Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "The remainder of the main mm/ queue.

  143 patches.

  Subsystems affected by this patch series (all mm): pagecache, hugetlb,
  userfaultfd, vmscan, compaction, migration, cma, ksm, vmstat, mmap,
  kconfig, util, memory-hotplug, zswap, zsmalloc, highmem, cleanups, and
  kfence"

* emailed patches from Andrew Morton <[email protected]>: (143 commits)
  kfence: use power-efficient work queue to run delayed work
  kfence: maximize allocation wait timeout duration
  kfence: await for allocation using wait_event
  kfence: zero guard page after out-of-bounds access
  mm/process_vm_access.c: remove duplicate include
  mm/mempool: minor coding style tweaks
  mm/highmem.c: fix coding style issue
  btrfs: use memzero_page() instead of open coded kmap pattern
  iov_iter: lift memzero_page() to highmem.h
  mm/zsmalloc: use BUG_ON instead of if condition followed by BUG.
  mm/zswap.c: switch from strlcpy to strscpy
  arm64/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
  x86/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
  mm,memory_hotplug: add kernel boot option to enable memmap_on_memory
  acpi,memhotplug: enable MHP_MEMMAP_ON_MEMORY when supported
  mm,memory_hotplug: allocate memmap from the added memory range
  mm,memory_hotplug: factor out adjusting present pages into adjust_present_page_count()
  mm,memory_hotplug: relax fully spanned sections check
  drivers/base/memory: introduce memory_block_{online,offline}
  mm/memory_hotplug: remove broken locking of zone PCP structures during hot remove
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-kernel-mm-cma

@@ -0,0 +1,25 @@
+What:		/sys/kernel/mm/cma/
+Date:		Feb 2021
+Contact:	Minchan Kim <[email protected]>
+Description:
+		/sys/kernel/mm/cma/ contains a subdirectory for each CMA
+		heap name (also sometimes called CMA areas).
+
+		Each CMA heap subdirectory (that is, each
+		/sys/kernel/mm/cma/<cma-heap-name> directory) contains the
+		following items:
+
+			alloc_pages_success
+			alloc_pages_fail
+
+What:		/sys/kernel/mm/cma/<cma-heap-name>/alloc_pages_success
+Date:		Feb 2021
+Contact:	Minchan Kim <[email protected]>
+Description:
+		the number of pages CMA API succeeded to allocate
+
+What:		/sys/kernel/mm/cma/<cma-heap-name>/alloc_pages_fail
+Date:		Feb 2021
+Contact:	Minchan Kim <[email protected]>
+Description:
+		the number of pages CMA API failed to allocate

Documentation/admin-guide/kernel-parameters.txt

@@ -2804,6 +2804,23 @@
 			seconds.  Use this parameter to check at some
 			other rate.  0 disables periodic checking.
 
+	memory_hotplug.memmap_on_memory
+			[KNL,X86,ARM] Boolean flag to enable this feature.
+			Format: {on | off (default)}
+			When enabled, runtime hotplugged memory will
+			allocate its internal metadata (struct pages)
+			from the hotadded memory which will allow to
+			hotadd a lot of memory without requiring
+			additional memory to do so.
+			This feature is disabled by default because it
+			has some implication on large (e.g. GB)
+			allocations in some configurations (e.g. small
+			memory blocks).
+			The state of the flag can be read in
+			/sys/module/memory_hotplug/parameters/memmap_on_memory.
+			Note that even when enabled, there are a few cases where
+			the feature is not effective.
+
 	memtest=	[KNL,X86,ARM,PPC] Enable memtest
 			Format: <integer>
 			default : 0 <disable>

Documentation/admin-guide/mm/memory-hotplug.rst

@@ -357,6 +357,15 @@ creates ZONE_MOVABLE as following.
    Unfortunately, there is no information to show which memory block belongs
    to ZONE_MOVABLE. This is TBD.
 
+.. note::
+   Techniques that rely on long-term pinnings of memory (especially, RDMA and
+   vfio) are fundamentally problematic with ZONE_MOVABLE and, therefore, memory
+   hot remove. Pinned pages cannot reside on ZONE_MOVABLE, to guarantee that
+   memory can still get hot removed - be aware that pinning can fail even if
+   there is plenty of free memory in ZONE_MOVABLE. In addition, using
+   ZONE_MOVABLE might make page pinning more expensive, because pages have to be
+   migrated off that zone first.
+
 .. _memory_hotplug_how_to_offline_memory:
 
 How to offline memory

Documentation/admin-guide/mm/userfaultfd.rst

@@ -63,68 +63,93 @@ the generic ioctl available.
 
 The ``uffdio_api.features`` bitmask returned by the ``UFFDIO_API`` ioctl
 defines what memory types are supported by the ``userfaultfd`` and what
-events, except page fault notifications, may be generated.
-
-If the kernel supports registering ``userfaultfd`` ranges on hugetlbfs
-virtual memory areas, ``UFFD_FEATURE_MISSING_HUGETLBFS`` will be set in
-``uffdio_api.features``. Similarly, ``UFFD_FEATURE_MISSING_SHMEM`` will be
-set if the kernel supports registering ``userfaultfd`` ranges on shared
-memory (covering all shmem APIs, i.e. tmpfs, ``IPCSHM``, ``/dev/zero``,
-``MAP_SHARED``, ``memfd_create``, etc).
-
-The userland application that wants to use ``userfaultfd`` with hugetlbfs
-or shared memory need to set the corresponding flag in
-``uffdio_api.features`` to enable those features.
-
-If the userland desires to receive notifications for events other than
-page faults, it has to verify that ``uffdio_api.features`` has appropriate
-``UFFD_FEATURE_EVENT_*`` bits set. These events are described in more
-detail below in `Non-cooperative userfaultfd`_ section.
-
-Once the ``userfaultfd`` has been enabled the ``UFFDIO_REGISTER`` ioctl should
-be invoked (if present in the returned ``uffdio_api.ioctls`` bitmask) to
-register a memory range in the ``userfaultfd`` by setting the
+events, except page fault notifications, may be generated:
+
+- The ``UFFD_FEATURE_EVENT_*`` flags indicate that various other events
+  other than page faults are supported. These events are described in more
+  detail below in the `Non-cooperative userfaultfd`_ section.
+
+- ``UFFD_FEATURE_MISSING_HUGETLBFS`` and ``UFFD_FEATURE_MISSING_SHMEM``
+  indicate that the kernel supports ``UFFDIO_REGISTER_MODE_MISSING``
+  registrations for hugetlbfs and shared memory (covering all shmem APIs,
+  i.e. tmpfs, ``IPCSHM``, ``/dev/zero``, ``MAP_SHARED``, ``memfd_create``,
+  etc) virtual memory areas, respectively.
+
+- ``UFFD_FEATURE_MINOR_HUGETLBFS`` indicates that the kernel supports
+  ``UFFDIO_REGISTER_MODE_MINOR`` registration for hugetlbfs virtual memory
+  areas.
+
+The userland application should set the feature flags it intends to use
+when invoking the ``UFFDIO_API`` ioctl, to request that those features be
+enabled if supported.
+
+Once the ``userfaultfd`` API has been enabled the ``UFFDIO_REGISTER``
+ioctl should be invoked (if present in the returned ``uffdio_api.ioctls``
+bitmask) to register a memory range in the ``userfaultfd`` by setting the
 uffdio_register structure accordingly. The ``uffdio_register.mode``
 bitmask will specify to the kernel which kind of faults to track for
-the range (``UFFDIO_REGISTER_MODE_MISSING`` would track missing
-pages). The ``UFFDIO_REGISTER`` ioctl will return the
+the range. The ``UFFDIO_REGISTER`` ioctl will return the
 ``uffdio_register.ioctls`` bitmask of ioctls that are suitable to resolve
 userfaults on the range registered. Not all ioctls will necessarily be
-supported for all memory types depending on the underlying virtual
-memory backend (anonymous memory vs tmpfs vs real filebacked
-mappings).
+supported for all memory types (e.g. anonymous memory vs. shmem vs.
+hugetlbfs), or all types of intercepted faults.
 
 Userland can use the ``uffdio_register.ioctls`` to manage the virtual
 address space in the background (to add or potentially also remove
 memory from the ``userfaultfd`` registered range). This means a userfault
 could be triggering just before userland maps in the background the
 user-faulted page.
 
-The primary ioctl to resolve userfaults is ``UFFDIO_COPY``. That
-atomically copies a page into the userfault registered range and wakes
-up the blocked userfaults
-(unless ``uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE`` is set).
-Other ioctl works similarly to ``UFFDIO_COPY``. They're atomic as in
-guaranteeing that nothing can see an half copied page since it'll
-keep userfaulting until the copy has finished.
+Resolving Userfaults
+--------------------
+
+There are three basic ways to resolve userfaults:
+
+- ``UFFDIO_COPY`` atomically copies some existing page contents from
+  userspace.
+
+- ``UFFDIO_ZEROPAGE`` atomically zeros the new page.
+
+- ``UFFDIO_CONTINUE`` maps an existing, previously-populated page.
+
+These operations are atomic in the sense that they guarantee nothing can
+see a half-populated page, since readers will keep userfaulting until the
+operation has finished.
+
+By default, these wake up userfaults blocked on the range in question.
+They support a ``UFFDIO_*_MODE_DONTWAKE`` ``mode`` flag, which indicates
+that waking will be done separately at some later time.
+
+Which ioctl to choose depends on the kind of page fault, and what we'd
+like to do to resolve it:
+
+- For ``UFFDIO_REGISTER_MODE_MISSING`` faults, the fault needs to be
+  resolved by either providing a new page (``UFFDIO_COPY``), or mapping
+  the zero page (``UFFDIO_ZEROPAGE``). By default, the kernel would map
+  the zero page for a missing fault. With userfaultfd, userspace can
+  decide what content to provide before the faulting thread continues.
+
+- For ``UFFDIO_REGISTER_MODE_MINOR`` faults, there is an existing page (in
+  the page cache). Userspace has the option of modifying the page's
+  contents before resolving the fault. Once the contents are correct
+  (modified or not), userspace asks the kernel to map the page and let the
+  faulting thread continue with ``UFFDIO_CONTINUE``.
 
 Notes:
 
-- If you requested ``UFFDIO_REGISTER_MODE_MISSING`` when registering then
-  you must provide some kind of page in your thread after reading from
-  the uffd.  You must provide either ``UFFDIO_COPY`` or ``UFFDIO_ZEROPAGE``.
-  The normal behavior of the OS automatically providing a zero page on
-  an anonymous mmaping is not in place.
+- You can tell which kind of fault occurred by examining
+  ``pagefault.flags`` within the ``uffd_msg``, checking for the
+  ``UFFD_PAGEFAULT_FLAG_*`` flags.
 
 - None of the page-delivering ioctls default to the range that you
   registered with.  You must fill in all fields for the appropriate
   ioctl struct including the range.
 
 - You get the address of the access that triggered the missing page
   event out of a struct uffd_msg that you read in the thread from the
-  uffd.  You can supply as many pages as you want with ``UFFDIO_COPY`` or
-  ``UFFDIO_ZEROPAGE``.  Keep in mind that unless you used DONTWAKE then
-  the first of any of those IOCTLs wakes up the faulting thread.
+  uffd.  You can supply as many pages as you want with these IOCTLs.
+  Keep in mind that unless you used DONTWAKE then the first of any of
+  those IOCTLs wakes up the faulting thread.
 
 - Be sure to test for all errors including
   (``pollfd[0].revents & POLLERR``).  This can happen, e.g. when ranges

arch/arc/Kconfig

@@ -6,6 +6,7 @@
 config ARC
 	def_bool y
 	select ARC_TIMERS
+	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DMA_PREP_COHERENT
 	select ARCH_HAS_PTE_SPECIAL
@@ -28,6 +29,7 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARC_MMU_V4
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_FUTEX_CMPXCHG if FUTEX
@@ -48,9 +50,6 @@ config ARC
 	select HAVE_ARCH_JUMP_LABEL if ISA_ARCV2 && !CPU_ENDIAN_BE32
 	select SET_FS
 
-config ARCH_HAS_CACHE_LINE_SIZE
-	def_bool y
-
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
@@ -86,10 +85,6 @@ config STACKTRACE_SUPPORT
 	def_bool y
 	select STACKTRACE
 
-config HAVE_ARCH_TRANSPARENT_HUGEPAGE
-	def_bool y
-	depends on ARC_MMU_V4
-
 menu "ARC Architecture Configuration"
 
 menu "ARC Platform/SoC/Board"

arch/arm/Kconfig

@@ -31,6 +31,7 @@ config ARM
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_HUGETLBFS if ARM_LPAE
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_MEMTEST
@@ -77,6 +78,7 @@ config ARM
 	select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARM_LPAE
 	select HAVE_ARM_SMCCC if CPU_V7
 	select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32
 	select HAVE_CONTEXT_TRACKING
@@ -1511,14 +1513,6 @@ config HW_PERF_EVENTS
 	def_bool y
 	depends on ARM_PMU
 
-config SYS_SUPPORTS_HUGETLBFS
-       def_bool y
-       depends on ARM_LPAE
-
-config HAVE_ARCH_TRANSPARENT_HUGEPAGE
-       def_bool y
-       depends on ARM_LPAE
-
 config ARCH_WANT_GENERAL_HUGETLB
 	def_bool y
 

arch/arm64/Kconfig

@@ -11,6 +11,12 @@ config ARM64
 	select ACPI_PPTT if ACPI
 	select ARCH_HAS_DEBUG_WX
 	select ARCH_BINFMT_ELF_STATE
+	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
+	select ARCH_ENABLE_MEMORY_HOTPLUG
+	select ARCH_ENABLE_MEMORY_HOTREMOVE
+	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
+	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
+	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DMA_PREP_COHERENT
@@ -72,6 +78,7 @@ config ARM64
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_USE_SYM_ANNOTATIONS
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	select ARCH_SUPPORTS_HUGETLBFS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK
 	select ARCH_SUPPORTS_LTO_CLANG if CPU_LITTLE_ENDIAN
@@ -213,6 +220,7 @@ config ARM64
 	select SWIOTLB
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
+	select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -308,10 +316,7 @@ config ZONE_DMA32
 	bool "Support DMA32 zone" if EXPERT
 	default y
 
-config ARCH_ENABLE_MEMORY_HOTPLUG
-	def_bool y
-
-config ARCH_ENABLE_MEMORY_HOTREMOVE
+config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
 	def_bool y
 
 config SMP
@@ -1070,18 +1075,9 @@ config HW_PERF_EVENTS
 	def_bool y
 	depends on ARM_PMU
 
-config SYS_SUPPORTS_HUGETLBFS
-	def_bool y
-
-config ARCH_HAS_CACHE_LINE_SIZE
-	def_bool y
-
 config ARCH_HAS_FILTER_PGPROT
 	def_bool y
 
-config ARCH_ENABLE_SPLIT_PMD_PTLOCK
-	def_bool y if PGTABLE_LEVELS > 2
-
 # Supported by clang >= 7.0
 config CC_HAVE_SHADOW_CALL_STACK
 	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)
@@ -1923,14 +1919,6 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
-config ARCH_ENABLE_HUGEPAGE_MIGRATION
-	def_bool y
-	depends on HUGETLB_PAGE && MIGRATION
-
-config ARCH_ENABLE_THP_MIGRATION
-	def_bool y
-	depends on TRANSPARENT_HUGEPAGE
-
 menu "Power management options"
 
 source "kernel/power/Kconfig"

arch/arm64/mm/hugetlbpage.c

@@ -252,7 +252,7 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 		set_pte(ptep, pte);
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgdp;
@@ -284,9 +284,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		 */
 		ptep = pte_alloc_map(mm, pmdp, addr);
 	} else if (sz == PMD_SIZE) {
-		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
-		    pud_none(READ_ONCE(*pudp)))
-			ptep = huge_pmd_share(mm, addr, pudp);
+		if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp)))
+			ptep = huge_pmd_share(mm, vma, addr, pudp);
 		else
 			ptep = (pte_t *)pmd_alloc(mm, pudp, addr);
 	} else if (sz == (CONT_PMD_SIZE)) {