#if _MIPS_SIM != _MIPS_SIM_ABI64 && defined(CONFIG_64BIT)
/* Building 32-bit VDSO for the 64-bit kernel. Fake a 32-bit Kconfig. */
+#define BUILD_VDSO32_64
#undef CONFIG_64BIT
#define CONFIG_32BIT 1
#ifndef __ASSEMBLY__
acpi_gpe_apply_masked_gpes();
acpi_update_all_gpes();
+ /*
+ * Although we call __add_memory() that is documented to require the
+ * device_hotplug_lock, it is not necessary here because this is an
+ * early code when userspace or any other code path cannot trigger
+ * hotplug/hotunplug operations.
+ */
mutex_lock(&acpi_scan_lock);
/*
* Enumerate devices in the ACPI namespace.
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
+#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
*/
-static int format_corename(struct core_name *cn, struct coredump_params *cprm)
+static int format_corename(struct core_name *cn, struct coredump_params *cprm,
+ size_t **argv, int *argc)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
+ bool was_space = false;
int pid_in_pattern = 0;
int err = 0;
return -ENOMEM;
cn->corename[0] = '\0';
- if (ispipe)
+ if (ispipe) {
+ int argvs = sizeof(core_pattern) / 2;
+ (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL);
+ if (!(*argv))
+ return -ENOMEM;
+ (*argv)[(*argc)++] = 0;
++pat_ptr;
+ }
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
+ /*
+ * Split on spaces before doing template expansion so that
+ * %e and %E don't get split if they have spaces in them
+ */
+ if (ispipe) {
+ if (isspace(*pat_ptr)) {
+ was_space = true;
+ pat_ptr++;
+ continue;
+ } else if (was_space) {
+ was_space = false;
+ err = cn_printf(cn, "%c", '\0');
+ if (err)
+ return err;
+ (*argv)[(*argc)++] = cn->used;
+ }
+ }
if (*pat_ptr != '%') {
err = cn_printf(cn, "%c", *pat_ptr++);
} else {
struct cred *cred;
int retval = 0;
int ispipe;
+ size_t *argv = NULL;
+ int argc = 0;
struct files_struct *displaced;
/* require nonrelative corefile path and be extra careful */
bool need_suid_safe = false;
old_cred = override_creds(cred);
- ispipe = format_corename(&cn, &cprm);
+ ispipe = format_corename(&cn, &cprm, &argv, &argc);
if (ispipe) {
+ int argi;
int dump_count;
char **helper_argv;
struct subprocess_info *sub_info;
goto fail_dropcount;
}
- helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL);
+ helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv),
+ GFP_KERNEL);
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
goto fail_dropcount;
}
+ for (argi = 0; argi < argc; argi++)
+ helper_argv[argi] = cn.corename + argv[argi];
+ helper_argv[argi] = NULL;
retval = -ENOMEM;
sub_info = call_usermodehelper_setup(helper_argv[0],
retval = call_usermodehelper_exec(sub_info,
UMH_WAIT_EXEC);
- argv_free(helper_argv);
+ kfree(helper_argv);
if (retval) {
printk(KERN_INFO "Core dump to |%s pipe failed\n",
cn.corename);
if (ispipe)
atomic_dec(&core_dump_count);
fail_unlock:
+ kfree(argv);
kfree(cn.corename);
coredump_finish(mm, core_dumped);
revert_creds(old_cred);
u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
int low_bucket = 0, bucket, high_bucket;
struct ocfs2_xattr_bucket *search;
- u32 last_hash;
u64 blkno, lower_blkno = 0;
search = ocfs2_xattr_bucket_new(inode);
if (xh->xh_count)
xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1];
- last_hash = le32_to_cpu(xe->xe_name_hash);
-
/* record lower_blkno which may be the insert place. */
lower_blkno = blkno;
#include <linux/compiler.h>
#include <linux/log2.h>
-/*
- * Runtime evaluation of get_order()
- */
-static inline __attribute_const__
-int __get_order(unsigned long size)
-{
- int order;
-
- size--;
- size >>= PAGE_SHIFT;
-#if BITS_PER_LONG == 32
- order = fls(size);
-#else
- order = fls64(size);
-#endif
- return order;
-}
-
/**
* get_order - Determine the allocation order of a memory size
* @size: The size for which to get the order
* to hold an object of the specified size.
*
* The result is undefined if the size is 0.
- *
- * This function may be used to initialise variables with compile time
- * evaluations of constants.
*/
-#define get_order(n) \
-( \
- __builtin_constant_p(n) ? ( \
- ((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT : \
- (((n) < (1UL << PAGE_SHIFT)) ? 0 : \
- ilog2((n) - 1) - PAGE_SHIFT + 1) \
- ) : \
- __get_order(n) \
-)
+static inline __attribute_const__ int get_order(unsigned long size)
+{
+ if (__builtin_constant_p(size)) {
+ if (!size)
+ return BITS_PER_LONG - PAGE_SHIFT;
+
+ if (size < (1UL << PAGE_SHIFT))
+ return 0;
+
+ return ilog2((size) - 1) - PAGE_SHIFT + 1;
+ }
+
+ size--;
+ size >>= PAGE_SHIFT;
+#if BITS_PER_LONG == 32
+ return fls(size);
+#else
+ return fls64(size);
+#endif
+}
#endif /* __ASSEMBLY__ */
#endif /* CONFIG_SPARSEMEM */
+#ifndef BUILD_VDSO32_64
/*
* page->flags layout:
*
#define LAST_CPUPID_SHIFT 0
#endif
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#ifdef CONFIG_KASAN_SW_TAGS
+#define KASAN_TAG_WIDTH 8
+#else
+#define KASAN_TAG_WIDTH 0
+#endif
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT+KASAN_TAG_WIDTH \
+ <= BITS_PER_LONG - NR_PAGEFLAGS
#define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
#else
#define LAST_CPUPID_WIDTH 0
#endif
-#ifdef CONFIG_KASAN_SW_TAGS
-#define KASAN_TAG_WIDTH 8
#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \
> BITS_PER_LONG - NR_PAGEFLAGS
-#error "KASAN: not enough bits in page flags for tag"
-#endif
-#else
-#define KASAN_TAG_WIDTH 0
+#error "Not enough bits in page flags"
#endif
/*
#define LAST_CPUPID_NOT_IN_PAGE_FLAGS
#endif
+#endif
#endif /* _LINUX_PAGE_FLAGS_LAYOUT */
obj-$(CONFIG_TORTURE_TEST) += torture.o
obj-$(CONFIG_HAS_IOMEM) += iomem.o
-obj-$(CONFIG_ZONE_DEVICE) += memremap.o
obj-$(CONFIG_RSEQ) += rseq.o
obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
-#include <linux/device.h>
-#include <linux/io.h>
-#include <linux/kasan.h>
-#include <linux/memory_hotplug.h>
-#include <linux/mm.h>
-#include <linux/pfn_t.h>
-#include <linux/swap.h>
-#include <linux/swapops.h>
-#include <linux/types.h>
-#include <linux/wait_bit.h>
-#include <linux/xarray.h>
-
-static DEFINE_XARRAY(pgmap_array);
-#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
-#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL(devmap_managed_key);
-static atomic_t devmap_managed_enable;
-
-static void devmap_managed_enable_put(void *data)
-{
- if (atomic_dec_and_test(&devmap_managed_enable))
- static_branch_disable(&devmap_managed_key);
-}
-
-static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
-{
- if (!pgmap->ops || !pgmap->ops->page_free) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- if (atomic_inc_return(&devmap_managed_enable) == 1)
- static_branch_enable(&devmap_managed_key);
- return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
-}
-#else
-static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
-{
- return -EINVAL;
-}
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
-
-static void pgmap_array_delete(struct resource *res)
-{
- xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
- NULL, GFP_KERNEL);
- synchronize_rcu();
-}
-
-static unsigned long pfn_first(struct dev_pagemap *pgmap)
-{
- return PHYS_PFN(pgmap->res.start) +
- vmem_altmap_offset(pgmap_altmap(pgmap));
-}
-
-static unsigned long pfn_end(struct dev_pagemap *pgmap)
-{
- const struct resource *res = &pgmap->res;
-
- return (res->start + resource_size(res)) >> PAGE_SHIFT;
-}
-
-static unsigned long pfn_next(unsigned long pfn)
-{
- if (pfn % 1024 == 0)
- cond_resched();
- return pfn + 1;
-}
-
-#define for_each_device_pfn(pfn, map) \
- for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
-
-static void dev_pagemap_kill(struct dev_pagemap *pgmap)
-{
- if (pgmap->ops && pgmap->ops->kill)
- pgmap->ops->kill(pgmap);
- else
- percpu_ref_kill(pgmap->ref);
-}
-
-static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
- if (pgmap->ops && pgmap->ops->cleanup) {
- pgmap->ops->cleanup(pgmap);
- } else {
- wait_for_completion(&pgmap->done);
- percpu_ref_exit(pgmap->ref);
- }
-}
-
-static void devm_memremap_pages_release(void *data)
-{
- struct dev_pagemap *pgmap = data;
- struct device *dev = pgmap->dev;
- struct resource *res = &pgmap->res;
- unsigned long pfn;
- int nid;
-
- dev_pagemap_kill(pgmap);
- for_each_device_pfn(pfn, pgmap)
- put_page(pfn_to_page(pfn));
- dev_pagemap_cleanup(pgmap);
-
- /* pages are dead and unused, undo the arch mapping */
- nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
-
- mem_hotplug_begin();
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- pfn = PHYS_PFN(res->start);
- __remove_pages(page_zone(pfn_to_page(pfn)), pfn,
- PHYS_PFN(resource_size(res)), NULL);
- } else {
- arch_remove_memory(nid, res->start, resource_size(res),
- pgmap_altmap(pgmap));
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- }
- mem_hotplug_done();
-
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- pgmap_array_delete(res);
- dev_WARN_ONCE(dev, pgmap->altmap.alloc,
- "%s: failed to free all reserved pages\n", __func__);
-}
-
-static void dev_pagemap_percpu_release(struct percpu_ref *ref)
-{
- struct dev_pagemap *pgmap =
- container_of(ref, struct dev_pagemap, internal_ref);
-
- complete(&pgmap->done);
-}
-
-/**
- * devm_memremap_pages - remap and provide memmap backing for the given resource
- * @dev: hosting device for @res
- * @pgmap: pointer to a struct dev_pagemap
- *
- * Notes:
- * 1/ At a minimum the res and type members of @pgmap must be initialized
- * by the caller before passing it to this function
- *
- * 2/ The altmap field may optionally be initialized, in which case
- * PGMAP_ALTMAP_VALID must be set in pgmap->flags.
- *
- * 3/ The ref field may optionally be provided, in which pgmap->ref must be
- * 'live' on entry and will be killed and reaped at
- * devm_memremap_pages_release() time, or if this routine fails.
- *
- * 4/ res is expected to be a host memory range that could feasibly be
- * treated as a "System RAM" range, i.e. not a device mmio range, but
- * this is not enforced.
- */
-void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
-{
- struct resource *res = &pgmap->res;
- struct dev_pagemap *conflict_pgmap;
- struct mhp_restrictions restrictions = {
- /*
- * We do not want any optional features only our own memmap
- */
- .altmap = pgmap_altmap(pgmap),
- };
- pgprot_t pgprot = PAGE_KERNEL;
- int error, nid, is_ram;
- bool need_devmap_managed = true;
-
- switch (pgmap->type) {
- case MEMORY_DEVICE_PRIVATE:
- if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
- WARN(1, "Device private memory not supported\n");
- return ERR_PTR(-EINVAL);
- }
- if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
- WARN(1, "Missing migrate_to_ram method\n");
- return ERR_PTR(-EINVAL);
- }
- break;
- case MEMORY_DEVICE_FS_DAX:
- if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
- IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
- WARN(1, "File system DAX not supported\n");
- return ERR_PTR(-EINVAL);
- }
- break;
- case MEMORY_DEVICE_DEVDAX:
- case MEMORY_DEVICE_PCI_P2PDMA:
- need_devmap_managed = false;
- break;
- default:
- WARN(1, "Invalid pgmap type %d\n", pgmap->type);
- break;
- }
-
- if (!pgmap->ref) {
- if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
- return ERR_PTR(-EINVAL);
-
- init_completion(&pgmap->done);
- error = percpu_ref_init(&pgmap->internal_ref,
- dev_pagemap_percpu_release, 0, GFP_KERNEL);
- if (error)
- return ERR_PTR(error);
- pgmap->ref = &pgmap->internal_ref;
- } else {
- if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
- WARN(1, "Missing reference count teardown definition\n");
- return ERR_PTR(-EINVAL);
- }
- }
-
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(dev, pgmap);
- if (error)
- return ERR_PTR(error);
- }
-
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
- if (conflict_pgmap) {
- dev_WARN(dev, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
- if (conflict_pgmap) {
- dev_WARN(dev, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- is_ram = region_intersects(res->start, resource_size(res),
- IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
-
- if (is_ram != REGION_DISJOINT) {
- WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
- is_ram == REGION_MIXED ? "mixed" : "ram", res);
- error = -ENXIO;
- goto err_array;
- }
-
- pgmap->dev = dev;
-
- error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
- PHYS_PFN(res->end), pgmap, GFP_KERNEL));
- if (error)
- goto err_array;
-
- nid = dev_to_node(dev);
- if (nid < 0)
- nid = numa_mem_id();
-
- error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
- resource_size(res));
- if (error)
- goto err_pfn_remap;
-
- mem_hotplug_begin();
-
- /*
- * For device private memory we call add_pages() as we only need to
- * allocate and initialize struct page for the device memory. More-
- * over the device memory is un-accessible thus we do not want to
- * create a linear mapping for the memory like arch_add_memory()
- * would do.
- *
- * For all other device memory types, which are accessible by
- * the CPU, we do want the linear mapping and thus use
- * arch_add_memory().
- */
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- error = add_pages(nid, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), &restrictions);
- } else {
- error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
- if (error) {
- mem_hotplug_done();
- goto err_kasan;
- }
-
- error = arch_add_memory(nid, res->start, resource_size(res),
- &restrictions);
- }
-
- if (!error) {
- struct zone *zone;
-
- zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
- move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), restrictions.altmap);
- }
-
- mem_hotplug_done();
- if (error)
- goto err_add_memory;
-
- /*
- * Initialization of the pages has been deferred until now in order
- * to allow us to do the work while not holding the hotplug lock.
- */
- memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
- PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), pgmap);
- percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-
- error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
- pgmap);
- if (error)
- return ERR_PTR(error);
-
- return __va(res->start);
-
- err_add_memory:
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- err_kasan:
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- err_pfn_remap:
- pgmap_array_delete(res);
- err_array:
- dev_pagemap_kill(pgmap);
- dev_pagemap_cleanup(pgmap);
- return ERR_PTR(error);
-}
-EXPORT_SYMBOL_GPL(devm_memremap_pages);
-
-void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
-{
- devm_release_action(dev, devm_memremap_pages_release, pgmap);
-}
-EXPORT_SYMBOL_GPL(devm_memunmap_pages);
-
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
- /* number of pfns from base where pfn_to_page() is valid */
- if (altmap)
- return altmap->reserve + altmap->free;
- return 0;
-}
-
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
-{
- altmap->alloc -= nr_pfns;
-}
-
-/**
- * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
- * @pfn: page frame number to lookup page_map
- * @pgmap: optional known pgmap that already has a reference
- *
- * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap
- * is non-NULL but does not cover @pfn the reference to it will be released.
- */
-struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
- struct dev_pagemap *pgmap)
-{
- resource_size_t phys = PFN_PHYS(pfn);
-
- /*
- * In the cached case we're already holding a live reference.
- */
- if (pgmap) {
- if (phys >= pgmap->res.start && phys <= pgmap->res.end)
- return pgmap;
- put_dev_pagemap(pgmap);
- }
-
- /* fall back to slow path lookup */
- rcu_read_lock();
- pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
- if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
- pgmap = NULL;
- rcu_read_unlock();
-
- return pgmap;
-}
-EXPORT_SYMBOL_GPL(get_dev_pagemap);
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
-{
- int count = page_ref_dec_return(page);
-
- /*
- * If refcount is 1 then page is freed and refcount is stable as nobody
- * holds a reference on the page.
- */
- if (count == 1) {
- /* Clear Active bit in case of parallel mark_page_accessed */
- __ClearPageActive(page);
- __ClearPageWaiters(page);
-
- mem_cgroup_uncharge(page);
-
- page->pgmap->ops->page_free(page);
- } else if (!count)
- __put_page(page);
-}
-EXPORT_SYMBOL(__put_devmap_managed_page);
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
* @task has %JOBCTL_STOP_PENDING set and is participating in a group stop.
* Group stop states are cleared and the group stop count is consumed if
* %JOBCTL_STOP_CONSUME was set. If the consumption completes the group
- * stop, the appropriate %SIGNAL_* flags are set.
+ * stop, the appropriate `SIGNAL_*` flags are set.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
config KASAN_STACK_ENABLE
bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
- default !(CLANG_VERSION < 90000)
depends on KASAN
help
The LLVM stack address sanitizer has a know problem that
Disabling asan-stack makes it safe to run kernels build
with clang-8 with KASAN enabled, though it loses some of
the functionality.
- This feature is always disabled when compile-testing with clang-8
- or earlier to avoid cluttering the output in stack overflow
- warnings, but clang-8 users can still enable it for builds without
- CONFIG_COMPILE_TEST. On gcc and later clang versions it is
- assumed to always be safe to use and enabled by default.
+ This feature is always disabled when compile-testing with clang
+ to avoid cluttering the output in stack overflow warnings,
+ but clang users can still enable it for builds without
+ CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe
+ to use and enabled by default.
config KASAN_STACK
int
obj-$(CONFIG_UBSAN) += ubsan.o
UBSAN_SANITIZE_ubsan.o := n
-CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+KASAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := $(call cc-option, -fno-stack-protector) $(DISABLE_STACKLEAK_PLUGIN)
obj-$(CONFIG_SBITMAP) += sbitmap.o
* Copy the buffer to check that it's not wiped on
* free().
*/
- buf_copy = kmalloc(size, GFP_KERNEL);
+ buf_copy = kmalloc(size, GFP_ATOMIC);
if (buf_copy)
memcpy(buf_copy, buf, size);
obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
+obj-$(CONFIG_ZONE_DEVICE) += memremap.o
obj-$(CONFIG_HMM_MIRROR) += hmm.o
obj-$(CONFIG_MEMFD_CREATE) += memfd.o
/*
* Periodically drop the lock (if held) regardless of its
- * contention, to give chance to IRQs. Abort async compaction
- * if contended.
+ * contention, to give chance to IRQs. Abort completely if
+ * a fatal signal is pending.
*/
if (!(low_pfn % SWAP_CLUSTER_MAX)
&& compact_unlock_should_abort(&pgdat->lru_lock,
- flags, &locked, cc))
- break;
+ flags, &locked, cc)) {
+ low_pfn = 0;
+ goto fatal_pending;
+ }
if (!pfn_valid_within(low_pfn))
goto isolate_fail;
trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
nr_scanned, nr_isolated);
+fatal_pending:
cc->total_migrate_scanned += nr_scanned;
if (nr_isolated)
count_compact_events(COMPACTISOLATED, nr_isolated);
/* GFP bitmask for kmemleak internal allocations */
#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
__GFP_NORETRY | __GFP_NOMEMALLOC | \
- __GFP_NOWARN | __GFP_NOFAIL)
+ __GFP_NOWARN)
/* scanning area inside a memory block */
struct kmemleak_scan_area {
return;
release_resource(res);
kfree(res);
- return;
}
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
arch_refresh_nodedata(nid, NULL);
free_percpu(pgdat->per_cpu_nodestats);
arch_free_nodedata(pgdat);
- return;
}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/kasan.h>
+#include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <linux/pfn_t.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/types.h>
+#include <linux/wait_bit.h>
+#include <linux/xarray.h>
+
+static DEFINE_XARRAY(pgmap_array);
+#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
+#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
+static atomic_t devmap_managed_enable;
+
+static void devmap_managed_enable_put(void *data)
+{
+ if (atomic_dec_and_test(&devmap_managed_enable))
+ static_branch_disable(&devmap_managed_key);
+}
+
+static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
+{
+ if (!pgmap->ops || !pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return -EINVAL;
+ }
+
+ if (atomic_inc_return(&devmap_managed_enable) == 1)
+ static_branch_enable(&devmap_managed_key);
+ return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
+}
+#else
+static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
+
+static void pgmap_array_delete(struct resource *res)
+{
+ xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+ NULL, GFP_KERNEL);
+ synchronize_rcu();
+}
+
+static unsigned long pfn_first(struct dev_pagemap *pgmap)
+{
+ return PHYS_PFN(pgmap->res.start) +
+ vmem_altmap_offset(pgmap_altmap(pgmap));
+}
+
+static unsigned long pfn_end(struct dev_pagemap *pgmap)
+{
+ const struct resource *res = &pgmap->res;
+
+ return (res->start + resource_size(res)) >> PAGE_SHIFT;
+}
+
+static unsigned long pfn_next(unsigned long pfn)
+{
+ if (pfn % 1024 == 0)
+ cond_resched();
+ return pfn + 1;
+}
+
+#define for_each_device_pfn(pfn, map) \
+ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
+
+static void dev_pagemap_kill(struct dev_pagemap *pgmap)
+{
+ if (pgmap->ops && pgmap->ops->kill)
+ pgmap->ops->kill(pgmap);
+ else
+ percpu_ref_kill(pgmap->ref);
+}
+
+static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
+{
+ if (pgmap->ops && pgmap->ops->cleanup) {
+ pgmap->ops->cleanup(pgmap);
+ } else {
+ wait_for_completion(&pgmap->done);
+ percpu_ref_exit(pgmap->ref);
+ }
+}
+
+static void devm_memremap_pages_release(void *data)
+{
+ struct dev_pagemap *pgmap = data;
+ struct device *dev = pgmap->dev;
+ struct resource *res = &pgmap->res;
+ unsigned long pfn;
+ int nid;
+
+ dev_pagemap_kill(pgmap);
+ for_each_device_pfn(pfn, pgmap)
+ put_page(pfn_to_page(pfn));
+ dev_pagemap_cleanup(pgmap);
+
+ /* pages are dead and unused, undo the arch mapping */
+ nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
+
+ mem_hotplug_begin();
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ pfn = PHYS_PFN(res->start);
+ __remove_pages(page_zone(pfn_to_page(pfn)), pfn,
+ PHYS_PFN(resource_size(res)), NULL);
+ } else {
+ arch_remove_memory(nid, res->start, resource_size(res),
+ pgmap_altmap(pgmap));
+ kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+ }
+ mem_hotplug_done();
+
+ untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
+ pgmap_array_delete(res);
+ dev_WARN_ONCE(dev, pgmap->altmap.alloc,
+ "%s: failed to free all reserved pages\n", __func__);
+}
+
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+ struct dev_pagemap *pgmap =
+ container_of(ref, struct dev_pagemap, internal_ref);
+
+ complete(&pgmap->done);
+}
+
+/**
+ * devm_memremap_pages - remap and provide memmap backing for the given resource
+ * @dev: hosting device for @res
+ * @pgmap: pointer to a struct dev_pagemap
+ *
+ * Notes:
+ * 1/ At a minimum the res and type members of @pgmap must be initialized
+ * by the caller before passing it to this function
+ *
+ * 2/ The altmap field may optionally be initialized, in which case
+ * PGMAP_ALTMAP_VALID must be set in pgmap->flags.
+ *
+ * 3/ The ref field may optionally be provided, in which pgmap->ref must be
+ * 'live' on entry and will be killed and reaped at
+ * devm_memremap_pages_release() time, or if this routine fails.
+ *
+ * 4/ res is expected to be a host memory range that could feasibly be
+ * treated as a "System RAM" range, i.e. not a device mmio range, but
+ * this is not enforced.
+ */
+void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
+{
+ struct resource *res = &pgmap->res;
+ struct dev_pagemap *conflict_pgmap;
+ struct mhp_restrictions restrictions = {
+ /*
+ * We do not want any optional features only our own memmap
+ */
+ .altmap = pgmap_altmap(pgmap),
+ };
+ pgprot_t pgprot = PAGE_KERNEL;
+ int error, nid, is_ram;
+ bool need_devmap_managed = true;
+
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
+ WARN(1, "Device private memory not supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
+ WARN(1, "Missing migrate_to_ram method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
+ case MEMORY_DEVICE_FS_DAX:
+ if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
+ IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
+ WARN(1, "File system DAX not supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
+ case MEMORY_DEVICE_DEVDAX:
+ case MEMORY_DEVICE_PCI_P2PDMA:
+ need_devmap_managed = false;
+ break;
+ default:
+ WARN(1, "Invalid pgmap type %d\n", pgmap->type);
+ break;
+ }
+
+ if (!pgmap->ref) {
+ if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+ return ERR_PTR(-EINVAL);
+
+ init_completion(&pgmap->done);
+ error = percpu_ref_init(&pgmap->internal_ref,
+ dev_pagemap_percpu_release, 0, GFP_KERNEL);
+ if (error)
+ return ERR_PTR(error);
+ pgmap->ref = &pgmap->internal_ref;
+ } else {
+ if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+ WARN(1, "Missing reference count teardown definition\n");
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
+ if (need_devmap_managed) {
+ error = devmap_managed_enable_get(dev, pgmap);
+ if (error)
+ return ERR_PTR(error);
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ error = -ENOMEM;
+ goto err_array;
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ error = -ENOMEM;
+ goto err_array;
+ }
+
+ is_ram = region_intersects(res->start, resource_size(res),
+ IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
+
+ if (is_ram != REGION_DISJOINT) {
+ WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
+ is_ram == REGION_MIXED ? "mixed" : "ram", res);
+ error = -ENXIO;
+ goto err_array;
+ }
+
+ pgmap->dev = dev;
+
+ error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
+ PHYS_PFN(res->end), pgmap, GFP_KERNEL));
+ if (error)
+ goto err_array;
+
+ nid = dev_to_node(dev);
+ if (nid < 0)
+ nid = numa_mem_id();
+
+ error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
+ resource_size(res));
+ if (error)
+ goto err_pfn_remap;
+
+ mem_hotplug_begin();
+
+ /*
+ * For device private memory we call add_pages() as we only need to
+ * allocate and initialize struct page for the device memory. More-
+ * over the device memory is un-accessible thus we do not want to
+ * create a linear mapping for the memory like arch_add_memory()
+ * would do.
+ *
+ * For all other device memory types, which are accessible by
+ * the CPU, we do want the linear mapping and thus use
+ * arch_add_memory().
+ */
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ error = add_pages(nid, PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), &restrictions);
+ } else {
+ error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
+ if (error) {
+ mem_hotplug_done();
+ goto err_kasan;
+ }
+
+ error = arch_add_memory(nid, res->start, resource_size(res),
+ &restrictions);
+ }
+
+ if (!error) {
+ struct zone *zone;
+
+ zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+ move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), restrictions.altmap);
+ }
+
+ mem_hotplug_done();
+ if (error)
+ goto err_add_memory;
+
+ /*
+ * Initialization of the pages has been deferred until now in order
+ * to allow us to do the work while not holding the hotplug lock.
+ */
+ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+ PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), pgmap);
+ percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
+
+ error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+ pgmap);
+ if (error)
+ return ERR_PTR(error);
+
+ return __va(res->start);
+
+ err_add_memory:
+ kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+ err_kasan:
+ untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
+ err_pfn_remap:
+ pgmap_array_delete(res);
+ err_array:
+ dev_pagemap_kill(pgmap);
+ dev_pagemap_cleanup(pgmap);
+ return ERR_PTR(error);
+}
+EXPORT_SYMBOL_GPL(devm_memremap_pages);
+
+void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
+{
+ devm_release_action(dev, devm_memremap_pages_release, pgmap);
+}
+EXPORT_SYMBOL_GPL(devm_memunmap_pages);
+
+unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+ /* number of pfns from base where pfn_to_page() is valid */
+ if (altmap)
+ return altmap->reserve + altmap->free;
+ return 0;
+}
+
+void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
+{
+ altmap->alloc -= nr_pfns;
+}
+
+/**
+ * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
+ * @pfn: page frame number to lookup page_map
+ * @pgmap: optional known pgmap that already has a reference
+ *
+ * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap
+ * is non-NULL but does not cover @pfn the reference to it will be released.
+ */
+struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
+ struct dev_pagemap *pgmap)
+{
+ resource_size_t phys = PFN_PHYS(pfn);
+
+ /*
+ * In the cached case we're already holding a live reference.
+ */
+ if (pgmap) {
+ if (phys >= pgmap->res.start && phys <= pgmap->res.end)
+ return pgmap;
+ put_dev_pagemap(pgmap);
+ }
+
+ /* fall back to slow path lookup */
+ rcu_read_lock();
+ pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
+ if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
+ pgmap = NULL;
+ rcu_read_unlock();
+
+ return pgmap;
+}
+EXPORT_SYMBOL_GPL(get_dev_pagemap);
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void __put_devmap_managed_page(struct page *page)
+{
+ int count = page_ref_dec_return(page);
+
+ /*
+ * If refcount is 1 then page is freed and refcount is stable as nobody
+ * holds a reference on the page.
+ */
+ if (count == 1) {
+ /* Clear Active bit in case of parallel mark_page_accessed */
+ __ClearPageActive(page);
+ __ClearPageWaiters(page);
+
+ mem_cgroup_uncharge(page);
+
+ page->pgmap->ops->page_free(page);
+ } else if (!count)
+ __put_page(page);
+}
+EXPORT_SYMBOL(__put_devmap_managed_page);
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
}
bh = bh->b_this_page;
} while (bh != head);
- spin_unlock(&mapping->private_lock);
if (busy) {
if (invalidated) {
rc = -EAGAIN;
goto unlock_buffers;
}
+ spin_unlock(&mapping->private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
+ if (check_refs)
+ spin_unlock(&mapping->private_lock);
bh = head;
do {
unlock_buffer(bh);
static void migrate_vma_collect(struct migrate_vma *migrate)
{
struct mmu_notifier_range range;
- struct mm_walk mm_walk;
-
- mm_walk.pmd_entry = migrate_vma_collect_pmd;
- mm_walk.pte_entry = NULL;
- mm_walk.pte_hole = migrate_vma_collect_hole;
- mm_walk.hugetlb_entry = NULL;
- mm_walk.test_walk = NULL;
- mm_walk.vma = migrate->vma;
- mm_walk.mm = migrate->vma->vm_mm;
- mm_walk.private = migrate;
+ struct mm_walk mm_walk = {
+ .pmd_entry = migrate_vma_collect_pmd,
+ .pte_hole = migrate_vma_collect_hole,
+ .vma = migrate->vma,
+ .mm = migrate->vma->vm_mm,
+ .private = migrate,
+ };
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm,
migrate->start,
unsigned long ret, freed = 0;
struct shrinker *shrinker;
- if (!mem_cgroup_is_root(memcg))
+ /*
+ * The root memcg might be allocated even though memcg is disabled
+ * via "cgroup_disable=memory" boot parameter. This could make
+ * mem_cgroup_is_root() return false, then just run memcg slab
+ * shrink, but skip global shrink. This may result in premature
+ * oom.
+ */
+ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
if (!down_read_trylock(&shrinker_rwsem))
strtok(NULL, delim);
strtok(NULL, delim);
- if (strcmp(fs, "cgroup") == 0 &&
- strcmp(type, "cgroup2") == 0) {
+ if (strcmp(type, "cgroup2") == 0) {
strncpy(root, mount, len);
return 0;
}