All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ard Biesheuvel <ardb@kernel.org>
To: stable@vger.kernel.org
Cc: linus.walleij@linaro.org, rmk+kernel@armlinux.org.uk,
	Ard Biesheuvel <ardb@kernel.org>
Subject: [PATCH for-stable-4.4 35/50] ARM: spectre-v1: mitigate user accesses
Date: Fri,  8 Nov 2019 13:35:39 +0100	[thread overview]
Message-ID: <20191108123554.29004-36-ardb@kernel.org> (raw)
In-Reply-To: <20191108123554.29004-1-ardb@kernel.org>

From: Russell King <rmk+kernel@armlinux.org.uk>

Commit a3c0f84765bb429ba0fd23de1c57b5e1591c9389 upstream.

Spectre variant 1 attacks are about this sequence of pseudo-code:

	index = load(user-manipulated pointer);
	access(base + index * stride);

In order for the cache side-channel to work, the access() must me made
to memory which userspace can detect whether cache lines have been
loaded.  On 32-bit ARM, this must be either user accessible memory, or
a kernel mapping of that same user accessible memory.

The problem occurs when the load() speculatively loads privileged data,
and the subsequent access() is made to user accessible memory.

Any load() which makes use of a user-maniplated pointer is a potential
problem if the data it has loaded is used in a subsequent access.  This
also applies for the access() if the data loaded by that access is used
by a subsequent access.

Harden the get_user() accessors against Spectre attacks by forcing out
of bounds addresses to a NULL pointer.  This prevents get_user() being
used as the load() step above.  As a side effect, put_user() will also
be affected even though it isn't implicated.

Also harden copy_from_user() by redoing the bounds check within the
arm_copy_from_user() code, and NULLing the pointer if out of bounds.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David A. Long <dave.long@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/arm/include/asm/assembler.h | 4 ++++
 arch/arm/lib/copy_from_user.S    | 9 +++++++++
 2 files changed, 13 insertions(+)

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 307901f88a1e..483481c6937e 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -454,6 +454,10 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	adds	\tmp, \addr, #\size - 1
 	sbcccs	\tmp, \tmp, \limit
 	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
 #endif
 	.endm
 
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 1512bebfbf1b..d36329cefedc 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -90,6 +90,15 @@
 	.text
 
 ENTRY(arm_copy_from_user)
+#ifdef CONFIG_CPU_SPECTRE
+	get_thread_info r3
+	ldr	r3, [r3, #TI_ADDR_LIMIT]
+	adds	ip, r1, r2	@ ip=addr+size
+	sub	r3, r3, #1	@ addr_limit - 1
+	cmpcc	ip, r3		@ if (addr+size > addr_limit - 1)
+	movcs	r1, #0		@ addr = NULL
+	csdb
+#endif
 
 #include "copy_template.S"
 
-- 
2.20.1


  parent reply	other threads:[~2019-11-08 12:37 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-08 12:35 [PATCH for-stable-4.4 00/50] ARM: spectre v1/v2 mitigations Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 01/50] ARM: 8051/1: put_user: fix possible data corruption in put_user Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 02/50] ARM: 8478/2: arm/arm64: add arm-smccc Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 03/50] ARM: 8479/2: add implementation for arm-smccc Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 04/50] ARM: 8480/2: arm64: " Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 05/50] ARM: 8481/2: drivers: psci: replace psci firmware calls Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 06/50] ARM: uaccess: remove put_user() code duplication Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 07/50] ARM: Move system register accessors to asm/cp15.h Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 08/50] arm/arm64: KVM: Advertise SMCCC v1.1 Ard Biesheuvel
2019-11-08 13:11   ` Greg KH
2019-11-08 13:29     ` Ard Biesheuvel
2019-11-08 13:39       ` Greg KH
2019-11-08 13:39     ` Russell King - ARM Linux admin
2019-11-08 13:48       ` Mark Rutland
2019-11-08 12:35 ` [PATCH for-stable-4.4 09/50] arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 10/50] firmware/psci: Expose PSCI conduit Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 11/50] firmware/psci: Expose SMCCC version through psci_ops Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 12/50] arm/arm64: smccc: Make function identifiers an unsigned quantity Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 13/50] arm/arm64: smccc: Implement SMCCC v1.1 inline primitive Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 14/50] arm/arm64: smccc: Add SMCCC-specific return codes Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 15/50] arm/arm64: smccc-1.1: Make return values unsigned long Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 16/50] arm/arm64: smccc-1.1: Handle function result as parameters Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 17/50] ARM: add more CPU part numbers for Cortex and Brahma B15 CPUs Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 18/50] ARM: bugs: prepare processor bug infrastructure Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 19/50] ARM: bugs: hook processor bug checking into SMP and suspend paths Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 20/50] ARM: bugs: add support for per-processor bug checking Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 21/50] ARM: spectre: add Kconfig symbol for CPUs vulnerable to Spectre Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 22/50] ARM: spectre-v2: harden branch predictor on context switches Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 23/50] ARM: spectre-v2: add Cortex A8 and A15 validation of the IBE bit Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 24/50] ARM: spectre-v2: harden user aborts in kernel space Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 25/50] ARM: spectre-v2: add firmware based hardening Ard Biesheuvel
2019-11-08 13:13   ` Greg KH
2019-11-08 12:35 ` [PATCH for-stable-4.4 26/50] ARM: spectre-v2: warn about incorrect context switching functions Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 27/50] ARM: spectre-v1: add speculation barrier (csdb) macros Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 28/50] ARM: spectre-v1: add array_index_mask_nospec() implementation Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 29/50] ARM: spectre-v1: fix syscall entry Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 30/50] ARM: signal: copy registers using __copy_from_user() Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 31/50] ARM: vfp: use __copy_from_user() when restoring VFP state Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 32/50] ARM: oabi-compat: copy semops using __copy_from_user() Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 33/50] ARM: use __inttype() in get_user() Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 34/50] ARM: spectre-v1: use get_user() for __get_user() Ard Biesheuvel
2019-11-08 12:35 ` Ard Biesheuvel [this message]
2019-11-08 12:35 ` [PATCH for-stable-4.4 36/50] ARM: 8789/1: signal: copy registers using __copy_to_user() Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 37/50] ARM: 8791/1: vfp: use __copy_to_user() when saving VFP state Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 38/50] ARM: 8792/1: oabi-compat: copy oabi events using __copy_to_user() Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 39/50] ARM: 8793/1: signal: replace __put_user_error with __put_user Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 40/50] ARM: 8794/1: uaccess: Prevent speculative use of the current addr_limit Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 41/50] ARM: 8795/1: spectre-v1.1: use put_user() for __put_user() Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 42/50] ARM: 8796/1: spectre-v1,v1.1: provide helpers for address sanitization Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 43/50] ARM: 8810/1: vfp: Fix wrong assignement to ufp_exc Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 44/50] ARM: make lookup_processor_type() non-__init Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 45/50] ARM: split out processor lookup Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 46/50] ARM: clean up per-processor check_bugs method call Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 47/50] ARM: add PROC_VTABLE and PROC_TABLE macros Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 48/50] ARM: spectre-v2: per-CPU vtables to work around big.Little systems Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 49/50] ARM: ensure that processor vtables is not lost after boot Ard Biesheuvel
2019-11-08 12:35 ` [PATCH for-stable-4.4 50/50] ARM: fix the cockup in the previous patch Ard Biesheuvel
2019-11-08 13:15 ` [PATCH for-stable-4.4 00/50] ARM: spectre v1/v2 mitigations Greg KH
2019-11-08 15:43 ` Linus Walleij

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=20191108123554.29004-36-ardb@kernel.org \
    --to=ardb@kernel.org \
    --cc=linus.walleij@linaro.org \
    --cc=rmk+kernel@armlinux.org.uk \
    --cc=stable@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.