[PATCH 6.6.y] x86/mce: Fix hardware debug register corruption on task migration

[Sasha Levin <sashal@kernel.org>]

From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>

[ Upstream commit b8d1d5b63a8ef532038eebd9d97d406860385668 ]

In exc_machine_check_user(), local_db_save() and local_db_restore() are
invoked in the outer entry stubs (DEFINE_IDTENTRY_MCE_USER,
DEFINE_FREDENTRY_MCE, and DEFINE_IDTENTRY_RAW), surrounding
exc_machine_check_user().

However, exc_machine_check_user() calls irqentry_exit_to_user_mode(), which
handles pending thread work and may schedule() if TIF_NEED_RESCHED is set. If
the task migrates to another CPU during schedule(), local_db_restore() runs on
the new CPU with the dr7 state saved from the old CPU. This corrupts the new
CPU's DR7 hardware debug register and leaves the old CPU's DR7 disabled.  In
short, local_db_save() and local_db_restore() pair must be run on the same
CPU.

To fix this, move local_db_save() and local_db_restore() inside
exc_machine_check_user() and exc_machine_check_kernel(). In
exc_machine_check_user(), DR7 is saved and restored strictly around
do_machine_check() to avoid schedule() during migration. In
exc_machine_check_kernel(), local_db_save() is called at the entry point to
prevent early memory accesses from triggering nested #DB exceptions, and
restored on all exits.

Fixes: cd840e424f27 ("x86/entry, mce: Disallow #DB during #MC")
Assisted-by: LLM
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@kernel.org>
Link: https://patch.msgid.link/179005109564.388919.3937970081044095776.stgit@devnote2
[ Omitted changes to the FRED machine-check handler because it is absent in Linux 6.6. ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kernel/cpu/mce/core.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 106436ec3c005..fe1bbe1973321 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2114,6 +2114,9 @@ bool filter_mce(struct mce *m)
 static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 {
 	irqentry_state_t irq_state;
+	unsigned long dr7;
+
+	dr7 = local_db_save();
 
 	WARN_ON_ONCE(user_mode(regs));
 
@@ -2122,20 +2125,26 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 	 * mce_check_crashing_cpu() for details.
 	 */
 	if (mca_cfg.initialized && mce_check_crashing_cpu())
-		return;
+		goto out;
 
 	irq_state = irqentry_nmi_enter(regs);
 
 	do_machine_check(regs);
 
 	irqentry_nmi_exit(regs, irq_state);
+out:
+	local_db_restore(dr7);
 }
 
 static __always_inline void exc_machine_check_user(struct pt_regs *regs)
 {
+	unsigned long dr7;
+
 	irqentry_enter_from_user_mode(regs);
 
+	dr7 = local_db_save();
 	do_machine_check(regs);
+	local_db_restore(dr7);
 
 	irqentry_exit_to_user_mode(regs);
 }
@@ -2144,34 +2153,22 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs)
 /* MCE hit kernel mode */
 DEFINE_IDTENTRY_MCE(exc_machine_check)
 {
-	unsigned long dr7;
-
-	dr7 = local_db_save();
 	exc_machine_check_kernel(regs);
-	local_db_restore(dr7);
 }
 
 /* The user mode variant. */
 DEFINE_IDTENTRY_MCE_USER(exc_machine_check)
 {
-	unsigned long dr7;
-
-	dr7 = local_db_save();
 	exc_machine_check_user(regs);
-	local_db_restore(dr7);
 }
 #else
 /* 32bit unified entry point */
 DEFINE_IDTENTRY_RAW(exc_machine_check)
 {
-	unsigned long dr7;
-
-	dr7 = local_db_save();
 	if (user_mode(regs))
 		exc_machine_check_user(regs);
 	else
 		exc_machine_check_kernel(regs);
-	local_db_restore(dr7);
 }
 #endif
 
-- 
2.53.0