| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <bdfea446-623c-d423-673f-496b3725ec2c@intel.com>
Date: Mon, 13 Jun 2022 11:18:14 +0800
From: "Huang, Shaoqin" <shaoqin.huang@...el.com>
To: Yosry Ahmed <yosryahmed@...gle.com>, Tejun Heo <tj@...nel.org>,
"Johannes Weiner" <hannes@...xchg.org>,
Zefan Li <lizefan.x@...edance.com>,
"Marc Zyngier" <maz@...nel.org>, James Morse <james.morse@....com>,
Alexandru Elisei <alexandru.elisei@....com>,
Suzuki K Poulose <suzuki.poulose@....com>,
"Paolo Bonzini" <pbonzini@...hat.com>,
Sean Christopherson <seanjc@...gle.com>,
Vitaly Kuznetsov <vkuznets@...hat.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
"Andrew Morton" <akpm@...ux-foundation.org>,
Michal Hocko <mhocko@...nel.org>,
"Roman Gushchin" <roman.gushchin@...ux.dev>,
Shakeel Butt <shakeelb@...gle.com>,
Oliver Upton <oupton@...gle.com>
CC: <cgroups@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<linux-arm-kernel@...ts.infradead.org>,
<kvmarm@...ts.cs.columbia.edu>, <kvm@...r.kernel.org>,
<linux-mm@...ck.org>
Subject: Re: [PATCH v5 1/4] mm: add NR_SECONDARY_PAGETABLE to count secondary
page table uses.
On 6/7/2022 6:20 AM, Yosry Ahmed wrote:
> Add NR_SECONDARY_PAGETABLE stat to count secondary page table uses, e.g.
> KVM mmu. This provides more insights on the kernel memory used
> by a workload.
>
> This stat will be used by subsequent patches to count KVM mmu
> memory usage.
>
> Signed-off-by: Yosry Ahmed <yosryahmed@...gle.com>
> ---
> Documentation/admin-guide/cgroup-v2.rst | 5 +++++
> Documentation/filesystems/proc.rst | 4 ++++
> drivers/base/node.c | 2 ++
> fs/proc/meminfo.c | 2 ++
> include/linux/mmzone.h | 1 +
> mm/memcontrol.c | 1 +
> mm/page_alloc.c | 6 +++++-
> mm/vmstat.c | 1 +
> 8 files changed, 21 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
> index 69d7a6983f781..307a284b99189 100644
> --- a/Documentation/admin-guide/cgroup-v2.rst
> +++ b/Documentation/admin-guide/cgroup-v2.rst
> @@ -1312,6 +1312,11 @@ PAGE_SIZE multiple when read back.
> pagetables
> Amount of memory allocated for page tables.
>
> + sec_pagetables
> + Amount of memory allocated for secondary page tables,
> + this currently includes KVM mmu allocations on x86
> + and arm64.
> +
> percpu (npn)
> Amount of memory used for storing per-cpu kernel
> data structures.
> diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
> index 061744c436d99..894d6317f3bdc 100644
> --- a/Documentation/filesystems/proc.rst
> +++ b/Documentation/filesystems/proc.rst
> @@ -973,6 +973,7 @@ You may not have all of these fields.
> SReclaimable: 159856 kB
> SUnreclaim: 124508 kB
> PageTables: 24448 kB
> + SecPageTables: 0 kB
> NFS_Unstable: 0 kB
> Bounce: 0 kB
> WritebackTmp: 0 kB
> @@ -1067,6 +1068,9 @@ SUnreclaim
> PageTables
> amount of memory dedicated to the lowest level of page
> tables.
> +SecPageTables
> + amount of memory dedicated to secondary page tables, this
> + currently includes KVM mmu allocations on x86 and arm64.
Just a notice. This patch in the latest 5.19.0-rc2+ have a conflict in
Documentation/filesystems/proc.rst file. But that's not a problem.
> NFS_Unstable
> Always zero. Previous counted pages which had been written to
> the server, but has not been committed to stable storage.
> diff --git a/drivers/base/node.c b/drivers/base/node.c
> index ec8bb24a5a227..9fe716832546f 100644
> --- a/drivers/base/node.c
> +++ b/drivers/base/node.c
> @@ -433,6 +433,7 @@ static ssize_t node_read_meminfo(struct device *dev,
> "Node %d ShadowCallStack:%8lu kB\n"
> #endif
> "Node %d PageTables: %8lu kB\n"
> + "Node %d SecPageTables: %8lu kB\n"
> "Node %d NFS_Unstable: %8lu kB\n"
> "Node %d Bounce: %8lu kB\n"
> "Node %d WritebackTmp: %8lu kB\n"
> @@ -459,6 +460,7 @@ static ssize_t node_read_meminfo(struct device *dev,
> nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
> #endif
> nid, K(node_page_state(pgdat, NR_PAGETABLE)),
> + nid, K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
> nid, 0UL,
> nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
> nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
> diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
> index 6fa761c9cc78e..fad29024eb2e0 100644
> --- a/fs/proc/meminfo.c
> +++ b/fs/proc/meminfo.c
> @@ -108,6 +108,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
> #endif
> show_val_kb(m, "PageTables: ",
> global_node_page_state(NR_PAGETABLE));
> + show_val_kb(m, "SecPageTables: ",
> + global_node_page_state(NR_SECONDARY_PAGETABLE));
>
> show_val_kb(m, "NFS_Unstable: ", 0);
> show_val_kb(m, "Bounce: ",
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 46ffab808f037..81d109e6c623a 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -219,6 +219,7 @@ enum node_stat_item {
> NR_KERNEL_SCS_KB, /* measured in KiB */
> #endif
> NR_PAGETABLE, /* used for pagetables */
> + NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. kvm shadow pagetables */
> #ifdef CONFIG_SWAP
> NR_SWAPCACHE,
> #endif
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 598fece89e2b7..ee1c3d464857c 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1398,6 +1398,7 @@ static const struct memory_stat memory_stats[] = {
> { "kernel", MEMCG_KMEM },
> { "kernel_stack", NR_KERNEL_STACK_KB },
> { "pagetables", NR_PAGETABLE },
> + { "sec_pagetables", NR_SECONDARY_PAGETABLE },
> { "percpu", MEMCG_PERCPU_B },
> { "sock", MEMCG_SOCK },
> { "vmalloc", MEMCG_VMALLOC },
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 0e42038382c12..29a7e9cd28c74 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5932,7 +5932,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
> " unevictable:%lu dirty:%lu writeback:%lu\n"
> " slab_reclaimable:%lu slab_unreclaimable:%lu\n"
> - " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
> + " mapped:%lu shmem:%lu pagetables:%lu\n"
> + " sec_pagetables:%lu bounce:%lu\n"
> " kernel_misc_reclaimable:%lu\n"
> " free:%lu free_pcp:%lu free_cma:%lu\n",
> global_node_page_state(NR_ACTIVE_ANON),
> @@ -5949,6 +5950,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> global_node_page_state(NR_FILE_MAPPED),
> global_node_page_state(NR_SHMEM),
> global_node_page_state(NR_PAGETABLE),
> + global_node_page_state(NR_SECONDARY_PAGETABLE),
> global_zone_page_state(NR_BOUNCE),
> global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE),
> global_zone_page_state(NR_FREE_PAGES),
> @@ -5982,6 +5984,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> " shadow_call_stack:%lukB"
> #endif
> " pagetables:%lukB"
> + " sec_pagetables:%lukB"
> " all_unreclaimable? %s"
> "\n",
> pgdat->node_id,
> @@ -6007,6 +6010,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
> node_page_state(pgdat, NR_KERNEL_SCS_KB),
> #endif
> K(node_page_state(pgdat, NR_PAGETABLE)),
> + K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
> pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
> "yes" : "no");
> }
> diff --git a/mm/vmstat.c b/mm/vmstat.c
> index b75b1a64b54cb..06eb52fe5be94 100644
> --- a/mm/vmstat.c
> +++ b/mm/vmstat.c
> @@ -1240,6 +1240,7 @@ const char * const vmstat_text[] = {
> "nr_shadow_call_stack",
> #endif
> "nr_page_table_pages",
> + "nr_sec_page_table_pages",
> #ifdef CONFIG_SWAP
> "nr_swapcached",
> #endif
Powered by blists - more mailing lists