Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 1 Feb 2021 16:17:49 +0800
From:   Aili Yao <yaoaili@kingsoft.com>
To:     <tony.luck@intel.com>, <dave.hansen@linux.intel.com>,
        <luto@kernel.org>, <peterz@infradead.org>, <tglx@linutronix.de>,
        <mingo@redhat.com>, <bp@alien8.de>, <naoya.horiguchi@nec.com>,
        <hpa@zytor.com>, <x86@kernel.org>, <hpa@zytor.com>
CC:     <YANGFENG1@kingsoft.com>, <linux-mm@kvack.org>,
        <linux-kernel@vger.kernel.org>
Subject: [PATCH v2] x86/fault: Send a SIGBUS to user process always for
 hwpoison page access.
Message-ID: <20210201161749.0e8dc212.yaoaili@kingsoft.com>
Organization: Kingsoft
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Precedence: bulk

When one page is already hwpoisoned by AO action, process may not be
killed, the process mapping this page may make a syscall include this
page and result to trigger a VM_FAULT_HWPOISON fault, if it's in kernel
mode it may be fixed by fixup_exception. Current code will just return
error code to user process.

This is not sufficient, we should send a SIGBUS to the process and log
the info to console, as we can't trust the process will handle the error
correctly.

Suggested-by: Feng Yang <yangfeng1@kingsoft.com>
Signed-off-by: Aili Yao <yaoaili@kingsoft.com>
---
 arch/x86/mm/fault.c | 34 +++++++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 7 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f1f1b5a0956a..23095b94cf42 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -631,7 +631,7 @@ static void set_signal_archinfo(unsigned long address,
 
 static noinline void
 no_context(struct pt_regs *regs, unsigned long error_code,
-	   unsigned long address, int signal, int si_code)
+	   unsigned long address, int signal, int si_code, vm_fault_t fault)
 {
 	struct task_struct *tsk = current;
 	unsigned long flags;
@@ -662,12 +662,32 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 		 * In this case we need to make sure we're not recursively
 		 * faulting through the emulate_vsyscall() logic.
 		 */
+
+		if (IS_ENABLED(CONFIG_MEMORY_FAILURE) &&
+		    fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+			unsigned int lsb = 0;
+
+			pr_err("MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+				current->comm, current->pid, address);
+
+			sanitize_error_code(address, &error_code);
+			set_signal_archinfo(address, error_code);
+
+			if (fault & VM_FAULT_HWPOISON_LARGE)
+				lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+			if (fault & VM_FAULT_HWPOISON)
+				lsb = PAGE_SHIFT;
+
+			force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb);
+
+			return;
+		}
+
 		if (current->thread.sig_on_uaccess_err && signal) {
 			sanitize_error_code(address, &error_code);
 
 			set_signal_archinfo(address, error_code);
 
-			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_fault(signal, si_code, (void __user *)address);
 		}
 
@@ -836,7 +856,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 	if (is_f00f_bug(regs, address))
 		return;
 
-	no_context(regs, error_code, address, SIGSEGV, si_code);
+	no_context(regs, error_code, address, SIGSEGV, si_code, 0);
 }
 
 static noinline void
@@ -927,7 +947,7 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 {
 	/* Kernel mode? Handle exceptions or die: */
 	if (!(error_code & X86_PF_USER)) {
-		no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
+		no_context(regs, error_code, address, SIGBUS, BUS_ADRERR, fault);
 		return;
 	}
 
@@ -966,7 +986,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, vm_fault_t fault)
 {
 	if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) {
-		no_context(regs, error_code, address, 0, 0);
+		no_context(regs, error_code, address, 0, 0, 0);
 		return;
 	}
 
@@ -974,7 +994,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		/* Kernel mode? Handle exceptions or die: */
 		if (!(error_code & X86_PF_USER)) {
 			no_context(regs, error_code, address,
-				   SIGSEGV, SEGV_MAPERR);
+				   SIGSEGV, SEGV_MAPERR, 0);
 			return;
 		}
 
@@ -1396,7 +1416,7 @@ void do_user_addr_fault(struct pt_regs *regs,
 	if (fault_signal_pending(fault, regs)) {
 		if (!user_mode(regs))
 			no_context(regs, hw_error_code, address, SIGBUS,
-				   BUS_ADRERR);
+				   BUS_ADRERR, 0);
 		return;
 	}
 
-- 
2.25.1