The patch titled Subject: mm: allow page fault handlers to perform the COW has been added to the -mm tree. Its filename is mm-allow-page-fault-handlers-to-perform-the-cow.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-allow-page-fault-handlers-to-perform-the-cow.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-allow-page-fault-handlers-to-perform-the-cow.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Matthew Wilcox <matthew.r.wilcox@xxxxxxxxx> Subject: mm: allow page fault handlers to perform the COW Currently COW of an XIP file is done by first bringing in a read-only mapping, then retrying the fault and copying the page. It is much more efficient to tell the fault handler that a COW is being attempted (by passing in the pre-allocated page in the vm_fault structure), and allow the handler to perform the COW operation itself. The handler cannot insert the page itself if there is already a read-only mapping at that address, so allow the handler to return VM_FAULT_LOCKED and set the fault_page to be NULL. This indicates to the MM code that the i_mmap_lock is held instead of the page lock. Signed-off-by: Matthew Wilcox <matthew.r.wilcox@xxxxxxxxx> Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Andreas Dilger <andreas.dilger@xxxxxxxxx> Cc: Boaz Harrosh <boaz@xxxxxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Cc: Dave Chinner <david@xxxxxxxxxxxxx> Cc: Jan Kara <jack@xxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx> Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx> Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx> Cc: Theodore Ts'o <tytso@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mm.h | 1 + mm/memory.c | 33 ++++++++++++++++++++++++--------- 2 files changed, 25 insertions(+), 9 deletions(-) diff -puN include/linux/mm.h~mm-allow-page-fault-handlers-to-perform-the-cow include/linux/mm.h --- a/include/linux/mm.h~mm-allow-page-fault-handlers-to-perform-the-cow +++ a/include/linux/mm.h @@ -227,6 +227,7 @@ struct vm_fault { pgoff_t pgoff; /* Logical page offset based on vma */ void __user *virtual_address; /* Faulting virtual address */ + struct page *cow_page; /* Handler may choose to COW */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by diff -puN mm/memory.c~mm-allow-page-fault-handlers-to-perform-the-cow mm/memory.c --- a/mm/memory.c~mm-allow-page-fault-handlers-to-perform-the-cow +++ a/mm/memory.c @@ -1995,6 +1995,7 @@ static int do_page_mkwrite(struct vm_are vmf.pgoff = page->index; vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; vmf.page = page; + vmf.cow_page = NULL; ret = vma->vm_ops->page_mkwrite(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) @@ -2701,7 +2702,8 @@ oom: * See filemap_fault() and __lock_page_retry(). */ static int __do_fault(struct vm_area_struct *vma, unsigned long address, - pgoff_t pgoff, unsigned int flags, struct page **page) + pgoff_t pgoff, unsigned int flags, + struct page *cow_page, struct page **page) { struct vm_fault vmf; int ret; @@ -2710,10 +2712,13 @@ static int __do_fault(struct vm_area_str vmf.pgoff = pgoff; vmf.flags = flags; vmf.page = NULL; + vmf.cow_page = cow_page; ret = vma->vm_ops->fault(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; + if (!vmf.page) + goto out; if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) @@ -2727,6 +2732,7 @@ static int __do_fault(struct vm_area_str else VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); + out: *page = vmf.page; return ret; } @@ -2900,7 +2906,7 @@ static int do_read_fault(struct mm_struc pte_unmap_unlock(pte, ptl); } - ret = __do_fault(vma, address, pgoff, flags, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; @@ -2940,26 +2946,35 @@ static int do_cow_fault(struct mm_struct return VM_FAULT_OOM; } - ret = __do_fault(vma, address, pgoff, flags, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; - copy_user_highpage(new_page, fault_page, address, vma); + if (fault_page) + copy_user_highpage(new_page, fault_page, address, vma); __SetPageUptodate(new_page); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); - unlock_page(fault_page); - page_cache_release(fault_page); + if (fault_page) { + unlock_page(fault_page); + page_cache_release(fault_page); + } else { + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + } goto uncharge_out; } do_set_pte(vma, address, new_page, pte, true, true); mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); pte_unmap_unlock(pte, ptl); - unlock_page(fault_page); - page_cache_release(fault_page); + if (fault_page) { + unlock_page(fault_page); + page_cache_release(fault_page); + } else { + mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex); + } return ret; uncharge_out: mem_cgroup_cancel_charge(new_page, memcg); @@ -2978,7 +2993,7 @@ static int do_shared_fault(struct mm_str int dirtied = 0; int ret, tmp; - ret = __do_fault(vma, address, pgoff, flags, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; _ Patches currently in -mm which might be from matthew.r.wilcox@xxxxxxxxx are axonram-fix-bug-in-direct_access.patch block-change-direct_access-calling-convention.patch mm-fix-xip-fault-vs-truncate-race.patch mm-fix-xip-fault-vs-truncate-race-fix.patch mm-allow-page-fault-handlers-to-perform-the-cow.patch mm-allow-page-fault-handlers-to-perform-the-cow-fix.patch vfsext2-introduce-is_daxinode.patch daxext2-replace-xip-read-and-write-with-dax-i-o.patch daxext2-replace-ext2_clear_xip_target-with-dax_clear_blocks.patch daxext2-replace-the-xip-page-fault-handler-with-the-dax-page-fault-handler.patch daxext2-replace-the-xip-page-fault-handler-with-the-dax-page-fault-handler-fix.patch daxext2-replace-xip_truncate_page-with-dax_truncate_page.patch vfs-remove-get_xip_mem.patch ext2-remove-ext2_xip_verify_sb.patch ext2-remove-ext2_use_xip.patch ext2-remove-xipc-and-xiph.patch vfsext2-remove-config_ext2_fs_xip-and-rename-config_fs_xip-to-config_fs_dax.patch ext2-remove-ext2_aops_xip.patch ext2-get-rid-of-most-mentions-of-xip-in-ext2.patch dax-add-dax_zero_page_range.patch dax-add-dax_zero_page_range-fix.patch ext4-add-dax-functionality.patch brd-rename-xip-to-dax.patch do_shared_fault-check-that-mmap_sem-is-held.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html