Home
last modified time | relevance | path

Searched full:guarantees (Results 1 – 25 of 1173) sorted by relevance

12345678910>>...47

/kernel/linux/linux-6.6/Documentation/core-api/
Drefcount-vs-atomic.rst14 ``atomic_*()`` functions with regards to the memory ordering guarantees.
17 these memory ordering guarantees.
33 In the absence of any memory ordering guarantees (i.e. fully unordered)
35 program order (po) relation (on the same CPU). It guarantees that
41 A strong (full) memory ordering guarantees that all prior loads and
44 It also guarantees that all po-earlier stores on the same CPU
49 A RELEASE memory ordering guarantees that all prior loads and
51 before the operation. It also guarantees that all po-earlier
57 An ACQUIRE memory ordering guarantees that all post loads and
59 completed after the acquire operation. It also guarantees that all
[all …]
/kernel/linux/linux-5.10/Documentation/core-api/
Drefcount-vs-atomic.rst14 ``atomic_*()`` functions with regards to the memory ordering guarantees.
17 these memory ordering guarantees.
33 In the absence of any memory ordering guarantees (i.e. fully unordered)
35 program order (po) relation (on the same CPU). It guarantees that
41 A strong (full) memory ordering guarantees that all prior loads and
44 It also guarantees that all po-earlier stores on the same CPU
49 A RELEASE memory ordering guarantees that all prior loads and
51 before the operation. It also guarantees that all po-earlier
57 An ACQUIRE memory ordering guarantees that all post loads and
59 completed after the acquire operation. It also guarantees that all
[all …]
/kernel/linux/linux-5.10/Documentation/block/
Dbfq-iosched.rst9 - BFQ guarantees a high system and application responsiveness, and a
70 4-1 Service guarantees provided
84 Regardless of the actual background workload, BFQ guarantees that, for
126 Strong fairness, bandwidth and delay guarantees
132 guarantees, it is possible to compute tight per-I/O-request delay
133 guarantees by a simple formula. If not configured for strict service
134 guarantees, BFQ switches to time-based resource sharing (only) for
142 possibly heavy workloads are being served, BFQ guarantees:
193 - With respect to idling for service guarantees, if several
196 guarantees the expected throughput distribution without ever
[all …]
/kernel/linux/linux-6.6/Documentation/block/
Dbfq-iosched.rst9 - BFQ guarantees a high system and application responsiveness, and a
70 4-1 Service guarantees provided
84 Regardless of the actual background workload, BFQ guarantees that, for
126 Strong fairness, bandwidth and delay guarantees
132 guarantees, it is possible to compute tight per-I/O-request delay
133 guarantees by a simple formula. If not configured for strict service
134 guarantees, BFQ switches to time-based resource sharing (only) for
142 possibly heavy workloads are being served, BFQ guarantees:
193 - With respect to idling for service guarantees, if several
196 guarantees the expected throughput distribution without ever
[all …]
/kernel/linux/linux-6.6/Documentation/ABI/testing/
Dsysfs-kernel-mm-numa22 the guarantees of cpusets. This should not be enabled
24 guarantees.
/kernel/linux/linux-6.6/arch/riscv/include/asm/
Dbitops.h106 * Note: there are no guarantees that this function will not be reordered
108 * make sure not to rely on its reordering guarantees.
123 * Note: there are no guarantees that this function will not be reordered
125 * make sure not to rely on its reordering guarantees.
/kernel/linux/linux-5.10/arch/riscv/include/asm/
Dbitops.h107 * Note: there are no guarantees that this function will not be reordered
109 * make sure not to rely on its reordering guarantees.
124 * Note: there are no guarantees that this function will not be reordered
126 * make sure not to rely on its reordering guarantees.
/kernel/linux/linux-5.10/kernel/
DKconfig.preempt12 time, but there are no guarantees and occasional longer delays
73 require real-time guarantees.
/kernel/linux/linux-6.6/arch/parisc/include/asm/
Dldcw.h5 /* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
6 and GCC only guarantees 8-byte alignment for stack locals, we can't
/kernel/linux/linux-5.10/arch/parisc/include/asm/
Dldcw.h5 /* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
6 and GCC only guarantees 8-byte alignment for stack locals, we can't
/kernel/linux/linux-6.6/tools/memory-model/Documentation/
Dlocking.txt43 The basic rule guarantees that if CPU0() acquires mylock before CPU1(),
75 This converse to the basic rule guarantees that if CPU0() acquires
135 The smp_load_acquire() guarantees that its load from "flags" will
137 problem. The smp_store_release() guarantees that its store will be
/kernel/linux/linux-6.6/arch/x86/include/asm/
Dkmsan.h89 * Note, this sacrifices occasionally breaking scheduling guarantees. in kmsan_virt_addr_valid()
91 * performance guarantees due to being heavily instrumented. in kmsan_virt_addr_valid()
/kernel/linux/linux-6.6/kernel/
DKconfig.preempt24 time, but there are no guarantees and occasional longer delays
85 require real-time guarantees.
/kernel/linux/linux-5.10/drivers/gpu/drm/i915/gem/
Di915_gem_busy.c24 * The uABI guarantees an active writer is also amongst the read in __busy_write_id()
45 * guarantees forward progress. We could rely on the idle worker in __busy_set_if_active()
/kernel/linux/linux-5.10/arch/arm/nwfpe/
DChangeLog61 comment in the code beside init_flag state the kernel guarantees
64 I couldn't even find anything that guarantees it is zeroed when
/kernel/linux/linux-6.6/arch/arm/nwfpe/
DChangeLog61 comment in the code beside init_flag state the kernel guarantees
64 I couldn't even find anything that guarantees it is zeroed when
/kernel/linux/linux-6.6/kernel/livepatch/
Dshadow.c189 * This function guarantees that the constructor function is called only when
218 * This function guarantees that only one shadow variable exists with the given
219 * @id for the given @obj. It also guarantees that the constructor function
/kernel/linux/linux-5.10/drivers/mmc/core/
Dsd_ops.c219 /* NOTE: caller guarantees scr is heap-allocated */ in mmc_app_send_scr()
272 /* NOTE: caller guarantees resp is heap-allocated */ in mmc_sd_switch()
314 /* NOTE: caller guarantees ssr is heap-allocated */ in mmc_app_sd_status()
/kernel/linux/linux-5.10/kernel/livepatch/
Dshadow.c189 * This function guarantees that the constructor function is called only when
218 * This function guarantees that only one shadow variable exists with the given
219 * @id for the given @obj. It also guarantees that the constructor function
/kernel/linux/linux-6.6/drivers/gpu/drm/i915/gem/
Di915_gem_busy.c26 * The uABI guarantees an active writer is also amongst the read in __busy_write_id()
47 * guarantees forward progress. We could rely on the idle worker in __busy_set_if_active()
/kernel/linux/linux-6.6/lib/
DKconfig.kgdb140 'go', KDB tries to continue. No guarantees that the
143 No guarantees that the kernel is still usable in this situation.
/kernel/linux/linux-5.10/lib/
DKconfig.kgdb140 'go', KDB tries to continue. No guarantees that the
143 No guarantees that the kernel is still usable in this situation.
/kernel/linux/linux-6.6/drivers/mmc/core/
Dsd_ops.c265 /* NOTE: caller guarantees scr is heap-allocated */ in mmc_app_send_scr()
315 /* NOTE: caller guarantees resp is heap-allocated */ in mmc_sd_switch()
336 /* NOTE: caller guarantees ssr is heap-allocated */ in mmc_app_sd_status()
/kernel/linux/linux-5.10/include/linux/
Ddm-bufio.h91 * dm_bufio_write_dirty_buffers guarantees that the buffer is on-disk but
111 * Write all dirty buffers. Guarantees that all dirty buffers created prior
/kernel/linux/linux-6.6/include/linux/
Ddm-bufio.h100 * dm_bufio_write_dirty_buffers guarantees that the buffer is on-disk but
120 * Write all dirty buffers. Guarantees that all dirty buffers created prior

12345678910>>...47