Home
last modified time | relevance | path

Searched +full:access +full:- +full:granularity (Results 1 – 25 of 248) sorted by relevance

12345678910

/linux/drivers/acpi/acpica/
H A Dexprep.c1 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
4 * Module Name: exprep - ACPI AML field prep utilities
6 * Copyright (C) 2000 - 2025, Intel Corp.
35 * PARAMETERS: field_bit_offset - Start of field within parent region/buffer
36 * field_bit_length - Length of field in bits
37 * region_length - Length of parent in bytes
39 * RETURN: Field granularity (8, 16, 32 or 64) and
42 * DESCRIPTION: Generate an optimal access width for fields defined with the
46 * conditions (end-of-region). However, the region_length is a deferred
48 * of this access width must be deferred until the region length has
[all …]
H A Drsdumpinfo.c1 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
4 * Module Name: rsdumpinfo - Tables used to display resource descriptors.
59 "Start-Dependent-Functions", NULL},
70 "End-Dependent-Functions", NULL}
107 "24-Bit Memory Range", NULL},
122 "32-Bit Memory Range", NULL},
137 "32-Bit Fixed Memory Range", NULL},
148 "16-Bit WORD Address Space", NULL},
150 {ACPI_RSD_UINT16, ACPI_RSD_OFFSET(address16.address.granularity),
151 "Granularity", NULL},
[all …]
H A Dhwvalid.c1 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
4 * Module Name: hwvalid - I/O request validation
6 * Copyright (C) 2000 - 2025, Intel Corp.
24 * The table is used to implement the Microsoft port access rules that
37 * RTC: Real-time clock
109 last_address = address + byte_width - 1; in acpi_hw_validate_io_request()
116 /* Maximum 16-bit address in I/O space */ in acpi_hw_validate_io_request()
127 if (address > acpi_protected_ports[ACPI_PORT_INFO_ENTRIES - 1].end) { in acpi_hw_validate_io_request()
143 if ((address <= port_info->end) in acpi_hw_validate_io_request()
144 && (last_address >= port_info->start)) { in acpi_hw_validate_io_request()
[all …]
/linux/drivers/gpu/drm/i915/
H A DKconfig.profile16 int "Timeout for unsignaled foreign fences (ms, jiffy granularity)"
33 their next access. The revocation and subsequent recreation of
35 that complements the runtime-pm autosuspend and provides a lower
46 check the health of the GPU and undertake regular house-keeping of
56 int "Preempt timeout (ms, jiffy granularity)"
74 int "Preempt timeout for compute engines (ms, jiffy granularity)"
98 take a non-negligible time to setup, we do a short spin first to
124 int "Scheduling quantum for userspace batches (ms, jiffy granularity)"
/linux/Documentation/ABI/testing/
H A Dsysfs-memory-page-offline6 Soft-offline the memory page containing the physical address
9 to soft-offline it, by moving the contents elsewhere or
13 The offlining is done in kernel specific granularity.
28 Hard-offline the memory page containing the physical
31 kernel will then attempt to hard-offline the page, by
35 to access this page assuming it's poisoned by the
38 The offlining is done in kernel specific granularity.
/linux/Documentation/driver-api/cxl/linux/
H A Dcxl-driver.rst1 .. SPDX-License-Identifier: GPL-2.0
12 The :code:`cxl-cli` library, maintained as part of the NDTCL project, may
19 * cxl_core - fundamental init interface and core object creation
20 * cxl_port - initializes root and provides port enumeration interface.
21 * cxl_acpi - initializes root decoders and interacts with ACPI data.
22 * cxl_p/mem - initializes memory devices
23 * cxl_pci - uses cxl_port to enumerate the actual fabric hierarchy.
27 Here is an example from a single-socket system with 4 host bridges. Two host
38 .. kernel-render:: DOT
39 :alt: Digraph of CXL fabric describing host-bridge interleaving
[all …]
/linux/sound/pci/pcxhr/
H A Dpcxhr.h1 /* SPDX-License-Identifier: GPL-2.0-or-later */
25 /* transfer granularity of pipes and the dsp time (MBOX4) */
27 /* TODO : granularity could be 64 or 128 */
28 #define PCXHR_GRANULARITY_HR22 192 /* granularity for stereo cards */
59 int granularity; member
61 /* card access with 1 mem bar and 2 io bar's */
H A Dpcxhr_core.c1 // SPDX-License-Identifier: GPL-2.0-or-later
50 /* access to the card */
59 #define PCXHR_INPB(mgr,x) inb((mgr)->port[PCXHR_REG_TO_PORT(x)] + (x))
60 #define PCXHR_INPL(mgr,x) inl((mgr)->port[PCXHR_REG_TO_PORT(x)] + (x))
61 #define PCXHR_OUTPB(mgr,x,data) outb((data), (mgr)->port[PCXHR_REG_TO_PORT(x)] + (x))
62 #define PCXHR_OUTPL(mgr,x,data) outl((data), (mgr)->por
[all...]
/linux/drivers/gpu/drm/amd/amdkfd/
H A Dkfd_svm.h1 /* SPDX-License-Identifier: GPL-2.0 OR MIT */
3 * Copyright 2020-2021 Advanced Micro Devices, Inc.
40 ((adev)->hive ? (void *)(adev)->hive : (void *)(adev))
69 * struct svm_range - shared virtual memory range
76 * aligned, page size is (last - start + 1)
95 * @granularity:migration granularity, log2 num pages
102 * @bitmap_access: index bitmap of GPUs which can access the range
103 * @bitmap_aip: index bitmap of GPUs which can access the range in place
130 uint8_t granularity; member
145 mutex_lock(&prange->lock); in svm_range_lock()
[all …]
H A Dkfd_svm.c1 // SPDX-License-Identifier: GPL-2.0 OR MIT
3 * Copyright 2020-2021 Advanced Micro Devices, Inc.
84 * svm_range_unlink - unlink svm_range from lists and interval tree
90 * Context: The caller must hold svms->lock
94 pr_debug("svms 0x%p prange 0x%p [0x%lx 0x%lx]\n", prange->svms, in svm_range_unlink()
95 prange, prange->start, prange->last); in svm_range_unlink()
97 if (prange->svm_bo) { in svm_range_unlink()
98 spin_lock(&prange->svm_bo->list_lock); in svm_range_unlink()
99 list_del(&prange->svm_bo_list); in svm_range_unlink()
100 spin_unlock(&prange->svm_bo->list_lock); in svm_range_unlink()
[all …]
/linux/Documentation/mm/damon/
H A Dfaq.rst1 .. SPDX-License-Identifier: GPL-2.0
12 constructions and actual access checks can be implemented and configured on the
14 space with any access check technique.
21 Can I simply monitor page granularity?
/linux/Documentation/admin-guide/mm/damon/
H A Dlru_sort.rst1 .. SPDX-License-Identifier: GPL-2.0
4 DAMON-based LRU-lists Sorting
7 DAMON-based LRU-lists Sorting (DAMON_LRU_SORT) is a static kernel module that
8 aimed to be used for proactive and lightweight data access pattern based
9 (de)prioritization of pages on their LRU-lists for making LRU-lists a more
10 trusworthy data access pattern source.
12 Where Proactive LRU-lists Sorting is Required?
15 As page-granularity access checking overhead could be significant on huge
19 perfectly prepared to be used as a trustworthy access pattern source for some
23 Because DAMON can identify access patterns of best-effort accuracy while
[all …]
/linux/sound/pci/lola/
H A Dlola.c1 // SPDX-License-Identifier: GPL-2.0-or-later
3 * Support for Digigram Lola PCI-e boards
11 #include <linux/dma-mapping.h>
34 /* Lola-specific options */
36 /* for instance use always max granularity which is compatible
39 static int granularity[SNDRV_CARD variable
[all...]
/linux/arch/riscv/kernel/
H A Dunaligned_access_speed.c1 // SPDX-License-Identifier: GPL-2.0-only
17 #include "copy-unaligned.h"
22 #define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80)
54 word_cycles = -1ULL; in check_unaligned_access()
74 if ((end_cycles - start_cycles) < word_cycles) in check_unaligned_access()
75 word_cycles = end_cycles - start_cycles; in check_unaligned_access()
78 byte_cycles = -1ULL; in check_unaligned_access()
90 if ((end_cycles - start_cycles) < byte_cycles) in check_unaligned_access()
91 byte_cycles = end_cycles - start_cycles; in check_unaligned_access()
98 pr_warn("cpu%d: rdtime lacks granularity needed to measure unaligned access speed\n", in check_unaligned_access()
[all …]
/linux/Documentation/devicetree/bindings/memory-controllers/
H A Dti,gpmc-child.yaml1 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
3 ---
4 $id: http://devicetree.org/schemas/memory-controllers/ti,gpmc-child.yaml#
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
10 - Tony Lindgren <tony@atomide.com>
11 - Roger Quadros <rogerq@kernel.org>
24 gpmc,sync-clk-ps:
28 # Chip-select signal timings corresponding to GPMC_CONFIG2:
29 gpmc,cs-on-ns:
33 gpmc,cs-rd-off-ns:
[all …]
/linux/Documentation/mm/
H A Dmemory-model.rst1 .. SPDX-License-Identifier: GPL-2.0
23 Regardless of the selected memory model, there exists one-to-one
35 non-NUMA systems with contiguous, or mostly contiguous, physical
54 straightforward: `PFN - ARCH_PFN_OFFSET` is an index to the
65 as hot-plug and hot-remove of the physical memory, alternative memory
66 maps for non-volatile memory devices and deferred initialization of
85 NR\_MEM\_SECTIONS = 2 ^ {(MAX\_PHYSMEM\_BITS - SECTION\_SIZE\_BITS)}
87 The `mem_section` objects are arranged in a two-dimensional array
104 corresponding `struct page` - a "classic sparse" and "sparse
108 The classic sparse encodes the section number of a page in page->flags
[all …]
/linux/tools/testing/selftests/rtc/
H A Drtctest.c1 // SPDX-License-Identifier: GPL-2.0
40 self->fd = open(rtc_file, O_RDONLY); in FIXTURE_SETUP()
44 close(self->fd); in FIXTURE_TEARDOWN()
51 if (self->fd == -1 && errno == ENOENT) in TEST_F()
53 ASSERT_NE(-1, self->fd); in TEST_F()
56 rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm); in TEST_F()
57 ASSERT_NE(-1, rc); in TEST_F()
67 .tm_sec = rtc_time->tm_sec, in rtc_time_to_timestamp()
68 .tm_min = rtc_time->tm_min, in rtc_time_to_timestamp()
69 .tm_hour = rtc_time->tm_hour, in rtc_time_to_timestamp()
[all …]
/linux/Documentation/timers/
H A Dhrtimers.rst2 hrtimers - subsystem for high-resolution kernel timers
5 This patch introduces a new subsystem for high-resolution kernel timers.
9 back and forth trying to integrate high-resolution and high-precision
11 such high-resolution timer implementations in practice, we came to the
18 - the forced handling of low-resolution and high-resolution timers in
21 32-bitness assumptions, and has been honed and micro-optimized for a
23 for many years - and thus even small extensions to it easily break
26 current usage - but it is simply not suitable to be extended for
27 high-res timers.
29 - the unpredictable [O(N)] overhead of cascading leads to delays which
[all …]
/linux/drivers/nvme/host/
H A Dconstants.c1 // SPDX-License-Identifier: GPL-2.0
96 [NVME_SC_SGL_INVALID_GRANULARITY] = "SGL Data Block Granularity Invalid",
136 [NVME_SC_SELF_TEST_IN_PROGRESS] = "Device Self-test In Progress",
159 [NVME_SC_GUARD_CHECK] = "End-to-end Guard Check Error",
160 [NVME_SC_APPTAG_CHECK] = "End-to-end Application Tag Check Error",
161 [NVME_SC_REFTAG_CHECK] = "End-to-end Reference Tag Check Error",
163 [NVME_SC_ACCESS_DENIED] = "Access Denied",
166 [NVME_SC_ANA_PERSISTENT_LOSS] = "Asymmetric Access Persistent Loss",
167 [NVME_SC_ANA_INACCESSIBLE] = "Asymmetric Access Inaccessible",
168 [NVME_SC_ANA_TRANSITION] = "Asymmetric Access Transition",
/linux/drivers/net/ipa/
H A Dipa_main.c1 // SPDX-License-Identifier: GPL-2.0
3 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
4 * Copyright (C) 2018-2024 Linaro Ltd.
51 * currently supported. Despite that, some resources--including routing
52 * tables and filter tables--are defined in this driver because they must
58 * well-defined communication layer between the AP subsystem and the IPA
101 * ipa_setup() - Set up IPA hardware
115 struct device *dev = ipa->dev; in ipa_setup()
118 ret = gsi_setup(&ipa->gsi); in ipa_setup()
127 command_endpoint = ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]; in ipa_setup()
[all …]
/linux/include/sound/
H A Dvx_core.h1 /* SPDX-License-Identifier: GPL-2.0-or-later */
45 int granularity; /* granularity */ member
59 int hbuf_size; /* H-buffer size in bytes */
75 /* low-level i/o */
122 /* VX-pocket */
149 /* low-level functions */
183 int audio_monitor[4]; /* playback hw-monitor level */
184 unsigned char audio_monitor_active[4]; /* playback hw-monitor mute/unmute */
216 return chip->ops->test_and_ack(chip); in vx_test_and_ack()
221 chip->ops->validate_irq(chip, enable); in vx_validate_irq()
[all …]
/linux/Documentation/dev-tools/kunit/
H A Dindex.rst1 .. SPDX-License-Identifier: GPL-2.0
4 KUnit - Linux Kernel Unit Testing
29 if built-in, or load as a module. KUnit automatically flags and reports
31 :doc:`KTAP (Kernel - Test Anything Protocol) format</dev-tools/ktap>`.
42 KUnit follows the white-box testing approach. The test has access to
44 restricted to things exposed to user-space.
53 --------
55 - Provides a framework for writing unit tests.
56 - Runs tests on any kernel architecture.
57 - Runs a test in milliseconds.
[all …]
/linux/drivers/net/ethernet/freescale/fman/
H A Dfman_sp.c1 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0-or-later
3 * Copyright 2008 - 2015 Freescale Semiconductor Inc.
20 for (i = 0; i < fm_ext_pools->num_of_pools_used; i++) { in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
22 buf_size = fm_ext_pools->ext_buf_pool[i].size; in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
25 * for direct access in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
27 sizes_array[fm_ext_pools->ext_buf_pool[i].id] = buf_size; in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
34 fm_ext_pools->ext_buf_pool[i].id; in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
41 for (k = i; k > j; k--) in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
43 ordered_array[k - 1]; in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
49 fm_ext_pools->ext_buf_pool[i].id; in fman_sp_set_buf_pools_in_asc_order_of_buf_sizes()
[all …]
/linux/tools/testing/selftests/kvm/
H A Dkvm_page_table_test.c1 // SPDX-License-Identifier: GPL-2.0
8 * page size have been pre-allocated on your system, if you are planning to
96 addr = p->guest_test_virt_mem; in guest_code()
107 * Before dirty logging, vCPUs concurrently access the first in guest_code()
114 for (i = 0; i < p->large_num_pages; i++) { in guest_code()
120 addr += p->large_page_size; in guest_code()
132 if (p->src_type == VM_MEM_SRC_ANONYMOUS) { in guest_code()
133 for (i = 0; i < p->host_num_pages; i++) { in guest_code()
135 addr += p->host_page_size; in guest_code()
140 for (i = 0; i < p->large_num_pages; i++) { in guest_code()
[all …]
/linux/tools/perf/Documentation/
H A Dperf-c2c.txt1 perf-c2c(1)
5 ----
6 perf-c2c - Shared Data C2C/HITM Analyzer.
9 --------
12 'perf c2c record' [<options>] \-- [<record command options>] <command>
16 -----------
27 required. See linkperf:perf-arm-spe[1] for a setup guide. Due to the
32 - memory address of the access
33 - type of the access (load and store details)
34 - latency (in cycles) of the load access
[all …]

12345678910