Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Tong Tiangen <tongtiangen@huawei.com>
To:     Catalin Marinas <catalin.marinas@arm.com>,
        Mark Rutland <mark.rutland@arm.com>,
        James Morse <james.morse@arm.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        Robin Murphy <robin.murphy@arm.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Will Deacon <will@kernel.org>,
        Alexander Viro <viro@zeniv.linux.org.uk>, <x86@kernel.org>,
        "H . Peter Anvin" <hpa@zytor.com>
CC:     <linux-arm-kernel@lists.infradead.org>,
        <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
        Kefeng Wang <wangkefeng.wang@huawei.com>,
        Guohanjun <guohanjun@huawei.com>,
        Xie XiuQi <xiexiuqi@huawei.com>,
        Tong Tiangen <tongtiangen@huawei.com>
Subject: [PATCH -next v9 2/5] arm64: add support for machine check error safe
Date:   Mon, 8 May 2023 09:44:33 +0800
Message-ID: <20230508014436.198717-3-tongtiangen@huawei.com>
In-Reply-To: <20230508014436.198717-1-tongtiangen@huawei.com>
References: <20230508014436.198717-1-tongtiangen@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

For the arm64 kernel, when it processes hardware memory errors for
synchronize notifications(do_sea()), if the errors is consumed within the
kernel, the current processing is panic. However, it is not optimal.

Take uaccess for example, if the uaccess operation fails due to memory
error, only the user process will be affected. Killing the user process and
isolating the corrupt page is a better choice.

This patch only enable machine error check framework and adds an exception
fixup before the kernel panic in do_sea().

Signed-off-by: Tong Tiangen <tongtiangen@huawei.com>
---
 arch/arm64/Kconfig               |  1 +
 arch/arm64/include/asm/extable.h |  1 +
 arch/arm64/mm/extable.c          | 16 ++++++++++++++++
 arch/arm64/mm/fault.c            | 29 ++++++++++++++++++++++++++++-
 4 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b1201d25a8a4..730b815acfca 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -20,6 +20,7 @@ config ARM64
 	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
 	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
 	select ARCH_HAS_CACHE_LINE_SIZE
+	select ARCH_HAS_COPY_MC if ACPI_APEI_GHES
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
index 72b0e71cc3de..f80ebd0addfd 100644
--- a/arch/arm64/include/asm/extable.h
+++ b/arch/arm64/include/asm/extable.h
@@ -46,4 +46,5 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 #endif /* !CONFIG_BPF_JIT */
 
 bool fixup_exception(struct pt_regs *regs);
+bool fixup_exception_mc(struct pt_regs *regs);
 #endif
diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c
index 228d681a8715..478e639f8680 100644
--- a/arch/arm64/mm/extable.c
+++ b/arch/arm64/mm/extable.c
@@ -76,3 +76,19 @@ bool fixup_exception(struct pt_regs *regs)
 
 	BUG();
 }
+
+bool fixup_exception_mc(struct pt_regs *regs)
+{
+	const struct exception_table_entry *ex;
+
+	ex = search_exception_tables(instruction_pointer(regs));
+	if (!ex)
+		return false;
+
+	/*
+	 * This is not complete, More Machine check safe extable type can
+	 * be processed here.
+	 */
+
+	return false;
+}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 9e0db5c387e3..4d490d820f1a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -749,6 +749,31 @@ static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs)
 	return 1; /* "fault" */
 }
 
+static bool arm64_do_kernel_sea(unsigned long addr, unsigned int esr,
+				     struct pt_regs *regs, int sig, int code)
+{
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_COPY_MC))
+		return false;
+
+	if (user_mode(regs))
+		return false;
+
+	if (apei_claim_sea(regs) < 0)
+		return false;
+
+	if (!fixup_exception_mc(regs))
+		return false;
+
+	if (current->flags & PF_KTHREAD)
+		return true;
+
+	set_thread_esr(0, esr);
+	arm64_force_sig_fault(sig, code, addr,
+		"Uncorrected memory error on access to user memory\n");
+
+	return true;
+}
+
 static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs)
 {
 	const struct fault_info *inf;
@@ -774,7 +799,9 @@ static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs)
 		 */
 		siaddr  = untagged_addr(far);
 	}
-	arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
+
+	if (!arm64_do_kernel_sea(siaddr, esr, regs, inf->sig, inf->code))
+		arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
 
 	return 0;
 }
-- 
2.25.1