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 <akpm@linux-foundation.org>: (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 @@ my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';
 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 @@ $regex_lru_shrink_inactive = 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 @@ EVENT_PROCESS:
 			}
 
 			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,
+  long hmm_range_snapshot(struct hmm_range *range);
-                      struct hmm_range *range,
+  long hmm_range_fault(struct hmm_range *range, bool block);
-                      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
+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);
+      down_read(&mm->mmap_sem);
-      if (ret)
+      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
+update() callback. That lock must be held before checking the range.valid
-any race with a concurrent CPU page table update.
+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 <mark@fasheh.com>
 M:	Joel Becker <jlbec@evilplan.org>
+M:	Joseph Qi <joseph.qi@linux.alibaba.com>
 L:	ocfs2-devel@oss.oracle.com (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;
+	err = vm_map_pages(vma, pages, nr_pages);
+	if (err)
+		pr_err("Remapping memory failed: %d\n", err);
 
-	do {
+	return err;
-		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);
-
-	return 0;
 }
 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)
-		if (start == initrd_start)
+		start = round_down(start, PAGE_SIZE);
-			start = round_down(start, PAGE_SIZE);
+	if (end == initrd_end)
-		if (end == initrd_end)
+		end = round_up(end, PAGE_SIZE);
-			end = round_up(end, PAGE_SIZE);
 
-		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
+	poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area((void *)start, (void *)end, -1, "initrd");
+	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");
-		free_reserved_area((void *)start, (void *)end, 0, "initrd");
+	memblock_free(__virt_to_phys(start), end - start);
-		memblock_free(__virt_to_phys(start), end - start);
-	}
 }
-
-static int __init keepinitrd_setup(char *__unused)
-{
-	keep_initrd = 1;
-	return 1;
-}
-
-__setup("keepinitrd", keepinitrd_setup);
 #endif
 
 /*

arch/arm64/mm/mmu.c

@@ -1065,8 +1065,8 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int arch_add_memory(int nid, u64 start, u64 size,
-		    bool want_memblock)
+			struct mhp_restrictions *restrictions)
 {
 	int flags = 0;
 
@@ -1077,6 +1077,6 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
-			   altmap, want_memblock);
+			   restrictions);
 }
 #endif

arch/c6x/mm/init.c

@@ -68,15 +68,3 @@ void __init mem_init(void)
 
 	mem_init_print_info(NULL);
 }
-
-#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
-
-void __init free_initmem(void)
-{
-	free_initmem_default(-1);
-}

arch/h8300/mm/init.c

@@ -102,17 +102,3 @@ void __init mem_init(void)
 
 	mem_init_print_info(NULL);
 }
-
-
-#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
-
-void
-free_initmem(void)
-{
-	free_initmem_default(-1);
-}

arch/hexagon/Kconfig

@@ -22,7 +22,6 @@ config HEXAGON
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select ARCH_DISCARD_MEMBLOCK
 	select NEED_SG_DMA_LENGTH
 	select NO_IOPORT_MAP
 	select GENERIC_IOMAP

arch/hexagon/mm/init.c

@@ -84,16 +84,6 @@ void __init mem_init(void)
 	init_mm.context.ptbase = __pa(init_mm.pgd);
 }
 
-/*
- * free_initmem - frees memory used by stuff declared with __init
- *
- * Todo:  free pages between __init_begin and __init_end; possibly
- * some devtree related stuff as well.
- */
-void __ref free_initmem(void)
-{
-}
-
 /*
  * free_initrd_mem - frees...  initrd memory.
  * @start - start of init memory

arch/ia64/Kconfig

@@ -33,7 +33,6 @@ config IA64
 	select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
 	select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB
 	select VIRT_TO_BUS
-	select ARCH_DISCARD_MEMBLOCK
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_IRQ_SHOW

arch/ia64/mm/init.c

@@ -666,14 +666,14 @@ mem_init (void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int arch_add_memory(int nid, u64 start, u64 size,
-		bool want_memblock)
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	if (ret)
 		printk("%s: Problem encountered in __add_pages() as ret=%d\n",
 		       __func__,  ret);
@@ -682,20 +682,15 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(int nid, u64 start, u64 size,
+			struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
-	int ret;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
-	if (ret)
-		pr_warn("%s: Problem encountered in __remove_pages() as"
-			" ret=%d\n", __func__,  ret);
-
-	return ret;
 }
 #endif
 #endif

arch/m68k/Kconfig

@@ -26,7 +26,6 @@ config M68K
 	select MODULES_USE_ELF_RELA
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
-	select ARCH_DISCARD_MEMBLOCK
 	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN

arch/m68k/mm/init.c

@@ -147,10 +147,3 @@ void __init mem_init(void)
 	init_pointer_tables();
 	mem_init_print_info(NULL);
 }
-
-#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/microblaze/mm/init.c

@@ -186,18 +186,6 @@ void __init setup_memory(void)
 	paging_init();
 }
 
-#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
-
-void free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
 void __init mem_init(void)
 {
 	high_memory = (void *)__va(memory_start + lowmem_size - 1);

arch/mips/Kconfig

@@ -5,7 +5,6 @@ config MIPS
 	select ARCH_32BIT_OFF_T if !64BIT
 	select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT
 	select ARCH_CLOCKSOURCE_DATA
-	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL

arch/mips/mm/gup.c

@@ -235,7 +235,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
- * @write:	whether pages will be written to
+ * @gup_flags:	flags modifying pin behaviour
  * @pages:	array that receives pointers to the pages pinned.
  *		Should be at least nr_pages long.
  *
@@ -247,8 +247,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
  * requested. If nr_pages is 0 or negative, returns 0. If no pages
  * were pinned, returns -errno.
  */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+int get_user_pages_fast(unsigned long start, int nr_pages,
-			struct page **pages)
+			unsigned int gup_flags, struct page **pages)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr, len, end;
@@ -273,7 +273,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			goto slow;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
+				   pages, &nr))
 			goto slow;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_enable();
@@ -289,7 +290,7 @@ slow_irqon:
 	pages += nr;
 
 	ret = get_user_pages_unlocked(start, (end - start) >> PAGE_SHIFT,
-				      pages, write ? FOLL_WRITE : 0);
+				      pages, gup_flags);
 
 	/* Have to be a bit careful with return values */
 	if (nr > 0) {

arch/mips/mm/init.c

@@ -504,14 +504,6 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
-			   "initrd");
-}
-#endif
-
 void (*free_init_pages_eva)(void *begin, void *end) = NULL;
 
 void __ref free_initmem(void)

arch/nds32/mm/init.c

@@ -252,18 +252,6 @@ void __init mem_init(void)
 	return;
 }
 
-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
-
 void __set_fixmap(enum fixed_addresses idx,
 			       phys_addr_t phys, pgprot_t flags)
 {

arch/nios2/Kconfig

@@ -23,7 +23,6 @@ config NIOS2
 	select SPARSE_IRQ
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
-	select ARCH_DISCARD_MEMBLOCK
 	select MMU_GATHER_NO_RANGE if MMU
 
 config GENERIC_CSUM

arch/nios2/mm/init.c

@@ -82,18 +82,6 @@ void __init mmu_init(void)
 	flush_tlb_all();
 }
 
-#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
-
-void __ref free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
 #define __page_aligned(order) __aligned(PAGE_SIZE << (order))
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned(PGD_ORDER);
 pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned(PTE_ORDER);

arch/openrisc/mm/init.c

@@ -223,15 +223,3 @@ void __init mem_init(void)
 	mem_init_done = 1;
 	return;
 }
-
-#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
-
-void free_initmem(void)
-{
-	free_initmem_default(-1);
-}

arch/parisc/mm/init.c

@@ -917,10 +917,3 @@ void flush_tlb_all(void)
 	spin_unlock(&sid_lock);
 }
 #endif
-
-#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/powerpc/Kconfig

@@ -137,6 +137,7 @@ config PPC
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAS_ZONE_DEVICE		if PPC_BOOK3S_64
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_KEEP_MEMBLOCK
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX

arch/powerpc/include/asm/book3s/64/hugetlb.h

@@ -36,8 +36,8 @@ static inline int hstate_get_psize(struct hstate *hstate)
 	}
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
+#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
-static inline bool gigantic_page_supported(void)
+static inline bool gigantic_page_runtime_supported(void)
 {
 	/*
 	 * We used gigantic page reservation with hypervisor assist in some case.
@@ -49,7 +49,6 @@ static inline bool gigantic_page_supported(void)
 
 	return true;
 }
-#endif
 
 /* hugepd entry valid bit */
 #define HUGEPD_VAL_BITS		(0x8000000000000000UL)

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -600,7 +600,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* If writing != 0, then the HPTE must allow writing, if we get here */
 	write_ok = writing;
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	npages = get_user_pages_fast(hva, 1, writing, pages);
+	npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
 	if (npages < 1) {
 		/* Check if it's an I/O mapping */
 		down_read(&current->mm->mmap_sem);
@@ -1193,7 +1193,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		goto err;
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	npages = get_user_pages_fast(hva, 1, 1, pages);
+	npages = get_user_pages_fast(hva, 1, FOLL_WRITE, pages);
 	if (npages < 1)
 		goto err;
 	page = pages[0];

arch/powerpc/kvm/e500_mmu.c

@@ -783,7 +783,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 	if (!pages)
 		return -ENOMEM;
 
-	ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
+	ret = get_user_pages_fast(cfg->array, num_pages, FOLL_WRITE, pages);
 	if (ret < 0)
 		goto free_pages;
 

arch/powerpc/mm/book3s64/iommu_api.c

@@ -141,8 +141,9 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	for (entry = 0; entry < entries; entry += chunk) {
 		unsigned long n = min(entries - entry, chunk);
 
-		ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+		ret = get_user_pages(ua + (entry << PAGE_SHIFT), n,
-				FOLL_WRITE, mem->hpages + entry, NULL);
+				FOLL_WRITE | FOLL_LONGTERM,
+				mem->hpages + entry, NULL);
 		if (ret == n) {
 			pinned += n;
 			continue;

arch/powerpc/mm/mem.c

@@ -109,8 +109,8 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 	return -ENODEV;
 }
 
-int __ref arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int __ref arch_add_memory(int nid, u64 start, u64 size,
-			  bool want_memblock)
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
@@ -127,11 +127,11 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altm
 	}
 	flush_inval_dcache_range(start, start + size);
 
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int __ref arch_remove_memory(int nid, u64 start, u64 size,
+void __ref arch_remove_memory(int nid, u64 start, u64 size,
 			     struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
@@ -147,14 +147,13 @@ int __ref arch_remove_memory(int nid, u64 start, u64 size,
 	if (altmap)
 		page += vmem_altmap_offset(altmap);
 
-	ret = __remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
+	__remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
-	if (ret)
-		return ret;
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
 	flush_inval_dcache_range(start, start + size);
 	ret = remove_section_mapping(start, start + size);
+	WARN_ON_ONCE(ret);
 
 	/* Ensure all vmalloc mappings are flushed in case they also
 	 * hit that section of memory
@@ -163,8 +162,6 @@ int __ref arch_remove_memory(int nid, u64 start, u64 size,
 
 	if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC)
 		pr_warn("Hash collision while resizing HPT\n");
-
-	return ret;
 }
 #endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
@@ -338,13 +335,6 @@ void free_initmem(void)
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
-#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
-
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache

arch/powerpc/platforms/Kconfig.cputype

@@ -331,7 +331,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
 	depends on PPC_BOOK3S_64 && HUGETLB_PAGE
-	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+	select ARCH_HAS_GIGANTIC_PAGE
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
 	default y

arch/riscv/mm/init.c

@@ -66,11 +66,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-void free_initmem(void)
-{
-	free_initmem_default(0);
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {

arch/s390/Kconfig

@@ -63,7 +63,7 @@ config S390
 	select ARCH_HAS_ELF_RANDOMIZE
 	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_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
@@ -100,6 +100,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_BH
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+	select ARCH_KEEP_MEMBLOCK
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING

arch/s390/include/asm/hugetlb.h

@@ -116,7 +116,9 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 	return pte_modify(pte, newprot);
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
+static inline bool gigantic_page_runtime_supported(void)
-static inline bool gigantic_page_supported(void) { return true; }
+{
-#endif
+	return true;
+}
+
 #endif /* _ASM_S390_HUGETLB_H */

arch/s390/kvm/interrupt.c

@@ -2376,7 +2376,7 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
 		ret = -EFAULT;
 		goto out;
 	}
-	ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
+	ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page);
 	if (ret < 0)
 		goto out;
 	BUG_ON(ret != 1);

arch/s390/mm/init.c

@@ -157,14 +157,6 @@ void free_initmem(void)
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
-			   "initrd");
-}
-#endif
-
 unsigned long memory_block_size_bytes(void)
 {
 	/*
@@ -227,8 +219,8 @@ device_initcall(s390_cma_mem_init);
 
 #endif /* CONFIG_CMA */
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int arch_add_memory(int nid, u64 start, u64 size,
-		bool want_memblock)
+		struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long size_pages = PFN_DOWN(size);
@@ -238,21 +230,22 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 	if (rc)
 		return rc;
 
-	rc = __add_pages(nid, start_pfn, size_pages, altmap, want_memblock);
+	rc = __add_pages(nid, start_pfn, size_pages, restrictions);
 	if (rc)
 		vmem_remove_mapping(start, size);
 	return rc;
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(int nid, u64 start, u64 size,
+			struct vmem_altmap *altmap)
 {
 	/*
 	 * There is no hardware or firmware interface which could trigger a
 	 * hot memory remove on s390. So there is nothing that needs to be
 	 * implemented.
 	 */
-	return -EBUSY;
+	BUG();
 }
 #endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/sh/Kconfig

@@ -10,7 +10,6 @@ config SUPERH
 	select DMA_DECLARE_COHERENT
 	select HAVE_IDE if HAS_IOPORT_MAP
 	select HAVE_MEMBLOCK_NODE_MAP
-	select ARCH_DISCARD_MEMBLOCK
 	select HAVE_OPROFILE
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_PERF_EVENTS
@@ -53,6 +52,7 @@ config SUPERH
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_NMI
 	select NEED_SG_DMA_LENGTH
+	select ARCH_HAS_GIGANTIC_PAGE
 
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems

arch/sh/boards/mach-dreamcast/irq.c

@@ -10,7 +10,6 @@
  */
 #include <linux/irq.h>
 #include <linux/io.h>
-#include <linux/irq.h>
 #include <linux/export.h>
 #include <linux/err.h>
 #include <mach/sysasic.h>

arch/sh/mm/gup.c

@@ -204,7 +204,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
  * @nr_pages:	number of pages from start to pin
- * @write:	whether pages will be written to
+ * @gup_flags:	flags modifying pin behaviour
  * @pages:	array that receives pointers to the pages pinned.
  *		Should be at least nr_pages long.
  *
@@ -216,8 +216,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
  * requested. If nr_pages is 0 or negative, returns 0. If no pages
  * were pinned, returns -errno.
  */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+int get_user_pages_fast(unsigned long start, int nr_pages,
-			struct page **pages)
+			unsigned int gup_flags, struct page **pages)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr, len, end;
@@ -241,7 +241,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			goto slow;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
+				   pages, &nr))
 			goto slow;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_enable();
@@ -261,7 +262,7 @@ slow_irqon:
 
 		ret = get_user_pages_unlocked(start,
 			(end - start) >> PAGE_SHIFT, pages,
-			write ? FOLL_WRITE : 0);
+			gup_flags);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {

arch/sh/mm/init.c

@@ -403,28 +403,16 @@ void __init mem_init(void)
 	mem_init_done = 1;
 }
 
-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
-
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int arch_add_memory(int nid, u64 start, u64 size,
-		bool want_memblock)
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
 	/* We only have ZONE_NORMAL, so this is easy.. */
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	if (unlikely(ret))
 		printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
 
@@ -441,20 +429,15 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(int nid, u64 start, u64 size,
+			struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = PFN_DOWN(start);
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
-	int ret;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
-	if (unlikely(ret))
-		pr_warn("%s: Failed, __remove_pages() == %d\n", __func__,
-			ret);
-
-	return ret;
 }
 #endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/sparc/Kconfig

@@ -92,6 +92,7 @@ config SPARC64
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_PTE_SPECIAL
 	select PCI_DOMAINS if PCI
+	select ARCH_HAS_GIGANTIC_PAGE
 
 config ARCH_DEFCONFIG
 	string

arch/sparc/include/asm/pgtable_64.h

@@ -231,36 +231,6 @@ extern unsigned long _PAGE_ALL_SZ_BITS;
 extern struct page *mem_map_zero;
 #define ZERO_PAGE(vaddr)	(mem_map_zero)
 
-/* This macro must be updated when the size of struct page grows above 80
- * or reduces below 64.
- * The idea that compiler optimizes out switch() statement, and only
- * leaves clrx instructions
- */
-#define	mm_zero_struct_page(pp) do {					\
-	unsigned long *_pp = (void *)(pp);				\
-									\
-	 /* Check that struct page is either 64, 72, or 80 bytes */	\
-	BUILD_BUG_ON(sizeof(struct page) & 7);				\
-	BUILD_BUG_ON(sizeof(struct page) < 64);				\
-	BUILD_BUG_ON(sizeof(struct page) > 80);				\
-									\
-	switch (sizeof(struct page)) {					\
-	case 80:							\
-		_pp[9] = 0;	/* fallthrough */			\
-	case 72:							\
-		_pp[8] = 0;	/* fallthrough */			\
-	default:							\
-		_pp[7] = 0;						\
-		_pp[6] = 0;						\
-		_pp[5] = 0;						\
-		_pp[4] = 0;						\
-		_pp[3] = 0;						\
-		_pp[2] = 0;						\
-		_pp[1] = 0;						\
-		_pp[0] = 0;						\
-	}								\
-} while (0)
-
 /* PFNs are real physical page numbers.  However, mem_map only begins to record
  * per-page information starting at pfn_base.  This is to handle systems where
  * the first physical page in the machine is at some huge physical address,

arch/sparc/mm/gup.c

@@ -245,8 +245,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	return nr;
 }
 
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+int get_user_pages_fast(unsigned long start, int nr_pages,
-			struct page **pages)
+			unsigned int gup_flags, struct page **pages)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr, len, end;
@@ -303,7 +303,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			goto slow;
-		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+		if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
+				   pages, &nr))
 			goto slow;
 	} while (pgdp++, addr = next, addr != end);
 
@@ -324,7 +325,7 @@ slow:
 
 		ret = get_user_pages_unlocked(start,
 			(end - start) >> PAGE_SHIFT, pages,
-			write ? FOLL_WRITE : 0);
+			gup_flags);
 
 		/* Have to be a bit careful with return values */
 		if (nr > 0) {

arch/sparc/mm/init_32.c

@@ -294,19 +294,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-void free_initmem (void)
-{
-	free_initmem_default(POISON_FREE_INITMEM);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
-			   "initrd");
-}
-#endif
-
 void sparc_flush_page_to_ram(struct page *page)
 {
 	unsigned long vaddr = (unsigned long)page_address(page);

arch/sparc/mm/init_64.c

@@ -2572,14 +2572,6 @@ void free_initmem(void)
 	}
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
-			   "initrd");
-}
-#endif
-
 pgprot_t PAGE_KERNEL __read_mostly;
 EXPORT_SYMBOL(PAGE_KERNEL);
 

arch/um/kernel/mem.c

@@ -188,13 +188,6 @@ void free_initmem(void)
 {
 }
 
-#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
-
 /* Allocate and free page tables. */
 
 pgd_t *pgd_alloc(struct mm_struct *mm)

arch/unicore32/Kconfig

@@ -3,6 +3,7 @@ config UNICORE32
 	def_bool y
 	select ARCH_32BIT_OFF_T
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_KEEPINITRD
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_KERNEL_GZIP

arch/unicore32/mm/init.c

@@ -287,27 +287,3 @@ void __init mem_init(void)
 		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
 	}
 }
-
-void free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-
-static int keep_initrd;
-
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (!keep_initrd)
-		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/x86/Kconfig

@@ -22,7 +22,7 @@ config X86_64
 	def_bool y
 	depends on 64BIT
 	# Options that are inherently 64-bit kernel only:
-	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
+	select ARCH_HAS_GIGANTIC_PAGE
 	select ARCH_SUPPORTS_INT128
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_ARCH_SOFT_DIRTY
@@ -47,7 +47,6 @@ config X86
 	select ARCH_32BIT_OFF_T			if X86_32
 	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_CLOCKSOURCE_INIT
-	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED

arch/x86/include/asm/hugetlb.h

@@ -17,8 +17,4 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
-#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
-static inline bool gigantic_page_supported(void) { return true; }
-#endif
-
 #endif /* _ASM_X86_HUGETLB_H */

arch/x86/kvm/paging_tmpl.h

@@ -140,7 +140,7 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	pt_element_t *table;
 	struct page *page;
 
-	npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
+	npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
 	/* Check if the user is doing something meaningless. */
 	if (unlikely(npages != 1))
 		return -EFAULT;

arch/x86/kvm/svm.c

@@ -1805,7 +1805,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
+	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;

arch/x86/mm/hugetlbpage.c

@@ -203,7 +203,7 @@ static __init int setup_hugepagesz(char *opt)
 }
 __setup("hugepagesz=", setup_hugepagesz);
 
-#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
+#ifdef CONFIG_CONTIG_ALLOC
 static __init int gigantic_pages_init(void)
 {
 	/* With compaction or CMA we can allocate gigantic pages at runtime */

arch/x86/mm/init_32.c

@@ -850,24 +850,25 @@ void __init mem_init(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int arch_add_memory(int nid, u64 start, u64 size,
-		bool want_memblock)
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-int arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(int nid, u64 start, u64 size,
+			struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct zone *zone;
 
 	zone = page_zone(pfn_to_page(start_pfn));
-	return __remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
 }
 #endif
 #endif

arch/x86/mm/init_64.c

@@ -777,11 +777,11 @@ static void update_end_of_memory_vars(u64 start, u64 size)
 }
 
 int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
-		struct vmem_altmap *altmap, bool want_memblock)
+				struct mhp_restrictions *restrictions)
 {
 	int ret;
 
-	ret = __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	ret = __add_pages(nid, start_pfn, nr_pages, restrictions);
 	WARN_ON_ONCE(ret);
 
 	/* update max_pfn, max_low_pfn and high_memory */
@@ -791,15 +791,15 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
 	return ret;
 }
 
-int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
+int arch_add_memory(int nid, u64 start, u64 size,
-		bool want_memblock)
+			struct mhp_restrictions *restrictions)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
 	init_memory_mapping(start, start + size);
 
-	return add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
+	return add_pages(nid, start_pfn, nr_pages, restrictions);
 }
 
 #define PAGE_INUSE 0xFD
@@ -1141,24 +1141,20 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 	remove_pagetable(start, end, true, NULL);
 }
 
-int __ref arch_remove_memory(int nid, u64 start, u64 size,
+void __ref arch_remove_memory(int nid, u64 start, u64 size,
-				struct vmem_altmap *altmap)
+			      struct vmem_altmap *altmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	struct page *page = pfn_to_page(start_pfn);
 	struct zone *zone;
-	int ret;
 
 	/* With altmap the first mapped page is offset from @start */
 	if (altmap)
 		page += vmem_altmap_offset(altmap);
 	zone = page_zone(page);
-	ret = __remove_pages(zone, start_pfn, nr_pages, altmap);
+	__remove_pages(zone, start_pfn, nr_pages, altmap);
-	WARN_ON_ONCE(ret);
 	kernel_physical_mapping_remove(start, start + size);
-
-	return ret;
 }
 #endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/xtensa/mm/init.c

@@ -216,11 +216,6 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
-void free_initmem(void)
-{
-	free_initmem_default(-1);
-}
-
 static void __init parse_memmap_one(char *p)
 {
 	char *oldp;

drivers/base/memory.c

@@ -231,13 +231,14 @@ static bool pages_correctly_probed(unsigned long start_pfn)
  * OK to have direct references to sparsemem variables in here.
  */
 static int
-memory_block_action(unsigned long phys_index, unsigned long action, int online_type)
+memory_block_action(unsigned long start_section_nr, unsigned long action,
+		    int online_type)
 {
 	unsigned long start_pfn;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
 	int ret;
 
-	start_pfn = section_nr_to_pfn(phys_index);
+	start_pfn = section_nr_to_pfn(start_section_nr);
 
 	switch (action) {
 	case MEM_ONLINE:
@@ -251,7 +252,7 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 		break;
 	default:
 		WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
-		     "%ld\n", __func__, phys_index, action, action);
+		     "%ld\n", __func__, start_section_nr, action, action);
 		ret = -EINVAL;
 	}
 
@@ -733,16 +734,18 @@ unregister_memory(struct memory_block *memory)
 {
 	BUG_ON(memory->dev.bus != &memory_subsys);
 
-	/* drop the ref. we got in remove_memory_section() */
+	/* drop the ref. we got via find_memory_block() */
 	put_device(&memory->dev);
 	device_unregister(&memory->dev);
 }
 
-static int remove_memory_section(unsigned long node_id,
+void unregister_memory_section(struct mem_section *section)
-			       struct mem_section *section, int phys_device)
 {
 	struct memory_block *mem;
 
+	if (WARN_ON_ONCE(!present_section(section)))
+		return;
+
 	mutex_lock(&mem_sysfs_mutex);
 
 	/*
@@ -763,15 +766,6 @@ static int remove_memory_section(unsigned long node_id,
 
 out_unlock:
 	mutex_unlock(&mem_sysfs_mutex);
-	return 0;
-}
-
-int unregister_memory_section(struct mem_section *section)
-{
-	if (!present_section(section))
-		return -EINVAL;
-
-	return remove_memory_section(0, section, 0);
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 

drivers/dax/device.c

@@ -184,8 +184,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 
 	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, *pfn,
+	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
-			vmf->flags & FAULT_FLAG_WRITE);
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
@@ -235,8 +234,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 
 	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, *pfn,
+	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
-			vmf->flags & FAULT_FLAG_WRITE);
 }
 #else
 static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,

drivers/firewire/core-iso.c

@@ -107,19 +107,8 @@ EXPORT_SYMBOL(fw_iso_buffer_init);
 int fw_iso_buffer_map_vma(struct fw_iso_buffer *buffer,
 			  struct vm_area_struct *vma)
 {
-	unsigned long uaddr;
+	return vm_map_pages_zero(vma, buffer->pages,
-	int i, err;
+					buffer->page_count);
-
-	uaddr = vma->vm_start;
-	for (i = 0; i < buffer->page_count; i++) {
-		err = vm_insert_page(vma, uaddr, buffer->pages[i]);
-		if (err)
-			return err;
-
-		uaddr += PAGE_SIZE;
-	}
-
-	return 0;
 }
 
 void fw_iso_buffer_destroy(struct fw_iso_buffer *buffer,

drivers/fpga/dfl-afu-dma-region.c

@@ -102,7 +102,7 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
 		goto unlock_vm;
 	}
 
-	pinned = get_user_pages_fast(region->user_addr, npages, 1,
+	pinned = get_user_pages_fast(region->user_addr, npages, FOLL_WRITE,
 				     region->pages);
 	if (pinned < 0) {
 		ret = pinned;

drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c

@@ -256,14 +256,14 @@ static int amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
 	/* TODO we should be able to split locking for interval tree and
 	 * amdgpu_mn_invalidate_node
 	 */
-	if (amdgpu_mn_read_lock(amn, range->blockable))
+	if (amdgpu_mn_read_lock(amn, mmu_notifier_range_blockable(range)))
 		return -EAGAIN;
 
 	it = interval_tree_iter_first(&amn->objects, range->start, end);
 	while (it) {
 		struct amdgpu_mn_node *node;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			amdgpu_mn_read_unlock(amn);
 			return -EAGAIN;
 		}
@@ -299,7 +299,7 @@ static int amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
 	/* notification is exclusive, but interval is inclusive */
 	end = range->end - 1;
 
-	if (amdgpu_mn_read_lock(amn, range->blockable))
+	if (amdgpu_mn_read_lock(amn, mmu_notifier_range_blockable(range)))
 		return -EAGAIN;
 
 	it = interval_tree_iter_first(&amn->objects, range->start, end);
@@ -307,7 +307,7 @@ static int amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
 		struct amdgpu_mn_node *node;
 		struct amdgpu_bo *bo;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			amdgpu_mn_read_unlock(amn);
 			return -EAGAIN;
 		}

drivers/gpu/drm/i915/i915_gem_userptr.c

@@ -122,7 +122,7 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	while (it) {
 		struct drm_i915_gem_object *obj;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			ret = -EAGAIN;
 			break;
 		}

drivers/gpu/drm/radeon/radeon_mn.c

@@ -133,7 +133,7 @@ static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 	/* TODO we should be able to split locking for interval tree and
 	 * the tear down.
 	 */
-	if (range->blockable)
+	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&rmn->lock);
 	else if (!mutex_trylock(&rmn->lock))
 		return -EAGAIN;
@@ -144,7 +144,7 @@ static int radeon_mn_invalidate_range_start(struct mmu_notifier *mn,
 		struct radeon_bo *bo;
 		long r;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			ret = -EAGAIN;
 			goto out_unlock;
 		}

drivers/gpu/drm/rockchip/rockchip_drm_gem.c

@@ -221,26 +221,13 @@ static int rockchip_drm_gem_object_mmap_iommu(struct drm_gem_object *obj,
 					      struct vm_area_struct *vma)
 {
 	struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj);
-	unsigned int i, count = obj->size >> PAGE_SHIFT;
+	unsigned int count = obj->size >> PAGE_SHIFT;
 	unsigned long user_count = vma_pages(vma);
-	unsigned long uaddr = vma->vm_start;
-	unsigned long offset = vma->vm_pgoff;
-	unsigned long end = user_count + offset;
-	int ret;
 
 	if (user_count == 0)
 		return -ENXIO;
-	if (end > count)
-		return -ENXIO;
 
-	for (i = offset; i < end; i++) {
+	return vm_map_pages(vma, rk_obj->pages, count);
-		ret = vm_insert_page(vma, uaddr, rk_obj->pages[i]);
-		if (ret)
-			return ret;
-		uaddr += PAGE_SIZE;
-	}
-
-	return 0;
 }
 
 static int rockchip_drm_gem_object_mmap_dma(struct drm_gem_object *obj,

drivers/gpu/drm/via/via_dmablit.c

@@ -243,7 +243,8 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg,  drm_via_dmablit_t *xfer)
 	if (NULL == vsg->pages)
 		return -ENOMEM;
 	ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
-			vsg->num_pages, vsg->direction == DMA_FROM_DEVICE,
+			vsg->num_pages,
+			vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
 			vsg->pages);
 	if (ret != vsg->num_pages) {
 		if (ret < 0)

drivers/gpu/drm/xen/xen_drm_front_gem.c

@@ -224,8 +224,7 @@ xen_drm_front_gem_import_sg_table(struct drm_device *dev,
 static int gem_mmap_obj(struct xen_gem_object *xen_obj,
 			struct vm_area_struct *vma)
 {
-	unsigned long addr = vma->vm_start;
+	int ret;
-	int i;
 
 	/*
 	 * clear the VM_PFNMAP flag that was set by drm_gem_mmap(), and set the
@@ -252,18 +251,11 @@ static int gem_mmap_obj(struct xen_gem_object *xen_obj,
 	 * FIXME: as we insert all the pages now then no .fault handler must
 	 * be called, so don't provide one
 	 */
-	for (i = 0; i < xen_obj->num_pages; i++) {
+	ret = vm_map_pages(vma, xen_obj->pages, xen_obj->num_pages);
-		int ret;
+	if (ret < 0)
+		DRM_ERROR("Failed to map pages into vma: %d\n", ret);
 
-		ret = vm_insert_page(vma, addr, xen_obj->pages[i]);
+	return ret;
-		if (ret < 0) {
-			DRM_ERROR("Failed to insert pages into vma: %d\n", ret);
-			return ret;
-		}
-
-		addr += PAGE_SIZE;
-	}
-	return 0;
 }
 
 int xen_drm_front_gem_mmap(struct file *filp, struct vm_area_struct *vma)

drivers/infiniband/core/umem.c

@@ -295,10 +295,11 @@ struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
 
 	while (npages) {
 		down_read(&mm->mmap_sem);
-		ret = get_user_pages_longterm(cur_base,
+		ret = get_user_pages(cur_base,
 				     min_t(unsigned long, npages,
 					   PAGE_SIZE / sizeof (struct page *)),
-				     gup_flags, page_list, NULL);
+				     gup_flags | FOLL_LONGTERM,
+				     page_list, NULL);
 		if (ret < 0) {
 			up_read(&mm->mmap_sem);
 			goto umem_release;

drivers/infiniband/core/umem_odp.c

@@ -152,7 +152,7 @@ static int ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	struct ib_ucontext_per_mm *per_mm =
 		container_of(mn, struct ib_ucontext_per_mm, mn);
 
-	if (range->blockable)
+	if (mmu_notifier_range_blockable(range))
 		down_read(&per_mm->umem_rwsem);
 	else if (!down_read_trylock(&per_mm->umem_rwsem))
 		return -EAGAIN;
@@ -170,7 +170,8 @@ static int ib_umem_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	return rbt_ib_umem_for_each_in_range(&per_mm->umem_tree, range->start,
 					     range->end,
 					     invalidate_range_start_trampoline,
-					     range->blockable, NULL);
+					     mmu_notifier_range_blockable(range),
+					     NULL);
 }
 
 static int invalidate_range_end_trampoline(struct ib_umem_odp *item, u64 start,

drivers/infiniband/hw/hfi1/user_pages.c

@@ -104,8 +104,9 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 			    bool writable, struct page **pages)
 {
 	int ret;
+	unsigned int gup_flags = FOLL_LONGTERM | (writable ? FOLL_WRITE : 0);
 
-	ret = get_user_pages_fast(vaddr, npages, writable, pages);
+	ret = get_user_pages_fast(vaddr, npages, gup_flags, pages);
 	if (ret < 0)
 		return ret;
 

drivers/infiniband/hw/mthca/mthca_memfree.c

@@ -472,7 +472,8 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 		goto out;
 	}
 
-	ret = get_user_pages_fast(uaddr & PAGE_MASK, 1, FOLL_WRITE, pages);
+	ret = get_user_pages_fast(uaddr & PAGE_MASK, 1,
+				  FOLL_WRITE | FOLL_LONGTERM, pages);
 	if (ret < 0)
 		goto out;
 

drivers/infiniband/hw/qib/qib_user_pages.c

@@ -114,10 +114,10 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 
 	down_read(&current->mm->mmap_sem);
 	for (got = 0; got < num_pages; got += ret) {
-		ret = get_user_pages_longterm(start_page + got * PAGE_SIZE,
+		ret = get_user_pages(start_page + got * PAGE_SIZE,
-					      num_pages - got,
+				     num_pages - got,
-					      FOLL_WRITE | FOLL_FORCE,
+				     FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE,
-					      p + got, NULL);
+				     p + got, NULL);
 		if (ret < 0) {
 			up_read(&current->mm->mmap_sem);
 			goto bail_release;

drivers/infiniband/hw/qib/qib_user_sdma.c

@@ -670,7 +670,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 		else
 			j = npages;
 
-		ret = get_user_pages_fast(addr, j, 0, pages);
+		ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
 		if (ret != j) {
 			i = 0;
 			j = ret;

drivers/infiniband/hw/usnic/usnic_uiom.c

@@ -143,10 +143,11 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 	ret = 0;
 
 	while (npages) {
-		ret = get_user_pages_longterm(cur_base,
+		ret = get_user_pages(cur_base,
-					min_t(unsigned long, npages,
+				     min_t(unsigned long, npages,
-					PAGE_SIZE / sizeof(struct page *)),
+				     PAGE_SIZE / sizeof(struct page *)),
-					gup_flags, page_list, NULL);
+				     gup_flags | FOLL_LONGTERM,
+				     page_list, NULL);
 
 		if (ret < 0)
 			goto out;

drivers/iommu/dma-iommu.c

@@ -619,17 +619,7 @@ out_free_pages:
 
 int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma)
 {
-	unsigned long uaddr = vma->vm_start;
+	return vm_map_pages(vma, pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
-	unsigned int i, count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	int ret = -ENXIO;
-
-	for (i = vma->vm_pgoff; i < count && uaddr < vma->vm_end; i++) {
-		ret = vm_insert_page(vma, uaddr, pages[i]);
-		if (ret)
-			break;
-		uaddr += PAGE_SIZE;
-	}
-	return ret;
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,

drivers/media/common/videobuf2/videobuf2-core.c

@@ -2201,6 +2201,13 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma)
 		goto unlock;
 	}
 
+	/*
+	 * vm_pgoff is treated in V4L2 API as a 'cookie' to select a buffer,
+	 * not as a in-buffer offset. We always want to mmap a whole buffer
+	 * from its beginning.
+	 */
+	vma->vm_pgoff = 0;
+
 	ret = call_memop(vb, mmap, vb->planes[plane].mem_priv, vma);
 
 unlock:

drivers/media/common/videobuf2/videobuf2-dma-contig.c

@@ -186,12 +186,6 @@ static int vb2_dc_mmap(void *buf_priv, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 
-	/*
-	 * dma_mmap_* uses vm_pgoff as in-buffer offset, but we want to
-	 * map whole buffer
-	 */
-	vma->vm_pgoff = 0;
-
 	ret = dma_mmap_attrs(buf->dev, vma, buf->cookie,
 		buf->dma_addr, buf->size, buf->attrs);
 

drivers/media/common/videobuf2/videobuf2-dma-sg.c

@@ -328,28 +328,18 @@ static unsigned int vb2_dma_sg_num_users(void *buf_priv)
 static int vb2_dma_sg_mmap(void *buf_priv, struct vm_area_struct *vma)
 {
 	struct vb2_dma_sg_buf *buf = buf_priv;
-	unsigned long uaddr = vma->vm_start;
+	int err;
-	unsigned long usize = vma->vm_end - vma->vm_start;
-	int i = 0;
 
 	if (!buf) {
 		printk(KERN_ERR "No memory to map\n");
 		return -EINVAL;
 	}
 
-	do {
+	err = vm_map_pages(vma, buf->pages, buf->num_pages);
-		int ret;
+	if (err) {
-
+		printk(KERN_ERR "Remapping memory, error: %d\n", err);
-		ret = vm_insert_page(vma, uaddr, buf->pages[i++]);
+		return err;
-		if (ret) {
+	}
-			printk(KERN_ERR "Remapping memory, error: %d\n", ret);
-			return ret;
-		}
-
-		uaddr += PAGE_SIZE;
-		usize -= PAGE_SIZE;
-	} while (usize > 0);
-
 
 	/*
 	 * Use common vm_area operations to track buffer refcount.

drivers/media/v4l2-core/videobuf-dma-sg.c

@@ -186,12 +186,12 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
 		data, size, dma->nr_pages);
 
-	err = get_user_pages_longterm(data & PAGE_MASK, dma->nr_pages,
+	err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
-			     flags, dma->pages, NULL);
+			     flags | FOLL_LONGTERM, dma->pages, NULL);
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
-		dprintk(1, "get_user_pages_longterm: err=%d [%d]\n", err,
+		dprintk(1, "get_user_pages: err=%d [%d]\n", err,
 			dma->nr_pages);
 		return err < 0 ? err : -EINVAL;
 	}

drivers/misc/genwqe/card_utils.c

@@ -603,7 +603,7 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
 	/* pin user pages in memory */
 	rc = get_user_pages_fast(data & PAGE_MASK, /* page aligned addr */
 				 m->nr_pages,
-				 m->write,		/* readable/writable */
+				 m->write ? FOLL_WRITE : 0,	/* readable/writable */
 				 m->page_list);	/* ptrs to pages */
 	if (rc < 0)
 		goto fail_get_user_pages;

drivers/misc/vmw_vmci/vmci_host.c

@@ -242,7 +242,7 @@ static int vmci_host_setup_notify(struct vmci_ctx *context,
 	/*
 	 * Lock physical page backing a given user VA.
 	 */
-	retval = get_user_pages_fast(uva, 1, 1, &context->notify_page);
+	retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &context->notify_page);
 	if (retval != 1) {
 		context->notify_page = NULL;
 		return VMCI_ERROR_GENERIC;

drivers/misc/vmw_vmci/vmci_queue_pair.c

@@ -659,7 +659,8 @@ static int qp_host_get_user_memory(u64 produce_uva,
 	int err = VMCI_SUCCESS;
 
 	retval = get_user_pages_fast((uintptr_t) produce_uva,
-				     produce_q->kernel_if->num_pages, 1,
+				     produce_q->kernel_if->num_pages,
+				     FOLL_WRITE,
 				     produce_q->kernel_if->u.h.header_page);
 	if (retval < (int)produce_q->kernel_if->num_pages) {
 		pr_debug("get_user_pages_fast(produce) failed (retval=%d)",
@@ -671,7 +672,8 @@ static int qp_host_get_user_memory(u64 produce_uva,
 	}
 
 	retval = get_user_pages_fast((uintptr_t) consume_uva,
-				     consume_q->kernel_if->num_pages, 1,
+				     consume_q->kernel_if->num_pages,
+				     FOLL_WRITE,
 				     consume_q->kernel_if->u.h.header_page);
 	if (retval < (int)consume_q->kernel_if->num_pages) {
 		pr_debug("get_user_pages_fast(consume) failed (retval=%d)",

drivers/platform/goldfish/goldfish_pipe.c

@@ -274,7 +274,8 @@ static int pin_user_pages(unsigned long first_page,
 		*iter_last_page_size = last_page_size;
 	}
 
-	ret = get_user_pages_fast(first_page, requested_pages, !is_write,
+	ret = get_user_pages_fast(first_page, requested_pages,
+				  !is_write ? FOLL_WRITE : 0,
 				  pages);
 	if (ret <= 0)
 		return -EFAULT;

drivers/rapidio/devices/rio_mport_cdev.c

@@ -868,7 +868,9 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
 
 		pinned = get_user_pages_fast(
 				(unsigned long)xfer->loc_addr & PAGE_MASK,
-				nr_pages, dir == DMA_FROM_DEVICE, page_list);
+				nr_pages,
+				dir == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
+				page_list);
 
 		if (pinned != nr_pages) {
 			if (pinned < 0) {

drivers/sbus/char/oradax.c

@@ -437,7 +437,7 @@ static int dax_lock_page(void *va, struct page **p)
 
 	dax_dbg("uva %p", va);
 
-	ret = get_user_pages_fast((unsigned long)va, 1, 1, p);
+	ret = get_user_pages_fast((unsigned long)va, 1, FOLL_WRITE, p);
 	if (ret == 1) {
 		dax_dbg("locked page %p, for VA %p", *p, va);
 		return 0;

drivers/scsi/st.c

@@ -4922,7 +4922,8 @@ static int sgl_map_user_pages(struct st_buffer *STbp,
 
         /* Try to fault in all of the necessary pages */
         /* rw==READ means read from drive, write into memory area */
-	res = get_user_pages_fast(uaddr, nr_pages, rw == READ, pages);
+	res = get_user_pages_fast(uaddr, nr_pages, rw == READ ? FOLL_WRITE : 0,
+				  pages);
 
 	/* Errors and no page mapped should return here */
 	if (res < nr_pages)

drivers/staging/gasket/gasket_page_table.c

@@ -486,8 +486,8 @@ static int gasket_perform_mapping(struct gasket_page_table *pg_tbl,
 			ptes[i].dma_addr = pg_tbl->coherent_pages[0].paddr +
 					   off + i * PAGE_SIZE;
 		} else {
-			ret = get_user_pages_fast(page_addr - offset, 1, 1,
+			ret = get_user_pages_fast(page_addr - offset, 1,
-						  &page);
+						  FOLL_WRITE, &page);
 
 			if (ret <= 0) {
 				dev_err(pg_tbl->device,

drivers/tee/tee_shm.c

@@ -273,7 +273,7 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
 		goto err;
 	}
 
-	rc = get_user_pages_fast(start, num_pages, 1, shm->pages);
+	rc = get_user_pages_fast(start, num_pages, FOLL_WRITE, shm->pages);
 	if (rc > 0)
 		shm->num_pages = rc;
 	if (rc != num_pages) {

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -532,7 +532,8 @@ static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
 	enum dma_data_direction direction = iommu_tce_direction(tce);
 
 	if (get_user_pages_fast(tce & PAGE_MASK, 1,
-			direction != DMA_TO_DEVICE, &page) != 1)
+			direction != DMA_TO_DEVICE ? FOLL_WRITE : 0,
+			&page) != 1)
 		return -EFAULT;
 
 	*hpa = __pa((unsigned long) page_address(page));

drivers/vfio/vfio_iommu_type1.c

@@ -358,7 +358,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 
 	down_read(&mm->mmap_sem);
 	if (mm == current->mm) {
-		ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas);
+		ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
+				     vmas);
 	} else {
 		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
 					    vmas, NULL);

drivers/vhost/vhost.c

@@ -1704,7 +1704,7 @@ static int set_bit_to_user(int nr, void __user *addr)
 	int bit = nr + (log % PAGE_SIZE) * 8;
 	int r;
 
-	r = get_user_pages_fast(log, 1, 1, &page);
+	r = get_user_pages_fast(log, 1, FOLL_WRITE, &page);
 	if (r < 0)
 		return r;
 	BUG_ON(r != 1);

drivers/video/fbdev/pvr2fb.c

@@ -686,7 +686,7 @@ static ssize_t pvr2fb_write(struct fb_info *info, const char *buf,
 	if (!pages)
 		return -ENOMEM;
 
-	ret = get_user_pages_fast((unsigned long)buf, nr_pages, true, pages);
+	ret = get_user_pages_fast((unsigned long)buf, nr_pages, FOLL_WRITE, pages);
 	if (ret < nr_pages) {
 		nr_pages = ret;
 		ret = -EINVAL;

drivers/virt/fsl_hypervisor.c

@@ -244,7 +244,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
 
 	/* Get the physical addresses of the source buffer */
 	num_pinned = get_user_pages_fast(param.local_vaddr - lb_offset,
-		num_pages, param.source != -1, pages);
+		num_pages, param.source != -1 ? FOLL_WRITE : 0, pages);
 
 	if (num_pinned != num_pages) {
 		/* get_user_pages() failed */

drivers/xen/gntdev.c

@@ -526,20 +526,20 @@ static int mn_invl_range_start(struct mmu_notifier *mn,
 	struct gntdev_grant_map *map;
 	int ret = 0;
 
-	if (range->blockable)
+	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&priv->lock);
 	else if (!mutex_trylock(&priv->lock))
 		return -EAGAIN;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		ret = unmap_if_in_range(map, range->start, range->end,
-					range->blockable);
+					mmu_notifier_range_blockable(range));
 		if (ret)
 			goto out_unlock;
 	}
 	list_for_each_entry(map, &priv->freeable_maps, next) {
 		ret = unmap_if_in_range(map, range->start, range->end,
-					range->blockable);
+					mmu_notifier_range_blockable(range));
 		if (ret)
 			goto out_unlock;
 	}
@@ -852,7 +852,7 @@ static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt,
 	unsigned long xen_pfn;
 	int ret;
 
-	ret = get_user_pages_fast(addr, 1, writeable, &page);
+	ret = get_user_pages_fast(addr, 1, writeable ? FOLL_WRITE : 0, &page);
 	if (ret < 0)
 		return ret;
 
@@ -1084,7 +1084,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	int index = vma->vm_pgoff;
 	int count = vma_pages(vma);
 	struct gntdev_grant_map *map;
-	int i, err = -EINVAL;
+	int err = -EINVAL;
 
 	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
@@ -1145,12 +1145,9 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		goto out_put_map;
 
 	if (!use_ptemod) {
-		for (i = 0; i < count; i++) {
+		err = vm_map_pages(vma, map->pages, map->count);
-			err = vm_insert_page(vma, vma->vm_start + i*PAGE_SIZE,
+		if (err)
-				map->pages[i]);
+			goto out_put_map;
-			if (err)
-				goto out_put_map;
-		}
 	} else {
 #ifdef CONFIG_X86
 		/*