From d8626138009ba58ae2c22356966c2edaa1f1c3b5 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:18 -0700 Subject: mm: add functions to track page directory modifications Patch series "mm: Get rid of vmalloc_sync_(un)mappings()", v3. After the recent issue with vmalloc and tracing code[1] on x86 and a long history of previous issues related to the vmalloc_sync_mappings() interface, I thought the time has come to remove it. Please see [2], [3], and [4] for some other issues in the past. The patches add tracking of page-table directory changes to the vmalloc and ioremap code. Depending on which page-table levels changes have been made, a new per-arch function is called: arch_sync_kernel_mappings(). On x86-64 with 4-level paging, this function will not be called more than 64 times in a systems runtime (because vmalloc-space takes 64 PGD entries which are only populated, but never cleared). As a side effect this also allows to get rid of vmalloc faults on x86, making it safe to touch vmalloc'ed memory in the page-fault handler. Note that this potentially includes per-cpu memory. This patch (of 7): Add page-table allocation functions which will keep track of changed directory entries. They are needed for new PGD, P4D, PUD, and PMD entries and will be used in vmalloc and ioremap code to decide whether any changes in the kernel mappings need to be synchronized between page-tables in the system. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: "H . Peter Anvin" Cc: Dave Hansen Cc: "Rafael J. Wysocki" Cc: Arnd Bergmann Cc: Steven Rostedt (VMware) Cc: Vlastimil Babka Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20200515140023.25469-1-joro@8bytes.org Link: http://lkml.kernel.org/r/20200515140023.25469-2-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index ebbb0acbeee2..fda41eb7f1c8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2091,13 +2091,54 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } + +static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, + unsigned long address, + pgtbl_mod_mask *mod_mask) + +{ + if (unlikely(pgd_none(*pgd))) { + if (__p4d_alloc(mm, pgd, address)) + return NULL; + *mod_mask |= PGTBL_PGD_MODIFIED; + } + + return p4d_offset(pgd, address); +} + #endif /* !__ARCH_HAS_5LEVEL_HACK */ +static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(p4d_none(*p4d))) { + if (__pud_alloc(mm, p4d, address)) + return NULL; + *mod_mask |= PGTBL_P4D_MODIFIED; + } + + return pud_offset(p4d, address); +} + static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } + +static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, + unsigned long address, + pgtbl_mod_mask *mod_mask) +{ + if (unlikely(pud_none(*pud))) { + if (__pmd_alloc(mm, pud, address)) + return NULL; + *mod_mask |= PGTBL_PUD_MODIFIED; + } + + return pmd_offset(pud, address); +} #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS @@ -2213,6 +2254,11 @@ static inline void pgtable_pte_page_dtor(struct page *page) ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) +#define pte_alloc_kernel_track(pmd, address, mask) \ + ((unlikely(pmd_none(*(pmd))) && \ + (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ + NULL: pte_offset_kernel(pmd, address)) + #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) -- cgit v1.2.3