diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2015-11-17 12:39:27 +1100 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2015-11-17 12:39:27 +1100 |
commit | a0bab9bf631ead38ba92ab1183da77bd9c15c840 (patch) | |
tree | 42d9fe4fd887cff224e189e3db5090969fce0e8e | |
parent | 5bf60e8b49c3f6d5f326d242c2f3c79d0cd0d9be (diff) | |
parent | dcbefa17259c026e13990b06c3e884202b4ffc75 (diff) |
Merge branch 'akpm-current/current'
141 files changed, 4662 insertions, 3124 deletions
diff --git a/Documentation/ABI/testing/configfs-iio b/Documentation/ABI/testing/configfs-iio new file mode 100644 index 000000000000..2483756fccf5 --- /dev/null +++ b/Documentation/ABI/testing/configfs-iio @@ -0,0 +1,21 @@ +What: /config/iio +Date: October 2015 +KernelVersion: 4.4 +Contact: linux-iio@vger.kernel.org +Description: + This represents Industrial IO configuration entry point + directory. It contains sub-groups corresponding to IIO + objects. + +What: /config/iio/triggers +Date: October 2015 +KernelVersion: 4.4 +Description: + Industrial IO software triggers directory. + +What: /config/iio/triggers/hrtimers +Date: October 2015 +KernelVersion: 4.4 +Description: + High resolution timers directory. Creating a directory here + will result in creating a hrtimer trigger in the IIO subsystem. 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/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt index ce1126aceed8..223c32171dcc 100644 --- a/Documentation/filesystems/vfat.txt +++ b/Documentation/filesystems/vfat.txt @@ -180,6 +180,16 @@ dos1xfloppy -- If set, use a fallback default BIOS Parameter Block <bool>: 0,1,yes,no,true,false +LIMITATION +--------------------------------------------------------------------- +* The fallocated region of file is discarded at umount/evict time + when using fallocate with FALLOC_FL_KEEP_SIZE. + So, User should assume that fallocated region can be discarded at + last close if there is memory pressure resulting in eviction of + the inode from the memory. As a result, for any dependency on + the fallocated region, user should make sure to recheck fallocate + after reopening the file. + TODO ---------------------------------------------------------------------- * Need to get rid of the raw scanning stuff. Instead, always use diff --git a/Documentation/iio/iio_configfs.txt b/Documentation/iio/iio_configfs.txt new file mode 100644 index 000000000000..f0add35cd52e --- /dev/null +++ b/Documentation/iio/iio_configfs.txt @@ -0,0 +1,93 @@ +Industrial IIO configfs support + +1. Overview + +Configfs is a filesystem-based manager of kernel objects. IIO uses some +objects that could be easily configured using configfs (e.g.: devices, +triggers). + +See Documentation/filesystems/configfs/configfs.txt for more information +about how configfs works. + +2. Usage + +In order to use configfs support in IIO we need to select it at compile +time via CONFIG_IIO_CONFIGFS config option. + +Then, mount the configfs filesystem (usually under /config directory): + +$ mkdir /config +$ mount -t configfs none /config + +At this point, all default IIO groups will be created and can be accessed +under /config/iio. Next chapters will describe available IIO configuration +objects. + +3. Software triggers + +One of the IIO default configfs groups is the "triggers" group. It is +automagically accessible when the configfs is mounted and can be found +under /config/iio/triggers. + +IIO software triggers implementation offers support for creating multiple +trigger types. A new trigger type is usually implemented as a separate +kernel module following the interface in include/linux/iio/sw_trigger.h: + +/* + * drivers/iio/trigger/iio-trig-sample.c + * sample kernel module implementing a new trigger type + */ +#include <linux/iio/sw_trigger.h> + + +static struct iio_sw_trigger *iio_trig_sample_probe(const char *name) +{ + /* + * This allocates and registers an IIO trigger plus other + * trigger type specific initialization. + */ +} + +static int iio_trig_hrtimer_remove(struct iio_sw_trigger *swt) +{ + /* + * This undoes the actions in iio_trig_sample_probe + */ +} + +static const struct iio_sw_trigger_ops iio_trig_sample_ops = { + .probe = iio_trig_sample_probe, + .remove = iio_trig_sample_remove, +}; + +static struct iio_sw_trigger_type iio_trig_sample = { + .name = "trig-sample", + .owner = THIS_MODULE, + .ops = &iio_trig_sample_ops, +}; + +module_iio_sw_trigger_driver(iio_trig_sample); + +Each trigger type has its own directory under /config/iio/triggers. Loading +iio-trig-sample module will create 'trig-sample' trigger type directory +/config/iio/triggers/trig-sample. + +We support the following interrupt sources (trigger types): + * hrtimer, uses high resolution timers as interrupt source + +3.1 Hrtimer triggers creation and destruction + +Loading iio-trig-hrtimer module will register hrtimer trigger types allowing +users to create hrtimer triggers under /config/iio/triggers/hrtimer. + +e.g: + +$ mkdir /config/triggers/hrtimer/instance1 +$ rmdir /config/triggers/hrtimer/instance1 + +Each trigger can have one or more attributes specific to the trigger type. + +3.2 "hrtimer" trigger types attributes + +"hrtimer" trigger type doesn't have any configurable attribute from /config dir. +It does introduce the sampling_frequency attribute to trigger directory. 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/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/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a745a2a53853..59d1457ca551 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) \ @@ -246,7 +238,6 @@ 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(mkyoung, |= PMD_SECT_AF); diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c index d72b90905132..96554afe1b83 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/pgtable.h b/arch/arm64/include/asm/pgtable.h index 9819a9426b69..fe2943396fdf 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -332,19 +332,11 @@ 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_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index c26b804015e8..3d59de89c042 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -99,19 +99,3 @@ 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/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/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/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index 3245f2d96d4f..0db2a3f8e554 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -374,11 +374,6 @@ void pgtable_cache_init(void); #endif /* __ASSEMBLY__ */ /* - * 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 */ @@ -387,9 +382,8 @@ void pgtable_cache_init(void); /* * 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) +#define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \ + _PAGE_ACCESSED | _PAGE_THP_HUGE) #ifndef __ASSEMBLY__ /* @@ -471,13 +465,6 @@ static inline int pmd_trans_huge(pmd_t pmd) return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _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; -} - extern int has_transparent_hugepage(void); #else static inline void hpte_do_hugepage_flush(struct mm_struct *mm, @@ -536,12 +523,6 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd; } -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - pmd_val(pmd) |= _PAGE_SPLITTING; - return pmd; -} - #define __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { @@ -592,10 +573,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); } -#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/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 4d87122cf6a7..6ffade530dab 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 9833fee493ec..cd2d82efe1cd 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -1030,10 +1030,6 @@ 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; @@ -1071,7 +1067,7 @@ 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; @@ -1094,7 +1090,6 @@ 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; @@ -1116,15 +1111,5 @@ 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 e92cb2146b18..422c59a24561 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\ - ori %1,%0,%4 \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/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 12bbf0e8478f..79f09170943c 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 54ef3bc01b43..34f3790fe459 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1308,22 +1308,6 @@ 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/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/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 131d36fcd07a..f5bfcd66aeb5 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) @@ -735,15 +728,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) return __pmd(pte_val(pte)); } -static inline pmd_t pmd_mksplitting(pmd_t pmd) -{ - pte_t pte = __pte(pmd_val(pmd)); - - pte = pte_mkspecial(pte); - - return __pmd(pte_val(pte)); -} - static inline pgprot_t pmd_pgprot(pmd_t entry) { unsigned long val = pmd_val(entry); 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/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6ec0c8b2e9df..a8d1aa3a43b0 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -165,11 +165,6 @@ 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; @@ -816,10 +811,6 @@ 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 dd5b0aa9dd2f..116fc4ee586f 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,7 +22,6 @@ #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 */ @@ -46,7 +45,6 @@ #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 diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 819ab3f9c9c7..22db575a2fec 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -337,6 +337,7 @@ void arch_crash_save_vmcoreinfo(void) #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + VMCOREINFO_PHYS_BASE(phys_base); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 524619351961..3a5330213aca 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/mm/gup.c b/arch/x86/mm/gup.c index ae9a37bf1371..f8cb3e8ac250 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -136,8 +136,6 @@ 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 +156,7 @@ 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 +199,6 @@ 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/pgtable.c b/arch/x86/mm/pgtable.c index fb0a9dd1d6e4..f52caf9c519b 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -509,20 +509,6 @@ 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) { - pmd_update(vma->vm_mm, address, pmdp); - /* need tlb flush only to serialize against gup-fast */ - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - } -} #endif /** 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/block/genhd.c b/block/genhd.c index e5cafa51567c..ebb41feea357 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -852,7 +852,7 @@ static int show_partition(struct seq_file *seqf, void *v) char buf[BDEVNAME_SIZE]; /* Don't show non-partitionable removeable devices or empty devices */ - if (!get_capacity(sgp) || (!disk_max_parts(sgp) && + if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) && (sgp->flags & GENHD_FL_REMOVABLE))) return 0; if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig index 66792e707d74..5dfb4f1c348c 100644 --- a/drivers/iio/Kconfig +++ b/drivers/iio/Kconfig @@ -22,6 +22,14 @@ if IIO_BUFFER source "drivers/iio/buffer/Kconfig" endif # IIO_BUFFER +config IIO_CONFIGFS + tristate "Enable IIO configuration via configfs" + select CONFIGFS_FS + help + This allows configuring various IIO bits through configfs + (e.g. software triggers). For more info see + Documentation/iio/iio_configfs.txt. + config IIO_TRIGGER bool "Enable triggered sampling support" help @@ -38,6 +46,14 @@ config IIO_CONSUMERS_PER_TRIGGER This value controls the maximum number of consumers that a given trigger may handle. Default is 2. +config IIO_SW_TRIGGER + tristate "Enable software triggers support" + select IIO_CONFIGFS + help + Provides IIO core support for software triggers. A software + trigger can be created via configfs or directly by a driver + using the API provided. + config IIO_TRIGGERED_EVENT tristate select IIO_TRIGGER diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile index aeca7269fe44..dc73c1f1583f 100644 --- a/drivers/iio/Makefile +++ b/drivers/iio/Makefile @@ -7,6 +7,8 @@ industrialio-y := industrialio-core.o industrialio-event.o inkern.o industrialio-$(CONFIG_IIO_BUFFER) += industrialio-buffer.o industrialio-$(CONFIG_IIO_TRIGGER) += industrialio-trigger.o +obj-$(CONFIG_IIO_CONFIGFS) += industrialio-configfs.o +obj-$(CONFIG_IIO_SW_TRIGGER) += industrialio-sw-trigger.o obj-$(CONFIG_IIO_TRIGGERED_EVENT) += industrialio-triggered-event.o obj-y += accel/ diff --git a/drivers/iio/industrialio-configfs.c b/drivers/iio/industrialio-configfs.c new file mode 100644 index 000000000000..83563dd7fcf4 --- /dev/null +++ b/drivers/iio/industrialio-configfs.c @@ -0,0 +1,50 @@ +/* + * Industrial I/O configfs bits + * + * Copyright (c) 2015 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/configfs.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kmod.h> +#include <linux/slab.h> + +#include <linux/iio/iio.h> + +static struct config_item_type iio_root_group_type = { + .ct_owner = THIS_MODULE, +}; + +struct configfs_subsystem iio_configfs_subsys = { + .su_group = { + .cg_item = { + .ci_namebuf = "iio", + .ci_type = &iio_root_group_type, + }, + }, + .su_mutex = __MUTEX_INITIALIZER(iio_configfs_subsys.su_mutex), +}; +EXPORT_SYMBOL(iio_configfs_subsys); + +static int __init iio_configfs_init(void) +{ + config_group_init(&iio_configfs_subsys.su_group); + + return configfs_register_subsystem(&iio_configfs_subsys); +} +module_init(iio_configfs_init); + +static void __exit iio_configfs_exit(void) +{ + configfs_unregister_subsystem(&iio_configfs_subsys); +} +module_exit(iio_configfs_exit); + +MODULE_AUTHOR("Daniel Baluta <daniel.baluta@intel.com>"); +MODULE_DESCRIPTION("Industrial I/O configfs support"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c new file mode 100644 index 000000000000..22262f68db6e --- /dev/null +++ b/drivers/iio/industrialio-sw-trigger.c @@ -0,0 +1,181 @@ +/* + * The Industrial I/O core, software trigger functions + * + * Copyright (c) 2015 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kmod.h> +#include <linux/list.h> +#include <linux/slab.h> + +#include <linux/iio/sw_trigger.h> +#include <linux/configfs.h> + +static struct config_group *iio_triggers_group; +static struct config_item_type iio_trigger_type_group_type; + +static struct config_item_type iio_triggers_group_type = { + .ct_owner = THIS_MODULE, +}; + +static LIST_HEAD(iio_trigger_types_list); +static DEFINE_MUTEX(iio_trigger_types_lock); + +static +struct iio_sw_trigger_type *__iio_find_sw_trigger_type(const char *name, + unsigned len) +{ + struct iio_sw_trigger_type *t = NULL, *iter; + + list_for_each_entry(iter, &iio_trigger_types_list, list) + if (!strcmp(iter->name, name)) { + t = iter; + break; + } + + return t; +} + +int iio_register_sw_trigger_type(struct iio_sw_trigger_type *t) +{ + struct iio_sw_trigger_type *iter; + int ret = 0; + + mutex_lock(&iio_trigger_types_lock); + iter = __iio_find_sw_trigger_type(t->name, strlen(t->name)); + if (iter) + ret = -EBUSY; + else + list_add_tail(&t->list, &iio_trigger_types_list); + mutex_unlock(&iio_trigger_types_lock); + + if (ret) + return ret; + + t->group = configfs_register_default_group(iio_triggers_group, t->name, + &iio_trigger_type_group_type); + if (IS_ERR(t->group)) + ret = PTR_ERR(t->group); + + return ret; +} +EXPORT_SYMBOL(iio_register_sw_trigger_type); + +void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *t) +{ + struct iio_sw_trigger_type *iter; + + mutex_lock(&iio_trigger_types_lock); + iter = __iio_find_sw_trigger_type(t->name, strlen(t->name)); + if (iter) + list_del(&t->list); + mutex_unlock(&iio_trigger_types_lock); + + configfs_unregister_default_group(t->group); +} +EXPORT_SYMBOL(iio_unregister_sw_trigger_type); + +static +struct iio_sw_trigger_type *iio_get_sw_trigger_type(const char *name) +{ + struct iio_sw_trigger_type *t; + + mutex_lock(&iio_trigger_types_lock); + t = __iio_find_sw_trigger_type(name, strlen(name)); + if (t && !try_module_get(t->owner)) + t = NULL; + mutex_unlock(&iio_trigger_types_lock); + + return t; +} + +struct iio_sw_trigger *iio_sw_trigger_create(const char *type, const char *name) +{ + struct iio_sw_trigger *t; + struct iio_sw_trigger_type *tt; + + tt = iio_get_sw_trigger_type(type); + if (!tt) { + pr_err("Invalid trigger type: %s\n", type); + return ERR_PTR(-EINVAL); + } + t = tt->ops->probe(name); + if (IS_ERR(t)) + goto out_module_put; + + t->trigger_type = tt; + + return t; +out_module_put: + module_put(tt->owner); + return t; +} +EXPORT_SYMBOL(iio_sw_trigger_create); + +void iio_sw_trigger_destroy(struct iio_sw_trigger *t) +{ + struct iio_sw_trigger_type *tt = t->trigger_type; + + tt->ops->remove(t); + module_put(tt->owner); +} +EXPORT_SYMBOL(iio_sw_trigger_destroy); + +static struct config_group *trigger_make_group(struct config_group *group, + const char *name) +{ + struct iio_sw_trigger *t; + + t = iio_sw_trigger_create(group->cg_item.ci_name, name); + if (IS_ERR(t)) + return ERR_CAST(t); + + config_item_set_name(&t->group.cg_item, "%s", name); + + return &t->group; +} + +static void trigger_drop_group(struct config_group *group, + struct config_item *item) +{ + struct iio_sw_trigger *t = to_iio_sw_trigger(item); + + iio_sw_trigger_destroy(t); + config_item_put(item); +} + +static struct configfs_group_operations trigger_ops = { + .make_group = &trigger_make_group, + .drop_item = &trigger_drop_group, +}; + +static struct config_item_type iio_trigger_type_group_type = { + .ct_group_ops = &trigger_ops, + .ct_owner = THIS_MODULE, +}; + +static int __init iio_sw_trigger_init(void) +{ + iio_triggers_group = + configfs_register_default_group(&iio_configfs_subsys.su_group, + "triggers", + &iio_triggers_group_type); + return PTR_ERR_OR_ZERO(iio_triggers_group); +} +module_init(iio_sw_trigger_init); + +static void __exit iio_sw_trigger_exit(void) +{ + configfs_unregister_default_group(iio_triggers_group); +} +module_exit(iio_sw_trigger_exit); + +MODULE_AUTHOR("Daniel Baluta <daniel.baluta@intel.com>"); +MODULE_DESCRIPTION("Industrial I/O software triggers support"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/trigger/Kconfig b/drivers/iio/trigger/Kconfig index 79996123a71b..519e6772f6f5 100644 --- a/drivers/iio/trigger/Kconfig +++ b/drivers/iio/trigger/Kconfig @@ -5,6 +5,16 @@ menu "Triggers - standalone" +config IIO_HRTIMER_TRIGGER + tristate "High resolution timer trigger" + depends on IIO_SW_TRIGGER + help + Provides a frequency based IIO trigger using high resolution + timers as interrupt source. + + To compile this driver as a module, choose M here: the + module will be called iio-trig-hrtimer. + config IIO_INTERRUPT_TRIGGER tristate "Generic interrupt trigger" help diff --git a/drivers/iio/trigger/Makefile b/drivers/iio/trigger/Makefile index 0694daecaf22..fe06eb564367 100644 --- a/drivers/iio/trigger/Makefile +++ b/drivers/iio/trigger/Makefile @@ -3,5 +3,7 @@ # # When adding new entries keep the list in alphabetical order + +obj-$(CONFIG_IIO_HRTIMER_TRIGGER) += iio-trig-hrtimer.o obj-$(CONFIG_IIO_INTERRUPT_TRIGGER) += iio-trig-interrupt.o obj-$(CONFIG_IIO_SYSFS_TRIGGER) += iio-trig-sysfs.o diff --git a/drivers/iio/trigger/iio-trig-hrtimer.c b/drivers/iio/trigger/iio-trig-hrtimer.c new file mode 100644 index 000000000000..5e6d451febeb --- /dev/null +++ b/drivers/iio/trigger/iio-trig-hrtimer.c @@ -0,0 +1,193 @@ +/** + * The industrial I/O periodic hrtimer trigger driver + * + * Copyright (C) Intuitive Aerial AB + * Written by Marten Svanfeldt, marten@intuitiveaerial.com + * Copyright (C) 2012, Analog Device Inc. + * Author: Lars-Peter Clausen <lars@metafoo.de> + * Copyright (C) 2015, Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + */ +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/hrtimer.h> + +#include <linux/iio/iio.h> +#include <linux/iio/trigger.h> +#include <linux/iio/sw_trigger.h> + +/* default sampling frequency - 100Hz */ +#define HRTIMER_DEFAULT_SAMPLING_FREQUENCY 100 + +struct iio_hrtimer_info { + struct iio_sw_trigger swt; + struct hrtimer timer; + unsigned long sampling_frequency; + ktime_t period; +}; + +static struct config_item_type iio_hrtimer_type = { + .ct_owner = THIS_MODULE, +}; + +static +ssize_t iio_hrtimer_show_sampling_frequency(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct iio_trigger *trig = to_iio_trigger(dev); + struct iio_hrtimer_info *info = iio_trigger_get_drvdata(trig); + + return snprintf(buf, PAGE_SIZE, "%lu\n", info->sampling_frequency); +} + +static +ssize_t iio_hrtimer_store_sampling_frequency(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct iio_trigger *trig = to_iio_trigger(dev); + struct iio_hrtimer_info *info = iio_trigger_get_drvdata(trig); + unsigned long val; + int ret; + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (!val || val > NSEC_PER_SEC) + return -EINVAL; + + info->sampling_frequency = val; + info->period = ktime_set(0, NSEC_PER_SEC / val); + + return len; +} + +static DEVICE_ATTR(sampling_frequency, S_IRUGO | S_IWUSR, + iio_hrtimer_show_sampling_frequency, + iio_hrtimer_store_sampling_frequency); + +static struct attribute *iio_hrtimer_attrs[] = { + &dev_attr_sampling_frequency.attr, + NULL +}; + +static const struct attribute_group iio_hrtimer_attr_group = { + .attrs = iio_hrtimer_attrs, +}; + +static const struct attribute_group *iio_hrtimer_attr_groups[] = { + &iio_hrtimer_attr_group, + NULL +}; + +static enum hrtimer_restart iio_hrtimer_trig_handler(struct hrtimer *timer) +{ + struct iio_hrtimer_info *info; + + info = container_of(timer, struct iio_hrtimer_info, timer); + + hrtimer_forward_now(timer, info->period); + iio_trigger_poll(info->swt.trigger); + + return HRTIMER_RESTART; +} + +static int iio_trig_hrtimer_set_state(struct iio_trigger *trig, bool state) +{ + struct iio_hrtimer_info *trig_info; + + trig_info = iio_trigger_get_drvdata(trig); + + if (state) + hrtimer_start(&trig_info->timer, trig_info->period, + HRTIMER_MODE_REL); + else + hrtimer_cancel(&trig_info->timer); + + return 0; +} + +static const struct iio_trigger_ops iio_hrtimer_trigger_ops = { + .owner = THIS_MODULE, + .set_trigger_state = iio_trig_hrtimer_set_state, +}; + +static struct iio_sw_trigger *iio_trig_hrtimer_probe(const char *name) +{ + struct iio_hrtimer_info *trig_info; + int ret; + + trig_info = kzalloc(sizeof(*trig_info), GFP_KERNEL); + if (!trig_info) + return ERR_PTR(-ENOMEM); + + trig_info->swt.trigger = iio_trigger_alloc("%s", name); + if (!trig_info->swt.trigger) { + ret = -ENOMEM; + goto err_free_trig_info; + } + + iio_trigger_set_drvdata(trig_info->swt.trigger, trig_info); + trig_info->swt.trigger->ops = &iio_hrtimer_trigger_ops; + trig_info->swt.trigger->dev.groups = iio_hrtimer_attr_groups; + + hrtimer_init(&trig_info->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + trig_info->timer.function = iio_hrtimer_trig_handler; + + trig_info->sampling_frequency = HRTIMER_DEFAULT_SAMPLING_FREQUENCY; + trig_info->period = ktime_set(0, NSEC_PER_SEC / + trig_info->sampling_frequency); + + ret = iio_trigger_register(trig_info->swt.trigger); + if (ret) + goto err_free_trigger; + + iio_swt_group_init_type_name(&trig_info->swt, name, &iio_hrtimer_type); + return &trig_info->swt; +err_free_trigger: + iio_trigger_free(trig_info->swt.trigger); +err_free_trig_info: + kfree(trig_info); + + return ERR_PTR(ret); +} + +static int iio_trig_hrtimer_remove(struct iio_sw_trigger *swt) +{ + struct iio_hrtimer_info *trig_info; + + trig_info = iio_trigger_get_drvdata(swt->trigger); + + iio_trigger_unregister(swt->trigger); + + /* cancel the timer after unreg to make sure no one rearms it */ + hrtimer_cancel(&trig_info->timer); + iio_trigger_free(swt->trigger); + kfree(trig_info); + + return 0; +} + +static const struct iio_sw_trigger_ops iio_trig_hrtimer_ops = { + .probe = iio_trig_hrtimer_probe, + .remove = iio_trig_hrtimer_remove, +}; + +static struct iio_sw_trigger_type iio_trig_hrtimer = { + .name = "hrtimer", + .owner = THIS_MODULE, + .ops = &iio_trig_hrtimer_ops, +}; + +module_iio_sw_trigger_driver(iio_trig_hrtimer); + +MODULE_AUTHOR("Marten Svanfeldt <marten@intuitiveaerial.com>"); +MODULE_AUTHOR("Daniel Baluta <daniel.baluta@intel.com>"); +MODULE_DESCRIPTION("Periodic hrtimer trigger for the IIO subsystem"); +MODULE_LICENSE("GPL v2"); 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/configfs/dir.c b/fs/configfs/dir.c index c81ce7f200a6..a7a1b218f308 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1636,6 +1636,116 @@ const struct file_operations configfs_dir_operations = { .iterate = configfs_readdir, }; +/** + * configfs_register_group - creates a parent-child relation between two groups + * @parent_group: parent group + * @group: child group + * + * link groups, creates dentry for the child and attaches it to the + * parent dentry. + * + * Return: 0 on success, negative errno code on error + */ +int configfs_register_group(struct config_group *parent_group, + struct config_group *group) +{ + struct configfs_subsystem *subsys = parent_group->cg_subsys; + struct dentry *parent; + int ret; + + mutex_lock(&subsys->su_mutex); + link_group(parent_group, group); + mutex_unlock(&subsys->su_mutex); + + parent = parent_group->cg_item.ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + ret = create_default_group(parent_group, group); + if (!ret) { + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + } + mutex_unlock(&d_inode(parent)->i_mutex); + return ret; +} +EXPORT_SYMBOL(configfs_register_group); + +/** + * configfs_unregister_group() - unregisters a child group from its parent + * @group: parent group to be unregistered + * + * Undoes configfs_register_group() + */ +void configfs_unregister_group(struct config_group *group) +{ + struct configfs_subsystem *subsys = group->cg_subsys; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + spin_lock(&configfs_dirent_lock); + configfs_detach_prep(dentry, NULL); + spin_unlock(&configfs_dirent_lock); + + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + d_delete(dentry); + mutex_unlock(&d_inode(parent)->i_mutex); + + dput(dentry); + + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); +} +EXPORT_SYMBOL(configfs_unregister_group); + +/** + * configfs_register_default_group() - allocates and registers a child group + * @parent_group: parent group + * @name: child group name + * @item_type: child item type description + * + * boilerplate to allocate and register a child group with its parent. We need + * kzalloc'ed memory because child's default_group is initially empty. + * + * Return: allocated config group or ERR_PTR() on error + */ +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type) +{ + int ret; + struct config_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + config_group_init_type_name(group, name, item_type); + + ret = configfs_register_group(parent_group, group); + if (ret) { + kfree(group); + return ERR_PTR(ret); + } + return group; +} +EXPORT_SYMBOL(configfs_register_default_group); + +/** + * configfs_unregister_default_group() - unregisters and frees a child group + * @group: the group to act on + */ +void configfs_unregister_default_group(struct config_group *group) +{ + configfs_unregister_group(group); + kfree(group); +} +EXPORT_SYMBOL(configfs_unregister_default_group); + int configfs_register_subsystem(struct configfs_subsystem *subsys) { int err; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 73c64daa0f55..60f03b78914e 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate); return page; } else { diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 8850254136ae..7002467bfbac 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -106,7 +106,10 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } if (!journal) { - ret = generic_file_fsync(file, start, end, datasync); + if (test_opt(inode->i_sb, BARRIER)) + ret = generic_file_fsync(file, start, end, datasync); + else + ret = __generic_file_fsync(file, start, end, datasync); if (!ret && !hlist_empty(&inode->i_dentry)) ret = ext4_sync_parent(inode); goto out; diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 93fc62232ec2..5d384921524d 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -301,15 +301,59 @@ static int fat_bmap_cluster(struct inode *inode, int cluster) return dclus; } -int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, - unsigned long *mapped_blocks, int create) +int fat_get_mapped_cluster(struct inode *inode, sector_t sector, + sector_t last_block, + unsigned long *mapped_blocks, sector_t *bmap) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); + int cluster, offset; + + cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits); + offset = sector & (sbi->sec_per_clus - 1); + cluster = fat_bmap_cluster(inode, cluster); + if (cluster < 0) + return cluster; + else if (cluster) { + *bmap = fat_clus_to_blknr(sbi, cluster) + offset; + *mapped_blocks = sbi->sec_per_clus - offset; + if (*mapped_blocks > last_block - sector) + *mapped_blocks = last_block - sector; + } + + return 0; +} + +static int is_exceed_eof(struct inode *inode, sector_t sector, + sector_t *last_block, int create) +{ + struct super_block *sb = inode->i_sb; const unsigned long blocksize = sb->s_blocksize; const unsigned char blocksize_bits = sb->s_blocksize_bits; + + *last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits; + if (sector >= *last_block) { + if (!create) + return 1; + + /* + * ->mmu_private can access on only allocation path. + * (caller must hold ->i_mutex) + */ + *last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1)) + >> blocksize_bits; + if (sector >= *last_block) + return 1; + } + + return 0; +} + +int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, + unsigned long *mapped_blocks, int create, bool from_bmap) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); sector_t last_block; - int cluster, offset; *phys = 0; *mapped_blocks = 0; @@ -321,31 +365,16 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, return 0; } - last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits; - if (sector >= last_block) { - if (!create) + if (!from_bmap) { + if (is_exceed_eof(inode, sector, &last_block, create)) return 0; - - /* - * ->mmu_private can access on only allocation path. - * (caller must hold ->i_mutex) - */ - last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1)) - >> blocksize_bits; + } else { + last_block = inode->i_blocks >> + (inode->i_sb->s_blocksize_bits - 9); if (sector >= last_block) return 0; } - cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits); - offset = sector & (sbi->sec_per_clus - 1); - cluster = fat_bmap_cluster(inode, cluster); - if (cluster < 0) - return cluster; - else if (cluster) { - *phys = fat_clus_to_blknr(sbi, cluster) + offset; - *mapped_blocks = sbi->sec_per_clus - offset; - if (*mapped_blocks > last_block - sector) - *mapped_blocks = last_block - sector; - } - return 0; + return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks, + phys); } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 4afc4d9d2e41..4c71c8c76426 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -91,7 +91,7 @@ next: *bh = NULL; iblock = *pos >> sb->s_blocksize_bits; - err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0); + err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false); if (err || !phys) return -1; /* beyond EOF or error */ diff --git a/fs/fat/fat.h b/fs/fat/fat.h index be5e15323bab..4307cd4f8da0 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -285,8 +285,11 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len) extern void fat_cache_inval_inode(struct inode *inode); extern int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus); +extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector, + sector_t last_block, + unsigned long *mapped_blocks, sector_t *bmap); extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, - unsigned long *mapped_blocks, int create); + unsigned long *mapped_blocks, int create, bool from_bmap); /* fat/dir.c */ extern const struct file_operations fat_dir_operations; @@ -384,6 +387,7 @@ static inline unsigned long fat_dir_hash(int logstart) { return hash_32(logstart, FAT_HASH_BITS); } +extern int fat_add_cluster(struct inode *inode); /* fat/misc.c */ extern __printf(3, 4) __cold diff --git a/fs/fat/file.c b/fs/fat/file.c index a08f1039909a..43d3475da83a 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -14,8 +14,12 @@ #include <linux/backing-dev.h> #include <linux/fsnotify.h> #include <linux/security.h> +#include <linux/falloc.h> #include "fat.h" +static long fat_fallocate(struct file *file, int mode, + loff_t offset, loff_t len); + static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) { u32 attr; @@ -177,6 +181,7 @@ const struct file_operations fat_file_operations = { #endif .fsync = fat_file_fsync, .splice_read = generic_file_splice_read, + .fallocate = fat_fallocate, }; static int fat_cont_expand(struct inode *inode, loff_t size) @@ -215,6 +220,62 @@ out: return err; } +/* + * Preallocate space for a file. This implements fat's fallocate file + * operation, which gets called from sys_fallocate system call. User + * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set + * we just allocate clusters without zeroing them out. Otherwise we + * allocate and zero out clusters via an expanding truncate. + */ +static long fat_fallocate(struct file *file, int mode, + loff_t offset, loff_t len) +{ + int nr_cluster; /* Number of clusters to be allocated */ + loff_t mm_bytes; /* Number of bytes to be allocated for file */ + loff_t ondisksize; /* block aligned on-disk size in bytes*/ + struct inode *inode = file->f_mapping->host; + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int err = 0; + + /* No support for hole punch or other fallocate flags. */ + if (mode & ~FALLOC_FL_KEEP_SIZE) + return -EOPNOTSUPP; + + /* No support for dir */ + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + mutex_lock(&inode->i_mutex); + if (mode & FALLOC_FL_KEEP_SIZE) { + ondisksize = inode->i_blocks << 9; + if ((offset + len) <= ondisksize) + goto error; + + /* First compute the number of clusters to be allocated */ + mm_bytes = offset + len - ondisksize; + nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >> + sbi->cluster_bits; + + /* Start the allocation.We are not zeroing out the clusters */ + while (nr_cluster-- > 0) { + err = fat_add_cluster(inode); + if (err) + goto error; + } + } else { + if ((offset + len) <= i_size_read(inode)) + goto error; + + /* This is just an expanding truncate */ + err = fat_cont_expand(inode, (offset + len)); + } + +error: + mutex_unlock(&inode->i_mutex); + return err; +} + /* Free all clusters after the skip'th cluster. */ static int fat_free(struct inode *inode, int skip) { diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 509411dd3698..d04c87da4255 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -93,7 +93,7 @@ static struct fat_floppy_defaults { }, }; -static int fat_add_cluster(struct inode *inode) +int fat_add_cluster(struct inode *inode) { int err, cluster; @@ -115,10 +115,10 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); unsigned long mapped_blocks; - sector_t phys; + sector_t phys, last_block; int err, offset; - err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create); + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (phys) { @@ -135,8 +135,14 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, return -EIO; } + last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); - if (!offset) { + /* + * allocate a cluster according to the following. + * 1) no more available blocks + * 2) not part of fallocate region + */ + if (!offset && !(iblock < last_block)) { /* TODO: multiple cluster allocation would be desirable. */ err = fat_add_cluster(inode); if (err) @@ -148,7 +154,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, *max_blocks = min(mapped_blocks, *max_blocks); MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; - err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create); + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; @@ -273,13 +279,38 @@ static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter, return ret; } +static int fat_get_block_bmap(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; + int err; + sector_t bmap; + unsigned long mapped_blocks; + + BUG_ON(create != 0); + + err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true); + if (err) + return err; + + if (bmap) { + map_bh(bh_result, sb, bmap); + max_blocks = min(mapped_blocks, max_blocks); + } + + bh_result->b_size = max_blocks << sb->s_blocksize_bits; + + return 0; +} + static sector_t _fat_bmap(struct address_space *mapping, sector_t block) { sector_t blocknr; /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ down_read(&MSDOS_I(mapping->host)->truncate_lock); - blocknr = generic_block_bmap(mapping, block, fat_get_block); + blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); up_read(&MSDOS_I(mapping->host)->truncate_lock); return blocknr; @@ -553,13 +584,43 @@ out: EXPORT_SYMBOL_GPL(fat_build_inode); +static int __fat_write_inode(struct inode *inode, int wait); + +static void fat_free_eofblocks(struct inode *inode) +{ + /* Release unwritten fallocated blocks on inode eviction. */ + if ((inode->i_blocks << 9) > + round_up(MSDOS_I(inode)->mmu_private, + MSDOS_SB(inode->i_sb)->cluster_size)) { + int err; + + fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private); + /* Fallocate results in updating the i_start/iogstart + * for the zero byte file. So, make it return to + * original state during evict and commit it to avoid + * any corruption on the next access to the cluster + * chain for the file. + */ + err = __fat_write_inode(inode, inode_needs_sync(inode)); + if (err) { + fat_msg(inode->i_sb, KERN_WARNING, "Failed to " + "update on disk inode for unused " + "fallocated blocks, inode could be " + "corrupted. Please run fsck"); + } + + } +} + static void fat_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; fat_truncate_blocks(inode, 0); - } + } else + fat_free_eofblocks(inode); + invalidate_inode_buffers(inode); clear_inode(inode); fat_cache_inval_inode(inode); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316adb968b65..30cf53435087 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -368,10 +368,25 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, lookup_nr = end - next; /* - * This pagevec_lookup() may return pages past 'end', - * so we must check for page->index > end. + * When no more pages are found, take different action for + * hole punch and truncate. + * + * For hole punch, this indicates we have removed each page + * within the range and are done. Note that pages may have + * been faulted in after being removed in the hole punch case. + * This is OK as long as each page in the range was removed + * once. + * + * For truncate, we need to make sure all pages within the + * range are removed when exiting this routine. We could + * have raced with a fault that brought in a page after it + * was first removed. Check the range again until no pages + * are found. */ if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) { + if (!truncate_op) + break; + if (next == start) break; next = start; @@ -382,19 +397,23 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, struct page *page = pvec.pages[i]; u32 hash; + /* + * The page (index) could be beyond end. This is + * only possible in the punch hole case as end is + * LLONG_MAX for truncate. + */ + if (page->index >= end) { + next = end; /* we are done */ + break; + } + next = page->index; + hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); lock_page(page); - if (page->index >= end) { - unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - next = end; /* we are done */ - break; - } - /* * If page is mapped, it was faulted in after being * unmapped. Do nothing in this race case. In the @@ -423,15 +442,13 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, } } - if (page->index > next) - next = page->index; - ++next; unlock_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); } huge_pagevec_release(&pvec); + cond_resched(); } if (truncate_op) @@ -647,9 +664,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = CURRENT_TIME; - spin_lock(&inode->i_lock); - inode->i_private = NULL; - spin_unlock(&inode->i_lock); out: mutex_unlock(&inode->i_mutex); return error; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 5c0c6b58157f..9aebffb40505 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate); return page; } diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 86181d6526dc..c2cb51d4f6e9 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -2516,21 +2516,6 @@ static int ocfs2_update_edge_lengths(handle_t *handle, struct ocfs2_extent_block *eb; u32 range; - /* - * In normal tree rotation process, we will never touch the - * tree branch above subtree_index and ocfs2_extend_rotate_transaction - * doesn't reserve the credits for them either. - * - * But we do have a special case here which will update the rightmost - * records for all the bh in the path. - * So we have to allocate extra credits and access them. - */ - ret = ocfs2_extend_trans(handle, subtree_index); - if (ret) { - mlog_errno(ret); - goto out; - } - ret = ocfs2_journal_access_path(et->et_ci, handle, path); if (ret) { mlog_errno(ret); @@ -2956,7 +2941,7 @@ static int __ocfs2_rotate_tree_left(handle_t *handle, right_path->p_node[subtree_root].bh->b_blocknr, right_path->p_tree_depth); - ret = ocfs2_extend_rotate_transaction(handle, subtree_root, + ret = ocfs2_extend_rotate_transaction(handle, 0, orig_credits, left_path); if (ret) { mlog_errno(ret); @@ -3029,21 +3014,9 @@ static int ocfs2_remove_rightmost_path(handle_t *handle, struct ocfs2_extent_block *eb; struct ocfs2_extent_list *el; - ret = ocfs2_et_sanity_check(et); if (ret) goto out; - /* - * There's two ways we handle this depending on - * whether path is the only existing one. - */ - ret = ocfs2_extend_rotate_transaction(handle, 0, - handle->h_buffer_credits, - path); - if (ret) { - mlog_errno(ret); - goto out; - } ret = ocfs2_journal_access_path(et->et_ci, handle, path); if (ret) { @@ -3641,6 +3614,14 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path, */ if (le16_to_cpu(right_rec->e_leaf_clusters) == 0 && le16_to_cpu(el->l_next_free_rec) == 1) { + /* extend credit for ocfs2_remove_rightmost_path */ + ret = ocfs2_extend_rotate_transaction(handle, 0, + handle->h_buffer_credits, + right_path); + if (ret) { + mlog_errno(ret); + goto out; + } ret = ocfs2_remove_rightmost_path(handle, et, right_path, @@ -3679,6 +3660,14 @@ static int ocfs2_try_to_merge_extent(handle_t *handle, BUG_ON(ctxt->c_contig_type == CONTIG_NONE); if (ctxt->c_split_covers_rec && ctxt->c_has_empty_extent) { + /* extend credit for ocfs2_remove_rightmost_path */ + ret = ocfs2_extend_rotate_transaction(handle, 0, + handle->h_buffer_credits, + path); + if (ret) { + mlog_errno(ret); + goto out; + } /* * The merge code will need to create an empty * extent to take the place of the newly @@ -3727,6 +3716,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle, */ BUG_ON(!ocfs2_is_empty_extent(&el->l_recs[0])); + /* extend credit for ocfs2_remove_rightmost_path */ + ret = ocfs2_extend_rotate_transaction(handle, 0, + handle->h_buffer_credits, + path); + if (ret) { + mlog_errno(ret); + goto out; + } + /* The merge left us with an empty extent, remove it. */ ret = ocfs2_rotate_tree_left(handle, et, path, dealloc); if (ret) { @@ -3748,6 +3746,15 @@ static int ocfs2_try_to_merge_extent(handle_t *handle, goto out; } + /* extend credit for ocfs2_remove_rightmost_path */ + ret = ocfs2_extend_rotate_transaction(handle, 0, + handle->h_buffer_credits, + path); + if (ret) { + mlog_errno(ret); + goto out; + } + ret = ocfs2_rotate_tree_left(handle, et, path, dealloc); /* * Error from this last rotate is not critical, so @@ -3783,6 +3790,16 @@ static int ocfs2_try_to_merge_extent(handle_t *handle, } if (ctxt->c_split_covers_rec) { + /* extend credit for ocfs2_remove_rightmost_path */ + ret = ocfs2_extend_rotate_transaction(handle, 0, + handle->h_buffer_credits, + path); + if (ret) { + mlog_errno(ret); + ret = 0; + goto out; + } + /* * The merge may have left an empty extent in * our leaf. Try to rotate it away. @@ -5342,6 +5359,15 @@ static int ocfs2_truncate_rec(handle_t *handle, struct ocfs2_extent_block *eb; if (ocfs2_is_empty_extent(&el->l_recs[0]) && index > 0) { + /* extend credit for ocfs2_remove_rightmost_path */ + ret = ocfs2_extend_rotate_transaction(handle, 0, + handle->h_buffer_credits, + path); + if (ret) { + mlog_errno(ret); + goto out; + } + ret = ocfs2_rotate_tree_left(handle, et, path, dealloc); if (ret) { mlog_errno(ret); @@ -5928,16 +5954,6 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, ocfs2_journal_dirty(handle, tl_bh); - /* TODO: Perhaps we can calculate the bulk of the - * credits up front rather than extending like - * this. */ - status = ocfs2_extend_trans(handle, - OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); - if (status < 0) { - mlog_errno(status); - goto bail; - } - rec = tl->tl_recs[i]; start_blk = ocfs2_clusters_to_blocks(data_alloc_inode->i_sb, le32_to_cpu(rec.t_start)); @@ -5958,6 +5974,13 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb, goto bail; } } + + status = ocfs2_extend_trans(handle, + OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); + if (status < 0) { + mlog_errno(status); + goto bail; + } i--; } @@ -6016,7 +6039,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) goto out_mutex; } - handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_UPDATE); + handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); @@ -6079,7 +6102,7 @@ void ocfs2_schedule_truncate_log_flush(struct ocfs2_super *osb, if (cancel) cancel_delayed_work(&osb->osb_truncate_log_wq); - queue_delayed_work(ocfs2_wq, &osb->osb_truncate_log_wq, + queue_delayed_work(osb->ocfs2_wq, &osb->osb_truncate_log_wq, OCFS2_TRUNCATE_LOG_FLUSH_INTERVAL); } } @@ -6254,7 +6277,7 @@ void ocfs2_truncate_log_shutdown(struct ocfs2_super *osb) if (tl_inode) { cancel_delayed_work(&osb->osb_truncate_log_wq); - flush_workqueue(ocfs2_wq); + flush_workqueue(osb->ocfs2_wq); status = ocfs2_flush_truncate_log(osb); if (status < 0) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 7f604727f487..4bb992145385 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -499,153 +499,6 @@ bail: return status; } -/* - * TODO: Make this into a generic get_blocks function. - * - * From do_direct_io in direct-io.c: - * "So what we do is to permit the ->get_blocks function to populate - * bh.b_size with the size of IO which is permitted at this offset and - * this i_blkbits." - * - * This function is called directly from get_more_blocks in direct-io.c. - * - * called like this: dio->get_blocks(dio->inode, fs_startblk, - * fs_count, map_bh, dio->rw == WRITE); - */ -static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) -{ - int ret; - u32 cpos = 0; - int alloc_locked = 0; - u64 p_blkno, inode_blocks, contig_blocks; - unsigned int ext_flags; - unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits; - unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; - unsigned long len = bh_result->b_size; - unsigned int clusters_to_alloc = 0, contig_clusters = 0; - - cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock); - - /* This function won't even be called if the request isn't all - * nicely aligned and of the right size, so there's no need - * for us to check any of that. */ - - inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); - - down_read(&OCFS2_I(inode)->ip_alloc_sem); - - /* This figures out the size of the next contiguous block, and - * our logical offset */ - ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, - &contig_blocks, &ext_flags); - up_read(&OCFS2_I(inode)->ip_alloc_sem); - - if (ret) { - mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n", - (unsigned long long)iblock); - ret = -EIO; - goto bail; - } - - /* We should already CoW the refcounted extent in case of create. */ - BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED)); - - /* allocate blocks if no p_blkno is found, and create == 1 */ - if (!p_blkno && create) { - ret = ocfs2_inode_lock(inode, NULL, 1); - if (ret < 0) { - mlog_errno(ret); - goto bail; - } - - alloc_locked = 1; - - down_write(&OCFS2_I(inode)->ip_alloc_sem); - - /* fill hole, allocate blocks can't be larger than the size - * of the hole */ - clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len); - contig_clusters = ocfs2_clusters_for_blocks(inode->i_sb, - contig_blocks); - if (clusters_to_alloc > contig_clusters) - clusters_to_alloc = contig_clusters; - - /* allocate extent and insert them into the extent tree */ - ret = ocfs2_extend_allocation(inode, cpos, - clusters_to_alloc, 0); - if (ret < 0) { - up_write(&OCFS2_I(inode)->ip_alloc_sem); - mlog_errno(ret); - goto bail; - } - - ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, - &contig_blocks, &ext_flags); - if (ret < 0) { - up_write(&OCFS2_I(inode)->ip_alloc_sem); - mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n", - (unsigned long long)iblock); - ret = -EIO; - goto bail; - } - set_buffer_new(bh_result); - up_write(&OCFS2_I(inode)->ip_alloc_sem); - } - - /* - * get_more_blocks() expects us to describe a hole by clearing - * the mapped bit on bh_result(). - * - * Consider an unwritten extent as a hole. - */ - if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN)) - map_bh(bh_result, inode->i_sb, p_blkno); - else - clear_buffer_mapped(bh_result); - - /* make sure we don't map more than max_blocks blocks here as - that's all the kernel will handle at this point. */ - if (max_blocks < contig_blocks) - contig_blocks = max_blocks; - bh_result->b_size = contig_blocks << blocksize_bits; -bail: - if (alloc_locked) - ocfs2_inode_unlock(inode, 1); - return ret; -} - -/* - * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're - * particularly interested in the aio/dio case. We use the rw_lock DLM lock - * to protect io on one node from truncation on another. - */ -static void ocfs2_dio_end_io(struct kiocb *iocb, - loff_t offset, - ssize_t bytes, - void *private) -{ - struct inode *inode = file_inode(iocb->ki_filp); - int level; - - /* this io's submitter should not have unlocked this before we could */ - BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); - - if (ocfs2_iocb_is_unaligned_aio(iocb)) { - ocfs2_iocb_clear_unaligned_aio(iocb); - - mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio); - } - - /* Let rw unlock to be done later to protect append direct io write */ - if (offset + bytes <= i_size_read(inode)) { - ocfs2_iocb_clear_rw_locked(iocb); - - level = ocfs2_iocb_rw_locked_level(iocb); - ocfs2_rw_unlock(inode, level); - } -} - static int ocfs2_releasepage(struct page *page, gfp_t wait) { if (!page_has_buffers(page)) @@ -653,362 +506,6 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait) return try_to_free_buffers(page); } -static int ocfs2_is_overwrite(struct ocfs2_super *osb, - struct inode *inode, loff_t offset) -{ - int ret = 0; - u32 v_cpos = 0; - u32 p_cpos = 0; - unsigned int num_clusters = 0; - unsigned int ext_flags = 0; - - v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset); - ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, - &num_clusters, &ext_flags); - if (ret < 0) { - mlog_errno(ret); - return ret; - } - - if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) - return 1; - - return 0; -} - -static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb, - struct inode *inode, loff_t offset, - u64 zero_len, int cluster_align) -{ - u32 p_cpos = 0; - u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode)); - unsigned int num_clusters = 0; - unsigned int ext_flags = 0; - int ret = 0; - - if (offset <= i_size_read(inode) || cluster_align) - return 0; - - ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters, - &ext_flags); - if (ret < 0) { - mlog_errno(ret); - return ret; - } - - if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { - u64 s = i_size_read(inode); - sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) + - (do_div(s, osb->s_clustersize) >> 9); - - ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector, - zero_len >> 9, GFP_NOFS, false); - if (ret < 0) - mlog_errno(ret); - } - - return ret; -} - -static int ocfs2_direct_IO_extend_no_holes(struct ocfs2_super *osb, - struct inode *inode, loff_t offset) -{ - u64 zero_start, zero_len, total_zero_len; - u32 p_cpos = 0, clusters_to_add; - u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, i_size_read(inode)); - unsigned int num_clusters = 0; - unsigned int ext_flags = 0; - u32 size_div, offset_div; - int ret = 0; - - { - u64 o = offset; - u64 s = i_size_read(inode); - - offset_div = do_div(o, osb->s_clustersize); - size_div = do_div(s, osb->s_clustersize); - } - - if (offset <= i_size_read(inode)) - return 0; - - clusters_to_add = ocfs2_bytes_to_clusters(inode->i_sb, offset) - - ocfs2_bytes_to_clusters(inode->i_sb, i_size_read(inode)); - total_zero_len = offset - i_size_read(inode); - if (clusters_to_add) - total_zero_len -= offset_div; - - /* Allocate clusters to fill out holes, and this is only needed - * when we add more than one clusters. Otherwise the cluster will - * be allocated during direct IO */ - if (clusters_to_add > 1) { - ret = ocfs2_extend_allocation(inode, - OCFS2_I(inode)->ip_clusters, - clusters_to_add - 1, 0); - if (ret) { - mlog_errno(ret); - goto out; - } - } - - while (total_zero_len) { - ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, &num_clusters, - &ext_flags); - if (ret < 0) { - mlog_errno(ret); - goto out; - } - - zero_start = ocfs2_clusters_to_bytes(osb->sb, p_cpos) + - size_div; - zero_len = ocfs2_clusters_to_bytes(osb->sb, num_clusters) - - size_div; - zero_len = min(total_zero_len, zero_len); - - if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { - ret = blkdev_issue_zeroout(osb->sb->s_bdev, - zero_start >> 9, zero_len >> 9, - GFP_NOFS, false); - if (ret < 0) { - mlog_errno(ret); - goto out; - } - } - - total_zero_len -= zero_len; - v_cpos += ocfs2_bytes_to_clusters(osb->sb, zero_len + size_div); - - /* Only at first iteration can be cluster not aligned. - * So set size_div to 0 for the rest */ - size_div = 0; - } - -out: - return ret; -} - -static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, - struct iov_iter *iter, - loff_t offset) -{ - ssize_t ret = 0; - ssize_t written = 0; - bool orphaned = false; - int is_overwrite = 0; - struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file)->i_mapping->host; - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - struct buffer_head *di_bh = NULL; - size_t count = iter->count; - journal_t *journal = osb->journal->j_journal; - u64 zero_len_head, zero_len_tail; - int cluster_align_head, cluster_align_tail; - loff_t final_size = offset + count; - int append_write = offset >= i_size_read(inode) ? 1 : 0; - unsigned int num_clusters = 0; - unsigned int ext_flags = 0; - - { - u64 o = offset; - u64 s = i_size_read(inode); - - zero_len_head = do_div(o, 1 << osb->s_clustersize_bits); - cluster_align_head = !zero_len_head; - - zero_len_tail = osb->s_clustersize - - do_div(s, osb->s_clustersize); - if ((offset - i_size_read(inode)) < zero_len_tail) - zero_len_tail = offset - i_size_read(inode); - cluster_align_tail = !zero_len_tail; - } - - /* - * when final_size > inode->i_size, inode->i_size will be - * updated after direct write, so add the inode to orphan - * dir first. - */ - if (final_size > i_size_read(inode)) { - ret = ocfs2_add_inode_to_orphan(osb, inode); - if (ret < 0) { - mlog_errno(ret); - goto out; - } - orphaned = true; - } - - if (append_write) { - ret = ocfs2_inode_lock(inode, NULL, 1); - if (ret < 0) { - mlog_errno(ret); - goto clean_orphan; - } - - /* zeroing out the previously allocated cluster tail - * that but not zeroed */ - if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) { - down_read(&OCFS2_I(inode)->ip_alloc_sem); - ret = ocfs2_direct_IO_zero_extend(osb, inode, offset, - zero_len_tail, cluster_align_tail); - up_read(&OCFS2_I(inode)->ip_alloc_sem); - } else { - down_write(&OCFS2_I(inode)->ip_alloc_sem); - ret = ocfs2_direct_IO_extend_no_holes(osb, inode, - offset); - up_write(&OCFS2_I(inode)->ip_alloc_sem); - } - if (ret < 0) { - mlog_errno(ret); - ocfs2_inode_unlock(inode, 1); - goto clean_orphan; - } - - is_overwrite = ocfs2_is_overwrite(osb, inode, offset); - if (is_overwrite < 0) { - mlog_errno(is_overwrite); - ret = is_overwrite; - ocfs2_inode_unlock(inode, 1); - goto clean_orphan; - } - - ocfs2_inode_unlock(inode, 1); - } - - written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - offset, ocfs2_direct_IO_get_blocks, - ocfs2_dio_end_io, NULL, 0); - /* overwrite aio may return -EIOCBQUEUED, and it is not an error */ - if ((written < 0) && (written != -EIOCBQUEUED)) { - loff_t i_size = i_size_read(inode); - - if (offset + count > i_size) { - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret < 0) { - mlog_errno(ret); - goto clean_orphan; - } - - if (i_size == i_size_read(inode)) { - ret = ocfs2_truncate_file(inode, di_bh, - i_size); - if (ret < 0) { - if (ret != -ENOSPC) - mlog_errno(ret); - - ocfs2_inode_unlock(inode, 1); - brelse(di_bh); - di_bh = NULL; - goto clean_orphan; - } - } - - ocfs2_inode_unlock(inode, 1); - brelse(di_bh); - di_bh = NULL; - - ret = jbd2_journal_force_commit(journal); - if (ret < 0) - mlog_errno(ret); - } - } else if (written > 0 && append_write && !is_overwrite && - !cluster_align_head) { - /* zeroing out the allocated cluster head */ - u32 p_cpos = 0; - u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset); - - ret = ocfs2_inode_lock(inode, NULL, 0); - if (ret < 0) { - mlog_errno(ret); - goto clean_orphan; - } - - ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos, - &num_clusters, &ext_flags); - if (ret < 0) { - mlog_errno(ret); - ocfs2_inode_unlock(inode, 0); - goto clean_orphan; - } - - BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN)); - - ret = blkdev_issue_zeroout(osb->sb->s_bdev, - (u64)p_cpos << (osb->s_clustersize_bits - 9), - zero_len_head >> 9, GFP_NOFS, false); - if (ret < 0) - mlog_errno(ret); - - ocfs2_inode_unlock(inode, 0); - } - -clean_orphan: - if (orphaned) { - int tmp_ret; - int update_isize = written > 0 ? 1 : 0; - loff_t end = update_isize ? offset + written : 0; - - tmp_ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (tmp_ret < 0) { - ret = tmp_ret; - mlog_errno(ret); - goto out; - } - - tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, - update_isize, end); - if (tmp_ret < 0) { - ret = tmp_ret; - mlog_errno(ret); - brelse(di_bh); - goto out; - } - - ocfs2_inode_unlock(inode, 1); - brelse(di_bh); - - tmp_ret = jbd2_journal_force_commit(journal); - if (tmp_ret < 0) { - ret = tmp_ret; - mlog_errno(tmp_ret); - } - } - -out: - if (ret >= 0) - ret = written; - return ret; -} - -static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, - loff_t offset) -{ - struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file)->i_mapping->host; - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - int full_coherency = !(osb->s_mount_opt & - OCFS2_MOUNT_COHERENCY_BUFFERED); - - /* - * Fallback to buffered I/O if we see an inode without - * extents. - */ - if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) - return 0; - - /* Fallback to buffered I/O if we are appending and - * concurrent O_DIRECT writes are allowed. - */ - if (i_size_read(inode) <= offset && !full_coherency) - return 0; - - if (iov_iter_rw(iter) == READ) - return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, - iter, offset, - ocfs2_direct_IO_get_blocks, - ocfs2_dio_end_io, NULL, 0); - else - return ocfs2_direct_IO_write(iocb, iter, offset); -} - static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb, u32 cpos, unsigned int *start, @@ -1195,6 +692,13 @@ next_bh: #define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE) +struct ocfs2_unwritten_extent { + struct list_head ue_node; + struct list_head ue_ip_node; + u32 ue_cpos; + u32 ue_phys; +}; + /* * Describe the state of a single cluster to be written to. */ @@ -1206,7 +710,7 @@ struct ocfs2_write_cluster_desc { * filled. */ unsigned c_new; - unsigned c_unwritten; + unsigned c_clear_unwritten; unsigned c_needs_zero; }; @@ -1218,6 +722,9 @@ struct ocfs2_write_ctxt { /* First cluster allocated in a nonsparse extend */ u32 w_first_new_cpos; + /* Type of caller. Must be one of buffer, mmap, direct. */ + ocfs2_write_type_t w_type; + struct ocfs2_write_cluster_desc w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE]; /* @@ -1266,6 +773,8 @@ struct ocfs2_write_ctxt { struct buffer_head *w_di_bh; struct ocfs2_cached_dealloc_ctxt w_dealloc; + + struct list_head w_unwritten_list; }; void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages) @@ -1304,8 +813,25 @@ static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc) ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages); } -static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) +static void ocfs2_free_unwritten_list(struct inode *inode, + struct list_head *head) +{ + struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL; + + list_for_each_entry_safe(ue, tmp, head, ue_node) { + list_del(&ue->ue_node); + spin_lock(&oi->ip_lock); + list_del(&ue->ue_ip_node); + spin_unlock(&oi->ip_lock); + kfree(ue); + } +} + +static void ocfs2_free_write_ctxt(struct inode *inode, + struct ocfs2_write_ctxt *wc) { + ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list); ocfs2_unlock_pages(wc); brelse(wc->w_di_bh); kfree(wc); @@ -1313,7 +839,8 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc) static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, struct ocfs2_super *osb, loff_t pos, - unsigned len, struct buffer_head *di_bh) + unsigned len, ocfs2_write_type_t type, + struct buffer_head *di_bh) { u32 cend; struct ocfs2_write_ctxt *wc; @@ -1328,6 +855,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, wc->w_clen = cend - wc->w_cpos + 1; get_bh(di_bh); wc->w_di_bh = di_bh; + wc->w_type = type; if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits)) wc->w_large_pages = 1; @@ -1335,6 +863,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, wc->w_large_pages = 0; ocfs2_init_dealloc_ctxt(&wc->w_dealloc); + INIT_LIST_HEAD(&wc->w_unwritten_list); *wcp = wc; @@ -1395,12 +924,13 @@ static void ocfs2_write_failure(struct inode *inode, to = user_pos + user_len; struct page *tmppage; - ocfs2_zero_new_buffers(wc->w_target_page, from, to); + if (wc->w_target_page) + ocfs2_zero_new_buffers(wc->w_target_page, from, to); for(i = 0; i < wc->w_num_pages; i++) { tmppage = wc->w_pages[i]; - if (page_has_buffers(tmppage)) { + if (tmppage && page_has_buffers(tmppage)) { if (ocfs2_should_order_data(inode)) ocfs2_jbd2_file_inode(wc->w_handle, inode); @@ -1530,11 +1060,13 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, wc->w_num_pages = 1; start = target_index; } + end_index = (user_pos + user_len - 1) >> PAGE_CACHE_SHIFT; for(i = 0; i < wc->w_num_pages; i++) { index = start + i; - if (index == target_index && mmap_page) { + if (index >= target_index && index <= end_index && + wc->w_type == OCFS2_WRITE_MMAP) { /* * ocfs2_pagemkwrite() is a little different * and wants us to directly use the page @@ -1553,6 +1085,11 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping, page_cache_get(mmap_page); wc->w_pages[i] = mmap_page; wc->w_target_locked = true; + } else if (index >= target_index && index <= end_index && + wc->w_type == OCFS2_WRITE_DIRECT) { + /* Direct write has no mapping page. */ + wc->w_pages[i] = NULL; + continue; } else { wc->w_pages[i] = find_or_create_page(mapping, index, GFP_NOFS); @@ -1577,19 +1114,20 @@ out: * Prepare a single cluster for write one cluster into the file. */ static int ocfs2_write_cluster(struct address_space *mapping, - u32 phys, unsigned int unwritten, + u32 *phys, unsigned int new, + unsigned int clear_unwritten, unsigned int should_zero, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, unsigned user_len) { - int ret, i, new; - u64 v_blkno, p_blkno; + int ret, i; + u64 p_blkno; struct inode *inode = mapping->host; struct ocfs2_extent_tree et; + int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1); - new = phys == 0 ? 1 : 0; if (new) { u32 tmp_pos; @@ -1599,9 +1137,9 @@ static int ocfs2_write_cluster(struct address_space *mapping, */ tmp_pos = cpos; ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode, - &tmp_pos, 1, 0, wc->w_di_bh, - wc->w_handle, data_ac, - meta_ac, NULL); + &tmp_pos, 1, !clear_unwritten, + wc->w_di_bh, wc->w_handle, + data_ac, meta_ac, NULL); /* * This shouldn't happen because we must have already * calculated the correct meta data allocation required. The @@ -1618,11 +1156,11 @@ static int ocfs2_write_cluster(struct address_space *mapping, mlog_errno(ret); goto out; } - } else if (unwritten) { + } else if (clear_unwritten) { ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), wc->w_di_bh); ret = ocfs2_mark_extent_written(inode, &et, - wc->w_handle, cpos, 1, phys, + wc->w_handle, cpos, 1, *phys, meta_ac, &wc->w_dealloc); if (ret < 0) { mlog_errno(ret); @@ -1630,30 +1168,33 @@ static int ocfs2_write_cluster(struct address_space *mapping, } } - if (should_zero) - v_blkno = ocfs2_clusters_to_blocks(inode->i_sb, cpos); - else - v_blkno = user_pos >> inode->i_sb->s_blocksize_bits; - /* * The only reason this should fail is due to an inability to * find the extent added. */ - ret = ocfs2_extent_map_get_blocks(inode, v_blkno, &p_blkno, NULL, - NULL); + ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL); if (ret < 0) { mlog(ML_ERROR, "Get physical blkno failed for inode %llu, " - "at logical block %llu", - (unsigned long long)OCFS2_I(inode)->ip_blkno, - (unsigned long long)v_blkno); + "at logical cluster %u", + (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos); goto out; } - BUG_ON(p_blkno == 0); + BUG_ON(*phys == 0); + + p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys); + if (!should_zero) + p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1); for(i = 0; i < wc->w_num_pages; i++) { int tmpret; + /* This is the direct io target page. */ + if (wc->w_pages[i] == NULL) { + p_blkno++; + continue; + } + tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc, wc->w_pages[i], cpos, user_pos, user_len, @@ -1700,8 +1241,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping, if ((cluster_off + local_len) > osb->s_clustersize) local_len = osb->s_clustersize - cluster_off; - ret = ocfs2_write_cluster(mapping, desc->c_phys, - desc->c_unwritten, + ret = ocfs2_write_cluster(mapping, &desc->c_phys, + desc->c_new, + desc->c_clear_unwritten, desc->c_needs_zero, data_ac, meta_ac, wc, desc->c_cpos, pos, local_len); @@ -1772,6 +1314,66 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb, } /* + * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to + * do the zero work. And should not to clear UNWRITTEN since it will be cleared + * by the direct io procedure. + * If this is a new extent that allocated by direct io, we should mark it in + * the ip_unwritten_list. + */ +static int ocfs2_unwritten_check(struct inode *inode, + struct ocfs2_write_ctxt *wc, + struct ocfs2_write_cluster_desc *desc) +{ + struct ocfs2_inode_info *oi = OCFS2_I(inode); + struct ocfs2_unwritten_extent *ue = NULL, *new = NULL; + int ret = 0; + + if (!desc->c_needs_zero) + return 0; + +retry: + spin_lock(&oi->ip_lock); + /* Needs not to zero no metter buffer or direct. The one who is zero + * the cluster is doing zero. And he will clear unwritten after all + * cluster io finished. */ + list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) { + if (desc->c_cpos == ue->ue_cpos) { + BUG_ON(desc->c_new); + desc->c_needs_zero = 0; + desc->c_clear_unwritten = 0; + goto unlock; + } + } + + if (wc->w_type != OCFS2_WRITE_DIRECT) + goto unlock; + + if (new == NULL) { + spin_unlock(&oi->ip_lock); + new = kmalloc(sizeof(struct ocfs2_unwritten_extent), + GFP_NOFS); + if (new == NULL) { + ret = -ENOMEM; + goto out; + } + goto retry; + } + /* This direct write will doing zero. */ + new->ue_cpos = desc->c_cpos; + new->ue_phys = desc->c_phys; + desc->c_clear_unwritten = 0; + list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list); + list_add_tail(&new->ue_node, &wc->w_unwritten_list); + new = NULL; +unlock: + spin_unlock(&oi->ip_lock); +out: + if (new) + kfree(new); + return ret; +} + +/* * Populate each single-cluster write descriptor in the write context * with information about the i/o to be done. * @@ -1846,14 +1448,21 @@ static int ocfs2_populate_write_desc(struct inode *inode, if (phys == 0) { desc->c_new = 1; desc->c_needs_zero = 1; + desc->c_clear_unwritten = 1; *clusters_to_alloc = *clusters_to_alloc + 1; } if (ext_flags & OCFS2_EXT_UNWRITTEN) { - desc->c_unwritten = 1; + desc->c_clear_unwritten = 1; desc->c_needs_zero = 1; } + ret = ocfs2_unwritten_check(inode, wc, desc); + if (ret) { + mlog_errno(ret); + goto out; + } + num_clusters--; } @@ -2016,8 +1625,10 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode, if (ret) mlog_errno(ret); - wc->w_first_new_cpos = - ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)); + /* There is no wc if this is call from direct. */ + if (wc) + wc->w_first_new_cpos = + ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)); return ret; } @@ -2071,9 +1682,8 @@ out: return ret; } -int ocfs2_write_begin_nolock(struct file *filp, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, +int ocfs2_write_begin_nolock(struct address_space *mapping, + loff_t pos, unsigned len, ocfs2_write_type_t type, struct page **pagep, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page) { @@ -2090,7 +1700,7 @@ int ocfs2_write_begin_nolock(struct file *filp, int try_free = 1, ret1; try_again: - ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, di_bh); + ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh); if (ret) { mlog_errno(ret); return ret; @@ -2109,14 +1719,17 @@ try_again: } } - if (ocfs2_sparse_alloc(osb)) - ret = ocfs2_zero_tail(inode, di_bh, pos); - else - ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len, - wc); - if (ret) { - mlog_errno(ret); - goto out; + /* Direct io change i_size late, should not zero tail here. */ + if (type != OCFS2_WRITE_DIRECT) { + if (ocfs2_sparse_alloc(osb)) + ret = ocfs2_zero_tail(inode, di_bh, pos); + else + ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, + len, wc); + if (ret) { + mlog_errno(ret); + goto out; + } } ret = ocfs2_check_range_for_refcount(inode, pos, len); @@ -2147,7 +1760,7 @@ try_again: (unsigned long long)OCFS2_I(inode)->ip_blkno, (long long)i_size_read(inode), le32_to_cpu(di->i_clusters), - pos, len, flags, mmap_page, + pos, len, type, mmap_page, clusters_to_alloc, extents_to_split); /* @@ -2177,17 +1790,17 @@ try_again: credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list); - - } + } else if (type == OCFS2_WRITE_DIRECT) + /* direct write needs not to start trans if no extents alloc. */ + goto success; /* * We have to zero sparse allocated clusters, unwritten extent clusters, * and non-sparse clusters we just extended. For non-sparse writes, * we know zeros will only be needed in the first and/or last cluster. */ - if (clusters_to_alloc || extents_to_split || - (wc->w_clen && (wc->w_desc[0].c_needs_zero || - wc->w_desc[wc->w_clen - 1].c_needs_zero))) + if (wc->w_clen && (wc->w_desc[0].c_needs_zero || + wc->w_desc[wc->w_clen - 1].c_needs_zero)) cluster_of_pages = 1; else cluster_of_pages = 0; @@ -2254,7 +1867,8 @@ try_again: ocfs2_free_alloc_context(meta_ac); success: - *pagep = wc->w_target_page; + if (pagep) + *pagep = wc->w_target_page; *fsdata = wc; return 0; out_quota: @@ -2265,7 +1879,7 @@ out_commit: ocfs2_commit_trans(osb, handle); out: - ocfs2_free_write_ctxt(wc); + ocfs2_free_write_ctxt(inode, wc); if (data_ac) { ocfs2_free_alloc_context(data_ac); @@ -2317,8 +1931,8 @@ static int ocfs2_write_begin(struct file *file, struct address_space *mapping, */ down_write(&OCFS2_I(inode)->ip_alloc_sem); - ret = ocfs2_write_begin_nolock(file, mapping, pos, len, flags, pagep, - fsdata, di_bh, NULL); + ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER, + pagep, fsdata, di_bh, NULL); if (ret) { mlog_errno(ret); goto out_fail; @@ -2375,12 +1989,16 @@ int ocfs2_write_end_nolock(struct address_space *mapping, handle_t *handle = wc->w_handle; struct page *tmppage; - ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - copied = ret; - mlog_errno(ret); - goto out; + BUG_ON(!list_empty(&wc->w_unwritten_list)); + + if (handle) { + ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), + wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + copied = ret; + mlog_errno(ret); + goto out; + } } if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { @@ -2388,18 +2006,23 @@ int ocfs2_write_end_nolock(struct address_space *mapping, goto out_write_size; } - if (unlikely(copied < len)) { + if (unlikely(copied < len) && wc->w_target_page) { if (!PageUptodate(wc->w_target_page)) copied = 0; ocfs2_zero_new_buffers(wc->w_target_page, start+copied, start+len); } - flush_dcache_page(wc->w_target_page); + if (wc->w_target_page) + flush_dcache_page(wc->w_target_page); for(i = 0; i < wc->w_num_pages; i++) { tmppage = wc->w_pages[i]; + /* This is the direct io target page. */ + if (tmppage == NULL) + continue; + if (tmppage == wc->w_target_page) { from = wc->w_target_from; to = wc->w_target_to; @@ -2418,25 +2041,29 @@ int ocfs2_write_end_nolock(struct address_space *mapping, } if (page_has_buffers(tmppage)) { - if (ocfs2_should_order_data(inode)) - ocfs2_jbd2_file_inode(wc->w_handle, inode); + if (handle && ocfs2_should_order_data(inode)) + ocfs2_jbd2_file_inode(handle, inode); block_commit_write(tmppage, from, to); } } out_write_size: - pos += copied; - if (pos > i_size_read(inode)) { - i_size_write(inode, pos); - mark_inode_dirty(inode); - } - inode->i_blocks = ocfs2_inode_sector_count(inode); - di->i_size = cpu_to_le64((u64)i_size_read(inode)); - inode->i_mtime = inode->i_ctime = CURRENT_TIME; - di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); - di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); - ocfs2_update_inode_fsync_trans(handle, inode, 1); - ocfs2_journal_dirty(handle, wc->w_di_bh); + /* Direct io do not update i_size here. */ + if (wc->w_type != OCFS2_WRITE_DIRECT) { + pos += copied; + if (pos > i_size_read(inode)) { + i_size_write(inode, pos); + mark_inode_dirty(inode); + } + inode->i_blocks = ocfs2_inode_sector_count(inode); + di->i_size = cpu_to_le64((u64)i_size_read(inode)); + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); + di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + ocfs2_update_inode_fsync_trans(handle, inode, 1); + } + if (handle) + ocfs2_journal_dirty(handle, wc->w_di_bh); out: /* unlock pages before dealloc since it needs acquiring j_trans_barrier @@ -2446,7 +2073,8 @@ out: */ ocfs2_unlock_pages(wc); - ocfs2_commit_trans(osb, handle); + if (handle) + ocfs2_commit_trans(osb, handle); ocfs2_run_deallocs(osb, &wc->w_dealloc); @@ -2471,6 +2099,340 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping, return ret; } +struct ocfs2_dio_write_ctxt { + struct list_head dw_zero_list; + unsigned dw_zero_count; + int dw_orphaned; + pid_t dw_writer_pid; +}; + +static struct ocfs2_dio_write_ctxt * +ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc) +{ + struct ocfs2_dio_write_ctxt *dwc = NULL; + + if (bh->b_private) + return bh->b_private; + + dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS); + if (dwc == NULL) + return NULL; + INIT_LIST_HEAD(&dwc->dw_zero_list); + dwc->dw_zero_count = 0; + dwc->dw_orphaned = 0; + dwc->dw_writer_pid = task_pid_nr(current); + bh->b_private = dwc; + *alloc = 1; + + return dwc; +} + +static void ocfs2_dio_free_write_ctx(struct inode *inode, + struct ocfs2_dio_write_ctxt *dwc) +{ + ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list); + kfree(dwc); +} + +/* + * TODO: Make this into a generic get_blocks function. + * + * From do_direct_io in direct-io.c: + * "So what we do is to permit the ->get_blocks function to populate + * bh.b_size with the size of IO which is permitted at this offset and + * this i_blkbits." + * + * This function is called directly from get_more_blocks in direct-io.c. + * + * called like this: dio->get_blocks(dio->inode, fs_startblk, + * fs_count, map_bh, dio->rw == WRITE); + */ +static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct ocfs2_write_ctxt *wc; + struct ocfs2_write_cluster_desc *desc = NULL; + struct ocfs2_dio_write_ctxt *dwc = NULL; + struct buffer_head *di_bh = NULL; + u64 p_blkno; + loff_t pos = iblock << inode->i_sb->s_blocksize_bits; + unsigned len, total_len = bh_result->b_size; + int ret = 0, first_get_block = 0; + + len = osb->s_clustersize - (pos & (osb->s_clustersize - 1)); + len = min(total_len, len); + + mlog(0, "get block of %lu at %llu:%u req %u\n", + inode->i_ino, pos, len, total_len); + + /* This is the fast path for re-write. */ + ret = ocfs2_get_block(inode, iblock, bh_result, create); + + if (buffer_mapped(bh_result) && + !buffer_new(bh_result) && + ret == 0) + goto out; + + /* Clear state set by ocfs2_get_block. */ + bh_result->b_state = 0; + + dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block); + if (unlikely(dwc == NULL)) { + ret = -ENOMEM; + mlog_errno(ret); + goto out; + } + + if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) > + ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) && + !dwc->dw_orphaned) { + /* + * when we are going to alloc extents beyond file size, add the + * inode to orphan dir, so we can recall those spaces when + * system crashed during write. + */ + ret = ocfs2_add_inode_to_orphan(osb, inode); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + dwc->dw_orphaned = 1; + } + + ret = ocfs2_inode_lock(inode, &di_bh, 1); + if (ret) { + mlog_errno(ret); + goto out; + } + + if (first_get_block) { + if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) + ret = ocfs2_zero_tail(inode, di_bh, pos); + else + ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, + total_len, NULL); + if (ret < 0) { + mlog_errno(ret); + goto unlock; + } + } + + ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len, + OCFS2_WRITE_DIRECT, NULL, + (void **)&wc, di_bh, NULL); + if (ret) { + mlog_errno(ret); + goto unlock; + } + + desc = &wc->w_desc[0]; + + p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys); + BUG_ON(p_blkno == 0); + p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1); + + map_bh(bh_result, inode->i_sb, p_blkno); + bh_result->b_size = len; + if (desc->c_needs_zero) + set_buffer_new(bh_result); + + /* May sleep in end_io. It should not happen in a irq context. So defer + * it to dio work queue. */ + set_buffer_defer_completion(bh_result); + + if (!list_empty(&wc->w_unwritten_list)) { + struct ocfs2_unwritten_extent *ue = NULL; + + ue = list_first_entry(&wc->w_unwritten_list, + struct ocfs2_unwritten_extent, + ue_node); + BUG_ON(ue->ue_cpos != desc->c_cpos); + /* The physical address may be 0, fill it. */ + ue->ue_phys = desc->c_phys; + + list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list); + dwc->dw_zero_count++; + } + + ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, NULL, wc); + BUG_ON(ret != len); + ret = 0; +unlock: + ocfs2_inode_unlock(inode, 1); + brelse(di_bh); +out: + if (ret < 0) + ret = -EIO; + return ret; +} + +static void ocfs2_dio_end_io_write(struct inode *inode, + struct ocfs2_dio_write_ctxt *dwc, + loff_t offset, + ssize_t bytes) +{ + struct ocfs2_cached_dealloc_ctxt dealloc; + struct ocfs2_extent_tree et; + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + struct ocfs2_unwritten_extent *ue = NULL; + struct buffer_head *di_bh = NULL; + struct ocfs2_dinode *di; + struct ocfs2_alloc_context *data_ac = NULL; + struct ocfs2_alloc_context *meta_ac = NULL; + handle_t *handle = NULL; + loff_t end = offset + bytes; + int ret = 0, credits = 0, locked = 0; + + ocfs2_init_dealloc_ctxt(&dealloc); + + /* We do clear unwritten, delete orphan, change i_size here. If neither + * of these happen, we can skip all this. */ + if (list_empty(&dwc->dw_zero_list) && + end <= i_size_read(inode) && + !dwc->dw_orphaned) + goto out; + + ret = ocfs2_inode_lock(inode, &di_bh, 1); + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we + * are in that context. */ + if (dwc->dw_writer_pid != task_pid_nr(current)) { + mutex_lock(&inode->i_mutex); + locked = 1; + } + + /* Delete orphan before acquire i_mutex. */ + if (dwc->dw_orphaned) { + BUG_ON(dwc->dw_writer_pid != task_pid_nr(current)); + + end = end > i_size_read(inode) ? end : 0; + + ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, + !!end, end); + if (ret < 0) + mlog_errno(ret); + } + + di = (struct ocfs2_dinode *)di_bh; + + ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh); + + ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2, + &data_ac, &meta_ac); + + credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list); + + handle = ocfs2_start_trans(osb, credits); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + goto unlock; + } + ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) { + mlog_errno(ret); + goto commit; + } + + list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) { + ret = ocfs2_mark_extent_written(inode, &et, handle, + ue->ue_cpos, 1, + ue->ue_phys, + meta_ac, &dealloc); + if (ret < 0) { + mlog_errno(ret); + break; + } + } + + if (end > i_size_read(inode)) { + ret = ocfs2_set_inode_size(handle, inode, di_bh, end); + if (ret < 0) + mlog_errno(ret); + } +commit: + ocfs2_commit_trans(osb, handle); +unlock: + ocfs2_inode_unlock(inode, 1); + brelse(di_bh); +out: + ocfs2_run_deallocs(osb, &dealloc); + if (locked) + mutex_unlock(&inode->i_mutex); + ocfs2_dio_free_write_ctx(inode, dwc); + if (data_ac) + ocfs2_free_alloc_context(data_ac); + if (meta_ac) + ocfs2_free_alloc_context(meta_ac); +} + +/* + * ocfs2_dio_end_io is called by the dio core when a dio is finished. We're + * particularly interested in the aio/dio case. We use the rw_lock DLM lock + * to protect io on one node from truncation on another. + */ +static void ocfs2_dio_end_io(struct kiocb *iocb, + loff_t offset, + ssize_t bytes, + void *private) +{ + struct inode *inode = file_inode(iocb->ki_filp); + int level; + + /* this io's submitter should not have unlocked this before we could */ + BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); + + if (ocfs2_iocb_is_unaligned_aio(iocb)) { + ocfs2_iocb_clear_unaligned_aio(iocb); + + mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio); + } + + if (private) + ocfs2_dio_end_io_write(inode, private, offset, bytes); + + ocfs2_iocb_clear_rw_locked(iocb); + + level = ocfs2_iocb_rw_locked_level(iocb); + ocfs2_rw_unlock(inode, level); +} + +static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file)->i_mapping->host; + struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); + loff_t end = offset + iter->count; + get_block_t *get_block; + + /* + * Fallback to buffered I/O if we see an inode without + * extents. + */ + if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) + return 0; + + /* Fallback to buffered I/O if we do not support append dio. */ + if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb)) + return 0; + + if (iov_iter_rw(iter) == READ) + get_block = ocfs2_get_block; + else + get_block = ocfs2_dio_get_block; + + return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, + iter, offset, get_block, + ocfs2_dio_end_io, NULL, 0); +} + const struct address_space_operations ocfs2_aops = { .readpage = ocfs2_readpage, .readpages = ocfs2_readpages, diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 24e496d6bdcd..d06b80f58f83 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -47,9 +47,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); -int ocfs2_write_begin_nolock(struct file *filp, - struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, +typedef enum { + OCFS2_WRITE_BUFFER = 0, + OCFS2_WRITE_DIRECT, + OCFS2_WRITE_MMAP, +} ocfs2_write_type_t; + +int ocfs2_write_begin_nolock(struct address_space *mapping, + loff_t pos, unsigned len, ocfs2_write_type_t type, struct page **pagep, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page); diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index e36d63ff1783..f90931335c6b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -262,6 +262,7 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, struct dlm_lock *lock, int flags, int type) { enum dlm_status status; + u8 old_owner = res->owner; mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type, lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS); @@ -287,6 +288,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, status = DLM_DENIED; goto bail; } + + if (lock->ml.type == type && lock->ml.convert_type == LKM_IVMODE) { + mlog(0, "last convert request returned DLM_RECOVERING, but " + "owner has already queued and sent ast to me. res %.*s, " + "(cookie=%u:%llu, type=%d, conv=%d)\n", + res->lockname.len, res->lockname.name, + dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)), + dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)), + lock->ml.type, lock->ml.convert_type); + status = DLM_NORMAL; + goto bail; + } + res->state |= DLM_LOCK_RES_IN_PROGRESS; /* move lock to local convert queue */ /* do not alter lock refcount. switching lists. */ @@ -316,11 +330,19 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm, spin_lock(&res->spinlock); res->state &= ~DLM_LOCK_RES_IN_PROGRESS; lock->convert_pending = 0; - /* if it failed, move it back to granted queue */ + /* if it failed, move it back to granted queue. + * if master returns DLM_NORMAL and then down before sending ast, + * it may have already been moved to granted queue, reset to + * DLM_RECOVERING and retry convert */ if (status != DLM_NORMAL) { if (status != DLM_NOTQUEUED) dlm_error(status); dlm_revert_pending_convert(res, lock); + } else if ((res->state & DLM_LOCK_RES_RECOVERING) || + (old_owner != res->owner)) { + mlog(0, "res %.*s is in recovering or has been recovered.\n", + res->lockname.len, res->lockname.name); + status = DLM_RECOVERING; } bail: spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 9e4f862d20fe..8caf88160942 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2064,7 +2064,6 @@ void dlm_move_lockres_to_recovery_list(struct dlm_ctxt *dlm, dlm_lock_get(lock); if (lock->convert_pending) { /* move converting lock back to granted */ - BUG_ON(i != DLM_CONVERTING_LIST); mlog(0, "node died with convert pending " "on %.*s. move back to granted list.\n", res->lockname.len, res->lockname.name); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 0e5b4515f92e..05346fb8d5fd 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1373,44 +1373,6 @@ out: return ret; } -/* - * Will look for holes and unwritten extents in the range starting at - * pos for count bytes (inclusive). - */ -static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos, - size_t count) -{ - int ret = 0; - unsigned int extent_flags; - u32 cpos, clusters, extent_len, phys_cpos; - struct super_block *sb = inode->i_sb; - - cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits; - clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos; - - while (clusters) { - ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len, - &extent_flags); - if (ret < 0) { - mlog_errno(ret); - goto out; - } - - if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) { - ret = 1; - break; - } - - if (extent_len > clusters) - extent_len = clusters; - - clusters -= extent_len; - cpos += extent_len; - } -out: - return ret; -} - static int ocfs2_write_remove_suid(struct inode *inode) { int ret; @@ -2121,18 +2083,12 @@ out: static int ocfs2_prepare_inode_for_write(struct file *file, loff_t pos, - size_t count, - int appending, - int *direct_io, - int *has_refcount) + size_t count) { int ret = 0, meta_level = 0; struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); loff_t end; - struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - int full_coherency = !(osb->s_mount_opt & - OCFS2_MOUNT_COHERENCY_BUFFERED); /* * We start with a read level meta lock and only jump to an ex @@ -2181,10 +2137,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file, pos, count, &meta_level); - if (has_refcount) - *has_refcount = 1; - if (direct_io) - *direct_io = 0; } if (ret < 0) { @@ -2192,67 +2144,12 @@ static int ocfs2_prepare_inode_for_write(struct file *file, goto out_unlock; } - /* - * Skip the O_DIRECT checks if we don't need - * them. - */ - if (!direct_io || !(*direct_io)) - break; - - /* - * There's no sane way to do direct writes to an inode - * with inline data. - */ - if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { - *direct_io = 0; - break; - } - - /* - * Allowing concurrent direct writes means - * i_size changes wouldn't be synchronized, so - * one node could wind up truncating another - * nodes writes. - */ - if (end > i_size_read(inode) && !full_coherency) { - *direct_io = 0; - break; - } - - /* - * Fallback to old way if the feature bit is not set. - */ - if (end > i_size_read(inode) && - !ocfs2_supports_append_dio(osb)) { - *direct_io = 0; - break; - } - - /* - * We don't fill holes during direct io, so - * check for them here. If any are found, the - * caller will have to retake some cluster - * locks and initiate the io as buffered. - */ - ret = ocfs2_check_range_for_holes(inode, pos, count); - if (ret == 1) { - /* - * Fallback to old way if the feature bit is not set. - * Otherwise try dio first and then complete the rest - * request through buffer io. - */ - if (!ocfs2_supports_append_dio(osb)) - *direct_io = 0; - ret = 0; - } else if (ret < 0) - mlog_errno(ret); break; } out_unlock: trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno, - pos, appending, count, - direct_io, has_refcount); + pos, count); if (meta_level >= 0) ocfs2_inode_unlock(inode, meta_level); @@ -2264,18 +2161,16 @@ out: static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { - int direct_io, appending, rw_level; - int can_do_direct, has_refcount = 0; + int direct_io, rw_level; ssize_t written = 0; ssize_t ret; - size_t count = iov_iter_count(from), orig_count; + size_t count = iov_iter_count(from); struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); int unaligned_dio = 0; - int dropped_dio = 0; int append_write = ((iocb->ki_pos + count) >= i_size_read(inode) ? 1 : 0); @@ -2288,12 +2183,10 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, if (count == 0) return 0; - appending = iocb->ki_flags & IOCB_APPEND ? 1 : 0; direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; mutex_lock(&inode->i_mutex); -relock: /* * Concurrent O_DIRECT writes are allowed with * mount_option "coherency=buffered". @@ -2326,7 +2219,6 @@ relock: ocfs2_inode_unlock(inode, 1); } - orig_count = iov_iter_count(from); ret = generic_write_checks(iocb, from); if (ret <= 0) { if (ret) @@ -2335,9 +2227,7 @@ relock: } count = ret; - can_do_direct = direct_io; - ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, appending, - &can_do_direct, &has_refcount); + ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count); if (ret < 0) { mlog_errno(ret); goto out; @@ -2346,22 +2236,6 @@ relock: if (direct_io && !is_sync_kiocb(iocb)) unaligned_dio = ocfs2_is_io_unaligned(inode, count, iocb->ki_pos); - /* - * We can't complete the direct I/O as requested, fall back to - * buffered I/O. - */ - if (direct_io && !can_do_direct) { - ocfs2_rw_unlock(inode, rw_level); - - rw_level = -1; - - direct_io = 0; - iocb->ki_flags &= ~IOCB_DIRECT; - iov_iter_reexpand(from, orig_count); - dropped_dio = 1; - goto relock; - } - if (unaligned_dio) { /* * Wait on previous unaligned aio to complete before @@ -2397,7 +2271,7 @@ relock: goto no_sync; if (((file->f_flags & O_DSYNC) && !direct_io) || - IS_SYNC(inode) || dropped_dio) { + IS_SYNC(inode)) { ret = filemap_fdatawrite_range(file->f_mapping, iocb->ki_pos - written, iocb->ki_pos - 1); diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 8f87e05ee25d..0fd9ebdd3ed8 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1125,6 +1125,9 @@ static void ocfs2_clear_inode(struct inode *inode) mlog_bug_on_msg(!list_empty(&oi->ip_io_markers), "Clear inode of %llu, inode has io markers\n", (unsigned long long)oi->ip_blkno); + mlog_bug_on_msg(!list_empty(&oi->ip_unwritten_list), + "Clear inode of %llu, inode has unwritten extents\n", + (unsigned long long)oi->ip_blkno); ocfs2_extent_map_trunc(inode, 0); diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index aac8b86f312e..0c22ddd4b0dd 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -57,6 +57,9 @@ struct ocfs2_inode_info u32 ip_flags; /* see below */ u32 ip_attr; /* inode attributes */ + /* Record unwritten extents during direct io. */ + struct list_head ip_unwritten_list; + /* protected by recovery_lock. */ struct inode *ip_next_orphan; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 13534f4fe5b5..af0c6b36cc66 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -231,7 +231,7 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb) /* At this point, we know that no more recovery threads can be * launched, so wait for any recovery completion work to * complete. */ - flush_workqueue(ocfs2_wq); + flush_workqueue(osb->ocfs2_wq); /* * Now that recovery is shut down, and the osb is about to be @@ -1327,7 +1327,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal, spin_lock(&journal->j_lock); list_add_tail(&item->lri_list, &journal->j_la_cleanups); - queue_work(ocfs2_wq, &journal->j_recovery_work); + queue_work(journal->j_osb->ocfs2_wq, &journal->j_recovery_work); spin_unlock(&journal->j_lock); } @@ -1972,7 +1972,7 @@ static void ocfs2_orphan_scan_work(struct work_struct *work) mutex_lock(&os->os_lock); ocfs2_queue_orphan_scan(osb); if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE) - queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work, + queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work, ocfs2_orphan_scan_timeout()); mutex_unlock(&os->os_lock); } @@ -2012,7 +2012,7 @@ void ocfs2_orphan_scan_start(struct ocfs2_super *osb) atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); else { atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE); - queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work, + queue_delayed_work(osb->ocfs2_wq, &os->os_orphan_scan_work, ocfs2_orphan_scan_timeout()); } } diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 0a4457fb0711..3e1931273268 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -387,7 +387,7 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); - flush_workqueue(ocfs2_wq); + flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; @@ -1087,7 +1087,7 @@ static int ocfs2_recalc_la_window(struct ocfs2_super *osb, } else { osb->local_alloc_state = OCFS2_LA_DISABLED; } - queue_delayed_work(ocfs2_wq, &osb->la_enable_wq, + queue_delayed_work(osb->ocfs2_wq, &osb->la_enable_wq, OCFS2_LA_ENABLE_INTERVAL); goto out_unlock; } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 9581d190f6e1..a88707a0f4da 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -104,8 +104,8 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, if (page->index == last_index) len = ((size - 1) & ~PAGE_CACHE_MASK) + 1; - ret = ocfs2_write_begin_nolock(file, mapping, pos, len, 0, &locked_page, - &fsdata, di_bh, page); + ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, + &locked_page, &fsdata, di_bh, page); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 7a0126267847..6cf6538a0651 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -464,6 +464,14 @@ struct ocfs2_super struct ocfs2_refcount_tree *osb_ref_tree_lru; struct mutex system_file_mutex; + + /* + * OCFS2 needs to schedule several different types of work which + * require cluster locking, disk I/O, recovery waits, etc. Since these + * types of work tend to be heavy we avoid using the kernel events + * workqueue and schedule on our own. + */ + struct workqueue_struct *ocfs2_wq; }; #define OCFS2_SB(sb) ((struct ocfs2_super *)(sb)->s_fs_info) diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 6cb019b7c6a8..09d0c89a9daf 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -1450,28 +1450,20 @@ DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_remove_inode_range); TRACE_EVENT(ocfs2_prepare_inode_for_write, TP_PROTO(unsigned long long ino, unsigned long long saved_pos, - int appending, unsigned long count, - int *direct_io, int *has_refcount), - TP_ARGS(ino, saved_pos, appending, count, direct_io, has_refcount), + unsigned long count), + TP_ARGS(ino, saved_pos, count), TP_STRUCT__entry( __field(unsigned long long, ino) __field(unsigned long long, saved_pos) - __field(int, appending) __field(unsigned long, count) - __field(int, direct_io) - __field(int, has_refcount) ), TP_fast_assign( __entry->ino = ino; __entry->saved_pos = saved_pos; - __entry->appending = appending; __entry->count = count; - __entry->direct_io = direct_io ? *direct_io : -1; - __entry->has_refcount = has_refcount ? *has_refcount : -1; ), - TP_printk("%llu %llu %d %lu %d %d", __entry->ino, - __entry->saved_pos, __entry->appending, __entry->count, - __entry->direct_io, __entry->has_refcount) + TP_printk("%llu %llu %lu", __entry->ino, + __entry->saved_pos, __entry->count) ); DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index c93d67220887..44df24b62fef 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -726,7 +726,7 @@ static int ocfs2_release_dquot(struct dquot *dquot) dqgrab(dquot); /* First entry on list -> queue work */ if (llist_add(&OCFS2_DQUOT(dquot)->list, &osb->dquot_drop_list)) - queue_work(ocfs2_wq, &osb->dquot_drop_work); + queue_work(osb->ocfs2_wq, &osb->dquot_drop_work); goto out; } status = ocfs2_lock_global_qf(oinfo, 1); diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index d5da6f624142..10ad87ba02e0 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -187,7 +187,7 @@ static int update_backups(struct inode * inode, u32 clusters, char *data) for (i = 0; i < OCFS2_MAX_BACKUP_SUPERBLOCKS; i++) { blkno = ocfs2_backup_super_blkno(inode->i_sb, i); cluster = ocfs2_blocks_to_clusters(inode->i_sb, blkno); - if (cluster > clusters) + if (cluster >= clusters) break; ret = ocfs2_read_blocks_sync(osb, blkno, 1, &backup); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 2de4c8a9340c..427248de9da5 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -79,12 +79,6 @@ static struct kmem_cache *ocfs2_inode_cachep; struct kmem_cache *ocfs2_dquot_cachep; struct kmem_cache *ocfs2_qf_chunk_cachep; -/* OCFS2 needs to schedule several different types of work which - * require cluster locking, disk I/O, recovery waits, etc. Since these - * types of work tend to be heavy we avoid using the kernel events - * workqueue and schedule on our own. */ -struct workqueue_struct *ocfs2_wq = NULL; - static struct dentry *ocfs2_debugfs_root; MODULE_AUTHOR("Oracle"); @@ -1612,33 +1606,25 @@ static int __init ocfs2_init(void) if (status < 0) goto out2; - ocfs2_wq = create_singlethread_workqueue("ocfs2_wq"); - if (!ocfs2_wq) { - status = -ENOMEM; - goto out3; - } - ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL); if (!ocfs2_debugfs_root) { status = -ENOMEM; mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n"); - goto out4; + goto out3; } ocfs2_set_locking_protocol(); status = register_quota_format(&ocfs2_quota_format); if (status < 0) - goto out4; + goto out3; status = register_filesystem(&ocfs2_fs_type); if (!status) return 0; unregister_quota_format(&ocfs2_quota_format); -out4: - destroy_workqueue(ocfs2_wq); - debugfs_remove(ocfs2_debugfs_root); out3: + debugfs_remove(ocfs2_debugfs_root); ocfs2_free_mem_caches(); out2: exit_ocfs2_uptodate_cache(); @@ -1649,11 +1635,6 @@ out1: static void __exit ocfs2_exit(void) { - if (ocfs2_wq) { - flush_workqueue(ocfs2_wq); - destroy_workqueue(ocfs2_wq); - } - unregister_quota_format(&ocfs2_quota_format); debugfs_remove(ocfs2_debugfs_root); @@ -1744,6 +1725,7 @@ static void ocfs2_inode_init_once(void *data) spin_lock_init(&oi->ip_lock); ocfs2_extent_map_init(&oi->vfs_inode); INIT_LIST_HEAD(&oi->ip_io_markers); + INIT_LIST_HEAD(&oi->ip_unwritten_list); oi->ip_dir_start_lookup = 0; mutex_init(&oi->ip_unaligned_aio); init_rwsem(&oi->ip_alloc_sem); @@ -2348,6 +2330,12 @@ static int ocfs2_initialize_super(struct super_block *sb, } cleancache_init_shared_fs(sb); + osb->ocfs2_wq = create_singlethread_workqueue("ocfs2_wq"); + if (!osb->ocfs2_wq) { + status = -ENOMEM; + mlog_errno(status); + } + bail: return status; } @@ -2535,6 +2523,12 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb) { /* This function assumes that the caller has the main osb resource */ + /* ocfs2_initializer_super have already created this workqueue */ + if (osb->ocfs2_wq) { + flush_workqueue(osb->ocfs2_wq); + destroy_workqueue(osb->ocfs2_wq); + } + ocfs2_free_slot_info(osb); kfree(osb->osb_orphan_wipes); diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h index b477d0b1c7b6..b023e4f3d740 100644 --- a/fs/ocfs2/super.h +++ b/fs/ocfs2/super.h @@ -26,8 +26,6 @@ #ifndef OCFS2_SUPER_H #define OCFS2_SUPER_H -extern struct workqueue_struct *ocfs2_wq; - int ocfs2_publish_get_mount_state(struct ocfs2_super *osb, int node_num); 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 187b3b5f242e..9e0938bdf85d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -454,9 +454,10 @@ 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; @@ -465,23 +466,37 @@ 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; + } } } @@ -516,7 +531,8 @@ 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 @@ -532,8 +548,7 @@ 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, @@ -549,7 +564,7 @@ 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; @@ -838,7 +853,7 @@ 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; @@ -1112,7 +1127,7 @@ 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; @@ -1444,7 +1459,7 @@ 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/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h index b1bc954eccf3..0f3e16b1ea64 100644 --- a/include/asm-generic/dma-mapping-common.h +++ b/include/asm-generic/dma-mapping-common.h @@ -260,7 +260,7 @@ static inline void *dma_alloc_attrs(struct device *dev, size_t size, return NULL; cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr); + debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr, flag); return cpu_addr; } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 14b0ff32fb9f..63abda1ac06d 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -207,11 +207,6 @@ 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, @@ -619,10 +614,6 @@ 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/linux/configfs.h b/include/linux/configfs.h index a8a335b7fce0..758a029011b1 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -197,6 +197,16 @@ static inline struct configfs_subsystem *to_configfs_subsystem(struct config_gro int configfs_register_subsystem(struct configfs_subsystem *subsys); void configfs_unregister_subsystem(struct configfs_subsystem *subsys); +int configfs_register_group(struct config_group *parent_group, + struct config_group *group); +void configfs_unregister_group(struct config_group *group); + +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type); +void configfs_unregister_default_group(struct config_group *group); + /* These functions can sleep and can alloc with GFP_KERNEL */ /* WARNING: These cannot be called underneath configfs callbacks!! */ int configfs_depend_item(struct configfs_subsystem *subsys, struct config_item *target); diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h new file mode 100644 index 000000000000..bba7a4d692b3 --- /dev/null +++ b/include/linux/crc64_ecma.h @@ -0,0 +1,56 @@ +/* + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __CRC64_ECMA_H_ +#define __CRC64_ECMA_H_ + +#include <linux/types.h> + + +#define CRC64_DEFAULT_INITVAL 0xFFFFFFFFFFFFFFFFULL + + +/* + * crc64_ecma_seed - Initializes the CRC64 ECMA seed. + */ +u64 crc64_ecma_seed(void); + +/* + * crc64_ecma - Computes the 64 bit ECMA CRC. + * + * @pdata: pointer to the data to compute checksum for. + * @nbytes: number of bytes in data buffer. + * @seed: CRC seed. + */ +u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed); + +#endif /* __CRC64_ECMA_H_ */ diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h index fe8cb610deac..e5f539dd56bf 100644 --- a/include/linux/dma-debug.h +++ b/include/linux/dma-debug.h @@ -51,7 +51,8 @@ extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, int dir); extern void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt); + dma_addr_t dma_addr, void *virt, + gfp_t flags); extern void debug_dma_free_coherent(struct device *dev, size_t size, void *virt, dma_addr_t addr); @@ -132,7 +133,8 @@ static inline void debug_dma_unmap_sg(struct device *dev, } static inline void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt) + dma_addr_t dma_addr, void *virt, + gfp_t flags) { } diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ecb080d6ff42..72cd942edb22 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -25,7 +25,7 @@ extern int zap_huge_pmd(struct mmu_gather *tlb, 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, @@ -48,17 +48,6 @@ 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) @@ -95,30 +84,27 @@ 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)) \ + __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 +114,17 @@ 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)) return __pmd_trans_huge_lock(pmd, vma, ptl); else - return 0; + return false; } static inline int hpage_nr_pages(struct page *page) { @@ -183,11 +169,8 @@ 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 +184,10 @@ 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, diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h new file mode 100644 index 000000000000..c2f33b2b35a5 --- /dev/null +++ b/include/linux/iio/sw_trigger.h @@ -0,0 +1,71 @@ +/* + * Industrial I/O software trigger interface + * + * Copyright (c) 2015 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#ifndef __IIO_SW_TRIGGER +#define __IIO_SW_TRIGGER + +#include <linux/module.h> +#include <linux/device.h> +#include <linux/iio/iio.h> +#include <linux/configfs.h> + +#define module_iio_sw_trigger_driver(__iio_sw_trigger_type) \ + module_driver(__iio_sw_trigger_type, iio_register_sw_trigger_type, \ + iio_unregister_sw_trigger_type) + +extern struct configfs_subsystem iio_configfs_subsys; +struct iio_sw_trigger_ops; + +struct iio_sw_trigger_type { + const char *name; + struct module *owner; + const struct iio_sw_trigger_ops *ops; + struct list_head list; + struct config_group *group; +}; + +struct iio_sw_trigger { + struct iio_trigger *trigger; + struct iio_sw_trigger_type *trigger_type; + struct config_group group; +}; + +struct iio_sw_trigger_ops { + struct iio_sw_trigger* (*probe)(const char *); + int (*remove)(struct iio_sw_trigger *); +}; + +static inline +struct iio_sw_trigger *to_iio_sw_trigger(struct config_item *item) +{ + return container_of(to_config_group(item), struct iio_sw_trigger, + group); +} + +int iio_register_sw_trigger_type(struct iio_sw_trigger_type *tt); +void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *tt); + +struct iio_sw_trigger *iio_sw_trigger_create(const char *, const char *); +void iio_sw_trigger_destroy(struct iio_sw_trigger *); + +int iio_sw_trigger_type_configfs_register(struct iio_sw_trigger_type *tt); +void iio_sw_trigger_type_configfs_unregister(struct iio_sw_trigger_type *tt); + +static inline +void iio_swt_group_init_type_name(struct iio_sw_trigger *t, + const char *name, + struct config_item_type *type) +{ +#ifdef CONFIG_CONFIGFS_FS + config_group_init_type_name(&t->group, name, type); +#endif +} + +#endif /* __IIO_SW_TRIGGER */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d140b1e9faa7..2da38f093391 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -269,6 +269,8 @@ unsigned long paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) +#define VMCOREINFO_PHYS_BASE(value) \ + vmcoreinfo_append_str("PHYS_BASE=%lx\n", (unsigned long)value) extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index cd0e2413c358..ffc5460ed9e5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -294,10 +294,12 @@ 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); @@ -513,7 +515,8 @@ 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; @@ -521,12 +524,13 @@ 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/mm.h b/include/linux/mm.h index 00bad7793788..fc9a3b8335bd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -395,39 +395,17 @@ 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 -} - -static inline void compound_unlock(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; + return &page[1].compound_mapcount; } -static inline void compound_unlock_irqrestore(struct page *page, - unsigned long flags) +static inline int compound_mapcount(struct page *page) { -#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; } /* @@ -440,55 +418,34 @@ 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); + if (unlikely(PageCompound(page))) + return __page_mapcount(page); + return atomic_read(&page->_mapcount) + 1; } -/* - * 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) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int total_mapcount(struct page *page); +#else +static inline int total_mapcount(struct page *page) { - VM_BUG_ON_PAGE(!PageHead(page), page); - return __compound_tail_refcounted(page); + return page_mapcount(page); } +#endif -static inline void get_huge_page_tail(struct page *page) +static inline int page_count(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 atomic_read(&compound_head(page)->_count); } -extern bool __get_page_tail(struct page *page); - static inline void get_page(struct page *page) { - if (unlikely(PageTail(page))) - if (likely(__get_page_tail(page))) - return; + page = compound_head(page); /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. @@ -513,7 +470,15 @@ 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); + +static inline void put_page(struct page *page) +{ + page = compound_head(page); + if (put_page_testzero(page)) + __put_page(page); +} + void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); @@ -533,6 +498,9 @@ 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[]; @@ -562,6 +530,8 @@ 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 @@ -978,10 +948,21 @@ 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; } /* @@ -2222,7 +2203,7 @@ 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 f8d1492a114f..5e37e918c614 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; diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 877ef226f90f..c447d8055e50 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -55,4 +55,10 @@ 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..dab6cff11e18 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 +126,108 @@ 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); } + { return test_and_clear_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); } + { 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; } @@ -204,47 +256,56 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; } #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 +318,34 @@ 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) + __TESTCLEARFLAG(Mlocked, mlocked, PF_NO_TAIL) #else PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_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 +353,10 @@ 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 +381,7 @@ 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 +394,7 @@ 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 +406,9 @@ 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 +425,24 @@ 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 +462,7 @@ 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 +474,6 @@ 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 +534,43 @@ 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 +654,6 @@ 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 +663,7 @@ 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 +690,10 @@ 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/poison.h b/include/linux/poison.h index 317e16de09e5..deabe23b426d 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. @@ -73,6 +77,9 @@ #define MUTEX_DEBUG_INIT 0x11 #define MUTEX_DEBUG_FREE 0x22 +/********** lib/dma_debug.c **********/ +#define DMA_ALLOC_POISON 0xee + /********** lib/flex_array.c **********/ #define FLEX_ARRAY_FREE 0x6c /* for use-after-free poisoning */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 29446aeef36e..ebf3750e42b2 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -161,25 +161,31 @@ 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); } /* diff --git a/include/linux/slab.h b/include/linux/slab.h index 7c82e3b307a3..96940772bb92 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -158,6 +158,24 @@ size_t ksize(const void *); #endif /* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + +/* + * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned + * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN + * aligned pointers. + */ +#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) +#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) +#define __assume_page_alignment __assume_aligned(PAGE_SIZE) + +/* * Kmalloc array related definitions */ @@ -286,8 +304,8 @@ static __always_inline int kmalloc_index(size_t size) } #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags); -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags); +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment; +void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment; void kmem_cache_free(struct kmem_cache *, void *); /* @@ -301,8 +319,8 @@ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); bool kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node); -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment; +void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -316,12 +334,12 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t); +extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size); + int node, size_t size) __assume_slab_alignment; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, @@ -354,10 +372,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) @@ -482,15 +500,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) return __kmalloc_node(size, flags, node); } -/* - * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. - * Intended for arches that get misalignment faults even for 64 bit integer - * aligned buffers. - */ -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - struct memcg_cache_array { struct rcu_head rcu; struct kmem_cache *entries[0]; diff --git a/include/linux/string.h b/include/linux/string.h index 9ef7795e65e4..cc77d6477fc2 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -121,6 +121,7 @@ extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp); extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); +extern char *kstrimdup(const char *s, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); diff --git a/include/linux/swap.h b/include/linux/swap.h index 7ba7dccaf0e7..457181844b6e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -154,7 +154,7 @@ enum { SWP_SCANNING = (1 << 10), /* refcount in scan_swap_map */ }; -#define SWAP_CLUSTER_MAX 32UL +#define SWAP_CLUSTER_MAX 256UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* @@ -539,7 +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..e1f8c993e73b 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -68,7 +68,9 @@ 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 new file mode 100644 index 000000000000..11c59ca5e145 --- /dev/null +++ b/include/trace/events/huge_memory.h @@ -0,0 +1,166 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM huge_memory + +#if !defined(__HUGE_MEMORY_H) || defined(TRACE_HEADER_MULTI_READ) +#define __HUGE_MEMORY_H + +#include <linux/tracepoint.h> + +#include <trace/events/gfpflags.h> + +#define SCAN_STATUS \ + EM( SCAN_FAIL, "failed") \ + EM( SCAN_SUCCEED, "succeeded") \ + EM( SCAN_PMD_NULL, "pmd_null") \ + EM( SCAN_EXCEED_NONE_PTE, "exceed_none_pte") \ + EM( SCAN_PTE_NON_PRESENT, "pte_non_present") \ + EM( SCAN_PAGE_RO, "no_writable_page") \ + EM( SCAN_NO_REFERENCED_PAGE, "no_referenced_page") \ + EM( SCAN_PAGE_NULL, "page_null") \ + EM( SCAN_SCAN_ABORT, "scan_aborted") \ + EM( SCAN_PAGE_COUNT, "not_suitable_page_count") \ + 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") \ + EM( SCAN_ADDRESS_RANGE, "not_suitable_address_range") \ + EM( SCAN_SWAP_CACHE_PAGE, "page_swap_cache") \ + EM( SCAN_DEL_PAGE_LRU, "could_not_delete_page_from_lru")\ + EM( SCAN_ALLOC_HUGE_PAGE_FAIL, "alloc_huge_page_failed") \ + EM( SCAN_CGROUP_CHARGE_FAIL, "ccgroup_charge_failed") \ + EMe( SCAN_EXCEED_SWAP_PTE, "exceed_swap_pte") + +#undef EM +#undef EMe +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +SCAN_STATUS + +#undef EM +#undef EMe +#define EM(a, b) {a, b}, +#define EMe(a, b) {a, b} + +TRACE_EVENT(mm_khugepaged_scan_pmd, + + TP_PROTO(struct mm_struct *mm, unsigned long pfn, bool writable, + bool referenced, int none_or_zero, int status, int unmapped), + + TP_ARGS(mm, pfn, writable, referenced, none_or_zero, status, unmapped), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(unsigned long, pfn) + __field(bool, writable) + __field(bool, referenced) + __field(int, none_or_zero) + __field(int, status) + __field(int, unmapped) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->pfn = pfn; + __entry->writable = writable; + __entry->referenced = referenced; + __entry->none_or_zero = none_or_zero; + __entry->status = status; + __entry->unmapped = unmapped; + ), + + TP_printk("mm=%p, scan_pfn=0x%lx, writable=%d, referenced=%d, none_or_zero=%d, status=%s, unmapped=%d", + __entry->mm, + __entry->pfn, + __entry->writable, + __entry->referenced, + __entry->none_or_zero, + __print_symbolic(__entry->status, SCAN_STATUS), + __entry->unmapped) +); + +TRACE_EVENT(mm_collapse_huge_page, + + TP_PROTO(struct mm_struct *mm, int isolated, int status), + + TP_ARGS(mm, isolated, status), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(int, isolated) + __field(int, status) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->isolated = isolated; + __entry->status = status; + ), + + TP_printk("mm=%p, isolated=%d, status=%s", + __entry->mm, + __entry->isolated, + __print_symbolic(__entry->status, SCAN_STATUS)) +); + +TRACE_EVENT(mm_collapse_huge_page_isolate, + + TP_PROTO(unsigned long pfn, int none_or_zero, + bool referenced, bool writable, int status), + + TP_ARGS(pfn, none_or_zero, referenced, writable, status), + + TP_STRUCT__entry( + __field(unsigned long, pfn) + __field(int, none_or_zero) + __field(bool, referenced) + __field(bool, writable) + __field(int, status) + ), + + TP_fast_assign( + __entry->pfn = pfn; + __entry->none_or_zero = none_or_zero; + __entry->referenced = referenced; + __entry->writable = writable; + __entry->status = status; + ), + + TP_printk("scan_pfn=0x%lx, none_or_zero=%d, referenced=%d, writable=%d, status=%s", + __entry->pfn, + __entry->none_or_zero, + __entry->referenced, + __entry->writable, + __print_symbolic(__entry->status, SCAN_STATUS)) +); + +TRACE_EVENT(mm_collapse_huge_page_swapin, + + TP_PROTO(struct mm_struct *mm, int swapped_in, int ret), + + TP_ARGS(mm, swapped_in, ret), + + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(int, swapped_in) + __field(int, ret) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->swapped_in = swapped_in; + __entry->ret = ret; + ), + + TP_printk("mm=%p, swapped_in=%d, ret=%d", + __entry->mm, + __entry->swapped_in, + __entry->ret) +); + +#endif /* __HUGE_MEMORY_H */ +#include <trace/define_trace.h> + diff --git a/ipc/msg.c b/ipc/msg.c index 1471db9a7e61..59559a215401 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -37,6 +37,7 @@ #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/ipc_namespace.h> +#include <linux/freezer.h> #include <asm/current.h> #include <linux/uaccess.h> @@ -675,7 +676,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); - schedule(); + freezable_schedule(); rcu_read_lock(); ipc_lock_object(&msq->q_perm); @@ -917,7 +918,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl ipc_unlock_object(&msq->q_perm); rcu_read_unlock(); - schedule(); + freezable_schedule(); /* Lockless receive, part 1: * Disable preemption. We don't hold a reference to the queue diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4e5e9798aa0c..51373997f479 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 684d7549825a..b29add22c454 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; } diff --git a/lib/Kconfig b/lib/Kconfig index f0df318104e7..f7e64c7748cb 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -185,6 +185,13 @@ config CRC8 when they need to do cyclic redundancy check according CRC8 algorithm. Module will be called crc8. +config CRC64_ECMA + tristate "CRC64 ECMA function" + help + This option provides CRC64 ECMA function. Drivers may select this + when they need to do cyclic redundancy check according to the CRC64 + ECMA algorithm. + config AUDIT_GENERIC bool depends on AUDIT && !AUDIT_ARCH diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 749e886a94b6..526105c18566 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 @@ -1765,6 +1773,16 @@ config DMA_API_DEBUG If unsure, say N. +config DMA_API_DEBUG_POISON + bool "Poison coherent DMA buffers" + depends on DMA_API_DEBUG && EXPERT + help + Poison DMA buffers returned by dma_alloc_coherent unless __GFP_ZERO + is explicitly specified, to catch drivers depending on zeroed buffers + without passing the correct flags. + + Only say Y if you're prepared for almost everything to break. + config TEST_LKM tristate "Test module loading with 'hello world' module" default n diff --git a/lib/Makefile b/lib/Makefile index d82cb5bac5bc..5f4a9e8c1779 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -84,6 +84,7 @@ obj-$(CONFIG_CRC32) += crc32.o obj-$(CONFIG_CRC7) += crc7.o obj-$(CONFIG_LIBCRC32C) += libcrc32c.o obj-$(CONFIG_CRC8) += crc8.o +obj-$(CONFIG_CRC64_ECMA) += crc64_ecma.o obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o obj-$(CONFIG_842_COMPRESS) += 842/ diff --git a/lib/crc64_ecma.c b/lib/crc64_ecma.c new file mode 100644 index 000000000000..41629ea5a60c --- /dev/null +++ b/lib/crc64_ecma.c @@ -0,0 +1,341 @@ +/* + * Copyright 2013 Freescale Semiconductor Inc. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of Freescale Semiconductor nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/module.h> +#include <linux/crc64_ecma.h> + + +#define CRC64_BYTE_MASK 0xFF +#define CRC64_TABLE_SIZE 256 + + +struct crc64_table { + u64 seed; + u64 table[CRC64_TABLE_SIZE]; +}; + + +static struct crc64_table CRC64_ECMA_182 = { + CRC64_DEFAULT_INITVAL, + { + 0x0000000000000000ULL, + 0xb32e4cbe03a75f6fULL, + 0xf4843657a840a05bULL, + 0x47aa7ae9abe7ff34ULL, + 0x7bd0c384ff8f5e33ULL, + 0xc8fe8f3afc28015cULL, + 0x8f54f5d357cffe68ULL, + 0x3c7ab96d5468a107ULL, + 0xf7a18709ff1ebc66ULL, + 0x448fcbb7fcb9e309ULL, + 0x0325b15e575e1c3dULL, + 0xb00bfde054f94352ULL, + 0x8c71448d0091e255ULL, + 0x3f5f08330336bd3aULL, + 0x78f572daa8d1420eULL, + 0xcbdb3e64ab761d61ULL, + 0x7d9ba13851336649ULL, + 0xceb5ed8652943926ULL, + 0x891f976ff973c612ULL, + 0x3a31dbd1fad4997dULL, + 0x064b62bcaebc387aULL, + 0xb5652e02ad1b6715ULL, + 0xf2cf54eb06fc9821ULL, + 0x41e11855055bc74eULL, + 0x8a3a2631ae2dda2fULL, + 0x39146a8fad8a8540ULL, + 0x7ebe1066066d7a74ULL, + 0xcd905cd805ca251bULL, + 0xf1eae5b551a2841cULL, + 0x42c4a90b5205db73ULL, + 0x056ed3e2f9e22447ULL, + 0xb6409f5cfa457b28ULL, + 0xfb374270a266cc92ULL, + 0x48190ecea1c193fdULL, + 0x0fb374270a266cc9ULL, + 0xbc9d3899098133a6ULL, + 0x80e781f45de992a1ULL, + 0x33c9cd4a5e4ecdceULL, + 0x7463b7a3f5a932faULL, + 0xc74dfb1df60e6d95ULL, + 0x0c96c5795d7870f4ULL, + 0xbfb889c75edf2f9bULL, + 0xf812f32ef538d0afULL, + 0x4b3cbf90f69f8fc0ULL, + 0x774606fda2f72ec7ULL, + 0xc4684a43a15071a8ULL, + 0x83c230aa0ab78e9cULL, + 0x30ec7c140910d1f3ULL, + 0x86ace348f355aadbULL, + 0x3582aff6f0f2f5b4ULL, + 0x7228d51f5b150a80ULL, + 0xc10699a158b255efULL, + 0xfd7c20cc0cdaf4e8ULL, + 0x4e526c720f7dab87ULL, + 0x09f8169ba49a54b3ULL, + 0xbad65a25a73d0bdcULL, + 0x710d64410c4b16bdULL, + 0xc22328ff0fec49d2ULL, + 0x85895216a40bb6e6ULL, + 0x36a71ea8a7ace989ULL, + 0x0adda7c5f3c4488eULL, + 0xb9f3eb7bf06317e1ULL, + 0xfe5991925b84e8d5ULL, + 0x4d77dd2c5823b7baULL, + 0x64b62bcaebc387a1ULL, + 0xd7986774e864d8ceULL, + 0x90321d9d438327faULL, + 0x231c512340247895ULL, + 0x1f66e84e144cd992ULL, + 0xac48a4f017eb86fdULL, + 0xebe2de19bc0c79c9ULL, + 0x58cc92a7bfab26a6ULL, + 0x9317acc314dd3bc7ULL, + 0x2039e07d177a64a8ULL, + 0x67939a94bc9d9b9cULL, + 0xd4bdd62abf3ac4f3ULL, + 0xe8c76f47eb5265f4ULL, + 0x5be923f9e8f53a9bULL, + 0x1c4359104312c5afULL, + 0xaf6d15ae40b59ac0ULL, + 0x192d8af2baf0e1e8ULL, + 0xaa03c64cb957be87ULL, + 0xeda9bca512b041b3ULL, + 0x5e87f01b11171edcULL, + 0x62fd4976457fbfdbULL, + 0xd1d305c846d8e0b4ULL, + 0x96797f21ed3f1f80ULL, + 0x2557339fee9840efULL, + 0xee8c0dfb45ee5d8eULL, + 0x5da24145464902e1ULL, + 0x1a083bacedaefdd5ULL, + 0xa9267712ee09a2baULL, + 0x955cce7fba6103bdULL, + 0x267282c1b9c65cd2ULL, + 0x61d8f8281221a3e6ULL, + 0xd2f6b4961186fc89ULL, + 0x9f8169ba49a54b33ULL, + 0x2caf25044a02145cULL, + 0x6b055fede1e5eb68ULL, + 0xd82b1353e242b407ULL, + 0xe451aa3eb62a1500ULL, + 0x577fe680b58d4a6fULL, + 0x10d59c691e6ab55bULL, + 0xa3fbd0d71dcdea34ULL, + 0x6820eeb3b6bbf755ULL, + 0xdb0ea20db51ca83aULL, + 0x9ca4d8e41efb570eULL, + 0x2f8a945a1d5c0861ULL, + 0x13f02d374934a966ULL, + 0xa0de61894a93f609ULL, + 0xe7741b60e174093dULL, + 0x545a57dee2d35652ULL, + 0xe21ac88218962d7aULL, + 0x5134843c1b317215ULL, + 0x169efed5b0d68d21ULL, + 0xa5b0b26bb371d24eULL, + 0x99ca0b06e7197349ULL, + 0x2ae447b8e4be2c26ULL, + 0x6d4e3d514f59d312ULL, + 0xde6071ef4cfe8c7dULL, + 0x15bb4f8be788911cULL, + 0xa6950335e42fce73ULL, + 0xe13f79dc4fc83147ULL, + 0x521135624c6f6e28ULL, + 0x6e6b8c0f1807cf2fULL, + 0xdd45c0b11ba09040ULL, + 0x9aefba58b0476f74ULL, + 0x29c1f6e6b3e0301bULL, + 0xc96c5795d7870f42ULL, + 0x7a421b2bd420502dULL, + 0x3de861c27fc7af19ULL, + 0x8ec62d7c7c60f076ULL, + 0xb2bc941128085171ULL, + 0x0192d8af2baf0e1eULL, + 0x4638a2468048f12aULL, + 0xf516eef883efae45ULL, + 0x3ecdd09c2899b324ULL, + 0x8de39c222b3eec4bULL, + 0xca49e6cb80d9137fULL, + 0x7967aa75837e4c10ULL, + 0x451d1318d716ed17ULL, + 0xf6335fa6d4b1b278ULL, + 0xb199254f7f564d4cULL, + 0x02b769f17cf11223ULL, + 0xb4f7f6ad86b4690bULL, + 0x07d9ba1385133664ULL, + 0x4073c0fa2ef4c950ULL, + 0xf35d8c442d53963fULL, + 0xcf273529793b3738ULL, + 0x7c0979977a9c6857ULL, + 0x3ba3037ed17b9763ULL, + 0x888d4fc0d2dcc80cULL, + 0x435671a479aad56dULL, + 0xf0783d1a7a0d8a02ULL, + 0xb7d247f3d1ea7536ULL, + 0x04fc0b4dd24d2a59ULL, + 0x3886b22086258b5eULL, + 0x8ba8fe9e8582d431ULL, + 0xcc0284772e652b05ULL, + 0x7f2cc8c92dc2746aULL, + 0x325b15e575e1c3d0ULL, + 0x8175595b76469cbfULL, + 0xc6df23b2dda1638bULL, + 0x75f16f0cde063ce4ULL, + 0x498bd6618a6e9de3ULL, + 0xfaa59adf89c9c28cULL, + 0xbd0fe036222e3db8ULL, + 0x0e21ac88218962d7ULL, + 0xc5fa92ec8aff7fb6ULL, + 0x76d4de52895820d9ULL, + 0x317ea4bb22bfdfedULL, + 0x8250e80521188082ULL, + 0xbe2a516875702185ULL, + 0x0d041dd676d77eeaULL, + 0x4aae673fdd3081deULL, + 0xf9802b81de97deb1ULL, + 0x4fc0b4dd24d2a599ULL, + 0xfceef8632775faf6ULL, + 0xbb44828a8c9205c2ULL, + 0x086ace348f355aadULL, + 0x34107759db5dfbaaULL, + 0x873e3be7d8faa4c5ULL, + 0xc094410e731d5bf1ULL, + 0x73ba0db070ba049eULL, + 0xb86133d4dbcc19ffULL, + 0x0b4f7f6ad86b4690ULL, + 0x4ce50583738cb9a4ULL, + 0xffcb493d702be6cbULL, + 0xc3b1f050244347ccULL, + 0x709fbcee27e418a3ULL, + 0x3735c6078c03e797ULL, + 0x841b8ab98fa4b8f8ULL, + 0xadda7c5f3c4488e3ULL, + 0x1ef430e13fe3d78cULL, + 0x595e4a08940428b8ULL, + 0xea7006b697a377d7ULL, + 0xd60abfdbc3cbd6d0ULL, + 0x6524f365c06c89bfULL, + 0x228e898c6b8b768bULL, + 0x91a0c532682c29e4ULL, + 0x5a7bfb56c35a3485ULL, + 0xe955b7e8c0fd6beaULL, + 0xaeffcd016b1a94deULL, + 0x1dd181bf68bdcbb1ULL, + 0x21ab38d23cd56ab6ULL, + 0x9285746c3f7235d9ULL, + 0xd52f0e859495caedULL, + 0x6601423b97329582ULL, + 0xd041dd676d77eeaaULL, + 0x636f91d96ed0b1c5ULL, + 0x24c5eb30c5374ef1ULL, + 0x97eba78ec690119eULL, + 0xab911ee392f8b099ULL, + 0x18bf525d915feff6ULL, + 0x5f1528b43ab810c2ULL, + 0xec3b640a391f4fadULL, + 0x27e05a6e926952ccULL, + 0x94ce16d091ce0da3ULL, + 0xd3646c393a29f297ULL, + 0x604a2087398eadf8ULL, + 0x5c3099ea6de60cffULL, + 0xef1ed5546e415390ULL, + 0xa8b4afbdc5a6aca4ULL, + 0x1b9ae303c601f3cbULL, + 0x56ed3e2f9e224471ULL, + 0xe5c372919d851b1eULL, + 0xa26908783662e42aULL, + 0x114744c635c5bb45ULL, + 0x2d3dfdab61ad1a42ULL, + 0x9e13b115620a452dULL, + 0xd9b9cbfcc9edba19ULL, + 0x6a978742ca4ae576ULL, + 0xa14cb926613cf817ULL, + 0x1262f598629ba778ULL, + 0x55c88f71c97c584cULL, + 0xe6e6c3cfcadb0723ULL, + 0xda9c7aa29eb3a624ULL, + 0x69b2361c9d14f94bULL, + 0x2e184cf536f3067fULL, + 0x9d36004b35545910ULL, + 0x2b769f17cf112238ULL, + 0x9858d3a9ccb67d57ULL, + 0xdff2a94067518263ULL, + 0x6cdce5fe64f6dd0cULL, + 0x50a65c93309e7c0bULL, + 0xe388102d33392364ULL, + 0xa4226ac498dedc50ULL, + 0x170c267a9b79833fULL, + 0xdcd7181e300f9e5eULL, + 0x6ff954a033a8c131ULL, + 0x28532e49984f3e05ULL, + 0x9b7d62f79be8616aULL, + 0xa707db9acf80c06dULL, + 0x14299724cc279f02ULL, + 0x5383edcd67c06036ULL, + 0xe0ada17364673f59ULL + } +}; + + +/* + * crc64_ecma_seed - Initializes the CRC64 ECMA seed. + */ +u64 crc64_ecma_seed(void) +{ + return CRC64_ECMA_182.seed; +} +EXPORT_SYMBOL(crc64_ecma_seed); + +/* + * crc64_ecma - Computes the 64 bit ECMA CRC. + * + * pdata: pointer to the data to compute checksum for. + * nbytes: number of bytes in data buffer. + * seed: CRC seed. + */ +u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed) +{ + unsigned int i; + u64 crc = seed; + + for (i = 0; i < nbytes; i++) + crc = CRC64_ECMA_182.table[(crc ^ pdata[i]) & CRC64_BYTE_MASK] ^ + (crc >> 8); + + return crc; +} +EXPORT_SYMBOL(crc64_ecma); + +MODULE_DESCRIPTION("CRC64 ECMA function"); +MODULE_AUTHOR("Freescale Semiconductor Inc."); +MODULE_LICENSE("GPL"); diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 8855f019ebe8..af6262b4e02c 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -30,6 +30,7 @@ #include <linux/sched.h> #include <linux/ctype.h> #include <linux/list.h> +#include <linux/poison.h> #include <linux/slab.h> #include <asm/sections.h> @@ -1447,7 +1448,7 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, EXPORT_SYMBOL(debug_dma_unmap_sg); void debug_dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t dma_addr, void *virt) + dma_addr_t dma_addr, void *virt, gfp_t flags) { struct dma_debug_entry *entry; @@ -1457,6 +1458,9 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, if (unlikely(virt == NULL)) return; + if (IS_ENABLED(CONFIG_DMA_API_DEBUG_POISON) && !(flags & __GFP_ZERO)) + memset(virt, DMA_ALLOC_POISON, size); + entry = dma_entry_alloc(); if (!entry) return; diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 5939f63d90cd..5c88204b6f1f 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -43,50 +43,73 @@ void string_get_size(u64 size, u64 blk_size, const enum string_size_units units, [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; - int i, j; - u32 remainder = 0, sf_cap, exp; + static const unsigned int rounding[] = { 500, 50, 5 }; + int i = 0, j; + u32 remainder = 0, sf_cap; char tmp[8]; const char *unit; tmp[0] = '\0'; - i = 0; - if (!size) + + if (blk_size == 0) + size = 0; + if (size == 0) goto out; - while (blk_size >= divisor[units]) { - remainder = do_div(blk_size, divisor[units]); + /* This is Napier's algorithm. Reduce the original block size to + * + * coefficient * divisor[units]^i + * + * we do the reduction so both coefficients are just under 32 bits so + * that multiplying them together won't overflow 64 bits and we keep + * as much precision as possible in the numbers. + * + * Note: it's safe to throw away the remainders here because all the + * precision is in the coefficients. + */ + while (blk_size >> 32) { + do_div(blk_size, divisor[units]); i++; } - exp = divisor[units] / (u32)blk_size; - /* - * size must be strictly greater than exp here to ensure that remainder - * is greater than divisor[units] coming out of the if below. - */ - if (size > exp) { - remainder = do_div(size, divisor[units]); - remainder *= blk_size; + while (size >> 32) { + do_div(size, divisor[units]); i++; - } else { - remainder *= size; } + /* now perform the actual multiplication keeping i as the sum of the + * two logarithms */ size *= blk_size; - size += remainder / divisor[units]; - remainder %= divisor[units]; + /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units]) { remainder = do_div(size, divisor[units]); i++; } + /* work out in j how many digits of precision we need from the + * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; - if (j) { + if (units == STRING_UNITS_2) { + /* express the remainder as a decimal. It's currently the + * numerator of a fraction whose denominator is + * divisor[units], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; - remainder /= divisor[units]; + remainder >>= 10; + } + + /* add a 5 to the digit below what will be printed to ensure + * an arithmetical round up and carry it through to size */ + remainder += rounding[j]; + if (remainder >= 1000) { + remainder -= 1000; + size += 1; + } + + if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } diff --git a/mm/debug.c b/mm/debug.c index 668aa35191ca..836276586185 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 1bb007624b53..834cd1425307 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); @@ -116,8 +116,21 @@ retry: } } + 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_foll(page); + get_page(page); if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -130,6 +143,10 @@ 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 +237,38 @@ 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); - } - 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 + 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, @@ -896,7 +924,6 @@ 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 +1063,6 @@ 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 +1090,7 @@ 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 +1102,17 @@ 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 +1145,7 @@ 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 +1154,6 @@ 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 +1174,13 @@ 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 +1189,6 @@ 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 +1209,6 @@ 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 +1217,7 @@ 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 +1225,6 @@ 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 +1245,6 @@ 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 +1259,7 @@ 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 c29ddebc8705..6834b39a7114 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -26,11 +26,41 @@ #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> +#include <linux/swapops.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" +enum scan_result { + SCAN_FAIL, + SCAN_SUCCEED, + SCAN_PMD_NULL, + SCAN_EXCEED_NONE_PTE, + SCAN_PTE_NON_PRESENT, + SCAN_PAGE_RO, + SCAN_NO_REFERENCED_PAGE, + SCAN_PAGE_NULL, + SCAN_SCAN_ABORT, + SCAN_PAGE_COUNT, + SCAN_PAGE_LRU, + SCAN_PAGE_LOCK, + SCAN_PAGE_ANON, + SCAN_PAGE_COMPOUND, + SCAN_ANY_PROCESS, + SCAN_VMA_NULL, + SCAN_VMA_CHECK, + SCAN_ADDRESS_RANGE, + SCAN_SWAP_CACHE_PAGE, + SCAN_DEL_PAGE_LRU, + SCAN_ALLOC_HUGE_PAGE_FAIL, + SCAN_CGROUP_CHARGE_FAIL, + SCAN_EXCEED_SWAP_PTE +}; + +#define CREATE_TRACE_POINTS +#include <trace/events/huge_memory.h> + /* * By default transparent hugepage support is disabled in order that avoid * to risk increase the memory footprint of applications without a guaranteed @@ -67,6 +97,7 @@ static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); * fault. */ static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1; +static unsigned int khugepaged_max_ptes_swap __read_mostly = HPAGE_PMD_NR/8; static int khugepaged(void *none); static int khugepaged_slab_init(void); @@ -106,6 +137,10 @@ 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) { @@ -553,6 +588,33 @@ static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show, khugepaged_max_ptes_none_store); +static ssize_t khugepaged_max_ptes_swap_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%u\n", khugepaged_max_ptes_swap); +} + +static ssize_t khugepaged_max_ptes_swap_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err; + unsigned long max_ptes_swap; + + err = kstrtoul(buf, 10, &max_ptes_swap); + if (err || max_ptes_swap > HPAGE_PMD_NR-1) + return -EINVAL; + + khugepaged_max_ptes_swap = max_ptes_swap; + + return count; +} + +static struct kobj_attribute khugepaged_max_ptes_swap_attr = + __ATTR(max_ptes_swap, 0644, khugepaged_max_ptes_swap_show, + khugepaged_max_ptes_swap_store); + static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, @@ -561,6 +623,7 @@ static struct attribute *khugepaged_attr[] = { &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, + &khugepaged_max_ptes_swap_attr.attr, NULL, }; @@ -638,6 +701,9 @@ 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, @@ -655,6 +721,8 @@ 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(); @@ -711,6 +779,27 @@ 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, @@ -724,7 +813,7 @@ 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; @@ -732,7 +821,7 @@ 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; } @@ -748,7 +837,7 @@ 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 { @@ -759,7 +848,7 @@ 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, @@ -770,8 +859,8 @@ 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); @@ -865,6 +954,7 @@ 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); } @@ -956,19 +1046,10 @@ 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; - } src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); get_page(src_page); - page_dup_rmap(src_page); + page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); pmdp_set_wrprotect(src_mm, addr, src_pmd); @@ -1008,37 +1089,6 @@ 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, @@ -1068,13 +1118,14 @@ 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); @@ -1112,8 +1163,8 @@ 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)); @@ -1124,7 +1175,7 @@ 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); @@ -1141,7 +1192,7 @@ 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); @@ -1171,7 +1222,17 @@ 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); @@ -1180,7 +1241,7 @@ 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) && @@ -1190,30 +1251,33 @@ 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; @@ -1233,10 +1297,10 @@ 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 { @@ -1244,8 +1308,8 @@ 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); @@ -1254,7 +1318,7 @@ 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; @@ -1308,7 +1372,20 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, update_mmu_cache_pmd(vma, addr, pmd); } if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { - if (page->mapping && trylock_page(page)) { + /* + * 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. + */ + if (compound_mapcount(page) == 1 && !PageDoubleMap(page) && + page->mapping && trylock_page(page)) { lru_add_drain(); if (page->mapping) mlock_vma_page(page); @@ -1318,7 +1395,7 @@ 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; @@ -1459,7 +1536,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, 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 @@ -1481,7 +1558,7 @@ 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); @@ -1493,13 +1570,12 @@ 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; @@ -1508,7 +1584,7 @@ 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() @@ -1516,15 +1592,14 @@ 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); @@ -1540,9 +1615,9 @@ 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; } /* @@ -1558,7 +1633,7 @@ 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; @@ -1589,405 +1664,19 @@ 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))) + 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) @@ -2198,26 +1887,33 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte) { - struct page *page; + struct page *page = NULL; pte_t *_pte; - int none_or_zero = 0; + int none_or_zero = 0, result = 0; bool referenced = false, writable = false; + for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) + ++none_or_zero <= khugepaged_max_ptes_none) { continue; - else + } else { + result = SCAN_EXCEED_NONE_PTE; goto out; + } } - if (!pte_present(pteval)) + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; goto out; + } page = vm_normal_page(vma, address, pteval); - if (unlikely(!page)) + if (unlikely(!page)) { + result = SCAN_PAGE_NULL; goto out; + } VM_BUG_ON_PAGE(PageCompound(page), page); VM_BUG_ON_PAGE(!PageAnon(page), page); @@ -2229,8 +1925,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, * is needed to serialize against split_huge_page * when invoked from the VM. */ - if (!trylock_page(page)) + if (!trylock_page(page)) { + result = SCAN_PAGE_LOCK; goto out; + } /* * cannot use mapcount: can't collapse if there's a gup pin. @@ -2239,6 +1937,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, */ if (page_count(page) != 1 + !!PageSwapCache(page)) { unlock_page(page); + result = SCAN_PAGE_COUNT; goto out; } if (pte_write(pteval)) { @@ -2246,6 +1945,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, } else { if (PageSwapCache(page) && !reuse_swap_page(page)) { unlock_page(page); + result = SCAN_SWAP_CACHE_PAGE; goto out; } /* @@ -2260,6 +1960,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, */ if (isolate_lru_page(page)) { unlock_page(page); + result = SCAN_DEL_PAGE_LRU; goto out; } /* 0 stands for page_is_file_cache(page) == false */ @@ -2273,10 +1974,21 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, mmu_notifier_test_young(vma->vm_mm, address)) referenced = true; } - if (likely(referenced && writable)) - return 1; + if (likely(writable)) { + if (likely(referenced)) { + result = SCAN_SUCCEED; + trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero, + referenced, writable, result); + return 1; + } + } else { + result = SCAN_PAGE_RO; + } + out: release_pte_pages(pte, _pte); + trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero, + referenced, writable, result); return 0; } @@ -2321,7 +2033,7 @@ 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); } @@ -2431,6 +2143,7 @@ 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; } @@ -2442,8 +2155,12 @@ 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) @@ -2493,7 +2210,6 @@ 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)) @@ -2502,6 +2218,44 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return true; } +/* + * Bring missing pages in from swap, to complete THP collapse. + * Only done if khugepaged_scan_pmd believes it is worthwhile. + * + * Called and returns without pte mapped or spinlocks held, + * but with mmap_sem held to protect against vma changes. + */ + +static void __collapse_huge_page_swapin(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd) +{ + unsigned long _address; + pte_t *pte, pteval; + int swapped_in = 0, ret = 0; + + pte = pte_offset_map(pmd, address); + for (_address = address; _address < address + HPAGE_PMD_NR*PAGE_SIZE; + pte++, _address += PAGE_SIZE) { + pteval = *pte; + if (!is_swap_pte(pteval)) + continue; + swapped_in++; + ret = do_swap_page(mm, vma, _address, pte, pmd, + FAULT_FLAG_ALLOW_RETRY|FAULT_FLAG_RETRY_NOWAIT, + pteval); + if (ret & VM_FAULT_ERROR) { + trace_mm_collapse_huge_page_swapin(mm, swapped_in, 0); + return; + } + /* pte is unmapped now, we need to map it */ + pte = pte_offset_map(pmd, _address); + } + pte--; + pte_unmap(pte); + trace_mm_collapse_huge_page_swapin(mm, swapped_in, 1); +} + static void collapse_huge_page(struct mm_struct *mm, unsigned long address, struct page **hpage, @@ -2513,7 +2267,7 @@ static void collapse_huge_page(struct mm_struct *mm, pgtable_t pgtable; struct page *new_page; spinlock_t *pmd_ptl, *pte_ptl; - int isolated; + int isolated = 0, result = 0; unsigned long hstart, hend; struct mem_cgroup *memcg; unsigned long mmun_start; /* For mmu_notifiers */ @@ -2528,12 +2282,15 @@ static void collapse_huge_page(struct mm_struct *mm, /* release the mmap_sem read lock. */ new_page = khugepaged_alloc_page(hpage, gfp, mm, address, node); - if (!new_page) - return; + if (!new_page) { + result = SCAN_ALLOC_HUGE_PAGE_FAIL; + goto out_nolock; + } - if (unlikely(mem_cgroup_try_charge(new_page, mm, - gfp, &memcg))) - return; + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { + result = SCAN_CGROUP_CHARGE_FAIL; + goto out_nolock; + } /* * Prevent all access to pagetables with the exception of @@ -2541,21 +2298,33 @@ static void collapse_huge_page(struct mm_struct *mm, * handled by the anon_vma lock + PG_lock. */ down_write(&mm->mmap_sem); - if (unlikely(khugepaged_test_exit(mm))) + if (unlikely(khugepaged_test_exit(mm))) { + result = SCAN_ANY_PROCESS; goto out; + } vma = find_vma(mm, address); - if (!vma) + if (!vma) { + result = SCAN_VMA_NULL; goto out; + } hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; - if (address < hstart || address + HPAGE_PMD_SIZE > hend) + if (address < hstart || address + HPAGE_PMD_SIZE > hend) { + result = SCAN_ADDRESS_RANGE; goto out; - if (!hugepage_vma_check(vma)) + } + if (!hugepage_vma_check(vma)) { + result = SCAN_VMA_CHECK; goto out; + } pmd = mm_find_pmd(mm, address); - if (!pmd) + if (!pmd) { + result = SCAN_PMD_NULL; goto out; + } + + __collapse_huge_page_swapin(mm, vma, address, pmd); anon_vma_lock_write(vma->anon_vma); @@ -2592,6 +2361,7 @@ static void collapse_huge_page(struct mm_struct *mm, pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); + result = SCAN_FAIL; goto out; } @@ -2618,8 +2388,8 @@ 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); @@ -2629,12 +2399,14 @@ static void collapse_huge_page(struct mm_struct *mm, *hpage = NULL; khugepaged_pages_collapsed++; + result = SCAN_SUCCEED; out_up_write: up_write(&mm->mmap_sem); +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; } @@ -2645,39 +2417,62 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, { pmd_t *pmd; pte_t *pte, *_pte; - int ret = 0, none_or_zero = 0; - struct page *page; + int ret = 0, none_or_zero = 0, result = 0; + struct page *page = NULL; unsigned long _address; spinlock_t *ptl; - int node = NUMA_NO_NODE; + int node = NUMA_NO_NODE, unmapped = 0; bool writable = false, referenced = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); pmd = mm_find_pmd(mm, address); - if (!pmd) + if (!pmd) { + result = SCAN_PMD_NULL; goto out; + } memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); pte = pte_offset_map_lock(mm, pmd, address, &ptl); for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = *_pte; + if (is_swap_pte(pteval)) { + if (++unmapped <= khugepaged_max_ptes_swap) { + continue; + } else { + result = SCAN_EXCEED_SWAP_PTE; + goto out_unmap; + } + } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { if (!userfaultfd_armed(vma) && - ++none_or_zero <= khugepaged_max_ptes_none) + ++none_or_zero <= khugepaged_max_ptes_none) { continue; - else + } else { + result = SCAN_EXCEED_NONE_PTE; goto out_unmap; + } } - if (!pte_present(pteval)) + if (!pte_present(pteval)) { + result = SCAN_PTE_NON_PRESENT; goto out_unmap; + } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); - if (unlikely(!page)) + if (unlikely(!page)) { + 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[]. @@ -2685,26 +2480,48 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, * hit record. */ node = page_to_nid(page); - if (khugepaged_scan_abort(node)) + if (khugepaged_scan_abort(node)) { + result = SCAN_SCAN_ABORT; goto out_unmap; + } khugepaged_node_load[node]++; - VM_BUG_ON_PAGE(PageCompound(page), page); - if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) + if (!PageLRU(page)) { + result = SCAN_SCAN_ABORT; goto out_unmap; + } + if (PageLocked(page)) { + result = SCAN_PAGE_LOCK; + goto out_unmap; + } + if (!PageAnon(page)) { + result = SCAN_PAGE_ANON; + goto out_unmap; + } + /* * cannot use mapcount: can't collapse if there's a gup pin. * The page must only be referenced by the scanned process * and page swap cache. */ - if (page_count(page) != 1 + !!PageSwapCache(page)) + if (page_count(page) != 1 + !!PageSwapCache(page)) { + result = SCAN_PAGE_COUNT; goto out_unmap; + } if (pte_young(pteval) || page_is_young(page) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) referenced = true; } - if (referenced && writable) - ret = 1; + if (writable) { + if (referenced) { + result = SCAN_SUCCEED; + ret = 1; + } else { + result = SCAN_NO_REFERENCED_PAGE; + } + } else { + result = SCAN_PAGE_RO; + } out_unmap: pte_unmap_unlock(pte, ptl); if (ret) { @@ -2713,6 +2530,8 @@ out_unmap: collapse_huge_page(mm, address, hpage, vma, node); } out: + trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced, + none_or_zero, result, unmapped); return ret; } @@ -2938,8 +2757,8 @@ 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); @@ -2958,66 +2777,130 @@ 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; + 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)); + + 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); - split_huge_page(page); - put_page(page); + /* 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); + + 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(pte_mkdirty(entry), vma); + if (!write) + entry = pte_wrprotect(entry); + if (!young) + entry = pte_mkold(entry); + } + 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); + } /* - * 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. + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). */ - if (unlikely(pmd_trans_huge(*pmd))) - goto again; + 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 */ + 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 (unlikely(!pmd_trans_huge(*pmd))) + goto out; + page = pmd_page(*pmd); + __split_huge_pmd_locked(vma, pmd, haddr, false); + if (PageMlocked(page)) + get_page(page); + else + page = NULL; +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; @@ -3026,7 +2909,7 @@ 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; @@ -3035,13 +2918,13 @@ 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)) 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, @@ -3057,7 +2940,7 @@ 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 @@ -3067,7 +2950,7 @@ 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 @@ -3081,6 +2964,427 @@ 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) +{ + spinlock_t *ptl; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int i; + + 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, address, true); + spin_unlock(ptl); + return; + } + spin_unlock(ptl); + + pte = pte_offset_map_lock(vma->vm_mm, pmd, address, &ptl); + for (i = 0; i < HPAGE_PMD_NR; i++, address += PAGE_SIZE, page++) { + pte_t entry, swp_pte; + swp_entry_t swp_entry; + + if (!pte_present(pte[i])) + continue; + if (page_to_pfn(page) != pte_pfn(pte[i])) + continue; + flush_cache_page(vma, address, page_to_pfn(page)); + entry = ptep_clear_flush(vma, address, pte + i); + 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 + i, swp_pte); + page_remove_rmap(page, false); + put_page(page); + } + pte_unmap_unlock(pte, 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 haddr; + + haddr = __vma_address(page, avc->vma) & HPAGE_PMD_MASK; + mmu_notifier_invalidate_range_start(avc->vma->vm_mm, + haddr, haddr + HPAGE_PMD_SIZE); + freeze_page_vma(avc->vma, page, haddr); + mmu_notifier_invalidate_range_end(avc->vma->vm_mm, + haddr, haddr + 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; + int i; + + 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 < HPAGE_PMD_NR; i++, address += PAGE_SIZE, page++) { + if (!is_swap_pte(pte[i])) + continue; + + swp_entry = pte_to_swp_entry(pte[i]); + 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)); + 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 + i, entry); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, address, pte + i); + } + pte_unmap_unlock(pte, 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))); + page_tail->flags |= (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); + + spin_lock(&split_queue_lock); + if (!list_empty(page_deferred_list(head))) { + split_queue_len--; + list_del(page_deferred_list(head)); + } + spin_unlock(&split_queue_lock); + + /* 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; + + 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; + } + + freeze_page(anon_vma, head); + VM_BUG_ON_PAGE(compound_mapcount(head), head); + + count = page_count(head); + mapcount = total_mapcount(head); + if (mapcount == count - 1) { + __split_huge_page(page, list); + ret = 0; + } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount > count - 1) { + pr_alert("total_mapcount: %u, page_count(): %u\n", + mapcount, count); + if (PageTail(page)) + dump_page(head, NULL); + dump_page(page, "total_mapcount(head) > page_count(head) - 1"); + BUG(); + } else { + 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, +}; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 827bb02a43a4..acc8b9ab3a5e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1258,8 +1258,8 @@ 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 @@ -3126,7 +3126,7 @@ 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); } @@ -3210,7 +3210,7 @@ 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; @@ -3439,7 +3439,7 @@ 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; @@ -3609,7 +3609,7 @@ 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); @@ -3889,7 +3889,7 @@ 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..4ae7b7c7462b 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 @@ -33,6 +34,10 @@ /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) +extern int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + unsigned int flags, pte_t orig_pte); + void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); @@ -66,50 +71,6 @@ 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 +270,27 @@ 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) { } @@ -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 { @@ -958,13 +944,13 @@ 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); @@ -977,33 +963,6 @@ 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 @@ -1022,9 +981,6 @@ 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; @@ -1037,6 +993,13 @@ 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 @@ -1067,6 +1030,7 @@ static int try_to_merge_one_page(struct vm_area_struct *vma, } } +out_unlock: unlock_page(page); out: return err; @@ -1639,8 +1603,7 @@ 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, @@ -1903,7 +1866,7 @@ 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/memcontrol.c b/mm/memcontrol.c index 9acfb165eb52..fcd7c4e83c87 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -696,7 +696,7 @@ 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 @@ -709,9 +709,11 @@ 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) @@ -2435,9 +2437,7 @@ 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) { @@ -4499,38 +4499,30 @@ 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; @@ -4585,9 +4577,9 @@ 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: @@ -4677,7 +4669,7 @@ 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); @@ -4861,17 +4853,7 @@ 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; @@ -4880,7 +4862,7 @@ 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; @@ -4909,7 +4891,8 @@ retry: page = target.page; 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++; @@ -5250,10 +5233,11 @@ 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()) @@ -5283,11 +5267,6 @@ 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); @@ -5316,9 +5295,9 @@ 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); @@ -5335,13 +5314,8 @@ 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(); @@ -5363,9 +5337,10 @@ 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; @@ -5377,11 +5352,6 @@ 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); } @@ -5627,7 +5597,7 @@ 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..1b99403d76f2 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", @@ -1750,21 +1718,28 @@ 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) && PageTransHuge(hpage)) { + lock_page(hpage); + ret = split_huge_page(hpage); + unlock_page(hpage); + if (unlikely(ret || PageTransCompound(page) || + !PageAnon(page))) { + pr_info("soft offline: %#lx: failed to split THP\n", + pfn); + if (flags & MF_COUNT_INCREASED) + put_hwpoison_page(hpage); + return -EBUSY; + } + get_hwpoison_page(page); + put_hwpoison_page(hpage); + } + if (PageHuge(page)) ret = soft_offline_huge_page(page, flags); else diff --git a/mm/memory.c b/mm/memory.c index deb679c31f2a..7f3b9f2769ad 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -566,7 +566,6 @@ 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 +585,14 @@ 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 +608,7 @@ 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); @@ -873,7 +867,7 @@ 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); if (PageAnon(page)) rss[MM_ANONPAGES]++; else @@ -1125,7 +1119,7 @@ again: mark_page_accessed(page); rss[MM_FILEPAGES]--; } - 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))) { @@ -1204,7 +1198,7 @@ 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 */ @@ -2083,7 +2077,7 @@ 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); @@ -2113,8 +2107,8 @@ 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 @@ -2146,14 +2140,14 @@ 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) @@ -2168,7 +2162,8 @@ 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); @@ -2443,7 +2438,7 @@ EXPORT_SYMBOL(unmap_mapping_range); * We return with the mmap_sem locked or unlocked in the same cases * as does filemap_fault(). */ -static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, +int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, unsigned int flags, pte_t orig_pte) { @@ -2528,7 +2523,7 @@ 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; } @@ -2562,7 +2557,7 @@ 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)) @@ -2570,10 +2565,10 @@ 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); } @@ -2608,7 +2603,7 @@ 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); @@ -2702,7 +2697,7 @@ 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; /* @@ -2723,15 +2718,15 @@ 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); @@ -2742,7 +2737,7 @@ 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: @@ -2818,7 +2813,7 @@ 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_FILEPAGES); page_add_file_rmap(page); @@ -2993,7 +2988,7 @@ 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; } @@ -3022,7 +3017,7 @@ 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) { @@ -3037,7 +3032,7 @@ 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; } @@ -3089,7 +3084,7 @@ 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) { /* @@ -3191,6 +3186,12 @@ 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 @@ -3366,14 +3367,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (pmd_trans_huge(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); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 87a177917cb2..4a02de4e173f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -489,14 +489,31 @@ 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; + } + } + } +retry: pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) @@ -513,6 +530,21 @@ 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); 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 339d9e0949b6..0147b57f9704 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -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 @@ -444,7 +449,10 @@ 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 +485,6 @@ 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/mprotect.c b/mm/mprotect.c index ef5be8eaab00..9c1445dc8a4c 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -160,7 +160,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, if (pmd_trans_huge(*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 c25bc6268e46..9acf51a4f682 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 17a3c66639a9..9c0908c97f09 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -229,13 +229,15 @@ 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; @@ -457,7 +459,7 @@ 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)); } @@ -473,8 +475,10 @@ 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 @@ -739,7 +743,7 @@ 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"; @@ -863,6 +867,27 @@ 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; @@ -873,6 +898,7 @@ 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; } @@ -1336,7 +1362,7 @@ 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"; diff --git a/mm/page_idle.c b/mm/page_idle.c index d5dd79041484..2c553ba969f8 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -56,24 +56,70 @@ static int page_idle_clear_pte_refs_one(struct page *page, { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; + pgd_t *pgd; + pud_t *pud; pmd_t *pmd; pte_t *pte; 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); + pgd = pgd_offset(mm, addr); + if (!pgd_present(*pgd)) + return SWAP_AGAIN; + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) + return SWAP_AGAIN; + pmd = pmd_offset(pud, addr); + + 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; + + referenced = pmdp_clear_young_notify(vma, addr, pmd); + spin_unlock(ptl); + goto found; +unlock_pmd: + spin_unlock(ptl); + return SWAP_AGAIN; } 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); - } + pmd_t pmde = *pmd; + + barrier(); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) + return SWAP_AGAIN; + + } +map_pte: + pte = pte_offset_map(pmd, addr); + if (!pte_present(*pte)) { + pte_unmap(pte); + return SWAP_AGAIN; } + + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + + if (!pte_present(*pte)) { + pte_unmap_unlock(pte, ptl); + return SWAP_AGAIN; + } + + /* 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 SWAP_AGAIN; + } + + referenced = ptep_clear_young_notify(vma, addr, pte); + pte_unmap_unlock(pte, ptl); +found: if (referenced) { clear_page_idle(page); /* 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 7d3db0247983..69261d4c774d 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -139,18 +139,6 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, } #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 b577fbb98d4b..e90b81ff306d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -565,27 +565,6 @@ 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) { @@ -833,60 +812,105 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma, spinlock_t *ptl; int referenced = 0; struct page_referenced_arg *pra = arg; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; - 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) + if (unlikely(PageHuge(page))) { + /* when pud is not present, pte will be NULL */ + pte = huge_pte_offset(mm, address); + if (!pte) return SWAP_AGAIN; - if (vma->vm_flags & VM_LOCKED) { + ptl = huge_pte_lockptr(page_hstate(page), mm, pte); + goto check_pte; + } + + pgd = pgd_offset(mm, address); + if (!pgd_present(*pgd)) + return SWAP_AGAIN; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return SWAP_AGAIN; + pmd = pmd_offset(pud, address); + + if (pmd_trans_huge(*pmd)) { + int ret = SWAP_AGAIN; + + 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; + + if (vma->vm_flags & VM_LOCKED) { pra->vm_flags |= VM_LOCKED; - return SWAP_FAIL; /* To break the loop */ + ret = SWAP_FAIL; /* To break the loop */ + goto unlock_pmd; } - /* go ahead even if the pmd is pmd_trans_splitting() */ if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; spin_unlock(ptl); + goto found; +unlock_pmd: + spin_unlock(ptl); + return ret; } else { - pte_t *pte; + pmd_t pmde = *pmd; - /* - * 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) + barrier(); + if (!pmd_present(pmde) || pmd_trans_huge(pmde)) return SWAP_AGAIN; + } +map_pte: + pte = pte_offset_map(pmd, address); + if (!pte_present(*pte)) { + pte_unmap(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 */ - } + ptl = pte_lockptr(mm, pmd); +check_pte: + spin_lock(ptl); - if (ptep_clear_flush_young_notify(vma, address, pte)) { - /* - * Don't treat a reference through a sequentially read - * mapping as such. If the page has been used in - * another mapping, we will catch it; if this other - * mapping is already gone, the unmap path will have - * set PG_referenced or activated the page. - */ - if (likely(!(vma->vm_flags & VM_SEQ_READ))) - referenced++; - } + if (!pte_present(*pte)) { + pte_unmap_unlock(pte, ptl); + return SWAP_AGAIN; + } + + /* 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 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 */ + } + + if (ptep_clear_flush_young_notify(vma, address, pte)) { + /* + * Don't treat a reference through a sequentially read + * mapping as such. If the page has been used in + * another mapping, we will catch it; if this other + * mapping is already gone, the unmap path will have + * set PG_referenced or activated the page. + */ + if (likely(!(vma->vm_flags & VM_SEQ_READ))) + referenced++; + } + pte_unmap_unlock(pte, ptl); + +found: if (referenced) clear_page_idle(page); if (test_and_clear_page_young(page)) @@ -933,7 +957,7 @@ 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 = { @@ -1122,7 +1146,7 @@ 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 } @@ -1131,6 +1155,7 @@ 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, @@ -1138,9 +1163,9 @@ 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); } /* @@ -1149,29 +1174,44 @@ 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); } @@ -1181,21 +1221,31 @@ 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); } @@ -1223,12 +1273,15 @@ 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; /* @@ -1245,41 +1298,76 @@ 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 (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 @@ -1420,7 +1508,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } else dec_mm_counter(mm, MM_FILEPAGES); - page_remove_rmap(page); + page_remove_rmap(page, false); page_cache_release(page); out_unmap: @@ -1702,7 +1790,7 @@ 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); } @@ -1711,7 +1799,7 @@ 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 9187eee4128b..529a7d5083f1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -729,7 +729,8 @@ 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 */ @@ -752,9 +753,9 @@ 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); @@ -1004,7 +1005,7 @@ 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); @@ -1137,7 +1138,8 @@ 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)); @@ -1154,14 +1156,14 @@ 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--; @@ -1196,11 +1198,12 @@ 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); @@ -1210,10 +1213,10 @@ 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/slab.c b/mm/slab.c index e0819fa96559..6070d4ba5be4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3231,11 +3231,15 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) #endif /* CONFIG_NUMA */ static __always_inline void * -slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) +slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller, + bool irq_off_needed) { unsigned long save_flags; void *objp; + /* Compiler need to remove irq_off_needed branch statements */ + BUILD_BUG_ON(!__builtin_constant_p(irq_off_needed)); + flags &= gfp_allowed_mask; lockdep_trace_alloc(flags); @@ -3246,9 +3250,11 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller) cachep = memcg_kmem_get_cache(cachep, flags); cache_alloc_debugcheck_before(cachep, flags); - local_irq_save(save_flags); + if (irq_off_needed) + local_irq_save(save_flags); objp = __do_cache_alloc(cachep, flags); - local_irq_restore(save_flags); + if (irq_off_needed) + local_irq_restore(save_flags); objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags, flags); @@ -3404,7 +3410,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp, */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - void *ret = slab_alloc(cachep, flags, _RET_IP_); + void *ret = slab_alloc(cachep, flags, _RET_IP_, true); trace_kmem_cache_alloc(_RET_IP_, ret, cachep->object_size, cachep->size, flags); @@ -3413,16 +3419,23 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) } EXPORT_SYMBOL(kmem_cache_alloc); -void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) -{ - __kmem_cache_free_bulk(s, size, p); -} -EXPORT_SYMBOL(kmem_cache_free_bulk); - +/* Note that interrupts must be enabled when calling this function. */ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, - void **p) + void **p) { - return __kmem_cache_alloc_bulk(s, flags, size, p); + size_t i; + + local_irq_disable(); + for (i = 0; i < size; i++) { + void *x = p[i] = slab_alloc(s, flags, _RET_IP_, false); + + if (!x) { + __kmem_cache_free_bulk(s, i, p); + return false; + } + } + local_irq_enable(); + return true; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); @@ -3432,7 +3445,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) { void *ret; - ret = slab_alloc(cachep, flags, _RET_IP_); + ret = slab_alloc(cachep, flags, _RET_IP_, true); trace_kmalloc(_RET_IP_, ret, size, cachep->size, flags); @@ -3523,7 +3536,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = slab_alloc(cachep, flags, caller); + ret = slab_alloc(cachep, flags, caller, true); trace_kmalloc(caller, ret, size, cachep->size, flags); @@ -3543,32 +3556,56 @@ void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) } EXPORT_SYMBOL(__kmalloc_track_caller); -/** - * kmem_cache_free - Deallocate an object - * @cachep: The cache the allocation was from. - * @objp: The previously allocated object. - * - * Free an object which was previously allocated from this - * cache. - */ -void kmem_cache_free(struct kmem_cache *cachep, void *objp) +/* Caller is responsible for disabling local IRQs */ +static __always_inline void __kmem_cache_free(struct kmem_cache *cachep, + void *objp, bool irq_off_needed) { unsigned long flags; + + /* Compiler need to remove irq_off_needed branch statements */ + BUILD_BUG_ON(!__builtin_constant_p(irq_off_needed)); + cachep = cache_from_obj(cachep, objp); if (!cachep) return; - local_irq_save(flags); + if (irq_off_needed) + local_irq_save(flags); debug_check_no_locks_freed(objp, cachep->object_size); if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(objp, cachep->object_size); __cache_free(cachep, objp, _RET_IP_); - local_irq_restore(flags); + if (irq_off_needed) + local_irq_restore(flags); +} +/** + * kmem_cache_free - Deallocate an object + * @cachep: The cache the allocation was from. + * @objp: The previously allocated object. + * + * Free an object which was previously allocated from this + * cache. + */ +void kmem_cache_free(struct kmem_cache *cachep, void *objp) +{ + __kmem_cache_free(cachep, objp, true); trace_kmem_cache_free(_RET_IP_, objp); } EXPORT_SYMBOL(kmem_cache_free); +/* Note that interrupts must be enabled when calling this function. */ +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) +{ + size_t i; + + local_irq_disable(); + for (i = 0; i < size; i++) + __kmem_cache_free(s, p[i], false); + local_irq_enable(); +} +EXPORT_SYMBOL(kmem_cache_free_bulk); + /** * kfree - free previously allocated memory * @objp: pointer returned by kmalloc. diff --git a/mm/slub.c b/mm/slub.c index 7cb4bf9ae320..438ebf8bbab1 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); } @@ -1065,11 +1067,15 @@ bad: return 0; } +/* Supports checking bulk free of a constructed freelist */ static noinline struct kmem_cache_node *free_debug_processing( - struct kmem_cache *s, struct page *page, void *object, + struct kmem_cache *s, struct page *page, + void *head, void *tail, int bulk_cnt, unsigned long addr, unsigned long *flags) { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + void *object = head; + int cnt = 0; spin_lock_irqsave(&n->list_lock, *flags); slab_lock(page); @@ -1077,6 +1083,9 @@ static noinline struct kmem_cache_node *free_debug_processing( if (!check_slab(s, page)) goto fail; +next_object: + cnt++; + if (!check_valid_pointer(s, page, object)) { slab_err(s, page, "Invalid object pointer 0x%p", object); goto fail; @@ -1107,8 +1116,19 @@ static noinline struct kmem_cache_node *free_debug_processing( if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_FREE, addr); trace(s, page, object, 0); + /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ init_object(s, object, SLUB_RED_INACTIVE); + + /* Reached end of constructed freelist yet? */ + if (object != tail) { + object = get_freepointer(s, object); + goto next_object; + } out: + if (cnt != bulk_cnt) + slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n", + bulk_cnt, cnt); + slab_unlock(page); /* * Keep node_lock to preserve integrity @@ -1204,7 +1224,7 @@ unsigned long kmem_cache_flags(unsigned long object_size, return flags; } -#else +#else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} @@ -1212,7 +1232,8 @@ static inline int alloc_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { return 0; } static inline struct kmem_cache_node *free_debug_processing( - struct kmem_cache *s, struct page *page, void *object, + struct kmem_cache *s, struct page *page, + void *head, void *tail, int bulk_cnt, unsigned long addr, unsigned long *flags) { return NULL; } static inline int slab_pad_check(struct kmem_cache *s, struct page *page) @@ -1308,6 +1329,29 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) kasan_slab_free(s, x); } +static inline void slab_free_freelist_hook(struct kmem_cache *s, + void *head, void *tail) +{ +/* + * Compiler cannot detect this function can be removed if slab_free_hook() + * evaluates to nothing. Thus, catch all relevant config debug options here. + */ +#if defined(CONFIG_KMEMCHECK) || \ + defined(CONFIG_LOCKDEP) || \ + defined(CONFIG_DEBUG_KMEMLEAK) || \ + defined(CONFIG_DEBUG_OBJECTS_FREE) || \ + defined(CONFIG_KASAN) + + void *object = head; + void *tail_obj = tail ? : head; + + do { + slab_free_hook(s, object); + } while ((object != tail_obj) && + (object = get_freepointer(s, object))); +#endif +} + static void setup_object(struct kmem_cache *s, struct page *page, void *object) { @@ -2295,23 +2339,15 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * And if we were unable to get a new slab from the partial slab lists then * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. + * + * Version of __slab_alloc to use when we know that interrupts are + * already disabled (which is the case for bulk allocation). */ -static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void *freelist; struct page *page; - unsigned long flags; - - local_irq_save(flags); -#ifdef CONFIG_PREEMPT - /* - * We may have been preempted and rescheduled on a different - * cpu before disabling interrupts. Need to reload cpu area - * pointer. - */ - c = this_cpu_ptr(s->cpu_slab); -#endif page = c->page; if (!page) @@ -2369,7 +2405,6 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); - local_irq_restore(flags); return freelist; new_slab: @@ -2386,7 +2421,6 @@ new_slab: if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); return NULL; } @@ -2402,11 +2436,35 @@ new_slab: deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); return freelist; } /* + * Another one that disabled interrupt and compensates for possible + * cpu changes by refetching the per cpu area pointer. + */ +static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) +{ + void *p; + unsigned long flags; + + local_irq_save(flags); +#ifdef CONFIG_PREEMPT + /* + * We may have been preempted and rescheduled on a different + * cpu before disabling interrupts. Need to reload cpu area + * pointer. + */ + c = this_cpu_ptr(s->cpu_slab); +#endif + + p = ___slab_alloc(s, gfpflags, node, addr, c); + local_irq_restore(flags); + return p; +} + +/* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. @@ -2569,10 +2627,11 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); * handling required then we can return immediately. */ static void __slab_free(struct kmem_cache *s, struct page *page, - void *x, unsigned long addr) + void *head, void *tail, int cnt, + unsigned long addr) + { void *prior; - void **object = (void *)x; int was_frozen; struct page new; unsigned long counters; @@ -2582,7 +2641,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page, stat(s, FREE_SLOWPATH); if (kmem_cache_debug(s) && - !(n = free_debug_processing(s, page, x, addr, &flags))) + !(n = free_debug_processing(s, page, head, tail, cnt, + addr, &flags))) return; do { @@ -2592,10 +2652,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page, } prior = page->freelist; counters = page->counters; - set_freepointer(s, object, prior); + set_freepointer(s, tail, prior); new.counters = counters; was_frozen = new.frozen; - new.inuse--; + new.inuse -= cnt; if ((!new.inuse || !prior) && !was_frozen) { if (kmem_cache_has_cpu_partial(s) && !prior) { @@ -2626,7 +2686,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, } while (!cmpxchg_double_slab(s, page, prior, counters, - object, new.counters, + head, new.counters, "__slab_free")); if (likely(!n)) { @@ -2691,15 +2751,20 @@ slab_empty: * * If fastpath is not possible then fall back to __slab_free where we deal * with all sorts of special processing. + * + * Bulk free of a freelist with several objects (all pointing to the + * same page) possible by specifying head and tail ptr, plus objects + * count (cnt). Bulk free indicated by tail pointer being set. */ -static __always_inline void slab_free(struct kmem_cache *s, - struct page *page, void *x, unsigned long addr) +static __always_inline void slab_free(struct kmem_cache *s, struct page *page, + void *head, void *tail, int cnt, + unsigned long addr) { - void **object = (void *)x; + void *tail_obj = tail ? : head; struct kmem_cache_cpu *c; unsigned long tid; - slab_free_hook(s, x); + slab_free_freelist_hook(s, head, tail); redo: /* @@ -2718,19 +2783,19 @@ redo: barrier(); if (likely(page == c->page)) { - set_freepointer(s, object, c->freelist); + set_freepointer(s, tail_obj, c->freelist); if (unlikely(!this_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, c->freelist, tid, - object, next_tid(tid)))) { + head, next_tid(tid)))) { note_cmpxchg_failure("slab_free", s, tid); goto redo; } stat(s, FREE_FASTPATH); } else - __slab_free(s, page, x, addr); + __slab_free(s, page, head, tail_obj, cnt, addr); } @@ -2739,49 +2804,98 @@ void kmem_cache_free(struct kmem_cache *s, void *x) s = cache_from_obj(s, x); if (!s) return; - slab_free(s, virt_to_head_page(x), x, _RET_IP_); + slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_); trace_kmem_cache_free(_RET_IP_, x); } EXPORT_SYMBOL(kmem_cache_free); -/* Note that interrupts must be enabled when calling this function. */ -void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) -{ - struct kmem_cache_cpu *c; +struct detached_freelist { struct page *page; - int i; + void *tail; + void *freelist; + int cnt; +}; - local_irq_disable(); - c = this_cpu_ptr(s->cpu_slab); +/* + * This function progressively scans the array with free objects (with + * a limited look ahead) and extract objects belonging to the same + * page. It builds a detached freelist directly within the given + * page/objects. This can happen without any need for + * synchronization, because the objects are owned by running process. + * The freelist is build up as a single linked list in the objects. + * The idea is, that this detached freelist can then be bulk + * transferred to the real freelist(s), but only requiring a single + * synchronization primitive. Look ahead in the array is limited due + * to performance reasons. + */ +static int build_detached_freelist(struct kmem_cache *s, size_t size, + void **p, struct detached_freelist *df) +{ + size_t first_skipped_index = 0; + int lookahead = 3; + void *object; - for (i = 0; i < size; i++) { - void *object = p[i]; + /* Always re-init detached_freelist */ + df->page = NULL; - BUG_ON(!object); - /* kmem cache debug support */ - s = cache_from_obj(s, object); - if (unlikely(!s)) - goto exit; - slab_free_hook(s, object); + do { + object = p[--size]; + } while (!object && size); - page = virt_to_head_page(object); + if (!object) + return 0; - if (c->page == page) { - /* Fastpath: local CPU free */ - set_freepointer(s, object, c->freelist); - c->freelist = object; - } else { - c->tid = next_tid(c->tid); - local_irq_enable(); - /* Slowpath: overhead locked cmpxchg_double_slab */ - __slab_free(s, page, object, _RET_IP_); - local_irq_disable(); - c = this_cpu_ptr(s->cpu_slab); + /* Start new detached freelist */ + set_freepointer(s, object, NULL); + df->page = virt_to_head_page(object); + df->tail = object; + df->freelist = object; + p[size] = NULL; /* mark object processed */ + df->cnt = 1; + + while (size) { + object = p[--size]; + if (!object) + continue; /* Skip processed objects */ + + /* df->page is always set at this point */ + if (df->page == virt_to_head_page(object)) { + /* Opportunity build freelist */ + set_freepointer(s, object, df->freelist); + df->freelist = object; + df->cnt++; + p[size] = NULL; /* mark object processed */ + + continue; } + + /* Limit look ahead search */ + if (!--lookahead) + break; + + if (!first_skipped_index) + first_skipped_index = size + 1; } -exit: - c->tid = next_tid(c->tid); - local_irq_enable(); + + return first_skipped_index; +} + + +/* Note that interrupts must be enabled when calling this function. */ +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) +{ + if (WARN_ON(!size)) + return; + + do { + struct detached_freelist df; + + size = build_detached_freelist(s, size, p, &df); + if (unlikely(!df.page)) + continue; + + slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_); + } while (likely(size)); } EXPORT_SYMBOL(kmem_cache_free_bulk); @@ -2804,30 +2918,23 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void *object = c->freelist; if (unlikely(!object)) { - local_irq_enable(); /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist */ - p[i] = __slab_alloc(s, flags, NUMA_NO_NODE, + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_, c); - if (unlikely(!p[i])) { - __kmem_cache_free_bulk(s, i, p); - return false; - } - local_irq_disable(); + if (unlikely(!p[i])) + goto error; + c = this_cpu_ptr(s->cpu_slab); continue; /* goto for-loop */ } /* kmem_cache debug support */ s = slab_pre_alloc_hook(s, flags); - if (unlikely(!s)) { - __kmem_cache_free_bulk(s, i, p); - c->tid = next_tid(c->tid); - local_irq_enable(); - return false; - } + if (unlikely(!s)) + goto error; c->freelist = get_freepointer(s, object); p[i] = object; @@ -2847,6 +2954,11 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, } return true; + +error: + __kmem_cache_free_bulk(s, i, p); + local_irq_enable(); + return false; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); @@ -3511,7 +3623,7 @@ void kfree(const void *x) __free_kmem_pages(page, compound_order(page)); return; } - slab_free(page->slab_cache, page, object, _RET_IP_); + slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); } EXPORT_SYMBOL(kfree); diff --git a/mm/swap.c b/mm/swap.c index 39395fb549c0..abffc33bb975 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -89,260 +89,14 @@ 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 +358,7 @@ 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)) { @@ -918,15 +673,6 @@ 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 +683,19 @@ 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..d783872d746c 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -353,7 +353,7 @@ 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 +367,7 @@ 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 58877312cf6b..7073faecb38f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -929,6 +929,9 @@ 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); @@ -1145,14 +1148,15 @@ 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); + mem_cgroup_cancel_charge(page, memcg, false); ret = 0; goto out; } @@ -1163,11 +1167,11 @@ 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); 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 9af1c12b310c..22dae03a4ae1 100644 --- a/mm/util.c +++ b/mm/util.c @@ -3,6 +3,7 @@ #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> +#include <linux/ctype.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/security.h> @@ -100,6 +101,35 @@ char *kstrndup(const char *s, size_t max, gfp_t gfp) EXPORT_SYMBOL(kstrndup); /** + * kstrimdup - Trim and copy a %NUL terminated string. + * @s: the string to trim and duplicate + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Returns an address, which the caller must kfree, containing + * a duplicate of the passed string with leading and/or trailing + * whitespace (as defined by isspace) removed. + */ +char *kstrimdup(const char *s, gfp_t gfp) +{ + char *buf; + char *begin = skip_spaces(s); + size_t len = strlen(begin); + + while (len && isspace(begin[len - 1])) + len--; + + buf = kmalloc_track_caller(len + 1, gfp); + if (!buf) + return NULL; + + memcpy(buf, begin, len); + buf[len] = '\0'; + + return buf; +} +EXPORT_SYMBOL(kstrimdup); + +/** * kmemdup - duplicate region of memory * * @src: memory region to duplicate @@ -355,7 +385,9 @@ 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))) @@ -368,11 +400,25 @@ 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; + + page = compound_head(page); + ret = atomic_read(&page->_mapcount) + 1; + 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/vmpressure.c b/mm/vmpressure.c index c5afd573d7da..4c25e621a40b 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -38,7 +38,7 @@ * TODO: Make the window size depend on machine size, as we do for vmstat * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). */ -static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; +static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 2; /* * These thresholds are used when we account memory pressure through diff --git a/mm/vmscan.c b/mm/vmscan.c index 2aec4241b42a..a4507ecaefbf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1184,7 +1184,7 @@ 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: nr_reclaimed++; diff --git a/mm/vmstat.c b/mm/vmstat.c index 879a2be23325..45dcbcb5c594 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -842,7 +842,9 @@ 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/checkpatch.pl b/scripts/checkpatch.pl index 2b3c22808c3b..9f0949b28445 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -433,6 +433,28 @@ our @typeList = ( qr{${Ident}_handler_fn}, @typeListMisordered, ); + +our $C90_int_types = qr{(?x: + long\s+long\s+int\s+(?:un)?signed| + long\s+long\s+(?:un)?signed\s+int| + long\s+long\s+(?:un)?signed| + (?:(?:un)?signed\s+)?long\s+long\s+int| + (?:(?:un)?signed\s+)?long\s+long| + int\s+long\s+long\s+(?:un)?signed| + int\s+(?:(?:un)?signed\s+)?long\s+long| + + long\s+int\s+(?:un)?signed| + long\s+(?:un)?signed\s+int| + long\s+(?:un)?signed| + (?:(?:un)?signed\s+)?long\s+int| + (?:(?:un)?signed\s+)?long| + int\s+long\s+(?:un)?signed| + int\s+(?:(?:un)?signed\s+)?long| + + int\s+(?:un)?signed| + (?:(?:un)?signed\s+)?int +)}; + our @typeListFile = (); our @typeListWithAttr = ( @typeList, @@ -4517,7 +4539,7 @@ sub process { #print "LINE<$lines[$ln-1]> len<" . length($lines[$ln-1]) . "\n"; $has_flow_statement = 1 if ($ctx =~ /\b(goto|return)\b/); - $has_arg_concat = 1 if ($ctx =~ /\#\#/); + $has_arg_concat = 1 if ($ctx =~ /\#\#/ && $ctx !~ /\#\#\s*(?:__VA_ARGS__|args)\b/); $dstat =~ s/^.\s*\#\s*define\s+$Ident(?:\([^\)]*\))?\s*//; $dstat =~ s/$;//g; @@ -5241,6 +5263,26 @@ sub process { } } +# check for cast of C90 native int or longer types constants + if ($line =~ /(\(\s*$C90_int_types\s*\)\s*)($Constant)\b/) { + my $cast = $1; + my $const = $2; + if (WARN("TYPECAST_INT_CONSTANT", + "Unnecessary typecast of c90 int constant\n" . $herecurr) && + $fix) { + my $suffix = ""; + my $newconst = $const; + $newconst =~ s/${Int_type}$//; + $suffix .= 'U' if ($cast =~ /\bunsigned\b/); + if ($cast =~ /\blong\s+long\b/) { + $suffix .= 'LL'; + } elsif ($cast =~ /\blong\b/) { + $suffix .= 'L'; + } + $fixed[$fixlinenr] =~ s/\Q$cast\E$const\b/$newconst$suffix/; + } + } + # check for sizeof(&) if ($line =~ /\bsizeof\s*\(\s*\&/) { WARN("SIZEOF_ADDRESS", |