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;
Sender: "andreyknvl via sendgmr" <andreyknvl@andreyknvl3.muc.corp.google.com>
Date:   Fri, 13 Nov 2020 23:15:55 +0100
In-Reply-To: <cover.1605305705.git.andreyknvl@google.com>
Message-Id: <86f8a9be5ab50af11e5b1203157a39f0d9902024.1605305705.git.andreyknvl@google.com>
Mime-Version: 1.0
References: <cover.1605305705.git.andreyknvl@google.com>
Subject: [PATCH mm v10 27/42] arm64: mte: Add in-kernel tag fault handler
From:   Andrey Konovalov <andreyknvl@google.com>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Vincenzo Frascino <vincenzo.frascino@arm.com>,
        Dmitry Vyukov <dvyukov@google.com>,
        Andrey Ryabinin <aryabinin@virtuozzo.com>,
        Alexander Potapenko <glider@google.com>,
        Marco Elver <elver@google.com>,
        Evgenii Stepanov <eugenis@google.com>,
        Branislav Rankov <Branislav.Rankov@arm.com>,
        Kevin Brodsky <kevin.brodsky@arm.com>,
        kasan-dev@googlegroups.com, linux-arm-kernel@lists.infradead.org,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Andrey Konovalov <andreyknvl@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

From: Vincenzo Frascino <vincenzo.frascino@arm.com>

Add the implementation of the in-kernel fault handler.

When a tag fault happens on a kernel address:
* MTE is disabled on the current CPU,
* the execution continues.

When a tag fault happens on a user address:
* the kernel executes do_bad_area() and panics.

The tag fault handler for kernel addresses is currently empty and will be
filled in by a future commit.

Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Co-developed-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Andrey Konovalov <andreyknvl@google.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
---
Change-Id: I9b8aa79567f7c45f4d6a1290efcf34567e620717
---
 arch/arm64/include/asm/uaccess.h | 23 ++++++++++++++++
 arch/arm64/mm/fault.c            | 45 ++++++++++++++++++++++++++++++++
 2 files changed, 68 insertions(+)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 385a189f7d39..d841a560fae7 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -200,13 +200,36 @@ do {									\
 				CONFIG_ARM64_PAN));			\
 } while (0)
 
+/*
+ * The Tag Check Flag (TCF) mode for MTE is per EL, hence TCF0
+ * affects EL0 and TCF affects EL1 irrespective of which TTBR is
+ * used.
+ * The kernel accesses TTBR0 usually with LDTR/STTR instructions
+ * when UAO is available, so these would act as EL0 accesses using
+ * TCF0.
+ * However futex.h code uses exclusives which would be executed as
+ * EL1, this can potentially cause a tag check fault even if the
+ * user disables TCF0.
+ *
+ * To address the problem we set the PSTATE.TCO bit in uaccess_enable()
+ * and reset it in uaccess_disable().
+ *
+ * The Tag check override (TCO) bit disables temporarily the tag checking
+ * preventing the issue.
+ */
 static inline void uaccess_disable(void)
 {
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+
 	__uaccess_disable(ARM64_HAS_PAN);
 }
 
 static inline void uaccess_enable(void)
 {
+	asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1),
+				 ARM64_MTE, CONFIG_KASAN_HW_TAGS));
+
 	__uaccess_enable(ARM64_HAS_PAN);
 }
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 183d1e6dd9e0..1e4b9353c68a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -34,6 +34,7 @@
 #include <asm/debug-monitors.h>
 #include <asm/esr.h>
 #include <asm/kprobes.h>
+#include <asm/mte.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
@@ -297,6 +298,44 @@ static void die_kernel_fault(const char *msg, unsigned long addr,
 	do_exit(SIGKILL);
 }
 
+static void report_tag_fault(unsigned long addr, unsigned int esr,
+			     struct pt_regs *regs)
+{
+}
+
+static void do_tag_recovery(unsigned long addr, unsigned int esr,
+			   struct pt_regs *regs)
+{
+	static bool reported;
+
+	if (!READ_ONCE(reported)) {
+		report_tag_fault(addr, esr, regs);
+		WRITE_ONCE(reported, true);
+	}
+
+	/*
+	 * Disable MTE Tag Checking on the local CPU for the current EL.
+	 * It will be done lazily on the other CPUs when they will hit a
+	 * tag fault.
+	 */
+	sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_NONE);
+	isb();
+}
+
+static bool is_el1_mte_sync_tag_check_fault(unsigned int esr)
+{
+	unsigned int ec = ESR_ELx_EC(esr);
+	unsigned int fsc = esr & ESR_ELx_FSC;
+
+	if (ec != ESR_ELx_EC_DABT_CUR)
+		return false;
+
+	if (fsc == ESR_ELx_FSC_MTE)
+		return true;
+
+	return false;
+}
+
 static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
@@ -313,6 +352,12 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
 	    "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr))
 		return;
 
+	if (is_el1_mte_sync_tag_check_fault(esr)) {
+		do_tag_recovery(addr, esr, regs);
+
+		return;
+	}
+
 	if (is_el1_permission_fault(addr, esr, regs)) {
 		if (esr & ESR_ELx_WNR)
 			msg = "write to read-only memory";
-- 
2.29.2.299.gdc1121823c-goog