| /Linux-v5.10/Documentation/vm/ |
| D | frontswap.rst | 7 Frontswap provides a "transcendent memory" interface for swap pages.
9 swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
20 a "backing" store for a swap device. The storage is assumed to be
31 with the specified swap device number (aka "type"). A "store" will
37 associated with the swap type (e.g., like swapoff) and notify the "device"
38 to refuse further stores with that swap type.
42 to swap out a page, it first attempts to use frontswap. If the store returns
46 page can be written to swap as usual.
50 in swap device writes is lost (and also a non-trivial performance advantage)
61 frontswap can be measured (across all swap devices) with:
[all …]
|
| D | swap_numa.rst | 4 Automatically bind swap device to numa node
7 If the system has more than one swap device and swap device has the node
8 information, we can make use of this information to decide which swap
15 Swap device has priority and that decides the order of it to be used. To make
17 for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and
24 Then node 0 will use the two swap devices in the order of swapA then swapB and
25 node 1 will use the two swap devices in the order of swapB then swapA. Note
28 A more complex example on a 4 node machine. Assume 6 swap devices are going to
31 The way to swap them on is the same as above::
44 swapA and swapB will be used in a round robin mode before any other swap device.
[all …]
|
| D | zswap.rst | 10 Zswap is a lightweight compressed cache for swap pages. It takes pages that are
13 for potentially reduced swap I/O. This trade-off can also result in a
15 faster than reads from a swap device.
28 dramatically reduce their swap I/O pressure, avoiding heavy handed I/O
31 * Users with SSDs as swap devices can extend the life of the device by
34 Zswap evicts pages from compressed cache on an LRU basis to the backing swap
53 pages out of the compressed pool, a swapoff on the swap device(s) will
62 the backing swap device in the case that the compressed pool is full.
83 When a swap page is passed from frontswap to zswap, zswap maintains a mapping
84 of the swap entry, a combination of the swap type and swap offset, to the zpool
[all …]
|
| /Linux-v5.10/Documentation/power/ |
| D | swsusp-and-swap-files.rst | 2 Using swap files with software suspend (swsusp)
7 The Linux kernel handles swap files almost in the same way as it handles swap
8 partitions and there are only two differences between these two types of swap
10 (1) swap files need not be contiguous,
11 (2) the header of a swap file is not in the first block of the partition that
13 already taken care of by the swap-handling code, but (2) has to be taken into
16 In principle the location of a swap file's header may be determined with the
18 filesystem holding the swap file to be mounted, and if this filesystem is
20 identify a swap file swsusp uses the name of the partition that holds the file
21 and the offset from the beginning of the partition at which the swap file's
[all …]
|
| D | swsusp.rst | 2 Swap suspend
34 Swap partition:
38 Swap file:
51 - If you would like to write hibernation image to swap and then suspend
102 powerdowns. You must explicitly specify the swap partition to resume from with
185 encryption) and arbitrary backends for writing the image (eg to swap
224 * SUSPEND all but swap device and parents
227 * SUSPEND swap device and parents
230 Oh no, that does not work, if swap device or its parents uses DMA,
233 * SUSPEND all but swap device and parents
[all …]
|
| D | userland-swsusp.rst | 76 return the amount of available swap in bytes
81 allocate a swap page from the resume partition
83 will contain the swap page offset if the call is successful)
86 free all swap pages allocated by
91 units) from the beginning of the partition at which the swap header is
94 containing the resume device specification and the offset); for swap
96 swap files (see Documentation/power/swsusp-and-swap-files.rst for
130 and all swap pages allocated with SNAPSHOT_ALLOC_SWAP_PAGE (if any).
137 snapshot image from/to the kernel will use a swap partition, called the resume
138 partition, or a swap file as storage space (if a swap file is used, the resume
|
| D | swsusp-dmcrypt.rst | 17 the swap device(s) and the boot partition which may contain a mini
21 At this point you want to encrypt your swap, too. Still you want to
27 swap device.
30 a way that the swap device you suspend to/resume from has
33 to always set up this swap device first with dmsetup, so that
56 card contains at least the encrypted swap setup in a file
67 initrd that allows you to resume from encrypted swap and that
126 pcmcia flash disk. If this succeeds we need to reset the swap
133 Otherwise we just remove the encrypted swap device and leave it to the
|
| /Linux-v5.10/mm/ |
| D | swap_state.c | 6 * Swap reorganised 29.12.95, Stephen Tweedie
13 #include <linux/swap.h>
81 /* Avoid get_swap_device() to warn for bad swap entry */ in total_swapcache_pages()
101 printk("%lu pages in swap cache\n", total_swapcache_pages()); in show_swap_cache_info()
102 printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n", in show_swap_cache_info()
105 printk("Free swap = %ldkB\n", in show_swap_cache_info()
107 printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10)); in show_swap_cache_info()
181 * been verified to be in the swap cache.
210 * add_to_swap - allocate swap space for a page
211 * @page: page we want to move to swap
[all …]
|
| D | swapfile.c | 6 * Swap reorganised 29.12.95, Stephen Tweedie
16 #include <linux/swap.h>
56 * Some modules use swappable objects and may try to swap them out under
58 * check to see if any swap space is available.
65 static const char Bad_file[] = "Bad swap file entry ";
66 static const char Unused_file[] = "Unused swap file entry ";
67 static const char Bad_offset[] = "Bad swap offset entry ";
68 static const char Unused_offset[] = "Unused swap offset entry ";
115 /* Reclaim the swap entry anyway if possible */
118 * Reclaim the swap entry if there are no more mappings of the
[all …]
|
| D | swap_slots.c | 3 * Manage cache of swap slots to be used for and returned from
4 * swap.
10 * We allocate the swap slots from the global pool and put
21 * The swap entry allocated is marked with SWAP_HAS_CACHE
25 * The swap slots cache is protected by a mutex instead of
42 /* Serialize swap slots cache enable/disable operations */
209 * a swap device; in __drain_swap_slots_cache()
210 * 2) disabling of swap slot cache, when we run low in __drain_swap_slots_cache()
211 * on swap slots when allocating memory and need in __drain_swap_slots_cache()
212 * to return swap slots to global pool. in __drain_swap_slots_cache()
[all …]
|
| D | page_io.c | 7 * Swap reorganised 29.12.95,
10 * Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie
18 #include <linux/swap.h>
55 * We failed to write the page out to swap-space. in end_swap_bio_write()
63 pr_alert("Write-error on swap-device (%u:%u:%llu)\n", in end_swap_bio_write()
79 * There is no guarantee that the page is in swap cache - the software in swap_slot_free_notify()
92 * The swap subsystem performs lazy swap slot freeing, in swap_slot_free_notify()
96 * This is good for real swap storage because we can in swap_slot_free_notify()
98 * if an SSD is used as the as swap device. in swap_slot_free_notify()
99 * But if in-memory swap device (eg zram) is used, in swap_slot_free_notify()
[all …]
|
| D | frontswap.c | 14 #include <linux/swap.h>
37 * a result, the swap subsystem will always write the page to swap, in
39 * there is no direct reduction in swap writes, but a frontswap backend
84 * _after_ the swap system has been activated, we have chokepoints
93 * swapoff) is again guarded by the swap subsystem.
98 * The time between the backend being registered and the swap file system
130 /* the new ops needs to know the currently active swap devices */ in frontswap_register_ops()
153 * On the very unlikely chance that a swap device was added or in frontswap_register_ops()
188 * Called when a swap device is swapon'd.
240 * swaptype and offset. Page must be locked and in the swap cache.
[all …]
|
| D | Kconfig | 432 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP
434 Swap transparent huge pages in one piece, without splitting.
435 XXX: For now, swap cluster backing transparent huge page
471 bool "Enable frontswap to cache swap pages if tmem is present"
472 depends on SWAP
475 of a "backing" store for a swap device. The data is stored into
479 a significant swap I/O reduction may be achieved. When none is
482 and swap data is stored as normal on the matching swap device.
541 bool "Compressed cache for swap pages (EXPERIMENTAL)"
545 A lightweight compressed cache for swap pages. It takes
[all …]
|
| /Linux-v5.10/include/linux/ |
| D | swap.h | 23 #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */
26 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */
27 #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */
42 * be swapped to. The swap type and the offset into that swap type are
51 * Use some of the swap files numbers for other purposes. This
99 * Magic header for a swap area. The first part of the union is
100 * what the swap magic looks like for the old (limited to 128MB)
101 * swap area format, the second part of the union adds - in the
105 * Having the magic at the end of the PAGE_SIZE makes detecting swap
113 char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
[all …]
|
| /Linux-v5.10/Documentation/ABI/testing/ |
| D | sysfs-kernel-mm-swap | 1 What: /sys/kernel/mm/swap/
6 What: /sys/kernel/mm/swap/vma_ra_enabled
9 Description: Enable/disable VMA based swap readahead.
11 If set to true, the VMA based swap readahead algorithm
13 VMA, and the global swap readahead algorithm will be
15 false, the global swap readahead algorithm will be
|
| /Linux-v5.10/arch/arm/vdso/ |
| D | vdsomunge.c | 101 static Elf32_Word read_elf_word(Elf32_Word word, bool swap) in read_elf_word() argument
103 return swap ? swab32(word) : word; in read_elf_word()
106 static Elf32_Half read_elf_half(Elf32_Half half, bool swap) in read_elf_half() argument
108 return swap ? swab16(half) : half; in read_elf_half()
111 static void write_elf_word(Elf32_Word val, Elf32_Word *dst, bool swap) in write_elf_word() argument
113 *dst = swap ? swab32(val) : val; in write_elf_word()
125 bool swap; in main() local
159 swap = inhdr->e_ident[EI_DATA] != HOST_ORDER; in main()
161 if (read_elf_half(inhdr->e_type, swap) != ET_DYN) in main()
164 if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) in main()
[all …]
|
| /Linux-v5.10/drivers/net/wireless/ath/ath10k/ |
| D | swap.c | 6 /* This file has implementation for code swap logic. With code swap feature,
28 /* Parse swap bin and copy the content to host allocated memory. in ath10k_swap_code_seg_fill()
47 ath10k_err(ar, "refusing an invalid swap file\n"); in ath10k_swap_code_seg_fill()
64 ath10k_err(ar, "failed to parse invalid swap file\n"); in ath10k_swap_code_seg_fill()
98 ath10k_err(ar, "refusing code swap bin because it is too big %zu > %d\n", in ath10k_swap_code_seg_alloc()
133 ath10k_dbg(ar, ATH10K_DBG_BOOT, "boot found firmware code swap binary\n"); in ath10k_swap_code_seg_configure()
141 ath10k_err(ar, "failed to write Code swap segment information (%d)\n", in ath10k_swap_code_seg_configure()
178 ath10k_err(ar, "failed to allocate fw code swap segment\n"); in ath10k_swap_code_seg_init()
186 ath10k_warn(ar, "failed to initialize fw code swap segment: %d\n", in ath10k_swap_code_seg_init()
|
| /Linux-v5.10/fs/iomap/ |
| D | swapfile.c | 10 #include <linux/swap.h>
24 * Collect physical extents for this swap file. Physical extents reported to
25 * the swap code must be trimmed to align to a page boundary. The logical
27 * page numbers of the swap device to the physical page-aligned extents.
52 * Calculate how much swap space we're adding; the first page contains in iomap_swapfile_add_extent()
53 * the swap header and doesn't count. The mm still wants that first in iomap_swapfile_add_extent()
74 * Accumulate iomaps for this swap file. We have to accumulate iomaps because
75 * swap only cares about contiguous page-aligned physical extents and makes no
109 /* Only one bdev per swap file. */ in iomap_swapfile_activate_actor()
132 * Iterate a swap file's iomaps to construct physical extents that can be
|
| /Linux-v5.10/Documentation/admin-guide/cgroup-v1/ |
| D | memory.rst | 46 - accounting anonymous pages, file caches, swap caches usage and limiting them.
48 - optionally, memory+swap usage can be accounted and limited.
69 memory.memsw.usage_in_bytes show current usage for memory+Swap
72 memory.memsw.limit_in_bytes set/show limit of memory+Swap usage
74 memory.memsw.failcnt show the number of memory+Swap hits limits
76 memory.memsw.max_usage_in_bytes show max memory+Swap usage recorded
205 Since page's memcg recorded into swap whatever memsw enabled, the page will
225 2.4 Swap Extension
228 Swap usage is always recorded for each of cgroup. Swap Extension allows you to
236 memsw means memory+swap. Usage of memory+swap is limited by
[all …]
|
| D | memcg_test.rst | 47 Called when swp_entry's refcnt goes down to 0. A charge against swap
74 4.1 Swap-in.
75 At swap-in, the page is taken from swap-cache. There are 2 cases.
81 4.2 Swap-out.
82 At swap-out, typical state transition is below.
84 (a) add to swap cache. (marked as SwapCache)
88 (c) write back to swap.
89 (d) delete from swap cache. (remove from SwapCache)
121 - Both on radix-tree and SwapCache. This happens at swap-in
122 and swap-out,
[all …]
|
| /Linux-v5.10/kernel/power/ |
| D | user.c | 16 #include <linux/swap.h>
32 int swap; member
72 data->swap = swap_type_of(swsusp_resume_device, 0); in snapshot_open()
83 data->swap = -1; in snapshot_open()
114 free_all_swap_pages(data->swap); in snapshot_release()
232 data->swap = swap_type_of(swdev, offset); in snapshot_set_swap_area()
233 if (data->swap < 0) in snapshot_set_swap_area()
344 size = count_swap_pages(data->swap, 1); in snapshot_ioctl()
350 if (data->swap < 0 || data->swap >= MAX_SWAPFILES) { in snapshot_ioctl()
354 offset = alloc_swapdev_block(data->swap); in snapshot_ioctl()
[all …]
|
| D | swap.c | 3 * linux/kernel/power/swap.c
6 * and writing it to a swap partition.
23 #include <linux/swap.h>
48 * The swap map is a data structure used for keeping track of each page
49 * written to a swap partition. It consists of many swap_map_page
50 * structures that contain each an array of MAP_PAGE_ENTRIES swap entries.
51 * These structures are stored on the swap and linked together with the
54 * The swap map is created during suspend. The swap map pages are
91 * The swap_map_handle structure is used for handling swap in
119 * swap pages, so that they can be freed in case of an error.
[all …]
|
| /Linux-v5.10/arch/sh/include/mach-se/mach/ |
| D | mrshpc.h | 25 /* common mode & bus width 16bit SWAP = 1*/ in mrshpc_setup_windows()
28 /* common mode & bus width 16bit SWAP = 0*/ in mrshpc_setup_windows()
34 /* attribute mode & bus width 16bit SWAP = 1*/ in mrshpc_setup_windows()
37 /* attribute mode & bus width 16bit SWAP = 0*/ in mrshpc_setup_windows()
44 __raw_writew(0x0a00, MRSHPC_IOWCR2); /* bus width 16bit SWAP = 1*/ in mrshpc_setup_windows()
46 __raw_writew(0x0200, MRSHPC_IOWCR2); /* bus width 16bit SWAP = 0*/ in mrshpc_setup_windows()
|
| /Linux-v5.10/drivers/gpu/drm/xlnx/ |
| D | zynqmp_disp.c | 83 * @swap: Flag to swap R & B for RGB formats, and U & V for YUV formats
90 bool swap; member
262 .swap = true,
267 .swap = false,
272 .swap = false,
277 .swap = true,
282 .swap = false,
287 .swap = true,
292 .swap = false,
297 .swap = true,
[all …]
|
| /Linux-v5.10/include/linux/mtd/ |
| D | cfi_endian.h | 29 #define cpu_to_cfi16(map, x) _cpu_to_cfi(16, (map)->swap, (x))
30 #define cpu_to_cfi32(map, x) _cpu_to_cfi(32, (map)->swap, (x))
31 #define cpu_to_cfi64(map, x) _cpu_to_cfi(64, (map)->swap, (x))
32 #define cfi16_to_cpu(map, x) _cfi_to_cpu(16, (map)->swap, (x))
33 #define cfi32_to_cpu(map, x) _cfi_to_cpu(32, (map)->swap, (x))
34 #define cfi64_to_cpu(map, x) _cfi_to_cpu(64, (map)->swap, (x))
|
