| /linux-6.8/Documentation/scheduler/ |
| D | sched-debug.rst | 20 -------------------------------------------------------------------
26 end of the address space is reached the scanner restarts from the beginning.
33 the higher the "scan size", the higher the scan rate.
35 Higher scan rates incur higher system overhead as page faults must be
36 trapped and potentially data must be migrated. However, the higher the scan
|
| /linux-6.8/fs/erofs/ |
| D | Kconfig | 1 # SPDX-License-Identifier: GPL-2.0-only
9 EROFS (Enhanced Read-Only File System) is a lightweight read-only
11 xattrs/data, chunk-based deduplication, multiple devices, etc.) for
12 scenarios which need high-performance read-only solutions, e.g.
13 smartphones with Android OS, LiveCDs and high-density hosts with
16 It also provides fixed-sized output compression support in order to
17 improve storage density as well as keep relatively higher compression
18 ratios and implements in-place decompression to reuse the file page
20 quite useful to ensure guaranteed end-to-end runtime decompression
83 Enable fixed-sized output compression for EROFS.
[all …]
|
| /linux-6.8/arch/arc/kernel/ |
| D | entry-arcv2.S | 1 /* SPDX-License-Identifier: GPL-2.0-only */
3 * ARCv2 ISA based core Low Level Intr/Traps/Exceptions(non-TLB) Handling
56 # End of fixed IRQs
58 .rept NR_CPU_IRQS - 8
81 # Note this disable is only for consistent book-keeping as further interrupts
84 # unless this one returns (or higher prio becomes pending in 2-prio scheme)
89 ; so a higher prio interrupt taken here won't clobber prev prio icause
96 END(handle_interrupt)
104 END(EV_SWI)
110 END(EV_DivZero)
[all …]
|
| /linux-6.8/arch/arm64/kernel/ |
| D | perf_callchain.c | 1 // SPDX-License-Identifier: GPL-2.0-only
47 * (towards higher addresses). in user_backtrace()
57 * The registers we're interested in are at the end of the variable
58 * length saved register structure. The fp points at the end of this
60 * (struct compat_frame_tail *)(xxx->fp)-1
92 * (towards higher addresses). in compat_user_backtrace()
98 return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1; in compat_user_backtrace()
110 perf_callchain_store(entry, regs->pc); in perf_callchain_user()
116 tail = (struct frame_tail __user *)regs->regs[29]; in perf_callchain_user()
118 while (entry->nr < entry->max_stack && in perf_callchain_user()
[all …]
|
| /linux-6.8/Documentation/trace/ |
| D | osnoise-tracer.rst | 5 In the context of high-performance computing (HPC), the Operating System
9 system. Moreover, hardware-related jobs can also cause noise, for example,
21 NMI or in the hardware itself. At the end of the period, hwlatd enables
32 source of interferences, increasing a per-cpu interference counter. The
38 hardware-related noise. In this way, osnoise can account for any
39 source of interference. At the end of the period, the osnoise tracer
44 -----
59 # _-----=> irqs-off
60 # / _----=> need-resched
61 # | / _---=> hardirq/softirq
[all …]
|
| /linux-6.8/Documentation/process/ |
| D | 8.Conclusion.rst | 9 top-level :ref:`process/howto.rst <process_howto>`; also read
10 :ref:`process/submitting-patches.rst <submittingpatches>`. Many internal
33 Rubini, and Greg Kroah-Hartman). Online at
49 https://www.kernel.org/pub/software/scm/git/docs/user-manual.html
55 Congratulations to anybody who has made it through this long-winded
59 In the end, it's the participation that matters. Any open source software
69 kernel. Getting code into the mainline is the key to higher code quality,
70 lower maintenance and distribution costs, a higher level of influence over
|
| /linux-6.8/tools/perf/pmu-events/arch/x86/graniterapids/ |
| D | pipeline.json | 48 "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
51 …"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon eve…
56 "BriefDescription": "Number of instructions retired. General Counter - architectural event",
60 …"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon eve…
72 …the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end re…
75 …-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution…
80 …"BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - archit…
82 …-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TM…
87 …n": "TMA slots available for an unhalted logical processor. General counter - architectural event",
90 …-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. Th…
[all …]
|
| /linux-6.8/include/linux/ |
| D | dim.h | 1 /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
24 ((ref) && (((100UL * abs((val) - (ref))) / (ref)) > 10))
28 * Take wrap-around and variable size into consideration.
30 #define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) \ argument
31 & (BIT_ULL(bits) - 1))
34 * struct dim_cq_moder - Structure for CQ moderation values.
50 * struct dim_sample - Structure for DIM sample data.
68 * struct dim_stats - Structure for DIM stats.
86 * struct dim - Main structure for dynamic interrupt moderation (DIM).
98 * @steps_right: Number of steps taken towards higher moderation
[all …]
|
| /linux-6.8/tools/testing/selftests/drivers/net/mlxsw/ |
| D | fib_offload.sh | 2 # SPDX-License-Identifier: GPL-2.0
65 num=$(ip -6 route show match ${pfx} | grep "offload" | wc -l)
67 if [ $num -eq $expected_num ]; then
79 ip -6 route add 2001:db8:3::/64 dev $spine_p1 metric 100
83 # Append an identical prefix route with an higher metric and check that
85 ip -6 route append 2001:db8:3::/64 dev $spine_p1 metric 200
93 ip -6 route append 2001:db8:3::/64 dev $spine_p1 metric 10
103 ip -6 route flush 2001:db8:3::/64 dev $spine_p1
104 ip -6 route add 2001:db8:3::/64 dev $spine_p2
109 ip -6 route flush 2001:db8:3::/64
[all …]
|
| /linux-6.8/arch/powerpc/platforms/powermac/ |
| D | pci.c | 1 // SPDX-License-Identifier: GPL-2.0-or-later
5 * Copyright (C) 2003-2005 Benjamin Herrenschmuidt (benh@kernel.crashing.org)
21 #include <asm/pci-bridge.h>
25 #include <asm/ppc-pci.h>
37 /* XXX Could be per-controller, but I don't think we risk anything by
60 static int __init fixup_one_level_bus_range(struct device_node *node, int higher) in fixup_one_level_bus_range() argument
62 for (; node; node = node->sibling) { in fixup_one_level_bus_range()
67 /* For PCI<->PCI bridges or CardBus bridges, we go down */ in fixup_one_level_bus_range()
68 class_code = of_get_property(node, "class-code", NULL); in fixup_one_level_bus_range()
72 bus_range = of_get_property(node, "bus-range", &len); in fixup_one_level_bus_range()
[all …]
|
| /linux-6.8/Documentation/mm/ |
| D | zsmalloc.rst | 7 never attempts higher order page allocation which is very likely to
9 (0-order) pages, it would suffer from very high fragmentation --
13 To overcome these issues, zsmalloc allocates a bunch of 0-order pages
15 pages act as a single higher-order page i.e. an object can span 0-order
21 worst case, page is incompressible and is thus stored "as-is" i.e. in
29 issues on 32-bit systems where the VA region for kernel space mappings
85 the number of 0-order pages to make a zspage
99 Each zspage can contain up to ZSMALLOC_CHAIN_SIZE physical (0-order) pages.
116 Size classes #95-99 are merged with size class #100. This means that when we
117 need to store an object of size, say, 1568 bytes, we end up using size class
[all …]
|
| D | page_tables.rst | 1 .. SPDX-License-Identifier: GPL-2.0
10 feature of all Unix-like systems as time went by. In 1985 the feature was
34 As you can see, with 4KB pages the page base address uses bits 12-31 of the
42 this single table were referred to as *PTE*:s - page table entries.
53 to mark large areas as unmapped at a higher level in the page table hierarchy.
55 Additionally, on modern CPUs, a higher level page table entry can point directly
57 megabytes or even gigabytes in a single high-level page table entry, taking
63 +-----+
65 +-----+
67 | +-----+
[all …]
|
| /linux-6.8/arch/arm/kernel/ |
| D | perf_callchain.c | 1 // SPDX-License-Identifier: GPL-2.0
16 * The registers we're interested in are at the end of the variable
17 * length saved register structure. The fp points at the end of this
19 * (struct frame_tail *)(xxx->fp)-1
54 * (towards higher addresses). in user_backtrace()
59 return buftail.fp - 1; in user_backtrace()
67 perf_callchain_store(entry, regs->ARM_pc); in perf_callchain_user()
69 if (!current->mm) in perf_callchain_user()
72 tail = (struct frame_tail __user *)regs->ARM_fp - 1; in perf_callchain_user()
74 while ((entry->nr < entry->max_stack) && in perf_callchain_user()
|
| /linux-6.8/Documentation/arch/arm64/ |
| D | memory.rst | 12 with the 4KB page configuration, allowing 39-bit (512GB) or 48-bit
14 64KB pages, only 2 levels of translation tables, allowing 42-bit (4TB)
24 mappings while the user pgd contains only user (non-global) mappings.
29 AArch64 Linux memory layout with 4KB pages + 4 levels (48-bit)::
31 Start End Size Use
32 -----------------------------------------------------------------------
46 AArch64 Linux memory layout with 64KB pages + 3 levels (52-bit with HW support)::
48 Start End Size Use
49 -----------------------------------------------------------------------
65 +--------+--------+--------+--------+--------+--------+--------+--------+
[all …]
|
| /linux-6.8/arch/mips/kernel/ |
| D | genex.S | 6 * Copyright (C) 1994 - 2000, 2001, 2003 Ralf Baechle
43 END(except_vec3_generic)
75 * load / store will be re-executed.
79 li k1, -4 # Is this ...
103 END(except_vec3_r4000)
127 /* end of rollback region (the region size must be power of two) */
132 END(__r4k_wait)
201 daddiu k1, %higher(irq_stack)
211 PTR_LI t1, ~(_THREAD_SIZE-1)
231 END(handle_int)
[all …]
|
| /linux-6.8/tools/perf/pmu-events/arch/x86/lunarlake/ |
| D | pipeline.json | 25 …-speculative execution path is known. The branch prediction unit (BPU) predicts the target address…
108 "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
111 …"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon eve…
125 "BriefDescription": "Number of instructions retired. General Counter - architectural event",
129 …"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon eve…
134 … because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forw…
152 …the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end re…
155 …-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution…
161 …"BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - archit…
163 …-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TM…
[all …]
|
| /linux-6.8/drivers/staging/greybus/ |
| D | gb-camera.h | 1 /* SPDX-License-Identifier: GPL-2.0 */
10 #include <linux/v4l2-mediabus.h>
18 * struct gb_camera_stream - Represents greybus camera stream.
26 * that all data between the Frame Start and Frame End packet for
40 * struct gb_camera_csi_params - CSI configuration parameters
50 * struct gb_camera_ops - Greybus camera operations, used by the Greybus camera
72 * returns its CSI-2 bus parameters in the 'csi_params'
76 * and higher than the IDs of all the previously submitted requests.
86 * frames. All queued capture requests with IDs higher than the returned
101 * struct gb_camera_module - Represents greybus camera module.
[all …]
|
| /linux-6.8/drivers/crypto/ |
| D | omap-aes.h | 1 /* SPDX-License-Identifier: GPL-2.0-only */
17 #define _calc_walked(inout) (dd->inout##_walk.offset - dd->inout##_sg->offset)
20 * OMAP TRM gives bitfields as start:end, where start is the higher bit
23 #define FLD_MASK(start, end) (((1 << ((start) - (end) + 1)) - 1) << (end)) argument
24 #define FLD_VAL(val, start, end) (((val) << (end)) & FLD_MASK(start, end)) argument
26 #define AES_REG_KEY(dd, x) ((dd)->pdata->key_ofs - \
28 #define AES_REG_IV(dd, x) ((dd)->pdata->iv_ofs + ((x) * 0x04))
30 #define AES_REG_CTRL(dd) ((dd)->pdata->ctrl_ofs)
50 #define AES_REG_DATA_N(dd, x) ((dd)->pdata->data_ofs + ((x) * 0x04))
53 #define AES_REG_REV(dd) ((dd)->pdata->rev_ofs)
[all …]
|
| /linux-6.8/mm/damon/ |
| D | core-test.h | 1 /* SPDX-License-Identifier: GPL-2.0 */
23 KUNIT_EXPECT_EQ(test, 1ul, r->ar.start); in damon_test_regions()
24 KUNIT_EXPECT_EQ(test, 2ul, r->ar.end); in damon_test_regions()
25 KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses); in damon_test_regions()
71 * access frequency of each region. In detail, it increases '->nr_accesses' of
73 * the aggregated information ('->nr_accesses' of each regions) to the result
74 * buffer. As a result of the flushing, the '->nr_accesses' of regions are
96 r->nr_accesses = accesses[it][ir]; in damon_test_aggregate()
97 r->nr_accesses_bp = accesses[it][ir] * 10000; in damon_test_aggregate()
106 /* '->nr_accesses' should be zeroed */ in damon_test_aggregate()
[all …]
|
| /linux-6.8/Documentation/tools/rtla/ |
| D | rtla-hwnoise.rst | 1 .. SPDX-License-Identifier: GPL-2.0
4 rtla-hwnoise
6 ------------------------------------------
7 Detect and quantify hardware-related noise
8 ------------------------------------------
22 of threads as a consequence, only non-maskable interrupts and hardware-related
38 In the example below, the **rtla hwnoise** tool is set to run on CPUs *1-7*
39 on a system with 8 cores/16 threads with hyper-threading enabled.
41 The tool is set to detect any noise higher than *one microsecond*,
43 end of the session::
[all …]
|
| /linux-6.8/arch/mips/cavium-octeon/executive/ |
| D | cvmx-pko.c | 7 * Copyright (c) 2003-2008 Cavium Networks
14 * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
21 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
26 ***********************license end**************************************/
34 #include <asm/octeon/cvmx-config.h>
35 #include <asm/octeon/cvmx-pko.h>
36 #include <asm/octeon/cvmx-helper.h>
64 return -1; in __cvmx_pko_int()
85 config.s.tail = (queue == (num_queues - 1)); in __cvmx_pko_iport_config()
95 (CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE - in __cvmx_pko_iport_config()
[all …]
|
| /linux-6.8/Documentation/block/ |
| D | bfq-iosched.rst | 5 BFQ is a proportional-share I/O scheduler, with some extra
6 low-latency capabilities. In addition to cgroups support (blkio or io
9 - BFQ guarantees a high system and application responsiveness, and a
10 low latency for time-sensitive applications, such as audio or video
12 - BFQ distributes bandwidth, and not just time, among processes or
19 goal, for a given device, is to achieve the maximum-possible
20 throughput at all times, then do switch off all low-latency heuristics
25 As every I/O scheduler, BFQ adds some overhead to per-I/O-request
27 single-lock-protected, per-request processing time of BFQ---i.e., the
29 completion hooks---is, e.g., 1.9 us on an Intel Core i7-2760QM@2.40GHz
[all …]
|
| /linux-6.8/Documentation/admin-guide/mm/damon/ |
| D | lru_sort.rst | 1 .. 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
9 (de)prioritization of pages on their LRU-lists for making LRU-lists a more
12 Where Proactive LRU-lists Sorting is Required?
15 As page-granularity access checking overhead could be significant on huge
23 Because DAMON can identify access patterns of best-effort accuracy while
24 inducing only user-specified range of overhead, proactively running
32 rates that higher than a user-specified threshold) and cold pages (pages of
34 user-specified threshold) using DAMON, and prioritizes hot pages while
[all …]
|
| /linux-6.8/arch/powerpc/mm/ |
| D | hugetlbpage.c | 7 * Based on the IA-32 version:
26 #include <asm/pte-walk.h>
33 #define PTE_T_ORDER (__builtin_ffs(sizeof(pte_basic_t)) - \
42 return __find_linux_pte(mm->pgd, addr, NULL, NULL); in huge_pte_offset()
56 num_hugepd = 1 << (pshift - pdshift); in __hugepte_alloc()
58 cachep = PGT_CACHE(pdshift - pshift); in __hugepte_alloc()
64 return -ENOMEM; in __hugepte_alloc()
73 return -ENOMEM; in __hugepte_alloc()
84 * We have multiple higher-level entries that point to the same in __hugepte_alloc()
87 * right higher-level entry without knowing if it's a hugepage or not. in __hugepte_alloc()
[all …]
|
| /linux-6.8/drivers/pci/pcie/ |
| D | Kconfig | 1 # SPDX-License-Identifier: GPL-2.0
10 support for Native Hot-Plug, Advanced Error Reporting, Power
46 to trigger various real hardware errors. Software-based
48 help of a user space helper tool aer-inject, which can be
50 https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/
69 (transaction layer end-to-end CRC checking).
85 Linux can modify this state in order to disable ASPM on known-bad
86 hardware or configurations and enable it when known-safe.
116 possible. This would result in higher power savings while staying in L1
|