Merge branch 'akpm' (patches from Andrew)

0cbeafb2 · Linus Torvalds <[email protected]> · 2016-01-17 12:58:52 -08:00

Merge second patch-bomb from Andrew Morton:

 - more MM stuff:

    - Kirill's page-flags rework

    - Kirill's now-allegedly-fixed THP rework

    - MADV_FREE implementation

    - DAX feature work (msync/fsync).  This isn't quite complete but DAX
      is new and it's good enough and the guys have a handle on what
      needs to be done - I expect this to be wrapped in the next week or
      two.

  - some vsprintf maintenance work

  - various other misc bits

* emailed patches from Andrew Morton <[email protected]>: (145 commits)
  printk: change recursion_bug type to bool
  lib/vsprintf: factor out %pN[F] handler as netdev_bits()
  lib/vsprintf: refactor duplicate code to special_hex_number()
  printk-formats.txt: remove unimplemented %pT
  printk: help pr_debug and pr_devel to optimize out arguments
  lib/test_printf.c: test dentry printing
  lib/test_printf.c: add test for large bitmaps
  lib/test_printf.c: account for kvasprintf tests
  lib/test_printf.c: add a few number() tests
  lib/test_printf.c: test precision quirks
  lib/test_printf.c: check for out-of-bound writes
  lib/test_printf.c: don't BUG
  lib/kasprintf.c: add sanity check to kvasprintf
  lib/vsprintf.c: warn about too large precisions and field widths
  lib/vsprintf.c: help gcc make number() smaller
  lib/vsprintf.c: expand field_width to 24 bits
  lib/vsprintf.c: eliminate potential race in string()
  lib/vsprintf.c: move string() below widen_string()
  lib/vsprintf.c: pull out padding code from dentry_name()
  printk: do cond_resched() between lines while outputting to consoles
  ...

Commit: 0cbeafb245ca568bc0765645aa64f0451b716657
Parents: 58cf279a · 06b031de

Merge commit. Changes below are compared with the first parent: 58cf279a.

Changes

189 files changed · +4429 −2958

File	Status	Add	Del	Content
Documentation/features/vm/pmdp_splitting_flush/arch-support.txt	deleted	+0	−40	View before deletion
Documentation/printk-formats.txt	modified	+0	−9	View file
Documentation/vm/transhuge.txt	modified	+96	−55	View file
arch/alpha/include/uapi/asm/mman.h	modified	+2	−0	View file
arch/arc/Kconfig	modified	+0	−3	View file
arch/arc/mm/cache.c	modified	+2	−2	View file
arch/arm/Kconfig	modified	+0	−5	View file
arch/arm/include/asm/kvm_mmu.h	modified	+3	−2	View file
arch/arm/include/asm/pgtable-3level.h	modified	+1	−9	View file
arch/arm/kvm/mmu.c	modified	+5	−5	View file
arch/arm/lib/uaccess_with_memcpy.c	modified	+2	−3	View file
arch/arm/mm/flush.c	modified	+1	−16	View file
arch/arm64/include/asm/kvm_mmu.h	modified	+2	−1	View file
arch/arm64/include/asm/pgtable.h	modified	+1	−8	View file
arch/arm64/mm/flush.c	modified	+0	−16	View file
arch/avr32/include/asm/page.h	modified	+4	−4	View file
arch/frv/include/asm/page.h	modified	+1	−1	View file
arch/ia64/include/asm/page.h	modified	+1	−0	View file
arch/metag/Kconfig	modified	+0	−3	View file
arch/microblaze/Kconfig	modified	+0	−3	View file
arch/mips/include/asm/kvm_host.h	modified	+3	−3	View file
arch/mips/include/asm/pgtable-bits.h	modified	+4	−6	View file
arch/mips/include/asm/pgtable.h	modified	+0	−18	View file
arch/mips/include/uapi/asm/mman.h	modified	+2	−0	View file
arch/mips/kvm/emulate.c	modified	+1	−1	View file
arch/mips/kvm/tlb.c	modified	+7	−7	View file
arch/mips/mm/c-r4k.c	modified	+2	−1	View file
arch/mips/mm/cache.c	modified	+1	−1	View file
arch/mips/mm/gup.c	modified	+1	−16	View file
arch/mips/mm/init.c	modified	+3	−3	View file
arch/mips/mm/pgtable-64.c	modified	+0	−14	View file
arch/mips/mm/tlbex.c	modified	+0	−1	View file
arch/mn10300/include/asm/page.h	modified	+1	−0	View file
arch/parisc/Kconfig	modified	+0	−3	View file
arch/parisc/include/uapi/asm/mman.h	modified	+2	−0	View file
arch/powerpc/Kconfig	modified	+0	−3	View file
arch/powerpc/include/asm/book3s/64/hash-64k.h	modified	+0	−12	View file
arch/powerpc/include/asm/book3s/64/hash.h	modified	+2	−8	View file
arch/powerpc/include/asm/book3s/64/pgtable.h	modified	+2	−4	View file
arch/powerpc/include/asm/kvm_book3s.h	modified	+2	−2	View file
arch/powerpc/include/asm/kvm_ppc.h	modified	+1	−1	View file
arch/powerpc/kvm/book3s.c	modified	+3	−3	View file
arch/powerpc/kvm/book3s_32_mmu_host.c	modified	+1	−1	View file
arch/powerpc/kvm/book3s_64_mmu_host.c	modified	+1	−1	View file
arch/powerpc/kvm/e500.h	modified	+1	−1	View file
arch/powerpc/kvm/e500_mmu_host.c	modified	+4	−4	View file
arch/powerpc/kvm/trace_pr.h	modified	+1	−1	View file
arch/powerpc/mm/hugepage-hash64.c	modified	+0	−3	View file
arch/powerpc/mm/hugetlbpage.c	modified	+1	−16	View file
arch/powerpc/mm/pgtable_64.c	modified	+0	−49	View file
arch/powerpc/mm/subpage-prot.c	modified	+1	−1	View file
arch/powerpc/sysdev/axonram.c	modified	+4	−5	View file
arch/s390/Kconfig	modified	+0	−3	View file
arch/s390/include/asm/pgtable.h	modified	+1	−15	View file
arch/s390/mm/gup.c	modified	+2	−22	View file
arch/s390/mm/pgtable.c	modified	+28	−19	View file
arch/sh/Kconfig	modified	+0	−3	View file
arch/sh/mm/cache-sh4.c	modified	+1	−1	View file
arch/sh/mm/cache.c	modified	+4	−4	View file
arch/sparc/Kconfig	modified	+0	−4	View file
arch/sparc/include/asm/pgtable_64.h	modified	+6	−13	View file
arch/sparc/mm/fault_64.c	modified	+0	−3	View file
arch/sparc/mm/gup.c	modified	+2	−14	View file
arch/tile/include/asm/pgtable.h	modified	+0	−10	View file
arch/um/include/asm/page.h	modified	+3	−4	View file
arch/um/include/asm/pgtable-3level.h	modified	+2	−2	View file
arch/um/include/asm/pgtable.h	modified	+1	−1	View file
arch/unicore32/Kconfig	modified	+0	−3	View file
arch/x86/Kconfig	modified	+0	−3	View file
arch/x86/include/asm/pgtable.h	modified	+30	−10	View file
arch/x86/include/asm/pgtable_types.h	modified	+6	−3	View file
arch/x86/include/asm/pmem.h	modified	+1	−6	View file
arch/x86/kernel/vm86_32.c	modified	+5	−1	View file
arch/x86/kvm/iommu.c	modified	+6	−5	View file
arch/x86/kvm/mmu.c	modified	+19	−18	View file
arch/x86/kvm/mmu_audit.c	modified	+1	−1	View file
arch/x86/kvm/paging_tmpl.h	modified	+3	−3	View file
arch/x86/kvm/vmx.c	modified	+1	−1	View file
arch/x86/kvm/x86.c	modified	+1	−1	View file
arch/x86/mm/gup.c	modified	+55	−19	View file
arch/x86/mm/init_64.c	modified	+26	−7	View file
arch/x86/mm/pat.c	modified	+3	−2	View file
arch/x86/mm/pgtable.c	modified	+0	−13	View file
arch/xtensa/include/uapi/asm/mman.h	modified	+2	−0	View file
arch/xtensa/mm/tlb.c	modified	+1	−1	View file
drivers/base/memory.c	modified	+13	−0	View file
drivers/block/brd.c	modified	+5	−2	View file
drivers/block/zram/zram_drv.c	modified	+4	−3	View file
drivers/gpu/drm/exynos/exynos_drm_gem.c	modified	+3	−1	View file
drivers/gpu/drm/gma500/framebuffer.c	modified	+3	−1	View file
drivers/gpu/drm/msm/msm_gem.c	modified	+3	−1	View file
drivers/gpu/drm/omapdrm/omap_gem.c	modified	+5	−2	View file
drivers/gpu/drm/ttm/ttm_bo_vm.c	modified	+3	−1	View file
drivers/iio/industrialio-core.c	modified	+4	−5	View file
drivers/net/wireless/intel/iwlwifi/dvm/calib.c	modified	+1	−1	View file
drivers/nvdimm/pfn_devs.c	modified	+1	−2	View file
drivers/nvdimm/pmem.c	modified	+52	−21	View file
drivers/s390/block/dcssblk.c	modified	+5	−6	View file
fs/Kconfig	modified	+2	−1	View file
fs/block_dev.c	modified	+7	−8	View file
fs/cifs/file.c	modified	+4	−4	View file
fs/dax.c	modified	+197	−104	View file
fs/fs-writeback.c	modified	+0	−2	View file
fs/hugetlbfs/inode.c	modified	+76	−67	View file
fs/proc/page.c	modified	+2	−2	View file
fs/proc/task_mmu.c	modified	+35	−20	View file
fs/stat.c	modified	+1	−1	View file
include/asm-generic/pgtable.h	modified	+4	−11	View file
include/asm-generic/sections.h	modified	+65	−0	View file
include/linux/blkdev.h	modified	+17	−3	View file
include/linux/console.h	modified	+1	−0	View file
include/linux/err.h	modified	+1	−1	View file
include/linux/huge_mm.h	modified	+37	−42	View file
include/linux/hugetlb.h	modified	+1	−0	View file
include/linux/io.h	modified	+0	−15	View file
include/linux/kdev_t.h	modified	+0	−5	View file
include/linux/kernel.h	modified	+18	−18	View file
include/linux/kvm_host.h	modified	+19	−18	View file
include/linux/kvm_types.h	modified	+1	−1	View file
include/linux/list.h	modified	+11	−0	View file
include/linux/memblock.h	modified	+9	−9	View file
include/linux/memcontrol.h	modified	+10	−6	View file
include/linux/memory_hotplug.h	modified	+2	−1	View file
include/linux/memremap.h	added	+114	−0	View file
include/linux/mm.h	modified	+115	−84	View file
include/linux/mm_types.h	modified	+11	−14	View file
include/linux/mmdebug.h	modified	+6	−0	View file
include/linux/page-flags.h	modified	+173	−113	View file
include/linux/pagemap.h	modified	+20	−18	View file
include/linux/pfn.h	modified	+9	−0	View file
include/linux/pfn_t.h	added	+102	−0	View file
include/linux/poison.h	modified	+5	−1	View file
include/linux/printk.h	modified	+6	−6	View file
include/linux/rmap.h	modified	+32	−5	View file
include/linux/swap.h	modified	+3	−1	View file
include/linux/vm_event_item.h	modified	+4	−1	View file
include/trace/events/huge_memory.h	modified	+1	−0	View file
include/uapi/asm-generic/mman-common.h	modified	+1	−0	View file
init/Kconfig	modified	+1	−1	View file
kernel/events/uprobes.c	modified	+6	−5	View file
kernel/futex.c	modified	+15	−50	View file
kernel/memremap.c	modified	+210	−9	View file
kernel/panic.c	modified	+1	−2	View file
kernel/printk/printk.c	modified	+62	−5	View file
kernel/stop_machine.c	modified	+0	−4	View file
lib/Kconfig.debug	modified	+8	−1	View file
lib/kasprintf.c	modified	+6	−4	View file
lib/list_debug.c	modified	+9	−0	View file
lib/test_printf.c	modified	+109	−12	View file
lib/vsprintf.c	modified	+145	−107	View file
mm/debug.c	modified	+4	−4	View file
mm/filemap.c	modified	+14	−11	View file
mm/gup.c	modified	+109	−63	View file
mm/huge_memory.c	modified	+1017	−633	View file
mm/hugetlb.c	modified	+6	−6	View file
mm/internal.h	modified	+22	−48	View file
mm/ksm.c	modified	+19	−50	View file
mm/madvise.c	modified	+201	−0	View file
mm/memcontrol.c	modified	+41	−65	View file
mm/memory-failure.c	modified	+58	−67	View file
mm/memory.c	modified	+49	−52	View file
mm/memory_hotplug.c	modified	+48	−19	View file
mm/mempolicy.c	modified	+40	−5	View file
mm/migrate.c	modified	+13	−8	View file
mm/mincore.c	modified	+1	−1	View file
mm/mlock.c	modified	+20	−7	View file
mm/mmap.c	modified	+20	−5	View file
mm/mprotect.c	modified	+4	−3	View file
mm/mremap.c	modified	+7	−8	View file
mm/page_alloc.c	modified	+40	−7	View file
mm/page_idle.c	modified	+14	−13	View file
mm/page_isolation.c	modified	+4	−2	View file
mm/pagewalk.c	modified	+1	−1	View file
mm/pgtable-generic.c	modified	+1	−13	View file
mm/rmap.c	modified	+258	−111	View file
mm/shmem.c	modified	+14	−11	View file
mm/slub.c	modified	+2	−0	View file
mm/sparse-vmemmap.c	modified	+74	−2	View file
mm/sparse.c	modified	+5	−3	View file
mm/swap.c	modified	+60	−259	View file
mm/swap_state.c	modified	+4	−5	View file
mm/swapfile.c	modified	+14	−20	View file
mm/userfaultfd.c	modified	+4	−4	View file
mm/util.c	modified	+20	−4	View file
mm/vmalloc.c	modified	+2	−2	View file
mm/vmscan.c	modified	+13	−3	View file
mm/vmstat.c	modified	+4	−1	View file
scripts/tags.sh	modified	+0	−2	View file
virt/kvm/kvm_main.c	modified	+24	−23	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/features/vm/pmdp_splitting_flush/arch-support.txt

View before deletion

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 26f74b4..0000000
--- 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 |
-    -----------------------

Documentation/printk-formats.txt

View file

diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 6389551..5d1128b 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -306,15 +306,6 @@ Network device features:
 
 	Passed by reference.
 
-Command from struct task_struct
-
-	%pT	ls
-
-	For printing executable name excluding path from struct
-	task_struct.
-
-	Passed by reference.
-
 If you add other %p extensions, please extend lib/test_printf.c with
 one or more test cases, if at all feasible.
 

Documentation/vm/transhuge.txt

View file

diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 8a28268..21cf34f 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.

arch/alpha/include/uapi/asm/mman.h

View file

diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index f2f9496..ab336c0 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -47,8 +47,10 @@
 #define MADV_WILLNEED	3		/* will need these pages */
 #define	MADV_SPACEAVAIL	5		/* ensure resources are available */
 #define MADV_DONTNEED	6		/* don't need these pages */
+#define MADV_FREE	7		/* free pages only if memory pressure */
 
 /* common/generic parameters */
+#define MADV_FREE	8		/* free pages only if memory pressure */
 #define MADV_REMOVE	9		/* remove these pages & resources */
 #define MADV_DONTFORK	10		/* don't inherit across fork */
 #define MADV_DOFORK	11		/* do inherit across fork */

arch/arc/Kconfig

View file

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 6312f60..76dde9d 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -73,9 +73,6 @@ config STACKTRACE_SUPPORT
 	def_bool y
 	select STACKTRACE
 
-config HAVE_LATENCYTOP_SUPPORT
-	def_bool y
-
 config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	def_bool y
 	depends on ARC_MMU_V4

arch/arc/mm/cache.c

View file

diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index ff7ff6c..b65f797 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;
 	}

arch/arm/Kconfig

View file

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4e489cc..6a889af 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -168,11 +168,6 @@ config STACKTRACE_SUPPORT
 	bool
 	default y
 
-config HAVE_LATENCYTOP_SUPPORT
-	bool
-	depends on !SMP
-	default y
-
 config LOCKDEP_SUPPORT
 	bool
 	default y

arch/arm/include/asm/kvm_mmu.h

View file

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 9203c21..a520b79 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -182,7 +182,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;
 }
 
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
+					       kvm_pfn_t pfn,
 					       unsigned long size,
 					       bool ipa_uncached)
 {
@@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte)
 static inline void __kvm_flush_dcache_pmd(pmd_t pmd)
 {
 	unsigned long size = PMD_SIZE;
-	pfn_t pfn = pmd_pfn(pmd);
+	kvm_pfn_t pfn = pmd_pfn(pmd);
 
 	while (size) {
 		void *va = kmap_atomic_pfn(pfn);

arch/arm/include/asm/pgtable-3level.h

View file

diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index a745a2a..dc46398 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -88,7 +88,6 @@
 
 #define L_PMD_SECT_VALID	(_AT(pmdval_t, 1) << 0)
 #define L_PMD_SECT_DIRTY	(_AT(pmdval_t, 1) << 55)
-#define L_PMD_SECT_SPLITTING	(_AT(pmdval_t, 1) << 56)
 #define L_PMD_SECT_NONE		(_AT(pmdval_t, 1) << 57)
 #define L_PMD_SECT_RDONLY	(_AT(pteval_t, 1) << 58)
 
@@ -232,13 +231,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !pmd_table(pmd))
-#define pmd_trans_splitting(pmd) (pmd_isset((pmd), L_PMD_SECT_SPLITTING))
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
-			  pmd_t *pmdp);
-#endif
 #endif
 
 #define PMD_BIT_FUNC(fn,op) \
@@ -246,9 +238,9 @@ static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
 
 PMD_BIT_FUNC(wrprotect,	|= L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkold,	&= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= L_PMD_SECT_SPLITTING);
 PMD_BIT_FUNC(mkwrite,   &= ~L_PMD_SECT_RDONLY);
 PMD_BIT_FUNC(mkdirty,   |= L_PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkclean,   &= ~L_PMD_SECT_DIRTY);
 PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
 
 #define pmd_mkhuge(pmd)		(__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))

arch/arm/kvm/mmu.c

View file

diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 22f7fa0..aba61fd 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -992,9 +992,9 @@ out:
 	return ret;
 }
 
-static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
+static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
 {
-	pfn_t pfn = *pfnp;
+	kvm_pfn_t pfn = *pfnp;
 	gfn_t gfn = *ipap >> PAGE_SHIFT;
 
 	if (PageTransCompound(pfn_to_page(pfn))) {
@@ -1201,7 +1201,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
 }
 
-static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,
 				      unsigned long size, bool uncached)
 {
 	__coherent_cache_guest_page(vcpu, pfn, size, uncached);
@@ -1218,7 +1218,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
 	bool fault_ipa_uncached;
 	bool logging_active = memslot_is_logging(memslot);
@@ -1346,7 +1346,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa)
 {
 	pmd_t *pmd;
 	pte_t *pte;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	bool pfn_valid = false;
 
 	trace_kvm_access_fault(fault_ipa);

arch/arm/lib/uaccess_with_memcpy.c

View file

diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 588bbc2..6bd1089 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 = &current->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;
 		}

arch/arm/mm/flush.c

View file

diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 1ec8e75..d0ba355 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 */

arch/arm64/include/asm/kvm_mmu.h

View file

diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 0bf8b43..7364339 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -230,7 +230,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
 }
 
-static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,
+static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
+					       kvm_pfn_t pfn,
 					       unsigned long size,
 					       bool ipa_uncached)
 {

arch/arm64/include/asm/pgtable.h

View file

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 69d2e2f..2d545d7 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -353,21 +353,14 @@ static inline pgprot_t mk_sect_prot(pgprot_t prot)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd)	pte_special(pmd_pte(pmd))
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
-struct vm_area_struct;
-void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
-			  pmd_t *pmdp);
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
-#define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkclean(pmd)       pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mknotpresent(pmd)	(__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))

arch/arm64/mm/flush.c

View file

diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 46649d6..60585bd 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -102,19 +102,3 @@ EXPORT_SYMBOL(flush_dcache_page);
  * Additional functions defined in assembly.
  */
 EXPORT_SYMBOL(flush_icache_range);
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
-			  pmd_t *pmdp)
-{
-	pmd_t pmd = pmd_mksplitting(*pmdp);
-
-	VM_BUG_ON(address & ~PMD_MASK);
-	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
-
-	/* dummy IPI to serialise against fast_gup */
-	kick_all_cpus_sync();
-}
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

arch/avr32/include/asm/page.h

View file

diff --git a/arch/avr32/include/asm/page.h b/arch/avr32/include/asm/page.h
index f805d1c..c5d2a3e 100644
--- a/arch/avr32/include/asm/page.h
+++ b/arch/avr32/include/asm/page.h
@@ -83,11 +83,9 @@ static inline int get_order(unsigned long size)
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 
-#define PHYS_PFN_OFFSET		(CONFIG_PHYS_OFFSET >> PAGE_SHIFT)
+#define ARCH_PFN_OFFSET		(CONFIG_PHYS_OFFSET >> PAGE_SHIFT)
 
-#define pfn_to_page(pfn)	(mem_map + ((pfn) - PHYS_PFN_OFFSET))
-#define page_to_pfn(page)	((unsigned long)((page) - mem_map) + PHYS_PFN_OFFSET)
-#define pfn_valid(pfn)		((pfn) >= PHYS_PFN_OFFSET && (pfn) < (PHYS_PFN_OFFSET + max_mapnr))
+#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && (pfn) < (ARCH_PFN_OFFSET + max_mapnr))
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
@@ -101,4 +99,6 @@ static inline int get_order(unsigned long size)
  */
 #define HIGHMEM_START		0x20000000UL
 
+#include <asm-generic/memory_model.h>
+
 #endif /* __ASM_AVR32_PAGE_H */

arch/frv/include/asm/page.h

View file

diff --git a/arch/frv/include/asm/page.h b/arch/frv/include/asm/page.h
index 8c97068..688d807 100644
--- a/arch/frv/include/asm/page.h
+++ b/arch/frv/include/asm/page.h
@@ -34,7 +34,7 @@ typedef struct page *pgtable_t;
 #define pgprot_val(x)	((x).pgprot)
 
 #define __pte(x)	((pte_t) { (x) } )

This diff is incomplete. Download the complete patch.