On Tue, Mar 27, 2018 at 06:27:24PM +0200, Greg Kroah-Hartman wrote:
4.4-stable review patch. If anyone has any objections, please let me know.
From: Toshi Kani toshi.kani@hpe.com
commit b6bdb7517c3d3f41f20e5c2948d6bc3f8897394e upstream.
On architectures with CONFIG_HAVE_ARCH_HUGE_VMAP set, ioremap() may create pud/pmd mappings. A kernel panic was observed on arm64 systems with Cortex-A75 in the following steps as described by Hanjun Guo.
- ioremap a 4K size, valid page table will build,
- iounmap it, pte0 will set to 0;
- ioremap the same address with 2M size, pgd/pmd is unchanged, then set the a new value for pmd;
- pte0 is leaked;
- CPU may meet exception because the old pmd is still in TLB, which will lead to kernel panic.
This panic is not reproducible on x86. INVLPG, called from iounmap, purges all levels of entries associated with purged address on x86. x86 still has memory leak.
The patch changes the ioremap path to free unmapped page table(s) since doing so in the unmap path has the following issues:
The iounmap() path is shared with vunmap(). Since vmap() only supports pte mappings, making vunmap() to free a pte page is an overhead for regular vmap users as they do not need a pte page freed up.
Checking if all entries in a pte page are cleared in the unmap path is racy, and serializing this check is expensive.
The unmap path calls free_vmap_area_noflush() to do lazy TLB purges. Clearing a pud/pmd entry before the lazy TLB purges needs extra TLB purge.
Add two interfaces, pud_free_pmd_page() and pmd_free_pte_page(), which clear a given pud/pmd entry and free up a page for the lower level entries.
This patch implements their stub functions on x86 and arm64, which work as workaround.
[akpm@linux-foundation.org: fix typo in pmd_free_pte_page() stub] Link: http://lkml.kernel.org/r/20180314180155.19492-2-toshi.kani@hpe.com Fixes: e61ce6ade404e ("mm: change ioremap to set up huge I/O mappings") Reported-by: Lei Li lious.lilei@hisilicon.com Signed-off-by: Toshi Kani toshi.kani@hpe.com Cc: Catalin Marinas catalin.marinas@arm.com Cc: Wang Xuefeng wxf.wang@hisilicon.com Cc: Will Deacon will.deacon@arm.com Cc: Hanjun Guo guohanjun@huawei.com Cc: Michal Hocko mhocko@suse.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Ingo Molnar mingo@redhat.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: Borislav Petkov bp@suse.de Cc: Matthew Wilcox willy@infradead.org Cc: Chintan Pandya cpandya@codeaurora.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
This patch causes the following build error on 4.4 arm64:
$ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- O=build-arm64 defconfig $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- O=build-arm64
CC arch/arm64/mm/mmu.o ../arch/arm64/mm/mmu.c:701:5: error: redefinition of ‘pud_free_pmd_page’ int pud_free_pmd_page(pud_t *pud) ^~~~~~~~~~~~~~~~~ In file included from ../arch/arm64/include/asm/pgtable.h:682:0, from ../include/linux/mm.h:55, from ../include/linux/mman.h:4, from ../arch/arm64/mm/mmu.c:25: ../include/asm-generic/pgtable.h:777:19: note: previous definition of ‘pud_free_pmd_page’ was here static inline int pud_free_pmd_page(pud_t *pud) ^~~~~~~~~~~~~~~~~ ../arch/arm64/mm/mmu.c:706:5: error: redefinition of ‘pmd_free_pte_page’ int pmd_free_pte_page(pmd_t *pmd) ^~~~~~~~~~~~~~~~~ In file included from ../arch/arm64/include/asm/pgtable.h:682:0, from ../include/linux/mm.h:55, from ../include/linux/mman.h:4, from ../arch/arm64/mm/mmu.c:25: ../include/asm-generic/pgtable.h:781:19: note: previous definition of ‘pmd_free_pte_page’ was here static inline int pmd_free_pte_page(pmd_t *pmd) ^~~~~~~~~~~~~~~~~ make[2]: *** [../scripts/Makefile.build:270: arch/arm64/mm/mmu.o] Error 1 make[1]: *** [/home/drue/src/linux/4.4-rc/Makefile:969: arch/arm64/mm] Error 2 make[1]: Leaving directory '/home/drue/src/linux/4.4-rc/build-arm64' make: *** [Makefile:152: sub-make] Error 2
arch/arm64/mm/mmu.c | 10 ++++++++++ arch/x86/mm/pgtable.c | 24 ++++++++++++++++++++++++ include/asm-generic/pgtable.h | 10 ++++++++++ lib/ioremap.c | 6 ++++-- 4 files changed, 48 insertions(+), 2 deletions(-)
--- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -697,3 +697,13 @@ void *__init fixmap_remap_fdt(phys_addr_ return dt_virt; }
+int pud_free_pmd_page(pud_t *pud) +{
- return pud_none(*pud);
+}
+int pmd_free_pte_page(pmd_t *pmd) +{
- return pmd_none(*pmd);
+} --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -666,4 +666,28 @@ int pmd_clear_huge(pmd_t *pmd) return 0; }
+/**
- pud_free_pmd_page - Clear pud entry and free pmd page.
- @pud: Pointer to a PUD.
- Context: The pud range has been unmaped and TLB purged.
- Return: 1 if clearing the entry succeeded. 0 otherwise.
- */
+int pud_free_pmd_page(pud_t *pud) +{
- return pud_none(*pud);
+}
+/**
- pmd_free_pte_page - Clear pmd entry and free pte page.
- @pmd: Pointer to a PMD.
- Context: The pmd range has been unmaped and TLB purged.
- Return: 1 if clearing the entry succeeded. 0 otherwise.
- */
+int pmd_free_pte_page(pmd_t *pmd) +{
- return pmd_none(*pmd);
+} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -755,6 +755,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); +int pud_free_pmd_page(pud_t *pud); +int pmd_free_pte_page(pmd_t *pmd); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { @@ -772,6 +774,14 @@ static inline int pmd_clear_huge(pmd_t * { return 0; } +static inline int pud_free_pmd_page(pud_t *pud) +{
- return 0;
+} +static inline int pmd_free_pte_page(pmd_t *pmd) +{
- return 0;
+} #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #endif /* !__ASSEMBLY__ */ --- a/lib/ioremap.c +++ b/lib/ioremap.c @@ -83,7 +83,8 @@ static inline int ioremap_pmd_range(pud_ if (ioremap_pmd_enabled() && ((next - addr) == PMD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PMD_SIZE)) {
IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&pmd_free_pte_page(pmd)) { if (pmd_set_huge(pmd, phys_addr + addr, prot)) continue;@@ -109,7 +110,8 @@ static inline int ioremap_pud_range(pgd_ if (ioremap_pud_enabled() && ((next - addr) == PUD_SIZE) &&
IS_ALIGNED(phys_addr + addr, PUD_SIZE)) {
IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&pud_free_pmd_page(pud)) { if (pud_set_huge(pud, phys_addr + addr, prot)) continue;