From mboxrd@z Thu Jan 1 00:00:00 1970 From: Mark Rutland Subject: [PATCHv3 09/11] arm64: perf: strip PAC when unwinding userspace Date: Tue, 17 Apr 2018 19:37:33 +0100 Message-ID: <20180417183735.56985-10-mark.rutland@arm.com> References: <20180417183735.56985-1-mark.rutland@arm.com> Return-path: In-Reply-To: <20180417183735.56985-1-mark.rutland@arm.com> Sender: linux-kernel-owner@vger.kernel.org To: linux-arm-kernel@lists.infradead.org Cc: arnd@arndb.de, catalin.marinas@arm.com, cdall@kernel.org, drjones@redhat.com, kvmarm@lists.cs.columbia.edu, linux-arch@vger.kernel.org, marc.zyngier@arm.com, mark.rutland@arm.com, ramana.radhakrishnan@arm.com, suzuki.poulose@arm.com, will.deacon@arm.com, linux-kernel@vger.kernel.org, awallis@codeaurora.org, kernel-hardening@lists.openwall.com List-Id: linux-arch.vger.kernel.org When the kernel is unwinding userspace callchains, we can't expect that the userspace consumer of these callchains has the data necessary to strip the PAC from the stored LR. This patch has the kernel strip the PAC from user stackframes when the in-kernel unwinder is used. This only affects the LR value, and not the FP. This only affects the in-kernel unwinder. When userspace performs unwinding, it is up to userspace to strip PACs as necessary (which can be determined from DWARF information). Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Ramana Radhakrishnan Cc: Will Deacon --- arch/arm64/include/asm/pointer_auth.h | 7 +++++++ arch/arm64/kernel/perf_callchain.c | 5 ++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index 5ff141245633..a9ad81791c7f 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -79,6 +79,12 @@ static inline void ptrauth_keys_dup(struct ptrauth_keys *old, */ #define ptrauth_pac_mask() GENMASK(54, VA_BITS) +/* Only valid for EL0 TTBR0 instruction pointers */ +static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr) +{ + return ptr & ~ptrauth_pac_mask(); +} + #define mm_ctx_ptrauth_init(ctx) \ ptrauth_keys_init(&(ctx)->ptrauth_keys) @@ -89,6 +95,7 @@ static inline void ptrauth_keys_dup(struct ptrauth_keys *old, ptrauth_keys_dup(&(oldctx)->ptrauth_keys, &(newctx)->ptrauth_keys) #else +#define ptrauth_strip_insn_pac(lr) (lr) #define mm_ctx_ptrauth_init(ctx) #define mm_ctx_ptrauth_switch(ctx) #define mm_ctx_ptrauth_dup(oldctx, newctx) diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index bcafd7dcfe8b..928204f6ab08 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -35,6 +35,7 @@ user_backtrace(struct frame_tail __user *tail, { struct frame_tail buftail; unsigned long err; + unsigned long lr; /* Also check accessibility of one struct frame_tail beyond */ if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) @@ -47,7 +48,9 @@ user_backtrace(struct frame_tail __user *tail, if (err) return NULL; - perf_callchain_store(entry, buftail.lr); + lr = ptrauth_strip_insn_pac(buftail.lr); + + perf_callchain_store(entry, lr); /* * Frame pointers should strictly progress back up the stack -- 2.11.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from foss.arm.com ([217.140.101.70]:47076 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752915AbeDQSiP (ORCPT ); Tue, 17 Apr 2018 14:38:15 -0400 From: Mark Rutland Subject: [PATCHv3 09/11] arm64: perf: strip PAC when unwinding userspace Date: Tue, 17 Apr 2018 19:37:33 +0100 Message-ID: <20180417183735.56985-10-mark.rutland@arm.com> In-Reply-To: <20180417183735.56985-1-mark.rutland@arm.com> References: <20180417183735.56985-1-mark.rutland@arm.com> Sender: linux-arch-owner@vger.kernel.org List-ID: To: linux-arm-kernel@lists.infradead.org Cc: arnd@arndb.de, catalin.marinas@arm.com, cdall@kernel.org, drjones@redhat.com, kvmarm@lists.cs.columbia.edu, linux-arch@vger.kernel.org, marc.zyngier@arm.com, mark.rutland@arm.com, ramana.radhakrishnan@arm.com, suzuki.poulose@arm.com, will.deacon@arm.com, linux-kernel@vger.kernel.org, awallis@codeaurora.org, kernel-hardening@lists.openwall.com Message-ID: <20180417183733.2Rg_dW9sl3YCbNq48jUDqAbQ8kiUFUE6suuFmQv9TQM@z> When the kernel is unwinding userspace callchains, we can't expect that the userspace consumer of these callchains has the data necessary to strip the PAC from the stored LR. This patch has the kernel strip the PAC from user stackframes when the in-kernel unwinder is used. This only affects the LR value, and not the FP. This only affects the in-kernel unwinder. When userspace performs unwinding, it is up to userspace to strip PACs as necessary (which can be determined from DWARF information). Signed-off-by: Mark Rutland Cc: Catalin Marinas Cc: Ramana Radhakrishnan Cc: Will Deacon --- arch/arm64/include/asm/pointer_auth.h | 7 +++++++ arch/arm64/kernel/perf_callchain.c | 5 ++++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index 5ff141245633..a9ad81791c7f 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -79,6 +79,12 @@ static inline void ptrauth_keys_dup(struct ptrauth_keys *old, */ #define ptrauth_pac_mask() GENMASK(54, VA_BITS) +/* Only valid for EL0 TTBR0 instruction pointers */ +static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr) +{ + return ptr & ~ptrauth_pac_mask(); +} + #define mm_ctx_ptrauth_init(ctx) \ ptrauth_keys_init(&(ctx)->ptrauth_keys) @@ -89,6 +95,7 @@ static inline void ptrauth_keys_dup(struct ptrauth_keys *old, ptrauth_keys_dup(&(oldctx)->ptrauth_keys, &(newctx)->ptrauth_keys) #else +#define ptrauth_strip_insn_pac(lr) (lr) #define mm_ctx_ptrauth_init(ctx) #define mm_ctx_ptrauth_switch(ctx) #define mm_ctx_ptrauth_dup(oldctx, newctx) diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index bcafd7dcfe8b..928204f6ab08 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -35,6 +35,7 @@ user_backtrace(struct frame_tail __user *tail, { struct frame_tail buftail; unsigned long err; + unsigned long lr; /* Also check accessibility of one struct frame_tail beyond */ if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) @@ -47,7 +48,9 @@ user_backtrace(struct frame_tail __user *tail, if (err) return NULL; - perf_callchain_store(entry, buftail.lr); + lr = ptrauth_strip_insn_pac(buftail.lr); + + perf_callchain_store(entry, lr); /* * Frame pointers should strictly progress back up the stack -- 2.11.0