From b888132b0ff29ca0733589a594c243ed612438eb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 11 Oct 2006 01:20:40 -0700 Subject: [PATCH] mm: remove memmap_zone_idx() memmap_zone_idx() is not used anymore. It was required by an earlier version of account-for-memmap-and-optionally-the-kernel-image-as-holes.patch but not any more. Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a8c003e7b3d5..8246e834b2f0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2294,19 +2294,6 @@ unsigned long __init zone_absent_pages_in_node(int nid, return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } -/* Return the zone index a PFN is in */ -int memmap_zone_idx(struct page *lmem_map) -{ - int i; - unsigned long phys_addr = virt_to_phys(lmem_map); - unsigned long pfn = phys_addr >> PAGE_SHIFT; - - for (i = 0; i < MAX_NR_ZONES; i++) - if (pfn < arch_zone_highest_possible_pfn[i]) - break; - - return i; -} #else static inline unsigned long zone_spanned_pages_in_node(int nid, unsigned long zone_type, @@ -2325,10 +2312,6 @@ static inline unsigned long zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } -static inline int memmap_zone_idx(struct page *lmem_map) -{ - return MAX_NR_ZONES; -} #endif static void __init calculate_node_totalpages(struct pglist_data *pgdat, -- cgit From dafb13673c463bc2aade4a4819704dde0f5fa37f Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 11 Oct 2006 01:21:30 -0700 Subject: [PATCH] mm: arch_free_page fix After the PG_reserved check was added, arch_free_page was being called in the wrong place (it could be called for a page we don't actually want to free). Fix that. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8246e834b2f0..c5caac2c3c5a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -495,7 +495,6 @@ static void __free_pages_ok(struct page *page, unsigned int order) int i; int reserved = 0; - arch_free_page(page, order); if (!PageHighMem(page)) debug_check_no_locks_freed(page_address(page), PAGE_SIZE<mapping = NULL; if (free_pages_check(page)) return; + arch_free_page(page, 0); kernel_map_pages(page, 1, 0); pcp = &zone_pcp(zone, get_cpu())->pcp[cold]; -- cgit From 9858db504caedb2424b9a32744c23f9a81ec1731 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 11 Oct 2006 01:21:30 -0700 Subject: [PATCH] mm: locks_freed fix Move the lock debug checks below the page reserved checks. Also, having debug_check_no_locks_freed in kernel_map_pages is wrong. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c5caac2c3c5a..40db96a655d0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -495,15 +495,13 @@ static void __free_pages_ok(struct page *page, unsigned int order) int i; int reserved = 0; - if (!PageHighMem(page)) - debug_check_no_locks_freed(page_address(page), - PAGE_SIZE< Date: Thu, 19 Oct 2006 23:28:16 -0700 Subject: [PATCH] separate bdi congestion functions from queue congestion functions Separate out the concept of "queue congestion" from "backing-dev congestion". Congestion is a backing-dev concept, not a queue concept. The blk_* congestion functions are retained, as wrappers around the core backing-dev congestion functions. This proper layering is needed so that NFS can cleanly use the congestion functions, and so that CONFIG_BLOCK=n actually links. Cc: "Thomas Maier" Cc: "Jens Axboe" Cc: Trond Myklebust Cc: David Howells Cc: Peter Osterlund Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 40db96a655d0..afee38f04d84 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -1050,7 +1051,7 @@ nofail_alloc: if (page) goto got_pg; if (gfp_mask & __GFP_NOFAIL) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto nofail_alloc; } } @@ -1113,7 +1114,7 @@ rebalance: do_retry = 1; } if (do_retry) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto rebalance; } -- cgit From 6220ec7844fda2686496013a66b5b9169976b991 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 19 Oct 2006 23:29:05 -0700 Subject: [PATCH] highest_possible_node_id() linkage fix Qooting Adrian: - net/sunrpc/svc.c uses highest_possible_node_id() - include/linux/nodemask.h says highest_possible_node_id() is out-of-line #if MAX_NUMNODES > 1 - the out-of-line highest_possible_node_id() is in lib/cpumask.c - lib/Makefile: lib-$(CONFIG_SMP) += cpumask.o CONFIG_ARCH_DISCONTIGMEM_ENABLE=y, CONFIG_SMP=n, CONFIG_SUNRPC=y -> highest_possible_node_id() is used in net/sunrpc/svc.c CONFIG_NODES_SHIFT defined and > 0 -> include/linux/numa.h: MAX_NUMNODES > 1 -> compile error The bug is not present on architectures where ARCH_DISCONTIGMEM_ENABLE depends on NUMA (but m32r isn't the only affected architecture). So move the function into page_alloc.c Cc: Adrian Bunk Cc: Paul Jackson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index afee38f04d84..ebd425c2e2a7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3120,3 +3120,19 @@ unsigned long page_to_pfn(struct page *page) EXPORT_SYMBOL(pfn_to_page); EXPORT_SYMBOL(page_to_pfn); #endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */ + +#if MAX_NUMNODES > 1 +/* + * Find the highest possible node id. + */ +int highest_possible_node_id(void) +{ + unsigned int node; + unsigned int highest = 0; + + for_each_node_mask(node, node_possible_map) + highest = node; + return highest; +} +EXPORT_SYMBOL(highest_possible_node_id); +#endif -- cgit From 7516795739bd53175629b90fab0ad488d7a6a9f7 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Sat, 21 Oct 2006 10:24:14 -0700 Subject: [PATCH] Reintroduce NODES_SPAN_OTHER_NODES for powerpc Reintroduce NODES_SPAN_OTHER_NODES for powerpc Revert "[PATCH] Remove SPAN_OTHER_NODES config definition" This reverts commit f62859bb6871c5e4a8e591c60befc8caaf54db8c. Revert "[PATCH] mm: remove arch independent NODES_SPAN_OTHER_NODES" This reverts commit a94b3ab7eab4edcc9b2cb474b188f774c331adf7. Also update the comments to indicate that this is still required and where its used. Signed-off-by: Andy Whitcroft Cc: Paul Mackerras Cc: Mike Kravetz Cc: Benjamin Herrenschmidt Acked-by: Mel Gorman Acked-by: Will Schmidt Cc: Christoph Lameter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ebd425c2e2a7..f5fc45472d5c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1689,6 +1689,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, for (pfn = start_pfn; pfn < end_pfn; pfn++) { if (!early_pfn_valid(pfn)) continue; + if (!early_pfn_in_nid(pfn, nid)) + continue; page = pfn_to_page(pfn); set_page_links(page, zone, nid, pfn); init_page_count(page); -- cgit From 3bb1a852ab6c9cdf211a2f4a2f502340c8c38eca Mon Sep 17 00:00:00 2001 From: Martin Bligh Date: Sat, 28 Oct 2006 10:38:24 -0700 Subject: [PATCH] vmscan: Fix temp_priority race The temp_priority field in zone is racy, as we can walk through a reclaim path, and just before we copy it into prev_priority, it can be overwritten (say with DEF_PRIORITY) by another reclaimer. The same bug is contained in both try_to_free_pages and balance_pgdat, but it is fixed slightly differently. In balance_pgdat, we keep a separate priority record per zone in a local array. In try_to_free_pages there is no need to do this, as the priority level is the same for all zones that we reclaim from. Impact of this bug is that temp_priority is copied into prev_priority, and setting this artificially high causes reclaimers to set distress artificially low. They then fail to reclaim mapped pages, when they are, in fact, under severe memory pressure (their priority may be as low as 0). This causes the OOM killer to fire incorrectly. From: Andrew Morton __zone_reclaim() isn't modifying zone->prev_priority. But zone->prev_priority is used in the decision whether or not to bring mapped pages onto the inactive list. Hence there's a risk here that __zone_reclaim() will fail because zone->prev_priority ir large (ie: low urgency) and lots of mapped pages end up stuck on the active list. Fix that up by decreasing (ie making more urgent) zone->prev_priority as __zone_reclaim() scans the zone's pages. This bug perhaps explains why ZONE_RECLAIM_PRIORITY was created. It should be possible to remove that now, and to just start out at DEF_PRIORITY? Cc: Nick Piggin Cc: Christoph Lameter Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f5fc45472d5c..ecf853b5e30e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2407,7 +2407,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, zone->zone_pgdat = pgdat; zone->free_pages = 0; - zone->temp_priority = zone->prev_priority = DEF_PRIORITY; + zone->prev_priority = DEF_PRIORITY; zone_pcp_init(zone); INIT_LIST_HEAD(&zone->active_list); -- cgit From 0c6cb974636dd29681b03f8eb0ae227decab01fb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Sat, 28 Oct 2006 10:38:59 -0700 Subject: [PATCH] Calculation fix for memory holes beyong the end of physical memory absent_pages_in_range() made the assumption that users of the arch-independent zone-sizing API would not care about holes beyound the end of physical memory. This was not the case and was "fixed" in a patch called "Account for holes that are outside the range of physical memory". However, when given a range that started before a hole in "real" memory and ended beyond the end of memory, it would get the result wrong. The bug is in mainline but a patch is below. It has been tested successfully on a number of machines and architectures. Additional credit to Keith Mannthey for discovering the problem, helping identify the correct fix and confirming it Worked For Him. Signed-off-by: Mel Gorman Cc: keith mannthey Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ecf853b5e30e..b55bb358b832 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2261,7 +2261,7 @@ unsigned long __init __absent_pages_in_range(int nid, /* Account for ranges past physical memory on this node */ if (range_end_pfn > prev_end_pfn) - hole_pages = range_end_pfn - + hole_pages += range_end_pfn - max(range_start_pfn, prev_end_pfn); return hole_pages; -- cgit From 941c7105dc4f4961727acc518e18e00b9a03cbf3 Mon Sep 17 00:00:00 2001 From: nkalmala Date: Thu, 2 Nov 2006 22:07:04 -0800 Subject: [PATCH] mm: un-needed add-store operation wastes a few bytes Un-needed add-store operation wastes a few bytes. 8 bytes wasted with -O2, on a ppc. Signed-off-by: nkalmala Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b55bb358b832..bf2f6cff1d6a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -853,7 +853,7 @@ again: pcp = &zone_pcp(zone, cpu)->pcp[cold]; local_irq_save(flags); if (!pcp->count) { - pcp->count += rmqueue_bulk(zone, 0, + pcp->count = rmqueue_bulk(zone, 0, pcp->batch, &pcp->list); if (unlikely(!pcp->count)) goto failed; -- cgit