stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg KH <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: torvalds@linux-foundation.org, akpm@linux-foundation.org,
	alan@lxorguk.ukuu.org.uk, Stephen Boyd <sboyd@codeaurora.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Nicolas Pitre <nico@linaro.org>,
	Russell King <rmk+kernel@arm.linux.org.uk>
Subject: [ 18/34] ARM: 7321/1: cache-v7: Disable preemption when reading CCSIDR
Date: Thu, 01 Mar 2012 13:39:40 -0800	[thread overview]
Message-ID: <20120301213925.183202699@linuxfoundation.org> (raw)
In-Reply-To: <20120301214654.GA13231@kroah.com>

2.6.32-longterm review patch.  If anyone has any objections, please let me know.

------------------

From: Stephen Boyd <sboyd@codeaurora.org>

commit b46c0f74657d1fe1c1b0c1452631cc38a9e6987f upstream.

armv7's flush_cache_all() flushes caches via set/way. To
determine the cache attributes (line size, number of sets,
etc.) the assembly first writes the CSSELR register to select a
cache level and then reads the CCSIDR register. The CSSELR register
is banked per-cpu and is used to determine which cache level CCSIDR
reads. If the task is migrated between when the CSSELR is written and
the CCSIDR is read the CCSIDR value may be for an unexpected cache
level (for example L1 instead of L2) and incorrect cache flushing
could occur.

Disable interrupts across the write and read so that the correct
cache attributes are read and used for the cache flushing
routine. We disable interrupts instead of disabling preemption
because the critical section is only 3 instructions and we want
to call v7_dcache_flush_all from __v7_setup which doesn't have a
full kernel stack with a struct thread_info.

This fixes a problem we see in scm_call() when flush_cache_all()
is called from preemptible context and sometimes the L2 cache is
not properly flushed out.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/arm/mm/cache-v7.S |    6 ++++++
 1 file changed, 6 insertions(+)

--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -39,9 +39,15 @@ loop1:
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
+#ifdef CONFIG_PREEMPT
+	save_and_disable_irqs r9		@ make cssr&csidr read atomic
+#endif
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
 	isb					@ isb to sych the new cssr&csidr
 	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
+#ifdef CONFIG_PREEMPT
+	restore_irqs_notrace r9
+#endif
 	and	r2, r1, #7			@ extract the length of the cache lines
 	add	r2, r2, #4			@ add 4 (line length offset)
 	ldr	r4, =0x3ff



  parent reply	other threads:[~2012-03-01 21:39 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-03-01 21:46 [ 00/34] 2.6.32.58-longterm review Greg KH
2012-03-01 21:39 ` [ 01/34] drm/i915: no lvds quirk for AOpen MP45 Greg KH
2012-03-01 21:39 ` [ 02/34] hwmon: (f75375s) Fix bit shifting in f75375_write16 Greg KH
2012-03-01 21:39 ` [ 03/34] lib: proportion: lower PROP_MAX_SHIFT to 32 on 64-bit kernel Greg KH
2012-03-05 15:06   ` Jan Kara
2012-03-05 21:31     ` Fengguang Wu
2012-03-06 20:35       ` Jan Kara
2012-03-07  5:14         ` Fengguang Wu
2012-03-01 21:39 ` [ 04/34] relay: prevent integer overflow in relay_open() Greg KH
2012-03-01 21:39 ` [ 05/34] mac80211: timeout a single frame in the rx reorder buffer Greg KH
2012-03-01 21:39 ` [ 06/34] kernel.h: fix wrong usage of __ratelimit() Greg KH
2012-03-01 21:39 ` [ 07/34] printk_ratelimited(): fix uninitialized spinlock Greg KH
2012-03-01 21:39 ` [ 08/34] hwmon: (f75375s) Fix automatic pwm mode setting for F75373 & F75375 Greg KH
2012-03-01 21:39 ` [ 09/34] crypto: sha512 - Use binary and instead of modulus Greg KH
2012-03-01 21:39 ` [ 10/34] crypto: sha512 - Avoid stack bloat on i386 Greg KH
2012-03-01 21:39 ` [ 11/34] eCryptfs: Remove mmap from directory operations Greg KH
2012-03-01 21:39 ` [ 12/34] Ban ecryptfs over ecryptfs Greg KH
2012-03-01 21:39 ` [ 13/34] Add mount option to check uid of device being mounted = expect uid, CVE-2011-1833 Greg KH
2012-03-01 21:39 ` [ 14/34] crypto: sha512 - use standard ror64() Greg KH
2012-03-01 21:39 ` [ 15/34] drm/radeon/kms: fix MSI re-arm on rv370+ Greg KH
2012-03-01 21:39 ` [ 16/34] ecryptfs: read on a directory should return EISDIR if not supported Greg KH
2012-03-01 21:39 ` [ 17/34] SCSI: 3w-9xxx fix bug in sgl loading Greg KH
2012-03-01 21:39 ` Greg KH [this message]
2012-03-01 21:39 ` [ 19/34] ARM: 7325/1: fix v7 boot with lockdep enabled Greg KH
2012-03-01 21:39 ` [ 20/34] USB: Added Kamstrup VID/PIDs to cp210x serial driver Greg KH
2012-03-01 21:39 ` [ 21/34] USB: Fix handoff when BIOS disables host PCI device Greg KH
2012-03-01 21:39 ` [ 22/34] xhci: Fix encoding for HS bulk/control NAK rate Greg KH
2012-03-01 21:39 ` [ 23/34] [media] hdpvr: fix race conditon during start of streaming Greg KH
2012-03-01 21:39 ` [ 24/34] eCryptfs: Use notify_change for truncating lower inodes Greg KH
2012-03-01 21:39 ` [ 25/34] eCryptfs: Remove extra d_delete in ecryptfs_rmdir Greg KH
2012-03-01 21:39 ` [ 26/34] eCryptfs: Clear i_nlink in rmdir Greg KH
2012-03-01 21:39 ` [ 27/34] cdrom: use copy_to_user() without the underscores Greg KH
2012-03-01 21:39 ` [ 28/34] autofs: work around unhappy compat problem on x86-64 Greg KH
2012-03-01 21:39 ` [ 29/34] Fix autofs compile without CONFIG_COMPAT Greg KH
2012-03-01 21:39 ` [ 30/34] compat: fix compile breakage on s390 Greg KH
2012-03-01 21:39 ` [ 31/34] PM: Print a warning if firmware is requested when tasks are frozen Greg KH
2012-03-01 21:39 ` [ 32/34] firmware loader: allow builtin firmware load even if usermodehelper is disabled Greg KH
2012-03-01 21:39 ` [ 33/34] PM / Sleep: Fix freezer failures due to racy usermodehelper_is_disabled() Greg KH
2012-03-01 21:39 ` [ 34/34] PM / Sleep: Fix read_unlock_usermodehelper() call Greg KH
2012-03-02  7:19 ` [ 00/34] 2.6.32.58-longterm review Willy Tarreau
2012-03-02 13:51   ` Stefan Bader
2012-03-02 15:37   ` Greg KH

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=20120301213925.183202699@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=akpm@linux-foundation.org \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=catalin.marinas@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nico@linaro.org \
    --cc=rmk+kernel@arm.linux.org.uk \
    --cc=sboyd@codeaurora.org \
    --cc=stable@vger.kernel.org \
    --cc=torvalds@linux-foundation.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 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).