mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 05:48:40 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
* memory_failure() gets confused by dev_pagemap backed mappings. The recovery code has specific enabling for several possible page states that needs new enabling to handle poison in dax mappings. Teach memory_failure() about ZONE_DEVICE pages. -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEE5DAy15EJMCV1R6v9YGjFFmlTOEoFAlt9ui8ACgkQYGjFFmlT OEpNRw//XGj9s7sezfJFeol4psJlRUd935yii/gmJRgi/yPf2VxxQG9qyM6SMBUc 75jASfOL6FSsfxHz0kplyWzMDNdrTkNNAD+9rv80FmY7GqWgcas9DaJX7jZ994vI 5SRO7pfvNZcXlo7IhqZippDw3yxkIU9Ufi0YQKaEUm7GFieptvCZ0p9x3VYfdvwM BExrxQe0X1XUF4xErp5P78+WUbKxP47DLcucRDig8Q7dmHELUdyNzo3E1SVoc7m+ 3CmvyTj6XuFQgOZw7ZKun1BJYfx/eD5ZlRJLZbx6wJHRtTXv/Uea8mZ8mJ31ykN9 F7QVd0Pmlyxys8lcXfK+nvpL09QBE0/PhwWKjmZBoU8AdgP/ZvBXLDL/D6YuMTg6 T4wwtPNJorfV4lVD06OliFkVI4qbKbmNsfRq43Ns7PCaLueu4U/eMaSwSH99UMaZ MGbO140XW2RZsHiU9yTRUmZq73AplePEjxtzR8oHmnjo45nPDPy8mucWPlkT9kXA oUFMhgiviK7dOo19H4eaPJGqLmHM93+x5tpYxGqTr0dUOXUadKWxMsTnkID+8Yi7 /kzQWCFvySz3VhiEHGuWkW08GZT6aCcpkREDomnRh4MEnETlZI8bblcuXYOCLs6c nNf1SIMtLdlsl7U1fEX89PNeQQ2y237vEDhFQZftaalPeu/JJV0= =Ftop -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.19_dax-memory-failure' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm memory-failure update from Dave Jiang: "As it stands, memory_failure() gets thoroughly confused by dev_pagemap backed mappings. The recovery code has specific enabling for several possible page states and needs new enabling to handle poison in dax mappings. In order to support reliable reverse mapping of user space addresses: 1/ Add new locking in the memory_failure() rmap path to prevent races that would typically be handled by the page lock. 2/ Since dev_pagemap pages are hidden from the page allocator and the "compound page" accounting machinery, add a mechanism to determine the size of the mapping that encompasses a given poisoned pfn. 3/ Given pmem errors can be repaired, change the speculatively accessed poison protection, mce_unmap_kpfn(), to be reversible and otherwise allow ongoing access from the kernel. A side effect of this enabling is that MADV_HWPOISON becomes usable for dax mappings, however the primary motivation is to allow the system to survive userspace consumption of hardware-poison via dax. Specifically the current behavior is: mce: Uncorrected hardware memory error in user-access at af34214200 {1}[Hardware Error]: It has been corrected by h/w and requires no further action mce: [Hardware Error]: Machine check events logged {1}[Hardware Error]: event severity: corrected Memory failure: 0xaf34214: reserved kernel page still referenced by 1 users [..] Memory failure: 0xaf34214: recovery action for reserved kernel page: Failed mce: Memory error not recovered <reboot> ...and with these changes: Injecting memory failure for pfn 0x20cb00 at process virtual address 0x7f763dd00000 Memory failure: 0x20cb00: Killing dax-pmd:5421 due to hardware memory corruption Memory failure: 0x20cb00: recovery action for dax page: Recovered Given all the cross dependencies I propose taking this through nvdimm.git with acks from Naoya, x86/core, x86/RAS, and of course dax folks" * tag 'libnvdimm-for-4.19_dax-memory-failure' of gitolite.kernel.org:pub/scm/linux/kernel/git/nvdimm/nvdimm: libnvdimm, pmem: Restore page attributes when clearing errors x86/memory_failure: Introduce {set, clear}_mce_nospec() x86/mm/pat: Prepare {reserve, free}_memtype() for "decoy" addresses mm, memory_failure: Teach memory_failure() about dev_pagemap pages filesystem-dax: Introduce dax_lock_mapping_entry() mm, memory_failure: Collect mapping size in collect_procs() mm, madvise_inject_error: Let memory_failure() optionally take a page reference mm, dev_pagemap: Do not clear ->mapping on final put mm, madvise_inject_error: Disable MADV_SOFT_OFFLINE for ZONE_DEVICE pages filesystem-dax: Set page->index device-dax: Set page->index device-dax: Enable page_mapping() device-dax: Convert to vmf_insert_mixed and vm_fault_t
375 lines
10 KiB
C
375 lines
10 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/device.h>
|
|
#include <linux/types.h>
|
|
#include <linux/pfn_t.h>
|
|
#include <linux/io.h>
|
|
#include <linux/kasan.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/memory_hotplug.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/wait_bit.h>
|
|
|
|
static DEFINE_MUTEX(pgmap_lock);
|
|
static RADIX_TREE(pgmap_radix, GFP_KERNEL);
|
|
#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
|
|
#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
|
|
|
|
static unsigned long order_at(struct resource *res, unsigned long pgoff)
|
|
{
|
|
unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
|
|
unsigned long nr_pages, mask;
|
|
|
|
nr_pages = PHYS_PFN(resource_size(res));
|
|
if (nr_pages == pgoff)
|
|
return ULONG_MAX;
|
|
|
|
/*
|
|
* What is the largest aligned power-of-2 range available from
|
|
* this resource pgoff to the end of the resource range,
|
|
* considering the alignment of the current pgoff?
|
|
*/
|
|
mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
|
|
if (!mask)
|
|
return ULONG_MAX;
|
|
|
|
return find_first_bit(&mask, BITS_PER_LONG);
|
|
}
|
|
|
|
#define foreach_order_pgoff(res, order, pgoff) \
|
|
for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
|
|
pgoff += 1UL << order, order = order_at((res), pgoff))
|
|
|
|
#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
|
|
vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
|
|
unsigned long addr,
|
|
swp_entry_t entry,
|
|
unsigned int flags,
|
|
pmd_t *pmdp)
|
|
{
|
|
struct page *page = device_private_entry_to_page(entry);
|
|
|
|
/*
|
|
* The page_fault() callback must migrate page back to system memory
|
|
* so that CPU can access it. This might fail for various reasons
|
|
* (device issue, device was unsafely unplugged, ...). When such
|
|
* error conditions happen, the callback must return VM_FAULT_SIGBUS.
|
|
*
|
|
* Note that because memory cgroup charges are accounted to the device
|
|
* memory, this should never fail because of memory restrictions (but
|
|
* allocation of regular system page might still fail because we are
|
|
* out of memory).
|
|
*
|
|
* There is a more in-depth description of what that callback can and
|
|
* cannot do, in include/linux/memremap.h
|
|
*/
|
|
return page->pgmap->page_fault(vma, addr, page, flags, pmdp);
|
|
}
|
|
EXPORT_SYMBOL(device_private_entry_fault);
|
|
#endif /* CONFIG_DEVICE_PRIVATE */
|
|
|
|
static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff)
|
|
{
|
|
unsigned long pgoff, order;
|
|
|
|
mutex_lock(&pgmap_lock);
|
|
foreach_order_pgoff(res, order, pgoff) {
|
|
if (pgoff >= end_pgoff)
|
|
break;
|
|
radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
|
|
}
|
|
mutex_unlock(&pgmap_lock);
|
|
|
|
synchronize_rcu();
|
|
}
|
|
|
|
static unsigned long pfn_first(struct dev_pagemap *pgmap)
|
|
{
|
|
const struct resource *res = &pgmap->res;
|
|
struct vmem_altmap *altmap = &pgmap->altmap;
|
|
unsigned long pfn;
|
|
|
|
pfn = res->start >> PAGE_SHIFT;
|
|
if (pgmap->altmap_valid)
|
|
pfn += vmem_altmap_offset(altmap);
|
|
return pfn;
|
|
}
|
|
|
|
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 devm_memremap_pages_release(void *data)
|
|
{
|
|
struct dev_pagemap *pgmap = data;
|
|
struct device *dev = pgmap->dev;
|
|
struct resource *res = &pgmap->res;
|
|
resource_size_t align_start, align_size;
|
|
unsigned long pfn;
|
|
|
|
for_each_device_pfn(pfn, pgmap)
|
|
put_page(pfn_to_page(pfn));
|
|
|
|
if (percpu_ref_tryget_live(pgmap->ref)) {
|
|
dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
|
|
percpu_ref_put(pgmap->ref);
|
|
}
|
|
|
|
/* pages are dead and unused, undo the arch mapping */
|
|
align_start = res->start & ~(SECTION_SIZE - 1);
|
|
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
|
|
- align_start;
|
|
|
|
mem_hotplug_begin();
|
|
arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
|
|
&pgmap->altmap : NULL);
|
|
kasan_remove_zero_shadow(__va(align_start), align_size);
|
|
mem_hotplug_done();
|
|
|
|
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
|
|
pgmap_radix_release(res, -1);
|
|
dev_WARN_ONCE(dev, pgmap->altmap.alloc,
|
|
"%s: failed to free all reserved pages\n", __func__);
|
|
}
|
|
|
|
/**
|
|
* devm_memremap_pages - remap and provide memmap backing for the given resource
|
|
* @dev: hosting device for @res
|
|
* @pgmap: pointer to a struct dev_pgmap
|
|
*
|
|
* Notes:
|
|
* 1/ At a minimum the res, ref 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 altmap_valid
|
|
* must be set to true
|
|
*
|
|
* 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages()
|
|
* time (or devm release event). The expected order of events is that ref has
|
|
* been through percpu_ref_kill() before devm_memremap_pages_release(). The
|
|
* wait for the completion of all references being dropped and
|
|
* percpu_ref_exit() must occur after devm_memremap_pages_release().
|
|
*
|
|
* 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)
|
|
{
|
|
resource_size_t align_start, align_size, align_end;
|
|
struct vmem_altmap *altmap = pgmap->altmap_valid ?
|
|
&pgmap->altmap : NULL;
|
|
struct resource *res = &pgmap->res;
|
|
unsigned long pfn, pgoff, order;
|
|
pgprot_t pgprot = PAGE_KERNEL;
|
|
int error, nid, is_ram;
|
|
struct dev_pagemap *conflict_pgmap;
|
|
|
|
align_start = res->start & ~(SECTION_SIZE - 1);
|
|
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
|
|
- align_start;
|
|
align_end = align_start + align_size - 1;
|
|
|
|
conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
|
|
if (conflict_pgmap) {
|
|
dev_WARN(dev, "Conflicting mapping in same section\n");
|
|
put_dev_pagemap(conflict_pgmap);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
|
|
if (conflict_pgmap) {
|
|
dev_WARN(dev, "Conflicting mapping in same section\n");
|
|
put_dev_pagemap(conflict_pgmap);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
is_ram = region_intersects(align_start, align_size,
|
|
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
|
|
|
|
if (is_ram == REGION_MIXED) {
|
|
WARN_ONCE(1, "%s attempted on mixed region %pr\n",
|
|
__func__, res);
|
|
return ERR_PTR(-ENXIO);
|
|
}
|
|
|
|
if (is_ram == REGION_INTERSECTS)
|
|
return __va(res->start);
|
|
|
|
if (!pgmap->ref)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
pgmap->dev = dev;
|
|
|
|
mutex_lock(&pgmap_lock);
|
|
error = 0;
|
|
|
|
foreach_order_pgoff(res, order, pgoff) {
|
|
error = __radix_tree_insert(&pgmap_radix,
|
|
PHYS_PFN(res->start) + pgoff, order, pgmap);
|
|
if (error) {
|
|
dev_err(dev, "%s: failed: %d\n", __func__, error);
|
|
break;
|
|
}
|
|
}
|
|
mutex_unlock(&pgmap_lock);
|
|
if (error)
|
|
goto err_radix;
|
|
|
|
nid = dev_to_node(dev);
|
|
if (nid < 0)
|
|
nid = numa_mem_id();
|
|
|
|
error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
|
|
align_size);
|
|
if (error)
|
|
goto err_pfn_remap;
|
|
|
|
mem_hotplug_begin();
|
|
error = kasan_add_zero_shadow(__va(align_start), align_size);
|
|
if (error) {
|
|
mem_hotplug_done();
|
|
goto err_kasan;
|
|
}
|
|
|
|
error = arch_add_memory(nid, align_start, align_size, altmap, false);
|
|
if (!error)
|
|
move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
|
|
align_start >> PAGE_SHIFT,
|
|
align_size >> PAGE_SHIFT, altmap);
|
|
mem_hotplug_done();
|
|
if (error)
|
|
goto err_add_memory;
|
|
|
|
for_each_device_pfn(pfn, pgmap) {
|
|
struct page *page = pfn_to_page(pfn);
|
|
|
|
/*
|
|
* ZONE_DEVICE pages union ->lru with a ->pgmap back
|
|
* pointer. It is a bug if a ZONE_DEVICE page is ever
|
|
* freed or placed on a driver-private list. Seed the
|
|
* storage with LIST_POISON* values.
|
|
*/
|
|
list_del(&page->lru);
|
|
page->pgmap = pgmap;
|
|
percpu_ref_get(pgmap->ref);
|
|
}
|
|
|
|
devm_add_action(dev, devm_memremap_pages_release, pgmap);
|
|
|
|
return __va(res->start);
|
|
|
|
err_add_memory:
|
|
kasan_remove_zero_shadow(__va(align_start), align_size);
|
|
err_kasan:
|
|
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
|
|
err_pfn_remap:
|
|
err_radix:
|
|
pgmap_radix_release(res, pgoff);
|
|
return ERR_PTR(error);
|
|
}
|
|
EXPORT_SYMBOL(devm_memremap_pages);
|
|
|
|
unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
|
|
{
|
|
/* number of pfns from base where pfn_to_page() is valid */
|
|
return altmap->reserve + altmap->free;
|
|
}
|
|
|
|
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 = radix_tree_lookup(&pgmap_radix, 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
|
|
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
|
|
EXPORT_SYMBOL(devmap_managed_key);
|
|
static atomic_t devmap_enable;
|
|
|
|
/*
|
|
* Toggle the static key for ->page_free() callbacks when dev_pagemap
|
|
* pages go idle.
|
|
*/
|
|
void dev_pagemap_get_ops(void)
|
|
{
|
|
if (atomic_inc_return(&devmap_enable) == 1)
|
|
static_branch_enable(&devmap_managed_key);
|
|
}
|
|
EXPORT_SYMBOL_GPL(dev_pagemap_get_ops);
|
|
|
|
void dev_pagemap_put_ops(void)
|
|
{
|
|
if (atomic_dec_and_test(&devmap_enable))
|
|
static_branch_disable(&devmap_managed_key);
|
|
}
|
|
EXPORT_SYMBOL_GPL(dev_pagemap_put_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->page_free(page, page->pgmap->data);
|
|
} else if (!count)
|
|
__put_page(page);
|
|
}
|
|
EXPORT_SYMBOL(__put_devmap_managed_page);
|
|
#endif /* CONFIG_DEV_PAGEMAP_OPS */
|