From 82524746c27fa418c250a56dd7606b9d3fc79826 Mon Sep 17 00:00:00 2001 From: Franck Bui-Huu Date: Mon, 12 May 2008 21:21:05 +0200 Subject: rcu: split list.h and move rcu-protected lists into rculist.h Move rcu-protected lists from list.h into a new header file rculist.h. This is done because list are a very used primitive structure all over the kernel and it's currently impossible to include other header files in this list.h without creating some circular dependencies. For example, list.h implements rcu-protected list and uses rcu_dereference() without including rcupdate.h. It actually compiles because users of rcu_dereference() are macros. Others RCU functions could be used too but aren't probably because of this. Therefore this patch creates rculist.h which includes rcupdates without to many changes/troubles. Signed-off-by: Franck Bui-Huu Acked-by: Paul E. McKenney Acked-by: Josh Triplett Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- lib/textsearch.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/textsearch.c b/lib/textsearch.c index be8bda3862f5..a3e500ad51d7 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -97,6 +97,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 41df0d61c266998b8049df7fec119cd518a43aa1 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Mon, 12 May 2008 21:21:13 +0200 Subject: x86: Add performance variants of cpumask operators * Increase performance for systems with large count NR_CPUS by limiting the range of the cpumask operators that loop over the bits in a cpumask_t variable. This removes a large amount of wasted cpu cycles. * Add performance variants of the cpumask operators: int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS int first_cpu_nr(mask) Number lowest set bit, or nr_cpu_ids int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids * Modify following to use performance variants: #define num_online_cpus() cpus_weight_nr(cpu_online_map) #define num_possible_cpus() cpus_weight_nr(cpu_possible_map) #define num_present_cpus() cpus_weight_nr(cpu_present_map) #define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) * Comment added to include/linux/cpumask.h: Note: The alternate operations with the suffix "_nr" are used to limit the range of the loop to nr_cpu_ids instead of NR_CPUS when NR_CPUS > 64 for performance reasons. If NR_CPUS is <= 64 then most assembler bitmask operators execute faster with a constant range, so the operator will continue to use NR_CPUS. Another consideration is that nr_cpu_ids is initialized to NR_CPUS and isn't lowered until the possible cpus are discovered (including any disabled cpus). So early uses will span the entire range of NR_CPUS. (The net effect is that for systems with 64 or less CPU's there are no functional changes.) For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Cc: Paul Jackson Cc: Christoph Lameter Reviewed-by: Paul Jackson Reviewed-by: Christoph Lameter Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- include/linux/cpumask.h | 92 +++++++++++++++++++++++++++++++++---------------- lib/cpumask.c | 9 +++++ 2 files changed, 71 insertions(+), 30 deletions(-) (limited to 'lib') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 5df3db58fcc6..b49472d1af84 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -17,6 +17,20 @@ * For details of cpus_onto(), see bitmap_onto in lib/bitmap.c. * For details of cpus_fold(), see bitmap_fold in lib/bitmap.c. * + * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . + * Note: The alternate operations with the suffix "_nr" are used + * to limit the range of the loop to nr_cpu_ids instead of + * NR_CPUS when NR_CPUS > 64 for performance reasons. + * If NR_CPUS is <= 64 then most assembler bitmask + * operators execute faster with a constant range, so + * the operator will continue to use NR_CPUS. + * + * Another consideration is that nr_cpu_ids is initialized + * to NR_CPUS and isn't lowered until the possible cpus are + * discovered (including any disabled cpus). So early uses + * will span the entire range of NR_CPUS. + * . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . + * * The available cpumask operations are: * * void cpu_set(cpu, mask) turn on bit 'cpu' in mask @@ -38,12 +52,14 @@ * int cpus_empty(mask) Is mask empty (no bits sets)? * int cpus_full(mask) Is mask full (all bits sets)? * int cpus_weight(mask) Hamming weigh - number of set bits + * int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS * * void cpus_shift_right(dst, src, n) Shift right * void cpus_shift_left(dst, src, n) Shift left * * int first_cpu(mask) Number lowest set bit, or NR_CPUS * int next_cpu(cpu, mask) Next cpu past 'cpu', or NR_CPUS + * int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids * * cpumask_t cpumask_of_cpu(cpu) Return cpumask with bit 'cpu' set * CPU_MASK_ALL Initializer - all bits set @@ -59,7 +75,8 @@ * void cpus_onto(dst, orig, relmap) *dst = orig relative to relmap * void cpus_fold(dst, orig, sz) dst bits = orig bits mod sz * - * for_each_cpu_mask(cpu, mask) for-loop cpu over mask + * for_each_cpu_mask(cpu, mask) for-loop cpu over mask using NR_CPUS + * for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids * * int num_online_cpus() Number of online CPUs * int num_possible_cpus() Number of all possible CPUs @@ -216,15 +233,6 @@ static inline void __cpus_shift_left(cpumask_t *dstp, bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } -#ifdef CONFIG_SMP -int __first_cpu(const cpumask_t *srcp); -#define first_cpu(src) __first_cpu(&(src)) -int __next_cpu(int n, const cpumask_t *srcp); -#define next_cpu(n, src) __next_cpu((n), &(src)) -#else -#define first_cpu(src) ({ (void)(src); 0; }) -#define next_cpu(n, src) ({ (void)(src); 1; }) -#endif #ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP extern cpumask_t *cpumask_of_cpu_map; @@ -343,15 +351,48 @@ static inline void __cpus_fold(cpumask_t *dstp, const cpumask_t *origp, bitmap_fold(dstp->bits, origp->bits, sz, nbits); } -#if NR_CPUS > 1 +#if NR_CPUS == 1 + +#define nr_cpu_ids 1 +#define first_cpu(src) ({ (void)(src); 0; }) +#define next_cpu(n, src) ({ (void)(src); 1; }) +#define any_online_cpu(mask) 0 +#define for_each_cpu_mask(cpu, mask) \ + for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) + +#else /* NR_CPUS > 1 */ + +extern int nr_cpu_ids; +int __first_cpu(const cpumask_t *srcp); +int __next_cpu(int n, const cpumask_t *srcp); +int __any_online_cpu(const cpumask_t *mask); + +#define first_cpu(src) __first_cpu(&(src)) +#define next_cpu(n, src) __next_cpu((n), &(src)) +#define any_online_cpu(mask) __any_online_cpu(&(mask)) #define for_each_cpu_mask(cpu, mask) \ for ((cpu) = first_cpu(mask); \ (cpu) < NR_CPUS; \ (cpu) = next_cpu((cpu), (mask))) -#else /* NR_CPUS == 1 */ -#define for_each_cpu_mask(cpu, mask) \ - for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) -#endif /* NR_CPUS */ +#endif + +#if NR_CPUS <= 64 + +#define next_cpu_nr(n, src) next_cpu(n, src) +#define cpus_weight_nr(cpumask) cpus_weight(cpumask) +#define for_each_cpu_mask_nr(cpu, mask) for_each_cpu_mask(cpu, mask) + +#else /* NR_CPUS > 64 */ + +int __next_cpu_nr(int n, const cpumask_t *srcp); +#define next_cpu_nr(n, src) __next_cpu_nr((n), &(src)) +#define cpus_weight_nr(cpumask) __cpus_weight(&(cpumask), nr_cpu_ids) +#define for_each_cpu_mask_nr(cpu, mask) \ + for ((cpu) = first_cpu(mask); \ + (cpu) < nr_cpu_ids; \ + (cpu) = next_cpu_nr((cpu), (mask))) + +#endif /* NR_CPUS > 64 */ /* * The following particular system cpumasks and operations manage @@ -414,9 +455,9 @@ extern cpumask_t cpu_online_map; extern cpumask_t cpu_present_map; #if NR_CPUS > 1 -#define num_online_cpus() cpus_weight(cpu_online_map) -#define num_possible_cpus() cpus_weight(cpu_possible_map) -#define num_present_cpus() cpus_weight(cpu_present_map) +#define num_online_cpus() cpus_weight_nr(cpu_online_map) +#define num_possible_cpus() cpus_weight_nr(cpu_possible_map) +#define num_present_cpus() cpus_weight_nr(cpu_present_map) #define cpu_online(cpu) cpu_isset((cpu), cpu_online_map) #define cpu_possible(cpu) cpu_isset((cpu), cpu_possible_map) #define cpu_present(cpu) cpu_isset((cpu), cpu_present_map) @@ -431,17 +472,8 @@ extern cpumask_t cpu_present_map; #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) -#ifdef CONFIG_SMP -extern int nr_cpu_ids; -#define any_online_cpu(mask) __any_online_cpu(&(mask)) -int __any_online_cpu(const cpumask_t *mask); -#else -#define nr_cpu_ids 1 -#define any_online_cpu(mask) 0 -#endif - -#define for_each_possible_cpu(cpu) for_each_cpu_mask((cpu), cpu_possible_map) -#define for_each_online_cpu(cpu) for_each_cpu_mask((cpu), cpu_online_map) -#define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map) +#define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_possible_map) +#define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_online_map) +#define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), cpu_present_map) #endif /* __LINUX_CPUMASK_H */ diff --git a/lib/cpumask.c b/lib/cpumask.c index bb4f76d3c3e7..5f97dc25ef9c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -15,6 +15,15 @@ int __next_cpu(int n, const cpumask_t *srcp) } EXPORT_SYMBOL(__next_cpu); +#if NR_CPUS > 64 +int __next_cpu_nr(int n, const cpumask_t *srcp) +{ + return min_t(int, nr_cpu_ids, + find_next_bit(srcp->bits, nr_cpu_ids, n+1)); +} +EXPORT_SYMBOL(__next_cpu_nr); +#endif + int __any_online_cpu(const cpumask_t *mask) { int cpu; -- cgit v1.2.3 From 6e766410c4babd37bc7cd5e25009c179781742c8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 12 May 2008 21:20:41 +0200 Subject: ftrace: annotate core code that should not be traced Mark with "notrace" functions in core code that should not be traced. The "notrace" attribute will prevent gcc from adding a call to ftrace on the annotated funtions. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/smp_processor_id.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 6c90fb90e19c..e555ab62fbad 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -7,7 +7,7 @@ #include #include -unsigned int debug_smp_processor_id(void) +notrace unsigned int debug_smp_processor_id(void) { unsigned long preempt_count = preempt_count(); int this_cpu = raw_smp_processor_id(); -- cgit v1.2.3 From 16444a8a40d4c7b4f6de34af0cae1f76a4f6c901 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 12 May 2008 21:20:42 +0200 Subject: ftrace: add basic support for gcc profiler instrumentation If CONFIG_FTRACE is selected and /proc/sys/kernel/ftrace_enabled is set to a non-zero value the ftrace routine will be called everytime we enter a kernel function that is not marked with the "notrace" attribute. The ftrace routine will then call a registered function if a function happens to be registered. [ This code has been highly hacked by Steven Rostedt and Ingo Molnar, so don't blame Arnaldo for all of this ;-) ] Update: It is now possible to register more than one ftrace function. If only one ftrace function is registered, that will be the function that ftrace calls directly. If more than one function is registered, then ftrace will call a function that will loop through the functions to call. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- Makefile | 4 ++ arch/x86/Kconfig | 1 + arch/x86/kernel/entry_32.S | 27 +++++++++ arch/x86/kernel/entry_64.S | 37 ++++++++++++ include/linux/ftrace.h | 38 +++++++++++++ kernel/Makefile | 1 + kernel/trace/Kconfig | 5 ++ kernel/trace/Makefile | 3 + kernel/trace/ftrace.c | 138 +++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 2 + 10 files changed, 256 insertions(+) create mode 100644 include/linux/ftrace.h create mode 100644 kernel/trace/Kconfig create mode 100644 kernel/trace/Makefile create mode 100644 kernel/trace/ftrace.c (limited to 'lib') diff --git a/Makefile b/Makefile index 20b32351906b..b4a273f19b52 100644 --- a/Makefile +++ b/Makefile @@ -528,6 +528,10 @@ KBUILD_CFLAGS += -g KBUILD_AFLAGS += -gdwarf-2 endif +ifdef CONFIG_FTRACE +KBUILD_CFLAGS += -pg +endif + # We trigger additional mismatches with less inlining ifdef CONFIG_DEBUG_SECTION_MISMATCH KBUILD_CFLAGS += $(call cc-option, -fno-inline-functions-called-once) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fe361ae7ef2f..c742dfeb0dbe 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -23,6 +23,7 @@ config X86 select HAVE_OPROFILE select HAVE_KPROBES select HAVE_KRETPROBES + select HAVE_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 2a609dc3271c..f47b9b5440d2 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -1109,6 +1109,33 @@ ENDPROC(xen_failsafe_callback) #endif /* CONFIG_XEN */ +#ifdef CONFIG_FTRACE +ENTRY(mcount) + cmpl $ftrace_stub, ftrace_trace_function + jnz trace + +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +trace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + + jmp ftrace_stub +END(mcount) +#endif + .section .rodata,"a" #include "syscall_table_32.S" diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 556a8df522a7..f046e0c64883 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -54,6 +54,43 @@ .code64 +#ifdef CONFIG_FTRACE +ENTRY(mcount) + cmpq $ftrace_stub, ftrace_trace_function + jnz trace +.globl ftrace_stub +ftrace_stub: + retq + +trace: + /* taken from glibc */ + subq $0x38, %rsp + movq %rax, (%rsp) + movq %rcx, 8(%rsp) + movq %rdx, 16(%rsp) + movq %rsi, 24(%rsp) + movq %rdi, 32(%rsp) + movq %r8, 40(%rsp) + movq %r9, 48(%rsp) + + movq 0x38(%rsp), %rdi + movq 8(%rbp), %rsi + + call *ftrace_trace_function + + movq 48(%rsp), %r9 + movq 40(%rsp), %r8 + movq 32(%rsp), %rdi + movq 24(%rsp), %rsi + movq 16(%rsp), %rdx + movq 8(%rsp), %rcx + movq (%rsp), %rax + addq $0x38, %rsp + + jmp ftrace_stub +END(mcount) +#endif + #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args #endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h new file mode 100644 index 000000000000..b96ef14c249a --- /dev/null +++ b/include/linux/ftrace.h @@ -0,0 +1,38 @@ +#ifndef _LINUX_FTRACE_H +#define _LINUX_FTRACE_H + +#ifdef CONFIG_FTRACE + +#include + +#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) +#define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1)) +#define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2)) + +typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); + +struct ftrace_ops { + ftrace_func_t func; + struct ftrace_ops *next; +}; + +/* + * The ftrace_ops must be a static and should also + * be read_mostly. These functions do modify read_mostly variables + * so use them sparely. Never free an ftrace_op or modify the + * next pointer after it has been registered. Even after unregistering + * it, the next pointer may still be used internally. + */ +int register_ftrace_function(struct ftrace_ops *ops); +int unregister_ftrace_function(struct ftrace_ops *ops); +void clear_ftrace_function(void); + +extern void ftrace_stub(unsigned long a0, unsigned long a1); +extern void mcount(void); + +#else /* !CONFIG_FTRACE */ +# define register_ftrace_function(ops) do { } while (0) +# define unregister_ftrace_function(ops) do { } while (0) +# define clear_ftrace_function(ops) do { } while (0) +#endif /* CONFIG_FTRACE */ +#endif /* _LINUX_FTRACE_H */ diff --git a/kernel/Makefile b/kernel/Makefile index 1c9938addb9d..fa05f6d8bdbf 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_MARKERS) += marker.o obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_FTRACE) += trace/ ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) # According to Alan Modra , the -fno-omit-frame-pointer is diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig new file mode 100644 index 000000000000..8185c91417bc --- /dev/null +++ b/kernel/trace/Kconfig @@ -0,0 +1,5 @@ +# +# Architectures that offer an FTRACE implementation should select HAVE_FTRACE: +# +config HAVE_FTRACE + bool diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile new file mode 100644 index 000000000000..bf4fd215a6a9 --- /dev/null +++ b/kernel/trace/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_FTRACE) += libftrace.o + +libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c new file mode 100644 index 000000000000..b6a80b98a3fb --- /dev/null +++ b/kernel/trace/ftrace.c @@ -0,0 +1,138 @@ +/* + * Infrastructure for profiling code inserted by 'gcc -pg'. + * + * Copyright (C) 2007-2008 Steven Rostedt + * Copyright (C) 2004-2008 Ingo Molnar + * + * Originally ported from the -rt patch by: + * Copyright (C) 2007 Arnaldo Carvalho de Melo + * + * Based on code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ + +#include +#include + +static DEFINE_SPINLOCK(ftrace_func_lock); +static struct ftrace_ops ftrace_list_end __read_mostly = +{ + .func = ftrace_stub, +}; + +static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; +ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; + +/* mcount is defined per arch in assembly */ +EXPORT_SYMBOL(mcount); + +notrace void ftrace_list_func(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_ops *op = ftrace_list; + + /* in case someone actually ports this to alpha! */ + read_barrier_depends(); + + while (op != &ftrace_list_end) { + /* silly alpha */ + read_barrier_depends(); + op->func(ip, parent_ip); + op = op->next; + }; +} + +/** + * register_ftrace_function - register a function for profiling + * @ops - ops structure that holds the function for profiling. + * + * Register a function to be called by all functions in the + * kernel. + * + * Note: @ops->func and all the functions it calls must be labeled + * with "notrace", otherwise it will go into a + * recursive loop. + */ +int register_ftrace_function(struct ftrace_ops *ops) +{ + unsigned long flags; + + spin_lock_irqsave(&ftrace_func_lock, flags); + ops->next = ftrace_list; + /* + * We are entering ops into the ftrace_list but another + * CPU might be walking that list. We need to make sure + * the ops->next pointer is valid before another CPU sees + * the ops pointer included into the ftrace_list. + */ + smp_wmb(); + ftrace_list = ops; + /* + * For one func, simply call it directly. + * For more than one func, call the chain. + */ + if (ops->next == &ftrace_list_end) + ftrace_trace_function = ops->func; + else + ftrace_trace_function = ftrace_list_func; + spin_unlock_irqrestore(&ftrace_func_lock, flags); + + return 0; +} + +/** + * unregister_ftrace_function - unresgister a function for profiling. + * @ops - ops structure that holds the function to unregister + * + * Unregister a function that was added to be called by ftrace profiling. + */ +int unregister_ftrace_function(struct ftrace_ops *ops) +{ + unsigned long flags; + struct ftrace_ops **p; + int ret = 0; + + spin_lock_irqsave(&ftrace_func_lock, flags); + + /* + * If we are the only function, then the ftrace pointer is + * pointing directly to that function. + */ + if (ftrace_list == ops && ops->next == &ftrace_list_end) { + ftrace_trace_function = ftrace_stub; + ftrace_list = &ftrace_list_end; + goto out; + } + + for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next) + if (*p == ops) + break; + + if (*p != ops) { + ret = -1; + goto out; + } + + *p = (*p)->next; + + /* If we only have one func left, then call that directly */ + if (ftrace_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_list->func; + + out: + spin_unlock_irqrestore(&ftrace_func_lock, flags); + + return 0; +} + +/** + * clear_ftrace_function - reset the ftrace function + * + * This NULLs the ftrace function and in essence stops + * tracing. There may be lag + */ +void clear_ftrace_function(void) +{ + ftrace_trace_function = ftrace_stub; +} diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d2099f41aa1e..d8b6279a9b42 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -634,6 +634,8 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. +source kernel/trace/Kconfig + config PROVIDE_OHCI1394_DMA_INIT bool "Remote debugging over FireWire early on boot" depends on PCI && X86 -- cgit v1.2.3 From 5568b139f4d196273958ae2947a736fdf1ffeece Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:44 +0200 Subject: ftrace: debug smp_processor_id, use notrace preempt disable The debug smp_processor_id caused a recursive fault in debugging the irqsoff tracer. The tracer used a smp_processor_id in the ftrace callback, and this function called preempt_disable which also is traced. This caused a recursive fault (stack overload). Since using smp_processor_id without debugging on does not cause faults with the tracer (even when the tracer is wrong), the debug version should not cause a system reboot. This changes the debug_smp_processor_id to use the notrace versions of preempt_disable and enable. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/smp_processor_id.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index e555ab62fbad..3b4dc098181e 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -37,7 +37,7 @@ notrace unsigned int debug_smp_processor_id(void) /* * Avoid recursion: */ - preempt_disable(); + preempt_disable_notrace(); if (!printk_ratelimit()) goto out_enable; @@ -49,7 +49,7 @@ notrace unsigned int debug_smp_processor_id(void) dump_stack(); out_enable: - preempt_enable_no_resched(); + preempt_enable_no_resched_notrace(); out: return this_cpu; } -- cgit v1.2.3 From 3594136ad67a54d77bcb2547e70011754a2f91d5 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:50 +0200 Subject: ftrace: do not profile lib/string.o Most archs define the string and memory compare functions in assembly. Some do not. But these functions may be used in some archs at early boot up. Since most archs define this code in assembly and they are not usually traced, there's no need to trace them when they are not defined in assembly. This patch removes the -pg from the CFLAGS for lib/string.o. This prevents the string functions use in either vdso or early bootup from crashing the system. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/Makefile | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 74b0cfb1fcc3..6ca9e6ee1e33 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -8,6 +8,14 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o +ifdef CONFIG_FTRACE +# Do not profile string.o, since it may be used in early boot or vdso +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(if $(subst string,,$(basename $(notdir $@))), \ + $(ORIG_CFLAGS), \ + $(subst -pg,,$(ORIG_CFLAGS))) +endif + lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o -- cgit v1.2.3 From 9d0a420b737f72d84fabebf29634d800cbf54538 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 12 May 2008 21:20:55 +0200 Subject: ftrace: remove function tracing from spinlock debug The debug functions in spin_lock debugging pollute the output of the function tracer. This patch adds the debug files in the lib director to those that should not be compiled with mcount tracing. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 6ca9e6ee1e33..d97ad1100b6f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -10,8 +10,9 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ ifdef CONFIG_FTRACE # Do not profile string.o, since it may be used in early boot or vdso +# Also do not profile any debug utilities ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(if $(subst string,,$(basename $(notdir $@))), \ +KBUILD_CFLAGS = $(if $(filter-out %debug debug% string%,$(basename $(notdir $@))), \ $(ORIG_CFLAGS), \ $(subst -pg,,$(ORIG_CFLAGS))) endif -- cgit v1.2.3 From 654e4787689faffdd2137fe91f59fd3ef3363ad2 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 14 May 2008 21:30:31 -0400 Subject: ftrace: use the new kbuild CFLAGS_REMOVE for lib directory This patch removes the Makefile turd and uses the nice CFLAGS_REMOVE macro in the lib directory. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/Makefile | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index d97ad1100b6f..4b836a53c08f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -10,11 +10,11 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ ifdef CONFIG_FTRACE # Do not profile string.o, since it may be used in early boot or vdso +CFLAGS_REMOVE_string.o = -pg # Also do not profile any debug utilities -ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(if $(filter-out %debug debug% string%,$(basename $(notdir $@))), \ - $(ORIG_CFLAGS), \ - $(subst -pg,,$(ORIG_CFLAGS))) +CFLAGS_REMOVE_spinlock_debug.o = -pg +CFLAGS_REMOVE_list_debug.o = -pg +CFLAGS_REMOVE_debugobjects.o = -pg endif lib-$(CONFIG_MMU) += ioremap.o -- cgit v1.2.3 From 9c44bc03fff44ff04237a7d92e35304a0e50c331 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 21:21:04 +0200 Subject: softlockup: allow panic on lockup allow users to configure the softlockup detector to generate a panic instead of a warning message. high-availability systems might opt for this strict method (combined with panic_timeout= boot option/sysctl), instead of generating softlockup warnings ad infinitum. also, automated tests work better if the system reboots reliably (into a safe kernel) in case of a lockup. The full spectrum of configurability is supported: boot option, sysctl option and Kconfig option. it's default-disabled. Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- Documentation/kernel-parameters.txt | 3 +++ include/linux/sched.h | 3 ++- kernel/softlockup.c | 21 +++++++++++++++++++++ kernel/sysctl.c | 11 +++++++++++ lib/Kconfig.debug | 26 +++++++++++++++++++++++++- 5 files changed, 62 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index e07c432c731f..042588fa12e5 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1971,6 +1971,9 @@ and is between 256 and 4096 characters. It is defined in the file snd-ymfpci= [HW,ALSA] + softlockup_panic= + [KNL] Should the soft-lockup detector generate panics. + sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/sonypi.txt diff --git a/include/linux/sched.h b/include/linux/sched.h index 5395a6176f4b..71f5972dc48e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -294,7 +294,8 @@ extern void softlockup_tick(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); -extern unsigned long softlockup_thresh; +extern unsigned int softlockup_panic; +extern unsigned long softlockup_thresh; extern unsigned long sysctl_hung_task_check_count; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_warnings; diff --git a/kernel/softlockup.c b/kernel/softlockup.c index 01b6522fd92b..78e0ad21cb0c 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -27,6 +27,21 @@ static DEFINE_PER_CPU(struct task_struct *, watchdog_task); static int __read_mostly did_panic; unsigned long __read_mostly softlockup_thresh = 60; +/* + * Should we panic (and reboot, if panic_timeout= is set) when a + * soft-lockup occurs: + */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; + +static int __init softlockup_panic_setup(char *str) +{ + softlockup_panic = simple_strtoul(str, NULL, 0); + + return 1; +} +__setup("softlockup_panic=", softlockup_panic_setup); + static int softlock_panic(struct notifier_block *this, unsigned long event, void *ptr) { @@ -120,6 +135,9 @@ void softlockup_tick(void) else dump_stack(); spin_unlock(&print_lock); + + if (softlockup_panic) + panic("softlockup: hung tasks"); } /* @@ -172,6 +190,9 @@ static void check_hung_task(struct task_struct *t, unsigned long now) t->last_switch_timestamp = now; touch_nmi_watchdog(); + + if (softlockup_panic) + panic("softlockup: blocked tasks"); } /* diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 29116652dca8..2d3b388c402d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -727,6 +727,17 @@ static struct ctl_table kern_table[] = { }, #endif #ifdef CONFIG_DETECT_SOFTLOCKUP + { + .ctl_name = CTL_UNNUMBERED, + .procname = "softlockup_panic", + .data = &softlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + .strategy = &sysctl_intvec, + .extra1 = &zero, + .extra2 = &one, + }, { .ctl_name = CTL_UNNUMBERED, .procname = "softlockup_thresh", diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d2099f41aa1e..509ae35a9ef5 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -147,7 +147,7 @@ config DETECT_SOFTLOCKUP help Say Y here to enable the kernel to detect "soft lockups", which are bugs that cause the kernel to loop in kernel - mode for more than 10 seconds, without giving other tasks a + mode for more than 60 seconds, without giving other tasks a chance to run. When a soft-lockup is detected, the kernel will print the @@ -159,6 +159,30 @@ config DETECT_SOFTLOCKUP can be detected via the NMI-watchdog, on platforms that support it.) +config BOOTPARAM_SOFTLOCKUP_PANIC + bool "Panic (Reboot) On Soft Lockups" + depends on DETECT_SOFTLOCKUP + help + Say Y here to enable the kernel to panic on "soft lockups", + which are bugs that cause the kernel to loop in kernel + mode for more than 60 seconds, without giving other tasks a + chance to run. + + The panic can be used in combination with panic_timeout, + to cause the system to reboot automatically after a + lockup has been detected. This feature is useful for + high-availability systems that have uptime guarantees and + where a lockup must be resolved ASAP. + + Say N if unsure. + +config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE + int + depends on DETECT_SOFTLOCKUP + range 0 1 + default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC + default 1 if BOOTPARAM_SOFTLOCKUP_PANIC + config SCHED_DEBUG bool "Collect scheduler debugging info" depends on DEBUG_KERNEL && PROC_FS -- cgit v1.2.3 From 886dd58258e6ddebe20e7aebef7b167a24bad7ee Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 12 May 2008 15:44:38 +0200 Subject: debugging: make stacktrace independent from DEBUG_KERNEL Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/Kconfig.debug | 1 - 1 file changed, 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d2099f41aa1e..9c17fb9d1d5e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -419,7 +419,6 @@ config DEBUG_LOCKING_API_SELFTESTS config STACKTRACE bool - depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT config DEBUG_KOBJECT -- cgit v1.2.3 From 8344b568f5bdc7ee1bba909de3294c6348c36056 Mon Sep 17 00:00:00 2001 From: Alex Chiang Date: Tue, 10 Jun 2008 15:30:42 -0600 Subject: PCI: ACPI PCI slot detection driver Detect all physical PCI slots as described by ACPI, and create entries in /sys/bus/pci/slots/. Not all physical slots are hotpluggable, and the acpiphp module does not detect them. Now we know the physical PCI geography of our system, without caring about hotplug. [kaneshige.kenji@jp.fujitsu.com: export-kobject_rename-for-pci_hotplug_core] Signed-off-by: Kenji Kaneshige Acked-by: Greg KH [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix build with CONFIG_DMI=n] Signed-off-by: Alex Chiang Cc: Greg KH Cc: Kristen Carlson Accardi Cc: Len Brown Acked-by: Len Brown Acked-by: Kenji Kaneshige Signed-off-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Jesse Barnes --- drivers/acpi/Kconfig | 9 + drivers/acpi/Makefile | 1 + drivers/acpi/pci_slot.c | 368 +++++++++++++++++++++++++++++++++ drivers/pci/hotplug/pci_hotplug_core.c | 16 ++ drivers/pci/hotplug/sgi_hotplug.c | 2 +- lib/kobject.c | 1 + 6 files changed, 396 insertions(+), 1 deletion(-) create mode 100644 drivers/acpi/pci_slot.c (limited to 'lib') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index c52fca833268..250d41a24f78 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -338,6 +338,15 @@ config ACPI_EC the battery and thermal drivers. If you are compiling for a mobile system, say Y. +config ACPI_PCI_SLOT + tristate "PCI slot detection driver" + default n + help + This driver will attempt to discover all PCI slots in your system, + and creates entries in /sys/bus/pci/slots/. This feature can + help you correlate PCI bus addresses with the physical geography + of your slots. If you are unsure, say N. + config ACPI_POWER bool default y diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 40b0fcae4c78..579c29c0665f 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_ACPI_DOCK) += dock.o obj-$(CONFIG_ACPI_BAY) += bay.o obj-$(CONFIG_ACPI_VIDEO) += video.o obj-y += pci_root.o pci_link.o pci_irq.o pci_bind.o +obj-$(CONFIG_ACPI_PCI_SLOT) += pci_slot.o obj-$(CONFIG_ACPI_POWER) += power.o obj-$(CONFIG_ACPI_PROCESSOR) += processor.o obj-$(CONFIG_ACPI_CONTAINER) += container.o diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c new file mode 100644 index 000000000000..b9ab030a52d5 --- /dev/null +++ b/drivers/acpi/pci_slot.c @@ -0,0 +1,368 @@ +/* + * pci_slot.c - ACPI PCI Slot Driver + * + * The code here is heavily leveraged from the acpiphp module. + * Thanks to Matthew Wilcox for much guidance. + * Thanks to Kenji Kaneshige for code + * review and fixes. + * + * Copyright (C) 2007 Alex Chiang + * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static int debug; +static int check_sta_before_sun; + +#define DRIVER_VERSION "0.1" +#define DRIVER_AUTHOR "Alex Chiang " +#define DRIVER_DESC "ACPI PCI Slot Detection Driver" +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL"); +MODULE_PARM_DESC(debug, "Debugging mode enabled or not"); +module_param(debug, bool, 0644); + +#define _COMPONENT ACPI_PCI_COMPONENT +ACPI_MODULE_NAME("pci_slot"); + +#define MY_NAME "pci_slot" +#define err(format, arg...) printk(KERN_ERR "%s: " format , MY_NAME , ## arg) +#define info(format, arg...) printk(KERN_INFO "%s: " format , MY_NAME , ## arg) +#define dbg(format, arg...) \ + do { \ + if (debug) \ + printk(KERN_DEBUG "%s: " format, \ + MY_NAME , ## arg); \ + } while (0) + +#define SLOT_NAME_SIZE 20 /* Inspired by #define in acpiphp.h */ + +struct acpi_pci_slot { + acpi_handle root_handle; /* handle of the root bridge */ + struct pci_slot *pci_slot; /* corresponding pci_slot */ + struct list_head list; /* node in the list of slots */ +}; + +static int acpi_pci_slot_add(acpi_handle handle); +static void acpi_pci_slot_remove(acpi_handle handle); + +static LIST_HEAD(slot_list); +static DEFINE_MUTEX(slot_list_lock); +static struct acpi_pci_driver acpi_pci_slot_driver = { + .add = acpi_pci_slot_add, + .remove = acpi_pci_slot_remove, +}; + +static int +check_slot(acpi_handle handle, int *device, unsigned long *sun) +{ + int retval = 0; + unsigned long adr, sta; + acpi_status status; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + + acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer); + dbg("Checking slot on path: %s\n", (char *)buffer.pointer); + + if (check_sta_before_sun) { + /* If SxFy doesn't have _STA, we just assume it's there */ + status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); + if (ACPI_SUCCESS(status) && !(sta & ACPI_STA_DEVICE_PRESENT)) { + retval = -1; + goto out; + } + } + + status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr); + if (ACPI_FAILURE(status)) { + dbg("_ADR returned %d on %s\n", status, (char *)buffer.pointer); + retval = -1; + goto out; + } + + *device = (adr >> 16) & 0xffff; + + /* No _SUN == not a slot == bail */ + status = acpi_evaluate_integer(handle, "_SUN", NULL, sun); + if (ACPI_FAILURE(status)) { + dbg("_SUN returned %d on %s\n", status, (char *)buffer.pointer); + retval = -1; + goto out; + } + +out: + kfree(buffer.pointer); + return retval; +} + +struct callback_args { + acpi_walk_callback user_function; /* only for walk_p2p_bridge */ + struct pci_bus *pci_bus; + acpi_handle root_handle; +}; + +/* + * register_slot + * + * Called once for each SxFy object in the namespace. Don't worry about + * calling pci_create_slot multiple times for the same pci_bus:device, + * since each subsequent call simply bumps the refcount on the pci_slot. + * + * The number of calls to pci_destroy_slot from unregister_slot is + * symmetrical. + */ +static acpi_status +register_slot(acpi_handle handle, u32 lvl, void *context, void **rv) +{ + int device; + unsigned long sun; + char name[SLOT_NAME_SIZE]; + struct acpi_pci_slot *slot; + struct pci_slot *pci_slot; + struct callback_args *parent_context = context; + struct pci_bus *pci_bus = parent_context->pci_bus; + + if (check_slot(handle, &device, &sun)) + return AE_OK; + + slot = kmalloc(sizeof(*slot), GFP_KERNEL); + if (!slot) { + err("%s: cannot allocate memory\n", __func__); + return AE_OK; + } + + snprintf(name, sizeof(name), "%u", (u32)sun); + pci_slot = pci_create_slot(pci_bus, device, name); + if (IS_ERR(pci_slot)) { + err("pci_create_slot returned %ld\n", PTR_ERR(pci_slot)); + kfree(slot); + } + + slot->root_handle = parent_context->root_handle; + slot->pci_slot = pci_slot; + INIT_LIST_HEAD(&slot->list); + mutex_lock(&slot_list_lock); + list_add(&slot->list, &slot_list); + mutex_unlock(&slot_list_lock); + + dbg("pci_slot: %p, pci_bus: %x, device: %d, name: %s\n", + pci_slot, pci_bus->number, device, name); + + return AE_OK; +} + +/* + * walk_p2p_bridge - discover and walk p2p bridges + * @handle: points to an acpi_pci_root + * @context: p2p_bridge_context pointer + * + * Note that when we call ourselves recursively, we pass a different + * value of pci_bus in the child_context. + */ +static acpi_status +walk_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv) +{ + int device, function; + unsigned long adr; + acpi_status status; + acpi_handle dummy_handle; + acpi_walk_callback user_function; + + struct pci_dev *dev; + struct pci_bus *pci_bus; + struct callback_args child_context; + struct callback_args *parent_context = context; + + pci_bus = parent_context->pci_bus; + user_function = parent_context->user_function; + + status = acpi_get_handle(handle, "_ADR", &dummy_handle); + if (ACPI_FAILURE(status)) + return AE_OK; + + status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr); + if (ACPI_FAILURE(status)) + return AE_OK; + + device = (adr >> 16) & 0xffff; + function = adr & 0xffff; + + dev = pci_get_slot(pci_bus, PCI_DEVFN(device, function)); + if (!dev || !dev->subordinate) + goto out; + + child_context.pci_bus = dev->subordinate; + child_context.user_function = user_function; + child_context.root_handle = parent_context->root_handle; + + dbg("p2p bridge walk, pci_bus = %x\n", dev->subordinate->number); + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, + user_function, &child_context, NULL); + if (ACPI_FAILURE(status)) + goto out; + + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, + walk_p2p_bridge, &child_context, NULL); +out: + pci_dev_put(dev); + return AE_OK; +} + +/* + * walk_root_bridge - generic root bridge walker + * @handle: points to an acpi_pci_root + * @user_function: user callback for slot objects + * + * Call user_function for all objects underneath this root bridge. + * Walk p2p bridges underneath us and call user_function on those too. + */ +static int +walk_root_bridge(acpi_handle handle, acpi_walk_callback user_function) +{ + int seg, bus; + unsigned long tmp; + acpi_status status; + acpi_handle dummy_handle; + struct pci_bus *pci_bus; + struct callback_args context; + + /* If the bridge doesn't have _STA, we assume it is always there */ + status = acpi_get_handle(handle, "_STA", &dummy_handle); + if (ACPI_SUCCESS(status)) { + status = acpi_evaluate_integer(handle, "_STA", NULL, &tmp); + if (ACPI_FAILURE(status)) { + info("%s: _STA evaluation failure\n", __func__); + return 0; + } + if ((tmp & ACPI_STA_DEVICE_FUNCTIONING) == 0) + /* don't register this object */ + return 0; + } + + status = acpi_evaluate_integer(handle, "_SEG", NULL, &tmp); + seg = ACPI_SUCCESS(status) ? tmp : 0; + + status = acpi_evaluate_integer(handle, "_BBN", NULL, &tmp); + bus = ACPI_SUCCESS(status) ? tmp : 0; + + pci_bus = pci_find_bus(seg, bus); + if (!pci_bus) + return 0; + + context.pci_bus = pci_bus; + context.user_function = user_function; + context.root_handle = handle; + + dbg("root bridge walk, pci_bus = %x\n", pci_bus->number); + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, + user_function, &context, NULL); + if (ACPI_FAILURE(status)) + return status; + + status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1, + walk_p2p_bridge, &context, NULL); + if (ACPI_FAILURE(status)) + err("%s: walk_p2p_bridge failure - %d\n", __func__, status); + + return status; +} + +/* + * acpi_pci_slot_add + * @handle: points to an acpi_pci_root + */ +static int +acpi_pci_slot_add(acpi_handle handle) +{ + acpi_status status; + + status = walk_root_bridge(handle, register_slot); + if (ACPI_FAILURE(status)) + err("%s: register_slot failure - %d\n", __func__, status); + + return status; +} + +/* + * acpi_pci_slot_remove + * @handle: points to an acpi_pci_root + */ +static void +acpi_pci_slot_remove(acpi_handle handle) +{ + struct acpi_pci_slot *slot, *tmp; + + mutex_lock(&slot_list_lock); + list_for_each_entry_safe(slot, tmp, &slot_list, list) { + if (slot->root_handle == handle) { + list_del(&slot->list); + pci_destroy_slot(slot->pci_slot); + kfree(slot); + } + } + mutex_unlock(&slot_list_lock); +} + +static int do_sta_before_sun(const struct dmi_system_id *d) +{ + info("%s detected: will evaluate _STA before calling _SUN\n", d->ident); + check_sta_before_sun = 1; + return 0; +} + +static struct dmi_system_id acpi_pci_slot_dmi_table[] __initdata = { + /* + * Fujitsu Primequest machines will return 1023 to indicate an + * error if the _SUN method is evaluated on SxFy objects that + * are not present (as indicated by _STA), so for those machines, + * we want to check _STA before evaluating _SUN. + */ + { + .callback = do_sta_before_sun, + .ident = "Fujitsu PRIMEQUEST", + .matches = { + DMI_MATCH(DMI_BIOS_VENDOR, "FUJITSU LIMITED"), + DMI_MATCH(DMI_BIOS_VERSION, "PRIMEQUEST"), + }, + }, + {} +}; + +static int __init +acpi_pci_slot_init(void) +{ + dmi_check_system(acpi_pci_slot_dmi_table); + acpi_pci_register_driver(&acpi_pci_slot_driver); + return 0; +} + +static void __exit +acpi_pci_slot_exit(void) +{ + acpi_pci_unregister_driver(&acpi_pci_slot_driver); +} + +module_init(acpi_pci_slot_init); +module_exit(acpi_pci_slot_exit); diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index 4df31f375197..b3b2d8cf4370 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -572,6 +572,11 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr) if (tmp) return -EEXIST; + /* + * No problems if we call this interface from both ACPI_PCI_SLOT + * driver and call it here again. If we've already created the + * pci_slot, the interface will simply bump the refcount. + */ pci_slot = pci_create_slot(bus, slot_nr, slot->name); if (IS_ERR(pci_slot)) return PTR_ERR(pci_slot); @@ -585,6 +590,17 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr) slot->pci_slot = pci_slot; pci_slot->hotplug = slot; + /* + * Allow pcihp drivers to override the ACPI_PCI_SLOT name. + */ + if (strcmp(kobject_name(&pci_slot->kobj), slot->name)) { + result = kobject_rename(&pci_slot->kobj, slot->name); + if (result) { + pci_destroy_slot(pci_slot); + return result; + } + } + spin_lock(&pci_hotplug_slot_list_lock); list_add(&slot->slot_list, &pci_hotplug_slot_list); spin_unlock(&pci_hotplug_slot_list_lock); diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index 2036a43ff2fd..410fe0394a8e 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -668,7 +668,7 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus) register_err: dev_dbg(&pci_bus->self->dev, "bus failed to register with err = %d\n", - rc); + rc); alloc_err: if (rc == -ENOMEM) diff --git a/lib/kobject.c b/lib/kobject.c index 718e5101c263..dcade0543bd2 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -439,6 +439,7 @@ out: return error; } +EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move - move object to another parent -- cgit v1.2.3 From 1462a200057df08be12f3719e1f37adbd2c6e4d0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 16 Jun 2008 08:40:04 +0200 Subject: Revert "prohibit rcutorture from being compiled into the kernel" This reverts commit 9aaffc898ff4a3df18c5fc4b9e0fa47e779ad726. That commit was a very bad idea. RCU_TORTURE found many boot timing bugs and other sorts of bugs in the past, so excluding it from boot images is very silly. The option already depends on DEBUG_KERNEL and is disabled by default. Even when it runs, the test threads are reniced. If it annoys people we could add a runtime sysctl. --- lib/Kconfig.debug | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d2099f41aa1e..f51ba2fa2662 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -531,13 +531,14 @@ config BOOT_PRINTK_DELAY config RCU_TORTURE_TEST tristate "torture tests for RCU" depends on DEBUG_KERNEL - depends on m default n help This option provides a kernel module that runs torture tests on the RCU infrastructure. The kernel module may be built after the fact on the running kernel to be tested, if desired. + Say Y here if you want RCU torture tests to start automatically + at boot time (you probably don't). Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. -- cgit v1.2.3 From 31a72bce0bd6f3e0114009288bccbc96376eeeca Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 18 Jun 2008 09:26:49 -0700 Subject: rcu: make rcutorture more vicious: reinstate boot-time testing This patch re-institutes the ability to build rcutorture directly into the Linux kernel. The reason that this capability was removed was that this could result in your kernel being pretty much useless, as rcutorture would be running starting from early boot. This problem has been avoided by (1) making rcutorture run only three seconds of every six by default, (2) adding a CONFIG_RCU_TORTURE_TEST_RUNNABLE that permits rcutorture to be quiesced at boot time, and (3) adding a sysctl in /proc named /proc/sys/kernel/rcutorture_runnable that permits rcutorture to be quiesced and unquiesced when built into the kernel. Please note that this /proc file is -not- available when rcutorture is built as a module. Please also note that to get the earlier take-no-prisoners behavior, you must use the boot command line to set rcutorture's "stutter" parameter to zero. The rcutorture quiescing mechanism is currently quite crude: loops in each rcutorture process that poll a global variable once per tick. Suggestions for improvement are welcome. The default action will be to reduce the polling rate to a few times per second. Signed-off-by: Paul E. McKenney Suggested-by: Ingo Molnar Signed-off-by: Ingo Molnar --- Documentation/RCU/torture.txt | 21 ++++++++++++++------- kernel/rcutorture.c | 9 ++++++++- kernel/sysctl.c | 13 +++++++++++++ lib/Kconfig.debug | 21 +++++++++++++++++++-- 4 files changed, 54 insertions(+), 10 deletions(-) (limited to 'lib') diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 02b3d14c0209..516527d4bc55 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -10,13 +10,20 @@ status messages via printk(), which can be examined via the dmesg command (perhaps grepping for "torture"). The test is started when the module is loaded, and stops when the module is unloaded. -However, actually setting this config option to "y" results in the system -running the test immediately upon boot, and ending only when the system -is taken down. Normally, one will instead want to build the system -with CONFIG_RCU_TORTURE_TEST=m and to use modprobe and rmmod to control -the test, perhaps using a script similar to the one shown at the end of -this document. Note that you will need CONFIG_MODULE_UNLOAD in order -to be able to end the test. +CONFIG_RCU_TORTURE_TEST_RUNNABLE + +It is also possible to specify CONFIG_RCU_TORTURE_TEST=y, which will +result in the tests being loaded into the base kernel. In this case, +the CONFIG_RCU_TORTURE_TEST_RUNNABLE config option is used to specify +whether the RCU torture tests are to be started immediately during +boot or whether the /proc/sys/kernel/rcutorture_runnable file is used +to enable them. This /proc file can be used to repeatedly pause and +restart the tests, regardless of the initial state specified by the +CONFIG_RCU_TORTURE_TEST_RUNNABLE config option. + +You will normally -not- want to start the RCU torture tests during boot +(and thus the default is CONFIG_RCU_TORTURE_TEST_RUNNABLE=n), but doing +this can sometimes be useful in finding boot-time bugs. MODULE PARAMETERS diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 98ae7d168225..27003e2421c7 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -125,6 +125,13 @@ static struct list_head rcu_torture_removed; static int stutter_pause_test = 0; +#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) +#define RCUTORTURE_RUNNABLE_INIT 1 +#else +#define RCUTORTURE_RUNNABLE_INIT 0 +#endif +int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; + /* * Allocate an element from the rcu_tortures pool. */ @@ -188,7 +195,7 @@ rcu_random(struct rcu_random_state *rrsp) static void rcu_stutter_wait(void) { - while (stutter_pause_test) + while (stutter_pause_test || !rcutorture_runnable) schedule_timeout_interruptible(1); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 29116652dca8..c6887cf135c8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -82,6 +82,9 @@ extern int maps_protect; extern int sysctl_stat_interval; extern int latencytop_enabled; extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifdef CONFIG_RCU_TORTURE_TEST +extern int rcutorture_runnable; +#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ /* Constants used for minimum and maximum */ #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM) @@ -813,6 +816,16 @@ static struct ctl_table kern_table[] = { .child = key_sysctls, }, #endif +#ifdef CONFIG_RCU_TORTURE_TEST + { + .ctl_name = CTL_UNNUMBERED, + .procname = "rcutorture_runnable", + .data = &rcutorture_runnable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f51ba2fa2662..c35a86a516a0 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -537,11 +537,28 @@ config RCU_TORTURE_TEST on the RCU infrastructure. The kernel module may be built after the fact on the running kernel to be tested, if desired. - Say Y here if you want RCU torture tests to start automatically - at boot time (you probably don't). + Say Y here if you want RCU torture tests to be built into + the kernel. Say M if you want the RCU torture tests to build as a module. Say N if you are unsure. +config RCU_TORTURE_TEST_RUNNABLE + bool "torture tests for RCU runnable by default" + depends on RCU_TORTURE_TEST = y + default n + help + This option provides a way to build the RCU torture tests + directly into the kernel without them starting up at boot + time. You can use /proc/sys/kernel/rcutorture_runnable + to manually override this setting. This /proc file is + available only when the RCU torture tests have been built + into the kernel. + + Say Y here if you want the RCU torture tests to start during + boot (you probably don't). + Say N here if you want the RCU torture tests to start only + after being manually enabled via /proc. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL -- cgit v1.2.3 From ad118c54a3587b2c69a769d0ba37d4d8dce4559d Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Fri, 27 Jun 2008 18:04:48 +0200 Subject: stacktrace: add saved stack traces to backtrace self-test This patch adds saved stack-traces to the backtrace suite of self-tests. Note that we don't depend on or unconditionally enable CONFIG_STACKTRACE because not all architectures may have it (and we still want to enable the other tests for those architectures). Cc: Arjan van de Ven Signed-off-by: Vegard Nossum Cc: Arjan van de Ven Cc: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/backtracetest.c | 30 +++++++++++++++++++++++++++++- lib/Kconfig.debug | 3 +++ 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c index d1a7605c5b8f..50f7abd0813d 100644 --- a/kernel/backtracetest.c +++ b/kernel/backtracetest.c @@ -10,9 +10,10 @@ * of the License. */ +#include #include #include -#include +#include static struct timer_list backtrace_timer; @@ -22,6 +23,31 @@ static void backtrace_test_timer(unsigned long data) printk("The following trace is a kernel self test and not a bug!\n"); dump_stack(); } + +#ifdef CONFIG_STACKTRACE +static void backtrace_test_saved(void) +{ + struct stack_trace trace; + unsigned long entries[8]; + + printk("Testing a saved backtrace.\n"); + printk("The following trace is a kernel self test and not a bug!\n"); + + trace.nr_entries = 0; + trace.max_entries = ARRAY_SIZE(entries); + trace.entries = entries; + trace.skip = 0; + + save_stack_trace(&trace); + print_stack_trace(&trace, 0); +} +#else +static void backtrace_test_saved(void) +{ + printk("Saved backtrace test skipped.\n"); +} +#endif + static int backtrace_regression_test(void) { printk("====[ backtrace testing ]===========\n"); @@ -29,6 +55,8 @@ static int backtrace_regression_test(void) printk("The following trace is a kernel self test and not a bug!\n"); dump_stack(); + backtrace_test_saved(); + init_timer(&backtrace_timer); backtrace_timer.function = backtrace_test_timer; mod_timer(&backtrace_timer, jiffies + 10); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9c17fb9d1d5e..6263e2d851f1 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -562,6 +562,9 @@ config BACKTRACE_SELF_TEST for distributions or general kernels, but only for kernel developers working on architecture code. + Note that if you want to also test saved backtraces, you will + have to enable STACKTRACE as well. + Say N if you are unsure. config LKDTM -- cgit v1.2.3 From b9c796783151678d08b1ec1ef410685b2515ba51 Mon Sep 17 00:00:00 2001 From: Joonwoo Park Date: Tue, 8 Jul 2008 02:37:31 -0700 Subject: textsearch: support for case insensitive searching The function textsearch_prepare has a new flag to support case insensitive searching. Signed-off-by: Joonwoo Park Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/textsearch.h | 10 +++++----- lib/textsearch.c | 14 ++++++++------ 2 files changed, 13 insertions(+), 11 deletions(-) (limited to 'lib') diff --git a/include/linux/textsearch.h b/include/linux/textsearch.h index 6f371f24160b..6c34cf28b7aa 100644 --- a/include/linux/textsearch.h +++ b/include/linux/textsearch.h @@ -10,10 +10,8 @@ struct ts_config; -/** - * TS_AUTOLOAD - Automatically load textsearch modules when needed - */ -#define TS_AUTOLOAD 1 +#define TS_AUTOLOAD 1 /* Automatically load textsearch modules when needed */ +#define TS_IGNORECASE 2 /* Searches string case insensitively */ /** * struct ts_state - search state @@ -39,7 +37,7 @@ struct ts_state struct ts_ops { const char *name; - struct ts_config * (*init)(const void *, unsigned int, gfp_t); + struct ts_config * (*init)(const void *, unsigned int, gfp_t, int); unsigned int (*find)(struct ts_config *, struct ts_state *); void (*destroy)(struct ts_config *); @@ -52,12 +50,14 @@ struct ts_ops /** * struct ts_config - search configuration * @ops: operations of chosen algorithm + * @flags: flags * @get_next_block: callback to fetch the next block to search in * @finish: callback to finalize a search */ struct ts_config { struct ts_ops *ops; + int flags; /** * get_next_block - fetch next block of data diff --git a/lib/textsearch.c b/lib/textsearch.c index be8bda3862f5..b451fcc9354c 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -54,10 +54,13 @@ * USAGE * * Before a search can be performed, a configuration must be created - * by calling textsearch_prepare() specyfing the searching algorithm and - * the pattern to look for. The returned configuration may then be used - * for an arbitary amount of times and even in parallel as long as a - * separate struct ts_state variable is provided to every instance. + * by calling textsearch_prepare() specifying the searching algorithm, + * the pattern to look for and flags. As a flag, you can set TS_IGNORECASE + * to perform case insensitive matching. But it might slow down + * performance of algorithm, so you should use it at own your risk. + * The returned configuration may then be used for an arbitary + * amount of times and even in parallel as long as a separate struct + * ts_state variable is provided to every instance. * * The actual search is performed by either calling textsearch_find_- * continuous() for linear data or by providing an own get_next_block() @@ -89,7 +92,6 @@ * panic("Oh my god, dancing chickens at %d\n", pos); * * textsearch_destroy(conf); - * * ========================================================================== */ @@ -279,7 +281,7 @@ struct ts_config *textsearch_prepare(const char *algo, const void *pattern, if (ops == NULL) goto errout; - conf = ops->init(pattern, len, gfp_mask); + conf = ops->init(pattern, len, gfp_mask, flags); if (IS_ERR(conf)) { err = PTR_ERR(conf); goto errout; -- cgit v1.2.3 From 3b76d08190e6b420ed3f5534aa99ee29d82d731f Mon Sep 17 00:00:00 2001 From: Joonwoo Park Date: Tue, 8 Jul 2008 02:37:54 -0700 Subject: textsearch: ts_bm: support case insensitive searching in Boyer-Moore algorithm Add support for case insensitive search to Boyer-Moore algorithm. Signed-off-by: Joonwoo Park Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- lib/ts_bm.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/ts_bm.c b/lib/ts_bm.c index 4a7fce72898e..9e66ee4020e9 100644 --- a/lib/ts_bm.c +++ b/lib/ts_bm.c @@ -39,6 +39,7 @@ #include #include #include +#include #include /* Alphabet size, use ASCII */ @@ -64,6 +65,7 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state) unsigned int i, text_len, consumed = state->offset; const u8 *text; int shift = bm->patlen - 1, bs; + const u8 icase = conf->flags & TS_IGNORECASE; for (;;) { text_len = conf->get_next_block(consumed, &text, conf, state); @@ -75,7 +77,9 @@ static unsigned int bm_find(struct ts_config *conf, struct ts_state *state) DEBUGP("Searching in position %d (%c)\n", shift, text[shift]); for (i = 0; i < bm->patlen; i++) - if (text[shift-i] != bm->pattern[bm->patlen-1-i]) + if ((icase ? toupper(text[shift-i]) + : text[shift-i]) + != bm->pattern[bm->patlen-1-i]) goto next; /* London calling... */ @@ -111,14 +115,18 @@ static int subpattern(u8 *pattern, int i, int j, int g) return ret; } -static void compute_prefix_tbl(struct ts_bm *bm) +static void compute_prefix_tbl(struct ts_bm *bm, int flags) { int i, j, g; for (i = 0; i < ASIZE; i++) bm->bad_shift[i] = bm->patlen; - for (i = 0; i < bm->patlen - 1; i++) + for (i = 0; i < bm->patlen - 1; i++) { bm->bad_shift[bm->pattern[i]] = bm->patlen - 1 - i; + if (flags & TS_IGNORECASE) + bm->bad_shift[tolower(bm->pattern[i])] + = bm->patlen - 1 - i; + } /* Compute the good shift array, used to match reocurrences * of a subpattern */ @@ -135,10 +143,11 @@ static void compute_prefix_tbl(struct ts_bm *bm) } static struct ts_config *bm_init(const void *pattern, unsigned int len, - gfp_t gfp_mask) + gfp_t gfp_mask, int flags) { struct ts_config *conf; struct ts_bm *bm; + int i; unsigned int prefix_tbl_len = len * sizeof(unsigned int); size_t priv_size = sizeof(*bm) + len + prefix_tbl_len; @@ -146,11 +155,16 @@ static struct ts_config *bm_init(const void *pattern, unsigned int len, if (IS_ERR(conf)) return conf; + conf->flags = flags; bm = ts_config_priv(conf); bm->patlen = len; bm->pattern = (u8 *) bm->good_shift + prefix_tbl_len; - memcpy(bm->pattern, pattern, len); - compute_prefix_tbl(bm); + if (flags & TS_IGNORECASE) + for (i = 0; i < len; i++) + bm->pattern[i] = toupper(((u8 *)pattern)[i]); + else + memcpy(bm->pattern, pattern, len); + compute_prefix_tbl(bm, flags); return conf; } -- cgit v1.2.3 From 2523c3fc2bc9e34c06a71517844d55353f1f904a Mon Sep 17 00:00:00 2001 From: Joonwoo Park Date: Tue, 8 Jul 2008 02:38:09 -0700 Subject: textsearch: ts_kmp: support case insensitive searching in Knuth-Morris-Pratt algorithm Add support for case insensitive search to Knuth-Morris-Pratt algorithm. Signed-off-by: Joonwoo Park Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- lib/ts_kmp.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/ts_kmp.c b/lib/ts_kmp.c index 3ced628cab4b..632f783e65f1 100644 --- a/lib/ts_kmp.c +++ b/lib/ts_kmp.c @@ -33,6 +33,7 @@ #include #include #include +#include #include struct ts_kmp @@ -47,6 +48,7 @@ static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state) struct ts_kmp *kmp = ts_config_priv(conf); unsigned int i, q = 0, text_len, consumed = state->offset; const u8 *text; + const int icase = conf->flags & TS_IGNORECASE; for (;;) { text_len = conf->get_next_block(consumed, &text, conf, state); @@ -55,9 +57,11 @@ static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state) break; for (i = 0; i < text_len; i++) { - while (q > 0 && kmp->pattern[q] != text[i]) + while (q > 0 && kmp->pattern[q] + != (icase ? toupper(text[i]) : text[i])) q = kmp->prefix_tbl[q - 1]; - if (kmp->pattern[q] == text[i]) + if (kmp->pattern[q] + == (icase ? toupper(text[i]) : text[i])) q++; if (unlikely(q == kmp->pattern_len)) { state->offset = consumed + i + 1; @@ -72,24 +76,28 @@ static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state) } static inline void compute_prefix_tbl(const u8 *pattern, unsigned int len, - unsigned int *prefix_tbl) + unsigned int *prefix_tbl, int flags) { unsigned int k, q; + const u8 icase = flags & TS_IGNORECASE; for (k = 0, q = 1; q < len; q++) { - while (k > 0 && pattern[k] != pattern[q]) + while (k > 0 && (icase ? toupper(pattern[k]) : pattern[k]) + != (icase ? toupper(pattern[q]) : pattern[q])) k = prefix_tbl[k-1]; - if (pattern[k] == pattern[q]) + if ((icase ? toupper(pattern[k]) : pattern[k]) + == (icase ? toupper(pattern[q]) : pattern[q])) k++; prefix_tbl[q] = k; } } static struct ts_config *kmp_init(const void *pattern, unsigned int len, - gfp_t gfp_mask) + gfp_t gfp_mask, int flags) { struct ts_config *conf; struct ts_kmp *kmp; + int i; unsigned int prefix_tbl_len = len * sizeof(unsigned int); size_t priv_size = sizeof(*kmp) + len + prefix_tbl_len; @@ -97,11 +105,16 @@ static struct ts_config *kmp_init(const void *pattern, unsigned int len, if (IS_ERR(conf)) return conf; + conf->flags = flags; kmp = ts_config_priv(conf); kmp->pattern_len = len; - compute_prefix_tbl(pattern, len, kmp->prefix_tbl); + compute_prefix_tbl(pattern, len, kmp->prefix_tbl, flags); kmp->pattern = (u8 *) kmp->prefix_tbl + prefix_tbl_len; - memcpy(kmp->pattern, pattern, len); + if (flags & TS_IGNORECASE) + for (i = 0; i < len; i++) + kmp->pattern[i] = toupper(((u8 *)pattern)[i]); + else + memcpy(kmp->pattern, pattern, len); return conf; } -- cgit v1.2.3 From 43138833ee9af07e865a4dcbfe81684c9c2f2262 Mon Sep 17 00:00:00 2001 From: Joonwoo Park Date: Tue, 8 Jul 2008 02:38:27 -0700 Subject: textsearch: ts_fsm: return error on request for case insensitive search For fsm text search, handle case insensitive parameter as -EINVAL. Signed-off-by: Joonwoo Park Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- lib/ts_fsm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/ts_fsm.c b/lib/ts_fsm.c index af575b61526b..5696a35184e4 100644 --- a/lib/ts_fsm.c +++ b/lib/ts_fsm.c @@ -257,7 +257,7 @@ found_match: } static struct ts_config *fsm_init(const void *pattern, unsigned int len, - gfp_t gfp_mask) + gfp_t gfp_mask, int flags) { int i, err = -EINVAL; struct ts_config *conf; @@ -269,6 +269,9 @@ static struct ts_config *fsm_init(const void *pattern, unsigned int len, if (len % sizeof(struct ts_fsm_token) || ntokens < 1) goto errout; + if (flags & TS_IGNORECASE) + goto errout; + for (i = 0; i < ntokens; i++) { struct ts_fsm_token *t = &tokens[i]; @@ -284,6 +287,7 @@ static struct ts_config *fsm_init(const void *pattern, unsigned int len, if (IS_ERR(conf)) return conf; + conf->flags = flags; fsm = ts_config_priv(conf); fsm->ntokens = ntokens; memcpy(fsm->tokens, pattern, len); -- cgit v1.2.3 From e8ced39d5e8911c662d4d69a342b9d053eaaac4e Mon Sep 17 00:00:00 2001 From: Mingming Cao Date: Fri, 11 Jul 2008 19:27:31 -0400 Subject: percpu_counter: new function percpu_counter_sum_and_set Delayed allocation need to check free blocks at every write time. percpu_counter_read_positive() is not quit accurate. delayed allocation need a more accurate accounting, but using percpu_counter_sum_positive() is frequently is quite expensive. This patch added a new function to update center counter when sum per-cpu counter, to increase the accurate rate for next percpu_counter_read() and require less calling expensive percpu_counter_sum(). Signed-off-by: Mingming Cao Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 2 +- include/linux/percpu_counter.h | 12 +++++++++--- lib/percpu_counter.c | 7 ++++++- 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 25f63d8c1b3d..6369bacf0dcb 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -1621,7 +1621,7 @@ ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi, #ifdef CONFIG_SMP if (free_blocks - root_blocks < FBC_BATCH) free_blocks = - percpu_counter_sum_positive(&sbi->s_freeblocks_counter); + percpu_counter_sum_and_set(&sbi->s_freeblocks_counter); #endif if (free_blocks - root_blocks < nblocks) return free_blocks - root_blocks; diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 9007ccdfc112..208388835357 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -35,7 +35,7 @@ int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount); void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch); -s64 __percpu_counter_sum(struct percpu_counter *fbc); +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set); static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { @@ -44,13 +44,19 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { - s64 ret = __percpu_counter_sum(fbc); + s64 ret = __percpu_counter_sum(fbc, 0); return ret < 0 ? 0 : ret; } +static inline s64 percpu_counter_sum_and_set(struct percpu_counter *fbc) +{ + return __percpu_counter_sum(fbc, 1); +} + + static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { - return __percpu_counter_sum(fbc); + return __percpu_counter_sum(fbc, 0); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 119174494cb5..4a8ba4bf5f6f 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -52,7 +52,7 @@ EXPORT_SYMBOL(__percpu_counter_add); * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ -s64 __percpu_counter_sum(struct percpu_counter *fbc) +s64 __percpu_counter_sum(struct percpu_counter *fbc, int set) { s64 ret; int cpu; @@ -62,7 +62,12 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc) for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; + if (set) + *pcount = 0; } + if (set) + fbc->count = ret; + spin_unlock(&fbc->lock); return ret; } -- cgit v1.2.3 From f11f594edba7f689af9792a5673ed59d660ad371 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Wed, 25 Jun 2008 11:22:42 -0400 Subject: [SCSI] lib: Add support for the T10 (SCSI) Data Integrity Field CRC The SCSI Block Protocol uses this 16-bit CRC to verify the integrity of each data sector. crc_t10dif() is used by sd_dif.c when performing I/O to or from disks formatted with protection information. Signed-off-by: Martin K. Petersen Signed-off-by: James Bottomley --- include/linux/crc-t10dif.h | 8 ++++++ lib/Kconfig | 7 +++++ lib/Makefile | 1 + lib/crc-t10dif.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 83 insertions(+) create mode 100644 include/linux/crc-t10dif.h create mode 100644 lib/crc-t10dif.c (limited to 'lib') diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h new file mode 100644 index 000000000000..a9c96d865ee7 --- /dev/null +++ b/include/linux/crc-t10dif.h @@ -0,0 +1,8 @@ +#ifndef _LINUX_CRC_T10DIF_H +#define _LINUX_CRC_T10DIF_H + +#include + +__u16 crc_t10dif(unsigned char const *, size_t); + +#endif diff --git a/lib/Kconfig b/lib/Kconfig index 8cc8e8722a3f..c7ad7a5b3535 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -29,6 +29,13 @@ config CRC16 the kernel tree does. Such modules that use library CRC16 functions require M here. +config CRC_T10DIF + tristate "CRC calculation for the T10 Data Integrity Field" + help + This option is only needed if a module that's not in the + kernel tree needs to calculate CRC checks for use with the + SCSI data integrity subsystem. + config CRC_ITU_T tristate "CRC ITU-T V.41 functions" help diff --git a/lib/Makefile b/lib/Makefile index 74b0cfb1fcc3..237a8298f8cb 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -45,6 +45,7 @@ endif obj-$(CONFIG_BITREVERSE) += bitrev.o obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o obj-$(CONFIG_CRC16) += crc16.o +obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o obj-$(CONFIG_CRC32) += crc32.o obj-$(CONFIG_CRC7) += crc7.o diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c new file mode 100644 index 000000000000..fbbd66ed86cd --- /dev/null +++ b/lib/crc-t10dif.c @@ -0,0 +1,67 @@ +/* + * T10 Data Integrity Field CRC16 calculation + * + * Copyright (c) 2007 Oracle Corporation. All rights reserved. + * Written by Martin K. Petersen + * + * This source code is licensed under the GNU General Public License, + * Version 2. See the file COPYING for more details. + */ + +#include +#include +#include + +/* Table generated using the following polynomium: + * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1 + * gt: 0x8bb7 + */ +static const __u16 t10_dif_crc_table[256] = { + 0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B, + 0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6, + 0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6, + 0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B, + 0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1, + 0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C, + 0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C, + 0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781, + 0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8, + 0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255, + 0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925, + 0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698, + 0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472, + 0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF, + 0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF, + 0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02, + 0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA, + 0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067, + 0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17, + 0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA, + 0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640, + 0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD, + 0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D, + 0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30, + 0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759, + 0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4, + 0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394, + 0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29, + 0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3, + 0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E, + 0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E, + 0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3 +}; + +__u16 crc_t10dif(const unsigned char *buffer, size_t len) +{ + __u16 crc = 0; + unsigned int i; + + for (i = 0 ; i < len ; i++) + crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff]; + + return crc; +} +EXPORT_SYMBOL(crc_t10dif); + +MODULE_DESCRIPTION("T10 DIF CRC calculation"); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 9fa111372a54f695f65e0de2f2a2108fe6cf3584 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 17 Jul 2008 17:38:17 +0200 Subject: ftrace: fix lockup with MAXSMP MAXSMP brings in lots of use of various bitops in smp_processor_id() and friends - causing ftrace to lock up during bootup: calling anon_inode_init+0x0/0x130 initcall anon_inode_init+0x0/0x130 returned 0 after 0 msecs calling acpi_event_init+0x0/0x57 [ hard hang ] So exclude the bitops facilities from tracing. Signed-off-by: Ingo Molnar --- lib/Makefile | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index 2c62a9c06fbe..d90d31102e05 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -15,6 +15,9 @@ CFLAGS_REMOVE_string.o = -pg CFLAGS_REMOVE_spinlock_debug.o = -pg CFLAGS_REMOVE_list_debug.o = -pg CFLAGS_REMOVE_debugobjects.o = -pg +CFLAGS_REMOVE_find_next_bit.o = -pg +CFLAGS_REMOVE_cpumask.o = -pg +CFLAGS_REMOVE_bitmap.o = -pg endif lib-$(CONFIG_MMU) += ioremap.o -- cgit v1.2.3 From 2464a609ded094204a3aed24823745ec58e3c879 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 17 Jul 2008 17:40:48 +0200 Subject: ftrace: do not trace library functions make function tracing more robust: do not trace library functions. We've already got a sizable list of exceptions: ifdef CONFIG_FTRACE # Do not profile string.o, since it may be used in early boot or vdso CFLAGS_REMOVE_string.o = -pg # Also do not profile any debug utilities CFLAGS_REMOVE_spinlock_debug.o = -pg CFLAGS_REMOVE_list_debug.o = -pg CFLAGS_REMOVE_debugobjects.o = -pg CFLAGS_REMOVE_find_next_bit.o = -pg CFLAGS_REMOVE_cpumask.o = -pg CFLAGS_REMOVE_bitmap.o = -pg endif ... and the pattern has been that random library functionality showed up in ftrace's critical path (outside of its recursion check), causing hard to debug lockups. So be a bit defensive about it and exclude all lib/*.o functions by default. It's not that they are overly interesting for tracing purposes anyway. Specific ones can still be traced, in an opt-in manner. Signed-off-by: Ingo Molnar --- lib/Makefile | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index d90d31102e05..818c4d455518 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -2,24 +2,17 @@ # Makefile for some libs needed in the kernel. # +ifdef CONFIG_FTRACE +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +endif + lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ proportions.o prio_heap.o ratelimit.o -ifdef CONFIG_FTRACE -# Do not profile string.o, since it may be used in early boot or vdso -CFLAGS_REMOVE_string.o = -pg -# Also do not profile any debug utilities -CFLAGS_REMOVE_spinlock_debug.o = -pg -CFLAGS_REMOVE_list_debug.o = -pg -CFLAGS_REMOVE_debugobjects.o = -pg -CFLAGS_REMOVE_find_next_bit.o = -pg -CFLAGS_REMOVE_cpumask.o = -pg -CFLAGS_REMOVE_bitmap.o = -pg -endif - lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o -- cgit v1.2.3 From 4755b9291204982ac908e069674d6e5eb45815b3 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Tue, 15 Jul 2008 14:14:35 -0700 Subject: cpumask: Optimize cpumask_of_cpu in lib/smp_processor_id.c * Optimize various places where a pointer to the cpumask_of_cpu value will result in reducing stack pressure. Signed-off-by: Mike Travis Signed-off-by: Ingo Molnar --- lib/smp_processor_id.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 3b4dc098181e..9fb2df0d8dfb 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -11,7 +11,7 @@ notrace unsigned int debug_smp_processor_id(void) { unsigned long preempt_count = preempt_count(); int this_cpu = raw_smp_processor_id(); - cpumask_t this_mask; + cpumask_of_cpu_ptr_declare(this_mask); if (likely(preempt_count)) goto out; @@ -23,9 +23,9 @@ notrace unsigned int debug_smp_processor_id(void) * Kernel threads bound to a single CPU can safely use * smp_processor_id(): */ - this_mask = cpumask_of_cpu(this_cpu); + cpumask_of_cpu_ptr_next(this_mask, cpu); - if (cpus_equal(current->cpus_allowed, this_mask)) + if (cpus_equal(current->cpus_allowed, *this_mask)) goto out; /* -- cgit v1.2.3 From 06f8d00e9eecb738c99b737ac38a585ea7583ad5 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 18 Jul 2008 22:34:00 +0200 Subject: cpumask: Optimize cpumask_of_cpu in lib/smp_processor_id.c, fix fix typo. Signed-off-by: Ingo Molnar --- lib/smp_processor_id.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 9fb2df0d8dfb..c4381d9516f6 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -23,7 +23,7 @@ notrace unsigned int debug_smp_processor_id(void) * Kernel threads bound to a single CPU can safely use * smp_processor_id(): */ - cpumask_of_cpu_ptr_next(this_mask, cpu); + cpumask_of_cpu_ptr_next(this_mask, this_cpu); if (cpus_equal(current->cpus_allowed, *this_mask)) goto out; -- cgit v1.2.3 From 9f255651fb41c111ee35a2ae632df8ce9bd61def Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Tue, 6 May 2008 22:24:04 +0200 Subject: kobject: replace '/' with '!' in name Some (block) devices have a '/' in the name, and need special handling. Let's have that rule to the core, so we can remove it from the block class. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- lib/kobject.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/kobject.c b/lib/kobject.c index dcade0543bd2..744401571ed7 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -216,13 +216,19 @@ static int kobject_add_internal(struct kobject *kobj) static int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { - /* Free the old name, if necessary. */ - kfree(kobj->name); + const char *old_name = kobj->name; + char *s; kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs); if (!kobj->name) return -ENOMEM; + /* ewww... some of these buggers have '/' in the name ... */ + s = strchr(kobj->name, '/'); + if (s) + s[0] = '!'; + + kfree(old_name); return 0; } -- cgit v1.2.3 From ff543332ec5d23833994fca9e7789f067fb51221 Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Tue, 20 May 2008 00:06:00 +0200 Subject: debugfs: Add a reference to the debugfs API documentation. Signed-off-by: Robert P. J. Day Cc: Jesper Juhl Signed-off-by: Greg Kroah-Hartman --- lib/Kconfig.debug | 3 +++ 1 file changed, 3 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index df27132a56f4..ba106db5a65b 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -74,6 +74,9 @@ config DEBUG_FS debugging files into. Enable this option to be able to read and write to these files. + For detailed documentation on the debugfs API, see + Documentation/DocBook/filesystems. + If unsure, say N. config HEADERS_CHECK -- cgit v1.2.3 From 0ad1d6f37cc3bb234c6e7ae30e40d1d40b9aa258 Mon Sep 17 00:00:00 2001 From: Wang Chen Date: Tue, 24 Jun 2008 16:59:02 +0800 Subject: kobject: Transmit return value of call_usermodehelper() to caller kobject_uevent_env() drops the return value of call_usermodehelper(). It will make upper caller, such as dm_send_uevents(), to lose error information. BTW, Previously kobject_uevent_env() transmitted return of call_usermodehelper() to callers, but commit 5f123fbd80f4f788554636f02bf73e40f914e0d6 "[PATCH] merge kobject_uevent and kobject_hotplug" removed it. Signed-off-by: Wang Chen Cc: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 2fa545a63160..9f8d599459d1 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -245,7 +245,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, if (retval) goto exit; - call_usermodehelper(argv[0], argv, env->envp, UMH_WAIT_EXEC); + retval = call_usermodehelper(argv[0], argv, + env->envp, UMH_WAIT_EXEC); } exit: -- cgit v1.2.3 From a00caa1fa954c734f4214a074727a329a9ba6568 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jul 2008 19:00:24 +0200 Subject: remove CONFIG_KMOD from lib textsearch algorithms can be loaded, make the code depend on CONFIG_MODULES instead of CONFIG_KMOD. Signed-off-by: Johannes Berg Signed-off-by: Rusty Russell --- lib/textsearch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/textsearch.c b/lib/textsearch.c index 4b7c6075256f..9fbcb44c554f 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -267,7 +267,7 @@ struct ts_config *textsearch_prepare(const char *algo, const void *pattern, return ERR_PTR(-EINVAL); ops = lookup_ts_algo(algo); -#ifdef CONFIG_KMOD +#ifdef CONFIG_MODULES /* * Why not always autoload you may ask. Some users are * in a situation where requesting a module may deadlock, -- cgit v1.2.3 From 137d3edb48425f82a6a4226b664f90ed5e42eea5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 19 Jul 2008 23:03:35 +0900 Subject: sg: reimplement sg mapping iterator This is alternative implementation of sg content iterator introduced by commit 83e7d317... from Pierre Ossman in next-20080716. As there's already an sg iterator which iterates over sg entries themselves, name this sg_mapping_iterator. Slightly edited description from the original implementation follows. Iteration over a sg list is not that trivial when you take into account that memory pages might have to be mapped before being used. Unfortunately, that means that some parts of the kernel restrict themselves to directly accesible memory just to not have to deal with the mess. This patch adds a simple iterator system that allows any code to easily traverse an sg list and not have to deal with all the details. The user can decide to consume part of the iteration. Also, iteration can be stopped and resumed later if releasing the kmap between iteration steps is necessary. These features are useful to implement piecemeal sg copying for interrupt drive PIO for example. Signed-off-by: Tejun Heo Signed-off-by: Pierre Ossman --- include/linux/scatterlist.h | 38 ++++++++++ lib/scatterlist.c | 176 ++++++++++++++++++++++++++++++++------------ 2 files changed, 168 insertions(+), 46 deletions(-) (limited to 'lib') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 71fc81360048..e5996984ddd0 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -224,4 +224,42 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents, */ #define SG_MAX_SINGLE_ALLOC (PAGE_SIZE / sizeof(struct scatterlist)) + +/* + * Mapping sg iterator + * + * Iterates over sg entries mapping page-by-page. On each successful + * iteration, @miter->page points to the mapped page and + * @miter->length bytes of data can be accessed at @miter->addr. As + * long as an interation is enclosed between start and stop, the user + * is free to choose control structure and when to stop. + * + * @miter->consumed is set to @miter->length on each iteration. It + * can be adjusted if the user can't consume all the bytes in one go. + * Also, a stopped iteration can be resumed by calling next on it. + * This is useful when iteration needs to release all resources and + * continue later (e.g. at the next interrupt). + */ + +#define SG_MITER_ATOMIC (1 << 0) /* use kmap_atomic */ + +struct sg_mapping_iter { + /* the following three fields can be accessed directly */ + struct page *page; /* currently mapped page */ + void *addr; /* pointer to the mapped area */ + size_t length; /* length of the mapped area */ + size_t consumed; /* number of consumed bytes */ + + /* these are internal states, keep away */ + struct scatterlist *__sg; /* current entry */ + unsigned int __nents; /* nr of remaining entries */ + unsigned int __offset; /* offset within sg */ + unsigned int __flags; +}; + +void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl, + unsigned int nents, unsigned int flags); +bool sg_miter_next(struct sg_mapping_iter *miter); +void sg_miter_stop(struct sg_mapping_iter *miter); + #endif /* _LINUX_SCATTERLIST_H */ diff --git a/lib/scatterlist.c b/lib/scatterlist.c index b80c21100d78..876ba6d5b670 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -294,6 +294,117 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask) } EXPORT_SYMBOL(sg_alloc_table); +/** + * sg_miter_start - start mapping iteration over a sg list + * @miter: sg mapping iter to be started + * @sgl: sg list to iterate over + * @nents: number of sg entries + * + * Description: + * Starts mapping iterator @miter. + * + * Context: + * Don't care. + */ +void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl, + unsigned int nents, unsigned int flags) +{ + memset(miter, 0, sizeof(struct sg_mapping_iter)); + + miter->__sg = sgl; + miter->__nents = nents; + miter->__offset = 0; + miter->__flags = flags; +} +EXPORT_SYMBOL(sg_miter_start); + +/** + * sg_miter_next - proceed mapping iterator to the next mapping + * @miter: sg mapping iter to proceed + * + * Description: + * Proceeds @miter@ to the next mapping. @miter@ should have been + * started using sg_miter_start(). On successful return, + * @miter@->page, @miter@->addr and @miter@->length point to the + * current mapping. + * + * Context: + * IRQ disabled if SG_MITER_ATOMIC. IRQ must stay disabled till + * @miter@ is stopped. May sleep if !SG_MITER_ATOMIC. + * + * Returns: + * true if @miter contains the next mapping. false if end of sg + * list is reached. + */ +bool sg_miter_next(struct sg_mapping_iter *miter) +{ + unsigned int off, len; + + /* check for end and drop resources from the last iteration */ + if (!miter->__nents) + return false; + + sg_miter_stop(miter); + + /* get to the next sg if necessary. __offset is adjusted by stop */ + if (miter->__offset == miter->__sg->length && --miter->__nents) { + miter->__sg = sg_next(miter->__sg); + miter->__offset = 0; + } + + /* map the next page */ + off = miter->__sg->offset + miter->__offset; + len = miter->__sg->length - miter->__offset; + + miter->page = nth_page(sg_page(miter->__sg), off >> PAGE_SHIFT); + off &= ~PAGE_MASK; + miter->length = min_t(unsigned int, len, PAGE_SIZE - off); + miter->consumed = miter->length; + + if (miter->__flags & SG_MITER_ATOMIC) + miter->addr = kmap_atomic(miter->page, KM_BIO_SRC_IRQ) + off; + else + miter->addr = kmap(miter->page) + off; + + return true; +} +EXPORT_SYMBOL(sg_miter_next); + +/** + * sg_miter_stop - stop mapping iteration + * @miter: sg mapping iter to be stopped + * + * Description: + * Stops mapping iterator @miter. @miter should have been started + * started using sg_miter_start(). A stopped iteration can be + * resumed by calling sg_miter_next() on it. This is useful when + * resources (kmap) need to be released during iteration. + * + * Context: + * IRQ disabled if the SG_MITER_ATOMIC is set. Don't care otherwise. + */ +void sg_miter_stop(struct sg_mapping_iter *miter) +{ + WARN_ON(miter->consumed > miter->length); + + /* drop resources from the last iteration */ + if (miter->addr) { + miter->__offset += miter->consumed; + + if (miter->__flags & SG_MITER_ATOMIC) { + WARN_ON(!irqs_disabled()); + kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ); + } else + kunmap(miter->addr); + + miter->page = NULL; + miter->addr = NULL; + miter->length = 0; + miter->consumed = 0; + } +} +EXPORT_SYMBOL(sg_miter_stop); + /** * sg_copy_buffer - Copy data between a linear buffer and an SG list * @sgl: The SG list @@ -309,56 +420,29 @@ EXPORT_SYMBOL(sg_alloc_table); static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents, void *buf, size_t buflen, int to_buffer) { - struct scatterlist *sg; - size_t buf_off = 0; - int i; - - WARN_ON(!irqs_disabled()); - - for_each_sg(sgl, sg, nents, i) { - struct page *page; - int n = 0; - unsigned int sg_off = sg->offset; - unsigned int sg_copy = sg->length; - - if (sg_copy > buflen) - sg_copy = buflen; - buflen -= sg_copy; - - while (sg_copy > 0) { - unsigned int page_copy; - void *p; - - page_copy = PAGE_SIZE - sg_off; - if (page_copy > sg_copy) - page_copy = sg_copy; - - page = nth_page(sg_page(sg), n); - p = kmap_atomic(page, KM_BIO_SRC_IRQ); - - if (to_buffer) - memcpy(buf + buf_off, p + sg_off, page_copy); - else { - memcpy(p + sg_off, buf + buf_off, page_copy); - flush_kernel_dcache_page(page); - } - - kunmap_atomic(p, KM_BIO_SRC_IRQ); - - buf_off += page_copy; - sg_off += page_copy; - if (sg_off == PAGE_SIZE) { - sg_off = 0; - n++; - } - sg_copy -= page_copy; + unsigned int offset = 0; + struct sg_mapping_iter miter; + + sg_miter_start(&miter, sgl, nents, SG_MITER_ATOMIC); + + while (sg_miter_next(&miter) && offset < buflen) { + unsigned int len; + + len = min(miter.length, buflen - offset); + + if (to_buffer) + memcpy(buf + offset, miter.addr, len); + else { + memcpy(miter.addr, buf + offset, len); + flush_kernel_dcache_page(miter.page); } - if (!buflen) - break; + offset += len; } - return buf_off; + sg_miter_stop(&miter); + + return offset; } /** -- cgit v1.2.3 From 68afab1cb31436fc9b256a5f44771fa58ed019e2 Mon Sep 17 00:00:00 2001 From: Jason Wessel Date: Wed, 23 Jul 2008 11:30:15 -0500 Subject: kgdb: remove unused HAVE_ARCH_KGDB_SHADOW_INFO config variable Remove HAVE_ARCH_KGDB_SHADOW_INFO because it does not exist anywhere in the kernel mainline sources Signed-off-by: Jason Wessel --- lib/Kconfig.kgdb | 3 --- 1 file changed, 3 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb index a5d4b1dac2a5..2cfd2721f7ed 100644 --- a/lib/Kconfig.kgdb +++ b/lib/Kconfig.kgdb @@ -1,7 +1,4 @@ -config HAVE_ARCH_KGDB_SHADOW_INFO - bool - config HAVE_ARCH_KGDB bool -- cgit v1.2.3