1 files changed, 109 insertions, 147 deletions

diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 3707c71ae4cd..4f5937090590 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -1,14 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * mm/percpu-vm.c - vmalloc area based chunk allocation
  *
  * Copyright (C) 2010		SUSE Linux Products GmbH
  * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
  *
- * This file is released under the GPLv2.
- *
  * Chunks are mapped into vmalloc areas and populated page by page.
  * This is the default chunk allocator.
  */
+#include "internal.h"
 
 static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
 				    unsigned int cpu, int page_idx)
@@ -20,46 +20,24 @@ static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
 }
 
 /**
- * pcpu_get_pages_and_bitmap - get temp pages array and bitmap
- * @chunk: chunk of interest
- * @bitmapp: output parameter for bitmap
- * @may_alloc: may allocate the array
+ * pcpu_get_pages - get temp pages array
  *
- * Returns pointer to array of pointers to struct page and bitmap,
- * both of which can be indexed with pcpu_page_idx().  The returned
- * array is cleared to zero and *@bitmapp is copied from
- * @chunk->populated.  Note that there is only one array and bitmap
- * and access exclusion is the caller's responsibility.
- *
- * CONTEXT:
- * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc.
- * Otherwise, don't care.
+ * Returns pointer to array of pointers to struct page which can be indexed
+ * with pcpu_page_idx().  Note that there is only one array and accesses
+ * should be serialized by pcpu_alloc_mutex.
  *
  * RETURNS:
- * Pointer to temp pages array on success, NULL on failure.
+ * Pointer to temp pages array on success.
  */
-static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
-					       unsigned long **bitmapp,
-					       bool may_alloc)
+static struct page **pcpu_get_pages(void)
 {
 	static struct page **pages;
-	static unsigned long *bitmap;
 	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
-	size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) *
-			     sizeof(unsigned long);
-
-	if (!pages || !bitmap) {
-		if (may_alloc && !pages)
-			pages = pcpu_mem_zalloc(pages_size);
-		if (may_alloc && !bitmap)
-			bitmap = pcpu_mem_zalloc(bitmap_size);
-		if (!pages || !bitmap)
-			return NULL;
-	}
 
-	bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
+	lockdep_assert_held(&pcpu_alloc_mutex);
 
-	*bitmapp = bitmap;
+	if (!pages)
+		pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL);
 	return pages;
 }
 
@@ -67,7 +45,6 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
  * pcpu_free_pages - free pages which were allocated for @chunk
  * @chunk: chunk pages were allocated for
  * @pages: array of pages to be freed, indexed by pcpu_page_idx()
- * @populated: populated bitmap
  * @page_start: page index of the first page to be freed
  * @page_end: page index of the last page to be freed + 1
  *
@@ -75,8 +52,7 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
  * The pages were allocated for @chunk.
  */
 static void pcpu_free_pages(struct pcpu_chunk *chunk,
-			    struct page **pages, unsigned long *populated,
-			    int page_start, int page_end)
+			    struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu;
 	int i;
@@ -95,35 +71,45 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
  * pcpu_alloc_pages - allocates pages for @chunk
  * @chunk: target chunk
  * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
- * @populated: populated bitmap
  * @page_start: page index of the first page to be allocated
  * @page_end: page index of the last page to be allocated + 1
+ * @gfp: allocation flags passed to the underlying allocator
  *
  * Allocate pages [@page_start,@page_end) into @pages for all units.
  * The allocation is for @chunk.  Percpu core doesn't care about the
  * content of @pages and will pass it verbatim to pcpu_map_pages().
  */
 static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
-			    struct page **pages, unsigned long *populated,
-			    int page_start, int page_end)
+			    struct page **pages, int page_start, int page_end,
+			    gfp_t gfp)
 {
-	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
-	unsigned int cpu;
+	unsigned int cpu, tcpu;
 	int i;
 
+	gfp |= __GFP_HIGHMEM;
+
 	for_each_possible_cpu(cpu) {
 		for (i = page_start; i < page_end; i++) {
 			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
 
 			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
-			if (!*pagep) {
-				pcpu_free_pages(chunk, pages, populated,
-						page_start, page_end);
-				return -ENOMEM;
-			}
+			if (!*pagep)
+				goto err;
 		}
 	}
 	return 0;
+
+err:
+	while (--i >= page_start)
+		__free_page(pages[pcpu_page_idx(cpu, i)]);
+
+	for_each_possible_cpu(tcpu) {
+		if (tcpu == cpu)
+			break;
+		for (i = page_start; i < page_end; i++)
+			__free_page(pages[pcpu_page_idx(tcpu, i)]);
+	}
+	return -ENOMEM;
 }
 
 /**
@@ -148,14 +134,13 @@ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
 
 static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
 {
-	unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
+	vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT));
 }
 
 /**
  * pcpu_unmap_pages - unmap pages out of a pcpu_chunk
  * @chunk: chunk of interest
  * @pages: pages array which can be used to pass information to free
- * @populated: populated bitmap
  * @page_start: page index of the first page to unmap
  * @page_end: page index of the last page to unmap + 1
  *
@@ -166,8 +151,7 @@ static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
  * proper pre/post flush functions.
  */
 static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
-			     struct page **pages, unsigned long *populated,
-			     int page_start, int page_end)
+			     struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu;
 	int i;
@@ -183,8 +167,6 @@ static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
 		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
 				   page_end - page_start);
 	}
-
-	bitmap_clear(populated, page_start, page_end - page_start);
 }
 
 /**
@@ -211,15 +193,14 @@ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
 static int __pcpu_map_pages(unsigned long addr, struct page **pages,
 			    int nr_pages)
 {
-	return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,
-					PAGE_KERNEL, pages);
+	return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT),
+			PAGE_KERNEL, pages, PAGE_SHIFT, GFP_KERNEL);
 }
 
 /**
  * pcpu_map_pages - map pages into a pcpu_chunk
  * @chunk: chunk of interest
  * @pages: pages array containing pages to be mapped
- * @populated: populated bitmap
  * @page_start: page index of the first page to map
  * @page_end: page index of the last page to map + 1
  *
@@ -227,13 +208,11 @@ static int __pcpu_map_pages(unsigned long addr, struct page **pages,
  * caller is responsible for calling pcpu_post_map_flush() after all
  * mappings are complete.
  *
- * This function is responsible for setting corresponding bits in
- * @chunk->populated bitmap and whatever is necessary for reverse
- * lookup (addr -> chunk).
+ * This function is responsible for setting up whatever is necessary for
+ * reverse lookup (addr -> chunk).
  */
 static int pcpu_map_pages(struct pcpu_chunk *chunk,
-			  struct page **pages, unsigned long *populated,
-			  int page_start, int page_end)
+			  struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu, tcpu;
 	int i, err;
@@ -244,25 +223,20 @@ static int pcpu_map_pages(struct pcpu_chunk *chunk,
 				       page_end - page_start);
 		if (err < 0)
 			goto err;
-	}
 
-	/* mapping successful, link chunk and mark populated */
-	for (i = page_start; i < page_end; i++) {
-		for_each_possible_cpu(cpu)
+		for (i = page_start; i < page_end; i++)
 			pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
 					    chunk);
-		__set_bit(i, populated);
 	}
-
 	return 0;
-
 err:
 	for_each_possible_cpu(tcpu) {
-		if (tcpu == cpu)
-			break;
 		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
 				   page_end - page_start);
+		if (tcpu == cpu)
+			break;
 	}
+	pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
 	return err;
 }
 
@@ -289,131 +263,79 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
 /**
  * pcpu_populate_chunk - populate and map an area of a pcpu_chunk
  * @chunk: chunk of interest
- * @off: offset to the area to populate
- * @size: size of the area to populate in bytes
+ * @page_start: the start page
+ * @page_end: the end page
+ * @gfp: allocation flags passed to the underlying memory allocator
  *
  * For each cpu, populate and map pages [@page_start,@page_end) into
- * @chunk.  The area is cleared on return.
+ * @chunk.
  *
  * CONTEXT:
  * pcpu_alloc_mutex, does GFP_KERNEL allocation.
  */
-static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static int pcpu_populate_chunk(struct pcpu_chunk *chunk,
+			       int page_start, int page_end, gfp_t gfp)
 {
-	int page_start = PFN_DOWN(off);
-	int page_end = PFN_UP(off + size);
-	int free_end = page_start, unmap_end = page_start;
 	struct page **pages;
-	unsigned long *populated;
-	unsigned int cpu;
-	int rs, re, rc;
-
-	/* quick path, check whether all pages are already there */
-	rs = page_start;
-	pcpu_next_pop(chunk, &rs, &re, page_end);
-	if (rs == page_start && re == page_end)
-		goto clear;
-
-	/* need to allocate and map pages, this chunk can't be immutable */
-	WARN_ON(chunk->immutable);
 
-	pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);
+	pages = pcpu_get_pages();
 	if (!pages)
 		return -ENOMEM;
 
-	/* alloc and map */
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-		rc = pcpu_alloc_pages(chunk, pages, populated, rs, re);
-		if (rc)
-			goto err_free;
-		free_end = re;
-	}
+	if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp))
+		return -ENOMEM;
 
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
-		rc = pcpu_map_pages(chunk, pages, populated, rs, re);
-		if (rc)
-			goto err_unmap;
-		unmap_end = re;
+	if (pcpu_map_pages(chunk, pages, page_start, page_end)) {
+		pcpu_free_pages(chunk, pages, page_start, page_end);
+		return -ENOMEM;
 	}
 	pcpu_post_map_flush(chunk, page_start, page_end);
 
-	/* commit new bitmap */
-	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
-clear:
-	for_each_possible_cpu(cpu)
-		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
 	return 0;
-
-err_unmap:
-	pcpu_pre_unmap_flush(chunk, page_start, unmap_end);
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end)
-		pcpu_unmap_pages(chunk, pages, populated, rs, re);
-	pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end);
-err_free:
-	pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end)
-		pcpu_free_pages(chunk, pages, populated, rs, re);
-	return rc;
 }
 
 /**
  * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
  * @chunk: chunk to depopulate
- * @off: offset to the area to depopulate
- * @size: size of the area to depopulate in bytes
+ * @page_start: the start page
+ * @page_end: the end page
  *
  * For each cpu, depopulate and unmap pages [@page_start,@page_end)
- * from @chunk.  If @flush is true, vcache is flushed before unmapping
- * and tlb after.
+ * from @chunk.
+ *
+ * Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the
+ * region back to vmalloc() which will lazily flush the tlb.
  *
  * CONTEXT:
  * pcpu_alloc_mutex.
  */
-static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size)
+static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk,
+				  int page_start, int page_end)
 {
-	int page_start = PFN_DOWN(off);
-	int page_end = PFN_UP(off + size);
 	struct page **pages;
-	unsigned long *populated;
-	int rs, re;
-
-	/* quick path, check whether it's empty already */
-	rs = page_start;
-	pcpu_next_unpop(chunk, &rs, &re, page_end);
-	if (rs == page_start && re == page_end)
-		return;
-
-	/* immutable chunks can't be depopulated */
-	WARN_ON(chunk->immutable);
 
 	/*
 	 * If control reaches here, there must have been at least one
 	 * successful population attempt so the temp pages array must
 	 * be available now.
 	 */
-	pages = pcpu_get_pages_and_bitmap(chunk, &populated, false);
+	pages = pcpu_get_pages();
 	BUG_ON(!pages);
 
 	/* unmap and free */
 	pcpu_pre_unmap_flush(chunk, page_start, page_end);
 
-	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
-		pcpu_unmap_pages(chunk, pages, populated, rs, re);
-
-	/* no need to flush tlb, vmalloc will handle it lazily */
-
-	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
-		pcpu_free_pages(chunk, pages, populated, rs, re);
+	pcpu_unmap_pages(chunk, pages, page_start, page_end);
 
-	/* commit new bitmap */
-	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
+	pcpu_free_pages(chunk, pages, page_start, page_end);
 }
 
-static struct pcpu_chunk *pcpu_create_chunk(void)
+static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp)
 {
 	struct pcpu_chunk *chunk;
 	struct vm_struct **vms;
 
-	chunk = pcpu_alloc_chunk();
+	chunk = pcpu_alloc_chunk(gfp);
 	if (!chunk)
 		return NULL;
 
@@ -426,12 +348,22 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 
 	chunk->data = vms;
 	chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
+
+	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(chunk->base_addr);
+
 	return chunk;
 }
 
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
 {
-	if (chunk && chunk->data)
+	if (!chunk)
+		return;
+
+	pcpu_stats_chunk_dealloc();
+	trace_percpu_destroy_chunk(chunk->base_addr);
+
+	if (chunk->data)
 		pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
 	pcpu_free_chunk(chunk);
 }
@@ -446,3 +378,33 @@ static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai)
 	/* no extra restriction */
 	return 0;
 }
+
+/**
+ * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim
+ * @chunk: chunk of interest
+ *
+ * This is the entry point for percpu reclaim.  If a chunk qualifies, it is then
+ * isolated and managed in separate lists at the back of pcpu_slot: sidelined
+ * and to_depopulate respectively.  The to_depopulate list holds chunks slated
+ * for depopulation.  They no longer contribute to pcpu_nr_empty_pop_pages once
+ * they are on this list.  Once depopulated, they are moved onto the sidelined
+ * list which enables them to be pulled back in for allocation if no other chunk
+ * can suffice the allocation.
+ */
+static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk)
+{
+	/* do not reclaim either the first chunk or reserved chunk */
+	if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk)
+		return false;
+
+	/*
+	 * If it is isolated, it may be on the sidelined list so move it back to
+	 * the to_depopulate list.  If we hit at least 1/4 pages empty pages AND
+	 * there is no system-wide shortage of empty pages aside from this
+	 * chunk, move it to the to_depopulate list.
+	 */
+	return ((chunk->isolated && chunk->nr_empty_pop_pages) ||
+		(pcpu_nr_empty_pop_pages >
+		 (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) &&
+		 chunk->nr_empty_pop_pages >= chunk->nr_pages / 4));
+}