From b6ab4afee4ed56d0f69df59485585cff828c327d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 30 Dec 2008 09:41:04 +0100 Subject: tracing, kvm: change MARKERS to select instead of depends on Impact: build fix fix: kernel/trace/Kconfig:42:error: found recursive dependency: TRACING -> TRACEPOINTS -> MARKERS -> KVM_TRACE -> RELAY -> KMEMTRACE -> TRACING markers is a facility that should be selected - not depended on by an interactive Kconfig entry. Signed-off-by: Ingo Molnar --- arch/x86/kvm/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b81125f0bdee..c7da3683f4c5 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -55,7 +55,8 @@ config KVM_AMD config KVM_TRACE bool "KVM trace support" - depends on KVM && MARKERS && SYSFS + depends on KVM && SYSFS + select MARKERS select RELAY select DEBUG_FS default n -- cgit v1.2.3 From fe6f90e57fd31af8daca534ea01db2e5666c15da Mon Sep 17 00:00:00 2001 From: Pekka Paalanen Date: Sat, 3 Jan 2009 21:23:51 +0200 Subject: trace: mmiotrace to the tracer menu in Kconfig Impact: cosmetic change in Kconfig menu layout This patch was originally suggested by Peter Zijlstra, but seems it was forgotten. CONFIG_MMIOTRACE and CONFIG_MMIOTRACE_TEST were selectable directly under the Kernel hacking / debugging menu in the kernel configuration system. They were present only for x86 and x86_64. Other tracers that use the ftrace tracing framework are in their own sub-menu. This patch moves the mmiotrace configuration options there. Since the Kconfig file, where the tracer menu is, is not architecture specific, HAVE_MMIOTRACE_SUPPORT is introduced and provided only by x86/x86_64. CONFIG_MMIOTRACE now depends on it. Signed-off-by: Pekka Paalanen Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/Kconfig.debug | 24 ++---------------------- 1 file changed, 2 insertions(+), 22 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 10d6cc3fd052..e1983fa025d2 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -174,28 +174,8 @@ config IOMMU_LEAK Add a simple leak tracer to the IOMMU code. This is useful when you are debugging a buggy device driver that leaks IOMMU mappings. -config MMIOTRACE - bool "Memory mapped IO tracing" - depends on DEBUG_KERNEL && PCI - select TRACING - help - Mmiotrace traces Memory Mapped I/O access and is meant for - debugging and reverse engineering. It is called from the ioremap - implementation and works via page faults. Tracing is disabled by - default and can be enabled at run-time. - - See Documentation/tracers/mmiotrace.txt. - If you are not helping to develop drivers, say N. - -config MMIOTRACE_TEST - tristate "Test module for mmiotrace" - depends on MMIOTRACE && m - help - This is a dumb module for testing mmiotrace. It is very dangerous - as it will write garbage to IO memory starting at a given address. - However, it should be safe to use on e.g. unused portion of VRAM. - - Say N, unless you absolutely know what you are doing. +config HAVE_MMIOTRACE_SUPPORT + def_bool y # # IO delay types: -- cgit v1.2.3 From b1818748b0cf9427e48acf9713295e829a0d715f Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Mon, 19 Jan 2009 10:31:01 +0100 Subject: x86, ftrace, hw-branch-tracer: dump trace on oops Dump the branch trace on an oops (based on ftrace_dump_on_oops). Signed-off-by: Markus Metzger Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/dumpstack.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 6b1f6f6f8661..077c9ea655fc 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -14,6 +14,7 @@ #include #include #include +#include #include @@ -195,6 +196,11 @@ unsigned __kprobes long oops_begin(void) int cpu; unsigned long flags; + /* notify the hw-branch tracer so it may disable tracing and + add the last trace to the trace buffer - + the earlier this happens, the more useful the trace. */ + trace_hw_branch_oops(); + oops_enter(); /* racy, but better than risking deadlock. */ -- cgit v1.2.3 From ce5e5540c0e839781e7cd134517d5d2e9e819636 Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Mon, 19 Jan 2009 10:38:35 +0100 Subject: x86, ds, bts: cleanup DS configuration Cleanup the cpuid check for DS configuration. Signed-off-by: Markus Metzger Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ds.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c index da91701a2348..169a120587be 100644 --- a/arch/x86/kernel/ds.c +++ b/arch/x86/kernel/ds.c @@ -15,8 +15,8 @@ * - buffer allocation (memory accounting) * * - * Copyright (C) 2007-2008 Intel Corporation. - * Markus Metzger , 2007-2008 + * Copyright (C) 2007-2009 Intel Corporation. + * Markus Metzger , 2007-2009 */ @@ -890,7 +890,7 @@ int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value) } static const struct ds_configuration ds_cfg_netburst = { - .name = "netburst", + .name = "Netburst", .ctl[dsf_bts] = (1 << 2) | (1 << 3), .ctl[dsf_bts_kernel] = (1 << 5), .ctl[dsf_bts_user] = (1 << 6), @@ -904,7 +904,7 @@ static const struct ds_configuration ds_cfg_netburst = { #endif }; static const struct ds_configuration ds_cfg_pentium_m = { - .name = "pentium m", + .name = "Pentium M", .ctl[dsf_bts] = (1 << 6) | (1 << 7), .sizeof_field = sizeof(long), @@ -915,8 +915,8 @@ static const struct ds_configuration ds_cfg_pentium_m = { .sizeof_rec[ds_pebs] = sizeof(long) * 18, #endif }; -static const struct ds_configuration ds_cfg_core2 = { - .name = "core 2", +static const struct ds_configuration ds_cfg_core2_atom = { + .name = "Core 2/Atom", .ctl[dsf_bts] = (1 << 6) | (1 << 7), .ctl[dsf_bts_kernel] = (1 << 9), .ctl[dsf_bts_user] = (1 << 10), @@ -949,19 +949,22 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c) switch (c->x86) { case 0x6: switch (c->x86_model) { - case 0 ... 0xC: - /* sorry, don't know about them */ - break; - case 0xD: - case 0xE: /* Pentium M */ + case 0x9: + case 0xd: /* Pentium M */ ds_configure(&ds_cfg_pentium_m); break; - default: /* Core2, Atom, ... */ - ds_configure(&ds_cfg_core2); + case 0xf: + case 0x17: /* Core2 */ + case 0x1c: /* Atom */ + ds_configure(&ds_cfg_core2_atom); + break; + case 0x1a: /* i7 */ + default: + /* sorry, don't know about them */ break; } break; - case 0xF: + case 0xf: switch (c->x86_model) { case 0x0: case 0x1: -- cgit v1.2.3 From 890252823766e562301e61340f3187a14033d045 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 26 Jan 2009 18:28:02 +0300 Subject: x86: ftrace - simplify wait_for_nmi Get rid of 'waited' stack variable. Signed-off-by: Cyrill Gorcunov Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1b43086b097a..4d33224c055f 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -133,15 +133,14 @@ void ftrace_nmi_exit(void) static void wait_for_nmi(void) { - int waited = 0; + if (!atomic_read(&in_nmi)) + return; - while (atomic_read(&in_nmi)) { - waited = 1; + do { cpu_relax(); - } + } while(atomic_read(&in_nmi)); - if (waited) - nmi_wait_count++; + nmi_wait_count++; } static int -- cgit v1.2.3 From 78d904b46a72fcf15ea6a39672bbef92953876b5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 Feb 2009 18:43:07 -0500 Subject: ring-buffer: add NMI protection for spinlocks Impact: prevent deadlock in NMI The ring buffers are not yet totally lockless with writing to the buffer. When a writer crosses a page, it grabs a per cpu spinlock to protect against a reader. The spinlocks taken by a writer are not to protect against other writers, since a writer can only write to its own per cpu buffer. The spinlocks protect against readers that can touch any cpu buffer. The writers are made to be reentrant with the spinlocks disabling interrupts. The problem arises when an NMI writes to the buffer, and that write crosses a page boundary. If it grabs a spinlock, it can be racing with another writer (since disabling interrupts does not protect against NMIs) or with a reader on the same CPU. Luckily, most of the users are not reentrant and protects against this issue. But if a user of the ring buffer becomes reentrant (which is what the ring buffers do allow), if the NMI also writes to the ring buffer then we risk the chance of a deadlock. This patch moves the ftrace_nmi_enter called by nmi_enter() to the ring buffer code. It replaces the current ftrace_nmi_enter that is used by arch specific code to arch_ftrace_nmi_enter and updates the Kconfig to handle it. When an NMI is called, it will set a per cpu variable in the ring buffer code and will clear it when the NMI exits. If a write to the ring buffer crosses page boundaries inside an NMI, a trylock is used on the spin lock instead. If the spinlock fails to be acquired, then the entry is discarded. This bug appeared in the ftrace work in the RT tree, where event tracing is reentrant. This workaround solved the deadlocks that appeared there. Signed-off-by: Steven Rostedt --- arch/x86/Kconfig | 1 + arch/x86/kernel/ftrace.c | 8 ++++---- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 73f7fe8fd4d1..a6be725cb049 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,6 +34,7 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE || FUNCTION_GRAPH_TRACER select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER select HAVE_ARCH_TRACEHOOK diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4d33224c055f..4c683587055b 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -113,7 +113,7 @@ static void ftrace_mod_code(void) MCOUNT_INSN_SIZE); } -void ftrace_nmi_enter(void) +void arch_ftrace_nmi_enter(void) { atomic_inc(&in_nmi); /* Must have in_nmi seen before reading write flag */ @@ -124,7 +124,7 @@ void ftrace_nmi_enter(void) } } -void ftrace_nmi_exit(void) +void arch_ftrace_nmi_exit(void) { /* Finish all executions before clearing in_nmi */ smp_wmb(); @@ -376,12 +376,12 @@ int ftrace_disable_ftrace_graph_caller(void) */ static atomic_t in_nmi; -void ftrace_nmi_enter(void) +void arch_ftrace_nmi_enter(void) { atomic_inc(&in_nmi); } -void ftrace_nmi_exit(void) +void arch_ftrace_nmi_exit(void) { atomic_dec(&in_nmi); } -- cgit v1.2.3 From 4e6ea1440c67de32d7c89aacf233472dfc3bce82 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 5 Feb 2009 22:30:07 -0500 Subject: ftrace, x86: rename in_nmi variable Impact: clean up The in_nmi variable in x86 arch ftrace.c is a misnomer. Andrew Morton pointed out that the in_nmi variable is incremented by all CPUS. It can be set when another CPU is running an NMI. Since this is actually intentional, the fix is to rename it to what it really is: "nmi_running" Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4c683587055b..e3fad2ef622c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -82,7 +82,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * are the same as what exists. */ -static atomic_t in_nmi = ATOMIC_INIT(0); +static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ static int mod_code_write; /* set when NMI should do the write */ static void *mod_code_ip; /* holds the IP to write to */ @@ -115,8 +115,8 @@ static void ftrace_mod_code(void) void arch_ftrace_nmi_enter(void) { - atomic_inc(&in_nmi); - /* Must have in_nmi seen before reading write flag */ + atomic_inc(&nmi_running); + /* Must have nmi_running seen before reading write flag */ smp_mb(); if (mod_code_write) { ftrace_mod_code(); @@ -126,19 +126,19 @@ void arch_ftrace_nmi_enter(void) void arch_ftrace_nmi_exit(void) { - /* Finish all executions before clearing in_nmi */ + /* Finish all executions before clearing nmi_running */ smp_wmb(); - atomic_dec(&in_nmi); + atomic_dec(&nmi_running); } static void wait_for_nmi(void) { - if (!atomic_read(&in_nmi)) + if (!atomic_read(&nmi_running)) return; do { cpu_relax(); - } while(atomic_read(&in_nmi)); + } while (atomic_read(&nmi_running)); nmi_wait_count++; } @@ -374,16 +374,16 @@ int ftrace_disable_ftrace_graph_caller(void) * this page for dynamic ftrace. They have been * simplified to ignore all traces in NMI context. */ -static atomic_t in_nmi; +static atomic_t nmi_running; void arch_ftrace_nmi_enter(void) { - atomic_inc(&in_nmi); + atomic_inc(&nmi_running); } void arch_ftrace_nmi_exit(void) { - atomic_dec(&in_nmi); + atomic_dec(&nmi_running); } #endif /* !CONFIG_DYNAMIC_FTRACE */ @@ -475,7 +475,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) &return_to_handler; /* Nmi's are currently unsupported */ - if (unlikely(atomic_read(&in_nmi))) + if (unlikely(atomic_read(&nmi_running))) return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) -- cgit v1.2.3 From 9a5fd902273d01170fd033691bd70b142baa7309 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 6 Feb 2009 01:14:26 -0500 Subject: ftrace: change function graph tracer to use new in_nmi The function graph tracer piggy backed onto the dynamic ftracer to use the in_nmi custom code for dynamic tracing. The problem was (as Andrew Morton pointed out) it really only wanted to bail out if the context of the current CPU was in NMI context. But the dynamic ftrace in_nmi custom code was true if _any_ CPU happened to be in NMI context. Now that we have a generic in_nmi interface, this patch changes the function graph code to use it instead of the dynamic ftarce custom code. Reported-by: Andrew Morton Signed-off-by: Steven Rostedt --- arch/x86/Kconfig | 2 +- arch/x86/kernel/ftrace.c | 21 +-------------------- 2 files changed, 2 insertions(+), 21 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a6be725cb049..2cf7bbcaed4e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,7 +34,7 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST - select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE || FUNCTION_GRAPH_TRACER + select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER select HAVE_ARCH_TRACEHOOK diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index e3fad2ef622c..918073c6681b 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -367,25 +367,6 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, old_offset, new_offset); } -#else /* CONFIG_DYNAMIC_FTRACE */ - -/* - * These functions are picked from those used on - * this page for dynamic ftrace. They have been - * simplified to ignore all traces in NMI context. - */ -static atomic_t nmi_running; - -void arch_ftrace_nmi_enter(void) -{ - atomic_inc(&nmi_running); -} - -void arch_ftrace_nmi_exit(void) -{ - atomic_dec(&nmi_running); -} - #endif /* !CONFIG_DYNAMIC_FTRACE */ /* Add a function return address to the trace stack on thread info.*/ @@ -475,7 +456,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) &return_to_handler; /* Nmi's are currently unsupported */ - if (unlikely(atomic_read(&nmi_running))) + if (unlikely(in_nmi())) return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) -- cgit v1.2.3 From a81bd80a0b0a405dc0483e2c428332d69da2c79f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 6 Feb 2009 01:45:16 -0500 Subject: ring-buffer: use generic version of in_nmi Impact: clean up Now that a generic in_nmi is available, this patch removes the special code in the ring_buffer and implements the in_nmi generic version instead. With this change, I was also able to rename the "arch_ftrace_nmi_enter" back to "ftrace_nmi_enter" and remove the code from the ring buffer. Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 918073c6681b..d74d75e0952d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -113,7 +113,7 @@ static void ftrace_mod_code(void) MCOUNT_INSN_SIZE); } -void arch_ftrace_nmi_enter(void) +void ftrace_nmi_enter(void) { atomic_inc(&nmi_running); /* Must have nmi_running seen before reading write flag */ @@ -124,7 +124,7 @@ void arch_ftrace_nmi_enter(void) } } -void arch_ftrace_nmi_exit(void) +void ftrace_nmi_exit(void) { /* Finish all executions before clearing nmi_running */ smp_wmb(); -- cgit v1.2.3 From 1292211058aaf872eeb2a0e2677d237916b4501f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 7 Feb 2009 22:16:12 +0100 Subject: tracing/power: move the power trace headers to a dedicated file Impact: cleanup Move the power tracer headers to trace/power.h to keep ftrace.h and power bits more easy to maintain as separated topics. Signed-off-by: Frederic Weisbecker Cc: Arjan van de Ven Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 2 +- arch/x86/kernel/process.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 4b1c319d30c3..7ed925edf4d2 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e68bb9e30864..026819ffcb0c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include -- cgit v1.2.3 From 3861a17bcc0af815f684c6178bc9ec2d790c350e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sun, 8 Feb 2009 00:04:02 +0100 Subject: tracing/function-graph-tracer: drop the kernel_text_address check When the function graph tracer picks a return address, it ensures this address is really a kernel text one by calling __kernel_text_address() Actually this path has never been taken.Its role was more likely to debug the tracer on the beginning of its development but this function is wasteful since it is called for every traced function. The fault check is already sufficient. Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d74d75e0952d..18828aee8781 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -491,13 +491,6 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - if (unlikely(!__kernel_text_address(old))) { - ftrace_graph_stop(); - *parent = old; - WARN_ON(1); - return; - } - calltime = cpu_clock(raw_smp_processor_id()); if (push_return_trace(old, calltime, -- cgit v1.2.3 From 966657883fdc3a2883a5e641ca4ec8f79ffb8ecd Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 10 Feb 2009 11:53:23 -0500 Subject: tracing, x86: fix constraint for parent variable The constraint used for retrieving and restoring the parent function pointer is incorrect. The parent variable is a pointer, and the address of the pointer is modified by the asm statement and not the pointer itself. It is incorrect to pass it in as an output constraint since the asm will never update the pointer. Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 18828aee8781..370bafaa43a3 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -468,8 +468,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) * ignore such a protection. */ asm volatile( - "1: " _ASM_MOV " (%[parent_old]), %[old]\n" - "2: " _ASM_MOV " %[return_hooker], (%[parent_replaced])\n" + "1: " _ASM_MOV " (%[parent]), %[old]\n" + "2: " _ASM_MOV " %[return_hooker], (%[parent])\n" " movl $0, %[faulted]\n" ".section .fixup, \"ax\"\n" @@ -479,9 +479,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) _ASM_EXTABLE(1b, 3b) _ASM_EXTABLE(2b, 3b) - : [parent_replaced] "=r" (parent), [old] "=r" (old), - [faulted] "=r" (faulted) - : [parent_old] "0" (parent), [return_hooker] "r" (return_hooker) + : [old] "=r" (old), [faulted] "=r" (faulted) + : [parent] "r" (parent), [return_hooker] "r" (return_hooker) : "memory" ); -- cgit v1.2.3 From b5f9fd0f8a05c9bafb91a9a85b9110938d8e585b Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Wed, 11 Feb 2009 13:57:25 -0500 Subject: tracing: convert c/p state power tracer to use tracepoints Convert the c/p state "power" tracer to use tracepoints. Avoids a function call when the tracer is disabled. Signed-off-by: Jason Baron Acked-by: Ingo Molnar Signed-off-by: Steven Rostedt --- arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c | 2 ++ arch/x86/kernel/process.c | 3 +++ 2 files changed, 5 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 7ed925edf4d2..c5d737cdb365 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -70,6 +70,8 @@ struct acpi_cpufreq_data { static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data); +DEFINE_TRACE(power_mark); + /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance *acpi_perf_data; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 026819ffcb0c..e0d0fd7ab514 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -19,6 +19,9 @@ EXPORT_SYMBOL(idle_nomwait); struct kmem_cache *task_xstate_cachep; +DEFINE_TRACE(power_start); +DEFINE_TRACE(power_end); + int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; -- cgit v1.2.3 From 16239630974516a8879a3695ee9b4dc661f79f96 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 17 Feb 2009 17:57:30 -0500 Subject: ftrace, x86: make kernel text writable only for conversions Impact: keep kernel text read only Because dynamic ftrace converts the calls to mcount into and out of nops at run time, we needed to always keep the kernel text writable. But this defeats the point of CONFIG_DEBUG_RODATA. This patch converts the kernel code to writable before ftrace modifies the text, and converts it back to read only afterward. The kernel text is converted to read/write, stop_machine is called to modify the code, then the kernel text is converted back to read only. The original version used SYSTEM_STATE to determine when it was OK or not to change the code to rw or ro. Andrew Morton pointed out that using SYSTEM_STATE is a bad idea since there is no guarantee to what its state will actually be. Instead, I moved the check into the set_kernel_text_* functions themselves, and use a local variable to determine when it is OK to change the kernel text RW permissions. [ Update: Ingo Molnar suggested moving the prototypes to cacheflush.h ] Reviewed-by: Andrew Morton Signed-off-by: Steven Rostedt --- arch/x86/include/asm/cacheflush.h | 5 +++++ arch/x86/kernel/ftrace.c | 13 +++++++++++++ arch/x86/mm/init_32.c | 35 ++++++++++++++++++++++++++++++++--- arch/x86/mm/init_64.c | 37 ++++++++++++++++++++++++++++++++----- 4 files changed, 82 insertions(+), 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index 2f8466540fb5..6145063cfe0e 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -104,6 +104,11 @@ void clflush_cache_range(void *addr, unsigned int size); #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; +void set_kernel_text_rw(void); +void set_kernel_text_ro(void); +#else +static inline void set_kernel_text_rw(void) { } +static inline void set_kernel_text_ro(void) { } #endif #ifdef CONFIG_DEBUG_RODATA_TEST diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 231bdd3c5b1c..77857d4f7d0f 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -26,6 +27,18 @@ #ifdef CONFIG_DYNAMIC_FTRACE +int ftrace_arch_code_modify_prepare(void) +{ + set_kernel_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_kernel_text_ro(); + return 0; +} + union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2cef05074413..3eb2ed188a4c 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1155,17 +1155,47 @@ static noinline int do_test_wp_bit(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, start+size); + + set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, start+size); + + set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; -#ifndef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); + kernel_set_to_readonly = 1; + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", start, start+size); @@ -1174,7 +1204,6 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif -#endif /* CONFIG_DYNAMIC_FTRACE */ start += size; size = (unsigned long)__end_rodata - start; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e6d36b490250..63fdc531601d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -986,21 +986,48 @@ void free_initmem(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, end); + + set_memory_rw(start, (end - start) >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, end); + + set_memory_ro(start, (end - start) >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); unsigned long rodata_start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; -#ifdef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ - start = rodata_start; -#endif - printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + kernel_set_to_readonly = 1; + /* * The rodata section (but not the kernel text!) should also be * not-executable. -- cgit v1.2.3 From 90c7ac49aa819feb9433b5310089fca6399881c0 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 19 Feb 2009 13:32:57 -0500 Subject: ftrace: immediately stop code modification if failure is detected Impact: fix to prevent NMI lockup If the page fault handler produces a WARN_ON in the modifying of text, and the system is setup to have a high frequency of NMIs, we can lock up the system on a failure to modify code. The modifying of code with NMIs allows all NMIs to modify the code if it is about to run. This prevents a modifier on one CPU from modifying code running in NMI context on another CPU. The modifying is done through stop_machine, so only NMIs must be considered. But if the write causes the page fault handler to produce a warning, the print can slow it down enough that as soon as it is done it will take another NMI before going back to the process context. The new NMI will perform the write again causing another print and this will hang the box. This patch turns off the writing as soon as a failure is detected and does not wait for it to be turned off by the process context. This will keep NMIs from getting stuck in this back and forth of print outs. Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 77857d4f7d0f..c56d73894322 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -124,6 +124,10 @@ static void ftrace_mod_code(void) */ mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); + + /* if we fail, then kill any new writers */ + if (mod_code_status) + mod_code_write = 0; } void ftrace_nmi_enter(void) -- cgit v1.2.3 From 499aa86dcbc3c4daf7d2c59c5c30e1a78220fbc1 Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Tue, 24 Feb 2009 14:12:34 +0100 Subject: x86, ptrace: remove CONFIG guards around declarations Remove unnecessary CONFIG guards around type declarations and macro definitions. Reported-by: Cyrill Gorcunov Signed-off-by: Markus Metzger Cc: markus.t.metzger@gmail.com Cc: roland@redhat.com Cc: eranian@googlemail.com Cc: oleg@redhat.com Cc: juan.villacis@intel.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/ptrace-abi.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 8e0f8d199e05..86723035a515 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -80,8 +80,6 @@ #define PTRACE_SINGLEBLOCK 33 /* resume execution until next branch */ -#ifdef CONFIG_X86_PTRACE_BTS - #ifndef __ASSEMBLY__ #include @@ -140,6 +138,5 @@ struct ptrace_bts_config { BTS records are read from oldest to newest. Returns number of BTS records drained. */ -#endif /* CONFIG_X86_PTRACE_BTS */ #endif /* _ASM_X86_PTRACE_ABI_H */ -- cgit v1.2.3 From 0012693ad4f636c720fed3802027f9427962f540 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Thu, 5 Mar 2009 01:49:22 +0100 Subject: tracing/function-graph-tracer: use the more lightweight local clock Impact: decrease hangs risks with the graph tracer on slow systems Since the function graph tracer can spend too much time on timer interrupts, it's better now to use the more lightweight local clock. Anyway, the function graph traces are more reliable on a per cpu trace. Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt Cc: Peter Zijlstra LKML-Reference: <49af243d.06e9300a.53ad.ffff840c@mx.google.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 3925ec0184b1..a85da1764b1c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -436,7 +436,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - calltime = cpu_clock(raw_smp_processor_id()); + calltime = trace_clock_local(); if (ftrace_push_return_trace(old, calltime, self_addr, &trace.depth) == -EBUSY) { -- cgit v1.2.3 From 3945dab45aa8c89014893bfa8eb1e1661a409cef Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Mar 2009 10:37:22 -0500 Subject: tracing, Text Edit Lock - SMP alternatives support Use the mutual exclusion provided by the text edit lock in alternatives code. Since alternative_smp_* will be called from module init code, etc, we'd better protect it from other subsystems. Signed-off-by: Masami Hiramatsu LKML-Reference: <49B14332.9030109@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/alternative.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4c80f1557433..092a7b8be68d 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -226,6 +227,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) { u8 **ptr; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -234,6 +236,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) /* turn DS segment override prefix into lock prefix */ text_poke(*ptr, ((unsigned char []){0xf0}), 1); }; + mutex_unlock(&text_mutex); } static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end) @@ -243,6 +246,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end if (noreplace_smp) return; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -251,6 +255,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end /* turn lock prefix into DS segment override prefix */ text_poke(*ptr, ((unsigned char []){0x3E}), 1); }; + mutex_unlock(&text_mutex); } struct smp_alt_module { -- cgit v1.2.3 From 78ff7fae04554b49d29226ed12536268c2500d1f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 6 Mar 2009 10:37:54 -0500 Subject: x86: implement atomic text_poke() via fixmap Use fixmaps instead of vmap/vunmap in text_poke() for avoiding page allocation and delayed unmapping. At the result of above change, text_poke() becomes atomic and can be called from stop_machine() etc. Signed-off-by: Masami Hiramatsu Acked-by: Mathieu Desnoyers LKML-Reference: <49B14352.2040705@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/fixmap.h | 2 ++ arch/x86/kernel/alternative.c | 24 +++++++++++++++--------- 2 files changed, 17 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 63a79c77d220..81937a5dc77c 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -111,6 +111,8 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif + FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ + FIX_TEXT_POKE1, __end_of_permanent_fixed_addresses, #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 092a7b8be68d..2d903b760ddb 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -13,7 +13,9 @@ #include #include #include +#include #include +#include #define MAX_PATCH_LEN (255-1) @@ -505,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len) * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. + * + * Note: Must be called under text_mutex. */ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) { + unsigned long flags; char *vaddr; - int nr_pages = 2; struct page *pages[2]; int i; - might_sleep(); if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -523,14 +526,17 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) pages[1] = virt_to_page(addr + PAGE_SIZE); } BUG_ON(!pages[0]); - if (!pages[1]) - nr_pages = 1; - vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - BUG_ON(!vaddr); - local_irq_disable(); + set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0])); + if (pages[1]) + set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1])); + vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0); + local_irq_save(flags); memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); - local_irq_enable(); - vunmap(vaddr); + local_irq_restore(flags); + clear_fixmap(FIX_TEXT_POKE0); + if (pages[1]) + clear_fixmap(FIX_TEXT_POKE1); + local_flush_tlb(); sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ -- cgit v1.2.3 From 7cf49427042400d40bdc80b5c3399b6b5945afa8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 9 Mar 2009 12:40:40 -0400 Subject: x86: expand irq-off region in text_poke() Expand irq-off region to cover fixmap using code and cache synchronizing. Signed-off-by: Masami Hiramatsu LKML-Reference: <49B54688.8090403@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/alternative.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 2d903b760ddb..f57658702571 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -526,13 +526,12 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) pages[1] = virt_to_page(addr + PAGE_SIZE); } BUG_ON(!pages[0]); + local_irq_save(flags); set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0])); if (pages[1]) set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1])); vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0); - local_irq_save(flags); memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); - local_irq_restore(flags); clear_fixmap(FIX_TEXT_POKE0); if (pages[1]) clear_fixmap(FIX_TEXT_POKE1); @@ -542,5 +541,6 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) that causes hangs on some VIA CPUs. */ for (i = 0; i < len; i++) BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]); + local_irq_restore(flags); return addr; } -- cgit v1.2.3 From 1b3fa2ce64363c289b3b14723cca7290bf91cfce Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 7 Mar 2009 05:53:00 +0100 Subject: tracing/x86: basic implementation of syscall tracing for x86 Provide the x86 trace callbacks to trace syscalls. Signed-off-by: Frederic Weisbecker Acked-by: Steven Rostedt Cc: Lai Jiangshan LKML-Reference: <1236401580-5758-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 1 + arch/x86/include/asm/thread_info.h | 9 ++++++--- arch/x86/kernel/ptrace.c | 7 +++++++ 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bdcee12c25ab..b0a638b4199a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -35,6 +35,7 @@ config X86 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE + select HAVE_FTRACE_SYSCALLS select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index df9d5f78385e..8820a73ae090 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -94,6 +94,7 @@ struct thread_info { #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ #define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -115,15 +116,17 @@ struct thread_info { #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) #define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE | \ _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ + _TIF_SYSCALL_FTRACE) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -132,7 +135,7 @@ struct thread_info { _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) /* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP) +#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 3d9672e59c16..99749d6e87a8 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -1416,6 +1417,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) tracehook_report_syscall_entry(regs)) ret = -1L; + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_enter(regs); + if (unlikely(current->audit_context)) { if (IS_IA32) audit_syscall_entry(AUDIT_ARCH_I386, @@ -1439,6 +1443,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_exit(regs); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); -- cgit v1.2.3 From f58ba100678f421bdcb000a3c71793f432dfab93 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 13 Mar 2009 15:42:12 +0100 Subject: tracing/syscalls: support for syscalls tracing on x86 Extend x86 architecture syscall tracing support with syscall metadata table details. (The upcoming core syscall tracing modifications rely on this.) Signed-off-by: Frederic Weisbecker Cc: Steven Rostedt LKML-Reference: <1236955332-10133-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/ftrace.h | 7 +++++ arch/x86/kernel/ftrace.c | 63 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index db24c2278be0..bd2c6511c887 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,6 +28,13 @@ #endif +/* FIXME: I don't want to stay hardcoded */ +#ifdef CONFIG_X86_64 +# define FTRACE_SYSCALL_MAX 296 +#else +# define FTRACE_SYSCALL_MAX 333 +#endif + #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_ADDR ((long)(mcount)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index a85da1764b1c..1d0d7f42efe3 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -453,3 +453,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS + +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; +extern unsigned long *sys_call_table; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + if (start->name && !strcmp(start->name, str)) + return start; + } + return NULL; +} + +struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +void arch_init_ftrace_syscalls(void) +{ + int i; + struct syscall_metadata *meta; + unsigned long **psys_syscall_table = &sys_call_table; + static atomic_t refs; + + if (atomic_inc_return(&refs) != 1) + goto end; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + FTRACE_SYSCALL_MAX, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } + + for (i = 0; i < FTRACE_SYSCALL_MAX; i++) { + meta = find_syscall_meta(psys_syscall_table[i]); + syscalls_metadata[i] = meta; + } + return; + + /* Paranoid: avoid overflow */ +end: + atomic_dec(&refs); +} +#endif -- cgit v1.2.3 From ccd50dfd92ea2c4ba9e39531ac55db53393e783e Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 17:02:17 +0100 Subject: tracing/syscalls: support for syscalls tracing on x86, fix Impact: build fix kernel/built-in.o: In function `ftrace_syscall_exit': (.text+0x76667): undefined reference to `syscall_nr_to_meta' ftrace.o is built: obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o But now a CONFIG_FTRACE_SYSCALLS dependency is needed too. Cc: Frederic Weisbecker Cc: Steven Rostedt Cc: Lai Jiangshan LKML-Reference: <1236401580-5758-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 339ce35648e6..84000eb931ff 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -66,7 +66,8 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o -- cgit v1.2.3 From e9d9df44736d116726f4596f7e2f9ce2764ffc0a Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 18 Mar 2009 16:42:57 +0800 Subject: ftrace: protect running nmi (V3) When I review the sensitive code ftrace_nmi_enter(), I found the atomic variable nmi_running does protect NMI VS do_ftrace_mod_code(), but it can not protects NMI(entered nmi) VS NMI(ftrace_nmi_enter()). cpu#1 | cpu#2 | cpu#3 ftrace_nmi_enter() | do_ftrace_mod_code() | not modify | | ------------------------|-----------------------|-- executing | set mod_code_write = 1| executing --|-----------------------|-------------------- executing | | ftrace_nmi_enter() executing | | do modify ------------------------|-----------------------|----------------- ftrace_nmi_exit() | | cpu#3 may be being modified the code which is still being executed on cpu#1, it will have undefined results and possibly take a GPF, this patch prevents it occurred. Signed-off-by: Lai Jiangshan LKML-Reference: <49C0B411.30003@cn.fujitsu.com> Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 63 ++++++++++++++++++++++++++++++------------------ 1 file changed, 40 insertions(+), 23 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 1d0d7f42efe3..57b33edb7ce3 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -79,11 +79,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * * 1) Put the instruction pointer into the IP buffer * and the new code into the "code" buffer. - * 2) Set a flag that says we are modifying code - * 3) Wait for any running NMIs to finish. - * 4) Write the code - * 5) clear the flag. - * 6) Wait for any running NMIs to finish. + * 2) Wait for any running NMIs to finish and set a flag that says + * we are modifying code, it is done in an atomic operation. + * 3) Write the code + * 4) clear the flag. + * 5) Wait for any running NMIs to finish. * * If an NMI is executed, the first thing it does is to call * "ftrace_nmi_enter". This will check if the flag is set to write @@ -95,9 +95,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * are the same as what exists. */ +#define MOD_CODE_WRITE_FLAG (1 << 31) /* set when NMI should do the write */ static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ -static int mod_code_write; /* set when NMI should do the write */ static void *mod_code_ip; /* holds the IP to write to */ static void *mod_code_newcode; /* holds the text to write to the IP */ @@ -114,6 +114,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size) return r; } +static void clear_mod_flag(void) +{ + int old = atomic_read(&nmi_running); + + for (;;) { + int new = old & ~MOD_CODE_WRITE_FLAG; + + if (old == new) + break; + + old = atomic_cmpxchg(&nmi_running, old, new); + } +} + static void ftrace_mod_code(void) { /* @@ -127,27 +141,39 @@ static void ftrace_mod_code(void) /* if we fail, then kill any new writers */ if (mod_code_status) - mod_code_write = 0; + clear_mod_flag(); } void ftrace_nmi_enter(void) { - atomic_inc(&nmi_running); - /* Must have nmi_running seen before reading write flag */ - smp_mb(); - if (mod_code_write) { + if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { + smp_rmb(); ftrace_mod_code(); atomic_inc(&nmi_update_count); } + /* Must have previous changes seen before executions */ + smp_mb(); } void ftrace_nmi_exit(void) { /* Finish all executions before clearing nmi_running */ - smp_wmb(); + smp_mb(); atomic_dec(&nmi_running); } +static void wait_for_nmi_and_set_mod_flag(void) +{ + if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)) + return; + + do { + cpu_relax(); + } while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)); + + nmi_wait_count++; +} + static void wait_for_nmi(void) { if (!atomic_read(&nmi_running)) @@ -167,14 +193,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) mod_code_newcode = new_code; /* The buffers need to be visible before we let NMIs write them */ - smp_wmb(); - - mod_code_write = 1; - - /* Make sure write bit is visible before we wait on NMIs */ smp_mb(); - wait_for_nmi(); + wait_for_nmi_and_set_mod_flag(); /* Make sure all running NMIs have finished before we write the code */ smp_mb(); @@ -182,13 +203,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) ftrace_mod_code(); /* Make sure the write happens before clearing the bit */ - smp_wmb(); - - mod_code_write = 0; - - /* make sure NMIs see the cleared bit */ smp_mb(); + clear_mod_flag(); wait_for_nmi(); return mod_code_status; -- cgit v1.2.3 From 5d1a03dc541dc6672e60e57249ed22f40654ca47 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 23 Mar 2009 23:38:49 -0400 Subject: function-graph: moved the timestamp from arch to generic code This patch move the timestamp from happening in the arch specific code into the general code. This allows for better control by the tracer to time manipulation. Signed-off-by: Steven Rostedt --- arch/x86/kernel/ftrace.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 57b33edb7ce3..61df77532120 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -410,7 +410,6 @@ int ftrace_disable_ftrace_graph_caller(void) void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - unsigned long long calltime; int faulted; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) @@ -453,10 +452,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - calltime = trace_clock_local(); - - if (ftrace_push_return_trace(old, calltime, - self_addr, &trace.depth) == -EBUSY) { + if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) { *parent = old; return; } -- cgit v1.2.3 From fee039a1d05c6e0f71b0fe270d847742a02d56c4 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 23 Mar 2009 10:14:52 -0400 Subject: x86: kretprobe-booster interrupt emulation code fix Fix interrupt emulation code in kretprobe-booster according to pt_regs update (es/ds change and gs adding). This issue has been reported on systemtap-bugzilla: http://sources.redhat.com/bugzilla/show_bug.cgi?id=9965 | On a -tip kernel on x86_32, kretprobe_example (from samples) triggers the | following backtrace when its retprobing a class of functions that cause a | copy_from/to_user(). | | BUG: sleeping function called from invalid context at mm/memory.c:3196 | in_atomic(): 0, irqs_disabled(): 1, pid: 2286, name: cat Signed-off-by: Masami Hiramatsu Acked-by: Ananth N Mavinakayanahalli Tested-by: Bharata B Rao Cc: systemtap-ml LKML-Reference: <49C7995C.2010601@redhat.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 4558dd3918cf..759095d53a06 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void) #else " pushf\n" /* - * Skip cs, ip, orig_ax. + * Skip cs, ip, orig_ax and gs. * trampoline_handler() will plug in these values */ - " subl $12, %esp\n" + " subl $16, %esp\n" " pushl %fs\n" - " pushl %ds\n" " pushl %es\n" + " pushl %ds\n" " pushl %eax\n" " pushl %ebp\n" " pushl %edi\n" @@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " movl %esp, %eax\n" " call trampoline_handler\n" /* Move flags to cs */ - " movl 52(%esp), %edx\n" - " movl %edx, 48(%esp)\n" + " movl 56(%esp), %edx\n" + " movl %edx, 52(%esp)\n" /* Replace saved flags with true return address. */ - " movl %eax, 52(%esp)\n" + " movl %eax, 56(%esp)\n" " popl %ebx\n" " popl %ecx\n" " popl %edx\n" @@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " popl %edi\n" " popl %ebp\n" " popl %eax\n" - /* Skip ip, orig_ax, es, ds, fs */ - " addl $20, %esp\n" + /* Skip ds, es, fs, gs, orig_ax and ip */ + " addl $24, %esp\n" " popf\n" #endif " ret\n"); @@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) regs->cs = __KERNEL_CS; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; -- cgit v1.2.3