During VM oom condition, kill all threads in process group
Will Schmidt [Tue, 16 Oct 2007 08:24:18 +0000 (01:24 -0700)]
We have had complaints where a threaded application is left in a bad state
after one of it's threads is killed when we hit a VM: out_of_memory
condition.

Killing just one of the process threads can leave the application in a bad
state, whereas killing the entire process group would allow for the
application to restart, or be otherwise handled, and makes it very obvious
that something has gone wrong.

This change allows the entire process group to be taken down, rather
than just the one thread.

Signed-off-by: Will Schmidt <will_schmidt@vnet.ibm.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Ian Molton <spyro@f2s.com>
Cc: Haavard Skinnemoen <hskinnemoen@atmel.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Matthew Wilcox <willy@debian.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Richard Curnow <rc@rc0.org.uk>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Chris Zankel <chris@zankel.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

18 files changed:
arch/alpha/mm/fault.c
arch/arm/mm/fault.c
arch/avr32/mm/fault.c
arch/cris/mm/fault.c
arch/frv/mm/fault.c
arch/ia64/mm/fault.c
arch/m32r/mm/fault.c
arch/m68k/mm/fault.c
arch/mips/mm/fault.c
arch/parisc/mm/fault.c
arch/ppc/mm/fault.c
arch/s390/mm/fault.c
arch/sh/mm/fault.c
arch/sh64/mm/fault.c
arch/sparc/mm/fault.c
arch/sparc64/mm/fault.c
arch/x86/mm/fault_32.c
arch/xtensa/mm/fault.c

index a0e18da..25154df 100644 (file)
@@ -197,7 +197,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
               current->comm, current->pid);
        if (!user_mode(regs))
                goto no_context;
-       do_exit(SIGKILL);
+       do_group_exit(SIGKILL);
 
  do_sigbus:
        /* Send a sigbus, regardless of whether we were in kernel
index 846cce4..59ed1d0 100644 (file)
@@ -266,7 +266,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
                 * the page fault gracefully.
                 */
                printk("VM: killing process %s\n", tsk->comm);
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
                return 0;
        }
        if (fault & VM_FAULT_SIGBUS) {
index ae2d2c5..11472f8 100644 (file)
@@ -216,7 +216,7 @@ out_of_memory:
        }
        printk("VM: Killing process %s\n", tsk->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 8672ab7..8aab814 100644 (file)
@@ -360,7 +360,7 @@ do_page_fault(unsigned long address, struct pt_regs *regs,
        up_read(&mm->mmap_sem);
        printk("VM: killing process %s\n", tsk->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
  do_sigbus:
index 6798fa0..05093d4 100644 (file)
@@ -259,7 +259,7 @@ asmlinkage void do_page_fault(int datammu, unsigned long esr0, unsigned long ear
        up_read(&mm->mmap_sem);
        printk("VM: killing process %s\n", current->comm);
        if (user_mode(__frame))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
  do_sigbus:
index 9150ffa..32f2625 100644 (file)
@@ -281,6 +281,6 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
        }
        printk(KERN_CRIT "VM: killing process %s\n", current->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 }
index 676a1c4..70a766a 100644 (file)
@@ -278,7 +278,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", tsk->comm);
        if (error_code & ACE_USERMODE)
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 578b48f..eaa6186 100644 (file)
@@ -188,7 +188,7 @@ out_of_memory:
 
        printk("VM: killing process %s\n", current->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
 
 no_context:
        current->thread.signo = SIGBUS;
index 521771b..5699c77 100644 (file)
@@ -180,7 +180,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", tsk->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 7899ab8..1c091b4 100644 (file)
@@ -263,6 +263,6 @@ no_context:
        up_read(&mm->mmap_sem);
        printk(KERN_CRIT "VM: killing process %s\n", current->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 }
index b98244e..94913dd 100644 (file)
@@ -297,7 +297,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", current->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        return SIGKILL;
 
 do_sigbus:
index 4c1ac34..14c241c 100644 (file)
@@ -218,7 +218,7 @@ static int do_out_of_memory(struct pt_regs *regs, unsigned long error_code,
        }
        printk("VM: killing process %s\n", tsk->comm);
        if (regs->psw.mask & PSW_MASK_PSTATE)
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        do_no_context(regs, error_code, address);
        return 0;
 }
index 04a39aa..4729668 100644 (file)
@@ -214,7 +214,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", tsk->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 0d069d8..dd81c66 100644 (file)
@@ -334,7 +334,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", tsk->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 50747fe..e4d9c8e 100644 (file)
@@ -369,7 +369,7 @@ out_of_memory:
        up_read(&mm->mmap_sem);
        printk("VM: killing process %s\n", tsk->comm);
        if (from_user)
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 9f7740e..e2027f2 100644 (file)
@@ -463,7 +463,7 @@ out_of_memory:
        up_read(&mm->mmap_sem);
        printk("VM: killing process %s\n", current->comm);
        if (!(regs->tstate & TSTATE_PRIV))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto handle_kernel_fault;
 
 intr_or_no_mm:
index be72c2a..c686ae2 100644 (file)
@@ -593,7 +593,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", tsk->comm);
        if (error_code & 4)
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        goto no_context;
 
 do_sigbus:
index 45d28f2..2f84285 100644 (file)
@@ -152,7 +152,7 @@ out_of_memory:
        }
        printk("VM: killing process %s\n", current->comm);
        if (user_mode(regs))
-               do_exit(SIGKILL);
+               do_group_exit(SIGKILL);
        bad_page_fault(regs, address, SIGKILL);
        return;