linux/mm/highmem.c

826 lines
20 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* High memory handling common code and variables.
*
* (C) 1999 Andrea Arcangeli, SuSE GmbH, andrea@suse.de
* Gerhard Wichert, Siemens AG, Gerhard.Wichert@pdb.siemens.de
*
*
* Redesigned the x86 32-bit VM architecture to deal with
* 64-bit physical space. With current x86 CPUs this
* means up to 64 Gigabytes physical RAM.
*
* Rewrote high memory support to move the page cache into
* high memory. Implemented permanent (schedulable) kmaps
* based on Linus' idea.
*
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
*/
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
#include <linux/kgdb.h>
#include <asm/tlbflush.h>
#include <linux/vmalloc.h>
#ifdef CONFIG_KMAP_LOCAL
static inline int kmap_local_calc_idx(int idx)
{
return idx + KM_MAX_IDX * smp_processor_id();
}
#ifndef arch_kmap_local_map_idx
#define arch_kmap_local_map_idx(idx, pfn) kmap_local_calc_idx(idx)
#endif
#endif /* CONFIG_KMAP_LOCAL */
/*
* Virtual_count is not a pure "count".
* 0 means that it is not mapped, and has not been mapped
* since a TLB flush - it is usable.
* 1 means that there are no users, but it has been mapped
* since the last TLB flush - so we can't use it.
* n means that there are (n-1) current users of it.
*/
#ifdef CONFIG_HIGHMEM
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
/*
* Architecture with aliasing data cache may define the following family of
* helper functions in its asm/highmem.h to control cache color of virtual
* addresses where physical memory pages are mapped by kmap.
*/
#ifndef get_pkmap_color
/*
* Determine color of virtual address where the page should be mapped.
*/
static inline unsigned int get_pkmap_color(struct page *page)
{
return 0;
}
#define get_pkmap_color get_pkmap_color
/*
* Get next index for mapping inside PKMAP region for page with given color.
*/
static inline unsigned int get_next_pkmap_nr(unsigned int color)
{
static unsigned int last_pkmap_nr;
last_pkmap_nr = (last_pkmap_nr + 1) & LAST_PKMAP_MASK;
return last_pkmap_nr;
}
/*
* Determine if page index inside PKMAP region (pkmap_nr) of given color
* has wrapped around PKMAP region end. When this happens an attempt to
* flush all unused PKMAP slots is made.
*/
static inline int no_more_pkmaps(unsigned int pkmap_nr, unsigned int color)
{
return pkmap_nr == 0;
}
/*
* Get the number of PKMAP entries of the given color. If no free slot is
* found after checking that many entries, kmap will sleep waiting for
* someone to call kunmap and free PKMAP slot.
*/
static inline int get_pkmap_entries_count(unsigned int color)
{
return LAST_PKMAP;
}
/*
* Get head of a wait queue for PKMAP entries of the given color.
* Wait queues for different mapping colors should be independent to avoid
* unnecessary wakeups caused by freeing of slots of other colors.
*/
static inline wait_queue_head_t *get_pkmap_wait_queue_head(unsigned int color)
{
static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
return &pkmap_map_wait;
}
#endif
unsigned long __nr_free_highpages(void)
{
unsigned long pages = 0;
struct zone *zone;
for_each_populated_zone(zone) {
if (is_highmem(zone))
pages += zone_page_state(zone, NR_FREE_PAGES);
Create the ZONE_MOVABLE zone The following 8 patches against 2.6.20-mm2 create a zone called ZONE_MOVABLE that is only usable by allocations that specify both __GFP_HIGHMEM and __GFP_MOVABLE. This has the effect of keeping all non-movable pages within a single memory partition while allowing movable allocations to be satisfied from either partition. The patches may be applied with the list-based anti-fragmentation patches that groups pages together based on mobility. The size of the zone is determined by a kernelcore= parameter specified at boot-time. This specifies how much memory is usable by non-movable allocations and the remainder is used for ZONE_MOVABLE. Any range of pages within ZONE_MOVABLE can be released by migrating the pages or by reclaiming. When selecting a zone to take pages from for ZONE_MOVABLE, there are two things to consider. First, only memory from the highest populated zone is used for ZONE_MOVABLE. On the x86, this is probably going to be ZONE_HIGHMEM but it would be ZONE_DMA on ppc64 or possibly ZONE_DMA32 on x86_64. Second, the amount of memory usable by the kernel will be spread evenly throughout NUMA nodes where possible. If the nodes are not of equal size, the amount of memory usable by the kernel on some nodes may be greater than others. By default, the zone is not as useful for hugetlb allocations because they are pinned and non-migratable (currently at least). A sysctl is provided that allows huge pages to be allocated from that zone. This means that the huge page pool can be resized to the size of ZONE_MOVABLE during the lifetime of the system assuming that pages are not mlocked. Despite huge pages being non-movable, we do not introduce additional external fragmentation of note as huge pages are always the largest contiguous block we care about. Credit goes to Andy Whitcroft for catching a large variety of problems during review of the patches. This patch creates an additional zone, ZONE_MOVABLE. This zone is only usable by allocations which specify both __GFP_HIGHMEM and __GFP_MOVABLE. Hot-added memory continues to be placed in their existing destination as there is no mechanism to redirect them to a specific zone. [y-goto@jp.fujitsu.com: Fix section mismatch of memory hotplug related code] [akpm@linux-foundation.org: various fixes] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Cc: William Lee Irwin III <wli@holomorphy.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:12 +08:00
}
return pages;
}
mm/highmem: reimplement totalhigh_pages() by walking zones Patch series "mm/highmem: don't track highmem pages manually". Let's remove highmem special-casing from adjust_managed_page_count(), to result in less confusion why memblock manually adjusts totalram_pages, and __free_pages_core() only adjusts the zone's managed pages -- what about the highmem pages that adjust_managed_page_count() updates? Now, we only maintain totalram_pages and a zone's managed pages independent of highmem support. We can derive the number of highmem pages simply by looking at the relevant zone's managed pages. I don't think there is any particular fast path that needs a maximum-efficient totalhigh_pages() implementation. Note that highmem memory is currently initialized using free_highmem_page()->free_reserved_page(), not __free_pages_core(). In the future we might want to also use __free_pages_core() to initialize highmem memory, to make that less special, and consider moving totalram_pages updates into __free_pages_core() [1], so we can just use adjust_managed_page_count() in there as well. Booting a simple kernel in QEMU reveals no highmem accounting change: Before: Memory: 3095448K/3145208K available (14802K kernel code, 2073K rwdata, 5000K rodata, 740K init, 556K bss, 49760K reserved, 0K cma-reserved, 2244488K highmem) After: Memory: 3095276K/3145208K available (14802K kernel code, 2073K rwdata, 5000K rodata, 740K init, 556K bss, 49932K reserved, 0K cma-reserved, 2244488K highmem) [1] https://lkml.kernel.org/r/20240601133402.2675-1-richard.weiyang@gmail.com This patch (of 2): Can we get rid of the highmem ifdef in adjust_managed_page_count()? Likely yes: we don't have that many totalhigh_pages() users, and they all don't seem to be very performance critical. So let's implement totalhigh_pages() like nr_free_highpages(), collecting information from all zones. This is now similar to what we do in si_meminfo_node() to collect the per-node highmem page count. In the common case (single node, 3-4 zones), we really shouldn't care. We could optimize a bit further (only walk ZONE_HIGHMEM and ZONE_MOVABLE if required), but there doesn't seem a real need for that. [david@redhat.com: fix build bot complaint] Link: https://lkml.kernel.org/r/b57e5bc4-eb72-40e3-add4-57dfa6e03df6@redhat.com Link: https://lkml.kernel.org/r/20240607083711.62833-1-david@redhat.com Link: https://lkml.kernel.org/r/20240607083711.62833-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Wei Yang <richard.weiyang@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-06-07 16:37:10 +08:00
unsigned long __totalhigh_pages(void)
{
unsigned long pages = 0;
struct zone *zone;
for_each_populated_zone(zone) {
if (is_highmem(zone))
pages += zone_managed_pages(zone);
}
return pages;
}
EXPORT_SYMBOL(__totalhigh_pages);
static int pkmap_count[LAST_PKMAP];
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
pte_t *pkmap_page_table;
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
/*
* Most architectures have no use for kmap_high_get(), so let's abstract
* the disabling of IRQ out of the locking in that case to save on a
* potential useless overhead.
*/
#ifdef ARCH_NEEDS_KMAP_HIGH_GET
#define lock_kmap() spin_lock_irq(&kmap_lock)
#define unlock_kmap() spin_unlock_irq(&kmap_lock)
#define lock_kmap_any(flags) spin_lock_irqsave(&kmap_lock, flags)
#define unlock_kmap_any(flags) spin_unlock_irqrestore(&kmap_lock, flags)
#else
#define lock_kmap() spin_lock(&kmap_lock)
#define unlock_kmap() spin_unlock(&kmap_lock)
#define lock_kmap_any(flags) \
do { spin_lock(&kmap_lock); (void)(flags); } while (0)
#define unlock_kmap_any(flags) \
do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
#endif
struct page *__kmap_to_page(void *vaddr)
{
unsigned long base = (unsigned long) vaddr & PAGE_MASK;
struct kmap_ctrl *kctrl = &current->kmap_ctrl;
unsigned long addr = (unsigned long)vaddr;
int i;
/* kmap() mappings */
if (WARN_ON_ONCE(addr >= PKMAP_ADDR(0) &&
addr < PKMAP_ADDR(LAST_PKMAP)))
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 23:15:45 +08:00
return pte_page(ptep_get(&pkmap_page_table[PKMAP_NR(addr)]));
/* kmap_local_page() mappings */
if (WARN_ON_ONCE(base >= __fix_to_virt(FIX_KMAP_END) &&
base < __fix_to_virt(FIX_KMAP_BEGIN))) {
for (i = 0; i < kctrl->idx; i++) {
unsigned long base_addr;
int idx;
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
base_addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
if (base_addr == base)
return pte_page(kctrl->pteval[i]);
}
}
return virt_to_page(vaddr);
}
EXPORT_SYMBOL(__kmap_to_page);
static void flush_all_zero_pkmaps(void)
{
int i;
int need_flush = 0;
flush_cache_kmaps();
for (i = 0; i < LAST_PKMAP; i++) {
struct page *page;
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 23:15:45 +08:00
pte_t ptent;
/*
* zero means we don't have anything to do,
* >1 means that it is still in use. Only
* a count of 1 means that it is free but
* needs to be unmapped
*/
if (pkmap_count[i] != 1)
continue;
pkmap_count[i] = 0;
/* sanity check */
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 23:15:45 +08:00
ptent = ptep_get(&pkmap_page_table[i]);
BUG_ON(pte_none(ptent));
/*
* Don't need an atomic fetch-and-clear op here;
* no-one has the page mapped, and cannot get at
* its virtual address (and hence PTE) without first
* getting the kmap_lock (which is held here).
* So no dangers, even with speculative execution.
*/
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 23:15:45 +08:00
page = pte_page(ptent);
pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]);
set_page_address(page, NULL);
need_flush = 1;
}
if (need_flush)
flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
}
void __kmap_flush_unused(void)
{
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
lock_kmap();
flush_all_zero_pkmaps();
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
unlock_kmap();
}
static inline unsigned long map_new_virtual(struct page *page)
{
unsigned long vaddr;
int count;
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
unsigned int last_pkmap_nr;
unsigned int color = get_pkmap_color(page);
start:
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
count = get_pkmap_entries_count(color);
/* Find an empty entry */
for (;;) {
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
last_pkmap_nr = get_next_pkmap_nr(color);
if (no_more_pkmaps(last_pkmap_nr, color)) {
flush_all_zero_pkmaps();
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
count = get_pkmap_entries_count(color);
}
if (!pkmap_count[last_pkmap_nr])
break; /* Found a usable entry */
if (--count)
continue;
/*
* Sleep for somebody else to unmap their entries
*/
{
DECLARE_WAITQUEUE(wait, current);
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
wait_queue_head_t *pkmap_map_wait =
get_pkmap_wait_queue_head(color);
__set_current_state(TASK_UNINTERRUPTIBLE);
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
add_wait_queue(pkmap_map_wait, &wait);
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
unlock_kmap();
schedule();
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
remove_wait_queue(pkmap_map_wait, &wait);
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
lock_kmap();
/* Somebody else might have mapped it while we slept */
if (page_address(page))
return (unsigned long)page_address(page);
/* Re-start */
goto start;
}
}
vaddr = PKMAP_ADDR(last_pkmap_nr);
set_pte_at(&init_mm, vaddr,
&(pkmap_page_table[last_pkmap_nr]), mk_pte(page, kmap_prot));
pkmap_count[last_pkmap_nr] = 1;
set_page_address(page, (void *)vaddr);
return vaddr;
}
/**
* kmap_high - map a highmem page into memory
* @page: &struct page to map
*
* Returns the page's virtual memory address.
*
* We cannot call this from interrupts, as it may block.
*/
void *kmap_high(struct page *page)
{
unsigned long vaddr;
/*
* For highmem pages, we can't trust "virtual" until
* after we have the lock.
*/
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
lock_kmap();
vaddr = (unsigned long)page_address(page);
if (!vaddr)
vaddr = map_new_virtual(page);
pkmap_count[PKMAP_NR(vaddr)]++;
BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
unlock_kmap();
return (void *) vaddr;
}
EXPORT_SYMBOL(kmap_high);
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
#ifdef ARCH_NEEDS_KMAP_HIGH_GET
/**
* kmap_high_get - pin a highmem page into memory
* @page: &struct page to pin
*
* Returns the page's current virtual memory address, or NULL if no mapping
* exists. If and only if a non null address is returned then a
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
* matching call to kunmap_high() is necessary.
*
* This can be called from any context.
*/
void *kmap_high_get(struct page *page)
{
unsigned long vaddr, flags;
lock_kmap_any(flags);
vaddr = (unsigned long)page_address(page);
if (vaddr) {
BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1);
pkmap_count[PKMAP_NR(vaddr)]++;
}
unlock_kmap_any(flags);
return (void *) vaddr;
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
}
#endif
/**
* kunmap_high - unmap a highmem page into memory
* @page: &struct page to unmap
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
*
* If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called
* only from user context.
*/
void kunmap_high(struct page *page)
{
unsigned long vaddr;
unsigned long nr;
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
unsigned long flags;
int need_wakeup;
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
unsigned int color = get_pkmap_color(page);
wait_queue_head_t *pkmap_map_wait;
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
lock_kmap_any(flags);
vaddr = (unsigned long)page_address(page);
BUG_ON(!vaddr);
nr = PKMAP_NR(vaddr);
/*
* A count must never go down to zero
* without a TLB flush!
*/
need_wakeup = 0;
switch (--pkmap_count[nr]) {
case 0:
BUG();
case 1:
/*
* Avoid an unnecessary wake_up() function call.
* The common case is pkmap_count[] == 1, but
* no waiters.
* The tasks queued in the wait-queue are guarded
* by both the lock in the wait-queue-head and by
* the kmap_lock. As the kmap_lock is held here,
* no need for the wait-queue-head's lock. Simply
* test if the queue is empty.
*/
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
pkmap_map_wait = get_pkmap_wait_queue_head(color);
need_wakeup = waitqueue_active(pkmap_map_wait);
}
highmem: atomic highmem kmap page pinning Most ARM machines have a non IO coherent cache, meaning that the dma_map_*() set of functions must clean and/or invalidate the affected memory manually before DMA occurs. And because the majority of those machines have a VIVT cache, the cache maintenance operations must be performed using virtual addresses. When a highmem page is kunmap'd, its mapping (and cache) remains in place in case it is kmap'd again. However if dma_map_page() is then called with such a page, some cache maintenance on the remaining mapping must be performed. In that case, page_address(page) is non null and we can use that to synchronize the cache. It is unlikely but still possible for kmap() to race and recycle the virtual address obtained above, and use it for another page before some on-going cache invalidation loop in dma_map_page() is done. In that case, the new mapping could end up with dirty cache lines for another page, and the unsuspecting cache invalidation loop in dma_map_page() might simply discard those dirty cache lines resulting in data loss. For example, let's consider this sequence of events: - dma_map_page(..., DMA_FROM_DEVICE) is called on a highmem page. --> - vaddr = page_address(page) is non null. In this case it is likely that the page has valid cache lines associated with vaddr. Remember that the cache is VIVT. --> for (i = vaddr; i < vaddr + PAGE_SIZE; i += 32) invalidate_cache_line(i); *** preemption occurs in the middle of the loop above *** - kmap_high() is called for a different page. --> - last_pkmap_nr wraps to zero and flush_all_zero_pkmaps() is called. The pkmap_count value for the page passed to dma_map_page() above happens to be 1, so the page is unmapped. But prior to that, flush_cache_kmaps() cleared the cache for it. So far so good. - A fresh pkmap entry is assigned for this kmap request. The Murphy law says this pkmap entry will eventually happen to use the same vaddr as the one which used to belong to the other page being processed by dma_map_page() in the preempted thread above. - The kmap_high() caller start dirtying the cache using the just assigned virtual mapping for its page. *** the first thread is rescheduled *** - The for(...) loop is resumed, but now cached data belonging to a different physical page is being discarded ! And this is not only a preemption issue as ARM can be SMP as well, making the above scenario just as likely. Hence the need for some kind of pkmap page pinning which can be used in any context, primarily for the benefit of dma_map_page() on ARM. This provides the necessary interface to cope with the above issue if ARCH_NEEDS_KMAP_HIGH_GET is defined, otherwise the resulting code is unchanged. Signed-off-by: Nicolas Pitre <nico@marvell.com> Reviewed-by: MinChan Kim <minchan.kim@gmail.com> Acked-by: Andrew Morton <akpm@linux-foundation.org>
2009-03-05 11:49:41 +08:00
unlock_kmap_any(flags);
/* do wake-up, if needed, race-free outside of the spin lock */
if (need_wakeup)
mm/highmem: make kmap cache coloring aware User-visible effect: Architectures that choose this method of maintaining cache coherency (MIPS and xtensa currently) are able to use high memory on cores with aliasing data cache. Without this fix such architectures can not use high memory (in case of xtensa it means that at most 128 MBytes of physical memory is available). The problem: VIPT cache with way size larger than MMU page size may suffer from aliasing problem: a single physical address accessed via different virtual addresses may end up in multiple locations in the cache. Virtual mappings of a physical address that always get cached in different cache locations are said to have different colors. L1 caching hardware usually doesn't handle this situation leaving it up to software. Software must avoid this situation as it leads to data corruption. What can be done: One way to handle this is to flush and invalidate data cache every time page mapping changes color. The other way is to always map physical page at a virtual address with the same color. Low memory pages already have this property. Giving architecture a way to control color of high memory page mapping allows reusing of existing low memory cache alias handling code. How this is done with this patch: Provide hooks that allow architectures with aliasing cache to align mapping address of high pages according to their color. Such architectures may enforce similar coloring of low- and high-memory page mappings and reuse existing cache management functions to support highmem. This code is based on the implementation of similar feature for MIPS by Leonid Yegoshin. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: Chris Zankel <chris@zankel.net> Cc: Marc Gauthier <marc@cadence.com> Cc: David Rientjes <rientjes@google.com> Cc: Steven Hill <Steven.Hill@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-07 07:08:23 +08:00
wake_up(pkmap_map_wait);
}
EXPORT_SYMBOL(kunmap_high);
void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
unsigned start2, unsigned end2)
{
unsigned int i;
BUG_ON(end1 > page_size(page) || end2 > page_size(page));
if (start1 >= end1)
start1 = end1 = 0;
if (start2 >= end2)
start2 = end2 = 0;
for (i = 0; i < compound_nr(page); i++) {
void *kaddr = NULL;
if (start1 >= PAGE_SIZE) {
start1 -= PAGE_SIZE;
end1 -= PAGE_SIZE;
} else {
unsigned this_end = min_t(unsigned, end1, PAGE_SIZE);
if (end1 > start1) {
mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Prathu Baronia <prathu.baronia@oneplus.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-06 04:45:06 +08:00
kaddr = kmap_local_page(page + i);
memset(kaddr + start1, 0, this_end - start1);
}
end1 -= this_end;
start1 = 0;
}
if (start2 >= PAGE_SIZE) {
start2 -= PAGE_SIZE;
end2 -= PAGE_SIZE;
} else {
unsigned this_end = min_t(unsigned, end2, PAGE_SIZE);
if (end2 > start2) {
if (!kaddr)
mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Prathu Baronia <prathu.baronia@oneplus.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-06 04:45:06 +08:00
kaddr = kmap_local_page(page + i);
memset(kaddr + start2, 0, this_end - start2);
}
end2 -= this_end;
start2 = 0;
}
if (kaddr) {
mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny <ira.weiny@intel.com> Signed-off-by: Prathu Baronia <prathu.baronia@oneplus.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-06 04:45:06 +08:00
kunmap_local(kaddr);
flush_dcache_page(page + i);
}
if (!end1 && !end2)
break;
}
BUG_ON((start1 | start2 | end1 | end2) != 0);
}
EXPORT_SYMBOL(zero_user_segments);
#endif /* CONFIG_HIGHMEM */
#ifdef CONFIG_KMAP_LOCAL
#include <asm/kmap_size.h>
/*
* With DEBUG_KMAP_LOCAL the stack depth is doubled and every second
* slot is unused which acts as a guard page
*/
#ifdef CONFIG_DEBUG_KMAP_LOCAL
# define KM_INCR 2
#else
# define KM_INCR 1
#endif
static inline int kmap_local_idx_push(void)
{
WARN_ON_ONCE(in_hardirq() && !irqs_disabled());
current->kmap_ctrl.idx += KM_INCR;
BUG_ON(current->kmap_ctrl.idx >= KM_MAX_IDX);
return current->kmap_ctrl.idx - 1;
}
static inline int kmap_local_idx(void)
{
return current->kmap_ctrl.idx - 1;
}
static inline void kmap_local_idx_pop(void)
{
current->kmap_ctrl.idx -= KM_INCR;
BUG_ON(current->kmap_ctrl.idx < 0);
}
#ifndef arch_kmap_local_post_map
# define arch_kmap_local_post_map(vaddr, pteval) do { } while (0)
#endif
#ifndef arch_kmap_local_pre_unmap
# define arch_kmap_local_pre_unmap(vaddr) do { } while (0)
#endif
#ifndef arch_kmap_local_post_unmap
# define arch_kmap_local_post_unmap(vaddr) do { } while (0)
#endif
#ifndef arch_kmap_local_unmap_idx
#define arch_kmap_local_unmap_idx(idx, vaddr) kmap_local_calc_idx(idx)
#endif
#ifndef arch_kmap_local_high_get
static inline void *arch_kmap_local_high_get(struct page *page)
{
return NULL;
}
#endif
#ifndef arch_kmap_local_set_pte
#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \
set_pte_at(mm, vaddr, ptep, ptev)
#endif
/* Unmap a local mapping which was obtained by kmap_high_get() */
static inline bool kmap_high_unmap_local(unsigned long vaddr)
{
#ifdef ARCH_NEEDS_KMAP_HIGH_GET
if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 23:15:45 +08:00
kunmap_high(pte_page(ptep_get(&pkmap_page_table[PKMAP_NR(vaddr)])));
return true;
}
#endif
return false;
}
static pte_t *__kmap_pte;
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
static pte_t *kmap_get_pte(unsigned long vaddr, int idx)
{
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
if (IS_ENABLED(CONFIG_KMAP_LOCAL_NON_LINEAR_PTE_ARRAY))
/*
* Set by the arch if __kmap_pte[-idx] does not produce
* the correct entry.
*/
return virt_to_kpte(vaddr);
if (!__kmap_pte)
__kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
return &__kmap_pte[-idx];
}
void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot)
{
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
pte_t pteval, *kmap_pte;
unsigned long vaddr;
int idx;
/*
* Disable migration so resulting virtual address is stable
* across preemption.
*/
migrate_disable();
preempt_disable();
idx = arch_kmap_local_map_idx(kmap_local_idx_push(), pfn);
vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
kmap_pte = kmap_get_pte(vaddr, idx);
mm: ptep_get() conversion Convert all instances of direct pte_t* dereferencing to instead use ptep_get() helper. This means that by default, the accesses change from a C dereference to a READ_ONCE(). This is technically the correct thing to do since where pgtables are modified by HW (for access/dirty) they are volatile and therefore we should always ensure READ_ONCE() semantics. But more importantly, by always using the helper, it can be overridden by the architecture to fully encapsulate the contents of the pte. Arch code is deliberately not converted, as the arch code knows best. It is intended that arch code (arm64) will override the default with its own implementation that can (e.g.) hide certain bits from the core code, or determine young/dirty status by mixing in state from another source. Conversion was done using Coccinelle: ---- // $ make coccicheck \ // COCCI=ptepget.cocci \ // SPFLAGS="--include-headers" \ // MODE=patch virtual patch @ depends on patch @ pte_t *v; @@ - *v + ptep_get(v) ---- Then reviewed and hand-edited to avoid multiple unnecessary calls to ptep_get(), instead opting to store the result of a single call in a variable, where it is correct to do so. This aims to negate any cost of READ_ONCE() and will benefit arch-overrides that may be more complex. Included is a fix for an issue in an earlier version of this patch that was pointed out by kernel test robot. The issue arose because config MMU=n elides definition of the ptep helper functions, including ptep_get(). HUGETLB_PAGE=n configs still define a simple huge_ptep_clear_flush() for linking purposes, which dereferences the ptep. So when both configs are disabled, this caused a build error because ptep_get() is not defined. Fix by continuing to do a direct dereference when MMU=n. This is safe because for this config the arch code cannot be trying to virtualize the ptes because none of the ptep helpers are defined. Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com Reported-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/ Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Christian Brauner <brauner@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Dave Airlie <airlied@gmail.com> Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Lorenzo Stoakes <lstoakes@gmail.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport (IBM) <rppt@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: SeongJae Park <sj@kernel.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vincenzo Frascino <vincenzo.frascino@arm.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 23:15:45 +08:00
BUG_ON(!pte_none(ptep_get(kmap_pte)));
pteval = pfn_pte(pfn, prot);
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
arch_kmap_local_set_pte(&init_mm, vaddr, kmap_pte, pteval);
arch_kmap_local_post_map(vaddr, pteval);
current->kmap_ctrl.pteval[kmap_local_idx()] = pteval;
preempt_enable();
return (void *)vaddr;
}
EXPORT_SYMBOL_GPL(__kmap_local_pfn_prot);
void *__kmap_local_page_prot(struct page *page, pgprot_t prot)
{
void *kmap;
/*
* To broaden the usage of the actual kmap_local() machinery always map
* pages when debugging is enabled and the architecture has no problems
* with alias mappings.
*/
if (!IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) && !PageHighMem(page))
return page_address(page);
/* Try kmap_high_get() if architecture has it enabled */
kmap = arch_kmap_local_high_get(page);
if (kmap)
return kmap;
return __kmap_local_pfn_prot(page_to_pfn(page), prot);
}
EXPORT_SYMBOL(__kmap_local_page_prot);
void kunmap_local_indexed(const void *vaddr)
{
unsigned long addr = (unsigned long) vaddr & PAGE_MASK;
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
pte_t *kmap_pte;
int idx;
if (addr < __fix_to_virt(FIX_KMAP_END) ||
addr > __fix_to_virt(FIX_KMAP_BEGIN)) {
if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP)) {
/* This _should_ never happen! See above. */
WARN_ON_ONCE(1);
return;
}
/*
* Handle mappings which were obtained by kmap_high_get()
* first as the virtual address of such mappings is below
* PAGE_OFFSET. Warn for all other addresses which are in
* the user space part of the virtual address space.
*/
if (!kmap_high_unmap_local(addr))
WARN_ON_ONCE(addr < PAGE_OFFSET);
return;
}
preempt_disable();
idx = arch_kmap_local_unmap_idx(kmap_local_idx(), addr);
WARN_ON_ONCE(addr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
kmap_pte = kmap_get_pte(addr, idx);
arch_kmap_local_pre_unmap(addr);
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
pte_clear(&init_mm, addr, kmap_pte);
arch_kmap_local_post_unmap(addr);
current->kmap_ctrl.pteval[kmap_local_idx()] = __pte(0);
kmap_local_idx_pop();
preempt_enable();
migrate_enable();
}
EXPORT_SYMBOL(kunmap_local_indexed);
/*
* Invoked before switch_to(). This is safe even when during or after
* clearing the maps an interrupt which needs a kmap_local happens because
* the task::kmap_ctrl.idx is not modified by the unmapping code so a
* nested kmap_local will use the next unused index and restore the index
* on unmap. The already cleared kmaps of the outgoing task are irrelevant
* because the interrupt context does not know about them. The same applies
* when scheduling back in for an interrupt which happens before the
* restore is complete.
*/
void __kmap_local_sched_out(void)
{
struct task_struct *tsk = current;
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
pte_t *kmap_pte;
int i;
/* Clear kmaps */
for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
pte_t pteval = tsk->kmap_ctrl.pteval[i];
unsigned long addr;
int idx;
/* With debug all even slots are unmapped and act as guard */
if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
highmem: fix checks in __kmap_local_sched_{in,out} When CONFIG_DEBUG_KMAP_LOCAL is enabled __kmap_local_sched_{in,out} check that even slots in the tsk->kmap_ctrl.pteval are unmapped. The slots are initialized with 0 value, but the check is done with pte_none. 0 pte however does not necessarily mean that pte_none will return true. e.g. on xtensa it returns false, resulting in the following runtime warnings: WARNING: CPU: 0 PID: 101 at mm/highmem.c:627 __kmap_local_sched_out+0x51/0x108 CPU: 0 PID: 101 Comm: touch Not tainted 5.17.0-rc7-00010-gd3a1cdde80d2-dirty #13 Call Trace: dump_stack+0xc/0x40 __warn+0x8f/0x174 warn_slowpath_fmt+0x48/0xac __kmap_local_sched_out+0x51/0x108 __schedule+0x71a/0x9c4 preempt_schedule_irq+0xa0/0xe0 common_exception_return+0x5c/0x93 do_wp_page+0x30e/0x330 handle_mm_fault+0xa70/0xc3c do_page_fault+0x1d8/0x3c4 common_exception+0x7f/0x7f WARNING: CPU: 0 PID: 101 at mm/highmem.c:664 __kmap_local_sched_in+0x50/0xe0 CPU: 0 PID: 101 Comm: touch Tainted: G W 5.17.0-rc7-00010-gd3a1cdde80d2-dirty #13 Call Trace: dump_stack+0xc/0x40 __warn+0x8f/0x174 warn_slowpath_fmt+0x48/0xac __kmap_local_sched_in+0x50/0xe0 finish_task_switch$isra$0+0x1ce/0x2f8 __schedule+0x86e/0x9c4 preempt_schedule_irq+0xa0/0xe0 common_exception_return+0x5c/0x93 do_wp_page+0x30e/0x330 handle_mm_fault+0xa70/0xc3c do_page_fault+0x1d8/0x3c4 common_exception+0x7f/0x7f Fix it by replacing !pte_none(pteval) with pte_val(pteval) != 0. Link: https://lkml.kernel.org/r/20220403235159.3498065-1-jcmvbkbc@gmail.com Fixes: 5fbda3ecd14a ("sched: highmem: Store local kmaps in task struct") Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-04-09 04:08:55 +08:00
WARN_ON_ONCE(pte_val(pteval) != 0);
continue;
}
if (WARN_ON_ONCE(pte_none(pteval)))
continue;
/*
* This is a horrible hack for XTENSA to calculate the
* coloured PTE index. Uses the PFN encoded into the pteval
* and the map index calculation because the actual mapped
* virtual address is not stored in task::kmap_ctrl.
* For any sane architecture this is optimized out.
*/
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
kmap_pte = kmap_get_pte(addr, idx);
arch_kmap_local_pre_unmap(addr);
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
pte_clear(&init_mm, addr, kmap_pte);
arch_kmap_local_post_unmap(addr);
}
}
void __kmap_local_sched_in(void)
{
struct task_struct *tsk = current;
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
pte_t *kmap_pte;
int i;
/* Restore kmaps */
for (i = 0; i < tsk->kmap_ctrl.idx; i++) {
pte_t pteval = tsk->kmap_ctrl.pteval[i];
unsigned long addr;
int idx;
/* With debug all even slots are unmapped and act as guard */
if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
highmem: fix checks in __kmap_local_sched_{in,out} When CONFIG_DEBUG_KMAP_LOCAL is enabled __kmap_local_sched_{in,out} check that even slots in the tsk->kmap_ctrl.pteval are unmapped. The slots are initialized with 0 value, but the check is done with pte_none. 0 pte however does not necessarily mean that pte_none will return true. e.g. on xtensa it returns false, resulting in the following runtime warnings: WARNING: CPU: 0 PID: 101 at mm/highmem.c:627 __kmap_local_sched_out+0x51/0x108 CPU: 0 PID: 101 Comm: touch Not tainted 5.17.0-rc7-00010-gd3a1cdde80d2-dirty #13 Call Trace: dump_stack+0xc/0x40 __warn+0x8f/0x174 warn_slowpath_fmt+0x48/0xac __kmap_local_sched_out+0x51/0x108 __schedule+0x71a/0x9c4 preempt_schedule_irq+0xa0/0xe0 common_exception_return+0x5c/0x93 do_wp_page+0x30e/0x330 handle_mm_fault+0xa70/0xc3c do_page_fault+0x1d8/0x3c4 common_exception+0x7f/0x7f WARNING: CPU: 0 PID: 101 at mm/highmem.c:664 __kmap_local_sched_in+0x50/0xe0 CPU: 0 PID: 101 Comm: touch Tainted: G W 5.17.0-rc7-00010-gd3a1cdde80d2-dirty #13 Call Trace: dump_stack+0xc/0x40 __warn+0x8f/0x174 warn_slowpath_fmt+0x48/0xac __kmap_local_sched_in+0x50/0xe0 finish_task_switch$isra$0+0x1ce/0x2f8 __schedule+0x86e/0x9c4 preempt_schedule_irq+0xa0/0xe0 common_exception_return+0x5c/0x93 do_wp_page+0x30e/0x330 handle_mm_fault+0xa70/0xc3c do_page_fault+0x1d8/0x3c4 common_exception+0x7f/0x7f Fix it by replacing !pte_none(pteval) with pte_val(pteval) != 0. Link: https://lkml.kernel.org/r/20220403235159.3498065-1-jcmvbkbc@gmail.com Fixes: 5fbda3ecd14a ("sched: highmem: Store local kmaps in task struct") Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-04-09 04:08:55 +08:00
WARN_ON_ONCE(pte_val(pteval) != 0);
continue;
}
if (WARN_ON_ONCE(pte_none(pteval)))
continue;
/* See comment in __kmap_local_sched_out() */
idx = arch_kmap_local_map_idx(i, pte_pfn(pteval));
addr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
kmap_local: don't assume kmap PTEs are linear arrays in memory The kmap_local conversion broke the ARM architecture, because the new code assumes that all PTEs used for creating kmaps form a linear array in memory, and uses array indexing to look up the kmap PTE belonging to a certain kmap index. On ARM, this cannot work, not only because the PTE pages may be non-adjacent in memory, but also because ARM/!LPAE interleaves hardware entries and extended entries (carrying software-only bits) in a way that is not compatible with array indexing. Fortunately, this only seems to affect configurations with more than 8 CPUs, due to the way the per-CPU kmap slots are organized in memory. Work around this by permitting an architecture to set a Kconfig symbol that signifies that the kmap PTEs do not form a lineary array in memory, and so the only way to locate the appropriate one is to walk the page tables. Link: https://lore.kernel.org/linux-arm-kernel/20211026131249.3731275-1-ardb@kernel.org/ Link: https://lkml.kernel.org/r/20211116094737.7391-1-ardb@kernel.org Fixes: 2a15ba82fa6c ("ARM: highmem: Switch to generic kmap atomic") Signed-off-by: Ard Biesheuvel <ardb@kernel.org> Reported-by: Quanyang Wang <quanyang.wang@windriver.com> Reviewed-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-11-20 08:43:55 +08:00
kmap_pte = kmap_get_pte(addr, idx);
set_pte_at(&init_mm, addr, kmap_pte, pteval);
arch_kmap_local_post_map(addr, pteval);
}
}
void kmap_local_fork(struct task_struct *tsk)
{
if (WARN_ON_ONCE(tsk->kmap_ctrl.idx))
memset(&tsk->kmap_ctrl, 0, sizeof(tsk->kmap_ctrl));
}
#endif
#if defined(HASHED_PAGE_VIRTUAL)
#define PA_HASH_ORDER 7
/*
* Describes one page->virtual association
*/
struct page_address_map {
struct page *page;
void *virtual;
struct list_head list;
};
static struct page_address_map page_address_maps[LAST_PKMAP];
/*
* Hash table bucket
*/
static struct page_address_slot {
struct list_head lh; /* List of page_address_maps */
spinlock_t lock; /* Protect this bucket's list */
} ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER];
static struct page_address_slot *page_slot(const struct page *page)
{
return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)];
}
/**
* page_address - get the mapped virtual address of a page
* @page: &struct page to get the virtual address of
*
* Returns the page's virtual address.
*/
void *page_address(const struct page *page)
{
unsigned long flags;
void *ret;
struct page_address_slot *pas;
if (!PageHighMem(page))
return lowmem_page_address(page);
pas = page_slot(page);
ret = NULL;
spin_lock_irqsave(&pas->lock, flags);
if (!list_empty(&pas->lh)) {
struct page_address_map *pam;
list_for_each_entry(pam, &pas->lh, list) {
if (pam->page == page) {
ret = pam->virtual;
break;
}
}
}
spin_unlock_irqrestore(&pas->lock, flags);
return ret;
}
EXPORT_SYMBOL(page_address);
/**
* set_page_address - set a page's virtual address
* @page: &struct page to set
* @virtual: virtual address to use
*/
void set_page_address(struct page *page, void *virtual)
{
unsigned long flags;
struct page_address_slot *pas;
struct page_address_map *pam;
BUG_ON(!PageHighMem(page));
pas = page_slot(page);
if (virtual) { /* Add */
pam = &page_address_maps[PKMAP_NR((unsigned long)virtual)];
pam->page = page;
pam->virtual = virtual;
spin_lock_irqsave(&pas->lock, flags);
list_add_tail(&pam->list, &pas->lh);
spin_unlock_irqrestore(&pas->lock, flags);
} else { /* Remove */
spin_lock_irqsave(&pas->lock, flags);
list_for_each_entry(pam, &pas->lh, list) {
if (pam->page == page) {
list_del(&pam->list);
break;
}
}
spin_unlock_irqrestore(&pas->lock, flags);
}
}
void __init page_address_init(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) {
INIT_LIST_HEAD(&page_address_htable[i].lh);
spin_lock_init(&page_address_htable[i].lock);
}
}
#endif /* defined(HASHED_PAGE_VIRTUAL) */