From: Zefan Li <lizf@kernel.org>
To: stable@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Mark Rutland <mark.rutland@arm.com>,
Will Deacon <will.deacon@arm.com>,
Russell King <rmk+kernel@arm.linux.org.uk>,
Zefan Li <lizefan@huawei.com>
Subject: [PATCH 3.4 32/45] ARM: 8129/1: errata: work around Cortex-A15 erratum 830321 using dummy strex
Date: Tue, 23 Sep 2014 10:31:34 +0800 [thread overview]
Message-ID: <1411439507-30391-32-git-send-email-lizf@kernel.org> (raw)
In-Reply-To: <1411439259-30224-1-git-send-email-lizf@kernel.org>
From: Mark Rutland <mark.rutland@arm.com>
3.4.104-rc1 review patch. If anyone has any objections, please let me know.
------------------
commit 2c32c65e3726c773760038910be30cce1b4d4149 upstream.
On revisions of Cortex-A15 prior to r3p3, a CLREX instruction at PL1 may
falsely trigger a watchpoint exception, leading to potential data aborts
during exception return and/or livelock.
This patch resolves the issue in the following ways:
- Replacing our uses of CLREX with a dummy STREX sequence instead (as
we did for v6 CPUs).
- Removing the clrex code from v7_exit_coherency_flush and derivatives,
since this only exists as a minor performance improvement when
non-cached exclusives are in use (Linux doesn't use these).
Benchmarking on a variety of ARM cores revealed no measurable
performance difference with this change applied, so the change is
performed unconditionally and no new Kconfig entry is added.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
[lizf: Backported to 3.4:
- Drop changes to arch/arm/include/asm/cacheflush.h and
arch/arm/mach-exynos/mcpm-exynos.c]
Signed-off-by: Zefan Li <lizefan@huawei.com>
---
| 29 +++++++++++++++--------------
1 file changed, 15 insertions(+), 14 deletions(-)
--git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 9a8531e..9d95a46 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -76,26 +76,21 @@
#ifndef CONFIG_THUMB2_KERNEL
.macro svc_exit, rpsr
msr spsr_cxsf, \rpsr
-#if defined(CONFIG_CPU_V6)
- ldr r0, [sp]
- strex r1, r2, [sp] @ clear the exclusive monitor
- ldmib sp, {r1 - pc}^ @ load r1 - pc, cpsr
-#elif defined(CONFIG_CPU_32v6K)
- clrex @ clear the exclusive monitor
- ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
-#else
- ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
+ @ We must avoid clrex due to Cortex-A15 erratum #830321
+ sub r0, sp, #4 @ uninhabited address
+ strex r1, r2, [r0] @ clear the exclusive monitor
#endif
+ ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr
.endm
.macro restore_user_regs, fast = 0, offset = 0
ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr
ldr lr, [sp, #\offset + S_PC]! @ get pc
msr spsr_cxsf, r1 @ save in spsr_svc
-#if defined(CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
+ @ We must avoid clrex due to Cortex-A15 erratum #830321
strex r1, r2, [sp] @ clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
- clrex @ clear the exclusive monitor
#endif
.if \fast
ldmdb sp, {r1 - lr}^ @ get calling r1 - lr
@@ -123,7 +118,10 @@
.macro svc_exit, rpsr
ldr lr, [sp, #S_SP] @ top of the stack
ldrd r0, r1, [sp, #S_LR] @ calling lr and pc
- clrex @ clear the exclusive monitor
+
+ @ We must avoid clrex due to Cortex-A15 erratum #830321
+ strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor
+
stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context
ldmia sp, {r0 - r12}
mov sp, lr
@@ -132,13 +130,16 @@
.endm
.macro restore_user_regs, fast = 0, offset = 0
- clrex @ clear the exclusive monitor
mov r2, sp
load_user_sp_lr r2, r3, \offset + S_SP @ calling sp, lr
ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr
ldr lr, [sp, #\offset + S_PC] @ get pc
add sp, sp, #\offset + S_SP
msr spsr_cxsf, r1 @ save in spsr_svc
+
+ @ We must avoid clrex due to Cortex-A15 erratum #830321
+ strex r1, r2, [sp] @ clear the exclusive monitor
+
.if \fast
ldmdb sp, {r1 - r12} @ get calling r1 - r12
.else
--
1.7.9.5
next prev parent reply other threads:[~2014-09-23 2:40 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-23 2:27 [PATCH 3.4 00/45] 3.4.104-rc1 review Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 01/45] stable_kernel_rules: Add pointer to netdev-FAQ for network patches Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 02/45] ASoC: pxa-ssp: drop SNDRV_PCM_FMTBIT_S24_LE Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 03/45] ibmveth: Fix endian issues with rx_no_buffer statistic Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 04/45] HID: fix a couple of off-by-ones Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 05/45] HID: logitech: perform bounds checking on device_id early enough Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 06/45] isofs: Fix unbounded recursion when processing relocated directories Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 07/45] MIPS: OCTEON: make get_system_type() thread-safe Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 08/45] kvm: iommu: fix the third parameter of kvm_iommu_put_pages (CVE-2014-3601) Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 09/45] pata_scc: propagate return value of scc_wait_after_reset Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 10/45] iommu/amd: Fix cleanup_domain for mass device removal Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 11/45] md/raid6: avoid data corruption during recovery of double-degraded RAID6 Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 12/45] CIFS: Fix wrong directory attributes after rename Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 13/45] ALSA: hda/realtek - Avoid setting wrong COEF on ALC269 & co Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 14/45] xtensa: replace IOCTL code definitions with constants Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 15/45] xtensa: fix address checks in dma_{alloc,free}_coherent Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 16/45] xtensa: fix TLBTEMP_BASE_2 region handling in fast_second_level_miss Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 17/45] xtensa: fix a6 and a7 handling in fast_syscall_xtensa Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 18/45] staging: et131x: Fix errors caused by phydev->addr accesses before initialisation Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 19/45] USB: option: add VIA Telecom CDS7 chipset device id Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 20/45] USB: ftdi_sio: add Basic Micro ATOM Nano USB2Serial PID Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 21/45] USB: serial: pl2303: add device id for ztek device Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 22/45] USB: ftdi_sio: Added PID for new ekey device Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 23/45] xhci: Treat not finding the event_seg on COMP_STOP the same as COMP_STOP_INVAL Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 24/45] usb: xhci: amd chipset also needs short TX quirk Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 25/45] USB: whiteheat: Added bounds checking for bulk command response Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 26/45] HID: logitech-dj: prevent false errors to be shown Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 27/45] USB: sisusb: add device id for Magic Control USB video Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 28/45] NFSv4: Fix problems with close in the presence of a delegation Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 29/45] HID: magicmouse: sanity check report size in raw_event() callback Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 30/45] HID: picolcd: " Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 31/45] ARM: 8128/1: abort: don't clear the exclusive monitors Zefan Li
2014-09-23 2:31 ` Zefan Li [this message]
2014-09-23 2:31 ` [PATCH 3.4 33/45] USB: serial: fix potential stack buffer overflow Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 34/45] USB: serial: fix potential heap " Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 35/45] MIPS: perf: Fix build error caused by unused counters_per_cpu_to_total() Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 36/45] MIPS: Fix accessing to per-cpu data when flushing the cache Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 37/45] openrisc: add missing header inclusion Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 38/45] slab/mempolicy: always use local policy from interrupt context Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 39/45] 8250_pci: fix warnings in backport of Broadcom TruManage support Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 40/45] unicore32: select generic atomic64_t support Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 41/45] UniCore32-bugfix: Remove definitions in asm/bug.h to solve difference between native and cross compiler Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 42/45] UniCore32-bugfix: fix mismatch return value of __xchg_bad_pointer Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 43/45] alpha: Fix fall-out from disintegrating asm/system.h Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 44/45] ext2: Fix fs corruption in ext2_get_xip_mem() Zefan Li
2014-09-23 2:31 ` [PATCH 3.4 45/45] alpha: add io{read,write}{16,32}be functions Zefan Li
2014-09-23 2:42 ` [PATCH 3.4 00/45] 3.4.104-rc1 review Guenter Roeck
2014-09-23 2:54 ` Guenter Roeck
2014-09-23 2:54 ` Zefan Li
2014-09-23 2:56 ` Zefan Li
2014-09-23 4:54 ` Satoru Takeuchi
2014-09-23 6:12 ` Zefan Li
2014-09-23 4:58 ` Guenter Roeck
2014-09-23 6:14 ` Zefan Li
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=1411439507-30391-32-git-send-email-lizf@kernel.org \
--to=lizf@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.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