From 397b080bb70f30d6b9778b0e607b67efcf64aa6e Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2016 15:20:59 -0700 Subject: arm: get rid of superfluous __GFP_REPEAT __GFP_REPEAT has a rather weak semantic but since it has been introduced around 2.6.12 it has been ignored for low order allocations. PGALLOC_GFP uses __GFP_REPEAT but none of the allocation which uses this flag is for more than order-2. This means that this flag has never been actually useful here because it has always been used only for PAGE_ALLOC_COSTLY requests. Link: http://lkml.kernel.org/r/1464599699-30131-5-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/pgalloc.h | 2 +- arch/arm/mm/pgd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 20febb368844..b2902a5cd780 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -57,7 +57,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) static inline void clean_pte_table(pte_t *pte) { diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c index b8d477321730..c1c1a5c67da1 100644 --- a/arch/arm/mm/pgd.c +++ b/arch/arm/mm/pgd.c @@ -23,7 +23,7 @@ #define __pgd_alloc() kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL) #define __pgd_free(pgd) kfree(pgd) #else -#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, 2) +#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL, 2) #define __pgd_free(pgd) free_pages((unsigned long)pgd, 2) #endif -- cgit v1.2.3 From c965b105bf1509beefbb78d33f721d92240a770c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 26 Jul 2016 15:21:17 -0700 Subject: kbuild: abort build on bad stack protector flag Before, the stack protector flag was sanity checked before .config had been reprocessed. This meant the build couldn't be aborted early, and only a warning could be emitted followed later by the compiler blowing up with an unknown flag. This has caused a lot of confusion over time, so this splits the flag selection from sanity checking and performs the sanity checking after the make has been restarted from a reprocessed .config, so builds can be aborted as early as possible now. Additionally moves the x86-specific sanity check to the same location, since it suffered from the same warn-then-wait-for-compiler-failure problem. Link: http://lkml.kernel.org/r/20160712223043.GA11664@www.outflux.net Signed-off-by: Kees Cook Cc: Michal Marek Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/Makefile | 8 -------- 1 file changed, 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 6fce7f096b88..830ed391e7ef 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -126,14 +126,6 @@ else KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args) endif -# Make sure compiler does not have buggy stack-protector support. -ifdef CONFIG_CC_STACKPROTECTOR - cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh - ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y) - $(warning stack-protector enabled but compiler support broken) - endif -endif - ifdef CONFIG_X86_X32 x32_ld_ok := $(call try-run,\ /bin/echo -e '1: .quad 1b' | \ -- cgit v1.2.3 From a44ce52363a886d45cf08b4b896cb65f0a9553eb Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Tue, 26 Jul 2016 15:21:23 -0700 Subject: m32r: add __ucmpdi2 to fix build failure We are having build failure with m32r and the error message being: ERROR: "__ucmpdi2" [lib/842/842_decompress.ko] undefined! ERROR: "__ucmpdi2" [fs/btrfs/btrfs.ko] undefined! ERROR: "__ucmpdi2" [drivers/scsi/sd_mod.ko] undefined! ERROR: "__ucmpdi2" [drivers/media/i2c/adv7842.ko] undefined! ERROR: "__ucmpdi2" [drivers/md/bcache/bcache.ko] undefined! ERROR: "__ucmpdi2" [drivers/iio/imu/inv_mpu6050/inv-mpu6050.ko] undefined! __ucmpdi2 is introduced to m32r architecture taking example from other architectures like h8300, microblaze, mips. Link: http://lkml.kernel.org/r/1465509213-4280-1-git-send-email-sudipm.mukherjee@gmail.com Signed-off-by: Sudip Mukherjee Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/m32r/kernel/m32r_ksyms.c | 3 +++ arch/m32r/lib/Makefile | 4 ++-- arch/m32r/lib/libgcc.h | 23 +++++++++++++++++++++++ arch/m32r/lib/ucmpdi2.c | 17 +++++++++++++++++ 4 files changed, 45 insertions(+), 2 deletions(-) create mode 100644 arch/m32r/lib/libgcc.h create mode 100644 arch/m32r/lib/ucmpdi2.c (limited to 'arch') diff --git a/arch/m32r/kernel/m32r_ksyms.c b/arch/m32r/kernel/m32r_ksyms.c index b727e693c805..23f26f4adfff 100644 --- a/arch/m32r/kernel/m32r_ksyms.c +++ b/arch/m32r/kernel/m32r_ksyms.c @@ -41,6 +41,9 @@ EXPORT_SYMBOL(cpu_data); EXPORT_SYMBOL(smp_flush_tlb_page); #endif +extern int __ucmpdi2(unsigned long long a, unsigned long long b); +EXPORT_SYMBOL(__ucmpdi2); + /* compiler generated symbol */ extern void __ashldi3(void); extern void __ashrdi3(void); diff --git a/arch/m32r/lib/Makefile b/arch/m32r/lib/Makefile index d16b4e40d1ae..5889eb9610b5 100644 --- a/arch/m32r/lib/Makefile +++ b/arch/m32r/lib/Makefile @@ -3,5 +3,5 @@ # lib-y := checksum.o ashxdi3.o memset.o memcpy.o \ - delay.o strlen.o usercopy.o csum_partial_copy.o - + delay.o strlen.o usercopy.o csum_partial_copy.o \ + ucmpdi2.o diff --git a/arch/m32r/lib/libgcc.h b/arch/m32r/lib/libgcc.h new file mode 100644 index 000000000000..267aa435bc35 --- /dev/null +++ b/arch/m32r/lib/libgcc.h @@ -0,0 +1,23 @@ +#ifndef __ASM_LIBGCC_H +#define __ASM_LIBGCC_H + +#include + +#ifdef __BIG_ENDIAN +struct DWstruct { + int high, low; +}; +#elif defined(__LITTLE_ENDIAN) +struct DWstruct { + int low, high; +}; +#else +#error I feel sick. +#endif + +typedef union { + struct DWstruct s; + long long ll; +} DWunion; + +#endif /* __ASM_LIBGCC_H */ diff --git a/arch/m32r/lib/ucmpdi2.c b/arch/m32r/lib/ucmpdi2.c new file mode 100644 index 000000000000..9d3c682c89b5 --- /dev/null +++ b/arch/m32r/lib/ucmpdi2.c @@ -0,0 +1,17 @@ +#include "libgcc.h" + +int __ucmpdi2(unsigned long long a, unsigned long long b) +{ + const DWunion au = {.ll = a}; + const DWunion bu = {.ll = b}; + + if ((unsigned int)au.s.high < (unsigned int)bu.s.high) + return 0; + else if ((unsigned int)au.s.high > (unsigned int)bu.s.high) + return 2; + if ((unsigned int)au.s.low < (unsigned int)bu.s.low) + return 0; + else if ((unsigned int)au.s.low > (unsigned int)bu.s.low) + return 2; + return 1; +} -- cgit v1.2.3 From 9af3f56ba19ef377170ab3614b9388cc7b7f3d74 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 26 Jul 2016 15:22:39 -0700 Subject: powerpc/mm: check for irq disabled() only if DEBUG_VM is enabled We don't need to check this always. The idea here is to capture the wrong usage of find_linux_pte_or_hugepte and we can do that by occasionally running with DEBUG_VM enabled. Link: http://lkml.kernel.org/r/1464692688-6612-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Reviewed-by: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/pgtable.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index ee09e99097f0..9bd87f269d6d 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -71,10 +71,8 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, bool *is_thp, unsigned *shift) { - if (!arch_irqs_disabled()) { - pr_info("%s called with irq enabled\n", __func__); - dump_stack(); - } + VM_WARN(!arch_irqs_disabled(), + "%s called with irq enabled\n", __func__); return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift); } -- cgit v1.2.3 From e9d55e157034a9efd99405c99c1565d64619d82b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 26 Jul 2016 15:24:09 -0700 Subject: mm: change the interface for __tlb_remove_page() This updates the generic and arch specific implementation to return true if we need to do a tlb flush. That means if a __tlb_remove_page indicate a flush is needed, the page we try to remove need to be tracked and added again after the flush. We need to track it because we have already update the pte to none and we can't just loop back. This change is done to enable us to do a tlb_flush when we try to flush a range that consists of different page sizes. For architectures like ppc64, we can do a range based tlb flush and we need to track page size for that. When we try to remove a huge page, we will force a tlb flush and starts a new mmu gather. [aneesh.kumar@linux.vnet.ibm.com: mm-change-the-interface-for-__tlb_remove_page-v3] Link: http://lkml.kernel.org/r/1465049193-22197-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1464860389-29019-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/tlb.h | 17 +++++++++++++---- arch/ia64/include/asm/tlb.h | 19 ++++++++++++++----- arch/s390/include/asm/tlb.h | 9 +++++++-- arch/sh/include/asm/tlb.h | 8 +++++++- arch/um/include/asm/tlb.h | 8 +++++++- 5 files changed, 48 insertions(+), 13 deletions(-) (limited to 'arch') diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 3cadb726ec88..a9d2aee3826f 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -209,17 +209,26 @@ tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) tlb_flush(tlb); } -static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { + if (tlb->nr == tlb->max) + return true; tlb->pages[tlb->nr++] = page; - VM_BUG_ON(tlb->nr > tlb->max); - return tlb->max - tlb->nr; + return false; } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { - if (!__tlb_remove_page(tlb, page)) + if (__tlb_remove_page(tlb, page)) { tlb_flush_mmu(tlb); + __tlb_remove_page(tlb, page); + } +} + +static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, + struct page *page) +{ + return __tlb_remove_page(tlb, page); } static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 39d64e0df1de..e7da41aa9110 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -205,17 +205,18 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) * must be delayed until after the TLB has been flushed (see comments at the beginning of * this file). */ -static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { + if (tlb->nr == tlb->max) + return true; + tlb->need_flush = 1; if (!tlb->nr && tlb->pages == tlb->local) __tlb_alloc_page(tlb); tlb->pages[tlb->nr++] = page; - VM_BUG_ON(tlb->nr > tlb->max); - - return tlb->max - tlb->nr; + return false; } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) @@ -235,8 +236,16 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) { - if (!__tlb_remove_page(tlb, page)) + if (__tlb_remove_page(tlb, page)) { tlb_flush_mmu(tlb); + __tlb_remove_page(tlb, page); + } +} + +static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, + struct page *page) +{ + return __tlb_remove_page(tlb, page); } /* diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 7a92e69c50bc..30759b560849 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -87,10 +87,10 @@ static inline void tlb_finish_mmu(struct mmu_gather *tlb, * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page * has already been freed, so just do free_page_and_swap_cache. */ -static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) +static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { free_page_and_swap_cache(page); - return 1; /* avoid calling tlb_flush_mmu */ + return false; /* avoid calling tlb_flush_mmu */ } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) @@ -98,6 +98,11 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) free_page_and_swap_cache(page); } +static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, + struct page *page) +{ + return __tlb_remove_page(tlb, page); +} /* * pte_free_tlb frees a pte table and clears the CRSTE for the * page table from the tlb. diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 62f80d2a9df9..21ae8f5546b2 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -101,7 +101,7 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb) static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { free_page_and_swap_cache(page); - return 1; /* avoid calling tlb_flush_mmu */ + return false; /* avoid calling tlb_flush_mmu */ } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) @@ -109,6 +109,12 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) __tlb_remove_page(tlb, page); } +static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, + struct page *page) +{ + return __tlb_remove_page(tlb, page); +} + #define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep) #define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp) #define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index 16eb63fac57d..3dc4cbb3c2c0 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -102,7 +102,7 @@ static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) { tlb->need_flush = 1; free_page_and_swap_cache(page); - return 1; /* avoid calling tlb_flush_mmu */ + return false; /* avoid calling tlb_flush_mmu */ } static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) @@ -110,6 +110,12 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) __tlb_remove_page(tlb, page); } +static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, + struct page *page) +{ + return __tlb_remove_page(tlb, page); +} + /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * -- cgit v1.2.3 From e77b0852b551ffd8b29fa0225e1ef62c195e3160 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 26 Jul 2016 15:24:12 -0700 Subject: mm/mmu_gather: track page size with mmu gather and force flush if page size change This allows an arch which needs to do special handing with respect to different page size when flushing tlb to implement the same in mmu gather. Link: http://lkml.kernel.org/r/1465049193-22197-3-git-send-email-aneesh.kumar@linux.vnet.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Michael Ellerman Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Vlastimil Babka Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/tlb.h | 12 ++++++++++++ arch/ia64/include/asm/tlb.h | 12 ++++++++++++ arch/s390/include/asm/tlb.h | 13 +++++++++++++ arch/sh/include/asm/tlb.h | 12 ++++++++++++ arch/um/include/asm/tlb.h | 12 ++++++++++++ 5 files changed, 61 insertions(+) (limited to 'arch') diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index a9d2aee3826f..1e25cd80589e 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -225,12 +225,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) } } +static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return __tlb_remove_page(tlb, page); +} + static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page(tlb, page); } +static inline void tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return tlb_remove_page(tlb, page); +} + static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr) { diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index e7da41aa9110..77e541cf0e5d 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -242,12 +242,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) } } +static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return __tlb_remove_page(tlb, page); +} + static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page(tlb, page); } +static inline void tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return tlb_remove_page(tlb, page); +} + /* * Remove TLB entry for PTE mapped at virtual address ADDRESS. This is called for any * PTE, not just those pointing to (normal) physical memory. diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 30759b560849..15711de10403 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -98,11 +98,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) free_page_and_swap_cache(page); } +static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return __tlb_remove_page(tlb, page); +} + static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page(tlb, page); } + +static inline void tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return tlb_remove_page(tlb, page); +} + /* * pte_free_tlb frees a pte table and clears the CRSTE for the * page table from the tlb. diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h index 21ae8f5546b2..025cdb1032f6 100644 --- a/arch/sh/include/asm/tlb.h +++ b/arch/sh/include/asm/tlb.h @@ -109,12 +109,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) __tlb_remove_page(tlb, page); } +static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return __tlb_remove_page(tlb, page); +} + static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page(tlb, page); } +static inline void tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return tlb_remove_page(tlb, page); +} + #define pte_free_tlb(tlb, ptep, addr) pte_free((tlb)->mm, ptep) #define pmd_free_tlb(tlb, pmdp, addr) pmd_free((tlb)->mm, pmdp) #define pud_free_tlb(tlb, pudp, addr) pud_free((tlb)->mm, pudp) diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h index 3dc4cbb3c2c0..821ff0acfe17 100644 --- a/arch/um/include/asm/tlb.h +++ b/arch/um/include/asm/tlb.h @@ -110,12 +110,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page) __tlb_remove_page(tlb, page); } +static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return __tlb_remove_page(tlb, page); +} + static inline bool __tlb_remove_pte_page(struct mmu_gather *tlb, struct page *page) { return __tlb_remove_page(tlb, page); } +static inline void tlb_remove_page_size(struct mmu_gather *tlb, + struct page *page, int page_size) +{ + return tlb_remove_page(tlb, page); +} + /** * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation. * -- cgit v1.2.3 From 3e79ec7ddc33e5c69c20ce7f768d0e5c8b824f69 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Tue, 26 Jul 2016 15:24:30 -0700 Subject: arch: x86: charge page tables to kmemcg Page tables can bite a relatively big chunk off system memory and their allocations are easy to trigger from userspace, so they should be accounted to kmemcg. This patch marks page table allocations as __GFP_ACCOUNT for x86. Note we must not charge allocations of kernel page tables, because they can be shared among processes from different cgroups so accounting them to a particular one can pin other cgroups for indefinitely long. So we clear __GFP_ACCOUNT flag if a page table is allocated for the kernel. Link: http://lkml.kernel.org/r/7d5c54f6a2bcbe76f03171689440003d87e6c742.1464079538.git.vdavydov@virtuozzo.com Signed-off-by: Vladimir Davydov Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Johannes Weiner Cc: Michal Hocko Cc: Eric Dumazet Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgalloc.h | 12 ++++++++++-- arch/x86/mm/pgtable.c | 10 +++++++--- 2 files changed, 17 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index 574c23cf761a..b6d425999f99 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -81,7 +81,11 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; - page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); + gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + page = alloc_pages(gfp, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -125,7 +129,11 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)get_zeroed_page(GFP_KERNEL); + gfp_t gfp = GFP_KERNEL_ACCOUNT; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; + return (pud_t *)get_zeroed_page(gfp); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index aa0ff4b02a96..3feec5af4e67 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include #include -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO +#define PGALLOC_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | __GFP_ZERO) #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM @@ -18,7 +18,7 @@ gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP; pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(PGALLOC_GFP); + return (pte_t *)__get_free_page(PGALLOC_GFP & ~__GFP_ACCOUNT); } pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) @@ -207,9 +207,13 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; bool failed = false; + gfp_t gfp = PGALLOC_GFP; + + if (mm == &init_mm) + gfp &= ~__GFP_ACCOUNT; for(i = 0; i < PREALLOCATED_PMDS; i++) { - pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP); + pmd_t *pmd = (pmd_t *)__get_free_page(gfp); if (!pmd) failed = true; if (pmd && !pgtable_pmd_page_ctor(virt_to_page(pmd))) { -- cgit v1.2.3 From dcddffd41d3f1d3bdcc1dce3f1cd142779b6d4c1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 26 Jul 2016 15:25:18 -0700 Subject: mm: do not pass mm_struct into handle_mm_fault We always have vma->vm_mm around. Link: http://lkml.kernel.org/r/1466021202-61880-8-git-send-email-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/mm/fault.c | 2 +- arch/arc/mm/fault.c | 2 +- arch/arm/mm/fault.c | 2 +- arch/arm64/mm/fault.c | 2 +- arch/avr32/mm/fault.c | 2 +- arch/cris/mm/fault.c | 2 +- arch/frv/mm/fault.c | 2 +- arch/hexagon/mm/vm_fault.c | 2 +- arch/ia64/mm/fault.c | 2 +- arch/m32r/mm/fault.c | 2 +- arch/m68k/mm/fault.c | 2 +- arch/metag/mm/fault.c | 2 +- arch/microblaze/mm/fault.c | 2 +- arch/mips/mm/fault.c | 2 +- arch/mn10300/mm/fault.c | 2 +- arch/nios2/mm/fault.c | 2 +- arch/openrisc/mm/fault.c | 2 +- arch/parisc/mm/fault.c | 2 +- arch/powerpc/mm/copro_fault.c | 2 +- arch/powerpc/mm/fault.c | 2 +- arch/s390/mm/fault.c | 2 +- arch/score/mm/fault.c | 2 +- arch/sh/mm/fault.c | 2 +- arch/sparc/mm/fault_32.c | 4 ++-- arch/sparc/mm/fault_64.c | 2 +- arch/tile/mm/fault.c | 2 +- arch/um/kernel/trap.c | 2 +- arch/unicore32/mm/fault.c | 2 +- arch/x86/mm/fault.c | 2 +- arch/xtensa/mm/fault.c | 2 +- 30 files changed, 31 insertions(+), 31 deletions(-) (limited to 'arch') diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 4a905bd667e2..83e9eee57a55 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -147,7 +147,7 @@ retry: /* If for any reason at all we couldn't handle the fault, make sure we exit gracefully rather than endlessly redo the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index af63f4a13e60..e94e5aa33985 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -137,7 +137,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); /* If Pagefault was interrupted by SIGKILL, exit page fault "early" */ if (unlikely(fatal_signal_pending(current))) { diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index ad5841856007..3a2e678b8d30 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -243,7 +243,7 @@ good_area: goto out; } - return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags); + return handle_mm_fault(vma, addr & PAGE_MASK, flags); check_stack: /* Don't allow expansion below FIRST_USER_ADDRESS */ diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index b1166d1e5955..031820d989a8 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -233,7 +233,7 @@ good_area: goto out; } - return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags); + return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags); check_stack: if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr)) diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c index c03533937a9f..a4b7edac8f10 100644 --- a/arch/avr32/mm/fault.c +++ b/arch/avr32/mm/fault.c @@ -134,7 +134,7 @@ good_area: * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c index 3066d40a6db1..112ef26c7f2e 100644 --- a/arch/cris/mm/fault.c +++ b/arch/cris/mm/fault.c @@ -168,7 +168,7 @@ retry: * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c index 61d99767fe16..614a46c413d2 100644 --- a/arch/frv/mm/fault.c +++ b/arch/frv/mm/fault.c @@ -164,7 +164,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, ear0, flags); + fault = handle_mm_fault(vma, ear0, flags); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index 8704c9320032..bd7c251e2bce 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -101,7 +101,7 @@ good_area: break; } - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 70b40d1205a6..fa6ad95e992e 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -159,7 +159,7 @@ retry: * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c index 8f9875b7933d..a3785d3644c2 100644 --- a/arch/m32r/mm/fault.c +++ b/arch/m32r/mm/fault.c @@ -196,7 +196,7 @@ good_area: */ addr = (address & PAGE_MASK); set_thread_fault_code(error_code); - fault = handle_mm_fault(mm, vma, addr, flags); + fault = handle_mm_fault(vma, addr, flags); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index 6a94cdd0c830..bd66a0b20c6b 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -136,7 +136,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); pr_debug("handle_mm_fault returns %d\n", fault); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) diff --git a/arch/metag/mm/fault.c b/arch/metag/mm/fault.c index f57edca63609..372783a67dda 100644 --- a/arch/metag/mm/fault.c +++ b/arch/metag/mm/fault.c @@ -133,7 +133,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return 0; diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index 177dfc003643..abb678ccde6f 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -216,7 +216,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 4b88fa031891..9560ad731120 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -153,7 +153,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c index 4a1d181ed32f..f23781d6bbb3 100644 --- a/arch/mn10300/mm/fault.c +++ b/arch/mn10300/mm/fault.c @@ -254,7 +254,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index b51878b0c6b8..affc4eb3f89e 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -131,7 +131,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index 230ac20ae794..e94cd225e816 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -163,7 +163,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 16dbe81c97c9..163af2c31d76 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -239,7 +239,7 @@ good_area: * fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index 6527882ce05e..bb0354222b11 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -75,7 +75,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, } ret = 0; - *flt = handle_mm_fault(mm, vma, ea, is_write ? FAULT_FLAG_WRITE : 0); + *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0); if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index a67c6d781c52..a4db22f65021 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -429,7 +429,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { if (fault & VM_FAULT_SIGSEGV) goto bad_area; diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 19288c1b36d3..6c47488745ae 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -456,7 +456,7 @@ retry: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); /* No reason to continue if interrupted by SIGKILL. */ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) { fault = VM_FAULT_SIGNAL; diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c index 37a6c2e0e969..995b71e4db4b 100644 --- a/arch/score/mm/fault.c +++ b/arch/score/mm/fault.c @@ -111,7 +111,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 79d8276377d1..9bf876780cef 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -487,7 +487,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR))) if (mm_fault_error(regs, error_code, address, fault)) diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index b6c559cbd64d..4714061d6cd3 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -241,7 +241,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; @@ -411,7 +411,7 @@ good_area: if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } - switch (handle_mm_fault(mm, vma, address, flags)) { + switch (handle_mm_fault(vma, address, flags)) { case VM_FAULT_SIGBUS: case VM_FAULT_OOM: goto do_sigbus; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index cb841a33da59..6c43b924a7a2 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -436,7 +436,7 @@ good_area: goto bad_area; } - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto exit_exception; diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 26734214818c..beba986589e5 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -434,7 +434,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return 0; diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 98783dd0fa2e..ad8f206ab5e8 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -73,7 +73,7 @@ good_area: do { int fault; - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; diff --git a/arch/unicore32/mm/fault.c b/arch/unicore32/mm/fault.c index 2ec3d3adcefc..6c7f70bcaae3 100644 --- a/arch/unicore32/mm/fault.c +++ b/arch/unicore32/mm/fault.c @@ -194,7 +194,7 @@ good_area: * If for any reason at all we couldn't handle the fault, make * sure we exit gracefully rather than endlessly redo the fault. */ - fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, flags); + fault = handle_mm_fault(vma, addr & PAGE_MASK, flags); return fault; check_stack: diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d22161ab941d..dc8023060456 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1353,7 +1353,7 @@ good_area: * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; /* diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 7f4a1fdb1502..2725e08ef353 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -110,7 +110,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(mm, vma, address, flags); + fault = handle_mm_fault(vma, address, flags); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) return; -- cgit v1.2.3