Home
last modified time | relevance | path

Searched full:pages (Results 1 – 25 of 2207) sorted by relevance

12345678910>>...89

/linux/drivers/iommu/iommufd/
H A Dpages.c73 * allocation can hold about 26M of 4k pages and 13G of 2M pages in an
167 static void iopt_pages_add_npinned(struct iopt_pages *pages, size_t npages) in iopt_pages_add_npinned() argument
171 rc = check_add_overflow(pages->npinned, npages, &pages->npinned); in iopt_pages_add_npinned()
173 WARN_ON(rc || pages->npinned > pages->npages); in iopt_pages_add_npinned()
176 static void iopt_pages_sub_npinned(struct iopt_pages *pages, size_t npages) in iopt_pages_sub_npinned() argument
180 rc = check_sub_overflow(pages->npinned, npages, &pages->npinned); in iopt_pages_sub_npinned()
182 WARN_ON(rc || pages->npinned > pages->npages); in iopt_pages_sub_npinned()
185 static void iopt_pages_err_unpin(struct iopt_pages *pages, in iopt_pages_err_unpin() argument
193 iopt_pages_sub_npinned(pages, npages); in iopt_pages_err_unpin()
199 * covers a portion of the first and last pages in the range.
[all …]
/linux/net/ceph/
H A Dpagevec.c13 void ceph_release_page_vector(struct page **pages, int num_pages) in ceph_release_page_vector() argument
18 __free_pages(pages[i], 0); in ceph_release_page_vector()
19 kfree(pages); in ceph_release_page_vector()
24 * allocate a vector new pages
28 struct page **pages; in ceph_alloc_page_vector() local
31 pages = kmalloc_objs(*pages, num_pages, flags); in ceph_alloc_page_vector()
32 if (!pages) in ceph_alloc_page_vector()
35 pages[i] = __page_cache_alloc(flags); in ceph_alloc_page_vector()
36 if (pages[i] == NULL) { in ceph_alloc_page_vector()
37 ceph_release_page_vector(pages, i); in ceph_alloc_page_vector()
[all …]
/linux/Documentation/mm/
H A Dunevictable-lru.rst34 main memory will have over 32 million 4k pages in a single node. When a large
35 fraction of these pages are not evictable for any reason [see below], vmscan
37 of pages that are evictable. This can result in a situation where all CPUs are
41 The unevictable list addresses the following classes of unevictable pages:
51 The infrastructure may also be able to handle other conditions that make pages
104 lru_list enum element). The memory controller tracks the movement of pages to
108 not attempt to reclaim pages on the unevictable list. This has a couple of
111 (1) Because the pages are "hidden" from reclaim on the unevictable list, the
112 reclaim process can be more efficient, dealing only with pages that have a
115 (2) On the other hand, if too many of the pages charged to the control group
[all …]
/linux/Documentation/admin-guide/mm/
H A Dksm.rst18 which have been registered with it, looking for pages of identical
21 content). The amount of pages that KSM daemon scans in a single pass
25 KSM only merges anonymous (private) pages, never pagecache (file) pages.
26 KSM's merged pages were originally locked into kernel memory, but can now
27 be swapped out just like other user pages (but sharing is broken when they
45 to cancel that advice and restore unshared pages: whereupon KSM
55 cannot contain any pages which KSM could actually merge; even if
80 how many pages to scan before ksmd goes to sleep
95 specifies if pages from different NUMA nodes can be merged.
96 When set to 0, ksm merges only pages which physically reside
[all …]
H A Dzswap.rst8 Zswap is a lightweight compressed cache for swap pages. It takes pages that are
26 Zswap evicts pages from compressed cache on an LRU basis to the backing swap
40 When zswap is disabled at runtime it will stop storing pages that are
42 back into memory all of the pages stored in the compressed pool. The
43 pages stored in zswap will remain in the compressed pool until they are
45 pages out of the compressed pool, a swapoff on the swap device(s) will
46 fault back into memory all swapped out pages, including those in the
52 Zswap receives pages for compression from the swap subsystem and is able to
53 evict pages from its own compressed pool on an LRU basis and write them back to
60 pages are freed. The pool is not preallocated.
[all …]
H A Dconcepts.rst41 The physical system memory is divided into page frames, or pages. The
48 pages. These mappings are described by page tables that allow
53 addresses of actual pages used by the software. The tables at higher
54 levels contain physical addresses of the pages belonging to the lower
64 Huge Pages
75 Many modern CPU architectures allow mapping of the memory pages
77 it is possible to map 2M and even 1G pages using entries in the second
78 and the third level page tables. In Linux such pages are called
79 `huge`. Usage of huge pages significantly reduces pressure on TLB,
83 memory with the huge pages. The first one is `HugeTLB filesystem`, or
[all …]
H A Didle_page_tracking.rst8 The idle page tracking feature allows to track which memory pages are being
37 Only accesses to user memory pages are tracked. These are pages mapped to a
38 process address space, page cache and buffer pages, swap cache pages. For other
39 page types (e.g. SLAB pages) an attempt to mark a page idle is silently ignored,
40 and hence such pages are never reported idle.
42 For huge pages the idle flag is set only on the head page, so one has to read
43 ``/proc/kpageflags`` in order to correctly count idle huge pages.
50 That said, in order to estimate the amount of pages that are not used by a
53 1. Mark all the workload's pages as idle by setting corresponding bits in
54 ``/sys/kernel/mm/page_idle/bitmap``. The pages can be found by reading
[all …]
H A Dtranshuge.rst11 using huge pages for the backing of virtual memory with huge pages
51 increments of a power-of-2 number of pages. mTHP can back anonymous
66 collapses sequences of basic pages into huge pages of either PMD size
124 Transparent Huge Pages globally. This is because ``madvise(...,
126 PMD-sized huge pages unconditionally.
156 pages unless hugepages are immediately available. Clearly if we spend CPU
158 use hugepages later instead of regular pages. This isn't always
172 allocation failure and directly reclaim pages and compact
179 to reclaim pages and wake kcompactd to compact memory so that
181 of khugepaged to then install the THP pages later.
[all …]
/linux/drivers/gpu/drm/i915/gem/selftests/
H A Dhuge_gem_object.c12 struct sg_table *pages) in huge_free_pages() argument
18 for_each_sgt_page(page, sgt_iter, pages) { in huge_free_pages()
24 sg_free_table(pages); in huge_free_pages()
25 kfree(pages); in huge_free_pages()
34 struct sg_table *pages; in huge_get_pages() local
41 pages = kmalloc_obj(*pages, GFP); in huge_get_pages()
42 if (!pages) in huge_get_pages()
45 if (sg_alloc_table(pages, npages, GFP)) { in huge_get_pages()
46 kfree(pages); in huge_get_pages()
50 sg = pages->sgl; in huge_get_pages()
[all …]
/linux/io_uring/
H A Dmemmap.c18 static bool io_mem_alloc_compound(struct page **pages, int nr_pages, in io_mem_alloc_compound() argument
34 * can hold more pages than the region exposes. Account those too, in io_mem_alloc_compound()
50 pages[i] = page + i; in io_mem_alloc_compound()
58 struct page **pages; in io_pin_pages() local
74 pages = kvmalloc_objs(struct page *, nr_pages, GFP_KERNEL_ACCOUNT); in io_pin_pages()
75 if (!pages) in io_pin_pages()
79 pages); in io_pin_pages()
80 /* success, mapped all pages */ in io_pin_pages()
83 return pages; in io_pin_pages()
88 /* if we did partial map, release any pages w in io_pin_pages()
160 struct page **pages; io_region_pin_pages() local
182 struct page **pages; io_region_allocate_pages() local
[all...]
/linux/mm/
H A Dgup_test.c17 static void put_back_pages(unsigned int cmd, struct page **pages, in put_back_pages() argument
26 put_page(pages[i]); in put_back_pages()
32 unpin_user_pages(pages, nr_pages); in put_back_pages()
36 unpin_user_pages(pages, nr_pages); in put_back_pages()
39 put_page(pages[i]); in put_back_pages()
46 static void verify_dma_pinned(unsigned int cmd, struct page **pages, in verify_dma_pinned() argument
57 folio = page_folio(pages[i]); in verify_dma_pinned()
60 "pages[%lu] is NOT dma-pinned\n", i)) { in verify_dma_pinned()
66 "pages[%lu] is NOT pinnable but pinned\n", in verify_dma_pinned()
76 static void dump_pages_test(struct gup_test *gup, struct page **pages, in dump_pages_test() argument
[all …]
H A Dgup.c31 static inline void sanity_check_pinned_pages(struct page **pages, in sanity_check_pinned_pages() argument
38 * We only pin anonymous pages if they are exclusive. Once pinned, we in sanity_check_pinned_pages()
42 * We'd like to verify that our pinned anonymous pages are still mapped in sanity_check_pinned_pages()
49 for (; npages; npages--, pages++) { in sanity_check_pinned_pages()
50 struct page *page = *pages; in sanity_check_pinned_pages()
180 * Pages that were pinned via pin_user_pages*() must be released via either
182 * that such pages can be separately tracked and uniquely handled. In
263 * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
264 * @pages: array of pages to be maybe marked dirty, and definitely released.
265 * @npages: number of pages in the @pages array.
[all …]
/linux/drivers/media/pci/intel/ipu6/
H A Dipu6-dma.c23 struct page **pages; member
49 * Ensure that the allocated pages are zeroed, and that any data in __clear_buffer()
62 struct page **pages; in __alloc_buffer() local
65 pages = kvzalloc(array_size, GFP_KERNEL); in __alloc_buffer()
66 if (!pages) in __alloc_buffer()
74 pages[i] = alloc_pages(gfp, order); in __alloc_buffer()
75 while (!pages[i] && order) in __alloc_buffer()
76 pages[i] = alloc_pages(gfp, --order); in __alloc_buffer()
77 if (!pages[i]) in __alloc_buffer()
81 split_page(pages[i], order); in __alloc_buffer()
[all …]
/linux/fs/isofs/
H A Dcompress.c37 * to one zisofs block. Store the data in the @pages array with @pcount
42 struct page **pages, unsigned poffset, in zisofs_uncompress_block() argument
70 if (!pages[i]) in zisofs_uncompress_block()
72 memzero_page(pages[i], off, PAGE_SIZE - off); in zisofs_uncompress_block()
73 SetPageUptodate(pages[i]); in zisofs_uncompress_block()
123 if (pages[curpage]) { in zisofs_uncompress_block()
124 stream.next_out = kmap_local_page(pages[curpage]) in zisofs_uncompress_block()
176 if (pages[curpage]) { in zisofs_uncompress_block()
177 flush_dcache_page(pages[curpage]); in zisofs_uncompress_block()
178 SetPageUptodate(pages[curpage]); in zisofs_uncompress_block()
[all …]
/linux/drivers/xen/
H A Dxlate_mmu.c47 /* Break down the pages in 4KB chunk and call fn for each gfn */
48 static void xen_for_each_gfn(struct page **pages, unsigned nr_gfn, in xen_for_each_gfn() argument
57 page = pages[i / XEN_PFN_PER_PAGE]; in xen_for_each_gfn()
71 struct page **pages; member
99 struct page *page = info->pages[info->index++]; in remap_pte_fn()
148 struct page **pages) in xen_xlate_remap_gfn_array() argument
163 data.pages = pages; in xen_xlate_remap_gfn_array()
184 int nr, struct page **pages) in xen_xlate_unmap_gfn_range() argument
186 xen_for_each_gfn(pages, nr, unmap_gfn, NULL); in xen_xlate_unmap_gfn_range()
205 * xen_xlate_map_ballooned_pages - map a new set of ballooned pages
[all …]
H A Dunpopulated-alloc.c21 /* Pages to subtract from the memory count when setting balloon target. */
156 * xen_alloc_unpopulated_pages - alloc unpopulated pages
157 * @nr_pages: Number of pages
158 * @pages: pages returned
161 int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) in xen_alloc_unpopulated_pages() argument
169 * construct pages. in xen_alloc_unpopulated_pages()
172 return xen_alloc_ballooned_pages(nr_pages, pages); in xen_alloc_unpopulated_pages()
187 pages[i] = pg; in xen_alloc_unpopulated_pages()
196 pages[j]->zone_device_data = page_list; in xen_alloc_unpopulated_pages()
197 page_list = pages[j]; in xen_alloc_unpopulated_pages()
[all …]
/linux/drivers/staging/media/ipu7/
H A Dipu7-dma.c23 struct page **pages; member
49 * Ensure that the allocated pages are zeroed, and that any data in __clear_buffer()
62 struct page **pages; in __alloc_buffer() local
65 pages = kvzalloc(array_size, GFP_KERNEL); in __alloc_buffer()
66 if (!pages) in __alloc_buffer()
74 pages[i] = alloc_pages(gfp, order); in __alloc_buffer()
75 while (!pages[i] && order) in __alloc_buffer()
76 pages[i] = alloc_pages(gfp, --order); in __alloc_buffer()
77 if (!pages[i]) in __alloc_buffer()
81 split_page(pages[i], order); in __alloc_buffer()
[all …]
/linux/include/drm/ttm/
H A Dttm_tt.h44 * struct ttm_tt - This is a structure holding the pages, caching- and aperture
49 /** @pages: Array of pages backing the data. */
50 struct page **pages; member
56 * TTM_TT_FLAG_SWAPPED: Set by TTM when the pages have been unpopulated
58 * pages back in, and unset the flag. Drivers should in general never
61 * TTM_TT_FLAG_ZERO_ALLOC: Set if the pages will be zeroed on
64 * TTM_TT_FLAG_EXTERNAL: Set if the underlying pages were allocated
66 * TTM swapping out such pages. Also important is to prevent TTM from
67 * ever directly mapping these pages.
74 * still valid to use TTM to map the pages directly. This is useful when
[all …]
/linux/drivers/misc/
H A Dvmw_balloon.c8 * acts like a "balloon" that can be inflated to reclaim physical pages by
10 * freeing up the underlying machine pages so they can be allocated to
51 /* Maximum number of refused pages we accumulate during inflation cycle */
147 * ballooned pages (up to 512).
149 * pages that are about to be deflated from the
152 * for 2MB pages.
155 * pages.
240 struct list_head pages; member
315 * @batch_max_pages: maximum pages that can be locked/unlocked.
317 * Indicates the number of pages that the hypervisor can lock or unlock
[all …]
/linux/tools/perf/pmu-events/arch/x86/amdzen4/
H A Dmemory.json40 "BriefDescription": "L1 DTLB misses with L2 DTLB hits for 4k pages.",
46 … misses with L2 DTLB hits for coalesced pages. A coalesced page is a 16k page created from four ad…
52 "BriefDescription": "L1 DTLB misses with L2 DTLB hits for 2M pages.",
58 "BriefDescription": "L1 DTLB misses with L2 DTLB hits for 1G pages.",
64 …fDescription": "L1 DTLB misses with L2 DTLB misses (page-table walks are requested) for 4k pages.",
70 …able walks are requested) for coalesced pages. A coalesced page is a 16k page created from four ad…
76 …fDescription": "L1 DTLB misses with L2 DTLB misses (page-table walks are requested) for 2M pages.",
82 …fDescription": "L1 DTLB misses with L2 DTLB misses (page-table walks are requested) for 1G pages.",
123 …tion fetches that miss in both the L1 and L2 ITLBs (page-table walks are requested) for 4k pages.",
129 …tion fetches that miss in both the L1 and L2 ITLBs (page-table walks are requested) for 2M pages.",
[all …]
/linux/kernel/dma/
H A Dremap.c17 return area->pages; in dma_common_find_pages()
21 * Remaps an array of PAGE_SIZE pages into another vm_area.
24 void *dma_common_pages_remap(struct page **pages, size_t size, in dma_common_pages_remap() argument
29 vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT, in dma_common_pages_remap()
32 find_vm_area(vaddr)->pages = pages; in dma_common_pages_remap()
44 struct page **pages; in dma_common_contiguous_remap() local
48 pages = kvmalloc_objs(struct page *, count); in dma_common_contiguous_remap()
49 if (!pages) in dma_common_contiguous_remap()
52 pages[i] = page++; in dma_common_contiguous_remap()
53 vaddr = vmap(pages, count, VM_DMA_COHERENT, prot); in dma_common_contiguous_remap()
[all …]
/linux/Documentation/arch/x86/
H A Dsgx.rst37 SGX utilizes an *Enclave Page Cache (EPC)* to store pages that are associated
39 Unlike pages used for regular memory, pages can only be accessed from outside of
56 Regular EPC pages contain the code and data of an enclave.
59 Thread Control Structure pages define the entry points to an enclave and
63 Version Array pages contain 512 slots, each of which can contain a version
69 The processor tracks EPC pages in a hardware metadata structure called the
95 pages and establish enclave page permissions.
108 adding and removing of enclave pages. When an enclave accesses an address
151 use since the reset, enclave pages may be in an inconsistent state. This might
153 reinitializes all enclave pages so that they can be allocated and re-used.
[all …]
/linux/drivers/media/common/videobuf2/
H A Dframe_vector.c16 * @nr_frames: number of pages / pfns from start to map
18 * @vec: structure which receives pages / pfns of the addresses mapped.
22 * with page frame numbers or page pointers to corresponding pages (choice
24 * belongs to a normal vma, the function grabs reference to each of the pages
29 * The function returns number of pages mapped which may be less than
72 * put_vaddr_frames() - drop references to pages if get_vaddr_frames() acquired
76 * Drop references to pages if get_vaddr_frames() acquired them. We also
82 struct page **pages; in put_vaddr_frames() local
86 pages = frame_vector_pages(vec); in put_vaddr_frames()
89 * get_vaddr_frames() got pages but vec was later converted to pfns. in put_vaddr_frames()
[all …]
/linux/drivers/staging/media/ipu3/
H A Dipu3-dmamap.c20 static void imgu_dmamap_free_buffer(struct page **pages, in imgu_dmamap_free_buffer() argument
26 __free_page(pages[count]); in imgu_dmamap_free_buffer()
27 kvfree(pages); in imgu_dmamap_free_buffer()
36 struct page **pages; in imgu_dmamap_alloc_buffer() local
42 pages = kvmalloc_objs(*pages, count); in imgu_dmamap_alloc_buffer()
44 if (!pages) in imgu_dmamap_alloc_buffer()
72 imgu_dmamap_free_buffer(pages, i << PAGE_SHIFT); in imgu_dmamap_alloc_buffer()
77 pages[i++] = page++; in imgu_dmamap_alloc_buffer()
80 return pages; in imgu_dmamap_alloc_buffer()
100 struct page **pages; in imgu_dmamap_alloc() local
[all …]
/linux/drivers/misc/bcm-vk/
H A Dbcm_vk_sg.c57 /* Calculate number of pages */ in bcm_vk_dma_alloc()
62 /* Allocate DMA pages */ in bcm_vk_dma_alloc()
63 dma->pages = kmalloc_objs(struct page *, dma->nr_pages); in bcm_vk_dma_alloc()
64 if (!dma->pages) in bcm_vk_dma_alloc()
67 dev_dbg(dev, "Alloc DMA Pages [0x%llx+0x%x => %d pages]\n", in bcm_vk_dma_alloc()
72 /* Get user pages into memory */ in bcm_vk_dma_alloc()
76 dma->pages); in bcm_vk_dma_alloc()
101 /* Map all pages into DMA */ in bcm_vk_dma_alloc()
105 dma->pages[0], in bcm_vk_dma_alloc()
111 __free_page(dma->pages[0]); in bcm_vk_dma_alloc()
[all …]

12345678910>>...89