diff options
189 files changed, 4357 insertions, 2886 deletions
diff --git a/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt b/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt deleted file mode 100644 index 26f74b457e0b..000000000000 --- a/Documentation/features/vm/pmdp_splitting_flush/arch-support.txt +++ /dev/null @@ -1,40 +0,0 @@ -# -# Feature name: pmdp_splitting_flush -# Kconfig: __HAVE_ARCH_PMDP_SPLITTING_FLUSH -# description: arch supports the pmdp_splitting_flush() VM API -# - ----------------------- - | arch |status| - ----------------------- - | alpha: | TODO | - | arc: | TODO | - | arm: | ok | - | arm64: | ok | - | avr32: | TODO | - | blackfin: | TODO | - | c6x: | TODO | - | cris: | TODO | - | frv: | TODO | - | h8300: | TODO | - | hexagon: | TODO | - | ia64: | TODO | - | m32r: | TODO | - | m68k: | TODO | - | metag: | TODO | - | microblaze: | TODO | - | mips: | ok | - | mn10300: | TODO | - | nios2: | TODO | - | openrisc: | TODO | - | parisc: | TODO | - | powerpc: | ok | - | s390: | ok | - | score: | TODO | - | sh: | TODO | - | sparc: | TODO | - | tile: | TODO | - | um: | TODO | - | unicore32: | TODO | - | x86: | ok | - | xtensa: | TODO | - ----------------------- diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index 6389551bbad6..5d1128bf0282 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -306,15 +306,6 @@ Network device features: Passed by reference. -Command from struct task_struct - - %pT ls - - For printing executable name excluding path from struct - task_struct. - - Passed by reference. - If you add other %p extensions, please extend lib/test_printf.c with one or more test cases, if at all feasible. diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt index 8a282687ee06..21cf34f3ddb2 100644 --- a/Documentation/vm/transhuge.txt +++ b/Documentation/vm/transhuge.txt @@ -35,10 +35,10 @@ miss is going to run faster. == Design == -- "graceful fallback": mm components which don't have transparent - hugepage knowledge fall back to breaking a transparent hugepage and - working on the regular pages and their respective regular pmd/pte - mappings +- "graceful fallback": mm components which don't have transparent hugepage + knowledge fall back to breaking huge pmd mapping into table of ptes and, + if necessary, split a transparent hugepage. Therefore these components + can continue working on the regular pages or regular pte mappings. - if a hugepage allocation fails because of memory fragmentation, regular pages should be gracefully allocated instead and mixed in @@ -221,9 +221,18 @@ thp_collapse_alloc_failed is incremented if khugepaged found a range of pages that should be collapsed into one huge page but failed the allocation. -thp_split is incremented every time a huge page is split into base +thp_split_page is incremented every time a huge page is split into base pages. This can happen for a variety of reasons but a common reason is that a huge page is old and is being reclaimed. + This action implies splitting all PMD the page mapped with. + +thp_split_page_failed is is incremented if kernel fails to split huge + page. This can happen if the page was pinned by somebody. + +thp_split_pmd is incremented every time a PMD split into table of PTEs. + This can happen, for instance, when application calls mprotect() or + munmap() on part of huge page. It doesn't split huge page, only + page table entry. thp_zero_page_alloc is incremented every time a huge zero page is successfully allocated. It includes allocations which where @@ -274,10 +283,8 @@ is complete, so they won't ever notice the fact the page is huge. But if any driver is going to mangle over the page structure of the tail page (like for checking page->mapping or other bits that are relevant for the head page and not the tail page), it should be updated to jump -to check head page instead (while serializing properly against -split_huge_page() to avoid the head and tail pages to disappear from -under it, see the futex code to see an example of that, hugetlbfs also -needed special handling in futex code for similar reasons). +to check head page instead. Taking reference on any head/tail page would +prevent page from being split by anyone. NOTE: these aren't new constraints to the GUP API, and they match the same constrains that applies to hugetlbfs too, so any driver capable @@ -312,9 +319,9 @@ unaffected. libhugetlbfs will also work fine as usual. == Graceful fallback == Code walking pagetables but unware about huge pmds can simply call -split_huge_page_pmd(vma, addr, pmd) where the pmd is the one returned by +split_huge_pmd(vma, pmd, addr) where the pmd is the one returned by pmd_offset. It's trivial to make the code transparent hugepage aware -by just grepping for "pmd_offset" and adding split_huge_page_pmd where +by just grepping for "pmd_offset" and adding split_huge_pmd where missing after pmd_offset returns the pmd. Thanks to the graceful fallback design, with a one liner change, you can avoid to write hundred if not thousand of lines of complex code to make your code @@ -323,7 +330,8 @@ hugepage aware. If you're not walking pagetables but you run into a physical hugepage but you can't handle it natively in your code, you can split it by calling split_huge_page(page). This is what the Linux VM does before -it tries to swapout the hugepage for example. +it tries to swapout the hugepage for example. split_huge_page() can fail +if the page is pinned and you must handle this correctly. Example to make mremap.c transparent hugepage aware with a one liner change: @@ -335,14 +343,14 @@ diff --git a/mm/mremap.c b/mm/mremap.c return NULL; pmd = pmd_offset(pud, addr); -+ split_huge_page_pmd(vma, addr, pmd); ++ split_huge_pmd(vma, pmd, addr); if (pmd_none_or_clear_bad(pmd)) return NULL; == Locking in hugepage aware code == We want as much code as possible hugepage aware, as calling -split_huge_page() or split_huge_page_pmd() has a cost. +split_huge_page() or split_huge_pmd() has a cost. To make pagetable walks huge pmd aware, all you need to do is to call pmd_trans_huge() on the pmd returned by pmd_offset. You must hold the @@ -351,47 +359,80 @@ created from under you by khugepaged (khugepaged collapse_huge_page takes the mmap_sem in write mode in addition to the anon_vma lock). If pmd_trans_huge returns false, you just fallback in the old code paths. If instead pmd_trans_huge returns true, you have to take the -mm->page_table_lock and re-run pmd_trans_huge. Taking the -page_table_lock will prevent the huge pmd to be converted into a -regular pmd from under you (split_huge_page can run in parallel to the +page table lock (pmd_lock()) and re-run pmd_trans_huge. Taking the +page table lock will prevent the huge pmd to be converted into a +regular pmd from under you (split_huge_pmd can run in parallel to the pagetable walk). If the second pmd_trans_huge returns false, you -should just drop the page_table_lock and fallback to the old code as -before. Otherwise you should run pmd_trans_splitting on the pmd. In -case pmd_trans_splitting returns true, it means split_huge_page is -already in the middle of splitting the page. So if pmd_trans_splitting -returns true it's enough to drop the page_table_lock and call -wait_split_huge_page and then fallback the old code paths. You are -guaranteed by the time wait_split_huge_page returns, the pmd isn't -huge anymore. If pmd_trans_splitting returns false, you can proceed to -process the huge pmd and the hugepage natively. Once finished you can -drop the page_table_lock. - -== compound_lock, get_user_pages and put_page == +should just drop the page table lock and fallback to the old code as +before. Otherwise you can proceed to process the huge pmd and the +hugepage natively. Once finished you can drop the page table lock. + +== Refcounts and transparent huge pages == + +Refcounting on THP is mostly consistent with refcounting on other compound +pages: + + - get_page()/put_page() and GUP operate in head page's ->_count. + + - ->_count in tail pages is always zero: get_page_unless_zero() never + succeed on tail pages. + + - map/unmap of the pages with PTE entry increment/decrement ->_mapcount + on relevant sub-page of the compound page. + + - map/unmap of the whole compound page accounted in compound_mapcount + (stored in first tail page). + +PageDoubleMap() indicates that ->_mapcount in all subpages is offset up by one. +This additional reference is required to get race-free detection of unmap of +subpages when we have them mapped with both PMDs and PTEs. + +This is optimization required to lower overhead of per-subpage mapcount +tracking. The alternative is alter ->_mapcount in all subpages on each +map/unmap of the whole compound page. + +We set PG_double_map when a PMD of the page got split for the first time, +but still have PMD mapping. The addtional references go away with last +compound_mapcount. split_huge_page internally has to distribute the refcounts in the head -page to the tail pages before clearing all PG_head/tail bits from the -page structures. It can do that easily for refcounts taken by huge pmd -mappings. But the GUI API as created by hugetlbfs (that returns head -and tail pages if running get_user_pages on an address backed by any -hugepage), requires the refcount to be accounted on the tail pages and -not only in the head pages, if we want to be able to run -split_huge_page while there are gup pins established on any tail -page. Failure to be able to run split_huge_page if there's any gup pin -on any tail page, would mean having to split all hugepages upfront in -get_user_pages which is unacceptable as too many gup users are -performance critical and they must work natively on hugepages like -they work natively on hugetlbfs already (hugetlbfs is simpler because -hugetlbfs pages cannot be split so there wouldn't be requirement of -accounting the pins on the tail pages for hugetlbfs). If we wouldn't -account the gup refcounts on the tail pages during gup, we won't know -anymore which tail page is pinned by gup and which is not while we run -split_huge_page. But we still have to add the gup pin to the head page -too, to know when we can free the compound page in case it's never -split during its lifetime. That requires changing not just -get_page, but put_page as well so that when put_page runs on a tail -page (and only on a tail page) it will find its respective head page, -and then it will decrease the head page refcount in addition to the -tail page refcount. To obtain a head page reliably and to decrease its -refcount without race conditions, put_page has to serialize against -__split_huge_page_refcount using a special per-page lock called -compound_lock. +page to the tail pages before clearing all PG_head/tail bits from the page +structures. It can be done easily for refcounts taken by page table +entries. But we don't have enough information on how to distribute any +additional pins (i.e. from get_user_pages). split_huge_page() fails any +requests to split pinned huge page: it expects page count to be equal to +sum of mapcount of all sub-pages plus one (split_huge_page caller must +have reference for head page). + +split_huge_page uses migration entries to stabilize page->_count and +page->_mapcount. + +We safe against physical memory scanners too: the only legitimate way +scanner can get reference to a page is get_page_unless_zero(). + +All tail pages has zero ->_count until atomic_add(). It prevent scanner +from geting reference to tail page up to the point. After the atomic_add() +we don't care about ->_count value. We already known how many references +with should uncharge from head page. + +For head page get_page_unless_zero() will succeed and we don't mind. It's +clear where reference should go after split: it will stay on head page. + +Note that split_huge_pmd() doesn't have any limitation on refcounting: +pmd can be split at any point and never fails. + +== Partial unmap and deferred_split_huge_page() == + +Unmapping part of THP (with munmap() or other way) is not going to free +memory immediately. Instead, we detect that a subpage of THP is not in use +in page_remove_rmap() and queue the THP for splitting if memory pressure +comes. Splitting will free up unused subpages. + +Splitting the page right away is not an option due to locking context in +the place where we can detect partial unmap. It's also might be +counterproductive since in many cases partial unmap unmap happens during +exit(2) if an THP crosses VMA boundary. + +Function deferred_split_huge_page() is used to queue page for splitting. +The splitting itself will happen when we get memory pressure via shrinker +interface. diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index f2f949671798..ab336c06153e 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -47,8 +47,10 @@ #define MADV_WILLNEED 3 /* will need these pages */ #define MADV_SPACEAVAIL 5 /* ensure resources are available */ #define MADV_DONTNEED 6 /* don't need these pages */ +#define MADV_FREE 7 /* free pages only if memory pressure */ /* common/generic parameters */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6312f607932f..76dde9db7934 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -73,9 +73,6 @@ config STACKTRACE_SUPPORT def_bool y select STACKTRACE -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y depends on ARC_MMU_V4 diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index ff7ff6cbb811..b65f797e9ad6 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -617,7 +617,7 @@ void flush_dcache_page(struct page *page) */ if (!mapping_mapped(mapping)) { clear_bit(PG_dc_clean, &page->flags); - } else if (page_mapped(page)) { + } else if (page_mapcount(page)) { /* kernel reading from page with U-mapping */ phys_addr_t paddr = (unsigned long)page_address(page); @@ -857,7 +857,7 @@ void copy_user_highpage(struct page *to, struct page *from, * For !VIPT cache, all of this gets compiled out as * addr_not_cache_congruent() is 0 */ - if (page_mapped(from) && addr_not_cache_congruent(kfrom, u_vaddr)) { + if (page_mapcount(from) && addr_not_cache_congruent(kfrom, u_vaddr)) { __flush_dcache_page((unsigned long)kfrom, u_vaddr); clean_src_k_mappings = 1; } diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4e489cc5c45e..6a889afa6a2c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -168,11 +168,6 @@ config STACKTRACE_SUPPORT bool default y -config HAVE_LATENCYTOP_SUPPORT - bool - depends on !SMP - default y - config LOCKDEP_SUPPORT bool default y diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 9203c21b4673..a520b7987a29 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -182,7 +182,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { @@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte) static inline void __kvm_flush_dcache_pmd(pmd_t pmd) { unsigned long size = PMD_SIZE; - pfn_t pfn = pmd_pfn(pmd); + kvm_pfn_t pfn = pmd_pfn(pmd); while (size) { void *va = kmap_atomic_pfn(pfn); diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a745a2a53853..dc46398bc3a5 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -88,7 +88,6 @@ #define L_PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) #define L_PMD_SECT_DIRTY (_AT(pmdval_t, 1) << 55) -#define L_PMD_SECT_SPLITTING (_AT(pmdval_t, 1) << 56) #define L_PMD_SECT_NONE (_AT(pmdval_t, 1) << 57) #define L_PMD_SECT_RDONLY (_AT(pteval_t, 1) << 58) @@ -232,13 +231,6 @@ static inline pte_t pte_mkspecial(pte_t pte) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !pmd_table(pmd)) -#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING)) - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); -#endif #endif #define PMD_BIT_FUNC(fn,op) \ @@ -246,9 +238,9 @@ static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } PMD_BIT_FUNC(wrprotect, |= L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF); -PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING); PMD_BIT_FUNC(mkwrite, &= ~L_PMD_SECT_RDONLY); PMD_BIT_FUNC(mkdirty, |= L_PMD_SECT_DIRTY); +PMD_BIT_FUNC(mkclean, &= ~L_PMD_SECT_DIRTY); PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 22f7fa0124ec..aba61fd3697a 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -992,9 +992,9 @@ out: return ret; } -static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap) +static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *ipap >> PAGE_SHIFT; if (PageTransCompound(pfn_to_page(pfn))) { @@ -1201,7 +1201,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn, unsigned long size, bool uncached) { __coherent_cache_guest_page(vcpu, pfn, size, uncached); @@ -1218,7 +1218,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm *kvm = vcpu->kvm; struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma; - pfn_t pfn; + kvm_pfn_t pfn; pgprot_t mem_type = PAGE_S2; bool fault_ipa_uncached; bool logging_active = memslot_is_logging(memslot); @@ -1346,7 +1346,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) { pmd_t *pmd; pte_t *pte; - pfn_t pfn; + kvm_pfn_t pfn; bool pfn_valid = false; trace_kvm_access_fault(fault_ipa); diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index 588bbc288396..6bd1089b07e0 100644 --- a/arch/arm/lib/uaccess_with_memcpy.c +++ b/arch/arm/lib/uaccess_with_memcpy.c @@ -52,14 +52,13 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp) * * Lock the page table for the destination and check * to see that it's still huge and whether or not we will - * need to fault on write, or if we have a splitting THP. + * need to fault on write. */ if (unlikely(pmd_thp_or_huge(*pmd))) { ptl = ¤t->mm->page_table_lock; spin_lock(ptl); if (unlikely(!pmd_thp_or_huge(*pmd) - || pmd_hugewillfault(*pmd) - || pmd_trans_splitting(*pmd))) { + || pmd_hugewillfault(*pmd))) { spin_unlock(ptl); return 0; } diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c index 1ec8e7590fc6..d0ba3551d49a 100644 --- a/arch/arm/mm/flush.c +++ b/arch/arm/mm/flush.c @@ -330,7 +330,7 @@ void flush_dcache_page(struct page *page) mapping = page_mapping(page); if (!cache_ops_need_broadcast() && - mapping && !page_mapped(page)) + mapping && !page_mapcount(page)) clear_bit(PG_dcache_clean, &page->flags); else { __flush_dcache_page(mapping, page); @@ -415,18 +415,3 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l */ __cpuc_flush_dcache_area(page_address(page), PAGE_SIZE); } - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - pmd_t pmd = pmd_mksplitting(*pmdp); - VM_BUG_ON(address & ~PMD_MASK); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - - /* dummy IPI to serialise against fast_gup */ - kick_all_cpus_sync(); -} -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 0bf8b4320a91..736433912a1e 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -230,7 +230,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } -static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, +static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, + kvm_pfn_t pfn, unsigned long size, bool ipa_uncached) { diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 69d2e2f86bce..2d545d7aa80b 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -353,21 +353,14 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_trans_huge(pmd) (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT)) -#define pmd_trans_splitting(pmd) pte_special(pmd_pte(pmd)) -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -struct vm_area_struct; -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp); -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) -#define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK)) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 46649d6e6c5a..60585bde1264 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -102,19 +102,3 @@ EXPORT_SYMBOL(flush_dcache_page); * Additional functions defined in assembly. */ EXPORT_SYMBOL(flush_icache_range); - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#ifdef CONFIG_HAVE_RCU_TABLE_FREE -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - pmd_t pmd = pmd_mksplitting(*pmdp); - - VM_BUG_ON(address & ~PMD_MASK); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - - /* dummy IPI to serialise against fast_gup */ - kick_all_cpus_sync(); -} -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/avr32/include/asm/page.h b/arch/avr32/include/asm/page.h index f805d1cb11bc..c5d2a3e2c62f 100644 --- a/arch/avr32/include/asm/page.h +++ b/arch/avr32/include/asm/page.h @@ -83,11 +83,9 @@ static inline int get_order(unsigned long size) #ifndef CONFIG_NEED_MULTIPLE_NODES -#define PHYS_PFN_OFFSET (CONFIG_PHYS_OFFSET >> PAGE_SHIFT) +#define ARCH_PFN_OFFSET (CONFIG_PHYS_OFFSET >> PAGE_SHIFT) -#define pfn_to_page(pfn) (mem_map + ((pfn) - PHYS_PFN_OFFSET)) -#define page_to_pfn(page) ((unsigned long)((page) - mem_map) + PHYS_PFN_OFFSET) -#define pfn_valid(pfn) ((pfn) >= PHYS_PFN_OFFSET && (pfn) < (PHYS_PFN_OFFSET + max_mapnr)) +#define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr)) #endif /* CONFIG_NEED_MULTIPLE_NODES */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) @@ -101,4 +99,6 @@ static inline int get_order(unsigned long size) */ #define HIGHMEM_START 0x20000000UL +#include <asm-generic/memory_model.h> + #endif /* __ASM_AVR32_PAGE_H */ diff --git a/arch/frv/include/asm/page.h b/arch/frv/include/asm/page.h index 8c97068ac8fc..688d8076a43a 100644 --- a/arch/frv/include/asm/page.h +++ b/arch/frv/include/asm/page.h @@ -34,7 +34,7 @@ typedef struct page *pgtable_t; #define pgprot_val(x) ((x).pgprot) #define __pte(x) ((pte_t) { (x) } ) -#define __pmd(x) ((pmd_t) { (x) } ) +#define __pmd(x) ((pmd_t) { { (x) } } ) #define __pud(x) ((pud_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __pgprot(x) ((pgprot_t) { (x) } ) diff --git a/arch/ia64/include/asm/page.h b/arch/ia64/include/asm/page.h index ec48bb9f95e1..e8c486ef0d76 100644 --- a/arch/ia64/include/asm/page.h +++ b/arch/ia64/include/asm/page.h @@ -105,6 +105,7 @@ extern struct page *vmem_map; #ifdef CONFIG_DISCONTIGMEM # define page_to_pfn(page) ((unsigned long) (page - vmem_map)) # define pfn_to_page(pfn) (vmem_map + (pfn)) +# define __pfn_to_phys(pfn) PFN_PHYS(pfn) #else # include <asm-generic/memory_model.h> #endif diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig index 0b389a81c43a..a0fa88da3e31 100644 --- a/arch/metag/Kconfig +++ b/arch/metag/Kconfig @@ -36,9 +36,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 0bce820428fc..5ecd0287a874 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -67,9 +67,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - source "init/Kconfig" source "kernel/Kconfig.freezer" diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6ded8d347af9..7c191443c7ea 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -101,9 +101,9 @@ #define CAUSEF_DC (_ULCAST_(1) << 27) extern atomic_t kvm_mips_instance; -extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn); -extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn); -extern bool(*kvm_mips_is_error_pfn) (pfn_t pfn); +extern kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); +extern void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn); +extern bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn); struct kvm_vm_stat { u32 remote_tlb_flush; diff --git a/arch/mips/include/asm/pgtable-bits.h b/arch/mips/include/asm/pgtable-bits.h index ff7ad91c85db..97b313882678 100644 --- a/arch/mips/include/asm/pgtable-bits.h +++ b/arch/mips/include/asm/pgtable-bits.h @@ -131,14 +131,12 @@ /* Huge TLB page */ #define _PAGE_HUGE_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #define _PAGE_HUGE (1 << _PAGE_HUGE_SHIFT) -#define _PAGE_SPLITTING_SHIFT (_PAGE_HUGE_SHIFT + 1) -#define _PAGE_SPLITTING (1 << _PAGE_SPLITTING_SHIFT) #endif /* CONFIG_64BIT && CONFIG_MIPS_HUGE_TLB_SUPPORT */ #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) /* XI - page cannot be executed */ -#ifdef _PAGE_SPLITTING_SHIFT -#define _PAGE_NO_EXEC_SHIFT (_PAGE_SPLITTING_SHIFT + 1) +#ifdef _PAGE_HUGE_SHIFT +#define _PAGE_NO_EXEC_SHIFT (_PAGE_HUGE_SHIFT + 1) #else #define _PAGE_NO_EXEC_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #endif @@ -153,8 +151,8 @@ #if defined(_PAGE_NO_READ_SHIFT) #define _PAGE_GLOBAL_SHIFT (_PAGE_NO_READ_SHIFT + 1) -#elif defined(_PAGE_SPLITTING_SHIFT) -#define _PAGE_GLOBAL_SHIFT (_PAGE_SPLITTING_SHIFT + 1) +#elif defined(_PAGE_HUGE_SHIFT) +#define _PAGE_GLOBAL_SHIFT (_PAGE_HUGE_SHIFT + 1) #else #define _PAGE_GLOBAL_SHIFT (_PAGE_MODIFIED_SHIFT + 1) #endif diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 8957f15e21ec..6995b4a02e23 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -482,27 +482,9 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd) return pmd; } -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return !!(pmd_val(pmd) & _PAGE_SPLITTING); -} - -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - pmd_val(pmd) |= _PAGE_SPLITTING; - - return pmd; -} - extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -/* Extern to avoid header file madness */ -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 97c03f468924..b0ebe59f73fd 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -73,8 +73,10 @@ #define MADV_SEQUENTIAL 2 /* expect sequential page references */ #define MADV_WILLNEED 3 /* will need these pages */ #define MADV_DONTNEED 4 /* don't need these pages */ +#define MADV_FREE 5 /* free pages only if memory pressure */ /* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 41b1b090f56f..1b675c7ce89f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1525,7 +1525,7 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; unsigned long pa; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; gfn = va >> PAGE_SHIFT; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index aed0ac2a4972..570479c03bdc 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -38,13 +38,13 @@ atomic_t kvm_mips_instance; EXPORT_SYMBOL(kvm_mips_instance); /* These function pointers are initialized once the KVM module is loaded */ -pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn); EXPORT_SYMBOL(kvm_mips_gfn_to_pfn); -void (*kvm_mips_release_pfn_clean)(pfn_t pfn); +void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn); EXPORT_SYMBOL(kvm_mips_release_pfn_clean); -bool (*kvm_mips_is_error_pfn)(pfn_t pfn); +bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn); EXPORT_SYMBOL(kvm_mips_is_error_pfn); uint32_t kvm_mips_get_kernel_asid(struct kvm_vcpu *vcpu) @@ -144,7 +144,7 @@ EXPORT_SYMBOL(kvm_mips_dump_guest_tlbs); static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) { int srcu_idx, err = 0; - pfn_t pfn; + kvm_pfn_t pfn; if (kvm->arch.guest_pmap[gfn] != KVM_INVALID_PAGE) return 0; @@ -262,7 +262,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu) { gfn_t gfn; - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; unsigned long vaddr = 0; unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; int even; @@ -313,7 +313,7 @@ EXPORT_SYMBOL(kvm_mips_handle_kseg0_tlb_fault); int kvm_mips_handle_commpage_tlb_fault(unsigned long badvaddr, struct kvm_vcpu *vcpu) { - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; unsigned long flags, old_entryhi = 0, vaddr = 0; unsigned long entrylo0 = 0, entrylo1 = 0; @@ -360,7 +360,7 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, { unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; - pfn_t pfn0, pfn1; + kvm_pfn_t pfn0, pfn1; if ((tlb->tlb_hi & VPN2_MASK) == 0) { pfn0 = 0; diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 5d3a25e1cfae..caac3d747a90 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -587,7 +587,8 @@ static inline void local_r4k_flush_cache_page(void *args) * another ASID than the current one. */ map_coherent = (cpu_has_dc_aliases && - page_mapped(page) && !Page_dcache_dirty(page)); + page_mapcount(page) && + !Page_dcache_dirty(page)); if (map_coherent) vaddr = kmap_coherent(page, addr); else diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index aab218c36e0d..3f159caf6dbc 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -106,7 +106,7 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) unsigned long addr = (unsigned long) page_address(page); if (pages_do_alias(addr, vmaddr)) { - if (page_mapped(page) && !Page_dcache_dirty(page)) { + if (page_mapcount(page) && !Page_dcache_dirty(page)) { void *kaddr; kaddr = kmap_coherent(page, vmaddr); diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c index 349995d19c7f..1afd87c999b0 100644 --- a/arch/mips/mm/gup.c +++ b/arch/mips/mm/gup.c @@ -87,8 +87,6 @@ static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -109,18 +107,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_huge(pmd))) { if (!gup_huge_pmd(pmd, addr, next, write, pages,nr)) @@ -153,8 +140,6 @@ static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 8770e619185e..7e5fa0938c21 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -165,7 +165,7 @@ void copy_user_highpage(struct page *to, struct page *from, vto = kmap_atomic(to); if (cpu_has_dc_aliases && - page_mapped(from) && !Page_dcache_dirty(from)) { + page_mapcount(from) && !Page_dcache_dirty(from)) { vfrom = kmap_coherent(from, vaddr); copy_page(vto, vfrom); kunmap_coherent(); @@ -187,7 +187,7 @@ void copy_to_user_page(struct vm_area_struct *vma, unsigned long len) { if (cpu_has_dc_aliases && - page_mapped(page) && !Page_dcache_dirty(page)) { + page_mapcount(page) && !Page_dcache_dirty(page)) { void *vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(vto, src, len); kunmap_coherent(); @@ -205,7 +205,7 @@ void copy_from_user_page(struct vm_area_struct *vma, unsigned long len) { if (cpu_has_dc_aliases && - page_mapped(page) && !Page_dcache_dirty(page)) { + page_mapcount(page) && !Page_dcache_dirty(page)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); kunmap_coherent(); diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c index e8adc0069d66..ce4473e7c0d2 100644 --- a/arch/mips/mm/pgtable-64.c +++ b/arch/mips/mm/pgtable-64.c @@ -62,20 +62,6 @@ void pmd_init(unsigned long addr, unsigned long pagetable) } #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, - pmd_t *pmdp) -{ - if (!pmd_trans_splitting(*pmdp)) { - pmd_t pmd = pmd_mksplitting(*pmdp); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - } -} - -#endif - pmd_t mk_pmd(struct page *page, pgprot_t prot) { pmd_t pmd; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 32e0be27673f..482192cc8f2b 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -240,7 +240,6 @@ static void output_pgtable_bits_defines(void) pr_define("_PAGE_MODIFIED_SHIFT %d\n", _PAGE_MODIFIED_SHIFT); #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT); - pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT); #endif #ifdef CONFIG_CPU_MIPSR2 if (cpu_has_rixi) { diff --git a/arch/mn10300/include/asm/page.h b/arch/mn10300/include/asm/page.h index 8288e124165b..3810a6f740fd 100644 --- a/arch/mn10300/include/asm/page.h +++ b/arch/mn10300/include/asm/page.h @@ -107,6 +107,7 @@ static inline int get_order(unsigned long size) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) #define pfn_to_page(pfn) (mem_map + ((pfn) - __pfn_disp)) #define page_to_pfn(page) ((unsigned long)((page) - mem_map) + __pfn_disp) +#define __pfn_to_phys(pfn) PFN_PHYS(pfn) #define pfn_valid(pfn) \ ({ \ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 729f89163bc3..7c34cafdf301 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -79,9 +79,6 @@ config TIME_LOW_RES depends on SMP default y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - # unless you want to implement ACPI on PA-RISC ... ;-) config PM bool diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index dd4d1876a020..cf830d465f75 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -43,8 +43,10 @@ #define MADV_SPACEAVAIL 5 /* insure that resources are reserved */ #define MADV_VPS_PURGE 6 /* Purge pages from VM page cache */ #define MADV_VPS_INHERIT 7 /* Inherit parents page size */ +#define MADV_FREE 8 /* free pages only if memory pressure */ /* common/generic parameters */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7d5a8350f913..94f6c5089e0c 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -47,9 +47,6 @@ config STACKTRACE_SUPPORT bool default y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config TRACE_IRQFLAGS_SUPPORT bool default y diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 9e55e3b1fef0..849bbec80f7b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -256,13 +256,6 @@ static inline int pmd_trans_huge(pmd_t pmd) (_PAGE_PTE | _PAGE_THP_HUGE)); } -static inline int pmd_trans_splitting(pmd_t pmd) -{ - if (pmd_trans_huge(pmd)) - return pmd_val(pmd) & _PAGE_SPLITTING; - return 0; -} - static inline int pmd_large(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_PTE); @@ -273,11 +266,6 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return __pmd(pmd_val(pmd) & ~_PAGE_PRESENT); } -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - return __pmd(pmd_val(pmd) | _PAGE_SPLITTING); -} - #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 2ff8b3df553d..06f17e778c27 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -41,11 +41,6 @@ #endif /* - * THP pages can't be special. So use the _PAGE_SPECIAL - */ -#define _PAGE_SPLITTING _PAGE_SPECIAL - -/* * We need to differentiate between explicit huge page and THP huge * page, since THP huge page also need to track real subpage details */ @@ -54,9 +49,8 @@ /* * set of bits not changed in pmd_modify. */ -#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | \ - _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_SPLITTING | \ - _PAGE_THP_HUGE | _PAGE_PTE | _PAGE_SOFT_DIRTY) +#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_THP_HUGE) #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/hash-64k.h> diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index b3a5badab69f..8204b0c393aa 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -223,9 +223,11 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd) #define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) +#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) +#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) @@ -266,10 +268,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, extern pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); - extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmdp_collapse_flush pmdp_collapse_flush diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 9fac01cb89c1..8f39796c9da8 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -154,8 +154,8 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, u32 val); extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr); extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu); -extern pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, - bool *writable); +extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, + bool writing, bool *writable); extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev, unsigned long *rmap, long pte_index, int realmode); extern void kvmppc_update_rmap_change(unsigned long *rmap, unsigned long psize); diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c6ef05bd0765..2241d5357129 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -515,7 +515,7 @@ void kvmppc_claim_lpid(long lpid); void kvmppc_free_lpid(long lpid); void kvmppc_init_lpid(unsigned long nr_lpids); -static inline void kvmppc_mmu_flush_icache(pfn_t pfn) +static inline void kvmppc_mmu_flush_icache(kvm_pfn_t pfn) { struct page *page; /* diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 099c79d8c160..638c6d9be9e0 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -366,7 +366,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvmppc_core_prepare_to_enter); -pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, +kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, bool *writable) { ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM; @@ -379,9 +379,9 @@ pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa, bool writing, gpa &= ~0xFFFULL; if (unlikely(mp_pa) && unlikely((gpa & KVM_PAM) == mp_pa)) { ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; - pfn_t pfn; + kvm_pfn_t pfn; - pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; + pfn = (kvm_pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); if (writable) *writable = true; diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index d5c9bfeb0c9c..55c4d51ea3e2 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -142,7 +142,7 @@ extern char etext[]; int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { - pfn_t hpaddr; + kvm_pfn_t hpaddr; u64 vpn; u64 vsid; struct kvmppc_sid_map *map; diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 79ad35abd196..913cd2198fa6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -83,7 +83,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte, bool iswrite) { unsigned long vpn; - pfn_t hpaddr; + kvm_pfn_t hpaddr; ulong hash, hpteg; u64 vsid; int ret; diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 72920bed3ac6..94f04fcb373e 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -41,7 +41,7 @@ enum vcpu_ftr { #define E500_TLB_MAS2_ATTR (0x7f) struct tlbe_ref { - pfn_t pfn; /* valid only for TLB0, except briefly */ + kvm_pfn_t pfn; /* valid only for TLB0, except briefly */ unsigned int flags; /* E500_TLB_* */ }; diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 34c43fff4adb..b0333cc737dd 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -163,9 +163,9 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu) struct kvm_book3e_206_tlb_entry magic; ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK; unsigned int stid; - pfn_t pfn; + kvm_pfn_t pfn; - pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; + pfn = (kvm_pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT; get_page(pfn_to_page(pfn)); preempt_disable(); @@ -246,7 +246,7 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; @@ -309,7 +309,7 @@ static void kvmppc_e500_setup_stlbe( int tsize, struct tlbe_ref *ref, u64 gvaddr, struct kvm_book3e_206_tlb_entry *stlbe) { - pfn_t pfn = ref->pfn; + kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; BUG_ON(!(ref->flags & E500_TLB_VALID)); diff --git a/arch/powerpc/kvm/trace_pr.h b/arch/powerpc/kvm/trace_pr.h index 810507cb688a..d44f324184fb 100644 --- a/arch/powerpc/kvm/trace_pr.h +++ b/arch/powerpc/kvm/trace_pr.h @@ -30,7 +30,7 @@ TRACE_EVENT(kvm_book3s_reenter, #ifdef CONFIG_PPC_BOOK3S_64 TRACE_EVENT(kvm_book3s_64_mmu_map, - TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr, + TP_PROTO(int rflags, ulong hpteg, ulong va, kvm_pfn_t hpaddr, struct kvmppc_pte *orig_pte), TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte), diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index baf1301ded0c..49b152b0f926 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -39,9 +39,6 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, /* If PMD busy, retry the access */ if (unlikely(old_pmd & _PAGE_BUSY)) return 0; - /* If PMD is trans splitting retry the access */ - if (unlikely(old_pmd & _PAGE_SPLITTING)) - return 0; /* If PMD permissions don't match, take page fault */ if (unlikely(access & ~old_pmd)) return 1; diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 61b8b7ccea4f..744e24bcb85c 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -958,10 +958,6 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, /* * A hugepage collapse is captured by pmd_none, because * it mark the pmd none and do a hpte invalidate. - * - * We don't worry about pmd_trans_splitting here, The - * caller if it needs to handle the splitting case - * should check for that. */ if (pmd_none(pmd)) return NULL; @@ -999,7 +995,7 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, { unsigned long mask; unsigned long pte_end; - struct page *head, *page, *tail; + struct page *head, *page; pte_t pte; int refs; @@ -1022,7 +1018,6 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, head = pte_page(pte); page = head + ((addr & (sz-1)) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -1044,15 +1039,5 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, return 0; } - /* - * Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index ea6bc31debb0..3124a20d0fab 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -604,55 +604,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, } /* - * We mark the pmd splitting and invalidate all the hpte - * entries for this hugepage. - */ -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - unsigned long old, tmp; - - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - -#ifdef CONFIG_DEBUG_VM - WARN_ON(!pmd_trans_huge(*pmdp)); - assert_spin_locked(&vma->vm_mm->page_table_lock); -#endif - -#ifdef PTE_ATOMIC_UPDATES - - __asm__ __volatile__( - "1: ldarx %0,0,%3\n\ - andi. %1,%0,%6\n\ - bne- 1b \n\ - oris %1,%0,%4@h \n\ - stdcx. %1,0,%3 \n\ - bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) - : "r" (pmdp), "i" (_PAGE_SPLITTING), "m" (*pmdp), "i" (_PAGE_BUSY) - : "cc" ); -#else - old = pmd_val(*pmdp); - *pmdp = __pmd(old | _PAGE_SPLITTING); -#endif - /* - * If we didn't had the splitting flag set, go and flush the - * HPTE entries. - */ - trace_hugepage_splitting(address, old); - if (!(old & _PAGE_SPLITTING)) { - /* We need to flush the hpte */ - if (old & _PAGE_HASHPTE) - hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old); - } - /* - * This ensures that generic code that rely on IRQ disabling - * to prevent a parallel THP split work as expected. - */ - kick_all_cpus_sync(); -} - -/* * We want to put the pgtable in pmd and use pgtable for tracking * the base page size hptes */ diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index fa9fb5b4c66c..d5543514c1df 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -135,7 +135,7 @@ static int subpage_walk_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); return 0; } diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index c713b349d967..0d112b94d91d 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -43,6 +43,7 @@ #include <linux/types.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/pfn_t.h> #include <asm/page.h> #include <asm/prom.h> @@ -142,15 +143,13 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) */ static long axon_ram_direct_access(struct block_device *device, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct axon_ram_bank *bank = device->bd_disk->private_data; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT; - void *addr = (void *)(bank->ph_addr + offset); - - *kaddr = (void __pmem *)addr; - *pfn = virt_to_phys(addr) >> PAGE_SHIFT; + *kaddr = (void __pmem __force *) bank->io_addr + offset; + *pfn = phys_to_pfn_t(bank->ph_addr + offset, PFN_DEV); return bank->size - offset; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 24490344c30f..dbeeb3a049f2 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -10,9 +10,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config RWSEM_GENERIC_SPINLOCK bool diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 024f85f947ae..64ead8091248 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -286,7 +286,6 @@ static inline int is_module_addr(void *addr) #define _SEGMENT_ENTRY_DIRTY 0x2000 /* SW segment dirty bit */ #define _SEGMENT_ENTRY_YOUNG 0x1000 /* SW segment young bit */ -#define _SEGMENT_ENTRY_SPLIT 0x0800 /* THP splitting bit */ #define _SEGMENT_ENTRY_LARGE 0x0400 /* STE-format control, large page */ #define _SEGMENT_ENTRY_READ 0x0002 /* SW segment read bit */ #define _SEGMENT_ENTRY_WRITE 0x0001 /* SW segment write bit */ @@ -318,8 +317,6 @@ static inline int is_module_addr(void *addr) * SW-bits: y young, d dirty, r read, w write */ -#define _SEGMENT_ENTRY_SPLIT_BIT 11 /* THP splitting bit number */ - /* Page status table bits for virtualization */ #define PGSTE_ACC_BITS 0xf000000000000000UL #define PGSTE_FP_BIT 0x0800000000000000UL @@ -523,10 +520,6 @@ static inline int pmd_bad(pmd_t pmd) return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, @@ -1424,8 +1417,7 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) if (pmd_large(pmd)) { pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | - _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SPLIT | - _SEGMENT_ENTRY_SOFT_DIRTY; + _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SOFT_DIRTY; pmd_val(pmd) |= massage_pgprot_pmd(newprot); if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; @@ -1533,12 +1525,6 @@ extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, #define __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) && - (pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT); -} - static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t entry) { diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 21c74a71e2ab..13dab0c1645c 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -55,7 +55,7 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask, result; - struct page *head, *page, *tail; + struct page *head, *page; int refs; result = write ? 0 : _SEGMENT_ENTRY_PROTECT; @@ -67,7 +67,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -88,16 +87,6 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; } - /* - * Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -116,16 +105,7 @@ static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, pmd = *pmdp; barrier(); next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush() has to serialize with - * smp_call_function() against our disabled IRQs, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd))) { /* diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index aa34af0a0b26..a809fa8e6f8b 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -578,17 +578,29 @@ int gmap_fault(struct gmap *gmap, unsigned long gaddr, { unsigned long vmaddr; int rc; + bool unlocked; down_read(&gmap->mm->mmap_sem); + +retry: + unlocked = false; vmaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(vmaddr)) { rc = vmaddr; goto out_up; } - if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags)) { + if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, + &unlocked)) { rc = -EFAULT; goto out_up; } + /* + * In the case that fixup_user_fault unlocked the mmap_sem during + * faultin redo __gmap_translate to not race with a map/unmap_segment. + */ + if (unlocked) + goto retry; + rc = __gmap_link(gmap, gaddr, vmaddr); out_up: up_read(&gmap->mm->mmap_sem); @@ -714,12 +726,14 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len) spinlock_t *ptl; pte_t *ptep, entry; pgste_t pgste; + bool unlocked; int rc = 0; if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK)) return -EINVAL; down_read(&gmap->mm->mmap_sem); while (len) { + unlocked = false; /* Convert gmap address and connect the page tables */ addr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(addr)) { @@ -727,10 +741,14 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len) break; } /* Get the page mapped */ - if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE)) { + if (fixup_user_fault(current, gmap->mm, addr, FAULT_FLAG_WRITE, + &unlocked)) { rc = -EFAULT; break; } + /* While trying to map mmap_sem got unlocked. Let us retry */ + if (unlocked) + continue; rc = __gmap_link(gmap, gaddr, addr); if (rc) break; @@ -791,9 +809,11 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, spinlock_t *ptl; pgste_t old, new; pte_t *ptep; + bool unlocked; down_read(&mm->mmap_sem); retry: + unlocked = false; ptep = get_locked_pte(mm, addr, &ptl); if (unlikely(!ptep)) { up_read(&mm->mmap_sem); @@ -802,7 +822,12 @@ retry: if (!(pte_val(*ptep) & _PAGE_INVALID) && (pte_val(*ptep) & _PAGE_PROTECT)) { pte_unmap_unlock(ptep, ptl); - if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) { + /* + * We do not really care about unlocked. We will retry either + * way. But this allows fixup_user_fault to enable userfaultfd. + */ + if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE, + &unlocked)) { up_read(&mm->mmap_sem); return -EFAULT; } @@ -1305,22 +1330,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, return 1; } -static void pmdp_splitting_flush_sync(void *arg) -{ - /* Simply deliver the interrupt */ -} - -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - if (!test_and_set_bit(_SEGMENT_ENTRY_SPLIT_BIT, - (unsigned long *) pmdp)) { - /* need to serialize against gup-fast (IRQ disabled) */ - smp_call_function(pmdp_splitting_flush_sync, NULL, 1); - } -} - void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) { diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index d514df7e04dd..6c391a5d3e5c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -130,9 +130,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 51d8f7f31d1d..58aaa4f33b81 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -241,7 +241,7 @@ static void sh4_flush_cache_page(void *args) */ map_coherent = (current_cpu_data.dcache.n_aliases && test_bit(PG_dcache_clean, &page->flags) && - page_mapped(page)); + page_mapcount(page)); if (map_coherent) vaddr = kmap_coherent(page, address); else diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index f770e3992620..e58cfbf45150 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -59,7 +59,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, unsigned long len) { - if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && test_bit(PG_dcache_clean, &page->flags)) { void *vto = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(vto, src, len); @@ -78,7 +78,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, const void *src, unsigned long len) { - if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && test_bit(PG_dcache_clean, &page->flags)) { void *vfrom = kmap_coherent(page, vaddr) + (vaddr & ~PAGE_MASK); memcpy(dst, vfrom, len); @@ -97,7 +97,7 @@ void copy_user_highpage(struct page *to, struct page *from, vto = kmap_atomic(to); - if (boot_cpu_data.dcache.n_aliases && page_mapped(from) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(from) && test_bit(PG_dcache_clean, &from->flags)) { vfrom = kmap_coherent(from, vaddr); copy_page(vto, vfrom); @@ -153,7 +153,7 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) unsigned long addr = (unsigned long) page_address(page); if (pages_do_alias(addr, vmaddr)) { - if (boot_cpu_data.dcache.n_aliases && page_mapped(page) && + if (boot_cpu_data.dcache.n_aliases && page_mapcount(page) && test_bit(PG_dcache_clean, &page->flags)) { void *kaddr; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 56442d2d7bbc..3203e42190dd 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -101,10 +101,6 @@ config LOCKDEP_SUPPORT bool default y if SPARC64 -config HAVE_LATENCYTOP_SUPPORT - bool - default y if SPARC64 - config ARCH_HIBERNATION_POSSIBLE def_bool y if SPARC64 diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 131d36fcd07a..7a38d6a576c5 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -681,13 +681,6 @@ static inline unsigned long pmd_trans_huge(pmd_t pmd) return pte_val(pte) & _PAGE_PMD_HUGE; } -static inline unsigned long pmd_trans_splitting(pmd_t pmd) -{ - pte_t pte = __pte(pmd_val(pmd)); - - return pmd_trans_huge(pmd) && pte_special(pte); -} - #define has_transparent_hugepage() 1 static inline pmd_t pmd_mkold(pmd_t pmd) @@ -717,29 +710,29 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mkyoung(pmd_t pmd) +static inline pmd_t pmd_mkclean(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - pte = pte_mkyoung(pte); + pte = pte_mkclean(pte); return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mkwrite(pmd_t pmd) +static inline pmd_t pmd_mkyoung(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - pte = pte_mkwrite(pte); + pte = pte_mkyoung(pte); return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mksplitting(pmd_t pmd) +static inline pmd_t pmd_mkwrite(pmd_t pmd) { pte_t pte = __pte(pmd_val(pmd)); - pte = pte_mkspecial(pte); + pte = pte_mkwrite(pte); return __pmd(pte_val(pte)); } diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index dbabe5713a15..cb841a33da59 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -113,9 +113,6 @@ static unsigned int get_user_insn(unsigned long tpc) #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmdp)) { - if (pmd_trans_splitting(*pmdp)) - goto out_irq_enable; - pa = pmd_pfn(*pmdp) << PAGE_SHIFT; pa += tpc & ~HPAGE_MASK; diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c index 2e5c4fc2daa9..eb3d8e8ebc6b 100644 --- a/arch/sparc/mm/gup.c +++ b/arch/sparc/mm/gup.c @@ -56,8 +56,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, put_page(head); return 0; } - if (head != page) - get_huge_page_tail(page); pages[*nr] = page; (*nr)++; @@ -70,7 +68,7 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (!(pmd_val(pmd) & _PAGE_VALID)) @@ -82,7 +80,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, refs = 0; head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON(compound_head(page) != head); pages[*nr] = page; @@ -103,15 +100,6 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, return 0; } - /* Any tail page need their mapcount reference taken before we - * return. - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -126,7 +114,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd))) { if (!gup_huge_pmd(pmdp, pmd, addr, next, diff --git a/arch/tile/include/asm/pgtable.h b/arch/tile/include/asm/pgtable.h index 2b05ccbebed9..96cecf55522e 100644 --- a/arch/tile/include/asm/pgtable.h +++ b/arch/tile/include/asm/pgtable.h @@ -489,16 +489,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 #define pmd_trans_huge pmd_huge_page - -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - return pte_pmd(hv_pte_set_client2(pmd_pte(pmd))); -} - -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return hv_pte_get_client2(pmd_pte(pmd)); -} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h index 71c5d132062a..e13d41c392ae 100644 --- a/arch/um/include/asm/page.h +++ b/arch/um/include/asm/page.h @@ -18,6 +18,7 @@ struct page; +#include <linux/pfn.h> #include <linux/types.h> #include <asm/vm-flags.h> @@ -52,7 +53,6 @@ typedef struct { unsigned long pgd; } pgd_t; #define pmd_val(x) ((x).pmd) #define __pmd(x) ((pmd_t) { (x) } ) -typedef unsigned long long pfn_t; typedef unsigned long long phys_t; #else @@ -76,7 +76,6 @@ typedef struct { unsigned long pmd; } pmd_t; #define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE)) #define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot)) -typedef unsigned long pfn_t; typedef unsigned long phys_t; #endif @@ -109,8 +108,8 @@ extern unsigned long uml_physmem; #define __pa(virt) to_phys((void *) (unsigned long) (virt)) #define __va(phys) to_virt((unsigned long) (phys)) -#define phys_to_pfn(p) ((pfn_t) ((p) >> PAGE_SHIFT)) -#define pfn_to_phys(pfn) ((phys_t) ((pfn) << PAGE_SHIFT)) +#define phys_to_pfn(p) ((p) >> PAGE_SHIFT) +#define pfn_to_phys(pfn) PFN_PHYS(pfn) #define pfn_valid(pfn) ((pfn) < max_mapnr) #define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v))) diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 2b4274e7c095..bae8523a162f 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -98,7 +98,7 @@ static inline unsigned long pte_pfn(pte_t pte) return phys_to_pfn(pte_val(pte)); } -static inline pte_t pfn_pte(pfn_t page_nr, pgprot_t pgprot) +static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { pte_t pte; phys_t phys = pfn_to_phys(page_nr); @@ -107,7 +107,7 @@ static inline pte_t pfn_pte(pfn_t page_nr, pgprot_t pgprot) return pte; } -static inline pmd_t pfn_pmd(pfn_t page_nr, pgprot_t pgprot) +static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)); } diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 18eb9924dda3..7485398d0737 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -271,7 +271,7 @@ static inline int pte_same(pte_t pte_a, pte_t pte_b) #define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys)) #define __virt_to_page(virt) phys_to_page(__pa(virt)) -#define page_to_phys(page) pfn_to_phys((pfn_t) page_to_pfn(page)) +#define page_to_phys(page) pfn_to_phys(page_to_pfn(page)) #define virt_to_page(addr) __virt_to_page((const unsigned long) addr) #define mk_pte(page, pgprot) \ diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 5dc4c0a43ccd..877342640b6e 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -34,9 +34,6 @@ config NO_IOPORT_MAP config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config LOCKDEP_SUPPORT def_bool y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 24f362bf3ec6..4a10ba9e95da 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -180,9 +180,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config MMU def_bool y diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d3eee663c41f..0687c4748b8f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -162,20 +162,22 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return pmd_val(pmd) & _PAGE_SPLITTING; -} - static inline int pmd_trans_huge(pmd_t pmd) { - return pmd_val(pmd) & _PAGE_PSE; + return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } static inline int has_transparent_hugepage(void) { return cpu_has_pse; } + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pmd_devmap(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_DEVMAP); +} +#endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) @@ -252,6 +254,11 @@ static inline pte_t pte_mkspecial(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); +} + static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); @@ -271,6 +278,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_ACCESSED); } +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_DIRTY); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); @@ -281,6 +293,11 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_DEVMAP); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); @@ -462,6 +479,13 @@ static inline int pte_present(pte_t a) return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t a) +{ + return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; +} +#endif + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -808,10 +832,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9630..04c27a013165 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,10 +22,11 @@ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ -#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +#define _PAGE_BIT_SOFTW4 58 /* available for programmer */ +#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ @@ -46,7 +47,6 @@ #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) -#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) #define __HAVE_ARCH_PTE_SPECIAL #ifdef CONFIG_KMEMCHECK @@ -85,8 +85,11 @@ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) +#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) +#define __HAVE_ARCH_PTE_DEVMAP #else #define _PAGE_NX (_AT(pteval_t, 0)) +#define _PAGE_DEVMAP (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index d8ce3ec816ab..1544fabcd7f9 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -132,12 +132,7 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size) { void *vaddr = (void __force *)addr; - /* TODO: implement the zeroing via non-temporal writes */ - if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - clear_page(vaddr); - else - memset(vaddr, 0, size); - + memset(vaddr, 0, size); __arch_wb_cache_pmem(vaddr, size); } diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 483231ebbb0b..e574b8546518 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -175,7 +175,11 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd_mm(mm, 0xA0000, pmd); + + if (pmd_trans_huge(*pmd)) { + struct vm_area_struct *vma = find_vma(mm, 0xA0000); + split_huge_pmd(vma, pmd, 0xA0000); + } if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 5c520ebf6343..a22a488b4622 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -43,11 +43,11 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, +static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, unsigned long npages) { gfn_t end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); end_gfn = gfn + npages; @@ -62,7 +62,8 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long npages) { unsigned long i; @@ -73,7 +74,7 @@ static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; int r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; int flags; @@ -275,7 +276,7 @@ static void kvm_iommu_put_pages(struct kvm *kvm, { struct iommu_domain *domain; gfn_t end_gfn, gfn; - pfn_t pfn; + kvm_pfn_t pfn; u64 phys; domain = kvm->arch.iommu_domain; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 420a5ca3c0ee..95a955de5964 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -259,7 +259,7 @@ static unsigned get_mmio_spte_access(u64 spte) } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -320,7 +320,7 @@ static int is_last_spte(u64 pte, int level) return 0; } -static pfn_t spte_to_pfn(u64 pte) +static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } @@ -582,7 +582,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) */ static int mmu_spte_clear_track_bits(u64 *sptep) { - pfn_t pfn; + kvm_pfn_t pfn; u64 old_spte = *sptep; if (!spte_has_volatile_bits(old_spte)) @@ -1372,7 +1372,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, int need_flush = 0; u64 new_spte; pte_t *ptep = (pte_t *)data; - pfn_t new_pfn; + kvm_pfn_t new_pfn; WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); @@ -2450,7 +2450,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } -static bool kvm_is_mmio_pfn(pfn_t pfn) +static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); @@ -2460,7 +2460,7 @@ static bool kvm_is_mmio_pfn(pfn_t pfn) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, - gfn_t gfn, pfn_t pfn, bool speculative, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { u64 spte; @@ -2539,7 +2539,7 @@ done: } static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, - int write_fault, int level, gfn_t gfn, pfn_t pfn, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool host_writable) { int was_rmapped = 0; @@ -2602,7 +2602,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, return emulate; } -static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, +static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -2684,7 +2684,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) } static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, - int level, gfn_t gfn, pfn_t pfn, bool prefault) + int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -2732,7 +2732,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_info(SIGBUS, &info, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) +static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { /* * Do not cache the mmio info caused by writing the readonly gfn @@ -2752,9 +2752,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, pfn_t *pfnp, int *levelp) + gfn_t *gfnp, kvm_pfn_t *pfnp, + int *levelp) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *gfnp; int level = *levelp; @@ -2793,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, } static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned access, int *ret_val) { bool ret = true; @@ -2947,7 +2948,7 @@ exit: } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable); + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); static void make_mmu_pages_available(struct kvm_vcpu *vcpu); static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, @@ -2956,7 +2957,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, int r; int level; bool force_pt_level = false; - pfn_t pfn; + kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; @@ -3410,7 +3411,7 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable) + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -3448,7 +3449,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { - pfn_t pfn; + kvm_pfn_t pfn; int r; int level; bool force_pt_level; @@ -4601,7 +4602,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, u64 *sptep; struct rmap_iterator iter; int need_tlb_flush = 0; - pfn_t pfn; + kvm_pfn_t pfn; struct kvm_mmu_page *sp; restart: diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 1cee3ec20dd2..dcce533d420c 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -97,7 +97,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) { struct kvm_mmu_page *sp; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; hpa_t hpa; sp = page_header(__pa(sptep)); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 91e939b486d1..6c9fed957cce 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -456,7 +456,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, { unsigned pte_access; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; @@ -551,7 +551,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; @@ -694,7 +694,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; int r; - pfn_t pfn; + kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; bool force_pt_level = false; unsigned long mmu_seq; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 04d61d496b14..e2951b6edbbc 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4251,7 +4251,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { int i, idx, r = 0; - pfn_t identity_map_pfn; + kvm_pfn_t identity_map_pfn; u32 tmp; if (!enable_ept) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f53f5b13c677..4244c2baf57d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5148,7 +5148,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, int emulation_type) { gpa_t gpa = cr2; - pfn_t pfn; + kvm_pfn_t pfn; if (emulation_type & EMULTYPE_NO_REEXECUTE) return false; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index ae9a37bf1371..6d5eb5900372 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -9,6 +9,7 @@ #include <linux/vmstat.h> #include <linux/highmem.h> #include <linux/swap.h> +#include <linux/memremap.h> #include <asm/pgtable.h> @@ -63,6 +64,16 @@ retry: #endif } +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + /* * The performance critical leaf functions are made noinline otherwise gcc * inlines everything into a single function which results in too much @@ -71,7 +82,9 @@ retry: static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; unsigned long mask; + int nr_start = *nr; pte_t *ptep; mask = _PAGE_PRESENT|_PAGE_USER; @@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } - if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { + page = pte_page(pte); + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + pte_unmap(ptep); + return 0; + } + } else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); get_page(page); + put_dev_pagemap(pgmap); SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -114,6 +135,32 @@ static inline void get_head_page_multiple(struct page *page, int nr) SetPageReferenced(page); } +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + unsigned long pfn = pmd_pfn(pmd); + struct dev_pagemap *pgmap = NULL; + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -126,9 +173,13 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, mask |= _PAGE_RW; if ((pmd_flags(pmd) & mask) != mask) return 0; + + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); + if (pmd_devmap(pmd)) + return __gup_device_huge_pmd(pmd, addr, end, pages, nr); + /* hugepages are never "special" */ VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); refs = 0; head = pmd_page(pmd); @@ -136,8 +187,6 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -158,18 +207,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* @@ -212,8 +250,6 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 8829482d69ec..5488d21123bd 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/memremap.h> #include <linux/nmi.h> #include <linux/gfp.h> #include <linux/kcore.h> @@ -714,6 +715,12 @@ static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; + struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page); + + if (altmap) { + vmem_altmap_free(altmap, nr_pages); + return; + } /* bootmem page has reserved flag */ if (PageReserved(page)) { @@ -1017,13 +1024,19 @@ int __ref arch_remove_memory(u64 start, u64 size) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + struct page *page = pfn_to_page(start_pfn); + struct vmem_altmap *altmap; struct zone *zone; int ret; - zone = page_zone(pfn_to_page(start_pfn)); - kernel_physical_mapping_remove(start, start + size); + /* With altmap the first mapped page is offset from @start */ + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + page += vmem_altmap_offset(altmap); + zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + kernel_physical_mapping_remove(start, start + size); return ret; } @@ -1235,7 +1248,7 @@ static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node) + unsigned long end, int node, struct vmem_altmap *altmap) { unsigned long addr; unsigned long next; @@ -1258,7 +1271,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; @@ -1279,7 +1292,8 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; continue; - } + } else if (altmap) + return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); continue; @@ -1293,11 +1307,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { + struct vmem_altmap *altmap = to_vmem_altmap(start); int err; if (cpu_has_pse) - err = vmemmap_populate_hugepages(start, end, node); - else + err = vmemmap_populate_hugepages(start, end, node, altmap); + else if (altmap) { + pr_err_once("%s: no cpu support for altmap allocations\n", + __func__); + err = -ENOMEM; + } else err = vmemmap_populate_basepages(start, end, node); if (!err) sync_global_pgds(start, end - 1, 0); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 031782e74231..f4ae536b0914 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -12,6 +12,7 @@ #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/fs.h> @@ -949,7 +950,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, } int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { enum page_cache_mode pcm; @@ -957,7 +958,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, return 0; /* Set prot based on lookup */ - pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); + pcm = lookup_memtype(pfn_t_to_phys(pfn)); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index ee9c2e3a7199..4eb287e25043 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -505,19 +505,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, return young; } - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - int set; - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - set = !test_and_set_bit(_PAGE_BIT_SPLITTING, - (unsigned long *)pmdp); - if (set) { - /* need tlb flush only to serialize against gup-fast */ - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - } -} #endif /** diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 360944e1da52..d030594ed22b 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -86,8 +86,10 @@ #define MADV_SEQUENTIAL 2 /* expect sequential page references */ #define MADV_WILLNEED 3 /* will need these pages */ #define MADV_DONTNEED 4 /* don't need these pages */ +#define MADV_FREE 5 /* free pages only if memory pressure */ /* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c index 5ece856c5725..35c822286bbe 100644 --- a/arch/xtensa/mm/tlb.c +++ b/arch/xtensa/mm/tlb.c @@ -245,7 +245,7 @@ static int check_tlb_entry(unsigned w, unsigned e, bool dtlb) page_mapcount(p)); if (!page_count(p)) rc |= TLB_INSANE; - else if (page_mapped(p)) + else if (page_mapcount(p)) rc |= TLB_SUSPICIOUS; } else { rc |= TLB_INSANE; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 619fe584a44c..213456c2b123 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -647,6 +647,13 @@ static int add_memory_block(int base_section_nr) return 0; } +static bool is_zone_device_section(struct mem_section *ms) +{ + struct page *page; + + page = sparse_decode_mem_map(ms->section_mem_map, __section_nr(ms)); + return is_zone_device_page(page); +} /* * need an interface for the VM to add new memory regions, @@ -657,6 +664,9 @@ int register_new_memory(int nid, struct mem_section *section) int ret = 0; struct memory_block *mem; + if (is_zone_device_section(section)) + return 0; + mutex_lock(&mem_sysfs_mutex); mem = find_memory_block(section); @@ -693,6 +703,9 @@ static int remove_memory_section(unsigned long node_id, { struct memory_block *mem; + if (is_zone_device_section(section)) + return 0; + mutex_lock(&mem_sysfs_mutex); mem = find_memory_block(section); unregister_mem_sect_under_nodes(mem, __section_nr(section)); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index a5880f4ab40e..cb27190e9f39 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -19,6 +19,9 @@ #include <linux/radix-tree.h> #include <linux/fs.h> #include <linux/slab.h> +#ifdef CONFIG_BLK_DEV_RAM_DAX +#include <linux/pfn_t.h> +#endif #include <asm/uaccess.h> @@ -378,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, #ifdef CONFIG_BLK_DEV_RAM_DAX static long brd_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct brd_device *brd = bdev->bd_disk->private_data; struct page *page; @@ -389,7 +392,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector, if (!page) return -ENOSPC; *kaddr = (void __pmem *)page_address(page); - *pfn = page_to_pfn(page); + *pfn = page_to_pfn_t(page); return PAGE_SIZE; } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 47915d736f8d..370c2f76016d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1325,7 +1325,6 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); - idr_remove(&zram_index_idr, zram->disk->first_minor); blk_cleanup_queue(zram->disk->queue); del_gendisk(zram->disk); put_disk(zram->disk); @@ -1367,10 +1366,12 @@ static ssize_t hot_remove_store(struct class *class, mutex_lock(&zram_index_mutex); zram = idr_find(&zram_index_idr, dev_id); - if (zram) + if (zram) { ret = zram_remove(zram); - else + idr_remove(&zram_index_idr, dev_id); + } else { ret = -ENODEV; + } mutex_unlock(&zram_index_mutex); return ret ? ret : count; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 252eb301470c..32358c5e3db4 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -14,6 +14,7 @@ #include <linux/shmem_fs.h> #include <linux/dma-buf.h> +#include <linux/pfn_t.h> #include <drm/exynos_drm.h> #include "exynos_drm_drv.h" @@ -490,7 +491,8 @@ int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } pfn = page_to_pfn(exynos_gem->pages[page_offset]); - ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn); + ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, + __pfn_to_pfn_t(pfn, PFN_DEV)); out: switch (ret) { diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index ee95c03a8c54..cb95765050cc 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -21,6 +21,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> +#include <linux/pfn_t.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/slab.h> @@ -132,7 +133,8 @@ static int psbfb_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) for (i = 0; i < page_num; i++) { pfn = (phys_addr >> PAGE_SHIFT); - ret = vm_insert_mixed(vma, address, pfn); + ret = vm_insert_mixed(vma, address, + __pfn_to_pfn_t(pfn, PFN_DEV)); if (unlikely((ret == -EBUSY) || (ret != 0 && i > 0))) break; else if (unlikely(ret != 0)) { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index c76cc853b08a..3cedb8d5c855 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -18,6 +18,7 @@ #include <linux/spinlock.h> #include <linux/shmem_fs.h> #include <linux/dma-buf.h> +#include <linux/pfn_t.h> #include "msm_drv.h" #include "msm_gem.h" @@ -222,7 +223,8 @@ int msm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address, pfn, pfn << PAGE_SHIFT); - ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn); + ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, + __pfn_to_pfn_t(pfn, PFN_DEV)); out_unlock: mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index 7ed08fdc4c42..ceba5459ceb7 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -19,6 +19,7 @@ #include <linux/shmem_fs.h> #include <linux/spinlock.h> +#include <linux/pfn_t.h> #include <drm/drm_vma_manager.h> @@ -385,7 +386,8 @@ static int fault_1d(struct drm_gem_object *obj, VERB("Inserting %p pfn %lx, pa %lx", vmf->virtual_address, pfn, pfn << PAGE_SHIFT); - return vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn); + return vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, + __pfn_to_pfn_t(pfn, PFN_DEV)); } /* Special handling for the case of faulting in 2d tiled buffers */ @@ -478,7 +480,8 @@ static int fault_2d(struct drm_gem_object *obj, pfn, pfn << PAGE_SHIFT); for (i = n; i > 0; i--) { - vm_insert_mixed(vma, (unsigned long)vaddr, pfn); + vm_insert_mixed(vma, (unsigned long)vaddr, + __pfn_to_pfn_t(pfn, PFN_DEV)); pfn += usergart[fmt].stride_pfn; vaddr += PAGE_SIZE * m; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 8fb7213277cc..06d26dc438b2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -35,6 +35,7 @@ #include <ttm/ttm_placement.h> #include <drm/drm_vma_manager.h> #include <linux/mm.h> +#include <linux/pfn_t.h> #include <linux/rbtree.h> #include <linux/module.h> #include <linux/uaccess.h> @@ -229,7 +230,8 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } if (vma->vm_flags & VM_MIXEDMAP) - ret = vm_insert_mixed(&cvma, address, pfn); + ret = vm_insert_mixed(&cvma, address, + __pfn_to_pfn_t(pfn, PFN_DEV)); else ret = vm_insert_pfn(&cvma, address, pfn); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index fd01f3493fc7..af7cc1e65656 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -433,16 +433,15 @@ ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals) scale_db = true; case IIO_VAL_INT_PLUS_MICRO: if (vals[1] < 0) - return sprintf(buf, "-%ld.%06u%s\n", abs(vals[0]), - -vals[1], - scale_db ? " dB" : ""); + return sprintf(buf, "-%d.%06u%s\n", abs(vals[0]), + -vals[1], scale_db ? " dB" : ""); else return sprintf(buf, "%d.%06u%s\n", vals[0], vals[1], scale_db ? " dB" : ""); case IIO_VAL_INT_PLUS_NANO: if (vals[1] < 0) - return sprintf(buf, "-%ld.%09u\n", abs(vals[0]), - -vals[1]); + return sprintf(buf, "-%d.%09u\n", abs(vals[0]), + -vals[1]); else return sprintf(buf, "%d.%09u\n", vals[0], vals[1]); case IIO_VAL_FRACTIONAL: diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/calib.c b/drivers/net/wireless/intel/iwlwifi/dvm/calib.c index 07a4c644fb9b..e9cef9de9ed8 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/calib.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/calib.c @@ -901,7 +901,7 @@ static void iwlagn_gain_computation(struct iwl_priv *priv, /* bound gain by 2 bits value max, 3rd bit is sign */ data->delta_gain_code[i] = min(abs(delta_g), - (long) CHAIN_NOISE_MAX_DELTA_GAIN_CODE); + (s32) CHAIN_NOISE_MAX_DELTA_GAIN_CODE); if (delta_g < 0) /* diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index f9b674bc49db..0cc9048b86e2 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -83,8 +83,7 @@ static ssize_t mode_store(struct device *dev, if (strncmp(buf, "pmem\n", n) == 0 || strncmp(buf, "pmem", n) == 0) { - /* TODO: allocate from PMEM support */ - rc = -ENOTTY; + nd_pfn->mode = PFN_MODE_PMEM; } else if (strncmp(buf, "ram\n", n) == 0 || strncmp(buf, "ram", n) == 0) nd_pfn->mode = PFN_MODE_RAM; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index b493ff3fccb2..7edf31671dab 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -21,10 +21,11 @@ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/module.h> -#include <linux/memory_hotplug.h> #include <linux/moduleparam.h> #include <linux/badblocks.h> +#include <linux/memremap.h> #include <linux/vmalloc.h> +#include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/pmem.h> #include <linux/nd.h> @@ -40,6 +41,7 @@ struct pmem_device { phys_addr_t phys_addr; /* when non-zero this device is hosting a 'pfn' instance */ phys_addr_t data_offset; + unsigned long pfn_flags; void __pmem *virt_addr; size_t size; struct badblocks bb; @@ -135,13 +137,13 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, } static long pmem_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct pmem_device *pmem = bdev->bd_disk->private_data; resource_size_t offset = sector * 512 + pmem->data_offset; *kaddr = pmem->virt_addr + offset; - *pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT; + *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); return pmem->size - offset; } @@ -157,6 +159,7 @@ static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res, int id) { struct pmem_device *pmem; + struct request_queue *q; pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); if (!pmem) @@ -174,16 +177,26 @@ static struct pmem_device *pmem_alloc(struct device *dev, return ERR_PTR(-EBUSY); } - if (pmem_should_map_pages(dev)) - pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res); - else + q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev)); + if (!q) + return ERR_PTR(-ENOMEM); + + pmem->pfn_flags = PFN_DEV; + if (pmem_should_map_pages(dev)) { + pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res, + &q->q_usage_counter, NULL); + pmem->pfn_flags |= PFN_MAP; + } else pmem->virt_addr = (void __pmem *) devm_memremap(dev, pmem->phys_addr, pmem->size, ARCH_MEMREMAP_PMEM); - if (IS_ERR(pmem->virt_addr)) + if (IS_ERR(pmem->virt_addr)) { + blk_cleanup_queue(q); return (void __force *) pmem->virt_addr; + } + pmem->pmem_queue = q; return pmem; } @@ -203,10 +216,6 @@ static int pmem_attach_disk(struct device *dev, int nid = dev_to_node(dev); struct gendisk *disk; - pmem->pmem_queue = blk_alloc_queue_node(GFP_KERNEL, nid); - if (!pmem->pmem_queue) - return -ENOMEM; - blk_queue_make_request(pmem->pmem_queue, pmem_make_request); blk_queue_physical_block_size(pmem->pmem_queue, PAGE_SIZE); blk_queue_max_hw_sectors(pmem->pmem_queue, UINT_MAX); @@ -352,12 +361,17 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns) struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim); struct device *dev = &nd_pfn->dev; - struct vmem_altmap *altmap; struct nd_region *nd_region; + struct vmem_altmap *altmap; struct nd_pfn_sb *pfn_sb; struct pmem_device *pmem; + struct request_queue *q; phys_addr_t offset; int rc; + struct vmem_altmap __altmap = { + .base_pfn = __phys_to_pfn(nsio->res.start), + .reserve = __phys_to_pfn(SZ_8K), + }; if (!nd_pfn->uuid || !nd_pfn->ndns) return -ENODEV; @@ -375,6 +389,17 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns) return -EINVAL; nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns); altmap = NULL; + } else if (nd_pfn->mode == PFN_MODE_PMEM) { + nd_pfn->npfns = (resource_size(&nsio->res) - offset) + / PAGE_SIZE; + if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns) + dev_info(&nd_pfn->dev, + "number of pfns truncated from %lld to %ld\n", + le64_to_cpu(nd_pfn->pfn_sb->npfns), + nd_pfn->npfns); + altmap = & __altmap; + altmap->free = __phys_to_pfn(offset - SZ_8K); + altmap->alloc = 0; } else { rc = -ENXIO; goto err; @@ -382,8 +407,11 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns) /* establish pfn range for lookup, and switch to direct map */ pmem = dev_get_drvdata(dev); + q = pmem->pmem_queue; devm_memunmap(dev, (void __force *) pmem->virt_addr); - pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res); + pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res, + &q->q_usage_counter, altmap); + pmem->pfn_flags |= PFN_MAP; if (IS_ERR(pmem->virt_addr)) { rc = PTR_ERR(pmem->virt_addr); goto err; @@ -424,19 +452,22 @@ static int nd_pmem_probe(struct device *dev) return -ENOMEM; nvdimm_namespace_add_poison(ndns, &pmem->bb, 0); - if (is_nd_btt(dev)) + if (is_nd_btt(dev)) { + /* btt allocates its own request_queue */ + blk_cleanup_queue(pmem->pmem_queue); + pmem->pmem_queue = NULL; return nvdimm_namespace_attach_btt(ndns); + } if (is_nd_pfn(dev)) return nvdimm_namespace_attach_pfn(ndns); - if (nd_btt_probe(ndns, pmem) == 0) { - /* we'll come back as btt-pmem */ - return -ENXIO; - } - - if (nd_pfn_probe(ndns, pmem) == 0) { - /* we'll come back as pfn-pmem */ + if (nd_btt_probe(ndns, pmem) == 0 || nd_pfn_probe(ndns, pmem) == 0) { + /* + * We'll come back as either btt-pmem, or pfn-pmem, so + * drop the queue allocation for now. + */ + blk_cleanup_queue(pmem->pmem_queue); return -ENXIO; } diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 94a8f4ab57bc..ce7b70181740 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -17,6 +17,7 @@ #include <linux/completion.h> #include <linux/interrupt.h> #include <linux/platform_device.h> +#include <linux/pfn_t.h> #include <asm/extmem.h> #include <asm/io.h> @@ -30,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode); static blk_qc_t dcssblk_make_request(struct request_queue *q, struct bio *bio); static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum, - void __pmem **kaddr, unsigned long *pfn); + void __pmem **kaddr, pfn_t *pfn); static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0"; @@ -883,20 +884,18 @@ fail: static long dcssblk_direct_access (struct block_device *bdev, sector_t secnum, - void __pmem **kaddr, unsigned long *pfn) + void __pmem **kaddr, pfn_t *pfn) { struct dcssblk_dev_info *dev_info; unsigned long offset, dev_sz; - void *addr; dev_info = bdev->bd_disk->private_data; if (!dev_info) return -ENODEV; dev_sz = dev_info->end - dev_info->start; offset = secnum * 512; - addr = (void *) (dev_info->start + offset); - *pfn = virt_to_phys(addr) >> PAGE_SHIFT; - *kaddr = (void __pmem *) addr; + *kaddr = (void __pmem *) (dev_info->start + offset); + *pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), PFN_DEV); return dev_sz - offset; } diff --git a/fs/Kconfig b/fs/Kconfig index 2bb1ef86c411..9adee0d7536e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -50,7 +50,8 @@ config FS_DAX_PMD bool default FS_DAX depends on FS_DAX - depends on BROKEN + depends on ZONE_DEVICE + depends on TRANSPARENT_HUGEPAGE endif # BLOCK diff --git a/fs/block_dev.c b/fs/block_dev.c index 81c0705558be..530145b607c4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -455,10 +455,7 @@ EXPORT_SYMBOL_GPL(bdev_write_page); /** * bdev_direct_access() - Get the address for directly-accessibly memory * @bdev: The device containing the memory - * @sector: The offset within the device - * @addr: Where to put the address of the memory - * @pfn: The Page Frame Number for the memory - * @size: The number of bytes requested + * @dax: control and output parameters for ->direct_access * * If a block device is made up of directly addressable memory, this function * will tell the caller the PFN and the address of the memory. The address @@ -469,10 +466,10 @@ EXPORT_SYMBOL_GPL(bdev_write_page); * Return: negative errno if an error occurs, otherwise the number of bytes * accessible at this address. */ -long bdev_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **addr, unsigned long *pfn, long size) +long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) { - long avail; + sector_t sector = dax->sector; + long avail, size = dax->size; const struct block_device_operations *ops = bdev->bd_disk->fops; /* @@ -491,9 +488,11 @@ long bdev_direct_access(struct block_device *bdev, sector_t sector, sector += get_start_sect(bdev); if (sector % (PAGE_SIZE / 512)) return -EINVAL; - avail = ops->direct_access(bdev, sector, addr, pfn); + avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn); if (!avail) return -ERANGE; + if (avail > 0 && avail & ~PAGE_MASK) + return -ENXIO; return min(avail, size); } EXPORT_SYMBOL_GPL(bdev_direct_access); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0068e82217c3..0a2752b79e72 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3391,13 +3391,13 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, * should have access to this page, we're safe to simply set * PG_locked without checking it first. */ - __set_page_locked(page); + __SetPageLocked(page); rc = add_to_page_cache_locked(page, mapping, page->index, gfp); /* give up if we can't stick it in the cache */ if (rc) { - __clear_page_locked(page); + __ClearPageLocked(page); return rc; } @@ -3418,9 +3418,9 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list, if (*bytes + PAGE_CACHE_SIZE > rsize) break; - __set_page_locked(page); + __SetPageLocked(page); if (add_to_page_cache_locked(page, mapping, page->index, gfp)) { - __clear_page_locked(page); + __ClearPageLocked(page); break; } list_move_tail(&page->lru, tmplist); diff --git a/fs/dax.c b/fs/dax.c index 43671b68220e..7af879759064 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -28,54 +28,68 @@ #include <linux/sched.h> #include <linux/uio.h> #include <linux/vmstat.h> +#include <linux/pfn_t.h> +#include <linux/sizes.h> + +static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax) +{ + struct request_queue *q = bdev->bd_queue; + long rc = -EIO; + + dax->addr = (void __pmem *) ERR_PTR(-EIO); + if (blk_queue_enter(q, true) != 0) + return rc; + + rc = bdev_direct_access(bdev, dax); + if (rc < 0) { + dax->addr = (void __pmem *) ERR_PTR(rc); + blk_queue_exit(q); + return rc; + } + return rc; +} + +static void dax_unmap_atomic(struct block_device *bdev, + const struct blk_dax_ctl *dax) +{ + if (IS_ERR(dax->addr)) + return; + blk_queue_exit(bdev->bd_queue); +} /* * dax_clear_blocks() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS * semantics for all operations. */ -int dax_clear_blocks(struct inode *inode, sector_t block, long size) +int dax_clear_blocks(struct inode *inode, sector_t block, long _size) { struct block_device *bdev = inode->i_sb->s_bdev; - sector_t sector = block << (inode->i_blkbits - 9); + struct blk_dax_ctl dax = { + .sector = block << (inode->i_blkbits - 9), + .size = _size, + }; might_sleep(); do { - void __pmem *addr; - unsigned long pfn; - long count; + long count, sz; - count = bdev_direct_access(bdev, sector, &addr, &pfn, size); + count = dax_map_atomic(bdev, &dax); if (count < 0) return count; - BUG_ON(size < count); - while (count > 0) { - unsigned pgsz = PAGE_SIZE - offset_in_page(addr); - if (pgsz > count) - pgsz = count; - clear_pmem(addr, pgsz); - addr += pgsz; - size -= pgsz; - count -= pgsz; - BUG_ON(pgsz & 511); - sector += pgsz / 512; - cond_resched(); - } - } while (size); + sz = min_t(long, count, SZ_128K); + clear_pmem(dax.addr, sz); + dax.size -= sz; + dax.sector += sz / 512; + dax_unmap_atomic(bdev, &dax); + cond_resched(); + } while (dax.size); wmb_pmem(); return 0; } EXPORT_SYMBOL_GPL(dax_clear_blocks); -static long dax_get_addr(struct buffer_head *bh, void __pmem **addr, - unsigned blkbits) -{ - unsigned long pfn; - sector_t sector = bh->b_blocknr << (blkbits - 9); - return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size); -} - /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */ static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first, loff_t pos, loff_t end) @@ -105,19 +119,29 @@ static bool buffer_size_valid(struct buffer_head *bh) return bh->b_state != 0; } + +static sector_t to_sector(const struct buffer_head *bh, + const struct inode *inode) +{ + sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); + + return sector; +} + static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, loff_t start, loff_t end, get_block_t get_block, struct buffer_head *bh) { - ssize_t retval = 0; - loff_t pos = start; - loff_t max = start; - loff_t bh_max = start; - void __pmem *addr; - bool hole = false; - bool need_wmb = false; - - if (iov_iter_rw(iter) != WRITE) + loff_t pos = start, max = start, bh_max = start; + bool hole = false, need_wmb = false; + struct block_device *bdev = NULL; + int rw = iov_iter_rw(iter), rc; + long map_len = 0; + struct blk_dax_ctl dax = { + .addr = (void __pmem *) ERR_PTR(-EIO), + }; + + if (rw == READ) end = min(end, i_size_read(inode)); while (pos < end) { @@ -132,13 +156,13 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, if (pos == bh_max) { bh->b_size = PAGE_ALIGN(end - pos); bh->b_state = 0; - retval = get_block(inode, block, bh, - iov_iter_rw(iter) == WRITE); - if (retval) + rc = get_block(inode, block, bh, rw == WRITE); + if (rc) break; if (!buffer_size_valid(bh)) bh->b_size = 1 << blkbits; bh_max = pos - first + bh->b_size; + bdev = bh->b_bdev; } else { unsigned done = bh->b_size - (bh_max - (pos - first)); @@ -146,47 +170,53 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, bh->b_size -= done; } - hole = iov_iter_rw(iter) != WRITE && !buffer_written(bh); + hole = rw == READ && !buffer_written(bh); if (hole) { - addr = NULL; size = bh->b_size - first; } else { - retval = dax_get_addr(bh, &addr, blkbits); - if (retval < 0) + dax_unmap_atomic(bdev, &dax); + dax.sector = to_sector(bh, inode); + dax.size = bh->b_size; + map_len = dax_map_atomic(bdev, &dax); + if (map_len < 0) { + rc = map_len; break; + } if (buffer_unwritten(bh) || buffer_new(bh)) { - dax_new_buf(addr, retval, first, pos, - end); + dax_new_buf(dax.addr, map_len, first, + pos, end); need_wmb = true; } - addr += first; - size = retval - first; + dax.addr += first; + size = map_len - first; } max = min(pos + size, end); } if (iov_iter_rw(iter) == WRITE) { - len = copy_from_iter_pmem(addr, max - pos, iter); + len = copy_from_iter_pmem(dax.addr, max - pos, iter); need_wmb = true; } else if (!hole) - len = copy_to_iter((void __force *)addr, max - pos, + len = copy_to_iter((void __force *) dax.addr, max - pos, iter); else len = iov_iter_zero(max - pos, iter); if (!len) { - retval = -EFAULT; + rc = -EFAULT; break; } pos += len; - addr += len; + if (!IS_ERR(dax.addr)) + dax.addr += len; } if (need_wmb) wmb_pmem(); + dax_unmap_atomic(bdev, &dax); - return (pos == start) ? retval : pos - start; + return (pos == start) ? rc : pos - start; } /** @@ -275,28 +305,35 @@ static int dax_load_hole(struct address_space *mapping, struct page *page, return VM_FAULT_LOCKED; } -static int copy_user_bh(struct page *to, struct buffer_head *bh, - unsigned blkbits, unsigned long vaddr) +static int copy_user_bh(struct page *to, struct inode *inode, + struct buffer_head *bh, unsigned long vaddr) { - void __pmem *vfrom; + struct blk_dax_ctl dax = { + .sector = to_sector(bh, inode), + .size = bh->b_size, + }; + struct block_device *bdev = bh->b_bdev; void *vto; - if (dax_get_addr(bh, &vfrom, blkbits) < 0) - return -EIO; + if (dax_map_atomic(bdev, &dax) < 0) + return PTR_ERR(dax.addr); vto = kmap_atomic(to); - copy_user_page(vto, (void __force *)vfrom, vaddr, to); + copy_user_page(vto, (void __force *)dax.addr, vaddr, to); kunmap_atomic(vto); + dax_unmap_atomic(bdev, &dax); return 0; } static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, struct vm_area_struct *vma, struct vm_fault *vmf) { - struct address_space *mapping = inode->i_mapping; - sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); unsigned long vaddr = (unsigned long)vmf->virtual_address; - void __pmem *addr; - unsigned long pfn; + struct address_space *mapping = inode->i_mapping; + struct block_device *bdev = bh->b_bdev; + struct blk_dax_ctl dax = { + .sector = to_sector(bh, inode), + .size = bh->b_size, + }; pgoff_t size; int error; @@ -315,20 +352,18 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, goto out; } - error = bdev_direct_access(bh->b_bdev, sector, &addr, &pfn, bh->b_size); - if (error < 0) - goto out; - if (error < PAGE_SIZE) { - error = -EIO; + if (dax_map_atomic(bdev, &dax) < 0) { + error = PTR_ERR(dax.addr); goto out; } if (buffer_unwritten(bh) || buffer_new(bh)) { - clear_pmem(addr, PAGE_SIZE); + clear_pmem(dax.addr, PAGE_SIZE); wmb_pmem(); } + dax_unmap_atomic(bdev, &dax); - error = vm_insert_mixed(vma, vaddr, pfn); + error = vm_insert_mixed(vma, vaddr, dax.pfn); out: i_mmap_unlock_read(mapping); @@ -422,7 +457,7 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, if (vmf->cow_page) { struct page *new_page = vmf->cow_page; if (buffer_written(&bh)) - error = copy_user_bh(new_page, &bh, blkbits, vaddr); + error = copy_user_bh(new_page, inode, &bh, vaddr); else clear_user_highpage(new_page, vaddr); if (error) @@ -523,6 +558,24 @@ EXPORT_SYMBOL_GPL(dax_fault); */ #define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) +static void __dax_dbg(struct buffer_head *bh, unsigned long address, + const char *reason, const char *fn) +{ + if (bh) { + char bname[BDEVNAME_SIZE]; + bdevname(bh->b_bdev, bname); + pr_debug("%s: %s addr: %lx dev %s state %lx start %lld " + "length %zd fallback: %s\n", fn, current->comm, + address, bname, bh->b_state, (u64)bh->b_blocknr, + bh->b_size, reason); + } else { + pr_debug("%s: %s addr: %lx fallback: %s\n", fn, + current->comm, address, reason); + } +} + +#define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd") + int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, get_block_t get_block, dax_iodone_t complete_unwritten) @@ -534,41 +587,49 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, unsigned blkbits = inode->i_blkbits; unsigned long pmd_addr = address & PMD_MASK; bool write = flags & FAULT_FLAG_WRITE; - long length; - void __pmem *kaddr; + struct block_device *bdev; pgoff_t size, pgoff; - sector_t block, sector; - unsigned long pfn; + sector_t block; int result = 0; - /* dax pmd mappings are broken wrt gup and fork */ + /* dax pmd mappings require pfn_t_devmap() */ if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) return VM_FAULT_FALLBACK; /* Fall back to PTEs if we're going to COW */ - if (write && !(vma->vm_flags & VM_SHARED)) + if (write && !(vma->vm_flags & VM_SHARED)) { + split_huge_pmd(vma, pmd, address); + dax_pmd_dbg(NULL, address, "cow write"); return VM_FAULT_FALLBACK; + } /* If the PMD would extend outside the VMA */ - if (pmd_addr < vma->vm_start) + if (pmd_addr < vma->vm_start) { + dax_pmd_dbg(NULL, address, "vma start unaligned"); return VM_FAULT_FALLBACK; - if ((pmd_addr + PMD_SIZE) > vma->vm_end) + } + if ((pmd_addr + PMD_SIZE) > vma->vm_end) { + dax_pmd_dbg(NULL, address, "vma end unaligned"); return VM_FAULT_FALLBACK; + } pgoff = linear_page_index(vma, pmd_addr); size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (pgoff >= size) return VM_FAULT_SIGBUS; /* If the PMD would cover blocks out of the file */ - if ((pgoff | PG_PMD_COLOUR) >= size) + if ((pgoff | PG_PMD_COLOUR) >= size) { + dax_pmd_dbg(NULL, address, + "offset + huge page size > file size"); return VM_FAULT_FALLBACK; + } memset(&bh, 0, sizeof(bh)); block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; - length = get_block(inode, block, &bh, write); - if (length) + if (get_block(inode, block, &bh, write) != 0) return VM_FAULT_SIGBUS; + bdev = bh.b_bdev; i_mmap_lock_read(mapping); /* @@ -576,8 +637,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, * just fall back to PTEs. Calling get_block 512 times in a loop * would be silly. */ - if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) + if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) { + dax_pmd_dbg(&bh, address, "allocated block too small"); goto fallback; + } /* * If we allocated new storage, make sure no process has any @@ -600,57 +663,82 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, result = VM_FAULT_SIGBUS; goto out; } - if ((pgoff | PG_PMD_COLOUR) >= size) + if ((pgoff | PG_PMD_COLOUR) >= size) { + dax_pmd_dbg(&bh, address, "pgoff unaligned"); goto fallback; + } if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) { spinlock_t *ptl; pmd_t entry; struct page *zero_page = get_huge_zero_page(); - if (unlikely(!zero_page)) + if (unlikely(!zero_page)) { + dax_pmd_dbg(&bh, address, "no zero page"); goto fallback; + } ptl = pmd_lock(vma->vm_mm, pmd); if (!pmd_none(*pmd)) { spin_unlock(ptl); + dax_pmd_dbg(&bh, address, "pmd already present"); goto fallback; } + dev_dbg(part_to_dev(bdev->bd_part), + "%s: %s addr: %lx pfn: <zero> sect: %llx\n", + __func__, current->comm, address, + (unsigned long long) to_sector(&bh, inode)); + entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry); result = VM_FAULT_NOPAGE; spin_unlock(ptl); } else { - sector = bh.b_blocknr << (blkbits - 9); - length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn, - bh.b_size); + struct blk_dax_ctl dax = { + .sector = to_sector(&bh, inode), + .size = PMD_SIZE, + }; + long length = dax_map_atomic(bdev, &dax); + if (length < 0) { result = VM_FAULT_SIGBUS; goto out; } - if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR)) + if (length < PMD_SIZE) { + dax_pmd_dbg(&bh, address, "dax-length too small"); + dax_unmap_atomic(bdev, &dax); goto fallback; + } + if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) { + dax_pmd_dbg(&bh, address, "pfn unaligned"); + dax_unmap_atomic(bdev, &dax); + goto fallback; + } - /* - * TODO: teach vmf_insert_pfn_pmd() to support - * 'pte_special' for pmds - */ - if (pfn_valid(pfn)) + if (!pfn_t_devmap(dax.pfn)) { + dax_unmap_atomic(bdev, &dax); + dax_pmd_dbg(&bh, address, "pfn not in memmap"); goto fallback; + } if (buffer_unwritten(&bh) || buffer_new(&bh)) { - int i; - for (i = 0; i < PTRS_PER_PMD; i++) - clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE); + clear_pmem(dax.addr, PMD_SIZE); wmb_pmem(); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); result |= VM_FAULT_MAJOR; } - - result |= vmf_insert_pfn_pmd(vma, address, pmd, pfn, write); + dax_unmap_atomic(bdev, &dax); + + dev_dbg(part_to_dev(bdev->bd_part), + "%s: %s addr: %lx pfn: %lx sect: %llx\n", + __func__, current->comm, address, + pfn_t_to_pfn(dax.pfn), + (unsigned long long) dax.sector); + result |= vmf_insert_pfn_pmd(vma, address, pmd, + dax.pfn, write); } out: @@ -752,12 +840,17 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length, if (err < 0) return err; if (buffer_written(&bh)) { - void __pmem *addr; - err = dax_get_addr(&bh, &addr, inode->i_blkbits); - if (err < 0) - return err; - clear_pmem(addr + offset, length); + struct block_device *bdev = bh.b_bdev; + struct blk_dax_ctl dax = { + .sector = to_sector(&bh, inode), + .size = PAGE_CACHE_SIZE, + }; + + if (dax_map_atomic(bdev, &dax) < 0) + return PTR_ERR(dax.addr); + clear_pmem(dax.addr + offset, length); wmb_pmem(); + dax_unmap_atomic(bdev, &dax); } return 0; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 023f6a1f23cd..6915c950e6e8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -677,9 +677,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page, if (!wbc->wb) return; - rcu_read_lock(); id = mem_cgroup_css_from_page(page)->id; - rcu_read_unlock(); if (id == wbc->wb_id) { wbc->wb_bytes += bytes; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 47789292a582..8bbf7f3e2a27 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -324,11 +324,48 @@ static void remove_huge_page(struct page *page) delete_from_page_cache(page); } +static void +hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) +{ + struct vm_area_struct *vma; + + /* + * end == 0 indicates that the entire range after + * start should be unmapped. + */ + vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { + unsigned long v_offset; + unsigned long v_end; + + /* + * Can the expression below overflow on 32-bit arches? + * No, because the interval tree returns us only those vmas + * which overlap the truncated area starting at pgoff, + * and no vma on a 32-bit arch can span beyond the 4GB. + */ + if (vma->vm_pgoff < start) + v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT; + else + v_offset = 0; + + if (!end) + v_end = vma->vm_end; + else { + v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + + vma->vm_start; + if (v_end > vma->vm_end) + v_end = vma->vm_end; + } + + unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end, + NULL); + } +} /* * remove_inode_hugepages handles two distinct cases: truncation and hole * punch. There are subtle differences in operation for each case. - + * * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv @@ -379,6 +416,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; + bool rsv_on_error; u32 hash; /* @@ -395,37 +433,43 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); - lock_page(page); - if (likely(!page_mapped(page))) { - bool rsv_on_error = !PagePrivate(page); - /* - * We must free the huge page and remove - * from page cache (remove_huge_page) BEFORE - * removing the region/reserve map - * (hugetlb_unreserve_pages). In rare out - * of memory conditions, removal of the - * region/reserve map could fail. Before - * free'ing the page, note PagePrivate which - * is used in case of error. - */ - remove_huge_page(page); - freed++; - if (!truncate_op) { - if (unlikely(hugetlb_unreserve_pages( - inode, next, - next + 1, 1))) - hugetlb_fix_reserve_counts( - inode, rsv_on_error); - } - } else { - /* - * If page is mapped, it was faulted in after - * being unmapped. It indicates a race between - * hole punch and page fault. Do nothing in - * this case. Getting here in a truncate - * operation is a bug. - */ + /* + * If page is mapped, it was faulted in after being + * unmapped in caller. Unmap (again) now after taking + * the fault mutex. The mutex will prevent faults + * until we finish removing the page. + * + * This race can only happen in the hole punch case. + * Getting here in a truncate operation is a bug. + */ + if (unlikely(page_mapped(page))) { BUG_ON(truncate_op); + + i_mmap_lock_write(mapping); + hugetlb_vmdelete_list(&mapping->i_mmap, + next * pages_per_huge_page(h), + (next + 1) * pages_per_huge_page(h)); + i_mmap_unlock_write(mapping); + } + + lock_page(page); + /* + * We must free the huge page and remove from page + * cache (remove_huge_page) BEFORE removing the + * region/reserve map (hugetlb_unreserve_pages). In + * rare out of memory conditions, removal of the + * region/reserve map could fail. Before free'ing + * the page, note PagePrivate which is used in case + * of error. + */ + rsv_on_error = !PagePrivate(page); + remove_huge_page(page); + freed++; + if (!truncate_op) { + if (unlikely(hugetlb_unreserve_pages(inode, + next, next + 1, 1))) + hugetlb_fix_reserve_counts(inode, + rsv_on_error); } unlock_page(page); @@ -452,41 +496,6 @@ static void hugetlbfs_evict_inode(struct inode *inode) clear_inode(inode); } -static inline void -hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) -{ - struct vm_area_struct *vma; - - /* - * end == 0 indicates that the entire range after - * start should be unmapped. - */ - vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) { - unsigned long v_offset; - - /* - * Can the expression below overflow on 32-bit arches? - * No, because the interval tree returns us only those vmas - * which overlap the truncated area starting at pgoff, - * and no vma on a 32-bit arch can span beyond the 4GB. - */ - if (vma->vm_pgoff < start) - v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT; - else - v_offset = 0; - - if (end) { - end = ((end - start) << PAGE_SHIFT) + - vma->vm_start + v_offset; - if (end > vma->vm_end) - end = vma->vm_end; - } else - end = vma->vm_end; - - unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL); - } -} - static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; @@ -708,7 +717,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, /* * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never * be taken from reclaim -- unlike regular filesystems. This needs an - * annotation because huge_pmd_share() does an allocation under + * annotation because huge_pmd_share() does an allocation under hugetlb's * i_mmap_rwsem. */ static struct lock_class_key hugetlbfs_i_mmap_rwsem_key; diff --git a/fs/proc/page.c b/fs/proc/page.c index 93484034a03d..b2855eea5405 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -103,9 +103,9 @@ u64 stable_page_flags(struct page *page) * pseudo flags for the well known (anonymous) memory mapped pages * * Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the - * simple test in page_mapped() is not enough. + * simple test in page_mapcount() is not enough. */ - if (!PageSlab(page) && page_mapped(page)) + if (!PageSlab(page) && page_mapcount(page)) u |= 1 << KPF_MMAP; if (PageAnon(page)) u |= 1 << KPF_ANON; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index a353b4c6e86e..65a1b6c69c11 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -466,9 +466,10 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - unsigned long size, bool young, bool dirty) + bool compound, bool young, bool dirty) { - int mapcount; + int i, nr = compound ? HPAGE_PMD_NR : 1; + unsigned long size = nr * PAGE_SIZE; if (PageAnon(page)) mss->anonymous += size; @@ -477,23 +478,37 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, /* Accumulate the size in pages that have been accessed. */ if (young || page_is_young(page) || PageReferenced(page)) mss->referenced += size; - mapcount = page_mapcount(page); - if (mapcount >= 2) { - u64 pss_delta; - if (dirty || PageDirty(page)) - mss->shared_dirty += size; - else - mss->shared_clean += size; - pss_delta = (u64)size << PSS_SHIFT; - do_div(pss_delta, mapcount); - mss->pss += pss_delta; - } else { + /* + * page_count(page) == 1 guarantees the page is mapped exactly once. + * If any subpage of the compound page mapped with PTE it would elevate + * page_count(). + */ + if (page_count(page) == 1) { if (dirty || PageDirty(page)) mss->private_dirty += size; else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + return; + } + + for (i = 0; i < nr; i++, page++) { + int mapcount = page_mapcount(page); + + if (mapcount >= 2) { + if (dirty || PageDirty(page)) + mss->shared_dirty += PAGE_SIZE; + else + mss->shared_clean += PAGE_SIZE; + mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + } else { + if (dirty || PageDirty(page)) + mss->private_dirty += PAGE_SIZE; + else + mss->private_clean += PAGE_SIZE; + mss->pss += PAGE_SIZE << PSS_SHIFT; + } } } @@ -554,7 +569,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte)); + + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -570,8 +586,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, if (IS_ERR_OR_NULL(page)) return; mss->anonymous_thp += HPAGE_PMD_SIZE; - smaps_account(mss, page, HPAGE_PMD_SIZE, - pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -587,7 +602,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { smaps_pmd_entry(pmd, addr, walk); spin_unlock(ptl); return 0; @@ -898,7 +913,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; struct page *page; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { if (cp->type == CLEAR_REFS_SOFT_DIRTY) { clear_soft_dirty_pmd(vma, addr, pmd); goto out; @@ -1172,7 +1187,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, int err = 0; #ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmdp, vma, &ptl)) { u64 flags = 0, frame = 0; pmd_t pmd = *pmdp; @@ -1504,7 +1519,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { pte_t huge_pte = *(pte_t *)pmd; struct page *page; diff --git a/fs/stat.c b/fs/stat.c index d4a61d8dc021..bc045c7994e1 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -219,7 +219,7 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev,new_valid_dev)(x) +#define valid_dev(x) choose_32_64(old_valid_dev(x),true) #define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) #ifndef INIT_STRUCT_STAT_PADDING diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 3a6803cb0ec9..0b3c0d39ef75 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1,6 +1,8 @@ #ifndef _ASM_GENERIC_PGTABLE_H #define _ASM_GENERIC_PGTABLE_H +#include <linux/pfn.h> + #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU @@ -207,11 +209,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif -#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp); -#endif - #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, @@ -554,7 +551,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, * by vm_insert_pfn(). */ static inline int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { return 0; } @@ -589,7 +586,7 @@ extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn); + pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); @@ -627,10 +624,6 @@ static inline int pmd_trans_huge(pmd_t pmd) { return 0; } -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return 0; -} #ifndef __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index b58fd667f87b..af0254c09424 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -4,6 +4,7 @@ /* References to section boundaries */ #include <linux/compiler.h> +#include <linux/types.h> /* * Usage guidelines: @@ -63,4 +64,68 @@ static inline int arch_is_kernel_data(unsigned long addr) } #endif +/** + * memory_contains - checks if an object is contained within a memory region + * @begin: virtual address of the beginning of the memory region + * @end: virtual address of the end of the memory region + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if the object specified by @virt and @size is entirely + * contained within the memory region defined by @begin and @end, false + * otherwise. + */ +static inline bool memory_contains(void *begin, void *end, void *virt, + size_t size) +{ + return virt >= begin && virt + size <= end; +} + +/** + * memory_intersects - checks if the region occupied by an object intersects + * with another memory region + * @begin: virtual address of the beginning of the memory regien + * @end: virtual address of the end of the memory region + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if an object's memory region, specified by @virt and @size, + * intersects with the region specified by @begin and @end, false otherwise. + */ +static inline bool memory_intersects(void *begin, void *end, void *virt, + size_t size) +{ + void *vend = virt + size; + + return (virt >= begin && virt < end) || (vend >= begin && vend < end); +} + +/** + * init_section_contains - checks if an object is contained within the init + * section + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if the object specified by @virt and @size is entirely + * contained within the init section, false otherwise. + */ +static inline bool init_section_contains(void *virt, size_t size) +{ + return memory_contains(__init_begin, __init_end, virt, size); +} + +/** + * init_section_intersects - checks if the region occupied by an object + * intersects with the init section + * @virt: virtual address of the memory object + * @size: size of the memory object + * + * Returns: true if an object's memory region, specified by @virt and @size, + * intersects with the init section, false otherwise. + */ +static inline bool init_section_intersects(void *virt, size_t size) +{ + return memory_intersects(__init_begin, __init_end, virt, size); +} + #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c70e3588a48c..bfb64d672e19 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -15,6 +15,7 @@ #include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> +#include <linux/pfn.h> #include <linux/bio.h> #include <linux/stringify.h> #include <linux/gfp.h> @@ -1617,6 +1618,20 @@ static inline bool integrity_req_gap_front_merge(struct request *req, #endif /* CONFIG_BLK_DEV_INTEGRITY */ +/** + * struct blk_dax_ctl - control and output parameters for ->direct_access + * @sector: (input) offset relative to a block_device + * @addr: (output) kernel virtual address for @sector populated by driver + * @pfn: (output) page frame number for @addr populated by driver + * @size: (input) number of bytes requested + */ +struct blk_dax_ctl { + sector_t sector; + void __pmem *addr; + long size; + pfn_t pfn; +}; + struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); @@ -1624,7 +1639,7 @@ struct block_device_operations { int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void __pmem **, - unsigned long *pfn); + pfn_t *); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ @@ -1643,8 +1658,7 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -extern long bdev_direct_access(struct block_device *, sector_t, - void __pmem **addr, unsigned long *pfn, long size); +extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *); #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/console.h b/include/linux/console.h index bd194343c346..ea731af2451e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -150,6 +150,7 @@ extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); +extern void console_flush_on_panic(void); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); diff --git a/include/linux/err.h b/include/linux/err.h index a729120644d5..56762ab41713 100644 --- a/include/linux/err.h +++ b/include/linux/err.h @@ -37,7 +37,7 @@ static inline bool __must_check IS_ERR(__force const void *ptr) static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { - return !ptr || IS_ERR_VALUE((unsigned long)ptr); + return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ecb080d6ff42..cfe81e10bd54 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -19,13 +19,16 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); +extern int madvise_free_huge_pmd(struct mmu_gather *tlb, + struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next); extern int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); -extern int move_huge_pmd(struct vm_area_struct *vma, +extern bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, @@ -34,8 +37,7 @@ extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, - unsigned long pfn, bool write); - + pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, @@ -48,21 +50,13 @@ enum transparent_hugepage_flag { #endif }; -enum page_check_address_pmd_flag { - PAGE_CHECK_ADDRESS_PMD_FLAG, - PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, - PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, -}; -extern pmd_t *page_check_address_pmd(struct page *page, - struct mm_struct *mm, - unsigned long address, - enum page_check_address_pmd_flag flag, - spinlock_t **ptl); - #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags); + #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) @@ -95,30 +89,28 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #endif /* CONFIG_DEBUG_VM */ extern unsigned long transparent_hugepage_flags; -extern int split_huge_page_to_list(struct page *page, struct list_head *list); + +extern void prep_transhuge_page(struct page *page); +extern void free_transhuge_page(struct page *page); + +int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } -extern void __split_huge_page_pmd(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd); -#define split_huge_page_pmd(__vma, __address, __pmd) \ +void deferred_split_huge_page(struct page *page); + +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address); + +#define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ - if (unlikely(pmd_trans_huge(*____pmd))) \ - __split_huge_page_pmd(__vma, __address, \ - ____pmd); \ + if (pmd_trans_huge(*____pmd) \ + || pmd_devmap(*____pmd)) \ + __split_huge_pmd(__vma, __pmd, __address); \ } while (0) -#define wait_split_huge_page(__anon_vma, __pmd) \ - do { \ - pmd_t *____pmd = (__pmd); \ - anon_vma_lock_write(__anon_vma); \ - anon_vma_unlock_write(__anon_vma); \ - BUG_ON(pmd_trans_splitting(*____pmd) || \ - pmd_trans_huge(*____pmd)); \ - } while (0) -extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, - pmd_t *pmd); + #if HPAGE_PMD_ORDER >= MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif @@ -128,17 +120,17 @@ extern void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); -extern int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +extern bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl); /* mmap_sem must be held on entry */ -static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); - if (pmd_trans_huge(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma, ptl); else - return 0; + return false; } static inline int hpage_nr_pages(struct page *page) { @@ -183,11 +175,8 @@ static inline int split_huge_page(struct page *page) { return 0; } -#define split_huge_page_pmd(__vma, __address, __pmd) \ - do { } while (0) -#define wait_split_huge_page(__anon_vma, __pmd) \ - do { } while (0) -#define split_huge_page_pmd_mm(__mm, __address, __pmd) \ +static inline void deferred_split_huge_page(struct page *page) {} +#define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) @@ -201,10 +190,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, long adjust_next) { } -static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { - return 0; + return false; } static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, @@ -218,6 +207,12 @@ static inline bool is_huge_zero_page(struct page *page) return false; } + +static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, int flags) +{ + return NULL; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e76574d8f9b5..7d953c2542a8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -8,6 +8,7 @@ #include <linux/cgroup.h> #include <linux/list.h> #include <linux/kref.h> +#include <asm/pgtable.h> struct ctl_table; struct user_struct; diff --git a/include/linux/io.h b/include/linux/io.h index de64c1e53612..fffd88d7f426 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -89,21 +89,6 @@ void devm_memunmap(struct device *dev, void *addr); void *__devm_memremap_pages(struct device *dev, struct resource *res); -#ifdef CONFIG_ZONE_DEVICE -void *devm_memremap_pages(struct device *dev, struct resource *res); -#else -static inline void *devm_memremap_pages(struct device *dev, struct resource *res) -{ - /* - * Fail attempts to call devm_memremap_pages() without - * ZONE_DEVICE support enabled, this requires callers to fall - * back to plain devm_memremap() based on config - */ - WARN_ON_ONCE(1); - return ERR_PTR(-ENXIO); -} -#endif - /* * Some systems do not have legacy ISA devices. * /dev/port is not a valid interface on these systems. diff --git a/include/linux/kdev_t.h b/include/linux/kdev_t.h index 052c7b32cc91..8e9e288b08c1 100644 --- a/include/linux/kdev_t.h +++ b/include/linux/kdev_t.h @@ -35,11 +35,6 @@ static inline dev_t old_decode_dev(u16 val) return MKDEV((val >> 8) & 255, val & 255); } -static inline bool new_valid_dev(dev_t dev) -{ - return 1; -} - static inline u32 new_encode_dev(dev_t dev) { unsigned major = MAJOR(dev); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7311c3294e25..f31638c6e873 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -202,26 +202,26 @@ extern int _cond_resched(void); /** * abs - return absolute value of an argument - * @x: the value. If it is unsigned type, it is converted to signed type first - * (s64, long or int depending on its size). + * @x: the value. If it is unsigned type, it is converted to signed type first. + * char is treated as if it was signed (regardless of whether it really is) + * but the macro's return type is preserved as char. * - * Return: an absolute value of x. If x is 64-bit, macro's return type is s64, - * otherwise it is signed long. + * Return: an absolute value of x. */ -#define abs(x) __builtin_choose_expr(sizeof(x) == sizeof(s64), ({ \ - s64 __x = (x); \ - (__x < 0) ? -__x : __x; \ - }), ({ \ - long ret; \ - if (sizeof(x) == sizeof(long)) { \ - long __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } else { \ - int __x = (x); \ - ret = (__x < 0) ? -__x : __x; \ - } \ - ret; \ - })) +#define abs(x) __abs_choose_expr(x, long long, \ + __abs_choose_expr(x, long, \ + __abs_choose_expr(x, int, \ + __abs_choose_expr(x, short, \ + __abs_choose_expr(x, char, \ + __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(x), char), \ + (char)({ signed char __x = (x); __x<0?-__x:__x; }), \ + ((void)0))))))) + +#define __abs_choose_expr(x, type, other) __builtin_choose_expr( \ + __builtin_types_compatible_p(typeof(x), signed type) || \ + __builtin_types_compatible_p(typeof(x), unsigned type), \ + ({ signed type __x = (x); __x < 0 ? -__x : __x; }), other) /** * reciprocal_scale - "scale" a value into range [0, ep_ro) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f707f74055c3..861f690aa791 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -66,7 +66,7 @@ * error pfns indicate that the gfn is in slot but faild to * translate it to pfn on host. */ -static inline bool is_error_pfn(pfn_t pfn) +static inline bool is_error_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_MASK); } @@ -76,13 +76,13 @@ static inline bool is_error_pfn(pfn_t pfn) * translated to pfn - it is not in slot or failed to * translate it to pfn. */ -static inline bool is_error_noslot_pfn(pfn_t pfn) +static inline bool is_error_noslot_pfn(kvm_pfn_t pfn) { return !!(pfn & KVM_PFN_ERR_NOSLOT_MASK); } /* noslot pfn indicates that the gfn is not in slot. */ -static inline bool is_noslot_pfn(pfn_t pfn) +static inline bool is_noslot_pfn(kvm_pfn_t pfn) { return pfn == KVM_PFN_NOSLOT; } @@ -591,19 +591,20 @@ void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); void kvm_set_page_accessed(struct page *page); -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, +kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable); +kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, + bool atomic, bool *async, bool write_fault, + bool *writable); -void kvm_release_pfn_clean(pfn_t pfn); -void kvm_set_pfn_dirty(pfn_t pfn); -void kvm_set_pfn_accessed(pfn_t pfn); -void kvm_get_pfn(pfn_t pfn); +void kvm_release_pfn_clean(kvm_pfn_t pfn); +void kvm_set_pfn_dirty(kvm_pfn_t pfn); +void kvm_set_pfn_accessed(kvm_pfn_t pfn); +void kvm_get_pfn(kvm_pfn_t pfn); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); @@ -629,8 +630,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn); -pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); -pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); +kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); +kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); @@ -811,7 +812,7 @@ void kvm_arch_sync_events(struct kvm *kvm); int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); -bool kvm_is_reserved_pfn(pfn_t pfn); +bool kvm_is_reserved_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -965,7 +966,7 @@ static inline gfn_t gpa_to_gfn(gpa_t gpa) return (gfn_t)(gpa >> PAGE_SHIFT); } -static inline hpa_t pfn_to_hpa(pfn_t pfn) +static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) { return (hpa_t)pfn << PAGE_SHIFT; } diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 1b47a185c2f0..8bf259dae9f6 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,7 +53,7 @@ typedef unsigned long hva_t; typedef u64 hpa_t; typedef u64 hfn_t; -typedef hfn_t pfn_t; +typedef hfn_t kvm_pfn_t; struct gfn_to_hva_cache { u64 generation; diff --git a/include/linux/list.h b/include/linux/list.h index 5356f4d661a7..30cf4200ab40 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -113,6 +113,17 @@ extern void __list_del_entry(struct list_head *entry); extern void list_del(struct list_head *entry); #endif +#ifdef CONFIG_DEBUG_LIST +/* + * See devm_memremap_pages() which wants DEBUG_LIST=y to assert if one + * of the pages it allocates is ever passed to list_add() + */ +extern void list_force_poison(struct list_head *entry); +#else +/* fallback to the less strict LIST_POISON* definitions */ +#define list_force_poison list_del +#endif + /** * list_replace - replace old entry by new one * @old : the element to be replaced diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 173fb44e22f1..3106ac1c895e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,14 @@ extern int memblock_debug; extern bool movable_node_enabled; #endif /* CONFIG_MOVABLE_NODE */ +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +#define __init_memblock __meminit +#define __initdata_memblock __meminitdata +#else +#define __init_memblock +#define __initdata_memblock +#endif + #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) @@ -166,7 +174,7 @@ static inline bool memblock_is_hotpluggable(struct memblock_region *m) return m->flags & MEMBLOCK_HOTPLUG; } -static inline bool movable_node_is_enabled(void) +static inline bool __init_memblock movable_node_is_enabled(void) { return movable_node_enabled; } @@ -405,14 +413,6 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo for (idx = 0; idx < memblock_type->cnt; \ idx++,rgn = &memblock_type->regions[idx]) -#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK -#define __init_memblock __meminit -#define __initdata_memblock __meminitdata -#else -#define __init_memblock -#define __initdata_memblock -#endif - #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); #else diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 2292468f2a30..189f04d4d2ec 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -280,10 +280,12 @@ static inline void mem_cgroup_events(struct mem_cgroup *memcg, bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp); + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare); -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg); + bool lrucare, bool compound); +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, + bool compound); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); @@ -515,7 +517,8 @@ static inline bool mem_cgroup_low(struct mem_cgroup *root, static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, - struct mem_cgroup **memcgp) + struct mem_cgroup **memcgp, + bool compound) { *memcgp = NULL; return 0; @@ -523,12 +526,13 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) + bool lrucare, bool compound) { } static inline void mem_cgroup_cancel_charge(struct page *page, - struct mem_cgroup *memcg) + struct mem_cgroup *memcg, + bool compound) { } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2ea574ff9714..43405992d027 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -275,7 +275,8 @@ extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn); -extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); +extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset); extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); diff --git a/include/linux/memremap.h b/include/linux/memremap.h new file mode 100644 index 000000000000..bcaa634139a9 --- /dev/null +++ b/include/linux/memremap.h @@ -0,0 +1,114 @@ +#ifndef _LINUX_MEMREMAP_H_ +#define _LINUX_MEMREMAP_H_ +#include <linux/mm.h> +#include <linux/ioport.h> +#include <linux/percpu-refcount.h> + +struct resource; +struct device; + +/** + * struct vmem_altmap - pre-allocated storage for vmemmap_populate + * @base_pfn: base of the entire dev_pagemap mapping + * @reserve: pages mapped, but reserved for driver use (relative to @base) + * @free: free pages set aside in the mapping for memmap storage + * @align: pages reserved to meet allocation alignments + * @alloc: track pages consumed, private to vmemmap_populate() + */ +struct vmem_altmap { + const unsigned long base_pfn; + const unsigned long reserve; + unsigned long free; + unsigned long align; + unsigned long alloc; +}; + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE) +struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start); +#else +static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +{ + return NULL; +} +#endif + +/** + * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @altmap: pre-allocated/reserved memory for vmemmap allocations + * @res: physical address range covered by @ref + * @ref: reference count that pins the devm_memremap_pages() mapping + * @dev: host device of the mapping for debug + */ +struct dev_pagemap { + struct vmem_altmap *altmap; + const struct resource *res; + struct percpu_ref *ref; + struct device *dev; +}; + +#ifdef CONFIG_ZONE_DEVICE +void *devm_memremap_pages(struct device *dev, struct resource *res, + struct percpu_ref *ref, struct vmem_altmap *altmap); +struct dev_pagemap *find_dev_pagemap(resource_size_t phys); +#else +static inline void *devm_memremap_pages(struct device *dev, + struct resource *res, struct percpu_ref *ref, + struct vmem_altmap *altmap) +{ + /* + * Fail attempts to call devm_memremap_pages() without + * ZONE_DEVICE support enabled, this requires callers to fall + * back to plain devm_memremap() based on config + */ + WARN_ON_ONCE(1); + return ERR_PTR(-ENXIO); +} + +static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +{ + return NULL; +} +#endif + +/** + * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn + * @pfn: page frame number to lookup page_map + * @pgmap: optional known pgmap that already has a reference + * + * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the + * same mapping. + */ +static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn, + struct dev_pagemap *pgmap) +{ + const struct resource *res = pgmap ? pgmap->res : NULL; + resource_size_t phys = PFN_PHYS(pfn); + + /* + * In the cached case we're already holding a live reference so + * we can simply do a blind increment + */ + if (res && phys >= res->start && phys <= res->end) { + percpu_ref_get(pgmap->ref); + return pgmap; + } + + /* fall back to slow path lookup */ + rcu_read_lock(); + pgmap = find_dev_pagemap(phys); + if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + pgmap = NULL; + rcu_read_unlock(); + + return pgmap; +} + +static inline void put_dev_pagemap(struct dev_pagemap *pgmap) +{ + if (pgmap) + percpu_ref_put(pgmap->ref); +} +#endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 839d9e9a1c38..f1cd22f2df1a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -16,6 +16,7 @@ #include <linux/mm_types.h> #include <linux/range.h> #include <linux/pfn.h> +#include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> @@ -329,6 +330,13 @@ struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) +#if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) +static inline int pmd_devmap(pmd_t pmd) +{ + return 0; +} +#endif + /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) @@ -410,39 +418,17 @@ static inline int is_vmalloc_or_module_addr(const void *x) extern void kvfree(const void *addr); -static inline void compound_lock(struct page *page) +static inline atomic_t *compound_mapcount_ptr(struct page *page) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(PageSlab(page), page); - bit_spin_lock(PG_compound_lock, &page->flags); -#endif + return &page[1].compound_mapcount; } -static inline void compound_unlock(struct page *page) +static inline int compound_mapcount(struct page *page) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - VM_BUG_ON_PAGE(PageSlab(page), page); - bit_spin_unlock(PG_compound_lock, &page->flags); -#endif -} - -static inline unsigned long compound_lock_irqsave(struct page *page) -{ - unsigned long uninitialized_var(flags); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - local_irq_save(flags); - compound_lock(page); -#endif - return flags; -} - -static inline void compound_unlock_irqrestore(struct page *page, - unsigned long flags) -{ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - compound_unlock(page); - local_irq_restore(flags); -#endif + if (!PageCompound(page)) + return 0; + page = compound_head(page); + return atomic_read(compound_mapcount_ptr(page)) + 1; } /* @@ -455,61 +441,29 @@ static inline void page_mapcount_reset(struct page *page) atomic_set(&(page)->_mapcount, -1); } +int __page_mapcount(struct page *page); + static inline int page_mapcount(struct page *page) { VM_BUG_ON_PAGE(PageSlab(page), page); - return atomic_read(&page->_mapcount) + 1; -} -static inline int page_count(struct page *page) -{ - return atomic_read(&compound_head(page)->_count); -} - -static inline bool __compound_tail_refcounted(struct page *page) -{ - return PageAnon(page) && !PageSlab(page) && !PageHeadHuge(page); -} - -/* - * This takes a head page as parameter and tells if the - * tail page reference counting can be skipped. - * - * For this to be safe, PageSlab and PageHeadHuge must remain true on - * any given page where they return true here, until all tail pins - * have been released. - */ -static inline bool compound_tail_refcounted(struct page *page) -{ - VM_BUG_ON_PAGE(!PageHead(page), page); - return __compound_tail_refcounted(page); + if (unlikely(PageCompound(page))) + return __page_mapcount(page); + return atomic_read(&page->_mapcount) + 1; } -static inline void get_huge_page_tail(struct page *page) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int total_mapcount(struct page *page); +#else +static inline int total_mapcount(struct page *page) { - /* - * __split_huge_page_refcount() cannot run from under us. - */ - VM_BUG_ON_PAGE(!PageTail(page), page); - VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); - VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); - if (compound_tail_refcounted(compound_head(page))) - atomic_inc(&page->_mapcount); + return page_mapcount(page); } +#endif -extern bool __get_page_tail(struct page *page); - -static inline void get_page(struct page *page) +static inline int page_count(struct page *page) { - if (unlikely(PageTail(page))) - if (likely(__get_page_tail(page))) - return; - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_count. - */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); - atomic_inc(&page->_count); + return atomic_read(&compound_head(page)->_count); } static inline struct page *virt_to_head_page(const void *x) @@ -528,7 +482,8 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } -void put_page(struct page *page); +void __put_page(struct page *page); + void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); @@ -548,6 +503,9 @@ enum compound_dtor_id { #ifdef CONFIG_HUGETLB_PAGE HUGETLB_PAGE_DTOR, #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + TRANSHUGE_PAGE_DTOR, +#endif NR_COMPOUND_DTORS, }; extern compound_page_dtor * const compound_page_dtors[]; @@ -577,6 +535,8 @@ static inline void set_compound_order(struct page *page, unsigned int order) page[1].compound_order = order; } +void free_compound_page(struct page *page); + #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when @@ -704,6 +664,51 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +#ifdef CONFIG_ZONE_DEVICE +void get_zone_device_page(struct page *page); +void put_zone_device_page(struct page *page); +static inline bool is_zone_device_page(const struct page *page) +{ + return page_zonenum(page) == ZONE_DEVICE; +} +#else +static inline void get_zone_device_page(struct page *page) +{ +} +static inline void put_zone_device_page(struct page *page) +{ +} +static inline bool is_zone_device_page(const struct page *page) +{ + return false; +} +#endif + +static inline void get_page(struct page *page) +{ + page = compound_head(page); + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. + */ + VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); + atomic_inc(&page->_count); + + if (unlikely(is_zone_device_page(page))) + get_zone_device_page(page); +} + +static inline void put_page(struct page *page) +{ + page = compound_head(page); + + if (put_page_testzero(page)) + __put_page(page); + + if (unlikely(is_zone_device_page(page))) + put_zone_device_page(page); +} + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -993,10 +998,21 @@ static inline pgoff_t page_file_index(struct page *page) /* * Return true if this page is mapped into pagetables. + * For compound page it returns true if any subpage of compound page is mapped. */ -static inline int page_mapped(struct page *page) -{ - return atomic_read(&(page)->_mapcount) >= 0; +static inline bool page_mapped(struct page *page) +{ + int i; + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) >= 0; + page = compound_head(page); + if (atomic_read(compound_mapcount_ptr(page)) >= 0) + return true; + for (i = 0; i < hpage_nr_pages(page); i++) { + if (atomic_read(&page[i]._mapcount) >= 0) + return true; + } + return false; } /* @@ -1084,7 +1100,7 @@ static inline bool shmem_mapping(struct address_space *mapping) } #endif -extern int can_do_mlock(void); +extern bool can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); @@ -1178,7 +1194,8 @@ int invalidate_inode_page(struct page *page); extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags); + unsigned long address, unsigned int fault_flags, + bool *unlocked); #else static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1190,7 +1207,7 @@ static inline int handle_mm_fault(struct mm_struct *mm, } static inline int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, - unsigned int fault_flags) + unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); @@ -1444,6 +1461,13 @@ static inline void sync_mm_rss(struct mm_struct *mm) } #endif +#ifndef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t pte) +{ + return 0; +} +#endif + int vma_wants_writenotify(struct vm_area_struct *vma); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, @@ -2114,7 +2138,7 @@ int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn); + pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -2224,7 +2248,14 @@ pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); -void *vmemmap_alloc_block_buf(unsigned long size, int node); +struct vmem_altmap; +void *__vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap); +static inline void *vmemmap_alloc_block_buf(unsigned long size, int node) +{ + return __vmemmap_alloc_block_buf(size, node, NULL); +} + void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node); @@ -2246,7 +2277,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); -extern void put_hwpoison_page(struct page *page); +#define put_hwpoison_page(page) put_page(page) extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6bc9a0ce2253..d3ebb9d21a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -54,6 +54,8 @@ struct page { * see PAGE_MAPPING_ANON below. */ void *s_mem; /* slab first object */ + atomic_t compound_mapcount; /* first tail page */ + /* page_deferred_list().next -- second tail page */ }; /* Second double word */ @@ -61,6 +63,7 @@ struct page { union { pgoff_t index; /* Our offset within mapping. */ void *freelist; /* sl[aou]b first free object */ + /* page_deferred_list().prev -- second tail page */ }; union { @@ -81,20 +84,9 @@ struct page { union { /* - * Count of ptes mapped in - * mms, to show when page is - * mapped & limit reverse map - * searches. - * - * Used also for tail pages - * refcounting instead of - * _count. Tail pages cannot - * be mapped and keeping the - * tail page _count zero at - * all times guarantees - * get_page_unless_zero() will - * never succeed on tail - * pages. + * Count of ptes mapped in mms, to show + * when page is mapped & limit reverse + * map searches. */ atomic_t _mapcount; @@ -124,6 +116,11 @@ struct page { * Can be used as a generic list * by the page owner. */ + struct dev_pagemap *pgmap; /* ZONE_DEVICE pages are never on an + * lru or handled by a slab + * allocator, this points to the + * hosting device page map. + */ struct { /* slub per cpu partial pages */ struct page *next; /* Next partial slab */ #ifdef CONFIG_64BIT diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 772362adf471..053824b0a412 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -56,4 +56,10 @@ void dump_mm(const struct mm_struct *mm); #define VIRTUAL_BUG_ON(cond) do { } while (0) #endif +#ifdef CONFIG_DEBUG_VM_PGFLAGS +#define VM_BUG_ON_PGFLAGS(cond, page) VM_BUG_ON_PAGE(cond, page) +#else +#define VM_BUG_ON_PGFLAGS(cond, page) BUILD_BUG_ON_INVALID(cond) +#endif + #endif diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index bb53c7b86315..19724e6ebd26 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -101,9 +101,6 @@ enum pageflags { #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - PG_compound_lock, -#endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) PG_young, PG_idle, @@ -129,53 +126,104 @@ enum pageflags { /* SLOB */ PG_slob_free = PG_private, + + /* Compound pages. Stored in first tail page's flags */ + PG_double_map = PG_private_2, }; #ifndef __GENERATING_BOUNDS_H +struct page; /* forward declaration */ + +static inline struct page *compound_head(struct page *page) +{ + unsigned long head = READ_ONCE(page->compound_head); + + if (unlikely(head & 1)) + return (struct page *) (head - 1); + return page; +} + +static inline int PageTail(struct page *page) +{ + return READ_ONCE(page->compound_head) & 1; +} + +static inline int PageCompound(struct page *page) +{ + return test_bit(PG_head, &page->flags) || PageTail(page); +} + +/* + * Page flags policies wrt compound pages + * + * PF_ANY: + * the page flag is relevant for small, head and tail pages. + * + * PF_HEAD: + * for compound page all operations related to the page flag applied to + * head page. + * + * PF_NO_TAIL: + * modifications of the page flag must be done on small or head pages, + * checks can be done on tail pages too. + * + * PF_NO_COMPOUND: + * the page flag is not relevant for compound pages. + */ +#define PF_ANY(page, enforce) page +#define PF_HEAD(page, enforce) compound_head(page) +#define PF_NO_TAIL(page, enforce) ({ \ + VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ + compound_head(page);}) +#define PF_NO_COMPOUND(page, enforce) ({ \ + VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ + page;}) + /* * Macros to create function definitions for page flags */ -#define TESTPAGEFLAG(uname, lname) \ -static inline int Page##uname(const struct page *page) \ - { return test_bit(PG_##lname, &page->flags); } +#define TESTPAGEFLAG(uname, lname, policy) \ +static inline int Page##uname(struct page *page) \ + { return test_bit(PG_##lname, &policy(page, 0)->flags); } -#define SETPAGEFLAG(uname, lname) \ +#define SETPAGEFLAG(uname, lname, policy) \ static inline void SetPage##uname(struct page *page) \ - { set_bit(PG_##lname, &page->flags); } + { set_bit(PG_##lname, &policy(page, 1)->flags); } -#define CLEARPAGEFLAG(uname, lname) \ +#define CLEARPAGEFLAG(uname, lname, policy) \ static inline void ClearPage##uname(struct page *page) \ - { clear_bit(PG_##lname, &page->flags); } + { clear_bit(PG_##lname, &policy(page, 1)->flags); } -#define __SETPAGEFLAG(uname, lname) \ +#define __SETPAGEFLAG(uname, lname, policy) \ static inline void __SetPage##uname(struct page *page) \ - { __set_bit(PG_##lname, &page->flags); } + { __set_bit(PG_##lname, &policy(page, 1)->flags); } -#define __CLEARPAGEFLAG(uname, lname) \ +#define __CLEARPAGEFLAG(uname, lname, policy) \ static inline void __ClearPage##uname(struct page *page) \ - { __clear_bit(PG_##lname, &page->flags); } + { __clear_bit(PG_##lname, &policy(page, 1)->flags); } -#define TESTSETFLAG(uname, lname) \ +#define TESTSETFLAG(uname, lname, policy) \ static inline int TestSetPage##uname(struct page *page) \ - { return test_and_set_bit(PG_##lname, &page->flags); } + { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } -#define TESTCLEARFLAG(uname, lname) \ +#define TESTCLEARFLAG(uname, lname, policy) \ static inline int TestClearPage##uname(struct page *page) \ - { return test_and_clear_bit(PG_##lname, &page->flags); } - -#define __TESTCLEARFLAG(uname, lname) \ -static inline int __TestClearPage##uname(struct page *page) \ - { return __test_and_clear_bit(PG_##lname, &page->flags); } + { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } -#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ - SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname) +#define PAGEFLAG(uname, lname, policy) \ + TESTPAGEFLAG(uname, lname, policy) \ + SETPAGEFLAG(uname, lname, policy) \ + CLEARPAGEFLAG(uname, lname, policy) -#define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ - __SETPAGEFLAG(uname, lname) __CLEARPAGEFLAG(uname, lname) +#define __PAGEFLAG(uname, lname, policy) \ + TESTPAGEFLAG(uname, lname, policy) \ + __SETPAGEFLAG(uname, lname, policy) \ + __CLEARPAGEFLAG(uname, lname, policy) -#define TESTSCFLAG(uname, lname) \ - TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname) +#define TESTSCFLAG(uname, lname, policy) \ + TESTSETFLAG(uname, lname, policy) \ + TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname) \ static inline int Page##uname(const struct page *page) { return 0; } @@ -195,56 +243,62 @@ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } -#define __TESTCLEARFLAG_FALSE(uname) \ -static inline int __TestClearPage##uname(struct page *page) { return 0; } - #define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) #define TESTSCFLAG_FALSE(uname) \ TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) -struct page; /* forward declaration */ - -TESTPAGEFLAG(Locked, locked) -PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error) -PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) - __SETPAGEFLAG(Referenced, referenced) -PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) -PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) -PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) - TESTCLEARFLAG(Active, active) -__PAGEFLAG(Slab, slab) -PAGEFLAG(Checked, checked) /* Used by some filesystems */ -PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ -PAGEFLAG(SavePinned, savepinned); /* Xen */ -PAGEFLAG(Foreign, foreign); /* Xen */ -PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) -PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) - __SETPAGEFLAG(SwapBacked, swapbacked) - -__PAGEFLAG(SlobFree, slob_free) +__PAGEFLAG(Locked, locked, PF_NO_TAIL) +PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND) +PAGEFLAG(Referenced, referenced, PF_HEAD) + TESTCLEARFLAG(Referenced, referenced, PF_HEAD) + __SETPAGEFLAG(Referenced, referenced, PF_HEAD) +PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) + __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) +PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) +PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) + TESTCLEARFLAG(Active, active, PF_HEAD) +__PAGEFLAG(Slab, slab, PF_NO_TAIL) +__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) +PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ + +/* Xen */ +PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) + TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) +PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); +PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); + +PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) +PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) + __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) + __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause releasepage() and co to be invoked */ -PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) - __CLEARPAGEFLAG(Private, private) -PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2) -PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) +PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY) + __CLEARPAGEFLAG(Private, private, PF_ANY) +PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) +PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) + TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ -TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) -PAGEFLAG(MappedToDisk, mappedtodisk) +TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) + TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) +PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_COMPOUND) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ -PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) -PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim) +PAGEFLAG(Reclaim, reclaim, PF_NO_COMPOUND) + TESTCLEARFLAG(Reclaim, reclaim, PF_NO_COMPOUND) +PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) + TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* @@ -257,31 +311,33 @@ PAGEFLAG_FALSE(HighMem) #endif #ifdef CONFIG_SWAP -PAGEFLAG(SwapCache, swapcache) +PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(SwapCache) #endif -PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) - TESTCLEARFLAG(Unevictable, unevictable) +PAGEFLAG(Unevictable, unevictable, PF_HEAD) + __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) + TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) #ifdef CONFIG_MMU -PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked) - TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked) +PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) + __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) + TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) - TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked) + TESTSCFLAG_FALSE(Mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED -PAGEFLAG(Uncached, uncached) +PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(Uncached) #endif #ifdef CONFIG_MEMORY_FAILURE -PAGEFLAG(HWPoison, hwpoison) -TESTSCFLAG(HWPoison, hwpoison) +PAGEFLAG(HWPoison, hwpoison, PF_ANY) +TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) #else PAGEFLAG_FALSE(HWPoison) @@ -289,10 +345,10 @@ PAGEFLAG_FALSE(HWPoison) #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) -TESTPAGEFLAG(Young, young) -SETPAGEFLAG(Young, young) -TESTCLEARFLAG(Young, young) -PAGEFLAG(Idle, idle) +TESTPAGEFLAG(Young, young, PF_ANY) +SETPAGEFLAG(Young, young, PF_ANY) +TESTCLEARFLAG(Young, young, PF_ANY) +PAGEFLAG(Idle, idle, PF_ANY) #endif /* @@ -317,6 +373,7 @@ PAGEFLAG(Idle, idle) static inline int PageAnon(struct page *page) { + page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; } @@ -329,6 +386,7 @@ static inline int PageAnon(struct page *page) */ static inline int PageKsm(struct page *page) { + page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM); } @@ -340,8 +398,9 @@ u64 stable_page_flags(struct page *page); static inline int PageUptodate(struct page *page) { - int ret = test_bit(PG_uptodate, &(page)->flags); - + int ret; + page = compound_head(page); + ret = test_bit(PG_uptodate, &(page)->flags); /* * Must ensure that the data we read out of the page is loaded * _after_ we've loaded page->flags to check for PageUptodate. @@ -358,22 +417,24 @@ static inline int PageUptodate(struct page *page) static inline void __SetPageUptodate(struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); - __set_bit(PG_uptodate, &(page)->flags); + __set_bit(PG_uptodate, &page->flags); } static inline void SetPageUptodate(struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the page * uptodate are actually visible before PageUptodate becomes true. */ smp_wmb(); - set_bit(PG_uptodate, &(page)->flags); + set_bit(PG_uptodate, &page->flags); } -CLEARPAGEFLAG(Uptodate, uptodate) +CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) int test_clear_page_writeback(struct page *page); int __test_set_page_writeback(struct page *page, bool keep_write); @@ -393,12 +454,7 @@ static inline void set_page_writeback_keepwrite(struct page *page) test_set_page_writeback_keepwrite(page); } -__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head) - -static inline int PageTail(struct page *page) -{ - return READ_ONCE(page->compound_head) & 1; -} +__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) static inline void set_compound_head(struct page *page, struct page *head) { @@ -410,20 +466,6 @@ static inline void clear_compound_head(struct page *page) WRITE_ONCE(page->compound_head, 0); } -static inline struct page *compound_head(struct page *page) -{ - unsigned long head = READ_ONCE(page->compound_head); - - if (unlikely(head & 1)) - return (struct page *) (head - 1); - return page; -} - -static inline int PageCompound(struct page *page) -{ - return PageHead(page) || PageTail(page); - -} #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { @@ -484,22 +526,43 @@ static inline int PageTransTail(struct page *page) return PageTail(page); } -#else - -static inline int PageTransHuge(struct page *page) +/* + * PageDoubleMap indicates that the compound page is mapped with PTEs as well + * as PMDs. + * + * This is required for optimization of rmap operations for THP: we can postpone + * per small page mapcount accounting (and its overhead from atomic operations) + * until the first PMD split. + * + * For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up + * by one. This reference will go away with last compound_mapcount. + * + * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). + */ +static inline int PageDoubleMap(struct page *page) { - return 0; + return PageHead(page) && test_bit(PG_double_map, &page[1].flags); } -static inline int PageTransCompound(struct page *page) +static inline int TestSetPageDoubleMap(struct page *page) { - return 0; + VM_BUG_ON_PAGE(!PageHead(page), page); + return test_and_set_bit(PG_double_map, &page[1].flags); } -static inline int PageTransTail(struct page *page) +static inline int TestClearPageDoubleMap(struct page *page) { - return 0; + VM_BUG_ON_PAGE(!PageHead(page), page); + return test_and_clear_bit(PG_double_map, &page[1].flags); } + +#else +TESTPAGEFLAG_FALSE(TransHuge) +TESTPAGEFLAG_FALSE(TransCompound) +TESTPAGEFLAG_FALSE(TransTail) +TESTPAGEFLAG_FALSE(DoubleMap) + TESTSETFLAG_FALSE(DoubleMap) + TESTCLEARFLAG_FALSE(DoubleMap) #endif /* @@ -583,12 +646,6 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) #define __PG_MLOCKED 0 #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define __PG_COMPOUND_LOCK (1 << PG_compound_lock) -#else -#define __PG_COMPOUND_LOCK 0 -#endif - /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. @@ -598,8 +655,7 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | \ - __PG_COMPOUND_LOCK) + 1 << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. @@ -626,6 +682,10 @@ static inline int page_has_private(struct page *page) return !!(page->flags & PAGE_FLAGS_PRIVATE); } +#undef PF_ANY +#undef PF_HEAD +#undef PF_NO_TAIL +#undef PF_NO_COMPOUND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 26eabf5ec718..4d08b6c33557 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -394,10 +394,21 @@ static inline struct page *read_mapping_page(struct address_space *mapping, */ static inline pgoff_t page_to_pgoff(struct page *page) { + pgoff_t pgoff; + if (unlikely(PageHeadHuge(page))) return page->index << compound_order(page); - else + + if (likely(!PageTransTail(page))) return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + + /* + * We don't initialize ->index for tail pages: calculate based on + * head page + */ + pgoff = compound_head(page)->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + pgoff += page - compound_head(page); + return pgoff; } /* @@ -433,18 +444,9 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); -static inline void __set_page_locked(struct page *page) -{ - __set_bit(PG_locked, &page->flags); -} - -static inline void __clear_page_locked(struct page *page) -{ - __clear_bit(PG_locked, &page->flags); -} - static inline int trylock_page(struct page *page) { + page = compound_head(page); return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); } @@ -497,9 +499,9 @@ extern int wait_on_page_bit_killable_timeout(struct page *page, static inline int wait_on_page_locked_killable(struct page *page) { - if (PageLocked(page)) - return wait_on_page_bit_killable(page, PG_locked); - return 0; + if (!PageLocked(page)) + return 0; + return wait_on_page_bit_killable(compound_head(page), PG_locked); } extern wait_queue_head_t *page_waitqueue(struct page *page); @@ -518,7 +520,7 @@ static inline void wake_up_page(struct page *page, int bit) static inline void wait_on_page_locked(struct page *page) { if (PageLocked(page)) - wait_on_page_bit(page, PG_locked); + wait_on_page_bit(compound_head(page), PG_locked); } /* @@ -664,17 +666,17 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: - * the page is new, so we can just run __set_page_locked() against it. + * the page is new, so we can just run __SetPageLocked() against it. */ static inline int add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int error; - __set_page_locked(page); + __SetPageLocked(page); error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); if (unlikely(error)) - __clear_page_locked(page); + __ClearPageLocked(page); return error; } diff --git a/include/linux/pfn.h b/include/linux/pfn.h index 97f3e88aead4..2d8e49711b63 100644 --- a/include/linux/pfn.h +++ b/include/linux/pfn.h @@ -3,6 +3,15 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> + +/* + * pfn_t: encapsulates a page-frame number that is optionally backed + * by memmap (struct page). Whether a pfn_t has a 'struct page' + * backing is indicated by flags in the high bits of the value. + */ +typedef struct { + unsigned long val; +} pfn_t; #endif #define PFN_ALIGN(x) (((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK) diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h new file mode 100644 index 000000000000..0703b5360d31 --- /dev/null +++ b/include/linux/pfn_t.h @@ -0,0 +1,102 @@ +#ifndef _LINUX_PFN_T_H_ +#define _LINUX_PFN_T_H_ +#include <linux/mm.h> + +/* + * PFN_FLAGS_MASK - mask of all the possible valid pfn_t flags + * PFN_SG_CHAIN - pfn is a pointer to the next scatterlist entry + * PFN_SG_LAST - pfn references a page and is the last scatterlist entry + * PFN_DEV - pfn is not covered by system memmap by default + * PFN_MAP - pfn has a dynamic page mapping established by a device driver + */ +#define PFN_FLAGS_MASK (((unsigned long) ~PAGE_MASK) \ + << (BITS_PER_LONG - PAGE_SHIFT)) +#define PFN_SG_CHAIN (1UL << (BITS_PER_LONG - 1)) +#define PFN_SG_LAST (1UL << (BITS_PER_LONG - 2)) +#define PFN_DEV (1UL << (BITS_PER_LONG - 3)) +#define PFN_MAP (1UL << (BITS_PER_LONG - 4)) + +static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, unsigned long flags) +{ + pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), }; + + return pfn_t; +} + +/* a default pfn to pfn_t conversion assumes that @pfn is pfn_valid() */ +static inline pfn_t pfn_to_pfn_t(unsigned long pfn) +{ + return __pfn_to_pfn_t(pfn, 0); +} + +extern pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags); + +static inline bool pfn_t_has_page(pfn_t pfn) +{ + return (pfn.val & PFN_MAP) == PFN_MAP || (pfn.val & PFN_DEV) == 0; +} + +static inline unsigned long pfn_t_to_pfn(pfn_t pfn) +{ + return pfn.val & ~PFN_FLAGS_MASK; +} + +static inline struct page *pfn_t_to_page(pfn_t pfn) +{ + if (pfn_t_has_page(pfn)) + return pfn_to_page(pfn_t_to_pfn(pfn)); + return NULL; +} + +static inline dma_addr_t pfn_t_to_phys(pfn_t pfn) +{ + return PFN_PHYS(pfn_t_to_pfn(pfn)); +} + +static inline void *pfn_t_to_virt(pfn_t pfn) +{ + if (pfn_t_has_page(pfn)) + return __va(pfn_t_to_phys(pfn)); + return NULL; +} + +static inline pfn_t page_to_pfn_t(struct page *page) +{ + return pfn_to_pfn_t(page_to_pfn(page)); +} + +static inline int pfn_t_valid(pfn_t pfn) +{ + return pfn_valid(pfn_t_to_pfn(pfn)); +} + +#ifdef CONFIG_MMU +static inline pte_t pfn_t_pte(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pte(pfn_t_to_pfn(pfn), pgprot); +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot) +{ + return pfn_pmd(pfn_t_to_pfn(pfn), pgprot); +} +#endif + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline bool pfn_t_devmap(pfn_t pfn) +{ + const unsigned long flags = PFN_DEV|PFN_MAP; + + return (pfn.val & flags) == flags; +} +#else +static inline bool pfn_t_devmap(pfn_t pfn) +{ + return false; +} +pte_t pte_mkdevmap(pte_t pte); +pmd_t pmd_mkdevmap(pmd_t pmd); +#endif +#endif /* _LINUX_PFN_T_H_ */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 317e16de09e5..4a27153574e2 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -27,11 +27,15 @@ * Magic number "tsta" to indicate a static timer initializer * for the object debugging code. */ -#define TIMER_ENTRY_STATIC ((void *) 0x74737461) +#define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) /********** mm/debug-pagealloc.c **********/ #define PAGE_POISON 0xaa +/********** mm/page_alloc.c ************/ + +#define TAIL_MAPPING ((void *) 0x400 + POISON_POINTER_DELTA) + /********** mm/slab.c **********/ /* * Magic nums for obj red zoning. diff --git a/include/linux/printk.h b/include/linux/printk.h index 9729565c25ff..9ccbdf2c1453 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -106,13 +106,13 @@ struct va_format { /* * Dummy printk for disabled debugging statements to use whilst maintaining - * gcc's format and side-effect checking. + * gcc's format checking. */ -static inline __printf(1, 2) -int no_printk(const char *fmt, ...) -{ - return 0; -} +#define no_printk(fmt, ...) \ +do { \ + if (0) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) #ifdef CONFIG_EARLY_PRINTK extern asmlinkage __printf(1, 2) diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 29446aeef36e..bdf597c4f0be 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -85,6 +85,7 @@ enum ttu_flags { TTU_UNMAP = 1, /* unmap mode */ TTU_MIGRATION = 2, /* migration mode */ TTU_MUNLOCK = 4, /* munlock mode */ + TTU_LZFREE = 8, /* lazy free mode */ TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ @@ -161,25 +162,31 @@ static inline void anon_vma_merge(struct vm_area_struct *vma, struct anon_vma *page_get_anon_vma(struct page *page); +/* bitflags for do_page_add_anon_rmap() */ +#define RMAP_EXCLUSIVE 0x01 +#define RMAP_COMPOUND 0x02 + /* * rmap interfaces called when adding or removing pte of page */ void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); -void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_add_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, int); -void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); +void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, + unsigned long, bool); void page_add_file_rmap(struct page *); -void page_remove_rmap(struct page *); +void page_remove_rmap(struct page *, bool); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); -static inline void page_dup_rmap(struct page *page) +static inline void page_dup_rmap(struct page *page, bool compound) { - atomic_inc(&page->_mapcount); + atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } /* @@ -210,6 +217,25 @@ static inline pte_t *page_check_address(struct page *page, struct mm_struct *mm, } /* + * Used by idle page tracking to check if a page was referenced via page + * tables. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +bool page_check_address_transhuge(struct page *page, struct mm_struct *mm, + unsigned long address, pmd_t **pmdp, + pte_t **ptep, spinlock_t **ptlp); +#else +static inline bool page_check_address_transhuge(struct page *page, + struct mm_struct *mm, unsigned long address, + pmd_t **pmdp, pte_t **ptep, spinlock_t **ptlp) +{ + *ptep = page_check_address(page, mm, address, ptlp, 0); + *pmdp = NULL; + return !!*ptep; +} +#endif + +/* * Used by swapoff to help locate where page is expected in vma. */ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); @@ -286,5 +312,6 @@ static inline int page_mkclean(struct page *page) #define SWAP_AGAIN 1 #define SWAP_FAIL 2 #define SWAP_MLOCK 3 +#define SWAP_LZFREE 4 #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 066bd21765ad..414e101cd061 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -307,6 +307,7 @@ extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); +extern void deactivate_page(struct page *page); extern void swap_setup(void); extern void add_page_to_unevictable_list(struct page *page); @@ -538,7 +539,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page) (page_mapcount(page) == 1) +#define reuse_swap_page(page) \ + (!PageTransCompound(page) && page_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) { diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index e623d392db0c..67c1dbd19c6d 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGALLOC), PGFREE, PGACTIVATE, PGDEACTIVATE, PGFAULT, PGMAJFAULT, + PGLAZYFREED, FOR_ALL_ZONES(PGREFILL), FOR_ALL_ZONES(PGSTEAL_KSWAPD), FOR_ALL_ZONES(PGSTEAL_DIRECT), @@ -68,7 +69,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_FAULT_FALLBACK, THP_COLLAPSE_ALLOC, THP_COLLAPSE_ALLOC_FAILED, - THP_SPLIT, + THP_SPLIT_PAGE, + THP_SPLIT_PAGE_FAILED, + THP_SPLIT_PMD, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 97d635cabac8..0f803d2783e3 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -22,6 +22,7 @@ EM( SCAN_PAGE_LRU, "page_not_in_lru") \ EM( SCAN_PAGE_LOCK, "page_locked") \ EM( SCAN_PAGE_ANON, "page_not_anon") \ + EM( SCAN_PAGE_COMPOUND, "page_compound") \ EM( SCAN_ANY_PROCESS, "no_process_for_page") \ EM( SCAN_VMA_NULL, "vma_null") \ EM( SCAN_VMA_CHECK, "vma_check_failed") \ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index a74dd84bbb6d..58274382a616 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -41,6 +41,7 @@ #define MADV_DONTNEED 4 /* don't need these pages */ /* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ diff --git a/init/Kconfig b/init/Kconfig index 5481b49e8c3f..4644217b2373 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -285,7 +285,7 @@ config FHANDLE config USELIB bool "uselib syscall" - default y + def_bool ALPHA || M68K || SPARC || X86_32 || IA32_EMULATION help This option enables the uselib syscall, a system call used in the dynamic linker from libc5 and earlier. glibc does not use this diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index bb0669169716..0167679182c0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -161,7 +161,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, const unsigned long mmun_end = addr + PAGE_SIZE; struct mem_cgroup *memcg; - err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg); + err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg, + false); if (err) return err; @@ -175,8 +176,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, goto unlock; get_page(kpage); - page_add_new_anon_rmap(kpage, vma, addr); - mem_cgroup_commit_charge(kpage, memcg, false); + page_add_new_anon_rmap(kpage, vma, addr, false); + mem_cgroup_commit_charge(kpage, memcg, false, false); lru_cache_add_active_or_unevictable(kpage, vma); if (!PageAnon(page)) { @@ -188,7 +189,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, ptep_clear_flush_notify(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); - page_remove_rmap(page); + page_remove_rmap(page, false); if (!page_mapped(page)) try_to_free_swap(page); pte_unmap_unlock(ptep, ptl); @@ -199,7 +200,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = 0; unlock: - mem_cgroup_cancel_charge(kpage, memcg); + mem_cgroup_cancel_charge(kpage, memcg, false); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(page); return err; diff --git a/kernel/futex.c b/kernel/futex.c index 8a310e240cda..c6f514573b28 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -469,7 +469,8 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct page *page, *page_head; + struct page *page; + struct address_space *mapping; int err, ro = 0; /* @@ -519,46 +520,9 @@ again: else err = 0; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - page_head = page; - if (unlikely(PageTail(page))) { - put_page(page); - /* serialize against __split_huge_page_splitting() */ - local_irq_disable(); - if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) { - page_head = compound_head(page); - /* - * page_head is valid pointer but we must pin - * it before taking the PG_lock and/or - * PG_compound_lock. The moment we re-enable - * irqs __split_huge_page_splitting() can - * return and the head page can be freed from - * under us. We can't take the PG_lock and/or - * PG_compound_lock on a page that could be - * freed from under us. - */ - if (page != page_head) { - get_page(page_head); - put_page(page); - } - local_irq_enable(); - } else { - local_irq_enable(); - goto again; - } - } -#else - page_head = compound_head(page); - if (page != page_head) { - get_page(page_head); - put_page(page); - } -#endif - - lock_page(page_head); - + lock_page(page); /* - * If page_head->mapping is NULL, then it cannot be a PageAnon + * If page->mapping is NULL, then it cannot be a PageAnon * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast @@ -570,12 +534,13 @@ again: * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: - * an unlikely race, but we do need to retry for page_head->mapping. + * an unlikely race, but we do need to retry for page->mapping. */ - if (!page_head->mapping) { - int shmem_swizzled = PageSwapCache(page_head); - unlock_page(page_head); - put_page(page_head); + mapping = compound_head(page)->mapping; + if (!mapping) { + int shmem_swizzled = PageSwapCache(page); + unlock_page(page); + put_page(page); if (shmem_swizzled) goto again; return -EFAULT; @@ -588,7 +553,7 @@ again: * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ - if (PageAnon(page_head)) { + if (PageAnon(page)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. @@ -603,15 +568,15 @@ again: key->private.address = address; } else { key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = page_head->mapping->host; + key->shared.inode = mapping->host; key->shared.pgoff = basepage_index(page); } get_futex_key_refs(key); /* implies MB (B) */ out: - unlock_page(page_head); - put_page(page_head); + unlock_page(page); + put_page(page); return err; } @@ -639,7 +604,7 @@ static int fault_in_user_writeable(u32 __user *uaddr) down_read(&mm->mmap_sem); ret = fixup_user_fault(current, mm, (unsigned long)uaddr, - FAULT_FLAG_WRITE); + FAULT_FLAG_WRITE, NULL); up_read(&mm->mmap_sem); return ret < 0 ? ret : 0; diff --git a/kernel/memremap.c b/kernel/memremap.c index 7658d32c5c78..e517a16cb426 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -10,8 +10,11 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <linux/radix-tree.h> +#include <linux/memremap.h> #include <linux/device.h> #include <linux/types.h> +#include <linux/pfn_t.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/memory_hotplug.h> @@ -147,24 +150,127 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); +pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +{ + return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); +} +EXPORT_SYMBOL(phys_to_pfn_t); + #ifdef CONFIG_ZONE_DEVICE +static DEFINE_MUTEX(pgmap_lock); +static RADIX_TREE(pgmap_radix, GFP_KERNEL); +#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) +#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) + struct page_map { struct resource res; + struct percpu_ref *ref; + struct dev_pagemap pgmap; + struct vmem_altmap altmap; }; -static void devm_memremap_pages_release(struct device *dev, void *res) +void get_zone_device_page(struct page *page) +{ + percpu_ref_get(page->pgmap->ref); +} +EXPORT_SYMBOL(get_zone_device_page); + +void put_zone_device_page(struct page *page) +{ + put_dev_pagemap(page->pgmap); +} +EXPORT_SYMBOL(put_zone_device_page); + +static void pgmap_radix_release(struct resource *res) +{ + resource_size_t key; + + mutex_lock(&pgmap_lock); + for (key = res->start; key <= res->end; key += SECTION_SIZE) + radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT); + mutex_unlock(&pgmap_lock); +} + +static unsigned long pfn_first(struct page_map *page_map) +{ + struct dev_pagemap *pgmap = &page_map->pgmap; + const struct resource *res = &page_map->res; + struct vmem_altmap *altmap = pgmap->altmap; + unsigned long pfn; + + pfn = res->start >> PAGE_SHIFT; + if (altmap) + pfn += vmem_altmap_offset(altmap); + return pfn; +} + +static unsigned long pfn_end(struct page_map *page_map) +{ + const struct resource *res = &page_map->res; + + return (res->start + resource_size(res)) >> PAGE_SHIFT; +} + +#define for_each_device_pfn(pfn, map) \ + for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++) + +static void devm_memremap_pages_release(struct device *dev, void *data) { - struct page_map *page_map = res; + struct page_map *page_map = data; + struct resource *res = &page_map->res; + resource_size_t align_start, align_size; + struct dev_pagemap *pgmap = &page_map->pgmap; + + if (percpu_ref_tryget_live(pgmap->ref)) { + dev_WARN(dev, "%s: page mapping is still live!\n", __func__); + percpu_ref_put(pgmap->ref); + } + + pgmap_radix_release(res); /* pages are dead and unused, undo the arch mapping */ - arch_remove_memory(page_map->res.start, resource_size(&page_map->res)); + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + arch_remove_memory(align_start, align_size); + dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, + "%s: failed to free all reserved pages\n", __func__); +} + +/* assumes rcu_read_lock() held at entry */ +struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +{ + struct page_map *page_map; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT); + return page_map ? &page_map->pgmap : NULL; } -void *devm_memremap_pages(struct device *dev, struct resource *res) +/** + * devm_memremap_pages - remap and provide memmap backing for the given resource + * @dev: hosting device for @res + * @res: "host memory" address range + * @ref: a live per-cpu reference count + * @altmap: optional descriptor for allocating the memmap from @res + * + * Notes: + * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time + * (or devm release event). + * + * 2/ @res is expected to be a host memory range that could feasibly be + * treated as a "System RAM" range, i.e. not a device mmio range, but + * this is not enforced. + */ +void *devm_memremap_pages(struct device *dev, struct resource *res, + struct percpu_ref *ref, struct vmem_altmap *altmap) { int is_ram = region_intersects(res->start, resource_size(res), "System RAM"); + resource_size_t key, align_start, align_size; + struct dev_pagemap *pgmap; struct page_map *page_map; + unsigned long pfn; int error, nid; if (is_ram == REGION_MIXED) { @@ -176,25 +282,120 @@ void *devm_memremap_pages(struct device *dev, struct resource *res) if (is_ram == REGION_INTERSECTS) return __va(res->start); + if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) { + dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n", + __func__); + return ERR_PTR(-ENXIO); + } + + if (!ref) + return ERR_PTR(-EINVAL); + page_map = devres_alloc_node(devm_memremap_pages_release, sizeof(*page_map), GFP_KERNEL, dev_to_node(dev)); if (!page_map) return ERR_PTR(-ENOMEM); + pgmap = &page_map->pgmap; memcpy(&page_map->res, res, sizeof(*res)); + pgmap->dev = dev; + if (altmap) { + memcpy(&page_map->altmap, altmap, sizeof(*altmap)); + pgmap->altmap = &page_map->altmap; + } + pgmap->ref = ref; + pgmap->res = &page_map->res; + + mutex_lock(&pgmap_lock); + error = 0; + for (key = res->start; key <= res->end; key += SECTION_SIZE) { + struct dev_pagemap *dup; + + rcu_read_lock(); + dup = find_dev_pagemap(key); + rcu_read_unlock(); + if (dup) { + dev_err(dev, "%s: %pr collides with mapping for %s\n", + __func__, res, dev_name(dup->dev)); + error = -EBUSY; + break; + } + error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT, + page_map); + if (error) { + dev_err(dev, "%s: failed: %d\n", __func__, error); + break; + } + } + mutex_unlock(&pgmap_lock); + if (error) + goto err_radix; + nid = dev_to_node(dev); if (nid < 0) nid = numa_mem_id(); - error = arch_add_memory(nid, res->start, resource_size(res), true); - if (error) { - devres_free(page_map); - return ERR_PTR(error); - } + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + error = arch_add_memory(nid, align_start, align_size, true); + if (error) + goto err_add_memory; + for_each_device_pfn(pfn, page_map) { + struct page *page = pfn_to_page(pfn); + + /* ZONE_DEVICE pages must never appear on a slab lru */ + list_force_poison(&page->lru); + page->pgmap = pgmap; + } devres_add(dev, page_map); return __va(res->start); + + err_add_memory: + err_radix: + pgmap_radix_release(res); + devres_free(page_map); + return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + /* number of pfns from base where pfn_to_page() is valid */ + return altmap->reserve + altmap->free; +} + +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) +{ + altmap->alloc -= nr_pfns; +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +{ + /* + * 'memmap_start' is the virtual address for the first "struct + * page" in this range of the vmemmap array. In the case of + * CONFIG_SPARSE_VMEMMAP a page_to_pfn conversion is simple + * pointer arithmetic, so we can perform this to_vmem_altmap() + * conversion without concern for the initialization state of + * the struct page fields. + */ + struct page *page = (struct page *) memmap_start; + struct dev_pagemap *pgmap; + + /* + * Uncoditionally retrieve a dev_pagemap associated with the + * given physical address, this is only for use in the + * arch_{add|remove}_memory() for setting up and tearing down + * the memmap. + */ + rcu_read_lock(); + pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page))); + rcu_read_unlock(); + + return pgmap ? pgmap->altmap : NULL; +} +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ #endif /* CONFIG_ZONE_DEVICE */ diff --git a/kernel/panic.c b/kernel/panic.c index b333380c6bb2..d96469de72dc 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -180,8 +180,7 @@ void panic(const char *fmt, ...) * panic() is not being callled from OOPS. */ debug_locks_off(); - console_trylock(); - console_unlock(); + console_flush_on_panic(); if (!panic_blink) panic_blink = no_blink; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2ce8826f1053..e79439134978 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -48,6 +48,7 @@ #include <linux/uio.h> #include <asm/uaccess.h> +#include <asm-generic/sections.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> @@ -1660,7 +1661,7 @@ asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) { - static int recursion_bug; + static bool recursion_bug; static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len = 0; @@ -1696,7 +1697,7 @@ asmlinkage int vprintk_emit(int facility, int level, * it can be printed at the next appropriate moment: */ if (!oops_in_progress && !lockdep_recursing(current)) { - recursion_bug = 1; + recursion_bug = true; local_irq_restore(flags); return 0; } @@ -1711,7 +1712,7 @@ asmlinkage int vprintk_emit(int facility, int level, static const char recursion_msg[] = "BUG: recent printk recursion!"; - recursion_bug = 0; + recursion_bug = false; /* emit KERN_CRIT message */ printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, NULL, 0, recursion_msg, @@ -2233,13 +2234,24 @@ void console_unlock(void) static u64 seen_seq; unsigned long flags; bool wake_klogd = false; - bool retry; + bool do_cond_resched, retry; if (console_suspended) { up_console_sem(); return; } + /* + * Console drivers are called under logbuf_lock, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. + */ + do_cond_resched = console_may_schedule; console_may_schedule = 0; /* flush buffered message fragment immediately to console */ @@ -2311,6 +2323,9 @@ skip: call_console_drivers(level, ext_text, ext_len, text, len); start_critical_timings(); local_irq_restore(flags); + + if (do_cond_resched) + cond_resched(); } console_locked = 0; @@ -2378,6 +2393,25 @@ void console_unblank(void) console_unlock(); } +/** + * console_flush_on_panic - flush console content on panic + * + * Immediately output all pending messages no matter what. + */ +void console_flush_on_panic(void) +{ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so + * that messages are flushed out. As this can be called from any + * context and we don't want to get preempted while flushing, + * ensure may_schedule is cleared. + */ + console_trylock(); + console_may_schedule = 0; + console_unlock(); +} + /* * Return the console tty driver structure and its associated index */ @@ -2658,13 +2692,36 @@ int unregister_console(struct console *console) } EXPORT_SYMBOL(unregister_console); +/* + * Some boot consoles access data that is in the init section and which will + * be discarded after the initcalls have been run. To make sure that no code + * will access this data, unregister the boot consoles in a late initcall. + * + * If for some reason, such as deferred probe or the driver being a loadable + * module, the real console hasn't registered yet at this point, there will + * be a brief interval in which no messages are logged to the console, which + * makes it difficult to diagnose problems that occur during this time. + * + * To mitigate this problem somewhat, only unregister consoles whose memory + * intersects with the init section. Note that code exists elsewhere to get + * rid of the boot console as soon as the proper console shows up, so there + * won't be side-effects from postponing the removal. + */ static int __init printk_late_init(void) { struct console *con; for_each_console(con) { if (!keep_bootcon && con->flags & CON_BOOT) { - unregister_console(con); + /* + * Make sure to unregister boot consoles whose data + * resides in the init section before the init section + * is discarded. Boot consoles whose data will stick + * around will automatically be unregistered when the + * proper console replaces them. + */ + if (init_section_intersects(con, sizeof(*con))) + unregister_console(con); } } hotcpu_notifier(console_cpu_notify, 0); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index edb6de4f5908..a467e6c28a3b 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -529,8 +529,6 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) - static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { @@ -628,5 +626,3 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, mutex_unlock(&stop_cpus_mutex); return ret ?: done.ret; } - -#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ee1ac1cc082c..f75a33f29f6e 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -580,6 +580,14 @@ config DEBUG_VM_RB If unsure, say N. +config DEBUG_VM_PGFLAGS + bool "Debug page-flags operations" + depends on DEBUG_VM + help + Enables extra validation on page flags operations. + + If unsure, say N. + config DEBUG_VIRTUAL bool "Debug VM translations" depends on DEBUG_KERNEL && X86 @@ -1589,7 +1597,6 @@ config FAULT_INJECTION_STACKTRACE_FILTER config LATENCYTOP bool "Latency measuring infrastructure" - depends on HAVE_LATENCYTOP_SUPPORT depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT depends on PROC_FS diff --git a/lib/kasprintf.c b/lib/kasprintf.c index f194e6e593e1..7f6c506a4942 100644 --- a/lib/kasprintf.c +++ b/lib/kasprintf.c @@ -13,19 +13,21 @@ /* Simplified asprintf. */ char *kvasprintf(gfp_t gfp, const char *fmt, va_list ap) { - unsigned int len; + unsigned int first, second; char *p; va_list aq; va_copy(aq, ap); - len = vsnprintf(NULL, 0, fmt, aq); + first = vsnprintf(NULL, 0, fmt, aq); va_end(aq); - p = kmalloc_track_caller(len+1, gfp); + p = kmalloc_track_caller(first+1, gfp); if (!p) return NULL; - vsnprintf(p, len+1, fmt, ap); + second = vsnprintf(p, first+1, fmt, ap); + WARN(first != second, "different return values (%u and %u) from vsnprintf(\"%s\", ...)", + first, second, fmt); return p; } diff --git a/lib/list_debug.c b/lib/list_debug.c index 3859bf63561c..3345a089ef7b 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -12,6 +12,13 @@ #include <linux/kernel.h> #include <linux/rculist.h> +static struct list_head force_poison; +void list_force_poison(struct list_head *entry) +{ + entry->next = &force_poison; + entry->prev = &force_poison; +} + /* * Insert a new entry between two known consecutive entries. * @@ -23,6 +30,8 @@ void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { + WARN(new->next == &force_poison || new->prev == &force_poison, + "list_add attempted on force-poisoned entry\n"); WARN(next->prev != prev, "list_add corruption. next->prev should be " "prev (%p), but was %p. (next=%p).\n", diff --git a/lib/test_printf.c b/lib/test_printf.c index c5a666af9ba5..4f6ae60433bc 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -12,10 +12,13 @@ #include <linux/slab.h> #include <linux/string.h> +#include <linux/bitmap.h> +#include <linux/dcache.h> #include <linux/socket.h> #include <linux/in.h> #define BUF_SIZE 256 +#define PAD_SIZE 16 #define FILL_CHAR '$' #define PTR1 ((void*)0x01234567) @@ -39,6 +42,7 @@ static unsigned total_tests __initdata; static unsigned failed_tests __initdata; static char *test_buffer __initdata; +static char *alloced_buffer __initdata; static int __printf(4, 0) __init do_test(int bufsize, const char *expect, int elen, @@ -49,7 +53,7 @@ do_test(int bufsize, const char *expect, int elen, total_tests++; - memset(test_buffer, FILL_CHAR, BUF_SIZE); + memset(alloced_buffer, FILL_CHAR, BUF_SIZE + 2*PAD_SIZE); va_copy(aq, ap); ret = vsnprintf(test_buffer, bufsize, fmt, aq); va_end(aq); @@ -60,8 +64,13 @@ do_test(int bufsize, const char *expect, int elen, return 1; } + if (memchr_inv(alloced_buffer, FILL_CHAR, PAD_SIZE)) { + pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote before buffer\n", bufsize, fmt); + return 1; + } + if (!bufsize) { - if (memchr_inv(test_buffer, FILL_CHAR, BUF_SIZE)) { + if (memchr_inv(test_buffer, FILL_CHAR, BUF_SIZE + PAD_SIZE)) { pr_warn("vsnprintf(buf, 0, \"%s\", ...) wrote to buffer\n", fmt); return 1; @@ -76,6 +85,12 @@ do_test(int bufsize, const char *expect, int elen, return 1; } + if (memchr_inv(test_buffer + written + 1, FILL_CHAR, BUF_SIZE + PAD_SIZE - (written + 1))) { + pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote beyond the nul-terminator\n", + bufsize, fmt); + return 1; + } + if (memcmp(test_buffer, expect, written)) { pr_warn("vsnprintf(buf, %d, \"%s\", ...) wrote '%s', expected '%.*s'\n", bufsize, fmt, test_buffer, written, expect); @@ -91,7 +106,12 @@ __test(const char *expect, int elen, const char *fmt, ...) int rand; char *p; - BUG_ON(elen >= BUF_SIZE); + if (elen >= BUF_SIZE) { + pr_err("error in test suite: expected output length %d too long. Format was '%s'.\n", + elen, fmt); + failed_tests++; + return; + } va_start(ap, fmt); @@ -109,6 +129,7 @@ __test(const char *expect, int elen, const char *fmt, ...) p = kvasprintf(GFP_KERNEL, fmt, ap); if (p) { + total_tests++; if (memcmp(p, expect, elen+1)) { pr_warn("kvasprintf(..., \"%s\", ...) returned '%s', expected '%s'\n", fmt, p, expect); @@ -140,6 +161,30 @@ test_number(void) test("0x1234abcd ", "%#-12x", 0x1234abcd); test(" 0x1234abcd", "%#12x", 0x1234abcd); test("0|001| 12|+123| 1234|-123|-1234", "%d|%03d|%3d|%+d|% d|%+d|% d", 0, 1, 12, 123, 1234, -123, -1234); + test("0|1|1|128|255", "%hhu|%hhu|%hhu|%hhu|%hhu", 0, 1, 257, 128, -1); + test("0|1|1|-128|-1", "%hhd|%hhd|%hhd|%hhd|%hhd", 0, 1, 257, 128, -1); + test("2015122420151225", "%ho%ho%#ho", 1037, 5282, -11627); + /* + * POSIX/C99: »The result of converting zero with an explicit + * precision of zero shall be no characters.« Hence the output + * from the below test should really be "00|0||| ". However, + * the kernel's printf also produces a single 0 in that + * case. This test case simply documents the current + * behaviour. + */ + test("00|0|0|0|0", "%.2d|%.1d|%.0d|%.*d|%1.0d", 0, 0, 0, 0, 0, 0); +#ifndef __CHAR_UNSIGNED__ + { + /* + * Passing a 'char' to a %02x specifier doesn't do + * what was presumably the intention when char is + * signed and the value is negative. One must either & + * with 0xff or cast to u8. + */ + char val = -16; + test("0xfffffff0|0xf0|0xf0", "%#02x|%#02x|%#02x", val, val & 0xff, (u8)val); + } +#endif } static void __init @@ -148,14 +193,23 @@ test_string(void) test("", "%s%.0s", "", "123"); test("ABCD|abc|123", "%s|%.3s|%.*s", "ABCD", "abcdef", 3, "123456"); test("1 | 2|3 | 4|5 ", "%-3s|%3s|%-*s|%*s|%*s", "1", "2", 3, "3", 3, "4", -3, "5"); + test("1234 ", "%-10.4s", "123456"); + test(" 1234", "%10.4s", "123456"); /* - * POSIX and C99 say that a missing precision should be - * treated as a precision of 0. However, the kernel's printf - * implementation treats this case as if the . wasn't - * present. Let's add a test case documenting the current - * behaviour; should anyone ever feel the need to follow the - * standards more closely, this can be revisited. + * POSIX and C99 say that a negative precision (which is only + * possible to pass via a * argument) should be treated as if + * the precision wasn't present, and that if the precision is + * omitted (as in %.s), the precision should be taken to be + * 0. However, the kernel's printf behave exactly opposite, + * treating a negative precision as 0 and treating an omitted + * precision specifier as if no precision was given. + * + * These test cases document the current behaviour; should + * anyone ever feel the need to follow the standards more + * closely, this can be revisited. */ + test(" ", "%4.*s", -5, "123456"); + test("123456", "%.s", "123456"); test("a||", "%.s|%.0s|%.*s", "a", "b", 0, "c"); test("a | | ", "%-3.s|%-3.0s|%-3.*s", "a", "b", 0, "c"); } @@ -273,9 +327,35 @@ uuid(void) test("03020100-0504-0706-0809-0A0B0C0D0E0F", "%pUL", uuid); } +static struct dentry test_dentry[4] __initdata = { + { .d_parent = &test_dentry[0], + .d_name = QSTR_INIT(test_dentry[0].d_iname, 3), + .d_iname = "foo" }, + { .d_parent = &test_dentry[0], + .d_name = QSTR_INIT(test_dentry[1].d_iname, 5), + .d_iname = "bravo" }, + { .d_parent = &test_dentry[1], + .d_name = QSTR_INIT(test_dentry[2].d_iname, 4), + .d_iname = "alfa" }, + { .d_parent = &test_dentry[2], + .d_name = QSTR_INIT(test_dentry[3].d_iname, 5), + .d_iname = "romeo" }, +}; + static void __init dentry(void) { + test("foo", "%pd", &test_dentry[0]); + test("foo", "%pd2", &test_dentry[0]); + + test("romeo", "%pd", &test_dentry[3]); + test("alfa/romeo", "%pd2", &test_dentry[3]); + test("bravo/alfa/romeo", "%pd3", &test_dentry[3]); + test("/bravo/alfa/romeo", "%pd4", &test_dentry[3]); + test("/bravo/alfa", "%pd4", &test_dentry[2]); + + test("bravo/alfa |bravo/alfa ", "%-12pd2|%*pd2", &test_dentry[2], -12, &test_dentry[2]); + test(" bravo/alfa| bravo/alfa", "%12pd2|%*pd2", &test_dentry[2], 12, &test_dentry[2]); } static void __init @@ -289,6 +369,20 @@ struct_clk(void) } static void __init +large_bitmap(void) +{ + const int nbits = 1 << 16; + unsigned long *bits = kcalloc(BITS_TO_LONGS(nbits), sizeof(long), GFP_KERNEL); + if (!bits) + return; + + bitmap_set(bits, 1, 20); + bitmap_set(bits, 60000, 15); + test("1-20,60000-60014", "%*pbl", nbits, bits); + kfree(bits); +} + +static void __init bitmap(void) { DECLARE_BITMAP(bits, 20); @@ -307,6 +401,8 @@ bitmap(void) bitmap_fill(bits, 20); test("fffff|fffff", "%20pb|%*pb", bits, 20, bits); test("0-19|0-19", "%20pbl|%*pbl", bits, 20, bits); + + large_bitmap(); } static void __init @@ -337,16 +433,17 @@ test_pointer(void) static int __init test_printf_init(void) { - test_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); - if (!test_buffer) + alloced_buffer = kmalloc(BUF_SIZE + 2*PAD_SIZE, GFP_KERNEL); + if (!alloced_buffer) return -ENOMEM; + test_buffer = alloced_buffer + PAD_SIZE; test_basic(); test_number(); test_string(); test_pointer(); - kfree(test_buffer); + kfree(alloced_buffer); if (failed_tests == 0) pr_info("all %u tests passed\n", total_tests); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index ac3f9476b776..48ff9c36644d 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -383,13 +383,14 @@ enum format_type { }; struct printf_spec { - u8 type; /* format_type enum */ - u8 flags; /* flags to number() */ - u8 base; /* number base, 8, 10 or 16 only */ - u8 qualifier; /* number qualifier, one of 'hHlLtzZ' */ - s16 field_width; /* width of output field */ - s16 precision; /* # of digits/chars */ -}; + unsigned int type:8; /* format_type enum */ + signed int field_width:24; /* width of output field */ + unsigned int flags:8; /* flags to number() */ + unsigned int base:8; /* number base, 8, 10 or 16 only */ + signed int precision:16; /* # of digits/chars */ +} __packed; +#define FIELD_WIDTH_MAX ((1 << 23) - 1) +#define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, @@ -402,6 +403,10 @@ char *number(char *buf, char *end, unsigned long long num, int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; + int field_width = spec.field_width; + int precision = spec.precision; + + BUILD_BUG_ON(sizeof(struct printf_spec) != 8); /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ @@ -413,20 +418,20 @@ char *number(char *buf, char *end, unsigned long long num, if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; - spec.field_width--; + field_width--; } else if (spec.flags & PLUS) { sign = '+'; - spec.field_width--; + field_width--; } else if (spec.flags & SPACE) { sign = ' '; - spec.field_width--; + field_width--; } } if (need_pfx) { if (spec.base == 16) - spec.field_width -= 2; + field_width -= 2; else if (!is_zero) - spec.field_width--; + field_width--; } /* generate full string in tmp[], in reverse order */ @@ -448,12 +453,12 @@ char *number(char *buf, char *end, unsigned long long num, } /* printing 100 using %2d gives "100", not "00" */ - if (i > spec.precision) - spec.precision = i; + if (i > precision) + precision = i; /* leading space padding */ - spec.field_width -= spec.precision; + field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { - while (--spec.field_width >= 0) { + while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; @@ -482,14 +487,14 @@ char *number(char *buf, char *end, unsigned long long num, if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); BUILD_BUG_ON(' ' + ZEROPAD != '0'); - while (--spec.field_width >= 0) { + while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ - while (i <= --spec.precision) { + while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; @@ -501,7 +506,7 @@ char *number(char *buf, char *end, unsigned long long num, ++buf; } /* trailing space padding */ - while (--spec.field_width >= 0) { + while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; @@ -511,37 +516,20 @@ char *number(char *buf, char *end, unsigned long long num, } static noinline_for_stack -char *string(char *buf, char *end, const char *s, struct printf_spec spec) +char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { - int len, i; - - if ((unsigned long)s < PAGE_SIZE) - s = "(null)"; + struct printf_spec spec; - len = strnlen(s, spec.precision); - - if (!(spec.flags & LEFT)) { - while (len < spec.field_width--) { - if (buf < end) - *buf = ' '; - ++buf; - } - } - for (i = 0; i < len; ++i) { - if (buf < end) - *buf = *s; - ++buf; ++s; - } - while (len < spec.field_width--) { - if (buf < end) - *buf = ' '; - ++buf; - } + spec.type = FORMAT_TYPE_PTR; + spec.field_width = 2 + 2 * size; /* 0x + hex */ + spec.flags = SPECIAL | SMALL | ZEROPAD; + spec.base = 16; + spec.precision = -1; - return buf; + return number(buf, end, num, spec); } -static void widen(char *buf, char *end, unsigned len, unsigned spaces) +static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ @@ -559,6 +547,56 @@ static void widen(char *buf, char *end, unsigned len, unsigned spaces) memset(buf, ' ', spaces); } +/* + * Handle field width padding for a string. + * @buf: current buffer position + * @n: length of string + * @end: end of output buffer + * @spec: for field width and flags + * Returns: new buffer position after padding. + */ +static noinline_for_stack +char *widen_string(char *buf, int n, char *end, struct printf_spec spec) +{ + unsigned spaces; + + if (likely(n >= spec.field_width)) + return buf; + /* we want to pad the sucker */ + spaces = spec.field_width - n; + if (!(spec.flags & LEFT)) { + move_right(buf - n, end, n, spaces); + return buf + spaces; + } + while (spaces--) { + if (buf < end) + *buf = ' '; + ++buf; + } + return buf; +} + +static noinline_for_stack +char *string(char *buf, char *end, const char *s, struct printf_spec spec) +{ + int len = 0; + size_t lim = spec.precision; + + if ((unsigned long)s < PAGE_SIZE) + s = "(null)"; + + while (lim--) { + char c = *s++; + if (!c) + break; + if (buf < end) + *buf = c; + ++buf; + ++len; + } + return widen_string(buf, len, end, spec); +} + static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) @@ -600,20 +638,7 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp *buf = c; } rcu_read_unlock(); - if (n < spec.field_width) { - /* we want to pad the sucker */ - unsigned spaces = spec.field_width - n; - if (!(spec.flags & LEFT)) { - widen(buf - n, end, n, spaces); - return buf + spaces; - } - while (spaces--) { - if (buf < end) - *buf = ' '; - ++buf; - } - } - return buf; + return widen_string(buf, n, end, spec); } #ifdef CONFIG_BLOCK @@ -659,11 +684,7 @@ char *symbol_string(char *buf, char *end, void *ptr, return string(buf, end, sym, spec); #else - spec.field_width = 2 * sizeof(void *); - spec.flags |= SPECIAL | SMALL | ZEROPAD; - spec.base = 16; - - return number(buf, end, value, spec); + return special_hex_number(buf, end, value, sizeof(void *)); #endif } @@ -1324,40 +1345,45 @@ char *uuid_string(char *buf, char *end, const u8 *addr, return string(buf, end, uuid, spec); } -static -char *netdev_feature_string(char *buf, char *end, const u8 *addr, - struct printf_spec spec) +static noinline_for_stack +char *netdev_bits(char *buf, char *end, const void *addr, const char *fmt) { - spec.flags |= SPECIAL | SMALL | ZEROPAD; - if (spec.field_width == -1) - spec.field_width = 2 + 2 * sizeof(netdev_features_t); - spec.base = 16; + unsigned long long num; + int size; - return number(buf, end, *(const netdev_features_t *)addr, spec); + switch (fmt[1]) { + case 'F': + num = *(const netdev_features_t *)addr; + size = sizeof(netdev_features_t); + break; + default: + num = (unsigned long)addr; + size = sizeof(unsigned long); + break; + } + + return special_hex_number(buf, end, num, size); } static noinline_for_stack -char *address_val(char *buf, char *end, const void *addr, - struct printf_spec spec, const char *fmt) +char *address_val(char *buf, char *end, const void *addr, const char *fmt) { unsigned long long num; - - spec.flags |= SPECIAL | SMALL | ZEROPAD; - spec.base = 16; + int size; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; - spec.field_width = sizeof(dma_addr_t) * 2 + 2; + size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; - spec.field_width = sizeof(phys_addr_t) * 2 + 2; + size = sizeof(phys_addr_t); break; } - return number(buf, end, num, spec); + return special_hex_number(buf, end, num, size); } static noinline_for_stack @@ -1376,10 +1402,7 @@ char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else - spec.base = 16; - spec.field_width = sizeof(unsigned long) * 2 + 2; - spec.flags |= SPECIAL | SMALL | ZEROPAD; - return number(buf, end, (unsigned long)clk, spec); + return special_hex_number(buf, end, (unsigned long)clk, sizeof(unsigned long)); #endif } } @@ -1609,13 +1632,9 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, break; case 'N': - switch (fmt[1]) { - case 'F': - return netdev_feature_string(buf, end, ptr, spec); - } - break; + return netdev_bits(buf, end, ptr, fmt); case 'a': - return address_val(buf, end, ptr, spec, fmt); + return address_val(buf, end, ptr, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 'C': @@ -1664,6 +1683,7 @@ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; + char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { @@ -1746,16 +1766,16 @@ precision: qualifier: /* get the conversion qualifier */ - spec->qualifier = -1; + qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || _tolower(*fmt) == 'z' || *fmt == 't') { - spec->qualifier = *fmt++; - if (unlikely(spec->qualifier == *fmt)) { - if (spec->qualifier == 'l') { - spec->qualifier = 'L'; + qualifier = *fmt++; + if (unlikely(qualifier == *fmt)) { + if (qualifier == 'l') { + qualifier = 'L'; ++fmt; - } else if (spec->qualifier == 'h') { - spec->qualifier = 'H'; + } else if (qualifier == 'h') { + qualifier = 'H'; ++fmt; } } @@ -1812,19 +1832,19 @@ qualifier: return fmt - start; } - if (spec->qualifier == 'L') + if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; - else if (spec->qualifier == 'l') { + else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); - } else if (_tolower(spec->qualifier) == 'z') { + } else if (_tolower(qualifier) == 'z') { spec->type = FORMAT_TYPE_SIZE_T; - } else if (spec->qualifier == 't') { + } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; - } else if (spec->qualifier == 'H') { + } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); - } else if (spec->qualifier == 'h') { + } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { @@ -1835,6 +1855,24 @@ qualifier: return ++fmt - start; } +static void +set_field_width(struct printf_spec *spec, int width) +{ + spec->field_width = width; + if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { + spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); + } +} + +static void +set_precision(struct printf_spec *spec, int prec) +{ + spec->precision = prec; + if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { + spec->precision = clamp(prec, 0, PRECISION_MAX); + } +} + /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into @@ -1902,11 +1940,11 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) } case FORMAT_TYPE_WIDTH: - spec.field_width = va_arg(args, int); + set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: - spec.precision = va_arg(args, int); + set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { @@ -2346,11 +2384,11 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) } case FORMAT_TYPE_WIDTH: - spec.field_width = get_arg(int); + set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: - spec.precision = get_arg(int); + set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { diff --git a/mm/debug.c b/mm/debug.c index 5d2072ed8d5e..f05b2d5d6481 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -40,9 +40,6 @@ static const struct trace_print_flags pageflag_names[] = { #ifdef CONFIG_MEMORY_FAILURE {1UL << PG_hwpoison, "hwpoison" }, #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - {1UL << PG_compound_lock, "compound_lock" }, -#endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) {1UL << PG_young, "young" }, {1UL << PG_idle, "idle" }, @@ -82,9 +79,12 @@ static void dump_flags(unsigned long flags, void dump_page_badflags(struct page *page, const char *reason, unsigned long badflags) { - pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx\n", + pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx", page, atomic_read(&page->_count), page_mapcount(page), page->mapping, page->index); + if (PageCompound(page)) + pr_cont(" compound_mapcount: %d", compound_mapcount(page)); + pr_cont("\n"); BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS); dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names)); if (reason) diff --git a/mm/filemap.c b/mm/filemap.c index ff42d31c891a..847ee43c2806 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -204,7 +204,7 @@ void __delete_from_page_cache(struct page *page, void *shadow, __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); - BUG_ON(page_mapped(page)); + VM_BUG_ON_PAGE(page_mapped(page), page); /* * At this point page must be either written or cleaned by truncate. @@ -618,7 +618,7 @@ static int __add_to_page_cache_locked(struct page *page, if (!huge) { error = mem_cgroup_try_charge(page, current->mm, - gfp_mask, &memcg); + gfp_mask, &memcg, false); if (error) return error; } @@ -626,7 +626,7 @@ static int __add_to_page_cache_locked(struct page *page, error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM); if (error) { if (!huge) - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); return error; } @@ -645,7 +645,7 @@ static int __add_to_page_cache_locked(struct page *page, __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); if (!huge) - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); trace_mm_filemap_add_to_page_cache(page); return 0; err_insert: @@ -653,7 +653,7 @@ err_insert: /* Leave page->index set: truncation relies upon it */ spin_unlock_irq(&mapping->tree_lock); if (!huge) - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); page_cache_release(page); return error; } @@ -682,11 +682,11 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, void *shadow = NULL; int ret; - __set_page_locked(page); + __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, gfp_mask, &shadow); if (unlikely(ret)) - __clear_page_locked(page); + __ClearPageLocked(page); else { /* * The page might have been evicted from cache only @@ -809,6 +809,7 @@ EXPORT_SYMBOL_GPL(add_page_wait_queue); */ void unlock_page(struct page *page) { + page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); clear_bit_unlock(PG_locked, &page->flags); smp_mb__after_atomic(); @@ -873,18 +874,20 @@ EXPORT_SYMBOL_GPL(page_endio); */ void __lock_page(struct page *page) { - DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); + struct page *page_head = compound_head(page); + DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked); - __wait_on_bit_lock(page_waitqueue(page), &wait, bit_wait_io, + __wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_page); int __lock_page_killable(struct page *page) { - DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); + struct page *page_head = compound_head(page); + DEFINE_WAIT_BIT(wait, &page_head->flags, PG_locked); - return __wait_on_bit_lock(page_waitqueue(page), &wait, + return __wait_on_bit_lock(page_waitqueue(page_head), &wait, bit_wait_io, TASK_KILLABLE); } EXPORT_SYMBOL_GPL(__lock_page_killable); diff --git a/mm/gup.c b/mm/gup.c index deafa2c91b36..b64a36175884 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -4,6 +4,7 @@ #include <linux/spinlock.h> #include <linux/mm.h> +#include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> @@ -62,6 +63,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { struct mm_struct *mm = vma->vm_mm; + struct dev_pagemap *pgmap = NULL; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; @@ -98,7 +100,17 @@ retry: } page = vm_normal_page(vma, address, pte); - if (unlikely(!page)) { + if (!page && pte_devmap(pte) && (flags & FOLL_GET)) { + /* + * Only return device mapping pages in the FOLL_GET case since + * they are only valid while holding the pgmap reference. + */ + pgmap = get_dev_pagemap(pte_pfn(pte), NULL); + if (pgmap) + page = pte_page(pte); + else + goto no_page; + } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); @@ -116,8 +128,28 @@ retry: } } - if (flags & FOLL_GET) - get_page_foll(page); + if (flags & FOLL_SPLIT && PageTransCompound(page)) { + int ret; + get_page(page); + pte_unmap_unlock(ptep, ptl); + lock_page(page); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + if (ret) + return ERR_PTR(ret); + goto retry; + } + + if (flags & FOLL_GET) { + get_page(page); + + /* drop the pgmap reference now that we hold the page */ + if (pgmap) { + put_dev_pagemap(pgmap); + pgmap = NULL; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -130,6 +162,10 @@ retry: mark_page_accessed(page); } if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { + /* Do not mlock pte-mapped THP */ + if (PageTransCompound(page)) + goto out; + /* * The preliminary mapping check is mainly to avoid the * pointless overhead of lock_page on the ZERO_PAGE @@ -220,27 +256,45 @@ struct page *follow_page_mask(struct vm_area_struct *vma, } if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) return no_page_table(vma, flags); - if (pmd_trans_huge(*pmd)) { - if (flags & FOLL_SPLIT) { - split_huge_page_pmd(vma, address, pmd); - return follow_page_pte(vma, address, pmd, flags); - } + if (pmd_devmap(*pmd)) { ptl = pmd_lock(mm, pmd); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(ptl); - wait_split_huge_page(vma->anon_vma, pmd); - } else { - page = follow_trans_huge_pmd(vma, address, - pmd, flags); - spin_unlock(ptl); - *page_mask = HPAGE_PMD_NR - 1; - return page; - } - } else + page = follow_devmap_pmd(vma, address, pmd, flags); + spin_unlock(ptl); + if (page) + return page; + } + if (likely(!pmd_trans_huge(*pmd))) + return follow_page_pte(vma, address, pmd, flags); + + ptl = pmd_lock(mm, pmd); + if (unlikely(!pmd_trans_huge(*pmd))) { + spin_unlock(ptl); + return follow_page_pte(vma, address, pmd, flags); + } + if (flags & FOLL_SPLIT) { + int ret; + page = pmd_page(*pmd); + if (is_huge_zero_page(page)) { + spin_unlock(ptl); + ret = 0; + split_huge_pmd(vma, pmd, address); + } else { + get_page(page); spin_unlock(ptl); + lock_page(page); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + } + + return ret ? ERR_PTR(ret) : + follow_page_pte(vma, address, pmd, flags); } - return follow_page_pte(vma, address, pmd, flags); + + page = follow_trans_huge_pmd(vma, address, pmd, flags); + spin_unlock(ptl); + *page_mask = HPAGE_PMD_NR - 1; + return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, @@ -564,6 +618,8 @@ EXPORT_SYMBOL(__get_user_pages); * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() + * @unlocked: did we unlock the mmap_sem while retrying, maybe NULL if caller + * does not allow retry * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() @@ -575,22 +631,28 @@ EXPORT_SYMBOL(__get_user_pages); * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while - * handle_mm_fault() only guarantees to update these in the struct page. + * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * - * This has the same semantics wrt the @mm->mmap_sem as does filemap_fault(). + * This function will not return with an unlocked mmap_sem. So it has not the + * same semantics wrt the @mm->mmap_sem as does filemap_fault(). */ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, - unsigned long address, unsigned int fault_flags) + unsigned long address, unsigned int fault_flags, + bool *unlocked) { struct vm_area_struct *vma; vm_flags_t vm_flags; - int ret; + int ret, major = 0; + if (unlocked) + fault_flags |= FAULT_FLAG_ALLOW_RETRY; + +retry: vma = find_extend_vma(mm, address); if (!vma || address < vma->vm_start) return -EFAULT; @@ -600,6 +662,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -EFAULT; ret = handle_mm_fault(mm, vma, address, fault_flags); + major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { if (ret & VM_FAULT_OOM) return -ENOMEM; @@ -609,8 +672,19 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -EFAULT; BUG(); } + + if (ret & VM_FAULT_RETRY) { + down_read(&mm->mmap_sem); + if (!(fault_flags & FAULT_FLAG_TRIED)) { + *unlocked = true; + fault_flags &= ~FAULT_FLAG_ALLOW_RETRY; + fault_flags |= FAULT_FLAG_TRIED; + goto retry; + } + } + if (tsk) { - if (ret & VM_FAULT_MAJOR) + if (major) tsk->maj_flt++; else tsk->min_flt++; @@ -896,7 +970,6 @@ long populate_vma_page_range(struct vm_area_struct *vma, gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK; if (vma->vm_flags & VM_LOCKONFAULT) gup_flags &= ~FOLL_POPULATE; - /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW @@ -1036,9 +1109,6 @@ struct page *get_dump_page(unsigned long addr) * *) HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table is used to free * pages containing page tables. * - * *) THP splits will broadcast an IPI, this can be achieved by overriding - * pmdp_splitting_flush. - * * *) ptes can be read atomically by the architecture. * * *) access_ok is sufficient to validate userspace address ranges. @@ -1066,7 +1136,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, * for an example see gup_get_pte in arch/x86/mm/gup.c */ pte_t pte = READ_ONCE(*ptep); - struct page *page; + struct page *head, *page; /* * Similar to the PMD case below, NUMA hinting must take slow @@ -1078,15 +1148,17 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); + head = compound_head(page); - if (!page_cache_get_speculative(page)) + if (!page_cache_get_speculative(head)) goto pte_unmap; if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_page(page); + put_page(head); goto pte_unmap; } + VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; (*nr)++; @@ -1119,7 +1191,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (write && !pmd_write(orig)) @@ -1128,7 +1200,6 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, refs = 0; head = pmd_page(orig); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; @@ -1149,24 +1220,13 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, return 0; } - /* - * Any tail pages need their mapcount reference taken before we - * return. (This allows the THP code to bump their ref count when - * they are split into base pages). - */ - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - struct page *head, *page, *tail; + struct page *head, *page; int refs; if (write && !pud_write(orig)) @@ -1175,7 +1235,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, refs = 0; head = pud_page(orig); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; @@ -1196,12 +1255,6 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 0; } - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -1210,7 +1263,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, struct page **pages, int *nr) { int refs; - struct page *head, *page, *tail; + struct page *head, *page; if (write && !pgd_write(orig)) return 0; @@ -1218,7 +1271,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, refs = 0; head = pgd_page(orig); page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); - tail = page; do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; @@ -1239,12 +1291,6 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 0; } - while (refs--) { - if (PageTail(tail)) - get_huge_page_tail(tail); - tail++; - } - return 1; } @@ -1259,7 +1305,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f952f055fdcf..b2db98136af9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -16,12 +16,16 @@ #include <linux/swap.h> #include <linux/shrinker.h> #include <linux/mm_inline.h> +#include <linux/swapops.h> #include <linux/dax.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> +#include <linux/pfn_t.h> #include <linux/mman.h> +#include <linux/memremap.h> #include <linux/pagemap.h> +#include <linux/debugfs.h> #include <linux/migrate.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> @@ -45,6 +49,7 @@ enum scan_result { SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, + SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, @@ -133,6 +138,10 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; +static DEFINE_SPINLOCK(split_queue_lock); +static LIST_HEAD(split_queue); +static unsigned long split_queue_len; +static struct shrinker deferred_split_shrinker; static void set_recommended_min_free_kbytes(void) { @@ -665,6 +674,9 @@ static int __init hugepage_init(void) err = register_shrinker(&huge_zero_page_shrinker); if (err) goto err_hzp_shrinker; + err = register_shrinker(&deferred_split_shrinker); + if (err) + goto err_split_shrinker; /* * By default disable transparent hugepages on smaller systems, @@ -682,6 +694,8 @@ static int __init hugepage_init(void) return 0; err_khugepaged: + unregister_shrinker(&deferred_split_shrinker); +err_split_shrinker: unregister_shrinker(&huge_zero_page_shrinker); err_hzp_shrinker: khugepaged_slab_exit(); @@ -738,6 +752,27 @@ static inline pmd_t mk_huge_pmd(struct page *page, pgprot_t prot) return entry; } +static inline struct list_head *page_deferred_list(struct page *page) +{ + /* + * ->lru in the tail pages is occupied by compound_head. + * Let's use ->mapping + ->index in the second tail page as list_head. + */ + return (struct list_head *)&page[2].mapping; +} + +void prep_transhuge_page(struct page *page) +{ + /* + * we use page->mapping and page->indexlru in second tail page + * as list_head: assuming THP order >= 2 + */ + BUILD_BUG_ON(HPAGE_PMD_ORDER < 2); + + INIT_LIST_HEAD(page_deferred_list(page)); + set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR); +} + static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, @@ -751,7 +786,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, mm, gfp, &memcg)) { + if (mem_cgroup_try_charge(page, mm, gfp, &memcg, true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -759,7 +794,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, pgtable = pte_alloc_one(mm, haddr); if (unlikely(!pgtable)) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, true); put_page(page); return VM_FAULT_OOM; } @@ -775,7 +810,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_none(*pmd))) { spin_unlock(ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, true); put_page(page); pte_free(mm, pgtable); } else { @@ -786,7 +821,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, int ret; spin_unlock(ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, true); put_page(page); pte_free(mm, pgtable); ret = handle_userfault(vma, address, flags, @@ -797,8 +832,8 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - page_add_new_anon_rmap(page, vma, haddr); - mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, haddr, true); + mem_cgroup_commit_charge(page, memcg, false, true); lru_cache_add_active_or_unevictable(page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); @@ -892,32 +927,33 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } + prep_transhuge_page(page); return __do_huge_pmd_anonymous_page(mm, vma, address, pmd, page, gfp, flags); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned long pfn, pgprot_t prot, bool write) + pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write) { struct mm_struct *mm = vma->vm_mm; pmd_t entry; spinlock_t *ptl; ptl = pmd_lock(mm, pmd); - if (pmd_none(*pmd)) { - entry = pmd_mkhuge(pfn_pmd(pfn, prot)); - if (write) { - entry = pmd_mkyoung(pmd_mkdirty(entry)); - entry = maybe_pmd_mkwrite(entry, vma); - } - set_pmd_at(mm, addr, pmd, entry); - update_mmu_cache_pmd(vma, addr, pmd); - } + entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pmd_mkdevmap(entry); + if (write) { + entry = pmd_mkyoung(pmd_mkdirty(entry)); + entry = maybe_pmd_mkwrite(entry, vma); + } + set_pmd_at(mm, addr, pmd, entry); + update_mmu_cache_pmd(vma, addr, pmd); spin_unlock(ptl); } int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned long pfn, bool write) + pmd_t *pmd, pfn_t pfn, bool write) { pgprot_t pgprot = vma->vm_page_prot; /* @@ -929,7 +965,7 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + BUG_ON(!pfn_t_devmap(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; @@ -939,6 +975,63 @@ int vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, return VM_FAULT_NOPAGE; } +static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd) +{ + pmd_t _pmd; + + /* + * We should set the dirty bit only for FOLL_WRITE but for now + * the dirty bit in the pmd is meaningless. And if the dirty + * bit will become meaningful and we'll only set it with + * FOLL_WRITE, an atomic set_bit will be required on the pmd to + * set the young bit, instead of the current set_pmd_at. + */ + _pmd = pmd_mkyoung(pmd_mkdirty(*pmd)); + if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, + pmd, _pmd, 1)) + update_mmu_cache_pmd(vma, addr, pmd); +} + +struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, int flags) +{ + unsigned long pfn = pmd_pfn(*pmd); + struct mm_struct *mm = vma->vm_mm; + struct dev_pagemap *pgmap; + struct page *page; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + if (flags & FOLL_WRITE && !pmd_write(*pmd)) + return NULL; + + if (pmd_present(*pmd) && pmd_devmap(*pmd)) + /* pass */; + else + return NULL; + + if (flags & FOLL_TOUCH) + touch_pmd(vma, addr, pmd); + + /* + * device mapped pages can only be returned if the + * caller will manage the page reference count. + */ + if (!(flags & FOLL_GET)) + return ERR_PTR(-EEXIST); + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + pgmap = get_dev_pagemap(pfn, NULL); + if (!pgmap) + return ERR_PTR(-EFAULT); + page = pfn_to_page(pfn); + get_page(page); + put_dev_pagemap(pgmap); + + return page; +} + int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma) @@ -960,7 +1053,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - if (unlikely(!pmd_trans_huge(pmd))) { + if (unlikely(!pmd_trans_huge(pmd) && !pmd_devmap(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } @@ -983,26 +1076,20 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (unlikely(pmd_trans_splitting(pmd))) { - /* split huge page running from under us */ - spin_unlock(src_ptl); - spin_unlock(dst_ptl); - pte_free(dst_mm, pgtable); - - wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */ - goto out; + if (pmd_trans_huge(pmd)) { + /* thp accounting separate from pmd_devmap accounting */ + src_page = pmd_page(pmd); + VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + get_page(src_page); + page_dup_rmap(src_page, true); + add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); + atomic_long_inc(&dst_mm->nr_ptes); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); } - src_page = pmd_page(pmd); - VM_BUG_ON_PAGE(!PageHead(src_page), src_page); - get_page(src_page); - page_dup_rmap(src_page); - add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); - pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); set_pmd_at(dst_mm, addr, dst_pmd, pmd); - atomic_long_inc(&dst_mm->nr_ptes); ret = 0; out_unlock: @@ -1035,37 +1122,6 @@ unlock: spin_unlock(ptl); } -/* - * Save CONFIG_DEBUG_PAGEALLOC from faulting falsely on tail pages - * during copy_user_huge_page()'s copy_page_rep(): in the case when - * the source page gets split and a tail freed before copy completes. - * Called under pmd_lock of checked pmd, so safe from splitting itself. - */ -static void get_user_huge_page(struct page *page) -{ - if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { - struct page *endpage = page + HPAGE_PMD_NR; - - atomic_add(HPAGE_PMD_NR, &page->_count); - while (++page < endpage) - get_huge_page_tail(page); - } else { - get_page(page); - } -} - -static void put_user_huge_page(struct page *page) -{ - if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) { - struct page *endpage = page + HPAGE_PMD_NR; - - while (page < endpage) - put_page(page++); - } else { - put_page(page); - } -} - static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -1095,13 +1151,14 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, vma, address, page_to_nid(page)); if (unlikely(!pages[i] || mem_cgroup_try_charge(pages[i], mm, GFP_KERNEL, - &memcg))) { + &memcg, false))) { if (pages[i]) put_page(pages[i]); while (--i >= 0) { memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - mem_cgroup_cancel_charge(pages[i], memcg); + mem_cgroup_cancel_charge(pages[i], memcg, + false); put_page(pages[i]); } kfree(pages); @@ -1139,8 +1196,8 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, entry = maybe_mkwrite(pte_mkdirty(entry), vma); memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - page_add_new_anon_rmap(pages[i], vma, haddr); - mem_cgroup_commit_charge(pages[i], memcg, false); + page_add_new_anon_rmap(pages[i], vma, haddr, false); + mem_cgroup_commit_charge(pages[i], memcg, false, false); lru_cache_add_active_or_unevictable(pages[i], vma); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte_none(*pte)); @@ -1151,7 +1208,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); - page_remove_rmap(page); + page_remove_rmap(page, true); spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); @@ -1168,7 +1225,7 @@ out_free_pages: for (i = 0; i < HPAGE_PMD_NR; i++) { memcg = (void *)page_private(pages[i]); set_page_private(pages[i], 0); - mem_cgroup_cancel_charge(pages[i], memcg); + mem_cgroup_cancel_charge(pages[i], memcg, false); put_page(pages[i]); } kfree(pages); @@ -1198,7 +1255,17 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, page = pmd_page(orig_pmd); VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page); - if (page_mapcount(page) == 1) { + /* + * We can only reuse the page if nobody else maps the huge page or it's + * part. We can do it by checking page_mapcount() on each sub-page, but + * it's expensive. + * The cheaper way is to check page_count() to be equal 1: every + * mapcount takes page reference reference, so this way we can + * guarantee, that the PMD is the only mapping. + * This can give false negative if somebody pinned the page, but that's + * fine. + */ + if (page_mapcount(page) == 1 && page_count(page) == 1) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); @@ -1207,7 +1274,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, ret |= VM_FAULT_WRITE; goto out_unlock; } - get_user_huge_page(page); + get_page(page); spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && @@ -1217,30 +1284,33 @@ alloc: } else new_page = NULL; - if (unlikely(!new_page)) { + if (likely(new_page)) { + prep_transhuge_page(new_page); + } else { if (!page) { - split_huge_page_pmd(vma, address, pmd); + split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); if (ret & VM_FAULT_OOM) { - split_huge_page(page); + split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; } - put_user_huge_page(page); + put_page(page); } count_vm_event(THP_FAULT_FALLBACK); goto out; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, huge_gfp, &memcg, + true))) { put_page(new_page); if (page) { - split_huge_page(page); - put_user_huge_page(page); + split_huge_pmd(vma, pmd, address); + put_page(page); } else - split_huge_page_pmd(vma, address, pmd); + split_huge_pmd(vma, pmd, address); ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); goto out; @@ -1260,10 +1330,10 @@ alloc: spin_lock(ptl); if (page) - put_user_huge_page(page); + put_page(page); if (unlikely(!pmd_same(*pmd, orig_pmd))) { spin_unlock(ptl); - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, true); put_page(new_page); goto out_mn; } else { @@ -1271,8 +1341,8 @@ alloc: entry = mk_huge_pmd(new_page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); pmdp_huge_clear_flush_notify(vma, haddr, pmd); - page_add_new_anon_rmap(new_page, vma, haddr); - mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, haddr, true); + mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_active_or_unevictable(new_page, vma); set_pmd_at(mm, haddr, pmd, entry); update_mmu_cache_pmd(vma, address, pmd); @@ -1281,7 +1351,7 @@ alloc: put_huge_zero_page(); } else { VM_BUG_ON_PAGE(!PageHead(page), page); - page_remove_rmap(page); + page_remove_rmap(page, true); put_page(page); } ret |= VM_FAULT_WRITE; @@ -1319,23 +1389,23 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page = pmd_page(*pmd); VM_BUG_ON_PAGE(!PageHead(page), page); - if (flags & FOLL_TOUCH) { - pmd_t _pmd; + if (flags & FOLL_TOUCH) + touch_pmd(vma, addr, pmd); + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* - * We should set the dirty bit only for FOLL_WRITE but - * for now the dirty bit in the pmd is meaningless. - * And if the dirty bit will become meaningful and - * we'll only set it with FOLL_WRITE, an atomic - * set_bit will be required on the pmd to set the - * young bit, instead of the current set_pmd_at. + * We don't mlock() pte-mapped THPs. This way we can avoid + * leaking mlocked pages into non-VM_LOCKED VMAs. + * + * In most cases the pmd is the only mapping of the page as we + * break COW for the mlock() -- see gup_flags |= FOLL_WRITE for + * writable private mappings in populate_vma_page_range(). + * + * The only scenario when we have the page shared here is if we + * mlocking read-only mapping shared over fork(). We skip + * mlocking such pages. */ - _pmd = pmd_mkyoung(pmd_mkdirty(*pmd)); - if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, - pmd, _pmd, 1)) - update_mmu_cache_pmd(vma, addr, pmd); - } - if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - if (page->mapping && trylock_page(page)) { + if (compound_mapcount(page) == 1 && !PageDoubleMap(page) && + page->mapping && trylock_page(page)) { lru_add_drain(); if (page->mapping) mlock_vma_page(page); @@ -1345,7 +1415,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; VM_BUG_ON_PAGE(!PageCompound(page), page); if (flags & FOLL_GET) - get_page_foll(page); + get_page(page); out: return page; @@ -1480,13 +1550,84 @@ out: return 0; } +int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long addr, unsigned long next) + +{ + spinlock_t *ptl; + pmd_t orig_pmd; + struct page *page; + struct mm_struct *mm = tlb->mm; + int ret = 0; + + if (!pmd_trans_huge_lock(pmd, vma, &ptl)) + goto out; + + orig_pmd = *pmd; + if (is_huge_zero_pmd(orig_pmd)) { + ret = 1; + goto out; + } + + page = pmd_page(orig_pmd); + /* + * If other processes are mapping this page, we couldn't discard + * the page unless they all do MADV_FREE so let's skip the page. + */ + if (page_mapcount(page) != 1) + goto out; + + if (!trylock_page(page)) + goto out; + + /* + * If user want to discard part-pages of THP, split it so MADV_FREE + * will deactivate only them. + */ + if (next - addr != HPAGE_PMD_SIZE) { + get_page(page); + spin_unlock(ptl); + if (split_huge_page(page)) { + put_page(page); + unlock_page(page); + goto out_unlocked; + } + put_page(page); + unlock_page(page); + ret = 1; + goto out_unlocked; + } + + if (PageDirty(page)) + ClearPageDirty(page); + unlock_page(page); + + if (PageActive(page)) + deactivate_page(page); + + if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { + orig_pmd = pmdp_huge_get_and_clear_full(tlb->mm, addr, pmd, + tlb->fullmm); + orig_pmd = pmd_mkold(orig_pmd); + orig_pmd = pmd_mkclean(orig_pmd); + + set_pmd_at(mm, addr, pmd, orig_pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + } + ret = 1; +out: + spin_unlock(ptl); +out_unlocked: + return ret; +} + int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { pmd_t orig_pmd; spinlock_t *ptl; - if (__pmd_trans_huge_lock(pmd, vma, &ptl) != 1) + if (!__pmd_trans_huge_lock(pmd, vma, &ptl)) return 0; /* * For architectures like ppc64 we look at deposited pgtable @@ -1508,7 +1649,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, put_huge_zero_page(); } else { struct page *page = pmd_page(orig_pmd); - page_remove_rmap(page); + page_remove_rmap(page, true); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); VM_BUG_ON_PAGE(!PageHead(page), page); @@ -1520,13 +1661,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, return 1; } -int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, +bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd) { spinlock_t *old_ptl, *new_ptl; - int ret = 0; pmd_t pmd; struct mm_struct *mm = vma->vm_mm; @@ -1535,7 +1675,7 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, (new_addr & ~HPAGE_PMD_MASK) || old_end - old_addr < HPAGE_PMD_SIZE || (new_vma->vm_flags & VM_NOHUGEPAGE)) - goto out; + return false; /* * The destination pmd shouldn't be established, free_pgtables() @@ -1543,15 +1683,14 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, */ if (WARN_ON(!pmd_none(*new_pmd))) { VM_BUG_ON(pmd_trans_huge(*new_pmd)); - goto out; + return false; } /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_sem prevents deadlock. */ - ret = __pmd_trans_huge_lock(old_pmd, vma, &old_ptl); - if (ret == 1) { + if (__pmd_trans_huge_lock(old_pmd, vma, &old_ptl)) { new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); @@ -1567,9 +1706,9 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, if (new_ptl != old_ptl) spin_unlock(new_ptl); spin_unlock(old_ptl); + return true; } -out: - return ret; + return false; } /* @@ -1585,7 +1724,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (__pmd_trans_huge_lock(pmd, vma, &ptl)) { pmd_t entry; bool preserve_write = prot_numa && pmd_write(*pmd); ret = 1; @@ -1616,405 +1755,19 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, } /* - * Returns 1 if a given pmd maps a stable (not under splitting) thp. - * Returns -1 if it maps a thp under splitting. Returns 0 otherwise. + * Returns true if a given pmd maps a thp, false otherwise. * - * Note that if it returns 1, this routine returns without unlocking page - * table locks. So callers must unlock them. + * Note that if it returns true, this routine returns without unlocking page + * table lock. So callers must unlock it. */ -int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, +bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, spinlock_t **ptl) { *ptl = pmd_lock(vma->vm_mm, pmd); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(*ptl); - wait_split_huge_page(vma->anon_vma, pmd); - return -1; - } else { - /* Thp mapped by 'pmd' is stable, so we can - * handle it as it is. */ - return 1; - } - } - spin_unlock(*ptl); - return 0; -} - -/* - * This function returns whether a given @page is mapped onto the @address - * in the virtual space of @mm. - * - * When it's true, this function returns *pmd with holding the page table lock - * and passing it back to the caller via @ptl. - * If it's false, returns NULL without holding the page table lock. - */ -pmd_t *page_check_address_pmd(struct page *page, - struct mm_struct *mm, - unsigned long address, - enum page_check_address_pmd_flag flag, - spinlock_t **ptl) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - - if (address & ~HPAGE_PMD_MASK) - return NULL; - - pgd = pgd_offset(mm, address); - if (!pgd_present(*pgd)) - return NULL; - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) - return NULL; - pmd = pmd_offset(pud, address); - - *ptl = pmd_lock(mm, pmd); - if (!pmd_present(*pmd)) - goto unlock; - if (pmd_page(*pmd) != page) - goto unlock; - /* - * split_vma() may create temporary aliased mappings. There is - * no risk as long as all huge pmd are found and have their - * splitting bit set before __split_huge_page_refcount - * runs. Finding the same huge pmd more than once during the - * same rmap walk is not a problem. - */ - if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG && - pmd_trans_splitting(*pmd)) - goto unlock; - if (pmd_trans_huge(*pmd)) { - VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG && - !pmd_trans_splitting(*pmd)); - return pmd; - } -unlock: + if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) + return true; spin_unlock(*ptl); - return NULL; -} - -static int __split_huge_page_splitting(struct page *page, - struct vm_area_struct *vma, - unsigned long address) -{ - struct mm_struct *mm = vma->vm_mm; - spinlock_t *ptl; - pmd_t *pmd; - int ret = 0; - /* For mmu_notifiers */ - const unsigned long mmun_start = address; - const unsigned long mmun_end = address + HPAGE_PMD_SIZE; - - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl); - if (pmd) { - /* - * We can't temporarily set the pmd to null in order - * to split it, the pmd must remain marked huge at all - * times or the VM won't take the pmd_trans_huge paths - * and it won't wait on the anon_vma->root->rwsem to - * serialize against split_huge_page*. - */ - pmdp_splitting_flush(vma, address, pmd); - - ret = 1; - spin_unlock(ptl); - } - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - - return ret; -} - -static void __split_huge_page_refcount(struct page *page, - struct list_head *list) -{ - int i; - struct zone *zone = page_zone(page); - struct lruvec *lruvec; - int tail_count = 0; - - /* prevent PageLRU to go away from under us, and freeze lru stats */ - spin_lock_irq(&zone->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, zone); - - compound_lock(page); - /* complete memcg works before add pages to LRU */ - mem_cgroup_split_huge_fixup(page); - - for (i = HPAGE_PMD_NR - 1; i >= 1; i--) { - struct page *page_tail = page + i; - - /* tail_page->_mapcount cannot change */ - BUG_ON(page_mapcount(page_tail) < 0); - tail_count += page_mapcount(page_tail); - /* check for overflow */ - BUG_ON(tail_count < 0); - BUG_ON(atomic_read(&page_tail->_count) != 0); - /* - * tail_page->_count is zero and not changing from - * under us. But get_page_unless_zero() may be running - * from under us on the tail_page. If we used - * atomic_set() below instead of atomic_add(), we - * would then run atomic_set() concurrently with - * get_page_unless_zero(), and atomic_set() is - * implemented in C not using locked ops. spin_unlock - * on x86 sometime uses locked ops because of PPro - * errata 66, 92, so unless somebody can guarantee - * atomic_set() here would be safe on all archs (and - * not only on x86), it's safer to use atomic_add(). - */ - atomic_add(page_mapcount(page) + page_mapcount(page_tail) + 1, - &page_tail->_count); - - /* after clearing PageTail the gup refcount can be released */ - smp_mb__after_atomic(); - - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; - page_tail->flags |= (page->flags & - ((1L << PG_referenced) | - (1L << PG_swapbacked) | - (1L << PG_mlocked) | - (1L << PG_uptodate) | - (1L << PG_active) | - (1L << PG_unevictable))); - page_tail->flags |= (1L << PG_dirty); - - clear_compound_head(page_tail); - - if (page_is_young(page)) - set_page_young(page_tail); - if (page_is_idle(page)) - set_page_idle(page_tail); - - /* - * __split_huge_page_splitting() already set the - * splitting bit in all pmd that could map this - * hugepage, that will ensure no CPU can alter the - * mapcount on the head page. The mapcount is only - * accounted in the head page and it has to be - * transferred to all tail pages in the below code. So - * for this code to be safe, the split the mapcount - * can't change. But that doesn't mean userland can't - * keep changing and reading the page contents while - * we transfer the mapcount, so the pmd splitting - * status is achieved setting a reserved bit in the - * pmd, not by clearing the present bit. - */ - page_tail->_mapcount = page->_mapcount; - - BUG_ON(page_tail->mapping); - page_tail->mapping = page->mapping; - - page_tail->index = page->index + i; - page_cpupid_xchg_last(page_tail, page_cpupid_last(page)); - - BUG_ON(!PageAnon(page_tail)); - BUG_ON(!PageUptodate(page_tail)); - BUG_ON(!PageDirty(page_tail)); - BUG_ON(!PageSwapBacked(page_tail)); - - lru_add_page_tail(page, page_tail, lruvec, list); - } - atomic_sub(tail_count, &page->_count); - BUG_ON(atomic_read(&page->_count) <= 0); - - __mod_zone_page_state(zone, NR_ANON_TRANSPARENT_HUGEPAGES, -1); - - ClearPageCompound(page); - compound_unlock(page); - spin_unlock_irq(&zone->lru_lock); - - for (i = 1; i < HPAGE_PMD_NR; i++) { - struct page *page_tail = page + i; - BUG_ON(page_count(page_tail) <= 0); - /* - * Tail pages may be freed if there wasn't any mapping - * like if add_to_swap() is running on a lru page that - * had its mapping zapped. And freeing these pages - * requires taking the lru_lock so we do the put_page - * of the tail pages after the split is complete. - */ - put_page(page_tail); - } - - /* - * Only the head page (now become a regular page) is required - * to be pinned by the caller. - */ - BUG_ON(page_count(page) <= 0); -} - -static int __split_huge_page_map(struct page *page, - struct vm_area_struct *vma, - unsigned long address) -{ - struct mm_struct *mm = vma->vm_mm; - spinlock_t *ptl; - pmd_t *pmd, _pmd; - int ret = 0, i; - pgtable_t pgtable; - unsigned long haddr; - - pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl); - if (pmd) { - pgtable = pgtable_trans_huge_withdraw(mm, pmd); - pmd_populate(mm, &_pmd, pgtable); - if (pmd_write(*pmd)) - BUG_ON(page_mapcount(page) != 1); - - haddr = address; - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { - pte_t *pte, entry; - BUG_ON(PageCompound(page+i)); - /* - * Note that NUMA hinting access restrictions are not - * transferred to avoid any possibility of altering - * permissions across VMAs. - */ - entry = mk_pte(page + i, vma->vm_page_prot); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - if (!pmd_write(*pmd)) - entry = pte_wrprotect(entry); - if (!pmd_young(*pmd)) - entry = pte_mkold(entry); - pte = pte_offset_map(&_pmd, haddr); - BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); - pte_unmap(pte); - } - - smp_wmb(); /* make pte visible before pmd */ - /* - * Up to this point the pmd is present and huge and - * userland has the whole access to the hugepage - * during the split (which happens in place). If we - * overwrite the pmd with the not-huge version - * pointing to the pte here (which of course we could - * if all CPUs were bug free), userland could trigger - * a small page size TLB miss on the small sized TLB - * while the hugepage TLB entry is still established - * in the huge TLB. Some CPU doesn't like that. See - * http://support.amd.com/us/Processor_TechDocs/41322.pdf, - * Erratum 383 on page 93. Intel should be safe but is - * also warns that it's only safe if the permission - * and cache attributes of the two entries loaded in - * the two TLB is identical (which should be the case - * here). But it is generally safer to never allow - * small and huge TLB entries for the same virtual - * address to be loaded simultaneously. So instead of - * doing "pmd_populate(); flush_pmd_tlb_range();" we first - * mark the current pmd notpresent (atomically because - * here the pmd_trans_huge and pmd_trans_splitting - * must remain set at all times on the pmd until the - * split is complete for this pmd), then we flush the - * SMP TLB and finally we write the non-huge version - * of the pmd entry with pmd_populate. - */ - pmdp_invalidate(vma, address, pmd); - pmd_populate(mm, pmd, pgtable); - ret = 1; - spin_unlock(ptl); - } - - return ret; -} - -/* must be called with anon_vma->root->rwsem held */ -static void __split_huge_page(struct page *page, - struct anon_vma *anon_vma, - struct list_head *list) -{ - int mapcount, mapcount2; - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - struct anon_vma_chain *avc; - - BUG_ON(!PageHead(page)); - BUG_ON(PageTail(page)); - - mapcount = 0; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long addr = vma_address(page, vma); - BUG_ON(is_vma_temporary_stack(vma)); - mapcount += __split_huge_page_splitting(page, vma, addr); - } - /* - * It is critical that new vmas are added to the tail of the - * anon_vma list. This guarantes that if copy_huge_pmd() runs - * and establishes a child pmd before - * __split_huge_page_splitting() freezes the parent pmd (so if - * we fail to prevent copy_huge_pmd() from running until the - * whole __split_huge_page() is complete), we will still see - * the newly established pmd of the child later during the - * walk, to be able to set it as pmd_trans_splitting too. - */ - if (mapcount != page_mapcount(page)) { - pr_err("mapcount %d page_mapcount %d\n", - mapcount, page_mapcount(page)); - BUG(); - } - - __split_huge_page_refcount(page, list); - - mapcount2 = 0; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { - struct vm_area_struct *vma = avc->vma; - unsigned long addr = vma_address(page, vma); - BUG_ON(is_vma_temporary_stack(vma)); - mapcount2 += __split_huge_page_map(page, vma, addr); - } - if (mapcount != mapcount2) { - pr_err("mapcount %d mapcount2 %d page_mapcount %d\n", - mapcount, mapcount2, page_mapcount(page)); - BUG(); - } -} - -/* - * Split a hugepage into normal pages. This doesn't change the position of head - * page. If @list is null, tail pages will be added to LRU list, otherwise, to - * @list. Both head page and tail pages will inherit mapping, flags, and so on - * from the hugepage. - * Return 0 if the hugepage is split successfully otherwise return 1. - */ -int split_huge_page_to_list(struct page *page, struct list_head *list) -{ - struct anon_vma *anon_vma; - int ret = 1; - - BUG_ON(is_huge_zero_page(page)); - BUG_ON(!PageAnon(page)); - - /* - * The caller does not necessarily hold an mmap_sem that would prevent - * the anon_vma disappearing so we first we take a reference to it - * and then lock the anon_vma for write. This is similar to - * page_lock_anon_vma_read except the write lock is taken to serialise - * against parallel split or collapse operations. - */ - anon_vma = page_get_anon_vma(page); - if (!anon_vma) - goto out; - anon_vma_lock_write(anon_vma); - - ret = 0; - if (!PageCompound(page)) - goto out_unlock; - - BUG_ON(!PageSwapBacked(page)); - __split_huge_page(page, anon_vma, list); - count_vm_event(THP_SPLIT); - - BUG_ON(PageCompound(page)); -out_unlock: - anon_vma_unlock_write(anon_vma); - put_anon_vma(anon_vma); -out: - return ret; + return false; } #define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) @@ -2371,7 +2124,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, * superfluous. */ pte_clear(vma->vm_mm, address, _pte); - page_remove_rmap(src_page); + page_remove_rmap(src_page, false); spin_unlock(ptl); free_page_and_swap_cache(src_page); } @@ -2481,6 +2234,7 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, return NULL; } + prep_transhuge_page(*hpage); count_vm_event(THP_COLLAPSE_ALLOC); return *hpage; } @@ -2492,8 +2246,12 @@ static int khugepaged_find_target_node(void) static inline struct page *alloc_hugepage(int defrag) { - return alloc_pages(alloc_hugepage_gfpmask(defrag, 0), - HPAGE_PMD_ORDER); + struct page *page; + + page = alloc_pages(alloc_hugepage_gfpmask(defrag, 0), HPAGE_PMD_ORDER); + if (page) + prep_transhuge_page(page); + return page; } static struct page *khugepaged_alloc_hugepage(bool *wait) @@ -2543,7 +2301,6 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) || (vma->vm_flags & VM_NOHUGEPAGE)) return false; - if (!vma->anon_vma || vma->vm_ops) return false; if (is_vma_temporary_stack(vma)) @@ -2583,7 +2340,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -2682,8 +2439,8 @@ static void collapse_huge_page(struct mm_struct *mm, spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); - page_add_new_anon_rmap(new_page, vma, address); - mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, address, true); + mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_active_or_unevictable(new_page, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); @@ -2703,7 +2460,7 @@ out_nolock: trace_mm_collapse_huge_page(mm, isolated, result); return; out: - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, true); goto out_up_write; } @@ -2755,6 +2512,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, result = SCAN_PAGE_NULL; goto out_unmap; } + + /* TODO: teach khugepaged to collapse THP mapped with pte */ + if (PageCompound(page)) { + result = SCAN_PAGE_COMPOUND; + goto out_unmap; + } + /* * Record which node the original page is from and save this * information to khugepaged_node_load[]. @@ -2767,7 +2531,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, goto out_unmap; } khugepaged_node_load[node]++; - VM_BUG_ON_PAGE(PageCompound(page), page); if (!PageLRU(page)) { result = SCAN_SCAN_ABORT; goto out_unmap; @@ -3040,8 +2803,8 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pmd_t _pmd; int i; - pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* leave pmd empty until pte is filled */ + pmdp_huge_clear_flush_notify(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); @@ -3060,66 +2823,153 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, put_huge_zero_page(); } -void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmd) +static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long haddr, bool freeze) { - spinlock_t *ptl; - struct page *page = NULL; struct mm_struct *mm = vma->vm_mm; - unsigned long haddr = address & HPAGE_PMD_MASK; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ + struct page *page; + pgtable_t pgtable; + pmd_t _pmd; + bool young, write, dirty; + int i; - BUG_ON(vma->vm_start > haddr || vma->vm_end < haddr + HPAGE_PMD_SIZE); + VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); + VM_BUG_ON_VMA(vma->vm_start > haddr, vma); + VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); + VM_BUG_ON(!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)); + + count_vm_event(THP_SPLIT_PMD); - mmun_start = haddr; - mmun_end = haddr + HPAGE_PMD_SIZE; -again: - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_trans_huge(*pmd))) - goto unlock; if (vma_is_dax(vma)) { pmd_t _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); if (is_huge_zero_pmd(_pmd)) put_huge_zero_page(); + return; } else if (is_huge_zero_pmd(*pmd)) { - __split_huge_zero_page_pmd(vma, haddr, pmd); - } else { - page = pmd_page(*pmd); - VM_BUG_ON_PAGE(!page_count(page), page); - get_page(page); + return __split_huge_zero_page_pmd(vma, haddr, pmd); } - unlock: - spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (!page) - return; + page = pmd_page(*pmd); + VM_BUG_ON_PAGE(!page_count(page), page); + atomic_add(HPAGE_PMD_NR - 1, &page->_count); + write = pmd_write(*pmd); + young = pmd_young(*pmd); + dirty = pmd_dirty(*pmd); - split_huge_page(page); - put_page(page); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); + pmd_populate(mm, &_pmd, pgtable); + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + pte_t entry, *pte; + /* + * Note that NUMA hinting access restrictions are not + * transferred to avoid any possibility of altering + * permissions across VMAs. + */ + if (freeze) { + swp_entry_t swp_entry; + swp_entry = make_migration_entry(page + i, write); + entry = swp_entry_to_pte(swp_entry); + } else { + entry = mk_pte(page + i, vma->vm_page_prot); + entry = maybe_mkwrite(entry, vma); + if (!write) + entry = pte_wrprotect(entry); + if (!young) + entry = pte_mkold(entry); + } + if (dirty) + SetPageDirty(page + i); + pte = pte_offset_map(&_pmd, haddr); + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, haddr, pte, entry); + atomic_inc(&page[i]._mapcount); + pte_unmap(pte); + } + + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_inc(&page[i]._mapcount); + } + + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } + } + + smp_wmb(); /* make pte visible before pmd */ /* - * We don't always have down_write of mmap_sem here: a racing - * do_huge_pmd_wp_page() might have copied-on-write to another - * huge page before our split_huge_page() got the anon_vma lock. + * Up to this point the pmd is present and huge and userland has the + * whole access to the hugepage during the split (which happens in + * place). If we overwrite the pmd with the not-huge version pointing + * to the pte here (which of course we could if all CPUs were bug + * free), userland could trigger a small page size TLB miss on the + * small sized TLB while the hugepage TLB entry is still established in + * the huge TLB. Some CPU doesn't like that. + * See http://support.amd.com/us/Processor_TechDocs/41322.pdf, Erratum + * 383 on page 93. Intel should be safe but is also warns that it's + * only safe if the permission and cache attributes of the two entries + * loaded in the two TLB is identical (which should be the case here). + * But it is generally safer to never allow small and huge TLB entries + * for the same virtual address to be loaded simultaneously. So instead + * of doing "pmd_populate(); flush_pmd_tlb_range();" we first mark the + * current pmd notpresent (atomically because here the pmd_trans_huge + * and pmd_trans_splitting must remain set at all times on the pmd + * until the split is complete for this pmd), then we flush the SMP TLB + * and finally we write the non-huge version of the pmd entry with + * pmd_populate. */ - if (unlikely(pmd_trans_huge(*pmd))) - goto again; + pmdp_invalidate(vma, haddr, pmd); + pmd_populate(mm, pmd, pgtable); + + if (freeze) { + for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + page_remove_rmap(page + i, false); + put_page(page + i); + } + } } -void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, - pmd_t *pmd) +void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address) { - struct vm_area_struct *vma; + spinlock_t *ptl; + struct mm_struct *mm = vma->vm_mm; + struct page *page = NULL; + unsigned long haddr = address & HPAGE_PMD_MASK; - vma = find_vma(mm, address); - BUG_ON(vma == NULL); - split_huge_page_pmd(vma, address, pmd); + mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); + ptl = pmd_lock(mm, pmd); + if (pmd_trans_huge(*pmd)) { + page = pmd_page(*pmd); + if (PageMlocked(page)) + get_page(page); + else + page = NULL; + } else if (!pmd_devmap(*pmd)) + goto out; + __split_huge_pmd_locked(vma, pmd, haddr, false); +out: + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, haddr, haddr + HPAGE_PMD_SIZE); + if (page) { + lock_page(page); + munlock_vma_page(page); + unlock_page(page); + put_page(page); + } } -static void split_huge_page_address(struct mm_struct *mm, +static void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address) { pgd_t *pgd; @@ -3128,7 +2978,7 @@ static void split_huge_page_address(struct mm_struct *mm, VM_BUG_ON(!(address & ~HPAGE_PMD_MASK)); - pgd = pgd_offset(mm, address); + pgd = pgd_offset(vma->vm_mm, address); if (!pgd_present(*pgd)) return; @@ -3137,13 +2987,13 @@ static void split_huge_page_address(struct mm_struct *mm, return; pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) + if (!pmd_present(*pmd) || (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd))) return; /* * Caller holds the mmap_sem write mode, so a huge pmd cannot * materialize from under us. */ - split_huge_page_pmd_mm(mm, address, pmd); + split_huge_pmd(vma, pmd, address); } void vma_adjust_trans_huge(struct vm_area_struct *vma, @@ -3159,7 +3009,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, if (start & ~HPAGE_PMD_MASK && (start & HPAGE_PMD_MASK) >= vma->vm_start && (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) - split_huge_page_address(vma->vm_mm, start); + split_huge_pmd_address(vma, start); /* * If the new end address isn't hpage aligned and it could @@ -3169,7 +3019,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, if (end & ~HPAGE_PMD_MASK && (end & HPAGE_PMD_MASK) >= vma->vm_start && (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end) - split_huge_page_address(vma->vm_mm, end); + split_huge_pmd_address(vma, end); /* * If we're also updating the vma->vm_next->vm_start, if the new @@ -3183,6 +3033,540 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, if (nstart & ~HPAGE_PMD_MASK && (nstart & HPAGE_PMD_MASK) >= next->vm_start && (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end) - split_huge_page_address(next->vm_mm, nstart); + split_huge_pmd_address(next, nstart); + } +} + +static void freeze_page_vma(struct vm_area_struct *vma, struct page *page, + unsigned long address) +{ + unsigned long haddr = address & HPAGE_PMD_MASK; + spinlock_t *ptl; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i, nr = HPAGE_PMD_NR; + + /* Skip pages which doesn't belong to the VMA */ + if (address < vma->vm_start) { + int off = (vma->vm_start - address) >> PAGE_SHIFT; + page += off; + nr -= off; + address = vma->vm_start; + } + + pgd = pgd_offset(vma->vm_mm, address); + if (!pgd_present(*pgd)) + return; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return; + pmd = pmd_offset(pud, address); + ptl = pmd_lock(vma->vm_mm, pmd); + if (!pmd_present(*pmd)) { + spin_unlock(ptl); + return; + } + if (pmd_trans_huge(*pmd)) { + if (page == pmd_page(*pmd)) + __split_huge_pmd_locked(vma, pmd, haddr, true); + spin_unlock(ptl); + return; + } + spin_unlock(ptl); + + pte = pte_offset_map_lock(vma->vm_mm, pmd, address, &ptl); + for (i = 0; i < nr; i++, address += PAGE_SIZE, page++, pte++) { + pte_t entry, swp_pte; + swp_entry_t swp_entry; + + /* + * We've just crossed page table boundary: need to map next one. + * It can happen if THP was mremaped to non PMD-aligned address. + */ + if (unlikely(address == haddr + HPAGE_PMD_SIZE)) { + pte_unmap_unlock(pte - 1, ptl); + pmd = mm_find_pmd(vma->vm_mm, address); + if (!pmd) + return; + pte = pte_offset_map_lock(vma->vm_mm, pmd, + address, &ptl); + } + + if (!pte_present(*pte)) + continue; + if (page_to_pfn(page) != pte_pfn(*pte)) + continue; + flush_cache_page(vma, address, page_to_pfn(page)); + entry = ptep_clear_flush(vma, address, pte); + if (pte_dirty(entry)) + SetPageDirty(page); + swp_entry = make_migration_entry(page, pte_write(entry)); + swp_pte = swp_entry_to_pte(swp_entry); + if (pte_soft_dirty(entry)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + set_pte_at(vma->vm_mm, address, pte, swp_pte); + page_remove_rmap(page, false); + put_page(page); + } + pte_unmap_unlock(pte - 1, ptl); +} + +static void freeze_page(struct anon_vma *anon_vma, struct page *page) +{ + struct anon_vma_chain *avc; + pgoff_t pgoff = page_to_pgoff(page); + + VM_BUG_ON_PAGE(!PageHead(page), page); + + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, + pgoff + HPAGE_PMD_NR - 1) { + unsigned long address = __vma_address(page, avc->vma); + + mmu_notifier_invalidate_range_start(avc->vma->vm_mm, + address, address + HPAGE_PMD_SIZE); + freeze_page_vma(avc->vma, page, address); + mmu_notifier_invalidate_range_end(avc->vma->vm_mm, + address, address + HPAGE_PMD_SIZE); + } +} + +static void unfreeze_page_vma(struct vm_area_struct *vma, struct page *page, + unsigned long address) +{ + spinlock_t *ptl; + pmd_t *pmd; + pte_t *pte, entry; + swp_entry_t swp_entry; + unsigned long haddr = address & HPAGE_PMD_MASK; + int i, nr = HPAGE_PMD_NR; + + /* Skip pages which doesn't belong to the VMA */ + if (address < vma->vm_start) { + int off = (vma->vm_start - address) >> PAGE_SHIFT; + page += off; + nr -= off; + address = vma->vm_start; + } + + pmd = mm_find_pmd(vma->vm_mm, address); + if (!pmd) + return; + + pte = pte_offset_map_lock(vma->vm_mm, pmd, address, &ptl); + for (i = 0; i < nr; i++, address += PAGE_SIZE, page++, pte++) { + /* + * We've just crossed page table boundary: need to map next one. + * It can happen if THP was mremaped to non-PMD aligned address. + */ + if (unlikely(address == haddr + HPAGE_PMD_SIZE)) { + pte_unmap_unlock(pte - 1, ptl); + pmd = mm_find_pmd(vma->vm_mm, address); + if (!pmd) + return; + pte = pte_offset_map_lock(vma->vm_mm, pmd, + address, &ptl); + } + + if (!is_swap_pte(*pte)) + continue; + + swp_entry = pte_to_swp_entry(*pte); + if (!is_migration_entry(swp_entry)) + continue; + if (migration_entry_to_page(swp_entry) != page) + continue; + + get_page(page); + page_add_anon_rmap(page, vma, address, false); + + entry = pte_mkold(mk_pte(page, vma->vm_page_prot)); + if (PageDirty(page)) + entry = pte_mkdirty(entry); + if (is_write_migration_entry(swp_entry)) + entry = maybe_mkwrite(entry, vma); + + flush_dcache_page(page); + set_pte_at(vma->vm_mm, address, pte, entry); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, address, pte); + } + pte_unmap_unlock(pte - 1, ptl); +} + +static void unfreeze_page(struct anon_vma *anon_vma, struct page *page) +{ + struct anon_vma_chain *avc; + pgoff_t pgoff = page_to_pgoff(page); + + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, + pgoff, pgoff + HPAGE_PMD_NR - 1) { + unsigned long address = __vma_address(page, avc->vma); + + mmu_notifier_invalidate_range_start(avc->vma->vm_mm, + address, address + HPAGE_PMD_SIZE); + unfreeze_page_vma(avc->vma, page, address); + mmu_notifier_invalidate_range_end(avc->vma->vm_mm, + address, address + HPAGE_PMD_SIZE); + } +} + +static int __split_huge_page_tail(struct page *head, int tail, + struct lruvec *lruvec, struct list_head *list) +{ + int mapcount; + struct page *page_tail = head + tail; + + mapcount = atomic_read(&page_tail->_mapcount) + 1; + VM_BUG_ON_PAGE(atomic_read(&page_tail->_count) != 0, page_tail); + + /* + * tail_page->_count is zero and not changing from under us. But + * get_page_unless_zero() may be running from under us on the + * tail_page. If we used atomic_set() below instead of atomic_add(), we + * would then run atomic_set() concurrently with + * get_page_unless_zero(), and atomic_set() is implemented in C not + * using locked ops. spin_unlock on x86 sometime uses locked ops + * because of PPro errata 66, 92, so unless somebody can guarantee + * atomic_set() here would be safe on all archs (and not only on x86), + * it's safer to use atomic_add(). + */ + atomic_add(mapcount + 1, &page_tail->_count); + + + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + page_tail->flags |= (head->flags & + ((1L << PG_referenced) | + (1L << PG_swapbacked) | + (1L << PG_mlocked) | + (1L << PG_uptodate) | + (1L << PG_active) | + (1L << PG_locked) | + (1L << PG_unevictable) | + (1L << PG_dirty))); + + /* + * After clearing PageTail the gup refcount can be released. + * Page flags also must be visible before we make the page non-compound. + */ + smp_wmb(); + + clear_compound_head(page_tail); + + if (page_is_young(head)) + set_page_young(page_tail); + if (page_is_idle(head)) + set_page_idle(page_tail); + + /* ->mapping in first tail page is compound_mapcount */ + VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, + page_tail); + page_tail->mapping = head->mapping; + + page_tail->index = head->index + tail; + page_cpupid_xchg_last(page_tail, page_cpupid_last(head)); + lru_add_page_tail(head, page_tail, lruvec, list); + + return mapcount; +} + +static void __split_huge_page(struct page *page, struct list_head *list) +{ + struct page *head = compound_head(page); + struct zone *zone = page_zone(head); + struct lruvec *lruvec; + int i, tail_mapcount; + + /* prevent PageLRU to go away from under us, and freeze lru stats */ + spin_lock_irq(&zone->lru_lock); + lruvec = mem_cgroup_page_lruvec(head, zone); + + /* complete memcg works before add pages to LRU */ + mem_cgroup_split_huge_fixup(head); + + tail_mapcount = 0; + for (i = HPAGE_PMD_NR - 1; i >= 1; i--) + tail_mapcount += __split_huge_page_tail(head, i, lruvec, list); + atomic_sub(tail_mapcount, &head->_count); + + ClearPageCompound(head); + spin_unlock_irq(&zone->lru_lock); + + unfreeze_page(page_anon_vma(head), head); + + for (i = 0; i < HPAGE_PMD_NR; i++) { + struct page *subpage = head + i; + if (subpage == page) + continue; + unlock_page(subpage); + + /* + * Subpages may be freed if there wasn't any mapping + * like if add_to_swap() is running on a lru page that + * had its mapping zapped. And freeing these pages + * requires taking the lru_lock so we do the put_page + * of the tail pages after the split is complete. + */ + put_page(subpage); } } + +int total_mapcount(struct page *page) +{ + int i, ret; + + VM_BUG_ON_PAGE(PageTail(page), page); + + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) + 1; + + ret = compound_mapcount(page); + if (PageHuge(page)) + return ret; + for (i = 0; i < HPAGE_PMD_NR; i++) + ret += atomic_read(&page[i]._mapcount) + 1; + if (PageDoubleMap(page)) + ret -= HPAGE_PMD_NR; + return ret; +} + +/* + * This function splits huge page into normal pages. @page can point to any + * subpage of huge page to split. Split doesn't change the position of @page. + * + * Only caller must hold pin on the @page, otherwise split fails with -EBUSY. + * The huge page must be locked. + * + * If @list is null, tail pages will be added to LRU list, otherwise, to @list. + * + * Both head page and tail pages will inherit mapping, flags, and so on from + * the hugepage. + * + * GUP pin and PG_locked transferred to @page. Rest subpages can be freed if + * they are not mapped. + * + * Returns 0 if the hugepage is split successfully. + * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under + * us. + */ +int split_huge_page_to_list(struct page *page, struct list_head *list) +{ + struct page *head = compound_head(page); + struct anon_vma *anon_vma; + int count, mapcount, ret; + bool mlocked; + + VM_BUG_ON_PAGE(is_huge_zero_page(page), page); + VM_BUG_ON_PAGE(!PageAnon(page), page); + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageSwapBacked(page), page); + VM_BUG_ON_PAGE(!PageCompound(page), page); + + /* + * The caller does not necessarily hold an mmap_sem that would prevent + * the anon_vma disappearing so we first we take a reference to it + * and then lock the anon_vma for write. This is similar to + * page_lock_anon_vma_read except the write lock is taken to serialise + * against parallel split or collapse operations. + */ + anon_vma = page_get_anon_vma(head); + if (!anon_vma) { + ret = -EBUSY; + goto out; + } + anon_vma_lock_write(anon_vma); + + /* + * Racy check if we can split the page, before freeze_page() will + * split PMDs + */ + if (total_mapcount(head) != page_count(head) - 1) { + ret = -EBUSY; + goto out_unlock; + } + + mlocked = PageMlocked(page); + freeze_page(anon_vma, head); + VM_BUG_ON_PAGE(compound_mapcount(head), head); + + /* Make sure the page is not on per-CPU pagevec as it takes pin */ + if (mlocked) + lru_add_drain(); + + /* Prevent deferred_split_scan() touching ->_count */ + spin_lock(&split_queue_lock); + count = page_count(head); + mapcount = total_mapcount(head); + if (!mapcount && count == 1) { + if (!list_empty(page_deferred_list(head))) { + split_queue_len--; + list_del(page_deferred_list(head)); + } + spin_unlock(&split_queue_lock); + __split_huge_page(page, list); + ret = 0; + } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { + spin_unlock(&split_queue_lock); + pr_alert("total_mapcount: %u, page_count(): %u\n", + mapcount, count); + if (PageTail(page)) + dump_page(head, NULL); + dump_page(page, "total_mapcount(head) > 0"); + BUG(); + } else { + spin_unlock(&split_queue_lock); + unfreeze_page(anon_vma, head); + ret = -EBUSY; + } + +out_unlock: + anon_vma_unlock_write(anon_vma); + put_anon_vma(anon_vma); +out: + count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); + return ret; +} + +void free_transhuge_page(struct page *page) +{ + unsigned long flags; + + spin_lock_irqsave(&split_queue_lock, flags); + if (!list_empty(page_deferred_list(page))) { + split_queue_len--; + list_del(page_deferred_list(page)); + } + spin_unlock_irqrestore(&split_queue_lock, flags); + free_compound_page(page); +} + +void deferred_split_huge_page(struct page *page) +{ + unsigned long flags; + + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + + spin_lock_irqsave(&split_queue_lock, flags); + if (list_empty(page_deferred_list(page))) { + list_add_tail(page_deferred_list(page), &split_queue); + split_queue_len++; + } + spin_unlock_irqrestore(&split_queue_lock, flags); +} + +static unsigned long deferred_split_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + /* + * Split a page from split_queue will free up at least one page, + * at most HPAGE_PMD_NR - 1. We don't track exact number. + * Let's use HPAGE_PMD_NR / 2 as ballpark. + */ + return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2; +} + +static unsigned long deferred_split_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + unsigned long flags; + LIST_HEAD(list), *pos, *next; + struct page *page; + int split = 0; + + spin_lock_irqsave(&split_queue_lock, flags); + list_splice_init(&split_queue, &list); + + /* Take pin on all head pages to avoid freeing them under us */ + list_for_each_safe(pos, next, &list) { + page = list_entry((void *)pos, struct page, mapping); + page = compound_head(page); + /* race with put_compound_page() */ + if (!get_page_unless_zero(page)) { + list_del_init(page_deferred_list(page)); + split_queue_len--; + } + } + spin_unlock_irqrestore(&split_queue_lock, flags); + + list_for_each_safe(pos, next, &list) { + page = list_entry((void *)pos, struct page, mapping); + lock_page(page); + /* split_huge_page() removes page from list on success */ + if (!split_huge_page(page)) + split++; + unlock_page(page); + put_page(page); + } + + spin_lock_irqsave(&split_queue_lock, flags); + list_splice_tail(&list, &split_queue); + spin_unlock_irqrestore(&split_queue_lock, flags); + + return split * HPAGE_PMD_NR / 2; +} + +static struct shrinker deferred_split_shrinker = { + .count_objects = deferred_split_count, + .scan_objects = deferred_split_scan, + .seeks = DEFAULT_SEEKS, +}; + +#ifdef CONFIG_DEBUG_FS +static int split_huge_pages_set(void *data, u64 val) +{ + struct zone *zone; + struct page *page; + unsigned long pfn, max_zone_pfn; + unsigned long total = 0, split = 0; + + if (val != 1) + return -EINVAL; + + for_each_populated_zone(zone) { + max_zone_pfn = zone_end_pfn(zone); + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { + if (!pfn_valid(pfn)) + continue; + + page = pfn_to_page(pfn); + if (!get_page_unless_zero(page)) + continue; + + if (zone != page_zone(page)) + goto next; + + if (!PageHead(page) || !PageAnon(page) || + PageHuge(page)) + goto next; + + total++; + lock_page(page); + if (!split_huge_page(page)) + split++; + unlock_page(page); +next: + put_page(page); + } + } + + pr_info("%lu of %lu THP split", split, total); + + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set, + "%llu\n"); + +static int __init split_huge_pages_debugfs(void) +{ + void *ret; + + ret = debugfs_create_file("split_huge_pages", 0644, NULL, NULL, + &split_huge_pages_fops); + if (!ret) + pr_warn("Failed to create split_huge_pages in debugfs"); + return 0; +} +late_initcall(split_huge_pages_debugfs); +#endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index be934df69b85..12908dcf5831 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1267,8 +1267,8 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order) /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); - __SetPageHead(page); __ClearPageReserved(page); + __SetPageHead(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { /* * For gigantic hugepages allocated through bootmem at @@ -3102,7 +3102,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); - page_dup_rmap(ptepage); + page_dup_rmap(ptepage, true); set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(pages_per_huge_page(h), dst); } @@ -3186,7 +3186,7 @@ again: set_page_dirty(page); hugetlb_count_sub(pages_per_huge_page(h), mm); - page_remove_rmap(page); + page_remove_rmap(page, true); force_flush = !__tlb_remove_page(tlb, page); if (force_flush) { address += sz; @@ -3415,7 +3415,7 @@ retry_avoidcopy: mmu_notifier_invalidate_range(mm, mmun_start, mmun_end); set_huge_pte_at(mm, address, ptep, make_huge_pte(vma, new_page, 1)); - page_remove_rmap(old_page); + page_remove_rmap(old_page, true); hugepage_add_new_anon_rmap(new_page, vma, address); /* Make the old page be freed below */ new_page = old_page; @@ -3585,7 +3585,7 @@ retry: ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, address); } else - page_dup_rmap(page); + page_dup_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, address, ptep, new_pte); @@ -3865,7 +3865,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); - get_page_foll(pages[i]); + get_page(pages[i]); } if (vmas) diff --git a/mm/internal.h b/mm/internal.h index 38e24b89e4c4..ed8b5ffcf9b1 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -13,6 +13,7 @@ #include <linux/fs.h> #include <linux/mm.h> +#include <linux/pagemap.h> /* * The set of flags that only affect watermark checking and reclaim @@ -66,50 +67,6 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } -static inline void __get_page_tail_foll(struct page *page, - bool get_page_head) -{ - /* - * If we're getting a tail page, the elevated page->_count is - * required only in the head page and we will elevate the head - * page->_count and tail page->_mapcount. - * - * We elevate page_tail->_mapcount for tail pages to force - * page_tail->_count to be zero at all times to avoid getting - * false positives from get_page_unless_zero() with - * speculative page access (like in - * page_cache_get_speculative()) on tail pages. - */ - VM_BUG_ON_PAGE(atomic_read(&compound_head(page)->_count) <= 0, page); - if (get_page_head) - atomic_inc(&compound_head(page)->_count); - get_huge_page_tail(page); -} - -/* - * This is meant to be called as the FOLL_GET operation of - * follow_page() and it must be called while holding the proper PT - * lock while the pte (or pmd_trans_huge) is still mapping the page. - */ -static inline void get_page_foll(struct page *page) -{ - if (unlikely(PageTail(page))) - /* - * This is safe only because - * __split_huge_page_refcount() can't run under - * get_page_foll() because we hold the proper PT lock. - */ - __get_page_tail_foll(page, true); - else { - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_count. - */ - VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page); - atomic_inc(&page->_count); - } -} - extern unsigned long highest_memmap_pfn; /* @@ -309,10 +266,27 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -extern unsigned long vma_address(struct page *page, - struct vm_area_struct *vma); -#endif +/* + * At what user virtual address is page expected in @vma? + */ +static inline unsigned long +__vma_address(struct page *page, struct vm_area_struct *vma) +{ + pgoff_t pgoff = page_to_pgoff(page); + return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); +} + +static inline unsigned long +vma_address(struct page *page, struct vm_area_struct *vma) +{ + unsigned long address = __vma_address(page, vma); + + /* page should be within @vma mapping range */ + VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); + + return address; +} + #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } diff --git a/mm/ksm.c b/mm/ksm.c index 2d162c5625f6..ca6d2a06a615 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -441,20 +441,6 @@ static void break_cow(struct rmap_item *rmap_item) up_read(&mm->mmap_sem); } -static struct page *page_trans_compound_anon(struct page *page) -{ - if (PageTransCompound(page)) { - struct page *head = compound_head(page); - /* - * head may actually be splitted and freed from under - * us but it's ok here. - */ - if (PageAnon(head)) - return head; - } - return NULL; -} - static struct page *get_mergeable_page(struct rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; @@ -470,7 +456,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) page = follow_page(vma, addr, FOLL_GET); if (IS_ERR_OR_NULL(page)) goto out; - if (PageAnon(page) || page_trans_compound_anon(page)) { + if (PageAnon(page)) { flush_anon_page(vma, page, addr); flush_dcache_page(page); } else { @@ -956,13 +942,13 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, } get_page(kpage); - page_add_anon_rmap(kpage, vma, addr); + page_add_anon_rmap(kpage, vma, addr, false); flush_cache_page(vma, addr, pte_pfn(*ptep)); ptep_clear_flush_notify(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); - page_remove_rmap(page); + page_remove_rmap(page, false); if (!page_mapped(page)) try_to_free_swap(page); put_page(page); @@ -975,33 +961,6 @@ out: return err; } -static int page_trans_compound_anon_split(struct page *page) -{ - int ret = 0; - struct page *transhuge_head = page_trans_compound_anon(page); - if (transhuge_head) { - /* Get the reference on the head to split it. */ - if (get_page_unless_zero(transhuge_head)) { - /* - * Recheck we got the reference while the head - * was still anonymous. - */ - if (PageAnon(transhuge_head)) - ret = split_huge_page(transhuge_head); - else - /* - * Retry later if split_huge_page run - * from under us. - */ - ret = 1; - put_page(transhuge_head); - } else - /* Retry later if split_huge_page run from under us. */ - ret = 1; - } - return ret; -} - /* * try_to_merge_one_page - take two pages and merge them into one * @vma: the vma that holds the pte pointing to page @@ -1020,9 +979,6 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, if (page == kpage) /* ksm page forked */ return 0; - if (PageTransCompound(page) && page_trans_compound_anon_split(page)) - goto out; - BUG_ON(PageTransCompound(page)); if (!PageAnon(page)) goto out; @@ -1035,6 +991,13 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, */ if (!trylock_page(page)) goto out; + + if (PageTransCompound(page)) { + err = split_huge_page(page); + if (err) + goto out_unlock; + } + /* * If this anonymous page is mapped only here, its pte may need * to be write-protected. If it's mapped elsewhere, all of its @@ -1050,6 +1013,12 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, */ set_page_stable_node(page, NULL); mark_page_accessed(page); + /* + * Page reclaim just frees a clean page with no dirty + * ptes: make sure that the ksm page would be swapped. + */ + if (!PageDirty(page)) + SetPageDirty(page); err = 0; } else if (pages_identical(page, kpage)) err = replace_page(vma, page, kpage, orig_pte); @@ -1065,6 +1034,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, } } +out_unlock: unlock_page(page); out: return err; @@ -1635,8 +1605,7 @@ next_mm: cond_resched(); continue; } - if (PageAnon(*page) || - page_trans_compound_anon(*page)) { + if (PageAnon(*page)) { flush_anon_page(vma, *page, ksm_scan.address); flush_dcache_page(*page); rmap_item = get_next_rmap_item(slot, @@ -1899,7 +1868,7 @@ struct page *ksm_might_need_to_copy(struct page *page, SetPageDirty(new_page); __SetPageUptodate(new_page); - __set_page_locked(new_page); + __SetPageLocked(new_page); } return new_page; diff --git a/mm/madvise.c b/mm/madvise.c index c889fcbb530e..f56825b6d2e1 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -20,6 +20,9 @@ #include <linux/backing-dev.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/mmu_notifier.h> + +#include <asm/tlb.h> /* * Any behaviour which results in changes to the vma->vm_flags needs to @@ -32,6 +35,7 @@ static int madvise_need_mmap_write(int behavior) case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: + case MADV_FREE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ @@ -256,6 +260,194 @@ static long madvise_willneed(struct vm_area_struct *vma, return 0; } +static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) + +{ + struct mmu_gather *tlb = walk->private; + struct mm_struct *mm = tlb->mm; + struct vm_area_struct *vma = walk->vma; + spinlock_t *ptl; + pte_t *orig_pte, *pte, ptent; + struct page *page; + int nr_swap = 0; + unsigned long next; + + next = pmd_addr_end(addr, end); + if (pmd_trans_huge(*pmd)) + if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) + goto next; + + if (pmd_trans_unstable(pmd)) + return 0; + + orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); + for (; addr != end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + + if (pte_none(ptent)) + continue; + /* + * If the pte has swp_entry, just clear page table to + * prevent swap-in which is more expensive rather than + * (page allocation + zeroing). + */ + if (!pte_present(ptent)) { + swp_entry_t entry; + + entry = pte_to_swp_entry(ptent); + if (non_swap_entry(entry)) + continue; + nr_swap--; + free_swap_and_cache(entry); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + continue; + } + + page = vm_normal_page(vma, addr, ptent); + if (!page) + continue; + + /* + * If pmd isn't transhuge but the page is THP and + * is owned by only this process, split it and + * deactivate all pages. + */ + if (PageTransCompound(page)) { + if (page_mapcount(page) != 1) + goto out; + get_page(page); + if (!trylock_page(page)) { + put_page(page); + goto out; + } + pte_unmap_unlock(orig_pte, ptl); + if (split_huge_page(page)) { + unlock_page(page); + put_page(page); + pte_offset_map_lock(mm, pmd, addr, &ptl); + goto out; + } + put_page(page); + unlock_page(page); + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + pte--; + addr -= PAGE_SIZE; + continue; + } + + VM_BUG_ON_PAGE(PageTransCompound(page), page); + + if (PageSwapCache(page) || PageDirty(page)) { + if (!trylock_page(page)) + continue; + /* + * If page is shared with others, we couldn't clear + * PG_dirty of the page. + */ + if (page_mapcount(page) != 1) { + unlock_page(page); + continue; + } + + if (PageSwapCache(page) && !try_to_free_swap(page)) { + unlock_page(page); + continue; + } + + ClearPageDirty(page); + unlock_page(page); + } + + if (pte_young(ptent) || pte_dirty(ptent)) { + /* + * Some of architecture(ex, PPC) don't update TLB + * with set_pte_at and tlb_remove_tlb_entry so for + * the portability, remap the pte with old|clean + * after pte clearing. + */ + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + + ptent = pte_mkold(ptent); + ptent = pte_mkclean(ptent); + set_pte_at(mm, addr, pte, ptent); + if (PageActive(page)) + deactivate_page(page); + tlb_remove_tlb_entry(tlb, pte, addr); + } + } +out: + if (nr_swap) { + if (current->mm == mm) + sync_mm_rss(mm); + + add_mm_counter(mm, MM_SWAPENTS, nr_swap); + } + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(orig_pte, ptl); + cond_resched(); +next: + return 0; +} + +static void madvise_free_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + struct mm_walk free_walk = { + .pmd_entry = madvise_free_pte_range, + .mm = vma->vm_mm, + .private = tlb, + }; + + tlb_start_vma(tlb, vma); + walk_page_range(addr, end, &free_walk); + tlb_end_vma(tlb, vma); +} + +static int madvise_free_single_vma(struct vm_area_struct *vma, + unsigned long start_addr, unsigned long end_addr) +{ + unsigned long start, end; + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + + if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) + return -EINVAL; + + /* MADV_FREE works for only anon vma at the moment */ + if (!vma_is_anonymous(vma)) + return -EINVAL; + + start = max(vma->vm_start, start_addr); + if (start >= vma->vm_end) + return -EINVAL; + end = min(vma->vm_end, end_addr); + if (end <= vma->vm_start) + return -EINVAL; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, start, end); + update_hiwater_rss(mm); + + mmu_notifier_invalidate_range_start(mm, start, end); + madvise_free_page_range(&tlb, vma, start, end); + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_finish_mmu(&tlb, start, end); + + return 0; +} + +static long madvise_free(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end) +{ + *prev = vma; + return madvise_free_single_vma(vma, start, end); +} + /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about @@ -379,6 +571,14 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, return madvise_remove(vma, prev, start, end); case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); + case MADV_FREE: + /* + * XXX: In this implementation, MADV_FREE works like + * MADV_DONTNEED on swapless system or full swap. + */ + if (get_nr_swap_pages() > 0) + return madvise_free(vma, prev, start, end); + /* passthrough */ case MADV_DONTNEED: return madvise_dontneed(vma, prev, start, end); default: @@ -398,6 +598,7 @@ madvise_behavior_valid(int behavior) case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: + case MADV_FREE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 54eae4f19d80..0eda67376df4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -382,14 +382,11 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) { struct mem_cgroup *memcg; - rcu_read_lock(); - memcg = page->mem_cgroup; if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) memcg = root_mem_cgroup; - rcu_read_unlock(); return &memcg->css; } @@ -647,7 +644,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, struct page *page, - int nr_pages) + bool compound, int nr_pages) { /* * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is @@ -660,9 +657,11 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); - if (PageTransHuge(page)) + if (compound) { + VM_BUG_ON_PAGE(!PageTransHuge(page), page); __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_pages); + } /* pagein of a big page is an event. So, ignore page size */ if (nr_pages > 0) @@ -2431,9 +2430,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) /* * Because tail pages are not marked as "used", set it. We're under - * zone->lru_lock, 'splitting on pmd' and compound_lock. - * charge/uncharge will be never happen and move_account() is done under - * compound_lock(), so we don't have to take care of races. + * zone->lru_lock and migration entries setup in all page mappings. */ void mem_cgroup_split_huge_fixup(struct page *head) { @@ -3494,16 +3491,17 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg, swap_buffers: /* Swap primary and spare array */ thresholds->spare = thresholds->primary; - /* If all events are unregistered, free the spare array */ - if (!new) { - kfree(thresholds->spare); - thresholds->spare = NULL; - } rcu_assign_pointer(thresholds->primary, new); /* To be sure that nobody uses thresholds */ synchronize_rcu(); + + /* If all events are unregistered, free the spare array */ + if (!new) { + kfree(thresholds->spare); + thresholds->spare = NULL; + } unlock: mutex_unlock(&memcg->thresholds_lock); } @@ -4505,38 +4503,30 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, * @from: mem_cgroup which the page is moved from. * @to: mem_cgroup which the page is moved to. @from != @to. * - * The caller must confirm following. - * - page is not on LRU (isolate_page() is useful.) - * - compound_lock is held when nr_pages > 1 + * The caller must make sure the page is not on LRU (isolate_page() is useful.) * * This function doesn't do "charge" to new cgroup and doesn't do "uncharge" * from old cgroup. */ static int mem_cgroup_move_account(struct page *page, - unsigned int nr_pages, + bool compound, struct mem_cgroup *from, struct mem_cgroup *to) { unsigned long flags; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; bool anon; VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); - /* - * The page is isolated from LRU. So, collapse function - * will not handle this page. But page splitting can happen. - * Do this check under compound_page_lock(). The caller should - * hold it. - */ - ret = -EBUSY; - if (nr_pages > 1 && !PageTransHuge(page)) - goto out; + VM_BUG_ON(compound && !PageTransHuge(page)); /* * Prevent mem_cgroup_replace_page() from looking at * page->mem_cgroup of its source page while we change it. */ + ret = -EBUSY; if (!trylock_page(page)) goto out; @@ -4591,9 +4581,9 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; local_irq_disable(); - mem_cgroup_charge_statistics(to, page, nr_pages); + mem_cgroup_charge_statistics(to, page, compound, nr_pages); memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, -nr_pages); + mem_cgroup_charge_statistics(from, page, compound, -nr_pages); memcg_check_events(from, page); local_irq_enable(); out_unlock: @@ -4683,7 +4673,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) mc.precharge += HPAGE_PMD_NR; spin_unlock(ptl); @@ -4871,17 +4861,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, union mc_target target; struct page *page; - /* - * We don't take compound_lock() here but no race with splitting thp - * happens because: - * - if pmd_trans_huge_lock() returns 1, the relevant thp is not - * under splitting, which means there's no concurrent thp split, - * - if another thread runs into split_huge_page() just after we - * entered this if-block, the thread must wait for page table lock - * to be unlocked in __split_huge_page_splitting(), where the main - * part of thp split is not executed yet. - */ - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { if (mc.precharge < HPAGE_PMD_NR) { spin_unlock(ptl); return 0; @@ -4890,7 +4870,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, if (target_type == MC_TARGET_PAGE) { page = target.page; if (!isolate_lru_page(page)) { - if (!mem_cgroup_move_account(page, HPAGE_PMD_NR, + if (!mem_cgroup_move_account(page, true, mc.from, mc.to)) { mc.precharge -= HPAGE_PMD_NR; mc.moved_charge += HPAGE_PMD_NR; @@ -4917,9 +4897,18 @@ retry: switch (get_mctgt_type(vma, addr, ptent, &target)) { case MC_TARGET_PAGE: page = target.page; + /* + * We can have a part of the split pmd here. Moving it + * can be done but it would be too convoluted so simply + * ignore such a partial THP and keep it in original + * memcg. There should be somebody mapping the head. + */ + if (PageTransCompound(page)) + goto put; if (isolate_lru_page(page)) goto put; - if (!mem_cgroup_move_account(page, 1, mc.from, mc.to)) { + if (!mem_cgroup_move_account(page, false, + mc.from, mc.to)) { mc.precharge--; /* we uncharge from mc.from later. */ mc.moved_charge++; @@ -5258,10 +5247,11 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) * with mem_cgroup_cancel_charge() in case page instantiation fails. */ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask, struct mem_cgroup **memcgp) + gfp_t gfp_mask, struct mem_cgroup **memcgp, + bool compound) { struct mem_cgroup *memcg = NULL; - unsigned int nr_pages = 1; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret = 0; if (mem_cgroup_disabled()) @@ -5291,11 +5281,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, } } - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - if (!memcg) memcg = get_mem_cgroup_from_mm(mm); @@ -5324,9 +5309,9 @@ out: * Use mem_cgroup_cancel_charge() to cancel the transaction instead. */ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, - bool lrucare) + bool lrucare, bool compound) { - unsigned int nr_pages = 1; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; VM_BUG_ON_PAGE(!page->mapping, page); VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page); @@ -5343,13 +5328,8 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, commit_charge(page, memcg, lrucare); - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, nr_pages); + mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); memcg_check_events(memcg, page); local_irq_enable(); @@ -5371,9 +5351,10 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, * * Cancel a charge transaction started by mem_cgroup_try_charge(). */ -void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) +void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, + bool compound) { - unsigned int nr_pages = 1; + unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; if (mem_cgroup_disabled()) return; @@ -5385,11 +5366,6 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg) if (!memcg) return; - if (PageTransHuge(page)) { - nr_pages <<= compound_order(page); - VM_BUG_ON_PAGE(!PageTransHuge(page), page); - } - cancel_charge(memcg, nr_pages); } @@ -5750,7 +5726,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for udpating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, -1); + mem_cgroup_charge_statistics(memcg, page, false, -1); memcg_check_events(memcg, page); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8424b64711ac..ac595e7a3a95 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -882,15 +882,7 @@ int get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); - if (PageHuge(head)) - return get_page_unless_zero(head); - - /* - * Thp tail page has special refcounting rule (refcount of tail pages - * is stored in ->_mapcount,) so we can't call get_page_unless_zero() - * directly for tail pages. - */ - if (PageTransHuge(head)) { + if (!PageHuge(head) && PageTransHuge(head)) { /* * Non anonymous thp exists only in allocation/free time. We * can't handle such a case correctly, so let's give it up. @@ -902,41 +894,12 @@ int get_hwpoison_page(struct page *page) page_to_pfn(page)); return 0; } - - if (get_page_unless_zero(head)) { - if (PageTail(page)) - get_page(page); - return 1; - } else { - return 0; - } } - return get_page_unless_zero(page); + return get_page_unless_zero(head); } EXPORT_SYMBOL_GPL(get_hwpoison_page); -/** - * put_hwpoison_page() - Put refcount for memory error handling: - * @page: raw error page (hit by memory error) - */ -void put_hwpoison_page(struct page *page) -{ - struct page *head = compound_head(page); - - if (PageHuge(head)) { - put_page(head); - return; - } - - if (PageTransHuge(head)) - if (page != head) - put_page(head); - - put_page(page); -} -EXPORT_SYMBOL_GPL(put_hwpoison_page); - /* * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. @@ -1149,7 +1112,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (!PageHuge(p) && PageTransHuge(hpage)) { + lock_page(hpage); if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { + unlock_page(hpage); if (!PageAnon(hpage)) pr_err("MCE: %#lx: non anonymous thp\n", pfn); else @@ -1159,6 +1124,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) put_hwpoison_page(p); return -EBUSY; } + unlock_page(hpage); + get_hwpoison_page(p); + put_hwpoison_page(hpage); VM_BUG_ON_PAGE(!page_count(p), p); hpage = compound_head(p); } @@ -1166,7 +1134,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) /* * We ignore non-LRU pages for good reasons. * - PG_locked is only well defined for LRU pages and a few others - * - to avoid races with __set_page_locked() + * - to avoid races with __SetPageLocked() * - to avoid races with __SetPageSlab*() (and more non-atomic ops) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. @@ -1572,7 +1540,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) * Did it turn free? */ ret = __get_any_page(page, pfn, 0); - if (!PageLRU(page)) { + if (ret == 1 && !PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ put_hwpoison_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", @@ -1716,6 +1684,49 @@ static int __soft_offline_page(struct page *page, int flags) return ret; } +static int soft_offline_in_use_page(struct page *page, int flags) +{ + int ret; + struct page *hpage = compound_head(page); + + if (!PageHuge(page) && PageTransHuge(hpage)) { + lock_page(hpage); + if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { + unlock_page(hpage); + if (!PageAnon(hpage)) + pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page)); + else + pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page)); + put_hwpoison_page(hpage); + return -EBUSY; + } + unlock_page(hpage); + get_hwpoison_page(page); + put_hwpoison_page(hpage); + } + + if (PageHuge(page)) + ret = soft_offline_huge_page(page, flags); + else + ret = __soft_offline_page(page, flags); + + return ret; +} + +static void soft_offline_free_page(struct page *page) +{ + if (PageHuge(page)) { + struct page *hpage = compound_head(page); + + set_page_hwpoison_huge_page(hpage); + if (!dequeue_hwpoisoned_huge_page(hpage)) + num_poisoned_pages_add(1 << compound_order(hpage)); + } else { + if (!TestSetPageHWPoison(page)) + num_poisoned_pages_inc(); + } +} + /** * soft_offline_page - Soft offline a page. * @page: page to offline @@ -1742,7 +1753,6 @@ int soft_offline_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_head(page); if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); @@ -1750,34 +1760,15 @@ int soft_offline_page(struct page *page, int flags) put_hwpoison_page(page); return -EBUSY; } - if (!PageHuge(page) && PageTransHuge(hpage)) { - if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { - pr_info("soft offline: %#lx: failed to split THP\n", - pfn); - if (flags & MF_COUNT_INCREASED) - put_hwpoison_page(page); - return -EBUSY; - } - } get_online_mems(); - ret = get_any_page(page, pfn, flags); put_online_mems(); - if (ret > 0) { /* for in-use pages */ - if (PageHuge(page)) - ret = soft_offline_huge_page(page, flags); - else - ret = __soft_offline_page(page, flags); - } else if (ret == 0) { /* for free pages */ - if (PageHuge(page)) { - set_page_hwpoison_huge_page(hpage); - if (!dequeue_hwpoisoned_huge_page(hpage)) - num_poisoned_pages_add(1 << compound_order(hpage)); - } else { - if (!TestSetPageHWPoison(page)) - num_poisoned_pages_inc(); - } - } + + if (ret > 0) + ret = soft_offline_in_use_page(page, flags); + else if (ret == 0) + soft_offline_free_page(page); + return ret; } diff --git a/mm/memory.c b/mm/memory.c index d4e4d37c1989..ff17850a52d9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -50,6 +50,7 @@ #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> +#include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> @@ -566,7 +567,6 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm, address); - int wait_split_huge_page; if (!new) return -ENOMEM; @@ -586,18 +586,14 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); - wait_split_huge_page = 0; if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ atomic_long_inc(&mm->nr_ptes); pmd_populate(mm, pmd, new); new = NULL; - } else if (unlikely(pmd_trans_splitting(*pmd))) - wait_split_huge_page = 1; + } spin_unlock(ptl); if (new) pte_free(mm, new); - if (wait_split_huge_page) - wait_split_huge_page(vma->anon_vma, pmd); return 0; } @@ -613,8 +609,7 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; - } else - VM_BUG_ON(pmd_trans_splitting(*pmd)); + } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); @@ -870,7 +865,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, page = vm_normal_page(vma, addr, pte); if (page) { get_page(page); - page_dup_rmap(page); + page_dup_rmap(page, false); rss[mm_counter(page)]++; } @@ -955,7 +950,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*src_pmd)) { + if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON(next-addr != HPAGE_PMD_SIZE); err = copy_huge_pmd(dst_mm, src_mm, @@ -1118,7 +1113,7 @@ again: mark_page_accessed(page); } rss[mm_counter(page)]--; - page_remove_rmap(page); + page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(!__tlb_remove_page(tlb, page))) { @@ -1182,7 +1177,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*pmd)) { + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { #ifdef CONFIG_DEBUG_VM if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { @@ -1193,7 +1188,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, BUG(); } #endif - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ @@ -1506,7 +1501,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, EXPORT_SYMBOL(vm_insert_page); static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t prot) + pfn_t pfn, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; @@ -1522,7 +1517,10 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, goto out_unlock; /* Ok, finally just insert the thing.. */ - entry = pte_mkspecial(pfn_pte(pfn, prot)); + if (pfn_t_devmap(pfn)) + entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); + else + entry = pte_mkspecial(pfn_t_pte(pfn, prot)); set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ @@ -1569,17 +1567,17 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; - if (track_pfn_insert(vma, &pgprot, pfn)) + if (track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV))) return -EINVAL; - ret = insert_pfn(vma, addr, pfn, pgprot); + ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot); return ret; } EXPORT_SYMBOL(vm_insert_pfn); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) + pfn_t pfn) { BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); @@ -1593,10 +1591,10 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ - if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) { struct page *page; - page = pfn_to_page(pfn); + page = pfn_t_to_page(pfn); return insert_page(vma, addr, page, vma->vm_page_prot); } return insert_pfn(vma, addr, pfn, vma->vm_page_prot); @@ -2087,7 +2085,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, cow_user_page(new_page, old_page, address, vma); } - if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) goto oom_free_new; __SetPageUptodate(new_page); @@ -2118,8 +2116,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, * thread doing COW. */ ptep_clear_flush_notify(vma, address, page_table); - page_add_new_anon_rmap(new_page, vma, address); - mem_cgroup_commit_charge(new_page, memcg, false); + page_add_new_anon_rmap(new_page, vma, address, false); + mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary @@ -2151,14 +2149,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ - page_remove_rmap(old_page); + page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, false); } if (new_page) @@ -2173,7 +2171,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma, */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ - munlock_vma_page(old_page); + if (PageMlocked(old_page)) + munlock_vma_page(old_page); unlock_page(old_page); } page_cache_release(old_page); @@ -2533,7 +2532,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out_page; } - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) { ret = VM_FAULT_OOM; goto out_page; } @@ -2567,7 +2566,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, pte = maybe_mkwrite(pte_mkdirty(pte), vma); flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; - exclusive = 1; + exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(orig_pte)) @@ -2575,10 +2574,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, set_pte_at(mm, address, page_table, pte); if (page == swapcache) { do_page_add_anon_rmap(page, vma, address, exclusive); - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, address); - mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, address, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } @@ -2613,7 +2612,7 @@ unlock: out: return ret; out_nomap: - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); pte_unmap_unlock(page_table, ptl); out_page: unlock_page(page); @@ -2707,7 +2706,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!page) goto oom; - if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) goto oom_free_page; /* @@ -2728,15 +2727,15 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(page_table, ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); page_cache_release(page); return handle_userfault(vma, address, flags, VM_UFFD_MISSING); } inc_mm_counter_fast(mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address); - mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, address, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); setpte: set_pte_at(mm, address, page_table, entry); @@ -2747,7 +2746,7 @@ unlock: pte_unmap_unlock(page_table, ptl); return 0; release: - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); page_cache_release(page); goto unlock; oom_free_page: @@ -2824,7 +2823,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, vma, address); + page_add_new_anon_rmap(page, vma, address, false); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page); @@ -3000,7 +2999,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (!new_page) return VM_FAULT_OOM; - if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) { page_cache_release(new_page); return VM_FAULT_OOM; } @@ -3029,7 +3028,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, goto uncharge_out; } do_set_pte(vma, address, new_page, pte, true, true); - mem_cgroup_commit_charge(new_page, memcg, false); + mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); pte_unmap_unlock(pte, ptl); if (fault_page) { @@ -3044,7 +3043,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } return ret; uncharge_out: - mem_cgroup_cancel_charge(new_page, memcg); + mem_cgroup_cancel_charge(new_page, memcg, false); page_cache_release(new_page); return ret; } @@ -3096,7 +3095,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ - mapping = fault_page->mapping; + mapping = page_rmapping(fault_page); unlock_page(fault_page); if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) { /* @@ -3198,6 +3197,12 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, return 0; } + /* TODO: handle PTE-mapped THP */ + if (PageCompound(page)) { + pte_unmap_unlock(ptep, ptl); + return 0; + } + /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses @@ -3370,17 +3375,9 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, int ret; barrier(); - if (pmd_trans_huge(orig_pmd)) { + if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { unsigned int dirty = flags & FAULT_FLAG_WRITE; - /* - * If the pmd is splitting, return and retry the - * the fault. Alternative: wait until the split - * is done, and goto retry. - */ - if (pmd_trans_splitting(orig_pmd)) - return 0; - if (pmd_protnone(orig_pmd)) return do_huge_pmd_numa_page(mm, vma, address, orig_pmd, pmd); @@ -3407,7 +3404,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd))) + if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) return 0; /* * A regular pmd is established and it can't morph into a huge pmd diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 92f95952692b..4af58a3a8ffa 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -17,6 +17,7 @@ #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/memory.h> +#include <linux/memremap.h> #include <linux/memory_hotplug.h> #include <linux/highmem.h> #include <linux/vmalloc.h> @@ -506,10 +507,25 @@ int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, unsigned long i; int err = 0; int start_sec, end_sec; + struct vmem_altmap *altmap; + /* during initialize mem_map, align hot-added range to section */ start_sec = pfn_to_section_nr(phys_start_pfn); end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); + altmap = to_vmem_altmap((unsigned long) pfn_to_page(phys_start_pfn)); + if (altmap) { + /* + * Validate altmap is within bounds of the total request + */ + if (altmap->base_pfn != phys_start_pfn + || vmem_altmap_offset(altmap) > nr_pages) { + pr_warn_once("memory add fail, invalid altmap\n"); + return -EINVAL; + } + altmap->alloc = 0; + } + for (i = start_sec; i <= end_sec; i++) { err = __add_section(nid, zone, section_nr_to_pfn(i)); @@ -731,7 +747,8 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn) pgdat_resize_unlock(zone->zone_pgdat, &flags); } -static int __remove_section(struct zone *zone, struct mem_section *ms) +static int __remove_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset) { unsigned long start_pfn; int scn_nr; @@ -748,7 +765,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) start_pfn = section_nr_to_pfn(scn_nr); __remove_zone(zone, start_pfn); - sparse_remove_one_section(zone, ms); + sparse_remove_one_section(zone, ms, map_offset); return 0; } @@ -767,9 +784,32 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { unsigned long i; - int sections_to_remove; - resource_size_t start, size; - int ret = 0; + unsigned long map_offset = 0; + int sections_to_remove, ret = 0; + + /* In the ZONE_DEVICE case device driver owns the memory region */ + if (is_dev_zone(zone)) { + struct page *page = pfn_to_page(phys_start_pfn); + struct vmem_altmap *altmap; + + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + map_offset = vmem_altmap_offset(altmap); + } else { + resource_size_t start, size; + + start = phys_start_pfn << PAGE_SHIFT; + size = nr_pages * PAGE_SIZE; + + ret = release_mem_region_adjustable(&iomem_resource, start, + size); + if (ret) { + resource_size_t endres = start + size - 1; + + pr_warn("Unable to release resource <%pa-%pa> (%d)\n", + &start, &endres, ret); + } + } /* * We can only remove entire sections @@ -777,23 +817,12 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK); BUG_ON(nr_pages % PAGES_PER_SECTION); - start = phys_start_pfn << PAGE_SHIFT; - size = nr_pages * PAGE_SIZE; - - /* in the ZONE_DEVICE case device driver owns the memory region */ - if (!is_dev_zone(zone)) - ret = release_mem_region_adjustable(&iomem_resource, start, size); - if (ret) { - resource_size_t endres = start + size - 1; - - pr_warn("Unable to release resource <%pa-%pa> (%d)\n", - &start, &endres, ret); - } - sections_to_remove = nr_pages / PAGES_PER_SECTION; for (i = 0; i < sections_to_remove; i++) { unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION; - ret = __remove_section(zone, __pfn_to_section(pfn)); + + ret = __remove_section(zone, __pfn_to_section(pfn), map_offset); + map_offset = 0; if (ret) break; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d8caff071a30..27d135408a22 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -489,14 +489,33 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, struct page *page; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; - int nid; + int nid, ret; pte_t *pte; spinlock_t *ptl; - split_huge_page_pmd(vma, addr, pmd); - if (pmd_trans_unstable(pmd)) - return 0; + if (pmd_trans_huge(*pmd)) { + ptl = pmd_lock(walk->mm, pmd); + if (pmd_trans_huge(*pmd)) { + page = pmd_page(*pmd); + if (is_huge_zero_page(page)) { + spin_unlock(ptl); + split_huge_pmd(vma, pmd, addr); + } else { + get_page(page); + spin_unlock(ptl); + lock_page(page); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + if (ret) + return 0; + } + } else { + spin_unlock(ptl); + } + } +retry: pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) @@ -513,6 +532,21 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, nid = page_to_nid(page); if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT)) continue; + if (PageTail(page) && PageAnon(page)) { + get_page(page); + pte_unmap_unlock(pte, ptl); + lock_page(page); + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + /* Failed to split -- skip. */ + if (ret) { + pte = pte_offset_map_lock(walk->mm, pmd, + addr, &ptl); + continue; + } + goto retry; + } if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) migrate_page_add(page, qp->pagelist, flags); @@ -610,7 +644,8 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, if (flags & MPOL_MF_LAZY) { /* Similar to task_numa_work, skip inaccessible VMAs */ - if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) + if (vma_migratable(vma) && + vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) change_prot_numa(vma, start, endvma); return 1; } diff --git a/mm/migrate.c b/mm/migrate.c index 7890d0bb5e23..b1034f9c77e7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -165,9 +165,9 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, if (PageAnon(new)) hugepage_add_anon_rmap(new, vma, addr); else - page_dup_rmap(new); + page_dup_rmap(new, true); } else if (PageAnon(new)) - page_add_anon_rmap(new, vma, addr); + page_add_anon_rmap(new, vma, addr, false); else page_add_file_rmap(new); @@ -943,9 +943,13 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page, goto out; } - if (unlikely(PageTransHuge(page))) - if (unlikely(split_huge_page(page))) + if (unlikely(PageTransHuge(page))) { + lock_page(page); + rc = split_huge_page(page); + unlock_page(page); + if (rc) goto out; + } rc = __unmap_and_move(page, newpage, force, mode); if (rc == MIGRATEPAGE_SUCCESS) @@ -1756,6 +1760,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, HPAGE_PMD_ORDER); if (!new_page) goto out_fail; + prep_transhuge_page(new_page); isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) { @@ -1767,7 +1772,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, flush_tlb_range(vma, mmun_start, mmun_end); /* Prepare a page as a migration target */ - __set_page_locked(new_page); + __SetPageLocked(new_page); SetPageSwapBacked(new_page); /* anon mapping, we can simply copy page->mapping to the new page: */ @@ -1815,7 +1820,7 @@ fail_putback: * guarantee the copy is visible before the pagetable update. */ flush_cache_range(vma, mmun_start, mmun_end); - page_add_anon_rmap(new_page, vma, mmun_start); + page_add_anon_rmap(new_page, vma, mmun_start, true); pmdp_huge_clear_flush_notify(vma, mmun_start, pmd); set_pmd_at(mm, mmun_start, pmd, entry); flush_tlb_range(vma, mmun_start, mmun_end); @@ -1826,14 +1831,14 @@ fail_putback: flush_tlb_range(vma, mmun_start, mmun_end); mmu_notifier_invalidate_range(mm, mmun_start, mmun_end); update_mmu_cache_pmd(vma, address, &entry); - page_remove_rmap(new_page); + page_remove_rmap(new_page, true); goto fail_putback; } mlock_migrate_page(new_page, page); set_page_memcg(new_page, page_memcg(page)); set_page_memcg(page, NULL); - page_remove_rmap(page); + page_remove_rmap(page, true); spin_unlock(ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); diff --git a/mm/mincore.c b/mm/mincore.c index 14bb9fb37f0c..2a565ed8bb49 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -117,7 +117,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec = walk->private; int nr = (end - addr) >> PAGE_SHIFT; - if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + if (pmd_trans_huge_lock(pmd, vma, &ptl)) { memset(vec, 1, nr); spin_unlock(ptl); goto out; diff --git a/mm/mlock.c b/mm/mlock.c index 9cb87cbc4071..e1e2b1207bf2 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -24,13 +24,13 @@ #include "internal.h" -int can_do_mlock(void) +bool can_do_mlock(void) { if (rlimit(RLIMIT_MEMLOCK) != 0) - return 1; + return true; if (capable(CAP_IPC_LOCK)) - return 1; - return 0; + return true; + return false; } EXPORT_SYMBOL(can_do_mlock); @@ -82,6 +82,9 @@ void mlock_vma_page(struct page *page) /* Serialize with page migration */ BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(PageTail(page), page); + VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); + if (!TestSetPageMlocked(page)) { mod_zone_page_state(page_zone(page), NR_MLOCK, hpage_nr_pages(page)); @@ -178,6 +181,8 @@ unsigned int munlock_vma_page(struct page *page) /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); + VM_BUG_ON_PAGE(PageTail(page), page); + /* * Serialize with any parallel __split_huge_page_refcount() which * might otherwise copy PageMlocked to part of the tail pages before @@ -388,6 +393,13 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, if (!page || page_zone_id(page) != zoneid) break; + /* + * Do not use pagevec for PTE-mapped THP, + * munlock_vma_pages_range() will handle them. + */ + if (PageTransCompound(page)) + break; + get_page(page); /* * Increase the address that will be returned *before* the @@ -444,7 +456,10 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, &page_mask); if (page && !IS_ERR(page)) { - if (PageTransHuge(page)) { + if (PageTransTail(page)) { + VM_BUG_ON_PAGE(PageMlocked(page), page); + put_page(page); /* follow_page_mask() */ + } else if (PageTransHuge(page)) { lock_page(page); /* * Any THP page found by follow_page_mask() may @@ -477,8 +492,6 @@ void munlock_vma_pages_range(struct vm_area_struct *vma, goto next; } } - /* It's a bug to munlock in the middle of a THP page */ - VM_BUG_ON((start >> PAGE_SHIFT) & page_mask); page_increm = 1 + page_mask; start += page_increm * PAGE_SIZE; next: diff --git a/mm/mmap.c b/mm/mmap.c index b3f00b616b81..84b12624ceb0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3184,10 +3184,16 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * - * We can take all the locks in random order because the VM code - * taking i_mmap_rwsem or anon_vma->rwsem outside the mmap_sem never - * takes more than one of them in a row. Secondly we're protected - * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. + * We take locks in following order, accordingly to comment at beginning + * of mm/rmap.c: + * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for + * hugetlb mapping); + * - all i_mmap_rwsem locks; + * - all anon_vma->rwseml + * + * We can take all locks within these types randomly because the VM code + * doesn't nest them and we protected from parallel mm_take_all_locks() by + * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. @@ -3206,7 +3212,16 @@ int mm_take_all_locks(struct mm_struct *mm) for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; - if (vma->vm_file && vma->vm_file->f_mapping) + if (vma->vm_file && vma->vm_file->f_mapping && + is_vm_hugetlb_page(vma)) + vm_lock_mapping(mm, vma->vm_file->f_mapping); + } + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (signal_pending(current)) + goto out_unlock; + if (vma->vm_file && vma->vm_file->f_mapping && + !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } diff --git a/mm/mprotect.c b/mm/mprotect.c index c764402c464f..8eb7bb40dc40 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -149,7 +149,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, unsigned long this_pages; next = pmd_addr_end(addr, end); - if (!pmd_trans_huge(*pmd) && pmd_none_or_clear_bad(pmd)) + if (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd) + && pmd_none_or_clear_bad(pmd)) continue; /* invoke the mmu notifier if the pmd is populated */ @@ -158,9 +159,9 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(mm, mni_start, end); } - if (pmd_trans_huge(*pmd)) { + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) - split_huge_page_pmd(vma, addr, pmd); + split_huge_pmd(vma, pmd, addr); else { int nr_ptes = change_huge_pmd(vma, pmd, addr, newprot, prot_numa); diff --git a/mm/mremap.c b/mm/mremap.c index e55b157865d5..d77946a997f7 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -192,25 +192,24 @@ unsigned long move_page_tables(struct vm_area_struct *vma, if (!new_pmd) break; if (pmd_trans_huge(*old_pmd)) { - int err = 0; if (extent == HPAGE_PMD_SIZE) { + bool moved; VM_BUG_ON_VMA(vma->vm_file || !vma->anon_vma, vma); /* See comment in move_ptes() */ if (need_rmap_locks) anon_vma_lock_write(vma->anon_vma); - err = move_huge_pmd(vma, new_vma, old_addr, + moved = move_huge_pmd(vma, new_vma, old_addr, new_addr, old_end, old_pmd, new_pmd); if (need_rmap_locks) anon_vma_unlock_write(vma->anon_vma); + if (moved) { + need_flush = true; + continue; + } } - if (err > 0) { - need_flush = true; - continue; - } else if (!err) { - split_huge_page_pmd(vma, old_addr, old_pmd); - } + split_huge_pmd(vma, old_pmd, old_addr); VM_BUG_ON(pmd_trans_huge(*old_pmd)); } if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ce63d603820f..63358d9f9aa9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -43,6 +43,7 @@ #include <linux/vmalloc.h> #include <linux/vmstat.h> #include <linux/mempolicy.h> +#include <linux/memremap.h> #include <linux/stop_machine.h> #include <linux/sort.h> #include <linux/pfn.h> @@ -222,13 +223,15 @@ static char * const zone_names[MAX_NR_ZONES] = { #endif }; -static void free_compound_page(struct page *page); compound_page_dtor * const compound_page_dtors[] = { NULL, free_compound_page, #ifdef CONFIG_HUGETLB_PAGE free_huge_page, #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + free_transhuge_page, +#endif }; int min_free_kbytes = 1024; @@ -450,7 +453,7 @@ out: * This usage means that zero-order pages may not be compound. */ -static void free_compound_page(struct page *page) +void free_compound_page(struct page *page) { __free_pages_ok(page, compound_order(page)); } @@ -466,8 +469,10 @@ void prep_compound_page(struct page *page, unsigned int order) for (i = 1; i < nr_pages; i++) { struct page *p = page + i; set_page_count(p, 0); + p->mapping = TAIL_MAPPING; set_compound_head(p, page); } + atomic_set(compound_mapcount_ptr(page), -1); } #ifdef CONFIG_DEBUG_PAGEALLOC @@ -732,7 +737,7 @@ static inline int free_pages_check(struct page *page) const char *bad_reason = NULL; unsigned long bad_flags = 0; - if (unlikely(page_mapcount(page))) + if (unlikely(atomic_read(&page->_mapcount) != -1)) bad_reason = "nonzero mapcount"; if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; @@ -856,6 +861,27 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) ret = 0; goto out; } + switch (page - head_page) { + case 1: + /* the first tail page: ->mapping is compound_mapcount() */ + if (unlikely(compound_mapcount(page))) { + bad_page(page, "nonzero compound_mapcount", 0); + goto out; + } + break; + case 2: + /* + * the second tail page: ->mapping is + * page_deferred_list().next -- ignore value. + */ + break; + default: + if (page->mapping != TAIL_MAPPING) { + bad_page(page, "corrupted mapping in tail page", 0); + goto out; + } + break; + } if (unlikely(!PageTail(page))) { bad_page(page, "PageTail not set", 0); goto out; @@ -866,6 +892,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page) } ret = 0; out: + page->mapping = NULL; clear_compound_head(page); return ret; } @@ -1329,7 +1356,7 @@ static inline int check_new_page(struct page *page) const char *bad_reason = NULL; unsigned long bad_flags = 0; - if (unlikely(page_mapcount(page))) + if (unlikely(atomic_read(&page->_mapcount) != -1)) bad_reason = "nonzero mapcount"; if (unlikely(page->mapping != NULL)) bad_reason = "non-NULL mapping"; @@ -4459,16 +4486,22 @@ static inline unsigned long wait_table_bits(unsigned long size) void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context) { - pg_data_t *pgdat = NODE_DATA(nid); + struct vmem_altmap *altmap = to_vmem_altmap(__pfn_to_phys(start_pfn)); unsigned long end_pfn = start_pfn + size; + pg_data_t *pgdat = NODE_DATA(nid); unsigned long pfn; - struct zone *z; unsigned long nr_initialised = 0; if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; - z = &pgdat->node_zones[zone]; + /* + * Honor reservation requested by the driver for this ZONE_DEVICE + * memory + */ + if (altmap && start_pfn == altmap->base_pfn) + start_pfn += altmap->reserve; + for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* * There can be holes in boot-time mem_map[]s diff --git a/mm/page_idle.c b/mm/page_idle.c index d5dd79041484..4ea9c4ef5146 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -55,25 +55,26 @@ static int page_idle_clear_pte_refs_one(struct page *page, unsigned long addr, void *arg) { struct mm_struct *mm = vma->vm_mm; - spinlock_t *ptl; pmd_t *pmd; pte_t *pte; + spinlock_t *ptl; bool referenced = false; - if (unlikely(PageTransHuge(page))) { - pmd = page_check_address_pmd(page, mm, addr, - PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); - if (pmd) { - referenced = pmdp_clear_young_notify(vma, addr, pmd); - spin_unlock(ptl); - } + if (!page_check_address_transhuge(page, mm, addr, &pmd, &pte, &ptl)) + return SWAP_AGAIN; + + if (pte) { + referenced = ptep_clear_young_notify(vma, addr, pte); + pte_unmap(pte); + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + referenced = pmdp_clear_young_notify(vma, addr, pmd); } else { - pte = page_check_address(page, mm, addr, &ptl, 0); - if (pte) { - referenced = ptep_clear_young_notify(vma, addr, pte); - pte_unmap_unlock(pte, ptl); - } + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); } + + spin_unlock(ptl); + if (referenced) { clear_page_idle(page); /* diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 5e139fec6c6c..92c4c36501e7 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -196,8 +196,10 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, { unsigned long pfn; struct page *page; - BUG_ON((start_pfn) & (pageblock_nr_pages - 1)); - BUG_ON((end_pfn) & (pageblock_nr_pages - 1)); + + BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages)); + BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages)); + for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 29f2f8b853ae..207244489a68 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -58,7 +58,7 @@ again: if (!walk->pte_entry) continue; - split_huge_page_pmd_mm(walk->mm, addr, pmd); + split_huge_pmd(walk->vma, pmd, addr); if (pmd_trans_unstable(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4c681baff363..9d4767698a1c 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -132,25 +132,13 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON(!pmd_trans_huge(*pmdp)); + VM_BUG_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif -#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH -void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, - pmd_t *pmdp) -{ - pmd_t pmd = pmd_mksplitting(*pmdp); - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - set_pmd_at(vma->vm_mm, address, pmdp, pmd); - /* tlb flush only to serialize against gup-fast */ - flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); -} -#endif - #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable) diff --git a/mm/rmap.c b/mm/rmap.c index 622756c16ac8..79f3bf047f38 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -23,21 +23,22 @@ * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_sem * page->flags PG_locked (lock_page) - * mapping->i_mmap_rwsem - * anon_vma->rwsem - * mm->page_table_lock or pte_lock - * zone->lru_lock (in mark_page_accessed, isolate_lru_page) - * swap_lock (in swap_duplicate, swap_info_get) - * mmlist_lock (in mmput, drain_mmlist and others) - * mapping->private_lock (in __set_page_dirty_buffers) - * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) - * mapping->tree_lock (widely used) - * inode->i_lock (in set_page_dirty's __mark_inode_dirty) - * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) - * sb_lock (within inode_lock in fs/fs-writeback.c) - * mapping->tree_lock (widely used, in set_page_dirty, - * in arch-dependent flush_dcache_mmap_lock, - * within bdi.wb->list_lock in __sync_single_inode) + * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) + * mapping->i_mmap_rwsem + * anon_vma->rwsem + * mm->page_table_lock or pte_lock + * zone->lru_lock (in mark_page_accessed, isolate_lru_page) + * swap_lock (in swap_duplicate, swap_info_get) + * mmlist_lock (in mmput, drain_mmlist and others) + * mapping->private_lock (in __set_page_dirty_buffers) + * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) + * mapping->tree_lock (widely used) + * inode->i_lock (in set_page_dirty's __mark_inode_dirty) + * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within inode_lock in fs/fs-writeback.c) + * mapping->tree_lock (widely used, in set_page_dirty, + * in arch-dependent flush_dcache_mmap_lock, + * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) * ->tasklist_lock @@ -567,27 +568,6 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma) anon_vma_unlock_read(anon_vma); } -/* - * At what user virtual address is page expected in @vma? - */ -static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) -{ - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); -} - -inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) -{ - unsigned long address = __vma_address(page, vma); - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); - - return address; -} - #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH static void percpu_flush_tlb_batch_pages(void *data) { @@ -819,6 +799,96 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) return 1; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * Check that @page is mapped at @address into @mm. In contrast to + * page_check_address(), this function can handle transparent huge pages. + * + * On success returns true with pte mapped and locked. For PMD-mapped + * transparent huge pages *@ptep is set to NULL. + */ +bool page_check_address_transhuge(struct page *page, struct mm_struct *mm, + unsigned long address, pmd_t **pmdp, + pte_t **ptep, spinlock_t **ptlp) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + spinlock_t *ptl; + + if (unlikely(PageHuge(page))) { + /* when pud is not present, pte will be NULL */ + pte = huge_pte_offset(mm, address); + if (!pte) + return false; + + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); + pmd = NULL; + goto check_pte; + } + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return false; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return false; + pmd = pmd_offset(pud, address); + + if (pmd_trans_huge(*pmd)) { + ptl = pmd_lock(mm, pmd); + if (!pmd_present(*pmd)) + goto unlock_pmd; + if (unlikely(!pmd_trans_huge(*pmd))) { + spin_unlock(ptl); + goto map_pte; + } + + if (pmd_page(*pmd) != page) + goto unlock_pmd; + + pte = NULL; + goto found; +unlock_pmd: + spin_unlock(ptl); + return false; + } else { + pmd_t pmde = *pmd; + + barrier(); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) + return false; + } +map_pte: + pte = pte_offset_map(pmd, address); + if (!pte_present(*pte)) { + pte_unmap(pte); + return false; + } + + ptl = pte_lockptr(mm, pmd); +check_pte: + spin_lock(ptl); + + if (!pte_present(*pte)) { + pte_unmap_unlock(pte, ptl); + return false; + } + + /* THP can be referenced by any subpage */ + if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) { + pte_unmap_unlock(pte, ptl); + return false; + } +found: + *ptep = pte; + *pmdp = pmd; + *ptlp = ptl; + return true; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + struct page_referenced_arg { int mapcount; int referenced; @@ -832,49 +902,24 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; + struct page_referenced_arg *pra = arg; + pmd_t *pmd; + pte_t *pte; spinlock_t *ptl; int referenced = 0; - struct page_referenced_arg *pra = arg; - - if (unlikely(PageTransHuge(page))) { - pmd_t *pmd; - /* - * rmap might return false positives; we must filter - * these out using page_check_address_pmd(). - */ - pmd = page_check_address_pmd(page, mm, address, - PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl); - if (!pmd) - return SWAP_AGAIN; - - if (vma->vm_flags & VM_LOCKED) { - spin_unlock(ptl); - pra->vm_flags |= VM_LOCKED; - return SWAP_FAIL; /* To break the loop */ - } + if (!page_check_address_transhuge(page, mm, address, &pmd, &pte, &ptl)) + return SWAP_AGAIN; - /* go ahead even if the pmd is pmd_trans_splitting() */ - if (pmdp_clear_flush_young_notify(vma, address, pmd)) - referenced++; + if (vma->vm_flags & VM_LOCKED) { + if (pte) + pte_unmap(pte); spin_unlock(ptl); - } else { - pte_t *pte; - - /* - * rmap might return false positives; we must filter - * these out using page_check_address(). - */ - pte = page_check_address(page, mm, address, &ptl, 0); - if (!pte) - return SWAP_AGAIN; - - if (vma->vm_flags & VM_LOCKED) { - pte_unmap_unlock(pte, ptl); - pra->vm_flags |= VM_LOCKED; - return SWAP_FAIL; /* To break the loop */ - } + pra->vm_flags |= VM_LOCKED; + return SWAP_FAIL; /* To break the loop */ + } + if (pte) { if (ptep_clear_flush_young_notify(vma, address, pte)) { /* * Don't treat a reference through a sequentially read @@ -886,8 +931,15 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma, if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } - pte_unmap_unlock(pte, ptl); + pte_unmap(pte); + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { + if (pmdp_clear_flush_young_notify(vma, address, pmd)) + referenced++; + } else { + /* unexpected pmd-mapped page? */ + WARN_ON_ONCE(1); } + spin_unlock(ptl); if (referenced) clear_page_idle(page); @@ -935,7 +987,7 @@ int page_referenced(struct page *page, int ret; int we_locked = 0; struct page_referenced_arg pra = { - .mapcount = page_mapcount(page), + .mapcount = total_mapcount(page), .memcg = memcg, }; struct rmap_walk_control rwc = { @@ -1124,7 +1176,7 @@ static void __page_check_anon_rmap(struct page *page, * over the call to page_add_new_anon_rmap. */ BUG_ON(page_anon_vma(page)->root != vma->anon_vma->root); - BUG_ON(page->index != linear_page_index(vma, address)); + BUG_ON(page_to_pgoff(page) != linear_page_index(vma, address)); #endif } @@ -1133,6 +1185,7 @@ static void __page_check_anon_rmap(struct page *page, * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped + * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, @@ -1140,9 +1193,9 @@ static void __page_check_anon_rmap(struct page *page, * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long address, bool compound) { - do_page_add_anon_rmap(page, vma, address, 0); + do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); } /* @@ -1151,29 +1204,44 @@ void page_add_anon_rmap(struct page *page, * Everybody else should continue to use page_add_anon_rmap above. */ void do_page_add_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address, int exclusive) + struct vm_area_struct *vma, unsigned long address, int flags) { - int first = atomic_inc_and_test(&page->_mapcount); + bool compound = flags & RMAP_COMPOUND; + bool first; + + if (compound) { + atomic_t *mapcount; + VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + mapcount = compound_mapcount_ptr(page); + first = atomic_inc_and_test(mapcount); + } else { + first = atomic_inc_and_test(&page->_mapcount); + } + if (first) { + int nr = compound ? hpage_nr_pages(page) : 1; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption * disabled. */ - if (PageTransHuge(page)) + if (compound) { __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); - __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, - hpage_nr_pages(page)); + } + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr); } if (unlikely(PageKsm(page))) return; VM_BUG_ON_PAGE(!PageLocked(page), page); + /* address might be in next vma when migration races vma_adjust */ if (first) - __page_set_anon_rmap(page, vma, address, exclusive); + __page_set_anon_rmap(page, vma, address, + flags & RMAP_EXCLUSIVE); else __page_check_anon_rmap(page, vma, address); } @@ -1183,21 +1251,31 @@ void do_page_add_anon_rmap(struct page *page, * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped + * @compound: charge the page as compound or small page * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, - struct vm_area_struct *vma, unsigned long address) + struct vm_area_struct *vma, unsigned long address, bool compound) { + int nr = compound ? hpage_nr_pages(page) : 1; + VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); SetPageSwapBacked(page); - atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */ - if (PageTransHuge(page)) + if (compound) { + VM_BUG_ON_PAGE(!PageTransHuge(page), page); + /* increment count (starts at -1) */ + atomic_set(compound_mapcount_ptr(page), 0); __inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); - __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, - hpage_nr_pages(page)); + } else { + /* Anon THP always mapped first with PMD */ + VM_BUG_ON_PAGE(PageTransCompound(page), page); + /* increment count (starts at -1) */ + atomic_set(&page->_mapcount, 0); + } + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, nr); __page_set_anon_rmap(page, vma, address, 1); } @@ -1225,12 +1303,15 @@ static void page_remove_file_rmap(struct page *page) memcg = mem_cgroup_begin_page_stat(page); - /* page still mapped by someone else? */ - if (!atomic_add_negative(-1, &page->_mapcount)) + /* Hugepages are not counted in NR_FILE_MAPPED for now. */ + if (unlikely(PageHuge(page))) { + /* hugetlb pages are always mapped with pmds */ + atomic_dec(compound_mapcount_ptr(page)); goto out; + } - /* Hugepages are not counted in NR_FILE_MAPPED for now. */ - if (unlikely(PageHuge(page))) + /* page still mapped by someone else? */ + if (!atomic_add_negative(-1, &page->_mapcount)) goto out; /* @@ -1247,41 +1328,79 @@ out: mem_cgroup_end_page_stat(memcg); } +static void page_remove_anon_compound_rmap(struct page *page) +{ + int i, nr; + + if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) + return; + + /* Hugepages are not counted in NR_ANON_PAGES for now. */ + if (unlikely(PageHuge(page))) + return; + + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + return; + + __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); + + if (TestClearPageDoubleMap(page)) { + /* + * Subpages can be mapped with PTEs too. Check how many of + * themi are still mapped. + */ + for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) { + if (atomic_add_negative(-1, &page[i]._mapcount)) + nr++; + } + } else { + nr = HPAGE_PMD_NR; + } + + if (unlikely(PageMlocked(page))) + clear_page_mlock(page); + + if (nr) { + __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, -nr); + deferred_split_huge_page(page); + } +} + /** * page_remove_rmap - take down pte mapping from a page - * @page: page to remove mapping from + * @page: page to remove mapping from + * @compound: uncharge the page as compound or small page * * The caller needs to hold the pte lock. */ -void page_remove_rmap(struct page *page) +void page_remove_rmap(struct page *page, bool compound) { if (!PageAnon(page)) { + VM_BUG_ON_PAGE(compound && !PageHuge(page), page); page_remove_file_rmap(page); return; } + if (compound) + return page_remove_anon_compound_rmap(page); + /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) return; - /* Hugepages are not counted in NR_ANON_PAGES for now. */ - if (unlikely(PageHuge(page))) - return; - /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ - if (PageTransHuge(page)) - __dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES); - - __mod_zone_page_state(page_zone(page), NR_ANON_PAGES, - -hpage_nr_pages(page)); + __dec_zone_page_state(page, NR_ANON_PAGES); if (unlikely(PageMlocked(page))) clear_page_mlock(page); + if (PageTransCompound(page)) + deferred_split_huge_page(compound_head(page)); + /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap @@ -1293,6 +1412,11 @@ void page_remove_rmap(struct page *page) */ } +struct rmap_private { + enum ttu_flags flags; + int lazyfreed; +}; + /* * @arg: enum ttu_flags will be passed to this argument */ @@ -1304,7 +1428,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, pte_t pteval; spinlock_t *ptl; int ret = SWAP_AGAIN; - enum ttu_flags flags = (enum ttu_flags)arg; + struct rmap_private *rp = arg; + enum ttu_flags flags = rp->flags; /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) @@ -1396,6 +1521,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * See handle_pte_fault() ... */ VM_BUG_ON_PAGE(!PageSwapCache(page), page); + + if (!PageDirty(page) && (flags & TTU_LZFREE)) { + /* It's a freeable page by MADV_FREE */ + dec_mm_counter(mm, MM_ANONPAGES); + rp->lazyfreed++; + goto discard; + } + if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pte, pteval); ret = SWAP_FAIL; @@ -1416,7 +1549,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } else dec_mm_counter(mm, mm_counter_file(page)); - page_remove_rmap(page); +discard: + page_remove_rmap(page, PageHuge(page)); page_cache_release(page); out_unmap: @@ -1468,9 +1602,14 @@ static int page_not_mapped(struct page *page) int try_to_unmap(struct page *page, enum ttu_flags flags) { int ret; + struct rmap_private rp = { + .flags = flags, + .lazyfreed = 0, + }; + struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, - .arg = (void *)flags, + .arg = &rp, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; @@ -1490,8 +1629,11 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) ret = rmap_walk(page, &rwc); - if (ret != SWAP_MLOCK && !page_mapped(page)) + if (ret != SWAP_MLOCK && !page_mapped(page)) { ret = SWAP_SUCCESS; + if (rp.lazyfreed && !PageDirty(page)) + ret = SWAP_LZFREE; + } return ret; } @@ -1513,9 +1655,14 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) int try_to_munlock(struct page *page) { int ret; + struct rmap_private rp = { + .flags = TTU_MUNLOCK, + .lazyfreed = 0, + }; + struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, - .arg = (void *)TTU_MUNLOCK, + .arg = &rp, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, @@ -1698,7 +1845,7 @@ void hugepage_add_anon_rmap(struct page *page, BUG_ON(!PageLocked(page)); BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ - first = atomic_inc_and_test(&page->_mapcount); + first = atomic_inc_and_test(compound_mapcount_ptr(page)); if (first) __hugepage_set_anon_rmap(page, vma, address, 0); } @@ -1707,7 +1854,7 @@ void hugepage_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { BUG_ON(address < vma->vm_start || address >= vma->vm_end); - atomic_set(&page->_mapcount, 0); + atomic_set(compound_mapcount_ptr(page), 0); __hugepage_set_anon_rmap(page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/mm/shmem.c b/mm/shmem.c index 970ff5b80853..b98e1011858c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -810,7 +810,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg); + error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg, + false); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ @@ -833,9 +834,9 @@ int shmem_unuse(swp_entry_t swap, struct page *page) if (error) { if (error != -ENOMEM) error = 0; - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); } else - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); out: unlock_page(page); page_cache_release(page); @@ -1085,7 +1086,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, copy_highpage(newpage, oldpage); flush_dcache_page(newpage); - __set_page_locked(newpage); + __SetPageLocked(newpage); SetPageUptodate(newpage); SetPageSwapBacked(newpage); set_page_private(newpage, swap_index); @@ -1218,7 +1219,8 @@ repeat: goto failed; } - error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg); + error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg, + false); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap)); @@ -1235,14 +1237,14 @@ repeat: * "repeat": reading a hole and writing should succeed. */ if (error) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); delete_from_swap_cache(page); } } if (error) goto failed; - mem_cgroup_commit_charge(page, memcg, true); + mem_cgroup_commit_charge(page, memcg, true, false); spin_lock(&info->lock); info->swapped--; @@ -1277,11 +1279,12 @@ repeat: } __SetPageSwapBacked(page); - __set_page_locked(page); + __SetPageLocked(page); if (sgp == SGP_WRITE) __SetPageReferenced(page); - error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg); + error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg, + false); if (error) goto decused; error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); @@ -1291,10 +1294,10 @@ repeat: radix_tree_preload_end(); } if (error) { - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); goto decused; } - mem_cgroup_commit_charge(page, memcg, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_anon(page); spin_lock(&info->lock); diff --git a/mm/slub.c b/mm/slub.c index 2d0e610d195a..b21fd24b08b1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -338,11 +338,13 @@ static inline int oo_objects(struct kmem_cache_order_objects x) */ static __always_inline void slab_lock(struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); bit_spin_lock(PG_locked, &page->flags); } static __always_inline void slab_unlock(struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); __bit_spin_unlock(PG_locked, &page->flags); } diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 4cba9c2783a1..b60802b3e5ea 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/bootmem.h> +#include <linux/memremap.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -70,7 +71,7 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) } /* need to make sure size is all the same during early stage */ -void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node) +static void * __meminit alloc_block_buf(unsigned long size, int node) { void *ptr; @@ -87,6 +88,77 @@ void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node) return ptr; } +static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap) +{ + return altmap->base_pfn + altmap->reserve + altmap->alloc + + altmap->align; +} + +static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap) +{ + unsigned long allocated = altmap->alloc + altmap->align; + + if (altmap->free > allocated) + return altmap->free - allocated; + return 0; +} + +/** + * vmem_altmap_alloc - allocate pages from the vmem_altmap reservation + * @altmap - reserved page pool for the allocation + * @nr_pfns - size (in pages) of the allocation + * + * Allocations are aligned to the size of the request + */ +static unsigned long __meminit vmem_altmap_alloc(struct vmem_altmap *altmap, + unsigned long nr_pfns) +{ + unsigned long pfn = vmem_altmap_next_pfn(altmap); + unsigned long nr_align; + + nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG); + nr_align = ALIGN(pfn, nr_align) - pfn; + + if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap)) + return ULONG_MAX; + altmap->alloc += nr_pfns; + altmap->align += nr_align; + return pfn + nr_align; +} + +static void * __meminit altmap_alloc_block_buf(unsigned long size, + struct vmem_altmap *altmap) +{ + unsigned long pfn, nr_pfns; + void *ptr; + + if (size & ~PAGE_MASK) { + pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n", + __func__, size); + return NULL; + } + + nr_pfns = size >> PAGE_SHIFT; + pfn = vmem_altmap_alloc(altmap, nr_pfns); + if (pfn < ULONG_MAX) + ptr = __va(__pfn_to_phys(pfn)); + else + ptr = NULL; + pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n", + __func__, pfn, altmap->alloc, altmap->align, nr_pfns); + + return ptr; +} + +/* need to make sure size is all the same during early stage */ +void * __meminit __vmemmap_alloc_block_buf(unsigned long size, int node, + struct vmem_altmap *altmap) +{ + if (altmap) + return altmap_alloc_block_buf(size, altmap); + return alloc_block_buf(size, node); +} + void __meminit vmemmap_verify(pte_t *pte, int node, unsigned long start, unsigned long end) { @@ -103,7 +175,7 @@ pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node) pte_t *pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { pte_t entry; - void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node); + void *p = alloc_block_buf(PAGE_SIZE, node); if (!p) return NULL; entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL); diff --git a/mm/sparse.c b/mm/sparse.c index d1b48b691ac8..3717ceed4177 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -748,7 +748,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) if (!memmap) return; - for (i = 0; i < PAGES_PER_SECTION; i++) { + for (i = 0; i < nr_pages; i++) { if (PageHWPoison(&memmap[i])) { atomic_long_sub(1, &num_poisoned_pages); ClearPageHWPoison(&memmap[i]); @@ -788,7 +788,8 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) free_map_bootmem(memmap); } -void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) +void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, + unsigned long map_offset) { struct page *memmap = NULL; unsigned long *usemap = NULL, flags; @@ -804,7 +805,8 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) } pgdat_resize_unlock(pgdat, &flags); - clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION); + clear_hwpoisoned_pages(memmap + map_offset, + PAGES_PER_SECTION - map_offset); free_section_usemap(memmap, usemap); } #endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/swap.c b/mm/swap.c index 39395fb549c0..09fe5e97714a 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> +#include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> @@ -45,6 +46,7 @@ int page_cluster; static DEFINE_PER_CPU(struct pagevec, lru_add_pvec); static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs); static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs); +static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs); /* * This path almost never happens for VM activity - pages are normally @@ -89,260 +91,14 @@ static void __put_compound_page(struct page *page) (*dtor)(page); } -/** - * Two special cases here: we could avoid taking compound_lock_irqsave - * and could skip the tail refcounting(in _mapcount). - * - * 1. Hugetlbfs page: - * - * PageHeadHuge will remain true until the compound page - * is released and enters the buddy allocator, and it could - * not be split by __split_huge_page_refcount(). - * - * So if we see PageHeadHuge set, and we have the tail page pin, - * then we could safely put head page. - * - * 2. Slab THP page: - * - * PG_slab is cleared before the slab frees the head page, and - * tail pin cannot be the last reference left on the head page, - * because the slab code is free to reuse the compound page - * after a kfree/kmem_cache_free without having to check if - * there's any tail pin left. In turn all tail pinsmust be always - * released while the head is still pinned by the slab code - * and so we know PG_slab will be still set too. - * - * So if we see PageSlab set, and we have the tail page pin, - * then we could safely put head page. - */ -static __always_inline -void put_unrefcounted_compound_page(struct page *page_head, struct page *page) -{ - /* - * If @page is a THP tail, we must read the tail page - * flags after the head page flags. The - * __split_huge_page_refcount side enforces write memory barriers - * between clearing PageTail and before the head page - * can be freed and reallocated. - */ - smp_rmb(); - if (likely(PageTail(page))) { - /* - * __split_huge_page_refcount cannot race - * here, see the comment above this function. - */ - VM_BUG_ON_PAGE(!PageHead(page_head), page_head); - if (put_page_testzero(page_head)) { - /* - * If this is the tail of a slab THP page, - * the tail pin must not be the last reference - * held on the page, because the PG_slab cannot - * be cleared before all tail pins (which skips - * the _mapcount tail refcounting) have been - * released. - * - * If this is the tail of a hugetlbfs page, - * the tail pin may be the last reference on - * the page instead, because PageHeadHuge will - * not go away until the compound page enters - * the buddy allocator. - */ - VM_BUG_ON_PAGE(PageSlab(page_head), page_head); - __put_compound_page(page_head); - } - } else - /* - * __split_huge_page_refcount run before us, - * @page was a THP tail. The split @page_head - * has been freed and reallocated as slab or - * hugetlbfs page of smaller order (only - * possible if reallocated as slab on x86). - */ - if (put_page_testzero(page)) - __put_single_page(page); -} - -static __always_inline -void put_refcounted_compound_page(struct page *page_head, struct page *page) -{ - if (likely(page != page_head && get_page_unless_zero(page_head))) { - unsigned long flags; - - /* - * @page_head wasn't a dangling pointer but it may not - * be a head page anymore by the time we obtain the - * lock. That is ok as long as it can't be freed from - * under us. - */ - flags = compound_lock_irqsave(page_head); - if (unlikely(!PageTail(page))) { - /* __split_huge_page_refcount run before us */ - compound_unlock_irqrestore(page_head, flags); - if (put_page_testzero(page_head)) { - /* - * The @page_head may have been freed - * and reallocated as a compound page - * of smaller order and then freed - * again. All we know is that it - * cannot have become: a THP page, a - * compound page of higher order, a - * tail page. That is because we - * still hold the refcount of the - * split THP tail and page_head was - * the THP head before the split. - */ - if (PageHead(page_head)) - __put_compound_page(page_head); - else - __put_single_page(page_head); - } -out_put_single: - if (put_page_testzero(page)) - __put_single_page(page); - return; - } - VM_BUG_ON_PAGE(page_head != compound_head(page), page); - /* - * We can release the refcount taken by - * get_page_unless_zero() now that - * __split_huge_page_refcount() is blocked on the - * compound_lock. - */ - if (put_page_testzero(page_head)) - VM_BUG_ON_PAGE(1, page_head); - /* __split_huge_page_refcount will wait now */ - VM_BUG_ON_PAGE(page_mapcount(page) <= 0, page); - atomic_dec(&page->_mapcount); - VM_BUG_ON_PAGE(atomic_read(&page_head->_count) <= 0, page_head); - VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page); - compound_unlock_irqrestore(page_head, flags); - - if (put_page_testzero(page_head)) { - if (PageHead(page_head)) - __put_compound_page(page_head); - else - __put_single_page(page_head); - } - } else { - /* @page_head is a dangling pointer */ - VM_BUG_ON_PAGE(PageTail(page), page); - goto out_put_single; - } -} - -static void put_compound_page(struct page *page) -{ - struct page *page_head; - - /* - * We see the PageCompound set and PageTail not set, so @page maybe: - * 1. hugetlbfs head page, or - * 2. THP head page. - */ - if (likely(!PageTail(page))) { - if (put_page_testzero(page)) { - /* - * By the time all refcounts have been released - * split_huge_page cannot run anymore from under us. - */ - if (PageHead(page)) - __put_compound_page(page); - else - __put_single_page(page); - } - return; - } - - /* - * We see the PageCompound set and PageTail set, so @page maybe: - * 1. a tail hugetlbfs page, or - * 2. a tail THP page, or - * 3. a split THP page. - * - * Case 3 is possible, as we may race with - * __split_huge_page_refcount tearing down a THP page. - */ - page_head = compound_head(page); - if (!__compound_tail_refcounted(page_head)) - put_unrefcounted_compound_page(page_head, page); - else - put_refcounted_compound_page(page_head, page); -} - -void put_page(struct page *page) +void __put_page(struct page *page) { if (unlikely(PageCompound(page))) - put_compound_page(page); - else if (put_page_testzero(page)) + __put_compound_page(page); + else __put_single_page(page); } -EXPORT_SYMBOL(put_page); - -/* - * This function is exported but must not be called by anything other - * than get_page(). It implements the slow path of get_page(). - */ -bool __get_page_tail(struct page *page) -{ - /* - * This takes care of get_page() if run on a tail page - * returned by one of the get_user_pages/follow_page variants. - * get_user_pages/follow_page itself doesn't need the compound - * lock because it runs __get_page_tail_foll() under the - * proper PT lock that already serializes against - * split_huge_page(). - */ - unsigned long flags; - bool got; - struct page *page_head = compound_head(page); - - /* Ref to put_compound_page() comment. */ - if (!__compound_tail_refcounted(page_head)) { - smp_rmb(); - if (likely(PageTail(page))) { - /* - * This is a hugetlbfs page or a slab - * page. __split_huge_page_refcount - * cannot race here. - */ - VM_BUG_ON_PAGE(!PageHead(page_head), page_head); - __get_page_tail_foll(page, true); - return true; - } else { - /* - * __split_huge_page_refcount run - * before us, "page" was a THP - * tail. The split page_head has been - * freed and reallocated as slab or - * hugetlbfs page of smaller order - * (only possible if reallocated as - * slab on x86). - */ - return false; - } - } - - got = false; - if (likely(page != page_head && get_page_unless_zero(page_head))) { - /* - * page_head wasn't a dangling pointer but it - * may not be a head page anymore by the time - * we obtain the lock. That is ok as long as it - * can't be freed from under us. - */ - flags = compound_lock_irqsave(page_head); - /* here __split_huge_page_refcount won't run anymore */ - if (likely(PageTail(page))) { - __get_page_tail_foll(page, false); - got = true; - } - compound_unlock_irqrestore(page_head, flags); - if (unlikely(!got)) - put_page(page_head); - } - return got; -} -EXPORT_SYMBOL(__get_page_tail); +EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages @@ -604,6 +360,7 @@ static void __lru_cache_activate_page(struct page *page) */ void mark_page_accessed(struct page *page) { + page = compound_head(page); if (!PageActive(page) && !PageUnevictable(page) && PageReferenced(page)) { @@ -799,6 +556,24 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, update_page_reclaim_stat(lruvec, file, 0); } + +static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, + void *arg) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + int file = page_is_file_cache(page); + int lru = page_lru_base_type(page); + + del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); + ClearPageActive(page); + ClearPageReferenced(page); + add_page_to_lru_list(page, lruvec, lru); + + __count_vm_event(PGDEACTIVATE); + update_page_reclaim_stat(lruvec, file, 0); + } +} + /* * Drain pages out of the cpu's pagevecs. * Either "cpu" is the current CPU, and preemption has already been @@ -825,6 +600,10 @@ void lru_add_drain_cpu(int cpu) if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); + pvec = &per_cpu(lru_deactivate_pvecs, cpu); + if (pagevec_count(pvec)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + activate_page_drain(cpu); } @@ -854,6 +633,26 @@ void deactivate_file_page(struct page *page) } } +/** + * deactivate_page - deactivate a page + * @page: page to deactivate + * + * deactivate_page() moves @page to the inactive list if @page was on the active + * list and was not an unevictable page. This is done to accelerate the reclaim + * of @page. + */ +void deactivate_page(struct page *page) +{ + if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { + struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs); + + page_cache_get(page); + if (!pagevec_add(pvec, page)) + pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); + put_cpu_var(lru_deactivate_pvecs); + } +} + void lru_add_drain(void) { lru_add_drain_cpu(get_cpu()); @@ -883,6 +682,7 @@ void lru_add_drain_all(void) if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); schedule_work_on(cpu, work); @@ -918,15 +718,6 @@ void release_pages(struct page **pages, int nr, bool cold) for (i = 0; i < nr; i++) { struct page *page = pages[i]; - if (unlikely(PageCompound(page))) { - if (zone) { - spin_unlock_irqrestore(&zone->lru_lock, flags); - zone = NULL; - } - put_compound_page(page); - continue; - } - /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the @@ -937,9 +728,19 @@ void release_pages(struct page **pages, int nr, bool cold) zone = NULL; } + page = compound_head(page); if (!put_page_testzero(page)) continue; + if (PageCompound(page)) { + if (zone) { + spin_unlock_irqrestore(&zone->lru_lock, flags); + zone = NULL; + } + __put_compound_page(page); + continue; + } + if (PageLRU(page)) { struct zone *pagezone = page_zone(page); diff --git a/mm/swap_state.c b/mm/swap_state.c index d504adb7fa5f..676ff2991380 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -185,13 +185,12 @@ int add_to_swap(struct page *page, struct list_head *list) * deadlock in the swap out path. */ /* - * Add it to the swap cache and mark it dirty + * Add it to the swap cache. */ err = add_to_swap_cache(page, entry, __GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN); - if (!err) { /* Success */ - SetPageDirty(page); + if (!err) { return 1; } else { /* -ENOMEM radix-tree allocation failure */ /* @@ -353,7 +352,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, } /* May fail (-ENOMEM) if radix-tree node allocation failed. */ - __set_page_locked(new_page); + __SetPageLocked(new_page); SetPageSwapBacked(new_page); err = __add_to_swap_cache(new_page, entry); if (likely(!err)) { @@ -367,7 +366,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, } radix_tree_preload_end(); ClearPageSwapBacked(new_page); - __clear_page_locked(new_page); + __ClearPageLocked(new_page); /* * add_to_swap_cache() doesn't return -EEXIST, so we can safely * clear SWAP_HAS_CACHE flag. diff --git a/mm/swapfile.c b/mm/swapfile.c index e6b8591a3ed2..2bb30aa3a412 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -926,6 +926,9 @@ int reuse_swap_page(struct page *page) VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return 0; + /* The page is part of THP and cannot be reused */ + if (PageTransCompound(page)) + return 0; count = page_mapcount(page); if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); @@ -1108,19 +1111,9 @@ unsigned int count_swap_pages(int type, int free) } #endif /* CONFIG_HIBERNATION */ -static inline int maybe_same_pte(pte_t pte, pte_t swp_pte) +static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { -#ifdef CONFIG_MEM_SOFT_DIRTY - /* - * When pte keeps soft dirty bit the pte generated - * from swap entry does not has it, still it's same - * pte from logical point of view. - */ - pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte); - return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty); -#else - return pte_same(pte, swp_pte); -#endif + return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); } /* @@ -1142,14 +1135,15 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, if (unlikely(!page)) return -ENOMEM; - if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, + &memcg, false)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) { - mem_cgroup_cancel_charge(page, memcg); + if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { + mem_cgroup_cancel_charge(page, memcg, false); ret = 0; goto out; } @@ -1160,11 +1154,11 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { - page_add_anon_rmap(page, vma, addr); - mem_cgroup_commit_charge(page, memcg, true); + page_add_anon_rmap(page, vma, addr, false); + mem_cgroup_commit_charge(page, memcg, true, false); } else { /* ksm created a completely new copy */ - page_add_new_anon_rmap(page, vma, addr); - mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, vma, addr, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); @@ -1206,7 +1200,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ - if (unlikely(maybe_same_pte(*pte, swp_pte))) { + if (unlikely(pte_same_as_swp(*pte, swp_pte))) { pte_unmap(pte); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 77fee9325a57..806b0c758c5b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -63,7 +63,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg)) + if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false)) goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); @@ -76,8 +76,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, goto out_release_uncharge_unlock; inc_mm_counter(dst_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, dst_vma, dst_addr); - mem_cgroup_commit_charge(page, memcg, false); + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, dst_vma); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -91,7 +91,7 @@ out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); - mem_cgroup_cancel_charge(page, memcg); + mem_cgroup_cancel_charge(page, memcg, false); out_release: page_cache_release(page); goto out; diff --git a/mm/util.c b/mm/util.c index 2d28f7930043..6d1f9200f74e 100644 --- a/mm/util.c +++ b/mm/util.c @@ -386,7 +386,9 @@ struct anon_vma *page_anon_vma(struct page *page) struct address_space *page_mapping(struct page *page) { - unsigned long mapping; + struct address_space *mapping; + + page = compound_head(page); /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(PageSlab(page))) @@ -399,11 +401,25 @@ struct address_space *page_mapping(struct page *page) return swap_address_space(entry); } - mapping = (unsigned long)page->mapping; - if (mapping & PAGE_MAPPING_FLAGS) + mapping = page->mapping; + if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) return NULL; - return page->mapping; + return mapping; +} + +/* Slow path of page_mapcount() for compound pages */ +int __page_mapcount(struct page *page) +{ + int ret; + + ret = atomic_read(&page->_mapcount) + 1; + page = compound_head(page); + ret += atomic_read(compound_mapcount_ptr(page)) + 1; + if (PageDoubleMap(page)) + ret--; + return ret; } +EXPORT_SYMBOL_GPL(__page_mapcount); int overcommit_ratio_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 58ceeb107960..fb42a5bffe47 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -455,7 +455,7 @@ found: free_vmap_cache = &va->rb_node; spin_unlock(&vmap_area_lock); - BUG_ON(va->va_start & (align-1)); + BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); @@ -1086,7 +1086,7 @@ void vm_unmap_ram(const void *mem, unsigned int count) BUG_ON(!addr); BUG_ON(addr < VMALLOC_START); BUG_ON(addr > VMALLOC_END); - BUG_ON(addr & (PAGE_SIZE-1)); + BUG_ON(!IS_ALIGNED(addr, PAGE_SIZE)); debug_check_no_locks_freed(mem, size); vmap_debug_free_range(addr, addr+size); diff --git a/mm/vmscan.c b/mm/vmscan.c index 108bd119f2f6..5ac86956ff9d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -906,6 +906,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, int may_enter_fs; enum page_references references = PAGEREF_RECLAIM_CLEAN; bool dirty, writeback; + bool lazyfree = false; + int ret = SWAP_SUCCESS; cond_resched(); @@ -1049,6 +1051,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep_locked; if (!add_to_swap(page, page_list)) goto activate_locked; + lazyfree = true; may_enter_fs = 1; /* Adding to swap updated mapping */ @@ -1060,14 +1063,17 @@ static unsigned long shrink_page_list(struct list_head *page_list, * processes. Try to unmap it here. */ if (page_mapped(page) && mapping) { - switch (try_to_unmap(page, - ttu_flags|TTU_BATCH_FLUSH)) { + switch (ret = try_to_unmap(page, lazyfree ? + (ttu_flags | TTU_BATCH_FLUSH | TTU_LZFREE) : + (ttu_flags | TTU_BATCH_FLUSH))) { case SWAP_FAIL: goto activate_locked; case SWAP_AGAIN: goto keep_locked; case SWAP_MLOCK: goto cull_mlocked; + case SWAP_LZFREE: + goto lazyfree; case SWAP_SUCCESS: ; /* try to free the page below */ } @@ -1174,6 +1180,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } +lazyfree: if (!mapping || !__remove_mapping(mapping, page, true)) goto keep_locked; @@ -1184,8 +1191,11 @@ static unsigned long shrink_page_list(struct list_head *page_list, * we obviously don't have to worry about waking up a process * waiting on the page lock, because there are no references. */ - __clear_page_locked(page); + __ClearPageLocked(page); free_it: + if (ret == SWAP_LZFREE) + count_vm_event(PGLAZYFREED); + nr_reclaimed++; /* diff --git a/mm/vmstat.c b/mm/vmstat.c index 83a003bc3cae..64bd0aa13f75 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -783,6 +783,7 @@ const char * const vmstat_text[] = { "pgfault", "pgmajfault", + "pglazyfreed", TEXTS_FOR_ZONES("pgrefill") TEXTS_FOR_ZONES("pgsteal_kswapd") @@ -844,7 +845,9 @@ const char * const vmstat_text[] = { "thp_fault_fallback", "thp_collapse_alloc", "thp_collapse_alloc_failed", - "thp_split", + "thp_split_page", + "thp_split_page_failed", + "thp_split_pmd", "thp_zero_page_alloc", "thp_zero_page_alloc_failed", #endif diff --git a/scripts/tags.sh b/scripts/tags.sh index 262889046703..76f131ebc192 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -193,7 +193,6 @@ exuberant() --regex-c++='/CLEARPAGEFLAG_NOOP\(([^,)]*).*/ClearPage\1/' \ --regex-c++='/__CLEARPAGEFLAG_NOOP\(([^,)]*).*/__ClearPage\1/' \ --regex-c++='/TESTCLEARFLAG_FALSE\(([^,)]*).*/TestClearPage\1/' \ - --regex-c++='/__TESTCLEARFLAG_FALSE\(([^,)]*).*/__TestClearPage\1/' \ --regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/' \ --regex-c++='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/' \ --regex-c++='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/' \ @@ -260,7 +259,6 @@ emacs() --regex='/CLEARPAGEFLAG_NOOP(\([^,)]*\).*/ClearPage\1/' \ --regex='/__CLEARPAGEFLAG_NOOP(\([^,)]*\).*/__ClearPage\1/' \ --regex='/TESTCLEARFLAG_FALSE(\([^,)]*\).*/TestClearPage\1/' \ - --regex='/__TESTCLEARFLAG_FALSE(\([^,)]*\).*/__TestClearPage\1/' \ --regex='/TASK_PFA_TEST\([^,]*,\s*([^)]*)\)/task_\1/' \ --regex='/TASK_PFA_SET\([^,]*,\s*([^)]*)\)/task_set_\1/' \ --regex='/TASK_PFA_CLEAR\([^,]*,\s*([^)]*)\)/task_clear_\1/' \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 314c7774652e..a11cfd20a6a0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -111,7 +111,7 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -static void kvm_release_pfn_dirty(pfn_t pfn); +static void kvm_release_pfn_dirty(kvm_pfn_t pfn); static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); __visible bool kvm_rebooting; @@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; -bool kvm_is_reserved_pfn(pfn_t pfn) +bool kvm_is_reserved_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return PageReserved(pfn_to_page(pfn)); @@ -1289,7 +1289,7 @@ static inline int check_user_page_hwpoison(unsigned long addr) * true indicates success, otherwise false is returned. */ static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, - bool write_fault, bool *writable, pfn_t *pfn) + bool write_fault, bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; int npages; @@ -1322,7 +1322,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, * 1 indicates success, -errno is returned if error is detected. */ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, - bool *writable, pfn_t *pfn) + bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; int npages = 0; @@ -1386,11 +1386,11 @@ static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) * 2): @write_fault = false && @writable, @writable will tell the caller * whether the mapping is writable. */ -static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, +static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, bool write_fault, bool *writable) { struct vm_area_struct *vma; - pfn_t pfn = 0; + kvm_pfn_t pfn = 0; int npages; /* we can do it either atomically or asynchronously, not both */ @@ -1431,8 +1431,9 @@ exit: return pfn; } -pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, - bool *async, bool write_fault, bool *writable) +kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, + bool atomic, bool *async, bool write_fault, + bool *writable) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); @@ -1453,7 +1454,7 @@ pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, } EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, +kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, @@ -1461,37 +1462,37 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); -pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) +kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn); -pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) +kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } @@ -1514,7 +1515,7 @@ int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, } EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); -static struct page *kvm_pfn_to_page(pfn_t pfn) +static struct page *kvm_pfn_to_page(kvm_pfn_t pfn) { if (is_error_noslot_pfn(pfn)) return KVM_ERR_PTR_BAD_PAGE; @@ -1529,7 +1530,7 @@ static struct page *kvm_pfn_to_page(pfn_t pfn) struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn(kvm, gfn); @@ -1539,7 +1540,7 @@ EXPORT_SYMBOL_GPL(gfn_to_page); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) { - pfn_t pfn; + kvm_pfn_t pfn; pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn); @@ -1555,7 +1556,7 @@ void kvm_release_page_clean(struct page *page) } EXPORT_SYMBOL_GPL(kvm_release_page_clean); -void kvm_release_pfn_clean(pfn_t pfn) +void kvm_release_pfn_clean(kvm_pfn_t pfn) { if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn)) put_page(pfn_to_page(pfn)); @@ -1570,13 +1571,13 @@ void kvm_release_page_dirty(struct page *page) } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); -static void kvm_release_pfn_dirty(pfn_t pfn) +static void kvm_release_pfn_dirty(kvm_pfn_t pfn) { kvm_set_pfn_dirty(pfn); kvm_release_pfn_clean(pfn); } -void kvm_set_pfn_dirty(pfn_t pfn) +void kvm_set_pfn_dirty(kvm_pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) { struct page *page = pfn_to_page(pfn); @@ -1587,14 +1588,14 @@ void kvm_set_pfn_dirty(pfn_t pfn) } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); -void kvm_set_pfn_accessed(pfn_t pfn) +void kvm_set_pfn_accessed(kvm_pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) mark_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); -void kvm_get_pfn(pfn_t pfn) +void kvm_get_pfn(kvm_pfn_t pfn) { if (!kvm_is_reserved_pfn(pfn)) get_page(pfn_to_page(pfn)); |