From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Raymond Ngun <rngun@broadcom.com>,
Gregory Fong <gregory.0xf0@gmail.com>,
Will Deacon <will.deacon@arm.com>,
Russell King <rmk+kernel@arm.linux.org.uk>
Subject: [PATCH 3.18 16/39] ARM: 8299/1: mm: ensure local active ASID is marked as allocated on rollover
Date: Mon, 9 Feb 2015 16:33:59 +0800 [thread overview]
Message-ID: <20150209083329.540986037@linuxfoundation.org> (raw)
In-Reply-To: <20150209083328.753647350@linuxfoundation.org>
3.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Will Deacon <will.deacon@arm.com>
commit 8e64806672466392acf19e14427d1c29df3e58b9 upstream.
Commit e1a5848e3398 ("ARM: 7924/1: mm: don't bother with reserved ttbr0
when running with LPAE") removed the use of the reserved TTBR0 value
for LPAE systems, since the ASID is held in the TTBR and can be updated
atomicly with the pgd of the next mm.
Unfortunately, this patch forgot to update flush_context, which
deliberately avoids marking the local active ASID as allocated, since we
used to switch via ASID zero and didn't need to allocate the ASID of
the previous mm. The side-effect of this is that we can allocate the
same ASID to the next mm and, between flushing the local TLB and updating
TTBR0, we can perform speculative TLB fills for userspace nG mappings
using the page table of the previous mm.
The consequence of this is that the next mm can erroneously hit some
mappings of the previous mm. Note that this was made significantly
harder to hit by a391263cd84e ("ARM: 8203/1: mm: try to re-use old ASID
assignments following a rollover") but is still theoretically possible.
This patch fixes the problem by removing the code from flush_context
that forces the allocated ASID to zero for the local CPU. Many thanks
to the Broadcom guys for tracking this one down.
Fixes: e1a5848e3398 ("ARM: 7924/1: mm: don't bother with reserved ttbr0 when running with LPAE")
Reported-by: Raymond Ngun <rngun@broadcom.com>
Tested-by: Raymond Ngun <rngun@broadcom.com>
Reviewed-by: Gregory Fong <gregory.0xf0@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/arm/mm/context.c | 26 +++++++++++---------------
1 file changed, 11 insertions(+), 15 deletions(-)
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -144,21 +144,17 @@ static void flush_context(unsigned int c
/* Update the list of reserved ASIDs and the ASID bitmap. */
bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
for_each_possible_cpu(i) {
- if (i == cpu) {
- asid = 0;
- } else {
- asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
- /*
- * If this CPU has already been through a
- * rollover, but hasn't run another task in
- * the meantime, we must preserve its reserved
- * ASID, as this is the only trace we have of
- * the process it is still running.
- */
- if (asid == 0)
- asid = per_cpu(reserved_asids, i);
- __set_bit(asid & ~ASID_MASK, asid_map);
- }
+ asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+ /*
+ * If this CPU has already been through a
+ * rollover, but hasn't run another task in
+ * the meantime, we must preserve its reserved
+ * ASID, as this is the only trace we have of
+ * the process it is still running.
+ */
+ if (asid == 0)
+ asid = per_cpu(reserved_asids, i);
+ __set_bit(asid & ~ASID_MASK, asid_map);
per_cpu(reserved_asids, i) = asid;
}
next prev parent reply other threads:[~2015-02-09 8:36 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-09 8:33 [PATCH 3.18 00/39] 3.18.7-stable review Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 01/39] gpio: sysfs: fix memory leak in gpiod_export_link Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 02/39] gpio: sysfs: fix memory leak in gpiod_sysfs_set_active_low Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 03/39] gpio: mcp23s08: handle default gpio base Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 04/39] PCI: designware: Reject MSI-X IRQs Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 05/39] PCI: Add NEC variants to Stratus ftServer PCIe DMI check Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 06/39] PCI: Handle read-only BARs on AMD CS553x devices Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 07/39] spi: spi-fsl-dspi: Remove usage of devm_kzalloc Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 08/39] spi: imx: use pio mode for i.mx6dl Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 09/39] sd: Fix max transfer length for 4k disks Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 10/39] MIPS: Fix C0_Pagegrain[IEC] support Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 11/39] MIPS: IRQ: Fix disable_irq on CPU IRQs Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 12/39] MIPS: OCTEON: fix kernel crash when offlining a CPU Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 13/39] MIPS: Fix kernel lockup or crash after CPU offline/online Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 14/39] MIPS: mipsregs.h: Add write_32bit_cp1_register() Greg Kroah-Hartman
2015-02-09 8:33 ` [PATCH 3.18 15/39] MIPS: traps: Fix inline asm ctc1 missing .set hardfloat Greg Kroah-Hartman
2015-02-09 8:33 ` Greg Kroah-Hartman [this message]
2015-02-09 8:34 ` [PATCH 3.18 17/39] Complete oplock break jobs before closing file handle Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 18/39] md/raid5: fix another livelock caused by non-aligned writes Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 19/39] mm: pagewalk: call pte_hole() for VM_PFNMAP during walk_page_range Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 20/39] lib/checksum.c: fix carry in csum_tcpudp_nofold Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 21/39] memcg, shmem: fix shmem migration to use lrucare Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 22/39] nilfs2: fix deadlock of segment constructor over I_SYNC flag Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 23/39] drm/radeon: dont init gpuvm if accel is disabled (v3) Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 27/39] drm/radeon: properly set vm fragment size for TN/RL Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 29/39] arm64: Fix up /proc/cpuinfo Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 30/39] lib/checksum.c: fix build for generic csum_tcpudp_nofold Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 31/39] ASoC: atmel_ssc_dai: fix start event for I2S mode Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 32/39] ASoC: sgtl5000: add delay before first I2C access Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 33/39] ALSA: ak411x: Fix stall in work callback Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 34/39] ARM: dts: Fix I2S1, I2S2 compatible for exynos4 SoCs Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 35/39] x86, microcode: Return error from driver init code when loader is disabled Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 36/39] smpboot: Add missing get_online_cpus() in smpboot_register_percpu_thread() Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 37/39] hrtimer: Fix incorrect tai offset calculation for non high-res timer systems Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 38/39] tracing: Add condition check to RCU lockdep checks Greg Kroah-Hartman
2015-02-09 8:34 ` [PATCH 3.18 39/39] x86/tlb/trace: Do not trace on CPU that is offline Greg Kroah-Hartman
2015-02-09 16:40 ` [PATCH 3.18 00/39] 3.18.7-stable review Guenter Roeck
2015-02-09 18:27 ` Shuah Khan
2015-02-09 21:37 ` Greg Kroah-Hartman
2015-02-09 22:03 ` Guenter Roeck
2015-02-09 22:24 ` Winkler, Tomas
2015-02-09 23:19 ` Shuah Khan
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=20150209083329.540986037@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=gregory.0xf0@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rmk+kernel@arm.linux.org.uk \
--cc=rngun@broadcom.com \
--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