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:     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>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>,
        Alexander Viro <viro@zeniv.linux.org.uk>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>, <x86@kernel.org>,
        "H . Peter Anvin" <hpa@zytor.com>
CC:     <linuxppc-dev@lists.ozlabs.org>,
        <linux-arm-kernel@lists.infradead.org>,
        <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
        Kefeng Wang <wangkefeng.wang@huawei.com>,
        Xie XiuQi <xiexiuqi@huawei.com>,
        Guohanjun <guohanjun@huawei.com>,
        Tong Tiangen <tongtiangen@huawei.com>
Subject: [PATCH -next v6 08/10] arm64: add support for machine check error safe
Date:   Tue, 21 Jun 2022 07:26:36 +0000
Message-ID: <20220621072638.1273594-9-tongtiangen@huawei.com>
In-Reply-To: <20220621072638.1273594-1-tongtiangen@huawei.com>
References: <20220621072638.1273594-1-tongtiangen@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

During the processing of arm64 kernel hardware memory errors(do_sea()), if
the errors is consumed in 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, kill the user process
and isolate the user page with hardware memory errors is a better choice.

This patch only enable machine error check framework, it add exception
fixup before kernel panic in do_sea() and only limit the consumption of
hardware memory errors in kernel mode triggered by user mode processes.
If fixup successful, panic can be avoided.

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 9728103a13aa..a636e5ce02b5 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -19,6 +19,7 @@ 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 de166cdeb89a..bd6dd67c9ead 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -700,6 +700,31 @@ 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;
@@ -725,7 +750,9 @@ 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