| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sun, 30 Oct 2011 16:16:05 +0100
From: Eric Dumazet <eric.dumazet@...il.com>
To: Andi Kleen <andi@...stfloor.org>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Ben Hutchings <bhutchings@...arflare.com>,
linux-kernel <linux-kernel@...r.kernel.org>,
netdev <netdev@...r.kernel.org>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: >Re: [RFC] should VM_BUG_ON(cond) really evaluate cond
Le dimanche 30 octobre 2011 à 10:59 +0100, Andi Kleen a écrit :
> > +#define ACCESS_AT_MOST_ONCE(x) \
> > + ({ unsigned long __y; \
>
> why not typeof here?
>
> > + asm("":"=r" (__y):"0" (x)); \
> > + (__force __typeof__(x)) __y; \
> > + })
> > +
>
> -Andi
Because it doesnt work if x is const.
/data/src/linux/arch/x86/include/asm/atomic.h: In function
‘atomic_read’:
/data/src/linux/arch/x86/include/asm/atomic.h:25:2: erreur: read-only
variable ‘__y’ used as ‘asm’ output
I understand it wont work for u64 type on 32bit arches, but is
ACCESS_AT_MOST_ONCE() sensible for this kind of usage ?
In this V2, I added a check on sizeof(x) to trigger a compile error.
BTW, I forgot the atomic64_read() possible use of ACCESS_AT_MOST_ONCE()
in arch/x86/include/asm/atomic64_64.h, this saves 600 bytes more :)
On 32bit, I am afraid we cannot change current behavior, because of the
ATOMIC64_ALTERNATIVE() use.
Thanks !
[PATCH] atomic: introduce ACCESS_AT_MOST_ONCE() helper
In commit 4e60c86bd9e (gcc-4.6: mm: fix unused but set warnings)
Andi forced VM_BUG_ON(cond) to evaluate cond, even if CONFIG_DEBUG_VM is
not set :
#ifdef CONFIG_DEBUG_VM
#define VM_BUG_ON(cond) BUG_ON(cond)
#else
#define VM_BUG_ON(cond) do { (void)(cond); } while (0)
#endif
As a side effect, get_page()/put_page_testzero() are performing more bus
transactions on contended cache line on some workloads (tcp_sendmsg()
for example, where a page is acting as a shared buffer)
0,05 : ffffffff815e4775: je ffffffff815e4970 <tcp_sendmsg+0xc80>
0,05 : ffffffff815e477b: mov 0x1c(%r9),%eax // useless
3,32 : ffffffff815e477f: mov (%r9),%rax // useless
0,51 : ffffffff815e4782: lock incl 0x1c(%r9)
3,87 : ffffffff815e4787: mov (%r9),%rax
0,00 : ffffffff815e478a: test $0x80,%ah
0,00 : ffffffff815e478d: jne ffffffff815e49f2 <tcp_sendmsg+0xd02>
Thats because both atomic_read() and constant_test_bit() use a volatile
attribute and thus compiler is forced to perform a read, even if the
result is optimized away.
Linus suggested using an asm("") trick and place it in a variant of
ACCESS_ONCE(), allowing compiler to omit reading memory if result is
unused.
This patch introduces ACCESS_AT_MOST_ONCE() helper and use it in the x86
implementation of atomic_read() and constant_test_bit()
It's also used on x86_64 atomic64_read() implementation.
on x86_64, we thus reduce vmlinux text a bit (if CONFIG_DEBUG_VM=n)
# size vmlinux.old vmlinux.new
text data bss dec hex filename
10706848 2894216 1540096 15141160 e70928 vmlinux.old
10704040 2894216 1540096 15138352 e6fe30 vmlinux.new
Based on a prior patch from Linus, and review from Andi
Signed-off-by: Eric Dumazet <eric.dumazet@...il.com>
---
V2: Add a check on sizeof(x) in ACCESS_AT_MOST_ONCE()
Use ACCESS_AT_MOST_ONCE() on x86_64 atomic64_read()
arch/x86/include/asm/atomic.h | 2 +-
arch/x86/include/asm/atomic64_64.h | 2 +-
arch/x86/include/asm/bitops.h | 7 +++++--
include/asm-generic/atomic.h | 2 +-
include/linux/compiler.h | 15 +++++++++++++++
5 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 58cb6d4..b1f0c6b 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -22,7 +22,7 @@
*/
static inline int atomic_read(const atomic_t *v)
{
- return (*(volatile int *)&(v)->counter);
+ return ACCESS_AT_MOST_ONCE(v->counter);
}
/**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0e1cbfc..bdca6fa 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -18,7 +18,7 @@
*/
static inline long atomic64_read(const atomic64_t *v)
{
- return (*(volatile long *)&(v)->counter);
+ return ACCESS_AT_MOST_ONCE(v->counter);
}
/**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 1775d6e..e30a190 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -308,8 +308,11 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
{
- return ((1UL << (nr % BITS_PER_LONG)) &
- (addr[nr / BITS_PER_LONG])) != 0;
+ const unsigned long *word = (const unsigned long *)addr +
+ (nr / BITS_PER_LONG);
+ unsigned long bit = 1UL << (nr % BITS_PER_LONG);
+
+ return (bit & ACCESS_AT_MOST_ONCE(*word)) != 0;
}
static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index e37963c..c05e21f 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -39,7 +39,7 @@
* Atomically reads the value of @v.
*/
#ifndef atomic_read
-#define atomic_read(v) (*(volatile int *)&(v)->counter)
+#define atomic_read(v) ACCESS_AT_MOST_ONCE((v)->counter)
#endif
/**
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 320d6c9..bd18562 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -308,4 +308,19 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
*/
#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
+#ifndef __ASSEMBLY__
+/*
+ * Like ACCESS_ONCE, but can be optimized away if nothing uses the value,
+ * and/or merged with previous non-ONCE accesses.
+ */
+extern void ACCESS_AT_MOST_ONCE_bad(void);
+#define ACCESS_AT_MOST_ONCE(x) \
+ ({ unsigned long __y; \
+ if (sizeof(x) > sizeof(__y)) \
+ ACCESS_AT_MOST_ONCE_bad(); \
+ asm("":"=r" (__y):"0" (x)); \
+ (__force __typeof__(x)) __y; \
+ })
+#endif /* __ASSEMBLY__ */
+
#endif /* __LINUX_COMPILER_H */
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists