Mark poisoned page as not present, and to reverse the 'np' effect, restate the _PAGE_PRESENT bit. Please refer to discussions here for reason behind the decision. https://lore.kernel.org/all/CAPcyv4hrXPb1tASBZUg-GgdVs0OOFKXMXLiHmktg_kFi7YBMyQ@xxxxxxxxxxxxxx/ Fixes: 284ce4011ba6 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()") Signed-off-by: Jane Chu <jane.chu@xxxxxxxxxx> --- arch/x86/include/asm/set_memory.h | 17 +++++------------ arch/x86/kernel/cpu/mce/core.c | 6 +++--- arch/x86/mm/pat/set_memory.c | 8 +++++++- include/linux/set_memory.h | 2 +- 4 files changed, 16 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 872617542bbc..63539dfc6ae1 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -49,6 +49,7 @@ int set_memory_decrypted(unsigned long addr, int numpages); int set_memory_np_noalias(unsigned long addr, int numpages); int set_memory_nonglobal(unsigned long addr, int numpages); int set_memory_global(unsigned long addr, int numpages); +int _set_memory_present(unsigned long addr, int numpages); int set_pages_array_uc(struct page **pages, int addrinarray); int set_pages_array_wc(struct page **pages, int addrinarray); @@ -88,13 +89,8 @@ void notify_range_enc_status_changed(unsigned long vaddr, int npages, bool enc); 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) +/* Prevent speculative access to a page by marking it not-present */ +static inline int set_mce_nospec(unsigned long pfn) { unsigned long decoy_addr; int rc; @@ -113,10 +109,7 @@ static inline int set_mce_nospec(unsigned long pfn, bool unmap) */ 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); + 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; @@ -126,7 +119,7 @@ static inline int set_mce_nospec(unsigned long pfn, bool unmap) /* 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); + return _set_memory_present((unsigned long) pfn_to_kaddr(pfn), 1); } #define clear_mce_nospec clear_mce_nospec #else diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6ed365337a3b..814c016b75ab 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -601,7 +601,7 @@ 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; } @@ -1255,7 +1255,7 @@ 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; } @@ -1279,7 +1279,7 @@ 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 b4072115c8ef..68d84c8bd977 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1816,7 +1816,7 @@ 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. @@ -1983,6 +1983,12 @@ int set_memory_global(unsigned long addr, int numpages) __pgprot(_PAGE_GLOBAL), 0); } +int _set_memory_present(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} +EXPORT_SYMBOL_GPL(_set_memory_present); + /* * __set_memory_enc_pgtable() is used for the hypervisors that get * informed about "encryption" status via page tables. diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index f36be5166c19..9ad898d40e7e 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -43,7 +43,7 @@ static inline bool can_set_direct_map(void) #endif /* CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifndef set_mce_nospec -static inline int set_mce_nospec(unsigned long pfn, bool unmap) +static inline int set_mce_nospec(unsigned long pfn) { return 0; } -- 2.18.4
