x86/mce: Delay clearing IA32_MCG_STATUS to the end of do_machine_check()

A long time ago, Linux cleared IA32_MCG_STATUS at the very end of machine
check processing.

Then, some fancy recovery and IST manipulation was added in:

  d4812e169de4 ("x86, mce: Get rid of TIF_MCE_NOTIFY and associated mce tricks")

and clearing IA32_MCG_STATUS was pulled earlier in the function.

Next change moved the actual recovery out of do_machine_check() and
just used task_work_add() to schedule it later (before returning to the
user):

  5567d11c21a1 ("x86/mce: Send #MC singal from task work")

Most recently the fancy IST footwork was removed as no longer needed:

  b052df3da821 ("x86/entry: Get rid of ist_begin/end_non_atomic()")

At this point there is no reason remaining to clear IA32_MCG_STATUS early.
It can move back to the very end of the function.

Also move sync_core(). The comments for this function say that it should
only be called when instructions have been changed/re-mapped. Recovery
for an instruction fetch may change the physical address. But that
doesn't happen until the scheduled work runs (which could be on another
CPU).

 [ bp: Massage commit message. ]

Reported-by: Gabriele Paoloni <[email protected]>
Signed-off-by: Tony Luck <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

1 files changed, 4 insertions, 5 deletions

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index f43a78bde670..0ba24dfffdb2 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1190,6 +1190,7 @@ static void kill_me_maybe(struct callback_head *cb)
 
 	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
 		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
+		sync_core();
 		return;
 	}
 
@@ -1330,12 +1331,8 @@ noinstr void do_machine_check(struct pt_regs *regs)
 	if (worst > 0)
 		irq_work_queue(&mce_irq_work);
 
-	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-
-	sync_core();
-
 	if (worst != MCE_AR_SEVERITY && !kill_it)
-		return;
+		goto out;
 
 	/* Fault was in user mode and we need to take some action */
 	if ((m.cs & 3) == 3) {
@@ -1364,6 +1361,8 @@ noinstr void do_machine_check(struct pt_regs *regs)
 				mce_panic("Failed kernel mode recovery", &m, msg);
 		}
 	}
+out:
+	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);