From 67159813127309c1a65d86e40fa0368241fa668c Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 8 Sep 2010 10:19:41 +0900 Subject: page-types.c: fix name of unpoison interface The page-types utility still uses an out of date name for the unpoison interface: debugfs:hwpoison/renew-pfn This patch renames and fixes it. Signed-off-by: Naoya Horiguchi Acked-by: Wu Fengguang Signed-off-by: Andi Kleen --- Documentation/vm/page-types.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c index ccd951f..cc96ee2 100644 --- a/Documentation/vm/page-types.c +++ b/Documentation/vm/page-types.c @@ -478,7 +478,7 @@ static void prepare_hwpoison_fd(void) } if (opt_unpoison && !hwpoison_forget_fd) { - sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs); + sprintf(buf, "%s/unpoison-pfn", hwpoison_debug_fs); hwpoison_forget_fd = checked_open(buf, O_WRONLY); } } -- cgit v1.1 From a337fdac7a5622d1e6547f4b476c14dfe5a2c892 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 27 Sep 2010 20:32:19 +0200 Subject: HWPOISON: Copy si_addr_lsb to user The original hwpoison code added a new siginfo field si_addr_lsb to pass the granuality of the fault address to user space. Unfortunately this field was never copied to user space. Fix this here. I added explicit checks for the MCEERR codes to avoid having to patch all potential callers to initialize the field. Signed-off-by: Andi Kleen --- kernel/signal.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/signal.c b/kernel/signal.c index bded651..919562c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2215,6 +2215,14 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) #ifdef __ARCH_SI_TRAPNO err |= __put_user(from->si_trapno, &to->si_trapno); #endif +#ifdef BUS_MCEERR_AO + /* + * Other callers might not initialize the si_lsb field, + * so check explicitely for the right codes here. + */ + if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO) + err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb); +#endif break; case __SI_CHLD: err |= __put_user(from->si_pid, &to->si_pid); -- cgit v1.1 From 0d9ee6a2d4a6e92c49e6fa9469e5731d21ee203e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 27 Sep 2010 22:03:33 +0200 Subject: HWPOISON: Report correct address granuality for AO huge page errors The SIGBUS user space signalling is supposed to report the address granuality of a corruption. Pass this information correctly for huge pages by querying the hpage order. Reviewed-by: Naoya Horiguchi Reviewed-by: Wu Fengguang Signed-off-by: Andi Kleen --- mm/memory-failure.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9c26eec..cd7e697 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -183,7 +183,7 @@ EXPORT_SYMBOL_GPL(hwpoison_filter); * signal. */ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno, - unsigned long pfn) + unsigned long pfn, struct page *page) { struct siginfo si; int ret; @@ -198,7 +198,7 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno, #ifdef __ARCH_SI_TRAPNO si.si_trapno = trapno; #endif - si.si_addr_lsb = PAGE_SHIFT; + si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT; /* * Don't use force here, it's convenient if the signal * can be temporarily blocked. @@ -327,7 +327,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * wrong earlier. */ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno, - int fail, unsigned long pfn) + int fail, struct page *page, unsigned long pfn) { struct to_kill *tk, *next; @@ -352,7 +352,7 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno, * process anyways. */ else if (kill_proc_ao(tk->tsk, tk->addr, trapno, - pfn) < 0) + pfn, page) < 0) printk(KERN_ERR "MCE %#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); @@ -928,7 +928,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * any accesses to the poisoned memory. */ kill_procs_ao(&tokill, !!PageDirty(hpage), trapno, - ret != SWAP_SUCCESS, pfn); + ret != SWAP_SUCCESS, p, pfn); return ret; } -- cgit v1.1 From 47f43e7efadacc627f325aba64c6a547de0926db Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 28 Sep 2010 07:37:55 +0200 Subject: HWPOISON: Stop shrinking at right page count When we call the slab shrinker to free a page we need to stop at page count one because the caller always holds a single reference, not zero. This avoids useless looping over slab shrinkers and freeing too much memory. Reviewed-by: Wu Fengguang Signed-off-by: Andi Kleen --- mm/memory-failure.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index cd7e697..757f6b0 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -235,7 +235,7 @@ void shake_page(struct page *p, int access) int nr; do { nr = shrink_slab(1000, GFP_KERNEL, 1000); - if (page_count(p) == 0) + if (page_count(p) == 1) break; } while (nr > 10); } -- cgit v1.1