diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-25 18:43:59 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-25 18:43:59 -0700 |
commit | 2923b27e54242acf27fd16b299e102117c82f52f (patch) | |
tree | 86b3e27575814dab74307a7928bf579455b70e24 /drivers/nvdimm | |
parent | 828bf6e904eb8fc8969333568802689fbbf07a40 (diff) | |
parent | c953cc987ab87d180e1d5de2f1c217abe33aac77 (diff) | |
download | linux-stable-2923b27e54242acf27fd16b299e102117c82f52f.tar.gz linux-stable-2923b27e54242acf27fd16b299e102117c82f52f.tar.bz2 linux-stable-2923b27e54242acf27fd16b299e102117c82f52f.zip |
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
Diffstat (limited to 'drivers/nvdimm')
-rw-r--r-- | drivers/nvdimm/pmem.c | 26 | ||||
-rw-r--r-- | drivers/nvdimm/pmem.h | 13 |
2 files changed, 39 insertions, 0 deletions
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index c23649867696..6071e2942053 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -20,6 +20,7 @@ #include <linux/hdreg.h> #include <linux/init.h> #include <linux/platform_device.h> +#include <linux/set_memory.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/badblocks.h> @@ -51,6 +52,30 @@ static struct nd_region *to_region(struct pmem_device *pmem) return to_nd_region(to_dev(pmem)->parent); } +static void hwpoison_clear(struct pmem_device *pmem, + phys_addr_t phys, unsigned int len) +{ + unsigned long pfn_start, pfn_end, pfn; + + /* only pmem in the linear map supports HWPoison */ + if (is_vmalloc_addr(pmem->virt_addr)) + return; + + pfn_start = PHYS_PFN(phys); + pfn_end = pfn_start + PHYS_PFN(len); + for (pfn = pfn_start; pfn < pfn_end; pfn++) { + struct page *page = pfn_to_page(pfn); + + /* + * Note, no need to hold a get_dev_pagemap() reference + * here since we're in the driver I/O path and + * outstanding I/O requests pin the dev_pagemap. + */ + if (test_and_clear_pmem_poison(page)) + clear_mce_nospec(pfn); + } +} + static blk_status_t pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset, unsigned int len) { @@ -65,6 +90,7 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem, if (cleared < len) rc = BLK_STS_IOERR; if (cleared > 0 && cleared / 512) { + hwpoison_clear(pmem, pmem->phys_addr + offset, cleared); cleared /= 512; dev_dbg(dev, "%#llx clear %ld sector%s\n", (unsigned long long) sector, cleared, diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h index a64ebc78b5df..59cfe13ea8a8 100644 --- a/drivers/nvdimm/pmem.h +++ b/drivers/nvdimm/pmem.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NVDIMM_PMEM_H__ #define __NVDIMM_PMEM_H__ +#include <linux/page-flags.h> #include <linux/badblocks.h> #include <linux/types.h> #include <linux/pfn_t.h> @@ -27,4 +28,16 @@ struct pmem_device { long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); + +#ifdef CONFIG_MEMORY_FAILURE +static inline bool test_and_clear_pmem_poison(struct page *page) +{ + return TestClearPageHWPoison(page); +} +#else +static inline bool test_and_clear_pmem_poison(struct page *page) +{ + return false; +} +#endif #endif /* __NVDIMM_PMEM_H__ */ |