Merge branch 'akpm' (patches from Andrew)

Merge still more updates from Andrew Morton:
 "Various trees. Mainly those parts of MM whose linux-next dependents
  are now merged. I'm still sitting on ~160 patches which await merges
  from -next.

  Subsystems affected by this patch series: mm/proc, ipc, dynamic-debug,
  panic, lib, sysctl, mm/gup, mm/pagemap"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (52 commits)
  doc: cgroup: update note about conditions when oom killer is invoked
  module: move the set_fs hack for flush_icache_range to m68k
  nommu: use flush_icache_user_range in brk and mmap
  binfmt_flat: use flush_icache_user_range
  exec: use flush_icache_user_range in read_code
  exec: only build read_code when needed
  m68k: implement flush_icache_user_range
  arm: rename flush_cache_user_range to flush_icache_user_range
  xtensa: implement flush_icache_user_range
  sh: implement flush_icache_user_range
  asm-generic: add a flush_icache_user_range stub
  mm: rename flush_icache_user_range to flush_icache_user_page
  arm,sparc,unicore32: remove flush_icache_user_range
  riscv: use asm-generic/cacheflush.h
  powerpc: use asm-generic/cacheflush.h
  openrisc: use asm-generic/cacheflush.h
  m68knommu: use asm-generic/cacheflush.h
  microblaze: use asm-generic/cacheflush.h
  ia64: use asm-generic/cacheflush.h
  hexagon: use asm-generic/cacheflush.h
  ...

5 files changed, 58 insertions, 42 deletions

diff --git a/mm/frame_vector.c b/mm/frame_vector.c
index c431ca81dad5..4107dbca0056 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -72,7 +72,7 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
 		vec->got_ref = true;
 		vec->is_pfns = false;
-		ret = get_user_pages_locked(start, nr_frames,
+		ret = pin_user_pages_locked(start, nr_frames,
 			gup_flags, (struct page **)(vec->ptrs), &locked);
 		goto out;
 	}
@@ -122,7 +122,6 @@ EXPORT_SYMBOL(get_vaddr_frames);
  */
 void put_vaddr_frames(struct frame_vector *vec)
 {
-	int i;
 	struct page **pages;
 
 	if (!vec->got_ref)
@@ -135,8 +134,8 @@ void put_vaddr_frames(struct frame_vector *vec)
 	 */
 	if (WARN_ON(IS_ERR(pages)))
 		goto out;
-	for (i = 0; i < vec->nr_frames; i++)
-		put_page(pages[i]);
+
+	unpin_user_pages(pages, vec->nr_frames);
 	vec->got_ref = false;
 out:
 	vec->nr_frames = 0;
diff --git a/mm/gup.c b/mm/gup.c
index e19ff770eb4c..8bd090b36d1d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2035,6 +2035,12 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 	 */
 	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
 		return -EINVAL;
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
 
 	return __get_user_pages_locked(current, current->mm, start, nr_pages,
 				       pages, NULL, locked,
@@ -2294,7 +2300,7 @@ pte_unmap:
  * to be special.
  *
  * For a futex to be placed on a THP tail page, get_futex_key requires a
- * __get_user_pages_fast implementation that can pin pages. Thus it's still
+ * get_user_pages_fast_only implementation that can pin pages. Thus it's still
  * useful to have gup_huge_pmd even if we can't operate on ptes.
  */
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
@@ -2699,7 +2705,7 @@ static inline void gup_pgd_range(unsigned long addr, unsigned long end,
 
 #ifndef gup_fast_permitted
 /*
- * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * Check if it's allowed to use get_user_pages_fast_only() for the range, or
  * we need to fall back to the slow version:
  */
 static bool gup_fast_permitted(unsigned long start, unsigned long end)
@@ -2811,8 +2817,14 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
 
 	return ret;
 }
-
-/*
+/**
+ * get_user_pages_fast_only() - pin user pages in memory
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long.
+ *
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP.
  * Note a difference with get_user_pages_fast: this always returns the
@@ -2825,8 +2837,8 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
  * access can get ambiguous page results. If you call this function without
  * 'write' set, you'd better be sure that you're ok with that ambiguity.
  */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
+int get_user_pages_fast_only(unsigned long start, int nr_pages,
+			     unsigned int gup_flags, struct page **pages)
 {
 	int nr_pinned;
 	/*
@@ -2836,10 +2848,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	 * FOLL_FAST_ONLY is required in order to match the API description of
 	 * this routine: no fall back to regular ("slow") GUP.
 	 */
-	unsigned int gup_flags = FOLL_GET | FOLL_FAST_ONLY;
-
-	if (write)
-		gup_flags |= FOLL_WRITE;
+	gup_flags |= FOLL_GET | FOLL_FAST_ONLY;
 
 	nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
 						 pages);
@@ -2855,7 +2864,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 
 	return nr_pinned;
 }
-EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+EXPORT_SYMBOL_GPL(get_user_pages_fast_only);
 
 /**
  * get_user_pages_fast() - pin user pages in memory
@@ -2909,9 +2918,6 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast);
  *
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for further details.
- *
- * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It
- * is NOT intended for Case 2 (RDMA: long-term pins).
  */
 int pin_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages)
@@ -2926,8 +2932,8 @@ int pin_user_pages_fast(unsigned long start, int nr_pages,
 EXPORT_SYMBOL_GPL(pin_user_pages_fast);
 
 /*
- * This is the FOLL_PIN equivalent of __get_user_pages_fast(). Behavior is the
- * same, except that this one sets FOLL_PIN instead of FOLL_GET.
+ * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior
+ * is the same, except that this one sets FOLL_PIN instead of FOLL_GET.
  *
  * The API rules are the same, too: no negative values may be returned.
  */
@@ -2985,9 +2991,6 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_only);
  *
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for details.
- *
- * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It
- * is NOT intended for Case 2 (RDMA: long-term pins).
  */
 long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
@@ -3021,9 +3024,6 @@ EXPORT_SYMBOL(pin_user_pages_remote);
  *
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for details.
- *
- * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It
- * is NOT intended for Case 2 (RDMA: long-term pins).
  */
 long pin_user_pages(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages,
@@ -3055,3 +3055,32 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 	return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages_unlocked);
+
+/*
+ * pin_user_pages_locked() is the FOLL_PIN variant of get_user_pages_locked().
+ * Behavior is the same, except that this one sets FOLL_PIN and rejects
+ * FOLL_GET.
+ */
+long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   int *locked)
+{
+	/*
+	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas.  As there are no users of this flag in this call we simply
+	 * disallow this option for now.
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+		return -EINVAL;
+
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+				       pages, NULL, locked,
+				       gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(pin_user_pages_locked);
diff --git a/mm/nommu.c b/mm/nommu.c
index dfae55f41901..062dc1c90d21 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -433,7 +433,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	/*
 	 * Ok, looks good - let it rip.
 	 */
-	flush_icache_range(mm->brk, brk);
+	flush_icache_user_range(mm->brk, brk);
 	return mm->brk = brk;
 }
 
@@ -1277,7 +1277,7 @@ share:
 	/* we flush the region from the icache only when the first executable
 	 * mapping of it is made  */
 	if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
-		flush_icache_range(region->vm_start, region->vm_end);
+		flush_icache_user_range(region->vm_start, region->vm_end);
 		region->vm_icache_flushed = true;
 	}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 07ae77d97952..727751219003 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5575,15 +5575,6 @@ static int __parse_numa_zonelist_order(char *s)
 	return 0;
 }
 
-static __init int setup_numa_zonelist_order(char *s)
-{
-	if (!s)
-		return 0;
-
-	return __parse_numa_zonelist_order(s);
-}
-early_param("numa_zonelist_order", setup_numa_zonelist_order);
-
 char numa_zonelist_order[] = "Node";
 
 /*
diff --git a/mm/page_idle.c b/mm/page_idle.c
index 295512465065..057c61df12db 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -4,6 +4,7 @@
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kobject.h>
+#include <linux/memory_hotplug.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/pagemap.h>
@@ -30,13 +31,9 @@
  */
 static struct page *page_idle_get_page(unsigned long pfn)
 {
-	struct page *page;
+	struct page *page = pfn_to_online_page(pfn);
 	pg_data_t *pgdat;
 
-	if (!pfn_valid(pfn))
-		return NULL;
-
-	page = pfn_to_page(pfn);
 	if (!page || !PageLRU(page) ||
 	    !get_page_unless_zero(page))
 		return NULL;