From: "Luck, Tony" <tony.luck@intel.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>,
Paul McKenney <paulmck@linux.vnet.ibm.com>,
X86 ML <x86@kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Oleg Nesterov <oleg@redhat.com>, Andi Kleen <andi@firstfloor.org>,
Josh Triplett <josh@joshtriplett.org>, <fweisbec@gmail.com>
Subject: [PATCH] x86, mce: Get rid of TIF_MCE_NOTIFY and associated mce tricks
Date: Mon, 05 Jan 2015 16:44:42 -0800 [thread overview]
Message-ID: <54ab2ffa301102cd6e@agluck-desk.sc.intel.com> (raw)
In-Reply-To: <CALCETrV6=aWoAckieQkPJ4BCr9VzU=9080EmLfeL4ZWm+Hr55g@mail.gmail.com>
We now switch to the kernel stack when a machine check interrupts
during user mode. This means that we can perform recovery actions
in the tail of do_machine_check()
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
On top of Andy's x86/paranoid branch
Andy: Should I really move that:
pr_err("Uncorrected hardware memory error ...
inside the ist_begin_non_atomic() section?
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 51b26e895933..9b3de99dc004 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -190,7 +190,6 @@ enum mcp_flags {
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
int mce_notify_irq(void);
-void mce_notify_process(void);
DECLARE_PER_CPU(struct mce, injectm);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8b13b0fbda8e..e82e95abc92b 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -75,7 +75,6 @@ struct thread_info {
#define TIF_SYSCALL_EMU 6 /* syscall emulation active */
#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */
#define TIF_SECCOMP 8 /* secure computing */
-#define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */
#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
#define TIF_UPROBE 12 /* breakpointed or singlestepping */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
@@ -100,7 +99,6 @@ struct thread_info {
#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
-#define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY)
#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY)
#define _TIF_UPROBE (1 << TIF_UPROBE)
#define _TIF_NOTSC (1 << TIF_NOTSC)
@@ -140,7 +138,7 @@ struct thread_info {
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
- (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \
+ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \
_TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
/* flags to check in __switch_to() */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 800d423f1e92..f17a4f1aaa5d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1004,51 +1004,6 @@ static void mce_clear_state(unsigned long *toclear)
}
/*
- * Need to save faulting physical address associated with a process
- * in the machine check handler some place where we can grab it back
- * later in mce_notify_process()
- */
-#define MCE_INFO_MAX 16
-
-struct mce_info {
- atomic_t inuse;
- struct task_struct *t;
- __u64 paddr;
- int restartable;
-} mce_info[MCE_INFO_MAX];
-
-static void mce_save_info(__u64 addr, int c)
-{
- struct mce_info *mi;
-
- for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) {
- if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
- mi->t = current;
- mi->paddr = addr;
- mi->restartable = c;
- return;
- }
- }
-
- mce_panic("Too many concurrent recoverable errors", NULL, NULL);
-}
-
-static struct mce_info *mce_find_info(void)
-{
- struct mce_info *mi;
-
- for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++)
- if (atomic_read(&mi->inuse) && mi->t == current)
- return mi;
- return NULL;
-}
-
-static void mce_clear_info(struct mce_info *mi)
-{
- atomic_set(&mi->inuse, 0);
-}
-
-/*
* The actual machine check handler. This only handles real
* exceptions when something got corrupted coming in through int 18.
*
@@ -1086,6 +1041,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
char *msg = "Unknown";
+ u64 recover_paddr = ~0ull;
+ int flags = MF_ACTION_REQUIRED;
prev_state = ist_enter(regs);
@@ -1207,9 +1164,9 @@ void do_machine_check(struct pt_regs *regs, long error_code)
if (no_way_out)
mce_panic("Fatal machine check on current CPU", &m, msg);
if (worst == MCE_AR_SEVERITY) {
- /* schedule action before return to userland */
- mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
- set_thread_flag(TIF_MCE_NOTIFY);
+ recover_paddr = m.addr;
+ if (!(m.mcgstatus & MCG_STATUS_RIPV))
+ flags |= MF_MUST_KILL;
} else if (kill_it) {
force_sig(SIGBUS, current);
}
@@ -1220,6 +1177,26 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
out:
sync_core();
+
+ if (recover_paddr == ~0ull)
+ goto done;
+
+ pr_err("Uncorrected hardware memory error in user-access at %llx",
+ recover_paddr);
+ /*
+ * We must call memory_failure() here even if the current process is
+ * doomed. We still need to mark the page as poisoned and alert any
+ * other users of the page.
+ */
+ ist_begin_non_atomic(regs);
+ local_irq_enable();
+ if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) {
+ pr_err("Memory error not recovered");
+ force_sig(SIGBUS, current);
+ }
+ local_irq_disable();
+ ist_end_non_atomic();
+done:
ist_exit(regs, prev_state);
}
EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1238,42 +1215,6 @@ int memory_failure(unsigned long pfn, int vector, int flags)
#endif
/*
- * Called in process context that interrupted by MCE and marked with
- * TIF_MCE_NOTIFY, just before returning to erroneous userland.
- * This code is allowed to sleep.
- * Attempt possible recovery such as calling the high level VM handler to
- * process any corrupted pages, and kill/signal current process if required.
- * Action required errors are handled here.
- */
-void mce_notify_process(void)
-{
- unsigned long pfn;
- struct mce_info *mi = mce_find_info();
- int flags = MF_ACTION_REQUIRED;
-
- if (!mi)
- mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL);
- pfn = mi->paddr >> PAGE_SHIFT;
-
- clear_thread_flag(TIF_MCE_NOTIFY);
-
- pr_err("Uncorrected hardware memory error in user-access at %llx",
- mi->paddr);
- /*
- * We must call memory_failure() here even if the current process is
- * doomed. We still need to mark the page as poisoned and alert any
- * other users of the page.
- */
- if (!mi->restartable)
- flags |= MF_MUST_KILL;
- if (memory_failure(pfn, MCE_VECTOR, flags) < 0) {
- pr_err("Memory error not recovered");
- force_sig(SIGBUS, current);
- }
- mce_clear_info(mi);
-}
-
-/*
* Action optional processing happens here (picking up
* from the list of faulting pages that do_machine_check()
* placed into the "ring").
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index ed37a768d0fc..2a33c8f68319 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -740,12 +740,6 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
user_exit();
-#ifdef CONFIG_X86_MCE
- /* notify userspace of pending MCEs */
- if (thread_info_flags & _TIF_MCE_NOTIFY)
- mce_notify_process();
-#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
-
if (thread_info_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
next prev parent reply other threads:[~2015-01-06 0:44 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-21 21:26 [PATCH v4 0/5] x86: Rework IST interrupts Andy Lutomirski
2014-11-21 21:26 ` [PATCH v4 1/5] uprobes, x86: Fix _TIF_UPROBE vs _TIF_NOTIFY_RESUME Andy Lutomirski
2014-11-22 16:55 ` Borislav Petkov
2014-11-24 17:58 ` Andy Lutomirski
2014-11-21 21:26 ` [PATCH v4 2/5] x86, traps: Track entry into and exit from IST context Andy Lutomirski
2014-11-21 21:32 ` Andy Lutomirski
2014-11-21 22:07 ` Paul E. McKenney
2014-11-21 22:19 ` Andy Lutomirski
2014-11-21 22:55 ` Paul E. McKenney
2014-11-21 23:06 ` Andy Lutomirski
2014-11-21 23:38 ` Paul E. McKenney
2014-11-22 2:00 ` Andy Lutomirski
2014-11-22 4:20 ` Paul E. McKenney
2014-11-22 5:53 ` Andy Lutomirski
2014-11-22 23:41 ` Paul E. McKenney
2014-11-24 20:22 ` Andy Lutomirski
2014-11-24 20:54 ` Paul E. McKenney
2014-11-24 21:02 ` Andy Lutomirski
2014-11-24 21:35 ` Paul E. McKenney
2014-11-24 22:34 ` Paul E. McKenney
2014-11-24 22:36 ` Andy Lutomirski
2014-11-24 22:57 ` Paul E. McKenney
2014-11-24 23:31 ` Paul E. McKenney
2014-11-24 23:35 ` Andy Lutomirski
2014-11-24 23:50 ` Paul E. McKenney
2014-11-24 23:52 ` Andy Lutomirski
2014-11-25 18:58 ` Borislav Petkov
2014-11-25 19:16 ` Paul E. McKenney
2014-12-11 0:22 ` Tony Luck
2014-12-11 0:24 ` Andy Lutomirski
2015-01-05 21:46 ` Tony Luck
2015-01-05 21:54 ` Andy Lutomirski
2015-01-06 0:44 ` Luck, Tony [this message]
2015-01-06 1:01 ` [PATCH] x86, mce: Get rid of TIF_MCE_NOTIFY and associated mce tricks Andy Lutomirski
2015-01-06 18:00 ` Luck, Tony
2015-01-07 12:13 ` Borislav Petkov
2015-01-07 15:51 ` Andy Lutomirski
2015-01-07 15:58 ` Borislav Petkov
2015-01-07 16:12 ` Paul E. McKenney
2014-11-25 17:13 ` [PATCH v4 2/5] x86, traps: Track entry into and exit from IST context Paul E. McKenney
2014-11-27 7:03 ` Lai Jiangshan
2014-11-27 16:46 ` Paul E. McKenney
2014-11-24 21:27 ` Paul E. McKenney
2014-11-21 22:20 ` Frederic Weisbecker
2014-11-21 22:00 ` Paul E. McKenney
2014-11-22 17:20 ` Borislav Petkov
2014-11-24 19:48 ` Andy Lutomirski
2015-01-22 21:52 ` Sasha Levin
2015-01-23 17:58 ` Andy Lutomirski
2015-01-23 18:04 ` Borislav Petkov
2015-01-23 18:34 ` Andy Lutomirski
2015-01-23 20:48 ` Sasha Levin
2015-01-24 1:25 ` Andy Lutomirski
2015-01-28 16:33 ` Andy Lutomirski
2015-01-28 17:48 ` Paul E. McKenney
2015-01-28 21:02 ` Andy Lutomirski
2015-01-30 19:57 ` Sasha Levin
2015-01-31 1:28 ` Sasha Levin
2015-01-31 3:12 ` Andy Lutomirski
2015-01-31 12:50 ` Andy Lutomirski
2015-01-31 13:01 ` [PATCH] x86, traps: Fix ist_enter from userspace Andy Lutomirski
2015-01-31 15:09 ` Sasha Levin
2015-01-31 16:18 ` Paul E. McKenney
2015-02-01 2:17 ` Andy Lutomirski
2015-02-04 6:01 ` [tip:x86/asm] " tip-bot for Andy Lutomirski
2014-11-21 21:26 ` [PATCH v4 3/5] x86, entry: Switch stacks on a paranoid entry " Andy Lutomirski
2014-11-24 15:55 ` Borislav Petkov
2014-11-21 21:26 ` [PATCH v4 4/5] x86: Clean up current_stack_pointer Andy Lutomirski
2014-11-24 11:39 ` Borislav Petkov
2014-11-21 21:26 ` [PATCH v4 5/5] x86, traps: Add ist_begin_non_atomic and ist_end_non_atomic Andy Lutomirski
2014-11-24 15:54 ` Borislav Petkov
2014-11-24 19:52 ` Andy Lutomirski
-- strict thread matches above, loose matches on Subject: below --
2014-11-18 23:15 [PATCH v3 0/3] Handle IST interrupts from userspace on the normal stack Andy Lutomirski
2014-11-19 22:15 ` [PATCH] x86, mce: Get rid of TIF_MCE_NOTIFY and associated mce tricks Luck, Tony
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=54ab2ffa301102cd6e@agluck-desk.sc.intel.com \
--to=tony.luck@intel.com \
--cc=andi@firstfloor.org \
--cc=bp@alien8.de \
--cc=fweisbec@gmail.com \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=torvalds@linux-foundation.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).