iversion: use atomic64_try_cmpxchg)

Use atomic64_try_cmpxchg instead of
atomic64_cmpxchg (*ptr, old, new) == old in inode_set_max_iversion_raw,
inode_maybe_inc_version and inode_query_iversion. x86 CMPXCHG instruction
returns success in ZF flag, so this change saves a compare after cmpxchg
(and related move instruction in front of cmpxchg).

Also, try_cmpxchg implicitly assigns old *ptr value to "old" when cmpxchg
fails, enabling further code simplifications.

The loop in inode_maybe_inc_iversion improves from:

    5563:	48 89 ca             	mov    %rcx,%rdx
    5566:	48 89 c8             	mov    %rcx,%rax
    5569:	48 83 e2 fe          	and    $0xfffffffffffffffe,%rdx
    556d:	48 83 c2 02          	add    $0x2,%rdx
    5571:	f0 48 0f b1 16       	lock cmpxchg %rdx,(%rsi)
    5576:	48 39 c1             	cmp    %rax,%rcx
    5579:	0f 84 85 fc ff ff    	je     5204 <...>
    557f:	48 89 c1             	mov    %rax,%rcx
    5582:	eb df                	jmp    5563 <...>

to:

    5563:	48 89 c2             	mov    %rax,%rdx
    5566:	48 83 e2 fe          	and    $0xfffffffffffffffe,%rdx
    556a:	48 83 c2 02          	add    $0x2,%rdx
    556e:	f0 48 0f b1 11       	lock cmpxchg %rdx,(%rcx)
    5573:	0f 84 8b fc ff ff    	je     5204 <...>
    5579:	eb e8                	jmp    5563 <...>

Link: https://lkml.kernel.org/r/20220821193011.88208-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Uros Bizjak 2022-08-21 21:30:11 +02:00 committed by Andrew Morton
parent 38ace0d513
commit da3f52ba35
1 changed files with 9 additions and 23 deletions

View File

@ -123,17 +123,12 @@ inode_peek_iversion_raw(const struct inode *inode)
static inline void
inode_set_max_iversion_raw(struct inode *inode, u64 val)
{
u64 cur, old;
u64 cur = inode_peek_iversion_raw(inode);
cur = inode_peek_iversion_raw(inode);
for (;;) {
do {
if (cur > val)
break;
old = atomic64_cmpxchg(&inode->i_version, cur, val);
if (likely(old == cur))
break;
cur = old;
}
} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val));
}
/**
@ -197,7 +192,7 @@ inode_set_iversion_queried(struct inode *inode, u64 val)
static inline bool
inode_maybe_inc_iversion(struct inode *inode, bool force)
{
u64 cur, old, new;
u64 cur, new;
/*
* The i_version field is not strictly ordered with any other inode
@ -211,19 +206,14 @@ inode_maybe_inc_iversion(struct inode *inode, bool force)
*/
smp_mb();
cur = inode_peek_iversion_raw(inode);
for (;;) {
do {
/* If flag is clear then we needn't do anything */
if (!force && !(cur & I_VERSION_QUERIED))
return false;
/* Since lowest bit is flag, add 2 to avoid it */
new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT;
old = atomic64_cmpxchg(&inode->i_version, cur, new);
if (likely(old == cur))
break;
cur = old;
}
} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
return true;
}
@ -304,10 +294,10 @@ inode_peek_iversion(const struct inode *inode)
static inline u64
inode_query_iversion(struct inode *inode)
{
u64 cur, old, new;
u64 cur, new;
cur = inode_peek_iversion_raw(inode);
for (;;) {
do {
/* If flag is already set, then no need to swap */
if (cur & I_VERSION_QUERIED) {
/*
@ -320,11 +310,7 @@ inode_query_iversion(struct inode *inode)
}
new = cur | I_VERSION_QUERIED;
old = atomic64_cmpxchg(&inode->i_version, cur, new);
if (likely(old == cur))
break;
cur = old;
}
} while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new));
return cur >> I_VERSION_QUERIED_SHIFT;
}