ebc97a52b5
We keep track of several kernel memory stats (total kernel memory, page
tables, stack, vmalloc, etc) on multiple levels (global, per-node,
per-memcg, etc). These stats give insights to users to how much memory
is used by the kernel and for what purposes.
Currently, memory used by KVM mmu is not accounted in any of those
kernel memory stats. This patch series accounts the memory pages
used by KVM for page tables in those stats in a new
NR_SECONDARY_PAGETABLE stat. This stat can be later extended to account
for other types of secondary pages tables (e.g. iommu page tables).
KVM has a decent number of large allocations that aren't for page
tables, but for most of them, the number/size of those allocations
scales linearly with either the number of vCPUs or the amount of memory
assigned to the VM. KVM's secondary page table allocations do not scale
linearly, especially when nested virtualization is in use.
From a KVM perspective, NR_SECONDARY_PAGETABLE will scale with KVM's
per-VM pages_{4k,2m,1g} stats unless the guest is doing something
bizarre (e.g. accessing only 4kb chunks of 2mb pages so that KVM is
forced to allocate a large number of page tables even though the guest
isn't accessing that much memory). However, someone would need to either
understand how KVM works to make that connection, or know (or be told) to
go look at KVM's stats if they're running VMs to better decipher the stats.
Furthermore, having NR_PAGETABLE side-by-side with NR_SECONDARY_PAGETABLE
is informative. For example, when backing a VM with THP vs. HugeTLB,
NR_SECONDARY_PAGETABLE is roughly the same, but NR_PAGETABLE is an order
of magnitude higher with THP. So having this stat will at the very least
prove to be useful for understanding tradeoffs between VM backing types,
and likely even steer folks towards potential optimizations.
The original discussion with more details about the rationale:
https://lore.kernel.org/all/87ilqoi77b.wl-maz@kernel.org
This stat will be used by subsequent patches to count KVM mmu
memory usage.
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220823004639.2387269-2-yosryahmed@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
170 lines
5.5 KiB
C
170 lines
5.5 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/fs.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/vmstat.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/vmalloc.h>
|
|
#ifdef CONFIG_CMA
|
|
#include <linux/cma.h>
|
|
#endif
|
|
#include <asm/page.h>
|
|
#include "internal.h"
|
|
|
|
void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
|
|
{
|
|
}
|
|
|
|
static void show_val_kb(struct seq_file *m, const char *s, unsigned long num)
|
|
{
|
|
seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8);
|
|
seq_write(m, " kB\n", 4);
|
|
}
|
|
|
|
static int meminfo_proc_show(struct seq_file *m, void *v)
|
|
{
|
|
struct sysinfo i;
|
|
unsigned long committed;
|
|
long cached;
|
|
long available;
|
|
unsigned long pages[NR_LRU_LISTS];
|
|
unsigned long sreclaimable, sunreclaim;
|
|
int lru;
|
|
|
|
si_meminfo(&i);
|
|
si_swapinfo(&i);
|
|
committed = vm_memory_committed();
|
|
|
|
cached = global_node_page_state(NR_FILE_PAGES) -
|
|
total_swapcache_pages() - i.bufferram;
|
|
if (cached < 0)
|
|
cached = 0;
|
|
|
|
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
|
|
pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
|
|
|
|
available = si_mem_available();
|
|
sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B);
|
|
sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B);
|
|
|
|
show_val_kb(m, "MemTotal: ", i.totalram);
|
|
show_val_kb(m, "MemFree: ", i.freeram);
|
|
show_val_kb(m, "MemAvailable: ", available);
|
|
show_val_kb(m, "Buffers: ", i.bufferram);
|
|
show_val_kb(m, "Cached: ", cached);
|
|
show_val_kb(m, "SwapCached: ", total_swapcache_pages());
|
|
show_val_kb(m, "Active: ", pages[LRU_ACTIVE_ANON] +
|
|
pages[LRU_ACTIVE_FILE]);
|
|
show_val_kb(m, "Inactive: ", pages[LRU_INACTIVE_ANON] +
|
|
pages[LRU_INACTIVE_FILE]);
|
|
show_val_kb(m, "Active(anon): ", pages[LRU_ACTIVE_ANON]);
|
|
show_val_kb(m, "Inactive(anon): ", pages[LRU_INACTIVE_ANON]);
|
|
show_val_kb(m, "Active(file): ", pages[LRU_ACTIVE_FILE]);
|
|
show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]);
|
|
show_val_kb(m, "Unevictable: ", pages[LRU_UNEVICTABLE]);
|
|
show_val_kb(m, "Mlocked: ", global_zone_page_state(NR_MLOCK));
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
show_val_kb(m, "HighTotal: ", i.totalhigh);
|
|
show_val_kb(m, "HighFree: ", i.freehigh);
|
|
show_val_kb(m, "LowTotal: ", i.totalram - i.totalhigh);
|
|
show_val_kb(m, "LowFree: ", i.freeram - i.freehigh);
|
|
#endif
|
|
|
|
#ifndef CONFIG_MMU
|
|
show_val_kb(m, "MmapCopy: ",
|
|
(unsigned long)atomic_long_read(&mmap_pages_allocated));
|
|
#endif
|
|
|
|
show_val_kb(m, "SwapTotal: ", i.totalswap);
|
|
show_val_kb(m, "SwapFree: ", i.freeswap);
|
|
#ifdef CONFIG_ZSWAP
|
|
seq_printf(m, "Zswap: %8lu kB\n",
|
|
(unsigned long)(zswap_pool_total_size >> 10));
|
|
seq_printf(m, "Zswapped: %8lu kB\n",
|
|
(unsigned long)atomic_read(&zswap_stored_pages) <<
|
|
(PAGE_SHIFT - 10));
|
|
#endif
|
|
show_val_kb(m, "Dirty: ",
|
|
global_node_page_state(NR_FILE_DIRTY));
|
|
show_val_kb(m, "Writeback: ",
|
|
global_node_page_state(NR_WRITEBACK));
|
|
show_val_kb(m, "AnonPages: ",
|
|
global_node_page_state(NR_ANON_MAPPED));
|
|
show_val_kb(m, "Mapped: ",
|
|
global_node_page_state(NR_FILE_MAPPED));
|
|
show_val_kb(m, "Shmem: ", i.sharedram);
|
|
show_val_kb(m, "KReclaimable: ", sreclaimable +
|
|
global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE));
|
|
show_val_kb(m, "Slab: ", sreclaimable + sunreclaim);
|
|
show_val_kb(m, "SReclaimable: ", sreclaimable);
|
|
show_val_kb(m, "SUnreclaim: ", sunreclaim);
|
|
seq_printf(m, "KernelStack: %8lu kB\n",
|
|
global_node_page_state(NR_KERNEL_STACK_KB));
|
|
#ifdef CONFIG_SHADOW_CALL_STACK
|
|
seq_printf(m, "ShadowCallStack:%8lu kB\n",
|
|
global_node_page_state(NR_KERNEL_SCS_KB));
|
|
#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: ",
|
|
global_zone_page_state(NR_BOUNCE));
|
|
show_val_kb(m, "WritebackTmp: ",
|
|
global_node_page_state(NR_WRITEBACK_TEMP));
|
|
show_val_kb(m, "CommitLimit: ", vm_commit_limit());
|
|
show_val_kb(m, "Committed_AS: ", committed);
|
|
seq_printf(m, "VmallocTotal: %8lu kB\n",
|
|
(unsigned long)VMALLOC_TOTAL >> 10);
|
|
show_val_kb(m, "VmallocUsed: ", vmalloc_nr_pages());
|
|
show_val_kb(m, "VmallocChunk: ", 0ul);
|
|
show_val_kb(m, "Percpu: ", pcpu_nr_pages());
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
seq_printf(m, "HardwareCorrupted: %5lu kB\n",
|
|
atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10));
|
|
#endif
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
show_val_kb(m, "AnonHugePages: ",
|
|
global_node_page_state(NR_ANON_THPS));
|
|
show_val_kb(m, "ShmemHugePages: ",
|
|
global_node_page_state(NR_SHMEM_THPS));
|
|
show_val_kb(m, "ShmemPmdMapped: ",
|
|
global_node_page_state(NR_SHMEM_PMDMAPPED));
|
|
show_val_kb(m, "FileHugePages: ",
|
|
global_node_page_state(NR_FILE_THPS));
|
|
show_val_kb(m, "FilePmdMapped: ",
|
|
global_node_page_state(NR_FILE_PMDMAPPED));
|
|
#endif
|
|
|
|
#ifdef CONFIG_CMA
|
|
show_val_kb(m, "CmaTotal: ", totalcma_pages);
|
|
show_val_kb(m, "CmaFree: ",
|
|
global_zone_page_state(NR_FREE_CMA_PAGES));
|
|
#endif
|
|
|
|
hugetlb_report_meminfo(m);
|
|
|
|
arch_report_meminfo(m);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int __init proc_meminfo_init(void)
|
|
{
|
|
proc_create_single("meminfo", 0, NULL, meminfo_proc_show);
|
|
return 0;
|
|
}
|
|
fs_initcall(proc_meminfo_init);
|