lkml.org 
[lkml]   [2006]   [Apr]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    SubjectRe: [(resend)patch 3/7] Notify page fault call chain for ia64
    Date
    Anil S Keshavamurthy (on Wed, 19 Apr 2006 15:14:22 -0700) wrote:
    >Overloading of page fault notification with the
    >notify_die() has performance issues(since the
    >only interested components for page fault is
    >kprobes and/or kdb) and hence this patch introduces
    >the new notifier call chain exclusively for page
    >fault notifications their by avoiding notifying
    >unnecessary components in the do_page_fault() code
    >path.
    >
    >Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
    >
    >---
    > arch/ia64/kernel/traps.c | 11 +++++++++++
    >===================================================================
    >--- linux-2.6.17-rc1-mm3.orig/arch/ia64/kernel/traps.c
    >+++ linux-2.6.17-rc1-mm3/arch/ia64/kernel/traps.c
    >@@ -31,6 +31,7 @@ fpswa_interface_t *fpswa_interface;
    > EXPORT_SYMBOL(fpswa_interface);
    >
    > ATOMIC_NOTIFIER_HEAD(ia64die_chain);
    >+ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
    >
    > int
    > register_die_notifier(struct notifier_block *nb)
    >@@ -46,6 +47,16 @@ unregister_die_notifier(struct notifier_
    > }
    > EXPORT_SYMBOL_GPL(unregister_die_notifier);
    >
    >+int register_page_fault_notifier(struct notifier_block *nb)
    >+{
    >+ return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
    >+}
    >+
    >+int unregister_page_fault_notifier(struct notifier_block *nb)
    >+{
    >+ return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
    >+}
    >+

    Why is register_page_fault_notifier defined in traps.c? Surely it
    should be in mm/fault.c, which is the only place that uses the chain.

    > trap_init (void)
    > {
    >Index: linux-2.6.17-rc1-mm3/arch/ia64/mm/fault.c
    >===================================================================
    >--- linux-2.6.17-rc1-mm3.orig/arch/ia64/mm/fault.c
    >+++ linux-2.6.17-rc1-mm3/arch/ia64/mm/fault.c
    >@@ -84,7 +84,7 @@ ia64_do_page_fault (unsigned long addres
    > /*
    > * This is to handle the kprobes on user space access instructions
    > */
    >- if (notify_die(DIE_PAGE_FAULT, "page fault", regs, code, TRAP_BRKPT,
    >+ if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, code, TRAP_BRKPT,
    > SIGSEGV) == NOTIFY_STOP)
    > return;

    Since this is a critical path, please remove all references to
    notify_page_fault() and its register functions when CONFIG_KPROBES=n.

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2006-04-20 04:22    [W:2.523 / U:0.016 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site