diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-04 11:50:00 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-04 11:50:00 -0700 |
| commit | b8c0aa46b3e86083721b57ed2eec6bd2c29ebfba (patch) | |
| tree | 45e349bf8a14aa99279d323fdc515e849fd349f3 | |
| parent | c7ed326fa7cafb83ced5a8b02517a61672fe9e90 (diff) | |
| parent | dc6f03f26f570104a2bb03f9d1deb588026d7c75 (diff) | |
| download | op-kernel-dev-b8c0aa46b3e86083721b57ed2eec6bd2c29ebfba.zip op-kernel-dev-b8c0aa46b3e86083721b57ed2eec6bd2c29ebfba.tar.gz | |
Merge tag 'trace-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing updates from Steven Rostedt:
"This pull request has a lot of work done. The main thing is the
changes to the ftrace function callback infrastructure. It's
introducing a way to allow different functions to call directly
different trampolines instead of all calling the same "mcount" one.
The only user of this for now is the function graph tracer, which
always had a different trampoline, but the function tracer trampoline
was called and did basically nothing, and then the function graph
tracer trampoline was called. The difference now, is that the
function graph tracer trampoline can be called directly if a function
is only being traced by the function graph trampoline. If function
tracing is also happening on the same function, the old way is still
done.
The accounting for this takes up more memory when function graph
tracing is activated, as it needs to keep track of which functions it
uses. I have a new way that wont take as much memory, but it's not
ready yet for this merge window, and will have to wait for the next
one.
Another big change was the removal of the ftrace_start/stop() calls
that were used by the suspend/resume code that stopped function
tracing when entering into suspend and resume paths. The stop of
ftrace was done because there was some function that would crash the
system if one called smp_processor_id()! The stop/start was a big
hammer to solve the issue at the time, which was when ftrace was first
introduced into Linux. Now ftrace has better infrastructure to debug
such issues, and I found the problem function and labeled it with
"notrace" and function tracing can now safely be activated all the way
down into the guts of suspend and resume
Other changes include clean ups of uprobe code, clean up of the
trace_seq() code, and other various small fixes and clean ups to
ftrace and tracing"
* tag 'trace-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (57 commits)
ftrace: Add warning if tramp hash does not match nr_trampolines
ftrace: Fix trampoline hash update check on rec->flags
ring-buffer: Use rb_page_size() instead of open coded head_page size
ftrace: Rename ftrace_ops field from trampolines to nr_trampolines
tracing: Convert local function_graph functions to static
ftrace: Do not copy old hash when resetting
tracing: let user specify tracing_thresh after selecting function_graph
ring-buffer: Always run per-cpu ring buffer resize with schedule_work_on()
tracing: Remove function_trace_stop and HAVE_FUNCTION_TRACE_MCOUNT_TEST
s390/ftrace: remove check of obsolete variable function_trace_stop
arm64, ftrace: Remove check of obsolete variable function_trace_stop
Blackfin: ftrace: Remove check of obsolete variable function_trace_stop
metag: ftrace: Remove check of obsolete variable function_trace_stop
microblaze: ftrace: Remove check of obsolete variable function_trace_stop
MIPS: ftrace: Remove check of obsolete variable function_trace_stop
parisc: ftrace: Remove check of obsolete variable function_trace_stop
sh: ftrace: Remove check of obsolete variable function_trace_stop
sparc64,ftrace: Remove check of obsolete variable function_trace_stop
tile: ftrace: Remove check of obsolete variable function_trace_stop
ftrace: x86: Remove check of obsolete variable function_trace_stop
...
50 files changed, 1032 insertions, 693 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index b7fa2f5..45fbea7 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1097,6 +1097,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. that can be changed at run time by the set_graph_function file in the debugfs tracing directory. + ftrace_graph_notrace=[function-list] + [FTRACE] Do not trace from the functions specified in + function-list. This list is a comma separated list of + functions that can be changed at run time by the + set_graph_notrace file in the debugfs tracing directory. + gamecon.map[2|3]= [HW,JOY] Multisystem joystick and NES/SNES/PSX pad support via parallel port (up to 5 devices per port) diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt index 3f669b9..dd5f916 100644 --- a/Documentation/trace/ftrace-design.txt +++ b/Documentation/trace/ftrace-design.txt @@ -102,30 +102,6 @@ extern void mcount(void); EXPORT_SYMBOL(mcount); -HAVE_FUNCTION_TRACE_MCOUNT_TEST -------------------------------- - -This is an optional optimization for the normal case when tracing is turned off -in the system. If you do not enable this Kconfig option, the common ftrace -code will take care of doing the checking for you. - -To support this feature, you only need to check the function_trace_stop -variable in the mcount function. If it is non-zero, there is no tracing to be -done at all, so you can return. - -This additional pseudo code would simply be: -void mcount(void) -{ - /* save any bare state needed in order to do initial checking */ - -+ if (function_trace_stop) -+ return; - - extern void (*ftrace_trace_function)(unsigned long, unsigned long); - if (ftrace_trace_function != ftrace_stub) -... - - HAVE_FUNCTION_GRAPH_TRACER -------------------------- @@ -328,8 +304,6 @@ void mcount(void) void ftrace_caller(void) { - /* implement HAVE_FUNCTION_TRACE_MCOUNT_TEST if you desire */ - /* save all state needed by the ABI (see paragraph above) */ unsigned long frompc = ...; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index aa5f9fc..38e704e 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -96,11 +96,6 @@ * - ftrace_graph_caller to set up an exit hook */ ENTRY(_mcount) -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - ldr x0, =ftrace_trace_stop - ldr x0, [x0] // if ftrace_trace_stop - ret // return; -#endif mcount_enter ldr x0, =ftrace_trace_function diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig index f81e7b9..ed30699 100644 --- a/arch/blackfin/Kconfig +++ b/arch/blackfin/Kconfig @@ -18,7 +18,6 @@ config BLACKFIN select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_IDE select HAVE_KERNEL_GZIP if RAMKERNEL select HAVE_KERNEL_BZIP2 if RAMKERNEL diff --git a/arch/blackfin/kernel/ftrace-entry.S b/arch/blackfin/kernel/ftrace-entry.S index 7eed00b..28d0595 100644 --- a/arch/blackfin/kernel/ftrace-entry.S +++ b/arch/blackfin/kernel/ftrace-entry.S @@ -33,15 +33,6 @@ ENDPROC(__mcount) * function will be waiting there. mmmm pie. */ ENTRY(_ftrace_caller) -# ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* optional micro optimization: return if stopped */ - p1.l = _function_trace_stop; - p1.h = _function_trace_stop; - r3 = [p1]; - cc = r3 == 0; - if ! cc jump _ftrace_stub (bp); -# endif - /* save first/second/third function arg and the return register */ [--sp] = r2; [--sp] = r0; @@ -83,15 +74,6 @@ ENDPROC(_ftrace_caller) /* See documentation for _ftrace_caller */ ENTRY(__mcount) -# ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* optional micro optimization: return if stopped */ - p1.l = _function_trace_stop; - p1.h = _function_trace_stop; - r3 = [p1]; - cc = r3 == 0; - if ! cc jump _ftrace_stub (bp); -# endif - /* save third function arg early so we can do testing below */ [--sp] = r2; diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index 499b761..0b389a8 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -13,7 +13,6 @@ config METAG select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZO diff --git a/arch/metag/kernel/ftrace_stub.S b/arch/metag/kernel/ftrace_stub.S index e70bff7..3acc288 100644 --- a/arch/metag/kernel/ftrace_stub.S +++ b/arch/metag/kernel/ftrace_stub.S @@ -16,13 +16,6 @@ _mcount_wrapper: .global _ftrace_caller .type _ftrace_caller,function _ftrace_caller: - MOVT D0Re0,#HI(_function_trace_stop) - ADD D0Re0,D0Re0,#LO(_function_trace_stop) - GETD D0Re0,[D0Re0] - CMP D0Re0,#0 - BEQ $Lcall_stub - MOV PC,D0.4 -$Lcall_stub: MSETL [A0StP], D0Ar6, D0Ar4, D0Ar2, D0.4 MOV D1Ar1, D0.4 MOV D0Ar2, D1RtP @@ -42,13 +35,6 @@ _ftrace_call: .global _mcount_wrapper .type _mcount_wrapper,function _mcount_wrapper: - MOVT D0Re0,#HI(_function_trace_stop) - ADD D0Re0,D0Re0,#LO(_function_trace_stop) - GETD D0Re0,[D0Re0] - CMP D0Re0,#0 - BEQ $Lcall_mcount - MOV PC,D0.4 -$Lcall_mcount: MSETL [A0StP], D0Ar6, D0Ar4, D0Ar2, D0.4 MOV D1Ar1, D0.4 MOV D0Ar2, D1RtP diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 9ae0854..40e1c1d 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -22,7 +22,6 @@ config MICROBLAZE select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FUNCTION_TRACER select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c index bbcd253..fc7b48a 100644 --- a/arch/microblaze/kernel/ftrace.c +++ b/arch/microblaze/kernel/ftrace.c @@ -27,6 +27,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) unsigned long return_hooker = (unsigned long) &return_to_handler; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/microblaze/kernel/mcount.S b/arch/microblaze/kernel/mcount.S index fc1e132..fed9da5 100644 --- a/arch/microblaze/kernel/mcount.S +++ b/arch/microblaze/kernel/mcount.S @@ -91,11 +91,6 @@ ENTRY(ftrace_caller) #endif /* CONFIG_DYNAMIC_FTRACE */ SAVE_REGS swi r15, r1, 0; - /* MS: HAVE_FUNCTION_TRACE_MCOUNT_TEST begin of checking */ - lwi r5, r0, function_trace_stop; - bneid r5, end; - nop; - /* MS: HAVE_FUNCTION_TRACE_MCOUNT_TEST end of checking */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER #ifndef CONFIG_DYNAMIC_FTRACE lwi r5, r0, ftrace_graph_return; diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 4e238e6..10f270b 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -15,7 +15,6 @@ config MIPS select HAVE_BPF_JIT if !CPU_MICROMIPS select ARCH_HAVE_CUSTOM_GPIO_H select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_C_RECORDMCOUNT diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 60e7e5e..8b65387 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -302,6 +302,9 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, &return_to_handler; int faulted, insns; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S index 539b629..00940d1 100644 --- a/arch/mips/kernel/mcount.S +++ b/arch/mips/kernel/mcount.S @@ -74,10 +74,6 @@ _mcount: #endif /* When tracing is activated, it calls ftrace_caller+8 (aka here) */ - lw t1, function_trace_stop - bnez t1, ftrace_stub - nop - MCOUNT_SAVE_REGS #ifdef KBUILD_MCOUNT_RA_ADDRESS PTR_S MCOUNT_RA_ADDRESS_REG, PT_R12(sp) @@ -105,9 +101,6 @@ ftrace_stub: #else /* ! CONFIG_DYNAMIC_FTRACE */ NESTED(_mcount, PT_SIZE, ra) - lw t1, function_trace_stop - bnez t1, ftrace_stub - nop PTR_LA t1, ftrace_stub PTR_L t2, ftrace_trace_function /* Prepare t2 for (1) */ bne t1, t2, static_trace diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 108d48e..6e75e20 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -6,7 +6,6 @@ config PARISC select HAVE_OPROFILE select HAVE_FUNCTION_TRACER if 64BIT select HAVE_FUNCTION_GRAPH_TRACER if 64BIT - select HAVE_FUNCTION_TRACE_MCOUNT_TEST if 64BIT select ARCH_WANT_FRAME_POINTERS select RTC_CLASS select RTC_DRV_GENERIC diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 5beb97b..559d400 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -112,6 +112,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) unsigned long long calltime; struct ftrace_graph_ent trace; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; @@ -152,9 +155,6 @@ void ftrace_function_trampoline(unsigned long parent, { extern ftrace_func_t ftrace_trace_function; - if (function_trace_stop) - return; - if (ftrace_trace_function != ftrace_stub) { ftrace_trace_function(parent, self_addr); return; diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index d178834..390311c 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -525,6 +525,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long)&return_to_handler; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index bb63499..f5af5f6 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -116,7 +116,6 @@ config S390 select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 08dcf21..433c6db 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -21,13 +21,9 @@ ENTRY(_mcount) ENTRY(ftrace_caller) #endif stm %r2,%r5,16(%r15) - bras %r1,2f + bras %r1,1f 0: .long ftrace_trace_function -1: .long function_trace_stop -2: l %r2,1b-0b(%r1) - icm %r2,0xf,0(%r2) - jnz 3f - st %r14,56(%r15) +1: st %r14,56(%r15) lr %r0,%r15 ahi %r15,-96 l %r3,100(%r15) @@ -50,7 +46,7 @@ ENTRY(ftrace_graph_caller) #endif ahi %r15,96 l %r14,56(%r15) -3: lm %r2,%r5,16(%r15) + lm %r2,%r5,16(%r15) br %r14 #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/s390/kernel/mcount64.S b/arch/s390/kernel/mcount64.S index 1c52eae..c67a8bf 100644 --- a/arch/s390/kernel/mcount64.S +++ b/arch/s390/kernel/mcount64.S @@ -20,9 +20,6 @@ ENTRY(_mcount) ENTRY(ftrace_caller) #endif - larl %r1,function_trace_stop - icm %r1,0xf,0(%r1) - bnzr %r14 stmg %r2,%r5,32(%r15) stg %r14,112(%r15) lgr %r1,%r15 diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 834b67c..aa2df3e 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -57,7 +57,6 @@ config SUPERH32 select HAVE_FUNCTION_TRACER select HAVE_FTRACE_MCOUNT_RECORD select HAVE_DYNAMIC_FTRACE - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE select ARCH_WANT_IPC_PARSE_VERSION select HAVE_FUNCTION_GRAPH_TRACER diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 3c74f53..079d70e 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -344,6 +344,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long)&return_to_handler; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/sh/lib/mcount.S b/arch/sh/lib/mcount.S index 52aa201..7a8572f 100644 --- a/arch/sh/lib/mcount.S +++ b/arch/sh/lib/mcount.S @@ -92,13 +92,6 @@ mcount: rts nop #else -#ifndef CONFIG_DYNAMIC_FTRACE - mov.l .Lfunction_trace_stop, r0 - mov.l @r0, r0 - tst r0, r0 - bf ftrace_stub -#endif - MCOUNT_ENTER() #ifdef CONFIG_DYNAMIC_FTRACE @@ -174,11 +167,6 @@ ftrace_graph_call: .globl ftrace_caller ftrace_caller: - mov.l .Lfunction_trace_stop, r0 - mov.l @r0, r0 - tst r0, r0 - bf ftrace_stub - MCOUNT_ENTER() .globl ftrace_call @@ -196,8 +184,6 @@ ftrace_call: #endif /* CONFIG_DYNAMIC_FTRACE */ .align 2 -.Lfunction_trace_stop: - .long function_trace_stop /* * NOTE: From here on the locations of the .Lftrace_stub label and @@ -217,12 +203,7 @@ ftrace_stub: #ifdef CONFIG_FUNCTION_GRAPH_TRACER .globl ftrace_graph_caller ftrace_graph_caller: - mov.l 2f, r0 - mov.l @r0, r0 - tst r0, r0 - bt 1f - - mov.l 3f, r1 + mov.l 2f, r1 jmp @r1 nop 1: @@ -242,8 +223,7 @@ ftrace_graph_caller: MCOUNT_LEAVE() .align 2 -2: .long function_trace_stop -3: .long skip_trace +2: .long skip_trace .Lprepare_ftrace_return: .long prepare_ftrace_return diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 407c87d..4692c90 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -55,7 +55,6 @@ config SPARC64 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_FP_TEST - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KRETPROBES select HAVE_KPROBES select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/sparc/lib/mcount.S b/arch/sparc/lib/mcount.S index 3ad6cbd..0b0ed4d 100644 --- a/arch/sparc/lib/mcount.S +++ b/arch/sparc/lib/mcount.S @@ -24,10 +24,7 @@ mcount: #ifdef CONFIG_DYNAMIC_FTRACE /* Do nothing, the retl/nop below is all we need. */ #else - sethi %hi(function_trace_stop), %g1 - lduw [%g1 + %lo(function_trace_stop)], %g2 - brnz,pn %g2, 2f - sethi %hi(ftrace_trace_function), %g1 + sethi %hi(ftrace_trace_function), %g1 sethi %hi(ftrace_stub), %g2 ldx [%g1 + %lo(ftrace_trace_function)], %g1 or %g2, %lo(ftrace_stub), %g2 @@ -80,11 +77,8 @@ ftrace_stub: .globl ftrace_caller .type ftrace_caller,#function ftrace_caller: - sethi %hi(function_trace_stop), %g1 mov %i7, %g2 - lduw [%g1 + %lo(function_trace_stop)], %g1 - brnz,pn %g1, ftrace_stub - mov %fp, %g3 + mov %fp, %g3 save %sp, -176, %sp mov %g2, %o1 mov %g2, %l0 diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 4f3006b..7fcd492 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -128,7 +128,6 @@ config TILEGX select SPARSE_IRQ select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_FUNCTION_GRAPH_TRACER select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/tile/kernel/mcount_64.S b/arch/tile/kernel/mcount_64.S index 70d7bb0..3c2b8d5 100644 --- a/arch/tile/kernel/mcount_64.S +++ b/arch/tile/kernel/mcount_64.S @@ -77,15 +77,6 @@ STD_ENDPROC(__mcount) .align 64 STD_ENTRY(ftrace_caller) - moveli r11, hw2_last(function_trace_stop) - { shl16insli r11, r11, hw1(function_trace_stop); move r12, lr } - { shl16insli r11, r11, hw0(function_trace_stop); move lr, r10 } - ld r11, r11 - beqz r11, 1f - jrp r12 - -1: - { move r10, lr; move lr, r12 } MCOUNT_SAVE_REGS /* arg1: self return address */ @@ -119,15 +110,6 @@ STD_ENDPROC(ftrace_caller) .align 64 STD_ENTRY(__mcount) - moveli r11, hw2_last(function_trace_stop) - { shl16insli r11, r11, hw1(function_trace_stop); move r12, lr } - { shl16insli r11, r11, hw0(function_trace_stop); move lr, r10 } - ld r11, r11 - beqz r11, 1f - jrp r12 - -1: - { move r10, lr; move lr, r12 } { moveli r11, hw2_last(ftrace_trace_function) moveli r13, hw2_last(ftrace_stub) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d24887b..2840c27 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -54,7 +54,6 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_FP_TEST - select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_SYSCALL_TRACEPOINTS select SYSCTL_EXCEPTION_TRACE select HAVE_KVM diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 0525a8b..e1f7fec 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -68,6 +68,8 @@ struct dyn_arch_ftrace { int ftrace_int3_handler(struct pt_regs *regs); +#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR + #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 0d0c9d4..47c410d 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1059,9 +1059,6 @@ ENTRY(mcount) END(mcount) ENTRY(ftrace_caller) - cmpl $0, function_trace_stop - jne ftrace_stub - pushl %eax pushl %ecx pushl %edx @@ -1093,8 +1090,6 @@ END(ftrace_caller) ENTRY(ftrace_regs_caller) pushf /* push flags before compare (in cs location) */ - cmpl $0, function_trace_stop - jne ftrace_restore_flags /* * i386 does not save SS and ESP when coming from kernel. @@ -1153,7 +1148,6 @@ GLOBAL(ftrace_regs_call) popf /* Pop flags at end (no addl to corrupt flags) */ jmp ftrace_ret -ftrace_restore_flags: popf jmp ftrace_stub #else /* ! CONFIG_DYNAMIC_FTRACE */ @@ -1162,9 +1156,6 @@ ENTRY(mcount) cmpl $__PAGE_OFFSET, %esp jb ftrace_stub /* Paging not enabled yet? */ - cmpl $0, function_trace_stop - jne ftrace_stub - cmpl $ftrace_stub, ftrace_trace_function jnz trace #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cbc4a91..3386dc9 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -703,6 +703,9 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long return_hooker = (unsigned long) &return_to_handler; + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index c050a01..c73aecf 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -46,10 +46,6 @@ END(function_hook) .endm ENTRY(ftrace_caller) - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_stub - ftrace_caller_setup /* regs go into 4th parameter (but make it NULL) */ movq $0, %rcx @@ -73,10 +69,6 @@ ENTRY(ftrace_regs_caller) /* Save the current flags before compare (in SS location)*/ pushfq - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_restore_flags - /* skip=8 to skip flags saved in SS */ ftrace_caller_setup 8 @@ -131,7 +123,7 @@ GLOBAL(ftrace_regs_call) popfq jmp ftrace_return -ftrace_restore_flags: + popfq jmp ftrace_stub @@ -141,9 +133,6 @@ END(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(function_hook) - cmpl $0, function_trace_stop - jne ftrace_stub - cmpq $ftrace_stub, ftrace_trace_function jnz trace diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 9d2e0ff..2e5652b 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -22,7 +22,7 @@ __entry->unsync = sp->unsync; #define KVM_MMU_PAGE_PRINTK() ({ \ - const char *ret = p->buffer + p->len; \ + const char *ret = trace_seq_buffer_ptr(p); \ static const char *access_str[] = { \ "---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" \ }; \ diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 424f4c9..6ec7910 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -165,7 +165,7 @@ static void fix_processor_context(void) * by __save_processor_state() * @ctxt - structure to load the registers contents from */ -static void __restore_processor_state(struct saved_context *ctxt) +static void notrace __restore_processor_state(struct saved_context *ctxt) { if (ctxt->misc_enable_saved) wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); @@ -239,7 +239,7 @@ static void __restore_processor_state(struct saved_context *ctxt) } /* Needed by apm.c */ -void restore_processor_state(void) +void notrace restore_processor_state(void) { __restore_processor_state(&saved_context); } diff --git a/drivers/scsi/scsi_trace.c b/drivers/scsi/scsi_trace.c index 2bea4f0..503594e 100644 --- a/drivers/scsi/scsi_trace.c +++ b/drivers/scsi/scsi_trace.c @@ -28,7 +28,7 @@ scsi_trace_misc(struct trace_seq *, unsigned char *, int); static const char * scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); sector_t lba = 0, txlen = 0; lba |= ((cdb[1] & 0x1F) << 16); @@ -46,7 +46,7 @@ scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len) static const char * scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); sector_t lba = 0, txlen = 0; lba |= (cdb[2] << 24); @@ -71,7 +71,7 @@ scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len) static const char * scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); sector_t lba = 0, txlen = 0; lba |= (cdb[2] << 24); @@ -94,7 +94,7 @@ scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len) static const char * scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); sector_t lba = 0, txlen = 0; lba |= ((u64)cdb[2] << 56); @@ -125,7 +125,7 @@ scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len) static const char * scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len, *cmd; + const char *ret = trace_seq_buffer_ptr(p), *cmd; sector_t lba = 0, txlen = 0; u32 ei_lbrt = 0; @@ -180,7 +180,7 @@ out: static const char * scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); unsigned int regions = cdb[7] << 8 | cdb[8]; trace_seq_printf(p, "regions=%u", (regions - 8) / 16); @@ -192,7 +192,7 @@ scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len) static const char * scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len, *cmd; + const char *ret = trace_seq_buffer_ptr(p), *cmd; sector_t lba = 0; u32 alloc_len = 0; @@ -247,7 +247,7 @@ scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len) static const char * scsi_trace_misc(struct trace_seq *p, unsigned char *cdb, int len) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); trace_seq_printf(p, "-"); trace_seq_putc(p, 0); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 404a686..6bb5e3f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -33,8 +33,7 @@ * features, then it must call an indirect function that * does. Or at least does enough to prevent any unwelcomed side effects. */ -#if !defined(CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST) || \ - !ARCH_SUPPORTS_FTRACE_OPS +#if !ARCH_SUPPORTS_FTRACE_OPS # define FTRACE_FORCE_LIST_FUNC 1 #else # define FTRACE_FORCE_LIST_FUNC 0 @@ -118,17 +117,18 @@ struct ftrace_ops { ftrace_func_t func; struct ftrace_ops *next; unsigned long flags; - int __percpu *disabled; void *private; + int __percpu *disabled; #ifdef CONFIG_DYNAMIC_FTRACE + int nr_trampolines; struct ftrace_hash *notrace_hash; struct ftrace_hash *filter_hash; + struct ftrace_hash *tramp_hash; struct mutex regex_lock; + unsigned long trampoline; #endif }; -extern int function_trace_stop; - /* * Type of the current tracing. */ @@ -140,32 +140,6 @@ enum ftrace_tracing_type_t { /* Current tracing type, default is FTRACE_TYPE_ENTER */ extern enum ftrace_tracing_type_t ftrace_tracing_type; -/** - * ftrace_stop - stop function tracer. - * - * A quick way to stop the function tracer. Note this an on off switch, - * it is not something that is recursive like preempt_disable. - * This does not disable the calling of mcount, it only stops the - * calling of functions from mcount. - */ -static inline void ftrace_stop(void) -{ - function_trace_stop = 1; -} - -/** - * ftrace_start - start the function tracer. - * - * This function is the inverse of ftrace_stop. This does not enable - * the function tracing if the function tracer is disabled. This only - * sets the function tracer flag to continue calling the functions - * from mcount. - */ -static inline void ftrace_start(void) -{ - function_trace_stop = 0; -} - /* * The ftrace_ops must be a static and should also * be read_mostly. These functions do modify read_mostly variables @@ -242,8 +216,6 @@ static inline int ftrace_nr_registered_ops(void) } static inline void clear_ftrace_function(void) { } static inline void ftrace_kill(void) { } -static inline void ftrace_stop(void) { } -static inline void ftrace_start(void) { } #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_STACK_TRACER @@ -317,13 +289,20 @@ extern int ftrace_nr_registered_ops(void); * from tracing that function. */ enum { - FTRACE_FL_ENABLED = (1UL << 29), + FTRACE_FL_ENABLED = (1UL << 31), FTRACE_FL_REGS = (1UL << 30), - FTRACE_FL_REGS_EN = (1UL << 31) + FTRACE_FL_REGS_EN = (1UL << 29), + FTRACE_FL_TRAMP = (1UL << 28), + FTRACE_FL_TRAMP_EN = (1UL << 27), }; -#define FTRACE_FL_MASK (0x7UL << 29) -#define FTRACE_REF_MAX ((1UL << 29) - 1) +#define FTRACE_REF_MAX_SHIFT 27 +#define FTRACE_FL_BITS 5 +#define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1) +#define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT) +#define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) + +#define ftrace_rec_count(rec) ((rec)->flags & ~FTRACE_FL_MASK) struct dyn_ftrace { unsigned long ip; /* address of mcount call-site */ @@ -431,6 +410,10 @@ void ftrace_modify_all_code(int command); #define FTRACE_ADDR ((unsigned long)ftrace_caller) #endif +#ifndef FTRACE_GRAPH_ADDR +#define FTRACE_GRAPH_ADDR ((unsigned long)ftrace_graph_caller) +#endif + #ifndef FTRACE_REGS_ADDR #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS # define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller) @@ -439,6 +422,16 @@ void ftrace_modify_all_code(int command); #endif #endif +/* + * If an arch would like functions that are only traced + * by the function graph tracer to jump directly to its own + * trampoline, then they can define FTRACE_GRAPH_TRAMP_ADDR + * to be that address to jump to. + */ +#ifndef FTRACE_GRAPH_TRAMP_ADDR +#define FTRACE_GRAPH_TRAMP_ADDR ((unsigned long) 0) +#endif + #ifdef CONFIG_FUNCTION_GRAPH_TRACER extern void ftrace_graph_caller(void); extern int ftrace_enable_ftrace_graph_caller(void); @@ -736,6 +729,7 @@ extern char __irqentry_text_end[]; extern int register_ftrace_graph(trace_func_graph_ret_t retfunc, trace_func_graph_ent_t entryfunc); +extern bool ftrace_graph_is_dead(void); extern void ftrace_graph_stop(void); /* The current handlers in use */ diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 1361169..ea6c9de 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -25,6 +25,21 @@ trace_seq_init(struct trace_seq *s) s->full = 0; } +/** + * trace_seq_buffer_ptr - return pointer to next location in buffer + * @s: trace sequence descriptor + * + * Returns the pointer to the buffer where the next write to + * the buffer will happen. This is useful to save the location + * that is about to be written to and then return the result + * of that write. + */ +static inline unsigned char * +trace_seq_buffer_ptr(struct trace_seq *s) +{ + return s->buffer + s->len; +} + /* * Currently only defined when tracing is enabled. */ @@ -36,14 +51,13 @@ int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args); extern int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary); extern int trace_print_seq(struct seq_file *m, struct trace_seq *s); -extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, - size_t cnt); +extern int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, + int cnt); extern int trace_seq_puts(struct trace_seq *s, const char *str); extern int trace_seq_putc(struct trace_seq *s, unsigned char c); -extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len); +extern int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len); extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, - size_t len); -extern void *trace_seq_reserve(struct trace_seq *s, size_t len); + unsigned int len); extern int trace_seq_path(struct trace_seq *s, const struct path *path); extern int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, @@ -71,8 +85,8 @@ static inline int trace_print_seq(struct seq_file *m, struct trace_seq *s) { return 0; } -static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, - size_t cnt) +static inline int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, + int cnt) { return 0; } @@ -85,19 +99,15 @@ static inline int trace_seq_putc(struct trace_seq *s, unsigned char c) return 0; } static inline int -trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len) +trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len) { return 0; } static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, - size_t len) + unsigned int len) { return 0; } -static inline void *trace_seq_reserve(struct trace_seq *s, size_t len) -{ - return NULL; -} static inline int trace_seq_path(struct trace_seq *s, const struct path *path) { return 0; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index fcc2611..a9dfa79 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -371,7 +371,6 @@ int hibernation_snapshot(int platform_mode) } suspend_console(); - ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); @@ -397,7 +396,6 @@ int hibernation_snapshot(int platform_mode) if (error || !in_suspend) pm_restore_gfp_mask(); - ftrace_start(); resume_console(); dpm_complete(msg); @@ -500,7 +498,6 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); - ftrace_stop(); pm_restrict_gfp_mask(); error = dpm_suspend_start(PMSG_QUIESCE); if (!error) { @@ -508,7 +505,6 @@ int hibernation_restore(int platform_mode) dpm_resume_end(PMSG_RECOVER); } pm_restore_gfp_mask(); - ftrace_start(); resume_console(); pm_restore_console(); return error; @@ -535,7 +531,6 @@ int hibernation_platform_enter(void) entering_platform_hibernation = true; suspend_console(); - ftrace_stop(); error = dpm_suspend_start(PMSG_HIBERNATE); if (error) { if (hibernation_ops->recover) @@ -579,7 +574,6 @@ int hibernation_platform_enter(void) Resume_devices: entering_platform_hibernation = false; dpm_resume_end(PMSG_RESTORE); - ftrace_start(); resume_console(); Close: diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index ed35a47..4b736b4 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -248,7 +248,6 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) goto Platform_wake; } - ftrace_stop(); error = disable_nonboot_cpus(); if (error || suspend_test(TEST_CPUS)) goto Enable_cpus; @@ -275,7 +274,6 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) Enable_cpus: enable_nonboot_cpus(); - ftrace_start(); Platform_wake: if (need_suspend_ops(state) && suspend_ops->wake) diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d440935..a5da09c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -29,11 +29,6 @@ config HAVE_FUNCTION_GRAPH_FP_TEST help See Documentation/trace/ftrace-design.txt -config HAVE_FUNCTION_TRACE_MCOUNT_TEST - bool - help - See Documentation/trace/ftrace-design.txt - config HAVE_DYNAMIC_FTRACE bool help diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 2611613..67d6369 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_RING_BUFFER_BENCHMARK) += ring_buffer_benchmark.o obj-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_TRACING) += trace_output.o +obj-$(CONFIG_TRACING) += trace_seq.o obj-$(CONFIG_TRACING) += trace_stat.o obj-$(CONFIG_TRACING) += trace_printk.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ac9d1da..1654b12 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -80,9 +80,6 @@ static struct ftrace_ops ftrace_list_end __read_mostly = { int ftrace_enabled __read_mostly; static int last_ftrace_enabled; -/* Quick disabling of function tracer. */ -int function_trace_stop __read_mostly; - /* Current function tracing op */ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* What to set function_trace_op to */ @@ -1042,6 +1039,8 @@ static struct pid * const ftrace_swapper_pid = &init_struct_pid; #ifdef CONFIG_DYNAMIC_FTRACE +static struct ftrace_ops *removed_ops; + #ifndef CONFIG_FTRACE_MCOUNT_RECORD # error Dynamic ftrace depends on MCOUNT_RECORD #endif @@ -1304,25 +1303,15 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, struct ftrace_hash *new_hash; int size = src->count; int bits = 0; - int ret; int i; /* - * Remove the current set, update the hash and add - * them back. - */ - ftrace_hash_rec_disable(ops, enable); - - /* * If the new source is empty, just free dst and assign it * the empty_hash. */ if (!src->count) { - free_ftrace_hash_rcu(*dst); - rcu_assign_pointer(*dst, EMPTY_HASH); - /* still need to update the function records */ - ret = 0; - goto out; + new_hash = EMPTY_HASH; + goto update; } /* @@ -1335,10 +1324,9 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, if (bits > FTRACE_HASH_MAX_BITS) bits = FTRACE_HASH_MAX_BITS; - ret = -ENOMEM; new_hash = alloc_ftrace_hash(bits); if (!new_hash) - goto out; + return -ENOMEM; size = 1 << src->size_bits; for (i = 0; i < size; i++) { @@ -1349,20 +1337,20 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable, } } +update: + /* + * Remove the current set, update the hash and add + * them back. + */ + ftrace_hash_rec_disable(ops, enable); + old_hash = *dst; rcu_assign_pointer(*dst, new_hash); free_ftrace_hash_rcu(old_hash); - ret = 0; - out: - /* - * Enable regardless of ret: - * On success, we enable the new hash. - * On failure, we re-enable the original hash. - */ ftrace_hash_rec_enable(ops, enable); - return ret; + return 0; } /* @@ -1492,6 +1480,53 @@ int ftrace_text_reserved(const void *start, const void *end) return (int)!!ret; } +/* Test if ops registered to this rec needs regs */ +static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) +{ + struct ftrace_ops *ops; + bool keep_regs = false; + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) { + /* pass rec in as regs to have non-NULL val */ + if (ftrace_ops_test(ops, rec->ip, rec)) { + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + keep_regs = true; + break; + } + } + } + + return keep_regs; +} + +static void ftrace_remove_tramp(struct ftrace_ops *ops, + struct dyn_ftrace *rec) +{ + struct ftrace_func_entry *entry; + + entry = ftrace_lookup_ip(ops->tramp_hash, rec->ip); + if (!entry) + return; + + /* + * The tramp_hash entry will be removed at time + * of update. + */ + ops->nr_trampolines--; + rec->flags &= ~FTRACE_FL_TRAMP; +} + +static void ftrace_clear_tramps(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->nr_trampolines) + ftrace_remove_tramp(op, rec); + } while_for_each_ftrace_op(op); +} + static void __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1572,8 +1607,30 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (inc) { rec->flags++; - if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) + if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) return; + + /* + * If there's only a single callback registered to a + * function, and the ops has a trampoline registered + * for it, then we can call it directly. + */ + if (ftrace_rec_count(rec) == 1 && ops->trampoline) { + rec->flags |= FTRACE_FL_TRAMP; + ops->nr_trampolines++; + } else { + /* + * If we are adding another function callback + * to this function, and the previous had a + * trampoline used, then we need to go back to + * the default trampoline. + */ + rec->flags &= ~FTRACE_FL_TRAMP; + + /* remove trampolines from any ops for this rec */ + ftrace_clear_tramps(rec); + } + /* * If any ops wants regs saved for this function * then all ops will get saved regs. @@ -1581,9 +1638,30 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) rec->flags |= FTRACE_FL_REGS; } else { - if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) + if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0)) return; rec->flags--; + + if (ops->trampoline && !ftrace_rec_count(rec)) + ftrace_remove_tramp(ops, rec); + + /* + * If the rec had REGS enabled and the ops that is + * being removed had REGS set, then see if there is + * still any ops for this record that wants regs. + * If not, we can stop recording them. + */ + if (ftrace_rec_count(rec) > 0 && + rec->flags & FTRACE_FL_REGS && + ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + if (!test_rec_ops_needs_regs(rec)) + rec->flags &= ~FTRACE_FL_REGS; + } + + /* + * flags will be cleared in ftrace_check_record() + * if rec count is zero. + */ } count++; /* Shortcut, if we handled all records, we are done. */ @@ -1668,17 +1746,23 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) * If we are disabling calls, then disable all records that * are enabled. */ - if (enable && (rec->flags & ~FTRACE_FL_MASK)) + if (enable && ftrace_rec_count(rec)) flag = FTRACE_FL_ENABLED; /* - * If enabling and the REGS flag does not match the REGS_EN, then - * do not ignore this record. Set flags to fail the compare against - * ENABLED. + * If enabling and the REGS flag does not match the REGS_EN, or + * the TRAMP flag doesn't match the TRAMP_EN, then do not ignore + * this record. Set flags to fail the compare against ENABLED. */ - if (flag && - (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN))) - flag |= FTRACE_FL_REGS; + if (flag) { + if (!(rec->flags & FTRACE_FL_REGS) != + !(rec->flags & FTRACE_FL_REGS_EN)) + flag |= FTRACE_FL_REGS; + + if (!(rec->flags & FTRACE_FL_TRAMP) != + !(rec->flags & FTRACE_FL_TRAMP_EN)) + flag |= FTRACE_FL_TRAMP; + } /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) @@ -1696,6 +1780,12 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) else rec->flags &= ~FTRACE_FL_REGS_EN; } + if (flag & FTRACE_FL_TRAMP) { + if (rec->flags & FTRACE_FL_TRAMP) + rec->flags |= FTRACE_FL_TRAMP_EN; + else + rec->flags &= ~FTRACE_FL_TRAMP_EN; + } } /* @@ -1704,7 +1794,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) * Otherwise, * return UPDATE_MODIFY_CALL to tell the caller to convert * from the save regs, to a non-save regs function or - * vice versa. + * vice versa, or from a trampoline call. */ if (flag & FTRACE_FL_ENABLED) return FTRACE_UPDATE_MAKE_CALL; @@ -1714,7 +1804,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) if (update) { /* If there's no more users, clear all flags */ - if (!(rec->flags & ~FTRACE_FL_MASK)) + if (!ftrace_rec_count(rec)) rec->flags = 0; else /* Just disable the record (keep REGS state) */ @@ -1751,6 +1841,43 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) return ftrace_check_record(rec, enable, 0); } +static struct ftrace_ops * +ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + + /* Removed ops need to be tested first */ + if (removed_ops && removed_ops->tramp_hash) { + if (ftrace_lookup_ip(removed_ops->tramp_hash, rec->ip)) + return removed_ops; + } + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (!op->tramp_hash) + continue; + + if (ftrace_lookup_ip(op->tramp_hash, rec->ip)) + return op; + + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * +ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + /* pass rec in as regs to have non-NULL val */ + if (ftrace_ops_test(op, rec->ip, rec)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + /** * ftrace_get_addr_new - Get the call address to set to * @rec: The ftrace record descriptor @@ -1763,6 +1890,20 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) */ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) { + struct ftrace_ops *ops; + + /* Trampolines take precedence over regs */ + if (rec->flags & FTRACE_FL_TRAMP) { + ops = ftrace_find_tramp_ops_new(rec); + if (FTRACE_WARN_ON(!ops || !ops->trampoline)) { + pr_warning("Bad trampoline accounting at: %p (%pS)\n", + (void *)rec->ip, (void *)rec->ip); + /* Ftrace is shutting down, return anything */ + return (unsigned long)FTRACE_ADDR; + } + return ops->trampoline; + } + if (rec->flags & FTRACE_FL_REGS) return (unsigned long)FTRACE_REGS_ADDR; else @@ -1781,6 +1922,20 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) */ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) { + struct ftrace_ops *ops; + + /* Trampolines take precedence over regs */ + if (rec->flags & FTRACE_FL_TRAMP_EN) { + ops = ftrace_find_tramp_ops_curr(rec); + if (FTRACE_WARN_ON(!ops)) { + pr_warning("Bad trampoline accounting at: %p (%pS)\n", + (void *)rec->ip, (void *)rec->ip); + /* Ftrace is shutting down, return anything */ + return (unsigned long)FTRACE_ADDR; + } + return ops->trampoline; + } + if (rec->flags & FTRACE_FL_REGS_EN) return (unsigned long)FTRACE_REGS_ADDR; else @@ -2023,6 +2178,89 @@ void __weak arch_ftrace_update_code(int command) ftrace_run_stop_machine(command); } +static int ftrace_save_ops_tramp_hash(struct ftrace_ops *ops) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int size, bits; + int ret; + + size = ops->nr_trampolines; + bits = 0; + /* + * Make the hash size about 1/2 the # found + */ + for (size /= 2; size; size >>= 1) + bits++; + + ops->tramp_hash = alloc_ftrace_hash(bits); + /* + * TODO: a failed allocation is going to screw up + * the accounting of what needs to be modified + * and not. For now, we kill ftrace if we fail + * to allocate here. But there are ways around this, + * but that will take a little more work. + */ + if (!ops->tramp_hash) + return -ENOMEM; + + do_for_each_ftrace_rec(pg, rec) { + if (ftrace_rec_count(rec) == 1 && + ftrace_ops_test(ops, rec->ip, rec)) { + + /* + * If another ops adds to a rec, the rec will + * lose its trampoline and never get it back + * until all ops are off of it. + */ + if (!(rec->flags & FTRACE_FL_TRAMP)) + continue; + + /* This record had better have a trampoline */ + if (FTRACE_WARN_ON(!(rec->flags & FTRACE_FL_TRAMP_EN))) + return -1; + + ret = add_hash_entry(ops->tramp_hash, rec->ip); + if (ret < 0) + return ret; + } + } while_for_each_ftrace_rec(); + + /* The number of recs in the hash must match nr_trampolines */ + FTRACE_WARN_ON(ops->tramp_hash->count != ops->nr_trampolines); + + return 0; +} + +static int ftrace_save_tramp_hashes(void) +{ + struct ftrace_ops *op; + int ret; + + /* + * Now that any trampoline is being used, we need to save the + * hashes for the ops that have them. This allows the mapping + * back from the record to the ops that has the trampoline to + * know what code is being replaced. Modifying code must always + * verify what it is changing. + */ + do_for_each_ftrace_op(op, ftrace_ops_list) { + + /* The tramp_hash is recreated each time. */ + free_ftrace_hash(op->tramp_hash); + op->tramp_hash = NULL; + + if (op->nr_trampolines) { + ret = ftrace_save_ops_tramp_hash(op); + if (ret) + return ret; + } + + } while_for_each_ftrace_op(op); + + return 0; +} + static void ftrace_run_update_code(int command) { int ret; @@ -2031,11 +2269,6 @@ static void ftrace_run_update_code(int command) FTRACE_WARN_ON(ret); if (ret) return; - /* - * Do not call function tracer while we update the code. - * We are in stop machine. - */ - function_trace_stop++; /* * By default we use stop_machine() to modify the code. @@ -2045,15 +2278,15 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); - function_trace_stop--; - ret = ftrace_arch_code_modify_post_process(); FTRACE_WARN_ON(ret); + + ret = ftrace_save_tramp_hashes(); + FTRACE_WARN_ON(ret); } static ftrace_func_t saved_ftrace_func; static int ftrace_start_up; -static int global_start_up; static void control_ops_free(struct ftrace_ops *ops) { @@ -2117,8 +2350,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) ftrace_hash_rec_disable(ops, 1); - if (!global_start_up) - ops->flags &= ~FTRACE_OPS_FL_ENABLED; + ops->flags &= ~FTRACE_OPS_FL_ENABLED; command |= FTRACE_UPDATE_CALLS; @@ -2139,8 +2371,16 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) return 0; } + /* + * If the ops uses a trampoline, then it needs to be + * tested first on update. + */ + removed_ops = ops; + ftrace_run_update_code(command); + removed_ops = NULL; + /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. @@ -2398,7 +2638,8 @@ ftrace_allocate_pages(unsigned long num_to_init) return start_pg; free_pages: - while (start_pg) { + pg = start_pg; + while (pg) { order = get_count_order(pg->size / ENTRIES_PER_PAGE); free_pages((unsigned long)pg->records, order); start_pg = pg->next; @@ -2595,8 +2836,10 @@ static void *t_start(struct seq_file *m, loff_t *pos) * off, we can short cut and just print out that all * functions are enabled. */ - if (iter->flags & FTRACE_ITER_FILTER && - ftrace_hash_empty(ops->filter_hash)) { + if ((iter->flags & FTRACE_ITER_FILTER && + ftrace_hash_empty(ops->filter_hash)) || + (iter->flags & FTRACE_ITER_NOTRACE && + ftrace_hash_empty(ops->notrace_hash))) { if (*pos > 0) return t_hash_start(m, pos); iter->flags |= FTRACE_ITER_PRINTALL; @@ -2641,7 +2884,10 @@ static int t_show(struct seq_file *m, void *v) return t_hash_show(m, iter); if (iter->flags & FTRACE_ITER_PRINTALL) { - seq_printf(m, "#### all functions enabled ####\n"); + if (iter->flags & FTRACE_ITER_NOTRACE) + seq_printf(m, "#### no functions disabled ####\n"); + else + seq_printf(m, "#### all functions enabled ####\n"); return 0; } @@ -2651,10 +2897,22 @@ static int t_show(struct seq_file *m, void *v) return 0; seq_printf(m, "%ps", (void *)rec->ip); - if (iter->flags & FTRACE_ITER_ENABLED) + if (iter->flags & FTRACE_ITER_ENABLED) { seq_printf(m, " (%ld)%s", - rec->flags & ~FTRACE_FL_MASK, - rec->flags & FTRACE_FL_REGS ? " R" : ""); + ftrace_rec_count(rec), + rec->flags & FTRACE_FL_REGS ? " R" : " "); + if (rec->flags & FTRACE_FL_TRAMP_EN) { + struct ftrace_ops *ops; + + ops = ftrace_find_tramp_ops_curr(rec); + if (ops && ops->trampoline) + seq_printf(m, "\ttramp: %pS", + (void *)ops->trampoline); + else + seq_printf(m, "\ttramp: ERROR!"); + } + } + seq_printf(m, "\n"); return 0; @@ -2702,13 +2960,6 @@ ftrace_enabled_open(struct inode *inode, struct file *file) return iter ? 0 : -ENOMEM; } -static void ftrace_filter_reset(struct ftrace_hash *hash) -{ - mutex_lock(&ftrace_lock); - ftrace_hash_clear(hash); - mutex_unlock(&ftrace_lock); -} - /** * ftrace_regex_open - initialize function tracer filter files * @ops: The ftrace_ops that hold the hash filters @@ -2758,7 +3009,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, hash = ops->filter_hash; if (file->f_mode & FMODE_WRITE) { - iter->hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, hash); + const int size_bits = FTRACE_HASH_DEFAULT_BITS; + + if (file->f_flags & O_TRUNC) + iter->hash = alloc_ftrace_hash(size_bits); + else + iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash); + if (!iter->hash) { trace_parser_put(&iter->parser); kfree(iter); @@ -2767,10 +3024,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, } } - if ((file->f_mode & FMODE_WRITE) && - (file->f_flags & O_TRUNC)) - ftrace_filter_reset(iter->hash); - if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; @@ -3471,14 +3724,16 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, else orig_hash = &ops->notrace_hash; - hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (reset) + hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); + else + hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, *orig_hash); + if (!hash) { ret = -ENOMEM; goto out_regex_unlock; } - if (reset) - ftrace_filter_reset(hash); if (buf && !ftrace_match_records(hash, buf, len)) { ret = -EINVAL; goto out_regex_unlock; @@ -3630,6 +3885,7 @@ __setup("ftrace_filter=", set_ftrace_filter); #ifdef CONFIG_FUNCTION_GRAPH_TRACER static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; +static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer); static int __init set_graph_function(char *str) @@ -3639,16 +3895,29 @@ static int __init set_graph_function(char *str) } __setup("ftrace_graph_filter=", set_graph_function); -static void __init set_ftrace_early_graph(char *buf) +static int __init set_graph_notrace_function(char *str) +{ + strlcpy(ftrace_graph_notrace_buf, str, FTRACE_FILTER_SIZE); + return 1; +} +__setup("ftrace_graph_notrace=", set_graph_notrace_function); + +static void __init set_ftrace_early_graph(char *buf, int enable) { int ret; char *func; + unsigned long *table = ftrace_graph_funcs; + int *count = &ftrace_graph_count; + + if (!enable) { + table = ftrace_graph_notrace_funcs; + count = &ftrace_graph_notrace_count; + } while (buf) { func = strsep(&buf, ","); /* we allow only one expression at a time */ - ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, - FTRACE_GRAPH_MAX_FUNCS, func); + ret = ftrace_set_func(table, count, FTRACE_GRAPH_MAX_FUNCS, func); if (ret) printk(KERN_DEBUG "ftrace: function %s not " "traceable\n", func); @@ -3677,7 +3946,9 @@ static void __init set_ftrace_early_filters(void) ftrace_set_early_filter(&global_ops, ftrace_notrace_buf, 0); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (ftrace_graph_buf[0]) - set_ftrace_early_graph(ftrace_graph_buf); + set_ftrace_early_graph(ftrace_graph_buf, 1); + if (ftrace_graph_notrace_buf[0]) + set_ftrace_early_graph(ftrace_graph_notrace_buf, 0); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ } @@ -3819,7 +4090,12 @@ static int g_show(struct seq_file *m, void *v) return 0; if (ptr == (unsigned long *)1) { - seq_printf(m, "#### all functions enabled ####\n"); + struct ftrace_graph_data *fgd = m->private; + + if (fgd->table == ftrace_graph_funcs) + seq_printf(m, "#### all functions enabled ####\n"); + else + seq_printf(m, "#### no functions disabled ####\n"); return 0; } @@ -4447,9 +4723,6 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op; int bit; - if (function_trace_stop) - return; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return; @@ -4461,9 +4734,8 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, preempt_disable_notrace(); do_for_each_ftrace_op(op, ftrace_ops_list) { if (ftrace_ops_test(op, ip, regs)) { - if (WARN_ON(!op->func)) { - function_trace_stop = 1; - printk("op=%p %pS\n", op, op); + if (FTRACE_WARN_ON(!op->func)) { + pr_warn("op=%p %pS\n", op, op); goto out; } op->func(ip, parent_ip, op, regs); @@ -5084,6 +5356,12 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, /* Function graph doesn't use the .func field of global_ops */ global_ops.flags |= FTRACE_OPS_FL_STUB; +#ifdef CONFIG_DYNAMIC_FTRACE + /* Optimize function graph calling (if implemented by arch) */ + if (FTRACE_GRAPH_TRAMP_ADDR != 0) + global_ops.trampoline = FTRACE_GRAPH_TRAMP_ADDR; +#endif + ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET); out: @@ -5104,6 +5382,10 @@ void unregister_ftrace_graph(void) __ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET); global_ops.flags &= ~FTRACE_OPS_FL_STUB; +#ifdef CONFIG_DYNAMIC_FTRACE + if (FTRACE_GRAPH_TRAMP_ADDR != 0) + global_ops.trampoline = 0; +#endif unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); @@ -5183,9 +5465,4 @@ void ftrace_graph_exit_task(struct task_struct *t) kfree(ret_stack); } - -void ftrace_graph_stop(void) -{ - ftrace_stop(); -} #endif diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index ff70271..925f629 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1689,22 +1689,14 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, if (!cpu_buffer->nr_pages_to_update) continue; - /* The update must run on the CPU that is being updated. */ - preempt_disable(); - if (cpu == smp_processor_id() || !cpu_online(cpu)) { + /* Can't run something on an offline CPU. */ + if (!cpu_online(cpu)) { rb_update_pages(cpu_buffer); cpu_buffer->nr_pages_to_update = 0; } else { - /* - * Can not disable preemption for schedule_work_on() - * on PREEMPT_RT. - */ - preempt_enable(); schedule_work_on(cpu, &cpu_buffer->update_pages_work); - preempt_disable(); } - preempt_enable(); } /* wait for all the updates to complete */ @@ -1742,22 +1734,14 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, get_online_cpus(); - preempt_disable(); - /* The update must run on the CPU that is being updated. */ - if (cpu_id == smp_processor_id() || !cpu_online(cpu_id)) + /* Can't run something on an offline CPU. */ + if (!cpu_online(cpu_id)) rb_update_pages(cpu_buffer); else { - /* - * Can not disable preemption for schedule_work_on() - * on PREEMPT_RT. - */ - preempt_enable(); schedule_work_on(cpu_id, &cpu_buffer->update_pages_work); wait_for_completion(&cpu_buffer->update_done); - preempt_disable(); } - preempt_enable(); cpu_buffer->nr_pages_to_update = 0; put_online_cpus(); @@ -3775,7 +3759,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) if (rb_per_cpu_empty(cpu_buffer)) return NULL; - if (iter->head >= local_read(&iter->head_page->page->commit)) { + if (iter->head >= rb_page_size(iter->head_page)) { rb_inc_iter(iter); goto again; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 291397e..8bb80fe 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -937,30 +937,6 @@ out: return ret; } -ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) -{ - int len; - int ret; - - if (!cnt) - return 0; - - if (s->len <= s->readpos) - return -EBUSY; - - len = s->len - s->readpos; - if (cnt > len) - cnt = len; - ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); - if (ret == cnt) - return -EFAULT; - - cnt -= ret; - - s->readpos += cnt; - return cnt; -} - static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; @@ -3699,6 +3675,7 @@ static const char readme_msg[] = #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" + " set_graph_notrace\t- Do not trace the nested calls of a function (function_graph)\n" " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT @@ -4238,10 +4215,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, } static ssize_t -tracing_max_lat_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) +tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, + size_t cnt, loff_t *ppos) { - unsigned long *ptr = filp->private_data; char buf[64]; int r; @@ -4253,10 +4229,9 @@ tracing_max_lat_read(struct file *filp, char __user *ubuf, } static ssize_t -tracing_max_lat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, + size_t cnt, loff_t *ppos) { - unsigned long *ptr = filp->private_data; unsigned long val; int ret; @@ -4269,6 +4244,52 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, return cnt; } +static ssize_t +tracing_thresh_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return tracing_nsecs_read(&tracing_thresh, ubuf, cnt, ppos); +} + +static ssize_t +tracing_thresh_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + int ret; + + mutex_lock(&trace_types_lock); + ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); + if (ret < 0) + goto out; + + if (tr->current_trace->update_thresh) { + ret = tr->current_trace->update_thresh(tr); + if (ret < 0) + goto out; + } + + ret = cnt; +out: + mutex_unlock(&trace_types_lock); + + return ret; +} + +static ssize_t +tracing_max_lat_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return tracing_nsecs_read(filp->private_data, ubuf, cnt, ppos); +} + +static ssize_t +tracing_max_lat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos); +} + static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; @@ -5170,6 +5191,13 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) #endif /* CONFIG_TRACER_SNAPSHOT */ +static const struct file_operations tracing_thresh_fops = { + .open = tracing_open_generic, + .read = tracing_thresh_read, + .write = tracing_thresh_write, + .llseek = generic_file_llseek, +}; + static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, @@ -6107,10 +6135,8 @@ destroy_trace_option_files(struct trace_option_dentry *topts) if (!topts) return; - for (cnt = 0; topts[cnt].opt; cnt++) { - if (topts[cnt].entry) - debugfs_remove(topts[cnt].entry); - } + for (cnt = 0; topts[cnt].opt; cnt++) + debugfs_remove(topts[cnt].entry); kfree(topts); } @@ -6533,7 +6559,7 @@ static __init int tracer_init_debugfs(void) init_tracer_debugfs(&global_trace, d_tracer); trace_create_file("tracing_thresh", 0644, d_tracer, - &tracing_thresh, &tracing_max_lat_fops); + &global_trace, &tracing_thresh_fops); trace_create_file("README", 0444, d_tracer, NULL, &tracing_readme_fops); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 9258f5a..385391f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -339,6 +339,7 @@ struct tracer_flags { * @reset: called when one switches to another tracer * @start: called when tracing is unpaused (echo 1 > tracing_enabled) * @stop: called when tracing is paused (echo 0 > tracing_enabled) + * @update_thresh: called when tracing_thresh is updated * @open: called when the trace file is opened * @pipe_open: called when the trace_pipe file is opened * @close: called when the trace file is released @@ -357,6 +358,7 @@ struct tracer { void (*reset)(struct trace_array *tr); void (*start)(struct trace_array *tr); void (*stop)(struct trace_array *tr); + int (*update_thresh)(struct trace_array *tr); void (*open)(struct trace_iterator *iter); void (*pipe_open)(struct trace_iterator *iter); void (*close)(struct trace_iterator *iter); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 2de53628..3154eb3 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -8,6 +8,8 @@ * */ +#define pr_fmt(fmt) fmt + #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/kthread.h> @@ -1491,7 +1493,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name, dir->entry = debugfs_create_dir(name, parent); if (!dir->entry) { - pr_warning("Failed to create system directory %s\n", name); + pr_warn("Failed to create system directory %s\n", name); __put_system(system); goto out_free; } @@ -1507,7 +1509,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name, if (!entry) { kfree(system->filter); system->filter = NULL; - pr_warning("Could not create debugfs '%s/filter' entry\n", name); + pr_warn("Could not create debugfs '%s/filter' entry\n", name); } trace_create_file("enable", 0644, dir->entry, dir, @@ -1522,8 +1524,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name, out_fail: /* Only print this message if failed on memory allocation */ if (!dir || !system) - pr_warning("No memory to create event subsystem %s\n", - name); + pr_warn("No memory to create event subsystem %s\n", name); return NULL; } @@ -1551,8 +1552,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) name = ftrace_event_name(call); file->dir = debugfs_create_dir(name, d_events); if (!file->dir) { - pr_warning("Could not create debugfs '%s' directory\n", - name); + pr_warn("Could not create debugfs '%s' directory\n", name); return -1; } @@ -1575,8 +1575,8 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) if (list_empty(head)) { ret = call->class->define_fields(call); if (ret < 0) { - pr_warning("Could not initialize trace point" - " events/%s\n", name); + pr_warn("Could not initialize trace point events/%s\n", + name); return -1; } } @@ -1649,8 +1649,7 @@ static int event_init(struct ftrace_event_call *call) if (call->class->raw_init) { ret = call->class->raw_init(call); if (ret < 0 && ret != -ENOSYS) - pr_warn("Could not initialize trace events/%s\n", - name); + pr_warn("Could not initialize trace events/%s\n", name); } return ret; @@ -1895,8 +1894,8 @@ __trace_add_event_dirs(struct trace_array *tr) list_for_each_entry(call, &ftrace_events, list) { ret = __trace_add_new_event(call, tr); if (ret < 0) - pr_warning("Could not create directory for event %s\n", - ftrace_event_name(call)); + pr_warn("Could not create directory for event %s\n", + ftrace_event_name(call)); } } @@ -2208,8 +2207,8 @@ __trace_early_add_event_dirs(struct trace_array *tr) list_for_each_entry(file, &tr->events, list) { ret = event_create_dir(tr->event_dir, file); if (ret < 0) - pr_warning("Could not create directory for event %s\n", - ftrace_event_name(file->event_call)); + pr_warn("Could not create directory for event %s\n", + ftrace_event_name(file->event_call)); } } @@ -2232,8 +2231,8 @@ __trace_early_add_events(struct trace_array *tr) ret = __trace_early_add_new_event(call, tr); if (ret < 0) - pr_warning("Could not create early event %s\n", - ftrace_event_name(call)); + pr_warn("Could not create early event %s\n", + ftrace_event_name(call)); } } @@ -2280,13 +2279,13 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) entry = debugfs_create_file("set_event", 0644, parent, tr, &ftrace_set_event_fops); if (!entry) { - pr_warning("Could not create debugfs 'set_event' entry\n"); + pr_warn("Could not create debugfs 'set_event' entry\n"); return -ENOMEM; } d_events = debugfs_create_dir("events", parent); if (!d_events) { - pr_warning("Could not create debugfs 'events' directory\n"); + pr_warn("Could not create debugfs 'events' directory\n"); return -ENOMEM; } @@ -2462,11 +2461,10 @@ static __init int event_trace_init(void) entry = debugfs_create_file("available_events", 0444, d_tracer, tr, &ftrace_avail_fops); if (!entry) - pr_warning("Could not create debugfs " - "'available_events' entry\n"); + pr_warn("Could not create debugfs 'available_events' entry\n"); if (trace_define_common_fields()) - pr_warning("tracing: Failed to allocate common fields"); + pr_warn("tracing: Failed to allocate common fields"); ret = early_event_add_tracer(d_tracer, tr); if (ret) @@ -2475,7 +2473,7 @@ static __init int event_trace_init(void) #ifdef CONFIG_MODULES ret = register_module_notifier(&trace_module_nb); if (ret) - pr_warning("Failed to register trace events module notifier\n"); + pr_warn("Failed to register trace events module notifier\n"); #endif return 0; } @@ -2579,7 +2577,7 @@ static __init void event_trace_self_tests(void) * it and the self test should not be on. */ if (file->flags & FTRACE_EVENT_FL_ENABLED) { - pr_warning("Enabled event during self test!\n"); + pr_warn("Enabled event during self test!\n"); WARN_ON_ONCE(1); continue; } @@ -2607,8 +2605,8 @@ static __init void event_trace_self_tests(void) ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1); if (WARN_ON_ONCE(ret)) { - pr_warning("error enabling system %s\n", - system->name); + pr_warn("error enabling system %s\n", + system->name); continue; } @@ -2616,8 +2614,8 @@ static __init void event_trace_self_tests(void) ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0); if (WARN_ON_ONCE(ret)) { - pr_warning("error disabling system %s\n", - system->name); + pr_warn("error disabling system %s\n", + system->name); continue; } @@ -2631,7 +2629,7 @@ static __init void event_trace_self_tests(void) ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1); if (WARN_ON_ONCE(ret)) { - pr_warning("error enabling all events\n"); + pr_warn("error enabling all events\n"); return; } @@ -2640,7 +2638,7 @@ static __init void event_trace_self_tests(void) /* reset sysname */ ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0); if (WARN_ON_ONCE(ret)) { - pr_warning("error disabling all events\n"); + pr_warn("error disabling all events\n"); return; } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 4de3e57..f0a0c98 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -15,6 +15,33 @@ #include "trace.h" #include "trace_output.h" +static bool kill_ftrace_graph; + +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +bool ftrace_graph_is_dead(void) +{ + return kill_ftrace_graph; +} + +/** + * ftrace_graph_stop - set to permanently disable function graph tracincg + * + * In case of an error int function graph tracing, this is called + * to try to keep function graph tracing from causing any more harm. + * Usually this is pretty severe and this is called to try to at least + * get a warning out to the user. + */ +void ftrace_graph_stop(void) +{ + kill_ftrace_graph = true; +} + /* When set, irq functions will be ignored */ static int ftrace_graph_skip_irqs; @@ -92,6 +119,9 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long long calltime; int index; + if (unlikely(ftrace_graph_is_dead())) + return -EBUSY; + if (!current->ret_stack) return -EBUSY; @@ -323,7 +353,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) return ret; } -int trace_graph_thresh_entry(struct ftrace_graph_ent *trace) +static int trace_graph_thresh_entry(struct ftrace_graph_ent *trace) { if (tracing_thresh) return 1; @@ -412,7 +442,7 @@ void set_graph_array(struct trace_array *tr) smp_mb(); } -void trace_graph_thresh_return(struct ftrace_graph_ret *trace) +static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) { if (tracing_thresh && (trace->rettime - trace->calltime < tracing_thresh)) @@ -445,6 +475,12 @@ static void graph_trace_reset(struct trace_array *tr) unregister_ftrace_graph(); } +static int graph_trace_update_thresh(struct trace_array *tr) +{ + graph_trace_reset(tr); + return graph_trace_init(tr); +} + static int max_bytes_for_cpu; static enum print_line_t @@ -1399,7 +1435,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags) seq_printf(s, " | | | |\n"); } -void print_graph_headers(struct seq_file *s) +static void print_graph_headers(struct seq_file *s) { print_graph_headers_flags(s, tracer_flags.val); } @@ -1495,6 +1531,7 @@ static struct trace_event graph_trace_ret_event = { static struct tracer graph_trace __tracer_data = { .name = "function_graph", + .update_thresh = graph_trace_update_thresh, .open = graph_trace_open, .pipe_open = graph_trace_open, .close = graph_trace_close, diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index f3dad80..c6977d5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -20,23 +20,6 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly; static int next_event_type = __TRACE_LAST_TYPE + 1; -int trace_print_seq(struct seq_file *m, struct trace_seq *s) -{ - int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len; - int ret; - - ret = seq_write(m, s->buffer, len); - - /* - * Only reset this buffer if we successfully wrote to the - * seq_file buffer. - */ - if (!ret) - trace_seq_init(s); - - return ret; -} - enum print_line_t trace_print_bputs_msg_only(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; @@ -85,257 +68,6 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter) return TRACE_TYPE_HANDLED; } -/** - * trace_seq_printf - sequence printing of trace information - * @s: trace sequence descriptor - * @fmt: printf format string - * - * It returns 0 if the trace oversizes the buffer's free - * space, 1 otherwise. - * - * The tracer may use either sequence operations or its own - * copy to user routines. To simplify formating of a trace - * trace_seq_printf is used to store strings into a special - * buffer (@s). Then the output may be either used by - * the sequencer or pulled into another buffer. - */ -int -trace_seq_printf(struct trace_seq *s, const char *fmt, ...) -{ - int len = (PAGE_SIZE - 1) - s->len; - va_list ap; - int ret; - - if (s->full || !len) - return 0; - - va_start(ap, fmt); - ret = vsnprintf(s->buffer + s->len, len, fmt, ap); - va_end(ap); - - /* If we can't write it all, don't bother writing anything */ - if (ret >= len) { - s->full = 1; - return 0; - } - - s->len += ret; - - return 1; -} -EXPORT_SYMBOL_GPL(trace_seq_printf); - -/** - * trace_seq_bitmask - put a list of longs as a bitmask print output - * @s: trace sequence descriptor - * @maskp: points to an array of unsigned longs that represent a bitmask - * @nmaskbits: The number of bits that are valid in @maskp - * - * It returns 0 if the trace oversizes the buffer's free - * space, 1 otherwise. - * - * Writes a ASCII representation of a bitmask string into @s. - */ -int -trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, - int nmaskbits) -{ - int len = (PAGE_SIZE - 1) - s->len; - int ret; - - if (s->full || !len) - return 0; - - ret = bitmap_scnprintf(s->buffer, len, maskp, nmaskbits); - s->len += ret; - - return 1; -} -EXPORT_SYMBOL_GPL(trace_seq_bitmask); - -/** - * trace_seq_vprintf - sequence printing of trace information - * @s: trace sequence descriptor - * @fmt: printf format string - * - * The tracer may use either sequence operations or its own - * copy to user routines. To simplify formating of a trace - * trace_seq_printf is used to store strings into a special - * buffer (@s). Then the output may be either used by - * the sequencer or pulled into another buffer. - */ -int -trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) -{ - int len = (PAGE_SIZE - 1) - s->len; - int ret; - - if (s->full || !len) - return 0; - - ret = vsnprintf(s->buffer + s->len, len, fmt, args); - - /* If we can't write it all, don't bother writing anything */ - if (ret >= len) { - s->full = 1; - return 0; - } - - s->len += ret; - - return len; -} -EXPORT_SYMBOL_GPL(trace_seq_vprintf); - -int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) -{ - int len = (PAGE_SIZE - 1) - s->len; - int ret; - - if (s->full || !len) - return 0; - - ret = bstr_printf(s->buffer + s->len, len, fmt, binary); - - /* If we can't write it all, don't bother writing anything */ - if (ret >= len) { - s->full = 1; - return 0; - } - - s->len += ret; - - return len; -} - -/** - * trace_seq_puts - trace sequence printing of simple string - * @s: trace sequence descriptor - * @str: simple string to record - * - * The tracer may use either the sequence operations or its own - * copy to user routines. This function records a simple string - * into a special buffer (@s) for later retrieval by a sequencer - * or other mechanism. - */ -int trace_seq_puts(struct trace_seq *s, const char *str) -{ - int len = strlen(str); - - if (s->full) - return 0; - - if (len > ((PAGE_SIZE - 1) - s->len)) { - s->full = 1; - return 0; - } - - memcpy(s->buffer + s->len, str, len); - s->len += len; - - return len; -} - -int trace_seq_putc(struct trace_seq *s, unsigned char c) -{ - if (s->full) - return 0; - - if (s->len >= (PAGE_SIZE - 1)) { - s->full = 1; - return 0; - } - - s->buffer[s->len++] = c; - - return 1; -} -EXPORT_SYMBOL(trace_seq_putc); - -int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len) -{ - if (s->full) - return 0; - - if (len > ((PAGE_SIZE - 1) - s->len)) { - s->full = 1; - return 0; - } - - memcpy(s->buffer + s->len, mem, len); - s->len += len; - - return len; -} - -int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len) -{ - unsigned char hex[HEX_CHARS]; - const unsigned char *data = mem; - int i, j; - - if (s->full) - return 0; - -#ifdef __BIG_ENDIAN - for (i = 0, j = 0; i < len; i++) { -#else - for (i = len-1, j = 0; i >= 0; i--) { -#endif - hex[j++] = hex_asc_hi(data[i]); - hex[j++] = hex_asc_lo(data[i]); - } - hex[j++] = ' '; - - return trace_seq_putmem(s, hex, j); -} - -void *trace_seq_reserve(struct trace_seq *s, size_t len) -{ - void *ret; - - if (s->full) - return NULL; - - if (len > ((PAGE_SIZE - 1) - s->len)) { - s->full = 1; - return NULL; - } - - ret = s->buffer + s->len; - s->len += len; - - return ret; -} - -int trace_seq_path(struct trace_seq *s, const struct path *path) -{ - unsigned char *p; - - if (s->full) - return 0; - - if (s->len >= (PAGE_SIZE - 1)) { - s->full = 1; - return 0; - } - - p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); - if (!IS_ERR(p)) { - p = mangle_path(s->buffer + s->len, p, "\n"); - if (p) { - s->len = p - s->buffer; - return 1; - } - } else { - s->buffer[s->len++] = '?'; - return 1; - } - - s->full = 1; - return 0; -} - const char * ftrace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, @@ -343,7 +75,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim, { unsigned long mask; const char *str; - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); int i, first = 1; for (i = 0; flag_array[i].name && flags; i++) { @@ -379,7 +111,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, const struct trace_print_flags *symbol_array) { int i; - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); for (i = 0; symbol_array[i].name; i++) { @@ -390,7 +122,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val, break; } - if (ret == (const char *)(p->buffer + p->len)) + if (ret == (const char *)(trace_seq_buffer_ptr(p))) trace_seq_printf(p, "0x%lx", val); trace_seq_putc(p, 0); @@ -405,7 +137,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, const struct trace_print_flags_u64 *symbol_array) { int i; - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); for (i = 0; symbol_array[i].name; i++) { @@ -416,7 +148,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val, break; } - if (ret == (const char *)(p->buffer + p->len)) + if (ret == (const char *)(trace_seq_buffer_ptr(p))) trace_seq_printf(p, "0x%llx", val); trace_seq_putc(p, 0); @@ -430,7 +162,7 @@ const char * ftrace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, unsigned int bitmask_size) { - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); trace_seq_bitmask(p, bitmask_ptr, bitmask_size * 8); trace_seq_putc(p, 0); @@ -443,7 +175,7 @@ const char * ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len) { int i; - const char *ret = p->buffer + p->len; + const char *ret = trace_seq_buffer_ptr(p); for (i = 0; i < buf_len; i++) trace_seq_printf(p, "%s%2.2x", i == 0 ? "" : " ", buf[i]); diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index 127a9d8..80b25b5 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -35,9 +35,6 @@ trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry); extern int __unregister_ftrace_event(struct trace_event *event); extern struct rw_semaphore trace_event_sem; -#define MAX_MEMHEX_BYTES 8 -#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) - #define SEQ_PUT_FIELD_RET(s, x) \ do { \ if (!trace_seq_putmem(s, &(x), sizeof(x))) \ @@ -46,7 +43,6 @@ do { \ #define SEQ_PUT_HEX_FIELD_RET(s, x) \ do { \ - BUILD_BUG_ON(sizeof(x) > MAX_MEMHEX_BYTES); \ if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ return TRACE_TYPE_PARTIAL_LINE; \ } while (0) diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c new file mode 100644 index 0000000..1f24ed9 --- /dev/null +++ b/kernel/trace/trace_seq.c @@ -0,0 +1,428 @@ +/* + * trace_seq.c + * + * Copyright (C) 2008-2014 Red Hat Inc, Steven Rostedt <srostedt@redhat.com> + * + * The trace_seq is a handy tool that allows you to pass a descriptor around + * to a buffer that other functions can write to. It is similar to the + * seq_file functionality but has some differences. + * + * To use it, the trace_seq must be initialized with trace_seq_init(). + * This will set up the counters within the descriptor. You can call + * trace_seq_init() more than once to reset the trace_seq to start + * from scratch. + * + * The buffer size is currently PAGE_SIZE, although it may become dynamic + * in the future. + * + * A write to the buffer will either succed or fail. That is, unlike + * sprintf() there will not be a partial write (well it may write into + * the buffer but it wont update the pointers). This allows users to + * try to write something into the trace_seq buffer and if it fails + * they can flush it and try again. + * + */ +#include <linux/uaccess.h> +#include <linux/seq_file.h> +#include <linux/trace_seq.h> + +/* How much buffer is left on the trace_seq? */ +#define TRACE_SEQ_BUF_LEFT(s) ((PAGE_SIZE - 1) - (s)->len) + +/* How much buffer is written? */ +#define TRACE_SEQ_BUF_USED(s) min((s)->len, (unsigned int)(PAGE_SIZE - 1)) + +/** + * trace_print_seq - move the contents of trace_seq into a seq_file + * @m: the seq_file descriptor that is the destination + * @s: the trace_seq descriptor that is the source. + * + * Returns 0 on success and non zero on error. If it succeeds to + * write to the seq_file it will reset the trace_seq, otherwise + * it does not modify the trace_seq to let the caller try again. + */ +int trace_print_seq(struct seq_file *m, struct trace_seq *s) +{ + unsigned int len = TRACE_SEQ_BUF_USED(s); + int ret; + + ret = seq_write(m, s->buffer, len); + + /* + * Only reset this buffer if we successfully wrote to the + * seq_file buffer. This lets the caller try again or + * do something else with the contents. + */ + if (!ret) + trace_seq_init(s); + + return ret; +} + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf() is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + * + * Returns 1 if we successfully written all the contents to + * the buffer. + * Returns 0 if we the length to write is bigger than the + * reserved buffer space. In this case, nothing gets written. + */ +int trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + unsigned int len = TRACE_SEQ_BUF_LEFT(s); + va_list ap; + int ret; + + if (s->full || !len) + return 0; + + va_start(ap, fmt); + ret = vsnprintf(s->buffer + s->len, len, fmt, ap); + va_end(ap); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) { + s->full = 1; + return 0; + } + + s->len += ret; + + return 1; +} +EXPORT_SYMBOL_GPL(trace_seq_printf); + +/** + * trace_seq_bitmask - write a bitmask array in its ASCII representation + * @s: trace sequence descriptor + * @maskp: points to an array of unsigned longs that represent a bitmask + * @nmaskbits: The number of bits that are valid in @maskp + * + * Writes a ASCII representation of a bitmask string into @s. + * + * Returns 1 if we successfully written all the contents to + * the buffer. + * Returns 0 if we the length to write is bigger than the + * reserved buffer space. In this case, nothing gets written. + */ +int trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, + int nmaskbits) +{ + unsigned int len = TRACE_SEQ_BUF_LEFT(s); + int ret; + + if (s->full || !len) + return 0; + + ret = bitmap_scnprintf(s->buffer, len, maskp, nmaskbits); + s->len += ret; + + return 1; +} +EXPORT_SYMBOL_GPL(trace_seq_bitmask); + +/** + * trace_seq_vprintf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + * + * Returns how much it wrote to the buffer. + */ +int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args) +{ + unsigned int len = TRACE_SEQ_BUF_LEFT(s); + int ret; + + if (s->full || !len) + return 0; + + ret = vsnprintf(s->buffer + s->len, len, fmt, args); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) { + s->full = 1; + return 0; + } + + s->len += ret; + + return len; +} +EXPORT_SYMBOL_GPL(trace_seq_vprintf); + +/** + * trace_seq_bprintf - Write the printf string from binary arguments + * @s: trace sequence descriptor + * @fmt: The format string for the @binary arguments + * @binary: The binary arguments for @fmt. + * + * When recording in a fast path, a printf may be recorded with just + * saving the format and the arguments as they were passed to the + * function, instead of wasting cycles converting the arguments into + * ASCII characters. Instead, the arguments are saved in a 32 bit + * word array that is defined by the format string constraints. + * + * This function will take the format and the binary array and finish + * the conversion into the ASCII string within the buffer. + * + * Returns how much it wrote to the buffer. + */ +int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary) +{ + unsigned int len = TRACE_SEQ_BUF_LEFT(s); + int ret; + + if (s->full || !len) + return 0; + + ret = bstr_printf(s->buffer + s->len, len, fmt, binary); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) { + s->full = 1; + return 0; + } + + s->len += ret; + + return len; +} +EXPORT_SYMBOL_GPL(trace_seq_bprintf); + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + * + * Returns how much it wrote to the buffer. + */ +int trace_seq_puts(struct trace_seq *s, const char *str) +{ + unsigned int len = strlen(str); + + if (s->full) + return 0; + + if (len > TRACE_SEQ_BUF_LEFT(s)) { + s->full = 1; + return 0; + } + + memcpy(s->buffer + s->len, str, len); + s->len += len; + + return len; +} +EXPORT_SYMBOL_GPL(trace_seq_puts); + +/** + * trace_seq_putc - trace sequence printing of simple character + * @s: trace sequence descriptor + * @c: simple character to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple charater + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + * + * Returns how much it wrote to the buffer. + */ +int trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + if (s->full) + return 0; + + if (TRACE_SEQ_BUF_LEFT(s) < 1) { + s->full = 1; + return 0; + } + + s->buffer[s->len++] = c; + + return 1; +} +EXPORT_SYMBOL_GPL(trace_seq_putc); + +/** + * trace_seq_putmem - write raw data into the trace_seq buffer + * @s: trace sequence descriptor + * @mem: The raw memory to copy into the buffer + * @len: The length of the raw memory to copy (in bytes) + * + * There may be cases where raw memory needs to be written into the + * buffer and a strcpy() would not work. Using this function allows + * for such cases. + * + * Returns how much it wrote to the buffer. + */ +int trace_seq_putmem(struct trace_seq *s, const void *mem, unsigned int len) +{ + if (s->full) + return 0; + + if (len > TRACE_SEQ_BUF_LEFT(s)) { + s->full = 1; + return 0; + } + + memcpy(s->buffer + s->len, mem, len); + s->len += len; + + return len; +} +EXPORT_SYMBOL_GPL(trace_seq_putmem); + +#define MAX_MEMHEX_BYTES 8U +#define HEX_CHARS (MAX_MEMHEX_BYTES*2 + 1) + +/** + * trace_seq_putmem_hex - write raw memory into the buffer in ASCII hex + * @s: trace sequence descriptor + * @mem: The raw memory to write its hex ASCII representation of + * @len: The length of the raw memory to copy (in bytes) + * + * This is similar to trace_seq_putmem() except instead of just copying the + * raw memory into the buffer it writes its ASCII representation of it + * in hex characters. + * + * Returns how much it wrote to the buffer. + */ +int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, + unsigned int len) +{ + unsigned char hex[HEX_CHARS]; + const unsigned char *data = mem; + unsigned int start_len; + int i, j; + int cnt = 0; + + if (s->full) + return 0; + + while (len) { + start_len = min(len, HEX_CHARS - 1); +#ifdef __BIG_ENDIAN + for (i = 0, j = 0; i < start_len; i++) { +#else + for (i = start_len-1, j = 0; i >= 0; i--) { +#endif + hex[j++] = hex_asc_hi(data[i]); + hex[j++] = hex_asc_lo(data[i]); + } + if (WARN_ON_ONCE(j == 0 || j/2 > len)) + break; + + /* j increments twice per loop */ + len -= j / 2; + hex[j++] = ' '; + + cnt += trace_seq_putmem(s, hex, j); + } + return cnt; +} +EXPORT_SYMBOL_GPL(trace_seq_putmem_hex); + +/** + * trace_seq_path - copy a path into the sequence buffer + * @s: trace sequence descriptor + * @path: path to write into the sequence buffer. + * + * Write a path name into the sequence buffer. + * + * Returns 1 if we successfully written all the contents to + * the buffer. + * Returns 0 if we the length to write is bigger than the + * reserved buffer space. In this case, nothing gets written. + */ +int trace_seq_path(struct trace_seq *s, const struct path *path) +{ + unsigned char *p; + + if (s->full) + return 0; + + if (TRACE_SEQ_BUF_LEFT(s) < 1) { + s->full = 1; + return 0; + } + + p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len); + if (!IS_ERR(p)) { + p = mangle_path(s->buffer + s->len, p, "\n"); + if (p) { + s->len = p - s->buffer; + return 1; + } + } else { + s->buffer[s->len++] = '?'; + return 1; + } + + s->full = 1; + return 0; +} +EXPORT_SYMBOL_GPL(trace_seq_path); + +/** + * trace_seq_to_user - copy the squence buffer to user space + * @s: trace sequence descriptor + * @ubuf: The userspace memory location to copy to + * @cnt: The amount to copy + * + * Copies the sequence buffer into the userspace memory pointed to + * by @ubuf. It starts from the last read position (@s->readpos) + * and writes up to @cnt characters or till it reaches the end of + * the content in the buffer (@s->len), which ever comes first. + * + * On success, it returns a positive number of the number of bytes + * it copied. + * + * On failure it returns -EBUSY if all of the content in the + * sequence has been already read, which includes nothing in the + * sequenc (@s->len == @s->readpos). + * + * Returns -EFAULT if the copy to userspace fails. + */ +int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt) +{ + int len; + int ret; + + if (!cnt) + return 0; + + if (s->len <= s->readpos) + return -EBUSY; + + len = s->len - s->readpos; + if (cnt > len) + cnt = len; + ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); + if (ret == cnt) + return -EFAULT; + + cnt -= ret; + + s->readpos += cnt; + return cnt; +} +EXPORT_SYMBOL_GPL(trace_seq_to_user); diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h index 4b0113f..4764292 100644 --- a/samples/trace_events/trace-events-sample.h +++ b/samples/trace_events/trace-events-sample.h @@ -87,7 +87,7 @@ TRACE_EVENT(foo_bar, ), TP_fast_assign( - strncpy(__entry->foo, foo, 10); + strlcpy(__entry->foo, foo, 10); __entry->bar = bar; ), |
