From 15ae02baf025750cd79ef3929c28f7083a088bd2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Feb 2008 01:37:49 -0800 Subject: lib/extable.c: remove an expensive integer divide in search_extable() Actual code let compiler generates idiv instruction on x86. Using a right shift is OK here and readable as well. Before patch 10: 57 push %edi 11: 56 push %esi 12: 89 d6 mov %edx,%esi 14: 53 push %ebx 15: 89 c3 mov %eax,%ebx 17: eb 22 jmp 3b 19: 89 f0 mov %esi,%eax 1b: ba 02 00 00 00 mov $0x2,%edx 20: 29 d8 sub %ebx,%eax 22: 89 d7 mov %edx,%edi 24: c1 f8 03 sar $0x3,%eax 27: 99 cltd 28: f7 ff idiv %edi 2a: 8d 04 c3 lea (%ebx,%eax,8),%eax 2d: 39 08 cmp %ecx,(%eax) ... After patch 00000010 : 10: 53 push %ebx 11: 89 c3 mov %eax,%ebx 13: eb 18 jmp 2d 15: 89 d0 mov %edx,%eax 17: 29 d8 sub %ebx,%eax 19: c1 f8 04 sar $0x4,%eax 1c: 8d 04 c3 lea (%ebx,%eax,8),%eax 1f: 39 08 cmp %ecx,(%eax) ... Signed-off-by: Eric Dumazet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/extable.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/extable.c b/lib/extable.c index 463f456..179c087 100644 --- a/lib/extable.c +++ b/lib/extable.c @@ -57,10 +57,10 @@ search_extable(const struct exception_table_entry *first, while (first <= last) { const struct exception_table_entry *mid; - mid = (last - first) / 2 + first; + mid = ((last - first) >> 1) + first; /* - * careful, the distance between entries can be - * larger than 2GB: + * careful, the distance between value and insn + * can be larger than MAX_LONG: */ if (mid->insn < value) first = mid + 1; -- cgit v1.1 From b41ecbebd4091a15233abab2d771e65fb82cdb20 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 6 Feb 2008 01:37:57 -0800 Subject: debug_smp_processor_id() fixlets - Account for debug_smp_processor_id()'s own preempt_disable() when displaying the preempt_count(). - 80 cols, not 800. Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/smp_processor_id.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index eddc9b3..6c90fb9 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -42,7 +42,9 @@ unsigned int debug_smp_processor_id(void) if (!printk_ratelimit()) goto out_enable; - printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] code: %s/%d\n", preempt_count(), current->comm, current->pid); + printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] " + "code: %s/%d\n", + preempt_count() - 1, current->comm, current->pid); print_symbol("caller is %s\n", (long)__builtin_return_address(0)); dump_stack(); -- cgit v1.1 From 8ff12cfc009a2a38d87fa7058226fe197bb2696f Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 7 Feb 2008 17:47:41 -0800 Subject: SLUB: Support for performance statistics The statistics provided here allow the monitoring of allocator behavior but at the cost of some (minimal) loss of performance. Counters are placed in SLUB's per cpu data structure. The per cpu structure may be extended by the statistics to grow larger than one cacheline which will increase the cache footprint of SLUB. There is a compile option to enable/disable the inclusion of the runtime statistics and its off by default. The slabinfo tool is enhanced to support these statistics via two options: -D Switches the line of information displayed for a slab from size mode to activity mode. -A Sorts the slabs displayed by activity. This allows the display of the slabs most important to the performance of a certain load. -r Report option will report detailed statistics on Example (tbench load): slabinfo -AD ->Shows the most active slabs Name Objects Alloc Free %Fast skbuff_fclone_cache 33 111953835 111953835 99 99 :0000192 2666 5283688 5281047 99 99 :0001024 849 5247230 5246389 83 83 vm_area_struct 1349 119642 118355 91 22 :0004096 15 66753 66751 98 98 :0000064 2067 25297 23383 98 78 dentry 10259 28635 18464 91 45 :0000080 11004 18950 8089 98 98 :0000096 1703 12358 10784 99 98 :0000128 762 10582 9875 94 18 :0000512 184 9807 9647 95 81 :0002048 479 9669 9195 83 65 anon_vma 777 9461 9002 99 71 kmalloc-8 6492 9981 5624 99 97 :0000768 258 7174 6931 58 15 So the skbuff_fclone_cache is of highest importance for the tbench load. Pretty high load on the 192 sized slab. Look for the aliases slabinfo -a | grep 000192 :0000192 <- xfs_btree_cur filp kmalloc-192 uid_cache tw_sock_TCP request_sock_TCPv6 tw_sock_TCPv6 skbuff_head_cache xfs_ili Likely skbuff_head_cache. Looking into the statistics of the skbuff_fclone_cache is possible through slabinfo skbuff_fclone_cache ->-r option implied if cache name is mentioned .... Usual output ... Slab Perf Counter Alloc Free %Al %Fr -------------------------------------------------- Fastpath 111953360 111946981 99 99 Slowpath 1044 7423 0 0 Page Alloc 272 264 0 0 Add partial 25 325 0 0 Remove partial 86 264 0 0 RemoteObj/SlabFrozen 350 4832 0 0 Total 111954404 111954404 Flushes 49 Refill 0 Deactivate Full=325(92%) Empty=0(0%) ToHead=24(6%) ToTail=1(0%) Looks good because the fastpath is overwhelmingly taken. skbuff_head_cache: Slab Perf Counter Alloc Free %Al %Fr -------------------------------------------------- Fastpath 5297262 5259882 99 99 Slowpath 4477 39586 0 0 Page Alloc 937 824 0 0 Add partial 0 2515 0 0 Remove partial 1691 824 0 0 RemoteObj/SlabFrozen 2621 9684 0 0 Total 5301739 5299468 Deactivate Full=2620(100%) Empty=0(0%) ToHead=0(0%) ToTail=0(0%) Descriptions of the output: Total: The total number of allocation and frees that occurred for a slab Fastpath: The number of allocations/frees that used the fastpath. Slowpath: Other allocations Page Alloc: Number of calls to the page allocator as a result of slowpath processing Add Partial: Number of slabs added to the partial list through free or alloc (occurs during cpuslab flushes) Remove Partial: Number of slabs removed from the partial list as a result of allocations retrieving a partial slab or by a free freeing the last object of a slab. RemoteObj/Froz: How many times were remotely freed object encountered when a slab was about to be deactivated. Frozen: How many times was free able to skip list processing because the slab was in use as the cpuslab of another processor. Flushes: Number of times the cpuslab was flushed on request (kmem_cache_shrink, may result from races in __slab_alloc) Refill: Number of times we were able to refill the cpuslab from remotely freed objects for the same slab. Deactivate: Statistics how slabs were deactivated. Shows how they were put onto the partial list. In general fastpath is very good. Slowpath without partial list processing is also desirable. Any touching of partial list uses node specific locks which may potentially cause list lock contention. Signed-off-by: Christoph Lameter --- lib/Kconfig.debug | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0d385be..4f4008f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -205,6 +205,19 @@ config SLUB_DEBUG_ON off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying "slub_debug=-". +config SLUB_STATS + default n + bool "Enable SLUB performance statistics" + depends on SLUB + help + SLUB statistics are useful to debug SLUBs allocation behavior in + order find ways to optimize the allocator. This should never be + enabled for production use since keeping statistics slows down + the allocator by a few percentage points. The slabinfo command + supports the determination of the most active slabs to figure + out which slabs are relevant to a particular load. + Try running: slabinfo -DA + config DEBUG_PREEMPT bool "Debug preemptible kernel" depends on DEBUG_KERNEL && PREEMPT && (TRACE_IRQFLAGS_SUPPORT || PPC64) -- cgit v1.1 From b920de1b77b72ca9432ac3f97edb26541e65e5dd Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 8 Feb 2008 04:19:31 -0800 Subject: mn10300: add the MN10300/AM33 architecture to the kernel Add architecture support for the MN10300/AM33 CPUs produced by MEI to the kernel. This patch also adds board support for the ASB2303 with the ASB2308 daughter board, and the ASB2305. The only processor supported is the MN103E010, which is an AM33v2 core plus on-chip devices. [akpm@linux-foundation.org: nuke cvs control strings] Signed-off-by: Masakazu Urade Signed-off-by: Koichi Yasutake Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 4f4008f..ce0bb26 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -404,7 +404,8 @@ config DEBUG_HIGHMEM config DEBUG_BUGVERBOSE bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED depends on BUG - depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || FRV || SUPERH || GENERIC_BUG || BLACKFIN + depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \ + FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 default !EMBEDDED help Say Y here to make BUG() panics output the file name and line number @@ -454,7 +455,9 @@ config DEBUG_SG config FRAME_POINTER bool "Compile the kernel with frame pointers" - depends on DEBUG_KERNEL && (X86 || CRIS || M68K || M68KNOMMU || FRV || UML || S390 || AVR32 || SUPERH || BLACKFIN) + depends on DEBUG_KERNEL && \ + (X86 || CRIS || M68K || M68KNOMMU || FRV || UML || S390 || \ + AVR32 || SUPERH || BLACKFIN || MN10300) default y if DEBUG_INFO && UML help If you say Y here the resulting kernel image will be slightly larger -- cgit v1.1 From 9f741cb8fecef923cce1dff820ac6aa78c12d136 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Fri, 8 Feb 2008 04:19:55 -0800 Subject: lib: remove fastcall from lib/* [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Harvey Harrison Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/iomap.c | 32 ++++++++++++++++---------------- lib/rwsem-spinlock.c | 16 ++++++++-------- lib/semaphore-sleepers.c | 8 ++++---- 3 files changed, 28 insertions(+), 28 deletions(-) (limited to 'lib') diff --git a/lib/iomap.c b/lib/iomap.c index 72c4268..db004a9 100644 --- a/lib/iomap.c +++ b/lib/iomap.c @@ -69,27 +69,27 @@ static void bad_io_access(unsigned long port, const char *access) #define mmio_read32be(addr) be32_to_cpu(__raw_readl(addr)) #endif -unsigned int fastcall ioread8(void __iomem *addr) +unsigned int ioread8(void __iomem *addr) { IO_COND(addr, return inb(port), return readb(addr)); return 0xff; } -unsigned int fastcall ioread16(void __iomem *addr) +unsigned int ioread16(void __iomem *addr) { IO_COND(addr, return inw(port), return readw(addr)); return 0xffff; } -unsigned int fastcall ioread16be(void __iomem *addr) +unsigned int ioread16be(void __iomem *addr) { IO_COND(addr, return pio_read16be(port), return mmio_read16be(addr)); return 0xffff; } -unsigned int fastcall ioread32(void __iomem *addr) +unsigned int ioread32(void __iomem *addr) { IO_COND(addr, return inl(port), return readl(addr)); return 0xffffffff; } -unsigned int fastcall ioread32be(void __iomem *addr) +unsigned int ioread32be(void __iomem *addr) { IO_COND(addr, return pio_read32be(port), return mmio_read32be(addr)); return 0xffffffff; @@ -110,23 +110,23 @@ EXPORT_SYMBOL(ioread32be); #define mmio_write32be(val,port) __raw_writel(be32_to_cpu(val),port) #endif -void fastcall iowrite8(u8 val, void __iomem *addr) +void iowrite8(u8 val, void __iomem *addr) { IO_COND(addr, outb(val,port), writeb(val, addr)); } -void fastcall iowrite16(u16 val, void __iomem *addr) +void iowrite16(u16 val, void __iomem *addr) { IO_COND(addr, outw(val,port), writew(val, addr)); } -void fastcall iowrite16be(u16 val, void __iomem *addr) +void iowrite16be(u16 val, void __iomem *addr) { IO_COND(addr, pio_write16be(val,port), mmio_write16be(val, addr)); } -void fastcall iowrite32(u32 val, void __iomem *addr) +void iowrite32(u32 val, void __iomem *addr) { IO_COND(addr, outl(val,port), writel(val, addr)); } -void fastcall iowrite32be(u32 val, void __iomem *addr) +void iowrite32be(u32 val, void __iomem *addr) { IO_COND(addr, pio_write32be(val,port), mmio_write32be(val, addr)); } @@ -193,15 +193,15 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count) } #endif -void fastcall ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) { IO_COND(addr, insb(port,dst,count), mmio_insb(addr, dst, count)); } -void fastcall ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) { IO_COND(addr, insw(port,dst,count), mmio_insw(addr, dst, count)); } -void fastcall ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) { IO_COND(addr, insl(port,dst,count), mmio_insl(addr, dst, count)); } @@ -209,15 +209,15 @@ EXPORT_SYMBOL(ioread8_rep); EXPORT_SYMBOL(ioread16_rep); EXPORT_SYMBOL(ioread32_rep); -void fastcall iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) +void iowrite8_rep(void __iomem *addr, const void *src, unsigned long count) { IO_COND(addr, outsb(port, src, count), mmio_outsb(addr, src, count)); } -void fastcall iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) +void iowrite16_rep(void __iomem *addr, const void *src, unsigned long count) { IO_COND(addr, outsw(port, src, count), mmio_outsw(addr, src, count)); } -void fastcall iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) +void iowrite32_rep(void __iomem *addr, const void *src, unsigned long count) { IO_COND(addr, outsl(port, src,count), mmio_outsl(addr, src, count)); } diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c index c4cfd6c..9df3ca5 100644 --- a/lib/rwsem-spinlock.c +++ b/lib/rwsem-spinlock.c @@ -125,7 +125,7 @@ __rwsem_wake_one_writer(struct rw_semaphore *sem) /* * get a read lock on the semaphore */ -void fastcall __sched __down_read(struct rw_semaphore *sem) +void __sched __down_read(struct rw_semaphore *sem) { struct rwsem_waiter waiter; struct task_struct *tsk; @@ -168,7 +168,7 @@ void fastcall __sched __down_read(struct rw_semaphore *sem) /* * trylock for reading -- returns 1 if successful, 0 if contention */ -int fastcall __down_read_trylock(struct rw_semaphore *sem) +int __down_read_trylock(struct rw_semaphore *sem) { unsigned long flags; int ret = 0; @@ -191,7 +191,7 @@ int fastcall __down_read_trylock(struct rw_semaphore *sem) * get a write lock on the semaphore * - we increment the waiting count anyway to indicate an exclusive lock */ -void fastcall __sched __down_write_nested(struct rw_semaphore *sem, int subclass) +void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) { struct rwsem_waiter waiter; struct task_struct *tsk; @@ -231,7 +231,7 @@ void fastcall __sched __down_write_nested(struct rw_semaphore *sem, int subclass ; } -void fastcall __sched __down_write(struct rw_semaphore *sem) +void __sched __down_write(struct rw_semaphore *sem) { __down_write_nested(sem, 0); } @@ -239,7 +239,7 @@ void fastcall __sched __down_write(struct rw_semaphore *sem) /* * trylock for writing -- returns 1 if successful, 0 if contention */ -int fastcall __down_write_trylock(struct rw_semaphore *sem) +int __down_write_trylock(struct rw_semaphore *sem) { unsigned long flags; int ret = 0; @@ -260,7 +260,7 @@ int fastcall __down_write_trylock(struct rw_semaphore *sem) /* * release a read lock on the semaphore */ -void fastcall __up_read(struct rw_semaphore *sem) +void __up_read(struct rw_semaphore *sem) { unsigned long flags; @@ -275,7 +275,7 @@ void fastcall __up_read(struct rw_semaphore *sem) /* * release a write lock on the semaphore */ -void fastcall __up_write(struct rw_semaphore *sem) +void __up_write(struct rw_semaphore *sem) { unsigned long flags; @@ -292,7 +292,7 @@ void fastcall __up_write(struct rw_semaphore *sem) * downgrade a write lock into a read lock * - just wake up any readers at the front of the queue */ -void fastcall __downgrade_write(struct rw_semaphore *sem) +void __downgrade_write(struct rw_semaphore *sem) { unsigned long flags; diff --git a/lib/semaphore-sleepers.c b/lib/semaphore-sleepers.c index 1281805..0198782 100644 --- a/lib/semaphore-sleepers.c +++ b/lib/semaphore-sleepers.c @@ -48,12 +48,12 @@ * we cannot lose wakeup events. */ -fastcall void __up(struct semaphore *sem) +void __up(struct semaphore *sem) { wake_up(&sem->wait); } -fastcall void __sched __down(struct semaphore * sem) +void __sched __down(struct semaphore *sem) { struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); @@ -90,7 +90,7 @@ fastcall void __sched __down(struct semaphore * sem) tsk->state = TASK_RUNNING; } -fastcall int __sched __down_interruptible(struct semaphore * sem) +int __sched __down_interruptible(struct semaphore *sem) { int retval = 0; struct task_struct *tsk = current; @@ -153,7 +153,7 @@ fastcall int __sched __down_interruptible(struct semaphore * sem) * single "cmpxchg" without failure cases, * but then it wouldn't work on a 386. */ -fastcall int __down_trylock(struct semaphore * sem) +int __down_trylock(struct semaphore *sem) { int sleepers; unsigned long flags; -- cgit v1.1 From 8b88b0998e35d239e74446cc30f354bdab86df89 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 8 Feb 2008 04:20:26 -0800 Subject: libfs: allow error return from simple attributes Sometimes simple attributes might need to return an error, e.g. for acquiring a mutex interruptibly. In fact we have that situation in spufs already which is the original user of the simple attributes. This patch merged the temporarily forked attributes in spufs back into the main ones and allows to return errors. [akpm@linux-foundation.org: build fix] Signed-off-by: Christoph Hellwig Cc: Cc: Arnd Bergmann Cc: Greg KH Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/fault-inject.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/fault-inject.c b/lib/fault-inject.c index 23985a2..a50a311 100644 --- a/lib/fault-inject.c +++ b/lib/fault-inject.c @@ -134,23 +134,26 @@ bool should_fail(struct fault_attr *attr, ssize_t size) #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS -static void debugfs_ul_set(void *data, u64 val) +static int debugfs_ul_set(void *data, u64 val) { *(unsigned long *)data = val; + return 0; } #ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER -static void debugfs_ul_set_MAX_STACK_TRACE_DEPTH(void *data, u64 val) +static int debugfs_ul_set_MAX_STACK_TRACE_DEPTH(void *data, u64 val) { *(unsigned long *)data = val < MAX_STACK_TRACE_DEPTH ? val : MAX_STACK_TRACE_DEPTH; + return 0; } #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */ -static u64 debugfs_ul_get(void *data) +static int debugfs_ul_get(void *data, u64 *val) { - return *(unsigned long *)data; + *val = *(unsigned long *)data; + return 0; } DEFINE_SIMPLE_ATTRIBUTE(fops_ul, debugfs_ul_get, debugfs_ul_set, "%llu\n"); @@ -174,14 +177,16 @@ static struct dentry *debugfs_create_ul_MAX_STACK_TRACE_DEPTH( } #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */ -static void debugfs_atomic_t_set(void *data, u64 val) +static int debugfs_atomic_t_set(void *data, u64 val) { atomic_set((atomic_t *)data, val); + return 0; } -static u64 debugfs_atomic_t_get(void *data) +static int debugfs_atomic_t_get(void *data, u64 *val) { - return atomic_read((atomic_t *)data); + *val = atomic_read((atomic_t *)data); + return 0; } DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get, -- cgit v1.1 From 06b2a76d25d3cfbd14680021c1d356c91be6904e Mon Sep 17 00:00:00 2001 From: Yi Yang Date: Fri, 8 Feb 2008 04:21:57 -0800 Subject: Add new string functions strict_strto* and convert kernel params to use them Currently, for every sysfs node, the callers will be responsible for implementing store operation, so many many callers are doing duplicate things to validate input, they have the same mistakes because they are calling simple_strtol/ul/ll/uul, especially for module params, they are just numeric, but you can echo such values as 0x1234xxx, 07777888 and 1234aaa, for these cases, module params store operation just ignores succesive invalid char and converts prefix part to a numeric although input is acctually invalid. This patch tries to fix the aforementioned issues and implements strict_strtox serial functions, kernel/params.c uses them to strictly validate input, so module params will reject such values as 0x1234xxxx and returns an error: write error: Invalid argument Any modules which export numeric sysfs node can use strict_strtox instead of simple_strtox to reject any invalid input. Here are some test results: Before applying this patch: [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000g > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000gggggggg > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 010000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0100008 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 010000aaaaa > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# After applying this patch: [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000g > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo 0x1000gggggggg > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# echo 010000 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# echo 0100008 > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# echo 010000aaaaa > /sys/module/e1000/parameters/copybreak -bash: echo: write error: Invalid argument [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# echo -n 4096 > /sys/module/e1000/parameters/copybreak [root@yangyi-dev /]# cat /sys/module/e1000/parameters/copybreak 4096 [root@yangyi-dev /]# [akpm@linux-foundation.org: fix compiler warnings] [akpm@linux-foundation.org: fix off-by-one found by tiwai@suse.de] Signed-off-by: Yi Yang Cc: Greg KH Cc: "Randy.Dunlap" Cc: Takashi Iwai Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/vsprintf.c | 123 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 123 insertions(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 7b481ce..419993f 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -126,6 +126,129 @@ long long simple_strtoll(const char *cp,char **endp,unsigned int base) return simple_strtoull(cp,endp,base); } + +/** + * strict_strtoul - convert a string to an unsigned long strictly + * @cp: The string to be converted + * @base: The number base to use + * @res: The converted result value + * + * strict_strtoul converts a string to an unsigned long only if the + * string is really an unsigned long string, any string containing + * any invalid char at the tail will be rejected and -EINVAL is returned, + * only a newline char at the tail is acceptible because people generally + * change a module parameter in the following way: + * + * echo 1024 > /sys/module/e1000/parameters/copybreak + * + * echo will append a newline to the tail. + * + * It returns 0 if conversion is successful and *res is set to the converted + * value, otherwise it returns -EINVAL and *res is set to 0. + * + * simple_strtoul just ignores the successive invalid characters and + * return the converted value of prefix part of the string. + */ +int strict_strtoul(const char *cp, unsigned int base, unsigned long *res); + +/** + * strict_strtol - convert a string to a long strictly + * @cp: The string to be converted + * @base: The number base to use + * @res: The converted result value + * + * strict_strtol is similiar to strict_strtoul, but it allows the first + * character of a string is '-'. + * + * It returns 0 if conversion is successful and *res is set to the converted + * value, otherwise it returns -EINVAL and *res is set to 0. + */ +int strict_strtol(const char *cp, unsigned int base, long *res); + +/** + * strict_strtoull - convert a string to an unsigned long long strictly + * @cp: The string to be converted + * @base: The number base to use + * @res: The converted result value + * + * strict_strtoull converts a string to an unsigned long long only if the + * string is really an unsigned long long string, any string containing + * any invalid char at the tail will be rejected and -EINVAL is returned, + * only a newline char at the tail is acceptible because people generally + * change a module parameter in the following way: + * + * echo 1024 > /sys/module/e1000/parameters/copybreak + * + * echo will append a newline to the tail of the string. + * + * It returns 0 if conversion is successful and *res is set to the converted + * value, otherwise it returns -EINVAL and *res is set to 0. + * + * simple_strtoull just ignores the successive invalid characters and + * return the converted value of prefix part of the string. + */ +int strict_strtoull(const char *cp, unsigned int base, unsigned long long *res); + +/** + * strict_strtoll - convert a string to a long long strictly + * @cp: The string to be converted + * @base: The number base to use + * @res: The converted result value + * + * strict_strtoll is similiar to strict_strtoull, but it allows the first + * character of a string is '-'. + * + * It returns 0 if conversion is successful and *res is set to the converted + * value, otherwise it returns -EINVAL and *res is set to 0. + */ +int strict_strtoll(const char *cp, unsigned int base, long long *res); + +#define define_strict_strtoux(type, valtype) \ +int strict_strtou##type(const char *cp, unsigned int base, valtype *res)\ +{ \ + char *tail; \ + valtype val; \ + size_t len; \ + \ + *res = 0; \ + len = strlen(cp); \ + if (len == 0) \ + return -EINVAL; \ + \ + val = simple_strtoul(cp, &tail, base); \ + if ((*tail == '\0') || \ + ((len == (size_t)(tail - cp) + 1) && (*tail == '\n'))) {\ + *res = val; \ + return 0; \ + } \ + \ + return -EINVAL; \ +} \ + +#define define_strict_strtox(type, valtype) \ +int strict_strto##type(const char *cp, unsigned int base, valtype *res) \ +{ \ + int ret; \ + if (*cp == '-') { \ + ret = strict_strtou##type(cp+1, base, res); \ + if (ret != 0) \ + *res = -(*res); \ + } else \ + ret = strict_strtou##type(cp, base, res); \ + \ + return ret; \ +} \ + +define_strict_strtoux(l, unsigned long) +define_strict_strtox(l, long) +define_strict_strtoux(ll, unsigned long long) +define_strict_strtox(ll, long long) + +EXPORT_SYMBOL(strict_strtoul); +EXPORT_SYMBOL(strict_strtol); +EXPORT_SYMBOL(strict_strtoll); +EXPORT_SYMBOL(strict_strtoull); + static int skip_atoi(const char **s) { int i=0; -- cgit v1.1 From 4600ecfcf3ad160ac0c6fcff6115f6edb081ccfa Mon Sep 17 00:00:00 2001 From: Guennadi Liakhovetski Date: Fri, 8 Feb 2008 15:00:47 -0800 Subject: lib/scatterlist.o needed by a module only - link it in unconditionally lib/scatterlist.c is needed by drivers/media/video/videobuf-dma-sg.c, and we would like to be able to use the latter without PCI too, for example, on PXA270 ARM CPU. It is then possible to create a configuration with CONFIG_BLOCK=n, where only module code will need scatterlist.c. Therefore it must be in obj-y. Signed-off-by: Guennadi Liakhovetski Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/Makefile b/lib/Makefile index a18062e4..23de261 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -6,7 +6,7 @@ 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 scatterlist.o + proportions.o prio_heap.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o @@ -14,7 +14,7 @@ lib-$(CONFIG_SMP) += cpumask.o lib-y += kobject.o kref.o klist.o obj-y += div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ - bust_spinlocks.o hexdump.o kasprintf.o bitmap.o + bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG -- cgit v1.1 From 185c045c245f46485ad8bbd8cc1100e986ff3f13 Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Sat, 9 Feb 2008 23:24:09 +0100 Subject: x86, core: remove CONFIG_FORCED_INLINING Other than the defconfigs, remove the entry in compiler-gcc4.h, Kconfig.debug and feature-removal-schedule.txt. Signed-off-by: Harvey Harrison Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/Kconfig.debug | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ce0bb26..a370fe8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -465,20 +465,6 @@ config FRAME_POINTER some architectures or if you use external debuggers. If you don't debug the kernel, you can say N. -config FORCED_INLINING - bool "Force gcc to inline functions marked 'inline'" - depends on DEBUG_KERNEL - default y - help - This option determines if the kernel forces gcc to inline the functions - developers have marked 'inline'. Doing so takes away freedom from gcc to - do what it thinks is best, which is desirable for the gcc 3.x series of - compilers. The gcc 4.x series have a rewritten inlining algorithm and - disabling this option will generate a smaller kernel there. Hopefully - this algorithm is so good that allowing gcc4 to make the decision can - become the default in the future, until then this option is there to - test gcc for this. - config BOOT_PRINTK_DELAY bool "Delay each boot printk message by N milliseconds" depends on DEBUG_KERNEL && PRINTK && GENERIC_CALIBRATE_DELAY -- cgit v1.1 From 9b706aee7d92d6ac3002547aea12e3eaa0a750ae Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Sat, 9 Feb 2008 23:24:09 +0100 Subject: x86: trivial printk optimizations In arch/x86/boot/printf.c gets rid of unused tail of digits: const char *digits = "0123456789abcdefghijklmnopqrstuvwxyz"; (we are using 0-9a-f only) Uses smaller/faster lowercasing (by ORing with 0x20) if we know that we work on numbers/digits. Makes strtoul smaller, and also we are getting rid of static const char small_digits[] = "0123456789abcdefx"; static const char large_digits[] = "0123456789ABCDEFX"; since this works equally well: static const char digits[16] = "0123456789ABCDEF"; Size savings: $ size vmlinux.org vmlinux text data bss dec hex filename 877320 112252 90112 1079684 107984 vmlinux.org 877048 112252 90112 1079412 107874 vmlinux It may be also a tiny bit faster because code has less branches now, but I doubt it is measurable. [ hugh@veritas.com: uppercase pointers fix ] Signed-off-by: Denys Vlasenko Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- lib/vsprintf.c | 49 +++++++++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 22 deletions(-) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 419993f..fd987b1 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -26,6 +26,9 @@ #include /* for PAGE_SIZE */ #include +/* Works only for digits and letters, but small and fast */ +#define TOLOWER(x) ((x) | 0x20) + /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string @@ -41,17 +44,17 @@ unsigned long simple_strtoul(const char *cp,char **endp,unsigned int base) if (*cp == '0') { base = 8; cp++; - if ((toupper(*cp) == 'X') && isxdigit(cp[1])) { + if ((TOLOWER(*cp) == 'x') && isxdigit(cp[1])) { cp++; base = 16; } } } else if (base == 16) { - if (cp[0] == '0' && toupper(cp[1]) == 'X') + if (cp[0] == '0' && TOLOWER(cp[1]) == 'x') cp += 2; } while (isxdigit(*cp) && - (value = isdigit(*cp) ? *cp-'0' : toupper(*cp)-'A'+10) < base) { + (value = isdigit(*cp) ? *cp-'0' : TOLOWER(*cp)-'a'+10) < base) { result = result*base + value; cp++; } @@ -92,17 +95,17 @@ unsigned long long simple_strtoull(const char *cp,char **endp,unsigned int base) if (*cp == '0') { base = 8; cp++; - if ((toupper(*cp) == 'X') && isxdigit(cp[1])) { + if ((TOLOWER(*cp) == 'x') && isxdigit(cp[1])) { cp++; base = 16; } } } else if (base == 16) { - if (cp[0] == '0' && toupper(cp[1]) == 'X') + if (cp[0] == '0' && TOLOWER(cp[1]) == 'x') cp += 2; } - while (isxdigit(*cp) && (value = isdigit(*cp) ? *cp-'0' : (islower(*cp) - ? toupper(*cp) : *cp)-'A'+10) < base) { + while (isxdigit(*cp) + && (value = isdigit(*cp) ? *cp-'0' : TOLOWER(*cp)-'a'+10) < base) { result = result*base + value; cp++; } @@ -360,24 +363,25 @@ static noinline char* put_dec(char *buf, unsigned long long num) #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define LEFT 16 /* left justified */ -#define SPECIAL 32 /* 0x */ -#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */ +#define SMALL 32 /* Must be 32 == 0x20 */ +#define SPECIAL 64 /* 0x */ static char *number(char *buf, char *end, unsigned long long num, int base, int size, int precision, int type) { - char sign,tmp[66]; - const char *digits; - /* we are called with base 8, 10 or 16, only, thus don't need "g..." */ - static const char small_digits[] = "0123456789abcdefx"; /* "ghijklmnopqrstuvwxyz"; */ - static const char large_digits[] = "0123456789ABCDEFX"; /* "GHIJKLMNOPQRSTUVWXYZ"; */ + /* we are called with base 8, 10 or 16, only, thus don't need "G..." */ + static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */ + + char tmp[66]; + char sign; + char locase; int need_pfx = ((type & SPECIAL) && base != 10); int i; - digits = (type & LARGE) ? large_digits : small_digits; + /* locase = 0 or 0x20. ORing digits or letters with 'locase' + * produces same digits or (maybe lowercased) letters */ + locase = (type & SMALL); if (type & LEFT) type &= ~ZEROPAD; - if (base < 2 || base > 36) - return NULL; sign = 0; if (type & SIGN) { if ((signed long long) num < 0) { @@ -404,7 +408,7 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int tmp[i++] = '0'; /* Generic code, for any base: else do { - tmp[i++] = digits[do_div(num,base)]; + tmp[i++] = (digits[do_div(num,base)] | locase); } while (num != 0); */ else if (base != 10) { /* 8 or 16 */ @@ -412,7 +416,7 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int int shift = 3; if (base == 16) shift = 4; do { - tmp[i++] = digits[((unsigned char)num) & mask]; + tmp[i++] = (digits[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ @@ -444,7 +448,7 @@ static char *number(char *buf, char *end, unsigned long long num, int base, int ++buf; if (base == 16) { if (buf < end) - *buf = digits[16]; /* for arbitrary base: digits[33]; */ + *buf = ('X' | locase); ++buf; } } @@ -644,6 +648,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) continue; case 'p': + flags |= SMALL; if (field_width == -1) { field_width = 2*sizeof(void *); flags |= ZEROPAD; @@ -680,9 +685,9 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) base = 8; break; - case 'X': - flags |= LARGE; case 'x': + flags |= SMALL; + case 'X': base = 16; break; -- cgit v1.1