An implementation of a code generator for BPF programs to speed up packet
filtering on PPC64, inspired by Eric Dumazet's x86-64 version.
Filter code is generated as an ABI-compliant function in module_alloc()'d mem
with stackframe & prologue/epilogue generated if required (simple filters don't
need anything more than an li/blr). The filter's local variables, M[], live in
registers. Supports all BPF opcodes, although "complicated" loads from negative
packet offsets (e.g. SKF_LL_OFF) are not yet supported.
There are a couple of further optimisations left for future work; many-pass
assembly with branch-reach reduction and a register allocator to push M[]
variables into volatile registers would improve the code quality further.
This currently supports big-endian 64-bit PowerPC only (but is fairly simple
to port to PPC32 or LE!).
Enabled in the same way as x86-64:
echo 1 > /proc/sys/net/core/bpf_jit_enable
Or, enabled with extra debug output:
echo 2 > /proc/sys/net/core/bpf_jit_enable
Signed-off-by: Matt Evans <matt@ozlabs.org>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Video input mux settings for tvp7002 and imager inputs were swapped.
Comment was correct.
Tested on EVM with tvp7002 input.
Signed-off-by: Jon Povey <jon.povey@racelogic.co.uk>
Acked-by: Manjunath Hadli <manjunath.hadli@ti.com>
Cc: stable@kernel.org
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
This shift instruction appears to be shifting in the wrong direction.
Without this change, my SparcStation-20MP hangs just after bringing up
the second CPU:
Entering SMP Mode...
Starting CPU 2 at f02b4e90
Brought up 2 CPUs
Total of 2 processors activated (99.52 BogoMIPS).
*** stuck ***
Signed-off-by: Will Simoneau <simoneau@ele.uri.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Function declaration differs between file: dma.c and file:dma.h
and SPARSE (Documentation/sparse.txt) gives error messages
All dma channels are members of 'enum dma_ch' and not 'unsigned int'
Please have a look at channel definitions in:
arch/arm/mach-s3c64xx/include/mach/dma.h
arch/arm/plat-samsung/include/plat/s3c-dma-pl330.h
arch/arm/mach-s3c2410/include/mach/dma.h
So all arguments should be of type 'enum dma_ch'
Signed-off-by: Sangwook Lee <sangwook.lee@linaro.org>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Commit 234b6ceddb
clocksource: convert ARM 32-bit up counting clocksources
broke the build for ixp4xx and made big endian operation impossible.
This commit restores the original behaviour.
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Signed-off-by: Krzysztof Hałasa <khc@pm.waw.pl>
[ Thomas says that we might want to have generic BE accessor functions
to the MMIO clock source, but that hasn't happened yet, so in the
meantime this seems to be the short-term fix for the particular
problem - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The code in arch/mips/kernel/i8259.c still hasn't been converted to
using struct syscore_ops instead of a sysdev for resume and shutdown.
As a result, this code doesn't build any more after suspend, resume
and shutdown callbacks have been removed from struct sysdev_class.
Fix this problem by converting i8259.c to using syscore_ops.
Reported-and-tested-by: Roland Vossen <rvossen@broadcom.com>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Remove wrong setting of dev->flags. NETIF_F_NO_CSUM maps to IFF_DEBUG
there, so looks like a mistake.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 7416401 ("arm: davinci: Fix fallout from generic irq chip
conversion") introduced a bug, causing low level interrupt handlers to
get a bogus irq number as an argument. The gpio irq handler falsely
assumes that the handler data is the irq base number and that is no
longer true.
Set the irq handler data to be a pointer to the corresponding gpio
controller. The chained irq handler can then use it to extract both the
irq base number and the gpio registers structure.
Signed-off-by: Ido Yariv <ido@wizery.com>
CC: Thomas Gleixner <tglx@linutronix.de>
[nsekhar@ti.com: renamed "ctl" to "d", simplified indexing logic for chips and
took care of odd bank handling in irq handler]
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Just compiling pseries in the kernel causes it to override
memory_block_size_bytes() regardless of what is the runtime
platform.
This cleans up the implementation of that function, fixing
a bug or two while at it, so that it's harmless (and potentially
useful) for other platforms. Without this, bugs in that code
would trigger a WARN_ON() in drivers/base/memory.c when
booting some different platforms.
If/when we have another platform supporting memory hotplug we
might want to either move that out to a generic place or
make it a ppc_md. callback.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The macro MIN_MEMORY_BLOCK_SIZE is currently defined twice in two .c
files, and I need it in a third one to fix a powerpc bug, so let's
first move it into a header
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
In commit f0fba2ad (ASoC: multi-component - ASoC Multi-Component
Support), the name of the ak4104 codec driver was changed without
amending the platform code which uses it as well.
Signed-off-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
The display requires some milliseconds between GPIO_TFT_VA_EN
and GPIO_DISPLAY_ENABLE. Reorder initialisation to comply with
the display spec.
Also tune timings for better compliance with the spec.
Signed-off-by: Sven Neumann <s.neumann@raumfeld.com>
Acked-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
The backlight control is going to change back to PWM in the
upcoming Raumfeld Controller hardware revision.
Signed-off-by: Sven Neumann <s.neumann@raumfeld.com>
Acked-by: Daniel Mack <zonque@gmail.com>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
The PXA platform code has a static inline helper called
gpio_to_chip which clashes with the gpiolib namespace if we
try to expose the function with the same name from gpiolib,
and it's still confusing even if we don't do that. So rename
it to gpio_to_pxachip().
Reported-by: H Hartley Sweeten <hartleys@visionengravers.com>
Cc: Eric Miao <eric.miao@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
If mini2440_init() is in __init, mini2440_parse_features() should also
be in __init. Fixes:
(.text+0x9adc): Section mismatch in reference from the function mini2440_parse_features.clone.0() to the
(unknown reference) .init.data:(unknown)
The function mini2440_parse_features.clone.0() references the (unknown reference) __initdata (unknown).
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Cc: Michel Pollet <buserror@gmail.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Commit bb072c3c (ARM / Samsung: Use struct syscore_ops for "core" power
management) turned s3c2410_dma_resume_chan() from int to void. So, drop
the actual return values, too. Fixes:
arch/arm/plat-s3c24xx/dma.c: In function 's3c2410_dma_resume_chan':
arch/arm/plat-s3c24xx/dma.c:1238:3: warning: 'return' with a value, in function returning void
arch/arm/plat-s3c24xx/dma.c:1250:2: warning: 'return' with a value, in function returning void
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Commit 8970ef47 (S3C24XX: Remove hardware specific registers from DMA
calls) removed the parameter dcon in s3c2410_dma_config() and calculates
it on its own. So the debug-output for the old parameter can go, too.
Fixes:
arch/arm/plat-s3c24xx/dma.c: In function 's3c2410_dma_config':
arch/arm/plat-s3c24xx/dma.c:1030:2: warning: 'dcon' is used uninitialized in this function
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Cc: Ben Dooks <ben-linux@fluff.org>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Previously we would check for acpi_sci_override_gsi == gsi every time
a PCI device was enabled. That works during early bootup, but later
on it could lead to triggering unnecessarily the acpi_gsi_to_irq(..) lookup.
The reason is that acpi_sci_override_gsi was declared in __initdata and
after early bootup could contain bogus values.
This patch moves the check for acpi_sci_override_gsi to the
site where the ACPI SCI is preset.
CC: stable@kernel.org
Reported-by: Raghavendra D Prabhu <rprabhu@wnohang.net>
Tested-by: Raghavendra D Prabhu <rprabhu@wnohang.net>
[http://lists.xensource.com/archives/html/xen-devel/2011-07/msg00154.html]
Suggested-by: Ian Campbell <ijc@hellion.org.uk>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This fixes a regression introduced by e59347a "arm: orion:
Use generic irq chip".
Depending on the device, interrupts acknowledgement is done by setting
or by clearing a dedicated register. Replace irq_gc_ack() with some
{set,clr}_bit variants allows to handle both cases.
Note that this patch affects the following SoCs: Davinci, Samsung and
Orion. Except for this last, the change is minor: irq_gc_ack() is just
renamed into irq_gc_ack_set_bit().
For the Orion SoCs, the edge GPIO interrupts support is currently
broken. irq_gc_ack() try to acknowledge a such interrupt by setting
the corresponding cause register bit. The Orion GPIO device expect the
opposite. To fix this issue, the irq_gc_ack_clr_bit() variant is used.
Tested on Network Space v2.
Reported-by: Joey Oravec <joravec@drewtech.com>
Signed-off-by: Simon Guinot <sguinot@lacie.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
This platform has not been converted to 'struct irq_data' when the big
pile was done. It fails to compile nowadays, because the compatibility
code has gone.
CC arch/arm/mach-vt8500/irq.o
arch/arm/mach-vt8500/irq.c:118:2: error: unknown field 'ack' specified in initializer
arch/arm/mach-vt8500/irq.c:118:2: warning: initialization from incompatible pointer type
arch/arm/mach-vt8500/irq.c:119:2: error: unknown field 'mask' specified in initializer
arch/arm/mach-vt8500/irq.c:119:2: warning: initialization from incompatible pointer type
arch/arm/mach-vt8500/irq.c:120:2: error: unknown field 'unmask' specified in initializer
arch/arm/mach-vt8500/irq.c:120:2: warning: initialization from incompatible pointer type
arch/arm/mach-vt8500/irq.c:121:2: error: unknown field 'set_type' specified in initializer
arch/arm/mach-vt8500/irq.c:121:2: warning: initialization from incompatible pointer type
make[1]: *** [arch/arm/mach-vt8500/irq.o] Error 1
Add the missing conversion. Tested on a JayPC-Tablet.
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Alexey Charkov <alchark@gmail.com>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
To get hundredths of MHz the rate needs to be divided by 10'000.
Here is an example:
twd_timer_rate = 123456789
Before the patch:
twd_timer_rate / 1000000 = 123
(twd_timer_rate / 1000000) % 100 = 23
Result: 123.23MHz.
After being fixed:
twd_timer_rate / 1000000 = 123
(twd_timer_rate / 10000) % 100 = 45
Result: 123.45MHz.
Signed-off-by: Vitaly Kuzmichev <vkuzmichev@mvista.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Testing suggests that at least some Lenovos and some Intels will
fail to reboot via EFI, attempting to jump to an unmapped
physical address. In the long run we could handle this by
providing a page table with a 1:1 mapping of physical addresses,
but for now it's probably just easier to assume that ACPI or
legacy methods will be present and reboot via those.
Signed-off-by: Matthew Garrett <mjg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Alan Cox <alan@linux.intel.com>
Link: http://lkml.kernel.org/r/1309985557-15350-1-git-send-email-mjg@redhat.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Some BIOSes will reset the Intel MISC_ENABLE MSR (specifically the
XD_DISABLE bit) when resuming from S3, which can interact poorly with
ebba638ae7. In 32bit PAE mode, this can
lead to a fault when EFER is restored by the kernel wakeup routines,
due to it setting the NX bit for a CPU that (thanks to the BIOS reset)
now incorrectly thinks it lacks the NX feature. (64bit is not affected
because it uses a common CPU bring-up that specifically handles the
XD_DISABLE bit.)
The need for MISC_ENABLE being restored so early is specific to the S3
resume path. Normally, MISC_ENABLE is saved in save_processor_state(),
but this happens after the resume header is created, so just reproduce
the logic here. (acpi_suspend_lowlevel() creates the header, calls
do_suspend_lowlevel, which calls save_processor_state(), so the saved
processor context isn't available during resume header creation.)
[ hpa: Consider for stable if OK in mainline ]
Signed-off-by: Kees Cook <kees.cook@canonical.com>
Link: http://lkml.kernel.org/r/20110707011034.GA8523@outflux.net
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: <stable@kernel.org> 2.6.38+
The l2x0_disable function attempts to writel with the l2x0_lock held.
This results in deadlock when the writel contains an outer_sync call
for the platform since the l2x0_lock is already held by the disable
function. A further problem is that disabling the L2 without flushing it
first can lead to the spin_lock operation becoming visible after the
spin_unlock, causing any subsequent L2 maintenance to deadlock.
This patch replaces the writel with a call to writel_relaxed in the
disabling code and adds a flush before disabling in the control
register, preventing livelock from occurring.
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
It was discovered by Roberto Bergo, that RTS/DTR signals are inverted after
the boot, because it was causing him problems with hardware controlled modem
connected on ttyAM0. Todd Valentic came with this patch for the issue.
Discussion: http://tech.groups.yahoo.com/group/ts-7000/message/20259
Comments from Petr Štetiar:
Sorry, but forget to add Acked-by[1]:
1. https://patchwork.kernel.org/patch/873052/
Cc: Ryan Mallon <ryan@bluewatersys.com>
Cc: Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: Todd Valentic <todd.valentic@sri.com>
Tested-by: Roberto Bergo <roberto.bergo@robson.it>
Signed-off-by: Petr Štetiar <ynezz@true.cz>
Acked-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
This platform has not been converted to 'struct irq_data' when the big
pile was done and fails to compile nowadays. Tested on a JayPC-Tablet.
Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Alexey Charkov <alchark@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The original pair of <0x01db, 208000000> is invalid. Correct it to
the valid value.
The 6th bit of the NFC APMU register indicates NFC works whether
at 156Mhz or 78Mhz. So 0x19b indicates NFC works at 156Mhz, and
0x1db indicates it works at 78Mhz.
Signed-off-by: Lei Wen <leiwen@marvell.com>
Cc: stable@kernel.org
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
The original pair of <0x01db, 208000000> is invalid.
Correct to the valid value.
Signed-off-by: Lei Wen <leiwen@marvell.com>
Cc: stable@kernel.org
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
The file mfp-pxa2xx.c defines a macro, PGSR(), which translates a gpio
bank number to a PGSR register address. The function pxa2xx_mfp_suspend()
erroneously passed in a gpio number instead of a gpio bank number.
Signed-off-by: Paul Parsons <lost.distance@yahoo.com>
Cc: stable@kernel.org
Signed-off-by: Eric Miao <eric.y.miao@gmail.com>
The function leon_flush_needed() is called only during bootup from another
__init function. Therefore, we can also add __init to leon_flush_needed().
Signed-off-by: Matthias Rosenfelder <rosenfelder.lkml@googlemail.com>
Acked-by: Daniel Hellstrom <daniel@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Do not trace arch_local_save_flags(), arch_local_irq_*() and friends.
Although they are marked inline, gcc may still make a function out of
them and add it to the pool of functions that are traced by the function
tracer. This can cause undesirable results (kernel panic, triple faults,
etc).
Add the notrace notation to prevent them from ever being traced.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Set up a correct I2C bus controller variant name for Exynos4.
Without this change the I2C bus driver fails to acquire its
clocks.
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
tx_st_done is required for checking the transmission status of SPI
channels with different fifo levels
Signed-off-by: Padmavathi Venna <padma.v@samsung.com>
Acked-by: Jassi Brar <jassisinghbrar@gmail.com
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Since git commit
660e34cebf x86: reorder reboot method
preferences,
my Acer Aspire One hangs on reboot. It appears that its ACPI method
for rebooting is broken. The attached patch adds a quirk so that the
machine will reboot via the BIOS.
[ hpa: verified that the ACPI control on this machine is just plain broken. ]
Signed-off-by: Peter Chubb <peter.chubb@nicta.com.au>
Link: http://lkml.kernel.org/r/w439iki5vl.wl%25peter@chubb.wattle.id.au
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The section mismatch in headsmp.S made hotplug stop working after the
first instance of suspend-to-RAM and its wakeup.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
This patch fixes following.
<6>[ 0.000000] sched_clock: 32 bits at 33MHz, ...
<6>[ 128.651309] Calibrating delay loop...
There is a big jump. The reason is that PWM Timer which
is for HRTimer was used before its initialization.
So this patch changes its order and following is kernel
boot log message after this.
<6>[ 0.000000] sched_clock: 32 bits at 33MHz, ...
<6>[ 0.000088] Calibrating delay loop...
Signed-off-by: Sangbeom Kim <sbkim73@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
There has been no #ifndef - #define - #endif protection for this
header file.
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
These pins are incorrectly configured for PCM2
configure them to SPDIF(_OUT & _EXT_CLK)
Signed-off-by: Naveen Krishna Chatradhi <ch.naveen@samsung.com>
Acked-by: Jassi Brar <jassisinghbrar@gmail.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
On SMDKV310 board, a card detect gpio pin is available that is directly
connected to the io pad of the sdhci controller. Fix incorrect value
of cd_type field in platform data for sdhci instance 0 and 2.
Signed-off-by: Thomas Abraham <thomas.ab@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
Ensure that the meminfo array is sanity checked before we pass the
memory to memblock. This helps to ensure that memblock and meminfo
agree on the dimensions of memory, especially when more memory is
passed than the kernel can deal with.
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
armpmu_enable can be called in situations where no events are present
(for example, from the event rotation tick after a profiled task has
exited). In this case, we currently start the PMU anyway which may
leave it active inevitably without any events being monitored.
This patch adds a simple check to the enabling code so that we avoid
starting the PMU when no events are present.
Cc: <stable@kernel.org>
Reported-by: Ashwin Chaugle <ashwinc@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The recently modified nand buswitth configuration is not aligned with
board reality: the double footprint on boards is always populated with 8bits
buswidth nand flashes.
So we have to consider that without particular configuration the 8bits
buswidth is selected by default.
Moreover, the previous logic was always using !board_have_nand_8bit(), we
change it to a simpler: board_have_nand_16bit().
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Tested-by: Ludovic Desroches <ludovic.desroches@atmel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Pointers to statically declared platform device structures which are
registered with platform_device_register() are then used during run time
to access these structure members, for example from platform_uevent()
and much more. Therefore, these structures should never be placed inside
sections which are dropped after boot. Fix platform devices incorrectly
tagged with __initdata which happen to exist inside OMAP sub-trees.
This bug has exhibited itself on my ARM/OMAP1 based Amstrad Delta
videophone after commit 6d3163ce86, "mm:
check if any page in a pageblock is reserved before marking it
MIGRATE_RESERVE", resulting in reading from several
/sys/device/platform/*/uevent files always ending up with segmentation
faults.
Signed-off-by: Janusz Krzysztofik <jkrzyszt@tis.icnet.pl>
Acked-by: Felipe Balbi <balbi@ti.com>
Cc: Varadarajan, Charulatha <charu@ti.com>
Cc: Jarkko Nikula <jhnikula@gmail.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
When map_single() is unable to obtain a safe buffer, we must return
the dma_addr_t error value, which is ~0 rather than 0.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
During 32/64 NUMA init unification, commit 797390d855 ("x86-32,
NUMA: use sparse_memory_present_with_active_regions()") made
32bit mm init call memory_present() automatically from
active_regions instead of leaving it to each NUMA init path.
This commit description is inaccurate - memory_present() calls
aren't the same for flat and numaq. After the commit,
memory_present() is only called for the intersection of e820 and
NUMA layout. Before, on flatmem, memory_present() would be
called from 0 to max_pfn. After, it would be called only on the
areas that e820 indicates to be populated.
This is how x86_64 works and should be okay as memmap is allowed
to contain holes; however, x86_32 DISCONTIGMEM is missing
early_pfn_valid(), which makes memmap_init_zone() assume that
memmap doesn't contain any hole. This leads to the following
oops if e820 map contains holes as it often does on machine with
near or more 4GiB of memory by calling pfn_to_page() on a pfn
which isn't mapped to a NUMA node, a reported by Conny Seidel:
BUG: unable to handle kernel paging request at 000012b0
IP: [<c1aa13ce>] memmap_init_zone+0x6c/0xf2
*pdpt =3D 0000000000000000 *pde =3D f000eef3f000ee00
Oops: 0000 [#1] SMP
last sysfs file:
Modules linked in:
Pid: 0, comm: swapper Not tainted 2.6.39-rc5-00164-g797390d #1 To Be Filled By O.E.M. To Be Filled By O.E.M./E350M1
EIP: 0060:[<c1aa13ce>] EFLAGS: 00010012 CPU: 0
EIP is at memmap_init_zone+0x6c/0xf2
EAX: 00000000 EBX: 000a8000 ECX: 000a7fff EDX: f2c00b80
ESI: 000a8000 EDI: f2c00800 EBP: c19ffe54 ESP: c19ffe34
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Process swapper (pid: 0, ti=3Dc19fe000 task=3Dc1a07f60 task.ti=3Dc19fe000)
Stack:
00000002 00000000 0023f000 00000000 10000000 00000a00 f2c00000 f2c00b58
c19ffeb0 c1a80f24 000375fe 00000000 f2c00800 00000800 00000100 00000030
c1abb768 0000003c 00000000 00000000 00000004 00207a02 f2c00800 000375fe
Call Trace:
[<c1a80f24>] free_area_init_node+0x358/0x385
[<c1a81384>] free_area_init_nodes+0x420/0x487
[<c1a79326>] paging_init+0x114/0x11b
[<c1a6cb13>] setup_arch+0xb37/0xc0a
[<c1a69554>] start_kernel+0x76/0x316
[<c1a690a8>] i386_start_kernel+0xa8/0xb0
This patch fixes the bug by defining early_pfn_valid() to be the
same as pfn_valid() when DISCONTIGMEM.
Reported-bisected-and-tested-by: Conny Seidel <conny.seidel@amd.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: hans.rosenfeld@amd.com
Cc: Christoph Lameter <cl@linux.com>
Cc: Conny Seidel <conny.seidel@amd.com>
Link: http://lkml.kernel.org/r/20110628094107.GB3386@htj.dyndns.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In the past we would use the GSI value to preset the ACPI SCI
IRQ which worked great as GSI == IRQ:
ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level)
While that is most often seen, there are some oddities:
ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level)
which means that GSI 20 (or pin 20) is to be overriden for IRQ 9.
Our code that presets the interrupt for ACPI SCI however would
use the GSI 20 instead of IRQ 9 ending up with:
xen: sci override: global_irq=20 trigger=0 polarity=1
xen: registering gsi 20 triggering 0 polarity 1
xen: --> pirq=20 -> irq=20
xen: acpi sci 20
.. snip..
calling acpi_init+0x0/0xbc @ 1
ACPI: SCI (IRQ9) allocation failed
ACPI Exception: AE_NOT_ACQUIRED, Unable to install System Control Interrupt handler (20110413/evevent-119)
ACPI: Unable to start the ACPI Interpreter
as the ACPI interpreter made a call to 'acpi_gsi_to_irq' which got nine.
It used that value to request an IRQ (request_irq) and since that was not
present it failed.
The fix is to recognize that for interrupts that are overriden (in our
case we only care about the ACPI SCI) we should use the IRQ number
to present the IRQ instead of the using GSI. End result is that we get:
xen: sci override: global_irq=20 trigger=0 polarity=1
xen: registering gsi 20 triggering 0 polarity 1
xen: --> pirq=20 -> irq=9 (gsi=9)
xen: acpi sci 9
which fixes the ACPI interpreter failing on startup.
CC: stable@kernel.org
Reported-by: Liwei <xieliwei@gmail.com>
Tested-by: Liwei <xieliwei@gmail.com>
[http://lists.xensource.com/archives/html/xen-devel/2011-06/msg01727.html]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Simple enough - we use an extern defined symbol which is not
defined when CONFIG_SMP is not defined. This fixes the linker
dying.
CC: stable@kernel.org
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Matt Evans