mm: report per-page metadata information
Subsystems (9)
PATCH v13 1/1 mm: report per-page metadata information
Today, we do not have any observability of per-page metadata and how much it takes away from the machine capacity. Thus, we want to describe the amount of memory that is going towards per-page metadata, which can vary depending on build configuration, machine architecture, and system use.
This patch adds 2 fields to /proc/vmstat that can used as shown below:
Accounting per-page metadata allocated by boot-allocator:
/proc/vmstat:nr_memmap_boot * PAGE_SIZE
Accounting per-page metadata allocated by buddy-allocator:
/proc/vmstat:nr_memmap * PAGE_SIZE
Accounting total Perpage metadata allocated on the machine:
(/proc/vmstat:nr_memmap_boot +
/proc/vmstat:nr_memmap) * PAGE_SIZE
Utility for userspace:
Observability: Describe the amount of memory overhead that is going to per-page metadata on the system at any given time since this overhead is not currently observable.
Debugging: Tracking the changes or absolute value in struct pages can help detect anomalies as they can be correlated with other metrics in the machine (e.g., memtotal, number of huge pages, etc).
page_ext overheads: Some kernel features such as page_owner page_table_check that use page_ext can be optionally enabled via kernel parameters. Having the total per-page metadata information helps users precisely measure impact. Furthermore, page-metadata metrics will reflect the amount of struct pages reliquished (or overhead reduced) when hugetlbfs pages are reserved which will vary depending on whether hugetlb vmemmap optimization is enabled or not.
For background and results see:
lore.kernel.org/all/[email protected]
---
Changelog:
Synchronized with 6.10-rc2.
Added David Rientjes's Ack.
v12:
https://lore.kernel.org/all/[email protected]
--- include/linux/mmzone.h | 2 ++ include/linux/vmstat.h | 4 ++++ mm/hugetlb_vmemmap.c | 17 +++++++++++++---- mm/mm_init.c | 3 +++ mm/page_alloc.c | 1 + mm/page_ext.c | 32 +++++++++++++++++++++++--------- mm/sparse-vmemmap.c | 8 ++++++++ mm/sparse.c | 7 ++++++- mm/vmstat.c | 26 +++++++++++++++++++++++++- 9 files changed, 85 insertions(+), 15 deletions(-)
include/linux/mmzone.h +2 -0
@@ -220,6 +220,8 @@ enum node_stat_item {PGDEMOTE_KSWAPD ,PGDEMOTE_DIRECT ,PGDEMOTE_KHUGEPAGED , +NR_MEMMAP ,/* page metadata allocated through buddy allocator */ +NR_MEMMAP_BOOT ,/* page metadata allocated through boot allocator */ NR_VM_NODE_STAT_ITEMS };
include/linux/vmstat.h +4 -0
@@ -624,4 +624,8 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, {lruvec_stat_mod_folio (folio, idx, -folio_nr_pages (folio)); } + +void __meminit mod_node_early_perpage_metadata (int nid,long delta); +void __meminit store_early_perpage_metadata (void ); +#endif /* _LINUX_VMSTAT_H */
mm/hugetlb_vmemmap.c +13 -4
@@ -184,10 +184,13 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,*/ static inline void free_vmemmap_page (struct page *page) { -if (PageReserved (page)) +if (PageReserved (page)) {free_bootmem_page (page); -else +mod_node_page_state (page_pgdat (page),NR_MEMMAP_BOOT ,-1 ); + }else {__free_page (page); +mod_node_page_state (page_pgdat (page),NR_MEMMAP ,-1 ); + } }/* Free a list of the vmemmap pages */
@@ -338,6 +341,7 @@ static int vmemmap_remap_free(unsigned long start, unsigned long end,copy_page (page_to_virt (walk.reuse_page), (void *)walk.reuse_addr);list_add (&walk.reuse_page->lru, vmemmap_pages); +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP ,1 ); }/*
@@ -384,14 +388,19 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,unsigned long nr_pages = (end - start) >>PAGE_SHIFT ;int nid =page_to_nid ((struct page *)start);struct page *page, *next; +int i; -while (nr_pages--) { +for (i =0 ; i < nr_pages; i++) { page =alloc_pages_node (nid, gfp_mask,0 ); -if (!page) +if (!page) { +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP , i); goto out; + }list_add (&page->lru, list); } +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP , nr_pages); +return 0 ; out:list_for_each_entry_safe (page, next, list, lru)
mm/mm_init.c +3 -0
@@ -29,6 +29,7 @@#include <linux/cma.h> #include <linux/crash_dump.h> #include <linux/execmem.h> +#include <linux/vmstat.h> #include "internal.h" #include "slab.h" #include "shuffle.h"
@@ -1618,6 +1619,8 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)panic ("Failed to allocate %ld bytes for node %d memory map\n" , size, pgdat->node_id); pgdat->node_mem_map = map + offset; +mod_node_early_perpage_metadata (pgdat->node_id, +DIV_ROUND_UP (size,PAGE_SIZE ));pr_debug ("%s: node %d, pgdat %08lx, node_mem_map %08lx\n" , __func__, pgdat->node_id, (unsigned long )pgdat, (unsigned long )pgdat->node_mem_map);
mm/page_alloc.c +1 -0
@@ -5715,6 +5715,7 @@ void __init setup_per_cpu_pageset(void)for_each_online_pgdat (pgdat) pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); +store_early_perpage_metadata (); }__meminit void zone_pcp_init (struct zone *zone)
mm/page_ext.c +23 -9
@@ -214,6 +214,8 @@ static int __init alloc_node_page_ext(int nid)return -ENOMEM ;NODE_DATA (nid)->node_page_ext = base; total_usage += table_size; +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP_BOOT , +DIV_ROUND_UP (table_size,PAGE_SIZE ));return 0 ; }
@@ -268,12 +270,15 @@ static void *__meminit alloc_page_ext(size_t size, int nid)void *addr =NULL ; addr =alloc_pages_exact_nid (nid, size, flags); -if (addr) { +if (addr)kmemleak_alloc (addr, size,1 , flags); -return addr; - } +else + addr =vzalloc_node (size, nid); - addr =vzalloc_node (size, nid); +if (addr) { +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP , +DIV_ROUND_UP (size,PAGE_SIZE )); + }return addr; }
@@ -316,18 +321,27 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)static void free_page_ext (void *addr) { +size_t table_size; +struct page *page; +struct pglist_data *pgdat; + + table_size = page_ext_size *PAGES_PER_SECTION ; +if (is_vmalloc_addr (addr)) { + page =vmalloc_to_page (addr); + pgdat =page_pgdat (page);vfree (addr); }else { -struct page *page =virt_to_page (addr); -size_t table_size; - - table_size = page_ext_size *PAGES_PER_SECTION ; - + page =virt_to_page (addr); + pgdat =page_pgdat (page);BUG_ON (PageReserved (page));kmemleak_free (addr);free_pages_exact (addr, table_size); } + +mod_node_page_state (pgdat,NR_MEMMAP , +-1L * (DIV_ROUND_UP (table_size,PAGE_SIZE ))); + }static void __free_page_ext (unsigned long pfn)
mm/sparse-vmemmap.c +8 -0
@@ -469,5 +469,13 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,if (r <0 )return NULL ; +if (system_state ==SYSTEM_BOOTING ) { +mod_node_early_perpage_metadata (nid,DIV_ROUND_UP (end - start, +PAGE_SIZE )); + }else { +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP , +DIV_ROUND_UP (end - start,PAGE_SIZE )); + } +return pfn_to_page (pfn); }
mm/sparse.c +6 -1
@@ -14,7 +14,7 @@#include <linux/swap.h> #include <linux/swapops.h> #include <linux/bootmem_info.h> - +#include <linux/vmstat.h> #include "internal.h" #include <asm/dma.h>
@@ -465,6 +465,9 @@ static void __init sparse_buffer_init(unsigned long size, int nid)*/ sparsemap_buf =memmap_alloc (size,section_map_size (), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; +#ifndef CONFIG_SPARSEMEM_VMEMMAP +mod_node_early_perpage_metadata (nid,DIV_ROUND_UP (size,PAGE_SIZE )); +#endif }static void __init sparse_buffer_fini (void )
@@ -643,6 +646,8 @@ static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,unsigned long start = (unsigned long )pfn_to_page (pfn);unsigned long end = start + nr_pages *sizeof (struct page ); +mod_node_page_state (page_pgdat (pfn_to_page (pfn)),NR_MEMMAP , +-1L * (DIV_ROUND_UP (end - start,PAGE_SIZE )));vmemmap_free (start, end, altmap); }static void free_map_bootmem (struct page *memmap)
mm/vmstat.c +25 -1
@@ -1255,7 +1255,8 @@ const char * const vmstat_text[] = {"pgdemote_kswapd" ,"pgdemote_direct" ,"pgdemote_khugepaged" , - +"nr_memmap" , +"nr_memmap_boot" ,/* enum writeback_stat_item counters */ "nr_dirty_threshold" , "nr_dirty_background_threshold",
@@ -2282,4 +2283,27 @@ static int __init extfrag_debug_init(void) }module_init (extfrag_debug_init); +#endif + +/* +* Page metadata size (struct page and page_ext) in pages +*/ +static unsigned long early_perpage_metadata[MAX_NUMNODES ]__meminitdata ; + +void __meminit mod_node_early_perpage_metadata (int nid,long delta) +{ + early_perpage_metadata[nid] += delta; +} + +void __meminit store_early_perpage_metadata (void ) +{ +int nid; +struct pglist_data *pgdat; + +for_each_online_pgdat (pgdat) { + nid = pgdat->node_id; +mod_node_page_state (NODE_DATA (nid),NR_MEMMAP_BOOT , + early_perpage_metadata[nid]); + } +}
Signature · 1 line
2.45.1.467.gbab1589fc0-goog
Andrew Morton
maintainerQuoted 12 lines · On Wed, 5 Jun 2024 22:27:51 +0000 Sourav Panda <[email protected]> wrote:
Today, we do not have any observability of per-page metadata and how much it takes away from the machine capacity. Thus, we want to describe the amount of memory that is going towards per-page metadata, which can vary depending on build configuration, machine architecture, and system use.
This patch adds 2 fields to
/proc/vmstatthat can used as shown below:Accounting per-page metadata allocated by boot-allocator:
/proc/vmstat:nr_memmap_boot *PAGE_SIZE
Quoted 6 lines
Accounting per-page metadata allocated by buddy-allocator:
/proc/vmstat:nr_memmap *PAGE_SIZEAccounting total Perpage metadata allocated on the machine:
(/proc/vmstat:nr_memmap_boot +
/proc/vmstat:nr_memmap) *PAGE_SIZE
Under what circumstances do these change? Only hotplug?
It's nasty, but would it be sufficient to simply emit these numbers into dmesg when they change?
Quoted 15 lines · Andrew Morton
Quoted 12 lines · On Wed, 5 Jun 2024 22:27:51 +0000 Sourav Panda <[email protected]> wrote:
Today, we do not have any observability of per-page metadata and how much it takes away from the machine capacity. Thus, we want to describe the amount of memory that is going towards per-page metadata, which can vary depending on build configuration, machine architecture, and system use.
This patch adds 2 fields to
/proc/vmstatthat can used as shown below:Accounting per-page metadata allocated by boot-allocator:
/proc/vmstat:nr_memmap_boot *PAGE_SIZE
Quoted 8 lines
Quoted 6 lines
Accounting per-page metadata allocated by buddy-allocator:
/proc/vmstat:nr_memmap *PAGE_SIZEAccounting total Perpage metadata allocated on the machine:
(/proc/vmstat:nr_memmap_boot +
/proc/vmstat:nr_memmap) *PAGE_SIZEUnder what circumstances do these change? Only hotplug?
Currently, there are several reasons these numbers can change during runtime:
1. Memory hotplug/hotremove
2. Adding/Removing hugetlb pages with vmemmap optimization
3. Adding/Removing Device DAX with vmemmap optimization.
Quoted 3 lines
It's nasty, but would it be sufficient to simply emit these numbers into dmesg when they change?
These numbers should really be part of /proc/vmstat in order to provide an interface for determining the system memory overhead.
Pasha
Alison Schofield
maintainer++ nvdimm, linux-cxl, Yu Zhang
Quoted 39 lines · Sourav Panda
Today, we do not have any observability of per-page metadata and how much it takes away from the machine capacity. Thus, we want to describe the amount of memory that is going towards per-page metadata, which can vary depending on build configuration, machine architecture, and system use.
This patch adds 2 fields to
/proc/vmstatthat can used as shown below:Accounting per-page metadata allocated by boot-allocator:
/proc/vmstat:nr_memmap_boot *PAGE_SIZEAccounting per-page metadata allocated by buddy-allocator:
/proc/vmstat:nr_memmap *PAGE_SIZEAccounting total Perpage metadata allocated on the machine:
(/proc/vmstat:nr_memmap_boot +
/proc/vmstat:nr_memmap) *PAGE_SIZEUtility for userspace:
Observability: Describe the amount of memory overhead that is going to per-page metadata on the system at any given time since this overhead is not currently observable.
Debugging: Tracking the changes or absolute value in struct pages can help detect anomalies as they can be correlated with other metrics in the machine (e.g., memtotal, number of huge pages, etc).
page_extoverheads: Some kernel features such aspage_ownerpage_table_checkthat usepage_extcan be optionally enabled via kernel parameters. Having the total per-page metadata information helps users precisely measure impact. Furthermore, page-metadata metrics will reflect the amount of struct pages reliquished (or overhead reduced) when hugetlbfs pages are reserved which will vary depending on whether hugetlb vmemmap optimization is enabled or not.
Quoted 6 lines
For background and results see:
lore.kernel.org/all/[email protected]Acked-by David Rientjes <[email protected]>Signed-off-by Sourav Panda <[email protected]>Reviewed-by Pasha Tatashin <[email protected]>
This patch is leading to Oops in 6.11-rc1 when CONFIG_MEMORY_HOTPLUG is enabled. Folks hitting it have had success with reverting this patch. Disabling CONFIG_MEMORY_HOTPLUG is not a long term solution.
Reported here:
https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com/
A bit of detail below, follow above link for more:
dmesg:
[ 1408.632268] Oops: general protection fault, probably for non-canonical address 0xdffffc0000005650: 0000 [#1] PREEMPT SMP KASAN PTI [ 1408.644006] KASAN: probably user-memory-access in range [0x000000000002b280-0x000000000002b287] [ 1408.652699] CPU: 26 UID: 0 PID: 1868 Comm: ndctl Not tainted 6.11.0-rc1 #1 [ 1408.659571] Hardware name: Dell Inc. PowerEdge R640/08HT8T, BIOS 2.20.1 09/13/2023 [ 1408.667136] RIP: 0010:mod_node_page_state+0x2a/0x110 [ 1408.672112] Code: 0f 1f 44 00 00 48 b8 00 00 00 00 00 fc ff df 41 54 55 48 89 fd 48 81 c7 80 b2 02 00 53 48 89 f9 89 d3 48 c1 e9 03 48 83 ec 10 <80> 3c 01 00 0f 85 b8 00 00 00 48 8b bd 80 b2 02 00 41 89 f0 83 ee [ 1408.690856] RSP: 0018:ffffc900246d7388 EFLAGS: 00010286 [ 1408.696088] RAX: dffffc0000000000 RBX: 00000000fffffe00 RCX: 0000000000005650 [ 1408.703222] RDX: fffffffffffffe00 RSI: 000000000000002f RDI: 000000000002b280 [ 1408.710353] RBP: 0000000000000000 R08: ffff88a06ffcb1c8 R09: 1ffffffff218c681 [ 1408.717486] R10: ffffffff93d922bf R11: ffff88855e790f10 R12: 00000000000003ff [ 1408.724619] R13: 1ffff920048dae7b R14: ffffea0081e00000 R15: ffffffff90c63408 [ 1408.731750] FS: 00007f753c219200(0000) GS:ffff889bf2a00000(0000) knlGS:0000000000000000 [ 1408.739834] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1408.745581] CR2: 0000559f5902a5a8 CR3: 00000001292f0006 CR4: 00000000007706f0 [ 1408.752713] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1408.759843] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1408.766976] PKRU: 55555554 [ 1408.769690] Call Trace: [ 1408.772143] <TASK> [ 1408.774248] ? die_addr+0x3d/0xa0 [ 1408.777577] ? exc_general_protection+0x150/0x230 [ 1408.782297] ? asm_exc_general_protection+0x22/0x30 [ 1408.787182] ? mod_node_page_state+0x2a/0x110 [ 1408.791548] section_deactivate+0x519/0x780 [ 1408.795740] ? __pfx_section_deactivate+0x10/0x10 [ 1408.800449] __remove_pages+0x6c/0xa0 [ 1408.804119] arch_remove_memory+0x1a/0x70 [ 1408.808141] pageunmap_range+0x2ad/0x5e0 [ 1408.812067] memunmap_pages+0x320/0x5a0 [ 1408.815909] release_nodes+0xd6/0x170 [ 1408.819581] ? lockdep_hardirqs_on+0x78/0x100 [ 1408.823941] devres_release_all+0x106/0x170 [ 1408.828126] ? __pfx_devres_release_all+0x10/0x10 [ 1408.832834] device_unbind_cleanup+0x16/0x1a0 [ 1408.837198] device_release_driver_internal+0x3d5/0x530 [ 1408.842423] ? klist_put+0xf7/0x170 [ 1408.845916] bus_remove_device+0x1ed/0x3f0 [ 1408.850017] device_del+0x33b/0x8c0 [ 1408.853518] ? __pfx_device_del+0x10/0x10 [ 1408.857532] unregister_dev_dax+0x112/0x210 [ 1408.861722] release_nodes+0xd6/0x170 [ 1408.865387] ? lockdep_hardirqs_on+0x78/0x100 [ 1408.869749] devres_release_all+0x106/0x170 [ 1408.873933] ? __pfx_devres_release_all+0x10/0x10 [ 1408.878643] device_unbind_cleanup+0x16/0x1a0 [ 1408.883007] device_release_driver_internal+0x3d5/0x530 [ 1408.888235] ? __pfx_sysfs_kf_write+0x10/0x10 [ 1408.892598] unbind_store+0xdc/0xf0 [ 1408.896093] kernfs_fop_write_iter+0x358/0x530 [ 1408.900539] vfs_write+0x9b2/0xf60 [ 1408.903954] ? __pfx_vfs_write+0x10/0x10 [ 1408.907891] ? __fget_light+0x53/0x1e0 [ 1408.911646] ? __x64_sys_openat+0x11f/0x1e0 [ 1408.915835] ksys_write+0xf1/0x1d0 [ 1408.919249] ? __pfx_ksys_write+0x10/0x10 [ 1408.923264] do_syscall_64+0x8c/0x180 [ 1408.926934] ? __debug_check_no_obj_freed+0x253/0x520 [ 1408.931997] ? __pfx___debug_check_no_obj_freed+0x10/0x10 [ 1408.937405] ? kasan_quarantine_put+0x109/0x220 [ 1408.941944] ? lockdep_hardirqs_on+0x78/0x100 [ 1408.946304] ? kmem_cache_free+0x1a6/0x4c0 [ 1408.950408] ? do_sys_openat2+0x10a/0x160 [ 1408.954424] ? do_sys_openat2+0x10a/0x160 [ 1408.958434] ? __pfx_do_sys_openat2+0x10/0x10 [ 1408.962794] ? lockdep_hardirqs_on+0x78/0x100 [ 1408.967153] ? __pfx___debug_check_no_obj_freed+0x10/0x10 [ 1408.972554] ? __x64_sys_openat+0x11f/0x1e0 [ 1408.976737] ? __pfx___x64_sys_openat+0x10/0x10 [ 1408.981269] ? rcu_is_watching+0x11/0xb0 [ 1408.985204] ? lockdep_hardirqs_on_prepare+0x179/0x400 [ 1408.990351] ? do_syscall_64+0x98/0x180 [ 1408.994191] ? lockdep_hardirqs_on+0x78/0x100 [ 1408.998549] ? do_syscall_64+0x98/0x180 [ 1409.002386] ? do_syscall_64+0x98/0x180 [ 1409.006227] ? lockdep_hardirqs_on+0x78/0x100 [ 1409.010585] ? do_syscall_64+0x98/0x180 [ 1409.014425] ? lockdep_hardirqs_on_prepare+0x179/0x400 [ 1409.019565] ? do_syscall_64+0x98/0x180 [ 1409.023401] ? lockdep_hardirqs_on+0x78/0x100 [ 1409.027763] ? do_syscall_64+0x98/0x180 [ 1409.031600] ? do_syscall_64+0x98/0x180 [ 1409.035439] ? do_syscall_64+0x98/0x180 [ 1409.039281] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 1409.044331] RIP: 0033:0x7f753c0fda57 [ 1409.047911] Code: 0f 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 [ 1409.066655] RSP: 002b:00007ffc19323e28 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 1409.074220] RAX: ffffffffffffffda RBX: 0000000000000007 RCX: 00007f753c0fda57 [ 1409.081352] RDX: 0000000000000007 RSI: 0000559f5901f740 RDI: 0000000000000003 [ 1409.088483] RBP: 0000000000000003 R08: 0000000000000000 R09: 00007ffc19323d20 [ 1409.095616] R10: 0000000000000000 R11: 0000000000000246 R12: 0000559f5901f740 [ 1409.102748] R13: 00007ffc19323e90 R14: 00007f753c219120 R15: 0000559f5901fc30 [ 1409.109887] </TASK> [ 1409.112082] Modules linked in: kmem device_dax rpcsec_gss_krb5
auth_rpcgss nfsv4 dns_resolver nfs lockd grace netfs rfkill sunrpc dm_multipath intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common skx_edac skx_edac_common x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm mgag200 rapl cdc_ether iTCO_wdt dell_pc i2c_algo_bit iTCO_vendor_support ipmi_ssif usbnet acpi_power_meter drm_shmem_helper mei_me dell_smbios platform_profile intel_cstate dcdbas wmi_bmof dell_wmi_descriptor intel_uncore pcspkr mii drm_kms_helper i2c_i801 mei i2c_smbus intel_pch_thermal lpc_ich ipmi_si acpi_ipmi dax_pmem ipmi_devintf ipmi_msghandler drm fuse xfs libcrc32c sd_mod sg nd_pmem nd_btt crct10dif_pclmul crc32_pclmul crc32c_intel ahci ghash_clmulni_intel libahci bnxt_en megaraid_sas tg3 libata wmi nfit libnvdimm dm_mirror dm_region_hash dm_log dm_mod
[ 1409.189120] ---[ end trace 0000000000000000 ]---
-- snip
Quoted 1 line
Quoted 50 lines · Alison Schofield
++ nvdimm, linux-cxl, Yu Zhang
Quoted 39 lines · Sourav Panda
Today, we do not have any observability of per-page metadata and how much it takes away from the machine capacity. Thus, we want to describe the amount of memory that is going towards per-page metadata, which can vary depending on build configuration, machine architecture, and system use.
This patch adds 2 fields to
/proc/vmstatthat can used as shown below:Accounting per-page metadata allocated by boot-allocator:
/proc/vmstat:nr_memmap_boot *PAGE_SIZEAccounting per-page metadata allocated by buddy-allocator:
/proc/vmstat:nr_memmap *PAGE_SIZEAccounting total Perpage metadata allocated on the machine:
(/proc/vmstat:nr_memmap_boot +
/proc/vmstat:nr_memmap) *PAGE_SIZEUtility for userspace:
Observability: Describe the amount of memory overhead that is going to per-page metadata on the system at any given time since this overhead is not currently observable.
Debugging: Tracking the changes or absolute value in struct pages can help detect anomalies as they can be correlated with other metrics in the machine (e.g., memtotal, number of huge pages, etc).
page_extoverheads: Some kernel features such aspage_ownerpage_table_checkthat usepage_extcan be optionally enabled via kernel parameters. Having the total per-page metadata information helps users precisely measure impact. Furthermore, page-metadata metrics will reflect the amount of struct pages reliquished (or overhead reduced) when hugetlbfs pages are reserved which will vary depending on whether hugetlb vmemmap optimization is enabled or not.Quoted 6 lines
For background and results see:
lore.kernel.org/all/[email protected]Acked-by David Rientjes <[email protected]>Signed-off-by Sourav Panda <[email protected]>Reviewed-by Pasha Tatashin <[email protected]>
Quoted 6 lines
This patch is leading to Oops in 6.11-rc1 when
CONFIG_MEMORY_HOTPLUGis enabled. Folks hitting it have had success with reverting this patch. DisablingCONFIG_MEMORY_HOTPLUGis not a long term solution.Reported here:
https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com/
Thank you for the heads up. Can you please attach a full config file, also was anyone able to reproduce this problem in qemu with emulated nvdimm?
Pasha
Pasha Tatashin wrote:
[..]
Quoted 3 lines
Thank you for the heads up. Can you please attach a full config file, also was anyone able to reproduce this problem in qemu with emulated nvdimm?
Yes, I can reproduce the crash just by trying to reconfigure the mode of a pmem namespace:
# ndctl create-namespace -m raw -f -e namespace0.0
...where namespace0.0 results from:
memmap=4G!4G
...passed on the kernel command line.
Kernel config here:
https://gist.github.com/djbw/143705077103d43a735c179395d4f69a
Quoted 14 lines · Dan Williams
Pasha Tatashin wrote:
[..]Quoted 3 lines
Thank you for the heads up. Can you please attach a full config file, also was anyone able to reproduce this problem in qemu with emulated nvdimm?
Yes, I can reproduce the crash just by trying to reconfigure the mode of a pmem namespace:
# ndctl create-namespace -m raw -f -e namespace0.0...where namespace0.0 results from:
Quoted 7 lines
memmap=4G!4G...passed on the kernel command line.
Kernel config here:
https://gist.github.com/djbw/143705077103d43a735c179395d4f69a
Excellent, I was able to reproduce this problem.
The problem appear to be caused by this code:
Calling page_pgdat() in depopulate_section_memmap():
static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP,
<<<< We cannot do it.
-1L * (DIV_ROUND_UP(end - start, PAGE_SIZE)));
vmemmap_free(start, end, altmap);
}The page_pgdat() returns NULL starting from:pageunmap_range()
remove_pfn_range_from_zone() <- page is removed from the zone.
Pasha
A message that is not in the archive (sent off-list or not yet received): ZrKNKRfaH7GliS3C@iweiny-mobl
Quoted 60 lines · Ira Weiny
Quoted 41 lines · Pasha Tatashin
Quoted 14 lines · Dan Williams
Pasha Tatashin wrote:
[..]Quoted 3 lines
Thank you for the heads up. Can you please attach a full config file, also was anyone able to reproduce this problem in qemu with emulated nvdimm?
Yes, I can reproduce the crash just by trying to reconfigure the mode of a pmem namespace:
# ndctl create-namespace -m raw -f -e namespace0.0...where namespace0.0 results from:
Quoted 7 lines
memmap=4G!4G...passed on the kernel command line.
Kernel config here:
https://gist.github.com/djbw/143705077103d43a735c179395d4f69a
Excellent, I was able to reproduce this problem.
The problem appear to be caused by this code:
Calling
page_pgdat()indepopulate_section_memmap():static void depopulate_section_memmap(unsigned long pfn, unsigned long
nr_pages,
structvmem_altmap*altmap){ unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, <<<< We cannot do it. -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); }Quoted 3 lines
The
page_pgdat()returns NULL starting from:pageunmap_range()
remove_pfn_range_from_zone()<- page is removed from the zone.Is there any idea on a fix? I'm seeing the same error.
[ 561.867431] ? mod_node_page_state+0x11/0xa0 [ 561.867963] section_deactivate+0x2a0/0x2c0 [ 561.868496] __remove_pages+0x59/0x90 [ 561.868975] arch_remove_memory+0x1a/0x40 [ 561.869491] memunmap_pages+0x206/0x3d0 [ 561.869972] devres_release_all+0xa8/0xe0 [ 561.870466] device_unbind_cleanup+0xe/0x70 [ 561.870960] device_release_driver_internal+0x1ca/0x210 [ 561.871529] driver_detach+0x47/0x90 [ 561.871981] bus_remove_driver+0x6c/0xf0
Quoted 1 line
Shall we revert this patch until we figure out a fix?
I am working on a fix, and will send it out in a couple hours.
Pasha
Quoted 62 lines · Pasha Tatashin
Quoted 60 lines · Ira Weiny
Quoted 41 lines · Pasha Tatashin
Quoted 14 lines · Dan Williams
Pasha Tatashin wrote:
[..]Quoted 3 lines
Thank you for the heads up. Can you please attach a full config file, also was anyone able to reproduce this problem in qemu with emulated nvdimm?
Yes, I can reproduce the crash just by trying to reconfigure the mode of a pmem namespace:
# ndctl create-namespace -m raw -f -e namespace0.0...where namespace0.0 results from:
Quoted 7 lines
memmap=4G!4G...passed on the kernel command line.
Kernel config here:
https://gist.github.com/djbw/143705077103d43a735c179395d4f69a
Excellent, I was able to reproduce this problem.
The problem appear to be caused by this code:
Calling
page_pgdat()indepopulate_section_memmap():static void depopulate_section_memmap(unsigned long pfn, unsigned long
nr_pages,
structvmem_altmap*altmap){ unsigned long start = (unsigned long) pfn_to_page(pfn); unsigned long end = start + nr_pages * sizeof(struct page); mod_node_page_state(page_pgdat(pfn_to_page(pfn)), NR_MEMMAP, <<<< We cannot do it. -1L * (DIV_ROUND_UP(end - start, PAGE_SIZE))); vmemmap_free(start, end, altmap); }Quoted 3 lines
The
page_pgdat()returns NULL starting from:pageunmap_range()
remove_pfn_range_from_zone()<- page is removed from the zone.Is there any idea on a fix? I'm seeing the same error.
[ 561.867431] ? mod_node_page_state+0x11/0xa0 [ 561.867963] section_deactivate+0x2a0/0x2c0 [ 561.868496] __remove_pages+0x59/0x90 [ 561.868975] arch_remove_memory+0x1a/0x40 [ 561.869491] memunmap_pages+0x206/0x3d0 [ 561.869972] devres_release_all+0xa8/0xe0 [ 561.870466] device_unbind_cleanup+0xe/0x70 [ 561.870960] device_release_driver_internal+0x1ca/0x210 [ 561.871529] driver_detach+0x47/0x90 [ 561.871981] bus_remove_driver+0x6c/0xf0
Quoted 3 lines
Quoted 1 line
Shall we revert this patch until we figure out a fix?
I am working on a fix, and will send it out in a couple hours.
Patch is posted:
https://lore.kernel.org/all/[email protected]/#r
Quoted 2 lines
Pasha
Alison Schofield
maintainerQuoted 56 lines · Pasha Tatashin
Quoted 54 lines · Alison Schofield
++ nvdimm, linux-cxl, Yu Zhang
Quoted 39 lines · Sourav Panda
Today, we do not have any observability of per-page metadata and how much it takes away from the machine capacity. Thus, we want to describe the amount of memory that is going towards per-page metadata, which can vary depending on build configuration, machine architecture, and system use.
This patch adds 2 fields to
/proc/vmstatthat can used as shown below:Accounting per-page metadata allocated by boot-allocator:
/proc/vmstat:nr_memmap_boot *PAGE_SIZEAccounting per-page metadata allocated by buddy-allocator:
/proc/vmstat:nr_memmap *PAGE_SIZEAccounting total Perpage metadata allocated on the machine:
(/proc/vmstat:nr_memmap_boot +
/proc/vmstat:nr_memmap) *PAGE_SIZEUtility for userspace:
Observability: Describe the amount of memory overhead that is going to per-page metadata on the system at any given time since this overhead is not currently observable.
Debugging: Tracking the changes or absolute value in struct pages can help detect anomalies as they can be correlated with other metrics in the machine (e.g., memtotal, number of huge pages, etc).
page_extoverheads: Some kernel features such aspage_ownerpage_table_checkthat usepage_extcan be optionally enabled via kernel parameters. Having the total per-page metadata information helps users precisely measure impact. Furthermore, page-metadata metrics will reflect the amount of struct pages reliquished (or overhead reduced) when hugetlbfs pages are reserved which will vary depending on whether hugetlb vmemmap optimization is enabled or not.Quoted 6 lines
For background and results see:
lore.kernel.org/all/[email protected]Acked-by David Rientjes <[email protected]>Signed-off-by Sourav Panda <[email protected]>Reviewed-by Pasha Tatashin <[email protected]>This patch is leading to Oops in 6.11-rc1 when
CONFIG_MEMORY_HOTPLUGis enabled. Folks hitting it have had success with reverting this patch. DisablingCONFIG_MEMORY_HOTPLUGis not a long term solution.
Quoted 8 lines
Quoted 2 lines
Reported here:
https://lore.kernel.org/linux-cxl/CAHj4cs9Ax1=CoJkgBGP_+sNu6-6=6v=_L-ZBZY0bVLD3wUWZQg@mail.gmail.com/Thank you for the heads up. Can you please attach a full config file, also was anyone able to reproduce this problem in qemu with emulated nvdimm?
Pasha
Hi Pasha,
This hits every time when boot with a CXL enabled kernel and the cxl-test module loaded. After boot, modprobe -r cxl-test emits the TRACE appended below. Seems to be the same failing signature as in ndctl case above.
Applying the diff below works for the cxl-test unload failure. It moves the state update to before freeing the page. I saw a note in the patch review history about this:
"v8: Declined changing placement of metrics after attempting"
Hope it's as simple as this :)
mm/hugetlb_vmemmap.c +1 -1
@@ -188,8 +188,8 @@ static inline void free_vmemmap_page(struct page *page)free_bootmem_page (page);mod_node_page_state (page_pgdat (page),NR_MEMMAP_BOOT ,-1 ); }else { -__free_page (page);mod_node_page_state (page_pgdat (page),NR_MEMMAP ,-1 ); +__free_page (page); } }
Failure trace
[ 94.158105] BUG: unable to handle page fault for address: 0000000000004200 [ 94.159953] #PF: supervisor read access in kernel mode [ 94.161132] #PF: error_code(0x0000) - not-present page [ 94.162300] PGD 0 P4D 0 [ 94.162915] Oops: Oops: 0000 [#1] PREEMPT SMP PTI [ 94.164006] CPU: 0 UID: 0 PID: 1076 Comm: modprobe Tainted: G O N 6.11.0-rc1 #197 [ 94.165966] Tainted: [O]=OOT_MODULE, [N]=TEST [ 94.166973] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 [ 94.168768] RIP: 0010:mod_node_page_state+0x6/0x90 [ 94.169877] Code: 82 e9 ec fd ff ff 31 c9 e9 de fd ff ff 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 55 41 89 f2 89 d0 <4c> 8b 8f 00 42 00 00 83 ee 05 c1 f8 0c 83 fe 02 4f 8d 44 11 01 0f [ 94.172849] RSP: 0018:ffffc90002a4b760 EFLAGS: 00010287 [ 94.173645] RAX: 00000000fffffe00 RBX: ffffea03c0800000 RCX: 0000000000000000 [ 94.174762] RDX: fffffffffffffe00 RSI: 000000000000002d RDI: 0000000000000000 [ 94.175862] RBP: ffffc90002a4b7b0 R08: 0000000000000000 R09: 0000000000000000 [ 94.176973] R10: 000000000000002d R11: 0000000000080000 R12: ffff888012688040 [ 94.178078] R13: 0000000000200000 R14: ffffea03c0a00000 R15: ffff88812df6ce40 [ 94.179200] FS: 00007f9d9ea91740(0000) GS:ffff888077200000(0000) knlGS:0000000000000000 [ 94.180257] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 94.180888] CR2: 0000000000004200 CR3: 0000000129886000 CR4: 00000000000006f0 [ 94.181687] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 94.182487] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 94.183278] Call Trace: [ 94.183572] <TASK> [ 94.183825] ? show_regs+0x5f/0x70 [ 94.184217] ? __die+0x1f/0x70 [ 94.184556] ? page_fault_oops+0x14b/0x450 [ 94.185017] ? mod_node_page_state+0x6/0x90 [ 94.185479] ? search_exception_tables+0x5b/0x60 [ 94.185997] ? fixup_exception+0x22/0x300 [ 94.186449] ? kernelmode_fixup_or_oops.constprop.0+0x5a/0x70 [ 94.187088] ? __bad_area_nosemaphore+0x166/0x230 [ 94.187601] ? up_read+0x1d/0x30 [ 94.187973] ? bad_area_nosemaphore+0x11/0x20 [ 94.188452] ? do_user_addr_fault+0x2cb/0x6b0 [ 94.188940] ? __pfx_do_flush_tlb_all+0x10/0x10 [ 94.189445] ? exc_page_fault+0x6e/0x220 [ 94.189857] ? asm_exc_page_fault+0x27/0x30 [ 94.190212] ? mod_node_page_state+0x6/0x90 [ 94.190566] ? section_deactivate+0x242/0x290 [ 94.190946] sparse_remove_section+0x4d/0x70 [ 94.191312] __remove_pages+0x59/0x90 [ 94.191623] arch_remove_memory+0x1a/0x50 [ 94.192224] try_remove_memory+0xe9/0x150 [ 94.192858] remove_memory+0x1d/0x30 [ 94.193457] dev_dax_kmem_remove+0x9d/0x140 [kmem] [ 94.194140] dax_bus_remove+0x1d/0x30 [ 94.194723] device_remove+0x3e/0x70 [ 94.195283] device_release_driver_internal+0x1ae/0x220 [ 94.195980] device_release_driver+0xd/0x20 [ 94.196590] bus_remove_device+0xd7/0x140 [ 94.197189] device_del+0x15b/0x3a0 [ 94.197746] unregister_dev_dax+0x6c/0xd0 [ 94.198335] devm_action_release+0x10/0x20 [ 94.198945] devres_release_all+0xa8/0xe0 [ 94.199536] device_unbind_cleanup+0xd/0x70 [ 94.200138] device_release_driver_internal+0x1d3/0x220 [ 94.200809] device_release_driver+0xd/0x20 [ 94.201396] bus_remove_device+0xd7/0x140 [ 94.201977] device_del+0x15b/0x3a0 [ 94.202484] device_unregister+0x12/0x60 [ 94.203044] cxlr_dax_unregister+0x9/0x10 [cxl_core] [ 94.203712] devm_action_release+0x10/0x20 [ 94.204249] devres_release_all+0xa8/0xe0 [ 94.204780] device_unbind_cleanup+0xd/0x70 [ 94.205327] device_release_driver_internal+0x1d3/0x220 [ 94.205960] device_release_driver+0xd/0x20 [ 94.206485] bus_remove_device+0xd7/0x140 [ 94.207011] device_del+0x15b/0x3a0 [ 94.207486] unregister_region+0x2b/0x80 [cxl_core] [ 94.208092] devm_action_release+0x10/0x20 [ 94.208624] devres_release_all+0xa8/0xe0 [ 94.209130] device_unbind_cleanup+0xd/0x70 [ 94.209666] device_release_driver_internal+0x1d3/0x220 [ 94.210274] device_release_driver+0xd/0x20 [ 94.210812] bus_remove_device+0xd7/0x140 [ 94.211326] device_del+0x15b/0x3a0 [ 94.211807] ? __this_cpu_preempt_check+0x13/0x20 [ 94.212384] ? lock_release+0x133/0x290 [ 94.212896] ? __x64_sys_delete_module+0x171/0x260 [ 94.213474] platform_device_del.part.0+0x13/0x80 [ 94.214046] platform_device_unregister+0x1b/0x40 [ 94.214602] cxl_test_exit+0x1a/0xcb0 [cxl_test] [ 94.215164] __x64_sys_delete_module+0x182/0x260 [ 94.215720] ? __fput+0x1b5/0x2e0 [ 94.216176] ? debug_smp_processor_id+0x17/0x20 [ 94.216735] x64_sys_call+0xcc/0x1f30 [ 94.217206] do_syscall_64+0x47/0x110 [ 94.217691] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 94.218265] RIP: 0033:0x7f9d9e3128cb [ 94.218745] Code: 73 01 c3 48 8b 0d 55 55 0e 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 25 55 0e 00 f7 d8 64 89 01 48 [ 94.220590] RSP: 002b:00007ffd8ca73a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 [ 94.221403] RAX: ffffffffffffffda RBX: 0000564e9737f9f0 RCX: 00007f9d9e3128cb [ 94.222176] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 0000564e9737fa58 [ 94.222960] RBP: 0000564e9737fa58 R08: 1999999999999999 R09: 0000000000000000 [ 94.223772] R10: 00007f9d9e39dac0 R11: 0000000000000206 R12: 0000000000000001 [ 94.224538] R13: 0000000000000000 R14: 00007ffd8ca75dc8 R15: 0000564e9737f480 [ 94.225314] </TASK> [ 94.225721] Modules linked in: kmem device_dax dax_cxl cxl_pci cxl_mock_mem(ON) cxl_test(ON-) cxl_mem(ON) cxl_pmem(ON) cxl_port(ON) cxl_acpi(ON) cxl_mock(ON) cxl_core(ON) libnvdimm [ 94.227422] CR2: 0000000000004200 [ 94.227977] ---[ end trace 0000000000000000 ]--- [ 94.228585] RIP: 0010:mod_node_page_state+0x6/0x90 [ 94.229523] Code: 82 e9 ec fd ff ff 31 c9 e9 de fd ff ff 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 55 41 89 f2 89 d0 <4c> 8b 8f 00 42 00 00 83 ee 05 c1 f8 0c 83 fe 02 4f 8d 44 11 01 0f [ 94.232041] RSP: 0018:ffffc90002a4b760 EFLAGS: 00010287 [ 94.232891] RAX: 00000000fffffe00 RBX: ffffea03c0800000 RCX: 0000000000000000 [ 94.233921] RDX: fffffffffffffe00 RSI: 000000000000002d RDI: 0000000000000000 [ 94.234898] RBP: ffffc90002a4b7b0 R08: 0000000000000000 R09: 0000000000000000 [ 94.235908] R10: 000000000000002d R11: 0000000000080000 R12: ffff888012688040 [ 94.237077] R13: 0000000000200000 R14: ffffea03c0a00000 R15: ffff88812df6ce40 [ 94.237922] FS: 00007f9d9ea91740(0000) GS:ffff888077200000(0000) knlGS:0000000000000000 [ 94.238844] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 94.239584] CR2: 0000000000004200 CR3: 0000000129886000 CR4: 00000000000006f0 [ 94.240566] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 94.241787] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400