Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

4 files changed, 81 insertions, 63 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a3278f0..7125248 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -128,7 +128,6 @@ unsigned long global_dirty_limit;
  *
  */
 static struct prop_descriptor vm_completions;
-static struct prop_descriptor vm_dirties;
 
 /*
  * couple the period to the dirty_ratio:
@@ -154,7 +153,6 @@ static void update_completion_period(void)
 {
 	int shift = calc_period_shift();
 	prop_change_shift(&vm_completions, shift);
-	prop_change_shift(&vm_dirties, shift);
 
 	writeback_set_ratelimit();
 }
@@ -235,11 +233,6 @@ void bdi_writeout_inc(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL_GPL(bdi_writeout_inc);
 
-void task_dirty_inc(struct task_struct *tsk)
-{
-	prop_inc_single(&vm_dirties, &tsk->dirties);
-}
-
 /*
  * Obtain an accurate fraction of the BDI's portion.
  */
@@ -1133,17 +1126,17 @@ pause:
 					  pages_dirtied,
 					  pause,
 					  start_time);
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(TASK_KILLABLE);
 		io_schedule_timeout(pause);
 
-		dirty_thresh = hard_dirty_limit(dirty_thresh);
 		/*
-		 * max-pause area. If dirty exceeded but still within this
-		 * area, no need to sleep for more than 200ms: (a) 8 pages per
-		 * 200ms is typically more than enough to curb heavy dirtiers;
-		 * (b) the pause time limit makes the dirtiers more responsive.
+		 * This is typically equal to (nr_dirty < dirty_thresh) and can
+		 * also keep "1000+ dd on a slow USB stick" under control.
 		 */
-		if (nr_dirty < dirty_thresh)
+		if (task_ratelimit)
+			break;
+
+		if (fatal_signal_pending(current))
 			break;
 	}
 
@@ -1395,7 +1388,6 @@ void __init page_writeback_init(void)
 
 	shift = calc_period_shift();
 	prop_descriptor_init(&vm_completions, shift);
-	prop_descriptor_init(&vm_dirties, shift);
 }
 
 /**
@@ -1724,7 +1716,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		__inc_zone_page_state(page, NR_DIRTIED);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
-		task_dirty_inc(current);
 		task_io_account_write(PAGE_CACHE_SIZE);
 	}
 }
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index ea53496..12a48a88 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -50,14 +50,13 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
 
 	if (!pages || !bitmap) {
 		if (may_alloc && !pages)
-			pages = pcpu_mem_alloc(pages_size);
+			pages = pcpu_mem_zalloc(pages_size);
 		if (may_alloc && !bitmap)
-			bitmap = pcpu_mem_alloc(bitmap_size);
+			bitmap = pcpu_mem_zalloc(bitmap_size);
 		if (!pages || !bitmap)
 			return NULL;
 	}
 
-	memset(pages, 0, pages_size);
 	bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
 
 	*bitmapp = bitmap;
@@ -143,8 +142,8 @@ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
 				 int page_start, int page_end)
 {
 	flush_cache_vunmap(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
@@ -206,8 +205,8 @@ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
 				      int page_start, int page_end)
 {
 	flush_tlb_kernel_range(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 static int __pcpu_map_pages(unsigned long addr, struct page **pages,
@@ -284,8 +283,8 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
 				int page_start, int page_end)
 {
 	flush_cache_vmap(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 /**
diff --git a/mm/percpu.c b/mm/percpu.c
index bf80e55..3bb810a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -116,9 +116,9 @@ static int pcpu_atom_size __read_mostly;
 static int pcpu_nr_slots __read_mostly;
 static size_t pcpu_chunk_struct_size __read_mostly;
 
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
 
 /* the address of the first chunk which starts with the kernel static area */
 void *pcpu_base_addr __read_mostly;
@@ -273,11 +273,11 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
 	     (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))
 
 /**
- * pcpu_mem_alloc - allocate memory
+ * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
  *
  * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vmalloc() is used.  The returned
+ * kzalloc() is used; otherwise, vzalloc() is used.  The returned
  * memory is always zeroed.
  *
  * CONTEXT:
@@ -286,7 +286,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_mem_alloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size)
 {
 	if (WARN_ON_ONCE(!slab_is_available()))
 		return NULL;
@@ -302,7 +302,7 @@ static void *pcpu_mem_alloc(size_t size)
  * @ptr: memory to free
  * @size: size of the area
  *
- * Free @ptr.  @ptr should have been allocated using pcpu_mem_alloc().
+ * Free @ptr.  @ptr should have been allocated using pcpu_mem_zalloc().
  */
 static void pcpu_mem_free(void *ptr, size_t size)
 {
@@ -384,7 +384,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
-	new = pcpu_mem_alloc(new_size);
+	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
 
@@ -604,11 +604,12 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 {
 	struct pcpu_chunk *chunk;
 
-	chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
+	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
 	if (!chunk)
 		return NULL;
 
-	chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
+						sizeof(chunk->map[0]));
 	if (!chunk->map) {
 		kfree(chunk);
 		return NULL;
@@ -977,6 +978,17 @@ bool is_kernel_percpu_address(unsigned long addr)
  * address.  The caller is responsible for ensuring @addr stays valid
  * until this function finishes.
  *
+ * percpu allocator has special setup for the first chunk, which currently
+ * supports either embedding in linear address space or vmalloc mapping,
+ * and, from the second one, the backing allocator (currently either vm or
+ * km) provides translation.
+ *
+ * The addr can be tranlated simply without checking if it falls into the
+ * first chunk. But the current code reflects better how percpu allocator
+ * actually works, and the verification can discover both bugs in percpu
+ * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
+ * code.
+ *
  * RETURNS:
  * The physical address for @addr.
  */
@@ -984,19 +996,19 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
 {
 	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
 	bool in_first_chunk = false;
-	unsigned long first_start, first_end;
+	unsigned long first_low, first_high;
 	unsigned int cpu;
 
 	/*
-	 * The following test on first_start/end isn't strictly
+	 * The following test on unit_low/high isn't strictly
 	 * necessary but will speed up lookups of addresses which
 	 * aren't in the first chunk.
 	 */
-	first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
-	first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
-				    pcpu_unit_pages);
-	if ((unsigned long)addr >= first_start &&
-	    (unsigned long)addr < first_end) {
+	first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
+	first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
+				     pcpu_unit_pages);
+	if ((unsigned long)addr >= first_low &&
+	    (unsigned long)addr < first_high) {
 		for_each_possible_cpu(cpu) {
 			void *start = per_cpu_ptr(base, cpu);
 
@@ -1233,7 +1245,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
-	pcpu_first_unit_cpu = NR_CPUS;
+
+	pcpu_low_unit_cpu = NR_CPUS;
+	pcpu_high_unit_cpu = NR_CPUS;
 
 	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
 		const struct pcpu_group_info *gi = &ai->groups[group];
@@ -1253,9 +1267,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 			unit_map[cpu] = unit + i;
 			unit_off[cpu] = gi->base_offset + i * ai->unit_size;
 
-			if (pcpu_first_unit_cpu == NR_CPUS)
-				pcpu_first_unit_cpu = cpu;
-			pcpu_last_unit_cpu = cpu;
+			/* determine low/high unit_cpu */
+			if (pcpu_low_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+				pcpu_low_unit_cpu = cpu;
+			if (pcpu_high_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+				pcpu_high_unit_cpu = cpu;
 		}
 	}
 	pcpu_nr_units = unit;
@@ -1889,7 +1907,7 @@ void __init percpu_init_late(void)
 
 		BUILD_BUG_ON(size > PAGE_SIZE);
 
-		map = pcpu_mem_alloc(size);
+		map = pcpu_mem_zalloc(size);
 		BUG_ON(!map);
 
 		spin_lock_irqsave(&pcpu_lock, flags);
diff --git a/mm/slub.c b/mm/slub.c
index 7d2a996..ed3334d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1862,7 +1862,7 @@ static void unfreeze_partials(struct kmem_cache *s)
 {
 	struct kmem_cache_node *n = NULL;
 	struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
-	struct page *page;
+	struct page *page, *discard_page = NULL;
 
 	while ((page = c->partial)) {
 		enum slab_modes { M_PARTIAL, M_FREE };
@@ -1904,7 +1904,8 @@ static void unfreeze_partials(struct kmem_cache *s)
 				if (l == M_PARTIAL)
 					remove_partial(n, page);
 				else
-					add_partial(n, page, 1);
+					add_partial(n, page,
+						DEACTIVATE_TO_TAIL);
 
 				l = m;
 			}
@@ -1915,14 +1916,22 @@ static void unfreeze_partials(struct kmem_cache *s)
 				"unfreezing slab"));
 
 		if (m == M_FREE) {
-			stat(s, DEACTIVATE_EMPTY);
-			discard_slab(s, page);
-			stat(s, FREE_SLAB);
+			page->next = discard_page;
+			discard_page = page;
 		}
 	}
 
 	if (n)
 		spin_unlock(&n->list_lock);
+
+	while (discard_page) {
+		page = discard_page;
+		discard_page = discard_page->next;
+
+		stat(s, DEACTIVATE_EMPTY);
+		discard_slab(s, page);
+		stat(s, FREE_SLAB);
+	}
 }
 
 /*
@@ -1969,7 +1978,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->pobjects = pobjects;
 		page->next = oldpage;
 
-	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+	} while (irqsafe_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
 	stat(s, CPU_PARTIAL_FREE);
 	return pobjects;
 }
@@ -4435,30 +4444,31 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 		for_each_possible_cpu(cpu) {
 			struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+			int node = ACCESS_ONCE(c->node);
 			struct page *page;
 
-			if (!c || c->node < 0)
+			if (node < 0)
 				continue;
-
-			if (c->page) {
-					if (flags & SO_TOTAL)
-						x = c->page->objects;
+			page = ACCESS_ONCE(c->page);
+			if (page) {
+				if (flags & SO_TOTAL)
+					x = page->objects;
 				else if (flags & SO_OBJECTS)
-					x = c->page->inuse;
+					x = page->inuse;
 				else
 					x = 1;
 
 				total += x;
-				nodes[c->node] += x;
+				nodes[node] += x;
 			}
 			page = c->partial;
 
 			if (page) {
 				x = page->pobjects;
-                                total += x;
-                                nodes[c->node] += x;
+				total += x;
+				nodes[node] += x;
 			}
-			per_cpu[c->node]++;
+			per_cpu[node]++;
 		}
 	}