From 2ba3e6947aed9bb9575eb1603c0ac6e39185d32a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:22 -0700 Subject: [PATCH] mm/vmalloc: track which page-table levels were modified Track at which levels in the page-table entries were modified by vmap/vunmap. After the page-table has been modified, use that information do decide whether the new arch_sync_kernel_mappings() needs to be called. [akpm@linux-foundation.org: map_kernel_range_noflush() needs the arch_sync_kernel_mappings() call] Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-3-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 16 +++++++ mm/vmalloc.c | 95 ++++++++++++++++++++++++++++++----------- 2 files changed, 85 insertions(+), 26 deletions(-) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3332926295d47f..0efc35dc5b258d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -133,6 +133,22 @@ extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, void vmalloc_sync_mappings(void); void vmalloc_sync_unmappings(void); +/* + * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values + * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() + * needs to be called. + */ +#ifndef ARCH_PAGE_TABLE_SYNC_MASK +#define ARCH_PAGE_TABLE_SYNC_MASK 0 +#endif + +/* + * There is no default implementation for arch_sync_kernel_mappings(). It is + * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK + * is 0. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end); + /* * Lowlevel-APIs (not for driver use!) */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 410bfe26ee73ae..154e3396154cdb 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -69,7 +69,8 @@ static void free_work(struct work_struct *w) /*** Page table manipulation functions ***/ -static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) +static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { pte_t *pte; @@ -78,59 +79,81 @@ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; } -static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) +static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; + int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_clear_huge(pmd)) + + cleared = pmd_clear_huge(pmd); + if (cleared || pmd_bad(*pmd)) + *mask |= PGTBL_PMD_MODIFIED; + + if (cleared) continue; if (pmd_none_or_clear_bad(pmd)) continue; - vunmap_pte_range(pmd, addr, next); + vunmap_pte_range(pmd, addr, next, mask); } while (pmd++, addr = next, addr != end); } -static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end) +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; + int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); - if (pud_clear_huge(pud)) + + cleared = pud_clear_huge(pud); + if (cleared || pud_bad(*pud)) + *mask |= PGTBL_PUD_MODIFIED; + + if (cleared) continue; if (pud_none_or_clear_bad(pud)) continue; - vunmap_pmd_range(pud, addr, next); + vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } -static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; + int cleared; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); - if (p4d_clear_huge(p4d)) + + cleared = p4d_clear_huge(p4d); + if (cleared || p4d_bad(*p4d)) + *mask |= PGTBL_P4D_MODIFIED; + + if (cleared) continue; if (p4d_none_or_clear_bad(p4d)) continue; - vunmap_pud_range(p4d, addr, next); + vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /** * unmap_kernel_range_noflush - unmap kernel VM area - * @addr: start of the VM area to unmap + * @start: start of the VM area to unmap * @size: size of the VM area to unmap * * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size specify @@ -141,24 +164,33 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) * for calling flush_cache_vunmap() on to-be-mapped areas before calling this * function and flush_tlb_kernel_range() after. */ -void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) +void unmap_kernel_range_noflush(unsigned long start, unsigned long size) { - unsigned long end = addr + size; + unsigned long end = start + size; unsigned long next; pgd_t *pgd; + unsigned long addr = start; + pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); + start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); + if (pgd_bad(*pgd)) + mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; - vunmap_p4d_range(pgd, addr, next); + vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); } static int vmap_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { pte_t *pte; @@ -167,7 +199,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, * callers keep track of where we're up to. */ - pte = pte_alloc_kernel(pmd, addr); + pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { @@ -180,55 +212,59 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_pmd_range(pud_t *pud, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; - pmd = pmd_alloc(&init_mm, pud, addr); + pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); - if (vmap_pte_range(pmd, addr, next, prot, pages, nr)) + if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; - pud = pud_alloc(&init_mm, p4d, addr); + pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); - if (vmap_pmd_range(pud, addr, next, prot, pages, nr)) + if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; - p4d = p4d_alloc(&init_mm, pgd, addr); + p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); - if (vmap_pud_range(p4d, addr, next, prot, pages, nr)) + if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; @@ -255,21 +291,28 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, int map_kernel_range_noflush(unsigned long addr, unsigned long size, pgprot_t prot, struct page **pages) { + unsigned long start = addr; unsigned long end = addr + size; unsigned long next; pgd_t *pgd; int err = 0; int nr = 0; + pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr); + if (pgd_bad(*pgd)) + mask |= PGTBL_PGD_MODIFIED; + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) return err; } while (pgd++, addr = next, addr != end); + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); + return 0; }