[PATCH] zoned vm counters: conversion of nr_unstable to per zone counter

Conversion of nr_unstable to a per zone counter

We need to do some special modifications to the nfs code since there are
multiple cases of disposition and we need to have a page ref for proper
accounting.

This converts the last critical page state of the VM and therefore we need to
remove several functions that were depending on GET_PAGE_STATE_LAST in order
to make the kernel compile again.  We are only left with event type counters
in page state.

[akpm@osdl.org: bugfixes]
Signed-off-by: NChristoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@osdl.org>

drivers/base/node.c

@@ -40,13 +40,11 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 	int n;
 	int nid = dev->id;
 	struct sysinfo i;
-	struct page_state ps;
 	unsigned long inactive;
 	unsigned long active;
 	unsigned long free;
 
 	si_meminfo_node(&i, nid);
-	get_page_state_node(&ps, nid);
 	__get_zone_counts(&active, &inactive, &free, NODE_DATA(nid));
 
 
@@ -66,6 +64,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 		       "Node %d Mapped:       %8lu kB\n"
 		       "Node %d AnonPages:    %8lu kB\n"
 		       "Node %d PageTables:   %8lu kB\n"
+		       "Node %d NFS Unstable: %8lu kB\n"
 		       "Node %d Slab:         %8lu kB\n",
 		       nid, K(i.totalram),
 		       nid, K(i.freeram),
@@ -82,6 +81,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev, char * buf)
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
 		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
 		       nid, K(node_page_state(nid, NR_PAGETABLE)),
+		       nid, K(node_page_state(nid, NR_UNSTABLE_NFS)),
 		       nid, K(node_page_state(nid, NR_SLAB)));
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;

fs/fs-writeback.c

@@ -465,7 +465,7 @@ void sync_inodes_sb(struct super_block *sb, int wait)
 		.range_end	= LLONG_MAX,
 	};
 	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-	unsigned long nr_unstable = read_page_state(nr_unstable);
+	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 
 	wbc.nr_to_write = nr_dirty + nr_unstable +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused) +

fs/nfs/write.c

@@ -525,7 +525,7 @@ nfs_mark_request_commit(struct nfs_page *req)
 	nfs_list_add_request(req, &nfsi->commit);
 	nfsi->ncommit++;
 	spin_unlock(&nfsi->req_lock);
-	inc_page_state(nr_unstable);
+	inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
 	mark_inode_dirty(inode);
 }
 #endif
@@ -1393,7 +1393,6 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
 	struct nfs_page		*req;
-	int res = 0;
 
         dprintk("NFS: %4d nfs_commit_done (status %d)\n",
                                 task->tk_pid, task->tk_status);
@@ -1405,6 +1404,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
 	while (!list_empty(&data->pages)) {
 		req = nfs_list_entry(data->pages.next);
 		nfs_list_remove_request(req);
+		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
 
 		dprintk("NFS: commit (%s/%Ld %d@%Ld)",
 			req->wb_context->dentry->d_inode->i_sb->s_id,
@@ -1431,9 +1431,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
 		nfs_mark_request_dirty(req);
 	next:
 		nfs_clear_page_writeback(req);
-		res++;
 	}
-	sub_page_state(nr_unstable,res);
 }
 
 static const struct rpc_call_ops nfs_commit_ops = {

fs/proc/proc_misc.c

@@ -120,7 +120,6 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 {
 	struct sysinfo i;
 	int len;
-	struct page_state ps;
 	unsigned long inactive;
 	unsigned long active;
 	unsigned long free;
@@ -129,7 +128,6 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 	struct vmalloc_info vmi;
 	long cached;
 
-	get_page_state(&ps);
 	get_zone_counts(&active, &inactive, &free);
 
 /*
@@ -172,6 +170,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 		"Mapped:       %8lu kB\n"
 		"Slab:         %8lu kB\n"
 		"PageTables:   %8lu kB\n"
+		"NFS Unstable: %8lu kB\n"
 		"CommitLimit:  %8lu kB\n"
 		"Committed_AS: %8lu kB\n"
 		"VmallocTotal: %8lu kB\n"
@@ -196,6 +195,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 		K(global_page_state(NR_FILE_MAPPED)),
 		K(global_page_state(NR_SLAB)),
 		K(global_page_state(NR_PAGETABLE)),
+		K(global_page_state(NR_UNSTABLE_NFS)),
 		K(allowed),
 		K(committed),
 		(unsigned long)VMALLOC_TOTAL >> 10,

include/linux/mmzone.h

@@ -55,6 +55,7 @@ enum zone_stat_item {
 	NR_PAGETABLE,	/* used for pagetables */
 	NR_FILE_DIRTY,
 	NR_WRITEBACK,
+	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_VM_ZONE_STAT_ITEMS };
 
 struct per_cpu_pages {

include/linux/vmstat.h

@@ -22,13 +22,6 @@
  * commented here.
  */
 struct page_state {
-	unsigned long nr_unstable;	/* NFS unstable pages */
-#define GET_PAGE_STATE_LAST nr_unstable
-
-	/*
-	 * The below are zeroed by get_page_state().  Use get_full_page_state()
-	 * to add up all these.
-	 */
 	unsigned long pgpgin;		/* Disk reads */
 	unsigned long pgpgout;		/* Disk writes */
 	unsigned long pswpin;		/* swap reads */
@@ -77,8 +70,6 @@ struct page_state {
 	unsigned long nr_bounce;	/* pages for bounce buffers */
 };
 
-extern void get_page_state(struct page_state *ret);
-extern void get_page_state_node(struct page_state *ret, int node);
 extern void get_full_page_state(struct page_state *ret);
 extern unsigned long read_page_state_offset(unsigned long offset);
 extern void mod_page_state_offset(unsigned long offset, unsigned long delta);

mm/page-writeback.c

@@ -110,7 +110,7 @@ struct writeback_state
 static void get_writeback_state(struct writeback_state *wbs)
 {
 	wbs->nr_dirty = global_page_state(NR_FILE_DIRTY);
-	wbs->nr_unstable = read_page_state(nr_unstable);
+	wbs->nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 	wbs->nr_mapped = global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES);
 	wbs->nr_writeback = global_page_state(NR_WRITEBACK);

mm/page_alloc.c

@@ -1271,7 +1271,6 @@ void si_meminfo_node(struct sysinfo *val, int nid)
  */
 void show_free_areas(void)
 {
-	struct page_state ps;
 	int cpu, temperature;
 	unsigned long active;
 	unsigned long inactive;
@@ -1303,7 +1302,6 @@ void show_free_areas(void)
 		}
 	}
 
-	get_page_state(&ps);
 	get_zone_counts(&active, &inactive, &free);
 
 	printk("Free pages: %11ukB (%ukB HighMem)\n",
@@ -1316,7 +1314,7 @@ void show_free_areas(void)
 		inactive,
 		global_page_state(NR_FILE_DIRTY),
 		global_page_state(NR_WRITEBACK),
-		ps.nr_unstable,
+		global_page_state(NR_UNSTABLE_NFS),
 		nr_free_pages(),
 		global_page_state(NR_SLAB),
 		global_page_state(NR_FILE_MAPPED),

mm/vmstat.c

@@ -45,28 +45,6 @@ static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
 	}
 }
 
-void get_page_state_node(struct page_state *ret, int node)
-{
-	int nr;
-	cpumask_t mask = node_to_cpumask(node);
-
-	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-	nr /= sizeof(unsigned long);
-
-	__get_page_state(ret, nr+1, &mask);
-}
-
-void get_page_state(struct page_state *ret)
-{
-	int nr;
-	cpumask_t mask = CPU_MASK_ALL;
-
-	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
-	nr /= sizeof(unsigned long);
-
-	__get_page_state(ret, nr + 1, &mask);
-}
-
 void get_full_page_state(struct page_state *ret)
 {
 	cpumask_t mask = CPU_MASK_ALL;
@@ -402,10 +380,9 @@ static char *vmstat_text[] = {
 	"nr_page_table_pages",
 	"nr_dirty",
 	"nr_writeback",
-
-	/* Page state */
 	"nr_unstable",
 
+	/* Event counters */
 	"pgpgin",
 	"pgpgout",
 	"pswpin",