Reserve ECC Double Bit Error SMC call to alert U-Boot that a DBE has
occurred. Move the call from local EDAC header file to a common header.
[ bp: Merge the two patches. ]
Signed-off-by: Thor Thayer <thor.thayer@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Richard Gong <richard.gong@intel.com>
Reviewed-by: Alan Tull <atull@kernel.org> # firmware
Cc: Greg KH <greg@kroah.com>
Cc: James Morse <james.morse@arm.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: mchehab@kernel.org
Link: https://lkml.kernel.org/r/1553870639-23895-1-git-send-email-thor.thayer@linux.intel.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Improve the Arria10 and Stratix10 error injection routine
by reading the data and changing just 1 bit before writing
back out. Previous routine would overwrite the first bytes
to 0 then change 1 bit but this method is less intrusive.
Signed-off-by: Thor Thayer <thor.thayer@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: https://lkml.kernel.org/r/1553635771-32693-1-git-send-email-thor.thayer@linux.intel.com
Stratix10 Double Bit Error Address was always read from SDRAM Address
register instead of each device's Address register.
To determine which device had the DBE, cycle through the EDAC devices
comparing the DBE value to the db_irq value. Once found, report the DBE
Address from the device registers as well as the device name.
Finally, notify the system via an SMC call and indicate the panic should
result in a system reboot. Change a run-time check to a Stratix10
compile-time check for a clean SMC notification.
Fixes: d5fc912556 ("EDAC, altera: Combine Stratix10 and Arria10 probe functions")
Signed-off-by: Thor Thayer <thor.thayer@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: https://lkml.kernel.org/r/1552490842-25440-1-git-send-email-thor.thayer@linux.intel.com
On Stratix10, uncorrectable errors are routed to the SError exception
instead of the IRQ exceptions. In Stratix10, uncorrectable SErrors
must be treated as fatal and will cause a panic. Older Altera/Intel
parts printed out a message for UE so do that here using the notifier
framework.
Record the UE in sticky registers that retain the state through a reset.
Check these registers on probe and printout the error on startup.
Signed-off-by: Thor Thayer <thor.thayer@linux.intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: mark.rutland@arm.com
Cc: mchehab@kernel.org
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1526079610-5527-1-git-send-email-thor.thayer@linux.intel.com
[ Remove unused var in s10_edac_dberr_handler(), reorder args. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
The L2 and OCRAM devices have different ecc trigger names than the other
EDAC devices (FIFO peripherals). Make them all the same and remove the
character array from the device structure.
Signed-off-by: Thor Thayer <tthayer@opensource.altera.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1471622666-15197-2-git-send-email-tthayer@opensource.altera.com
Signed-off-by: Borislav Petkov <bp@suse.de>
In preparation for additional memory module ECCs, the IRQ function will
check a panic flag before doing a kernel panic on double bit errors.
OCRAM uncorrectable errors cause a panic because sleep/resume functions
and FPGA contents during sleep are stored in OCRAM.
ECCs on peripheral FIFO buffers will not cause a kernel panic on DBERRs
because the packet can be retried and therefore recovered.
Signed-off-by: Thor Thayer <tthayer@opensource.altera.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1466603939-7526-3-git-send-email-tthayer@opensource.altera.com
Signed-off-by: Borislav Petkov <bp@suse.de>
The bootloader may or may not enable the ECC_CORR_EN bit. By
not enabling ECC_CORR_EN, when error happens, it is the user's
responsibility to perform a full SDRAM scrub.
Remove the check for ECC_CORR_EN.
Signed-off-by: Dinh Nguyen <dinguyen@opensource.altera.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Cc: Thor Thayer <tthayer@opensource.altera.com>
Link: http://lkml.kernel.org/r/1444864456-21778-1-git-send-email-dinguyen@opensource.altera.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Thor Thayer