vmalloc_to_page returns NULL for addresses mapped by larger pages[*]. Whether or not a vmap is huge depends on the architecture details, alignments, boot options, etc., which the caller can not be expected to know. Therefore HUGE_VMAP is a regression for vmalloc_to_page. This change teaches vmalloc_to_page about larger pages, and returns the struct page that corresponds to the offset within the large page. This makes the API agnostic to mapping implementation details. [*] As explained by commit 029c54b095995 ("mm/vmalloc.c: huge-vmap: fail gracefully on unexpected huge vmap mappings") Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx> --- include/asm-generic/4level-fixup.h | 1 + include/asm-generic/5level-fixup.h | 1 + mm/vmalloc.c | 37 +++++++++++++++++++----------- 3 files changed, 26 insertions(+), 13 deletions(-) diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index e3667c9a33a5..3cc65a4dd093 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -20,6 +20,7 @@ #define pud_none(pud) 0 #define pud_bad(pud) 0 #define pud_present(pud) 1 +#define pud_large(pud) 0 #define pud_ERROR(pud) do { } while (0) #define pud_clear(pud) pgd_clear(pud) #define pud_val(pud) pgd_val(pud) diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index bb6cb347018c..c4377db09a4f 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -22,6 +22,7 @@ #define p4d_none(p4d) 0 #define p4d_bad(p4d) 0 #define p4d_present(p4d) 1 +#define p4d_large(p4d) 0 #define p4d_ERROR(p4d) do { } while (0) #define p4d_clear(p4d) pgd_clear(p4d) #define p4d_val(p4d) pgd_val(p4d) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4c9e150e5ad3..4be98f700862 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -36,6 +36,7 @@ #include <linux/rbtree_augmented.h> #include <linux/uaccess.h> +#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> @@ -284,26 +285,36 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) if (pgd_none(*pgd)) return NULL; + p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; - pud = pud_offset(p4d, addr); + if (WARN_ON_ONCE(p4d_bad(*p4d))) + return NULL; +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + if (p4d_large(*p4d)) + return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); +#endif - /* - * Don't dereference bad PUD or PMD (below) entries. This will also - * identify huge mappings, which we may encounter on architectures - * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be - * identified as vmalloc addresses by is_vmalloc_addr(), but are - * not [unambiguously] associated with a struct page, so there is - * no correct value to return for them. - */ - WARN_ON_ONCE(pud_bad(*pud)); - if (pud_none(*pud) || pud_bad(*pud)) + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + if (pud_large(*pud)) + return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); +#endif + pmd = pmd_offset(pud, addr); - WARN_ON_ONCE(pmd_bad(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + if (pmd_none(*pmd)) + return NULL; + if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + if (pmd_large(*pmd)) + return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); +#endif ptep = pte_offset_map(pmd, addr); pte = *ptep; -- 2.20.1