Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things and hotfixes

 - ocfs2

 - almost all of MM

* emailed patches from Andrew Morton <[email protected]>: (139 commits)
  kernel/memremap.c: remove the unused device_private_entry_fault() export
  mm: delete find_get_entries_tag
  mm/huge_memory.c: make __thp_get_unmapped_area static
  mm/mprotect.c: fix compilation warning because of unused 'mm' variable
  mm/page-writeback: introduce tracepoint for wait_on_page_writeback()
  mm/vmscan: simplify trace_reclaim_flags and trace_shrink_flags
  mm/Kconfig: update "Memory Model" help text
  mm/vmscan.c: don't disable irq again when count pgrefill for memcg
  mm: memblock: make keeping memblock memory opt-in rather than opt-out
  hugetlbfs: always use address space in inode for resv_map pointer
  mm/z3fold.c: support page migration
  mm/z3fold.c: add structure for buddy handles
  mm/z3fold.c: improve compression by extending search
  mm/z3fold.c: introduce helper functions
  mm/page_alloc.c: remove unnecessary parameter in rmqueue_pcplist
  mm/hmm: add ARCH_HAS_HMM_MIRROR ARCH_HAS_HMM_DEVICE Kconfig
  mm/vmscan.c: simplify shrink_inactive_list()
  fs/sync.c: sync_file_range(2) may use WB_SYNC_ALL writeback
  xen/privcmd-buf.c: convert to use vm_map_pages_zero()
  xen/gntdev.c: convert to use vm_map_pages()
  ...

Documentation/sysctl/vm.txt

@@ -61,6 +61,7 @@ Currently, these files are in /proc/sys/vm:
 - stat_refresh
 - numa_stat
 - swappiness
+- unprivileged_userfaultfd
 - user_reserve_kbytes
 - vfs_cache_pressure
 - watermark_boost_factor
@@ -818,6 +819,17 @@ The default value is 60.
 
 ==============================================================
 
+unprivileged_userfaultfd
+
+This flag controls whether unprivileged users can use the userfaultfd
+system calls.  Set this to 1 to allow unprivileged users to use the
+userfaultfd system calls, or set this to 0 to restrict userfaultfd to only
+privileged users (with SYS_CAP_PTRACE capability).
+
+The default value is 1.
+
+==============================================================
+
 - user_reserve_kbytes
 
 When overcommit_memory is set to 2, "never overcommit" mode, reserve

Documentation/trace/postprocess/trace-vmscan-postprocess.pl

@@ -113,7 +113,7 @@ sub sigint_handler {
 my $regex_kswapd_sleep_default = 'nid=([0-9]*)';
 my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)';
 my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) classzone_idx=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)';
-my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';
+my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate_anon=([0-9]*) nr_activate_file=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';
 my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)';
 my $regex_writepage_default = 'page=([0-9a-f]*) pfn=([0-9]*) flags=([A-Z_|]*)';
 
@@ -212,7 +212,8 @@ sub generate_traceevent_regex {
 			"vmscan/mm_vmscan_lru_shrink_inactive",
 			$regex_lru_shrink_inactive_default,
 			"nid", "nr_scanned", "nr_reclaimed", "nr_dirty", "nr_writeback",
-			"nr_congested", "nr_immediate", "nr_activate", "nr_ref_keep",
+			"nr_congested", "nr_immediate", "nr_activate_anon",
+			"nr_activate_file", "nr_ref_keep",
 			"nr_unmap_fail", "priority", "flags");
 $regex_lru_shrink_active = generate_traceevent_regex(
 			"vmscan/mm_vmscan_lru_shrink_active",
@@ -407,7 +408,7 @@ sub process_events {
 			}
 
 			my $nr_reclaimed = $3;
-			my $flags = $12;
+			my $flags = $13;
 			my $file = 0;
 			if ($flags =~ /RECLAIM_WB_FILE/) {
 				$file = 1;

Documentation/vm/hmm.rst

@@ -189,20 +189,10 @@ the driver callback returns.
 When the device driver wants to populate a range of virtual addresses, it can
 use either::
 
-  int hmm_vma_get_pfns(struct vm_area_struct *vma,
-                      struct hmm_range *range,
-                      unsigned long start,
-                      unsigned long end,
-                      hmm_pfn_t *pfns);
-  int hmm_vma_fault(struct vm_area_struct *vma,
-                    struct hmm_range *range,
-                    unsigned long start,
-                    unsigned long end,
-                    hmm_pfn_t *pfns,
-                    bool write,
-                    bool block);
-
-The first one (hmm_vma_get_pfns()) will only fetch present CPU page table
+  long hmm_range_snapshot(struct hmm_range *range);
+  long hmm_range_fault(struct hmm_range *range, bool block);
+
+The first one (hmm_range_snapshot()) will only fetch present CPU page table
 entries and will not trigger a page fault on missing or non-present entries.
 The second one does trigger a page fault on missing or read-only entry if the
 write parameter is true. Page faults use the generic mm page fault code path
@@ -220,25 +210,56 @@ respect in order to keep things properly synchronized. The usage pattern is::
  {
       struct hmm_range range;
       ...
+
+      range.start = ...;
+      range.end = ...;
+      range.pfns = ...;
+      range.flags = ...;
+      range.values = ...;
+      range.pfn_shift = ...;
+      hmm_range_register(&range);
+
+      /*
+       * Just wait for range to be valid, safe to ignore return value as we
+       * will use the return value of hmm_range_snapshot() below under the
+       * mmap_sem to ascertain the validity of the range.
+       */
+      hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
+
  again:
-      ret = hmm_vma_get_pfns(vma, &range, start, end, pfns);
-      if (ret)
+      down_read(&mm->mmap_sem);
+      ret = hmm_range_snapshot(&range);
+      if (ret) {
+          up_read(&mm->mmap_sem);
+          if (ret == -EAGAIN) {
+            /*
+             * No need to check hmm_range_wait_until_valid() return value
+             * on retry we will get proper error with hmm_range_snapshot()
+             */
+            hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
+            goto again;
+          }
+          hmm_mirror_unregister(&range);
           return ret;
+      }
       take_lock(driver->update);
-      if (!hmm_vma_range_done(vma, &range)) {
+      if (!range.valid) {
           release_lock(driver->update);
+          up_read(&mm->mmap_sem);
           goto again;
       }
 
       // Use pfns array content to update device page table
 
+      hmm_mirror_unregister(&range);
       release_lock(driver->update);
+      up_read(&mm->mmap_sem);
       return 0;
  }
 
 The driver->update lock is the same lock that the driver takes inside its
-update() callback. That lock must be held before hmm_vma_range_done() to avoid
-any race with a concurrent CPU page table update.
+update() callback. That lock must be held before checking the range.valid
+field to avoid any race with a concurrent CPU page table update.
 
 HMM implements all this on top of the mmu_notifier API because we wanted a
 simpler API and also to be able to perform optimizations latter on like doing
@@ -255,6 +276,41 @@ report commands as executed is serialized (there is no point in doing this
 concurrently).
 
 
+Leverage default_flags and pfn_flags_mask
+=========================================
+
+The hmm_range struct has 2 fields default_flags and pfn_flags_mask that allows
+to set fault or snapshot policy for a whole range instead of having to set them
+for each entries in the range.
+
+For instance if the device flags for device entries are:
+    VALID (1 << 63)
+    WRITE (1 << 62)
+
+Now let say that device driver wants to fault with at least read a range then
+it does set:
+    range->default_flags = (1 << 63)
+    range->pfn_flags_mask = 0;
+
+and calls hmm_range_fault() as described above. This will fill fault all page
+in the range with at least read permission.
+
+Now let say driver wants to do the same except for one page in the range for
+which its want to have write. Now driver set:
+    range->default_flags = (1 << 63);
+    range->pfn_flags_mask = (1 << 62);
+    range->pfns[index_of_write] = (1 << 62);
+
+With this HMM will fault in all page with at least read (ie valid) and for the
+address == range->start + (index_of_write << PAGE_SHIFT) it will fault with
+write permission ie if the CPU pte does not have write permission set then HMM
+will call handle_mm_fault().
+
+Note that HMM will populate the pfns array with write permission for any entry
+that have write permission within the CPU pte no matter what are the values set
+in default_flags or pfn_flags_mask.
+
+
 Represent and manage device memory from core kernel point of view
 =================================================================
 

MAINTAINERS

@@ -11746,6 +11746,7 @@ F:	include/linux/oprofile.h
 ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
 M:	Mark Fasheh <[email protected]>
 M:	Joel Becker <[email protected]>
+M:	Joseph Qi <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 W:	http://ocfs2.wiki.kernel.org
 S:	Supported

arch/Kconfig

@@ -245,6 +245,13 @@ config ARCH_HAS_FORTIFY_SOURCE
 	  An architecture should select this when it can successfully
 	  build and run with CONFIG_FORTIFY_SOURCE.
 
+#
+# Select if the arch provides a historic keepinit alias for the retain_initrd
+# command line option
+#
+config ARCH_HAS_KEEPINITRD
+	bool
+
 # Select if arch has all set_memory_ro/rw/x/nx() functions in asm/cacheflush.h
 config ARCH_HAS_SET_MEMORY
 	bool

arch/alpha/mm/init.c

@@ -285,17 +285,3 @@ mem_init(void)
 	memblock_free_all();
 	mem_init_print_info(NULL);
 }
-
-void
-free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void
-free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif

arch/arc/mm/init.c

@@ -206,18 +206,3 @@ void __init mem_init(void)
 	memblock_free_all();
 	mem_init_print_info(NULL);
 }
-
-/*
- * free_initmem: Free all the __init memory.
- */
-void __ref free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif

arch/arm/Kconfig

@@ -4,11 +4,11 @@ config ARM
 	default y
 	select ARCH_32BIT_OFF_T
 	select ARCH_CLOCKSOURCE_DATA
-	select ARCH_DISCARD_MEMBLOCK if !HAVE_ARCH_PFN_VALID && !KEXEC
 	select ARCH_HAS_DEBUG_VIRTUAL if MMU
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
@@ -21,6 +21,7 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_KEEP_MEMBLOCK if HAVE_ARCH_PFN_VALID || KEXEC
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_NO_SG_CHAIN if !ARM_HAS_SG_CHAIN
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX

arch/arm/mm/dma-mapping.c

@@ -1577,31 +1577,21 @@ static int __arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    unsigned long attrs)
 {
-	unsigned long uaddr = vma->vm_start;
-	unsigned long usize = vma->vm_end - vma->vm_start;
 	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long off = vma->vm_pgoff;
+	int err;
 
 	if (!pages)
 		return -ENXIO;
 
-	if (off >= nr_pages || (usize >> PAGE_SHIFT) > nr_pages - off)
+	if (vma->vm_pgoff >= nr_pages)
 		return -ENXIO;
 
-	pages += off;
-
-	do {
-		int ret = vm_insert_page(vma, uaddr, *pages++);
-		if (ret) {
-			pr_err("Remapping memory failed: %d\n", ret);
-			return ret;
-		}
-		uaddr += PAGE_SIZE;
-		usize -= PAGE_SIZE;
-	} while (usize > 0);
+	err = vm_map_pages(vma, pages, nr_pages);
+	if (err)
+		pr_err("Remapping memory failed: %d\n", err);
 
-	return 0;
+	return err;
 }
 static int arm_iommu_mmap_attrs(struct device *dev,
 		struct vm_area_struct *vma, void *cpu_addr,

arch/arm/mm/init.c

@@ -695,27 +695,14 @@ void free_initmem(void)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-
-static int keep_initrd;
-
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd) {
-		if (start == initrd_start)
-			start = round_down(start, PAGE_SIZE);
-		if (end == initrd_end)
-			end = round_up(end, PAGE_SIZE);
+	if (start == initrd_start)
+		start = round_down(start, PAGE_SIZE);
+	if (end == initrd_end)
+		end = round_up(end, PAGE_SIZE);
 
-		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area((void *)start, (void *)end, -1, "initrd");
-	}
+	poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
+	free_reserved_area((void *)start, (void *)end, -1, "initrd");
 }
-
-static int __init keepinitrd_setup(char *__unused)
-{
-	keep_initrd = 1;
-	return 1;
-}
-
-__setup("keepinitrd", keepinitrd_setup);
 #endif

arch/arm64/Kconfig

@@ -19,8 +19,9 @@ config ARM64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_KEEPINITRD
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SETUP_DMA_OPS
@@ -59,6 +60,7 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPT
 	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPT
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPT
+	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS

arch/arm64/include/asm/hugetlb.h

@@ -70,8 +70,4 @@ extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #include <asm-generic/hugetlb.h>
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
 #endif /* __ASM_HUGETLB_H */

arch/arm64/mm/init.c

@@ -578,24 +578,11 @@ void free_initmem(void)
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-
-static int keep_initrd __initdata;
-
 void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd) {
-		free_reserved_area((void *)start, (void *)end, 0, "initrd");
-		memblock_free(__virt_to_phys(start), end - start);
-	}
-}
-
-static int __init keepinitrd_setup(char *__unused)
-{
-	keep_initrd = 1;
-	return 1;
+	free_reserved_area((void *)start, (void *)end, 0, "initrd");
+	memblock_free(__virt_to_phys(start), end - start);
 }
-
-__setup("keepinitrd", keepinitrd_setup);
 #endif
 
 /*