From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nicholas Piggin Subject: [PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings Date: Mon, 13 Apr 2020 22:53:00 +1000 Message-ID: <20200413125303.423864-2-npiggin@gmail.com> References: <20200413125303.423864-1-npiggin@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20200413125303.423864-1-npiggin@gmail.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane-mx.org@lists.infradead.org To: linux-mm@kvack.org Cc: linux-arch@vger.kernel.org, Catalin Marinas , x86@kernel.org, linuxppc-dev@lists.ozlabs.org, Nicholas Piggin , linux-kernel@vger.kernel.org, Ingo Molnar , Borislav Petkov , "H. Peter Anvin" , Thomas Gleixner , Will Deacon , linux-arm-kernel@lists.infradead.org List-Id: linux-arch.vger.kernel.org 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 --- mm/vmalloc.c | 40 ++++++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 399f219544f7..1afec7def23f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -36,6 +36,7 @@ #include #include +#include #include #include @@ -272,7 +273,9 @@ int is_vmalloc_or_module_addr(const void *x) } /* - * Walk a vmap address to the struct page it maps. + * Walk a vmap address to the struct page it maps. Huge vmap mappings will + * return the tail page that corresponds to the base page address, which + * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { @@ -292,25 +295,33 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) if (pgd_none(*pgd)) return NULL; + if (WARN_ON_ONCE(pgd_leaf(*pgd))) + return NULL; /* XXX: no allowance for huge pgd */ + if (WARN_ON_ONCE(pgd_bad(*pgd))) + return NULL; + p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; - pud = pud_offset(p4d, addr); + if (p4d_leaf(*p4d)) + return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(p4d_bad(*p4d))) + return NULL; - /* - * 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 (pud_leaf(*pud)) + return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; + 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 (pmd_leaf(*pmd)) + return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; ptep = pte_offset_map(pmd, addr); @@ -318,6 +329,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) if (pte_present(pte)) page = pte_page(pte); pte_unmap(ptep); + return page; } EXPORT_SYMBOL(vmalloc_to_page); -- 2.23.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Nicholas Piggin Subject: [PATCH v2 1/4] mm/vmalloc: fix vmalloc_to_page for huge vmap mappings Date: Mon, 13 Apr 2020 22:53:00 +1000 Message-ID: <20200413125303.423864-2-npiggin@gmail.com> In-Reply-To: <20200413125303.423864-1-npiggin@gmail.com> References: <20200413125303.423864-1-npiggin@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org To: linux-mm@kvack.org Cc: Nicholas Piggin , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, Catalin Marinas , Will Deacon , linux-arm-kernel@lists.infradead.org, Thomas Gleixner , Ingo Molnar , Borislav Petkov , x86@kernel.org, "H. Peter Anvin" List-ID: Message-ID: <20200413125300.S5J5J140EMgntlED1V7CA-eXy9DrnWKGnYVBeiupi9Q@z> 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 --- mm/vmalloc.c | 40 ++++++++++++++++++++++++++-------------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 399f219544f7..1afec7def23f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -36,6 +36,7 @@ #include =20 #include +#include #include #include =20 @@ -272,7 +273,9 @@ int is_vmalloc_or_module_addr(const void *x) } =20 /* - * Walk a vmap address to the struct page it maps. + * Walk a vmap address to the struct page it maps. Huge vmap mappings wi= ll + * return the tail page that corresponds to the base page address, which + * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { @@ -292,25 +295,33 @@ struct page *vmalloc_to_page(const void *vmalloc_ad= dr) =20 if (pgd_none(*pgd)) return NULL; + if (WARN_ON_ONCE(pgd_leaf(*pgd))) + return NULL; /* XXX: no allowance for huge pgd */ + if (WARN_ON_ONCE(pgd_bad(*pgd))) + return NULL; + p4d =3D p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; - pud =3D pud_offset(p4d, addr); + if (p4d_leaf(*p4d)) + return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(p4d_bad(*p4d))) + return NULL; =20 - /* - * 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=3Dy. 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 =3D pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + if (pud_leaf(*pud)) + return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; + pmd =3D pmd_offset(pud, addr); - WARN_ON_ONCE(pmd_bad(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + if (pmd_none(*pmd)) + return NULL; + if (pmd_leaf(*pmd)) + return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; =20 ptep =3D pte_offset_map(pmd, addr); @@ -318,6 +329,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr= ) if (pte_present(pte)) page =3D pte_page(pte); pte_unmap(ptep); + return page; } EXPORT_SYMBOL(vmalloc_to_page); --=20 2.23.0