From 17d9ddc72fb8bba0d4f67868c9c612e472a594a9 Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Wed, 10 Feb 2010 15:23:44 -0800 Subject: rbtree: Add support for augmented rbtrees Add support for augmented rbtrees in core rbtree code. This will be used in subsequent patches, in x86 PAT code, which needs interval trees to efficiently keep track of PAT ranges. Signed-off-by: Venkatesh Pallipadi LKML-Reference: <20100210232343.GA11465@linux-os.sc.intel.com> Signed-off-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- lib/rbtree.c | 48 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/rbtree.c b/lib/rbtree.c index e2aa3be29858..15e10b1afdd2 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -44,6 +44,11 @@ static void __rb_rotate_left(struct rb_node *node, struct rb_root *root) else root->rb_node = right; rb_set_parent(node, right); + + if (root->augment_cb) { + root->augment_cb(node); + root->augment_cb(right); + } } static void __rb_rotate_right(struct rb_node *node, struct rb_root *root) @@ -67,12 +72,20 @@ static void __rb_rotate_right(struct rb_node *node, struct rb_root *root) else root->rb_node = left; rb_set_parent(node, left); + + if (root->augment_cb) { + root->augment_cb(node); + root->augment_cb(left); + } } void rb_insert_color(struct rb_node *node, struct rb_root *root) { struct rb_node *parent, *gparent; + if (root->augment_cb) + root->augment_cb(node); + while ((parent = rb_parent(node)) && rb_is_red(parent)) { gparent = rb_parent(parent); @@ -227,12 +240,15 @@ void rb_erase(struct rb_node *node, struct rb_root *root) else { struct rb_node *old = node, *left; + int old_parent_cb = 0; + int successor_parent_cb = 0; node = node->rb_right; while ((left = node->rb_left) != NULL) node = left; if (rb_parent(old)) { + old_parent_cb = 1; if (rb_parent(old)->rb_left == old) rb_parent(old)->rb_left = node; else @@ -247,8 +263,10 @@ void rb_erase(struct rb_node *node, struct rb_root *root) if (parent == old) { parent = node; } else { + successor_parent_cb = 1; if (child) rb_set_parent(child, parent); + parent->rb_left = child; node->rb_right = old->rb_right; @@ -259,6 +277,24 @@ void rb_erase(struct rb_node *node, struct rb_root *root) node->rb_left = old->rb_left; rb_set_parent(old->rb_left, node); + if (root->augment_cb) { + /* + * Here, three different nodes can have new children. + * The parent of the successor node that was selected + * to replace the node to be erased. + * The node that is getting erased and is now replaced + * by its successor. + * The parent of the node getting erased-replaced. + */ + if (successor_parent_cb) + root->augment_cb(parent); + + root->augment_cb(node); + + if (old_parent_cb) + root->augment_cb(rb_parent(old)); + } + goto color; } @@ -267,15 +303,19 @@ void rb_erase(struct rb_node *node, struct rb_root *root) if (child) rb_set_parent(child, parent); - if (parent) - { + + if (parent) { if (parent->rb_left == node) parent->rb_left = child; else parent->rb_right = child; - } - else + + if (root->augment_cb) + root->augment_cb(parent); + + } else { root->rb_node = child; + } color: if (color == RB_BLACK) -- cgit v1.2.3 From 86a8938078a8bb518c5376de493e348c7490d506 Mon Sep 17 00:00:00 2001 From: Luca Barbieri Date: Wed, 24 Feb 2010 10:54:24 +0100 Subject: lib: Add self-test for atomic64_t This patch adds self-test on boot code for atomic64_t. This has been used to test the later changes in this patchset. Signed-off-by: Luca Barbieri LKML-Reference: <1267005265-27958-4-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin --- lib/Kconfig.debug | 7 +++ lib/Makefile | 2 + lib/atomic64_test.c | 158 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 167 insertions(+) create mode 100644 lib/atomic64_test.c (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 25c3ed594c54..3676c517a073 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1054,6 +1054,13 @@ config DMA_API_DEBUG This option causes a performance degredation. Use only if you want to debug device drivers. If unsure, say N. +config ATOMIC64_SELFTEST + bool "Perform an atomic64_t self-test at boot" + help + Enable this option to test the atomic64_t functions at boot. + + If unsure, say N. + source "samples/Kconfig" source "lib/Kconfig.kgdb" diff --git a/lib/Makefile b/lib/Makefile index 347ad8db29d3..4af4786fe281 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -99,6 +99,8 @@ obj-$(CONFIG_GENERIC_CSUM) += checksum.o obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o +obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c new file mode 100644 index 000000000000..4ff649e46bad --- /dev/null +++ b/lib/atomic64_test.c @@ -0,0 +1,158 @@ +/* + * Testsuite for atomic64_t functions + * + * Copyright © 2010 Luca Barbieri + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#include +#include + +#define INIT(c) do { atomic64_set(&v, c); r = c; } while (0) +static __init int test_atomic64(void) +{ + long long v0 = 0xaaa31337c001d00dLL; + long long v1 = 0xdeadbeefdeafcafeLL; + long long v2 = 0xfaceabadf00df001LL; + long long onestwos = 0x1111111122222222LL; + long long one = 1LL; + + atomic64_t v = ATOMIC64_INIT(v0); + long long r = v0; + BUG_ON(v.counter != r); + + atomic64_set(&v, v1); + r = v1; + BUG_ON(v.counter != r); + BUG_ON(atomic64_read(&v) != r); + + INIT(v0); + atomic64_add(onestwos, &v); + r += onestwos; + BUG_ON(v.counter != r); + + INIT(v0); + atomic64_add(-one, &v); + r += -one; + BUG_ON(v.counter != r); + + INIT(v0); + r += onestwos; + BUG_ON(atomic64_add_return(onestwos, &v) != r); + BUG_ON(v.counter != r); + + INIT(v0); + r += -one; + BUG_ON(atomic64_add_return(-one, &v) != r); + BUG_ON(v.counter != r); + + INIT(v0); + atomic64_sub(onestwos, &v); + r -= onestwos; + BUG_ON(v.counter != r); + + INIT(v0); + atomic64_sub(-one, &v); + r -= -one; + BUG_ON(v.counter != r); + + INIT(v0); + r -= onestwos; + BUG_ON(atomic64_sub_return(onestwos, &v) != r); + BUG_ON(v.counter != r); + + INIT(v0); + r -= -one; + BUG_ON(atomic64_sub_return(-one, &v) != r); + BUG_ON(v.counter != r); + + INIT(v0); + atomic64_inc(&v); + r += one; + BUG_ON(v.counter != r); + + INIT(v0); + r += one; + BUG_ON(atomic64_inc_return(&v) != r); + BUG_ON(v.counter != r); + + INIT(v0); + atomic64_dec(&v); + r -= one; + BUG_ON(v.counter != r); + + INIT(v0); + r -= one; + BUG_ON(atomic64_dec_return(&v) != r); + BUG_ON(v.counter != r); + + INIT(v0); + BUG_ON(atomic64_xchg(&v, v1) != v0); + r = v1; + BUG_ON(v.counter != r); + + INIT(v0); + BUG_ON(atomic64_cmpxchg(&v, v0, v1) != v0); + r = v1; + BUG_ON(v.counter != r); + + INIT(v0); + BUG_ON(atomic64_cmpxchg(&v, v2, v1) != v0); + BUG_ON(v.counter != r); + + INIT(v0); + BUG_ON(!atomic64_add_unless(&v, one, v0)); + BUG_ON(v.counter != r); + + INIT(v0); + BUG_ON(atomic64_add_unless(&v, one, v1)); + r += one; + BUG_ON(v.counter != r); + + INIT(onestwos); + BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1)); + r -= one; + BUG_ON(v.counter != r); + + INIT(0); + BUG_ON(atomic64_dec_if_positive(&v) != -one); + BUG_ON(v.counter != r); + + INIT(-one); + BUG_ON(atomic64_dec_if_positive(&v) != (-one - one)); + BUG_ON(v.counter != r); + + INIT(onestwos); + BUG_ON(atomic64_inc_not_zero(&v)); + r += one; + BUG_ON(v.counter != r); + + INIT(0); + BUG_ON(!atomic64_inc_not_zero(&v)); + BUG_ON(v.counter != r); + + INIT(-one); + BUG_ON(atomic64_inc_not_zero(&v)); + r += one; + BUG_ON(v.counter != r); + +#ifdef CONFIG_X86 + printk(KERN_INFO "atomic64 test passed for %s+ platform %s CX8 and %s SSE\n", +#ifdef CONFIG_X86_CMPXCHG64 + "586", +#else + "386", +#endif + boot_cpu_has(X86_FEATURE_CX8) ? "with" : "without", + boot_cpu_has(X86_FEATURE_XMM) ? "with" : "without"); +#else + printk(KERN_INFO "atomic64 test passed\n"); +#endif + + return 0; +} + +core_initcall(test_atomic64); -- cgit v1.2.3 From 8f4f202b335144bf5be5c9e5b1bc9477ecdae958 Mon Sep 17 00:00:00 2001 From: Luca Barbieri Date: Fri, 26 Feb 2010 12:22:40 +0100 Subject: lib: Only test atomic64_dec_if_positive on archs having it Currently atomic64_dec_if_positive() is only supported by PowerPC, MIPS and x86-32. Signed-off-by: Luca Barbieri LKML-Reference: <1267183361-20775-1-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin --- lib/atomic64_test.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'lib') diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index 4ff649e46bad..0effcacbebda 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -112,6 +112,7 @@ static __init int test_atomic64(void) r += one; BUG_ON(v.counter != r); +#if defined(CONFIG_X86_32) || defined(CONFIG_MIPS) || defined(CONFIG_PPC) || defined(_ASM_GENERIC_ATOMIC64_H) INIT(onestwos); BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1)); r -= one; @@ -124,6 +125,9 @@ static __init int test_atomic64(void) INIT(-one); BUG_ON(atomic64_dec_if_positive(&v) != (-one - one)); BUG_ON(v.counter != r); +#else +#warning Please implement atomic64_dec_if_positive for your architecture, and add it to the IF above +#endif INIT(onestwos); BUG_ON(atomic64_inc_not_zero(&v)); -- cgit v1.2.3 From d7f6de1e9c4a12e11ba7186c70f0f40caa76f590 Mon Sep 17 00:00:00 2001 From: Luca Barbieri Date: Fri, 26 Feb 2010 12:22:41 +0100 Subject: x86: Implement atomic[64]_dec_if_positive() Add support for atomic_dec_if_positive(), and atomic64_dec_if_positive() for x86-64. atomic64_dec_if_positive() for x86-32 was already implemented in a previous patch. Signed-off-by: Luca Barbieri LKML-Reference: <1267183361-20775-2-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/atomic.h | 23 +++++++++++++++++++++++ arch/x86/include/asm/atomic64_64.h | 23 +++++++++++++++++++++++ lib/atomic64_test.c | 2 +- 3 files changed, 47 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 8f8217b9bdac..706c69492c14 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -246,6 +246,29 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) +/* + * atomic_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic_t + * + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ +static inline int atomic_dec_if_positive(atomic_t *v) +{ + int c, old, dec; + c = atomic_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + /** * atomic_inc_short - increment of a short integer * @v: pointer to type int diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 51c5b4056929..4d6e2cd6c88c 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -221,4 +221,27 @@ static inline int atomic64_add_unless(atomic64_t *v, long a, long u) #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) +/* + * atomic64_dec_if_positive - decrement by 1 if old value positive + * @v: pointer of type atomic_t + * + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ +static inline long atomic64_dec_if_positive(atomic64_t *v) +{ + long c, old, dec; + c = atomic64_read(v); + for (;;) { + dec = c - 1; + if (unlikely(dec < 0)) + break; + old = atomic64_cmpxchg((v), c, dec); + if (likely(old == c)) + break; + c = old; + } + return dec; +} + #endif /* _ASM_X86_ATOMIC64_64_H */ diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index 0effcacbebda..58efdabb3845 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -112,7 +112,7 @@ static __init int test_atomic64(void) r += one; BUG_ON(v.counter != r); -#if defined(CONFIG_X86_32) || defined(CONFIG_MIPS) || defined(CONFIG_PPC) || defined(_ASM_GENERIC_ATOMIC64_H) +#if defined(CONFIG_X86) || defined(CONFIG_MIPS) || defined(CONFIG_PPC) || defined(_ASM_GENERIC_ATOMIC64_H) INIT(onestwos); BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1)); r -= one; -- cgit v1.2.3 From 9efbcd590243045111670c171a951923b877b57d Mon Sep 17 00:00:00 2001 From: Luca Barbieri Date: Mon, 1 Mar 2010 19:55:45 +0100 Subject: lib: Fix atomic64_add_unless test atomic64_add_unless must return 1 if it perfomed the add and 0 otherwise. The test assumed the opposite convention. Reported-by: H. Peter Anvin Signed-off-by: Luca Barbieri LKML-Reference: <1267469749-11878-2-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin --- lib/atomic64_test.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index 58efdabb3845..ee8e6de8b413 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -104,11 +104,11 @@ static __init int test_atomic64(void) BUG_ON(v.counter != r); INIT(v0); - BUG_ON(!atomic64_add_unless(&v, one, v0)); + BUG_ON(atomic64_add_unless(&v, one, v0)); BUG_ON(v.counter != r); INIT(v0); - BUG_ON(atomic64_add_unless(&v, one, v1)); + BUG_ON(!atomic64_add_unless(&v, one, v1)); r += one; BUG_ON(v.counter != r); -- cgit v1.2.3 From 97577896f6b9c056fa0a5e9f6a608110cb3dcd33 Mon Sep 17 00:00:00 2001 From: Luca Barbieri Date: Mon, 1 Mar 2010 19:55:47 +0100 Subject: lib: Fix atomic64_add_unless return value convention atomic64_add_unless must return 1 if it perfomed the add and 0 otherwise. The generic implementation did the opposite thing. Reported-by: H. Peter Anvin Confirmed-by: Paul Mackerras Signed-off-by: Luca Barbieri LKML-Reference: <1267469749-11878-4-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin --- lib/atomic64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/atomic64.c b/lib/atomic64.c index 8bee16ec7524..a21c12bc727c 100644 --- a/lib/atomic64.c +++ b/lib/atomic64.c @@ -162,12 +162,12 @@ int atomic64_add_unless(atomic64_t *v, long long a, long long u) { unsigned long flags; spinlock_t *lock = lock_addr(v); - int ret = 1; + int ret = 0; spin_lock_irqsave(lock, flags); if (v->counter != u) { v->counter += a; - ret = 0; + ret = 1; } spin_unlock_irqrestore(lock, flags); return ret; -- cgit v1.2.3 From 25a304f277ad70166eeae25a4958d2049005c33a Mon Sep 17 00:00:00 2001 From: Luca Barbieri Date: Mon, 1 Mar 2010 19:55:48 +0100 Subject: lib: Fix atomic64_inc_not_zero test atomic64_inc_not_zero must return 1 if it perfomed the add and 0 otherwise. The test assumed the opposite convention. Signed-off-by: Luca Barbieri LKML-Reference: <1267469749-11878-5-git-send-email-luca@luca-barbieri.com> Signed-off-by: H. Peter Anvin --- lib/atomic64_test.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index ee8e6de8b413..f7bb706c9c3a 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -130,16 +130,16 @@ static __init int test_atomic64(void) #endif INIT(onestwos); - BUG_ON(atomic64_inc_not_zero(&v)); + BUG_ON(!atomic64_inc_not_zero(&v)); r += one; BUG_ON(v.counter != r); INIT(0); - BUG_ON(!atomic64_inc_not_zero(&v)); + BUG_ON(atomic64_inc_not_zero(&v)); BUG_ON(v.counter != r); INIT(-one); - BUG_ON(atomic64_inc_not_zero(&v)); + BUG_ON(!atomic64_inc_not_zero(&v)); r += one; BUG_ON(v.counter != r); -- cgit v1.2.3 From a5c9161f27c3e1ae6c0094d262f03a7e98262181 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 1 Mar 2010 11:49:23 -0800 Subject: x86, atomic64: In selftest, distinguish x86-64 from 586+ The x86-64 implementation of the atomics is totally different from the i586+ implementation, which makes it quite confusing to call it "586+". Also fix indentation, and add "i" for "i386" and "i586" as used elsewhere in the kernel. Signed-off-by: H. Peter Anvin Cc: Luca Barbieri LKML-Reference: <1267005265-27958-4-git-send-email-luca@luca-barbieri.com> --- lib/atomic64_test.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c index f7bb706c9c3a..65e482caf5e9 100644 --- a/lib/atomic64_test.c +++ b/lib/atomic64_test.c @@ -144,14 +144,16 @@ static __init int test_atomic64(void) BUG_ON(v.counter != r); #ifdef CONFIG_X86 - printk(KERN_INFO "atomic64 test passed for %s+ platform %s CX8 and %s SSE\n", -#ifdef CONFIG_X86_CMPXCHG64 - "586", + printk(KERN_INFO "atomic64 test passed for %s platform %s CX8 and %s SSE\n", +#ifdef CONFIG_X86_64 + "x86-64", +#elif defined(CONFIG_X86_CMPXCHG64) + "i586+", #else - "386", + "i386+", #endif - boot_cpu_has(X86_FEATURE_CX8) ? "with" : "without", - boot_cpu_has(X86_FEATURE_XMM) ? "with" : "without"); + boot_cpu_has(X86_FEATURE_CX8) ? "with" : "without", + boot_cpu_has(X86_FEATURE_XMM) ? "with" : "without"); #else printk(KERN_INFO "atomic64 test passed\n"); #endif -- cgit v1.2.3 From 2cda2728aa1c8c006418a24f867b25e5eb7a32e2 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 15 Mar 2010 12:46:51 +0100 Subject: block: Fix overrun in lcm() and move it to lib lcm() was defined to take integer-sized arguments. The supplied arguments are multiplied, however, causing us to overflow given sufficiently large input. That in turn led to incorrect optimal I/O size reporting in some cases (RAID over RAID). Switch lcm() over to unsigned long similar to gcd() and move the function from blk-settings.c to lib. Signed-off-by: Martin K. Petersen Signed-off-by: Jens Axboe --- block/blk-settings.c | 11 +---------- include/linux/lcm.h | 8 ++++++++ lib/Makefile | 2 +- lib/lcm.c | 15 +++++++++++++++ 4 files changed, 25 insertions(+), 11 deletions(-) create mode 100644 include/linux/lcm.h create mode 100644 lib/lcm.c (limited to 'lib') diff --git a/block/blk-settings.c b/block/blk-settings.c index 31e7a9375c13..4c4700dca56a 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -8,6 +8,7 @@ #include #include /* for max_pfn/max_low_pfn */ #include +#include #include #include "blk.h" @@ -461,16 +462,6 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) } EXPORT_SYMBOL(blk_queue_stack_limits); -static unsigned int lcm(unsigned int a, unsigned int b) -{ - if (a && b) - return (a * b) / gcd(a, b); - else if (b) - return b; - - return a; -} - /** * blk_stack_limits - adjust queue_limits for stacked devices * @t: the stacking driver limits (top device) diff --git a/include/linux/lcm.h b/include/linux/lcm.h new file mode 100644 index 000000000000..7bf01d779b45 --- /dev/null +++ b/include/linux/lcm.h @@ -0,0 +1,8 @@ +#ifndef _LCM_H +#define _LCM_H + +#include + +unsigned long lcm(unsigned long a, unsigned long b) __attribute_const__; + +#endif /* _LCM_H */ diff --git a/lib/Makefile b/lib/Makefile index 2e152aed7198..0d4015205c64 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -21,7 +21,7 @@ lib-y += kobject.o kref.o klist.o obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ - string_helpers.o gcd.o list_sort.o + string_helpers.o gcd.o lcm.o list_sort.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG diff --git a/lib/lcm.c b/lib/lcm.c new file mode 100644 index 000000000000..157cd88a6ffc --- /dev/null +++ b/lib/lcm.c @@ -0,0 +1,15 @@ +#include +#include +#include + +/* Lowest common multiple */ +unsigned long lcm(unsigned long a, unsigned long b) +{ + if (a && b) + return (a * b) / gcd(a, b); + else if (b) + return b; + + return a; +} +EXPORT_SYMBOL_GPL(lcm); -- cgit v1.2.3 From 1fb2f77c037624601fd214fb7c29faa84cd7bdd7 Mon Sep 17 00:00:00 2001 From: Henrik Kretzschmar Date: Fri, 26 Mar 2010 20:38:35 +0100 Subject: debugobjects: Section mismatch cleanup This patch marks two functions, which only get called at initialization, as __init. Here is also interesting, that modpost doesn't catch here the right function name. WARNING: lib/built-in.o(.text+0x585f): Section mismatch in reference from the function T.506() to the variable .init.data:obj The function T.506() references the variable __initdata obj. This is often because T.506 lacks a __initdata annotation or the annotation of obj is wrong. Signed-off-by: Henrik Kretzschmar LKML-Reference: <1269632315-19403-1-git-send-email-henne@nachtwindheim.de> Signed-off-by: Thomas Gleixner --- lib/debugobjects.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a9a8996d286a..c4ecd3ce7fd4 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -773,7 +773,7 @@ static int __init fixup_free(void *addr, enum debug_obj_state state) } } -static int +static int __init check_results(void *addr, enum debug_obj_state state, int fixups, int warnings) { struct debug_bucket *db; @@ -916,7 +916,7 @@ void __init debug_objects_early_init(void) /* * Convert the statically allocated objects to dynamic ones: */ -static int debug_objects_replace_static_objects(void) +static int __init debug_objects_replace_static_objects(void) { struct debug_bucket *db = obj_hash; struct hlist_node *node, *tmp; -- cgit v1.2.3 From 1527bc8b928dd1399c3d3467dd47d9ede210978a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 1 Feb 2010 15:03:07 +0100 Subject: bitops: Optimize hweight() by making use of compile-time evaluation Rename the extisting runtime hweight() implementations to __arch_hweight(), rename the compile-time versions to __const_hweight() and then have hweight() pick between them. Suggested-by: H. Peter Anvin Signed-off-by: Peter Zijlstra LKML-Reference: <20100318111929.GB11152@aftab> Acked-by: H. Peter Anvin LKML-Reference: <1265028224.24455.154.camel@laptop> Signed-off-by: H. Peter Anvin --- arch/alpha/include/asm/bitops.h | 18 +++++++------ arch/ia64/include/asm/bitops.h | 11 ++++---- arch/sparc/include/asm/bitops_64.h | 11 ++++---- include/asm-generic/bitops/arch_hweight.h | 11 ++++++++ include/asm-generic/bitops/const_hweight.h | 42 ++++++++++++++++++++++++++++++ include/asm-generic/bitops/hweight.h | 8 ++---- include/linux/bitops.h | 25 ------------------ lib/hweight.c | 19 +++++++------- 8 files changed, 87 insertions(+), 58 deletions(-) create mode 100644 include/asm-generic/bitops/arch_hweight.h create mode 100644 include/asm-generic/bitops/const_hweight.h (limited to 'lib') diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h index 15f3ae25c511..296da1d5ed57 100644 --- a/arch/alpha/include/asm/bitops.h +++ b/arch/alpha/include/asm/bitops.h @@ -405,29 +405,31 @@ static inline int fls(int x) #if defined(CONFIG_ALPHA_EV6) && defined(CONFIG_ALPHA_EV67) /* Whee. EV67 can calculate it directly. */ -static inline unsigned long hweight64(unsigned long w) +static inline unsigned long __arch_hweight64(unsigned long w) { return __kernel_ctpop(w); } -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_weight32(unsigned int w) { - return hweight64(w); + return __arch_hweight64(w); } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { - return hweight64(w & 0xffff); + return __arch_hweight64(w & 0xffff); } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { - return hweight64(w & 0xff); + return __arch_hweight64(w & 0xff); } #else -#include +#include #endif +#include + #endif /* __KERNEL__ */ #include diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h index 6ebc229a1c51..9da3df6f1a52 100644 --- a/arch/ia64/include/asm/bitops.h +++ b/arch/ia64/include/asm/bitops.h @@ -437,17 +437,18 @@ __fls (unsigned long x) * hweightN: returns the hamming weight (i.e. the number * of bits set) of a N-bit word */ -static __inline__ unsigned long -hweight64 (unsigned long x) +static __inline__ unsigned long __arch_hweight64(unsigned long x) { unsigned long result; result = ia64_popcnt(x); return result; } -#define hweight32(x) (unsigned int) hweight64((x) & 0xfffffffful) -#define hweight16(x) (unsigned int) hweight64((x) & 0xfffful) -#define hweight8(x) (unsigned int) hweight64((x) & 0xfful) +#define __arch_hweight32(x) ((unsigned int) __arch_hweight64((x) & 0xfffffffful)) +#define __arch_hweight16(x) ((unsigned int) __arch_hweight64((x) & 0xfffful)) +#define __arch_hweight8(x) ((unsigned int) __arch_hweight64((x) & 0xfful)) + +#include #endif /* __KERNEL__ */ diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h index e72ac9cdfb98..766121a67a24 100644 --- a/arch/sparc/include/asm/bitops_64.h +++ b/arch/sparc/include/asm/bitops_64.h @@ -44,7 +44,7 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr); #ifdef ULTRA_HAS_POPULATION_COUNT -static inline unsigned int hweight64(unsigned long w) +static inline unsigned int __arch_hweight64(unsigned long w) { unsigned int res; @@ -52,7 +52,7 @@ static inline unsigned int hweight64(unsigned long w) return res; } -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; @@ -60,7 +60,7 @@ static inline unsigned int hweight32(unsigned int w) return res; } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { unsigned int res; @@ -68,7 +68,7 @@ static inline unsigned int hweight16(unsigned int w) return res; } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { unsigned int res; @@ -78,9 +78,10 @@ static inline unsigned int hweight8(unsigned int w) #else -#include +#include #endif +#include #include #endif /* __KERNEL__ */ diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h new file mode 100644 index 000000000000..3a7be842cdce --- /dev/null +++ b/include/asm-generic/bitops/arch_hweight.h @@ -0,0 +1,11 @@ +#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ + +#include + +extern unsigned int __arch_hweight32(unsigned int w); +extern unsigned int __arch_hweight16(unsigned int w); +extern unsigned int __arch_hweight8(unsigned int w); +extern unsigned long __arch_hweight64(__u64 w); + +#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h new file mode 100644 index 000000000000..fa2a50b7ee66 --- /dev/null +++ b/include/asm-generic/bitops/const_hweight.h @@ -0,0 +1,42 @@ +#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ + +/* + * Compile time versions of __arch_hweightN() + */ +#define __const_hweight8(w) \ + ( (!!((w) & (1ULL << 0))) + \ + (!!((w) & (1ULL << 1))) + \ + (!!((w) & (1ULL << 2))) + \ + (!!((w) & (1ULL << 3))) + \ + (!!((w) & (1ULL << 4))) + \ + (!!((w) & (1ULL << 5))) + \ + (!!((w) & (1ULL << 6))) + \ + (!!((w) & (1ULL << 7))) ) + +#define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) +#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) +#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) + +/* + * Generic interface. + */ +#define hweight8(w) (__builtin_constant_p(w) ? __const_hweight8(w) : __arch_hweight8(w)) +#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w)) +#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w)) +#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) + +/* + * Interface for known constant arguments + */ +#define HWEIGHT8(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w)) +#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w)) +#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w)) +#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w)) + +/* + * Type invariant interface to the compile time constant hweight functions. + */ +#define HWEIGHT(w) HWEIGHT64((u64)w) + +#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */ diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h index fbbc383771da..a94d6519c7ed 100644 --- a/include/asm-generic/bitops/hweight.h +++ b/include/asm-generic/bitops/hweight.h @@ -1,11 +1,7 @@ #ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_ #define _ASM_GENERIC_BITOPS_HWEIGHT_H_ -#include - -extern unsigned int hweight32(unsigned int w); -extern unsigned int hweight16(unsigned int w); -extern unsigned int hweight8(unsigned int w); -extern unsigned long hweight64(__u64 w); +#include +#include #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index b79389879238..c55d5bc4ee58 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -47,31 +47,6 @@ static inline unsigned long hweight_long(unsigned long w) return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } -/* - * Clearly slow versions of the hweightN() functions, their benefit is - * of course compile time evaluation of constant arguments. - */ -#define HWEIGHT8(w) \ - ( BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + \ - (!!((w) & (1ULL << 0))) + \ - (!!((w) & (1ULL << 1))) + \ - (!!((w) & (1ULL << 2))) + \ - (!!((w) & (1ULL << 3))) + \ - (!!((w) & (1ULL << 4))) + \ - (!!((w) & (1ULL << 5))) + \ - (!!((w) & (1ULL << 6))) + \ - (!!((w) & (1ULL << 7))) ) - -#define HWEIGHT16(w) (HWEIGHT8(w) + HWEIGHT8((w) >> 8)) -#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16)) -#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32)) - -/* - * Type invariant version that simply casts things to the - * largest type. - */ -#define HWEIGHT(w) HWEIGHT64((u64)(w)) - /** * rol32 - rotate a 32-bit value left * @word: value to rotate diff --git a/lib/hweight.c b/lib/hweight.c index 63ee4eb1228d..a6927e76840f 100644 --- a/lib/hweight.c +++ b/lib/hweight.c @@ -9,7 +9,7 @@ * The Hamming Weight of a number is the total number of bits set in it. */ -unsigned int hweight32(unsigned int w) +unsigned int __arch_hweight32(unsigned int w) { #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; @@ -24,29 +24,30 @@ unsigned int hweight32(unsigned int w) return (res + (res >> 16)) & 0x000000FF; #endif } -EXPORT_SYMBOL(hweight32); +EXPORT_SYMBOL(__arch_hweight32); -unsigned int hweight16(unsigned int w) +unsigned int __arch_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } -EXPORT_SYMBOL(hweight16); +EXPORT_SYMBOL(__arch_hweight16); -unsigned int hweight8(unsigned int w) +unsigned int __arch_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } -EXPORT_SYMBOL(hweight8); +EXPORT_SYMBOL(__arch_hweight8); -unsigned long hweight64(__u64 w) +unsigned long __arch_hweight64(__u64 w) { #if BITS_PER_LONG == 32 - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); + return __arch_hweight32((unsigned int)(w >> 32)) + + __arch_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; @@ -63,4 +64,4 @@ unsigned long hweight64(__u64 w) #endif #endif } -EXPORT_SYMBOL(hweight64); +EXPORT_SYMBOL(__arch_hweight64); -- cgit v1.2.3 From d61931d89be506372d01a90d1755f6d0a9fafe2d Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 5 Mar 2010 17:34:46 +0100 Subject: x86: Add optimized popcnt variants Add support for the hardware version of the Hamming weight function, popcnt, present in CPUs which advertize it under CPUID, Function 0x0000_0001_ECX[23]. On CPUs which don't support it, we fallback to the default lib/hweight.c sw versions. A synthetic benchmark comparing popcnt with __sw_hweight64 showed almost a 3x speedup on a F10h machine. Signed-off-by: Borislav Petkov LKML-Reference: <20100318112015.GC11152@aftab> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 5 +++ arch/x86/include/asm/alternative.h | 9 +++-- arch/x86/include/asm/arch_hweight.h | 59 +++++++++++++++++++++++++++++++ arch/x86/include/asm/bitops.h | 4 ++- include/asm-generic/bitops/arch_hweight.h | 22 +++++++++--- lib/Makefile | 3 ++ lib/hweight.c | 20 +++++------ scripts/Makefile.lib | 4 +++ 8 files changed, 108 insertions(+), 18 deletions(-) create mode 100644 arch/x86/include/asm/arch_hweight.h (limited to 'lib') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0eacb1ffb421..89d8c54cdd37 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -238,6 +238,11 @@ config X86_32_LAZY_GS def_bool y depends on X86_32 && !CC_STACKPROTECTOR +config ARCH_HWEIGHT_CFLAGS + string + default "-fcall-saved-ecx -fcall-saved-edx" if X86_32 + default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64 + config KTIME_SCALAR def_bool X86_32 source "init/Kconfig" diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index b09ec55650b3..67dae51e7fd0 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -39,9 +39,6 @@ #define LOCK_PREFIX "" #endif -/* This must be included *after* the definition of LOCK_PREFIX */ -#include - struct alt_instr { u8 *instr; /* original instruction */ u8 *replacement; @@ -95,6 +92,12 @@ static inline int alternatives_text_reserved(void *start, void *end) "663:\n\t" newinstr "\n664:\n" /* replacement */ \ ".previous" +/* + * This must be included *after* the definition of ALTERNATIVE due to + * + */ +#include + /* * Alternative instructions for different CPU types or capabilities. * diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h new file mode 100644 index 000000000000..d1fc3c219ae6 --- /dev/null +++ b/arch/x86/include/asm/arch_hweight.h @@ -0,0 +1,59 @@ +#ifndef _ASM_X86_HWEIGHT_H +#define _ASM_X86_HWEIGHT_H + +#ifdef CONFIG_64BIT +/* popcnt %rdi, %rax */ +#define POPCNT ".byte 0xf3,0x48,0x0f,0xb8,0xc7" +#define REG_IN "D" +#define REG_OUT "a" +#else +/* popcnt %eax, %eax */ +#define POPCNT ".byte 0xf3,0x0f,0xb8,0xc0" +#define REG_IN "a" +#define REG_OUT "a" +#endif + +/* + * __sw_hweightXX are called from within the alternatives below + * and callee-clobbered registers need to be taken care of. See + * ARCH_HWEIGHT_CFLAGS in for the respective + * compiler switches. + */ +static inline unsigned int __arch_hweight32(unsigned int w) +{ + unsigned int res = 0; + + asm (ALTERNATIVE("call __sw_hweight32", POPCNT, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); + + return res; +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __arch_hweight32(w & 0xffff); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __arch_hweight32(w & 0xff); +} + +static inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res = 0; + +#ifdef CONFIG_X86_32 + return __arch_hweight32((u32)w) + + __arch_hweight32((u32)(w >> 32)); +#else + asm (ALTERNATIVE("call __sw_hweight64", POPCNT, X86_FEATURE_POPCNT) + : "="REG_OUT (res) + : REG_IN (w)); +#endif /* CONFIG_X86_32 */ + + return res; +} + +#endif diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 02b47a603fc8..545776efeb16 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -444,7 +444,9 @@ static inline int fls(int x) #define ARCH_HAS_FAST_MULTIPLIER 1 -#include +#include + +#include #endif /* __KERNEL__ */ diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h index 3a7be842cdce..9a81c1e9436c 100644 --- a/include/asm-generic/bitops/arch_hweight.h +++ b/include/asm-generic/bitops/arch_hweight.h @@ -3,9 +3,23 @@ #include -extern unsigned int __arch_hweight32(unsigned int w); -extern unsigned int __arch_hweight16(unsigned int w); -extern unsigned int __arch_hweight8(unsigned int w); -extern unsigned long __arch_hweight64(__u64 w); +inline unsigned int __arch_hweight32(unsigned int w) +{ + return __sw_hweight32(w); +} +inline unsigned int __arch_hweight16(unsigned int w) +{ + return __sw_hweight16(w); +} + +inline unsigned int __arch_hweight8(unsigned int w) +{ + return __sw_hweight8(w); +} + +inline unsigned long __arch_hweight64(__u64 w) +{ + return __sw_hweight64(w); +} #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/lib/Makefile b/lib/Makefile index 2e152aed7198..abe63a8ad143 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -39,7 +39,10 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o obj-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o + +CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS)) obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o + obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o obj-$(CONFIG_BTREE) += btree.o obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o diff --git a/lib/hweight.c b/lib/hweight.c index a6927e76840f..3c79d50814cf 100644 --- a/lib/hweight.c +++ b/lib/hweight.c @@ -9,7 +9,7 @@ * The Hamming Weight of a number is the total number of bits set in it. */ -unsigned int __arch_hweight32(unsigned int w) +unsigned int __sw_hweight32(unsigned int w) { #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x55555555; @@ -24,30 +24,30 @@ unsigned int __arch_hweight32(unsigned int w) return (res + (res >> 16)) & 0x000000FF; #endif } -EXPORT_SYMBOL(__arch_hweight32); +EXPORT_SYMBOL(__sw_hweight32); -unsigned int __arch_hweight16(unsigned int w) +unsigned int __sw_hweight16(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x5555); res = (res & 0x3333) + ((res >> 2) & 0x3333); res = (res + (res >> 4)) & 0x0F0F; return (res + (res >> 8)) & 0x00FF; } -EXPORT_SYMBOL(__arch_hweight16); +EXPORT_SYMBOL(__sw_hweight16); -unsigned int __arch_hweight8(unsigned int w) +unsigned int __sw_hweight8(unsigned int w) { unsigned int res = w - ((w >> 1) & 0x55); res = (res & 0x33) + ((res >> 2) & 0x33); return (res + (res >> 4)) & 0x0F; } -EXPORT_SYMBOL(__arch_hweight8); +EXPORT_SYMBOL(__sw_hweight8); -unsigned long __arch_hweight64(__u64 w) +unsigned long __sw_hweight64(__u64 w) { #if BITS_PER_LONG == 32 - return __arch_hweight32((unsigned int)(w >> 32)) + - __arch_hweight32((unsigned int)w); + return __sw_hweight32((unsigned int)(w >> 32)) + + __sw_hweight32((unsigned int)w); #elif BITS_PER_LONG == 64 #ifdef ARCH_HAS_FAST_MULTIPLIER w -= (w >> 1) & 0x5555555555555555ul; @@ -64,4 +64,4 @@ unsigned long __arch_hweight64(__u64 w) #endif #endif } -EXPORT_SYMBOL(__arch_hweight64); +EXPORT_SYMBOL(__sw_hweight64); diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index f9bdf264473d..cbcd654215e6 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -245,3 +245,7 @@ quiet_cmd_lzo = LZO $@ cmd_lzo = (cat $(filter-out FORCE,$^) | \ lzop -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \ (rm -f $@ ; false) + +# misc stuff +# --------------------------------------------------------------------------- +quote:=" -- cgit v1.2.3 From 47c4c864af60d14926f4017d23968a8341b8ab9f Mon Sep 17 00:00:00 2001 From: Michal Simek Date: Tue, 6 Apr 2010 10:19:30 +0200 Subject: microblaze: Enable memory leak detector Enable DEBUG_KMEMLEAK for microblaze Signed-off-by: Michal Simek --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1fafb4b99c9b..ff017108700d 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -356,7 +356,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390 || SUPERH) + (X86 || ARM || PPC || S390 || SUPERH || MICROBLAZE) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT -- cgit v1.2.3 From 39a37ce1cc5eef420604fa68b776ff5dab400340 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 6 Apr 2010 19:45:12 +0300 Subject: dma-debug: Cleanup for copy-loop in filter_write() Earlier in this function we set the last byte of "buf" to NULL so we always hit the break statement and "i" is never equal to NAME_MAX_LEN. This patch doesn't change how the driver works but it silences a Smatch warning and it makes it clearer that we don't write past the end of the array. Signed-off-by: Dan Carpenter Signed-off-by: Joerg Roedel --- lib/dma-debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/dma-debug.c b/lib/dma-debug.c index ba8b67039d13..01e64270e246 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -570,7 +570,7 @@ static ssize_t filter_write(struct file *file, const char __user *userbuf, * Now parse out the first token and use it as the name for the * driver to filter for. */ - for (i = 0; i < NAME_MAX_LEN; ++i) { + for (i = 0; i < NAME_MAX_LEN - 1; ++i) { current_driver_name[i] = buf[i]; if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0) break; -- cgit v1.2.3 From 2a7268abc48c8009b284bd88605d14fcb65772ec Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Tue, 6 Apr 2010 14:35:01 -0700 Subject: ratelimit: annotate ___ratelimit() To prevent from wrongly using the return value. [akpm@linux-foundation.org: fix spello] Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Dave Young Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ratelimit.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 09f5ce1810dc..b4cd24ff9b29 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -16,9 +16,14 @@ /* * __ratelimit - rate limiting * @rs: ratelimit_state data + * @func: name of calling function * - * This enforces a rate limit: not more than @rs->ratelimit_burst callbacks - * in every @rs->ratelimit_jiffies + * This enforces a rate limit: not more than @rs->burst callbacks + * in every @rs->interval + * + * RETURNS: + * 0 means callbacks will be suppressed. + * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { -- cgit v1.2.3 From 57119c34e53bbb8d244c3ff1335ef5145768538f Mon Sep 17 00:00:00 2001 From: Yong Zhang Date: Tue, 6 Apr 2010 14:35:03 -0700 Subject: ratelimit: fix the return value when __ratelimit() fails to acquire the lock The log of commit edaac8e3167501cda336231d00611bf59c164346 ("ratelimit: Fix/allow use in atomic contexts"), indicates that we want to suppress the callback when the trylock fails. Signed-off-by: Yong Zhang Cc: Ingo Molnar Cc: Christian Borntraeger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/ratelimit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/ratelimit.c b/lib/ratelimit.c index b4cd24ff9b29..027a03f4c56d 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -40,7 +40,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) * the entity that is holding the lock already: */ if (!spin_trylock_irqsave(&rs->lock, flags)) - return 1; + return 0; if (!rs->begin) rs->begin = jiffies; -- cgit v1.2.3 From 3eac4abaa69949af0e2f64e5c55ee8a22bbdd3e7 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Wed, 7 Apr 2010 11:52:46 -0700 Subject: rwsem generic spinlock: use IRQ save/restore spinlocks rwsems can be used with IRQs disabled, particularily in early boot before IRQs are enabled. Currently the spin_unlock_irq() usage in the slow-patch will unconditionally enable interrupts and cause problems since interrupts are not yet initialized or enabled. This patch uses save/restore versions of IRQ spinlocks in the slowpath to ensure interrupts are not unintentionally disabled. Signed-off-by: Kevin Hilman Signed-off-by: Linus Torvalds --- lib/rwsem-spinlock.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c index ccf95bff7984..ffc9fc7f3b05 100644 --- a/lib/rwsem-spinlock.c +++ b/lib/rwsem-spinlock.c @@ -143,13 +143,14 @@ void __sched __down_read(struct rw_semaphore *sem) { struct rwsem_waiter waiter; struct task_struct *tsk; + unsigned long flags; - spin_lock_irq(&sem->wait_lock); + spin_lock_irqsave(&sem->wait_lock, flags); if (sem->activity >= 0 && list_empty(&sem->wait_list)) { /* granted */ sem->activity++; - spin_unlock_irq(&sem->wait_lock); + spin_unlock_irqrestore(&sem->wait_lock, flags); goto out; } @@ -164,7 +165,7 @@ void __sched __down_read(struct rw_semaphore *sem) list_add_tail(&waiter.list, &sem->wait_list); /* we don't need to touch the semaphore struct anymore */ - spin_unlock_irq(&sem->wait_lock); + spin_unlock_irqrestore(&sem->wait_lock, flags); /* wait to be given the lock */ for (;;) { @@ -209,13 +210,14 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) { struct rwsem_waiter waiter; struct task_struct *tsk; + unsigned long flags; - spin_lock_irq(&sem->wait_lock); + spin_lock_irqsave(&sem->wait_lock, flags); if (sem->activity == 0 && list_empty(&sem->wait_list)) { /* granted */ sem->activity = -1; - spin_unlock_irq(&sem->wait_lock); + spin_unlock_irqrestore(&sem->wait_lock, flags); goto out; } @@ -230,7 +232,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) list_add_tail(&waiter.list, &sem->wait_list); /* we don't need to touch the semaphore struct anymore */ - spin_unlock_irq(&sem->wait_lock); + spin_unlock_irqrestore(&sem->wait_lock, flags); /* wait to be given the lock */ for (;;) { -- cgit v1.2.3 From ce82653d6cfcc95ba88c25908664878459fb1b8d Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 6 Apr 2010 22:36:20 +0100 Subject: radix_tree_tag_get() is not as safe as the docs make out [ver #2] radix_tree_tag_get() is not safe to use concurrently with radix_tree_tag_set() or radix_tree_tag_clear(). The problem is that the double tag_get() in radix_tree_tag_get(): if (!tag_get(node, tag, offset)) saw_unset_tag = 1; if (height == 1) { int ret = tag_get(node, tag, offset); may see the value change due to the action of set/clear. RCU is no protection against this as no pointers are being changed, no nodes are being replaced according to a COW protocol - set/clear alter the node directly. The documentation in linux/radix-tree.h, however, says that radix_tree_tag_get() is an exception to the rule that "any function modifying the tree or tags (...) must exclude other modifications, and exclude any functions reading the tree". The problem is that the next statement in radix_tree_tag_get() checks that the tag doesn't vary over time: BUG_ON(ret && saw_unset_tag); This has been seen happening in FS-Cache: https://www.redhat.com/archives/linux-cachefs/2010-April/msg00013.html To this end, remove the BUG_ON() from radix_tree_tag_get() and note in various comments that the value of the tag may change whilst the RCU read lock is held, and thus that the return value of radix_tree_tag_get() may not be relied upon unless radix_tree_tag_set/clear() and radix_tree_delete() are excluded from running concurrently with it. Reported-by: Romain DEGEZ Signed-off-by: David Howells Acked-by: Nick Piggin Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 7 +++++++ lib/radix-tree.c | 12 ++++++------ 2 files changed, 13 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index c5da74918096..55ca73cf25e5 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -121,6 +121,13 @@ do { \ * (Note, rcu_assign_pointer and rcu_dereference are not needed to control * access to data items when inserting into or looking up from the radix tree) * + * Note that the value returned by radix_tree_tag_get() may not be relied upon + * if only the RCU read lock is held. Functions to set/clear tags and to + * delete nodes running concurrently with it may affect its result such that + * two consecutive reads in the same locked section may return different + * values. If reliability is required, modification functions must also be + * excluded from concurrency. + * * radix_tree_tagged is able to be called without locking or RCU. */ diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 0871582aa29d..2a087e0f9863 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -555,6 +555,10 @@ EXPORT_SYMBOL(radix_tree_tag_clear); * * 0: tag not present or not set * 1: tag set + * + * Note that the return value of this function may not be relied on, even if + * the RCU lock is held, unless tag modification and node deletion are excluded + * from concurrency. */ int radix_tree_tag_get(struct radix_tree_root *root, unsigned long index, unsigned int tag) @@ -595,12 +599,8 @@ int radix_tree_tag_get(struct radix_tree_root *root, */ if (!tag_get(node, tag, offset)) saw_unset_tag = 1; - if (height == 1) { - int ret = tag_get(node, tag, offset); - - BUG_ON(ret && saw_unset_tag); - return !!ret; - } + if (height == 1) + return !!tag_get(node, tag, offset); node = rcu_dereference_raw(node->slots[offset]); shift -= RADIX_TREE_MAP_SHIFT; height--; -- cgit v1.2.3 From 8b8d8e2840a440d62e8dc0ef36ba433b26f70d32 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 9 Apr 2010 00:14:35 -0700 Subject: sparc64: Support kmemleak. Only missing thing was an _sdata marker in vmlinux.lds.S Signed-off-by: David S. Miller --- arch/sparc/kernel/vmlinux.lds.S | 4 ++++ lib/Kconfig.debug | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index c4f5758c9dc7..0c1e6783657f 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -52,6 +52,10 @@ SECTIONS _etext = .; RO_DATA(PAGE_SIZE) + + /* Start of data section */ + _sdata = .; + .data1 : { *(.data1) } diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1fafb4b99c9b..6c2be6089559 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -356,7 +356,7 @@ config SLUB_STATS config DEBUG_KMEMLEAK bool "Kernel memory leak detector" depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \ - (X86 || ARM || PPC || S390 || SUPERH) + (X86 || ARM || PPC || S390 || SPARC64 || SUPERH) select DEBUG_FS if SYSFS select STACKTRACE if STACKTRACE_SUPPORT -- cgit v1.2.3 From 4e310fda91cb095915395f811d10b2c900c9589e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 14 Apr 2010 09:27:40 -0700 Subject: vsprintf: Change struct printf_spec.precision from s8 to s16 Commit ef0658f3de484bf9b173639cd47544584e01efa5 changed precision from int to s8. There is existing kernel code that uses a larger precision. An example from the audit code: vsnprintf(...,..., " msg='%.1024s'", (char *)data); which overflows precision and truncates to nothing. Extending precision size fixes the audit system issue. Other changes: Change the size of the struct printf_spec.type from u16 to u8 so sizeof(struct printf_spec) stays as small as possible. Reorder the struct members so sizeof(struct printf_spec) remains 64 bits without alignment holes. Document the struct members a bit more. Original-patch-by: Eric Paris Signed-off-by: Joe Perches Tested-by: Justin P. Mattock Signed-off-by: Linus Torvalds --- lib/vsprintf.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 24112e5a5780..7376b7c55ffe 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -408,12 +408,12 @@ enum format_type { }; struct printf_spec { - u16 type; - s16 field_width; /* width of output field */ + u8 type; /* format_type enum */ u8 flags; /* flags to number() */ - u8 base; - s8 precision; /* # of digits/chars */ - u8 qualifier; + u8 base; /* number base, 8, 10 or 16 only */ + u8 qualifier; /* number qualifier, one of 'hHlLtzZ' */ + s16 field_width; /* width of output field */ + s16 precision; /* # of digits/chars */ }; static char *number(char *buf, char *end, unsigned long long num, -- cgit v1.2.3 From e59464c735db19619cde2aa331609adb02005f5b Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Fri, 23 Apr 2010 13:17:45 -0400 Subject: flex_array: fix the panic when calling flex_array_alloc() without __GFP_ZERO memset() is called with the wrong address and the kernel panics. Signed-off-by: Changli Gao Cc: Patrick McHardy Acked-by: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/flex_array.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/flex_array.c b/lib/flex_array.c index 66eef2e4483e..41b1804fa728 100644 --- a/lib/flex_array.c +++ b/lib/flex_array.c @@ -99,7 +99,7 @@ struct flex_array *flex_array_alloc(int element_size, unsigned int total, ret->element_size = element_size; ret->total_nr_elements = total; if (elements_fit_in_base(ret) && !(flags & __GFP_ZERO)) - memset(ret->parts[0], FLEX_ARRAY_FREE, + memset(&ret->parts[0], FLEX_ARRAY_FREE, FLEX_ARRAY_BASE_BYTES_LEFT); return ret; } -- cgit v1.2.3 From ccdb40048b2972f10bdc944913c0e0ee26b5d1f2 Mon Sep 17 00:00:00 2001 From: Albin Tonnerre Date: Fri, 23 Apr 2010 13:17:58 -0400 Subject: lib: fix the use of LZO to decompress initramfs images This patch fixes 2 issues with the LZO decompressor: - It doesn't handle the case where a block isn't compressed at all. In this case, calling lzo1x_decompress_safe will fail, so we need to just use memcpy() instead (the upstream LZO code does something similar) - Since commit 54291362d2a5738e1b0495df2abcb9e6b0563a3f ("initramfs: add missing decompressor error check") , the decompressor return code is checked in the init/initramfs.c The LZO decompressor didn't return the expected value, causing the initramfs code to falsely believe a decompression error occured Signed-off-by: Albin Tonnerre Tested-by: bert schulze Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/decompress_unlzo.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) (limited to 'lib') diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c index db521f45626e..bcb3a4bd68ff 100644 --- a/lib/decompress_unlzo.c +++ b/lib/decompress_unlzo.c @@ -97,7 +97,7 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, u32 src_len, dst_len; size_t tmp; u8 *in_buf, *in_buf_save, *out_buf; - int obytes_processed = 0; + int ret = -1; set_error_fn(error_fn); @@ -174,15 +174,22 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, /* decompress */ tmp = dst_len; - r = lzo1x_decompress_safe((u8 *) in_buf, src_len, + + /* When the input data is not compressed at all, + * lzo1x_decompress_safe will fail, so call memcpy() + * instead */ + if (unlikely(dst_len == src_len)) + memcpy(out_buf, in_buf, src_len); + else { + r = lzo1x_decompress_safe((u8 *) in_buf, src_len, out_buf, &tmp); - if (r != LZO_E_OK || dst_len != tmp) { - error("Compressed data violation"); - goto exit_2; + if (r != LZO_E_OK || dst_len != tmp) { + error("Compressed data violation"); + goto exit_2; + } } - obytes_processed += dst_len; if (flush) flush(out_buf, dst_len); if (output) @@ -196,6 +203,7 @@ STATIC inline int INIT unlzo(u8 *input, int in_len, in_buf += src_len; } + ret = 0; exit_2: if (!input) free(in_buf); @@ -203,7 +211,7 @@ exit_1: if (!output) free(out_buf); exit: - return obytes_processed; + return ret; } #define decompress unlzo -- cgit v1.2.3 From 98d5ce0d0044666fc85a01915a1d22407eb546fd Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Fri, 23 Apr 2010 13:18:04 -0400 Subject: lib/vsprintf.c: add missing EXPORT_SYMBOL(simple_strtoll) Add a missing EXPORT_SYMBOL. I must be the first person that wants to use this function :-) Signed-off-by: Hans Verkuil Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/vsprintf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'lib') diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 7376b7c55ffe..46d34b0b74a8 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -118,6 +118,7 @@ long long simple_strtoll(const char *cp, char **endp, unsigned int base) return simple_strtoull(cp, endp, base); } +EXPORT_SYMBOL(simple_strtoll); /** * strict_strtoul - convert a string to an unsigned long strictly -- cgit v1.2.3 From 2b3fc35f6919344e3cf722dde8308f47235c0b70 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Tue, 20 Apr 2010 16:23:07 +0800 Subject: rcu: optionally leave lockdep enabled after RCU lockdep splat There is no need to disable lockdep after an RCU lockdep splat, so remove the debug_lockdeps_off() from lockdep_rcu_dereference(). To avoid repeated lockdep splats, use a static variable in the inlined rcu_dereference_check() and rcu_dereference_protected() macros so that a given instance splats only once, but so that multiple instances can be detected per boot. This is controlled by a new config variable CONFIG_PROVE_RCU_REPEATEDLY, which is disabled by default. This provides the normal lockdep behavior by default, but permits people who want to find multiple RCU-lockdep splats per boot to easily do so. Requested-by: Eric Paris Signed-off-by: Lai Jiangshan Tested-by: Eric Paris Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 15 +++++++++++---- kernel/lockdep.c | 3 +++ lib/Kconfig.debug | 12 ++++++++++++ 3 files changed, 26 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index db266bbed23f..4dca2752cfde 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -192,6 +192,15 @@ static inline int rcu_read_lock_sched_held(void) extern int rcu_my_thread_group_empty(void); +#define __do_rcu_dereference_check(c) \ + do { \ + static bool __warned; \ + if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \ + __warned = true; \ + lockdep_rcu_dereference(__FILE__, __LINE__); \ + } \ + } while (0) + /** * rcu_dereference_check - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing @@ -221,8 +230,7 @@ extern int rcu_my_thread_group_empty(void); */ #define rcu_dereference_check(p, c) \ ({ \ - if (debug_lockdep_rcu_enabled() && !(c)) \ - lockdep_rcu_dereference(__FILE__, __LINE__); \ + __do_rcu_dereference_check(c); \ rcu_dereference_raw(p); \ }) @@ -239,8 +247,7 @@ extern int rcu_my_thread_group_empty(void); */ #define rcu_dereference_protected(p, c) \ ({ \ - if (debug_lockdep_rcu_enabled() && !(c)) \ - lockdep_rcu_dereference(__FILE__, __LINE__); \ + __do_rcu_dereference_check(c); \ (p); \ }) diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 2594e1ce41cb..3a756ba8d5d8 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -3801,8 +3801,11 @@ void lockdep_rcu_dereference(const char *file, const int line) { struct task_struct *curr = current; +#ifndef CONFIG_PROVE_RCU_REPEATEDLY if (!debug_locks_off()) return; +#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */ + /* Note: the following can be executed concurrently, so be careful. */ printk("\n===================================================\n"); printk( "[ INFO: suspicious rcu_dereference_check() usage. ]\n"); printk( "---------------------------------------------------\n"); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 935248bdbc47..94090b4bb7d2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -512,6 +512,18 @@ config PROVE_RCU Say N if you are unsure. +config PROVE_RCU_REPEATEDLY + bool "RCU debugging: don't disable PROVE_RCU on first splat" + depends on PROVE_RCU + default n + help + By itself, PROVE_RCU will disable checking upon issuing the + first warning (or "splat"). This feature prevents such + disabling, allowing multiple RCU-lockdep warnings to be printed + on a single reboot. + + Say N if you are unsure. + config LOCKDEP bool depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT -- cgit v1.2.3 From 55ec936ff4e57cc626db336a7bf33b267390e9b4 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 13 Apr 2010 12:22:33 -0700 Subject: rcu: enable CPU_STALL_VERBOSE by default The CPU_STALL_VERBOSE kernel configuration parameter was added to 2.6.34 to identify any preempted/blocked tasks that were preventing the current grace period from completing when running preemptible RCU. As is conventional for new configurations parameters, this defaulted disabled. It is now time to enable it by default. Signed-off-by: Paul E. McKenney --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 94090b4bb7d2..930a9e5eae08 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -805,7 +805,7 @@ config RCU_CPU_STALL_DETECTOR config RCU_CPU_STALL_VERBOSE bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR" depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU - default n + default y help This option causes RCU to printk detailed per-task information for any tasks that are stalling the current RCU grace period. -- cgit v1.2.3 From a5d8e467f83f6672104f276223a88e3b50cbd375 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 17 Apr 2010 08:48:38 -0400 Subject: Debugobjects transition check Implement a basic state machine checker in the debugobjects. This state machine checker detects races and inconsistencies within the "active" life of a debugobject. The checker only keeps track of the current state; all the state machine logic is kept at the object instance level. The checker works by adding a supplementary "unsigned int astate" field to the debug_obj structure. It keeps track of the current "active state" of the object. The only constraints that are imposed on the states by the debugobjects system is that: - activation of an object sets the current active state to 0, - deactivation of an object expects the current active state to be 0. For the rest of the states, the state mapping is determined by the specific object instance. Therefore, the logic keeping track of the state machine is within the specialized instance, without any need to know about it at the debugobject level. The current object active state is changed by calling: debug_object_active_state(addr, descr, expect, next) where "expect" is the expected state and "next" is the next state to move to if the expected state is found. A warning is generated if the expected is not found. Signed-off-by: Mathieu Desnoyers Reviewed-by: Thomas Gleixner Acked-by: David S. Miller CC: "Paul E. McKenney" CC: akpm@linux-foundation.org CC: mingo@elte.hu CC: laijs@cn.fujitsu.com CC: dipankar@in.ibm.com CC: josh@joshtriplett.org CC: dvhltc@us.ibm.com CC: niv@us.ibm.com CC: peterz@infradead.org CC: rostedt@goodmis.org CC: Valdis.Kletnieks@vt.edu CC: dhowells@redhat.com CC: eric.dumazet@gmail.com CC: Alexey Dobriyan Signed-off-by: Paul E. McKenney --- include/linux/debugobjects.h | 11 +++++++++ lib/debugobjects.c | 59 +++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 67 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 8c243aaa86a7..597692f1fc8d 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -20,12 +20,14 @@ struct debug_obj_descr; * struct debug_obj - representaion of an tracked object * @node: hlist node to link the object into the tracker list * @state: tracked object state + * @astate: current active state * @object: pointer to the real object * @descr: pointer to an object type specific debug description structure */ struct debug_obj { struct hlist_node node; enum debug_obj_state state; + unsigned int astate; void *object; struct debug_obj_descr *descr; }; @@ -60,6 +62,15 @@ extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr); extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr); extern void debug_object_free (void *addr, struct debug_obj_descr *descr); +/* + * Active state: + * - Set at 0 upon initialization. + * - Must return to 0 before deactivation. + */ +extern void +debug_object_active_state(void *addr, struct debug_obj_descr *descr, + unsigned int expect, unsigned int next); + extern void debug_objects_early_init(void); extern void debug_objects_mem_init(void); #else diff --git a/lib/debugobjects.c b/lib/debugobjects.c index b862b30369ff..076464fd2072 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -141,6 +141,7 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) obj->object = addr; obj->descr = descr; obj->state = ODEBUG_STATE_NONE; + obj->astate = 0; hlist_del(&obj->node); hlist_add_head(&obj->node, &b->list); @@ -252,8 +253,10 @@ static void debug_print_object(struct debug_obj *obj, char *msg) if (limit < 5 && obj->descr != descr_test) { limit++; - WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg, - obj_states[obj->state], obj->descr->name); + WARN(1, KERN_ERR "ODEBUG: %s %s (active state %u) " + "object type: %s\n", + msg, obj_states[obj->state], obj->astate, + obj->descr->name); } debug_objects_warnings++; } @@ -447,7 +450,10 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: case ODEBUG_STATE_ACTIVE: - obj->state = ODEBUG_STATE_INACTIVE; + if (!obj->astate) + obj->state = ODEBUG_STATE_INACTIVE; + else + debug_print_object(obj, "deactivate"); break; case ODEBUG_STATE_DESTROYED: @@ -553,6 +559,53 @@ out_unlock: raw_spin_unlock_irqrestore(&db->lock, flags); } +/** + * debug_object_active_state - debug checks object usage state machine + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + * @expect: expected state + * @next: state to move to if expected state is found + */ +void +debug_object_active_state(void *addr, struct debug_obj_descr *descr, + unsigned int expect, unsigned int next) +{ + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (obj) { + switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + if (obj->astate == expect) + obj->astate = next; + else + debug_print_object(obj, "active_state"); + break; + + default: + debug_print_object(obj, "active_state"); + break; + } + } else { + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; + + debug_print_object(&o, "active_state"); + } + + raw_spin_unlock_irqrestore(&db->lock, flags); +} + #ifdef CONFIG_DEBUG_OBJECTS_FREE static void __debug_check_no_obj_freed(const void *address, unsigned long size) { -- cgit v1.2.3 From 91af70814105f4c05e6e11b51c3269907b71794b Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Wed, 12 May 2010 11:38:45 +0100 Subject: rwsem: Test for no active locks in __rwsem_do_wake undo code If there are no active threasd using a semaphore, it is always correct to unqueue blocked threads. This seems to be what was intended in the undo code. What was done instead, was to look for a sem count of zero - this is an impossible situation, given that at least one thread is known to be queued on the semaphore. The code might be correct as written, but it's hard to reason about and it's not what was intended (otherwise the goto out would have been unconditional). Go for checking the active count - the alternative is not worth the headache. Signed-off-by: Michel Lespinasse Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- lib/rwsem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/rwsem.c b/lib/rwsem.c index 3e3365e5665e..ceba8e28807a 100644 --- a/lib/rwsem.c +++ b/lib/rwsem.c @@ -136,9 +136,10 @@ __rwsem_do_wake(struct rw_semaphore *sem, int downgrading) out: return sem; - /* undo the change to count, but check for a transition 1->0 */ + /* undo the change to the active count, but check for a transition + * 1->0 */ undo: - if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) != 0) + if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK) goto out; goto try_again; } -- cgit v1.2.3 From 43aa7ac736a4e21aae4882bd8f7c67403aed45b8 Mon Sep 17 00:00:00 2001 From: "kirjanov@gmail.com" Date: Sat, 15 May 2010 12:32:34 -0400 Subject: lib/btree: fix possible NULL pointer dereference mempool_alloc() can return null in atomic case. Signed-off-by: Denis Kirjanov Cc: Joern Engel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/btree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/btree.c b/lib/btree.c index 41859a820218..c9c6f0351526 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -95,7 +95,8 @@ static unsigned long *btree_node_alloc(struct btree_head *head, gfp_t gfp) unsigned long *node; node = mempool_alloc(head->mempool, gfp); - memset(node, 0, NODESIZE); + if (likely(node)) + memset(node, 0, NODESIZE); return node; } -- cgit v1.2.3