linux/arch/x86/include/asm/atomic.h

272 lines
5.9 KiB
C
Raw Normal View History

#ifndef _ASM_X86_ATOMIC_H
#define _ASM_X86_ATOMIC_H
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/alternative.h>
#include <asm/cmpxchg.h>
#include <asm/rmwcc.h>
#include <asm/barrier.h>
/*
* Atomic operations that C can't guarantee us. Useful for
* resource counting etc..
*/
#define ATOMIC_INIT(i) { (i) }
/**
* atomic_read - read atomic variable
* @v: pointer of type atomic_t
*
* Atomically reads the value of @v.
*/
x86: Force inlining of atomic ops With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined: $ nm --size-sort vmlinux | grep -iF ' t ' | uniq -c | grep -v '^ *1 ' | sort -rn 473 000000000000000b t spin_unlock_irqrestore 449 000000000000005f t rcu_read_unlock 355 0000000000000009 t atomic_inc <== THIS 353 000000000000006e t rcu_read_lock 350 0000000000000075 t rcu_read_lock_sched_held 291 000000000000000b t spin_unlock 266 0000000000000019 t arch_local_irq_restore 215 000000000000000b t spin_lock 180 0000000000000011 t kzalloc 165 0000000000000012 t list_add_tail 161 0000000000000019 t arch_local_save_flags 153 0000000000000016 t test_and_set_bit 134 000000000000000b t spin_unlock_irq 134 0000000000000009 t atomic_dec <== THIS 130 000000000000000b t spin_unlock_bh 122 0000000000000010 t brelse 120 0000000000000016 t test_and_clear_bit 120 000000000000000b t spin_lock_irq 119 000000000000001e t get_dma_ops 117 0000000000000053 t cpumask_next 116 0000000000000036 t kref_get 114 000000000000001a t schedule_work 106 000000000000000b t spin_lock_bh 103 0000000000000019 t arch_local_irq_disable ... Note sizes of marked functions. They are merely 9 bytes long! Selecting function with 'atomic' in their names: 355 0000000000000009 t atomic_inc 134 0000000000000009 t atomic_dec 98 0000000000000014 t atomic_dec_and_test 31 000000000000000e t atomic_add_return 27 000000000000000a t atomic64_inc 26 000000000000002f t kmap_atomic 24 0000000000000009 t atomic_add 12 0000000000000009 t atomic_sub 10 0000000000000021 t __atomic_add_unless 10 000000000000000a t atomic64_add 5 000000000000001f t __atomic_add_unless.constprop.7 5 000000000000000a t atomic64_dec 4 000000000000001f t __atomic_add_unless.constprop.18 4 000000000000001f t __atomic_add_unless.constprop.12 4 000000000000001f t __atomic_add_unless.constprop.10 3 000000000000001f t __atomic_add_unless.constprop.13 3 0000000000000011 t atomic64_add_return 2 000000000000001f t __atomic_add_unless.constprop.9 2 000000000000001f t __atomic_add_unless.constprop.8 2 000000000000001f t __atomic_add_unless.constprop.6 2 000000000000001f t __atomic_add_unless.constprop.5 2 000000000000001f t __atomic_add_unless.constprop.3 2 000000000000001f t __atomic_add_unless.constprop.22 2 000000000000001f t __atomic_add_unless.constprop.14 2 000000000000001f t __atomic_add_unless.constprop.11 2 000000000000001e t atomic_dec_if_positive 2 0000000000000014 t atomic_inc_and_test 2 0000000000000011 t atomic_add_return.constprop.4 2 0000000000000011 t atomic_add_return.constprop.17 2 0000000000000011 t atomic_add_return.constprop.16 2 000000000000000d t atomic_inc.constprop.4 2 000000000000000c t atomic_cmpxchg This patch fixes this for x86 atomic ops via s/inline/__always_inline/. This decreases allyesconfig kernel by about 25k: text data bss dec hex filename 82399481 22255416 20627456 125282353 777a831 vmlinux.before 82375570 22255544 20627456 125258570 7774b4a vmlinux Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Drewry <wad@chromium.org> Link: http://lkml.kernel.org/r/1431080762-17797-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-08 10:26:02 +00:00
static __always_inline int atomic_read(const atomic_t *v)
{
return READ_ONCE((v)->counter);
}
/**
* atomic_set - set atomic variable
* @v: pointer of type atomic_t
* @i: required value
*
* Atomically sets the value of @v to @i.
*/
x86: Force inlining of atomic ops With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined: $ nm --size-sort vmlinux | grep -iF ' t ' | uniq -c | grep -v '^ *1 ' | sort -rn 473 000000000000000b t spin_unlock_irqrestore 449 000000000000005f t rcu_read_unlock 355 0000000000000009 t atomic_inc <== THIS 353 000000000000006e t rcu_read_lock 350 0000000000000075 t rcu_read_lock_sched_held 291 000000000000000b t spin_unlock 266 0000000000000019 t arch_local_irq_restore 215 000000000000000b t spin_lock 180 0000000000000011 t kzalloc 165 0000000000000012 t list_add_tail 161 0000000000000019 t arch_local_save_flags 153 0000000000000016 t test_and_set_bit 134 000000000000000b t spin_unlock_irq 134 0000000000000009 t atomic_dec <== THIS 130 000000000000000b t spin_unlock_bh 122 0000000000000010 t brelse 120 0000000000000016 t test_and_clear_bit 120 000000000000000b t spin_lock_irq 119 000000000000001e t get_dma_ops 117 0000000000000053 t cpumask_next 116 0000000000000036 t kref_get 114 000000000000001a t schedule_work 106 000000000000000b t spin_lock_bh 103 0000000000000019 t arch_local_irq_disable ... Note sizes of marked functions. They are merely 9 bytes long! Selecting function with 'atomic' in their names: 355 0000000000000009 t atomic_inc 134 0000000000000009 t atomic_dec 98 0000000000000014 t atomic_dec_and_test 31 000000000000000e t atomic_add_return 27 000000000000000a t atomic64_inc 26 000000000000002f t kmap_atomic 24 0000000000000009 t atomic_add 12 0000000000000009 t atomic_sub 10 0000000000000021 t __atomic_add_unless 10 000000000000000a t atomic64_add 5 000000000000001f t __atomic_add_unless.constprop.7 5 000000000000000a t atomic64_dec 4 000000000000001f t __atomic_add_unless.constprop.18 4 000000000000001f t __atomic_add_unless.constprop.12 4 000000000000001f t __atomic_add_unless.constprop.10 3 000000000000001f t __atomic_add_unless.constprop.13 3 0000000000000011 t atomic64_add_return 2 000000000000001f t __atomic_add_unless.constprop.9 2 000000000000001f t __atomic_add_unless.constprop.8 2 000000000000001f t __atomic_add_unless.constprop.6 2 000000000000001f t __atomic_add_unless.constprop.5 2 000000000000001f t __atomic_add_unless.constprop.3 2 000000000000001f t __atomic_add_unless.constprop.22 2 000000000000001f t __atomic_add_unless.constprop.14 2 000000000000001f t __atomic_add_unless.constprop.11 2 000000000000001e t atomic_dec_if_positive 2 0000000000000014 t atomic_inc_and_test 2 0000000000000011 t atomic_add_return.constprop.4 2 0000000000000011 t atomic_add_return.constprop.17 2 0000000000000011 t atomic_add_return.constprop.16 2 000000000000000d t atomic_inc.constprop.4 2 000000000000000c t atomic_cmpxchg This patch fixes this for x86 atomic ops via s/inline/__always_inline/. This decreases allyesconfig kernel by about 25k: text data bss dec hex filename 82399481 22255416 20627456 125282353 777a831 vmlinux.before 82375570 22255544 20627456 125258570 7774b4a vmlinux Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Drewry <wad@chromium.org> Link: http://lkml.kernel.org/r/1431080762-17797-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-08 10:26:02 +00:00
static __always_inline void atomic_set(atomic_t *v, int i)
{
WRITE_ONCE(v->counter, i);
}
/**
* atomic_add - add integer to atomic variable
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-20 21:27:11 +00:00
static __always_inline void atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
: "ir" (i));
}
/**
* atomic_sub - subtract integer from atomic variable
* @i: integer value to subtract
* @v: pointer of type atomic_t
*
* Atomically subtracts @i from @v.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-20 21:27:11 +00:00
static __always_inline void atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
: "ir" (i));
}
/**
* atomic_sub_and_test - subtract value from variable and test result
* @i: integer value to subtract
* @v: pointer of type atomic_t
*
* Atomically subtracts @i from @v and returns
* true if the result is zero, or false for all
* other cases.
*/
static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
}
/**
* atomic_inc - increment atomic variable
* @v: pointer of type atomic_t
*
* Atomically increments @v by 1.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-20 21:27:11 +00:00
static __always_inline void atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
: "+m" (v->counter));
}
/**
* atomic_dec - decrement atomic variable
* @v: pointer of type atomic_t
*
* Atomically decrements @v by 1.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-20 21:27:11 +00:00
static __always_inline void atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
: "+m" (v->counter));
}
/**
* atomic_dec_and_test - decrement and test
* @v: pointer of type atomic_t
*
* Atomically decrements @v by 1 and
* returns true if the result is 0, or false for all other
* cases.
*/
static __always_inline bool atomic_dec_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
}
/**
* atomic_inc_and_test - increment and test
* @v: pointer of type atomic_t
*
* Atomically increments @v by 1
* and returns true if the result is zero, or false for all
* other cases.
*/
static __always_inline bool atomic_inc_and_test(atomic_t *v)
{
GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
}
/**
* atomic_add_negative - add and test if negative
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v and returns true
* if the result is negative, or false when
* result is greater than or equal to zero.
*/
static __always_inline bool atomic_add_negative(int i, atomic_t *v)
{
GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
}
/**
* atomic_add_return - add integer and return
* @i: integer value to add
* @v: pointer of type atomic_t
*
* Atomically adds @i to @v and returns @i + @v
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-20 21:27:11 +00:00
static __always_inline int atomic_add_return(int i, atomic_t *v)
{
return i + xadd(&v->counter, i);
}
/**
* atomic_sub_return - subtract integer and return
* @v: pointer of type atomic_t
* @i: integer value to subtract
*
* Atomically subtracts @i from @v and returns @v - @i
*/
x86: Force inlining of atomic ops With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined: $ nm --size-sort vmlinux | grep -iF ' t ' | uniq -c | grep -v '^ *1 ' | sort -rn 473 000000000000000b t spin_unlock_irqrestore 449 000000000000005f t rcu_read_unlock 355 0000000000000009 t atomic_inc <== THIS 353 000000000000006e t rcu_read_lock 350 0000000000000075 t rcu_read_lock_sched_held 291 000000000000000b t spin_unlock 266 0000000000000019 t arch_local_irq_restore 215 000000000000000b t spin_lock 180 0000000000000011 t kzalloc 165 0000000000000012 t list_add_tail 161 0000000000000019 t arch_local_save_flags 153 0000000000000016 t test_and_set_bit 134 000000000000000b t spin_unlock_irq 134 0000000000000009 t atomic_dec <== THIS 130 000000000000000b t spin_unlock_bh 122 0000000000000010 t brelse 120 0000000000000016 t test_and_clear_bit 120 000000000000000b t spin_lock_irq 119 000000000000001e t get_dma_ops 117 0000000000000053 t cpumask_next 116 0000000000000036 t kref_get 114 000000000000001a t schedule_work 106 000000000000000b t spin_lock_bh 103 0000000000000019 t arch_local_irq_disable ... Note sizes of marked functions. They are merely 9 bytes long! Selecting function with 'atomic' in their names: 355 0000000000000009 t atomic_inc 134 0000000000000009 t atomic_dec 98 0000000000000014 t atomic_dec_and_test 31 000000000000000e t atomic_add_return 27 000000000000000a t atomic64_inc 26 000000000000002f t kmap_atomic 24 0000000000000009 t atomic_add 12 0000000000000009 t atomic_sub 10 0000000000000021 t __atomic_add_unless 10 000000000000000a t atomic64_add 5 000000000000001f t __atomic_add_unless.constprop.7 5 000000000000000a t atomic64_dec 4 000000000000001f t __atomic_add_unless.constprop.18 4 000000000000001f t __atomic_add_unless.constprop.12 4 000000000000001f t __atomic_add_unless.constprop.10 3 000000000000001f t __atomic_add_unless.constprop.13 3 0000000000000011 t atomic64_add_return 2 000000000000001f t __atomic_add_unless.constprop.9 2 000000000000001f t __atomic_add_unless.constprop.8 2 000000000000001f t __atomic_add_unless.constprop.6 2 000000000000001f t __atomic_add_unless.constprop.5 2 000000000000001f t __atomic_add_unless.constprop.3 2 000000000000001f t __atomic_add_unless.constprop.22 2 000000000000001f t __atomic_add_unless.constprop.14 2 000000000000001f t __atomic_add_unless.constprop.11 2 000000000000001e t atomic_dec_if_positive 2 0000000000000014 t atomic_inc_and_test 2 0000000000000011 t atomic_add_return.constprop.4 2 0000000000000011 t atomic_add_return.constprop.17 2 0000000000000011 t atomic_add_return.constprop.16 2 000000000000000d t atomic_inc.constprop.4 2 000000000000000c t atomic_cmpxchg This patch fixes this for x86 atomic ops via s/inline/__always_inline/. This decreases allyesconfig kernel by about 25k: text data bss dec hex filename 82399481 22255416 20627456 125282353 777a831 vmlinux.before 82375570 22255544 20627456 125258570 7774b4a vmlinux Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Drewry <wad@chromium.org> Link: http://lkml.kernel.org/r/1431080762-17797-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-08 10:26:02 +00:00
static __always_inline int atomic_sub_return(int i, atomic_t *v)
{
return atomic_add_return(-i, v);
}
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))
static __always_inline int atomic_fetch_add(int i, atomic_t *v)
{
return xadd(&v->counter, i);
}
static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
{
return xadd(&v->counter, -i);
}
x86: Force inlining of atomic ops With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined: $ nm --size-sort vmlinux | grep -iF ' t ' | uniq -c | grep -v '^ *1 ' | sort -rn 473 000000000000000b t spin_unlock_irqrestore 449 000000000000005f t rcu_read_unlock 355 0000000000000009 t atomic_inc <== THIS 353 000000000000006e t rcu_read_lock 350 0000000000000075 t rcu_read_lock_sched_held 291 000000000000000b t spin_unlock 266 0000000000000019 t arch_local_irq_restore 215 000000000000000b t spin_lock 180 0000000000000011 t kzalloc 165 0000000000000012 t list_add_tail 161 0000000000000019 t arch_local_save_flags 153 0000000000000016 t test_and_set_bit 134 000000000000000b t spin_unlock_irq 134 0000000000000009 t atomic_dec <== THIS 130 000000000000000b t spin_unlock_bh 122 0000000000000010 t brelse 120 0000000000000016 t test_and_clear_bit 120 000000000000000b t spin_lock_irq 119 000000000000001e t get_dma_ops 117 0000000000000053 t cpumask_next 116 0000000000000036 t kref_get 114 000000000000001a t schedule_work 106 000000000000000b t spin_lock_bh 103 0000000000000019 t arch_local_irq_disable ... Note sizes of marked functions. They are merely 9 bytes long! Selecting function with 'atomic' in their names: 355 0000000000000009 t atomic_inc 134 0000000000000009 t atomic_dec 98 0000000000000014 t atomic_dec_and_test 31 000000000000000e t atomic_add_return 27 000000000000000a t atomic64_inc 26 000000000000002f t kmap_atomic 24 0000000000000009 t atomic_add 12 0000000000000009 t atomic_sub 10 0000000000000021 t __atomic_add_unless 10 000000000000000a t atomic64_add 5 000000000000001f t __atomic_add_unless.constprop.7 5 000000000000000a t atomic64_dec 4 000000000000001f t __atomic_add_unless.constprop.18 4 000000000000001f t __atomic_add_unless.constprop.12 4 000000000000001f t __atomic_add_unless.constprop.10 3 000000000000001f t __atomic_add_unless.constprop.13 3 0000000000000011 t atomic64_add_return 2 000000000000001f t __atomic_add_unless.constprop.9 2 000000000000001f t __atomic_add_unless.constprop.8 2 000000000000001f t __atomic_add_unless.constprop.6 2 000000000000001f t __atomic_add_unless.constprop.5 2 000000000000001f t __atomic_add_unless.constprop.3 2 000000000000001f t __atomic_add_unless.constprop.22 2 000000000000001f t __atomic_add_unless.constprop.14 2 000000000000001f t __atomic_add_unless.constprop.11 2 000000000000001e t atomic_dec_if_positive 2 0000000000000014 t atomic_inc_and_test 2 0000000000000011 t atomic_add_return.constprop.4 2 0000000000000011 t atomic_add_return.constprop.17 2 0000000000000011 t atomic_add_return.constprop.16 2 000000000000000d t atomic_inc.constprop.4 2 000000000000000c t atomic_cmpxchg This patch fixes this for x86 atomic ops via s/inline/__always_inline/. This decreases allyesconfig kernel by about 25k: text data bss dec hex filename 82399481 22255416 20627456 125282353 777a831 vmlinux.before 82375570 22255544 20627456 125258570 7774b4a vmlinux Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Drewry <wad@chromium.org> Link: http://lkml.kernel.org/r/1431080762-17797-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-08 10:26:02 +00:00
static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
{
return cmpxchg(&v->counter, old, new);
}
static inline int atomic_xchg(atomic_t *v, int new)
{
return xchg(&v->counter, new);
}
#define ATOMIC_OP(op) \
static inline void atomic_##op(int i, atomic_t *v) \
{ \
asm volatile(LOCK_PREFIX #op"l %1,%0" \
: "+m" (v->counter) \
: "ir" (i) \
: "memory"); \
}
#define ATOMIC_FETCH_OP(op, c_op) \
static inline int atomic_fetch_##op(int i, atomic_t *v) \
{ \
int old, val = atomic_read(v); \
for (;;) { \
old = atomic_cmpxchg(v, val, val c_op i); \
if (old == val) \
break; \
val = old; \
} \
return old; \
}
#define ATOMIC_OPS(op, c_op) \
ATOMIC_OP(op) \
ATOMIC_FETCH_OP(op, c_op)
ATOMIC_OPS(and, &)
ATOMIC_OPS(or , |)
ATOMIC_OPS(xor, ^)
#undef ATOMIC_OPS
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP
/**
* __atomic_add_unless - add unless the number is already a given value
* @v: pointer of type atomic_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
*
* Atomically adds @a to @v, so long as @v was not already @u.
* Returns the old value of @v.
*/
x86/asm: Always inline atomics During some code analysis I realized that atomic_add(), atomic_sub() and friends are not necessarily inlined AND that each function is defined multiple times: atomic_inc: 544 duplicates atomic_dec: 215 duplicates atomic_dec_and_test: 107 duplicates atomic64_inc: 38 duplicates [...] Each definition is exact equally, e.g.: ffffffff813171b8 <atomic_add>: 55 push %rbp 48 89 e5 mov %rsp,%rbp f0 01 3e lock add %edi,(%rsi) 5d pop %rbp c3 retq In turn each definition has one or more callsites (sure): ffffffff81317c78: e8 3b f5 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a062: e8 51 d1 ff ff callq ffffffff813171b8 <atomic_add> [...] ffffffff8131a190: e8 23 d0 ff ff callq ffffffff813171b8 <atomic_add> [...] The other way around would be to remove the static linkage - but I prefer an enforced inlining here. Before: text data bss dec hex filename 81467393 19874720 20168704 121510817 73e1ba1 vmlinux.orig After: text data bss dec hex filename 81461323 19874720 20168704 121504747 73e03eb vmlinux.inlined Yes, the inlining here makes the kernel even smaller! ;) Linus further observed: "I have this memory of having seen that before - the size heuristics for gcc getting confused by inlining. [...] It might be a good idea to mark things that are basically just wrappers around a single (or a couple of) asm instruction to be always_inline." Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Borislav Petkov <bp@alien8.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1429565231-4609-1-git-send-email-hagen@jauu.net Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-20 21:27:11 +00:00
static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
{
int c, old;
c = atomic_read(v);
for (;;) {
if (unlikely(c == (u)))
break;
old = atomic_cmpxchg((v), c, c + (a));
if (likely(old == c))
break;
c = old;
}
return c;
}
/**
* atomic_inc_short - increment of a short integer
* @v: pointer to type int
*
* Atomically adds 1 to @v
* Returns the new value of @u
*/
x86: Force inlining of atomic ops With both gcc 4.7.2 and 4.9.2, sometimes gcc mysteriously doesn't inline very small functions we expect to be inlined: $ nm --size-sort vmlinux | grep -iF ' t ' | uniq -c | grep -v '^ *1 ' | sort -rn 473 000000000000000b t spin_unlock_irqrestore 449 000000000000005f t rcu_read_unlock 355 0000000000000009 t atomic_inc <== THIS 353 000000000000006e t rcu_read_lock 350 0000000000000075 t rcu_read_lock_sched_held 291 000000000000000b t spin_unlock 266 0000000000000019 t arch_local_irq_restore 215 000000000000000b t spin_lock 180 0000000000000011 t kzalloc 165 0000000000000012 t list_add_tail 161 0000000000000019 t arch_local_save_flags 153 0000000000000016 t test_and_set_bit 134 000000000000000b t spin_unlock_irq 134 0000000000000009 t atomic_dec <== THIS 130 000000000000000b t spin_unlock_bh 122 0000000000000010 t brelse 120 0000000000000016 t test_and_clear_bit 120 000000000000000b t spin_lock_irq 119 000000000000001e t get_dma_ops 117 0000000000000053 t cpumask_next 116 0000000000000036 t kref_get 114 000000000000001a t schedule_work 106 000000000000000b t spin_lock_bh 103 0000000000000019 t arch_local_irq_disable ... Note sizes of marked functions. They are merely 9 bytes long! Selecting function with 'atomic' in their names: 355 0000000000000009 t atomic_inc 134 0000000000000009 t atomic_dec 98 0000000000000014 t atomic_dec_and_test 31 000000000000000e t atomic_add_return 27 000000000000000a t atomic64_inc 26 000000000000002f t kmap_atomic 24 0000000000000009 t atomic_add 12 0000000000000009 t atomic_sub 10 0000000000000021 t __atomic_add_unless 10 000000000000000a t atomic64_add 5 000000000000001f t __atomic_add_unless.constprop.7 5 000000000000000a t atomic64_dec 4 000000000000001f t __atomic_add_unless.constprop.18 4 000000000000001f t __atomic_add_unless.constprop.12 4 000000000000001f t __atomic_add_unless.constprop.10 3 000000000000001f t __atomic_add_unless.constprop.13 3 0000000000000011 t atomic64_add_return 2 000000000000001f t __atomic_add_unless.constprop.9 2 000000000000001f t __atomic_add_unless.constprop.8 2 000000000000001f t __atomic_add_unless.constprop.6 2 000000000000001f t __atomic_add_unless.constprop.5 2 000000000000001f t __atomic_add_unless.constprop.3 2 000000000000001f t __atomic_add_unless.constprop.22 2 000000000000001f t __atomic_add_unless.constprop.14 2 000000000000001f t __atomic_add_unless.constprop.11 2 000000000000001e t atomic_dec_if_positive 2 0000000000000014 t atomic_inc_and_test 2 0000000000000011 t atomic_add_return.constprop.4 2 0000000000000011 t atomic_add_return.constprop.17 2 0000000000000011 t atomic_add_return.constprop.16 2 000000000000000d t atomic_inc.constprop.4 2 000000000000000c t atomic_cmpxchg This patch fixes this for x86 atomic ops via s/inline/__always_inline/. This decreases allyesconfig kernel by about 25k: text data bss dec hex filename 82399481 22255416 20627456 125282353 777a831 vmlinux.before 82375570 22255544 20627456 125258570 7774b4a vmlinux Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> Cc: Alexei Starovoitov <ast@plumgrid.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Drewry <wad@chromium.org> Link: http://lkml.kernel.org/r/1431080762-17797-1-git-send-email-dvlasenk@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-08 10:26:02 +00:00
static __always_inline short int atomic_inc_short(short int *v)
{
asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
return *v;
}
#ifdef CONFIG_X86_32
# include <asm/atomic64_32.h>
#else
# include <asm/atomic64_64.h>
#endif
#endif /* _ASM_X86_ATOMIC_H */