linux/mm/mempolicy.c

1939 lines
48 KiB
C
Raw Normal View History

/*
* Simple NUMA memory policy for the Linux kernel.
*
* Copyright 2003,2004 Andi Kleen, SuSE Labs.
* (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
* Subject to the GNU Public License, version 2.
*
* NUMA policy allows the user to give hints in which node(s) memory should
* be allocated.
*
* Support four policies per VMA and per process:
*
* The VMA policy has priority over the process policy for a page fault.
*
* interleave Allocate memory interleaved over a set of nodes,
* with normal fallback if it fails.
* For VMA based allocations this interleaves based on the
* offset into the backing object or offset into the mapping
* for anonymous memory. For process policy an process counter
* is used.
*
* bind Only allocate memory on a specific set of nodes,
* no fallback.
* FIXME: memory is allocated starting with the first node
* to the last. It would be better if bind would truly restrict
* the allocation to memory nodes instead
*
* preferred Try a specific node first before normal fallback.
* As a special case node -1 here means do the allocation
* on the local CPU. This is normally identical to default,
* but useful to set in a VMA when you have a non default
* process policy.
*
* default Allocate on the local node first, or when on a VMA
* use the process policy. This is what Linux always did
* in a NUMA aware kernel and still does by, ahem, default.
*
* The process policy is applied for most non interrupt memory allocations
* in that process' context. Interrupts ignore the policies and always
* try to allocate on the local CPU. The VMA policy is only applied for memory
* allocations for a VMA in the VM.
*
* Currently there are a few corner cases in swapping where the policy
* is not applied, but the majority should be handled. When process policy
* is used it is not remembered over swap outs/swap ins.
*
* Only the highest zone in the zone hierarchy gets policied. Allocations
* requesting a lower zone just use default policy. This implies that
* on systems with highmem kernel lowmem allocation don't get policied.
* Same with GFP_DMA allocations.
*
* For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between
* all users and remembered even when nobody has memory mapped.
*/
/* Notebook:
fix mmap readahead to honour policy and enable policy for any page cache
object
statistics for bigpages
global policy for page cache? currently it uses process policy. Requires
first item above.
handle mremap for shared memory (currently ignored for the policy)
grows down?
make bind policy root only? It can trigger oom much faster and the
kernel is not always grateful with that.
could replace all the switch()es with a mempolicy_ops structure.
*/
#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/nodemask.h>
#include <linux/cpuset.h>
#include <linux/gfp.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compat.h>
#include <linux/mempolicy.h>
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <linux/migrate.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
/* Internal flags */
#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */
#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2) /* Gather statistics */
static struct kmem_cache *policy_cache;
static struct kmem_cache *sn_cache;
/* Highest zone. An specific allocation for a zone below that is not
policied. */
[PATCH] optional ZONE_DMA: deal with cases of ZONE_DMA meaning the first zone This patchset follows up on the earlier work in Andrew's tree to reduce the number of zones. The patches allow to go to a minimum of 2 zones. This one allows also to make ZONE_DMA optional and therefore the number of zones can be reduced to one. ZONE_DMA is usually used for ISA DMA devices. There are a number of reasons why we would not want to have ZONE_DMA 1. Some arches do not need ZONE_DMA at all. 2. With the advent of IOMMUs DMA zones are no longer needed. The necessity of DMA zones may drastically be reduced in the future. This patchset allows a compilation of a kernel without that overhead. 3. Devices that require ISA DMA get rare these days. All my systems do not have any need for ISA DMA. 4. The presence of an additional zone unecessarily complicates VM operations because it must be scanned and balancing logic must operate on its. 5. With only ZONE_NORMAL one can reach the situation where we have only one zone. This will allow the unrolling of many loops in the VM and allows the optimization of varous code paths in the VM. 6. Having only a single zone in a NUMA system results in a 1-1 correspondence between nodes and zones. Various additional optimizations to critical VM paths become possible. Many systems today can operate just fine with a single zone. If you look at what is in ZONE_DMA then one usually sees that nothing uses it. The DMA slabs are empty (Some arches use ZONE_DMA instead of ZONE_NORMAL, then ZONE_NORMAL will be empty instead). On all of my systems (i386, x86_64, ia64) ZONE_DMA is completely empty. Why constantly look at an empty zone in /proc/zoneinfo and empty slab in /proc/slabinfo? Non i386 also frequently have no need for ZONE_DMA and zones stay empty. The patchset was tested on i386 (UP / SMP), x86_64 (UP, NUMA) and ia64 (NUMA). The RFC posted earlier (see http://marc.theaimsgroup.com/?l=linux-kernel&m=115231723513008&w=2) had lots of #ifdefs in them. An effort has been made to minize the number of #ifdefs and make this as compact as possible. The job was made much easier by the ongoing efforts of others to extract common arch specific functionality. I have been running this for awhile now on my desktop and finally Linux is using all my available RAM instead of leaving the 16MB in ZONE_DMA untouched: christoph@pentium940:~$ cat /proc/zoneinfo Node 0, zone Normal pages free 4435 min 1448 low 1810 high 2172 active 241786 inactive 210170 scanned 0 (a: 0 i: 0) spanned 524224 present 524224 nr_anon_pages 61680 nr_mapped 14271 nr_file_pages 390264 nr_slab_reclaimable 27564 nr_slab_unreclaimable 1793 nr_page_table_pages 449 nr_dirty 39 nr_writeback 0 nr_unstable 0 nr_bounce 0 cpu: 0 pcp: 0 count: 156 high: 186 batch: 31 cpu: 0 pcp: 1 count: 9 high: 62 batch: 15 vm stats threshold: 20 cpu: 1 pcp: 0 count: 177 high: 186 batch: 31 cpu: 1 pcp: 1 count: 12 high: 62 batch: 15 vm stats threshold: 20 all_unreclaimable: 0 prev_priority: 12 temp_priority: 12 start_pfn: 0 This patch: In two places in the VM we use ZONE_DMA to refer to the first zone. If ZONE_DMA is optional then other zones may be first. So simply replace ZONE_DMA with zone 0. This also fixes ZONETABLE_PGSHIFT. If we have only a single zone then ZONES_PGSHIFT may become 0 because there is no need anymore to encode the zone number related to a pgdat. However, we still need a zonetable to index all the zones for each node if this is a NUMA system. Therefore define ZONETABLE_SHIFT unconditionally as the offset of the ZONE field in page flags. [apw@shadowen.org: fix mismerge] Acked-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Matthew Wilcox <willy@debian.org> Cc: James Bottomley <James.Bottomley@steeleye.com> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-02-10 17:43:07 +08:00
enum zone_type policy_zone = 0;
struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
.policy = MPOL_DEFAULT,
};
/* Do sanity checking on a policy */
static int mpol_check_policy(int mode, nodemask_t *nodes)
{
int empty = nodes_empty(*nodes);
switch (mode) {
case MPOL_DEFAULT:
if (!empty)
return -EINVAL;
break;
case MPOL_BIND:
case MPOL_INTERLEAVE:
/* Preferred will only use the first bit, but allow
more for now. */
if (empty)
return -EINVAL;
break;
}
return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL;
}
/* Generate a custom zonelist for the BIND policy. */
static struct zonelist *bind_zonelist(nodemask_t *nodes)
{
struct zonelist *zl;
int num, max, nd;
enum zone_type k;
max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
[PATCH] memory page_alloc zonelist caching speedup Optimize the critical zonelist scanning for free pages in the kernel memory allocator by caching the zones that were found to be full recently, and skipping them. Remembers the zones in a zonelist that were short of free memory in the last second. And it stashes a zone-to-node table in the zonelist struct, to optimize that conversion (minimize its cache footprint.) Recent changes: This differs in a significant way from a similar patch that I posted a week ago. Now, instead of having a nodemask_t of recently full nodes, I have a bitmask of recently full zones. This solves a problem that last weeks patch had, which on systems with multiple zones per node (such as DMA zone) would take seeing any of these zones full as meaning that all zones on that node were full. Also I changed names - from "zonelist faster" to "zonelist cache", as that seemed to better convey what we're doing here - caching some of the key zonelist state (for faster access.) See below for some performance benchmark results. After all that discussion with David on why I didn't need them, I went and got some ;). I wanted to verify that I had not hurt the normal case of memory allocation noticeably. At least for my one little microbenchmark, I found (1) the normal case wasn't affected, and (2) workloads that forced scanning across multiple nodes for memory improved up to 10% fewer System CPU cycles and lower elapsed clock time ('sys' and 'real'). Good. See details, below. I didn't have the logic in get_page_from_freelist() for various full nodes and zone reclaim failures correct. That should be fixed up now - notice the new goto labels zonelist_scan, this_zone_full, and try_next_zone, in get_page_from_freelist(). There are two reasons I persued this alternative, over some earlier proposals that would have focused on optimizing the fake numa emulation case by caching the last useful zone: 1) Contrary to what I said before, we (SGI, on large ia64 sn2 systems) have seen real customer loads where the cost to scan the zonelist was a problem, due to many nodes being full of memory before we got to a node we could use. Or at least, I think we have. This was related to me by another engineer, based on experiences from some time past. So this is not guaranteed. Most likely, though. The following approach should help such real numa systems just as much as it helps fake numa systems, or any combination thereof. 2) The effort to distinguish fake from real numa, using node_distance, so that we could cache a fake numa node and optimize choosing it over equivalent distance fake nodes, while continuing to properly scan all real nodes in distance order, was going to require a nasty blob of zonelist and node distance munging. The following approach has no new dependency on node distances or zone sorting. See comment in the patch below for a description of what it actually does. Technical details of note (or controversy): - See the use of "zlc_active" and "did_zlc_setup" below, to delay adding any work for this new mechanism until we've looked at the first zone in zonelist. I figured the odds of the first zone having the memory we needed were high enough that we should just look there, first, then get fancy only if we need to keep looking. - Some odd hackery was needed to add items to struct zonelist, while not tripping up the custom zonelists built by the mm/mempolicy.c code for MPOL_BIND. My usual wordy comments below explain this. Search for "MPOL_BIND". - Some per-node data in the struct zonelist is now modified frequently, with no locking. Multiple CPU cores on a node could hit and mangle this data. The theory is that this is just performance hint data, and the memory allocator will work just fine despite any such mangling. The fields at risk are the struct 'zonelist_cache' fields 'fullzones' (a bitmask) and 'last_full_zap' (unsigned long jiffies). It should all be self correcting after at most a one second delay. - This still does a linear scan of the same lengths as before. All I've optimized is making the scan faster, not algorithmically shorter. It is now able to scan a compact array of 'unsigned short' in the case of many full nodes, so one cache line should cover quite a few nodes, rather than each node hitting another one or two new and distinct cache lines. - If both Andi and Nick don't find this too complicated, I will be (pleasantly) flabbergasted. - I removed the comment claiming we only use one cachline's worth of zonelist. We seem, at least in the fake numa case, to have put the lie to that claim. - I pay no attention to the various watermarks and such in this performance hint. A node could be marked full for one watermark, and then skipped over when searching for a page using a different watermark. I think that's actually quite ok, as it will tend to slightly increase the spreading of memory over other nodes, away from a memory stressed node. =============== Performance - some benchmark results and analysis: This benchmark runs a memory hog program that uses multiple threads to touch alot of memory as quickly as it can. Multiple runs were made, touching 12, 38, 64 or 90 GBytes out of the total 96 GBytes on the system, and using 1, 19, 37, or 55 threads (on a 56 CPU system.) System, user and real (elapsed) timings were recorded for each run, shown in units of seconds, in the table below. Two kernels were tested - 2.6.18-mm3 and the same kernel with this zonelist caching patch added. The table also shows the percentage improvement the zonelist caching sys time is over (lower than) the stock *-mm kernel. number 2.6.18-mm3 zonelist-cache delta (< 0 good) percent GBs N ------------ -------------- ---------------- systime mem threads sys user real sys user real sys user real better 12 1 153 24 177 151 24 176 -2 0 -1 1% 12 19 99 22 8 99 22 8 0 0 0 0% 12 37 111 25 6 112 25 6 1 0 0 -0% 12 55 115 25 5 110 23 5 -5 -2 0 4% 38 1 502 74 576 497 73 570 -5 -1 -6 0% 38 19 426 78 48 373 76 39 -53 -2 -9 12% 38 37 544 83 36 547 82 36 3 -1 0 -0% 38 55 501 77 23 511 80 24 10 3 1 -1% 64 1 917 125 1042 890 124 1014 -27 -1 -28 2% 64 19 1118 138 119 965 141 103 -153 3 -16 13% 64 37 1202 151 94 1136 150 81 -66 -1 -13 5% 64 55 1118 141 61 1072 140 58 -46 -1 -3 4% 90 1 1342 177 1519 1275 174 1450 -67 -3 -69 4% 90 19 2392 199 192 2116 189 176 -276 -10 -16 11% 90 37 3313 238 175 2972 225 145 -341 -13 -30 10% 90 55 1948 210 104 1843 213 100 -105 3 -4 5% Notes: 1) This test ran a memory hog program that started a specified number N of threads, and had each thread allocate and touch 1/N'th of the total memory to be used in the test run in a single loop, writing a constant word to memory, one store every 4096 bytes. Watching this test during some earlier trial runs, I would see each of these threads sit down on one CPU and stay there, for the remainder of the pass, a different CPU for each thread. 2) The 'real' column is not comparable to the 'sys' or 'user' columns. The 'real' column is seconds wall clock time elapsed, from beginning to end of that test pass. The 'sys' and 'user' columns are total CPU seconds spent on that test pass. For a 19 thread test run, for example, the sum of 'sys' and 'user' could be up to 19 times the number of 'real' elapsed wall clock seconds. 3) Tests were run on a fresh, single-user boot, to minimize the amount of memory already in use at the start of the test, and to minimize the amount of background activity that might interfere. 4) Tests were done on a 56 CPU, 28 Node system with 96 GBytes of RAM. 5) Notice that the 'real' time gets large for the single thread runs, even though the measured 'sys' and 'user' times are modest. I'm not sure what that means - probably something to do with it being slow for one thread to be accessing memory along ways away. Perhaps the fake numa system, running ostensibly the same workload, would not show this substantial degradation of 'real' time for one thread on many nodes -- lets hope not. 6) The high thread count passes (one thread per CPU - on 55 of 56 CPUs) ran quite efficiently, as one might expect. Each pair of threads needed to allocate and touch the memory on the node the two threads shared, a pleasantly parallizable workload. 7) The intermediate thread count passes, when asking for alot of memory forcing them to go to a few neighboring nodes, improved the most with this zonelist caching patch. Conclusions: * This zonelist cache patch probably makes little difference one way or the other for most workloads on real numa hardware, if those workloads avoid heavy off node allocations. * For memory intensive workloads requiring substantial off-node allocations on real numa hardware, this patch improves both kernel and elapsed timings up to ten per-cent. * For fake numa systems, I'm optimistic, but will have to leave that up to Rohit Seth to actually test (once I get him a 2.6.18 backport.) Signed-off-by: Paul Jackson <pj@sgi.com> Cc: Rohit Seth <rohitseth@google.com> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: David Rientjes <rientjes@cs.washington.edu> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 12:31:48 +08:00
max++; /* space for zlcache_ptr (see mmzone.h) */
zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL);
if (!zl)
return ERR_PTR(-ENOMEM);
[PATCH] memory page_alloc zonelist caching speedup Optimize the critical zonelist scanning for free pages in the kernel memory allocator by caching the zones that were found to be full recently, and skipping them. Remembers the zones in a zonelist that were short of free memory in the last second. And it stashes a zone-to-node table in the zonelist struct, to optimize that conversion (minimize its cache footprint.) Recent changes: This differs in a significant way from a similar patch that I posted a week ago. Now, instead of having a nodemask_t of recently full nodes, I have a bitmask of recently full zones. This solves a problem that last weeks patch had, which on systems with multiple zones per node (such as DMA zone) would take seeing any of these zones full as meaning that all zones on that node were full. Also I changed names - from "zonelist faster" to "zonelist cache", as that seemed to better convey what we're doing here - caching some of the key zonelist state (for faster access.) See below for some performance benchmark results. After all that discussion with David on why I didn't need them, I went and got some ;). I wanted to verify that I had not hurt the normal case of memory allocation noticeably. At least for my one little microbenchmark, I found (1) the normal case wasn't affected, and (2) workloads that forced scanning across multiple nodes for memory improved up to 10% fewer System CPU cycles and lower elapsed clock time ('sys' and 'real'). Good. See details, below. I didn't have the logic in get_page_from_freelist() for various full nodes and zone reclaim failures correct. That should be fixed up now - notice the new goto labels zonelist_scan, this_zone_full, and try_next_zone, in get_page_from_freelist(). There are two reasons I persued this alternative, over some earlier proposals that would have focused on optimizing the fake numa emulation case by caching the last useful zone: 1) Contrary to what I said before, we (SGI, on large ia64 sn2 systems) have seen real customer loads where the cost to scan the zonelist was a problem, due to many nodes being full of memory before we got to a node we could use. Or at least, I think we have. This was related to me by another engineer, based on experiences from some time past. So this is not guaranteed. Most likely, though. The following approach should help such real numa systems just as much as it helps fake numa systems, or any combination thereof. 2) The effort to distinguish fake from real numa, using node_distance, so that we could cache a fake numa node and optimize choosing it over equivalent distance fake nodes, while continuing to properly scan all real nodes in distance order, was going to require a nasty blob of zonelist and node distance munging. The following approach has no new dependency on node distances or zone sorting. See comment in the patch below for a description of what it actually does. Technical details of note (or controversy): - See the use of "zlc_active" and "did_zlc_setup" below, to delay adding any work for this new mechanism until we've looked at the first zone in zonelist. I figured the odds of the first zone having the memory we needed were high enough that we should just look there, first, then get fancy only if we need to keep looking. - Some odd hackery was needed to add items to struct zonelist, while not tripping up the custom zonelists built by the mm/mempolicy.c code for MPOL_BIND. My usual wordy comments below explain this. Search for "MPOL_BIND". - Some per-node data in the struct zonelist is now modified frequently, with no locking. Multiple CPU cores on a node could hit and mangle this data. The theory is that this is just performance hint data, and the memory allocator will work just fine despite any such mangling. The fields at risk are the struct 'zonelist_cache' fields 'fullzones' (a bitmask) and 'last_full_zap' (unsigned long jiffies). It should all be self correcting after at most a one second delay. - This still does a linear scan of the same lengths as before. All I've optimized is making the scan faster, not algorithmically shorter. It is now able to scan a compact array of 'unsigned short' in the case of many full nodes, so one cache line should cover quite a few nodes, rather than each node hitting another one or two new and distinct cache lines. - If both Andi and Nick don't find this too complicated, I will be (pleasantly) flabbergasted. - I removed the comment claiming we only use one cachline's worth of zonelist. We seem, at least in the fake numa case, to have put the lie to that claim. - I pay no attention to the various watermarks and such in this performance hint. A node could be marked full for one watermark, and then skipped over when searching for a page using a different watermark. I think that's actually quite ok, as it will tend to slightly increase the spreading of memory over other nodes, away from a memory stressed node. =============== Performance - some benchmark results and analysis: This benchmark runs a memory hog program that uses multiple threads to touch alot of memory as quickly as it can. Multiple runs were made, touching 12, 38, 64 or 90 GBytes out of the total 96 GBytes on the system, and using 1, 19, 37, or 55 threads (on a 56 CPU system.) System, user and real (elapsed) timings were recorded for each run, shown in units of seconds, in the table below. Two kernels were tested - 2.6.18-mm3 and the same kernel with this zonelist caching patch added. The table also shows the percentage improvement the zonelist caching sys time is over (lower than) the stock *-mm kernel. number 2.6.18-mm3 zonelist-cache delta (< 0 good) percent GBs N ------------ -------------- ---------------- systime mem threads sys user real sys user real sys user real better 12 1 153 24 177 151 24 176 -2 0 -1 1% 12 19 99 22 8 99 22 8 0 0 0 0% 12 37 111 25 6 112 25 6 1 0 0 -0% 12 55 115 25 5 110 23 5 -5 -2 0 4% 38 1 502 74 576 497 73 570 -5 -1 -6 0% 38 19 426 78 48 373 76 39 -53 -2 -9 12% 38 37 544 83 36 547 82 36 3 -1 0 -0% 38 55 501 77 23 511 80 24 10 3 1 -1% 64 1 917 125 1042 890 124 1014 -27 -1 -28 2% 64 19 1118 138 119 965 141 103 -153 3 -16 13% 64 37 1202 151 94 1136 150 81 -66 -1 -13 5% 64 55 1118 141 61 1072 140 58 -46 -1 -3 4% 90 1 1342 177 1519 1275 174 1450 -67 -3 -69 4% 90 19 2392 199 192 2116 189 176 -276 -10 -16 11% 90 37 3313 238 175 2972 225 145 -341 -13 -30 10% 90 55 1948 210 104 1843 213 100 -105 3 -4 5% Notes: 1) This test ran a memory hog program that started a specified number N of threads, and had each thread allocate and touch 1/N'th of the total memory to be used in the test run in a single loop, writing a constant word to memory, one store every 4096 bytes. Watching this test during some earlier trial runs, I would see each of these threads sit down on one CPU and stay there, for the remainder of the pass, a different CPU for each thread. 2) The 'real' column is not comparable to the 'sys' or 'user' columns. The 'real' column is seconds wall clock time elapsed, from beginning to end of that test pass. The 'sys' and 'user' columns are total CPU seconds spent on that test pass. For a 19 thread test run, for example, the sum of 'sys' and 'user' could be up to 19 times the number of 'real' elapsed wall clock seconds. 3) Tests were run on a fresh, single-user boot, to minimize the amount of memory already in use at the start of the test, and to minimize the amount of background activity that might interfere. 4) Tests were done on a 56 CPU, 28 Node system with 96 GBytes of RAM. 5) Notice that the 'real' time gets large for the single thread runs, even though the measured 'sys' and 'user' times are modest. I'm not sure what that means - probably something to do with it being slow for one thread to be accessing memory along ways away. Perhaps the fake numa system, running ostensibly the same workload, would not show this substantial degradation of 'real' time for one thread on many nodes -- lets hope not. 6) The high thread count passes (one thread per CPU - on 55 of 56 CPUs) ran quite efficiently, as one might expect. Each pair of threads needed to allocate and touch the memory on the node the two threads shared, a pleasantly parallizable workload. 7) The intermediate thread count passes, when asking for alot of memory forcing them to go to a few neighboring nodes, improved the most with this zonelist caching patch. Conclusions: * This zonelist cache patch probably makes little difference one way or the other for most workloads on real numa hardware, if those workloads avoid heavy off node allocations. * For memory intensive workloads requiring substantial off-node allocations on real numa hardware, this patch improves both kernel and elapsed timings up to ten per-cent. * For fake numa systems, I'm optimistic, but will have to leave that up to Rohit Seth to actually test (once I get him a 2.6.18 backport.) Signed-off-by: Paul Jackson <pj@sgi.com> Cc: Rohit Seth <rohitseth@google.com> Cc: Christoph Lameter <clameter@engr.sgi.com> Cc: David Rientjes <rientjes@cs.washington.edu> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 12:31:48 +08:00
zl->zlcache_ptr = NULL;
num = 0;
/* First put in the highest zones from all nodes, then all the next
lower zones etc. Avoid empty zones because the memory allocator
doesn't like them. If you implement node hot removal you
have to fix that. */
Apply memory policies to top two highest zones when highest zone is ZONE_MOVABLE The NUMA layer only supports NUMA policies for the highest zone. When ZONE_MOVABLE is configured with kernelcore=, the the highest zone becomes ZONE_MOVABLE. The result is that policies are only applied to allocations like anonymous pages and page cache allocated from ZONE_MOVABLE when the zone is used. This patch applies policies to the two highest zones when the highest zone is ZONE_MOVABLE. As ZONE_MOVABLE consists of pages from the highest "real" zone, it's always functionally equivalent. The patch has been tested on a variety of machines both NUMA and non-NUMA covering x86, x86_64 and ppc64. No abnormal results were seen in kernbench, tbench, dbench or hackbench. It passes regression tests from the numactl package with and without kernelcore= once numactl tests are patched to wait for vmstat counters to update. akpm: this is the nasty hack to fix NUMA mempolicies in the presence of ZONE_MOVABLE and kernelcore= in 2.6.23. Christoph says "For .24 either merge the mobility or get the other solution that Mel is working on. That solution would only use a single zonelist per node and filter on the fly. That may help performance and also help to make memory policies work better." Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Tested-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Acked-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@suse.de> Cc: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-08-23 05:02:05 +08:00
k = MAX_NR_ZONES - 1;
while (1) {
for_each_node_mask(nd, *nodes) {
struct zone *z = &NODE_DATA(nd)->node_zones[k];
if (z->present_pages > 0)
zl->zones[num++] = z;
}
if (k == 0)
break;
k--;
}
if (num == 0) {
kfree(zl);
return ERR_PTR(-EINVAL);
}
zl->zones[num] = NULL;
return zl;
}
/* Create a new policy */
static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
{
struct mempolicy *policy;
pr_debug("setting mode %d nodes[0] %lx\n",
mode, nodes ? nodes_addr(*nodes)[0] : -1);
if (mode == MPOL_DEFAULT)
return NULL;
policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!policy)
return ERR_PTR(-ENOMEM);
atomic_set(&policy->refcnt, 1);
switch (mode) {
case MPOL_INTERLEAVE:
policy->v.nodes = *nodes;
if (nodes_weight(*nodes) == 0) {
kmem_cache_free(policy_cache, policy);
return ERR_PTR(-EINVAL);
}
break;
case MPOL_PREFERRED:
policy->v.preferred_node = first_node(*nodes);
if (policy->v.preferred_node >= MAX_NUMNODES)
policy->v.preferred_node = -1;
break;
case MPOL_BIND:
policy->v.zonelist = bind_zonelist(nodes);
if (IS_ERR(policy->v.zonelist)) {
void *error_code = policy->v.zonelist;
kmem_cache_free(policy_cache, policy);
return error_code;
}
break;
}
policy->policy = mode;
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
return policy;
}
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
static void gather_stats(struct page *, void *, int pte_dirty);
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags);
/* Scan through pages checking if pages follow certain conditions. */
2005-10-30 09:16:12 +08:00
static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
{
pte_t *orig_pte;
pte_t *pte;
spinlock_t *ptl;
orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
do {
struct page *page;
int nid;
if (!pte_present(*pte))
continue;
page = vm_normal_page(vma, addr, *pte);
if (!page)
continue;
/*
* The check for PageReserved here is important to avoid
* handling zero pages and other pages that may have been
* marked special by the system.
*
* If the PageReserved would not be checked here then f.e.
* the location of the zero page could have an influence
* on MPOL_MF_STRICT, zero pages would be counted for
* the per node stats, and there would be useless attempts
* to put zero pages on the migration list.
*/
if (PageReserved(page))
continue;
nid = page_to_nid(page);
if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
continue;
if (flags & MPOL_MF_STATS)
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
gather_stats(page, private, pte_dirty(*pte));
else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
migrate_page_add(page, private, flags);
else
break;
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap_unlock(orig_pte, ptl);
return addr != end;
}
2005-10-30 09:16:12 +08:00
static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
{
pmd_t *pmd;
unsigned long next;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
if (check_pte_range(vma, pmd, addr, next, nodes,
flags, private))
return -EIO;
} while (pmd++, addr = next, addr != end);
return 0;
}
2005-10-30 09:16:12 +08:00
static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
{
pud_t *pud;
unsigned long next;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
if (check_pmd_range(vma, pud, addr, next, nodes,
flags, private))
return -EIO;
} while (pud++, addr = next, addr != end);
return 0;
}
2005-10-30 09:16:12 +08:00
static inline int check_pgd_range(struct vm_area_struct *vma,
unsigned long addr, unsigned long end,
const nodemask_t *nodes, unsigned long flags,
void *private)
{
pgd_t *pgd;
unsigned long next;
2005-10-30 09:16:12 +08:00
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
if (check_pud_range(vma, pgd, addr, next, nodes,
flags, private))
return -EIO;
} while (pgd++, addr = next, addr != end);
return 0;
}
/*
* Check if all pages in a range are on a set of nodes.
* If pagelist != NULL then isolate pages from the LRU and
* put them on the pagelist.
*/
static struct vm_area_struct *
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
const nodemask_t *nodes, unsigned long flags, void *private)
{
int err;
struct vm_area_struct *first, *vma, *prev;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
err = migrate_prep();
if (err)
return ERR_PTR(err);
}
first = find_vma(mm, start);
if (!first)
return ERR_PTR(-EFAULT);
prev = NULL;
for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
if (!(flags & MPOL_MF_DISCONTIG_OK)) {
if (!vma->vm_next && vma->vm_end < end)
return ERR_PTR(-EFAULT);
if (prev && prev->vm_end < vma->vm_start)
return ERR_PTR(-EFAULT);
}
if (!is_vm_hugetlb_page(vma) &&
((flags & MPOL_MF_STRICT) ||
((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
vma_migratable(vma)))) {
unsigned long endvma = vma->vm_end;
if (endvma > end)
endvma = end;
if (vma->vm_start > start)
start = vma->vm_start;
err = check_pgd_range(vma, start, endvma, nodes,
flags, private);
if (err) {
first = ERR_PTR(err);
break;
}
}
prev = vma;
}
return first;
}
/* Apply policy to a single VMA */
static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
{
int err = 0;
struct mempolicy *old = vma->vm_policy;
pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
vma->vm_start, vma->vm_end, vma->vm_pgoff,
vma->vm_ops, vma->vm_file,
vma->vm_ops ? vma->vm_ops->set_policy : NULL);
if (vma->vm_ops && vma->vm_ops->set_policy)
err = vma->vm_ops->set_policy(vma, new);
if (!err) {
mpol_get(new);
vma->vm_policy = new;
mpol_free(old);
}
return err;
}
/* Step 2: apply policy to a range and do splits. */
static int mbind_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct mempolicy *new)
{
struct vm_area_struct *next;
int err;
err = 0;
for (; vma && vma->vm_start < end; vma = next) {
next = vma->vm_next;
if (vma->vm_start < start)
err = split_vma(vma->vm_mm, vma, start, 1);
if (!err && vma->vm_end > end)
err = split_vma(vma->vm_mm, vma, end, 0);
if (!err)
err = policy_vma(vma, new);
if (err)
break;
}
return err;
}
static int contextualize_policy(int mode, nodemask_t *nodes)
{
if (!nodes)
return 0;
cpuset_update_task_memory_state();
if (!cpuset_nodes_subset_current_mems_allowed(*nodes))
return -EINVAL;
return mpol_check_policy(mode, nodes);
}
/*
* Update task->flags PF_MEMPOLICY bit: set iff non-default
* mempolicy. Allows more rapid checking of this (combined perhaps
* with other PF_* flag bits) on memory allocation hot code paths.
*
* If called from outside this file, the task 'p' should -only- be
* a newly forked child not yet visible on the task list, because
* manipulating the task flags of a visible task is not safe.
*
* The above limitation is why this routine has the funny name
* mpol_fix_fork_child_flag().
*
* It is also safe to call this with a task pointer of current,
* which the static wrapper mpol_set_task_struct_flag() does,
* for use within this file.
*/
void mpol_fix_fork_child_flag(struct task_struct *p)
{
if (p->mempolicy)
p->flags |= PF_MEMPOLICY;
else
p->flags &= ~PF_MEMPOLICY;
}
static void mpol_set_task_struct_flag(void)
{
mpol_fix_fork_child_flag(current);
}
/* Set the process memory policy */
long do_set_mempolicy(int mode, nodemask_t *nodes)
{
struct mempolicy *new;
if (contextualize_policy(mode, nodes))
return -EINVAL;
new = mpol_new(mode, nodes);
if (IS_ERR(new))
return PTR_ERR(new);
mpol_free(current->mempolicy);
current->mempolicy = new;
mpol_set_task_struct_flag();
if (new && new->policy == MPOL_INTERLEAVE)
current->il_next = first_node(new->v.nodes);
return 0;
}
/* Fill a zone bitmap for a policy */
static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
{
int i;
nodes_clear(*nodes);
switch (p->policy) {
case MPOL_BIND:
for (i = 0; p->v.zonelist->zones[i]; i++)
node_set(zone_to_nid(p->v.zonelist->zones[i]),
*nodes);
break;
case MPOL_DEFAULT:
break;
case MPOL_INTERLEAVE:
*nodes = p->v.nodes;
break;
case MPOL_PREFERRED:
/* or use current node instead of online map? */
if (p->v.preferred_node < 0)
*nodes = node_online_map;
else
node_set(p->v.preferred_node, *nodes);
break;
default:
BUG();
}
}
static int lookup_node(struct mm_struct *mm, unsigned long addr)
{
struct page *p;
int err;
err = get_user_pages(current, mm, addr & PAGE_MASK, 1, 0, 0, &p, NULL);
if (err >= 0) {
err = page_to_nid(p);
put_page(p);
}
return err;
}
/* Retrieve NUMA policy */
long do_get_mempolicy(int *policy, nodemask_t *nmask,
unsigned long addr, unsigned long flags)
{
int err;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = NULL;
struct mempolicy *pol = current->mempolicy;
cpuset_update_task_memory_state();
if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
return -EINVAL;
if (flags & MPOL_F_ADDR) {
down_read(&mm->mmap_sem);
vma = find_vma_intersection(mm, addr, addr+1);
if (!vma) {
up_read(&mm->mmap_sem);
return -EFAULT;
}
if (vma->vm_ops && vma->vm_ops->get_policy)
pol = vma->vm_ops->get_policy(vma, addr);
else
pol = vma->vm_policy;
} else if (addr)
return -EINVAL;
if (!pol)
pol = &default_policy;
if (flags & MPOL_F_NODE) {
if (flags & MPOL_F_ADDR) {
err = lookup_node(mm, addr);
if (err < 0)
goto out;
*policy = err;
} else if (pol == current->mempolicy &&
pol->policy == MPOL_INTERLEAVE) {
*policy = current->il_next;
} else {
err = -EINVAL;
goto out;
}
} else
*policy = pol->policy;
if (vma) {
up_read(&current->mm->mmap_sem);
vma = NULL;
}
err = 0;
if (nmask)
get_zonemask(pol, nmask);
out:
if (vma)
up_read(&current->mm->mmap_sem);
return err;
}
#ifdef CONFIG_MIGRATION
/*
* page migration
*/
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
/*
* Avoid migrating a page that is shared with others.
*/
if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1)
isolate_lru_page(page, pagelist);
}
[PATCH] page migration: sys_move_pages(): support moving of individual pages move_pages() is used to move individual pages of a process. The function can be used to determine the location of pages and to move them onto the desired node. move_pages() returns status information for each page. long move_pages(pid, number_of_pages_to_move, addresses_of_pages[], nodes[] or NULL, status[], flags); The addresses of pages is an array of void * pointing to the pages to be moved. The nodes array contains the node numbers that the pages should be moved to. If a NULL is passed instead of an array then no pages are moved but the status array is updated. The status request may be used to determine the page state before issuing another move_pages() to move pages. The status array will contain the state of all individual page migration attempts when the function terminates. The status array is only valid if move_pages() completed successfullly. Possible page states in status[]: 0..MAX_NUMNODES The page is now on the indicated node. -ENOENT Page is not present -EACCES Page is mapped by multiple processes and can only be moved if MPOL_MF_MOVE_ALL is specified. -EPERM The page has been mlocked by a process/driver and cannot be moved. -EBUSY Page is busy and cannot be moved. Try again later. -EFAULT Invalid address (no VMA or zero page). -ENOMEM Unable to allocate memory on target node. -EIO Unable to write back page. The page must be written back in order to move it since the page is dirty and the filesystem does not provide a migration function that would allow the moving of dirty pages. -EINVAL A dirty page cannot be moved. The filesystem does not provide a migration function and has no ability to write back pages. The flags parameter indicates what types of pages to move: MPOL_MF_MOVE Move pages that are only mapped by the process. MPOL_MF_MOVE_ALL Also move pages that are mapped by multiple processes. Requires sufficient capabilities. Possible return codes from move_pages() -ENOENT No pages found that would require moving. All pages are either already on the target node, not present, had an invalid address or could not be moved because they were mapped by multiple processes. -EINVAL Flags other than MPOL_MF_MOVE(_ALL) specified or an attempt to migrate pages in a kernel thread. -EPERM MPOL_MF_MOVE_ALL specified without sufficient priviledges. or an attempt to move a process belonging to another user. -EACCES One of the target nodes is not allowed by the current cpuset. -ENODEV One of the target nodes is not online. -ESRCH Process does not exist. -E2BIG Too many pages to move. -ENOMEM Not enough memory to allocate control array. -EFAULT Parameters could not be accessed. A test program for move_pages() may be found with the patches on ftp.kernel.org:/pub/linux/kernel/people/christoph/pmig/patches-2.6.17-rc4-mm3 From: Christoph Lameter <clameter@sgi.com> Detailed results for sys_move_pages() Pass a pointer to an integer to get_new_page() that may be used to indicate where the completion status of a migration operation should be placed. This allows sys_move_pags() to report back exactly what happened to each page. Wish there would be a better way to do this. Looks a bit hacky. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Jes Sorensen <jes@trained-monkey.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Andi Kleen <ak@muc.de> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:55 +08:00
static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:05 +08:00
return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
}
/*
* Migrate pages from one node to a target node.
* Returns error or the number of pages not migrated.
*/
int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags)
{
nodemask_t nmask;
LIST_HEAD(pagelist);
int err = 0;
nodes_clear(nmask);
node_set(source, nmask);
check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask,
flags | MPOL_MF_DISCONTIG_OK, &pagelist);
if (!list_empty(&pagelist))
err = migrate_pages(&pagelist, new_node_page, dest);
return err;
}
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
/*
* Move pages between the two nodesets so as to preserve the physical
* layout as much as possible.
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
*
* Returns the number of page that could not be moved.
*/
int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
LIST_HEAD(pagelist);
int busy = 0;
int err = 0;
nodemask_t tmp;
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
down_read(&mm->mmap_sem);
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
err = migrate_vmas(mm, from_nodes, to_nodes, flags);
if (err)
goto out;
/*
* Find a 'source' bit set in 'tmp' whose corresponding 'dest'
* bit in 'to' is not also set in 'tmp'. Clear the found 'source'
* bit in 'tmp', and return that <source, dest> pair for migration.
* The pair of nodemasks 'to' and 'from' define the map.
*
* If no pair of bits is found that way, fallback to picking some
* pair of 'source' and 'dest' bits that are not the same. If the
* 'source' and 'dest' bits are the same, this represents a node
* that will be migrating to itself, so no pages need move.
*
* If no bits are left in 'tmp', or if all remaining bits left
* in 'tmp' correspond to the same bit in 'to', return false
* (nothing left to migrate).
*
* This lets us pick a pair of nodes to migrate between, such that
* if possible the dest node is not already occupied by some other
* source node, minimizing the risk of overloading the memory on a
* node that would happen if we migrated incoming memory to a node
* before migrating outgoing memory source that same node.
*
* A single scan of tmp is sufficient. As we go, we remember the
* most recent <s, d> pair that moved (s != d). If we find a pair
* that not only moved, but what's better, moved to an empty slot
* (d is not set in tmp), then we break out then, with that pair.
* Otherwise when we finish scannng from_tmp, we at least have the
* most recent <s, d> pair that moved. If we get all the way through
* the scan of tmp without finding any node that moved, much less
* moved to an empty node, then there is nothing left worth migrating.
*/
tmp = *from_nodes;
while (!nodes_empty(tmp)) {
int s,d;
int source = -1;
int dest = 0;
for_each_node_mask(s, tmp) {
d = node_remap(s, *from_nodes, *to_nodes);
if (s == d)
continue;
source = s; /* Node moved. Memorize */
dest = d;
/* dest not in remaining from nodes? */
if (!node_isset(dest, tmp))
break;
}
if (source == -1)
break;
node_clear(source, tmp);
err = migrate_to_node(mm, source, dest, flags);
if (err > 0)
busy += err;
if (err < 0)
break;
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
}
out:
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
up_read(&mm->mmap_sem);
if (err < 0)
return err;
return busy;
}
[PATCH] page migration: sys_move_pages(): support moving of individual pages move_pages() is used to move individual pages of a process. The function can be used to determine the location of pages and to move them onto the desired node. move_pages() returns status information for each page. long move_pages(pid, number_of_pages_to_move, addresses_of_pages[], nodes[] or NULL, status[], flags); The addresses of pages is an array of void * pointing to the pages to be moved. The nodes array contains the node numbers that the pages should be moved to. If a NULL is passed instead of an array then no pages are moved but the status array is updated. The status request may be used to determine the page state before issuing another move_pages() to move pages. The status array will contain the state of all individual page migration attempts when the function terminates. The status array is only valid if move_pages() completed successfullly. Possible page states in status[]: 0..MAX_NUMNODES The page is now on the indicated node. -ENOENT Page is not present -EACCES Page is mapped by multiple processes and can only be moved if MPOL_MF_MOVE_ALL is specified. -EPERM The page has been mlocked by a process/driver and cannot be moved. -EBUSY Page is busy and cannot be moved. Try again later. -EFAULT Invalid address (no VMA or zero page). -ENOMEM Unable to allocate memory on target node. -EIO Unable to write back page. The page must be written back in order to move it since the page is dirty and the filesystem does not provide a migration function that would allow the moving of dirty pages. -EINVAL A dirty page cannot be moved. The filesystem does not provide a migration function and has no ability to write back pages. The flags parameter indicates what types of pages to move: MPOL_MF_MOVE Move pages that are only mapped by the process. MPOL_MF_MOVE_ALL Also move pages that are mapped by multiple processes. Requires sufficient capabilities. Possible return codes from move_pages() -ENOENT No pages found that would require moving. All pages are either already on the target node, not present, had an invalid address or could not be moved because they were mapped by multiple processes. -EINVAL Flags other than MPOL_MF_MOVE(_ALL) specified or an attempt to migrate pages in a kernel thread. -EPERM MPOL_MF_MOVE_ALL specified without sufficient priviledges. or an attempt to move a process belonging to another user. -EACCES One of the target nodes is not allowed by the current cpuset. -ENODEV One of the target nodes is not online. -ESRCH Process does not exist. -E2BIG Too many pages to move. -ENOMEM Not enough memory to allocate control array. -EFAULT Parameters could not be accessed. A test program for move_pages() may be found with the patches on ftp.kernel.org:/pub/linux/kernel/people/christoph/pmig/patches-2.6.17-rc4-mm3 From: Christoph Lameter <clameter@sgi.com> Detailed results for sys_move_pages() Pass a pointer to an integer to get_new_page() that may be used to indicate where the completion status of a migration operation should be placed. This allows sys_move_pags() to report back exactly what happened to each page. Wish there would be a better way to do this. Looks a bit hacky. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Jes Sorensen <jes@trained-monkey.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Andi Kleen <ak@muc.de> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:03:55 +08:00
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
struct vm_area_struct *vma = (struct vm_area_struct *)private;
Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated It is often known at allocation time whether a page may be migrated or not. This patch adds a flag called __GFP_MOVABLE and a new mask called GFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated using the page migration mechanism or reclaimed by syncing with backing storage and discarding. An API function very similar to alloc_zeroed_user_highpage() is added for __GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The flags used by alloc_zeroed_user_highpage() are not changed because it would change the semantics of an existing API. After this patch is applied there are no in-kernel users of alloc_zeroed_user_highpage() so it probably should be marked deprecated if this patch is merged. Note that this patch includes a minor cleanup to the use of __GFP_ZERO in shmem.c to keep all flag modifications to inode->mapping in the shmem_dir_alloc() helper function. This clean-up suggestion is courtesy of Hugh Dickens. Additional credit goes to Christoph Lameter and Linus Torvalds for shaping the concept. Credit to Hugh Dickens for catching issues with shmem swap vector and ramfs allocations. [akpm@linux-foundation.org: build fix] [hugh@veritas.com: __GFP_ZERO cleanup] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Cc: Andy Whitcroft <apw@shadowen.org> Cc: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-17 19:03:05 +08:00
return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
page_address_in_vma(page, vma));
}
#else
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
}
int do_migrate_pages(struct mm_struct *mm,
const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
{
return -ENOSYS;
}
static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
{
return NULL;
}
#endif
long do_mbind(unsigned long start, unsigned long len,
unsigned long mode, nodemask_t *nmask, unsigned long flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
struct mempolicy *new;
unsigned long end;
int err;
LIST_HEAD(pagelist);
if ((flags & ~(unsigned long)(MPOL_MF_STRICT |
MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
|| mode > MPOL_MAX)
return -EINVAL;
if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
return -EPERM;
if (start & ~PAGE_MASK)
return -EINVAL;
if (mode == MPOL_DEFAULT)
flags &= ~MPOL_MF_STRICT;
len = (len + PAGE_SIZE - 1) & PAGE_MASK;
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
if (mpol_check_policy(mode, nmask))
return -EINVAL;
new = mpol_new(mode, nmask);
if (IS_ERR(new))
return PTR_ERR(new);
/*
* If we are using the default policy then operation
* on discontinuous address spaces is okay after all
*/
if (!new)
flags |= MPOL_MF_DISCONTIG_OK;
pr_debug("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
mode, nmask ? nodes_addr(*nmask)[0] : -1);
down_write(&mm->mmap_sem);
vma = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
err = PTR_ERR(vma);
if (!IS_ERR(vma)) {
int nr_failed = 0;
err = mbind_range(vma, start, end, new);
if (!list_empty(&pagelist))
nr_failed = migrate_pages(&pagelist, new_vma_page,
(unsigned long)vma);
if (!err && nr_failed && (flags & MPOL_MF_STRICT))
err = -EIO;
}
up_write(&mm->mmap_sem);
mpol_free(new);
return err;
}
/*
* User space interface with variable sized bitmaps for nodelists.
*/
/* Copy a node mask from user space. */
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
unsigned long maxnode)
{
unsigned long k;
unsigned long nlongs;
unsigned long endmask;
--maxnode;
nodes_clear(*nodes);
if (maxnode == 0 || !nmask)
return 0;
if (maxnode > PAGE_SIZE*BITS_PER_BYTE)
return -EINVAL;
nlongs = BITS_TO_LONGS(maxnode);
if ((maxnode % BITS_PER_LONG) == 0)
endmask = ~0UL;
else
endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;
/* When the user specified more nodes than supported just check
if the non supported part is all zero. */
if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
if (nlongs > PAGE_SIZE/sizeof(long))
return -EINVAL;
for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
unsigned long t;
if (get_user(t, nmask + k))
return -EFAULT;
if (k == nlongs - 1) {
if (t & endmask)
return -EINVAL;
} else if (t)
return -EINVAL;
}
nlongs = BITS_TO_LONGS(MAX_NUMNODES);
endmask = ~0UL;
}
if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
return -EFAULT;
nodes_addr(*nodes)[nlongs-1] &= endmask;
return 0;
}
/* Copy a kernel node mask to user space */
static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
nodemask_t *nodes)
{
unsigned long copy = ALIGN(maxnode-1, 64) / 8;
const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);
if (copy > nbytes) {
if (copy > PAGE_SIZE)
return -EINVAL;
if (clear_user((char __user *)mask + nbytes, copy - nbytes))
return -EFAULT;
copy = nbytes;
}
return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
}
asmlinkage long sys_mbind(unsigned long start, unsigned long len,
unsigned long mode,
unsigned long __user *nmask, unsigned long maxnode,
unsigned flags)
{
nodemask_t nodes;
int err;
err = get_nodes(&nodes, nmask, maxnode);
if (err)
return err;
#ifdef CONFIG_CPUSETS
/* Restrict the nodes to the allowed nodes in the cpuset */
nodes_and(nodes, nodes, current->mems_allowed);
#endif
return do_mbind(start, len, mode, &nodes, flags);
}
/* Set the process memory policy */
asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
unsigned long maxnode)
{
int err;
nodemask_t nodes;
if (mode < 0 || mode > MPOL_MAX)
return -EINVAL;
err = get_nodes(&nodes, nmask, maxnode);
if (err)
return err;
return do_set_mempolicy(mode, &nodes);
}
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
const unsigned long __user *old_nodes,
const unsigned long __user *new_nodes)
{
struct mm_struct *mm;
struct task_struct *task;
nodemask_t old;
nodemask_t new;
nodemask_t task_nodes;
int err;
err = get_nodes(&old, old_nodes, maxnode);
if (err)
return err;
err = get_nodes(&new, new_nodes, maxnode);
if (err)
return err;
/* Find the mm_struct */
read_lock(&tasklist_lock);
task = pid ? find_task_by_pid(pid) : current;
if (!task) {
read_unlock(&tasklist_lock);
return -ESRCH;
}
mm = get_task_mm(task);
read_unlock(&tasklist_lock);
if (!mm)
return -EINVAL;
/*
* Check if this process has the right to modify the specified
* process. The right exists if the process has administrative
* capabilities, superuser privileges or the same
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
* userid as the target process.
*/
if ((current->euid != task->suid) && (current->euid != task->uid) &&
(current->uid != task->suid) && (current->uid != task->uid) &&
!capable(CAP_SYS_NICE)) {
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
err = -EPERM;
goto out;
}
task_nodes = cpuset_mems_allowed(task);
/* Is the user allowed to access the target nodes? */
if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_NICE)) {
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
err = -EPERM;
goto out;
}
err = security_task_movememory(task);
if (err)
goto out;
err = do_migrate_pages(mm, &old, &new,
capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE);
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:00:51 +08:00
out:
mmput(mm);
return err;
}
/* Retrieve NUMA policy */
asmlinkage long sys_get_mempolicy(int __user *policy,
unsigned long __user *nmask,
unsigned long maxnode,
unsigned long addr, unsigned long flags)
{
int err, pval;
nodemask_t nodes;
if (nmask != NULL && maxnode < MAX_NUMNODES)
return -EINVAL;
err = do_get_mempolicy(&pval, &nodes, addr, flags);
if (err)
return err;
if (policy && put_user(pval, policy))
return -EFAULT;
if (nmask)
err = copy_nodes_to_user(nmask, maxnode, &nodes);
return err;
}
#ifdef CONFIG_COMPAT
asmlinkage long compat_sys_get_mempolicy(int __user *policy,
compat_ulong_t __user *nmask,
compat_ulong_t maxnode,
compat_ulong_t addr, compat_ulong_t flags)
{
long err;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
DECLARE_BITMAP(bm, MAX_NUMNODES);
nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask)
nm = compat_alloc_user_space(alloc_size);
err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags);
if (!err && nmask) {
err = copy_from_user(bm, nm, alloc_size);
/* ensure entire bitmap is zeroed */
err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8);
err |= compat_put_bitmap(nmask, bm, nr_bits);
}
return err;
}
asmlinkage long compat_sys_set_mempolicy(int mode, compat_ulong_t __user *nmask,
compat_ulong_t maxnode)
{
long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
DECLARE_BITMAP(bm, MAX_NUMNODES);
nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
err = compat_get_bitmap(bm, nmask, nr_bits);
nm = compat_alloc_user_space(alloc_size);
err |= copy_to_user(nm, bm, alloc_size);
}
if (err)
return -EFAULT;
return sys_set_mempolicy(mode, nm, nr_bits+1);
}
asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
compat_ulong_t mode, compat_ulong_t __user *nmask,
compat_ulong_t maxnode, compat_ulong_t flags)
{
long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
nodemask_t bm;
nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES);
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
nm = compat_alloc_user_space(alloc_size);
err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
}
if (err)
return -EFAULT;
return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}
#endif
/* Return effective policy for a VMA */
static struct mempolicy * get_vma_policy(struct task_struct *task,
struct vm_area_struct *vma, unsigned long addr)
{
[PATCH] /proc/<pid>/numa_maps to show on which nodes pages reside This patch was recently discussed on linux-mm: http://marc.theaimsgroup.com/?t=112085728500002&r=1&w=2 I inherited a large code base from Ray for page migration. There was a small patch in there that I find to be very useful since it allows the display of the locality of the pages in use by a process. I reworked that patch and came up with a /proc/<pid>/numa_maps that gives more information about the vma's of a process. numa_maps is indexes by the start address found in /proc/<pid>/maps. F.e. with this patch you can see the page use of the "getty" process: margin:/proc/12008 # cat maps 00000000-00004000 r--p 00000000 00:00 0 2000000000000000-200000000002c000 r-xp 00000000 08:04 516 /lib/ld-2.3.3.so 2000000000038000-2000000000040000 rw-p 00028000 08:04 516 /lib/ld-2.3.3.so 2000000000040000-2000000000044000 rw-p 2000000000040000 00:00 0 2000000000058000-2000000000260000 r-xp 00000000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000260000-2000000000268000 ---p 00208000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000268000-2000000000274000 rw-p 00200000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000274000-2000000000280000 rw-p 2000000000274000 00:00 0 2000000000280000-20000000002b4000 r--p 00000000 08:04 9126923 /usr/lib/locale/en_US.utf8/LC_CTYPE 2000000000300000-2000000000308000 r--s 00000000 08:04 60071467 /usr/lib/gconv/gconv-modules.cache 2000000000318000-2000000000328000 rw-p 2000000000318000 00:00 0 4000000000000000-4000000000008000 r-xp 00000000 08:04 29576399 /sbin/mingetty 6000000000004000-6000000000008000 rw-p 00004000 08:04 29576399 /sbin/mingetty 6000000000008000-600000000002c000 rw-p 6000000000008000 00:00 0 [heap] 60000fff7fffc000-60000fff80000000 rw-p 60000fff7fffc000 00:00 0 60000ffffff44000-60000ffffff98000 rw-p 60000ffffff44000 00:00 0 [stack] a000000000000000-a000000000020000 ---p 00000000 00:00 0 [vdso] cat numa_maps 2000000000000000 default MaxRef=43 Pages=11 Mapped=11 N0=4 N1=3 N2=2 N3=2 2000000000038000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000040000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 2000000000058000 default MaxRef=43 Pages=61 Mapped=61 N0=14 N1=15 N2=16 N3=16 2000000000268000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000274000 default MaxRef=1 Pages=3 Mapped=3 Anon=3 N0=3 2000000000280000 default MaxRef=8 Pages=3 Mapped=3 N0=3 2000000000300000 default MaxRef=8 Pages=2 Mapped=2 N0=2 2000000000318000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N2=1 4000000000000000 default MaxRef=6 Pages=2 Mapped=2 N1=2 6000000000004000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 6000000000008000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000fff7fffc000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000ffffff44000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 getty uses ld.so. The first vma is the code segment which is used by 43 other processes and the pages are evenly distributed over the 4 nodes. The second vma is the process specific data portion for ld.so. This is only one page. The display format is: <startaddress> Links to information in /proc/<pid>/map <memory policy> This can be "default" "interleave={}", "prefer=<node>" or "bind={<zones>}" MaxRef= <maximum reference to a page in this vma> Pages= <Nr of pages in use> Mapped= <Nr of pages with mapcount > Anon= <nr of anonymous pages> Nx= <Nr of pages on Node x> The content of the proc-file is self-evident. If this would be tied into the sparsemem system then the contents of this file would not be too useful. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-04 06:54:45 +08:00
struct mempolicy *pol = task->mempolicy;
if (vma) {
if (vma->vm_ops && vma->vm_ops->get_policy)
pol = vma->vm_ops->get_policy(vma, addr);
else if (vma->vm_policy &&
vma->vm_policy->policy != MPOL_DEFAULT)
pol = vma->vm_policy;
}
if (!pol)
pol = &default_policy;
return pol;
}
/* Return a zonelist representing a mempolicy */
static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
{
int nd;
switch (policy->policy) {
case MPOL_PREFERRED:
nd = policy->v.preferred_node;
if (nd < 0)
nd = numa_node_id();
break;
case MPOL_BIND:
/* Lower zones don't get a policy applied */
/* Careful: current->mems_allowed might have moved */
if (gfp_zone(gfp) >= policy_zone)
if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
return policy->v.zonelist;
/*FALL THROUGH*/
case MPOL_INTERLEAVE: /* should not happen */
case MPOL_DEFAULT:
nd = numa_node_id();
break;
default:
nd = 0;
BUG();
}
return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
}
/* Do dynamic interleaving for a process */
static unsigned interleave_nodes(struct mempolicy *policy)
{
unsigned nid, next;
struct task_struct *me = current;
nid = me->il_next;
next = next_node(nid, policy->v.nodes);
if (next >= MAX_NUMNODES)
next = first_node(policy->v.nodes);
me->il_next = next;
return nid;
}
[PATCH] NUMA policies in the slab allocator V2 This patch fixes a regression in 2.6.14 against 2.6.13 that causes an imbalance in memory allocation during bootup. The slab allocator in 2.6.13 is not numa aware and simply calls alloc_pages(). This means that memory policies may control the behavior of alloc_pages(). During bootup the memory policy is set to MPOL_INTERLEAVE resulting in the spreading out of allocations during bootup over all available nodes. The slab allocator in 2.6.13 has only a single list of slab pages. As a result the per cpu slab cache and the spinlock controlled page lists may contain slab entries from off node memory. The slab allocator in 2.6.13 makes no effort to discern the locality of an entry on its lists. The NUMA aware slab allocator in 2.6.14 controls locality of the slab pages explicitly by calling alloc_pages_node(). The NUMA slab allocator manages slab entries by having lists of available slab pages for each node. The per cpu slab cache can only contain slab entries associated with the node local to the processor. This guarantees that the default allocation mode of the slab allocator always assigns local memory if available. Setting MPOL_INTERLEAVE as a default policy during bootup has no effect anymore. In 2.6.14 all node unspecific slab allocations are performed on the boot processor. This means that most of key data structures are allocated on one node. Most processors will have to refer to these structures making the boot node a potential bottleneck. This may reduce performance and cause unnecessary memory pressure on the boot node. This patch implements NUMA policies in the slab layer. There is the need of explicit application of NUMA memory policies by the slab allcator itself since the NUMA slab allocator does no longer let the page_allocator control locality. The check for policies is made directly at the beginning of __cache_alloc using current->mempolicy. The memory policy is already frequently checked by the page allocator (alloc_page_vma() and alloc_page_current()). So it is highly likely that the cacheline is present. For MPOL_INTERLEAVE kmalloc() will spread out each request to one node after another so that an equal distribution of allocations can be obtained during bootup. It is not possible to push the policy check to lower layers of the NUMA slab allocator since the per cpu caches are now only containing slab entries from the current node. If the policy says that the local node is not to be preferred or forbidden then there is no point in checking the slab cache or local list of slab pages. The allocation better be directed immediately to the lists containing slab entries for the allowed set of nodes. This way of applying policy also fixes another strange behavior in 2.6.13. alloc_pages() is controlled by the memory allocation policy of the current process. It could therefore be that one process is running with MPOL_INTERLEAVE and would f.e. obtain a new page following that policy since no slab entries are in the lists anymore. A page can typically be used for multiple slab entries but lets say that the current process is only using one. The other entries are then added to the slab lists. These are now non local entries in the slab lists despite of the possible availability of local pages that would provide faster access and increase the performance of the application. Another process without MPOL_INTERLEAVE may now run and expect a local slab entry from kmalloc(). However, there are still these free slab entries from the off node page obtained from the other process via MPOL_INTERLEAVE in the cache. The process will then get an off node slab entry although other slab entries may be available that are local to that process. This means that the policy if one process may contaminate the locality of the slab caches for other processes. This patch in effect insures that a per process policy is followed for the allocation of slab entries and that there cannot be a memory policy influence from one process to another. A process with default policy will always get a local slab entry if one is available. And the process using memory policies will get its memory arranged as requested. Off-node slab allocation will require the use of spinlocks and will make the use of per cpu caches not possible. A process using memory policies to redirect allocations offnode will have to cope with additional lock overhead in addition to the latency added by the need to access a remote slab entry. Changes V1->V2 - Remove #ifdef CONFIG_NUMA by moving forward declaration into prior #ifdef CONFIG_NUMA section. - Give the function determining the node number to use a saner name. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:42:36 +08:00
/*
* Depending on the memory policy provide a node from which to allocate the
* next slab entry.
*/
unsigned slab_node(struct mempolicy *policy)
{
[PATCH] GFP_THISNODE for the slab allocator This patch insures that the slab node lists in the NUMA case only contain slabs that belong to that specific node. All slab allocations use GFP_THISNODE when calling into the page allocator. If an allocation fails then we fall back in the slab allocator according to the zonelists appropriate for a certain context. This allows a replication of the behavior of alloc_pages and alloc_pages node in the slab layer. Currently allocations requested from the page allocator may be redirected via cpusets to other nodes. This results in remote pages on nodelists and that in turn results in interrupt latency issues during cache draining. Plus the slab is handing out memory as local when it is really remote. Fallback for slab memory allocations will occur within the slab allocator and not in the page allocator. This is necessary in order to be able to use the existing pools of objects on the nodes that we fall back to before adding more pages to a slab. The fallback function insures that the nodes we fall back to obey cpuset restrictions of the current context. We do not allocate objects from outside of the current cpuset context like before. Note that the implementation of locality constraints within the slab allocator requires importing logic from the page allocator. This is a mischmash that is not that great. Other allocators (uncached allocator, vmalloc, huge pages) face similar problems and have similar minimal reimplementations of the basic fallback logic of the page allocator. There is another way of implementing a slab by avoiding per node lists (see modular slab) but this wont work within the existing slab. V1->V2: - Use NUMA_BUILD to avoid #ifdef CONFIG_NUMA - Exploit GFP_THISNODE being 0 in the NON_NUMA case to avoid another #ifdef [akpm@osdl.org: build fix] Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-27 16:50:08 +08:00
int pol = policy ? policy->policy : MPOL_DEFAULT;
switch (pol) {
[PATCH] NUMA policies in the slab allocator V2 This patch fixes a regression in 2.6.14 against 2.6.13 that causes an imbalance in memory allocation during bootup. The slab allocator in 2.6.13 is not numa aware and simply calls alloc_pages(). This means that memory policies may control the behavior of alloc_pages(). During bootup the memory policy is set to MPOL_INTERLEAVE resulting in the spreading out of allocations during bootup over all available nodes. The slab allocator in 2.6.13 has only a single list of slab pages. As a result the per cpu slab cache and the spinlock controlled page lists may contain slab entries from off node memory. The slab allocator in 2.6.13 makes no effort to discern the locality of an entry on its lists. The NUMA aware slab allocator in 2.6.14 controls locality of the slab pages explicitly by calling alloc_pages_node(). The NUMA slab allocator manages slab entries by having lists of available slab pages for each node. The per cpu slab cache can only contain slab entries associated with the node local to the processor. This guarantees that the default allocation mode of the slab allocator always assigns local memory if available. Setting MPOL_INTERLEAVE as a default policy during bootup has no effect anymore. In 2.6.14 all node unspecific slab allocations are performed on the boot processor. This means that most of key data structures are allocated on one node. Most processors will have to refer to these structures making the boot node a potential bottleneck. This may reduce performance and cause unnecessary memory pressure on the boot node. This patch implements NUMA policies in the slab layer. There is the need of explicit application of NUMA memory policies by the slab allcator itself since the NUMA slab allocator does no longer let the page_allocator control locality. The check for policies is made directly at the beginning of __cache_alloc using current->mempolicy. The memory policy is already frequently checked by the page allocator (alloc_page_vma() and alloc_page_current()). So it is highly likely that the cacheline is present. For MPOL_INTERLEAVE kmalloc() will spread out each request to one node after another so that an equal distribution of allocations can be obtained during bootup. It is not possible to push the policy check to lower layers of the NUMA slab allocator since the per cpu caches are now only containing slab entries from the current node. If the policy says that the local node is not to be preferred or forbidden then there is no point in checking the slab cache or local list of slab pages. The allocation better be directed immediately to the lists containing slab entries for the allowed set of nodes. This way of applying policy also fixes another strange behavior in 2.6.13. alloc_pages() is controlled by the memory allocation policy of the current process. It could therefore be that one process is running with MPOL_INTERLEAVE and would f.e. obtain a new page following that policy since no slab entries are in the lists anymore. A page can typically be used for multiple slab entries but lets say that the current process is only using one. The other entries are then added to the slab lists. These are now non local entries in the slab lists despite of the possible availability of local pages that would provide faster access and increase the performance of the application. Another process without MPOL_INTERLEAVE may now run and expect a local slab entry from kmalloc(). However, there are still these free slab entries from the off node page obtained from the other process via MPOL_INTERLEAVE in the cache. The process will then get an off node slab entry although other slab entries may be available that are local to that process. This means that the policy if one process may contaminate the locality of the slab caches for other processes. This patch in effect insures that a per process policy is followed for the allocation of slab entries and that there cannot be a memory policy influence from one process to another. A process with default policy will always get a local slab entry if one is available. And the process using memory policies will get its memory arranged as requested. Off-node slab allocation will require the use of spinlocks and will make the use of per cpu caches not possible. A process using memory policies to redirect allocations offnode will have to cope with additional lock overhead in addition to the latency added by the need to access a remote slab entry. Changes V1->V2 - Remove #ifdef CONFIG_NUMA by moving forward declaration into prior #ifdef CONFIG_NUMA section. - Give the function determining the node number to use a saner name. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:42:36 +08:00
case MPOL_INTERLEAVE:
return interleave_nodes(policy);
case MPOL_BIND:
/*
* Follow bind policy behavior and start allocation at the
* first node.
*/
return zone_to_nid(policy->v.zonelist->zones[0]);
[PATCH] NUMA policies in the slab allocator V2 This patch fixes a regression in 2.6.14 against 2.6.13 that causes an imbalance in memory allocation during bootup. The slab allocator in 2.6.13 is not numa aware and simply calls alloc_pages(). This means that memory policies may control the behavior of alloc_pages(). During bootup the memory policy is set to MPOL_INTERLEAVE resulting in the spreading out of allocations during bootup over all available nodes. The slab allocator in 2.6.13 has only a single list of slab pages. As a result the per cpu slab cache and the spinlock controlled page lists may contain slab entries from off node memory. The slab allocator in 2.6.13 makes no effort to discern the locality of an entry on its lists. The NUMA aware slab allocator in 2.6.14 controls locality of the slab pages explicitly by calling alloc_pages_node(). The NUMA slab allocator manages slab entries by having lists of available slab pages for each node. The per cpu slab cache can only contain slab entries associated with the node local to the processor. This guarantees that the default allocation mode of the slab allocator always assigns local memory if available. Setting MPOL_INTERLEAVE as a default policy during bootup has no effect anymore. In 2.6.14 all node unspecific slab allocations are performed on the boot processor. This means that most of key data structures are allocated on one node. Most processors will have to refer to these structures making the boot node a potential bottleneck. This may reduce performance and cause unnecessary memory pressure on the boot node. This patch implements NUMA policies in the slab layer. There is the need of explicit application of NUMA memory policies by the slab allcator itself since the NUMA slab allocator does no longer let the page_allocator control locality. The check for policies is made directly at the beginning of __cache_alloc using current->mempolicy. The memory policy is already frequently checked by the page allocator (alloc_page_vma() and alloc_page_current()). So it is highly likely that the cacheline is present. For MPOL_INTERLEAVE kmalloc() will spread out each request to one node after another so that an equal distribution of allocations can be obtained during bootup. It is not possible to push the policy check to lower layers of the NUMA slab allocator since the per cpu caches are now only containing slab entries from the current node. If the policy says that the local node is not to be preferred or forbidden then there is no point in checking the slab cache or local list of slab pages. The allocation better be directed immediately to the lists containing slab entries for the allowed set of nodes. This way of applying policy also fixes another strange behavior in 2.6.13. alloc_pages() is controlled by the memory allocation policy of the current process. It could therefore be that one process is running with MPOL_INTERLEAVE and would f.e. obtain a new page following that policy since no slab entries are in the lists anymore. A page can typically be used for multiple slab entries but lets say that the current process is only using one. The other entries are then added to the slab lists. These are now non local entries in the slab lists despite of the possible availability of local pages that would provide faster access and increase the performance of the application. Another process without MPOL_INTERLEAVE may now run and expect a local slab entry from kmalloc(). However, there are still these free slab entries from the off node page obtained from the other process via MPOL_INTERLEAVE in the cache. The process will then get an off node slab entry although other slab entries may be available that are local to that process. This means that the policy if one process may contaminate the locality of the slab caches for other processes. This patch in effect insures that a per process policy is followed for the allocation of slab entries and that there cannot be a memory policy influence from one process to another. A process with default policy will always get a local slab entry if one is available. And the process using memory policies will get its memory arranged as requested. Off-node slab allocation will require the use of spinlocks and will make the use of per cpu caches not possible. A process using memory policies to redirect allocations offnode will have to cope with additional lock overhead in addition to the latency added by the need to access a remote slab entry. Changes V1->V2 - Remove #ifdef CONFIG_NUMA by moving forward declaration into prior #ifdef CONFIG_NUMA section. - Give the function determining the node number to use a saner name. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:42:36 +08:00
case MPOL_PREFERRED:
if (policy->v.preferred_node >= 0)
return policy->v.preferred_node;
/* Fall through */
default:
return numa_node_id();
}
}
/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
struct vm_area_struct *vma, unsigned long off)
{
unsigned nnodes = nodes_weight(pol->v.nodes);
unsigned target = (unsigned)off % nnodes;
int c;
int nid = -1;
c = 0;
do {
nid = next_node(nid, pol->v.nodes);
c++;
} while (c <= target);
return nid;
}
/* Determine a node number for interleave */
static inline unsigned interleave_nid(struct mempolicy *pol,
struct vm_area_struct *vma, unsigned long addr, int shift)
{
if (vma) {
unsigned long off;
/*
* for small pages, there is no difference between
* shift and PAGE_SHIFT, so the bit-shift is safe.
* for huge pages, since vm_pgoff is in units of small
* pages, we need to shift off the always 0 bits to get
* a useful offset.
*/
BUG_ON(shift < PAGE_SHIFT);
off = vma->vm_pgoff >> (shift - PAGE_SHIFT);
off += (addr - vma->vm_start) >> shift;
return offset_il_node(pol, vma, off);
} else
return interleave_nodes(pol);
}
#ifdef CONFIG_HUGETLBFS
/* Return a zonelist suitable for a huge page allocation. */
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
gfp_t gfp_flags)
{
struct mempolicy *pol = get_vma_policy(current, vma, addr);
if (pol->policy == MPOL_INTERLEAVE) {
unsigned nid;
nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
}
return zonelist_policy(GFP_HIGHUSER, pol);
}
#endif
/* Allocate a page in interleaved policy.
Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
unsigned nid)
{
struct zonelist *zl;
struct page *page;
zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
page = __alloc_pages(gfp, order, zl);
if (page && page_zone(page) == zl->zones[0])
inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
return page;
}
/**
* alloc_page_vma - Allocate a page for a VMA.
*
* @gfp:
* %GFP_USER user allocation.
* %GFP_KERNEL kernel allocations,
* %GFP_HIGHMEM highmem/user allocations,
* %GFP_FS allocation should not call back into a file system.
* %GFP_ATOMIC don't sleep.
*
* @vma: Pointer to VMA or NULL if not available.
* @addr: Virtual Address of the allocation. Must be inside the VMA.
*
* This function allocates a page from the kernel page pool and applies
* a NUMA policy associated with the VMA or the current process.
* When VMA is not NULL caller must hold down_read on the mmap_sem of the
* mm_struct of the VMA to prevent it from going away. Should be used for
* all allocations for pages that will be mapped into
* user space. Returns NULL when no page can be allocated.
*
* Should be called with the mm_sem of the vma hold.
*/
struct page *
alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
{
[PATCH] /proc/<pid>/numa_maps to show on which nodes pages reside This patch was recently discussed on linux-mm: http://marc.theaimsgroup.com/?t=112085728500002&r=1&w=2 I inherited a large code base from Ray for page migration. There was a small patch in there that I find to be very useful since it allows the display of the locality of the pages in use by a process. I reworked that patch and came up with a /proc/<pid>/numa_maps that gives more information about the vma's of a process. numa_maps is indexes by the start address found in /proc/<pid>/maps. F.e. with this patch you can see the page use of the "getty" process: margin:/proc/12008 # cat maps 00000000-00004000 r--p 00000000 00:00 0 2000000000000000-200000000002c000 r-xp 00000000 08:04 516 /lib/ld-2.3.3.so 2000000000038000-2000000000040000 rw-p 00028000 08:04 516 /lib/ld-2.3.3.so 2000000000040000-2000000000044000 rw-p 2000000000040000 00:00 0 2000000000058000-2000000000260000 r-xp 00000000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000260000-2000000000268000 ---p 00208000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000268000-2000000000274000 rw-p 00200000 08:04 54707842 /lib/tls/libc.so.6.1 2000000000274000-2000000000280000 rw-p 2000000000274000 00:00 0 2000000000280000-20000000002b4000 r--p 00000000 08:04 9126923 /usr/lib/locale/en_US.utf8/LC_CTYPE 2000000000300000-2000000000308000 r--s 00000000 08:04 60071467 /usr/lib/gconv/gconv-modules.cache 2000000000318000-2000000000328000 rw-p 2000000000318000 00:00 0 4000000000000000-4000000000008000 r-xp 00000000 08:04 29576399 /sbin/mingetty 6000000000004000-6000000000008000 rw-p 00004000 08:04 29576399 /sbin/mingetty 6000000000008000-600000000002c000 rw-p 6000000000008000 00:00 0 [heap] 60000fff7fffc000-60000fff80000000 rw-p 60000fff7fffc000 00:00 0 60000ffffff44000-60000ffffff98000 rw-p 60000ffffff44000 00:00 0 [stack] a000000000000000-a000000000020000 ---p 00000000 00:00 0 [vdso] cat numa_maps 2000000000000000 default MaxRef=43 Pages=11 Mapped=11 N0=4 N1=3 N2=2 N3=2 2000000000038000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000040000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 2000000000058000 default MaxRef=43 Pages=61 Mapped=61 N0=14 N1=15 N2=16 N3=16 2000000000268000 default MaxRef=1 Pages=2 Mapped=2 Anon=2 N0=2 2000000000274000 default MaxRef=1 Pages=3 Mapped=3 Anon=3 N0=3 2000000000280000 default MaxRef=8 Pages=3 Mapped=3 N0=3 2000000000300000 default MaxRef=8 Pages=2 Mapped=2 N0=2 2000000000318000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N2=1 4000000000000000 default MaxRef=6 Pages=2 Mapped=2 N1=2 6000000000004000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 6000000000008000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000fff7fffc000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 60000ffffff44000 default MaxRef=1 Pages=1 Mapped=1 Anon=1 N0=1 getty uses ld.so. The first vma is the code segment which is used by 43 other processes and the pages are evenly distributed over the 4 nodes. The second vma is the process specific data portion for ld.so. This is only one page. The display format is: <startaddress> Links to information in /proc/<pid>/map <memory policy> This can be "default" "interleave={}", "prefer=<node>" or "bind={<zones>}" MaxRef= <maximum reference to a page in this vma> Pages= <Nr of pages in use> Mapped= <Nr of pages with mapcount > Anon= <nr of anonymous pages> Nx= <Nr of pages on Node x> The content of the proc-file is self-evident. If this would be tied into the sparsemem system then the contents of this file would not be too useful. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-04 06:54:45 +08:00
struct mempolicy *pol = get_vma_policy(current, vma, addr);
cpuset_update_task_memory_state();
if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
unsigned nid;
nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
return alloc_page_interleave(gfp, 0, nid);
}
return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol));
}
/**
* alloc_pages_current - Allocate pages.
*
* @gfp:
* %GFP_USER user allocation,
* %GFP_KERNEL kernel allocation,
* %GFP_HIGHMEM highmem allocation,
* %GFP_FS don't call back into a file system.
* %GFP_ATOMIC don't sleep.
* @order: Power of two of allocation size in pages. 0 is a single page.
*
* Allocate a page from the kernel page pool. When not in
* interrupt context and apply the current process NUMA policy.
* Returns NULL when no page can be allocated.
*
* Don't call cpuset_update_task_memory_state() unless
* 1) it's ok to take cpuset_sem (can WAIT), and
* 2) allocating for current task (not interrupt).
*/
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
struct mempolicy *pol = current->mempolicy;
if ((gfp & __GFP_WAIT) && !in_interrupt())
cpuset_update_task_memory_state();
if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
pol = &default_policy;
if (pol->policy == MPOL_INTERLEAVE)
return alloc_page_interleave(gfp, order, interleave_nodes(pol));
return __alloc_pages(gfp, order, zonelist_policy(gfp, pol));
}
EXPORT_SYMBOL(alloc_pages_current);
[PATCH] cpuset: rebind vma mempolicies fix Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:59 +08:00
/*
* If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
* rebinds the mempolicy its copying by calling mpol_rebind_policy()
* with the mems_allowed returned by cpuset_mems_allowed(). This
* keeps mempolicies cpuset relative after its cpuset moves. See
* further kernel/cpuset.c update_nodemask().
*/
void *cpuset_being_rebound;
/* Slow path of a mempolicy copy */
struct mempolicy *__mpol_copy(struct mempolicy *old)
{
struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!new)
return ERR_PTR(-ENOMEM);
[PATCH] cpuset: rebind vma mempolicies fix Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:59 +08:00
if (current_cpuset_is_being_rebound()) {
nodemask_t mems = cpuset_mems_allowed(current);
mpol_rebind_policy(old, &mems);
}
*new = *old;
atomic_set(&new->refcnt, 1);
if (new->policy == MPOL_BIND) {
int sz = ksize(old->v.zonelist);
new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL);
if (!new->v.zonelist) {
kmem_cache_free(policy_cache, new);
return ERR_PTR(-ENOMEM);
}
}
return new;
}
/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
if (!a || !b)
return 0;
if (a->policy != b->policy)
return 0;
switch (a->policy) {
case MPOL_DEFAULT:
return 1;
case MPOL_INTERLEAVE:
return nodes_equal(a->v.nodes, b->v.nodes);
case MPOL_PREFERRED:
return a->v.preferred_node == b->v.preferred_node;
case MPOL_BIND: {
int i;
for (i = 0; a->v.zonelist->zones[i]; i++)
if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i])
return 0;
return b->v.zonelist->zones[i] == NULL;
}
default:
BUG();
return 0;
}
}
/* Slow path of a mpol destructor. */
void __mpol_free(struct mempolicy *p)
{
if (!atomic_dec_and_test(&p->refcnt))
return;
if (p->policy == MPOL_BIND)
kfree(p->v.zonelist);
p->policy = MPOL_DEFAULT;
kmem_cache_free(policy_cache, p);
}
/*
* Shared memory backing store policy support.
*
* Remember policies even when nobody has shared memory mapped.
* The policies are kept in Red-Black tree linked from the inode.
* They are protected by the sp->lock spinlock, which should be held
* for any accesses to the tree.
*/
/* lookup first element intersecting start-end */
/* Caller holds sp->lock */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
struct rb_node *n = sp->root.rb_node;
while (n) {
struct sp_node *p = rb_entry(n, struct sp_node, nd);
if (start >= p->end)
n = n->rb_right;
else if (end <= p->start)
n = n->rb_left;
else
break;
}
if (!n)
return NULL;
for (;;) {
struct sp_node *w = NULL;
struct rb_node *prev = rb_prev(n);
if (!prev)
break;
w = rb_entry(prev, struct sp_node, nd);
if (w->end <= start)
break;
n = prev;
}
return rb_entry(n, struct sp_node, nd);
}
/* Insert a new shared policy into the list. */
/* Caller holds sp->lock */
static void sp_insert(struct shared_policy *sp, struct sp_node *new)
{
struct rb_node **p = &sp->root.rb_node;
struct rb_node *parent = NULL;
struct sp_node *nd;
while (*p) {
parent = *p;
nd = rb_entry(parent, struct sp_node, nd);
if (new->start < nd->start)
p = &(*p)->rb_left;
else if (new->end > nd->end)
p = &(*p)->rb_right;
else
BUG();
}
rb_link_node(&new->nd, parent, p);
rb_insert_color(&new->nd, &sp->root);
pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
new->policy ? new->policy->policy : 0);
}
/* Find shared policy intersecting idx */
struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
struct mempolicy *pol = NULL;
struct sp_node *sn;
if (!sp->root.rb_node)
return NULL;
spin_lock(&sp->lock);
sn = sp_lookup(sp, idx, idx+1);
if (sn) {
mpol_get(sn->policy);
pol = sn->policy;
}
spin_unlock(&sp->lock);
return pol;
}
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
rb_erase(&n->nd, &sp->root);
mpol_free(n->policy);
kmem_cache_free(sn_cache, n);
}
struct sp_node *
sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol)
{
struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
if (!n)
return NULL;
n->start = start;
n->end = end;
mpol_get(pol);
n->policy = pol;
return n;
}
/* Replace a policy range. */
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
unsigned long end, struct sp_node *new)
{
struct sp_node *n, *new2 = NULL;
restart:
spin_lock(&sp->lock);
n = sp_lookup(sp, start, end);
/* Take care of old policies in the same range. */
while (n && n->start < end) {
struct rb_node *next = rb_next(&n->nd);
if (n->start >= start) {
if (n->end <= end)
sp_delete(sp, n);
else
n->start = end;
} else {
/* Old policy spanning whole new range. */
if (n->end > end) {
if (!new2) {
spin_unlock(&sp->lock);
new2 = sp_alloc(end, n->end, n->policy);
if (!new2)
return -ENOMEM;
goto restart;
}
n->end = start;
sp_insert(sp, new2);
new2 = NULL;
break;
} else
n->end = start;
}
if (!next)
break;
n = rb_entry(next, struct sp_node, nd);
}
if (new)
sp_insert(sp, new);
spin_unlock(&sp->lock);
if (new2) {
mpol_free(new2->policy);
kmem_cache_free(sn_cache, new2);
}
return 0;
}
void mpol_shared_policy_init(struct shared_policy *info, int policy,
nodemask_t *policy_nodes)
{
info->root = RB_ROOT;
spin_lock_init(&info->lock);
if (policy != MPOL_DEFAULT) {
struct mempolicy *newpol;
/* Falls back to MPOL_DEFAULT on any error */
newpol = mpol_new(policy, policy_nodes);
if (!IS_ERR(newpol)) {
/* Create pseudo-vma that contains just the policy */
struct vm_area_struct pvma;
memset(&pvma, 0, sizeof(struct vm_area_struct));
/* Policy covers entire file */
pvma.vm_end = TASK_SIZE;
mpol_set_shared_policy(info, &pvma, newpol);
mpol_free(newpol);
}
}
}
int mpol_set_shared_policy(struct shared_policy *info,
struct vm_area_struct *vma, struct mempolicy *npol)
{
int err;
struct sp_node *new = NULL;
unsigned long sz = vma_pages(vma);
pr_debug("set_shared_policy %lx sz %lu %d %lx\n",
vma->vm_pgoff,
sz, npol? npol->policy : -1,
npol ? nodes_addr(npol->v.nodes)[0] : -1);
if (npol) {
new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol);
if (!new)
return -ENOMEM;
}
err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
if (err && new)
kmem_cache_free(sn_cache, new);
return err;
}
/* Free a backing policy store on inode delete. */
void mpol_free_shared_policy(struct shared_policy *p)
{
struct sp_node *n;
struct rb_node *next;
if (!p->root.rb_node)
return;
spin_lock(&p->lock);
next = rb_first(&p->root);
while (next) {
n = rb_entry(next, struct sp_node, nd);
next = rb_next(&n->nd);
rb_erase(&n->nd, &p->root);
mpol_free(n->policy);
kmem_cache_free(sn_cache, n);
}
spin_unlock(&p->lock);
}
/* assumes fs == KERNEL_DS */
void __init numa_policy_init(void)
{
nodemask_t interleave_nodes;
unsigned long largest = 0;
int nid, prefer = 0;
policy_cache = kmem_cache_create("numa_policy",
sizeof(struct mempolicy),
0, SLAB_PANIC, NULL);
sn_cache = kmem_cache_create("shared_policy_node",
sizeof(struct sp_node),
0, SLAB_PANIC, NULL);
/*
* Set interleaving policy for system init. Interleaving is only
* enabled across suitably sized nodes (default is >= 16MB), or
* fall back to the largest node if they're all smaller.
*/
nodes_clear(interleave_nodes);
for_each_online_node(nid) {
unsigned long total_pages = node_present_pages(nid);
/* Preserve the largest node */
if (largest < total_pages) {
largest = total_pages;
prefer = nid;
}
/* Interleave this node? */
if ((total_pages << PAGE_SHIFT) >= (16 << 20))
node_set(nid, interleave_nodes);
}
/* All too small, use the largest */
if (unlikely(nodes_empty(interleave_nodes)))
node_set(prefer, interleave_nodes);
if (do_set_mempolicy(MPOL_INTERLEAVE, &interleave_nodes))
printk("numa_policy_init: interleaving failed\n");
}
/* Reset policy of current process to default */
void numa_default_policy(void)
{
do_set_mempolicy(MPOL_DEFAULT, NULL);
}
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
/* Migrate a policy to a different set of nodes */
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
{
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
nodemask_t *mpolmask;
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
nodemask_t tmp;
if (!pol)
return;
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
mpolmask = &pol->cpuset_mems_allowed;
if (nodes_equal(*mpolmask, *newmask))
return;
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
switch (pol->policy) {
case MPOL_DEFAULT:
break;
case MPOL_INTERLEAVE:
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
nodes_remap(tmp, pol->v.nodes, *mpolmask, *newmask);
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
pol->v.nodes = tmp;
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
*mpolmask = *newmask;
current->il_next = node_remap(current->il_next,
*mpolmask, *newmask);
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
break;
case MPOL_PREFERRED:
pol->v.preferred_node = node_remap(pol->v.preferred_node,
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
*mpolmask, *newmask);
*mpolmask = *newmask;
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
break;
case MPOL_BIND: {
nodemask_t nodes;
struct zone **z;
struct zonelist *zonelist;
nodes_clear(nodes);
for (z = pol->v.zonelist->zones; *z; z++)
node_set(zone_to_nid(*z), nodes);
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
nodes_remap(tmp, nodes, *mpolmask, *newmask);
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
nodes = tmp;
zonelist = bind_zonelist(&nodes);
/* If no mem, then zonelist is NULL and we keep old zonelist.
* If that old zonelist has no remaining mems_allowed nodes,
* then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT.
*/
if (!IS_ERR(zonelist)) {
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
/* Good - got mem - substitute new zonelist */
kfree(pol->v.zonelist);
pol->v.zonelist = zonelist;
}
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
*mpolmask = *newmask;
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
break;
}
default:
BUG();
break;
}
}
/*
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
* Wrapper for mpol_rebind_policy() that just requires task
* pointer, and updates task mempolicy.
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
*/
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
{
[PATCH] cpuset: numa_policy_rebind cleanup Cleanup, reorganize and make more robust the mempolicy.c code to rebind mempolicies relative to the containing cpuset after a tasks memory placement changes. The real motivator for this cleanup patch is to lay more groundwork for the upcoming patch to correctly rebind NUMA mempolicies that are attached to vma's after the containing cpuset memory placement changes. NUMA mempolicies are constrained by the cpuset their task is a member of. When either (1) a task is moved to a different cpuset, or (2) the 'mems' mems_allowed of a cpuset is changed, then the NUMA mempolicies have embedded node numbers (for MPOL_BIND, MPOL_INTERLEAVE and MPOL_PREFERRED) that need to be recalculated, relative to their new cpuset placement. The old code used an unreliable method of determining what was the old mems_allowed constraining the mempolicy. It just looked at the tasks mems_allowed value. This sort of worked with the present code, that just rebinds the -task- mempolicy, and leaves any -vma- mempolicies broken, referring to the old nodes. But in an upcoming patch, the vma mempolicies will be rebound as well. Then the order in which the various task and vma mempolicies are updated will no longer be deterministic, and one can no longer count on the task->mems_allowed holding the old value for as long as needed. It's not even clear if the current code was guaranteed to work reliably for task mempolicies. So I added a mems_allowed field to each mempolicy, stating exactly what mems_allowed the policy is relative to, and updated synchronously and reliably anytime that the mempolicy is rebound. Also removed a useless wrapper routine, numa_policy_rebind(), and had its caller, cpuset_update_task_memory_state(), call directly to the rewritten policy_rebind() routine, and made that rebind routine extern instead of static, and added a "mpol_" prefix to its name, making it mpol_rebind_policy(). Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:56 +08:00
mpol_rebind_policy(tsk->mempolicy, new);
[PATCH] cpusets: automatic numa mempolicy rebinding This patch automatically updates a tasks NUMA mempolicy when its cpuset memory placement changes. It does so within the context of the task, without any need to support low level external mempolicy manipulation. If a system is not using cpusets, or if running on a system with just the root (all-encompassing) cpuset, then this remap is a no-op. Only when a task is moved between cpusets, or a cpusets memory placement is changed does the following apply. Otherwise, the main routine below, rebind_policy() is not even called. When mixing cpusets, scheduler affinity, and NUMA mempolicies, the essential role of cpusets is to place jobs (several related tasks) on a set of CPUs and Memory Nodes, the essential role of sched_setaffinity is to manage a jobs processor placement within its allowed cpuset, and the essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs memory placement within its allowed cpuset. However, CPU affinity and NUMA memory placement are managed within the kernel using absolute system wide numbering, not cpuset relative numbering. This is ok until a job is migrated to a different cpuset, or what's the same, a jobs cpuset is moved to different CPUs and Memory Nodes. Then the CPU affinity and NUMA memory placement of the tasks in the job need to be updated, to preserve their cpuset-relative position. This can be done for CPU affinity using sched_setaffinity() from user code, as one task can modify anothers CPU affinity. This cannot be done from an external task for NUMA memory placement, as that can only be modified in the context of the task using it. However, it easy enough to remap a tasks NUMA mempolicy automatically when a task is migrated, using the existing cpuset mechanism to trigger a refresh of a tasks memory placement after its cpuset has changed. All that is needed is the old and new nodemask, and notice to the task that it needs to rebind its mempolicy. The tasks mems_allowed has the old mask, the tasks cpuset has the new mask, and the existing cpuset_update_current_mems_allowed() mechanism provides the notice. The bitmap/cpumask/nodemask remap operators provide the cpuset relative calculations. This patch leaves open a couple of issues: 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies: These mempolicies may reference nodes outside of those allowed to the current task by its cpuset. Tasks are migrated as part of jobs, which reside on what might be several cpusets in a subtree. When such a job is migrated, all NUMA memory policy references to nodes within that cpuset subtree should be translated, and references to any nodes outside that subtree should be left untouched. A future patch will provide the cpuset mechanism needed to mark such subtrees. With that patch, we will be able to correctly migrate these other memory policies across a job migration. 2) Updating cpuset, affinity and memory policies in user space: This is harder. Any placement state stored in user space using system-wide numbering will be invalidated across a migration. More work will be required to provide user code with a migration-safe means to manage its cpuset relative placement, while preserving the current API's that pass system wide numbers, not cpuset relative numbers across the kernel-user boundary. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-31 07:02:36 +08:00
}
[PATCH] cpuset: rebind vma mempolicies fix Fix more of longstanding bug in cpuset/mempolicy interaction. NUMA mempolicies (mm/mempolicy.c) are constrained by the current tasks cpuset to just the Memory Nodes allowed by that cpuset. The kernel maintains internal state for each mempolicy, tracking what nodes are used for the MPOL_INTERLEAVE, MPOL_BIND or MPOL_PREFERRED policies. When a tasks cpuset memory placement changes, whether because the cpuset changed, or because the task was attached to a different cpuset, then the tasks mempolicies have to be rebound to the new cpuset placement, so as to preserve the cpuset-relative numbering of the nodes in that policy. An earlier fix handled such mempolicy rebinding for mempolicies attached to a task. This fix rebinds mempolicies attached to vma's (address ranges in a tasks address space.) Due to the need to hold the task->mm->mmap_sem semaphore while updating vma's, the rebinding of vma mempolicies has to be done when the cpuset memory placement is changed, at which time mmap_sem can be safely acquired. The tasks mempolicy is rebound later, when the task next attempts to allocate memory and notices that its task->cpuset_mems_generation is out-of-date with its cpusets mems_generation. Because walking the tasklist to find all tasks attached to a changing cpuset requires holding tasklist_lock, a spinlock, one cannot update the vma's of the affected tasks while doing the tasklist scan. In general, one cannot acquire a semaphore (which can sleep) while already holding a spinlock (such as tasklist_lock). So a list of mm references has to be built up during the tasklist scan, then the tasklist lock dropped, then for each mm, its mmap_sem acquired, and the vma's in that mm rebound. Once the tasklist lock is dropped, affected tasks may fork new tasks, before their mm's are rebound. A kernel global 'cpuset_being_rebound' is set to point to the cpuset being rebound (there can only be one; cpuset modifications are done under a global 'manage_sem' semaphore), and the mpol_copy code that is used to copy a tasks mempolicies during fork catches such forking tasks, and ensures their children are also rebound. When a task is moved to a different cpuset, it is easier, as there is only one task involved. It's mm->vma's are scanned, using the same mpol_rebind_policy() as used above. It may happen that both the mpol_copy hook and the update done via the tasklist scan update the same mm twice. This is ok, as the mempolicies of each vma in an mm keep track of what mems_allowed they are relative to, and safely no-op a second request to rebind to the same nodes. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:01:59 +08:00
/*
* Rebind each vma in mm to new nodemask.
*
* Call holding a reference to mm. Takes mm->mmap_sem during call.
*/
void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
struct vm_area_struct *vma;
down_write(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next)
mpol_rebind_policy(vma->vm_policy, new);
up_write(&mm->mmap_sem);
}
/*
* Display pages allocated per node and memory policy via /proc.
*/
static const char * const policy_types[] =
{ "default", "prefer", "bind", "interleave" };
/*
* Convert a mempolicy into a string.
* Returns the number of characters in buffer (if positive)
* or an error (negative)
*/
static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
{
char *p = buffer;
int l;
nodemask_t nodes;
int mode = pol ? pol->policy : MPOL_DEFAULT;
switch (mode) {
case MPOL_DEFAULT:
nodes_clear(nodes);
break;
case MPOL_PREFERRED:
nodes_clear(nodes);
node_set(pol->v.preferred_node, nodes);
break;
case MPOL_BIND:
get_zonemask(pol, &nodes);
break;
case MPOL_INTERLEAVE:
nodes = pol->v.nodes;
break;
default:
BUG();
return -EFAULT;
}
l = strlen(policy_types[mode]);
if (buffer + maxlen < p + l + 1)
return -ENOSPC;
strcpy(p, policy_types[mode]);
p += l;
if (!nodes_empty(nodes)) {
if (buffer + maxlen < p + 2)
return -ENOSPC;
*p++ = '=';
p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
}
return p - buffer;
}
struct numa_maps {
unsigned long pages;
unsigned long anon;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
unsigned long active;
unsigned long writeback;
unsigned long mapcount_max;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
unsigned long dirty;
unsigned long swapcache;
unsigned long node[MAX_NUMNODES];
};
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
static void gather_stats(struct page *page, void *private, int pte_dirty)
{
struct numa_maps *md = private;
int count = page_mapcount(page);
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
md->pages++;
if (pte_dirty || PageDirty(page))
md->dirty++;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (PageSwapCache(page))
md->swapcache++;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (PageActive(page))
md->active++;
if (PageWriteback(page))
md->writeback++;
if (PageAnon(page))
md->anon++;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (count > md->mapcount_max)
md->mapcount_max = count;
md->node[page_to_nid(page)]++;
}
#ifdef CONFIG_HUGETLB_PAGE
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
static void check_huge_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct numa_maps *md)
{
unsigned long addr;
struct page *page;
for (addr = start; addr < end; addr += HPAGE_SIZE) {
pte_t *ptep = huge_pte_offset(vma->vm_mm, addr & HPAGE_MASK);
pte_t pte;
if (!ptep)
continue;
pte = *ptep;
if (pte_none(pte))
continue;
page = pte_page(pte);
if (!page)
continue;
gather_stats(page, md, pte_dirty(*ptep));
}
}
#else
static inline void check_huge_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct numa_maps *md)
{
}
#endif
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
int show_numa_map(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
struct vm_area_struct *vma = v;
struct numa_maps *md;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
struct file *file = vma->vm_file;
struct mm_struct *mm = vma->vm_mm;
int n;
char buffer[50];
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (!mm)
return 0;
md = kzalloc(sizeof(struct numa_maps), GFP_KERNEL);
if (!md)
return 0;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
mpol_to_str(buffer, sizeof(buffer),
get_vma_policy(priv->task, vma, vma->vm_start));
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
if (file) {
seq_printf(m, " file=");
seq_path(m, file->f_path.mnt, file->f_path.dentry, "\n\t= ");
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_printf(m, " heap");
} else if (vma->vm_start <= mm->start_stack &&
vma->vm_end >= mm->start_stack) {
seq_printf(m, " stack");
}
if (is_vm_hugetlb_page(vma)) {
check_huge_range(vma, vma->vm_start, vma->vm_end, md);
seq_printf(m, " huge");
} else {
check_pgd_range(vma, vma->vm_start, vma->vm_end,
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
&node_online_map, MPOL_MF_STATS, md);
}
if (!md->pages)
goto out;
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (md->anon)
seq_printf(m," anon=%lu",md->anon);
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (md->dirty)
seq_printf(m," dirty=%lu",md->dirty);
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (md->pages != md->anon && md->pages != md->dirty)
seq_printf(m, " mapped=%lu", md->pages);
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (md->mapcount_max > 1)
seq_printf(m, " mapmax=%lu", md->mapcount_max);
[PATCH] numa_maps update Change the format of numa_maps to be more compact and contain additional information that is useful for managing and troubleshooting memory on a NUMA system. Numa_maps can now also support huge pages. Fixes: 1. More compact format. Only display fields if they contain additional information. 2. Always display information for all vmas. The old numa_maps did not display vma with no mapped entries. This was a bit confusing because page migration removes ptes for file backed vmas. After page migration a part of the vmas vanished. 3. Rename maxref to maxmap. This is the maximum mapcount of all the pages in a vma and may be used as an indicator as to how many processes may be using a certain vma. 4. Include the ability to scan over huge page vmas. New items shown: dirty Number of pages in a vma that have either the dirty bit set in the page_struct or in the pte. file=<filename> The file backing the pages if any stack Stack area heap Heap area huge Huge page area. The number of pages shows is the number of huge pages not the regular sized pages. swapcache Number of pages with swap references. Must be >0 in order to be shown. active Number of active pages. Only displayed if different from the number of pages mapped. writeback Number of pages under writeback. Only displayed if >0. Sample ouput of a process using huge pages: 00000000 default 2000000000000000 default file=/lib/ld-2.3.90.so mapped=13 mapmax=30 N0=13 2000000000044000 default file=/lib/ld-2.3.90.so anon=2 dirty=2 swapcache=2 N2=2 2000000000064000 default file=/lib/librt-2.3.90.so mapped=2 active=1 N1=1 N3=1 2000000000074000 default file=/lib/librt-2.3.90.so 2000000000080000 default file=/lib/librt-2.3.90.so anon=1 swapcache=1 N2=1 2000000000084000 default 2000000000088000 default file=/lib/libc-2.3.90.so mapped=52 mapmax=32 active=48 N0=52 20000000002bc000 default file=/lib/libc-2.3.90.so 20000000002c8000 default file=/lib/libc-2.3.90.so anon=3 dirty=2 swapcache=3 active=2 N1=1 N2=2 20000000002d4000 default anon=1 swapcache=1 N1=1 20000000002d8000 default file=/lib/libpthread-2.3.90.so mapped=8 mapmax=3 active=7 N2=2 N3=6 20000000002fc000 default file=/lib/libpthread-2.3.90.so 2000000000308000 default file=/lib/libpthread-2.3.90.so anon=1 dirty=1 swapcache=1 N1=1 200000000030c000 default anon=1 dirty=1 swapcache=1 N1=1 2000000000320000 default anon=1 dirty=1 N1=1 200000000071c000 default 2000000000720000 default anon=2 dirty=2 swapcache=1 N1=1 N2=1 2000000000f1c000 default 2000000000f20000 default anon=2 dirty=2 swapcache=1 active=1 N2=1 N3=1 200000000171c000 default 2000000001720000 default anon=1 dirty=1 swapcache=1 N1=1 2000000001b20000 default 2000000001b38000 default file=/lib/libgcc_s.so.1 mapped=2 N1=2 2000000001b48000 default file=/lib/libgcc_s.so.1 2000000001b54000 default file=/lib/libgcc_s.so.1 anon=1 dirty=1 active=0 N1=1 2000000001b58000 default file=/lib/libunwind.so.7.0.0 mapped=2 active=1 N1=2 2000000001b74000 default file=/lib/libunwind.so.7.0.0 2000000001b80000 default file=/lib/libunwind.so.7.0.0 2000000001b84000 default 4000000000000000 default file=/media/huge/test9 mapped=1 N1=1 6000000000000000 default file=/media/huge/test9 anon=1 dirty=1 active=0 N1=1 6000000000004000 default heap 607fffff7fffc000 default anon=1 dirty=1 swapcache=1 N2=1 607fffffff06c000 default stack anon=1 dirty=1 active=0 N1=1 8000000060000000 default file=/mnt/huge/test0 huge dirty=3 N1=3 8000000090000000 default file=/mnt/huge/test1 huge dirty=3 N0=1 N2=2 80000000c0000000 default file=/mnt/huge/test2 huge dirty=3 N1=1 N3=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-07 07:42:53 +08:00
if (md->swapcache)
seq_printf(m," swapcache=%lu", md->swapcache);
if (md->active < md->pages && !is_vm_hugetlb_page(vma))
seq_printf(m," active=%lu", md->active);
if (md->writeback)
seq_printf(m," writeback=%lu", md->writeback);
for_each_online_node(n)
if (md->node[n])
seq_printf(m, " N%d=%lu", n, md->node[n]);
out:
seq_putc(m, '\n');
kfree(md);
if (m->count < m->size)
m->version = (vma != priv->tail_vma) ? vma->vm_start : 0;
return 0;
}