From ca215086b14b89a0e70fc211314944aa6ce50020 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:23 -0800 Subject: mm: convert PG_balloon to PG_offline PG_balloon was introduced to implement page migration/compaction for pages inflated in virtio-balloon. Nowadays, it is only a marker that a page is part of virtio-balloon and therefore logically offline. We also want to make use of this flag in other balloon drivers - for inflated pages or when onlining a section but keeping some pages offline (e.g. used right now by XEN and Hyper-V via set_online_page_callback()). We are going to expose this flag to dump tools like makedumpfile. But instead of exposing PG_balloon, let's generalize the concept of marking pages as logically offline, so it can be reused for other purposes later on. Rename PG_balloon to PG_offline. This is an indicator that the page is logically offline, the content stale and that it should not be touched (e.g. a hypervisor would have to allocate backing storage in order for the guest to dump an unused page). We can then e.g. exclude such pages from dumps. We replace and reuse KPF_BALLOON (23), as this shouldn't really harm (and for now the semantics stay the same). In following patches, we will make use of this bit also in other balloon drivers. While at it, document PGTABLE. [akpm@linux-foundation.org: fix comment text, per David] Link: http://lkml.kernel.org/r/20181119101616.8901-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Konstantin Khlebnikov Acked-by: Michael S. Tsirkin Acked-by: Pankaj gupta Cc: Jonathan Corbet Cc: Alexey Dobriyan Cc: Mike Rapoport Cc: Christian Hansen Cc: Vlastimil Babka Cc: "Kirill A. Shutemov" Cc: Stephen Rothwell Cc: Matthew Wilcox Cc: Michal Hocko Cc: Pavel Tatashin Cc: Alexander Duyck Cc: Naoya Horiguchi Cc: Miles Chen Cc: David Rientjes Cc: Kazuhito Hagio Cc: Arnd Bergmann Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Dave Young Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Lianbo Jiang Cc: Michal Hocko Cc: Nadav Amit Cc: Omar Sandoval Cc: Pavel Machek Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Vitaly Kuznetsov Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/page.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/page.c b/fs/proc/page.c index 40b05e0d4274..544d1ee15aee 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page) else if (page_count(page) == 0 && is_free_buddy_page(page)) u |= 1 << KPF_BUDDY; - if (PageBalloon(page)) - u |= 1 << KPF_BALLOON; + if (PageOffline(page)) + u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; -- cgit v1.2.3 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 ++++-- arch/x86/include/asm/paravirt.h | 11 ++++++----- arch/x86/include/asm/paravirt_types.h | 5 +++-- arch/x86/xen/mmu.h | 4 ++-- arch/x86/xen/mmu_pv.c | 8 ++++---- fs/proc/task_mmu.c | 4 ++-- include/asm-generic/pgtable.h | 16 ++++++++-------- mm/memory.c | 4 ++-- mm/mprotect.c | 4 ++-- 10 files changed, 35 insertions(+), 31 deletions(-) (limited to 'fs/proc') diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 063732414dfb..5d730199e37b 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 689b66f29fc6..71aa01170768 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; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index a97f28d914d5..c5a7f18cce7e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -422,25 +422,26 @@ static inline pgdval_t pgd_val(pgd_t pgd) } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION -static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pteval_t ret; - ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep); + ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep); return (pte_t) { .pte = ret }; } -static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { + if (sizeof(pteval_t) > sizeof(long)) /* 5 arg words */ - pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte); + pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte); else PVOP_VCALL4(mmu.ptep_modify_prot_commit, - mm, addr, ptep, pte.pte); + vma, addr, ptep, pte.pte); } static inline void set_pte(pte_t *ptep, pte_t pte) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 488c59686a73..2474e434a6f7 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -55,6 +55,7 @@ struct task_struct; struct cpumask; struct flush_tlb_info; struct mmu_gather; +struct vm_area_struct; /* * Wrapper type for pointers to code which uses the non-standard @@ -254,9 +255,9 @@ struct pv_mmu_ops { pte_t *ptep, pte_t pteval); void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); - 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); - 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); struct paravirt_callee_save pte_val; diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index a7e47cf7ec6c..6e4c6bd62203 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -17,8 +17,8 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); -pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep); -void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, +pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte); unsigned long xen_read_cr2_direct(void); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 0f4fe206dcc2..856a85814f00 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -306,20 +306,20 @@ static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr, __xen_set_pte(ptep, pteval); } -pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, +pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* Just return the pte as-is. We preserve the bits on commit */ - trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep); + trace_xen_mmu_ptep_modify_prot_start(vma->vm_mm, addr, ptep, *ptep); return *ptep; } -void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, +void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { struct mmu_update u; - trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte); + trace_xen_mmu_ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte); xen_mc_batch(); u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85b0ef890b28..9c2ef731dd5f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -948,10 +948,10 @@ 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->vm_mm, addr, pte); + ptent = ptep_modify_prot_start(vma, addr, pte); ptent = pte_wrprotect(ptent); ptent = pte_clear_soft_dirty(ptent); - ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, 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 05e61e6c843f..8b0e933efe26 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -606,7 +606,7 @@ static inline int pmd_none_or_clear_bad(pmd_t *pmd) return 0; } -static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm, +static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { @@ -615,10 +615,10 @@ static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm, * non-present, preventing the hardware from asynchronously * updating it. */ - return ptep_get_and_clear(mm, addr, ptep); + return ptep_get_and_clear(vma->vm_mm, addr, ptep); } -static inline void __ptep_modify_prot_commit(struct mm_struct *mm, +static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { @@ -626,7 +626,7 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm, * The pte is non-present, so there's no hardware state to * preserve. */ - set_pte_at(mm, addr, ptep, pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); } #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -644,22 +644,22 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm, * queue the update to be done at some later time. The update must be * actually committed before the pte lock is released, however. */ -static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - return __ptep_modify_prot_start(mm, addr, ptep); + return __ptep_modify_prot_start(vma, addr, ptep); } /* * Commit an update to a pte, leaving any hardware-controlled bits in * the PTE unmodified. */ -static inline void ptep_modify_prot_commit(struct mm_struct *mm, +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { - __ptep_modify_prot_commit(mm, addr, ptep, pte); + __ptep_modify_prot_commit(vma, addr, ptep, pte); } #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ #endif /* CONFIG_MMU */ diff --git a/mm/memory.c b/mm/memory.c index 6aff43171a7b..5ade52502ea0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -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->vm_mm, vmf->address, vmf->pte); + pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); pte = pte_modify(pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); - ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte); + ptep_modify_prot_commit(vma, vmf->address, vmf->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 36cb358db170..c89ce07923c8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -110,7 +110,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, continue; } - ptent = ptep_modify_prot_start(mm, addr, pte); + ptent = ptep_modify_prot_start(vma, addr, pte); ptent = pte_modify(ptent, 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(mm, addr, pte, ptent); + ptep_modify_prot_commit(vma, addr, pte, ptent); pages++; } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); -- 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 'fs/proc') diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 5d730199e37b..76dc344edb8c 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 71aa01170768..8485d6dc2754 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 c5a7f18cce7e..c25c38a05c1c 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 9c2ef731dd5f..beccb0b1d57c 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 8b0e933efe26..fa782fba51ee 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 5ade52502ea0..557c6fffedd1 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 c89ce07923c8..028c724dcb1a 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 756ca74c7f656b6ed3cb60344845878226b658ae Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Tue, 5 Mar 2019 15:50:22 -0800 Subject: fs/proc/self.c: code cleanup for proc_setup_self() Remove unnecessary ERR_PTR()/PTR_ERR() cast in proc_setup_self(). Link: http://lkml.kernel.org/r/20190124030150.8472-1-cgxu519@gmx.com Signed-off-by: Chengguang Xu Reviewed-by: Andrew Morton Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/self.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/self.c b/fs/proc/self.c index 127265e5c55f..57c0a1047250 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -38,6 +38,7 @@ int proc_setup_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; + int ret = -ENOMEM; inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); @@ -51,20 +52,19 @@ int proc_setup_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_self_inode_operations; d_add(self, inode); + ret = 0; } else { dput(self); - self = ERR_PTR(-ENOMEM); } - } else { - self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); - return PTR_ERR(self); - } - ns->proc_self = self; - return 0; + else + ns->proc_self = self; + + return ret; } void __init proc_self_init(void) -- cgit v1.2.3 From 45f68ab50234e825cdc7aee76a40d227d92eea14 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Tue, 5 Mar 2019 15:50:25 -0800 Subject: fs/proc/thread_self.c: code cleanup for proc_setup_thread_self() Remove unnecessary ERR_PTR()/PTR_ERR() cast in proc_setup_thread_self(). Link: http://lkml.kernel.org/r/20190124030150.8472-2-cgxu519@gmx.com Signed-off-by: Chengguang Xu Reviewed-by: Andrew Morton Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/thread_self.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index b905010ca9eb..f61ae53533f5 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -38,6 +38,7 @@ int proc_setup_thread_self(struct super_block *s) struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *thread_self; + int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); @@ -51,20 +52,19 @@ int proc_setup_thread_self(struct super_block *s) inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); + ret = 0; } else { dput(thread_self); - thread_self = ERR_PTR(-ENOMEM); } - } else { - thread_self = ERR_PTR(-ENOMEM); } inode_unlock(root_inode); - if (IS_ERR(thread_self)) { + + if (ret) pr_err("proc_fill_super: can't allocate /proc/thread_self\n"); - return PTR_ERR(thread_self); - } - ns->proc_thread_self = thread_self; - return 0; + else + ns->proc_thread_self = thread_self; + + return ret; } void __init proc_thread_self_init(void) -- cgit v1.2.3 From 867aaccf1f2c35eff4706ea69299f731f2a1953e Mon Sep 17 00:00:00 2001 From: Zhikang Zhang Date: Tue, 5 Mar 2019 15:50:29 -0800 Subject: proc: remove unused argument in proc_pid_lookup() [adobriyan@gmail.com: delete "extern" from prototype] Link: http://lkml.kernel.org/r/20190114195635.GA9372@avx2 Signed-off-by: Zhikang Zhang Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 2 +- fs/proc/internal.h | 2 +- fs/proc/root.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index f5ed9512d193..fcb0180d3988 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3161,7 +3161,7 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry, return d_splice_alias(inode, dentry); } -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) +struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags) { struct task_struct *task; unsigned tgid; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 95b14196f284..4fc5a9b68f76 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -162,7 +162,7 @@ extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struc extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); -extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int); +struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ diff --git a/fs/proc/root.c b/fs/proc/root.c index f4b1a9d2eca6..621e6ec322ca 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -154,7 +154,7 @@ static int proc_root_getattr(const struct path *path, struct kstat *stat, static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags) { - if (!proc_pid_lookup(dir, dentry, flags)) + if (!proc_pid_lookup(dentry, flags)) return NULL; return proc_lookup(dir, dentry, flags); -- cgit v1.2.3 From 5713f35c0575a1137b705e13d10f8ee58f2ec7e8 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 5 Mar 2019 15:50:32 -0800 Subject: proc: read kernel cpu stat pointer once Help gcc generate better code: $ ./scripts/bloat-o-meter ../vmlinux-000 ../vmlinux-001 add/remove: 2/2 grow/shrink: 0/1 up/down: 92/-142 (-50) Function old new delta get_iowait_time.isra - 46 +46 get_idle_time.isra - 46 +46 show_stat 1489 1477 -12 get_iowait_time 65 - -65 get_idle_time 65 - -65 Link: http://lkml.kernel.org/r/20190114195907.GA9680@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/stat.c | 60 +++++++++++++++++++++++++++++++--------------------------- 1 file changed, 32 insertions(+), 28 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 535eda7857cf..49aa0a2b0d9e 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -23,21 +23,21 @@ #ifdef arch_idle_time -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; if (cpu_online(cpu) && !nr_iowait_cpu(cpu)) idle += arch_idle_time(cpu); return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait; - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; if (cpu_online(cpu) && nr_iowait_cpu(cpu)) iowait += arch_idle_time(cpu); return iowait; @@ -45,7 +45,7 @@ static u64 get_iowait_time(int cpu) #else -static u64 get_idle_time(int cpu) +static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; @@ -54,14 +54,14 @@ static u64 get_idle_time(int cpu) if (idle_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.idle */ - idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE]; + idle = kcs->cpustat[CPUTIME_IDLE]; else idle = idle_usecs * NSEC_PER_USEC; return idle; } -static u64 get_iowait_time(int cpu) +static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) { u64 iowait, iowait_usecs = -1ULL; @@ -70,7 +70,7 @@ static u64 get_iowait_time(int cpu) if (iowait_usecs == -1ULL) /* !NO_HZ or cpu offline so we can rely on cpustat.iowait */ - iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT]; + iowait = kcs->cpustat[CPUTIME_IOWAIT]; else iowait = iowait_usecs * NSEC_PER_USEC; @@ -95,16 +95,18 @@ static int show_stat(struct seq_file *p, void *v) getboottime64(&boottime); for_each_possible_cpu(i) { - user += kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle += get_idle_time(i); - iowait += get_iowait_time(i); - irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + + user += kcs->cpustat[CPUTIME_USER]; + nice += kcs->cpustat[CPUTIME_NICE]; + system += kcs->cpustat[CPUTIME_SYSTEM]; + idle += get_idle_time(kcs, i); + iowait += get_iowait_time(kcs, i); + irq += kcs->cpustat[CPUTIME_IRQ]; + softirq += kcs->cpustat[CPUTIME_SOFTIRQ]; + steal += kcs->cpustat[CPUTIME_STEAL]; + guest += kcs->cpustat[CPUTIME_GUEST]; + guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE]; sum += kstat_cpu_irqs_sum(i); sum += arch_irq_stat_cpu(i); @@ -130,17 +132,19 @@ static int show_stat(struct seq_file *p, void *v) seq_putc(p, '\n'); for_each_online_cpu(i) { + struct kernel_cpustat *kcs = &kcpustat_cpu(i); + /* Copy values here to work around gcc-2.95.3, gcc-2.96 */ - user = kcpustat_cpu(i).cpustat[CPUTIME_USER]; - nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE]; - system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]; - idle = get_idle_time(i); - iowait = get_iowait_time(i); - irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ]; - softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]; - steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL]; - guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST]; - guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE]; + user = kcs->cpustat[CPUTIME_USER]; + nice = kcs->cpustat[CPUTIME_NICE]; + system = kcs->cpustat[CPUTIME_SYSTEM]; + idle = get_idle_time(kcs, i); + iowait = get_iowait_time(kcs, i); + irq = kcs->cpustat[CPUTIME_IRQ]; + softirq = kcs->cpustat[CPUTIME_SOFTIRQ]; + steal = kcs->cpustat[CPUTIME_STEAL]; + guest = kcs->cpustat[CPUTIME_GUEST]; + guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE]; seq_printf(p, "cpu%d", i); seq_put_decimal_ull(p, " ", nsec_to_clock_t(user)); seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice)); -- cgit v1.2.3 From 08b55775133b77acc9975ad772b41813cbfea674 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 5 Mar 2019 15:50:35 -0800 Subject: proc: use seq_puts() everywhere seq_printf() without format specifiers == faster seq_puts() Link: http://lkml.kernel.org/r/20190114200545.GC9680@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 16 ++++++++-------- fs/proc/base.c | 2 +- fs/proc/task_nommu.c | 2 +- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/array.c b/fs/proc/array.c index 9d428d5a0ac8..2edbb657f859 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -343,28 +343,28 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif - seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + seq_puts(m, "\nSpeculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: - seq_printf(m, "unknown"); + seq_puts(m, "unknown"); break; case PR_SPEC_NOT_AFFECTED: - seq_printf(m, "not vulnerable"); + seq_puts(m, "not vulnerable"); break; case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: - seq_printf(m, "thread force mitigated"); + seq_puts(m, "thread force mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_DISABLE: - seq_printf(m, "thread mitigated"); + seq_puts(m, "thread mitigated"); break; case PR_SPEC_PRCTL | PR_SPEC_ENABLE: - seq_printf(m, "thread vulnerable"); + seq_puts(m, "thread vulnerable"); break; case PR_SPEC_DISABLE: - seq_printf(m, "globally mitigated"); + seq_puts(m, "globally mitigated"); break; default: - seq_printf(m, "vulnerable"); + seq_puts(m, "vulnerable"); break; } seq_putc(m, '\n'); diff --git a/fs/proc/base.c b/fs/proc/base.c index fcb0180d3988..511b279ec69c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -456,7 +456,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { if (unlikely(!sched_info_on())) - seq_printf(m, "0 0 0\n"); + seq_puts(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", (unsigned long long)task->se.sum_exec_runtime, diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 0b63d68dedb2..3b7e310297d2 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -178,7 +178,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) seq_file_path(m, file, ""); } else if (mm && is_stack(vma)) { seq_pad(m, ' '); - seq_printf(m, "[stack]"); + seq_puts(m, "[stack]"); } seq_putc(m, '\n'); -- cgit v1.2.3