crash/0044-Fix-for-ps-vm-commands-to-display-correct-MEM-and-RS.patch

From 4a6f318a39f78648a3bb13d74e31e3a331254e30 Mon Sep 17 00:00:00 2001
From: Lianbo Jiang <lijiang@redhat.com>
Date: Wed, 9 Nov 2022 14:21:57 +0800
Subject: [PATCH 44/89] Fix for "ps/vm" commands to display correct %MEM and
 RSS values

The ps/vm commands may print the bogus value of the %MEM and RSS, the
reason is that the counter of rss stat is updated in asynchronous manner
and may become negative, when the SPLIT_RSS_COUNTING is enabled in kernel.

As a result, crash will read it from memory and convert from negative to
unsigned long integer, eventually it overflows and gets a big integer. For
example:

  crash> ps 1393
      PID    PPID  CPU       TASK        ST  %MEM      VSZ      RSS  COMM
     1393       1  24  ffff9584bb542100  RU  541298032135.9     4132 18014398509481908  enlinuxpc64
                                             ^^^^^^^^^^^^^^          ^^^^^^^^^^^^^^^^^

This is unexpected, crash needs to correct its value for this case.

Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
---
 memory.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/memory.c b/memory.c
index 8724c4aa3d8a..9c15c1b745ef 100644
--- a/memory.c
+++ b/memory.c
@@ -4714,18 +4714,29 @@ get_task_mem_usage(ulong task, struct task_mem_usage *tm)
 		 *  Latest kernels have mm_struct.mm_rss_stat[].
 		 */ 
 		if (VALID_MEMBER(mm_struct_rss_stat)) {
-			long anonpages, filepages;
+			long anonpages, filepages, count;
 
 			anonpages = tt->anonpages;
 			filepages = tt->filepages;
-			rss += LONG(tt->mm_struct +
+			count = LONG(tt->mm_struct +
 				OFFSET(mm_struct_rss_stat) +
 				OFFSET(mm_rss_stat_count) +
 				(filepages * sizeof(long)));
-			rss += LONG(tt->mm_struct +
+
+			/*
+			 * The counter is updated in asynchronous manner
+			 * and may become negative, see:
+			 * include/linux/mm.h: get_mm_counter()
+			 */
+			if (count > 0)
+				rss += count;
+
+			count = LONG(tt->mm_struct +
 				OFFSET(mm_struct_rss_stat) +
 				OFFSET(mm_rss_stat_count) +
 				(anonpages * sizeof(long)));
+			if (count > 0)
+				rss += count;
 		}
 
 		/* Check whether SPLIT_RSS_COUNTING is enabled */
@@ -4769,7 +4780,8 @@ get_task_mem_usage(ulong task, struct task_mem_usage *tm)
 							RETURN_ON_ERROR))
 								continue;
 
-						rss_cache += sync_rss;
+						if (sync_rss > 0)
+							rss_cache += sync_rss;
 
 						/* count 1 -> anonpages */
 						if (!readmem(first->task +
@@ -4782,7 +4794,8 @@ get_task_mem_usage(ulong task, struct task_mem_usage *tm)
 							RETURN_ON_ERROR))
 								continue;
 
-						rss_cache += sync_rss;
+						if (sync_rss > 0)
+							rss_cache += sync_rss;
 
 						if (first == last)
 							break;
-- 
2.37.1