linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Viresh Kumar <viresh.kumar@linaro.org>
To: linux-arm-kernel@lists.infradead.org,
	Julien Thierry <Julien.Thierry@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
	Marc Zyngier <marc.zyngier@arm.com>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Will Deacon <will.deacon@arm.com>,
	stable@vger.kernel.org, mark.brown@arm.com,
	Catalin Marinas <catalin.marinas@arm.com>,
	Russell King <rmk+kernel@arm.linux.org.uk>
Subject: [PATCH v4.4 09/45] arm64: uaccess: Don't bother eliding access_ok checks in __{get, put}_user
Date: Fri, 14 Jun 2019 08:37:52 +0530	[thread overview]
Message-ID: <fa281cb205c71d33bc2d9f971717d4073409f43e.1560480942.git.viresh.kumar@linaro.org> (raw)
In-Reply-To: <cover.1560480942.git.viresh.kumar@linaro.org>

From: Will Deacon <will.deacon@arm.com>

commit 84624087dd7e3b482b7b11c170ebc1f329b3a218 upstream.

access_ok isn't an expensive operation once the addr_limit for the current
thread has been loaded into the cache. Given that the initial access_ok
check preceding a sequence of __{get,put}_user operations will take
the brunt of the miss, we can make the __* variants identical to the
full-fat versions, which brings with it the benefits of address masking.

The likely cost in these sequences will be from toggling PAN/UAO, which
we can address later by implementing the *_unsafe versions.

Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
[ v4.4: Fixed conflicts around {__get_user|__put_user}_unaligned macros ]
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 arch/arm64/include/asm/uaccess.h | 62 ++++++++++++++++++--------------
 1 file changed, 36 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index fc11c50af558..a34324436ce1 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -200,30 +200,35 @@ do {									\
 			CONFIG_ARM64_PAN));				\
 } while (0)
 
-#define __get_user(x, ptr)						\
+#define __get_user_check(x, ptr, err)					\
 ({									\
-	int __gu_err = 0;						\
-	__get_user_err((x), (ptr), __gu_err);				\
-	__gu_err;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_READ, __p, sizeof(*__p))) {		\
+		__p = uaccess_mask_ptr(__p);				\
+		__get_user_err((x), __p, (err));			\
+	} else {							\
+		(x) = 0; (err) = -EFAULT;				\
+	}								\
 })
 
 #define __get_user_error(x, ptr, err)					\
 ({									\
-	__get_user_err((x), (ptr), (err));				\
+	__get_user_check((x), (ptr), (err));				\
 	(void)0;							\
 })
 
-#define __get_user_unaligned __get_user
-
-#define get_user(x, ptr)						\
+#define __get_user(x, ptr)						\
 ({									\
-	__typeof__(*(ptr)) __user *__p = (ptr);				\
-	might_fault();							\
-	access_ok(VERIFY_READ, __p, sizeof(*__p)) ?			\
-		__p = uaccess_mask_ptr(__p), __get_user((x), __p) :	\
-		((x) = 0, -EFAULT);					\
+	int __gu_err = 0;						\
+	__get_user_check((x), (ptr), __gu_err);				\
+	__gu_err;							\
 })
 
+#define __get_user_unaligned __get_user
+
+#define get_user	__get_user
+
 #define __put_user_asm(instr, reg, x, addr, err)			\
 	asm volatile(							\
 	"1:	" instr "	" reg "1, [%2]\n"			\
@@ -266,30 +271,35 @@ do {									\
 			CONFIG_ARM64_PAN));				\
 } while (0)
 
-#define __put_user(x, ptr)						\
+#define __put_user_check(x, ptr, err)					\
 ({									\
-	int __pu_err = 0;						\
-	__put_user_err((x), (ptr), __pu_err);				\
-	__pu_err;							\
+	__typeof__(*(ptr)) __user *__p = (ptr);				\
+	might_fault();							\
+	if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) {		\
+		__p = uaccess_mask_ptr(__p);				\
+		__put_user_err((x), __p, (err));			\
+	} else	{							\
+		(err) = -EFAULT;					\
+	}								\
 })
 
 #define __put_user_error(x, ptr, err)					\
 ({									\
-	__put_user_err((x), (ptr), (err));				\
+	__put_user_check((x), (ptr), (err));				\
 	(void)0;							\
 })
 
-#define __put_user_unaligned __put_user
-
-#define put_user(x, ptr)						\
+#define __put_user(x, ptr)						\
 ({									\
-	__typeof__(*(ptr)) __user *__p = (ptr);				\
-	might_fault();							\
-	access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ?			\
-		__p = uaccess_mask_ptr(__p), __put_user((x), __p) :	\
-		-EFAULT;						\
+	int __pu_err = 0;						\
+	__put_user_check((x), (ptr), __pu_err);				\
+	__pu_err;							\
 })
 
+#define __put_user_unaligned __put_user
+
+#define put_user	__put_user
+
 extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
 extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
 extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
-- 
2.21.0.rc0.269.g1a574e7a288b


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  parent reply	other threads:[~2019-06-14  3:15 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-14  3:07 [PATCH v4.4 00/45] V4.4 backport of arm64 Spectre patches Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 01/45] arm64: barrier: Add CSDB macros to control data-value prediction Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 02/45] arm64: Implement array_index_mask_nospec() Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 03/45] arm64: remove duplicate macro __KERNEL__ check Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 04/45] arm64: move TASK_* definitions to <asm/processor.h> Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 05/45] arm64: Make USER_DS an inclusive limit Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 06/45] arm64: Use pointer masking to limit uaccess speculation Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 07/45] arm64: entry: Ensure branch through syscall table is bounded under speculation Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 08/45] arm64: uaccess: Prevent speculative use of the current addr_limit Viresh Kumar
2019-06-14  3:07 ` Viresh Kumar [this message]
2019-06-14  3:07 ` [PATCH v4.4 10/45] mm/kasan: add API to check memory regions Viresh Kumar
2019-07-04 14:15   ` Julien Thierry
2019-07-05  3:13     ` Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 11/45] arm64: kasan: instrument user memory access API Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 12/45] arm64: uaccess: Mask __user pointers for __arch_{clear, copy_*}_user Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 13/45] arm64: cpufeature: Pass capability structure to ->enable callback Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 14/45] drivers/firmware: Expose psci_get_version through psci_ops structure Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 15/45] arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro Viresh Kumar
2019-06-14  3:07 ` [PATCH v4.4 16/45] arm64: Move post_ttbr_update_workaround to C code Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 17/45] arm64: cpufeature: Add scope for capability check Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 18/45] arm64: Add skeleton to harden the branch predictor against aliasing attacks Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 19/45] arm64: Move BP hardening to check_and_switch_context Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 20/45] mm: Introduce lm_alias Viresh Kumar
2019-06-17 12:33   ` Julien Thierry
2019-06-18  5:00     ` Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 21/45] arm64: entry: Apply BP hardening for high-priority synchronous exceptions Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 22/45] arm64: entry: Apply BP hardening for suspicious interrupts from EL0 Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 23/45] arm64: cputype: Add missing MIDR values for Cortex-A72 and Cortex-A75 Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 24/45] arm64: cpu_errata: Allow an erratum to be match for all revisions of a core Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 25/45] arm64: Implement branch predictor hardening for affected Cortex-A CPUs Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 26/45] arm64: cputype info for Broadcom Vulcan Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 27/45] arm64: cputype: Add MIDR values for Cavium ThunderX2 CPUs Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 28/45] arm64: Branch predictor hardening for Cavium ThunderX2 Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 29/45] arm64: KVM: Increment PC after handling an SMC trap Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 30/45] arm/arm64: KVM: Consolidate the PSCI include files Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 31/45] arm/arm64: KVM: Add PSCI_VERSION helper Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 32/45] arm/arm64: KVM: Add smccc accessors to PSCI code Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 33/45] ARM: 8478/2: arm/arm64: add arm-smccc Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 34/45] arm/arm64: KVM: Implement PSCI 1.0 support Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 35/45] arm/arm64: KVM: Advertise SMCCC v1.1 Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 36/45] arm/arm64: KVM: Turn kvm_psci_version into a static inline Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 37/45] arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 38/45] arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 39/45] firmware/psci: Expose PSCI conduit Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 40/45] firmware/psci: Expose SMCCC version through psci_ops Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 41/45] arm/arm64: smccc: Make function identifiers an unsigned quantity Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 42/45] arm/arm64: smccc: Implement SMCCC v1.1 inline primitive Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 43/45] arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 44/45] arm64: Kill PSCI_GET_VERSION as a variant-2 workaround Viresh Kumar
2019-06-14  3:08 ` [PATCH v4.4 45/45] arm64: futex: Mask __user pointers prior to dereference Viresh Kumar
2019-06-17 12:10 ` [PATCH v4.4 00/45] V4.4 backport of arm64 Spectre patches Greg KH
2019-06-17 16:03 ` Julien Thierry
2019-06-18 10:21   ` Viresh Kumar
2019-06-19 11:03     ` Julien Thierry
2019-06-19 11:20       ` Viresh Kumar
2019-06-17 16:30 ` Julien Thierry
2019-07-11 13:57 ` Julien Thierry

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=fa281cb205c71d33bc2d9f971717d4073409f43e.1560480942.git.viresh.kumar@linaro.org \
    --to=viresh.kumar@linaro.org \
    --cc=Julien.Thierry@arm.com \
    --cc=catalin.marinas@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=marc.zyngier@arm.com \
    --cc=mark.brown@arm.com \
    --cc=mark.rutland@arm.com \
    --cc=rmk+kernel@arm.linux.org.uk \
    --cc=stable@vger.kernel.org \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).