| /linux/mm/ |
| H A D | zpool.c | 101 * the requested module, if needed, but there is no guarantee the module will
141 * Implementations must guarantee this to be thread-safe.
192 * Implementations must guarantee this to be thread-safe,
214 * Implementations must guarantee this to be thread-safe.
230 * Implementations must guarantee this to be thread-safe.
251 * Implementations must guarantee this to be thread-safe.
266 * This frees previously allocated memory. This does not guarantee
270 * Implementations must guarantee this to be thread-safe,
|
| H A D | shrinker.c | 492 * step 1: use rcu_read_lock() to guarantee existence of the in shrink_slab_memcg()
497 * step 4: use rcu_read_lock() to guarantee existence of the shrinker. in shrink_slab_memcg()
499 * shrinker_try_get() to guarantee existence of the shrinker, in shrink_slab_memcg()
506 * need to acquire the RCU lock to guarantee existence of in shrink_slab_memcg()
638 * step 1: use rcu_read_lock() to guarantee existence of the shrinker in shrink_slab()
|
| /linux/kernel/sched/ |
| H A D | membarrier.c | 20 * order to enforce the guarantee that any writes occurring on CPU0 before
42 * and r2 == 0. This violates the guarantee that membarrier() is
56 * order to enforce the guarantee that any writes occurring on CPU1 before
77 * the guarantee that membarrier() is supposed to provide.
181 * A sync_core() would provide this guarantee, but in ipi_sync_core()
214 * guarantee that no memory access following registration is reordered in ipi_sync_rq_state()
224 * guarantee that no memory access prior to exec is reordered after in membarrier_exec_mmap()
448 * mm and in the current runqueue to guarantee that no memory in sync_runqueues_membarrier_state()
|
| /linux/include/linux/ |
| H A D | rbtree_latch.h | 9 * lockless lookups; we cannot guarantee they return a correct result.
21 * However, while we have the guarantee that there is at all times one stable
22 * copy, this does not guarantee an iteration will not observe modifications.
61 * guarantee on which of the elements matching the key is found. See
|
| H A D | types.h | 225 * The alignment is required to guarantee that bit 0 of @next will be
229 * This guarantee is important for few reasons:
232 * which encode PageTail() in bit 0. The guarantee is needed to avoid
|
| H A D | u64_stats_sync.h | 26 * 4) If reader fetches several counters, there is no guarantee the whole values
47 * snapshot for each variable (but no guarantee on several ones)
|
| /linux/kernel/printk/ |
| H A D | printk_ringbuffer.c | 459 * Guarantee the state is loaded before copying the descriptor in desc_read()
491 * 1. Guarantee the descriptor content is loaded before re-checking in desc_read()
507 * 2. Guarantee the record data is loaded before re-checking the in desc_read()
681 * 1. Guarantee the block ID loaded in in data_push_tail()
708 * 2. Guarantee the descriptor state loaded in in data_push_tail()
748 * Guarantee any descriptor states that have transitioned to in data_push_tail()
833 * Guarantee any descriptor states that have transitioned to in desc_push_tail()
843 * Guarantee the last state load from desc_read() is before in desc_push_tail()
895 * Guarantee the head ID is read before reading the tail ID. in desc_reserve()
929 * 1. Guarantee the tail ID is read before validating the in desc_reserve()
[all …]
|
| /linux/arch/x86/include/asm/vdso/ |
| H A D | gettimeofday.h | 204 * Note: The kernel and hypervisor must guarantee that cpu ID in vread_pvclock()
208 * preemption, it cannot guarantee that per-CPU pvclock time in vread_pvclock()
214 * guarantee than we get with a normal seqlock. in vread_pvclock()
216 * On Xen, we don't appear to have that guarantee, but Xen still in vread_pvclock()
|
| /linux/Documentation/locking/ |
| H A D | spinlocks.rst | 19 spinlock itself will guarantee the global lock, so it will guarantee that
117 guarantee the same kind of exclusive access, and it will be much faster.
|
| /linux/Documentation/core-api/ |
| H A D | refcount-vs-atomic.rst | 84 Memory ordering guarantee changes:
97 Memory ordering guarantee changes:
108 Memory ordering guarantee changes:
|
| H A D | this_cpu_ops.rst | 111 surrounding code this_cpu_inc() will only guarantee that one of the
113 guarantee that the OS will not move the process directly before or
229 These operations have no guarantee against concurrent interrupts or
|
| /linux/tools/memory-model/Documentation/ |
| H A D | ordering.txt | 101 with void return types) do not guarantee any ordering whatsoever. Nor do
106 operations such as atomic_read() do not guarantee full ordering, and
130 such as atomic_inc() and atomic_dec() guarantee no ordering whatsoever.
150 atomic_inc() implementations do not guarantee full ordering, thus
278 from "x" instead of writing to it. Then an smp_wmb() could not guarantee
501 and further do not guarantee "atomic" access. For example, the compiler
|
| /linux/Documentation/driver-api/ |
| H A D | reset.rst | 87 Exclusive resets on the other hand guarantee direct control.
99 is no guarantee that calling reset_control_assert() on a shared reset control
152 The reset control API does not guarantee the order in which the individual
|
| /linux/Documentation/ |
| H A D | memory-barriers.txt | 331 of the standard containing this guarantee is Section 3.14, which
381 A write memory barrier gives a guarantee that all the STORE operations
444 A read barrier is an address-dependency barrier plus a guarantee that all
461 A general memory barrier gives a guarantee that all the LOAD and STORE
532 There are certain things that the Linux kernel memory barriers do not guarantee:
534 (*) There is no guarantee that any of the memory accesses specified before a
539 (*) There is no guarantee that issuing a memory barrier on one CPU will have
544 (*) There is no guarantee that a CPU will see the correct order of effects
549 (*) There is no guarantee that some intervening piece of off-the-CPU
897 However, they do -not- guarantee any other sort of ordering:
[all …]
|
| /linux/rust/kernel/ |
| H A D | build_assert.rs | 8 /// If the compiler or optimizer cannot guarantee that `build_error!` can never
36 /// will panic. If the compiler or optimizer cannot guarantee the condition will
|
| H A D | types.rs | 236 // The type invariants guarantee that `unwrap` will succeed. in deref()
243 // The type invariants guarantee that `unwrap` will succeed. in deref_mut()
392 // INVARIANT: The safety requirements guarantee that the new instance now owns the in from_raw()
442 // SAFETY: The type invariants guarantee that the object is valid. in deref()
457 // SAFETY: The type invariants guarantee that the `ARef` owns the reference we're about to in drop()
|
| /linux/drivers/net/ethernet/meta/fbnic/ |
| H A D | fbnic_txrx.h | 15 /* Guarantee we have space needed for storing the buffer
21 * If we cannot guarantee that then we should return TX_BUSY
|
| /linux/net/smc/ |
| H A D | smc_cdc.c | 46 /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ in smc_cdc_tx_handler()
273 /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ in smcd_cdc_msg_send()
349 /* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */ in smc_cdc_msg_recv_action()
367 /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ in smc_cdc_msg_recv_action()
384 /* guarantee 0 <= bytes_to_rcv <= rmb_desc->len */ in smc_cdc_msg_recv_action()
|
| /linux/Documentation/driver-api/usb/ |
| H A D | anchors.rst | 55 Therefore no guarantee is made that the URBs have been unlinked when
82 destinations in one anchor you have no guarantee the chronologically
|
| /linux/arch/arc/include/asm/ |
| H A D | futex.h | 82 preempt_disable(); /* to guarantee atomic r-m-w of futex op */ in arch_futex_atomic_op_inuser()
131 preempt_disable(); /* to guarantee atomic r-m-w of futex op */ in futex_atomic_cmpxchg_inatomic()
|
| /linux/Documentation/RCU/Design/Requirements/ |
| H A D | Requirements.rst | 58 #. `Grace-Period Guarantee`_
59 #. `Publish/Subscribe Guarantee`_
64 Grace-Period Guarantee
67 RCU's grace-period guarantee is unusual in being premeditated: Jack
68 Slingwine and I had this guarantee firmly in mind when we started work
71 understanding of this guarantee.
73 RCU's grace-period guarantee allows updaters to wait for the completion
83 This guarantee allows ordering to be enforced with extremely low
174 the synchronize_rcu() in start_recovery() to guarantee that
196 Although RCU's grace-period guarantee is useful in and of itself, with
[all …]
|
| /linux/Documentation/filesystems/xfs/ |
| H A D | xfs-delayed-logging-design.rst | 17 guarantee forwards progress for long running transactions with finite initial
51 followed to guarantee forwards progress and prevent deadlocks.
119 there is no guarantee of how much of the operation reached stale storage. Hence
121 the high level operation must use intents and deferred operations to guarantee
130 xfs_trans_commit() does not guarantee that the modification has been committed
154 provide a forwards progress guarantee so that no modification ever stalls
160 A transaction reservation provides a guarantee that there is physical log space
178 for the transaction that is calculated at mount time. We must guarantee that the
416 It should be noted that this does not change the guarantee that log recovery
892 guarantee which context the pin count is associated with. This is because of
[all …]
|
| /linux/Documentation/block/ |
| H A D | stat.rst | 15 By having a single file, the kernel can guarantee that the statistics
18 each, it would be impossible to guarantee that a set of readings
|
| /linux/Documentation/RCU/Design/Memory-Ordering/ |
| H A D | Tree-RCU-Memory-Ordering.rst | 13 grace-period memory ordering guarantee is provided.
15 What Is Tree RCU's Grace Period Memory Ordering Guarantee?
33 RCU updaters use this guarantee by splitting their updates into
42 The RCU implementation provides this guarantee using a network
145 RCU's grace-period memory ordering guarantee to extend to any
254 Tree RCU's grace-period memory-ordering guarantee is provided by a
272 If RCU's grace-period guarantee is to mean anything at all, any access
275 portion of RCU's grace period guarantee is shown in the following
|
| /linux/drivers/clocksource/ |
| H A D | timer-pxa.c | 116 * register 0 and the OSCR, to guarantee that we will receive in pxa_timer_resume()
118 * to OSCR to guarantee that OSCR is monotonically incrementing. in pxa_timer_resume()
|