summary refs log tree commit diff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig1
-rw-r--r--mm/gup.c4
-rw-r--r--mm/ksm.c2
-rw-r--r--mm/memcontrol.c6
-rw-r--r--mm/memory.c2
-rw-r--r--mm/nommu.c1
-rw-r--r--mm/page_alloc.c82
-rw-r--r--mm/pagewalk.c5
-rw-r--r--mm/shmem.c2
-rw-r--r--mm/vmscan.c2
10 files changed, 50 insertions, 57 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 1d1ae6b078fd..4395b12869c8 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -325,6 +325,7 @@ config VIRT_TO_BUS
 
 config MMU_NOTIFIER
 	bool
+	select SRCU
 
 config KSM
 	bool "Enable KSM for page merging"
diff --git a/mm/gup.c b/mm/gup.c
index a900759cc807..8dd50ce6326f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -296,7 +296,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
@@ -571,7 +571,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 			return -ENOMEM;
 		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
 			return -EHWPOISON;
-		if (ret & VM_FAULT_SIGBUS)
+		if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV))
 			return -EFAULT;
 		BUG();
 	}
diff --git a/mm/ksm.c b/mm/ksm.c
index d247efab5073..15647fb0394f 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
 		else
 			ret = VM_FAULT_WRITE;
 		put_page(page);
-	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM)));
+	} while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
 	/*
 	 * We must loop because handle_mm_fault() may back out if there's
 	 * any difficulty e.g. if pte accessed bit gets updated concurrently.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 851924fa5170..2f6893c2f01b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1477,9 +1477,9 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 
 	pr_info("Task in ");
 	pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
-	pr_info(" killed as a result of limit of ");
+	pr_cont(" killed as a result of limit of ");
 	pr_cont_cgroup_path(memcg->css.cgroup);
-	pr_info("\n");
+	pr_cont("\n");
 
 	rcu_read_unlock();
 
@@ -5773,7 +5773,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
  * mem_cgroup_migrate - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
- * @lrucare: both pages might be on the LRU already
+ * @lrucare: either or both pages might be on the LRU already
  *
  * Migrate the charge from @oldpage to @newpage.
  *
diff --git a/mm/memory.c b/mm/memory.c
index dc2e01a315e2..d707c4dfbbb4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2634,7 +2634,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
-		return VM_FAULT_SIGBUS;
+		return VM_FAULT_SIGSEGV;
 
 	/* Use the zero-page for reads */
 	if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
diff --git a/mm/nommu.c b/mm/nommu.c
index b51eadf6d952..28bd8c4dff6f 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -59,6 +59,7 @@
 #endif
 
 void *high_memory;
+EXPORT_SYMBOL(high_memory);
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long highest_memmap_pfn;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7633c503a116..8e20f9c2fa5a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2332,12 +2332,21 @@ static inline struct page *
 __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, struct zone *preferred_zone,
-	int classzone_idx, int migratetype)
+	int classzone_idx, int migratetype, unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	/* Acquire the per-zone oom lock for each zone */
+	*did_some_progress = 0;
+
+	if (oom_killer_disabled)
+		return NULL;
+
+	/*
+	 * Acquire the per-zone oom lock for each zone.  If that
+	 * fails, somebody else is making progress for us.
+	 */
 	if (!oom_zonelist_trylock(zonelist, gfp_mask)) {
+		*did_some_progress = 1;
 		schedule_timeout_uninterruptible(1);
 		return NULL;
 	}
@@ -2363,12 +2372,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 		goto out;
 
 	if (!(gfp_mask & __GFP_NOFAIL)) {
+		/* Coredumps can quickly deplete all memory reserves */
+		if (current->flags & PF_DUMPCORE)
+			goto out;
 		/* The OOM killer will not help higher order allocs */
 		if (order > PAGE_ALLOC_COSTLY_ORDER)
 			goto out;
 		/* The OOM killer does not needlessly kill tasks for lowmem */
 		if (high_zoneidx < ZONE_NORMAL)
 			goto out;
+		/* The OOM killer does not compensate for light reclaim */
+		if (!(gfp_mask & __GFP_FS))
+			goto out;
 		/*
 		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
 		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2381,7 +2396,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	}
 	/* Exhausted what can be done so it's blamo time */
 	out_of_memory(zonelist, gfp_mask, order, nodemask, false);
-
+	*did_some_progress = 1;
 out:
 	oom_zonelist_unlock(zonelist, gfp_mask);
 	return page;
@@ -2658,7 +2673,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	    (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
-restart:
+retry:
 	if (!(gfp_mask & __GFP_NO_KSWAPD))
 		wake_all_kswapds(order, zonelist, high_zoneidx,
 				preferred_zone, nodemask);
@@ -2681,7 +2696,6 @@ restart:
 		classzone_idx = zonelist_zone_idx(preferred_zoneref);
 	}
 
-rebalance:
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2788,54 +2802,28 @@ rebalance:
 	if (page)
 		goto got_pg;
 
-	/*
-	 * If we failed to make any progress reclaiming, then we are
-	 * running out of options and have to consider going OOM
-	 */
-	if (!did_some_progress) {
-		if (oom_gfp_allowed(gfp_mask)) {
-			if (oom_killer_disabled)
-				goto nopage;
-			/* Coredumps can quickly deplete all memory reserves */
-			if ((current->flags & PF_DUMPCORE) &&
-			    !(gfp_mask & __GFP_NOFAIL))
-				goto nopage;
-			page = __alloc_pages_may_oom(gfp_mask, order,
-					zonelist, high_zoneidx,
-					nodemask, preferred_zone,
-					classzone_idx, migratetype);
-			if (page)
-				goto got_pg;
-
-			if (!(gfp_mask & __GFP_NOFAIL)) {
-				/*
-				 * The oom killer is not called for high-order
-				 * allocations that may fail, so if no progress
-				 * is being made, there are no other options and
-				 * retrying is unlikely to help.
-				 */
-				if (order > PAGE_ALLOC_COSTLY_ORDER)
-					goto nopage;
-				/*
-				 * The oom killer is not called for lowmem
-				 * allocations to prevent needlessly killing
-				 * innocent tasks.
-				 */
-				if (high_zoneidx < ZONE_NORMAL)
-					goto nopage;
-			}
-
-			goto restart;
-		}
-	}
-
 	/* Check if we should retry the allocation */
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, did_some_progress,
 						pages_reclaimed)) {
+		/*
+		 * If we fail to make progress by freeing individual
+		 * pages, but the allocation wants us to keep going,
+		 * start OOM killing tasks.
+		 */
+		if (!did_some_progress) {
+			page = __alloc_pages_may_oom(gfp_mask, order, zonelist,
+						high_zoneidx, nodemask,
+						preferred_zone, classzone_idx,
+						migratetype,&did_some_progress);
+			if (page)
+				goto got_pg;
+			if (!did_some_progress)
+				goto nopage;
+		}
 		/* Wait for some write requests to complete then retry */
 		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
-		goto rebalance;
+		goto retry;
 	} else {
 		/*
 		 * High-order allocations do not necessarily loop after
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ad83195521f2..b264bda46e1b 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -199,7 +199,10 @@ int walk_page_range(unsigned long addr, unsigned long end,
 			 */
 			if ((vma->vm_start <= addr) &&
 			    (vma->vm_flags & VM_PFNMAP)) {
-				next = vma->vm_end;
+				if (walk->pte_hole)
+					err = walk->pte_hole(addr, next, walk);
+				if (err)
+					break;
 				pgd = pgd_offset(walk->mm, next);
 				continue;
 			}
diff --git a/mm/shmem.c b/mm/shmem.c
index 73ba1df7c8ba..993e6ba689cc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1013,7 +1013,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_migrate(oldpage, newpage, false);
+		mem_cgroup_migrate(oldpage, newpage, true);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ab2505c3ef54..dcd90c891d8e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2656,7 +2656,7 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
 	 * should make reasonable progress.
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					gfp_mask, nodemask) {
+					gfp_zone(gfp_mask), nodemask) {
 		if (zone_idx(zone) > ZONE_NORMAL)
 			continue;
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-09 16:36:44 +0000