;
+
+		data.regs = &regs;
+		intel_pmu_drain_bts_buffer(cpuc, &data);
+	}
 	cpuc->counters[idx] = NULL;
 	clear_bit(idx, cpuc->used_mask);
 
@@ -1280,6 +1586,7 @@ static int intel_pmu_save_and_restart(struct perf_counter *counter)
 
 static void intel_pmu_reset(void)
 {
+	struct debug_store *ds = __get_cpu_var(cpu_hw_counters).ds;
 	unsigned long flags;
 	int idx;
 
@@ -1297,6 +1604,8 @@ static void intel_pmu_reset(void)
 	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
 		checking_wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
 	}
+	if (ds)
+		ds->bts_index = ds->bts_buffer_base;
 
 	local_irq_restore(flags);
 }
@@ -1362,6 +1671,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	cpuc = &__get_cpu_var(cpu_hw_counters);
 
 	perf_disable();
+	intel_pmu_drain_bts_buffer(cpuc, &data);
 	status = intel_pmu_get_status();
 	if (!status) {
 		perf_enable();
@@ -1571,6 +1881,8 @@ static struct x86_pmu intel_pmu = {
 	 * the generic counter period:
 	 */
 	.max_period		= (1ULL << 31) - 1,
+	.enable_bts		= intel_pmu_enable_bts,
+	.disable_bts		= intel_pmu_disable_bts,
 };
 
 static struct x86_pmu amd_pmu = {
@@ -1962,3 +2274,8 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 
 	return entry;
 }
+
+void hw_perf_counter_setup_online(int cpu)
+{
+	init_debug_store_on_cpu(cpu);
+}