From f9ebcd9d410ba7209a8f321c41edf8615fc3ce67 Mon Sep 17 00:00:00 2001 From: Kumar Gala Date: Sun, 18 May 2008 13:18:01 -0500 Subject: lmb: Fix compile warning lib/lmb.c: In function 'lmb_dump_all': lib/lmb.c:51: warning: format '%lx' expects type 'long unsigned int', but argument 2 has type 'u64' Signed-off-by: Kumar Gala --- lib/lmb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/lmb.c b/lib/lmb.c index 867f7b5a823..5d7b9286503 100644 --- a/lib/lmb.c +++ b/lib/lmb.c @@ -48,7 +48,8 @@ void lmb_dump_all(void) } pr_info(" reserved.cnt = 0x%lx\n", lmb.reserved.cnt); - pr_info(" reserved.size = 0x%lx\n", lmb.reserved.size); + pr_info(" reserved.size = 0x%llx\n", + (unsigned long long)lmb.memory.size); for (i=0; i < lmb.reserved.cnt ;i++) { pr_info(" reserved.region[0x%lx].base = 0x%llx\n", i, (unsigned long long)lmb.reserved.region[i].base); -- cgit v1.2.3-70-g09d2 From 3527fb326f07bc8e85cf66d4f987ebeea24e8e4a Mon Sep 17 00:00:00 2001 From: Harvey Harrison Date: Thu, 5 Jun 2008 22:46:19 -0700 Subject: lib: export bitrev16 Bluetooth will be able to use this. Signed-off-by: Harvey Harrison Cc: Marcel Holtmann Cc: Dave Young Cc: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitrev.h | 1 + lib/bitrev.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'lib') diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index 05e540d6963..7ffe03f4693 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -10,6 +10,7 @@ static inline u8 bitrev8(u8 byte) return byte_rev_table[byte]; } +extern u16 bitrev16(u16 in); extern u32 bitrev32(u32 in); #endif /* _LINUX_BITREV_H */ diff --git a/lib/bitrev.c b/lib/bitrev.c index 989aff73f88..3956203456d 100644 --- a/lib/bitrev.c +++ b/lib/bitrev.c @@ -42,10 +42,11 @@ const u8 byte_rev_table[256] = { }; EXPORT_SYMBOL_GPL(byte_rev_table); -static __always_inline u16 bitrev16(u16 x) +u16 bitrev16(u16 x) { return (bitrev8(x & 0xff) << 8) | bitrev8(x >> 8); } +EXPORT_SYMBOL(bitrev16); /** * bitrev32 - reverse the order of bits in a u32 value -- cgit v1.2.3-70-g09d2 From f595ec964daf7f99668039d7303ddedd09a75142 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 12 Jun 2008 10:47:56 +0200 Subject: common implementation of iterative div/mod We have a few instances of the open-coded iterative div/mod loop, used when we don't expcet the dividend to be much bigger than the divisor. Unfortunately modern gcc's have the tendency to strength "reduce" this into a full mod operation, which isn't necessarily any faster, and even if it were, doesn't exist if gcc implements it in libgcc. The workaround is to put a dummy asm statement in the loop to prevent gcc from performing the transformation. This patch creates a single implementation of this loop, and uses it to replace the open-coded versions I know about. Signed-off-by: Jeremy Fitzhardinge Cc: Andrew Morton Cc: john stultz Cc: Segher Boessenkool Cc: Christian Kujau Cc: Robert Hancock Signed-off-by: Ingo Molnar --- arch/x86/xen/time.c | 13 +++---------- include/linux/math64.h | 2 ++ include/linux/time.h | 11 ++--------- lib/div64.c | 23 +++++++++++++++++++++++ 4 files changed, 30 insertions(+), 19 deletions(-) (limited to 'lib') diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index c39e1a5aa24..52b2e385698 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -150,11 +151,7 @@ static void do_stolen_accounting(void) if (stolen < 0) stolen = 0; - ticks = 0; - while (stolen >= NS_PER_TICK) { - ticks++; - stolen -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __get_cpu_var(residual_stolen) = stolen; account_steal_time(NULL, ticks); @@ -166,11 +163,7 @@ static void do_stolen_accounting(void) if (blocked < 0) blocked = 0; - ticks = 0; - while (blocked >= NS_PER_TICK) { - ticks++; - blocked -= NS_PER_TICK; - } + ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); __get_cpu_var(residual_blocked) = blocked; account_steal_time(idle_task(smp_processor_id()), ticks); } diff --git a/include/linux/math64.h b/include/linux/math64.h index c1a5f81501f..177785e1e4a 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -81,4 +81,6 @@ static inline s64 div_s64(s64 dividend, s32 divisor) } #endif +u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); + #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/time.h b/include/linux/time.h index d32ef0ad4c0..05f9517a8ed 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -6,6 +6,7 @@ #ifdef __KERNEL__ # include # include +# include #endif #ifndef _STRUCT_TIMESPEC @@ -172,15 +173,7 @@ extern struct timeval ns_to_timeval(const s64 nsec); */ static inline void timespec_add_ns(struct timespec *a, u64 ns) { - ns += a->tv_nsec; - while(unlikely(ns >= NSEC_PER_SEC)) { - /* The following asm() prevents the compiler from - * optimising this loop into a modulo operation. */ - asm("" : "+r"(ns)); - - ns -= NSEC_PER_SEC; - a->tv_sec++; - } + a->tv_sec += iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } #endif /* __KERNEL__ */ diff --git a/lib/div64.c b/lib/div64.c index bb5bd0c0f03..76c01542d3e 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -98,3 +98,26 @@ EXPORT_SYMBOL(div64_u64); #endif #endif /* BITS_PER_LONG == 32 */ + +/* + * Iterative div/mod for use when dividend is not expected to be much + * bigger than divisor. + */ +u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{ + u32 ret = 0; + + while (dividend >= divisor) { + /* The following asm() prevents the compiler from + optimising this loop into a modulo operation. */ + asm("" : "+rm"(dividend)); + + dividend -= divisor; + ret++; + } + + *remainder = dividend; + + return ret; +} +EXPORT_SYMBOL(iter_div_u64_rem); -- cgit v1.2.3-70-g09d2 From d5e181f78ac753893eb930868a52a4488cd3de0a Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 12 Jun 2008 10:47:58 +0200 Subject: add an inlined version of iter_div_u64_rem iter_div_u64_rem is used in the x86-64 vdso, which cannot call other kernel code. For this case, provide the always_inlined version, __iter_div_u64_rem. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- include/linux/math64.h | 19 +++++++++++++++++++ lib/div64.c | 15 +-------------- 2 files changed, 20 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/include/linux/math64.h b/include/linux/math64.h index 177785e1e4a..c87f1528703 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -83,4 +83,23 @@ static inline s64 div_s64(s64 dividend, s32 divisor) u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder); +static __always_inline u32 +__iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{ + u32 ret = 0; + + while (dividend >= divisor) { + /* The following asm() prevents the compiler from + optimising this loop into a modulo operation. */ + asm("" : "+rm"(dividend)); + + dividend -= divisor; + ret++; + } + + *remainder = dividend; + + return ret; +} + #endif /* _LINUX_MATH64_H */ diff --git a/lib/div64.c b/lib/div64.c index 76c01542d3e..a111eb8de9c 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -105,19 +105,6 @@ EXPORT_SYMBOL(div64_u64); */ u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) { - u32 ret = 0; - - while (dividend >= divisor) { - /* The following asm() prevents the compiler from - optimising this loop into a modulo operation. */ - asm("" : "+rm"(dividend)); - - dividend -= divisor; - ret++; - } - - *remainder = dividend; - - return ret; + return __iter_div_u64_rem(dividend, divisor, remainder); } EXPORT_SYMBOL(iter_div_u64_rem); -- cgit v1.2.3-70-g09d2 From 643b52b9c0b4e959436b4b551ebf4060d06d5ae8 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 12 Jun 2008 15:21:52 -0700 Subject: radix-tree: fix small lockless radix-tree bug We shrink a radix tree when its root node has only one child, in the left most slot. The child becomes the new root node. To perform this operation in a manner compatible with concurrent lockless lookups, we atomically switch the root pointer from the parent to its child. However a concurrent lockless lookup may now have loaded a pointer to the parent (and is presently deciding what to do next). For this reason, we also have to keep the parent node in a valid state after shrinking the tree, until the next RCU grace period -- otherwise this lookup with the parent pointer may not do the right thing. Notably, we need to keep the child in the left most slot there in case that is requested by the lookup. This is all pretty standard RCU stuff. It is worth repeating because in my eagerness to obey the radix tree node constructor scheme, I had broken it by zeroing the radix tree node before the grace period. What could happen is that a lookup can load the parent pointer, then decide it wants to follow the left most child slot, only to find the slot contained NULL due to the concurrent shrinker having zeroed the parent node before waiting for a grace period. The lookup would return a false negative as a result. Fix it by doing that clearing in the RCU callback. I would normally want to rip out the constructor entirely, but radix tree nodes are one of those places where they make sense (only few cachelines will be touched soon after allocation). This was never actually found in any lockless pagecache testing or by the test harness, but by seeing the odd problem with my scalable vmap rewrite. I have not tickled the test harness into reproducing it yet, but I'll keep working at it. Fortunately, it is not a problem anywhere lockless pagecache is used in mainline kernels (pagecache probe is not a guarantee, and brd does not have concurrent lookups and deletes). Signed-off-by: Nick Piggin Acked-by: Peter Zijlstra Cc: "Paul E. McKenney" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/radix-tree.c | 120 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 62 insertions(+), 58 deletions(-) (limited to 'lib') diff --git a/lib/radix-tree.c b/lib/radix-tree.c index bd521716ab1..169a2f8dabc 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -88,6 +88,57 @@ static inline gfp_t root_gfp_mask(struct radix_tree_root *root) return root->gfp_mask & __GFP_BITS_MASK; } +static inline void tag_set(struct radix_tree_node *node, unsigned int tag, + int offset) +{ + __set_bit(offset, node->tags[tag]); +} + +static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, + int offset) +{ + __clear_bit(offset, node->tags[tag]); +} + +static inline int tag_get(struct radix_tree_node *node, unsigned int tag, + int offset) +{ + return test_bit(offset, node->tags[tag]); +} + +static inline void root_tag_set(struct radix_tree_root *root, unsigned int tag) +{ + root->gfp_mask |= (__force gfp_t)(1 << (tag + __GFP_BITS_SHIFT)); +} + +static inline void root_tag_clear(struct radix_tree_root *root, unsigned int tag) +{ + root->gfp_mask &= (__force gfp_t)~(1 << (tag + __GFP_BITS_SHIFT)); +} + +static inline void root_tag_clear_all(struct radix_tree_root *root) +{ + root->gfp_mask &= __GFP_BITS_MASK; +} + +static inline int root_tag_get(struct radix_tree_root *root, unsigned int tag) +{ + return (__force unsigned)root->gfp_mask & (1 << (tag + __GFP_BITS_SHIFT)); +} + +/* + * Returns 1 if any slot in the node has this tag set. + * Otherwise returns 0. + */ +static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag) +{ + int idx; + for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { + if (node->tags[tag][idx]) + return 1; + } + return 0; +} /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. @@ -124,6 +175,17 @@ static void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); + + /* + * must only free zeroed nodes into the slab. radix_tree_shrink + * can leave us with a non-NULL entry in the first slot, so clear + * that here to make sure. + */ + tag_clear(node, 0, 0); + tag_clear(node, 1, 0); + node->slots[0] = NULL; + node->count = 0; + kmem_cache_free(radix_tree_node_cachep, node); } @@ -165,59 +227,6 @@ out: } EXPORT_SYMBOL(radix_tree_preload); -static inline void tag_set(struct radix_tree_node *node, unsigned int tag, - int offset) -{ - __set_bit(offset, node->tags[tag]); -} - -static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, - int offset) -{ - __clear_bit(offset, node->tags[tag]); -} - -static inline int tag_get(struct radix_tree_node *node, unsigned int tag, - int offset) -{ - return test_bit(offset, node->tags[tag]); -} - -static inline void root_tag_set(struct radix_tree_root *root, unsigned int tag) -{ - root->gfp_mask |= (__force gfp_t)(1 << (tag + __GFP_BITS_SHIFT)); -} - - -static inline void root_tag_clear(struct radix_tree_root *root, unsigned int tag) -{ - root->gfp_mask &= (__force gfp_t)~(1 << (tag + __GFP_BITS_SHIFT)); -} - -static inline void root_tag_clear_all(struct radix_tree_root *root) -{ - root->gfp_mask &= __GFP_BITS_MASK; -} - -static inline int root_tag_get(struct radix_tree_root *root, unsigned int tag) -{ - return (__force unsigned)root->gfp_mask & (1 << (tag + __GFP_BITS_SHIFT)); -} - -/* - * Returns 1 if any slot in the node has this tag set. - * Otherwise returns 0. - */ -static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag) -{ - int idx; - for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { - if (node->tags[tag][idx]) - return 1; - } - return 0; -} - /* * Return the maximum key which can be store into a * radix tree with height HEIGHT. @@ -930,11 +939,6 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) newptr = radix_tree_ptr_to_indirect(newptr); root->rnode = newptr; root->height--; - /* must only free zeroed nodes into the slab */ - tag_clear(to_free, 0, 0); - tag_clear(to_free, 1, 0); - to_free->slots[0] = NULL; - to_free->count = 0; radix_tree_node_free(to_free); } } -- cgit v1.2.3-70-g09d2