From 624531886987f0f1b5d01fb598034d039198e090 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 7 Jun 2016 17:57:54 +0100 Subject: ARM: 8578/1: mm: ensure pmd_present only checks the valid bit In a subsequent patch, pmd_mknotpresent will clear the valid bit of the pmd entry, resulting in a not-present entry from the hardware's perspective. Unfortunately, pmd_present simply checks for a non-zero pmd value and will therefore continue to return true even after a pmd_mknotpresent operation. Since pmd_mknotpresent is only used for managing huge entries, this is only an issue for the 3-level case. This patch fixes the 3-level pmd_present implementation to take into account the valid bit. For bisectability, the change is made before the fix to pmd_mknotpresent. [catalin.marinas@arm.com: comment update regarding pmd_mknotpresent patch] Fixes: 8d9625070073 ("ARM: mm: Transparent huge page support for LPAE systems.") Cc: # 3.11+ Cc: Russell King Cc: Steve Capper Signed-off-by: Will Deacon Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/pgtable-2level.h | 1 + arch/arm/include/asm/pgtable-3level.h | 1 + arch/arm/include/asm/pgtable.h | 1 - 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index aeddd28b3595..92fd2c8a9af0 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ do { \ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fa70db7c714b..4dce1580bc15 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -211,6 +211,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) : !!(pmd_val(pmd) & (val))) #define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val))) +#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID)) #define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF)) #define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL)) static inline pte_t pte_mkspecial(pte_t pte) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 348caabb7625..d62204060cbe 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) static inline pte_t *pmd_page_vaddr(pmd_t pmd) { -- cgit v1.2.3 From 56530f5d2ddc9b9fade7ef8db9cb886e9dc689b5 Mon Sep 17 00:00:00 2001 From: Steve Capper Date: Tue, 7 Jun 2016 17:58:06 +0100 Subject: ARM: 8579/1: mm: Fix definition of pmd_mknotpresent Currently pmd_mknotpresent will use a zero entry to respresent an invalidated pmd. Unfortunately this definition clashes with pmd_none, thus it is possible for a race condition to occur if zap_pmd_range sees pmd_none whilst __split_huge_pmd_locked is running too with pmdp_invalidate just called. This patch fixes the race condition by modifying pmd_mknotpresent to create non-zero faulting entries (as is done in other architectures), removing the ambiguity with pmd_none. [catalin.marinas@arm.com: using L_PMD_SECT_VALID instead of PMD_TYPE_SECT] Fixes: 8d9625070073 ("ARM: mm: Transparent huge page support for LPAE systems.") Cc: # 3.11+ Reported-by: Kirill A. Shutemov Acked-by: Will Deacon Cc: Russell King Signed-off-by: Steve Capper Signed-off-by: Catalin Marinas Signed-off-by: Russell King --- arch/arm/include/asm/pgtable-3level.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 4dce1580bc15..2a029bceaf2f 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -250,10 +250,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) -/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */ +/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */ static inline pmd_t pmd_mknotpresent(pmd_t pmd) { - return __pmd(0); + return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) -- cgit v1.2.3 From 32d6bd9059f265f617f6502c68dfbcae7e515add Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 24 Jun 2016 14:48:47 -0700 Subject: tree wide: get rid of __GFP_REPEAT for order-0 allocations part I This is the third version of the patchset previously sent [1]. I have basically only rebased it on top of 4.7-rc1 tree and dropped "dm: get rid of superfluous gfp flags" which went through dm tree. I am sending it now because it is tree wide and chances for conflicts are reduced considerably when we want to target rc2. I plan to send the next step and rename the flag and move to a better semantic later during this release cycle so we will have a new semantic ready for 4.8 merge window hopefully. Motivation: While working on something unrelated I've checked the current usage of __GFP_REPEAT in the tree. It seems that a majority of the usage is and always has been bogus because __GFP_REPEAT has always been about costly high order allocations while we are using it for order-0 or very small orders very often. It seems that a big pile of them is just a copy&paste when a code has been adopted from one arch to another. I think it makes some sense to get rid of them because they are just making the semantic more unclear. Please note that GFP_REPEAT is documented as * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt * _might_ fail. This depends upon the particular VM implementation. while !costly requests have basically nofail semantic. So one could reasonably expect that order-0 request with __GFP_REPEAT will not loop for ever. This is not implemented right now though. I would like to move on with __GFP_REPEAT and define a better semantic for it. $ git grep __GFP_REPEAT origin/master | wc -l 111 $ git grep __GFP_REPEAT | wc -l 36 So we are down to the third after this patch series. The remaining places really seem to be relying on __GFP_REPEAT due to large allocation requests. This still needs some double checking which I will do later after all the simple ones are sorted out. I am touching a lot of arch specific code here and I hope I got it right but as a matter of fact I even didn't compile test for some archs as I do not have cross compiler for them. Patches should be quite trivial to review for stupid compile mistakes though. The tricky parts are usually hidden by macro definitions and thats where I would appreciate help from arch maintainers. [1] http://lkml.kernel.org/r/1461849846-27209-1-git-send-email-mhocko@kernel.org This patch (of 19): __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. Yet we have the full kernel tree with its usage for apparently order-0 allocations. This is really confusing because __GFP_REPEAT is explicitly documented to allow allocation failures which is a weaker semantic than the current order-0 has (basically nofail). Let's simply drop __GFP_REPEAT from those places. This would allow to identify place which really need allocator to retry harder and formulate a more specific semantic for what the flag is supposed to do actually. Link: http://lkml.kernel.org/r/1464599699-30131-2-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: "David S. Miller" Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: "Theodore Ts'o" Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Chen Liqin Cc: Chris Metcalf [for tile] Cc: Guan Xuetao Cc: Heiko Carstens Cc: Helge Deller Cc: Ingo Molnar Cc: Jan Kara Cc: John Crispin Cc: Lennox Wu Cc: Ley Foon Tan Cc: Martin Schwidefsky Cc: Matt Fleming Cc: Ralf Baechle Cc: Rich Felker Cc: Russell King Cc: Thomas Gleixner Cc: Vineet Gupta Cc: Will Deacon Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/include/asm/pgalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm/include') diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 19cfab526d13..20febb368844 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + return (pmd_t *)get_zeroed_page(GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -- cgit v1.2.3