diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-05-28 01:49:30 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-05-28 01:49:30 +0300 |
commit | 35cdd8656eac470b9abc9de8d4bd268fbc0fb34b (patch) | |
tree | 261e2d2fc3dc5059ce3ffaf9bf231109bbbd6d0e /arch | |
parent | ea6c3bc6ed93dd032568427e92424f6d33deb99b (diff) | |
parent | f42e8e5088b9e791c8f7ac661f68e29a4996a4e3 (diff) | |
download | linux-35cdd8656eac470b9abc9de8d4bd268fbc0fb34b.tar.xz |
Merge tag 'libnvdimm-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm and DAX updates from Dan Williams:
"New support for clearing memory errors when a file is in DAX mode,
alongside with some other fixes and cleanups.
Previously it was only possible to clear these errors using a truncate
or hole-punch operation to trigger the filesystem to reallocate the
block, now, any page aligned write can opportunistically clear errors
as well.
This change spans x86/mm, nvdimm, and fs/dax, and has received the
appropriate sign-offs. Thanks to Jane for her work on this.
Summary:
- Add support for clearing memory error via pwrite(2) on DAX
- Fix 'security overwrite' support in the presence of media errors
- Miscellaneous cleanups and fixes for nfit_test (nvdimm unit tests)"
* tag 'libnvdimm-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
pmem: implement pmem_recovery_write()
pmem: refactor pmem_clear_poison()
dax: add .recovery_write dax_operation
dax: introduce DAX_RECOVERY_WRITE dax access mode
mce: fix set_mce_nospec to always unmap the whole page
x86/mce: relocate set{clear}_mce_nospec() functions
acpi/nfit: rely on mce->misc to determine poison granularity
testing: nvdimm: asm/mce.h is not needed in nfit.c
testing: nvdimm: iomap: make __nfit_test_ioremap a macro
nvdimm: Allow overwrite in the presence of disabled dimms
tools/testing/nvdimm: remove unneeded flush_workqueue
Diffstat (limited to 'arch')
-rw-r--r-- | arch/x86/include/asm/set_memory.h | 52 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 6 | ||||
-rw-r--r-- | arch/x86/mm/pat/set_memory.c | 49 |
3 files changed, 50 insertions, 57 deletions
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 78ca53512486..b45c4d27fd46 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -86,56 +86,4 @@ bool kernel_page_present(struct page *page); extern int kernel_set_to_readonly; -#ifdef CONFIG_X86_64 -/* - * Prevent speculative access to the page by either unmapping - * it (if we do not require access to any part of the page) or - * marking it uncacheable (if we want to try to retrieve data - * from non-poisoned lines in the page). - */ -static inline int set_mce_nospec(unsigned long pfn, bool unmap) -{ - unsigned long decoy_addr; - int rc; - - /* SGX pages are not in the 1:1 map */ - if (arch_is_platform_page(pfn << PAGE_SHIFT)) - return 0; - /* - * We would like to just call: - * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); - * but doing that would radically increase the odds of a - * speculative access to the poison page because we'd have - * the virtual address of the kernel 1:1 mapping sitting - * around in registers. - * Instead we get tricky. We create a non-canonical address - * that looks just like the one we want, but has bit 63 flipped. - * This relies on set_memory_XX() properly sanitizing any __pa() - * results with __PHYSICAL_MASK or PTE_PFN_MASK. - */ - decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); - - if (unmap) - rc = set_memory_np(decoy_addr, 1); - else - rc = set_memory_uc(decoy_addr, 1); - if (rc) - pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); - return rc; -} -#define set_mce_nospec set_mce_nospec - -/* Restore full speculative operation to the pfn. */ -static inline int clear_mce_nospec(unsigned long pfn) -{ - return set_memory_wb((unsigned long) pfn_to_kaddr(pfn), 1); -} -#define clear_mce_nospec clear_mce_nospec -#else -/* - * Few people would run a 32-bit kernel on a machine that supports - * recoverable errors because they have too much memory to boot 32-bit. - */ -#endif - #endif /* _ASM_X86_SET_MEMORY_H */ diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index d775fcd74e98..2c8ec5c71712 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -581,7 +581,7 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, pfn = mce->addr >> PAGE_SHIFT; if (!memory_failure(pfn, 0)) { - set_mce_nospec(pfn, whole_page(mce)); + set_mce_nospec(pfn); mce->kflags |= MCE_HANDLED_UC; } @@ -1318,7 +1318,7 @@ static void kill_me_maybe(struct callback_head *cb) ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags); if (!ret) { - set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page); + set_mce_nospec(p->mce_addr >> PAGE_SHIFT); sync_core(); return; } @@ -1344,7 +1344,7 @@ static void kill_me_never(struct callback_head *cb) p->mce_count = 0; pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr); if (!memory_failure(p->mce_addr >> PAGE_SHIFT, 0)) - set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page); + set_mce_nospec(p->mce_addr >> PAGE_SHIFT); } static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *)) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 0656db33574d..1abd5438f126 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -19,6 +19,7 @@ #include <linux/vmstat.h> #include <linux/kernel.h> #include <linux/cc_platform.h> +#include <linux/set_memory.h> #include <asm/e820/api.h> #include <asm/processor.h> @@ -29,7 +30,6 @@ #include <asm/pgalloc.h> #include <asm/proto.h> #include <asm/memtype.h> -#include <asm/set_memory.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -1805,7 +1805,7 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages, } /* - * _set_memory_prot is an internal helper for callers that have been passed + * __set_memory_prot is an internal helper for callers that have been passed * a pgprot_t value from upper layers and a reservation has already been taken. * If you want to set the pgprot to a specific page protocol, use the * set_memory_xx() functions. @@ -1914,6 +1914,51 @@ int set_memory_wb(unsigned long addr, int numpages) } EXPORT_SYMBOL(set_memory_wb); +/* Prevent speculative access to a page by marking it not-present */ +#ifdef CONFIG_X86_64 +int set_mce_nospec(unsigned long pfn) +{ + unsigned long decoy_addr; + int rc; + + /* SGX pages are not in the 1:1 map */ + if (arch_is_platform_page(pfn << PAGE_SHIFT)) + return 0; + /* + * We would like to just call: + * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); + * but doing that would radically increase the odds of a + * speculative access to the poison page because we'd have + * the virtual address of the kernel 1:1 mapping sitting + * around in registers. + * Instead we get tricky. We create a non-canonical address + * that looks just like the one we want, but has bit 63 flipped. + * This relies on set_memory_XX() properly sanitizing any __pa() + * results with __PHYSICAL_MASK or PTE_PFN_MASK. + */ + decoy_addr = (pfn << PAGE_SHIFT) + (PAGE_OFFSET ^ BIT(63)); + + rc = set_memory_np(decoy_addr, 1); + if (rc) + pr_warn("Could not invalidate pfn=0x%lx from 1:1 map\n", pfn); + return rc; +} + +static int set_memory_present(unsigned long *addr, int numpages) +{ + return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + +/* Restore full speculative operation to the pfn. */ +int clear_mce_nospec(unsigned long pfn) +{ + unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); + + return set_memory_present(&addr, 1); +} +EXPORT_SYMBOL_GPL(clear_mce_nospec); +#endif /* CONFIG_X86_64 */ + int set_memory_x(unsigned long addr, int numpages) { if (!(__supported_pte_mask & _PAGE_NX)) |