mm: add NR_SECONDARY_PAGETABLE to count secondary page table uses.

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.comSigned-off-by: Sean Christopherson <seanjc@google.com>

Documentation/admin-guide/cgroup-v2.rst

@@ -1355,6 +1355,11 @@ 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.

Documentation/filesystems/proc.rst

@@ -982,6 +982,7 @@ Example output. You may not have all of these fields.
     SUnreclaim:       142336 kB
     KernelStack:       11168 kB
     PageTables:        20540 kB
+    SecPageTables:         0 kB
     NFS_Unstable:          0 kB
     Bounce:                0 kB
     WritebackTmp:          0 kB
@@ -1090,6 +1091,9 @@ KernelStack
               Memory consumed by the kernel stacks of all tasks
 PageTables
               Memory consumed by userspace page tables
+SecPageTables
+              Memory consumed by secondary page tables, this currently
+              currently includes KVM mmu allocations on x86 and arm64.
 NFS_Unstable
               Always zero. Previous counted pages which had been written to
               the server, but has not been committed to stable storage.

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)),

fs/proc/meminfo.c

@@ -115,6 +115,8 @@ 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:         ",

include/linux/mmzone.h

@@ -216,6 +216,7 @@ 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 pagetables */
 #ifdef CONFIG_SWAP
 	NR_SWAPCACHE,
 #endif

mm/memcontrol.c

@@ -1401,6 +1401,7 @@ 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			},

mm/page_alloc.c

@@ -6039,7 +6039,8 @@ 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),
@@ -6056,6 +6057,7 @@ 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),
@@ -6089,6 +6091,7 @@ 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,
@@ -6114,6 +6117,7 @@ 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");
 	}

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