From 0cbe3e26abe0cfe7effb67f620a77d46cce628b2 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 5 Mar 2019 15:46:26 -0800 Subject: mm: update ptep_modify_prot_start/commit to take vm_area_struct as arg Patch series "NestMMU pte upgrade workaround for mprotect", v5. We can upgrade pte access (R -> RW transition) via mprotect. We need to make sure we follow the recommended pte update sequence as outlined in commit bd5050e38aec ("powerpc/mm/radix: Change pte relax sequence to handle nest MMU hang") for such updates. This patch series does that. This patch (of 5): Some architectures may want to call flush_tlb_range from these helpers. Link: http://lkml.kernel.org/r/20190116085035.29729-2-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Nicholas Piggin Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/include/asm/pgtable.h | 4 ++-- arch/s390/mm/pgtable.c | 6 ++++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 063732414dfbb..5d730199e37b6 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1069,8 +1069,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION -pte_t ptep_modify_prot_start(struct mm_struct *, unsigned long, pte_t *); -void ptep_modify_prot_commit(struct mm_struct *, unsigned long, pte_t *, pte_t); +pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); +void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, pte_t *, pte_t); #define __HAVE_ARCH_PTEP_CLEAR_FLUSH static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 689b66f29fc60..71aa011707687 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -301,12 +301,13 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL(ptep_xchg_lazy); -pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgste_t pgste; pte_t old; int nodat; + struct mm_struct *mm = vma->vm_mm; preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); @@ -319,10 +320,11 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, return old; } -void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { pgste_t pgste; + struct mm_struct *mm = vma->vm_mm; if (!MACHINE_HAS_NX) pte_val(pte) &= ~_PAGE_NOEXEC; -- cgit v1.2.3 From 04a8645304500be88b3345b65fef7efe58016166 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 5 Mar 2019 15:46:29 -0800 Subject: mm: update ptep_modify_prot_commit to take old pte value as arg Architectures like ppc64 require to do a conditional tlb flush based on the old and new value of pte. Enable that by passing old pte value as the arg. Link: http://lkml.kernel.org/r/20190116085035.29729-3-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/include/asm/pgtable.h | 3 ++- arch/s390/mm/pgtable.c | 2 +- arch/x86/include/asm/paravirt.h | 2 +- fs/proc/task_mmu.c | 8 +++++--- include/asm-generic/pgtable.h | 2 +- mm/memory.c | 8 ++++---- mm/mprotect.c | 6 +++--- 7 files changed, 17 insertions(+), 14 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5d730199e37b6..76dc344edb8cf 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1070,7 +1070,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *); -void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, pte_t *, pte_t); +void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long, + pte_t *, pte_t, pte_t); #define __HAVE_ARCH_PTEP_CLEAR_FLUSH static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 71aa011707687..8485d6dc27549 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -321,7 +321,7 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, } void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t old_pte, pte_t pte) { pgste_t pgste; struct mm_struct *mm = vma->vm_mm; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c5a7f18cce7eb..c25c38a05c1c9 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -433,7 +433,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned } static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t old_pte, pte_t pte) { if (sizeof(pteval_t) > sizeof(long)) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9c2ef731dd5fe..beccb0b1d57c7 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -948,10 +948,12 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, pte_t ptent = *pte; if (pte_present(ptent)) { - ptent = ptep_modify_prot_start(vma, addr, pte); - ptent = pte_wrprotect(ptent); + pte_t old_pte; + + old_pte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); - ptep_modify_prot_commit(vma, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); } else if (is_swap_pte(ptent)) { ptent = pte_swp_clear_soft_dirty(ptent); set_pte_at(vma->vm_mm, addr, pte, ptent); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8b0e933efe263..fa782fba51eeb 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -657,7 +657,7 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, */ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, - pte_t *ptep, pte_t pte) + pte_t *ptep, pte_t old_pte, pte_t pte) { __ptep_modify_prot_commit(vma, addr, ptep, pte); } diff --git a/mm/memory.c b/mm/memory.c index 5ade52502ea03..557c6fffedd18 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3599,7 +3599,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) int last_cpupid; int target_nid; bool migrated = false; - pte_t pte; + pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; @@ -3619,12 +3619,12 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) * Make it present again, Depending on how arch implementes non * accessible ptes, some can allow access by kernel mode. */ - pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); - pte = pte_modify(pte, vma->vm_page_prot); + old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); + pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); - ptep_modify_prot_commit(vma, vmf->address, vmf->pte, pte); + ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); diff --git a/mm/mprotect.c b/mm/mprotect.c index c89ce07923c83..028c724dcb1ae 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -110,8 +110,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, continue; } - ptent = ptep_modify_prot_start(vma, addr, pte); - ptent = pte_modify(ptent, newprot); + oldpte = ptep_modify_prot_start(vma, addr, pte); + ptent = pte_modify(oldpte, newprot); if (preserve_write) ptent = pte_mk_savedwrite(ptent); @@ -121,7 +121,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, !(vma->vm_flags & VM_SOFTDIRTY))) { ptent = pte_mkwrite(ptent); } - ptep_modify_prot_commit(vma, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); pages++; } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); -- cgit v1.2.3 From 446d29645b7d2411a502885fc1cbd1746bcf80be Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:47:10 -0800 Subject: s390/vdso: don't clear PG_reserved The VDSO is part of the kernel image and therefore the struct pages are marked as reserved during boot. As we install a special mapping, the actual struct pages will never be exposed to MM via the page tables. We can therefore leave the pages marked as reserved. Link: http://lkml.kernel.org/r/20190114125903.24845-3-david@redhat.com Signed-off-by: David Hildenbrand Suggested-by: Martin Schwidefsky Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Matthew Wilcox Cc: Mike Rapoport Cc: Michal Hocko Cc: Vasily Gorbik Cc: Kees Cook Cc: Souptick Joarder Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/kernel/vdso.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index 4ff354887db41..e7920a68a12ec 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -291,7 +291,6 @@ static int __init vdso_init(void) BUG_ON(vdso32_pagelist == NULL); for (i = 0; i < vdso32_pages - 1; i++) { struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); - ClearPageReserved(pg); get_page(pg); vdso32_pagelist[i] = pg; } @@ -309,7 +308,6 @@ static int __init vdso_init(void) BUG_ON(vdso64_pagelist == NULL); for (i = 0; i < vdso64_pages - 1; i++) { struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); - ClearPageReserved(pg); get_page(pg); vdso64_pagelist[i] = pg; } -- cgit v1.2.3