aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPaul Jackson <pj@sgi.com>2006-05-20 18:00:09 -0400
committerLinus Torvalds <torvalds@g5.osdl.org>2006-05-21 15:59:18 -0400
commitbdd804f478a0cc74bf7db8e9f9d5fd379d1b31ca (patch)
tree2b8f083b1ca698c0f9321b3714dab036d2531f29
parent593ee20766921fec643194dff829e17f30552220 (diff)
[PATCH] Cpuset: might sleep checking zones allowed fix
Fix a couple of infrequently encountered 'sleeping function called from invalid context' in the cpuset hooks in __alloc_pages. Could sleep while interrupts disabled. The routine cpuset_zone_allowed() is called by code in mm/page_alloc.c __alloc_pages() to determine if a zone is allowed in the current tasks cpuset. This routine can sleep, for certain GFP_KERNEL allocations, if the zone is on a memory node not allowed in the current cpuset, but might be allowed in a parent cpuset. But we can't sleep in __alloc_pages() if in interrupt, nor if called for a GFP_ATOMIC request (__GFP_WAIT not set in gfp_flags). The rule was intended to be: Don't call cpuset_zone_allowed() if you can't sleep, unless you pass in the __GFP_HARDWALL flag set in gfp_flag, which disables the code that might scan up ancestor cpusets and sleep. This rule was being violated in a couple of places, due to a bogus change made (by myself, pj) to __alloc_pages() as part of the November 2005 effort to cleanup its logic, and also due to a later fix to constrain which swap daemons were awoken. The bogus change can be seen at: http://linux.derkeiler.com/Mailing-Lists/Kernel/2005-11/4691.html [PATCH 01/05] mm fix __alloc_pages cpuset ALLOC_* flags This was first noticed on a tight memory system, in code that was disabling interrupts and doing allocation requests with __GFP_WAIT not set, which resulted in __might_sleep() writing complaints to the log "Debug: sleeping function called ...", when the code in cpuset_zone_allowed() tried to take the callback_sem cpuset semaphore. We haven't seen a system hang on this 'might_sleep' yet, but we are at decent risk of seeing it fairly soon, especially since the additional cpuset_zone_allowed() check was added, conditioning wakeup_kswapd(), in March 2006. Special thanks to Dave Chinner, for figuring this out, and a tip of the hat to Nick Piggin who warned me of this back in Nov 2005, before I was ready to listen. Signed-off-by: Paul Jackson <pj@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--mm/page_alloc.c5
1 files changed, 3 insertions, 2 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 813b4ec1298a..bb3416932ab0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -951,7 +951,7 @@ restart:
951 goto got_pg; 951 goto got_pg;
952 952
953 do { 953 do {
954 if (cpuset_zone_allowed(*z, gfp_mask)) 954 if (cpuset_zone_allowed(*z, gfp_mask|__GFP_HARDWALL))
955 wakeup_kswapd(*z, order); 955 wakeup_kswapd(*z, order);
956 } while (*(++z)); 956 } while (*(++z));
957 957
@@ -970,7 +970,8 @@ restart:
970 alloc_flags |= ALLOC_HARDER; 970 alloc_flags |= ALLOC_HARDER;
971 if (gfp_mask & __GFP_HIGH) 971 if (gfp_mask & __GFP_HIGH)
972 alloc_flags |= ALLOC_HIGH; 972 alloc_flags |= ALLOC_HIGH;
973 alloc_flags |= ALLOC_CPUSET; 973 if (wait)
974 alloc_flags |= ALLOC_CPUSET;
974 975
975 /* 976 /*
976 * Go through the zonelist again. Let __GFP_HIGH and allocations 977 * Go through the zonelist again. Let __GFP_HIGH and allocations