summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-06-28 00:14:30 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-06-28 00:14:30 +0300
commitbc6cb4d5bc3a44197de30784eae71d8ba28483eb (patch)
treefdd00391c6068c217eeb8a4a06afc40cc1fc6853 /mm
parented3b7923a816ded62dccef377c9ee346c7d3b1b4 (diff)
parentb33eb50a92b0a298fa8a6ac350e741c3ec100f6d (diff)
downloadlinux-bc6cb4d5bc3a44197de30784eae71d8ba28483eb.tar.xz
Merge tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar: - Introduce cmpxchg128() -- aka. the demise of cmpxchg_double() The cmpxchg128() family of functions is basically & functionally the same as cmpxchg_double(), but with a saner interface. Instead of a 6-parameter horror that forced u128 - u64/u64-halves layout details on the interface and exposed users to complexity, fragility & bugs, use a natural 3-parameter interface with u128 types. - Restructure the generated atomic headers, and add kerneldoc comments for all of the generic atomic{,64,_long}_t operations. The generated definitions are much cleaner now, and come with documentation. - Implement lock_set_cmp_fn() on lockdep, for defining an ordering when taking multiple locks of the same type. This gets rid of one use of lockdep_set_novalidate_class() in the bcache code. - Fix raw_cpu_generic_try_cmpxchg() bug due to an unintended variable shadowing generating garbage code on Clang on certain ARM builds. * tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits) locking/atomic: scripts: fix ${atomic}_dec_if_positive() kerneldoc percpu: Fix self-assignment of __old in raw_cpu_generic_try_cmpxchg() locking/atomic: treewide: delete arch_atomic_*() kerneldoc locking/atomic: docs: Add atomic operations to the driver basic API documentation locking/atomic: scripts: generate kerneldoc comments docs: scripts: kernel-doc: accept bitwise negation like ~@var locking/atomic: scripts: simplify raw_atomic*() definitions locking/atomic: scripts: simplify raw_atomic_long*() definitions locking/atomic: scripts: split pfx/name/sfx/order locking/atomic: scripts: restructure fallback ifdeffery locking/atomic: scripts: build raw_atomic_long*() directly locking/atomic: treewide: use raw_atomic*_<op>() locking/atomic: scripts: add trivial raw_atomic*_<op>() locking/atomic: scripts: factor out order template generation locking/atomic: scripts: remove leftover "${mult}" locking/atomic: scripts: remove bogus order parameter locking/atomic: xtensa: add preprocessor symbols locking/atomic: x86: add preprocessor symbols locking/atomic: sparc: add preprocessor symbols locking/atomic: sh: add preprocessor symbols ...
Diffstat (limited to 'mm')
-rw-r--r--mm/slab.h53
-rw-r--r--mm/slub.c139
2 files changed, 128 insertions, 64 deletions
diff --git a/mm/slab.h b/mm/slab.h
index f01ac256a8f5..bc36edd5ba4f 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -6,6 +6,38 @@
*/
void __init kmem_cache_init(void);
+#ifdef CONFIG_64BIT
+# ifdef system_has_cmpxchg128
+# define system_has_freelist_aba() system_has_cmpxchg128()
+# define try_cmpxchg_freelist try_cmpxchg128
+# endif
+#define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg128
+typedef u128 freelist_full_t;
+#else /* CONFIG_64BIT */
+# ifdef system_has_cmpxchg64
+# define system_has_freelist_aba() system_has_cmpxchg64()
+# define try_cmpxchg_freelist try_cmpxchg64
+# endif
+#define this_cpu_try_cmpxchg_freelist this_cpu_try_cmpxchg64
+typedef u64 freelist_full_t;
+#endif /* CONFIG_64BIT */
+
+#if defined(system_has_freelist_aba) && !defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
+#undef system_has_freelist_aba
+#endif
+
+/*
+ * Freelist pointer and counter to cmpxchg together, avoids the typical ABA
+ * problems with cmpxchg of just a pointer.
+ */
+typedef union {
+ struct {
+ void *freelist;
+ unsigned long counter;
+ };
+ freelist_full_t full;
+} freelist_aba_t;
+
/* Reuses the bits in struct page */
struct slab {
unsigned long __page_flags;
@@ -38,14 +70,21 @@ struct slab {
#endif
};
/* Double-word boundary */
- void *freelist; /* first free object */
union {
- unsigned long counters;
struct {
- unsigned inuse:16;
- unsigned objects:15;
- unsigned frozen:1;
+ void *freelist; /* first free object */
+ union {
+ unsigned long counters;
+ struct {
+ unsigned inuse:16;
+ unsigned objects:15;
+ unsigned frozen:1;
+ };
+ };
};
+#ifdef system_has_freelist_aba
+ freelist_aba_t freelist_counter;
+#endif
};
};
struct rcu_head rcu_head;
@@ -72,8 +111,8 @@ SLAB_MATCH(memcg_data, memcg_data);
#endif
#undef SLAB_MATCH
static_assert(sizeof(struct slab) <= sizeof(struct page));
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && defined(CONFIG_SLUB)
-static_assert(IS_ALIGNED(offsetof(struct slab, freelist), 2*sizeof(void *)));
+#if defined(system_has_freelist_aba) && defined(CONFIG_SLUB)
+static_assert(IS_ALIGNED(offsetof(struct slab, freelist), sizeof(freelist_aba_t)));
#endif
/**
diff --git a/mm/slub.c b/mm/slub.c
index c87628cd8a9a..7529626bbec2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -292,7 +292,12 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
/* Poison object */
#define __OBJECT_POISON ((slab_flags_t __force)0x80000000U)
/* Use cmpxchg_double */
+
+#ifdef system_has_freelist_aba
#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0x40000000U)
+#else
+#define __CMPXCHG_DOUBLE ((slab_flags_t __force)0U)
+#endif
/*
* Tracking user of a slab.
@@ -512,6 +517,40 @@ static __always_inline void slab_unlock(struct slab *slab)
__bit_spin_unlock(PG_locked, &page->flags);
}
+static inline bool
+__update_freelist_fast(struct slab *slab,
+ void *freelist_old, unsigned long counters_old,
+ void *freelist_new, unsigned long counters_new)
+{
+#ifdef system_has_freelist_aba
+ freelist_aba_t old = { .freelist = freelist_old, .counter = counters_old };
+ freelist_aba_t new = { .freelist = freelist_new, .counter = counters_new };
+
+ return try_cmpxchg_freelist(&slab->freelist_counter.full, &old.full, new.full);
+#else
+ return false;
+#endif
+}
+
+static inline bool
+__update_freelist_slow(struct slab *slab,
+ void *freelist_old, unsigned long counters_old,
+ void *freelist_new, unsigned long counters_new)
+{
+ bool ret = false;
+
+ slab_lock(slab);
+ if (slab->freelist == freelist_old &&
+ slab->counters == counters_old) {
+ slab->freelist = freelist_new;
+ slab->counters = counters_new;
+ ret = true;
+ }
+ slab_unlock(slab);
+
+ return ret;
+}
+
/*
* Interrupts must be disabled (for the fallback code to work right), typically
* by an _irqsave() lock variant. On PREEMPT_RT the preempt_disable(), which is
@@ -519,33 +558,25 @@ static __always_inline void slab_unlock(struct slab *slab)
* allocation/ free operation in hardirq context. Therefore nothing can
* interrupt the operation.
*/
-static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab,
+static inline bool __slab_update_freelist(struct kmem_cache *s, struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
+ bool ret;
+
if (USE_LOCKLESS_FAST_PATH())
lockdep_assert_irqs_disabled();
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
- defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
+
if (s->flags & __CMPXCHG_DOUBLE) {
- if (cmpxchg_double(&slab->freelist, &slab->counters,
- freelist_old, counters_old,
- freelist_new, counters_new))
- return true;
- } else
-#endif
- {
- slab_lock(slab);
- if (slab->freelist == freelist_old &&
- slab->counters == counters_old) {
- slab->freelist = freelist_new;
- slab->counters = counters_new;
- slab_unlock(slab);
- return true;
- }
- slab_unlock(slab);
+ ret = __update_freelist_fast(slab, freelist_old, counters_old,
+ freelist_new, counters_new);
+ } else {
+ ret = __update_freelist_slow(slab, freelist_old, counters_old,
+ freelist_new, counters_new);
}
+ if (likely(ret))
+ return true;
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
@@ -557,36 +588,26 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab
return false;
}
-static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab,
+static inline bool slab_update_freelist(struct kmem_cache *s, struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
{
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
- defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
+ bool ret;
+
if (s->flags & __CMPXCHG_DOUBLE) {
- if (cmpxchg_double(&slab->freelist, &slab->counters,
- freelist_old, counters_old,
- freelist_new, counters_new))
- return true;
- } else
-#endif
- {
+ ret = __update_freelist_fast(slab, freelist_old, counters_old,
+ freelist_new, counters_new);
+ } else {
unsigned long flags;
local_irq_save(flags);
- slab_lock(slab);
- if (slab->freelist == freelist_old &&
- slab->counters == counters_old) {
- slab->freelist = freelist_new;
- slab->counters = counters_new;
- slab_unlock(slab);
- local_irq_restore(flags);
- return true;
- }
- slab_unlock(slab);
+ ret = __update_freelist_slow(slab, freelist_old, counters_old,
+ freelist_new, counters_new);
local_irq_restore(flags);
}
+ if (likely(ret))
+ return true;
cpu_relax();
stat(s, CMPXCHG_DOUBLE_FAIL);
@@ -2228,7 +2249,7 @@ static inline void *acquire_slab(struct kmem_cache *s,
VM_BUG_ON(new.frozen);
new.frozen = 1;
- if (!__cmpxchg_double_slab(s, slab,
+ if (!__slab_update_freelist(s, slab,
freelist, counters,
new.freelist, new.counters,
"acquire_slab"))
@@ -2554,7 +2575,7 @@ redo:
}
- if (!cmpxchg_double_slab(s, slab,
+ if (!slab_update_freelist(s, slab,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab")) {
@@ -2611,7 +2632,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
new.frozen = 0;
- } while (!__cmpxchg_double_slab(s, slab,
+ } while (!__slab_update_freelist(s, slab,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
@@ -3008,6 +3029,18 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
}
#ifndef CONFIG_SLUB_TINY
+static inline bool
+__update_cpu_freelist_fast(struct kmem_cache *s,
+ void *freelist_old, void *freelist_new,
+ unsigned long tid)
+{
+ freelist_aba_t old = { .freelist = freelist_old, .counter = tid };
+ freelist_aba_t new = { .freelist = freelist_new, .counter = next_tid(tid) };
+
+ return this_cpu_try_cmpxchg_freelist(s->cpu_slab->freelist_tid.full,
+ &old.full, new.full);
+}
+
/*
* Check the slab->freelist and either transfer the freelist to the
* per cpu freelist or deactivate the slab.
@@ -3034,7 +3067,7 @@ static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
new.inuse = slab->objects;
new.frozen = freelist != NULL;
- } while (!__cmpxchg_double_slab(s, slab,
+ } while (!__slab_update_freelist(s, slab,
freelist, counters,
NULL, new.counters,
"get_freelist"));
@@ -3359,11 +3392,7 @@ redo:
* against code executing on this cpu *not* from access by
* other cpus.
*/
- if (unlikely(!this_cpu_cmpxchg_double(
- s->cpu_slab->freelist, s->cpu_slab->tid,
- object, tid,
- next_object, next_tid(tid)))) {
-
+ if (unlikely(!__update_cpu_freelist_fast(s, object, next_object, tid))) {
note_cmpxchg_failure("slab_alloc", s, tid);
goto redo;
}
@@ -3631,7 +3660,7 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab,
}
}
- } while (!cmpxchg_double_slab(s, slab,
+ } while (!slab_update_freelist(s, slab,
prior, counters,
head, new.counters,
"__slab_free"));
@@ -3736,11 +3765,7 @@ redo:
set_freepointer(s, tail_obj, freelist);
- if (unlikely(!this_cpu_cmpxchg_double(
- s->cpu_slab->freelist, s->cpu_slab->tid,
- freelist, tid,
- head, next_tid(tid)))) {
-
+ if (unlikely(!__update_cpu_freelist_fast(s, freelist, head, tid))) {
note_cmpxchg_failure("slab_free", s, tid);
goto redo;
}
@@ -4505,11 +4530,11 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
}
}
-#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
- defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
- if (system_has_cmpxchg_double() && (s->flags & SLAB_NO_CMPXCHG) == 0)
+#ifdef system_has_freelist_aba
+ if (system_has_freelist_aba() && !(s->flags & SLAB_NO_CMPXCHG)) {
/* Enable fast mode */
s->flags |= __CMPXCHG_DOUBLE;
+ }
#endif
/*