From: Scott Wood <scottwood@freescale.com>
To: galak@kernel.crashing.org
Cc: linuxppc-dev@ozlabs.org
Subject: [PATCH 15/28] 8xx: Work around CPU15 erratum.
Date: Mon, 17 Sep 2007 11:57:44 -0500 [thread overview]
Message-ID: <20070917165744.GO6563@loki.buserror.net> (raw)
In-Reply-To: <20070917165643.GA6545@loki.buserror.net>
The CPU15 erratum on MPC8xx chips can cause incorrect code execution
under certain circumstances, where there is a conditional or indirect
branch in the last word of a page, with a target in the last cache line
of the next page. This patch implements one of the suggested
workarounds, by forcing a TLB miss whenever execution crosses a page
boundary. This is done by invalidating the pages before and after the
one being loaded into the TLB in the ITLB miss handler.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
arch/powerpc/kernel/head_8xx.S | 6 ++++++
arch/powerpc/platforms/8xx/Kconfig | 16 ++++++++++++++++
2 files changed, 22 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 0ad0d17..1cefa84 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -298,6 +298,12 @@ InstructionTLBMiss:
stw r10, 0(r0)
stw r11, 4(r0)
mfspr r10, SPRN_SRR0 /* Get effective address of fault */
+#ifdef CONFIG_8xx_CPU15
+ addi r11, r10, 0x1000
+ tlbie r11
+ addi r11, r10, -0x1000
+ tlbie r11
+#endif
DO_8xx_CPU6(0x3780, r3)
mtspr SPRN_MD_EPN, r10 /* Have to use MD_EPN for walk, MI_EPN can't */
mfspr r10, SPRN_M_TWB /* Get level 1 table entry address */
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index 8ecd01a..322b155 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -100,6 +100,22 @@ config 8xx_CPU6
If in doubt, say N here.
+config 8xx_CPU15
+ bool "CPU15 Silicon Errata"
+ default y
+ help
+ This enables a workaround for erratum CPU15 on MPC8xx chips.
+ This bug can cause incorrect code execution under certain
+ circumstances. This workaround adds some overhead (a TLB miss
+ every time execution crosses a page boundary), and you may wish
+ to disable it if you have worked around the bug in the compiler
+ (by not placing conditional branches or branches to LR or CTR
+ in the last word of a page, with a target of the last cache
+ line in the next page), or if you have used some other
+ workaround.
+
+ If in doubt, say Y here.
+
choice
prompt "Microcode patch selection"
default NO_UCODE_PATCH
--
1.5.3.1
next prev parent reply other threads:[~2007-09-17 16:58 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-17 16:56 [PATCH 00/28] 8xx/82xx patches Scott Wood
2007-09-17 16:57 ` [PATCH 01/28] CPM: Change from fsl,brg-frequency to brg/clock-frequency Scott Wood
2007-09-18 6:11 ` [PATCH 01/28] CPM: Change from fsl, brg-frequency " David Gibson
2007-09-18 14:21 ` Scott Wood
2007-09-18 23:48 ` David Gibson
2007-09-17 16:57 ` [PATCH 02/28] Introduce new CPM device bindings Scott Wood
2007-09-18 6:13 ` David Gibson
2007-09-17 16:57 ` [PATCH 03/28] Document local bus nodes in the device tree Scott Wood
2007-09-18 15:03 ` Kumar Gala
2007-09-17 16:57 ` [PATCH 04/28] Add early debug console for CPM serial ports Scott Wood
2007-09-19 3:10 ` David Gibson
2007-09-17 16:57 ` [PATCH 05/28] bootwrapper: Support all-in-one PCI nodes in cuboot-pq2 Scott Wood
2007-09-19 3:11 ` David Gibson
2007-09-17 16:57 ` [PATCH 06/28] bootwrapper: Add PlanetCore firmware support Scott Wood
2007-09-19 3:15 ` David Gibson
2007-09-17 16:57 ` [PATCH 07/28] bootwrapper: Add fsl_get_immr() and 8xx/pq2 clock functions Scott Wood
2007-09-19 3:16 ` David Gibson
2007-09-17 16:57 ` [PATCH 08/28] bootwrapper: Use fsl_get_immr() in cuboot-pq2.c Scott Wood
2007-09-19 3:16 ` David Gibson
2007-09-17 16:57 ` [PATCH 09/28] cpm_uart: Be an of_platform device when CONFIG_PPC_CPM_NEW_BINDING is set Scott Wood
2007-09-18 4:19 ` Stephen Rothwell
2007-09-17 16:57 ` [PATCH 10/28] cpm_uart: sparse fixes Scott Wood
2007-09-17 16:57 ` [PATCH 11/28] cpm_uart: Issue STOP_TX command before initializing console Scott Wood
2007-09-17 16:57 ` [PATCH 12/28] 8xx: Fix CONFIG_PIN_TLB Scott Wood
2007-09-17 16:57 ` [PATCH 13/28] 8xx: Infrastructure code cleanup Scott Wood
2007-09-19 4:25 ` David Gibson
2007-09-19 5:28 ` Scott Wood
2007-09-17 16:57 ` [PATCH 14/28] 8xx: Add pin and clock setting functions Scott Wood
2007-09-17 16:57 ` Scott Wood [this message]
2007-09-17 16:57 ` [PATCH 16/28] 8xx: Don't call non-existent Soft_emulate_8xx from SoftwareEmulation Scott Wood
2007-09-18 15:08 ` Kumar Gala
2007-09-18 15:11 ` Scott Wood
2007-09-18 15:19 ` Kumar Gala
2007-09-18 15:23 ` Scott Wood
2007-09-18 16:21 ` Kumar Gala
2007-09-17 16:58 ` [PATCH 17/28] 8xx: Set initial memory limit Scott Wood
2007-09-17 16:58 ` [PATCH 18/28] 8xx: mpc885ads cleanup Scott Wood
2007-09-18 13:21 ` Stephen Rothwell
2007-09-17 16:58 ` [PATCH 19/28] 8xx: Embedded Planet EP88xC support Scott Wood
2007-09-17 16:58 ` [PATCH 20/28] cpm2: Infrastructure code cleanup Scott Wood
2007-09-17 16:58 ` [PATCH 21/28] cpm2: Add SCCs to cpm2_clk_setup(), and cpm2_smc_clk_setup() Scott Wood
2007-09-17 16:58 ` [PATCH 22/28] cpm2: Add cpm2_set_pin() Scott Wood
2007-09-17 16:58 ` [PATCH 23/28] mpc82xx: Define CPU_FTR_NEED_COHERENT Scott Wood
2007-09-18 14:34 ` Rune Torgersen
2007-09-18 14:55 ` Scott Wood
2007-09-17 16:58 ` [PATCH 24/28] mpc82xx: Remove a bunch of cruft that duplicates generic functionality Scott Wood
2007-09-18 6:48 ` David Gibson
2007-09-17 16:58 ` [PATCH 25/28] mpc82xx: Rename mpc82xx_ads to mpc8272_ads Scott Wood
2007-09-17 16:58 ` [PATCH 26/28] mpc8272ads: Change references from 82xx_ADS to 8272_ADS Scott Wood
2007-09-17 16:58 ` [PATCH 27/28] mpc82xx: Update mpc8272ads, and factor out PCI and reset Scott Wood
2007-09-17 16:58 ` [PATCH 28/28] mpc82xx: Add pq2fads board support Scott Wood
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=20070917165744.GO6563@loki.buserror.net \
--to=scottwood@freescale.com \
--cc=galak@kernel.crashing.org \
--cc=linuxppc-dev@ozlabs.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).