delayacct: track delays from write-protect copy

Delay accounting does not track the delay of write-protect copy.  When
tasks trigger many write-protect copys(include COW and unsharing of
anonymous pages[1]), it may spend a amount of time waiting for them.  To
get the delay of tasks in write-protect copy, could help users to evaluate
the impact of using KSM or fork() or GUP.

Also update tools/accounting/getdelays.c:

    / # ./getdelays -dl -p 231
    print delayacct stats ON
    listen forever
    PID     231

    CPU             count     real total  virtual total    delay total  delay average
                     6247     1859000000     2154070021     1674255063          0.268ms
    IO              count    delay total  delay average
                        0              0              0ms
    SWAP            count    delay total  delay average
                        0              0              0ms
    RECLAIM         count    delay total  delay average
                        0              0              0ms
    THRASHING       count    delay total  delay average
                        0              0              0ms
    COMPACT         count    delay total  delay average
                        3          72758              0ms
    WPCOPY          count    delay total  delay average
                     3635      271567604              0ms

[1] commit 31cc5bc4af70("mm: support GUP-triggered unsharing of anonymous pages")

Link: https://lkml.kernel.org/r/20220409014342.2505532-1-yang.yang29@zte.com.cn
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jiang Xuexin <jiang.xuexin@zte.com.cn>
Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Reviewed-by: wangyong <wang.yong12@zte.com.cn>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 16 insertions, 0 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7c468ac1d069..a57e1be41401 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -32,6 +32,7 @@
 #include <linux/cma.h>
 #include <linux/migrate.h>
 #include <linux/nospec.h>
+#include <linux/delayacct.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -5230,6 +5231,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte = huge_ptep_get(ptep);
 	old_page = pte_page(pte);
 
+	delayacct_wpcopy_start();
+
 retry_avoidcopy:
 	/*
 	 * If no-one else is actually using this page, we're the exclusive
@@ -5240,6 +5243,8 @@ retry_avoidcopy:
 			page_move_anon_rmap(old_page, vma);
 		if (likely(!unshare))
 			set_huge_ptep_writable(vma, haddr, ptep);
+
+		delayacct_wpcopy_end();
 		return 0;
 	}
 	VM_BUG_ON_PAGE(PageAnon(old_page) && PageAnonExclusive(old_page),
@@ -5309,6 +5314,7 @@ retry_avoidcopy:
 			 * race occurs while re-acquiring page table
 			 * lock, and our job is done.
 			 */
+			delayacct_wpcopy_end();
 			return 0;
 		}
 
@@ -5367,6 +5373,8 @@ out_release_old:
 	put_page(old_page);
 
 	spin_lock(ptl); /* Caller expects lock to be held */
+
+	delayacct_wpcopy_end();
 	return ret;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 21dadf03f089..7a089145cad4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3090,6 +3090,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 	int page_copied = 0;
 	struct mmu_notifier_range range;
 
+	delayacct_wpcopy_start();
+
 	if (unlikely(anon_vma_prepare(vma)))
 		goto oom;
 
@@ -3114,6 +3116,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			put_page(new_page);
 			if (old_page)
 				put_page(old_page);
+
+			delayacct_wpcopy_end();
 			return 0;
 		}
 	}
@@ -3220,12 +3224,16 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 			free_swap_cache(old_page);
 		put_page(old_page);
 	}
+
+	delayacct_wpcopy_end();
 	return (page_copied && !unshare) ? VM_FAULT_WRITE : 0;
 oom_free_new:
 	put_page(new_page);
 oom:
 	if (old_page)
 		put_page(old_page);
+
+	delayacct_wpcopy_end();
 	return VM_FAULT_OOM;
 }