Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-18 18:11:56 +00:00
Code Issues Packages Projects Releases Wiki Activity
37fb9a0231
linux/arch/powerpc/kernel/perf_callchain.c

493 lines
12 KiB
C
Raw Normal View History

perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
/*
* 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>
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
#include <linux/perf_event.h>
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
#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
/*
* 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;
}
perf: Generalize some arch callchain code - Most archs use one callchain buffer per cpu, except x86 that needs to deal with NMIs. Provide a default perf_callchain_buffer() implementation that x86 overrides. - Centralize all the kernel/user regs handling and invoke new arch handlers from there: perf_callchain_user() / perf_callchain_kernel() That avoid all the user_mode(), current->mm checks and so... - Invert some parameters in perf_callchain_*() helpers: entry to the left, regs to the right, following the traditional (dst, src). Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-30 21:03:51 +00:00
void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
{
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];
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, regs->nip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
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;
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
} 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;
}
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
if (!valid_next_sp(next_sp, sp))
return;
sp = next_sp;
}
}
#ifdef CONFIG_PPC64
/*
* 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;
powerpc/mm: Allow more flexible layouts for hugepage pagetables Currently each available hugepage size uses a slightly different pagetable layout: that is, the bottem level table of pointers to hugepages is a different size, and may branch off from the normal page tables at a different level. Every hugepage aware path that needs to walk the pagetables must therefore look up the hugepage size from the slice info first, and work out the correct way to walk the pagetables accordingly. Future hardware is likely to add more possible hugepage sizes, more layout options and more mess. This patch, therefore reworks the handling of hugepage pagetables to reduce this complexity. In the new scheme, instead of having to consult the slice mask, pagetable walking code can check a flag in the PGD/PUD/PMD entries to see where to branch off to hugepage pagetables, and the entry also contains the information (eseentially hugepage shift) necessary to then interpret that table without recourse to the slice mask. This scheme can be extended neatly to handle multiple levels of self-describing "special" hugepage pagetables, although for now we assume only one level exists. This approach means that only the pagetable allocation path needs to know how the pagetables should be set out. All other (hugepage) pagetable walking paths can just interpret the structure as they go. There already was a flag bit in PGD/PUD/PMD entries for hugepage directory pointers, but it was only used for debug. We alter that flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable pointer (normally it would be 1 since the pointer lies in the linear mapping). This means that asm pagetable walking can test for (and punt on) hugepage pointers with the same test that checks for unpopulated page directory entries (beq becomes bge), since hugepage pointers will always be positive, and normal pointers always negative. While we're at it, we get rid of the confusing (and grep defeating) #defining of hugepte_shift to be the same thing as mmu_huge_psizes. Signed-off-by: David Gibson <dwg@au1.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-10-26 19:24:31 +00:00
unsigned shift;
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
unsigned long addr = (unsigned long) ptr;
unsigned long offset;
unsigned long pfn;
void *kaddr;
pgdir = current->mm->pgd;
if (!pgdir)
return -EFAULT;
powerpc/mm: Allow more flexible layouts for hugepage pagetables Currently each available hugepage size uses a slightly different pagetable layout: that is, the bottem level table of pointers to hugepages is a different size, and may branch off from the normal page tables at a different level. Every hugepage aware path that needs to walk the pagetables must therefore look up the hugepage size from the slice info first, and work out the correct way to walk the pagetables accordingly. Future hardware is likely to add more possible hugepage sizes, more layout options and more mess. This patch, therefore reworks the handling of hugepage pagetables to reduce this complexity. In the new scheme, instead of having to consult the slice mask, pagetable walking code can check a flag in the PGD/PUD/PMD entries to see where to branch off to hugepage pagetables, and the entry also contains the information (eseentially hugepage shift) necessary to then interpret that table without recourse to the slice mask. This scheme can be extended neatly to handle multiple levels of self-describing "special" hugepage pagetables, although for now we assume only one level exists. This approach means that only the pagetable allocation path needs to know how the pagetables should be set out. All other (hugepage) pagetable walking paths can just interpret the structure as they go. There already was a flag bit in PGD/PUD/PMD entries for hugepage directory pointers, but it was only used for debug. We alter that flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable pointer (normally it would be 1 since the pointer lies in the linear mapping). This means that asm pagetable walking can test for (and punt on) hugepage pointers with the same test that checks for unpopulated page directory entries (beq becomes bge), since hugepage pointers will always be positive, and normal pointers always negative. While we're at it, we get rid of the confusing (and grep defeating) #defining of hugepte_shift to be the same thing as mmu_huge_psizes. Signed-off-by: David Gibson <dwg@au1.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-10-26 19:24:31 +00:00
ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift);
if (!shift)
shift = PAGE_SHIFT;
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
/* align address to page boundary */
powerpc/mm: Allow more flexible layouts for hugepage pagetables Currently each available hugepage size uses a slightly different pagetable layout: that is, the bottem level table of pointers to hugepages is a different size, and may branch off from the normal page tables at a different level. Every hugepage aware path that needs to walk the pagetables must therefore look up the hugepage size from the slice info first, and work out the correct way to walk the pagetables accordingly. Future hardware is likely to add more possible hugepage sizes, more layout options and more mess. This patch, therefore reworks the handling of hugepage pagetables to reduce this complexity. In the new scheme, instead of having to consult the slice mask, pagetable walking code can check a flag in the PGD/PUD/PMD entries to see where to branch off to hugepage pagetables, and the entry also contains the information (eseentially hugepage shift) necessary to then interpret that table without recourse to the slice mask. This scheme can be extended neatly to handle multiple levels of self-describing "special" hugepage pagetables, although for now we assume only one level exists. This approach means that only the pagetable allocation path needs to know how the pagetables should be set out. All other (hugepage) pagetable walking paths can just interpret the structure as they go. There already was a flag bit in PGD/PUD/PMD entries for hugepage directory pointers, but it was only used for debug. We alter that flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable pointer (normally it would be 1 since the pointer lies in the linear mapping). This means that asm pagetable walking can test for (and punt on) hugepage pointers with the same test that checks for unpopulated page directory entries (beq becomes bge), since hugepage pointers will always be positive, and normal pointers always negative. While we're at it, we get rid of the confusing (and grep defeating) #defining of hugepte_shift to be the same thing as mmu_huge_psizes. Signed-off-by: David Gibson <dwg@au1.ibm.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-10-26 19:24:31 +00:00
offset = addr & ((1UL << shift) - 1);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
addr -= offset;
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;
powerpc/perf: Disable pagefaults during callchain stack read Panic observed on an older kernel when collecting call chains for the context-switch software event: [<b0180e00>]rb_erase+0x1b4/0x3e8 [<b00430f4>]__dequeue_entity+0x50/0xe8 [<b0043304>]set_next_entity+0x178/0x1bc [<b0043440>]pick_next_task_fair+0xb0/0x118 [<b02ada80>]schedule+0x500/0x614 [<b02afaa8>]rwsem_down_failed_common+0xf0/0x264 [<b02afca0>]rwsem_down_read_failed+0x34/0x54 [<b02aed4c>]down_read+0x3c/0x54 [<b0023b58>]do_page_fault+0x114/0x5e8 [<b001e350>]handle_page_fault+0xc/0x80 [<b0022dec>]perf_callchain+0x224/0x31c [<b009ba70>]perf_prepare_sample+0x240/0x2fc [<b009d760>]__perf_event_overflow+0x280/0x398 [<b009d914>]perf_swevent_overflow+0x9c/0x10c [<b009db54>]perf_swevent_ctx_event+0x1d0/0x230 [<b009dc38>]do_perf_sw_event+0x84/0xe4 [<b009dde8>]perf_sw_event_context_switch+0x150/0x1b4 [<b009de90>]perf_event_task_sched_out+0x44/0x2d4 [<b02ad840>]schedule+0x2c0/0x614 [<b0047dc0>]__cond_resched+0x34/0x90 [<b02adcc8>]_cond_resched+0x4c/0x68 [<b00bccf8>]move_page_tables+0xb0/0x418 [<b00d7ee0>]setup_arg_pages+0x184/0x2a0 [<b0110914>]load_elf_binary+0x394/0x1208 [<b00d6e28>]search_binary_handler+0xe0/0x2c4 [<b00d834c>]do_execve+0x1bc/0x268 [<b0015394>]sys_execve+0x84/0xc8 [<b001df10>]ret_from_syscall+0x0/0x3c A page fault occurred walking the callchain while creating a perf sample for the context-switch event. To handle the page fault the mmap_sem is needed, but it is currently held by setup_arg_pages. (setup_arg_pages calls shift_arg_pages with the mmap_sem held. shift_arg_pages then calls move_page_tables which has a cond_resched at the top of its for loop - hitting that cond_resched is what caused the context switch.) This is an extension of Anton's proposed patch: https://lkml.org/lkml/2011/7/24/151 adding case for 32-bit ppc. Tested on the system that first generated the panic and then again with latest kernel using a PPC VM. I am not able to test the 64-bit path - I do not have H/W for it and 64-bit PPC VMs (qemu on Intel) is horribly slow. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-07-30 10:53:20 +00:00
pagefault_disable();
if (!__get_user_inatomic(*ret, ptr)) {
pagefault_enable();
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
return 0;
powerpc/perf: Disable pagefaults during callchain stack read Panic observed on an older kernel when collecting call chains for the context-switch software event: [<b0180e00>]rb_erase+0x1b4/0x3e8 [<b00430f4>]__dequeue_entity+0x50/0xe8 [<b0043304>]set_next_entity+0x178/0x1bc [<b0043440>]pick_next_task_fair+0xb0/0x118 [<b02ada80>]schedule+0x500/0x614 [<b02afaa8>]rwsem_down_failed_common+0xf0/0x264 [<b02afca0>]rwsem_down_read_failed+0x34/0x54 [<b02aed4c>]down_read+0x3c/0x54 [<b0023b58>]do_page_fault+0x114/0x5e8 [<b001e350>]handle_page_fault+0xc/0x80 [<b0022dec>]perf_callchain+0x224/0x31c [<b009ba70>]perf_prepare_sample+0x240/0x2fc [<b009d760>]__perf_event_overflow+0x280/0x398 [<b009d914>]perf_swevent_overflow+0x9c/0x10c [<b009db54>]perf_swevent_ctx_event+0x1d0/0x230 [<b009dc38>]do_perf_sw_event+0x84/0xe4 [<b009dde8>]perf_sw_event_context_switch+0x150/0x1b4 [<b009de90>]perf_event_task_sched_out+0x44/0x2d4 [<b02ad840>]schedule+0x2c0/0x614 [<b0047dc0>]__cond_resched+0x34/0x90 [<b02adcc8>]_cond_resched+0x4c/0x68 [<b00bccf8>]move_page_tables+0xb0/0x418 [<b00d7ee0>]setup_arg_pages+0x184/0x2a0 [<b0110914>]load_elf_binary+0x394/0x1208 [<b00d6e28>]search_binary_handler+0xe0/0x2c4 [<b00d834c>]do_execve+0x1bc/0x268 [<b0015394>]sys_execve+0x84/0xc8 [<b001df10>]ret_from_syscall+0x0/0x3c A page fault occurred walking the callchain while creating a perf sample for the context-switch event. To handle the page fault the mmap_sem is needed, but it is currently held by setup_arg_pages. (setup_arg_pages calls shift_arg_pages with the mmap_sem held. shift_arg_pages then calls move_page_tables which has a cond_resched at the top of its for loop - hitting that cond_resched is what caused the context switch.) This is an extension of Anton's proposed patch: https://lkml.org/lkml/2011/7/24/151 adding case for 32-bit ppc. Tested on the system that first generated the panic and then again with latest kernel using a PPC VM. I am not able to test the 64-bit path - I do not have H/W for it and 64-bit PPC VMs (qemu on Intel) is horribly slow. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-07-30 10:53:20 +00:00
}
pagefault_enable();
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
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;
powerpc/perf: Disable pagefaults during callchain stack read Panic observed on an older kernel when collecting call chains for the context-switch software event: [<b0180e00>]rb_erase+0x1b4/0x3e8 [<b00430f4>]__dequeue_entity+0x50/0xe8 [<b0043304>]set_next_entity+0x178/0x1bc [<b0043440>]pick_next_task_fair+0xb0/0x118 [<b02ada80>]schedule+0x500/0x614 [<b02afaa8>]rwsem_down_failed_common+0xf0/0x264 [<b02afca0>]rwsem_down_read_failed+0x34/0x54 [<b02aed4c>]down_read+0x3c/0x54 [<b0023b58>]do_page_fault+0x114/0x5e8 [<b001e350>]handle_page_fault+0xc/0x80 [<b0022dec>]perf_callchain+0x224/0x31c [<b009ba70>]perf_prepare_sample+0x240/0x2fc [<b009d760>]__perf_event_overflow+0x280/0x398 [<b009d914>]perf_swevent_overflow+0x9c/0x10c [<b009db54>]perf_swevent_ctx_event+0x1d0/0x230 [<b009dc38>]do_perf_sw_event+0x84/0xe4 [<b009dde8>]perf_sw_event_context_switch+0x150/0x1b4 [<b009de90>]perf_event_task_sched_out+0x44/0x2d4 [<b02ad840>]schedule+0x2c0/0x614 [<b0047dc0>]__cond_resched+0x34/0x90 [<b02adcc8>]_cond_resched+0x4c/0x68 [<b00bccf8>]move_page_tables+0xb0/0x418 [<b00d7ee0>]setup_arg_pages+0x184/0x2a0 [<b0110914>]load_elf_binary+0x394/0x1208 [<b00d6e28>]search_binary_handler+0xe0/0x2c4 [<b00d834c>]do_execve+0x1bc/0x268 [<b0015394>]sys_execve+0x84/0xc8 [<b001df10>]ret_from_syscall+0x0/0x3c A page fault occurred walking the callchain while creating a perf sample for the context-switch event. To handle the page fault the mmap_sem is needed, but it is currently held by setup_arg_pages. (setup_arg_pages calls shift_arg_pages with the mmap_sem held. shift_arg_pages then calls move_page_tables which has a cond_resched at the top of its for loop - hitting that cond_resched is what caused the context switch.) This is an extension of Anton's proposed patch: https://lkml.org/lkml/2011/7/24/151 adding case for 32-bit ppc. Tested on the system that first generated the panic and then again with latest kernel using a PPC VM. I am not able to test the 64-bit path - I do not have H/W for it and 64-bit PPC VMs (qemu on Intel) is horribly slow. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-07-30 10:53:20 +00:00
pagefault_disable();
if (!__get_user_inatomic(*ret, ptr)) {
pagefault_enable();
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
return 0;
powerpc/perf: Disable pagefaults during callchain stack read Panic observed on an older kernel when collecting call chains for the context-switch software event: [<b0180e00>]rb_erase+0x1b4/0x3e8 [<b00430f4>]__dequeue_entity+0x50/0xe8 [<b0043304>]set_next_entity+0x178/0x1bc [<b0043440>]pick_next_task_fair+0xb0/0x118 [<b02ada80>]schedule+0x500/0x614 [<b02afaa8>]rwsem_down_failed_common+0xf0/0x264 [<b02afca0>]rwsem_down_read_failed+0x34/0x54 [<b02aed4c>]down_read+0x3c/0x54 [<b0023b58>]do_page_fault+0x114/0x5e8 [<b001e350>]handle_page_fault+0xc/0x80 [<b0022dec>]perf_callchain+0x224/0x31c [<b009ba70>]perf_prepare_sample+0x240/0x2fc [<b009d760>]__perf_event_overflow+0x280/0x398 [<b009d914>]perf_swevent_overflow+0x9c/0x10c [<b009db54>]perf_swevent_ctx_event+0x1d0/0x230 [<b009dc38>]do_perf_sw_event+0x84/0xe4 [<b009dde8>]perf_sw_event_context_switch+0x150/0x1b4 [<b009de90>]perf_event_task_sched_out+0x44/0x2d4 [<b02ad840>]schedule+0x2c0/0x614 [<b0047dc0>]__cond_resched+0x34/0x90 [<b02adcc8>]_cond_resched+0x4c/0x68 [<b00bccf8>]move_page_tables+0xb0/0x418 [<b00d7ee0>]setup_arg_pages+0x184/0x2a0 [<b0110914>]load_elf_binary+0x394/0x1208 [<b00d6e28>]search_binary_handler+0xe0/0x2c4 [<b00d834c>]do_execve+0x1bc/0x268 [<b0015394>]sys_execve+0x84/0xc8 [<b001df10>]ret_from_syscall+0x0/0x3c A page fault occurred walking the callchain while creating a perf sample for the context-switch event. To handle the page fault the mmap_sem is needed, but it is currently held by setup_arg_pages. (setup_arg_pages calls shift_arg_pages with the mmap_sem held. shift_arg_pages then calls move_page_tables which has a cond_resched at the top of its for loop - hitting that cond_resched is what caused the context switch.) This is an extension of Anton's proposed patch: https://lkml.org/lkml/2011/7/24/151 adding case for 32-bit ppc. Tested on the system that first generated the panic and then again with latest kernel using a PPC VM. I am not able to test the 64-bit path - I do not have H/W for it and 64-bit PPC VMs (qemu on Intel) is horribly slow. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-07-30 10:53:20 +00:00
}
pagefault_enable();
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
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;
}
perf: Generalize some arch callchain code - Most archs use one callchain buffer per cpu, except x86 that needs to deal with NMIs. Provide a default perf_callchain_buffer() implementation that x86 overrides. - Centralize all the kernel/user regs handling and invoke new arch handlers from there: perf_callchain_user() / perf_callchain_kernel() That avoid all the user_mode(), current->mm checks and so... - Invert some parameters in perf_callchain_*() helpers: entry to the left, regs to the right, following the traditional (dst, src). Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-30 21:03:51 +00:00
static void perf_callchain_user_64(struct perf_callchain_entry *entry,
struct pt_regs *regs)
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
{
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];
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
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;
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, PERF_CONTEXT_USER);
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
continue;
}
if (level == 0)
next_ip = lr;
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
++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)
{
powerpc/perf: Disable pagefaults during callchain stack read Panic observed on an older kernel when collecting call chains for the context-switch software event: [<b0180e00>]rb_erase+0x1b4/0x3e8 [<b00430f4>]__dequeue_entity+0x50/0xe8 [<b0043304>]set_next_entity+0x178/0x1bc [<b0043440>]pick_next_task_fair+0xb0/0x118 [<b02ada80>]schedule+0x500/0x614 [<b02afaa8>]rwsem_down_failed_common+0xf0/0x264 [<b02afca0>]rwsem_down_read_failed+0x34/0x54 [<b02aed4c>]down_read+0x3c/0x54 [<b0023b58>]do_page_fault+0x114/0x5e8 [<b001e350>]handle_page_fault+0xc/0x80 [<b0022dec>]perf_callchain+0x224/0x31c [<b009ba70>]perf_prepare_sample+0x240/0x2fc [<b009d760>]__perf_event_overflow+0x280/0x398 [<b009d914>]perf_swevent_overflow+0x9c/0x10c [<b009db54>]perf_swevent_ctx_event+0x1d0/0x230 [<b009dc38>]do_perf_sw_event+0x84/0xe4 [<b009dde8>]perf_sw_event_context_switch+0x150/0x1b4 [<b009de90>]perf_event_task_sched_out+0x44/0x2d4 [<b02ad840>]schedule+0x2c0/0x614 [<b0047dc0>]__cond_resched+0x34/0x90 [<b02adcc8>]_cond_resched+0x4c/0x68 [<b00bccf8>]move_page_tables+0xb0/0x418 [<b00d7ee0>]setup_arg_pages+0x184/0x2a0 [<b0110914>]load_elf_binary+0x394/0x1208 [<b00d6e28>]search_binary_handler+0xe0/0x2c4 [<b00d834c>]do_execve+0x1bc/0x268 [<b0015394>]sys_execve+0x84/0xc8 [<b001df10>]ret_from_syscall+0x0/0x3c A page fault occurred walking the callchain while creating a perf sample for the context-switch event. To handle the page fault the mmap_sem is needed, but it is currently held by setup_arg_pages. (setup_arg_pages calls shift_arg_pages with the mmap_sem held. shift_arg_pages then calls move_page_tables which has a cond_resched at the top of its for loop - hitting that cond_resched is what caused the context switch.) This is an extension of Anton's proposed patch: https://lkml.org/lkml/2011/7/24/151 adding case for 32-bit ppc. Tested on the system that first generated the panic and then again with latest kernel using a PPC VM. I am not able to test the 64-bit path - I do not have H/W for it and 64-bit PPC VMs (qemu on Intel) is horribly slow. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-07-30 10:53:20 +00:00
int rc;
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
((unsigned long)ptr & 3))
return -EFAULT;
powerpc/perf: Disable pagefaults during callchain stack read Panic observed on an older kernel when collecting call chains for the context-switch software event: [<b0180e00>]rb_erase+0x1b4/0x3e8 [<b00430f4>]__dequeue_entity+0x50/0xe8 [<b0043304>]set_next_entity+0x178/0x1bc [<b0043440>]pick_next_task_fair+0xb0/0x118 [<b02ada80>]schedule+0x500/0x614 [<b02afaa8>]rwsem_down_failed_common+0xf0/0x264 [<b02afca0>]rwsem_down_read_failed+0x34/0x54 [<b02aed4c>]down_read+0x3c/0x54 [<b0023b58>]do_page_fault+0x114/0x5e8 [<b001e350>]handle_page_fault+0xc/0x80 [<b0022dec>]perf_callchain+0x224/0x31c [<b009ba70>]perf_prepare_sample+0x240/0x2fc [<b009d760>]__perf_event_overflow+0x280/0x398 [<b009d914>]perf_swevent_overflow+0x9c/0x10c [<b009db54>]perf_swevent_ctx_event+0x1d0/0x230 [<b009dc38>]do_perf_sw_event+0x84/0xe4 [<b009dde8>]perf_sw_event_context_switch+0x150/0x1b4 [<b009de90>]perf_event_task_sched_out+0x44/0x2d4 [<b02ad840>]schedule+0x2c0/0x614 [<b0047dc0>]__cond_resched+0x34/0x90 [<b02adcc8>]_cond_resched+0x4c/0x68 [<b00bccf8>]move_page_tables+0xb0/0x418 [<b00d7ee0>]setup_arg_pages+0x184/0x2a0 [<b0110914>]load_elf_binary+0x394/0x1208 [<b00d6e28>]search_binary_handler+0xe0/0x2c4 [<b00d834c>]do_execve+0x1bc/0x268 [<b0015394>]sys_execve+0x84/0xc8 [<b001df10>]ret_from_syscall+0x0/0x3c A page fault occurred walking the callchain while creating a perf sample for the context-switch event. To handle the page fault the mmap_sem is needed, but it is currently held by setup_arg_pages. (setup_arg_pages calls shift_arg_pages with the mmap_sem held. shift_arg_pages then calls move_page_tables which has a cond_resched at the top of its for loop - hitting that cond_resched is what caused the context switch.) This is an extension of Anton's proposed patch: https://lkml.org/lkml/2011/7/24/151 adding case for 32-bit ppc. Tested on the system that first generated the panic and then again with latest kernel using a PPC VM. I am not able to test the 64-bit path - I do not have H/W for it and 64-bit PPC VMs (qemu on Intel) is horribly slow. Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-07-30 10:53:20 +00:00
pagefault_disable();
rc = __get_user_inatomic(*ret, ptr);
pagefault_enable();
return rc;
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
}
perf: Generalize some arch callchain code - Most archs use one callchain buffer per cpu, except x86 that needs to deal with NMIs. Provide a default perf_callchain_buffer() implementation that x86 overrides. - Centralize all the kernel/user regs handling and invoke new arch handlers from there: perf_callchain_user() / perf_callchain_kernel() That avoid all the user_mode(), current->mm checks and so... - Invert some parameters in perf_callchain_*() helpers: entry to the left, regs to the right, following the traditional (dst, src). Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-30 21:03:51 +00:00
static inline void perf_callchain_user_64(struct perf_callchain_entry *entry,
struct pt_regs *regs)
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
{
}
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;
}
perf: Generalize some arch callchain code - Most archs use one callchain buffer per cpu, except x86 that needs to deal with NMIs. Provide a default perf_callchain_buffer() implementation that x86 overrides. - Centralize all the kernel/user regs handling and invoke new arch handlers from there: perf_callchain_user() / perf_callchain_kernel() That avoid all the user_mode(), current->mm checks and so... - Invert some parameters in perf_callchain_*() helpers: entry to the left, regs to the right, following the traditional (dst, src). Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-30 21:03:51 +00:00
static void perf_callchain_user_32(struct perf_callchain_entry *entry,
struct pt_regs *regs)
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
{
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];
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
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;
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, PERF_CONTEXT_USER);
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
continue;
}
if (level == 0)
next_ip = lr;
perf: Generalize callchain_store() callchain_store() is the same on every archs, inline it in perf_event.h and rename it to perf_callchain_store() to avoid any collision. This removes repetitive code. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-29 17:34:05 +00:00
perf_callchain_store(entry, next_ip);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
++level;
sp = next_sp;
}
}
perf: Generalize some arch callchain code - Most archs use one callchain buffer per cpu, except x86 that needs to deal with NMIs. Provide a default perf_callchain_buffer() implementation that x86 overrides. - Centralize all the kernel/user regs handling and invoke new arch handlers from there: perf_callchain_user() / perf_callchain_kernel() That avoid all the user_mode(), current->mm checks and so... - Invert some parameters in perf_callchain_*() helpers: entry to the left, regs to the right, following the traditional (dst, src). Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-30 21:03:51 +00:00
void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
{
perf: Generalize some arch callchain code - Most archs use one callchain buffer per cpu, except x86 that needs to deal with NMIs. Provide a default perf_callchain_buffer() implementation that x86 overrides. - Centralize all the kernel/user regs handling and invoke new arch handlers from there: perf_callchain_user() / perf_callchain_kernel() That avoid all the user_mode(), current->mm checks and so... - Invert some parameters in perf_callchain_*() helpers: entry to the left, regs to the right, following the traditional (dst, src). Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Paul Mackerras <paulus@samba.org> Tested-by: Will Deacon <will.deacon@arm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Stephane Eranian <eranian@google.com> Cc: David Miller <davem@davemloft.net> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Borislav Petkov <bp@amd64.org>
2010-06-30 21:03:51 +00:00
if (current_is_64bit())
perf_callchain_user_64(entry, regs);
else
perf_callchain_user_32(entry, regs);
perf_counter: powerpc: Add callchain support This adds support for tracing callchains for powerpc, both 32-bit and 64-bit, and both in the kernel and userspace, from PMU interrupt context. The first three entries stored for each callchain are the NIP (next instruction pointer), LR (link register), and the contents of the LR save area in the second stack frame (the first is ignored because the ABI convention on powerpc is that functions save their return address in their caller's stack frame). Because leaf functions don't have to save their return address (LR value) and don't have to establish a stack frame, it's possible for either or both of LR and the second stack frame's LR save area to have valid return addresses in them. This is basically impossible to disambiguate without either reading the code or looking at auxiliary information such as CFI tables. Since we don't want to do either of those things at interrupt time, we store both LR and the second stack frame's LR save area. Once we get past the second stack frame, there is no ambiguity; all return addresses we get are reliable. For kernel traces, we check whether they are valid kernel instruction addresses and store zero instead if they are not (rather than omitting them, which would make it impossible for userspace to know which was which). We also store zero instead of the second stack frame's LR save area value if it is the same as LR. For kernel traces, we check for interrupt frames, and for user traces, we check for signal frames. In each case, since we're starting a new trace, we store a PERF_CONTEXT_KERNEL/USER marker so that userspace knows that the next three entries are NIP, LR and the second stack frame for the interrupted context. We read user memory with __get_user_inatomic. On 64-bit, if this PMU interrupt occurred while interrupts are soft-disabled, and there is no MMU hash table entry for the page, we will get an -EFAULT return from __get_user_inatomic even if there is a valid Linux PTE for the page, since hash_page isn't reentrant. Thus we have code here to read the Linux PTE and access the page via the kernel linear mapping. Since 64-bit doesn't use (or need) highmem there is no need to do kmap_atomic. On 32-bit, we don't do soft interrupt disabling, so this complication doesn't occur and there is no need to fall back to reading the Linux PTE, since hash_page (or the TLB miss handler) will get called automatically if necessary. Note that we cannot get PMU interrupts in the interval during context switch between switch_mm (which switches the user address space) and switch_to (which actually changes current to the new process). On 64-bit this is because interrupts are hard-disabled in switch_mm and stay hard-disabled until they are soft-enabled later, after switch_to has returned. So there is no possibility of trying to do a user stack trace when the user address space is not current's address space. Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
2009-08-17 22:25:32 +00:00
}
Reference in New Issue Copy Permalink