--- /dev/null
+Pinctrl-based I2C Bus Mux
+
+This binding describes an I2C bus multiplexer that uses pin multiplexing to
+route the I2C signals, and represents the pin multiplexing configuration
+using the pinctrl device tree bindings.
+
+ +-----+ +-----+
+ | dev | | dev |
+ +------------------------+ +-----+ +-----+
+ | SoC | | |
+ | /----|------+--------+
+ | +---+ +------+ | child bus A, on first set of pins
+ | |I2C|---|Pinmux| |
+ | +---+ +------+ | child bus B, on second set of pins
+ | \----|------+--------+--------+
+ | | | | |
+ +------------------------+ +-----+ +-----+ +-----+
+ | dev | | dev | | dev |
+ +-----+ +-----+ +-----+
+
+Required properties:
+- compatible: i2c-mux-pinctrl
+- i2c-parent: The phandle of the I2C bus that this multiplexer's master-side
+ port is connected to.
+
+Also required are:
+
+* Standard pinctrl properties that specify the pin mux state for each child
+ bus. See ../pinctrl/pinctrl-bindings.txt.
+
+* Standard I2C mux properties. See mux.txt in this directory.
+
+* I2C child bus nodes. See mux.txt in this directory.
+
+For each named state defined in the pinctrl-names property, an I2C child bus
+will be created. I2C child bus numbers are assigned based on the index into
+the pinctrl-names property.
+
+The only exception is that no bus will be created for a state named "idle". If
+such a state is defined, it must be the last entry in pinctrl-names. For
+example:
+
+ pinctrl-names = "ddc", "pta", "idle" -> ddc = bus 0, pta = bus 1
+ pinctrl-names = "ddc", "idle", "pta" -> Invalid ("idle" not last)
+ pinctrl-names = "idle", "ddc", "pta" -> Invalid ("idle" not last)
+
+Whenever an access is made to a device on a child bus, the relevant pinctrl
+state will be programmed into hardware.
+
+If an idle state is defined, whenever an access is not being made to a device
+on a child bus, the idle pinctrl state will be programmed into hardware.
+
+If an idle state is not defined, the most recently used pinctrl state will be
+left programmed into hardware whenever no access is being made of a device on
+a child bus.
+
+Example:
+
+ i2cmux {
+ compatible = "i2c-mux-pinctrl";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ i2c-parent = <&i2c1>;
+
+ pinctrl-names = "ddc", "pta", "idle";
+ pinctrl-0 = <&state_i2cmux_ddc>;
+ pinctrl-1 = <&state_i2cmux_pta>;
+ pinctrl-2 = <&state_i2cmux_idle>;
+
+ i2c@0 {
+ reg = <0>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eeprom {
+ compatible = "eeprom";
+ reg = <0x50>;
+ };
+ };
+
+ i2c@1 {
+ reg = <1>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ eeprom {
+ compatible = "eeprom";
+ reg = <0x50>;
+ };
+ };
+ };
+
sched_debug [KNL] Enables verbose scheduler debug messages.
+ skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
+ xtime_lock contention on larger systems, and/or RCU lock
+ contention on all systems with CONFIG_MAXSMP set.
+ Format: { "0" | "1" }
+ 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
+ 1 -- enable.
+ Note: increases power consumption, thus should only be
+ enabled if running jitter sensitive (HPC/RT) workloads.
+
security= [SECURITY] Choose a security module to enable at boot.
If this boot parameter is not specified, only the first
security module asking for security registration will be
will enable debug messages for when routes change.
+Counters for different types of packets entering and leaving the
+batman-adv module are available through ethtool:
+
+# ethtool --statistics bat0
+
BATCTL
------
--- /dev/null
+Frontswap provides a "transcendent memory" interface for swap pages.
+In some environments, dramatic performance savings may be obtained because
+swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
+
+(Note, frontswap -- and cleancache (merged at 3.0) -- are the "frontends"
+and the only necessary changes to the core kernel for transcendent memory;
+all other supporting code -- the "backends" -- is implemented as drivers.
+See the LWN.net article "Transcendent memory in a nutshell" for a detailed
+overview of frontswap and related kernel parts:
+https://lwn.net/Articles/454795/ )
+
+Frontswap is so named because it can be thought of as the opposite of
+a "backing" store for a swap device. The storage is assumed to be
+a synchronous concurrency-safe page-oriented "pseudo-RAM device" conforming
+to the requirements of transcendent memory (such as Xen's "tmem", or
+in-kernel compressed memory, aka "zcache", or future RAM-like devices);
+this pseudo-RAM device is not directly accessible or addressable by the
+kernel and is of unknown and possibly time-varying size. The driver
+links itself to frontswap by calling frontswap_register_ops to set the
+frontswap_ops funcs appropriately and the functions it provides must
+conform to certain policies as follows:
+
+An "init" prepares the device to receive frontswap pages associated
+with the specified swap device number (aka "type"). A "store" will
+copy the page to transcendent memory and associate it with the type and
+offset associated with the page. A "load" will copy the page, if found,
+from transcendent memory into kernel memory, but will NOT remove the page
+from from transcendent memory. An "invalidate_page" will remove the page
+from transcendent memory and an "invalidate_area" will remove ALL pages
+associated with the swap type (e.g., like swapoff) and notify the "device"
+to refuse further stores with that swap type.
+
+Once a page is successfully stored, a matching load on the page will normally
+succeed. So when the kernel finds itself in a situation where it needs
+to swap out a page, it first attempts to use frontswap. If the store returns
+success, the data has been successfully saved to transcendent memory and
+a disk write and, if the data is later read back, a disk read are avoided.
+If a store returns failure, transcendent memory has rejected the data, and the
+page can be written to swap as usual.
+
+If a backend chooses, frontswap can be configured as a "writethrough
+cache" by calling frontswap_writethrough(). In this mode, the reduction
+in swap device writes is lost (and also a non-trivial performance advantage)
+in order to allow the backend to arbitrarily "reclaim" space used to
+store frontswap pages to more completely manage its memory usage.
+
+Note that if a page is stored and the page already exists in transcendent memory
+(a "duplicate" store), either the store succeeds and the data is overwritten,
+or the store fails AND the page is invalidated. This ensures stale data may
+never be obtained from frontswap.
+
+If properly configured, monitoring of frontswap is done via debugfs in
+the /sys/kernel/debug/frontswap directory. The effectiveness of
+frontswap can be measured (across all swap devices) with:
+
+failed_stores - how many store attempts have failed
+loads - how many loads were attempted (all should succeed)
+succ_stores - how many store attempts have succeeded
+invalidates - how many invalidates were attempted
+
+A backend implementation may provide additional metrics.
+
+FAQ
+
+1) Where's the value?
+
+When a workload starts swapping, performance falls through the floor.
+Frontswap significantly increases performance in many such workloads by
+providing a clean, dynamic interface to read and write swap pages to
+"transcendent memory" that is otherwise not directly addressable to the kernel.
+This interface is ideal when data is transformed to a different form
+and size (such as with compression) or secretly moved (as might be
+useful for write-balancing for some RAM-like devices). Swap pages (and
+evicted page-cache pages) are a great use for this kind of slower-than-RAM-
+but-much-faster-than-disk "pseudo-RAM device" and the frontswap (and
+cleancache) interface to transcendent memory provides a nice way to read
+and write -- and indirectly "name" -- the pages.
+
+Frontswap -- and cleancache -- with a fairly small impact on the kernel,
+provides a huge amount of flexibility for more dynamic, flexible RAM
+utilization in various system configurations:
+
+In the single kernel case, aka "zcache", pages are compressed and
+stored in local memory, thus increasing the total anonymous pages
+that can be safely kept in RAM. Zcache essentially trades off CPU
+cycles used in compression/decompression for better memory utilization.
+Benchmarks have shown little or no impact when memory pressure is
+low while providing a significant performance improvement (25%+)
+on some workloads under high memory pressure.
+
+"RAMster" builds on zcache by adding "peer-to-peer" transcendent memory
+support for clustered systems. Frontswap pages are locally compressed
+as in zcache, but then "remotified" to another system's RAM. This
+allows RAM to be dynamically load-balanced back-and-forth as needed,
+i.e. when system A is overcommitted, it can swap to system B, and
+vice versa. RAMster can also be configured as a memory server so
+many servers in a cluster can swap, dynamically as needed, to a single
+server configured with a large amount of RAM... without pre-configuring
+how much of the RAM is available for each of the clients!
+
+In the virtual case, the whole point of virtualization is to statistically
+multiplex physical resources acrosst the varying demands of multiple
+virtual machines. This is really hard to do with RAM and efforts to do
+it well with no kernel changes have essentially failed (except in some
+well-publicized special-case workloads).
+Specifically, the Xen Transcendent Memory backend allows otherwise
+"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple
+virtual machines, but the pages can be compressed and deduplicated to
+optimize RAM utilization. And when guest OS's are induced to surrender
+underutilized RAM (e.g. with "selfballooning"), sudden unexpected
+memory pressure may result in swapping; frontswap allows those pages
+to be swapped to and from hypervisor RAM (if overall host system memory
+conditions allow), thus mitigating the potentially awful performance impact
+of unplanned swapping.
+
+A KVM implementation is underway and has been RFC'ed to lkml. And,
+using frontswap, investigation is also underway on the use of NVM as
+a memory extension technology.
+
+2) Sure there may be performance advantages in some situations, but
+ what's the space/time overhead of frontswap?
+
+If CONFIG_FRONTSWAP is disabled, every frontswap hook compiles into
+nothingness and the only overhead is a few extra bytes per swapon'ed
+swap device. If CONFIG_FRONTSWAP is enabled but no frontswap "backend"
+registers, there is one extra global variable compared to zero for
+every swap page read or written. If CONFIG_FRONTSWAP is enabled
+AND a frontswap backend registers AND the backend fails every "store"
+request (i.e. provides no memory despite claiming it might),
+CPU overhead is still negligible -- and since every frontswap fail
+precedes a swap page write-to-disk, the system is highly likely
+to be I/O bound and using a small fraction of a percent of a CPU
+will be irrelevant anyway.
+
+As for space, if CONFIG_FRONTSWAP is enabled AND a frontswap backend
+registers, one bit is allocated for every swap page for every swap
+device that is swapon'd. This is added to the EIGHT bits (which
+was sixteen until about 2.6.34) that the kernel already allocates
+for every swap page for every swap device that is swapon'd. (Hugh
+Dickins has observed that frontswap could probably steal one of
+the existing eight bits, but let's worry about that minor optimization
+later.) For very large swap disks (which are rare) on a standard
+4K pagesize, this is 1MB per 32GB swap.
+
+When swap pages are stored in transcendent memory instead of written
+out to disk, there is a side effect that this may create more memory
+pressure that can potentially outweigh the other advantages. A
+backend, such as zcache, must implement policies to carefully (but
+dynamically) manage memory limits to ensure this doesn't happen.
+
+3) OK, how about a quick overview of what this frontswap patch does
+ in terms that a kernel hacker can grok?
+
+Let's assume that a frontswap "backend" has registered during
+kernel initialization; this registration indicates that this
+frontswap backend has access to some "memory" that is not directly
+accessible by the kernel. Exactly how much memory it provides is
+entirely dynamic and random.
+
+Whenever a swap-device is swapon'd frontswap_init() is called,
+passing the swap device number (aka "type") as a parameter.
+This notifies frontswap to expect attempts to "store" swap pages
+associated with that number.
+
+Whenever the swap subsystem is readying a page to write to a swap
+device (c.f swap_writepage()), frontswap_store is called. Frontswap
+consults with the frontswap backend and if the backend says it does NOT
+have room, frontswap_store returns -1 and the kernel swaps the page
+to the swap device as normal. Note that the response from the frontswap
+backend is unpredictable to the kernel; it may choose to never accept a
+page, it could accept every ninth page, or it might accept every
+page. But if the backend does accept a page, the data from the page
+has already been copied and associated with the type and offset,
+and the backend guarantees the persistence of the data. In this case,
+frontswap sets a bit in the "frontswap_map" for the swap device
+corresponding to the page offset on the swap device to which it would
+otherwise have written the data.
+
+When the swap subsystem needs to swap-in a page (swap_readpage()),
+it first calls frontswap_load() which checks the frontswap_map to
+see if the page was earlier accepted by the frontswap backend. If
+it was, the page of data is filled from the frontswap backend and
+the swap-in is complete. If not, the normal swap-in code is
+executed to obtain the page of data from the real swap device.
+
+So every time the frontswap backend accepts a page, a swap device read
+and (potentially) a swap device write are replaced by a "frontswap backend
+store" and (possibly) a "frontswap backend loads", which are presumably much
+faster.
+
+4) Can't frontswap be configured as a "special" swap device that is
+ just higher priority than any real swap device (e.g. like zswap,
+ or maybe swap-over-nbd/NFS)?
+
+No. First, the existing swap subsystem doesn't allow for any kind of
+swap hierarchy. Perhaps it could be rewritten to accomodate a hierarchy,
+but this would require fairly drastic changes. Even if it were
+rewritten, the existing swap subsystem uses the block I/O layer which
+assumes a swap device is fixed size and any page in it is linearly
+addressable. Frontswap barely touches the existing swap subsystem,
+and works around the constraints of the block I/O subsystem to provide
+a great deal of flexibility and dynamicity.
+
+For example, the acceptance of any swap page by the frontswap backend is
+entirely unpredictable. This is critical to the definition of frontswap
+backends because it grants completely dynamic discretion to the
+backend. In zcache, one cannot know a priori how compressible a page is.
+"Poorly" compressible pages can be rejected, and "poorly" can itself be
+defined dynamically depending on current memory constraints.
+
+Further, frontswap is entirely synchronous whereas a real swap
+device is, by definition, asynchronous and uses block I/O. The
+block I/O layer is not only unnecessary, but may perform "optimizations"
+that are inappropriate for a RAM-oriented device including delaying
+the write of some pages for a significant amount of time. Synchrony is
+required to ensure the dynamicity of the backend and to avoid thorny race
+conditions that would unnecessarily and greatly complicate frontswap
+and/or the block I/O subsystem. That said, only the initial "store"
+and "load" operations need be synchronous. A separate asynchronous thread
+is free to manipulate the pages stored by frontswap. For example,
+the "remotification" thread in RAMster uses standard asynchronous
+kernel sockets to move compressed frontswap pages to a remote machine.
+Similarly, a KVM guest-side implementation could do in-guest compression
+and use "batched" hypercalls.
+
+In a virtualized environment, the dynamicity allows the hypervisor
+(or host OS) to do "intelligent overcommit". For example, it can
+choose to accept pages only until host-swapping might be imminent,
+then force guests to do their own swapping.
+
+There is a downside to the transcendent memory specifications for
+frontswap: Since any "store" might fail, there must always be a real
+slot on a real swap device to swap the page. Thus frontswap must be
+implemented as a "shadow" to every swapon'd device with the potential
+capability of holding every page that the swap device might have held
+and the possibility that it might hold no pages at all. This means
+that frontswap cannot contain more pages than the total of swapon'd
+swap devices. For example, if NO swap device is configured on some
+installation, frontswap is useless. Swapless portable devices
+can still use frontswap but a backend for such devices must configure
+some kind of "ghost" swap device and ensure that it is never used.
+
+5) Why this weird definition about "duplicate stores"? If a page
+ has been previously successfully stored, can't it always be
+ successfully overwritten?
+
+Nearly always it can, but no, sometimes it cannot. Consider an example
+where data is compressed and the original 4K page has been compressed
+to 1K. Now an attempt is made to overwrite the page with data that
+is non-compressible and so would take the entire 4K. But the backend
+has no more space. In this case, the store must be rejected. Whenever
+frontswap rejects a store that would overwrite, it also must invalidate
+the old data and ensure that it is no longer accessible. Since the
+swap subsystem then writes the new data to the read swap device,
+this is the correct course of action to ensure coherency.
+
+6) What is frontswap_shrink for?
+
+When the (non-frontswap) swap subsystem swaps out a page to a real
+swap device, that page is only taking up low-value pre-allocated disk
+space. But if frontswap has placed a page in transcendent memory, that
+page may be taking up valuable real estate. The frontswap_shrink
+routine allows code outside of the swap subsystem to force pages out
+of the memory managed by frontswap and back into kernel-addressable memory.
+For example, in RAMster, a "suction driver" thread will attempt
+to "repatriate" pages sent to a remote machine back to the local machine;
+this is driven using the frontswap_shrink mechanism when memory pressure
+subsides.
+
+7) Why does the frontswap patch create the new include file swapfile.h?
+
+The frontswap code depends on some swap-subsystem-internal data
+structures that have, over the years, moved back and forth between
+static and global. This seemed a reasonable compromise: Define
+them as global but declare them in a new include file that isn't
+included by the large number of source files that include swap.h.
+
+Dan Magenheimer, last updated April 9, 2012
ARM/SAMSUNG S5P SERIES Multi Format Codec (MFC) SUPPORT
M: Kyungmin Park <kyungmin.park@samsung.com>
M: Kamil Debski <k.debski@samsung.com>
-M: Jeongtae Park <jtp.park@samsung.com>
+M: Jeongtae Park <jtp.park@samsung.com>
L: linux-arm-kernel@lists.infradead.org
L: linux-media@vger.kernel.org
S: Maintained
CAPABILITIES
M: Serge Hallyn <serge.hallyn@canonical.com>
L: linux-security-module@vger.kernel.org
-S: Supported
+S: Supported
F: include/linux/capability.h
F: security/capability.c
-F: security/commoncap.c
+F: security/commoncap.c
F: kernel/capability.c
CELL BROADBAND ENGINE ARCHITECTURE
F: drivers/net/wan/pc300*
CYTTSP TOUCHSCREEN DRIVER
-M: Javier Martinez Canillas <javier@dowhile0.org>
-L: linux-input@vger.kernel.org
-S: Maintained
-F: drivers/input/touchscreen/cyttsp*
-F: include/linux/input/cyttsp.h
+M: Javier Martinez Canillas <javier@dowhile0.org>
+L: linux-input@vger.kernel.org
+S: Maintained
+F: drivers/input/touchscreen/cyttsp*
+F: include/linux/input/cyttsp.h
DAMA SLAVE for AX.25
M: Joerg Reuter <jreuter@yaina.de>
F: include/linux/dm-*.h
DIOLAN U2C-12 I2C DRIVER
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-diolan-u2c.c
F: include/linux/freezer.h
F: kernel/freezer.c
+FRONTSWAP API
+M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+L: linux-kernel@vger.kernel.org
+S: Maintained
+F: mm/frontswap.c
+F: include/linux/frontswap.h
+
FS-CACHE: LOCAL CACHING FOR NETWORK FILESYSTEMS
M: David Howells <dhowells@redhat.com>
L: linux-cachefs@redhat.com
HARDWARE MONITORING
M: Jean Delvare <khali@linux-fr.org>
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: lm-sensors@lm-sensors.org
W: http://www.lm-sensors.org/
T: quilt kernel.org/pub/linux/kernel/people/jdelvare/linux-2.6/jdelvare-hwmon/
LED SUBSYSTEM
M: Bryan Wu <bryan.wu@canonical.com>
M: Richard Purdie <rpurdie@rpsys.net>
+L: linux-leds@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/linux-leds.git
S: Maintained
F: drivers/leds/
F: include/linux/leds.h
F: drivers/video/matrox/matroxfb_*
F: include/linux/matroxfb.h
+MAX16065 HARDWARE MONITOR DRIVER
+M: Guenter Roeck <linux@roeck-us.net>
+L: lm-sensors@lm-sensors.org
+S: Maintained
+F: Documentation/hwmon/max16065
+F: drivers/hwmon/max16065.c
+
MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
M: "Hans J. Koch" <hjk@hansjkoch.de>
L: lm-sensors@lm-sensors.org
F: include/linux/leds-pca9532.h
PCA9541 I2C BUS MASTER SELECTOR DRIVER
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/muxes/i2c-mux-pca9541.c
F: drivers/firmware/pcdp.*
PCI ERROR RECOVERY
-M: Linas Vepstas <linasvepstas@gmail.com>
+M: Linas Vepstas <linasvepstas@gmail.com>
L: linux-pci@vger.kernel.org
S: Supported
F: Documentation/PCI/pci-error-recovery.txt
F: drivers/rtc/rtc-puv3.c
PMBUS HARDWARE MONITORING DRIVERS
-M: Guenter Roeck <guenter.roeck@ericsson.com>
+M: Guenter Roeck <linux@roeck-us.net>
L: lm-sensors@lm-sensors.org
W: http://www.lm-sensors.org/
W: http://www.roeck-us.net/linux/drivers/
F: drivers/uio/
F: include/linux/uio*.h
-UTIL-LINUX-NG PACKAGE
+UTIL-LINUX PACKAGE
M: Karel Zak <kzak@redhat.com>
-L: util-linux-ng@vger.kernel.org
-W: http://kernel.org/~kzak/util-linux-ng/
-T: git git://git.kernel.org/pub/scm/utils/util-linux-ng/util-linux-ng.git
+L: util-linux@vger.kernel.org
+W: http://en.wikipedia.org/wiki/Util-linux
+T: git git://git.kernel.org/pub/scm/utils/util-linux/util-linux.git
S: Maintained
UVESAFB DRIVER
VERSION = 3
PATCHLEVEL = 5
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
NAME = Saber-toothed Squirrel
# *DOCUMENTATION*
select HAVE_IDE if PCI || ISA || PCMCIA
select HAVE_DMA_ATTRS
select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
- select CMA if (CPU_V6 || CPU_V6K || CPU_V7)
select HAVE_MEMBLOCK
select RTC_LIB
select SYS_SUPPORTS_APM_EMULATION
goto err;
}
- r = omap_device_register(pdev);
+ r = platform_device_add(pdev);
if (r) {
- pr_err("Could not register omap_device for %s\n", pdev_name);
+ pr_err("Could not register platform_device for %s\n", pdev_name);
goto err;
}
help
This enables build of the TMU timer driver.
+config EM_TIMER_STI
+ bool "STI timer driver"
+ default y
+ help
+ This enables build of the STI timer driver.
+
endmenu
config SH_CLK_CPG
unsigned long base = consistent_base;
unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
-#ifndef CONFIG_ARM_DMA_USE_IOMMU
- if (cpu_architecture() >= CPU_ARCH_ARMv6)
+ if (IS_ENABLED(CONFIG_CMA) && !IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
return 0;
-#endif
consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
if (!consistent_pte) {
struct page *page;
void *ptr;
- if (cpu_architecture() < CPU_ARCH_ARMv6)
+ if (!IS_ENABLED(CONFIG_CMA))
return 0;
ptr = __alloc_from_contiguous(NULL, size, prot, &page);
if (arch_is_coherent() || nommu())
addr = __alloc_simple_buffer(dev, size, gfp, &page);
- else if (cpu_architecture() < CPU_ARCH_ARMv6)
+ else if (!IS_ENABLED(CONFIG_CMA))
addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
else if (gfp & GFP_ATOMIC)
addr = __alloc_from_pool(dev, size, &page, caller);
if (arch_is_coherent() || nommu()) {
__dma_free_buffer(page, size);
- } else if (cpu_architecture() < CPU_ARCH_ARMv6) {
+ } else if (!IS_ENABLED(CONFIG_CMA)) {
__dma_free_remap(cpu_addr, size);
__dma_free_buffer(page, size);
} else {
if ((sysreg_read(SR) & MODE_MASK) == MODE_SUPERVISOR)
syscall = 1;
- if (ti->flags & _TIF_SIGPENDING))
+ if (ti->flags & _TIF_SIGPENDING)
do_signal(regs, syscall);
if (ti->flags & _TIF_NOTIFY_RESUME) {
unsigned long newsp;
#ifdef __ARCH_SYNC_CORE_DCACHE
- if (current->rt.nr_cpus_allowed == num_possible_cpus())
+ if (current->nr_cpus_allowed == num_possible_cpus())
set_cpus_allowed_ptr(current, cpumask_of(smp_processor_id()));
#endif
select GENERIC_IRQ_SHOW
select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS
select GENERIC_CPU_DEVICES
+ select GENERIC_STRNCPY_FROM_USER if MMU
+ select GENERIC_STRNLEN_USER if MMU
select FPU if MMU
select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
include include/asm-generic/Kbuild.asm
header-y += cachectl.h
+
+generic-y += word-at-a-time.h
/*
* QSPI module.
*/
-#define MCFQSPI_IOBASE (MCF_IPSBAR + 0x340)
+#define MCFQSPI_BASE (MCF_IPSBAR + 0x340)
#define MCFQSPI_SIZE 0x40
#define MCFQSPI_CS0 147
#define copy_from_user(to, from, n) __copy_from_user(to, from, n)
#define copy_to_user(to, from, n) __copy_to_user(to, from, n)
-long strncpy_from_user(char *dst, const char __user *src, long count);
-long strnlen_user(const char __user *src, long n);
+#define user_addr_max() \
+ (segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+
+extern long strncpy_from_user(char *dst, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
unsigned long __clear_user(void __user *to, unsigned long n);
#define clear_user __clear_user
-#define strlen_user(str) strnlen_user(str, 32767)
-
#endif /* _M68K_UACCESS_H */
}
}
-#ifdef CONFIG_COLDFIRE
+#if defined(CONFIG_COLDFIRE) || !defined(CONFIG_MMU)
asmlinkage int syscall_trace_enter(void)
{
int ret = 0;
mach_sched_init(timer_interrupt);
}
-#ifdef CONFIG_M68KCLASSIC
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
u32 arch_gettimeoffset(void)
{
module_init(rtc_init);
-#endif /* CONFIG_M68KCLASSIC */
+#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
}
EXPORT_SYMBOL(__generic_copy_to_user);
-/*
- * Copy a null terminated string from userspace.
- */
-long strncpy_from_user(char *dst, const char __user *src, long count)
-{
- long res;
- char c;
-
- if (count <= 0)
- return count;
-
- asm volatile ("\n"
- "1: "MOVES".b (%2)+,%4\n"
- " move.b %4,(%1)+\n"
- " jeq 2f\n"
- " subq.l #1,%3\n"
- " jne 1b\n"
- "2: sub.l %3,%0\n"
- "3:\n"
- " .section .fixup,\"ax\"\n"
- " .even\n"
- "10: move.l %5,%0\n"
- " jra 3b\n"
- " .previous\n"
- "\n"
- " .section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 1b,10b\n"
- " .previous"
- : "=d" (res), "+a" (dst), "+a" (src), "+r" (count), "=&d" (c)
- : "i" (-EFAULT), "0" (count));
-
- return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
- * Return the size of a string (including the ending 0)
- *
- * Return 0 on exception, a value greater than N if too long
- */
-long strnlen_user(const char __user *src, long n)
-{
- char c;
- long res;
-
- asm volatile ("\n"
- "1: subq.l #1,%1\n"
- " jmi 3f\n"
- "2: "MOVES".b (%0)+,%2\n"
- " tst.b %2\n"
- " jne 1b\n"
- " jra 4f\n"
- "\n"
- "3: addq.l #1,%0\n"
- "4: sub.l %4,%0\n"
- "5:\n"
- " .section .fixup,\"ax\"\n"
- " .even\n"
- "20: sub.l %0,%0\n"
- " jra 5b\n"
- " .previous\n"
- "\n"
- " .section __ex_table,\"a\"\n"
- " .align 4\n"
- " .long 2b,20b\n"
- " .previous\n"
- : "=&a" (res), "+d" (n), "=&d" (c)
- : "0" (src), "r" (src));
-
- return res;
-}
-EXPORT_SYMBOL(strnlen_user);
-
/*
* Zero Userspace
*/
#endif
static u32 m68328_tick_cnt;
+static irq_handler_t timer_interrupt;
/***************************************************************************/
TSTAT &= 0;
m68328_tick_cnt += TICKS_PER_JIFFY;
- return arch_timer_interrupt(irq, dummy);
+ return timer_interrupt(irq, dummy);
}
/***************************************************************************/
/***************************************************************************/
-void hw_timer_init(void)
+void hw_timer_init(irq_handler_t handler)
{
/* disable timer 1 */
TCTL = 0;
/* Enable timer 1 */
TCTL |= TCTL_TEN;
clocksource_register_hz(&m68328_clk, TICKS_PER_JIFFY*HZ);
+ timer_interrupt = handler;
}
/***************************************************************************/
#define OSCILLATOR (unsigned long int)33000000
#endif
+static irq_handler_t timer_interrupt;
unsigned long int system_clock;
extern QUICC *pquicc;
pquicc->timer_ter1 = 0x0002; /* clear timer event */
- return arch_timer_interrupt(irq, dummy);
+ return timer_interrupt(irq, dummy);
}
static struct irqaction m68360_timer_irq = {
.handler = hw_tick,
};
-void hw_timer_init(void)
+void hw_timer_init(irq_handler_t handler)
{
unsigned char prescaler;
unsigned short tgcr_save;
pquicc->timer_ter1 = 0x0003; /* clear timer events */
+ timer_interrupt = handler;
+
/* enable timer 1 interrupt in CIMR */
setup_irq(CPMVEC_TIMER1, &m68360_timer_irq);
NM = sh $(srctree)/arch/parisc/nm
CHECKFLAGS += -D__hppa__=1
+LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
MACHINE := $(shell uname -m)
ifeq ($(MACHINE),parisc*)
kernel-$(CONFIG_HPUX) += hpux/
core-y += $(addprefix arch/parisc/, $(kernel-y))
-libs-y += arch/parisc/lib/ `$(CC) -print-libgcc-file-name`
+libs-y += arch/parisc/lib/ $(LIBGCC)
drivers-$(CONFIG_OPROFILE) += arch/parisc/oprofile/
include include/asm-generic/Kbuild.asm
header-y += pdc.h
+generic-y += word-at-a-time.h
#ifndef _PARISC_BUG_H
#define _PARISC_BUG_H
+#include <linux/kernel.h> /* for BUGFLAG_TAINT */
+
/*
* Tell the user there is some problem.
* The offending file and line are encoded in the __bug_table section.
static inline int entry_matches(struct ppc_plt_entry *entry, Elf32_Addr val)
{
- if (entry->jump[0] == 0x3d600000 + ((val + 0x8000) >> 16)
- && entry->jump[1] == 0x396b0000 + (val & 0xffff))
+ if (entry->jump[0] == 0x3d800000 + ((val + 0x8000) >> 16)
+ && entry->jump[1] == 0x398c0000 + (val & 0xffff))
return 1;
return 0;
}
entry++;
}
- /* Stolen from Paul Mackerras as well... */
- entry->jump[0] = 0x3d600000+((val+0x8000)>>16); /* lis r11,sym@ha */
- entry->jump[1] = 0x396b0000 + (val&0xffff); /* addi r11,r11,sym@l*/
- entry->jump[2] = 0x7d6903a6; /* mtctr r11 */
+ entry->jump[0] = 0x3d800000+((val+0x8000)>>16); /* lis r12,sym@ha */
+ entry->jump[1] = 0x398c0000 + (val&0xffff); /* addi r12,r12,sym@l*/
+ entry->jump[2] = 0x7d8903a6; /* mtctr r12 */
entry->jump[3] = 0x4e800420; /* bctr */
DEBUGP("Initialized plt for 0x%x at %p\n", val, entry);
struct pt_regs *old_regs;
u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
struct clock_event_device *evt = &__get_cpu_var(decrementers);
+ u64 now;
/* Ensure a positive value is written to the decrementer, or else
* some CPUs will continue to take decrementer exceptions.
irq_work_run();
}
- *next_tb = ~(u64)0;
- if (evt->event_handler)
- evt->event_handler(evt);
+ now = get_tb_or_rtc();
+ if (now >= *next_tb) {
+ *next_tb = ~(u64)0;
+ if (evt->event_handler)
+ evt->event_handler(evt);
+ } else {
+ now = *next_tb - now;
+ if (now <= DECREMENTER_MAX)
+ set_dec((int)now);
+ }
#ifdef CONFIG_PPC64
/* collect purr register values often, for accurate calculations */
select GENERIC_SMP_IDLE_THREAD
select GENERIC_CLOCKEVENTS
select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
help
The SuperH is a RISC processor targeted for use in embedded systems
and consumer electronics; it was also used in the Sega Dreamcast
# License. See the file "COPYING" in the main directory of this archive
# for more details.
#
+ifneq ($(SUBARCH),$(ARCH))
+ ifeq ($(CROSS_COMPILE),)
+ CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux- $(UTS_MACHINE)-linux-gnu- $(UTS_MACHINE)-unknown-linux-gnu-)
+ endif
+endif
+
isa-y := any
isa-$(CONFIG_SH_DSP) := sh
isa-$(CONFIG_CPU_SH2) := sh2
KBUILD_DEFCONFIG := cayman_defconfig
endif
-ifneq ($(SUBARCH),$(ARCH))
- ifeq ($(CROSS_COMPILE),)
- CROSS_COMPILE := $(call cc-cross-prefix, $(UTS_MACHINE)-linux- $(UTS_MACHINE)-linux-gnu- $(UTS_MACHINE)-unknown-linux-gnu-)
- endif
-endif
-
ifdef CONFIG_CPU_LITTLE_ENDIAN
ld-bfd := elf32-$(UTS_MACHINE)-linux
-LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64' --oformat $(ld-bfd)
+LDFLAGS_vmlinux += --defsym jiffies=jiffies_64 --oformat $(ld-bfd)
LDFLAGS += -EL
else
ld-bfd := elf32-$(UTS_MACHINE)big-linux
-LDFLAGS_vmlinux += --defsym 'jiffies=jiffies_64+4' --oformat $(ld-bfd)
+LDFLAGS_vmlinux += --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd)
LDFLAGS += -EB
endif
include include/asm-generic/Kbuild.asm
+generic-y += bitsperlong.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += errno.h
+generic-y += fcntl.h
+generic-y += ioctl.h
+generic-y += ipcbuf.h
+generic-y += irq_regs.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += param.h
+generic-y += parport.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += mman.h
+generic-y += msgbuf.h
+generic-y += resource.h
+generic-y += scatterlist.h
+generic-y += sembuf.h
+generic-y += serial.h
+generic-y += shmbuf.h
+generic-y += siginfo.h
+generic-y += sizes.h
+generic-y += socket.h
+generic-y += statfs.h
+generic-y += termbits.h
+generic-y += termios.h
+generic-y += ucontext.h
+generic-y += xor.h
+
header-y += cachectl.h
header-y += cpu-features.h
header-y += hw_breakpoint.h
+++ /dev/null
-#include <asm-generic/bitsperlong.h>
+++ /dev/null
-#ifndef __SH_CPUTIME_H
-#define __SH_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __SH_CPUTIME_H */
+++ /dev/null
-#include <asm-generic/current.h>
+++ /dev/null
-#include <asm-generic/delay.h>
+++ /dev/null
-#include <asm-generic/div64.h>
+++ /dev/null
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
+++ /dev/null
-#ifndef __ASM_SH_ERRNO_H
-#define __ASM_SH_ERRNO_H
-
-#include <asm-generic/errno.h>
-
-#endif /* __ASM_SH_ERRNO_H */
+++ /dev/null
-#include <asm-generic/fcntl.h>
+++ /dev/null
-#include <asm-generic/ioctl.h>
+++ /dev/null
-#include <asm-generic/ipcbuf.h>
+++ /dev/null
-#include <asm-generic/irq_regs.h>
+++ /dev/null
-#include <asm-generic/kvm_para.h>
+++ /dev/null
-#ifndef __ASM_SH_LOCAL_H
-#define __ASM_SH_LOCAL_H
-
-#include <asm-generic/local.h>
-
-#endif /* __ASM_SH_LOCAL_H */
-
+++ /dev/null
-#include <asm-generic/local64.h>
+++ /dev/null
-#include <asm-generic/mman.h>
+++ /dev/null
-#include <asm-generic/msgbuf.h>
+++ /dev/null
-#include <asm-generic/param.h>
+++ /dev/null
-#include <asm-generic/parport.h>
+++ /dev/null
-#ifndef __ARCH_SH_PERCPU
-#define __ARCH_SH_PERCPU
-
-#include <asm-generic/percpu.h>
-
-#endif /* __ARCH_SH_PERCPU */
+++ /dev/null
-#include <asm-generic/poll.h>
+++ /dev/null
-#ifndef __ASM_SH_RESOURCE_H
-#define __ASM_SH_RESOURCE_H
-
-#include <asm-generic/resource.h>
-
-#endif /* __ASM_SH_RESOURCE_H */
+++ /dev/null
-#ifndef __ASM_SH_SCATTERLIST_H
-#define __ASM_SH_SCATTERLIST_H
-
-#include <asm-generic/scatterlist.h>
-
-#endif /* __ASM_SH_SCATTERLIST_H */
+++ /dev/null
-#include <asm-generic/sembuf.h>
+++ /dev/null
-#include <asm-generic/serial.h>
+++ /dev/null
-#include <asm-generic/shmbuf.h>
+++ /dev/null
-#ifndef __ASM_SH_SIGINFO_H
-#define __ASM_SH_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-#endif /* __ASM_SH_SIGINFO_H */
+++ /dev/null
-#include <asm-generic/sizes.h>
+++ /dev/null
-#include <asm-generic/socket.h>
+++ /dev/null
-#ifndef __ASM_SH_STATFS_H
-#define __ASM_SH_STATFS_H
-
-#include <asm-generic/statfs.h>
-
-#endif /* __ASM_SH_STATFS_H */
+++ /dev/null
-#include <asm-generic/termbits.h>
+++ /dev/null
-#include <asm-generic/termios.h>
(__chk_user_ptr(addr), \
__access_ok((unsigned long __force)(addr), (size)))
+#define user_addr_max() (current_thread_info()->addr_limit.seg)
+
/*
* Uh, these should become the main single-value transfer routines ...
* They automatically use the right size if we just have the right
# include "uaccess_64.h"
#endif
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
+
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
/* Generic arbitrary sized copy. */
/* Return the number of bytes NOT copied */
__kernel_size_t __copy_user(void *to, const void *from, __kernel_size_t n);
__cl_size; \
})
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst: Destination address, in kernel space. This buffer must be at
- * least @count bytes long.
- * @src: Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-#define strncpy_from_user(dest,src,count) \
-({ \
- unsigned long __sfu_src = (unsigned long)(src); \
- int __sfu_count = (int)(count); \
- long __sfu_res = -EFAULT; \
- \
- if (__access_ok(__sfu_src, __sfu_count)) \
- __sfu_res = __strncpy_from_user((unsigned long)(dest), \
- __sfu_src, __sfu_count); \
- \
- __sfu_res; \
-})
-
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
return __copy_size;
}
-/**
- * strnlen_user: - Get the size of a string in user space.
- * @s: The string to measure.
- * @n: The maximum valid length
- *
- * Context: User context only. This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- * If the string is too long, returns a value greater than @n.
- */
-static inline long strnlen_user(const char __user *s, long n)
-{
- if (!__addr_ok(s))
- return 0;
- else
- return __strnlen_user(s, n);
-}
-
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only. This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str) strnlen_user(str, ~0UL >> 1)
-
/*
* The exception table consists of pairs of addresses: the first is the
* address of an instruction that is allowed to fault, and the second is
extern void __put_user_unknown(void);
-static inline int
-__strncpy_from_user(unsigned long __dest, unsigned long __user __src, int __count)
-{
- __kernel_size_t res;
- unsigned long __dummy, _d, _s, _c;
-
- __asm__ __volatile__(
- "9:\n"
- "mov.b @%2+, %1\n\t"
- "cmp/eq #0, %1\n\t"
- "bt/s 2f\n"
- "1:\n"
- "mov.b %1, @%3\n\t"
- "dt %4\n\t"
- "bf/s 9b\n\t"
- " add #1, %3\n\t"
- "2:\n\t"
- "sub %4, %0\n"
- "3:\n"
- ".section .fixup,\"ax\"\n"
- "4:\n\t"
- "mov.l 5f, %1\n\t"
- "jmp @%1\n\t"
- " mov %9, %0\n\t"
- ".balign 4\n"
- "5: .long 3b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .balign 4\n"
- " .long 9b,4b\n"
- ".previous"
- : "=r" (res), "=&z" (__dummy), "=r" (_s), "=r" (_d), "=r"(_c)
- : "0" (__count), "2" (__src), "3" (__dest), "4" (__count),
- "i" (-EFAULT)
- : "memory", "t");
-
- return res;
-}
-
-/*
- * Return the size of a string (including the ending 0 even when we have
- * exceeded the maximum string length).
- */
-static inline long __strnlen_user(const char __user *__s, long __n)
-{
- unsigned long res;
- unsigned long __dummy;
-
- __asm__ __volatile__(
- "1:\t"
- "mov.b @(%0,%3), %1\n\t"
- "cmp/eq %4, %0\n\t"
- "bt/s 2f\n\t"
- " add #1, %0\n\t"
- "tst %1, %1\n\t"
- "bf 1b\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3:\n\t"
- "mov.l 4f, %1\n\t"
- "jmp @%1\n\t"
- " mov #0, %0\n"
- ".balign 4\n"
- "4: .long 2b\n"
- ".previous\n"
- ".section __ex_table,\"a\"\n"
- " .balign 4\n"
- " .long 1b,3b\n"
- ".previous"
- : "=z" (res), "=&r" (__dummy)
- : "0" (0), "r" (__s), "r" (__n)
- : "t");
- return res;
-}
-
#endif /* __ASM_SH_UACCESS_32_H */
extern long __put_user_asm_q(void *, long);
extern void __put_user_unknown(void);
-extern long __strnlen_user(const char *__s, long __n);
-extern int __strncpy_from_user(unsigned long __dest,
- unsigned long __user __src, int __count);
-
#endif /* __ASM_SH_UACCESS_64_H */
+++ /dev/null
-#include <asm-generic/ucontext.h>
--- /dev/null
+#ifndef __ASM_SH_WORD_AT_A_TIME_H
+#define __ASM_SH_WORD_AT_A_TIME_H
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+# include <asm-generic/word-at-a-time.h>
+#else
+/*
+ * Little-endian version cribbed from x86.
+ */
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return count_masked_bytes(mask);
+}
+#endif
+
+#endif
+++ /dev/null
-#include <asm-generic/xor.h>
+++ /dev/null
-/*
- * SH-2A UBC definitions
- *
- * Copyright (C) 2008 Kieran Bingham
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef __ASM_CPU_SH2A_UBC_H
-#define __ASM_CPU_SH2A_UBC_H
-
-#define UBC_BARA 0xfffc0400
-#define UBC_BAMRA 0xfffc0404
-#define UBC_BBRA 0xfffc04a0 /* 16 bit access */
-#define UBC_BDRA 0xfffc0408
-#define UBC_BDMRA 0xfffc040c
-
-#define UBC_BARB 0xfffc0410
-#define UBC_BAMRB 0xfffc0414
-#define UBC_BBRB 0xfffc04b0 /* 16 bit access */
-#define UBC_BDRB 0xfffc0418
-#define UBC_BDMRB 0xfffc041c
-
-#define UBC_BRCR 0xfffc04c0
-
-#endif /* __ASM_CPU_SH2A_UBC_H */
#endif /* CONFIG_MMU */
-/*
- * int __strncpy_from_user(unsigned long __dest, unsigned long __src,
- * int __count)
- *
- * Inputs:
- * (r2) target address
- * (r3) source address
- * (r4) maximum size in bytes
- *
- * Ouputs:
- * (*r2) copied data
- * (r2) -EFAULT (in case of faulting)
- * copied data (otherwise)
- */
- .global __strncpy_from_user
-__strncpy_from_user:
- pta ___strncpy_from_user1, tr0
- pta ___strncpy_from_user_done, tr1
- or r4, ZERO, r5 /* r5 = original count */
- beq/u r4, r63, tr1 /* early exit if r4==0 */
- movi -(EFAULT), r6 /* r6 = reply, no real fixup */
- or ZERO, ZERO, r7 /* r7 = data, clear top byte of data */
-
-___strncpy_from_user1:
- ld.b r3, 0, r7 /* Fault address: only in reading */
- st.b r2, 0, r7
- addi r2, 1, r2
- addi r3, 1, r3
- beq/u ZERO, r7, tr1
- addi r4, -1, r4 /* return real number of copied bytes */
- bne/l ZERO, r4, tr0
-
-___strncpy_from_user_done:
- sub r5, r4, r6 /* If done, return copied */
-
-___strncpy_from_user_exit:
- or r6, ZERO, r2
- ptabs LINK, tr0
- blink tr0, ZERO
-
-/*
- * extern long __strnlen_user(const char *__s, long __n)
- *
- * Inputs:
- * (r2) source address
- * (r3) source size in bytes
- *
- * Ouputs:
- * (r2) -EFAULT (in case of faulting)
- * string length (otherwise)
- */
- .global __strnlen_user
-__strnlen_user:
- pta ___strnlen_user_set_reply, tr0
- pta ___strnlen_user1, tr1
- or ZERO, ZERO, r5 /* r5 = counter */
- movi -(EFAULT), r6 /* r6 = reply, no real fixup */
- or ZERO, ZERO, r7 /* r7 = data, clear top byte of data */
- beq r3, ZERO, tr0
-
-___strnlen_user1:
- ldx.b r2, r5, r7 /* Fault address: only in reading */
- addi r3, -1, r3 /* No real fixup */
- addi r5, 1, r5
- beq r3, ZERO, tr0
- bne r7, ZERO, tr1
-! The line below used to be active. This meant led to a junk byte lying between each pair
-! of entries in the argv & envp structures in memory. Whilst the program saw the right data
-! via the argv and envp arguments to main, it meant the 'flat' representation visible through
-! /proc/$pid/cmdline was corrupt, causing trouble with ps, for example.
-! addi r5, 1, r5 /* Include '\0' */
-
-___strnlen_user_set_reply:
- or r5, ZERO, r6 /* If done, return counter */
-
-___strnlen_user_exit:
- or r6, ZERO, r2
- ptabs LINK, tr0
- blink tr0, ZERO
-
/*
* extern long __get_user_asm_?(void *val, long addr)
*
.long ___copy_user2, ___copy_user_exit
.long ___clear_user1, ___clear_user_exit
#endif
- .long ___strncpy_from_user1, ___strncpy_from_user_exit
- .long ___strnlen_user1, ___strnlen_user_exit
.long ___get_user_asm_b1, ___get_user_asm_b_exit
.long ___get_user_asm_w1, ___get_user_asm_w_exit
.long ___get_user_asm_l1, ___get_user_asm_l_exit
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/stackprotector.h>
+#include <asm/fpu.h>
struct kmem_cache *task_xstate_cachep = NULL;
unsigned int xstate_size;
#include <asm/switch_to.h>
struct task_struct *last_task_used_math = NULL;
+struct pt_regs fake_swapper_regs = { 0, };
void show_regs(struct pt_regs *regs)
{
EXPORT_SYMBOL(__get_user_asm_w);
EXPORT_SYMBOL(__get_user_asm_l);
EXPORT_SYMBOL(__get_user_asm_q);
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
EXPORT_SYMBOL(__clear_user);
EXPORT_SYMBOL(copy_page);
EXPORT_SYMBOL(__copy_user);
/* Enable interrupts racelessly and nap forever: helper for cpu_idle(). */
extern void _cpu_idle(void);
-/* Switch boot idle thread to a freshly-allocated stack and free old stack. */
-extern void cpu_idle_on_new_stack(struct thread_info *old_ti,
- unsigned long new_sp,
- unsigned long new_ss10);
-
#else /* __ASSEMBLY__ */
/*
jrp lr /* keep backtracer happy */
STD_ENDPROC(KBacktraceIterator_init_current)
-/*
- * Reset our stack to r1/r2 (sp and ksp0+cpu respectively), then
- * free the old stack (passed in r0) and re-invoke cpu_idle().
- * We update sp and ksp0 simultaneously to avoid backtracer warnings.
- */
-STD_ENTRY(cpu_idle_on_new_stack)
- {
- move sp, r1
- mtspr SPR_SYSTEM_SAVE_K_0, r2
- }
- jal free_thread_info
- j cpu_idle
- STD_ENDPROC(cpu_idle_on_new_stack)
-
/* Loop forever on a nap during SMP boot. */
STD_ENTRY(smp_nap)
nap
#include <linux/smp.h>
#include <linux/timex.h>
#include <linux/hugetlb.h>
+#include <linux/start_kernel.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
.section ".bsdata", "a"
bugger_off_msg:
- .ascii "Direct booting from floppy is no longer supported.\r\n"
- .ascii "Please use a boot loader program instead.\r\n"
+ .ascii "Direct floppy boot is not supported. "
+ .ascii "Use a boot loader program instead.\r\n"
.ascii "\n"
- .ascii "Remove disk and press any key to reboot . . .\r\n"
+ .ascii "Remove disk and press any key to reboot ...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
#else
.word 0x8664 # x86-64
#endif
- .word 2 # nr_sections
+ .word 3 # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
#else
.quad 0 # ImageBase
#endif
- .long 0x1000 # SectionAlignment
- .long 0x200 # FileAlignment
+ .long 0x20 # SectionAlignment
+ .long 0x20 # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word 0 # MajorImageVersion
# Section table
section_table:
- .ascii ".text"
- .byte 0
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".setup"
.byte 0
.byte 0
.long 0
#
# The EFI application loader requires a relocation section
- # because EFI applications must be relocatable. But since
- # we don't need the loader to fixup any relocs for us, we
- # just create an empty (zero-length) .reloc section header.
+ # because EFI applications must be relocatable. The .reloc
+ # offset & size fields are filled in by build.c.
#
.ascii ".reloc"
.byte 0
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long 0x42100040 # Characteristics (section flags)
+
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".text"
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0 # startup_{32,64}
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0 # startup_{32,64}
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x60500020 # Characteristics (section flags)
+
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
u8 buf[SETUP_SECT_MAX*512];
int is_big_kernel;
+#define PECOFF_RELOC_RESERVE 0x20
+
/*----------------------------------------------------------------------*/
static const u32 crctab32[] = {
die("Usage: build setup system [> image]");
}
-int main(int argc, char ** argv)
-{
#ifdef CONFIG_EFI_STUB
- unsigned int file_sz, pe_header;
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+ unsigned int pe_header;
+ unsigned short num_sections;
+ u8 *section;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+ num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+ section = &buf[pe_header + 0xa8];
+#else
+ section = &buf[pe_header + 0xb8];
#endif
+
+ while (num_sections > 0) {
+ if (strncmp((char*)section, section_name, 8) == 0) {
+ /* section header size field */
+ put_unaligned_le32(size, section + 0x8);
+
+ /* section header vma field */
+ put_unaligned_le32(offset, section + 0xc);
+
+ /* section header 'size of initialised data' field */
+ put_unaligned_le32(size, section + 0x10);
+
+ /* section header 'file offset' field */
+ put_unaligned_le32(offset, section + 0x14);
+
+ break;
+ }
+ section += 0x28;
+ num_sections--;
+ }
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+ u32 setup_offset = 0x200;
+ u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+ u32 setup_size = reloc_offset - setup_offset;
+
+ update_pecoff_section_header(".setup", setup_offset, setup_size);
+ update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+ /*
+ * Modify .reloc section contents with a single entry. The
+ * relocation is applied to offset 10 of the relocation section.
+ */
+ put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+ put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+ unsigned int pe_header;
+ unsigned int text_sz = file_sz - text_start;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+
+ /* Size of image */
+ put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
+
+ /*
+ * Size of code: Subtract the size of the first sector (512 bytes)
+ * which includes the header.
+ */
+ put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Address of entry point.
+ *
+ * The EFI stub entry point is +16 bytes from the start of
+ * the .text section.
+ */
+ put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
+#else
+ /*
+ * Address of entry point. startup_32 is at the beginning and
+ * the 64-bit entry point (startup_64) is always 512 bytes
+ * after. The EFI stub entry point is 16 bytes after that, as
+ * the first instruction allows legacy loaders to jump over
+ * the EFI stub initialisation
+ */
+ put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
+#endif /* CONFIG_X86_32 */
+
+ update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+#endif /* CONFIG_EFI_STUB */
+
+int main(int argc, char ** argv)
+{
unsigned int i, sz, setup_sectors;
int c;
u32 sys_size;
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
+#ifdef CONFIG_EFI_STUB
+ /* Reserve 0x20 bytes for .reloc section */
+ memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+ c += PECOFF_RELOC_RESERVE;
+#endif
+
/* Pad unused space with zeros */
setup_sectors = (c + 511) / 512;
if (setup_sectors < SETUP_SECT_MIN)
i = setup_sectors*512;
memset(buf+c, 0, i-c);
+#ifdef CONFIG_EFI_STUB
+ update_pecoff_setup_and_reloc(i);
+#endif
+
/* Set the default root device */
put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
put_unaligned_le32(sys_size, &buf[0x1f4]);
#ifdef CONFIG_EFI_STUB
- file_sz = sz + i + ((sys_size * 16) - sz);
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
-
- /* Size of image */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
- /*
- * Subtract the size of the first section (512 bytes) which
- * includes the header and .reloc section. The remaining size
- * is that of the .text section.
- */
- file_sz -= 512;
-
- /* Size of code */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]);
-
-#ifdef CONFIG_X86_32
- /*
- * Address of entry point.
- *
- * The EFI stub entry point is +16 bytes from the start of
- * the .text section.
- */
- put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xb4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xbc]);
-#else
- /*
- * Address of entry point. startup_32 is at the beginning and
- * the 64-bit entry point (startup_64) is always 512 bytes
- * after. The EFI stub entry point is 16 bytes after that, as
- * the first instruction allows legacy loaders to jump over
- * the EFI stub initialisation
- */
- put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xc4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xcc]);
-#endif /* CONFIG_X86_32 */
-#endif /* CONFIG_EFI_STUB */
+ update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+#endif
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, stdout) != i)
pxor IN3, STATE4
movaps IN4, IV
#else
- pxor (INP), STATE2
- pxor 0x10(INP), STATE3
pxor IN1, STATE4
movaps IN2, IV
+ movups (INP), IN1
+ pxor IN1, STATE2
+ movups 0x10(INP), IN2
+ pxor IN2, STATE3
#endif
movups STATE1, (OUTP)
movups STATE2, 0x10(OUTP)
__register_nmi_handler((t), &fn##_na); \
})
+/*
+ * For special handlers that register/unregister in the
+ * init section only. This should be considered rare.
+ */
+#define register_nmi_handler_initonly(t, fn, fg, n) \
+({ \
+ static struct nmiaction fn##_na __initdata = { \
+ .handler = (fn), \
+ .name = (n), \
+ .flags = (fg), \
+ }; \
+ __register_nmi_handler((t), &fn##_na); \
+})
+
int __register_nmi_handler(unsigned int, struct nmiaction *);
void unregister_nmi_handler(unsigned int, const char *);
#define segment_eq(a, b) ((a).seg == (b).seg)
#define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr) \
- ((unsigned long __force)(addr) < \
- (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) \
+ ((unsigned long __force)(addr) < user_addr_max())
/*
* Test whether a block of memory is a valid user space address.
* This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
*/
-#define __range_not_ok(addr, size) \
+#define __range_not_ok(addr, size, limit) \
({ \
unsigned long flag, roksum; \
__chk_user_ptr(addr); \
asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \
: "=&r" (flag), "=r" (roksum) \
: "1" (addr), "g" ((long)(size)), \
- "rm" (current_thread_info()->addr_limit.seg)); \
+ "rm" (limit)); \
flag; \
})
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*/
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+ (likely(__range_not_ok(addr, size, user_addr_max()) == 0))
/*
* The exception table consists of pairs of addresses relative to the
/* 4 bits of software ack period */
#define UV2_ACK_MASK 0x7UL
#define UV2_ACK_UNITS_SHFT 3
-#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
/*
#include <linux/bitops.h>
#include <linux/ioport.h>
#include <linux/suspend.h>
-#include <linux/kmemleak.h>
#include <asm/e820.h>
#include <asm/io.h>
#include <asm/iommu.h>
return 0;
}
memblock_reserve(addr, aper_size);
- /*
- * Kmemleak should not scan this block as it may not be mapped via the
- * kernel direct mapping.
- */
- kmemleak_ignore(phys_to_virt(addr));
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
insert_aperture_resource((u32)addr, aper_size);
BUG_ON(!cfg->vector);
vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ for_each_cpu(cpu, cfg->domain)
per_cpu(vector_irq, cpu)[vector] = -1;
cfg->vector = 0;
if (likely(!cfg->move_in_progress))
return;
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu(cpu, cfg->old_domain) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
*/
iv = __this_cpu_read(mce_next_interval);
if (mce_notify_irq())
- iv = max(iv, (unsigned long) HZ/100);
+ iv = max(iv / 2, (unsigned long) HZ/100);
else
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
__this_cpu_write(mce_next_interval, iv);
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- unsigned long iv = __this_cpu_read(mce_next_interval);
+ unsigned long iv = check_interval * HZ;
setup_timer(t, mce_timer_fn, smp_processor_id());
if (!cpuc->shared_regs)
goto error;
}
+ cpuc->is_fake = 1;
return cpuc;
error:
free_fake_cpuc(cpuc);
dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
}
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+ return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
#ifdef CONFIG_COMPAT
#include <asm/compat.h>
if (bytes != sizeof(frame))
break;
- if (fp < compat_ptr(regs->sp))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
if (bytes != sizeof(frame))
break;
- if ((unsigned long)fp < regs->sp)
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
unsigned int group_flag;
+ int is_fake;
/*
* Intel DebugStore bits
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
+ void (*pebs_aliases)(struct perf_event *event);
/*
* Intel LBR
return NULL;
}
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
{
if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
- return false;
+ return idx;
- if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
- event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
- event->hw.config |= 0x01bb;
- event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
- event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
- } else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+ if (idx == EXTRA_REG_RSP_0)
+ return EXTRA_REG_RSP_1;
+
+ if (idx == EXTRA_REG_RSP_1)
+ return EXTRA_REG_RSP_0;
+
+ return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+ event->hw.extra_reg.idx = idx;
+
+ if (idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= 0x01b7;
- event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+ } else if (idx == EXTRA_REG_RSP_1) {
+ event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+ event->hw.config |= 0x01bb;
+ event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
}
-
- if (event->hw.extra_reg.idx == orig_idx)
- return false;
-
- return true;
}
/*
struct event_constraint *c = &emptyconstraint;
struct er_account *era;
unsigned long flags;
- int orig_idx = reg->idx;
+ int idx = reg->idx;
- /* already allocated shared msr */
- if (reg->alloc)
+ /*
+ * reg->alloc can be set due to existing state, so for fake cpuc we
+ * need to ignore this, otherwise we might fail to allocate proper fake
+ * state for this extra reg constraint. Also see the comment below.
+ */
+ if (reg->alloc && !cpuc->is_fake)
return NULL; /* call x86_get_event_constraint() */
again:
- era = &cpuc->shared_regs->regs[reg->idx];
+ era = &cpuc->shared_regs->regs[idx];
/*
* we use spin_lock_irqsave() to avoid lockdep issues when
* passing a fake cpuc
if (!atomic_read(&era->ref) || era->config == reg->config) {
+ /*
+ * If its a fake cpuc -- as per validate_{group,event}() we
+ * shouldn't touch event state and we can avoid doing so
+ * since both will only call get_event_constraints() once
+ * on each event, this avoids the need for reg->alloc.
+ *
+ * Not doing the ER fixup will only result in era->reg being
+ * wrong, but since we won't actually try and program hardware
+ * this isn't a problem either.
+ */
+ if (!cpuc->is_fake) {
+ if (idx != reg->idx)
+ intel_fixup_er(event, idx);
+
+ /*
+ * x86_schedule_events() can call get_event_constraints()
+ * multiple times on events in the case of incremental
+ * scheduling(). reg->alloc ensures we only do the ER
+ * allocation once.
+ */
+ reg->alloc = 1;
+ }
+
/* lock in msr value */
era->config = reg->config;
era->reg = reg->reg;
/* one more user */
atomic_inc(&era->ref);
- /* no need to reallocate during incremental event scheduling */
- reg->alloc = 1;
-
/*
* need to call x86_get_event_constraint()
* to check if associated event has constraints
*/
c = NULL;
- } else if (intel_try_alt_er(event, orig_idx)) {
- raw_spin_unlock_irqrestore(&era->lock, flags);
- goto again;
+ } else {
+ idx = intel_alt_er(idx);
+ if (idx != reg->idx) {
+ raw_spin_unlock_irqrestore(&era->lock, flags);
+ goto again;
+ }
}
raw_spin_unlock_irqrestore(&era->lock, flags);
struct er_account *era;
/*
- * only put constraint if extra reg was actually
- * allocated. Also takes care of event which do
- * not use an extra shared reg
+ * Only put constraint if extra reg was actually allocated. Also takes
+ * care of event which do not use an extra shared reg.
+ *
+ * Also, if this is a fake cpuc we shouldn't touch any event state
+ * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+ * either since it'll be thrown out.
*/
- if (!reg->alloc)
+ if (!reg->alloc || cpuc->is_fake)
return;
era = &cpuc->shared_regs->regs[reg->idx];
intel_put_shared_regs_event_constraints(cpuc, event);
}
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
{
- int ret = x86_pmu_hw_config(event);
-
- if (ret)
- return ret;
-
- if (event->attr.precise_ip &&
- (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
* Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
* (0x003c) so that we can use it with PEBS.
*/
u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
+ alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+ event->hw.config = alt_config;
+ }
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ /*
+ * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+ * (0x003c) so that we can use it with PEBS.
+ *
+ * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+ * PEBS capable. However we can use UOPS_RETIRED.ALL
+ * (0x01c2), which is a PEBS capable event, to get the same
+ * count.
+ *
+ * UOPS_RETIRED.ALL counts the number of cycles that retires
+ * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+ * larger than the maximum number of micro-ops that can be
+ * retired per cycle (4) and then inverting the condition, we
+ * count all cycles that retire 16 or less micro-ops, which
+ * is every cycle.
+ *
+ * Thereby we gain a PEBS capable cycle counter.
+ */
+ u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+ int ret = x86_pmu_hw_config(event);
+
+ if (ret)
+ return ret;
+
+ if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+ x86_pmu.pebs_aliases(event);
if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
+ .pebs_aliases = intel_pebs_aliases_core2,
.format_attrs = intel_arch3_formats_attr,
break;
case 42: /* SandyBridge */
- x86_add_quirk(intel_sandybridge_quirk);
case 45: /* SandyBridge, "Romely-EP" */
+ x86_add_quirk(intel_sandybridge_quirk);
+ case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
- INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
- INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
- INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
bool ret = false;
struct pvclock_vcpu_time_info *src;
- /*
- * per_cpu() is safe here because this function is only called from
- * timer functions where preemption is already disabled.
- */
- WARN_ON(!in_atomic());
src = &__get_cpu_var(hv_clock);
if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
__this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);
static void __init init_nmi_testsuite(void)
{
/* trap all the unknown NMIs we may generate */
- register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+ register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
}
static void __init cleanup_nmi_testsuite(void)
{
unsigned long timeout;
- if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+ if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
NMI_FLAG_FIRST, "nmi_selftest")) {
nmi_fail = FAILURE;
return;
set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
/*
- * O.K Now that I'm on the appropriate processor,
- * stop all of the others.
+ * O.K Now that I'm on the appropriate processor, stop all of the
+ * others. Also disable the local irq to not receive the per-cpu
+ * timer interrupt which may trigger scheduler's load balance.
*/
+ local_irq_disable();
stop_other_cpus();
#endif
if ((i == cpu) || (has_mc && match_llc(c, o)))
link_mask(llc_shared, cpu, i);
+ }
+
+ /*
+ * This needs a separate iteration over the cpus because we rely on all
+ * cpu_sibling_mask links to be set-up.
+ */
+ for_each_cpu(i, cpu_sibling_setup_mask) {
+ o = &cpu_data(i);
+
if ((i == cpu) || (has_mc && match_mc(c, o))) {
link_mask(core, cpu, i);
/* maps the cpu to the sched domain representing multi-core */
const struct cpumask *cpu_coregroup_mask(int cpu)
{
- struct cpuinfo_x86 *c = &cpu_data(cpu);
- /*
- * For perf, we return last level cache shared map.
- * And for power savings, we return cpu_core_map
- */
- if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
- return cpu_core_mask(cpu);
- else
- return cpu_llc_shared_mask(cpu);
+ return cpu_llc_shared_mask(cpu);
}
static void impress_friends(void)
#include <linux/module.h>
#include <asm/word-at-a-time.h>
+#include <linux/sched.h>
/*
* best effort, GUP based copy_from_user() that is NMI-safe
void *map;
int ret;
+ if (__range_not_ok(from, n, TASK_SIZE) == 0)
+ return len;
+
do {
ret = __get_user_pages_fast(addr, 1, 0, &page);
if (!ret)
# - (66): the last prefix is 0x66
# - (F3): the last prefix is 0xF3
# - (F2): the last prefix is 0xF2
-#
+# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
Table: one byte opcode
Referrer:
b5: LGS Gv,Mp
b6: MOVZX Gv,Eb
b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
b9: Grp10 (1A)
ba: Grp8 Ev,Ib (1A)
bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
be: MOVSX Gv,Eb
bf: MOVSX Gv,Ew
# 0x0f 0xc0-0xcf
extra += PMD_SIZE;
#endif
/* The first 2/4M doesn't use large pages. */
- extra += mr->end - mr->start;
+ if (mr->start < PMD_SIZE)
+ extra += mr->end - mr->start;
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
return;
}
+ node_set(node, numa_nodes_parsed);
+
printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1);
EXPORT_SYMBOL_GPL(intel_scu_notifier);
/* Called by IPC driver */
-void intel_scu_devices_create(void)
+void __devinit intel_scu_devices_create(void)
{
int i;
*/
mmr_image |= (1L << SOFTACK_MSHIFT);
if (is_uv2_hub()) {
- mmr_image &= ~(1L << UV2_LEG_SHFT);
mmr_image |= (1L << UV2_EXT_SHFT);
}
write_mmr_misc_control(pnode, mmr_image);
rex_expr = "^REX(\\.[XRWB]+)*"
fpu_expr = "^ESC" # TODO
- lprefix1_expr = "\\(66\\)"
+ lprefix1_expr = "\\((66|!F3)\\)"
lprefix2_expr = "\\(F3\\)"
- lprefix3_expr = "\\(F2\\)"
+ lprefix3_expr = "\\((F2|!F3)\\)"
+ lprefix_expr = "\\((66|F2|F3)\\)"
max_lprefix = 4
# All opcodes starting with lower-case 'v' or with (v1) superscript
if (match(ext, lprefix1_expr)) {
lptable1[idx] = add_flags(lptable1[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix2_expr)) {
+ }
+ if (match(ext, lprefix2_expr)) {
lptable2[idx] = add_flags(lptable2[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix3_expr)) {
+ }
+ if (match(ext, lprefix3_expr)) {
lptable3[idx] = add_flags(lptable3[idx],flags)
variant = "INAT_VARIANT"
- } else {
+ }
+ if (!match(ext, lprefix_expr)){
table[idx] = add_flags(table[idx],flags)
}
}
asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
struct timespec __user *tsp, const sigset_t __user *sigmask,
size_t sigsetsize);
-
-
+asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset,
+ size_t sigsetsize);
if (ret)
return;
- signal_delivered(signr, info, ka, regs, 0);
+ signal_delivered(signr, &info, &ka, regs, 0);
if (current->ptrace & PT_SINGLESTEP)
task_pt_regs(current)->icountlevel = 1;
config ACPI_HOTPLUG_CPU
bool
- depends on ACPI_PROCESSOR && HOTPLUG_CPU
+ depends on EXPERIMENTAL && ACPI_PROCESSOR && HOTPLUG_CPU
select ACPI_CONTAINER
default y
static void acpi_battery_refresh(struct acpi_battery *battery)
{
+ int power_unit;
+
if (!battery->bat.dev)
return;
+ power_unit = battery->power_unit;
+
acpi_battery_get_info(battery);
- /* The battery may have changed its reporting units. */
+
+ if (power_unit == battery->power_unit)
+ return;
+
+ /* The battery has changed its reporting units. */
sysfs_remove_battery(battery);
sysfs_add_battery(battery);
}
Power Management
-------------------------------------------------------------------------- */
+static const char *state_string(int state)
+{
+ switch (state) {
+ case ACPI_STATE_D0:
+ return "D0";
+ case ACPI_STATE_D1:
+ return "D1";
+ case ACPI_STATE_D2:
+ return "D2";
+ case ACPI_STATE_D3_HOT:
+ return "D3hot";
+ case ACPI_STATE_D3_COLD:
+ return "D3";
+ default:
+ return "(unknown)";
+ }
+}
+
static int __acpi_bus_get_power(struct acpi_device *device, int *state)
{
- int result = 0;
- acpi_status status = 0;
- unsigned long long psc = 0;
+ int result = ACPI_STATE_UNKNOWN;
if (!device || !state)
return -EINVAL;
- *state = ACPI_STATE_UNKNOWN;
-
- if (device->flags.power_manageable) {
- /*
- * Get the device's power state either directly (via _PSC) or
- * indirectly (via power resources).
- */
- if (device->power.flags.power_resources) {
- result = acpi_power_get_inferred_state(device, state);
- if (result)
- return result;
- } else if (device->power.flags.explicit_get) {
- status = acpi_evaluate_integer(device->handle, "_PSC",
- NULL, &psc);
- if (ACPI_FAILURE(status))
- return -ENODEV;
- *state = (int)psc;
- }
- } else {
+ if (!device->flags.power_manageable) {
/* TBD: Non-recursive algorithm for walking up hierarchy. */
*state = device->parent ?
device->parent->power.state : ACPI_STATE_D0;
+ goto out;
+ }
+
+ /*
+ * Get the device's power state either directly (via _PSC) or
+ * indirectly (via power resources).
+ */
+ if (device->power.flags.explicit_get) {
+ unsigned long long psc;
+ acpi_status status = acpi_evaluate_integer(device->handle,
+ "_PSC", NULL, &psc);
+ if (ACPI_FAILURE(status))
+ return -ENODEV;
+
+ result = psc;
+ }
+ /* The test below covers ACPI_STATE_UNKNOWN too. */
+ if (result <= ACPI_STATE_D2) {
+ ; /* Do nothing. */
+ } else if (device->power.flags.power_resources) {
+ int error = acpi_power_get_inferred_state(device, &result);
+ if (error)
+ return error;
+ } else if (result == ACPI_STATE_D3_HOT) {
+ result = ACPI_STATE_D3;
}
+ *state = result;
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] power state is D%d\n",
- device->pnp.bus_id, *state));
+ out:
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] power state is %s\n",
+ device->pnp.bus_id, state_string(*state)));
return 0;
}
/* Make sure this is a valid target state */
if (state == device->power.state) {
- ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device is already at D%d\n",
- state));
+ ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device is already at %s\n",
+ state_string(state)));
return 0;
}
if (!device->power.states[state].flags.valid) {
- printk(KERN_WARNING PREFIX "Device does not support D%d\n", state);
+ printk(KERN_WARNING PREFIX "Device does not support %s\n",
+ state_string(state));
return -ENODEV;
}
if (device->parent && (state < device->parent->power.state)) {
end:
if (result)
printk(KERN_WARNING PREFIX
- "Device [%s] failed to transition to D%d\n",
- device->pnp.bus_id, state);
+ "Device [%s] failed to transition to %s\n",
+ device->pnp.bus_id, state_string(state));
else {
device->power.state = state;
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "Device [%s] transitioned to D%d\n",
- device->pnp.bus_id, state));
+ "Device [%s] transitioned to %s\n",
+ device->pnp.bus_id, state_string(state)));
}
return result;
* We know a device's inferred power state when all the resources
* required for a given D-state are 'on'.
*/
- for (i = ACPI_STATE_D0; i < ACPI_STATE_D3_HOT; i++) {
+ for (i = ACPI_STATE_D0; i <= ACPI_STATE_D3_HOT; i++) {
list = &device->power.states[i].resources;
if (list->count < 1)
continue;
struct acpi_buffer state = { 0, NULL };
union acpi_object *pss = NULL;
int i;
+ int last_invalid = -1;
status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer);
((u32)(px->core_frequency * 1000) !=
(px->core_frequency * 1000))) {
printk(KERN_ERR FW_BUG PREFIX
- "Invalid BIOS _PSS frequency: 0x%llx MHz\n",
- px->core_frequency);
- result = -EFAULT;
- kfree(pr->performance->states);
- goto end;
+ "Invalid BIOS _PSS frequency found for processor %d: 0x%llx MHz\n",
+ pr->id, px->core_frequency);
+ if (last_invalid == -1)
+ last_invalid = i;
+ } else {
+ if (last_invalid != -1) {
+ /*
+ * Copy this valid entry over last_invalid entry
+ */
+ memcpy(&(pr->performance->states[last_invalid]),
+ px, sizeof(struct acpi_processor_px));
+ ++last_invalid;
+ }
}
}
+ if (last_invalid == 0) {
+ printk(KERN_ERR FW_BUG PREFIX
+ "No valid BIOS _PSS frequency found for processor %d\n", pr->id);
+ result = -EFAULT;
+ kfree(pr->performance->states);
+ pr->performance->states = NULL;
+ }
+
+ if (last_invalid > 0)
+ pr->performance->state_count = last_invalid;
+
end:
kfree(buffer.pointer);
ACPI_BUS_TYPE_POWER_BUTTON,
ACPI_STA_DEFAULT,
&ops);
+ device_init_wakeup(&device->dev, true);
}
if ((acpi_gbl_FADT.flags & ACPI_FADT_SLEEP_BUTTON) == 0) {
MODULE_PARM_DESC(bfs, "Enable evaluation of _BFS on resume".);
static u8 sleep_states[ACPI_S_STATE_COUNT];
+static bool pwr_btn_event_pending;
static void acpi_sleep_tts_switch(u32 acpi_state)
{
return error;
}
+static int find_powerf_dev(struct device *dev, void *data)
+{
+ struct acpi_device *device = to_acpi_device(dev);
+ const char *hid = acpi_device_hid(device);
+
+ return !strcmp(hid, ACPI_BUTTON_HID_POWERF);
+}
+
/**
* acpi_pm_finish - Instruct the platform to leave a sleep state.
*
*/
static void acpi_pm_finish(void)
{
+ struct device *pwr_btn_dev;
u32 acpi_state = acpi_target_sleep_state;
acpi_ec_unblock_transactions();
acpi_set_firmware_waking_vector((acpi_physical_address) 0);
acpi_target_sleep_state = ACPI_STATE_S0;
+
+ /* If we were woken with the fixed power button, provide a small
+ * hint to userspace in the form of a wakeup event on the fixed power
+ * button device (if it can be found).
+ *
+ * We delay the event generation til now, as the PM layer requires
+ * timekeeping to be running before we generate events. */
+ if (!pwr_btn_event_pending)
+ return;
+
+ pwr_btn_event_pending = false;
+ pwr_btn_dev = bus_find_device(&acpi_bus_type, NULL, NULL,
+ find_powerf_dev);
+ if (pwr_btn_dev) {
+ pm_wakeup_event(pwr_btn_dev, 0);
+ put_device(pwr_btn_dev);
+ }
}
/**
/* ACPI 3.0 specs (P62) says that it's the responsibility
* of the OSPM to clear the status bit [ implying that the
* POWER_BUTTON event should not reach userspace ]
+ *
+ * However, we do generate a small hint for userspace in the form of
+ * a wakeup event. We flag this condition for now and generate the
+ * event later, as we're currently too early in resume to be able to
+ * generate wakeup events.
*/
- if (ACPI_SUCCESS(status) && (acpi_state == ACPI_STATE_S3))
- acpi_clear_event(ACPI_EVENT_POWER_BUTTON);
+ if (ACPI_SUCCESS(status) && (acpi_state == ACPI_STATE_S3)) {
+ acpi_event_status pwr_btn_status;
+
+ acpi_get_event_status(ACPI_EVENT_POWER_BUTTON, &pwr_btn_status);
+
+ if (pwr_btn_status & ACPI_EVENT_FLAG_SET) {
+ acpi_clear_event(ACPI_EVENT_POWER_BUTTON);
+ /* Flag for later */
+ pwr_btn_event_pending = true;
+ }
+ }
/*
* Disable and clear GPE status before interrupt is enabled. Some GPEs
* can wake the system. _S0W may be valid, too.
*/
if (acpi_target_sleep_state == ACPI_STATE_S0 ||
- (device_may_wakeup(dev) &&
- adev->wakeup.sleep_state <= acpi_target_sleep_state)) {
+ (device_may_wakeup(dev) && adev->wakeup.flags.valid &&
+ adev->wakeup.sleep_state >= acpi_target_sleep_state)) {
acpi_status status;
acpi_method[3] = 'W';
set_bit(KEY_BRIGHTNESS_ZERO, input->keybit);
set_bit(KEY_DISPLAY_OFF, input->keybit);
- error = input_register_device(input);
- if (error)
- goto err_stop_video;
-
printk(KERN_INFO PREFIX "%s [%s] (multi-head: %s rom: %s post: %s)\n",
ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device),
video->flags.multihead ? "yes" : "no",
video->pm_nb.priority = 0;
error = register_pm_notifier(&video->pm_nb);
if (error)
- goto err_unregister_input_dev;
+ goto err_stop_video;
+
+ error = input_register_device(input);
+ if (error)
+ goto err_unregister_pm_notifier;
return 0;
- err_unregister_input_dev:
- input_unregister_device(input);
+ err_unregister_pm_notifier:
+ unregister_pm_notifier(&video->pm_nb);
err_stop_video:
acpi_video_bus_stop_devices(video);
err_free_input_dev:
return 0;
}
+static int __init is_i740(struct pci_dev *dev)
+{
+ if (dev->device == 0x00D1)
+ return 1;
+ if (dev->device == 0x7000)
+ return 1;
+ return 0;
+}
+
static int __init intel_opregion_present(void)
{
-#if defined(CONFIG_DRM_I915) || defined(CONFIG_DRM_I915_MODULE)
+ int opregion = 0;
struct pci_dev *dev = NULL;
u32 address;
continue;
if (dev->vendor != PCI_VENDOR_ID_INTEL)
continue;
+ /* We don't want to poke around undefined i740 registers */
+ if (is_i740(dev))
+ continue;
pci_read_config_dword(dev, 0xfc, &address);
if (!address)
continue;
- return 1;
+ opregion = 1;
}
-#endif
- return 0;
+ return opregion;
}
int acpi_video_register(void)
map->lock = regmap_lock_mutex;
map->unlock = regmap_unlock_mutex;
}
- map->format.buf_size = (config->reg_bits + config->val_bits) / 8;
map->format.reg_bytes = DIV_ROUND_UP(config->reg_bits, 8);
map->format.pad_bytes = config->pad_bits / 8;
map->format.val_bytes = DIV_ROUND_UP(config->val_bits, 8);
- map->format.buf_size += map->format.pad_bytes;
+ map->format.buf_size = DIV_ROUND_UP(config->reg_bits +
+ config->val_bits + config->pad_bits, 8);
map->reg_shift = config->pad_bits % 8;
if (config->reg_stride)
map->reg_stride = config->reg_stride;
ret = regcache_init(map, config);
if (ret < 0)
- goto err_free_workbuf;
+ goto err_debugfs;
/* Add a devres resource for dev_get_regmap() */
m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL);
err_cache:
regcache_exit(map);
-err_free_workbuf:
+err_debugfs:
+ regmap_debugfs_exit(map);
kfree(map->work_buf);
err_map:
kfree(map);
return ret;
}
+EXPORT_SYMBOL_GPL(regmap_reinit_cache);
/**
* regmap_exit(): Free a previously allocated register map
ID(PCI_DEVICE_ID_INTEL_B43_HB),
ID(PCI_DEVICE_ID_INTEL_B43_1_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB),
+ ID(PCI_DEVICE_ID_INTEL_IRONLAKE_D2_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB),
ID(PCI_DEVICE_ID_INTEL_IRONLAKE_MC2_HB),
#define PCI_DEVICE_ID_INTEL_G41_HB 0x2E30
#define PCI_DEVICE_ID_INTEL_G41_IG 0x2E32
#define PCI_DEVICE_ID_INTEL_IRONLAKE_D_HB 0x0040
+#define PCI_DEVICE_ID_INTEL_IRONLAKE_D2_HB 0x0069
#define PCI_DEVICE_ID_INTEL_IRONLAKE_D_IG 0x0042
#define PCI_DEVICE_ID_INTEL_IRONLAKE_M_HB 0x0044
#define PCI_DEVICE_ID_INTEL_IRONLAKE_MA_HB 0x0062
/* data ready? */
if (readl(trng->base + TRNG_ODATA) & 1) {
*data = readl(trng->base + TRNG_ODATA);
+ /*
+ ensure data ready is only set again AFTER the next data
+ word is ready in case it got set between checking ISR
+ and reading ODATA, so we don't risk re-reading the
+ same word
+ */
+ readl(trng->base + TRNG_ISR);
return 4;
} else
return 0;
obj-$(CONFIG_SH_TIMER_CMT) += sh_cmt.o
obj-$(CONFIG_SH_TIMER_MTU2) += sh_mtu2.o
obj-$(CONFIG_SH_TIMER_TMU) += sh_tmu.o
+obj-$(CONFIG_EM_TIMER_STI) += em_sti.o
obj-$(CONFIG_CLKBLD_I8253) += i8253.o
obj-$(CONFIG_CLKSRC_MMIO) += mmio.o
obj-$(CONFIG_DW_APB_TIMER) += dw_apb_timer.o
--- /dev/null
+/*
+ * Emma Mobile Timer Support - STI
+ *
+ * Copyright (C) 2012 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/irq.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+
+enum { USER_CLOCKSOURCE, USER_CLOCKEVENT, USER_NR };
+
+struct em_sti_priv {
+ void __iomem *base;
+ struct clk *clk;
+ struct platform_device *pdev;
+ unsigned int active[USER_NR];
+ unsigned long rate;
+ raw_spinlock_t lock;
+ struct clock_event_device ced;
+ struct clocksource cs;
+};
+
+#define STI_CONTROL 0x00
+#define STI_COMPA_H 0x10
+#define STI_COMPA_L 0x14
+#define STI_COMPB_H 0x18
+#define STI_COMPB_L 0x1c
+#define STI_COUNT_H 0x20
+#define STI_COUNT_L 0x24
+#define STI_COUNT_RAW_H 0x28
+#define STI_COUNT_RAW_L 0x2c
+#define STI_SET_H 0x30
+#define STI_SET_L 0x34
+#define STI_INTSTATUS 0x40
+#define STI_INTRAWSTATUS 0x44
+#define STI_INTENSET 0x48
+#define STI_INTENCLR 0x4c
+#define STI_INTFFCLR 0x50
+
+static inline unsigned long em_sti_read(struct em_sti_priv *p, int offs)
+{
+ return ioread32(p->base + offs);
+}
+
+static inline void em_sti_write(struct em_sti_priv *p, int offs,
+ unsigned long value)
+{
+ iowrite32(value, p->base + offs);
+}
+
+static int em_sti_enable(struct em_sti_priv *p)
+{
+ int ret;
+
+ /* enable clock */
+ ret = clk_enable(p->clk);
+ if (ret) {
+ dev_err(&p->pdev->dev, "cannot enable clock\n");
+ return ret;
+ }
+
+ /* configure channel, periodic mode and maximum timeout */
+ p->rate = clk_get_rate(p->clk);
+
+ /* reset the counter */
+ em_sti_write(p, STI_SET_H, 0x40000000);
+ em_sti_write(p, STI_SET_L, 0x00000000);
+
+ /* mask and clear pending interrupts */
+ em_sti_write(p, STI_INTENCLR, 3);
+ em_sti_write(p, STI_INTFFCLR, 3);
+
+ /* enable updates of counter registers */
+ em_sti_write(p, STI_CONTROL, 1);
+
+ return 0;
+}
+
+static void em_sti_disable(struct em_sti_priv *p)
+{
+ /* mask interrupts */
+ em_sti_write(p, STI_INTENCLR, 3);
+
+ /* stop clock */
+ clk_disable(p->clk);
+}
+
+static cycle_t em_sti_count(struct em_sti_priv *p)
+{
+ cycle_t ticks;
+ unsigned long flags;
+
+ /* the STI hardware buffers the 48-bit count, but to
+ * break it out into two 32-bit access the registers
+ * must be accessed in a certain order.
+ * Always read STI_COUNT_H before STI_COUNT_L.
+ */
+ raw_spin_lock_irqsave(&p->lock, flags);
+ ticks = (cycle_t)(em_sti_read(p, STI_COUNT_H) & 0xffff) << 32;
+ ticks |= em_sti_read(p, STI_COUNT_L);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+
+ return ticks;
+}
+
+static cycle_t em_sti_set_next(struct em_sti_priv *p, cycle_t next)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&p->lock, flags);
+
+ /* mask compare A interrupt */
+ em_sti_write(p, STI_INTENCLR, 1);
+
+ /* update compare A value */
+ em_sti_write(p, STI_COMPA_H, next >> 32);
+ em_sti_write(p, STI_COMPA_L, next & 0xffffffff);
+
+ /* clear compare A interrupt source */
+ em_sti_write(p, STI_INTFFCLR, 1);
+
+ /* unmask compare A interrupt */
+ em_sti_write(p, STI_INTENSET, 1);
+
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+
+ return next;
+}
+
+static irqreturn_t em_sti_interrupt(int irq, void *dev_id)
+{
+ struct em_sti_priv *p = dev_id;
+
+ p->ced.event_handler(&p->ced);
+ return IRQ_HANDLED;
+}
+
+static int em_sti_start(struct em_sti_priv *p, unsigned int user)
+{
+ unsigned long flags;
+ int used_before;
+ int ret = 0;
+
+ raw_spin_lock_irqsave(&p->lock, flags);
+ used_before = p->active[USER_CLOCKSOURCE] | p->active[USER_CLOCKEVENT];
+ if (!used_before)
+ ret = em_sti_enable(p);
+
+ if (!ret)
+ p->active[user] = 1;
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+
+ return ret;
+}
+
+static void em_sti_stop(struct em_sti_priv *p, unsigned int user)
+{
+ unsigned long flags;
+ int used_before, used_after;
+
+ raw_spin_lock_irqsave(&p->lock, flags);
+ used_before = p->active[USER_CLOCKSOURCE] | p->active[USER_CLOCKEVENT];
+ p->active[user] = 0;
+ used_after = p->active[USER_CLOCKSOURCE] | p->active[USER_CLOCKEVENT];
+
+ if (used_before && !used_after)
+ em_sti_disable(p);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
+}
+
+static struct em_sti_priv *cs_to_em_sti(struct clocksource *cs)
+{
+ return container_of(cs, struct em_sti_priv, cs);
+}
+
+static cycle_t em_sti_clocksource_read(struct clocksource *cs)
+{
+ return em_sti_count(cs_to_em_sti(cs));
+}
+
+static int em_sti_clocksource_enable(struct clocksource *cs)
+{
+ int ret;
+ struct em_sti_priv *p = cs_to_em_sti(cs);
+
+ ret = em_sti_start(p, USER_CLOCKSOURCE);
+ if (!ret)
+ __clocksource_updatefreq_hz(cs, p->rate);
+ return ret;
+}
+
+static void em_sti_clocksource_disable(struct clocksource *cs)
+{
+ em_sti_stop(cs_to_em_sti(cs), USER_CLOCKSOURCE);
+}
+
+static void em_sti_clocksource_resume(struct clocksource *cs)
+{
+ em_sti_clocksource_enable(cs);
+}
+
+static int em_sti_register_clocksource(struct em_sti_priv *p)
+{
+ struct clocksource *cs = &p->cs;
+
+ memset(cs, 0, sizeof(*cs));
+ cs->name = dev_name(&p->pdev->dev);
+ cs->rating = 200;
+ cs->read = em_sti_clocksource_read;
+ cs->enable = em_sti_clocksource_enable;
+ cs->disable = em_sti_clocksource_disable;
+ cs->suspend = em_sti_clocksource_disable;
+ cs->resume = em_sti_clocksource_resume;
+ cs->mask = CLOCKSOURCE_MASK(48);
+ cs->flags = CLOCK_SOURCE_IS_CONTINUOUS;
+
+ dev_info(&p->pdev->dev, "used as clock source\n");
+
+ /* Register with dummy 1 Hz value, gets updated in ->enable() */
+ clocksource_register_hz(cs, 1);
+ return 0;
+}
+
+static struct em_sti_priv *ced_to_em_sti(struct clock_event_device *ced)
+{
+ return container_of(ced, struct em_sti_priv, ced);
+}
+
+static void em_sti_clock_event_mode(enum clock_event_mode mode,
+ struct clock_event_device *ced)
+{
+ struct em_sti_priv *p = ced_to_em_sti(ced);
+
+ /* deal with old setting first */
+ switch (ced->mode) {
+ case CLOCK_EVT_MODE_ONESHOT:
+ em_sti_stop(p, USER_CLOCKEVENT);
+ break;
+ default:
+ break;
+ }
+
+ switch (mode) {
+ case CLOCK_EVT_MODE_ONESHOT:
+ dev_info(&p->pdev->dev, "used for oneshot clock events\n");
+ em_sti_start(p, USER_CLOCKEVENT);
+ clockevents_config(&p->ced, p->rate);
+ break;
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ case CLOCK_EVT_MODE_UNUSED:
+ em_sti_stop(p, USER_CLOCKEVENT);
+ break;
+ default:
+ break;
+ }
+}
+
+static int em_sti_clock_event_next(unsigned long delta,
+ struct clock_event_device *ced)
+{
+ struct em_sti_priv *p = ced_to_em_sti(ced);
+ cycle_t next;
+ int safe;
+
+ next = em_sti_set_next(p, em_sti_count(p) + delta);
+ safe = em_sti_count(p) < (next - 1);
+
+ return !safe;
+}
+
+static void em_sti_register_clockevent(struct em_sti_priv *p)
+{
+ struct clock_event_device *ced = &p->ced;
+
+ memset(ced, 0, sizeof(*ced));
+ ced->name = dev_name(&p->pdev->dev);
+ ced->features = CLOCK_EVT_FEAT_ONESHOT;
+ ced->rating = 200;
+ ced->cpumask = cpumask_of(0);
+ ced->set_next_event = em_sti_clock_event_next;
+ ced->set_mode = em_sti_clock_event_mode;
+
+ dev_info(&p->pdev->dev, "used for clock events\n");
+
+ /* Register with dummy 1 Hz value, gets updated in ->set_mode() */
+ clockevents_config_and_register(ced, 1, 2, 0xffffffff);
+}
+
+static int __devinit em_sti_probe(struct platform_device *pdev)
+{
+ struct em_sti_priv *p;
+ struct resource *res;
+ int irq, ret;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (p == NULL) {
+ dev_err(&pdev->dev, "failed to allocate driver data\n");
+ ret = -ENOMEM;
+ goto err0;
+ }
+
+ p->pdev = pdev;
+ platform_set_drvdata(pdev, p);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(&pdev->dev, "failed to get I/O memory\n");
+ ret = -EINVAL;
+ goto err0;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(&pdev->dev, "failed to get irq\n");
+ ret = -EINVAL;
+ goto err0;
+ }
+
+ /* map memory, let base point to the STI instance */
+ p->base = ioremap_nocache(res->start, resource_size(res));
+ if (p->base == NULL) {
+ dev_err(&pdev->dev, "failed to remap I/O memory\n");
+ ret = -ENXIO;
+ goto err0;
+ }
+
+ /* get hold of clock */
+ p->clk = clk_get(&pdev->dev, "sclk");
+ if (IS_ERR(p->clk)) {
+ dev_err(&pdev->dev, "cannot get clock\n");
+ ret = PTR_ERR(p->clk);
+ goto err1;
+ }
+
+ if (request_irq(irq, em_sti_interrupt,
+ IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING,
+ dev_name(&pdev->dev), p)) {
+ dev_err(&pdev->dev, "failed to request low IRQ\n");
+ ret = -ENOENT;
+ goto err2;
+ }
+
+ raw_spin_lock_init(&p->lock);
+ em_sti_register_clockevent(p);
+ em_sti_register_clocksource(p);
+ return 0;
+
+err2:
+ clk_put(p->clk);
+err1:
+ iounmap(p->base);
+err0:
+ kfree(p);
+ return ret;
+}
+
+static int __devexit em_sti_remove(struct platform_device *pdev)
+{
+ return -EBUSY; /* cannot unregister clockevent and clocksource */
+}
+
+static const struct of_device_id em_sti_dt_ids[] __devinitconst = {
+ { .compatible = "renesas,em-sti", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, em_sti_dt_ids);
+
+static struct platform_driver em_sti_device_driver = {
+ .probe = em_sti_probe,
+ .remove = __devexit_p(em_sti_remove),
+ .driver = {
+ .name = "em_sti",
+ .of_match_table = em_sti_dt_ids,
+ }
+};
+
+module_platform_driver(em_sti_device_driver);
+
+MODULE_AUTHOR("Magnus Damm");
+MODULE_DESCRIPTION("Renesas Emma Mobile STI Timer Driver");
+MODULE_LICENSE("GPL v2");
unsigned long next_match_value;
unsigned long max_match_value;
unsigned long rate;
- spinlock_t lock;
+ raw_spinlock_t lock;
struct clock_event_device ced;
struct clocksource cs;
unsigned long total_cycles;
};
-static DEFINE_SPINLOCK(sh_cmt_lock);
+static DEFINE_RAW_SPINLOCK(sh_cmt_lock);
#define CMSTR -1 /* shared register */
#define CMCSR 0 /* channel register */
unsigned long flags, value;
/* start stop register shared by multiple timer channels */
- spin_lock_irqsave(&sh_cmt_lock, flags);
+ raw_spin_lock_irqsave(&sh_cmt_lock, flags);
value = sh_cmt_read(p, CMSTR);
if (start)
value &= ~(1 << cfg->timer_bit);
sh_cmt_write(p, CMSTR, value);
- spin_unlock_irqrestore(&sh_cmt_lock, flags);
+ raw_spin_unlock_irqrestore(&sh_cmt_lock, flags);
}
static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
{
unsigned long flags;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
__sh_cmt_set_next(p, delta);
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
}
static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
int ret = 0;
unsigned long flags;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
if (!(p->flags & (FLAG_CLOCKEVENT | FLAG_CLOCKSOURCE)))
ret = sh_cmt_enable(p, &p->rate);
if ((flag == FLAG_CLOCKSOURCE) && (!(p->flags & FLAG_CLOCKEVENT)))
__sh_cmt_set_next(p, p->max_match_value);
out:
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
return ret;
}
unsigned long flags;
unsigned long f;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
f = p->flags & (FLAG_CLOCKEVENT | FLAG_CLOCKSOURCE);
p->flags &= ~flag;
if ((flag == FLAG_CLOCKEVENT) && (p->flags & FLAG_CLOCKSOURCE))
__sh_cmt_set_next(p, p->max_match_value);
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
}
static struct sh_cmt_priv *cs_to_sh_cmt(struct clocksource *cs)
unsigned long value;
int has_wrapped;
- spin_lock_irqsave(&p->lock, flags);
+ raw_spin_lock_irqsave(&p->lock, flags);
value = p->total_cycles;
raw = sh_cmt_get_counter(p, &has_wrapped);
if (unlikely(has_wrapped))
raw += p->match_value + 1;
- spin_unlock_irqrestore(&p->lock, flags);
+ raw_spin_unlock_irqrestore(&p->lock, flags);
return value + raw;
}
p->max_match_value = (1 << p->width) - 1;
p->match_value = p->max_match_value;
- spin_lock_init(&p->lock);
+ raw_spin_lock_init(&p->lock);
if (clockevent_rating)
sh_cmt_register_clockevent(p, name, clockevent_rating);
struct clock_event_device ced;
};
-static DEFINE_SPINLOCK(sh_mtu2_lock);
+static DEFINE_RAW_SPINLOCK(sh_mtu2_lock);
#define TSTR -1 /* shared register */
#define TCR 0 /* channel register */
unsigned long flags, value;
/* start stop register shared by multiple timer channels */
- spin_lock_irqsave(&sh_mtu2_lock, flags);
+ raw_spin_lock_irqsave(&sh_mtu2_lock, flags);
value = sh_mtu2_read(p, TSTR);
if (start)
value &= ~(1 << cfg->timer_bit);
sh_mtu2_write(p, TSTR, value);
- spin_unlock_irqrestore(&sh_mtu2_lock, flags);
+ raw_spin_unlock_irqrestore(&sh_mtu2_lock, flags);
}
static int sh_mtu2_enable(struct sh_mtu2_priv *p)
struct clocksource cs;
};
-static DEFINE_SPINLOCK(sh_tmu_lock);
+static DEFINE_RAW_SPINLOCK(sh_tmu_lock);
#define TSTR -1 /* shared register */
#define TCOR 0 /* channel register */
unsigned long flags, value;
/* start stop register shared by multiple timer channels */
- spin_lock_irqsave(&sh_tmu_lock, flags);
+ raw_spin_lock_irqsave(&sh_tmu_lock, flags);
value = sh_tmu_read(p, TSTR);
if (start)
value &= ~(1 << cfg->timer_bit);
sh_tmu_write(p, TSTR, value);
- spin_unlock_irqrestore(&sh_tmu_lock, flags);
+ raw_spin_unlock_irqrestore(&sh_tmu_lock, flags);
}
static int sh_tmu_enable(struct sh_tmu_priv *p)
sh_tmu_enable(p);
- /* TODO: calculate good shift from rate and counter bit width */
-
- ced->shift = 32;
- ced->mult = div_sc(p->rate, NSEC_PER_SEC, ced->shift);
- ced->max_delta_ns = clockevent_delta2ns(0xffffffff, ced);
- ced->min_delta_ns = 5000;
+ clockevents_config(ced, p->rate);
if (periodic) {
p->periodic = (p->rate + HZ/2) / HZ;
ced->set_mode = sh_tmu_clock_event_mode;
dev_info(&p->pdev->dev, "used for clock events\n");
- clockevents_register_device(ced);
+
+ clockevents_config_and_register(ced, 1, 0x300, 0xffffffff);
ret = setup_irq(p->irqaction.irq, &p->irqaction);
if (ret) {
}
/* need to set base address for gpc4 */
- exonys5_gpios_1[11].base = gpio_base1 + 0x2E0;
+ exynos5_gpios_1[11].base = gpio_base1 + 0x2E0;
/* need to set base address for gpx */
chip = &exynos5_gpios_1[21];
};
static struct drm_driver exynos_drm_driver = {
- .driver_features = DRIVER_HAVE_IRQ | DRIVER_BUS_PLATFORM |
- DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
+ .driver_features = DRIVER_HAVE_IRQ | DRIVER_MODESET |
+ DRIVER_GEM | DRIVER_PRIME,
.load = exynos_drm_load,
.unload = exynos_drm_unload,
.open = exynos_drm_open,
manager_ops->commit(manager->dev);
}
-static struct drm_crtc *
-exynos_drm_encoder_get_crtc(struct drm_encoder *encoder)
-{
- return encoder->crtc;
-}
-
static struct drm_encoder_helper_funcs exynos_encoder_helper_funcs = {
.dpms = exynos_drm_encoder_dpms,
.mode_fixup = exynos_drm_encoder_mode_fixup,
.mode_set = exynos_drm_encoder_mode_set,
.prepare = exynos_drm_encoder_prepare,
.commit = exynos_drm_encoder_commit,
- .get_crtc = exynos_drm_encoder_get_crtc,
};
static void exynos_drm_encoder_destroy(struct drm_encoder *encoder)
static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
{
struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
+ unsigned int i;
DRM_DEBUG_KMS("%s\n", __FILE__);
drm_framebuffer_cleanup(fb);
+ for (i = 0; i < ARRAY_SIZE(exynos_fb->exynos_gem_obj); i++) {
+ struct drm_gem_object *obj;
+
+ if (exynos_fb->exynos_gem_obj[i] == NULL)
+ continue;
+
+ obj = &exynos_fb->exynos_gem_obj[i]->base;
+ drm_gem_object_unreference_unlocked(obj);
+ }
+
kfree(exynos_fb);
exynos_fb = NULL;
}
return ERR_PTR(-ENOENT);
}
- drm_gem_object_unreference_unlocked(obj);
-
fb = exynos_drm_framebuffer_init(dev, mode_cmd, obj);
- if (IS_ERR(fb))
+ if (IS_ERR(fb)) {
+ drm_gem_object_unreference_unlocked(obj);
return fb;
+ }
exynos_fb = to_exynos_fb(fb);
nr = exynos_drm_format_num_buffers(fb->pixel_format);
return ERR_PTR(-ENOENT);
}
- drm_gem_object_unreference_unlocked(obj);
-
exynos_fb->exynos_gem_obj[i] = to_exynos_gem_obj(obj);
}
static inline int exynos_drm_format_num_buffers(uint32_t format)
{
switch (format) {
- case DRM_FORMAT_NV12M:
+ case DRM_FORMAT_NV12:
case DRM_FORMAT_NV12MT:
return 2;
- case DRM_FORMAT_YUV420M:
+ case DRM_FORMAT_YUV420:
return 3;
default:
return 1;
struct drm_device *dev, uint32_t handle,
uint64_t *offset)
{
- struct exynos_drm_gem_obj *exynos_gem_obj;
struct drm_gem_object *obj;
int ret = 0;
goto unlock;
}
- exynos_gem_obj = to_exynos_gem_obj(obj);
-
- if (!exynos_gem_obj->base.map_list.map) {
- ret = drm_gem_create_mmap_offset(&exynos_gem_obj->base);
+ if (!obj->map_list.map) {
+ ret = drm_gem_create_mmap_offset(obj);
if (ret)
goto out;
}
- *offset = (u64)exynos_gem_obj->base.map_list.hash.key << PAGE_SHIFT;
+ *offset = (u64)obj->map_list.hash.key << PAGE_SHIFT;
DRM_DEBUG_KMS("offset = 0x%lx\n", (unsigned long)*offset);
out:
switch (win_data->pixel_format) {
case DRM_FORMAT_NV12MT:
tiled_mode = true;
- case DRM_FORMAT_NV12M:
+ case DRM_FORMAT_NV12:
crcb_mode = false;
buf_num = 2;
break;
mixer_reg_write(res, MXR_BG_COLOR2, 0x008080);
/* setting graphical layers */
-
val = MXR_GRP_CFG_COLOR_KEY_DISABLE; /* no blank key */
val |= MXR_GRP_CFG_WIN_BLEND_EN;
+ val |= MXR_GRP_CFG_BLEND_PRE_MUL;
+ val |= MXR_GRP_CFG_PIXEL_BLEND_EN;
val |= MXR_GRP_CFG_ALPHA_VAL(0xff); /* non-transparent alpha */
/* the same configuration for both layers */
mixer_reg_write(res, MXR_GRAPHIC_CFG(0), val);
-
- val |= MXR_GRP_CFG_BLEND_PRE_MUL;
- val |= MXR_GRP_CFG_PIXEL_BLEND_EN;
mixer_reg_write(res, MXR_GRAPHIC_CFG(1), val);
+ /* setting video layers */
+ val = MXR_GRP_CFG_ALPHA_VAL(0);
+ mixer_reg_write(res, MXR_VIDEO_CFG, val);
+
/* configuration of Video Processor Registers */
vp_win_reset(ctx);
vp_default_filter(res);
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_sandybridge_m_info = {
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_ivybridge_d_info = {
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_ivybridge_m_info = {
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_valleyview_m_info = {
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct intel_device_info intel_haswell_m_info = {
.has_blt_ring = 1,
.has_llc = 1,
.has_pch_split = 1,
+ .has_force_wake = 1,
};
static const struct pci_device_id pciidlist[] = { /* aka */
/* We give fast paths for the really cool registers */
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
- (((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE)) && \
- (!IS_VALLEYVIEW((dev_priv)->dev))
+ ((HAS_FORCE_WAKE((dev_priv)->dev)) && \
+ ((reg) < 0x40000) && \
+ ((reg) != FORCEWAKE))
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
u8 is_ivybridge:1;
u8 is_valleyview:1;
u8 has_pch_split:1;
+ u8 has_force_wake:1;
u8 is_haswell:1;
u8 has_fbc:1;
u8 has_pipe_cxsr:1;
#define HAS_PCH_CPT(dev) (INTEL_PCH_TYPE(dev) == PCH_CPT)
#define HAS_PCH_IBX(dev) (INTEL_PCH_TYPE(dev) == PCH_IBX)
+#define HAS_FORCE_WAKE(dev) (INTEL_INFO(dev)->has_force_wake)
+
#include "i915_trace.h"
/**
return ret;
}
-static void pch_irq_handler(struct drm_device *dev, u32 pch_iir)
+static void ibx_irq_handler(struct drm_device *dev, u32 pch_iir)
{
drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
int pipe;
DRM_DEBUG_DRIVER("PCH transcoder A underrun interrupt\n");
}
+static void cpt_irq_handler(struct drm_device *dev, u32 pch_iir)
+{
+ drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+ int pipe;
+
+ if (pch_iir & SDE_AUDIO_POWER_MASK_CPT)
+ DRM_DEBUG_DRIVER("PCH audio power change on port %d\n",
+ (pch_iir & SDE_AUDIO_POWER_MASK_CPT) >>
+ SDE_AUDIO_POWER_SHIFT_CPT);
+
+ if (pch_iir & SDE_AUX_MASK_CPT)
+ DRM_DEBUG_DRIVER("AUX channel interrupt\n");
+
+ if (pch_iir & SDE_GMBUS_CPT)
+ DRM_DEBUG_DRIVER("PCH GMBUS interrupt\n");
+
+ if (pch_iir & SDE_AUDIO_CP_REQ_CPT)
+ DRM_DEBUG_DRIVER("Audio CP request interrupt\n");
+
+ if (pch_iir & SDE_AUDIO_CP_CHG_CPT)
+ DRM_DEBUG_DRIVER("Audio CP change interrupt\n");
+
+ if (pch_iir & SDE_FDI_MASK_CPT)
+ for_each_pipe(pipe)
+ DRM_DEBUG_DRIVER(" pipe %c FDI IIR: 0x%08x\n",
+ pipe_name(pipe),
+ I915_READ(FDI_RX_IIR(pipe)));
+}
+
static irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS)
{
struct drm_device *dev = (struct drm_device *) arg;
if (pch_iir & SDE_HOTPLUG_MASK_CPT)
queue_work(dev_priv->wq, &dev_priv->hotplug_work);
- pch_irq_handler(dev, pch_iir);
+ cpt_irq_handler(dev, pch_iir);
/* clear PCH hotplug event before clear CPU irq */
I915_WRITE(SDEIIR, pch_iir);
if (de_iir & DE_PCH_EVENT) {
if (pch_iir & hotplug_mask)
queue_work(dev_priv->wq, &dev_priv->hotplug_work);
- pch_irq_handler(dev, pch_iir);
+ if (HAS_PCH_CPT(dev))
+ cpt_irq_handler(dev, pch_iir);
+ else
+ ibx_irq_handler(dev, pch_iir);
}
if (de_iir & DE_PCU_EVENT) {
#define MI_DISPLAY_FLIP MI_INSTR(0x14, 2)
#define MI_DISPLAY_FLIP_I915 MI_INSTR(0x14, 1)
#define MI_DISPLAY_FLIP_PLANE(n) ((n) << 20)
+/* IVB has funny definitions for which plane to flip. */
+#define MI_DISPLAY_FLIP_IVB_PLANE_A (0 << 19)
+#define MI_DISPLAY_FLIP_IVB_PLANE_B (1 << 19)
+#define MI_DISPLAY_FLIP_IVB_SPRITE_A (2 << 19)
+#define MI_DISPLAY_FLIP_IVB_SPRITE_B (3 << 19)
+#define MI_DISPLAY_FLIP_IVB_PLANE_C (4 << 19)
+#define MI_DISPLAY_FLIP_IVB_SPRITE_C (5 << 19)
+
#define MI_SET_CONTEXT MI_INSTR(0x18, 0)
#define MI_MM_SPACE_GTT (1<<8)
#define MI_MM_SPACE_PHYSICAL (0<<8)
/* PCH */
-/* south display engine interrupt */
+/* south display engine interrupt: IBX */
#define SDE_AUDIO_POWER_D (1 << 27)
#define SDE_AUDIO_POWER_C (1 << 26)
#define SDE_AUDIO_POWER_B (1 << 25)
#define SDE_TRANSA_CRC_ERR (1 << 1)
#define SDE_TRANSA_FIFO_UNDER (1 << 0)
#define SDE_TRANS_MASK (0x3f)
-/* CPT */
-#define SDE_CRT_HOTPLUG_CPT (1 << 19)
+
+/* south display engine interrupt: CPT/PPT */
+#define SDE_AUDIO_POWER_D_CPT (1 << 31)
+#define SDE_AUDIO_POWER_C_CPT (1 << 30)
+#define SDE_AUDIO_POWER_B_CPT (1 << 29)
+#define SDE_AUDIO_POWER_SHIFT_CPT 29
+#define SDE_AUDIO_POWER_MASK_CPT (7 << 29)
+#define SDE_AUXD_CPT (1 << 27)
+#define SDE_AUXC_CPT (1 << 26)
+#define SDE_AUXB_CPT (1 << 25)
+#define SDE_AUX_MASK_CPT (7 << 25)
#define SDE_PORTD_HOTPLUG_CPT (1 << 23)
#define SDE_PORTC_HOTPLUG_CPT (1 << 22)
#define SDE_PORTB_HOTPLUG_CPT (1 << 21)
+#define SDE_CRT_HOTPLUG_CPT (1 << 19)
#define SDE_HOTPLUG_MASK_CPT (SDE_CRT_HOTPLUG_CPT | \
SDE_PORTD_HOTPLUG_CPT | \
SDE_PORTC_HOTPLUG_CPT | \
SDE_PORTB_HOTPLUG_CPT)
+#define SDE_GMBUS_CPT (1 << 17)
+#define SDE_AUDIO_CP_REQ_C_CPT (1 << 10)
+#define SDE_AUDIO_CP_CHG_C_CPT (1 << 9)
+#define SDE_FDI_RXC_CPT (1 << 8)
+#define SDE_AUDIO_CP_REQ_B_CPT (1 << 6)
+#define SDE_AUDIO_CP_CHG_B_CPT (1 << 5)
+#define SDE_FDI_RXB_CPT (1 << 4)
+#define SDE_AUDIO_CP_REQ_A_CPT (1 << 2)
+#define SDE_AUDIO_CP_CHG_A_CPT (1 << 1)
+#define SDE_FDI_RXA_CPT (1 << 0)
+#define SDE_AUDIO_CP_REQ_CPT (SDE_AUDIO_CP_REQ_C_CPT | \
+ SDE_AUDIO_CP_REQ_B_CPT | \
+ SDE_AUDIO_CP_REQ_A_CPT)
+#define SDE_AUDIO_CP_CHG_CPT (SDE_AUDIO_CP_CHG_C_CPT | \
+ SDE_AUDIO_CP_CHG_B_CPT | \
+ SDE_AUDIO_CP_CHG_A_CPT)
+#define SDE_FDI_MASK_CPT (SDE_FDI_RXC_CPT | \
+ SDE_FDI_RXB_CPT | \
+ SDE_FDI_RXA_CPT)
#define SDEISR 0xc4000
#define SDEIMR 0xc4004
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
struct intel_ring_buffer *ring = &dev_priv->ring[BCS];
+ uint32_t plane_bit = 0;
int ret;
ret = intel_pin_and_fence_fb_obj(dev, obj, ring);
if (ret)
goto err;
+ switch(intel_crtc->plane) {
+ case PLANE_A:
+ plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_A;
+ break;
+ case PLANE_B:
+ plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_B;
+ break;
+ case PLANE_C:
+ plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_C;
+ break;
+ default:
+ WARN_ONCE(1, "unknown plane in flip command\n");
+ ret = -ENODEV;
+ goto err;
+ }
+
ret = intel_ring_begin(ring, 4);
if (ret)
goto err_unpin;
- intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | (intel_crtc->plane << 19));
+ intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
intel_ring_emit(ring, (obj->gtt_offset));
intel_ring_emit(ring, (MI_NOOP));
static int init_ring_common(struct intel_ring_buffer *ring)
{
- drm_i915_private_t *dev_priv = ring->dev->dev_private;
+ struct drm_device *dev = ring->dev;
+ drm_i915_private_t *dev_priv = dev->dev_private;
struct drm_i915_gem_object *obj = ring->obj;
+ int ret = 0;
u32 head;
+ if (HAS_FORCE_WAKE(dev))
+ gen6_gt_force_wake_get(dev_priv);
+
/* Stop the ring if it's running. */
I915_WRITE_CTL(ring, 0);
I915_WRITE_HEAD(ring, 0);
I915_READ_HEAD(ring),
I915_READ_TAIL(ring),
I915_READ_START(ring));
- return -EIO;
+ ret = -EIO;
+ goto out;
}
if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
ring->head = I915_READ_HEAD(ring);
ring->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
ring->space = ring_space(ring);
+ ring->last_retired_head = -1;
}
- return 0;
+out:
+ if (HAS_FORCE_WAKE(dev))
+ gen6_gt_force_wake_put(dev_priv);
+
+ return ret;
}
static int
if (ret)
goto err_unref;
+ ret = i915_gem_object_set_to_gtt_domain(obj, true);
+ if (ret)
+ goto err_unpin;
+
ring->virtual_start = ioremap_wc(dev->agp->base + obj->gtt_offset,
ring->size);
if (ring->virtual_start == NULL) {
u32 cb_color_view[12];
u32 cb_color_pitch[12];
u32 cb_color_slice[12];
+ u32 cb_color_slice_idx[12];
u32 cb_color_attrib[12];
u32 cb_color_cmask_slice[8];/* unused */
u32 cb_color_fmask_slice[8];/* unused */
track->cb_color_info[i] = 0;
track->cb_color_view[i] = 0xFFFFFFFF;
track->cb_color_pitch[i] = 0;
- track->cb_color_slice[i] = 0;
+ track->cb_color_slice[i] = 0xfffffff;
+ track->cb_color_slice_idx[i] = 0;
}
track->cb_target_mask = 0xFFFFFFFF;
track->cb_shader_mask = 0xFFFFFFFF;
track->cb_dirty = true;
+ track->db_depth_slice = 0xffffffff;
track->db_depth_view = 0xFFFFC000;
track->db_depth_size = 0xFFFFFFFF;
track->db_depth_control = 0xFFFFFFFF;
{
struct evergreen_cs_track *track = p->track;
unsigned palign, halign, tileb, slice_pt;
+ unsigned mtile_pr, mtile_ps, mtileb;
tileb = 64 * surf->bpe * surf->nsamples;
- palign = track->group_size / (8 * surf->bpe * surf->nsamples);
- palign = MAX(8, palign);
slice_pt = 1;
if (tileb > surf->tsplit) {
slice_pt = tileb / surf->tsplit;
/* macro tile width & height */
palign = (8 * surf->bankw * track->npipes) * surf->mtilea;
halign = (8 * surf->bankh * surf->nbanks) / surf->mtilea;
- surf->layer_size = surf->nbx * surf->nby * surf->bpe * slice_pt;
+ mtileb = (palign / 8) * (halign / 8) * tileb;;
+ mtile_pr = surf->nbx / palign;
+ mtile_ps = (mtile_pr * surf->nby) / halign;
+ surf->layer_size = mtile_ps * mtileb * slice_pt;
surf->base_align = (palign / 8) * (halign / 8) * tileb;
surf->palign = palign;
surf->halign = halign;
offset += surf.layer_size * mslice;
if (offset > radeon_bo_size(track->cb_color_bo[id])) {
+ /* old ddx are broken they allocate bo with w*h*bpp but
+ * program slice with ALIGN(h, 8), catch this and patch
+ * command stream.
+ */
+ if (!surf.mode) {
+ volatile u32 *ib = p->ib.ptr;
+ unsigned long tmp, nby, bsize, size, min = 0;
+
+ /* find the height the ddx wants */
+ if (surf.nby > 8) {
+ min = surf.nby - 8;
+ }
+ bsize = radeon_bo_size(track->cb_color_bo[id]);
+ tmp = track->cb_color_bo_offset[id] << 8;
+ for (nby = surf.nby; nby > min; nby--) {
+ size = nby * surf.nbx * surf.bpe * surf.nsamples;
+ if ((tmp + size * mslice) <= bsize) {
+ break;
+ }
+ }
+ if (nby > min) {
+ surf.nby = nby;
+ slice = ((nby * surf.nbx) / 64) - 1;
+ if (!evergreen_surface_check(p, &surf, "cb")) {
+ /* check if this one works */
+ tmp += surf.layer_size * mslice;
+ if (tmp <= bsize) {
+ ib[track->cb_color_slice_idx[id]] = slice;
+ goto old_ddx_ok;
+ }
+ }
+ }
+ }
dev_warn(p->dev, "%s:%d cb[%d] bo too small (layer size %d, "
"offset %d, max layer %d, bo size %ld, slice %d)\n",
__func__, __LINE__, id, surf.layer_size,
surf.tsplit, surf.mtilea);
return -EINVAL;
}
+old_ddx_ok:
return 0;
}
case CB_COLOR7_SLICE:
tmp = (reg - CB_COLOR0_SLICE) / 0x3c;
track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
+ track->cb_color_slice_idx[tmp] = idx;
track->cb_dirty = true;
break;
case CB_COLOR8_SLICE:
case CB_COLOR11_SLICE:
tmp = ((reg - CB_COLOR8_SLICE) / 0x1c) + 8;
track->cb_color_slice[tmp] = radeon_get_ib_value(p, idx);
+ track->cb_color_slice_idx[tmp] = idx;
track->cb_dirty = true;
break;
case CB_COLOR0_ATTRIB:
rdev->config.cayman.max_pipes_per_simd = 4;
rdev->config.cayman.max_tile_pipes = 2;
if ((rdev->pdev->device == 0x9900) ||
- (rdev->pdev->device == 0x9901)) {
+ (rdev->pdev->device == 0x9901) ||
+ (rdev->pdev->device == 0x9905) ||
+ (rdev->pdev->device == 0x9906) ||
+ (rdev->pdev->device == 0x9907) ||
+ (rdev->pdev->device == 0x9908) ||
+ (rdev->pdev->device == 0x9909) ||
+ (rdev->pdev->device == 0x9910) ||
+ (rdev->pdev->device == 0x9917)) {
rdev->config.cayman.max_simds_per_se = 6;
rdev->config.cayman.max_backends_per_se = 2;
} else if ((rdev->pdev->device == 0x9903) ||
- (rdev->pdev->device == 0x9904)) {
+ (rdev->pdev->device == 0x9904) ||
+ (rdev->pdev->device == 0x990A) ||
+ (rdev->pdev->device == 0x9913) ||
+ (rdev->pdev->device == 0x9918)) {
rdev->config.cayman.max_simds_per_se = 4;
rdev->config.cayman.max_backends_per_se = 2;
- } else if ((rdev->pdev->device == 0x9990) ||
- (rdev->pdev->device == 0x9991)) {
+ } else if ((rdev->pdev->device == 0x9919) ||
+ (rdev->pdev->device == 0x9990) ||
+ (rdev->pdev->device == 0x9991) ||
+ (rdev->pdev->device == 0x9994) ||
+ (rdev->pdev->device == 0x99A0)) {
rdev->config.cayman.max_simds_per_se = 3;
rdev->config.cayman.max_backends_per_se = 1;
} else {
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ DRM_ERROR("radeon: audio init failed\n");
+ return r;
+ }
+
return 0;
}
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- DRM_ERROR("radeon: audio resume failed\n");
- return r;
- }
-
return r;
}
rdev->accel_working = false;
}
- r = r600_audio_init(rdev);
- if (r)
- return r; /* TODO error handling */
return 0;
}
struct radeon_device *rdev = dev->dev_private;
struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+ struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc);
int base_rate = 48000;
switch (radeon_encoder->encoder_id) {
WREG32(EVERGREEN_AUDIO_PLL1_DIV, clock * 10);
WREG32(EVERGREEN_AUDIO_PLL1_UNK, 0x00000071);
- /* Some magic trigger or src sel? */
- WREG32_P(0x5ac, 0x01, ~0x77);
+ /* Select DTO source */
+ WREG32(0x5ac, radeon_crtc->crtc_id);
} else {
switch (dig->dig_encoder) {
case 0:
WREG32(HDMI0_AUDIO_PACKET_CONTROL + offset,
HDMI0_AUDIO_SAMPLE_SEND | /* send audio packets */
HDMI0_AUDIO_DELAY_EN(1) | /* default audio delay */
- HDMI0_AUDIO_SEND_MAX_PACKETS | /* send NULL packets if no audio is available */
HDMI0_AUDIO_PACKETS_PER_LINE(3) | /* should be suffient for all audio modes and small enough for all hblanks */
HDMI0_60958_CS_UPDATE); /* allow 60958 channel status fields to be updated */
}
struct si_asic {
unsigned max_shader_engines;
- unsigned max_pipes_per_simd;
unsigned max_tile_pipes;
- unsigned max_simds_per_se;
+ unsigned max_cu_per_sh;
+ unsigned max_sh_per_se;
unsigned max_backends_per_se;
unsigned max_texture_channel_caches;
unsigned max_gprs;
unsigned sc_hiz_tile_fifo_size;
unsigned sc_earlyz_tile_fifo_size;
- unsigned num_shader_engines;
unsigned num_tile_pipes;
unsigned num_backends_per_se;
unsigned backend_disable_mask_per_asic;
* 2.13.0 - virtual memory support, streamout
* 2.14.0 - add evergreen tiling informations
* 2.15.0 - add max_pipes query
+ * 2.16.0 - fix evergreen 2D tiled surface calculation
*/
#define KMS_DRIVER_MAJOR 2
-#define KMS_DRIVER_MINOR 15
+#define KMS_DRIVER_MINOR 16
#define KMS_DRIVER_PATCHLEVEL 0
int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
int radeon_driver_unload_kms(struct drm_device *dev);
mutex_lock(&vm->mutex);
if (last_pfn > vm->last_pfn) {
- /* grow va space 32M by 32M */
- unsigned align = ((32 << 20) >> 12) - 1;
+ /* release mutex and lock in right order */
+ mutex_unlock(&vm->mutex);
radeon_mutex_lock(&rdev->cs_mutex);
- radeon_vm_unbind_locked(rdev, vm);
+ mutex_lock(&vm->mutex);
+ /* and check again */
+ if (last_pfn > vm->last_pfn) {
+ /* grow va space 32M by 32M */
+ unsigned align = ((32 << 20) >> 12) - 1;
+ radeon_vm_unbind_locked(rdev, vm);
+ vm->last_pfn = (last_pfn + align) & ~align;
+ }
radeon_mutex_unlock(&rdev->cs_mutex);
- vm->last_pfn = (last_pfn + align) & ~align;
}
head = &vm->va;
last_offset = 0;
if (bo_va == NULL)
return 0;
- mutex_lock(&vm->mutex);
radeon_mutex_lock(&rdev->cs_mutex);
+ mutex_lock(&vm->mutex);
radeon_vm_bo_update_pte(rdev, vm, bo, NULL);
radeon_mutex_unlock(&rdev->cs_mutex);
list_del(&bo_va->vm_list);
struct radeon_bo_va *bo_va, *tmp;
int r;
- mutex_lock(&vm->mutex);
-
radeon_mutex_lock(&rdev->cs_mutex);
+ mutex_lock(&vm->mutex);
radeon_vm_unbind_locked(rdev, vm);
radeon_mutex_unlock(&rdev->cs_mutex);
break;
case RADEON_INFO_MAX_PIPES:
if (rdev->family >= CHIP_TAHITI)
- value = rdev->config.si.max_pipes_per_simd;
+ value = rdev->config.si.max_cu_per_sh;
else if (rdev->family >= CHIP_CAYMAN)
value = rdev->config.cayman.max_pipes_per_simd;
else if (rdev->family >= CHIP_CEDAR)
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "failed initializing audio\n");
- return r;
- }
-
r = radeon_ib_pool_start(rdev);
if (r)
return r;
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ dev_err(rdev->dev, "failed initializing audio\n");
+ return r;
+ }
+
return 0;
}
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "failed initializing audio\n");
- return r;
- }
-
r = radeon_ib_pool_start(rdev);
if (r)
return r;
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ dev_err(rdev->dev, "failed initializing audio\n");
+ return r;
+ }
+
return 0;
}
if (r)
return r;
+ r = r600_audio_init(rdev);
+ if (r) {
+ DRM_ERROR("radeon: audio init failed\n");
+ return r;
+ }
+
return 0;
}
return r;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "radeon: audio init failed\n");
- return r;
- }
-
return r;
}
rdev->accel_working = false;
}
- r = r600_audio_init(rdev);
- if (r) {
- dev_err(rdev->dev, "radeon: audio init failed\n");
- return r;
- }
-
return 0;
}
/*
* Core functions
*/
-static u32 si_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
- u32 num_tile_pipes,
- u32 num_backends_per_asic,
- u32 *backend_disable_mask_per_asic,
- u32 num_shader_engines)
-{
- u32 backend_map = 0;
- u32 enabled_backends_mask = 0;
- u32 enabled_backends_count = 0;
- u32 num_backends_per_se;
- u32 cur_pipe;
- u32 swizzle_pipe[SI_MAX_PIPES];
- u32 cur_backend = 0;
- u32 i;
- bool force_no_swizzle;
-
- /* force legal values */
- if (num_tile_pipes < 1)
- num_tile_pipes = 1;
- if (num_tile_pipes > rdev->config.si.max_tile_pipes)
- num_tile_pipes = rdev->config.si.max_tile_pipes;
- if (num_shader_engines < 1)
- num_shader_engines = 1;
- if (num_shader_engines > rdev->config.si.max_shader_engines)
- num_shader_engines = rdev->config.si.max_shader_engines;
- if (num_backends_per_asic < num_shader_engines)
- num_backends_per_asic = num_shader_engines;
- if (num_backends_per_asic > (rdev->config.si.max_backends_per_se * num_shader_engines))
- num_backends_per_asic = rdev->config.si.max_backends_per_se * num_shader_engines;
-
- /* make sure we have the same number of backends per se */
- num_backends_per_asic = ALIGN(num_backends_per_asic, num_shader_engines);
- /* set up the number of backends per se */
- num_backends_per_se = num_backends_per_asic / num_shader_engines;
- if (num_backends_per_se > rdev->config.si.max_backends_per_se) {
- num_backends_per_se = rdev->config.si.max_backends_per_se;
- num_backends_per_asic = num_backends_per_se * num_shader_engines;
- }
-
- /* create enable mask and count for enabled backends */
- for (i = 0; i < SI_MAX_BACKENDS; ++i) {
- if (((*backend_disable_mask_per_asic >> i) & 1) == 0) {
- enabled_backends_mask |= (1 << i);
- ++enabled_backends_count;
- }
- if (enabled_backends_count == num_backends_per_asic)
- break;
- }
-
- /* force the backends mask to match the current number of backends */
- if (enabled_backends_count != num_backends_per_asic) {
- u32 this_backend_enabled;
- u32 shader_engine;
- u32 backend_per_se;
-
- enabled_backends_mask = 0;
- enabled_backends_count = 0;
- *backend_disable_mask_per_asic = SI_MAX_BACKENDS_MASK;
- for (i = 0; i < SI_MAX_BACKENDS; ++i) {
- /* calc the current se */
- shader_engine = i / rdev->config.si.max_backends_per_se;
- /* calc the backend per se */
- backend_per_se = i % rdev->config.si.max_backends_per_se;
- /* default to not enabled */
- this_backend_enabled = 0;
- if ((shader_engine < num_shader_engines) &&
- (backend_per_se < num_backends_per_se))
- this_backend_enabled = 1;
- if (this_backend_enabled) {
- enabled_backends_mask |= (1 << i);
- *backend_disable_mask_per_asic &= ~(1 << i);
- ++enabled_backends_count;
- }
- }
- }
-
-
- memset((uint8_t *)&swizzle_pipe[0], 0, sizeof(u32) * SI_MAX_PIPES);
- switch (rdev->family) {
- case CHIP_TAHITI:
- case CHIP_PITCAIRN:
- case CHIP_VERDE:
- force_no_swizzle = true;
- break;
- default:
- force_no_swizzle = false;
- break;
- }
- if (force_no_swizzle) {
- bool last_backend_enabled = false;
-
- force_no_swizzle = false;
- for (i = 0; i < SI_MAX_BACKENDS; ++i) {
- if (((enabled_backends_mask >> i) & 1) == 1) {
- if (last_backend_enabled)
- force_no_swizzle = true;
- last_backend_enabled = true;
- } else
- last_backend_enabled = false;
- }
- }
-
- switch (num_tile_pipes) {
- case 1:
- case 3:
- case 5:
- case 7:
- DRM_ERROR("odd number of pipes!\n");
- break;
- case 2:
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- break;
- case 4:
- if (force_no_swizzle) {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- swizzle_pipe[2] = 2;
- swizzle_pipe[3] = 3;
- } else {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 2;
- swizzle_pipe[2] = 1;
- swizzle_pipe[3] = 3;
- }
- break;
- case 6:
- if (force_no_swizzle) {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- swizzle_pipe[2] = 2;
- swizzle_pipe[3] = 3;
- swizzle_pipe[4] = 4;
- swizzle_pipe[5] = 5;
- } else {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 2;
- swizzle_pipe[2] = 4;
- swizzle_pipe[3] = 1;
- swizzle_pipe[4] = 3;
- swizzle_pipe[5] = 5;
- }
- break;
- case 8:
- if (force_no_swizzle) {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 1;
- swizzle_pipe[2] = 2;
- swizzle_pipe[3] = 3;
- swizzle_pipe[4] = 4;
- swizzle_pipe[5] = 5;
- swizzle_pipe[6] = 6;
- swizzle_pipe[7] = 7;
- } else {
- swizzle_pipe[0] = 0;
- swizzle_pipe[1] = 2;
- swizzle_pipe[2] = 4;
- swizzle_pipe[3] = 6;
- swizzle_pipe[4] = 1;
- swizzle_pipe[5] = 3;
- swizzle_pipe[6] = 5;
- swizzle_pipe[7] = 7;
- }
- break;
- }
-
- for (cur_pipe = 0; cur_pipe < num_tile_pipes; ++cur_pipe) {
- while (((1 << cur_backend) & enabled_backends_mask) == 0)
- cur_backend = (cur_backend + 1) % SI_MAX_BACKENDS;
-
- backend_map |= (((cur_backend & 0xf) << (swizzle_pipe[cur_pipe] * 4)));
-
- cur_backend = (cur_backend + 1) % SI_MAX_BACKENDS;
- }
-
- return backend_map;
-}
-
-static u32 si_get_disable_mask_per_asic(struct radeon_device *rdev,
- u32 disable_mask_per_se,
- u32 max_disable_mask_per_se,
- u32 num_shader_engines)
-{
- u32 disable_field_width_per_se = r600_count_pipe_bits(disable_mask_per_se);
- u32 disable_mask_per_asic = disable_mask_per_se & max_disable_mask_per_se;
-
- if (num_shader_engines == 1)
- return disable_mask_per_asic;
- else if (num_shader_engines == 2)
- return disable_mask_per_asic | (disable_mask_per_asic << disable_field_width_per_se);
- else
- return 0xffffffff;
-}
-
static void si_tiling_mode_table_init(struct radeon_device *rdev)
{
const u32 num_tile_mode_states = 32;
DRM_ERROR("unknown asic: 0x%x\n", rdev->family);
}
+static void si_select_se_sh(struct radeon_device *rdev,
+ u32 se_num, u32 sh_num)
+{
+ u32 data = INSTANCE_BROADCAST_WRITES;
+
+ if ((se_num == 0xffffffff) && (sh_num == 0xffffffff))
+ data = SH_BROADCAST_WRITES | SE_BROADCAST_WRITES;
+ else if (se_num == 0xffffffff)
+ data |= SE_BROADCAST_WRITES | SH_INDEX(sh_num);
+ else if (sh_num == 0xffffffff)
+ data |= SH_BROADCAST_WRITES | SE_INDEX(se_num);
+ else
+ data |= SH_INDEX(sh_num) | SE_INDEX(se_num);
+ WREG32(GRBM_GFX_INDEX, data);
+}
+
+static u32 si_create_bitmask(u32 bit_width)
+{
+ u32 i, mask = 0;
+
+ for (i = 0; i < bit_width; i++) {
+ mask <<= 1;
+ mask |= 1;
+ }
+ return mask;
+}
+
+static u32 si_get_cu_enabled(struct radeon_device *rdev, u32 cu_per_sh)
+{
+ u32 data, mask;
+
+ data = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
+ if (data & 1)
+ data &= INACTIVE_CUS_MASK;
+ else
+ data = 0;
+ data |= RREG32(GC_USER_SHADER_ARRAY_CONFIG);
+
+ data >>= INACTIVE_CUS_SHIFT;
+
+ mask = si_create_bitmask(cu_per_sh);
+
+ return ~data & mask;
+}
+
+static void si_setup_spi(struct radeon_device *rdev,
+ u32 se_num, u32 sh_per_se,
+ u32 cu_per_sh)
+{
+ int i, j, k;
+ u32 data, mask, active_cu;
+
+ for (i = 0; i < se_num; i++) {
+ for (j = 0; j < sh_per_se; j++) {
+ si_select_se_sh(rdev, i, j);
+ data = RREG32(SPI_STATIC_THREAD_MGMT_3);
+ active_cu = si_get_cu_enabled(rdev, cu_per_sh);
+
+ mask = 1;
+ for (k = 0; k < 16; k++) {
+ mask <<= k;
+ if (active_cu & mask) {
+ data &= ~mask;
+ WREG32(SPI_STATIC_THREAD_MGMT_3, data);
+ break;
+ }
+ }
+ }
+ }
+ si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+}
+
+static u32 si_get_rb_disabled(struct radeon_device *rdev,
+ u32 max_rb_num, u32 se_num,
+ u32 sh_per_se)
+{
+ u32 data, mask;
+
+ data = RREG32(CC_RB_BACKEND_DISABLE);
+ if (data & 1)
+ data &= BACKEND_DISABLE_MASK;
+ else
+ data = 0;
+ data |= RREG32(GC_USER_RB_BACKEND_DISABLE);
+
+ data >>= BACKEND_DISABLE_SHIFT;
+
+ mask = si_create_bitmask(max_rb_num / se_num / sh_per_se);
+
+ return data & mask;
+}
+
+static void si_setup_rb(struct radeon_device *rdev,
+ u32 se_num, u32 sh_per_se,
+ u32 max_rb_num)
+{
+ int i, j;
+ u32 data, mask;
+ u32 disabled_rbs = 0;
+ u32 enabled_rbs = 0;
+
+ for (i = 0; i < se_num; i++) {
+ for (j = 0; j < sh_per_se; j++) {
+ si_select_se_sh(rdev, i, j);
+ data = si_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+ disabled_rbs |= data << ((i * sh_per_se + j) * TAHITI_RB_BITMAP_WIDTH_PER_SH);
+ }
+ }
+ si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+
+ mask = 1;
+ for (i = 0; i < max_rb_num; i++) {
+ if (!(disabled_rbs & mask))
+ enabled_rbs |= mask;
+ mask <<= 1;
+ }
+
+ for (i = 0; i < se_num; i++) {
+ si_select_se_sh(rdev, i, 0xffffffff);
+ data = 0;
+ for (j = 0; j < sh_per_se; j++) {
+ switch (enabled_rbs & 3) {
+ case 1:
+ data |= (RASTER_CONFIG_RB_MAP_0 << (i * sh_per_se + j) * 2);
+ break;
+ case 2:
+ data |= (RASTER_CONFIG_RB_MAP_3 << (i * sh_per_se + j) * 2);
+ break;
+ case 3:
+ default:
+ data |= (RASTER_CONFIG_RB_MAP_2 << (i * sh_per_se + j) * 2);
+ break;
+ }
+ enabled_rbs >>= 2;
+ }
+ WREG32(PA_SC_RASTER_CONFIG, data);
+ }
+ si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
+}
+
static void si_gpu_init(struct radeon_device *rdev)
{
- u32 cc_rb_backend_disable = 0;
- u32 cc_gc_shader_array_config;
u32 gb_addr_config = 0;
u32 mc_shared_chmap, mc_arb_ramcfg;
- u32 gb_backend_map;
- u32 cgts_tcc_disable;
u32 sx_debug_1;
- u32 gc_user_shader_array_config;
- u32 gc_user_rb_backend_disable;
- u32 cgts_user_tcc_disable;
u32 hdp_host_path_cntl;
u32 tmp;
int i, j;
switch (rdev->family) {
case CHIP_TAHITI:
rdev->config.si.max_shader_engines = 2;
- rdev->config.si.max_pipes_per_simd = 4;
rdev->config.si.max_tile_pipes = 12;
- rdev->config.si.max_simds_per_se = 8;
+ rdev->config.si.max_cu_per_sh = 8;
+ rdev->config.si.max_sh_per_se = 2;
rdev->config.si.max_backends_per_se = 4;
rdev->config.si.max_texture_channel_caches = 12;
rdev->config.si.max_gprs = 256;
rdev->config.si.sc_prim_fifo_size_backend = 0x100;
rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TAHITI_GB_ADDR_CONFIG_GOLDEN;
break;
case CHIP_PITCAIRN:
rdev->config.si.max_shader_engines = 2;
- rdev->config.si.max_pipes_per_simd = 4;
rdev->config.si.max_tile_pipes = 8;
- rdev->config.si.max_simds_per_se = 5;
+ rdev->config.si.max_cu_per_sh = 5;
+ rdev->config.si.max_sh_per_se = 2;
rdev->config.si.max_backends_per_se = 4;
rdev->config.si.max_texture_channel_caches = 8;
rdev->config.si.max_gprs = 256;
rdev->config.si.sc_prim_fifo_size_backend = 0x100;
rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = TAHITI_GB_ADDR_CONFIG_GOLDEN;
break;
case CHIP_VERDE:
default:
rdev->config.si.max_shader_engines = 1;
- rdev->config.si.max_pipes_per_simd = 4;
rdev->config.si.max_tile_pipes = 4;
- rdev->config.si.max_simds_per_se = 2;
+ rdev->config.si.max_cu_per_sh = 2;
+ rdev->config.si.max_sh_per_se = 2;
rdev->config.si.max_backends_per_se = 4;
rdev->config.si.max_texture_channel_caches = 4;
rdev->config.si.max_gprs = 256;
rdev->config.si.sc_prim_fifo_size_backend = 0x40;
rdev->config.si.sc_hiz_tile_fifo_size = 0x30;
rdev->config.si.sc_earlyz_tile_fifo_size = 0x130;
+ gb_addr_config = VERDE_GB_ADDR_CONFIG_GOLDEN;
break;
}
mc_shared_chmap = RREG32(MC_SHARED_CHMAP);
mc_arb_ramcfg = RREG32(MC_ARB_RAMCFG);
- cc_rb_backend_disable = RREG32(CC_RB_BACKEND_DISABLE);
- cc_gc_shader_array_config = RREG32(CC_GC_SHADER_ARRAY_CONFIG);
- cgts_tcc_disable = 0xffff0000;
- for (i = 0; i < rdev->config.si.max_texture_channel_caches; i++)
- cgts_tcc_disable &= ~(1 << (16 + i));
- gc_user_rb_backend_disable = RREG32(GC_USER_RB_BACKEND_DISABLE);
- gc_user_shader_array_config = RREG32(GC_USER_SHADER_ARRAY_CONFIG);
- cgts_user_tcc_disable = RREG32(CGTS_USER_TCC_DISABLE);
-
- rdev->config.si.num_shader_engines = rdev->config.si.max_shader_engines;
rdev->config.si.num_tile_pipes = rdev->config.si.max_tile_pipes;
- tmp = ((~gc_user_rb_backend_disable) & BACKEND_DISABLE_MASK) >> BACKEND_DISABLE_SHIFT;
- rdev->config.si.num_backends_per_se = r600_count_pipe_bits(tmp);
- tmp = (gc_user_rb_backend_disable & BACKEND_DISABLE_MASK) >> BACKEND_DISABLE_SHIFT;
- rdev->config.si.backend_disable_mask_per_asic =
- si_get_disable_mask_per_asic(rdev, tmp, SI_MAX_BACKENDS_PER_SE_MASK,
- rdev->config.si.num_shader_engines);
- rdev->config.si.backend_map =
- si_get_tile_pipe_to_backend_map(rdev, rdev->config.si.num_tile_pipes,
- rdev->config.si.num_backends_per_se *
- rdev->config.si.num_shader_engines,
- &rdev->config.si.backend_disable_mask_per_asic,
- rdev->config.si.num_shader_engines);
- tmp = ((~cgts_user_tcc_disable) & TCC_DISABLE_MASK) >> TCC_DISABLE_SHIFT;
- rdev->config.si.num_texture_channel_caches = r600_count_pipe_bits(tmp);
rdev->config.si.mem_max_burst_length_bytes = 256;
tmp = (mc_arb_ramcfg & NOOFCOLS_MASK) >> NOOFCOLS_SHIFT;
rdev->config.si.mem_row_size_in_kb = (4 * (1 << (8 + tmp))) / 1024;
rdev->config.si.num_gpus = 1;
rdev->config.si.multi_gpu_tile_size = 64;
- gb_addr_config = 0;
- switch (rdev->config.si.num_tile_pipes) {
- case 1:
- gb_addr_config |= NUM_PIPES(0);
- break;
- case 2:
- gb_addr_config |= NUM_PIPES(1);
- break;
- case 4:
- gb_addr_config |= NUM_PIPES(2);
- break;
- case 8:
- default:
- gb_addr_config |= NUM_PIPES(3);
- break;
- }
-
- tmp = (rdev->config.si.mem_max_burst_length_bytes / 256) - 1;
- gb_addr_config |= PIPE_INTERLEAVE_SIZE(tmp);
- gb_addr_config |= NUM_SHADER_ENGINES(rdev->config.si.num_shader_engines - 1);
- tmp = (rdev->config.si.shader_engine_tile_size / 16) - 1;
- gb_addr_config |= SHADER_ENGINE_TILE_SIZE(tmp);
- switch (rdev->config.si.num_gpus) {
- case 1:
- default:
- gb_addr_config |= NUM_GPUS(0);
- break;
- case 2:
- gb_addr_config |= NUM_GPUS(1);
- break;
- case 4:
- gb_addr_config |= NUM_GPUS(2);
- break;
- }
- switch (rdev->config.si.multi_gpu_tile_size) {
- case 16:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(0);
- break;
- case 32:
- default:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(1);
- break;
- case 64:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(2);
- break;
- case 128:
- gb_addr_config |= MULTI_GPU_TILE_SIZE(3);
- break;
- }
+ /* fix up row size */
+ gb_addr_config &= ~ROW_SIZE_MASK;
switch (rdev->config.si.mem_row_size_in_kb) {
case 1:
default:
break;
}
- tmp = (gb_addr_config & NUM_PIPES_MASK) >> NUM_PIPES_SHIFT;
- rdev->config.si.num_tile_pipes = (1 << tmp);
- tmp = (gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT;
- rdev->config.si.mem_max_burst_length_bytes = (tmp + 1) * 256;
- tmp = (gb_addr_config & NUM_SHADER_ENGINES_MASK) >> NUM_SHADER_ENGINES_SHIFT;
- rdev->config.si.num_shader_engines = tmp + 1;
- tmp = (gb_addr_config & NUM_GPUS_MASK) >> NUM_GPUS_SHIFT;
- rdev->config.si.num_gpus = tmp + 1;
- tmp = (gb_addr_config & MULTI_GPU_TILE_SIZE_MASK) >> MULTI_GPU_TILE_SIZE_SHIFT;
- rdev->config.si.multi_gpu_tile_size = 1 << tmp;
- tmp = (gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT;
- rdev->config.si.mem_row_size_in_kb = 1 << tmp;
-
- gb_backend_map =
- si_get_tile_pipe_to_backend_map(rdev, rdev->config.si.num_tile_pipes,
- rdev->config.si.num_backends_per_se *
- rdev->config.si.num_shader_engines,
- &rdev->config.si.backend_disable_mask_per_asic,
- rdev->config.si.num_shader_engines);
-
/* setup tiling info dword. gb_addr_config is not adequate since it does
* not have bank info, so create a custom tiling dword.
* bits 3:0 num_pipes
rdev->config.si.tile_config |= (3 << 0);
break;
}
- rdev->config.si.tile_config |=
- ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4;
+ if ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT)
+ rdev->config.si.tile_config |= 1 << 4;
+ else
+ rdev->config.si.tile_config |= 0 << 4;
rdev->config.si.tile_config |=
((gb_addr_config & PIPE_INTERLEAVE_SIZE_MASK) >> PIPE_INTERLEAVE_SIZE_SHIFT) << 8;
rdev->config.si.tile_config |=
((gb_addr_config & ROW_SIZE_MASK) >> ROW_SIZE_SHIFT) << 12;
- rdev->config.si.backend_map = gb_backend_map;
WREG32(GB_ADDR_CONFIG, gb_addr_config);
WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
WREG32(HDP_ADDR_CONFIG, gb_addr_config);
- /* primary versions */
- WREG32(CC_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(CC_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(CC_GC_SHADER_ARRAY_CONFIG, cc_gc_shader_array_config);
-
- WREG32(CGTS_TCC_DISABLE, cgts_tcc_disable);
+ si_tiling_mode_table_init(rdev);
- /* user versions */
- WREG32(GC_USER_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(GC_USER_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
- WREG32(GC_USER_SHADER_ARRAY_CONFIG, cc_gc_shader_array_config);
+ si_setup_rb(rdev, rdev->config.si.max_shader_engines,
+ rdev->config.si.max_sh_per_se,
+ rdev->config.si.max_backends_per_se);
- WREG32(CGTS_USER_TCC_DISABLE, cgts_tcc_disable);
+ si_setup_spi(rdev, rdev->config.si.max_shader_engines,
+ rdev->config.si.max_sh_per_se,
+ rdev->config.si.max_cu_per_sh);
- si_tiling_mode_table_init(rdev);
/* set HW defaults for 3D engine */
WREG32(CP_QUEUE_THRESHOLDS, (ROQ_IB1_START(0x16) |
#ifndef SI_H
#define SI_H
+#define TAHITI_RB_BITMAP_WIDTH_PER_SH 2
+
+#define TAHITI_GB_ADDR_CONFIG_GOLDEN 0x12011003
+#define VERDE_GB_ADDR_CONFIG_GOLDEN 0x12010002
+
#define CG_MULT_THERMAL_STATUS 0x714
#define ASIC_MAX_TEMP(x) ((x) << 0)
#define ASIC_MAX_TEMP_MASK 0x000001ff
#define SOFT_RESET_IA (1 << 15)
#define GRBM_GFX_INDEX 0x802C
+#define INSTANCE_INDEX(x) ((x) << 0)
+#define SH_INDEX(x) ((x) << 8)
+#define SE_INDEX(x) ((x) << 16)
+#define SH_BROADCAST_WRITES (1 << 29)
+#define INSTANCE_BROADCAST_WRITES (1 << 30)
+#define SE_BROADCAST_WRITES (1 << 31)
#define GRBM_INT_CNTL 0x8060
# define RDERR_INT_ENABLE (1 << 0)
#define VGT_TF_MEMORY_BASE 0x89B8
#define CC_GC_SHADER_ARRAY_CONFIG 0x89bc
+#define INACTIVE_CUS_MASK 0xFFFF0000
+#define INACTIVE_CUS_SHIFT 16
#define GC_USER_SHADER_ARRAY_CONFIG 0x89c0
#define PA_CL_ENHANCE 0x8A14
#define RLC_MC_CNTL 0xC344
#define RLC_UCODE_CNTL 0xC348
+#define PA_SC_RASTER_CONFIG 0x28350
+# define RASTER_CONFIG_RB_MAP_0 0
+# define RASTER_CONFIG_RB_MAP_1 1
+# define RASTER_CONFIG_RB_MAP_2 2
+# define RASTER_CONFIG_RB_MAP_3 3
+
#define VGT_EVENT_INITIATOR 0x28a90
# define SAMPLE_STREAMOUTSTATS1 (1 << 0)
# define SAMPLE_STREAMOUTSTATS2 (2 << 0)
(*destroy)(bo);
else
kfree(bo);
+ ttm_mem_global_free(mem_glob, acc_size);
return -EINVAL;
}
bo->destroy = destroy;
struct ttm_buffer_object **p_bo)
{
struct ttm_buffer_object *bo;
- struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
size_t acc_size;
int ret;
- acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
- ret = ttm_mem_global_alloc(mem_glob, acc_size, false, false);
- if (unlikely(ret != 0))
- return ret;
-
bo = kzalloc(sizeof(*bo), GFP_KERNEL);
-
- if (unlikely(bo == NULL)) {
- ttm_mem_global_free(mem_glob, acc_size);
+ if (unlikely(bo == NULL))
return -ENOMEM;
- }
+ acc_size = ttm_bo_acc_size(bdev, size, sizeof(struct ttm_buffer_object));
ret = ttm_bo_init(bdev, bo, size, type, placement, page_alignment,
buffer_start, interruptible,
persistent_swap_storage, acc_size, NULL, NULL);
return NULL;
}
+int vga_switcheroo_get_client_state(struct pci_dev *pdev)
+{
+ struct vga_switcheroo_client *client;
+
+ client = find_client_from_pci(&vgasr_priv.clients, pdev);
+ if (!client)
+ return VGA_SWITCHEROO_NOT_FOUND;
+ if (!vgasr_priv.active)
+ return VGA_SWITCHEROO_INIT;
+ return client->pwr_state;
+}
+EXPORT_SYMBOL(vga_switcheroo_get_client_state);
+
void vga_switcheroo_unregister_client(struct pci_dev *pdev)
{
struct vga_switcheroo_client *client;
vga_switchon(new_client);
vga_set_default_device(new_client->pdev);
- set_audio_state(new_client->id, VGA_SWITCHEROO_ON);
-
return 0;
}
active->active = false;
+ set_audio_state(active->id, VGA_SWITCHEROO_OFF);
+
if (new_client->fb_info) {
struct fb_event event;
event.info = new_client->fb_info;
if (new_client->ops->reprobe)
new_client->ops->reprobe(new_client->pdev);
- set_audio_state(active->id, VGA_SWITCHEROO_OFF);
-
if (active->pwr_state == VGA_SWITCHEROO_ON)
vga_switchoff(active);
+ set_audio_state(new_client->id, VGA_SWITCHEROO_ON);
+
new_client->active = true;
return 0;
}
/* pwr off the device not in use */
if (strncmp(usercmd, "OFF", 3) == 0) {
list_for_each_entry(client, &vgasr_priv.clients, list) {
- if (client->active)
+ if (client->active || client_is_audio(client))
continue;
+ set_audio_state(client->id, VGA_SWITCHEROO_OFF);
if (client->pwr_state == VGA_SWITCHEROO_ON)
vga_switchoff(client);
}
/* pwr on the device not in use */
if (strncmp(usercmd, "ON", 2) == 0) {
list_for_each_entry(client, &vgasr_priv.clients, list) {
- if (client->active)
+ if (client->active || client_is_audio(client))
continue;
if (client->pwr_state == VGA_SWITCHEROO_OFF)
vga_switchon(client);
+ set_audio_state(client->id, VGA_SWITCHEROO_ON);
}
goto out;
}
This driver can also be built as a module. If so, the module
will be called i2c-mux-pca954x.
+config I2C_MUX_PINCTRL
+ tristate "pinctrl-based I2C multiplexer"
+ depends on PINCTRL
+ help
+ If you say yes to this option, support will be included for an I2C
+ multiplexer that uses the pinctrl subsystem, i.e. pin multiplexing.
+ This is useful for SoCs whose I2C module's signals can be routed to
+ different sets of pins at run-time.
+
+ This driver can also be built as a module. If so, the module will be
+ called pinctrl-i2cmux.
+
endmenu
obj-$(CONFIG_I2C_MUX_GPIO) += i2c-mux-gpio.o
obj-$(CONFIG_I2C_MUX_PCA9541) += i2c-mux-pca9541.o
obj-$(CONFIG_I2C_MUX_PCA954x) += i2c-mux-pca954x.o
+obj-$(CONFIG_I2C_MUX_PINCTRL) += i2c-mux-pinctrl.o
ccflags-$(CONFIG_I2C_DEBUG_BUS) := -DDEBUG
--- /dev/null
+/*
+ * I2C multiplexer using pinctrl API
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/i2c.h>
+#include <linux/i2c-mux.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_i2c.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/i2c-mux-pinctrl.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+struct i2c_mux_pinctrl {
+ struct device *dev;
+ struct i2c_mux_pinctrl_platform_data *pdata;
+ struct pinctrl *pinctrl;
+ struct pinctrl_state **states;
+ struct pinctrl_state *state_idle;
+ struct i2c_adapter *parent;
+ struct i2c_adapter **busses;
+};
+
+static int i2c_mux_pinctrl_select(struct i2c_adapter *adap, void *data,
+ u32 chan)
+{
+ struct i2c_mux_pinctrl *mux = data;
+
+ return pinctrl_select_state(mux->pinctrl, mux->states[chan]);
+}
+
+static int i2c_mux_pinctrl_deselect(struct i2c_adapter *adap, void *data,
+ u32 chan)
+{
+ struct i2c_mux_pinctrl *mux = data;
+
+ return pinctrl_select_state(mux->pinctrl, mux->state_idle);
+}
+
+#ifdef CONFIG_OF
+static int i2c_mux_pinctrl_parse_dt(struct i2c_mux_pinctrl *mux,
+ struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ int num_names, i, ret;
+ struct device_node *adapter_np;
+ struct i2c_adapter *adapter;
+
+ if (!np)
+ return 0;
+
+ mux->pdata = devm_kzalloc(&pdev->dev, sizeof(*mux->pdata), GFP_KERNEL);
+ if (!mux->pdata) {
+ dev_err(mux->dev,
+ "Cannot allocate i2c_mux_pinctrl_platform_data\n");
+ return -ENOMEM;
+ }
+
+ num_names = of_property_count_strings(np, "pinctrl-names");
+ if (num_names < 0) {
+ dev_err(mux->dev, "Cannot parse pinctrl-names: %d\n",
+ num_names);
+ return num_names;
+ }
+
+ mux->pdata->pinctrl_states = devm_kzalloc(&pdev->dev,
+ sizeof(*mux->pdata->pinctrl_states) * num_names,
+ GFP_KERNEL);
+ if (!mux->pdata->pinctrl_states) {
+ dev_err(mux->dev, "Cannot allocate pinctrl_states\n");
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < num_names; i++) {
+ ret = of_property_read_string_index(np, "pinctrl-names", i,
+ &mux->pdata->pinctrl_states[mux->pdata->bus_count]);
+ if (ret < 0) {
+ dev_err(mux->dev, "Cannot parse pinctrl-names: %d\n",
+ ret);
+ return ret;
+ }
+ if (!strcmp(mux->pdata->pinctrl_states[mux->pdata->bus_count],
+ "idle")) {
+ if (i != num_names - 1) {
+ dev_err(mux->dev, "idle state must be last\n");
+ return -EINVAL;
+ }
+ mux->pdata->pinctrl_state_idle = "idle";
+ } else {
+ mux->pdata->bus_count++;
+ }
+ }
+
+ adapter_np = of_parse_phandle(np, "i2c-parent", 0);
+ if (!adapter_np) {
+ dev_err(mux->dev, "Cannot parse i2c-parent\n");
+ return -ENODEV;
+ }
+ adapter = of_find_i2c_adapter_by_node(adapter_np);
+ if (!adapter) {
+ dev_err(mux->dev, "Cannot find parent bus\n");
+ return -ENODEV;
+ }
+ mux->pdata->parent_bus_num = i2c_adapter_id(adapter);
+ put_device(&adapter->dev);
+
+ return 0;
+}
+#else
+static inline int i2c_mux_pinctrl_parse_dt(struct i2c_mux_pinctrl *mux,
+ struct platform_device *pdev)
+{
+ return 0;
+}
+#endif
+
+static int __devinit i2c_mux_pinctrl_probe(struct platform_device *pdev)
+{
+ struct i2c_mux_pinctrl *mux;
+ int (*deselect)(struct i2c_adapter *, void *, u32);
+ int i, ret;
+
+ mux = devm_kzalloc(&pdev->dev, sizeof(*mux), GFP_KERNEL);
+ if (!mux) {
+ dev_err(&pdev->dev, "Cannot allocate i2c_mux_pinctrl\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+ platform_set_drvdata(pdev, mux);
+
+ mux->dev = &pdev->dev;
+
+ mux->pdata = pdev->dev.platform_data;
+ if (!mux->pdata) {
+ ret = i2c_mux_pinctrl_parse_dt(mux, pdev);
+ if (ret < 0)
+ goto err;
+ }
+ if (!mux->pdata) {
+ dev_err(&pdev->dev, "Missing platform data\n");
+ ret = -ENODEV;
+ goto err;
+ }
+
+ mux->states = devm_kzalloc(&pdev->dev,
+ sizeof(*mux->states) * mux->pdata->bus_count,
+ GFP_KERNEL);
+ if (!mux->states) {
+ dev_err(&pdev->dev, "Cannot allocate states\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ mux->busses = devm_kzalloc(&pdev->dev,
+ sizeof(mux->busses) * mux->pdata->bus_count,
+ GFP_KERNEL);
+ if (!mux->states) {
+ dev_err(&pdev->dev, "Cannot allocate busses\n");
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ mux->pinctrl = devm_pinctrl_get(&pdev->dev);
+ if (IS_ERR(mux->pinctrl)) {
+ ret = PTR_ERR(mux->pinctrl);
+ dev_err(&pdev->dev, "Cannot get pinctrl: %d\n", ret);
+ goto err;
+ }
+ for (i = 0; i < mux->pdata->bus_count; i++) {
+ mux->states[i] = pinctrl_lookup_state(mux->pinctrl,
+ mux->pdata->pinctrl_states[i]);
+ if (IS_ERR(mux->states[i])) {
+ ret = PTR_ERR(mux->states[i]);
+ dev_err(&pdev->dev,
+ "Cannot look up pinctrl state %s: %d\n",
+ mux->pdata->pinctrl_states[i], ret);
+ goto err;
+ }
+ }
+ if (mux->pdata->pinctrl_state_idle) {
+ mux->state_idle = pinctrl_lookup_state(mux->pinctrl,
+ mux->pdata->pinctrl_state_idle);
+ if (IS_ERR(mux->state_idle)) {
+ ret = PTR_ERR(mux->state_idle);
+ dev_err(&pdev->dev,
+ "Cannot look up pinctrl state %s: %d\n",
+ mux->pdata->pinctrl_state_idle, ret);
+ goto err;
+ }
+
+ deselect = i2c_mux_pinctrl_deselect;
+ } else {
+ deselect = NULL;
+ }
+
+ mux->parent = i2c_get_adapter(mux->pdata->parent_bus_num);
+ if (!mux->parent) {
+ dev_err(&pdev->dev, "Parent adapter (%d) not found\n",
+ mux->pdata->parent_bus_num);
+ ret = -ENODEV;
+ goto err;
+ }
+
+ for (i = 0; i < mux->pdata->bus_count; i++) {
+ u32 bus = mux->pdata->base_bus_num ?
+ (mux->pdata->base_bus_num + i) : 0;
+
+ mux->busses[i] = i2c_add_mux_adapter(mux->parent, &pdev->dev,
+ mux, bus, i,
+ i2c_mux_pinctrl_select,
+ deselect);
+ if (!mux->busses[i]) {
+ ret = -ENODEV;
+ dev_err(&pdev->dev, "Failed to add adapter %d\n", i);
+ goto err_del_adapter;
+ }
+ }
+
+ return 0;
+
+err_del_adapter:
+ for (; i > 0; i--)
+ i2c_del_mux_adapter(mux->busses[i - 1]);
+ i2c_put_adapter(mux->parent);
+err:
+ return ret;
+}
+
+static int __devexit i2c_mux_pinctrl_remove(struct platform_device *pdev)
+{
+ struct i2c_mux_pinctrl *mux = platform_get_drvdata(pdev);
+ int i;
+
+ for (i = 0; i < mux->pdata->bus_count; i++)
+ i2c_del_mux_adapter(mux->busses[i]);
+
+ i2c_put_adapter(mux->parent);
+
+ return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id i2c_mux_pinctrl_of_match[] __devinitconst = {
+ { .compatible = "i2c-mux-pinctrl", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, i2c_mux_pinctrl_of_match);
+#endif
+
+static struct platform_driver i2c_mux_pinctrl_driver = {
+ .driver = {
+ .name = "i2c-mux-pinctrl",
+ .owner = THIS_MODULE,
+ .of_match_table = of_match_ptr(i2c_mux_pinctrl_of_match),
+ },
+ .probe = i2c_mux_pinctrl_probe,
+ .remove = __devexit_p(i2c_mux_pinctrl_remove),
+};
+module_platform_driver(i2c_mux_pinctrl_driver);
+
+MODULE_DESCRIPTION("pinctrl-based I2C multiplexer driver");
+MODULE_AUTHOR("Stephen Warren <swarren@nvidia.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:i2c-mux-pinctrl");
struct net_device *pdev;
pdev = ip_dev_find(&init_net, peer_ip);
+ if (!pdev) {
+ err = -ENODEV;
+ goto out;
+ }
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, 0);
if (!ep->l2t)
props->max_mr_size = ~0ull;
props->page_size_cap = dev->dev->caps.page_size_cap;
props->max_qp = dev->dev->caps.num_qps - dev->dev->caps.reserved_qps;
- props->max_qp_wr = dev->dev->caps.max_wqes;
+ props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE;
props->max_sge = min(dev->dev->caps.max_sq_sg,
dev->dev->caps.max_rq_sg);
props->max_cq = dev->dev->caps.num_cqs - dev->dev->caps.reserved_cqs;
int total_eqs = 0;
int i, j, eq;
- /* Init eq table */
- ibdev->eq_table = NULL;
- ibdev->eq_added = 0;
-
- /* Legacy mode? */
- if (dev->caps.comp_pool == 0)
+ /* Legacy mode or comp_pool is not large enough */
+ if (dev->caps.comp_pool == 0 ||
+ dev->caps.num_ports > dev->caps.comp_pool)
return;
eq_per_port = rounddown_pow_of_two(dev->caps.comp_pool/
static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
{
int i;
- int total_eqs;
+
+ /* no additional eqs were added */
+ if (!ibdev->eq_table)
+ return;
/* Reset the advertised EQ number */
ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
mlx4_release_eq(dev, ibdev->eq_table[i]);
}
- total_eqs = dev->caps.num_comp_vectors + ibdev->eq_added;
- memset(ibdev->eq_table, 0, total_eqs * sizeof(int));
kfree(ibdev->eq_table);
-
- ibdev->eq_table = NULL;
- ibdev->eq_added = 0;
}
static void *mlx4_ib_add(struct mlx4_dev *dev)
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
+enum {
+ MLX4_IB_SQ_MIN_WQE_SHIFT = 6,
+ MLX4_IB_MAX_HEADROOM = 2048
+};
+
+#define MLX4_IB_SQ_HEADROOM(shift) ((MLX4_IB_MAX_HEADROOM >> (shift)) + 1)
+#define MLX4_IB_SQ_MAX_SPARE (MLX4_IB_SQ_HEADROOM(MLX4_IB_SQ_MIN_WQE_SHIFT))
+
struct mlx4_ib_ucontext {
struct ib_ucontext ibucontext;
struct mlx4_uar uar;
int is_user, int has_rq, struct mlx4_ib_qp *qp)
{
/* Sanity check RQ size before proceeding */
- if (cap->max_recv_wr > dev->dev->caps.max_wqes ||
- cap->max_recv_sge > dev->dev->caps.max_rq_sg)
+ if (cap->max_recv_wr > dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE ||
+ cap->max_recv_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg))
return -EINVAL;
if (!has_rq) {
qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg));
}
- cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt;
- cap->max_recv_sge = qp->rq.max_gs;
+ /* leave userspace return values as they were, so as not to break ABI */
+ if (is_user) {
+ cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt;
+ cap->max_recv_sge = qp->rq.max_gs;
+ } else {
+ cap->max_recv_wr = qp->rq.max_post =
+ min(dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE, qp->rq.wqe_cnt);
+ cap->max_recv_sge = min(qp->rq.max_gs,
+ min(dev->dev->caps.max_sq_sg,
+ dev->dev->caps.max_rq_sg));
+ }
return 0;
}
int s;
/* Sanity check SQ size before proceeding */
- if (cap->max_send_wr > dev->dev->caps.max_wqes ||
- cap->max_send_sge > dev->dev->caps.max_sq_sg ||
+ if (cap->max_send_wr > (dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE) ||
+ cap->max_send_sge > min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg) ||
cap->max_inline_data + send_wqe_overhead(type, qp->flags) +
sizeof (struct mlx4_wqe_inline_seg) > dev->dev->caps.max_sq_desc_sz)
return -EINVAL;
u32 entry_size;
u32 max_cnt;
u32 max_wqe_idx;
- u32 free_delta;
u16 dbid; /* qid, where to ring the doorbell. */
u32 len;
dma_addr_t pa;
u32 rsvd1;
u32 num_wqe_allocated;
u32 num_rqe_allocated;
- u32 free_wqe_delta;
- u32 free_rqe_delta;
u32 db_sq_offset;
u32 db_rq_offset;
u32 db_shift;
u32 db_rq_offset;
u32 db_shift;
- u32 free_rqe_delta;
- u32 rsvd2;
+ u64 rsvd2;
u64 rsvd3;
} __packed;
break;
case OCRDMA_SRQ_LIMIT_EVENT:
ib_evt.element.srq = &qp->srq->ibsrq;
- ib_evt.event = IB_EVENT_QP_LAST_WQE_REACHED;
+ ib_evt.event = IB_EVENT_SRQ_LIMIT_REACHED;
srq_event = 1;
qp_event = 0;
break;
max_wqe_allocated = 1 << max_wqe_allocated;
max_rqe_allocated = 1 << ((u16)rsp->max_wqe_rqe);
- if (qp->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) {
- qp->sq.free_delta = 0;
- qp->rq.free_delta = 1;
- } else
- qp->sq.free_delta = 1;
-
qp->sq.max_cnt = max_wqe_allocated;
qp->sq.max_wqe_idx = max_wqe_allocated - 1;
if (!attrs->srq) {
qp->rq.max_cnt = max_rqe_allocated;
qp->rq.max_wqe_idx = max_rqe_allocated - 1;
- qp->rq.free_delta = 1;
}
}
*******************************************************************/
#include <linux/module.h>
-#include <linux/version.h>
#include <linux/idr.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_user_verbs.h>
uresp.db_rq_offset = OCRDMA_DB_RQ_OFFSET;
uresp.db_shift = 16;
}
- uresp.free_wqe_delta = qp->sq.free_delta;
- uresp.free_rqe_delta = qp->rq.free_delta;
if (qp->dpp_enabled) {
uresp.dpp_credit = dpp_credit_lmt;
free_cnt = (q->max_cnt - q->head) + q->tail;
else
free_cnt = q->tail - q->head;
- if (q->free_delta)
- free_cnt -= q->free_delta;
return free_cnt;
}
(srq->pd->id * srq->dev->nic_info.db_page_size);
uresp.db_page_size = srq->dev->nic_info.db_page_size;
uresp.num_rqe_allocated = srq->rq.max_cnt;
- uresp.free_rqe_delta = 1;
if (srq->dev->nic_info.dev_family == OCRDMA_GEN2_FAMILY) {
uresp.db_rq_offset = OCRDMA_DB_GEN2_RQ1_OFFSET;
uresp.db_shift = 24;
#ifndef __OCRDMA_VERBS_H__
#define __OCRDMA_VERBS_H__
-#include <linux/version.h>
int ocrdma_post_send(struct ib_qp *, struct ib_send_wr *,
struct ib_send_wr **bad_wr);
int ocrdma_post_recv(struct ib_qp *, struct ib_recv_wr *,
spin_unlock_irqrestore(&iommu->lock, flags);
}
-static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u32 head)
+static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
{
struct amd_iommu_fault fault;
- volatile u64 *raw;
- int i;
INC_STATS_COUNTER(pri_requests);
- raw = (u64 *)(iommu->ppr_log + head);
-
- /*
- * Hardware bug: Interrupt may arrive before the entry is written to
- * memory. If this happens we need to wait for the entry to arrive.
- */
- for (i = 0; i < LOOP_TIMEOUT; ++i) {
- if (PPR_REQ_TYPE(raw[0]) != 0)
- break;
- udelay(1);
- }
-
if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
pr_err_ratelimited("AMD-Vi: Unknown PPR request received\n");
return;
fault.tag = PPR_TAG(raw[0]);
fault.flags = PPR_FLAGS(raw[0]);
- /*
- * To detect the hardware bug we need to clear the entry
- * to back to zero.
- */
- raw[0] = raw[1] = 0;
-
atomic_notifier_call_chain(&ppr_notifier, 0, &fault);
}
if (iommu->ppr_log == NULL)
return;
+ /* enable ppr interrupts again */
+ writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
spin_lock_irqsave(&iommu->lock, flags);
head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
while (head != tail) {
+ volatile u64 *raw;
+ u64 entry[2];
+ int i;
- /* Handle PPR entry */
- iommu_handle_ppr_entry(iommu, head);
+ raw = (u64 *)(iommu->ppr_log + head);
+
+ /*
+ * Hardware bug: Interrupt may arrive before the entry is
+ * written to memory. If this happens we need to wait for the
+ * entry to arrive.
+ */
+ for (i = 0; i < LOOP_TIMEOUT; ++i) {
+ if (PPR_REQ_TYPE(raw[0]) != 0)
+ break;
+ udelay(1);
+ }
+
+ /* Avoid memcpy function-call overhead */
+ entry[0] = raw[0];
+ entry[1] = raw[1];
- /* Update and refresh ring-buffer state*/
+ /*
+ * To detect the hardware bug we need to clear the entry
+ * back to zero.
+ */
+ raw[0] = raw[1] = 0UL;
+
+ /* Update head pointer of hardware ring-buffer */
head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE;
writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+
+ /*
+ * Release iommu->lock because ppr-handling might need to
+ * re-aquire it
+ */
+ spin_unlock_irqrestore(&iommu->lock, flags);
+
+ /* Handle PPR entry */
+ iommu_handle_ppr_entry(iommu, entry);
+
+ spin_lock_irqsave(&iommu->lock, flags);
+
+ /* Refresh ring-buffer information */
+ head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
}
- /* enable ppr interrupts again */
- writel(MMIO_STATUS_PPR_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET);
-
spin_unlock_irqrestore(&iommu->lock, flags);
}
if (!iommu->dev)
return 1;
+ iommu->root_pdev = pci_get_bus_and_slot(iommu->dev->bus->number,
+ PCI_DEVFN(0, 0));
+
iommu->cap_ptr = h->cap_ptr;
iommu->pci_seg = h->pci_seg;
iommu->mmio_phys = h->mmio_phys;
{
int i, j;
u32 ioc_feature_control;
- struct pci_dev *pdev = NULL;
+ struct pci_dev *pdev = iommu->root_pdev;
/* RD890 BIOSes may not have completely reconfigured the iommu */
- if (!is_rd890_iommu(iommu->dev))
+ if (!is_rd890_iommu(iommu->dev) || !pdev)
return;
/*
* First, we need to ensure that the iommu is enabled. This is
* controlled by a register in the northbridge
*/
- pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0));
-
- if (!pdev)
- return;
/* Select Northbridge indirect register 0x75 and enable writing */
pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
if (!(ioc_feature_control & 0x1))
pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
- pci_dev_put(pdev);
-
/* Restore the iommu BAR */
pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
iommu->stored_addr_lo);
/* Pointer to PCI device of this IOMMU */
struct pci_dev *dev;
+ /* Cache pdev to root device for resume quirks */
+ struct pci_dev *root_pdev;
+
/* physical address of MMIO space */
u64 mmio_phys;
/* virtual address of MMIO space */
config LEDS_ASIC3
bool "LED support for the HTC ASIC3"
- depends on LEDS_CLASS
+ depends on LEDS_CLASS=y
depends on MFD_ASIC3
default y
help
config LEDS_RENESAS_TPU
bool "LED support for Renesas TPU"
- depends on LEDS_CLASS && HAVE_CLK && GENERIC_GPIO
+ depends on LEDS_CLASS=y && HAVE_CLK && GENERIC_GPIO
help
This option enables build of the LED TPU platform driver,
suitable to drive any TPU channel on newer Renesas SoCs.
led_cdev->brightness = led_cdev->brightness_get(led_cdev);
}
-static ssize_t led_brightness_show(struct device *dev,
+static ssize_t led_brightness_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct led_classdev *led_cdev = dev_get_drvdata(dev);
if (!led_cdev->blink_brightness)
led_cdev->blink_brightness = led_cdev->max_brightness;
- if (led_get_trigger_data(led_cdev) &&
- delay_on == led_cdev->blink_delay_on &&
- delay_off == led_cdev->blink_delay_off)
- return;
-
- led_stop_software_blink(led_cdev);
-
led_cdev->blink_delay_on = delay_on;
led_cdev->blink_delay_off = delay_off;
err = -EINVAL;
spin_lock_init(&conf->device_lock);
rdev_for_each(rdev, mddev) {
+ struct request_queue *q;
int disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
if (disk->rdev)
goto abort;
disk->rdev = rdev;
+ q = bdev_get_queue(rdev->bdev);
+ if (q->merge_bvec_fn)
+ mddev->merge_check_needed = 1;
disk->head_position = 0;
}
rdev_for_each(rdev, mddev) {
long long diff;
+ struct request_queue *q;
disk_idx = rdev->raid_disk;
if (disk_idx < 0)
goto out_free_conf;
disk->rdev = rdev;
}
+ q = bdev_get_queue(rdev->bdev);
+ if (q->merge_bvec_fn)
+ mddev->merge_check_needed = 1;
diff = (rdev->new_data_offset - rdev->data_offset);
if (!mddev->reshape_backwards)
diff = -diff;
*/
int ubi_debugfs_init(void)
{
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
dfs_rootdir = debugfs_create_dir("ubi", NULL);
if (IS_ERR_OR_NULL(dfs_rootdir)) {
int err = dfs_rootdir ? -ENODEV : PTR_ERR(dfs_rootdir);
*/
void ubi_debugfs_exit(void)
{
- debugfs_remove(dfs_rootdir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove(dfs_rootdir);
}
/* Read an UBI debugfs file */
struct dentry *dent;
struct ubi_debug_info *d = ubi->dbg;
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
n = snprintf(d->dfs_dir_name, UBI_DFS_DIR_LEN + 1, UBI_DFS_DIR_NAME,
ubi->ubi_num);
if (n == UBI_DFS_DIR_LEN) {
*/
void ubi_debugfs_exit_dev(struct ubi_device *ubi)
{
- debugfs_remove_recursive(ubi->dbg->dfs_dir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove_recursive(ubi->dbg->dfs_dir);
}
dbg_wl("flush pending work for LEB %d:%d (%d pending works)",
vol_id, lnum, ubi->works_count);
- down_write(&ubi->work_sem);
while (found) {
struct ubi_work *wrk;
found = 0;
+ down_read(&ubi->work_sem);
spin_lock(&ubi->wl_lock);
list_for_each_entry(wrk, &ubi->works, list) {
if ((vol_id == UBI_ALL || wrk->vol_id == vol_id) &&
spin_unlock(&ubi->wl_lock);
err = wrk->func(ubi, wrk, 0);
- if (err)
- goto out;
+ if (err) {
+ up_read(&ubi->work_sem);
+ return err;
+ }
+
spin_lock(&ubi->wl_lock);
found = 1;
break;
}
}
spin_unlock(&ubi->wl_lock);
+ up_read(&ubi->work_sem);
}
-out:
+ /*
+ * Make sure all the works which have been done in parallel are
+ * finished.
+ */
+ down_write(&ubi->work_sem);
up_write(&ubi->work_sem);
+
return err;
}
out:
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
return NETDEV_TX_OK;
}
}
+ read_unlock(&bond->curr_slave_lock);
+
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
- read_unlock(&bond->curr_slave_lock);
-
return NETDEV_TX_OK;
}
out:
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
return NETDEV_TX_OK;
res = bond_dev_queue_xmit(bond, skb,
bond->curr_active_slave->dev);
+ read_unlock(&bond->curr_slave_lock);
+
if (res)
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
-
- read_unlock(&bond->curr_slave_lock);
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
if (res) {
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
return NETDEV_TX_OK;
res = bond_dev_queue_xmit(bond, skb2, tx_dev);
if (res) {
- dev_kfree_skb(skb2);
+ kfree_skb(skb2);
continue;
}
}
out:
if (res)
/* no suitable interface, frame not sent */
- dev_kfree_skb(skb);
+ kfree_skb(skb);
/* frame sent to all suitable interfaces */
return NETDEV_TX_OK;
pr_err("%s: Error: Unknown bonding mode %d\n",
dev->name, bond->params.mode);
WARN_ON_ONCE(1);
- dev_kfree_skb(skb);
+ kfree_skb(skb);
return NETDEV_TX_OK;
}
}
if (bond->slave_cnt)
ret = __bond_start_xmit(skb, dev);
else
- dev_kfree_skb(skb);
+ kfree_skb(skb);
read_unlock(&bond->lock);
priv->write_reg(priv, C_CAN_CTRL_REG,
CONTROL_ENABLE_AR);
- if (priv->can.ctrlmode & (CAN_CTRLMODE_LISTENONLY &
- CAN_CTRLMODE_LOOPBACK)) {
+ if ((priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) &&
+ (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)) {
/* loopback + silent mode : useful for hot self-test */
priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_EIE |
CONTROL_SIE | CONTROL_IE | CONTROL_TEST);
#include <linux/module.h>
#include <linux/moduleparam.h>
+#include <linux/stringify.h>
#include <linux/kernel.h>
#include <linux/timer.h>
#include <linux/errno.h>
#include "bnx2_fw.h"
#define DRV_MODULE_NAME "bnx2"
-#define DRV_MODULE_VERSION "2.2.1"
-#define DRV_MODULE_RELDATE "Dec 18, 2011"
+#define DRV_MODULE_VERSION "2.2.2"
+#define DRV_MODULE_RELDATE "June 16, 2012"
#define FW_MIPS_FILE_06 "bnx2/bnx2-mips-06-6.2.3.fw"
#define FW_RV2P_FILE_06 "bnx2/bnx2-rv2p-06-6.0.15.fw"
#define FW_MIPS_FILE_09 "bnx2/bnx2-mips-09-6.2.1b.fw"
bnx2_shmem_rd(bp, BNX2_BC_STATE_RESET_TYPE));
pr_cont(" condition[%08x]\n",
bnx2_shmem_rd(bp, BNX2_BC_STATE_CONDITION));
+ DP_SHMEM_LINE(bp, BNX2_BC_RESET_TYPE);
DP_SHMEM_LINE(bp, 0x3cc);
DP_SHMEM_LINE(bp, 0x3dc);
DP_SHMEM_LINE(bp, 0x3ec);
rtnl_unlock();
}
+#define BNX2_FTQ_ENTRY(ftq) { __stringify(ftq##FTQ_CTL), BNX2_##ftq##FTQ_CTL }
+
+static void
+bnx2_dump_ftq(struct bnx2 *bp)
+{
+ int i;
+ u32 reg, bdidx, cid, valid;
+ struct net_device *dev = bp->dev;
+ static const struct ftq_reg {
+ char *name;
+ u32 off;
+ } ftq_arr[] = {
+ BNX2_FTQ_ENTRY(RV2P_P),
+ BNX2_FTQ_ENTRY(RV2P_T),
+ BNX2_FTQ_ENTRY(RV2P_M),
+ BNX2_FTQ_ENTRY(TBDR_),
+ BNX2_FTQ_ENTRY(TDMA_),
+ BNX2_FTQ_ENTRY(TXP_),
+ BNX2_FTQ_ENTRY(TXP_),
+ BNX2_FTQ_ENTRY(TPAT_),
+ BNX2_FTQ_ENTRY(RXP_C),
+ BNX2_FTQ_ENTRY(RXP_),
+ BNX2_FTQ_ENTRY(COM_COMXQ_),
+ BNX2_FTQ_ENTRY(COM_COMTQ_),
+ BNX2_FTQ_ENTRY(COM_COMQ_),
+ BNX2_FTQ_ENTRY(CP_CPQ_),
+ };
+
+ netdev_err(dev, "<--- start FTQ dump --->\n");
+ for (i = 0; i < ARRAY_SIZE(ftq_arr); i++)
+ netdev_err(dev, "%s %08x\n", ftq_arr[i].name,
+ bnx2_reg_rd_ind(bp, ftq_arr[i].off));
+
+ netdev_err(dev, "CPU states:\n");
+ for (reg = BNX2_TXP_CPU_MODE; reg <= BNX2_CP_CPU_MODE; reg += 0x40000)
+ netdev_err(dev, "%06x mode %x state %x evt_mask %x pc %x pc %x instr %x\n",
+ reg, bnx2_reg_rd_ind(bp, reg),
+ bnx2_reg_rd_ind(bp, reg + 4),
+ bnx2_reg_rd_ind(bp, reg + 8),
+ bnx2_reg_rd_ind(bp, reg + 0x1c),
+ bnx2_reg_rd_ind(bp, reg + 0x1c),
+ bnx2_reg_rd_ind(bp, reg + 0x20));
+
+ netdev_err(dev, "<--- end FTQ dump --->\n");
+ netdev_err(dev, "<--- start TBDC dump --->\n");
+ netdev_err(dev, "TBDC free cnt: %ld\n",
+ REG_RD(bp, BNX2_TBDC_STATUS) & BNX2_TBDC_STATUS_FREE_CNT);
+ netdev_err(dev, "LINE CID BIDX CMD VALIDS\n");
+ for (i = 0; i < 0x20; i++) {
+ int j = 0;
+
+ REG_WR(bp, BNX2_TBDC_BD_ADDR, i);
+ REG_WR(bp, BNX2_TBDC_CAM_OPCODE,
+ BNX2_TBDC_CAM_OPCODE_OPCODE_CAM_READ);
+ REG_WR(bp, BNX2_TBDC_COMMAND, BNX2_TBDC_COMMAND_CMD_REG_ARB);
+ while ((REG_RD(bp, BNX2_TBDC_COMMAND) &
+ BNX2_TBDC_COMMAND_CMD_REG_ARB) && j < 100)
+ j++;
+
+ cid = REG_RD(bp, BNX2_TBDC_CID);
+ bdidx = REG_RD(bp, BNX2_TBDC_BIDX);
+ valid = REG_RD(bp, BNX2_TBDC_CAM_OPCODE);
+ netdev_err(dev, "%02x %06x %04lx %02x [%x]\n",
+ i, cid, bdidx & BNX2_TBDC_BDIDX_BDIDX,
+ bdidx >> 24, (valid >> 8) & 0x0ff);
+ }
+ netdev_err(dev, "<--- end TBDC dump --->\n");
+}
+
static void
bnx2_dump_state(struct bnx2 *bp)
{
{
struct bnx2 *bp = netdev_priv(dev);
+ bnx2_dump_ftq(bp);
bnx2_dump_state(bp);
bnx2_dump_mcp_state(bp);
else
strap = (val & BNX2_MISC_DUAL_MEDIA_CTRL_PHY_CTRL_STRAP) >> 8;
- if (PCI_FUNC(bp->pdev->devfn) == 0) {
+ if (bp->func == 0) {
switch (strap) {
case 0x4:
case 0x5:
reg = bnx2_reg_rd_ind(bp, BNX2_SHM_HDR_SIGNATURE);
+ if (bnx2_reg_rd_ind(bp, BNX2_MCP_TOE_ID) & BNX2_MCP_TOE_ID_FUNCTION_ID)
+ bp->func = 1;
+
if ((reg & BNX2_SHM_HDR_SIGNATURE_SIG_MASK) ==
BNX2_SHM_HDR_SIGNATURE_SIG) {
- u32 off = PCI_FUNC(pdev->devfn) << 2;
+ u32 off = bp->func << 2;
bp->shmem_base = bnx2_reg_rd_ind(bp, BNX2_SHM_HDR_ADDR_0 + off);
} else
#define BNX2_TBDR_FTQ_CTL_CUR_DEPTH (0x3ffL<<22)
+/*
+ * tbdc definition
+ * offset: 0x5400
+ */
+#define BNX2_TBDC_COMMAND 0x5400
+#define BNX2_TBDC_COMMAND_CMD_ENABLED (1UL<<0)
+#define BNX2_TBDC_COMMAND_CMD_FLUSH (1UL<<1)
+#define BNX2_TBDC_COMMAND_CMD_SOFT_RST (1UL<<2)
+#define BNX2_TBDC_COMMAND_CMD_REG_ARB (1UL<<3)
+#define BNX2_TBDC_COMMAND_WRCHK_RANGE_ERROR (1UL<<4)
+#define BNX2_TBDC_COMMAND_WRCHK_ALL_ONES_ERROR (1UL<<5)
+#define BNX2_TBDC_COMMAND_WRCHK_ALL_ZEROS_ERROR (1UL<<6)
+#define BNX2_TBDC_COMMAND_WRCHK_ANY_ONES_ERROR (1UL<<7)
+#define BNX2_TBDC_COMMAND_WRCHK_ANY_ZEROS_ERROR (1UL<<8)
+
+#define BNX2_TBDC_STATUS 0x5404
+#define BNX2_TBDC_STATUS_FREE_CNT (0x3fUL<<0)
+
+#define BNX2_TBDC_BD_ADDR 0x5424
+
+#define BNX2_TBDC_BIDX 0x542c
+#define BNX2_TBDC_BDIDX_BDIDX (0xffffUL<<0)
+#define BNX2_TBDC_BDIDX_CMD (0xffUL<<24)
+
+#define BNX2_TBDC_CID 0x5430
+
+#define BNX2_TBDC_CAM_OPCODE 0x5434
+#define BNX2_TBDC_CAM_OPCODE_OPCODE (0x7UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_SEARCH (0UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_CACHE_WRITE (1UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_INVALIDATE (2UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_CAM_WRITE (4UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_CAM_READ (5UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_RAM_WRITE (6UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_OPCODE_RAM_READ (7UL<<0)
+#define BNX2_TBDC_CAM_OPCODE_SMASK_BDIDX (1UL<<4)
+#define BNX2_TBDC_CAM_OPCODE_SMASK_CID (1UL<<5)
+#define BNX2_TBDC_CAM_OPCODE_SMASK_CMD (1UL<<6)
+#define BNX2_TBDC_CAM_OPCODE_WMT_FAILED (1UL<<7)
+#define BNX2_TBDC_CAM_OPCODE_CAM_VALIDS (0xffUL<<8)
+
/*
* tdma_reg definition
struct bnx2_irq irq_tbl[BNX2_MAX_MSIX_VEC];
int irq_nvecs;
+ u8 func;
+
u8 num_tx_rings;
u8 num_rx_rings;
#define BNX2_BC_STATE_RESET_TYPE_VALUE(msg) (BNX2_BC_STATE_RESET_TYPE_SIG | \
(msg))
+#define BNX2_BC_RESET_TYPE 0x000001c0
+
#define BNX2_BC_STATE 0x000001c4
#define BNX2_BC_STATE_ERR_MASK 0x0000ff00
#define BNX2_BC_STATE_SIGN 0x42530000
* (you will need to reboot afterwards) */
/* #define BNX2X_STOP_ON_ERROR */
-#define DRV_MODULE_VERSION "1.72.50-0"
-#define DRV_MODULE_RELDATE "2012/04/23"
+#define DRV_MODULE_VERSION "1.72.51-0"
+#define DRV_MODULE_RELDATE "2012/06/18"
#define BNX2X_BC_VER 0x040200
#if defined(CONFIG_DCB)
BNX2X_MAX_CNIC_ETH_CL_ID_IDX,
};
-#define BNX2X_CNIC_START_ETH_CID 48
-enum {
+#define BNX2X_CNIC_START_ETH_CID(bp) (BNX2X_NUM_NON_CNIC_QUEUES(bp) *\
+ (bp)->max_cos)
/* iSCSI L2 */
- BNX2X_ISCSI_ETH_CID = BNX2X_CNIC_START_ETH_CID,
+#define BNX2X_ISCSI_ETH_CID(bp) (BNX2X_CNIC_START_ETH_CID(bp))
/* FCoE L2 */
- BNX2X_FCOE_ETH_CID,
-};
+#define BNX2X_FCOE_ETH_CID(bp) (BNX2X_CNIC_START_ETH_CID(bp) + 1)
/** Additional rings budgeting */
#ifdef BCM_CNIC
#define FIRST_TX_ONLY_COS_INDEX 1
#define FIRST_TX_COS_INDEX 0
-/* defines for decodeing the fastpath index and the cos index out of the
- * transmission queue index
- */
-#define MAX_TXQS_PER_COS FP_SB_MAX_E1x
-
-#define TXQ_TO_FP(txq_index) ((txq_index) % MAX_TXQS_PER_COS)
-#define TXQ_TO_COS(txq_index) ((txq_index) / MAX_TXQS_PER_COS)
-
/* rules for calculating the cids of tx-only connections */
-#define CID_TO_FP(cid) ((cid) % MAX_TXQS_PER_COS)
-#define CID_COS_TO_TX_ONLY_CID(cid, cos) (cid + cos * MAX_TXQS_PER_COS)
+#define CID_TO_FP(cid, bp) ((cid) % BNX2X_NUM_NON_CNIC_QUEUES(bp))
+#define CID_COS_TO_TX_ONLY_CID(cid, cos, bp) \
+ (cid + cos * BNX2X_NUM_NON_CNIC_QUEUES(bp))
/* fp index inside class of service range */
-#define FP_COS_TO_TXQ(fp, cos) ((fp)->index + cos * MAX_TXQS_PER_COS)
-
-/*
- * 0..15 eth cos0
- * 16..31 eth cos1 if applicable
- * 32..47 eth cos2 If applicable
- * fcoe queue follows eth queues (16, 32, 48 depending on cos)
+#define FP_COS_TO_TXQ(fp, cos, bp) \
+ ((fp)->index + cos * BNX2X_NUM_NON_CNIC_QUEUES(bp))
+
+/* Indexes for transmission queues array:
+ * txdata for RSS i CoS j is at location i + (j * num of RSS)
+ * txdata for FCoE (if exist) is at location max cos * num of RSS
+ * txdata for FWD (if exist) is one location after FCoE
+ * txdata for OOO (if exist) is one location after FWD
*/
-#define MAX_ETH_TXQ_IDX(bp) (MAX_TXQS_PER_COS * (bp)->max_cos)
-#define FCOE_TXQ_IDX(bp) (MAX_ETH_TXQ_IDX(bp))
+enum {
+ FCOE_TXQ_IDX_OFFSET,
+ FWD_TXQ_IDX_OFFSET,
+ OOO_TXQ_IDX_OFFSET,
+};
+#define MAX_ETH_TXQ_IDX(bp) (BNX2X_NUM_NON_CNIC_QUEUES(bp) * (bp)->max_cos)
+#ifdef BCM_CNIC
+#define FCOE_TXQ_IDX(bp) (MAX_ETH_TXQ_IDX(bp) + FCOE_TXQ_IDX_OFFSET)
+#endif
/* fast path */
/*
__le16 *tx_cons_sb;
int txq_index;
+ struct bnx2x_fastpath *parent_fp;
+ int tx_ring_size;
};
enum bnx2x_tpa_mode_t {
enum bnx2x_tpa_mode_t mode;
u8 max_cos; /* actual number of active tx coses */
- struct bnx2x_fp_txdata txdata[BNX2X_MULTI_TX_COS];
+ struct bnx2x_fp_txdata *txdata_ptr[BNX2X_MULTI_TX_COS];
struct sw_rx_bd *rx_buf_ring; /* BDs mappings ring */
struct sw_rx_page *rx_page_ring; /* SGE pages mappings ring */
rx_calls;
/* TPA related */
- struct bnx2x_agg_info tpa_info[ETH_MAX_AGGREGATION_QUEUES_E1H_E2];
+ struct bnx2x_agg_info *tpa_info;
u8 disable_tpa;
#ifdef BNX2X_STOP_ON_ERROR
u64 tpa_queue_used;
#endif
-
- struct tstorm_per_queue_stats old_tclient;
- struct ustorm_per_queue_stats old_uclient;
- struct xstorm_per_queue_stats old_xclient;
- struct bnx2x_eth_q_stats eth_q_stats;
- struct bnx2x_eth_q_stats_old eth_q_stats_old;
-
/* The size is calculated using the following:
sizeof name field from netdev structure +
4 ('-Xx-' string) +
4 (for the digits and to make it DWORD aligned) */
#define FP_NAME_SIZE (sizeof(((struct net_device *)0)->name) + 8)
char name[FP_NAME_SIZE];
-
- /* MACs object */
- struct bnx2x_vlan_mac_obj mac_obj;
-
- /* Queue State object */
- struct bnx2x_queue_sp_obj q_obj;
-
};
-#define bnx2x_fp(bp, nr, var) (bp->fp[nr].var)
+#define bnx2x_fp(bp, nr, var) ((bp)->fp[(nr)].var)
+#define bnx2x_sp_obj(bp, fp) ((bp)->sp_objs[(fp)->index])
+#define bnx2x_fp_stats(bp, fp) (&((bp)->fp_stats[(fp)->index]))
+#define bnx2x_fp_qstats(bp, fp) (&((bp)->fp_stats[(fp)->index].eth_q_stats))
/* Use 2500 as a mini-jumbo MTU for FCoE */
#define BNX2X_FCOE_MINI_JUMBO_MTU 2500
-/* FCoE L2 `fastpath' entry is right after the eth entries */
-#define FCOE_IDX BNX2X_NUM_ETH_QUEUES(bp)
-#define bnx2x_fcoe_fp(bp) (&bp->fp[FCOE_IDX])
-#define bnx2x_fcoe(bp, var) (bnx2x_fcoe_fp(bp)->var)
-#define bnx2x_fcoe_tx(bp, var) (bnx2x_fcoe_fp(bp)-> \
- txdata[FIRST_TX_COS_INDEX].var)
+#define FCOE_IDX_OFFSET 0
+
+#define FCOE_IDX(bp) (BNX2X_NUM_NON_CNIC_QUEUES(bp) + \
+ FCOE_IDX_OFFSET)
+#define bnx2x_fcoe_fp(bp) (&bp->fp[FCOE_IDX(bp)])
+#define bnx2x_fcoe(bp, var) (bnx2x_fcoe_fp(bp)->var)
+#define bnx2x_fcoe_inner_sp_obj(bp) (&bp->sp_objs[FCOE_IDX(bp)])
+#define bnx2x_fcoe_sp_obj(bp, var) (bnx2x_fcoe_inner_sp_obj(bp)->var)
+#define bnx2x_fcoe_tx(bp, var) (bnx2x_fcoe_fp(bp)-> \
+ txdata_ptr[FIRST_TX_COS_INDEX] \
+ ->var)
#define IS_ETH_FP(fp) (fp->index < \
BNX2X_NUM_ETH_QUEUES(fp->bp))
#ifdef BCM_CNIC
-#define IS_FCOE_FP(fp) (fp->index == FCOE_IDX)
-#define IS_FCOE_IDX(idx) ((idx) == FCOE_IDX)
+#define IS_FCOE_FP(fp) (fp->index == FCOE_IDX(fp->bp))
+#define IS_FCOE_IDX(idx) ((idx) == FCOE_IDX(bp))
#else
#define IS_FCOE_FP(fp) false
#define IS_FCOE_IDX(idx) false
#define ETH_RX_ERROR_FALGS ETH_FAST_PATH_RX_CQE_PHY_DECODE_ERR_FLG
-#define BNX2X_IP_CSUM_ERR(cqe) \
- (!((cqe)->fast_path_cqe.status_flags & \
- ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG) && \
- ((cqe)->fast_path_cqe.type_error_flags & \
- ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG))
-
-#define BNX2X_L4_CSUM_ERR(cqe) \
- (!((cqe)->fast_path_cqe.status_flags & \
- ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG) && \
- ((cqe)->fast_path_cqe.type_error_flags & \
- ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG))
-
-#define BNX2X_RX_CSUM_OK(cqe) \
- (!(BNX2X_L4_CSUM_ERR(cqe) || BNX2X_IP_CSUM_ERR(cqe)))
-
#define BNX2X_PRS_FLAG_OVERETH_IPV4(flags) \
(((le16_to_cpu(flags) & \
PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) >> \
};
/* CDU host DB constants */
-#define CDU_ILT_PAGE_SZ_HW 3
-#define CDU_ILT_PAGE_SZ (8192 << CDU_ILT_PAGE_SZ_HW) /* 64K */
+#define CDU_ILT_PAGE_SZ_HW 2
+#define CDU_ILT_PAGE_SZ (8192 << CDU_ILT_PAGE_SZ_HW) /* 32K */
#define ILT_PAGE_CIDS (CDU_ILT_PAGE_SZ / sizeof(union cdu_context))
#ifdef BCM_CNIC
struct list_head list;
};
+struct bnx2x_sp_objs {
+ /* MACs object */
+ struct bnx2x_vlan_mac_obj mac_obj;
+
+ /* Queue State object */
+ struct bnx2x_queue_sp_obj q_obj;
+};
+
+struct bnx2x_fp_stats {
+ struct tstorm_per_queue_stats old_tclient;
+ struct ustorm_per_queue_stats old_uclient;
+ struct xstorm_per_queue_stats old_xclient;
+ struct bnx2x_eth_q_stats eth_q_stats;
+ struct bnx2x_eth_q_stats_old eth_q_stats_old;
+};
+
struct bnx2x {
/* Fields used in the tx and intr/napi performance paths
* are grouped together in the beginning of the structure
*/
struct bnx2x_fastpath *fp;
+ struct bnx2x_sp_objs *sp_objs;
+ struct bnx2x_fp_stats *fp_stats;
+ struct bnx2x_fp_txdata *bnx2x_txq;
+ int bnx2x_txq_size;
void __iomem *regview;
void __iomem *doorbells;
u16 db_size;
#define NO_FCOE_FLAG (1 << 15)
#define BC_SUPPORTS_PFC_STATS (1 << 17)
#define USING_SINGLE_MSIX_FLAG (1 << 20)
+#define BC_SUPPORTS_DCBX_MSG_NON_PMF (1 << 21)
#define NO_ISCSI(bp) ((bp)->flags & NO_ISCSI_FLAG)
#define NO_ISCSI_OOO(bp) ((bp)->flags & NO_ISCSI_OOO_FLAG)
#define BNX2X_MAX_COS 3
#define BNX2X_MAX_TX_COS 2
int num_queues;
+ int num_napi_queues;
int disable_tpa;
u32 rx_mode;
u8 igu_dsb_id;
u8 igu_base_sb;
u8 igu_sb_cnt;
+
dma_addr_t def_status_blk_mapping;
struct bnx2x_slowpath *slowpath;
dma_addr_t fw_stats_data_mapping;
int fw_stats_data_sz;
- struct hw_context context;
+ /* For max 196 cids (64*3 + non-eth), 32KB ILT page size and 1KB
+ * context size we need 8 ILT entries.
+ */
+#define ILT_MAX_L2_LINES 8
+ struct hw_context context[ILT_MAX_L2_LINES];
struct bnx2x_ilt *ilt;
#define BP_ILT(bp) ((bp)->ilt)
/*
* Maximum CID count that might be required by the bnx2x:
- * Max Tss * Max_Tx_Multi_Cos + CNIC L2 Clients (FCoE and iSCSI related)
+ * Max RSS * Max_Tx_Multi_Cos + FCoE + iSCSI
*/
-#define BNX2X_L2_CID_COUNT(bp) (MAX_TXQS_PER_COS * BNX2X_MULTI_TX_COS +\
- NON_ETH_CONTEXT_USE + CNIC_PRESENT)
+#define BNX2X_L2_CID_COUNT(bp) (BNX2X_NUM_ETH_QUEUES(bp) * BNX2X_MULTI_TX_COS \
+ + NON_ETH_CONTEXT_USE + CNIC_PRESENT)
+#define BNX2X_L2_MAX_CID(bp) (BNX2X_MAX_RSS_COUNT(bp) * BNX2X_MULTI_TX_COS \
+ + NON_ETH_CONTEXT_USE + CNIC_PRESENT)
#define L2_ILT_LINES(bp) (DIV_ROUND_UP(BNX2X_L2_CID_COUNT(bp),\
ILT_PAGE_CIDS))
-#define BNX2X_DB_SIZE(bp) (BNX2X_L2_CID_COUNT(bp) * (1 << BNX2X_DB_SHIFT))
int qm_cid_count;
extern int num_queues;
#define BNX2X_NUM_QUEUES(bp) (bp->num_queues)
#define BNX2X_NUM_ETH_QUEUES(bp) (BNX2X_NUM_QUEUES(bp) - NON_ETH_CONTEXT_USE)
+#define BNX2X_NUM_NON_CNIC_QUEUES(bp) (BNX2X_NUM_QUEUES(bp) - \
+ NON_ETH_CONTEXT_USE)
#define BNX2X_NUM_RX_QUEUES(bp) BNX2X_NUM_QUEUES(bp)
#define is_multi(bp) (BNX2X_NUM_QUEUES(bp) > 1)
continue; \
else
+#define for_each_napi_rx_queue(bp, var) \
+ for ((var) = 0; (var) < bp->num_napi_queues; (var)++)
+
/* Skip OOO FP */
#define for_each_tx_queue(bp, var) \
for ((var) = 0; (var) < BNX2X_NUM_QUEUES(bp); (var)++) \
#define LOAD_NORMAL 0
#define LOAD_OPEN 1
#define LOAD_DIAG 2
+#define LOAD_LOOPBACK_EXT 3
#define UNLOAD_NORMAL 0
#define UNLOAD_CLOSE 1
#define UNLOAD_RECOVERY 2
#define PCICFG_LINK_SPEED 0xf0000
#define PCICFG_LINK_SPEED_SHIFT 16
-
-#define BNX2X_NUM_TESTS 7
+#define BNX2X_NUM_TESTS_SF 7
+#define BNX2X_NUM_TESTS_MF 3
+#define BNX2X_NUM_TESTS(bp) (IS_MF(bp) ? BNX2X_NUM_TESTS_MF : \
+ BNX2X_NUM_TESTS_SF)
#define BNX2X_PHY_LOOPBACK 0
#define BNX2X_MAC_LOOPBACK 1
+#define BNX2X_EXT_LOOPBACK 2
#define BNX2X_PHY_LOOPBACK_FAILED 1
#define BNX2X_MAC_LOOPBACK_FAILED 2
+#define BNX2X_EXT_LOOPBACK_FAILED 3
#define BNX2X_LOOPBACK_FAILED (BNX2X_MAC_LOOPBACK_FAILED | \
BNX2X_PHY_LOOPBACK_FAILED)
* Makes sure the contents of the bp->fp[to].napi is kept
* intact. This is done by first copying the napi struct from
* the target to the source, and then mem copying the entire
- * source onto the target
+ * source onto the target. Update txdata pointers and related
+ * content.
*/
static inline void bnx2x_move_fp(struct bnx2x *bp, int from, int to)
{
struct bnx2x_fastpath *from_fp = &bp->fp[from];
struct bnx2x_fastpath *to_fp = &bp->fp[to];
+ struct bnx2x_sp_objs *from_sp_objs = &bp->sp_objs[from];
+ struct bnx2x_sp_objs *to_sp_objs = &bp->sp_objs[to];
+ struct bnx2x_fp_stats *from_fp_stats = &bp->fp_stats[from];
+ struct bnx2x_fp_stats *to_fp_stats = &bp->fp_stats[to];
+ int old_max_eth_txqs, new_max_eth_txqs;
+ int old_txdata_index = 0, new_txdata_index = 0;
/* Copy the NAPI object as it has been already initialized */
from_fp->napi = to_fp->napi;
/* Move bnx2x_fastpath contents */
memcpy(to_fp, from_fp, sizeof(*to_fp));
to_fp->index = to;
+
+ /* move sp_objs contents as well, as their indices match fp ones */
+ memcpy(to_sp_objs, from_sp_objs, sizeof(*to_sp_objs));
+
+ /* move fp_stats contents as well, as their indices match fp ones */
+ memcpy(to_fp_stats, from_fp_stats, sizeof(*to_fp_stats));
+
+ /* Update txdata pointers in fp and move txdata content accordingly:
+ * Each fp consumes 'max_cos' txdata structures, so the index should be
+ * decremented by max_cos x delta.
+ */
+
+ old_max_eth_txqs = BNX2X_NUM_ETH_QUEUES(bp) * (bp)->max_cos;
+ new_max_eth_txqs = (BNX2X_NUM_ETH_QUEUES(bp) - from + to) *
+ (bp)->max_cos;
+ if (from == FCOE_IDX(bp)) {
+ old_txdata_index = old_max_eth_txqs + FCOE_TXQ_IDX_OFFSET;
+ new_txdata_index = new_max_eth_txqs + FCOE_TXQ_IDX_OFFSET;
+ }
+
+ memcpy(&bp->bnx2x_txq[old_txdata_index],
+ &bp->bnx2x_txq[new_txdata_index],
+ sizeof(struct bnx2x_fp_txdata));
+ to_fp->txdata_ptr[0] = &bp->bnx2x_txq[new_txdata_index];
}
int load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */
if ((netif_tx_queue_stopped(txq)) &&
(bp->state == BNX2X_STATE_OPEN) &&
- (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 3))
+ (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4))
netif_tx_wake_queue(txq);
__netif_tx_unlock(txq);
where we are and drop the whole packet */
err = bnx2x_alloc_rx_sge(bp, fp, sge_idx);
if (unlikely(err)) {
- fp->eth_q_stats.rx_skb_alloc_failed++;
+ bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
return err;
}
/* drop the packet and keep the buffer in the bin */
DP(NETIF_MSG_RX_STATUS,
"Failed to allocate or map a new skb - dropping packet!\n");
- fp->eth_q_stats.rx_skb_alloc_failed++;
+ bnx2x_fp_stats(bp, fp)->eth_q_stats.rx_skb_alloc_failed++;
}
static int bnx2x_alloc_rx_data(struct bnx2x *bp,
return 0;
}
+static
+void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe,
+ struct bnx2x_fastpath *fp,
+ struct bnx2x_eth_q_stats *qstats)
+{
+ /* Do nothing if no IP/L4 csum validation was done */
+
+ if (cqe->fast_path_cqe.status_flags &
+ (ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG |
+ ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG))
+ return;
+
+ /* If both IP/L4 validation were done, check if an error was found. */
+
+ if (cqe->fast_path_cqe.type_error_flags &
+ (ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG |
+ ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG))
+ qstats->hw_csum_err++;
+ else
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
{
DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
"ERROR flags %x rx packet %u\n",
cqe_fp_flags, sw_comp_cons);
- fp->eth_q_stats.rx_err_discard_pkt++;
+ bnx2x_fp_qstats(bp, fp)->rx_err_discard_pkt++;
goto reuse_rx;
}
if (skb == NULL) {
DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
"ERROR packet dropped because of alloc failure\n");
- fp->eth_q_stats.rx_skb_alloc_failed++;
+ bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
goto reuse_rx;
}
memcpy(skb->data, data + pad, len);
skb = build_skb(data, 0);
if (unlikely(!skb)) {
kfree(data);
- fp->eth_q_stats.rx_skb_alloc_failed++;
+ bnx2x_fp_qstats(bp, fp)->
+ rx_skb_alloc_failed++;
goto next_rx;
}
skb_reserve(skb, pad);
} else {
DP(NETIF_MSG_RX_ERR | NETIF_MSG_RX_STATUS,
"ERROR packet dropped because of alloc failure\n");
- fp->eth_q_stats.rx_skb_alloc_failed++;
+ bnx2x_fp_qstats(bp, fp)->rx_skb_alloc_failed++;
reuse_rx:
bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
goto next_rx;
skb_checksum_none_assert(skb);
- if (bp->dev->features & NETIF_F_RXCSUM) {
-
- if (likely(BNX2X_RX_CSUM_OK(cqe)))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- else
- fp->eth_q_stats.hw_csum_err++;
- }
+ if (bp->dev->features & NETIF_F_RXCSUM)
+ bnx2x_csum_validate(skb, cqe, fp,
+ bnx2x_fp_qstats(bp, fp));
skb_record_rx_queue(skb, fp->rx_queue);
prefetch(fp->rx_cons_sb);
for_each_cos_in_tx_queue(fp, cos)
- prefetch(fp->txdata[cos].tx_cons_sb);
+ prefetch(fp->txdata_ptr[cos]->tx_cons_sb);
prefetch(&fp->sb_running_index[SM_RX_ID]);
napi_schedule(&bnx2x_fp(bp, fp->index, napi));
for_each_tx_queue(bp, i) {
struct bnx2x_fastpath *fp = &bp->fp[i];
for_each_cos_in_tx_queue(fp, cos) {
- struct bnx2x_fp_txdata *txdata = &fp->txdata[cos];
+ struct bnx2x_fp_txdata *txdata = fp->txdata_ptr[cos];
unsigned pkts_compl = 0, bytes_compl = 0;
u16 sw_prod = txdata->tx_pkt_prod;
sw_cons++;
}
netdev_tx_reset_queue(
- netdev_get_tx_queue(bp->dev, txdata->txq_index));
+ netdev_get_tx_queue(bp->dev,
+ txdata->txq_index));
}
}
}
free_irq(bp->dev->irq, bp->dev);
}
-int __devinit bnx2x_enable_msix(struct bnx2x *bp)
+int bnx2x_enable_msix(struct bnx2x *bp)
{
int msix_vec = 0, i, rc, req_cnt;
#endif
/* Add special queues */
bp->num_queues += NON_ETH_CONTEXT_USE;
+
+ BNX2X_DEV_INFO("set number of queues to %d\n", bp->num_queues);
}
/**
{
int rc, tx, rx;
- tx = MAX_TXQS_PER_COS * bp->max_cos;
- rx = BNX2X_NUM_ETH_QUEUES(bp);
+ tx = BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos;
+ rx = BNX2X_NUM_QUEUES(bp) - NON_ETH_CONTEXT_USE;
/* account for fcoe queue */
#ifdef BCM_CNIC
static int bnx2x_init_rss_pf(struct bnx2x *bp)
{
int i;
- u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
u8 num_eth_queues = BNX2X_NUM_ETH_QUEUES(bp);
/* Prepare the initial contents fo the indirection table if RSS is
* enabled
*/
- for (i = 0; i < sizeof(ind_table); i++)
- ind_table[i] =
+ for (i = 0; i < sizeof(bp->rss_conf_obj.ind_table); i++)
+ bp->rss_conf_obj.ind_table[i] =
bp->fp->cl_id +
ethtool_rxfh_indir_default(i, num_eth_queues);
* For 57712 and newer on the other hand it's a per-function
* configuration.
*/
- return bnx2x_config_rss_eth(bp, ind_table,
- bp->port.pmf || !CHIP_IS_E1x(bp));
+ return bnx2x_config_rss_eth(bp, bp->port.pmf || !CHIP_IS_E1x(bp));
}
int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
- u8 *ind_table, bool config_hash)
+ bool config_hash)
{
struct bnx2x_config_rss_params params = {NULL};
int i;
__set_bit(BNX2X_RSS_IPV4_TCP, ¶ms.rss_flags);
__set_bit(BNX2X_RSS_IPV6, ¶ms.rss_flags);
__set_bit(BNX2X_RSS_IPV6_TCP, ¶ms.rss_flags);
+ if (rss_obj->udp_rss_v4)
+ __set_bit(BNX2X_RSS_IPV4_UDP, ¶ms.rss_flags);
+ if (rss_obj->udp_rss_v6)
+ __set_bit(BNX2X_RSS_IPV6_UDP, ¶ms.rss_flags);
/* Hash bits */
params.rss_result_mask = MULTI_MASK;
- memcpy(params.ind_table, ind_table, sizeof(params.ind_table));
+ memcpy(params.ind_table, rss_obj->ind_table, sizeof(params.ind_table));
if (config_hash) {
/* RSS keys */
int rc;
unsigned long ramrod_flags = 0, vlan_mac_flags = 0;
struct bnx2x_mcast_ramrod_params rparam = {NULL};
- struct bnx2x_vlan_mac_obj *mac_obj = &bp->fp->mac_obj;
+ struct bnx2x_vlan_mac_obj *mac_obj = &bp->sp_objs->mac_obj;
/***************** Cleanup MACs' object first *************************/
/* Clean ETH primary MAC */
__set_bit(BNX2X_ETH_MAC, &vlan_mac_flags);
- rc = mac_obj->delete_all(bp, &bp->fp->mac_obj, &vlan_mac_flags,
+ rc = mac_obj->delete_all(bp, &bp->sp_objs->mac_obj, &vlan_mac_flags,
&ramrod_flags);
if (rc != 0)
BNX2X_ERR("Failed to clean ETH MACs: %d\n", rc);
static void bnx2x_bz_fp(struct bnx2x *bp, int index)
{
struct bnx2x_fastpath *fp = &bp->fp[index];
+ struct bnx2x_fp_stats *fp_stats = &bp->fp_stats[index];
+
+ int cos;
struct napi_struct orig_napi = fp->napi;
+ struct bnx2x_agg_info *orig_tpa_info = fp->tpa_info;
/* bzero bnx2x_fastpath contents */
- if (bp->stats_init)
+ if (bp->stats_init) {
+ memset(fp->tpa_info, 0, sizeof(*fp->tpa_info));
memset(fp, 0, sizeof(*fp));
- else {
+ } else {
/* Keep Queue statistics */
struct bnx2x_eth_q_stats *tmp_eth_q_stats;
struct bnx2x_eth_q_stats_old *tmp_eth_q_stats_old;
tmp_eth_q_stats = kzalloc(sizeof(struct bnx2x_eth_q_stats),
GFP_KERNEL);
if (tmp_eth_q_stats)
- memcpy(tmp_eth_q_stats, &fp->eth_q_stats,
+ memcpy(tmp_eth_q_stats, &fp_stats->eth_q_stats,
sizeof(struct bnx2x_eth_q_stats));
tmp_eth_q_stats_old =
kzalloc(sizeof(struct bnx2x_eth_q_stats_old),
GFP_KERNEL);
if (tmp_eth_q_stats_old)
- memcpy(tmp_eth_q_stats_old, &fp->eth_q_stats_old,
+ memcpy(tmp_eth_q_stats_old, &fp_stats->eth_q_stats_old,
sizeof(struct bnx2x_eth_q_stats_old));
+ memset(fp->tpa_info, 0, sizeof(*fp->tpa_info));
memset(fp, 0, sizeof(*fp));
if (tmp_eth_q_stats) {
- memcpy(&fp->eth_q_stats, tmp_eth_q_stats,
- sizeof(struct bnx2x_eth_q_stats));
+ memcpy(&fp_stats->eth_q_stats, tmp_eth_q_stats,
+ sizeof(struct bnx2x_eth_q_stats));
kfree(tmp_eth_q_stats);
}
if (tmp_eth_q_stats_old) {
- memcpy(&fp->eth_q_stats_old, tmp_eth_q_stats_old,
+ memcpy(&fp_stats->eth_q_stats_old, tmp_eth_q_stats_old,
sizeof(struct bnx2x_eth_q_stats_old));
kfree(tmp_eth_q_stats_old);
}
/* Restore the NAPI object as it has been already initialized */
fp->napi = orig_napi;
-
+ fp->tpa_info = orig_tpa_info;
fp->bp = bp;
fp->index = index;
if (IS_ETH_FP(fp))
/* Special queues support only one CoS */
fp->max_cos = 1;
+ /* Init txdata pointers */
+#ifdef BCM_CNIC
+ if (IS_FCOE_FP(fp))
+ fp->txdata_ptr[0] = &bp->bnx2x_txq[FCOE_TXQ_IDX(bp)];
+#endif
+ if (IS_ETH_FP(fp))
+ for_each_cos_in_tx_queue(fp, cos)
+ fp->txdata_ptr[cos] = &bp->bnx2x_txq[cos *
+ BNX2X_NUM_ETH_QUEUES(bp) + index];
+
/*
* set the tpa flag for each queue. The tpa flag determines the queue
* minimal size so it must be set prior to queue memory allocation
/*
* Zero fastpath structures preserving invariants like napi, which are
* allocated only once, fp index, max_cos, bp pointer.
- * Also set fp->disable_tpa.
+ * Also set fp->disable_tpa and txdata_ptr.
*/
DP(NETIF_MSG_IFUP, "num queues: %d", bp->num_queues);
for_each_queue(bp, i)
bnx2x_bz_fp(bp, i);
+ memset(bp->bnx2x_txq, 0, bp->bnx2x_txq_size *
+ sizeof(struct bnx2x_fp_txdata));
/* Set the receive queues buffer size */
break;
case LOAD_DIAG:
+ case LOAD_LOOPBACK_EXT:
bp->state = BNX2X_STATE_DIAG;
break;
/* re-read iscsi info */
bnx2x_get_iscsi_info(bp);
bnx2x_setup_cnic_irq_info(bp);
+ bnx2x_setup_cnic_info(bp);
if (bp->state == BNX2X_STATE_OPEN)
bnx2x_cnic_notify(bp, CNIC_CTL_START_CMD);
#endif
return -EBUSY;
}
- bnx2x_dcbx_init(bp);
+ /* If PMF - send ADMIN DCBX msg to MFW to initiate DCBX FSM */
+ if (bp->port.pmf && (bp->state != BNX2X_STATE_DIAG))
+ bnx2x_dcbx_init(bp, false);
+
return 0;
#ifndef BNX2X_STOP_ON_ERROR
/* Stop Tx */
bnx2x_tx_disable(bp);
+ netdev_reset_tc(bp->dev);
#ifdef BCM_CNIC
bnx2x_cnic_notify(bp, CNIC_CTL_STOP_CMD);
#endif
for_each_cos_in_tx_queue(fp, cos)
- if (bnx2x_tx_queue_has_work(&fp->txdata[cos]))
- bnx2x_tx_int(bp, &fp->txdata[cos]);
+ if (bnx2x_tx_queue_has_work(fp->txdata_ptr[cos]))
+ bnx2x_tx_int(bp, fp->txdata_ptr[cos]);
if (bnx2x_has_rx_work(fp)) {
/* we split the first BD into headers and data BDs
* to ease the pain of our fellow microcode engineers
* we use one mapping for both BDs
- * So far this has only been observed to happen
- * in Other Operating Systems(TM)
*/
static noinline u16 bnx2x_tx_split(struct bnx2x *bp,
struct bnx2x_fp_txdata *txdata,
{
struct bnx2x *bp = netdev_priv(dev);
- struct bnx2x_fastpath *fp;
struct netdev_queue *txq;
struct bnx2x_fp_txdata *txdata;
struct sw_tx_bd *tx_buf;
struct eth_tx_parse_bd_e2 *pbd_e2 = NULL;
u32 pbd_e2_parsing_data = 0;
u16 pkt_prod, bd_prod;
- int nbd, txq_index, fp_index, txdata_index;
+ int nbd, txq_index;
dma_addr_t mapping;
u32 xmit_type = bnx2x_xmit_type(bp, skb);
int i;
BUG_ON(txq_index >= MAX_ETH_TXQ_IDX(bp) + FCOE_PRESENT);
- /* decode the fastpath index and the cos index from the txq */
- fp_index = TXQ_TO_FP(txq_index);
- txdata_index = TXQ_TO_COS(txq_index);
-
-#ifdef BCM_CNIC
- /*
- * Override the above for the FCoE queue:
- * - FCoE fp entry is right after the ETH entries.
- * - FCoE L2 queue uses bp->txdata[0] only.
- */
- if (unlikely(!NO_FCOE(bp) && (txq_index ==
- bnx2x_fcoe_tx(bp, txq_index)))) {
- fp_index = FCOE_IDX;
- txdata_index = 0;
- }
-#endif
+ txdata = &bp->bnx2x_txq[txq_index];
/* enable this debug print to view the transmission queue being used
DP(NETIF_MSG_TX_QUEUED, "indices: txq %d, fp %d, txdata %d\n",
txq_index, fp_index, txdata_index); */
- /* locate the fastpath and the txdata */
- fp = &bp->fp[fp_index];
- txdata = &fp->txdata[txdata_index];
-
/* enable this debug print to view the tranmission details
DP(NETIF_MSG_TX_QUEUED,
"transmitting packet cid %d fp index %d txdata_index %d tx_data ptr %p fp pointer %p\n",
if (unlikely(bnx2x_tx_avail(bp, txdata) <
(skb_shinfo(skb)->nr_frags + 3))) {
- fp->eth_q_stats.driver_xoff++;
+ bnx2x_fp_qstats(bp, txdata->parent_fp)->driver_xoff++;
netif_tx_stop_queue(txq);
BNX2X_ERR("BUG! Tx ring full when queue awake!\n");
return NETDEV_TX_BUSY;
txdata->tx_bd_prod += nbd;
- if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_SKB_FRAGS + 3)) {
+ if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_SKB_FRAGS + 4)) {
netif_tx_stop_queue(txq);
/* paired memory barrier is in bnx2x_tx_int(), we have to keep
* fp->bd_tx_cons */
smp_mb();
- fp->eth_q_stats.driver_xoff++;
- if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 3)
+ bnx2x_fp_qstats(bp, txdata->parent_fp)->driver_xoff++;
+ if (bnx2x_tx_avail(bp, txdata) >= MAX_SKB_FRAGS + 4)
netif_tx_wake_queue(txq);
}
txdata->tx_pkt++;
/* configure traffic class to transmission queue mapping */
for (cos = 0; cos < bp->max_cos; cos++) {
count = BNX2X_NUM_ETH_QUEUES(bp);
- offset = cos * MAX_TXQS_PER_COS;
+ offset = cos * BNX2X_NUM_NON_CNIC_QUEUES(bp);
netdev_set_tc_queue(dev, cos, count, offset);
DP(BNX2X_MSG_SP | NETIF_MSG_IFUP,
"mapping tc %d to offset %d count %d\n",
if (!skip_tx_queue(bp, fp_index)) {
/* fastpath tx rings: tx_buf tx_desc */
for_each_cos_in_tx_queue(fp, cos) {
- struct bnx2x_fp_txdata *txdata = &fp->txdata[cos];
+ struct bnx2x_fp_txdata *txdata = fp->txdata_ptr[cos];
DP(NETIF_MSG_IFDOWN,
"freeing tx memory of fp %d cos %d cid %d\n",
cqe_ring_prod);
fp->rx_pkt = fp->rx_calls = 0;
- fp->eth_q_stats.rx_skb_alloc_failed += failure_cnt;
+ bnx2x_fp_stats(bp, fp)->eth_q_stats.rx_skb_alloc_failed += failure_cnt;
return i - failure_cnt;
}
if (!skip_tx_queue(bp, index)) {
/* fastpath tx rings: tx_buf tx_desc */
for_each_cos_in_tx_queue(fp, cos) {
- struct bnx2x_fp_txdata *txdata = &fp->txdata[cos];
+ struct bnx2x_fp_txdata *txdata = fp->txdata_ptr[cos];
DP(NETIF_MSG_IFUP,
"allocating tx memory of fp %d cos %d\n",
#ifdef BCM_CNIC
if (!NO_FCOE(bp))
/* FCoE */
- if (bnx2x_alloc_fp_mem_at(bp, FCOE_IDX))
+ if (bnx2x_alloc_fp_mem_at(bp, FCOE_IDX(bp)))
/* we will fail load process instead of mark
* NO_FCOE_FLAG
*/
*/
/* move FCoE fp even NO_FCOE_FLAG is on */
- bnx2x_move_fp(bp, FCOE_IDX, FCOE_IDX - delta);
+ bnx2x_move_fp(bp, FCOE_IDX(bp), FCOE_IDX(bp) - delta);
#endif
bp->num_queues -= delta;
BNX2X_ERR("Adjusted num of queues from %d to %d\n",
void bnx2x_free_mem_bp(struct bnx2x *bp)
{
+ kfree(bp->fp->tpa_info);
kfree(bp->fp);
+ kfree(bp->sp_objs);
+ kfree(bp->fp_stats);
+ kfree(bp->bnx2x_txq);
kfree(bp->msix_table);
kfree(bp->ilt);
}
struct msix_entry *tbl;
struct bnx2x_ilt *ilt;
int msix_table_size = 0;
+ int fp_array_size;
+ int i;
/*
* The biggest MSI-X table we might need is as a maximum number of fast
msix_table_size = bp->igu_sb_cnt + 1;
/* fp array: RSS plus CNIC related L2 queues */
- fp = kcalloc(BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE,
- sizeof(*fp), GFP_KERNEL);
+ fp_array_size = BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE;
+ BNX2X_DEV_INFO("fp_array_size %d", fp_array_size);
+
+ fp = kcalloc(fp_array_size, sizeof(*fp), GFP_KERNEL);
if (!fp)
goto alloc_err;
+ for (i = 0; i < fp_array_size; i++) {
+ fp[i].tpa_info =
+ kcalloc(ETH_MAX_AGGREGATION_QUEUES_E1H_E2,
+ sizeof(struct bnx2x_agg_info), GFP_KERNEL);
+ if (!(fp[i].tpa_info))
+ goto alloc_err;
+ }
+
bp->fp = fp;
+ /* allocate sp objs */
+ bp->sp_objs = kcalloc(fp_array_size, sizeof(struct bnx2x_sp_objs),
+ GFP_KERNEL);
+ if (!bp->sp_objs)
+ goto alloc_err;
+
+ /* allocate fp_stats */
+ bp->fp_stats = kcalloc(fp_array_size, sizeof(struct bnx2x_fp_stats),
+ GFP_KERNEL);
+ if (!bp->fp_stats)
+ goto alloc_err;
+
+ /* Allocate memory for the transmission queues array */
+ bp->bnx2x_txq_size = BNX2X_MAX_RSS_COUNT(bp) * BNX2X_MULTI_TX_COS;
+#ifdef BCM_CNIC
+ bp->bnx2x_txq_size++;
+#endif
+ bp->bnx2x_txq = kcalloc(bp->bnx2x_txq_size,
+ sizeof(struct bnx2x_fp_txdata), GFP_KERNEL);
+ if (!bp->bnx2x_txq)
+ goto alloc_err;
+
/* msix table */
tbl = kcalloc(msix_table_size, sizeof(*tbl), GFP_KERNEL);
if (!tbl)
extern int load_count[2][3]; /* per-path: 0-common, 1-port0, 2-port1 */
extern int num_queues;
+extern int int_mode;
/************************ Macros ********************************/
#define BNX2X_PCI_FREE(x, y, size) \
* @config_hash: re-configure RSS hash keys configuration
*/
int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
- u8 *ind_table, bool config_hash);
+ bool config_hash);
/**
* bnx2x__init_func_obj - init function object
* @bp: driver handle
*/
void bnx2x_setup_cnic_irq_info(struct bnx2x *bp);
+
+/**
+ * bnx2x_setup_cnic_info - provides cnic with updated info
+ *
+ * @bp: driver handle
+ */
+void bnx2x_setup_cnic_info(struct bnx2x *bp);
+
#endif
/**
*
* @bp: driver handle
*/
-void bnx2x_dcbx_init(struct bnx2x *bp);
+void bnx2x_dcbx_init(struct bnx2x *bp, bool update_shmem);
/**
* bnx2x_set_power_state - set power state to the requested value.
* fills msix_table, requests vectors, updates num_queues
* according to number of available vectors.
*/
-int __devinit bnx2x_enable_msix(struct bnx2x *bp);
+int bnx2x_enable_msix(struct bnx2x *bp);
/**
* bnx2x_enable_msi - request msi mode from OS, updated internals accordingly
{
u8 cos;
for_each_cos_in_tx_queue(fp, cos)
- if (bnx2x_tx_queue_has_work(&fp->txdata[cos]))
+ if (bnx2x_tx_queue_has_work(fp->txdata_ptr[cos]))
return true;
return false;
}
{
int i;
+ bp->num_napi_queues = bp->num_queues;
+
/* Add NAPI objects */
- for_each_rx_queue(bp, i)
+ for_each_napi_rx_queue(bp, i)
netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi),
bnx2x_poll, BNX2X_NAPI_WEIGHT);
}
{
int i;
- for_each_rx_queue(bp, i)
+ for_each_napi_rx_queue(bp, i)
netif_napi_del(&bnx2x_fp(bp, i, napi));
}
+void bnx2x_set_int_mode(struct bnx2x *bp);
+
static inline void bnx2x_disable_msi(struct bnx2x *bp)
{
if (bp->flags & USING_MSIX_FLAG) {
return 2 * vn + BP_PORT(bp);
}
-static inline int bnx2x_config_rss_eth(struct bnx2x *bp, u8 *ind_table,
- bool config_hash)
+static inline int bnx2x_config_rss_eth(struct bnx2x *bp, bool config_hash)
{
- return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, ind_table,
- config_hash);
+ return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, config_hash);
}
/**
struct bnx2x *bp = fp->bp;
/* Configure classification DBs */
- bnx2x_init_mac_obj(bp, &fp->mac_obj, fp->cl_id, fp->cid,
- BP_FUNC(bp), bnx2x_sp(bp, mac_rdata),
+ bnx2x_init_mac_obj(bp, &bnx2x_sp_obj(bp, fp).mac_obj, fp->cl_id,
+ fp->cid, BP_FUNC(bp), bnx2x_sp(bp, mac_rdata),
bnx2x_sp_mapping(bp, mac_rdata),
BNX2X_FILTER_MAC_PENDING,
&bp->sp_state, obj_type,
}
static inline void bnx2x_init_txdata(struct bnx2x *bp,
- struct bnx2x_fp_txdata *txdata, u32 cid, int txq_index,
- __le16 *tx_cons_sb)
+ struct bnx2x_fp_txdata *txdata, u32 cid,
+ int txq_index, __le16 *tx_cons_sb,
+ struct bnx2x_fastpath *fp)
{
txdata->cid = cid;
txdata->txq_index = txq_index;
txdata->tx_cons_sb = tx_cons_sb;
+ txdata->parent_fp = fp;
DP(NETIF_MSG_IFUP, "created tx data cid %d, txq %d\n",
txdata->cid, txdata->txq_index);
bnx2x_fcoe(bp, rx_queue) = BNX2X_NUM_ETH_QUEUES(bp);
bnx2x_fcoe(bp, cl_id) = bnx2x_cnic_eth_cl_id(bp,
BNX2X_FCOE_ETH_CL_ID_IDX);
- /** Current BNX2X_FCOE_ETH_CID deffinition implies not more than
- * 16 ETH clients per function when CNIC is enabled!
- *
- * Fix it ASAP!!!
- */
- bnx2x_fcoe(bp, cid) = BNX2X_FCOE_ETH_CID;
+ bnx2x_fcoe(bp, cid) = BNX2X_FCOE_ETH_CID(bp);
bnx2x_fcoe(bp, fw_sb_id) = DEF_SB_ID;
bnx2x_fcoe(bp, igu_sb_id) = bp->igu_dsb_id;
bnx2x_fcoe(bp, rx_cons_sb) = BNX2X_FCOE_L2_RX_INDEX;
-
- bnx2x_init_txdata(bp, &bnx2x_fcoe(bp, txdata[0]),
- fp->cid, FCOE_TXQ_IDX(bp), BNX2X_FCOE_L2_TX_INDEX);
+ bnx2x_init_txdata(bp, bnx2x_fcoe(bp, txdata_ptr[0]),
+ fp->cid, FCOE_TXQ_IDX(bp), BNX2X_FCOE_L2_TX_INDEX,
+ fp);
DP(NETIF_MSG_IFUP, "created fcoe tx data (fp index %d)\n", fp->index);
/* No multi-CoS for FCoE L2 client */
BUG_ON(fp->max_cos != 1);
- bnx2x_init_queue_obj(bp, &fp->q_obj, fp->cl_id, &fp->cid, 1,
- BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
+ bnx2x_init_queue_obj(bp, &bnx2x_sp_obj(bp, fp).q_obj, fp->cl_id,
+ &fp->cid, 1, BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
bnx2x_sp_mapping(bp, q_rdata), q_type);
DP(NETIF_MSG_IFUP,
bp->dcbx_config_params.admin_default_priority = 0;
}
-void bnx2x_dcbx_init(struct bnx2x *bp)
+void bnx2x_dcbx_init(struct bnx2x *bp, bool update_shmem)
{
u32 dcbx_lldp_params_offset = SHMEM_LLDP_DCBX_PARAMS_NONE;
+ /* only PMF can send ADMIN msg to MFW in old MFW versions */
+ if ((!bp->port.pmf) && (!(bp->flags & BC_SUPPORTS_DCBX_MSG_NON_PMF)))
+ return;
+
if (bp->dcbx_enabled <= 0)
return;
/* validate:
* chip of good for dcbx version,
* dcb is wanted
- * the function is pmf
* shmem2 contains DCBX support fields
*/
DP(BNX2X_MSG_DCB, "dcb_state %d bp->port.pmf %d\n",
bp->dcb_state, bp->port.pmf);
- if (bp->dcb_state == BNX2X_DCB_STATE_ON && bp->port.pmf &&
+ if (bp->dcb_state == BNX2X_DCB_STATE_ON &&
SHMEM2_HAS(bp, dcbx_lldp_params_offset)) {
dcbx_lldp_params_offset =
SHMEM2_RD(bp, dcbx_lldp_params_offset);
bnx2x_update_drv_flags(bp, 1 << DRV_FLAGS_DCB_CONFIGURED, 0);
if (SHMEM_LLDP_DCBX_PARAMS_NONE != dcbx_lldp_params_offset) {
- bnx2x_dcbx_admin_mib_updated_params(bp,
- dcbx_lldp_params_offset);
+ /* need HW lock to avoid scenario of two drivers
+ * writing in parallel to shmem
+ */
+ bnx2x_acquire_hw_lock(bp,
+ HW_LOCK_RESOURCE_DCBX_ADMIN_MIB);
+ if (update_shmem)
+ bnx2x_dcbx_admin_mib_updated_params(bp,
+ dcbx_lldp_params_offset);
/* Let HW start negotiation */
bnx2x_fw_command(bp,
DRV_MSG_CODE_DCBX_ADMIN_PMF_MSG, 0);
+ /* release HW lock only after MFW acks that it finished
+ * reading values from shmem
+ */
+ bnx2x_release_hw_lock(bp,
+ HW_LOCK_RESOURCE_DCBX_ADMIN_MIB);
}
}
}
"Handling parity error recovery. Try again later\n");
return 1;
}
- if (netif_running(bp->dev)) {
- bnx2x_nic_unload(bp, UNLOAD_NORMAL);
- rc = bnx2x_nic_load(bp, LOAD_NORMAL);
- }
+ if (netif_running(bp->dev))
+ bnx2x_dcbx_init(bp, true);
DP(BNX2X_MSG_DCB, "set_dcbx_params done (%d)\n", rc);
if (rc)
return 1;
((phy_fw_ver[0] != '\0') ? " phy " : ""), phy_fw_ver);
strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
info->n_stats = BNX2X_NUM_STATS;
- info->testinfo_len = BNX2X_NUM_TESTS;
+ info->testinfo_len = BNX2X_NUM_TESTS(bp);
info->eedump_len = bp->common.flash_size;
info->regdump_len = bnx2x_get_regs_len(dev);
}
return 0;
}
-static const struct {
- char string[ETH_GSTRING_LEN];
-} bnx2x_tests_str_arr[BNX2X_NUM_TESTS] = {
- { "register_test (offline)" },
- { "memory_test (offline)" },
- { "loopback_test (offline)" },
- { "nvram_test (online)" },
- { "interrupt_test (online)" },
- { "link_test (online)" },
- { "idle check (online)" }
+char *bnx2x_tests_str_arr[BNX2X_NUM_TESTS_SF] = {
+ "register_test (offline) ",
+ "memory_test (offline) ",
+ "int_loopback_test (offline)",
+ "ext_loopback_test (offline)",
+ "nvram_test (online) ",
+ "interrupt_test (online) ",
+ "link_test (online) "
};
static u32 bnx2x_eee_to_adv(u32 eee_adv)
if (cnt <= 0 && bnx2x_link_test(bp, is_serdes))
DP(BNX2X_MSG_ETHTOOL, "Timeout waiting for link up\n");
+
+ cnt = 1400;
+ while (!bp->link_vars.link_up && cnt--)
+ msleep(20);
+
+ if (cnt <= 0 && !bp->link_vars.link_up)
+ DP(BNX2X_MSG_ETHTOOL,
+ "Timeout waiting for link init\n");
}
}
unsigned char *packet;
struct bnx2x_fastpath *fp_rx = &bp->fp[0];
struct bnx2x_fastpath *fp_tx = &bp->fp[0];
- struct bnx2x_fp_txdata *txdata = &fp_tx->txdata[0];
+ struct bnx2x_fp_txdata *txdata = fp_tx->txdata_ptr[0];
u16 tx_start_idx, tx_idx;
u16 rx_start_idx, rx_idx;
u16 pkt_prod, bd_prod;
u16 len;
int rc = -ENODEV;
u8 *data;
- struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txdata->txq_index);
+ struct netdev_queue *txq = netdev_get_tx_queue(bp->dev,
+ txdata->txq_index);
/* check the loopback mode */
switch (loopback_mode) {
case BNX2X_PHY_LOOPBACK:
- if (bp->link_params.loopback_mode != LOOPBACK_XGXS)
+ if (bp->link_params.loopback_mode != LOOPBACK_XGXS) {
+ DP(BNX2X_MSG_ETHTOOL, "PHY loopback not supported\n");
return -EINVAL;
+ }
break;
case BNX2X_MAC_LOOPBACK:
if (CHIP_IS_E3(bp)) {
bnx2x_phy_init(&bp->link_params, &bp->link_vars);
break;
+ case BNX2X_EXT_LOOPBACK:
+ if (bp->link_params.loopback_mode != LOOPBACK_EXT) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "Can't configure external loopback\n");
+ return -EINVAL;
+ }
+ break;
default:
DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n");
return -EINVAL;
return rc;
}
+static int bnx2x_test_ext_loopback(struct bnx2x *bp)
+{
+ int rc;
+ u8 is_serdes =
+ (bp->link_vars.link_status & LINK_STATUS_SERDES_LINK) > 0;
+
+ if (BP_NOMCP(bp))
+ return -ENODEV;
+
+ if (!netif_running(bp->dev))
+ return BNX2X_EXT_LOOPBACK_FAILED;
+
+ bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+ rc = bnx2x_nic_load(bp, LOAD_LOOPBACK_EXT);
+ if (rc) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "Can't perform self-test, nic_load (for external lb) failed\n");
+ return -ENODEV;
+ }
+ bnx2x_wait_for_link(bp, 1, is_serdes);
+
+ bnx2x_netif_stop(bp, 1);
+
+ rc = bnx2x_run_loopback(bp, BNX2X_EXT_LOOPBACK);
+ if (rc)
+ DP(BNX2X_MSG_ETHTOOL, "EXT loopback failed (res %d)\n", rc);
+
+ bnx2x_netif_start(bp);
+
+ return rc;
+}
+
#define CRC32_RESIDUAL 0xdebb20e3
static int bnx2x_test_nvram(struct bnx2x *bp)
return -ENODEV;
}
- params.q_obj = &bp->fp->q_obj;
+ params.q_obj = &bp->sp_objs->q_obj;
params.cmd = BNX2X_Q_CMD_EMPTY;
__set_bit(RAMROD_COMP_WAIT, ¶ms.ramrod_flags);
{
struct bnx2x *bp = netdev_priv(dev);
u8 is_serdes;
+ int rc;
+
if (bp->recovery_state != BNX2X_RECOVERY_DONE) {
netdev_err(bp->dev,
"Handling parity error recovery. Try again later\n");
etest->flags |= ETH_TEST_FL_FAILED;
return;
}
+ DP(BNX2X_MSG_ETHTOOL,
+ "Self-test command parameters: offline = %d, external_lb = %d\n",
+ (etest->flags & ETH_TEST_FL_OFFLINE),
+ (etest->flags & ETH_TEST_FL_EXTERNAL_LB)>>2);
- memset(buf, 0, sizeof(u64) * BNX2X_NUM_TESTS);
+ memset(buf, 0, sizeof(u64) * BNX2X_NUM_TESTS(bp));
- if (!netif_running(dev))
+ if (!netif_running(dev)) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "Can't perform self-test when interface is down\n");
return;
+ }
- /* offline tests are not supported in MF mode */
- if (IS_MF(bp))
- etest->flags &= ~ETH_TEST_FL_OFFLINE;
is_serdes = (bp->link_vars.link_status & LINK_STATUS_SERDES_LINK) > 0;
- if (etest->flags & ETH_TEST_FL_OFFLINE) {
+ /* offline tests are not supported in MF mode */
+ if ((etest->flags & ETH_TEST_FL_OFFLINE) && !IS_MF(bp)) {
int port = BP_PORT(bp);
u32 val;
u8 link_up;
link_up = bp->link_vars.link_up;
bnx2x_nic_unload(bp, UNLOAD_NORMAL);
- bnx2x_nic_load(bp, LOAD_DIAG);
+ rc = bnx2x_nic_load(bp, LOAD_DIAG);
+ if (rc) {
+ etest->flags |= ETH_TEST_FL_FAILED;
+ DP(BNX2X_MSG_ETHTOOL,
+ "Can't perform self-test, nic_load (for offline) failed\n");
+ return;
+ }
+
/* wait until link state is restored */
bnx2x_wait_for_link(bp, 1, is_serdes);
etest->flags |= ETH_TEST_FL_FAILED;
}
- buf[2] = bnx2x_test_loopback(bp);
+ buf[2] = bnx2x_test_loopback(bp); /* internal LB */
if (buf[2] != 0)
etest->flags |= ETH_TEST_FL_FAILED;
+ if (etest->flags & ETH_TEST_FL_EXTERNAL_LB) {
+ buf[3] = bnx2x_test_ext_loopback(bp); /* external LB */
+ if (buf[3] != 0)
+ etest->flags |= ETH_TEST_FL_FAILED;
+ etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
+ }
+
bnx2x_nic_unload(bp, UNLOAD_NORMAL);
/* restore input for TX port IF */
REG_WR(bp, NIG_REG_EGRESS_UMP0_IN_EN + port*4, val);
-
- bnx2x_nic_load(bp, LOAD_NORMAL);
+ rc = bnx2x_nic_load(bp, LOAD_NORMAL);
+ if (rc) {
+ etest->flags |= ETH_TEST_FL_FAILED;
+ DP(BNX2X_MSG_ETHTOOL,
+ "Can't perform self-test, nic_load (for online) failed\n");
+ return;
+ }
/* wait until link state is restored */
bnx2x_wait_for_link(bp, link_up, is_serdes);
}
if (bnx2x_test_nvram(bp) != 0) {
- buf[3] = 1;
+ if (!IS_MF(bp))
+ buf[4] = 1;
+ else
+ buf[0] = 1;
etest->flags |= ETH_TEST_FL_FAILED;
}
if (bnx2x_test_intr(bp) != 0) {
- buf[4] = 1;
+ if (!IS_MF(bp))
+ buf[5] = 1;
+ else
+ buf[1] = 1;
etest->flags |= ETH_TEST_FL_FAILED;
}
if (bnx2x_link_test(bp, is_serdes) != 0) {
- buf[5] = 1;
+ if (!IS_MF(bp))
+ buf[6] = 1;
+ else
+ buf[2] = 1;
etest->flags |= ETH_TEST_FL_FAILED;
}
return num_stats;
case ETH_SS_TEST:
- return BNX2X_NUM_TESTS;
+ return BNX2X_NUM_TESTS(bp);
default:
return -EINVAL;
static void bnx2x_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
{
struct bnx2x *bp = netdev_priv(dev);
- int i, j, k;
+ int i, j, k, offset, start;
char queue_name[MAX_QUEUE_NAME_LEN+1];
switch (stringset) {
break;
case ETH_SS_TEST:
- memcpy(buf, bnx2x_tests_str_arr, sizeof(bnx2x_tests_str_arr));
+ /* First 4 tests cannot be done in MF mode */
+ if (!IS_MF(bp))
+ start = 0;
+ else
+ start = 4;
+ for (i = 0, j = start; j < (start + BNX2X_NUM_TESTS(bp));
+ i++, j++) {
+ offset = sprintf(buf+32*i, "%s",
+ bnx2x_tests_str_arr[j]);
+ *(buf+offset) = '\0';
+ }
break;
}
}
if (is_multi(bp)) {
for_each_eth_queue(bp, i) {
- hw_stats = (u32 *)&bp->fp[i].eth_q_stats;
+ hw_stats = (u32 *)&bp->fp_stats[i].eth_q_stats;
for (j = 0; j < BNX2X_NUM_Q_STATS; j++) {
if (bnx2x_q_stats_arr[j].size == 0) {
/* skip this counter */
return 0;
}
+static int bnx2x_get_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
+{
+
+ switch (info->flow_type) {
+ case TCP_V4_FLOW:
+ case TCP_V6_FLOW:
+ info->data = RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ break;
+ case UDP_V4_FLOW:
+ if (bp->rss_conf_obj.udp_rss_v4)
+ info->data = RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ else
+ info->data = RXH_IP_SRC | RXH_IP_DST;
+ break;
+ case UDP_V6_FLOW:
+ if (bp->rss_conf_obj.udp_rss_v6)
+ info->data = RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ else
+ info->data = RXH_IP_SRC | RXH_IP_DST;
+ break;
+ case IPV4_FLOW:
+ case IPV6_FLOW:
+ info->data = RXH_IP_SRC | RXH_IP_DST;
+ break;
+ default:
+ info->data = 0;
+ break;
+ }
+
+ return 0;
+}
+
static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
u32 *rules __always_unused)
{
case ETHTOOL_GRXRINGS:
info->data = BNX2X_NUM_ETH_QUEUES(bp);
return 0;
+ case ETHTOOL_GRXFH:
+ return bnx2x_get_rss_flags(bp, info);
+ default:
+ DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n");
+ return -EOPNOTSUPP;
+ }
+}
+
+static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
+{
+ int udp_rss_requested;
+
+ DP(BNX2X_MSG_ETHTOOL,
+ "Set rss flags command parameters: flow type = %d, data = %llu\n",
+ info->flow_type, info->data);
+
+ switch (info->flow_type) {
+ case TCP_V4_FLOW:
+ case TCP_V6_FLOW:
+ /* For TCP only 4-tupple hash is supported */
+ if (info->data ^ (RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "Command parameters not supported\n");
+ return -EINVAL;
+ } else {
+ return 0;
+ }
+
+ case UDP_V4_FLOW:
+ case UDP_V6_FLOW:
+ /* For UDP either 2-tupple hash or 4-tupple hash is supported */
+ if (info->data == (RXH_IP_SRC | RXH_IP_DST |
+ RXH_L4_B_0_1 | RXH_L4_B_2_3))
+ udp_rss_requested = 1;
+ else if (info->data == (RXH_IP_SRC | RXH_IP_DST))
+ udp_rss_requested = 0;
+ else
+ return -EINVAL;
+ if ((info->flow_type == UDP_V4_FLOW) &&
+ (bp->rss_conf_obj.udp_rss_v4 != udp_rss_requested)) {
+ bp->rss_conf_obj.udp_rss_v4 = udp_rss_requested;
+ DP(BNX2X_MSG_ETHTOOL,
+ "rss re-configured, UDP 4-tupple %s\n",
+ udp_rss_requested ? "enabled" : "disabled");
+ return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, 0);
+ } else if ((info->flow_type == UDP_V6_FLOW) &&
+ (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) {
+ bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested;
+ return bnx2x_config_rss_pf(bp, &bp->rss_conf_obj, 0);
+ DP(BNX2X_MSG_ETHTOOL,
+ "rss re-configured, UDP 4-tupple %s\n",
+ udp_rss_requested ? "enabled" : "disabled");
+ } else {
+ return 0;
+ }
+ case IPV4_FLOW:
+ case IPV6_FLOW:
+ /* For IP only 2-tupple hash is supported */
+ if (info->data ^ (RXH_IP_SRC | RXH_IP_DST)) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "Command parameters not supported\n");
+ return -EINVAL;
+ } else {
+ return 0;
+ }
+ case SCTP_V4_FLOW:
+ case AH_ESP_V4_FLOW:
+ case AH_V4_FLOW:
+ case ESP_V4_FLOW:
+ case SCTP_V6_FLOW:
+ case AH_ESP_V6_FLOW:
+ case AH_V6_FLOW:
+ case ESP_V6_FLOW:
+ case IP_USER_FLOW:
+ case ETHER_FLOW:
+ /* RSS is not supported for these protocols */
+ if (info->data) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "Command parameters not supported\n");
+ return -EINVAL;
+ } else {
+ return 0;
+ }
+ default:
+ return -EINVAL;
+ }
+}
+static int bnx2x_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
+{
+ struct bnx2x *bp = netdev_priv(dev);
+
+ switch (info->cmd) {
+ case ETHTOOL_SRXFH:
+ return bnx2x_set_rss_flags(bp, info);
default:
DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n");
return -EOPNOTSUPP;
{
struct bnx2x *bp = netdev_priv(dev);
size_t i;
- u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
/*
* align the received table to the Client ID of the leading RSS
* queue
*/
- ind_table[i] = indir[i] + bp->fp->cl_id;
+ bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
}
- return bnx2x_config_rss_eth(bp, ind_table, false);
+ return bnx2x_config_rss_eth(bp, false);
+}
+
+/**
+ * bnx2x_get_channels - gets the number of RSS queues.
+ *
+ * @dev: net device
+ * @channels: returns the number of max / current queues
+ */
+static void bnx2x_get_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct bnx2x *bp = netdev_priv(dev);
+
+ channels->max_combined = BNX2X_MAX_RSS_COUNT(bp);
+ channels->combined_count = BNX2X_NUM_ETH_QUEUES(bp);
+}
+
+/**
+ * bnx2x_change_num_queues - change the number of RSS queues.
+ *
+ * @bp: bnx2x private structure
+ *
+ * Re-configure interrupt mode to get the new number of MSI-X
+ * vectors and re-add NAPI objects.
+ */
+static void bnx2x_change_num_queues(struct bnx2x *bp, int num_rss)
+{
+ bnx2x_del_all_napi(bp);
+ bnx2x_disable_msi(bp);
+ BNX2X_NUM_QUEUES(bp) = num_rss + NON_ETH_CONTEXT_USE;
+ bnx2x_set_int_mode(bp);
+ bnx2x_add_all_napi(bp);
+}
+
+/**
+ * bnx2x_set_channels - sets the number of RSS queues.
+ *
+ * @dev: net device
+ * @channels: includes the number of queues requested
+ */
+static int bnx2x_set_channels(struct net_device *dev,
+ struct ethtool_channels *channels)
+{
+ struct bnx2x *bp = netdev_priv(dev);
+
+
+ DP(BNX2X_MSG_ETHTOOL,
+ "set-channels command parameters: rx = %d, tx = %d, other = %d, combined = %d\n",
+ channels->rx_count, channels->tx_count, channels->other_count,
+ channels->combined_count);
+
+ /* We don't support separate rx / tx channels.
+ * We don't allow setting 'other' channels.
+ */
+ if (channels->rx_count || channels->tx_count || channels->other_count
+ || (channels->combined_count == 0) ||
+ (channels->combined_count > BNX2X_MAX_RSS_COUNT(bp))) {
+ DP(BNX2X_MSG_ETHTOOL, "command parameters not supported\n");
+ return -EINVAL;
+ }
+
+ /* Check if there was a change in the active parameters */
+ if (channels->combined_count == BNX2X_NUM_ETH_QUEUES(bp)) {
+ DP(BNX2X_MSG_ETHTOOL, "No change in active parameters\n");
+ return 0;
+ }
+
+ /* Set the requested number of queues in bp context.
+ * Note that the actual number of queues created during load may be
+ * less than requested if memory is low.
+ */
+ if (unlikely(!netif_running(dev))) {
+ bnx2x_change_num_queues(bp, channels->combined_count);
+ return 0;
+ }
+ bnx2x_nic_unload(bp, UNLOAD_NORMAL);
+ bnx2x_change_num_queues(bp, channels->combined_count);
+ return bnx2x_nic_load(bp, LOAD_NORMAL);
}
static const struct ethtool_ops bnx2x_ethtool_ops = {
.set_phys_id = bnx2x_set_phys_id,
.get_ethtool_stats = bnx2x_get_ethtool_stats,
.get_rxnfc = bnx2x_get_rxnfc,
+ .set_rxnfc = bnx2x_set_rxnfc,
.get_rxfh_indir_size = bnx2x_get_rxfh_indir_size,
.get_rxfh_indir = bnx2x_get_rxfh_indir,
.set_rxfh_indir = bnx2x_set_rxfh_indir,
+ .get_channels = bnx2x_get_channels,
+ .set_channels = bnx2x_set_channels,
.get_eee = bnx2x_get_eee,
.set_eee = bnx2x_set_eee,
};
#define DRV_MSG_CODE_DCBX_ADMIN_PMF_MSG 0xb0000000
#define DRV_MSG_CODE_DCBX_PMF_DRV_OK 0xb2000000
+ #define REQ_BC_VER_4_DCBX_ADMIN_MSG_NON_PMF 0x00070401
#define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000
MDIO_WC_REG_DIGITAL4_MISC3, val | 0x8080);
/* Enable LPI pass through */
- if ((params->eee_mode & EEE_MODE_ADV_LPI) &&
- (phy->flags & FLAGS_EEE_10GBT) &&
- (!(params->eee_mode & EEE_MODE_ENABLE_LPI) ||
- bnx2x_eee_calc_timer(params)) &&
- (params->req_duplex[bnx2x_phy_selection(params)] == DUPLEX_FULL)) {
- DP(NETIF_MSG_LINK, "Configure WC for LPI pass through\n");
- bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
- MDIO_WC_REG_EEE_COMBO_CONTROL0,
- 0x7c);
- bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
- MDIO_WC_REG_DIGITAL4_MISC5, 0xc000);
- }
+ DP(NETIF_MSG_LINK, "Configure WC for LPI pass through\n");
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_EEE_COMBO_CONTROL0,
+ 0x7c);
+ bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_DIGITAL4_MISC5, 0xc000);
/* 10G XFI Full Duplex */
bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
#define INT_MODE_INTx 1
#define INT_MODE_MSI 2
-static int int_mode;
+int int_mode;
module_param(int_mode, int, 0);
MODULE_PARM_DESC(int_mode, " Force interrupt mode other than MSI-X "
"(1 INT#x; 2 MSI)");
/* Tx */
for_each_cos_in_tx_queue(fp, cos)
{
- txdata = fp->txdata[cos];
+ txdata = *fp->txdata_ptr[cos];
BNX2X_ERR("fp%d: tx_pkt_prod(0x%x) tx_pkt_cons(0x%x) tx_bd_prod(0x%x) tx_bd_cons(0x%x) *tx_cons_sb(0x%x)\n",
i, txdata.tx_pkt_prod,
txdata.tx_pkt_cons, txdata.tx_bd_prod,
for_each_tx_queue(bp, i) {
struct bnx2x_fastpath *fp = &bp->fp[i];
for_each_cos_in_tx_queue(fp, cos) {
- struct bnx2x_fp_txdata *txdata = &fp->txdata[cos];
+ struct bnx2x_fp_txdata *txdata = fp->txdata_ptr[cos];
start = TX_BD(le16_to_cpu(*txdata->tx_cons_sb) - 10);
end = TX_BD(le16_to_cpu(*txdata->tx_cons_sb) + 245);
int cid = SW_CID(rr_cqe->ramrod_cqe.conn_and_cmd_data);
int command = CQE_CMD(rr_cqe->ramrod_cqe.conn_and_cmd_data);
enum bnx2x_queue_cmd drv_cmd = BNX2X_Q_CMD_MAX;
- struct bnx2x_queue_sp_obj *q_obj = &fp->q_obj;
+ struct bnx2x_queue_sp_obj *q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
DP(BNX2X_MSG_SP,
"fp %d cid %d got ramrod #%d state is %x type is %d\n",
/* Handle Rx or Tx according to SB id */
prefetch(fp->rx_cons_sb);
for_each_cos_in_tx_queue(fp, cos)
- prefetch(fp->txdata[cos].tx_cons_sb);
+ prefetch(fp->txdata_ptr[cos]->tx_cons_sb);
prefetch(&fp->sb_running_index[SM_RX_ID]);
napi_schedule(&bnx2x_fp(bp, fp->index, napi));
status &= ~mask;
}
}
+ if (load_mode == LOAD_LOOPBACK_EXT) {
+ struct link_params *lp = &bp->link_params;
+ lp->loopback_mode = LOOPBACK_EXT;
+ }
+
rc = bnx2x_phy_init(&bp->link_params, &bp->link_vars);
bnx2x_release_phy_lock(bp);
struct bnx2x_fastpath *fp, struct bnx2x_txq_setup_params *txq_init,
u8 cos)
{
- txq_init->dscr_map = fp->txdata[cos].tx_desc_mapping;
+ txq_init->dscr_map = fp->txdata_ptr[cos]->tx_desc_mapping;
txq_init->sb_cq_index = HC_INDEX_ETH_FIRST_TX_CQ_CONS + cos;
txq_init->traffic_type = LLFC_TRAFFIC_TYPE_NW;
txq_init->fw_sb_id = fp->fw_sb_id;
memcpy(ether_stat->version, DRV_MODULE_VERSION,
ETH_STAT_INFO_VERSION_LEN - 1);
- bp->fp[0].mac_obj.get_n_elements(bp, &bp->fp[0].mac_obj,
- DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED,
- ether_stat->mac_local);
+ bp->sp_objs[0].mac_obj.get_n_elements(bp, &bp->sp_objs[0].mac_obj,
+ DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED,
+ ether_stat->mac_local);
ether_stat->mtu_size = bp->dev->mtu;
/* insert FCoE stats from ramrod response */
if (!NO_FCOE(bp)) {
struct tstorm_per_queue_stats *fcoe_q_tstorm_stats =
- &bp->fw_stats_data->queue_stats[FCOE_IDX].
+ &bp->fw_stats_data->queue_stats[FCOE_IDX(bp)].
tstorm_queue_statistics;
struct xstorm_per_queue_stats *fcoe_q_xstorm_stats =
- &bp->fw_stats_data->queue_stats[FCOE_IDX].
+ &bp->fw_stats_data->queue_stats[FCOE_IDX(bp)].
xstorm_queue_statistics;
struct fcoe_statistics_params *fw_fcoe_stat =
case BNX2X_FILTER_MAC_PENDING:
DP(BNX2X_MSG_SP, "Got SETUP_MAC completions\n");
#ifdef BCM_CNIC
- if (cid == BNX2X_ISCSI_ETH_CID)
+ if (cid == BNX2X_ISCSI_ETH_CID(bp))
vlan_mac_obj = &bp->iscsi_l2_mac_obj;
else
#endif
- vlan_mac_obj = &bp->fp[cid].mac_obj;
+ vlan_mac_obj = &bp->sp_objs[cid].mac_obj;
break;
case BNX2X_FILTER_MCAST_PENDING:
for_each_eth_queue(bp, q) {
/* Set the appropriate Queue object */
fp = &bp->fp[q];
- queue_params.q_obj = &fp->q_obj;
+ queue_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
/* send the ramrod */
rc = bnx2x_queue_state_change(bp, &queue_params);
#ifdef BCM_CNIC
if (!NO_FCOE(bp)) {
- fp = &bp->fp[FCOE_IDX];
- queue_params.q_obj = &fp->q_obj;
+ fp = &bp->fp[FCOE_IDX(bp)];
+ queue_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
/* clear pending completion bit */
__clear_bit(RAMROD_COMP_WAIT, &queue_params.ramrod_flags);
{
DP(BNX2X_MSG_SP, "retrieving fp from cid %d\n", cid);
#ifdef BCM_CNIC
- if (cid == BNX2X_FCOE_ETH_CID)
- return &bnx2x_fcoe(bp, q_obj);
+ if (cid == BNX2X_FCOE_ETH_CID(bp))
+ return &bnx2x_fcoe_sp_obj(bp, q_obj);
else
#endif
- return &bnx2x_fp(bp, CID_TO_FP(cid), q_obj);
+ return &bp->sp_objs[CID_TO_FP(cid, bp)].q_obj;
}
static void bnx2x_eq_int(struct bnx2x *bp)
/* init tx data */
for_each_cos_in_tx_queue(fp, cos) {
- bnx2x_init_txdata(bp, &fp->txdata[cos],
- CID_COS_TO_TX_ONLY_CID(fp->cid, cos),
- FP_COS_TO_TXQ(fp, cos),
- BNX2X_TX_SB_INDEX_BASE + cos);
- cids[cos] = fp->txdata[cos].cid;
+ bnx2x_init_txdata(bp, fp->txdata_ptr[cos],
+ CID_COS_TO_TX_ONLY_CID(fp->cid, cos, bp),
+ FP_COS_TO_TXQ(fp, cos, bp),
+ BNX2X_TX_SB_INDEX_BASE + cos, fp);
+ cids[cos] = fp->txdata_ptr[cos]->cid;
}
- bnx2x_init_queue_obj(bp, &fp->q_obj, fp->cl_id, cids, fp->max_cos,
- BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
+ bnx2x_init_queue_obj(bp, &bnx2x_sp_obj(bp, fp).q_obj, fp->cl_id, cids,
+ fp->max_cos, BP_FUNC(bp), bnx2x_sp(bp, q_rdata),
bnx2x_sp_mapping(bp, q_rdata), q_type);
/**
for_each_tx_queue(bp, i)
for_each_cos_in_tx_queue(&bp->fp[i], cos)
- bnx2x_init_tx_ring_one(&bp->fp[i].txdata[cos]);
+ bnx2x_init_tx_ring_one(bp->fp[i].txdata_ptr[cos]);
}
void bnx2x_nic_init(struct bnx2x *bp, u32 load_code)
cdu_ilt_start = ilt->clients[ILT_CLIENT_CDU].start;
for (i = 0; i < L2_ILT_LINES(bp); i++) {
- ilt->lines[cdu_ilt_start + i].page =
- bp->context.vcxt + (ILT_PAGE_CIDS * i);
+ ilt->lines[cdu_ilt_start + i].page = bp->context[i].vcxt;
ilt->lines[cdu_ilt_start + i].page_mapping =
- bp->context.cxt_mapping + (CDU_ILT_PAGE_SZ * i);
- /* cdu ilt pages are allocated manually so there's no need to
- set the size */
+ bp->context[i].cxt_mapping;
+ ilt->lines[cdu_ilt_start + i].size = bp->context[i].size;
}
bnx2x_ilt_init_op(bp, INITOP_SET);
void bnx2x_free_mem(struct bnx2x *bp)
{
+ int i;
+
/* fastpath */
bnx2x_free_fp_mem(bp);
/* end of fastpath */
BNX2X_PCI_FREE(bp->slowpath, bp->slowpath_mapping,
sizeof(struct bnx2x_slowpath));
- BNX2X_PCI_FREE(bp->context.vcxt, bp->context.cxt_mapping,
- bp->context.size);
-
+ for (i = 0; i < L2_ILT_LINES(bp); i++)
+ BNX2X_PCI_FREE(bp->context[i].vcxt, bp->context[i].cxt_mapping,
+ bp->context[i].size);
bnx2x_ilt_mem_op(bp, ILT_MEMOP_FREE);
BNX2X_FREE(bp->ilt->lines);
int bnx2x_alloc_mem(struct bnx2x *bp)
{
+ int i, allocated, context_size;
+
#ifdef BCM_CNIC
if (!CHIP_IS_E1x(bp))
/* size = the status block + ramrod buffers */
if (bnx2x_alloc_fw_stats_mem(bp))
goto alloc_mem_err;
- bp->context.size = sizeof(union cdu_context) * BNX2X_L2_CID_COUNT(bp);
-
- BNX2X_PCI_ALLOC(bp->context.vcxt, &bp->context.cxt_mapping,
- bp->context.size);
+ /* Allocate memory for CDU context:
+ * This memory is allocated separately and not in the generic ILT
+ * functions because CDU differs in few aspects:
+ * 1. There are multiple entities allocating memory for context -
+ * 'regular' driver, CNIC and SRIOV driver. Each separately controls
+ * its own ILT lines.
+ * 2. Since CDU page-size is not a single 4KB page (which is the case
+ * for the other ILT clients), to be efficient we want to support
+ * allocation of sub-page-size in the last entry.
+ * 3. Context pointers are used by the driver to pass to FW / update
+ * the context (for the other ILT clients the pointers are used just to
+ * free the memory during unload).
+ */
+ context_size = sizeof(union cdu_context) * BNX2X_L2_CID_COUNT(bp);
+ for (i = 0, allocated = 0; allocated < context_size; i++) {
+ bp->context[i].size = min(CDU_ILT_PAGE_SZ,
+ (context_size - allocated));
+ BNX2X_PCI_ALLOC(bp->context[i].vcxt,
+ &bp->context[i].cxt_mapping,
+ bp->context[i].size);
+ allocated += bp->context[i].size;
+ }
BNX2X_ALLOC(bp->ilt->lines, sizeof(struct ilt_line) * ILT_MAX_LINES);
if (bnx2x_ilt_mem_op(bp, ILT_MEMOP_ALLOC))
__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
/* Eth MAC is set on RSS leading client (fp[0]) */
- return bnx2x_set_mac_one(bp, bp->dev->dev_addr, &bp->fp->mac_obj, set,
- BNX2X_ETH_MAC, &ramrod_flags);
+ return bnx2x_set_mac_one(bp, bp->dev->dev_addr, &bp->sp_objs->mac_obj,
+ set, BNX2X_ETH_MAC, &ramrod_flags);
}
int bnx2x_setup_leading(struct bnx2x *bp)
*
* In case of MSI-X it will also try to enable MSI-X.
*/
-static void __devinit bnx2x_set_int_mode(struct bnx2x *bp)
+void bnx2x_set_int_mode(struct bnx2x *bp)
{
switch (int_mode) {
case INT_MODE_MSI:
BNX2X_DEV_INFO("set number of queues to 1\n");
break;
default:
- /* Set number of queues for MSI-X mode */
- bnx2x_set_num_queues(bp);
-
- BNX2X_DEV_INFO("set number of queues to %d\n", bp->num_queues);
-
/* if we can't use MSI-X we only need one fp,
* so try to enable MSI-X with the requested number of fp's
* and fallback to MSI or legacy INTx with one fp
{
u8 cos;
+ int cxt_index, cxt_offset;
+
/* FCoE Queue uses Default SB, thus has no HC capabilities */
if (!IS_FCOE_FP(fp)) {
__set_bit(BNX2X_Q_FLG_HC, &init_params->rx.flags);
fp->index, init_params->max_cos);
/* set the context pointers queue object */
- for (cos = FIRST_TX_COS_INDEX; cos < init_params->max_cos; cos++)
+ for (cos = FIRST_TX_COS_INDEX; cos < init_params->max_cos; cos++) {
+ cxt_index = fp->txdata_ptr[cos]->cid / ILT_PAGE_CIDS;
+ cxt_offset = fp->txdata_ptr[cos]->cid - (cxt_index *
+ ILT_PAGE_CIDS);
init_params->cxts[cos] =
- &bp->context.vcxt[fp->txdata[cos].cid].eth;
+ &bp->context[cxt_index].vcxt[cxt_offset].eth;
+ }
}
int bnx2x_setup_tx_only(struct bnx2x *bp, struct bnx2x_fastpath *fp,
bnx2x_ack_sb(bp, fp->igu_sb_id, USTORM_ID, 0,
IGU_INT_ENABLE, 0);
- q_params.q_obj = &fp->q_obj;
+ q_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
/* We want to wait for completion in this context */
__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
DP(NETIF_MSG_IFDOWN, "stopping queue %d cid %d\n", index, fp->cid);
- q_params.q_obj = &fp->q_obj;
+ q_params.q_obj = &bnx2x_sp_obj(bp, fp).q_obj;
/* We want to wait for completion in this context */
__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
tx_index++){
/* ascertain this is a normal queue*/
- txdata = &fp->txdata[tx_index];
+ txdata = fp->txdata_ptr[tx_index];
DP(NETIF_MSG_IFDOWN, "stopping tx-only queue %d\n",
txdata->txq_index);
struct bnx2x_fastpath *fp = &bp->fp[i];
for_each_cos_in_tx_queue(fp, cos)
- rc = bnx2x_clean_tx_queue(bp, &fp->txdata[cos]);
+ rc = bnx2x_clean_tx_queue(bp, fp->txdata_ptr[cos]);
#ifdef BNX2X_STOP_ON_ERROR
if (rc)
return;
usleep_range(1000, 1000);
/* Clean all ETH MACs */
- rc = bnx2x_del_all_macs(bp, &bp->fp[0].mac_obj, BNX2X_ETH_MAC, false);
+ rc = bnx2x_del_all_macs(bp, &bp->sp_objs[0].mac_obj, BNX2X_ETH_MAC,
+ false);
if (rc < 0)
BNX2X_ERR("Failed to delete all ETH macs: %d\n", rc);
/* Clean up UC list */
- rc = bnx2x_del_all_macs(bp, &bp->fp[0].mac_obj, BNX2X_UC_LIST_MAC,
+ rc = bnx2x_del_all_macs(bp, &bp->sp_objs[0].mac_obj, BNX2X_UC_LIST_MAC,
true);
if (rc < 0)
BNX2X_ERR("Failed to schedule DEL commands for UC MACs list: %d\n",
bp->flags |= (val >= REQ_BC_VER_4_PFC_STATS_SUPPORTED) ?
BC_SUPPORTS_PFC_STATS : 0;
+ bp->flags |= (val >= REQ_BC_VER_4_DCBX_ADMIN_MSG_NON_PMF) ?
+ BC_SUPPORTS_DCBX_MSG_NON_PMF : 0;
boot_mode = SHMEM_RD(bp,
dev_info.port_feature_config[BP_PORT(bp)].mba_config) &
PORT_FEATURE_MBA_BOOT_AGENT_TYPE_MASK;
int rc;
struct net_device *dev = bp->dev;
struct netdev_hw_addr *ha;
- struct bnx2x_vlan_mac_obj *mac_obj = &bp->fp->mac_obj;
+ struct bnx2x_vlan_mac_obj *mac_obj = &bp->sp_objs->mac_obj;
unsigned long ramrod_flags = 0;
/* First schedule a cleanup up of old configuration */
/* must be called after sriov-enable */
static int bnx2x_set_qm_cid_count(struct bnx2x *bp)
{
- int cid_count = BNX2X_L2_CID_COUNT(bp);
+ int cid_count = BNX2X_L2_MAX_CID(bp);
#ifdef BCM_CNIC
cid_count += CNIC_CID_MAX;
struct bnx2x *bp;
int pcie_width, pcie_speed;
int rc, max_non_def_sbs;
- int rx_count, tx_count, rss_count;
+ int rx_count, tx_count, rss_count, doorbell_size;
/*
* An estimated maximum supported CoS number according to the chip
* version.
max_non_def_sbs = bnx2x_get_num_non_def_sbs(pdev);
- /* !!! FIXME !!!
- * Do not allow the maximum SB count to grow above 16
- * since Special CIDs starts from 16*BNX2X_MULTI_TX_COS=48.
- * We will use the FP_SB_MAX_E1x macro for this matter.
- */
- max_non_def_sbs = min_t(int, FP_SB_MAX_E1x, max_non_def_sbs);
-
WARN_ON(!max_non_def_sbs);
/* Maximum number of RSS queues: one IGU SB goes to CNIC */
/*
* Maximum number of netdev Tx queues:
- * Maximum TSS queues * Maximum supported number of CoS + FCoE L2
+ * Maximum TSS queues * Maximum supported number of CoS + FCoE L2
*/
- tx_count = MAX_TXQS_PER_COS * max_cos_est + FCOE_PRESENT;
+ tx_count = rss_count * max_cos_est + FCOE_PRESENT;
/* dev zeroed in init_etherdev */
dev = alloc_etherdev_mqs(sizeof(*bp), tx_count, rx_count);
bp = netdev_priv(dev);
- BNX2X_DEV_INFO("Allocated netdev with %d tx and %d rx queues\n",
- tx_count, rx_count);
-
bp->igu_sb_cnt = max_non_def_sbs;
bp->msg_enable = debug;
pci_set_drvdata(pdev, dev);
BNX2X_DEV_INFO("max_non_def_sbs %d\n", max_non_def_sbs);
+ BNX2X_DEV_INFO("Allocated netdev with %d tx and %d rx queues\n",
+ tx_count, rx_count);
+
rc = bnx2x_init_bp(bp);
if (rc)
goto init_one_exit;
* Map doorbels here as we need the real value of bp->max_cos which
* is initialized in bnx2x_init_bp().
*/
+ doorbell_size = BNX2X_L2_MAX_CID(bp) * (1 << BNX2X_DB_SHIFT);
+ if (doorbell_size > pci_resource_len(pdev, 2)) {
+ dev_err(&bp->pdev->dev,
+ "Cannot map doorbells, bar size too small, aborting\n");
+ rc = -ENOMEM;
+ goto init_one_exit;
+ }
bp->doorbells = ioremap_nocache(pci_resource_start(pdev, 2),
- min_t(u64, BNX2X_DB_SIZE(bp),
- pci_resource_len(pdev, 2)));
+ doorbell_size);
if (!bp->doorbells) {
dev_err(&bp->pdev->dev,
"Cannot map doorbell space, aborting\n");
#endif
+
+ /* Set bp->num_queues for MSI-X mode*/
+ bnx2x_set_num_queues(bp);
+
/* Configure interrupt mode: try to enable MSI-X/MSI if
- * needed, set bp->num_queues appropriately.
+ * needed.
*/
bnx2x_set_int_mode(bp);
static void bnx2x_cnic_sp_post(struct bnx2x *bp, int count)
{
struct eth_spe *spe;
+ int cxt_index, cxt_offset;
#ifdef BNX2X_STOP_ON_ERROR
if (unlikely(bp->panic))
* ramrod
*/
if (type == ETH_CONNECTION_TYPE) {
- if (cmd == RAMROD_CMD_ID_ETH_CLIENT_SETUP)
- bnx2x_set_ctx_validation(bp, &bp->context.
- vcxt[BNX2X_ISCSI_ETH_CID].eth,
- BNX2X_ISCSI_ETH_CID);
+ if (cmd == RAMROD_CMD_ID_ETH_CLIENT_SETUP) {
+ cxt_index = BNX2X_ISCSI_ETH_CID(bp) /
+ ILT_PAGE_CIDS;
+ cxt_offset = BNX2X_ISCSI_ETH_CID(bp) -
+ (cxt_index * ILT_PAGE_CIDS);
+ bnx2x_set_ctx_validation(bp,
+ &bp->context[cxt_index].
+ vcxt[cxt_offset].eth,
+ BNX2X_ISCSI_ETH_CID(bp));
+ }
}
/*
cp->num_irq = 2;
}
+void bnx2x_setup_cnic_info(struct bnx2x *bp)
+{
+ struct cnic_eth_dev *cp = &bp->cnic_eth_dev;
+
+
+ cp->ctx_tbl_offset = FUNC_ILT_BASE(BP_FUNC(bp)) +
+ bnx2x_cid_ilt_lines(bp);
+ cp->starting_cid = bnx2x_cid_ilt_lines(bp) * ILT_PAGE_CIDS;
+ cp->fcoe_init_cid = BNX2X_FCOE_ETH_CID(bp);
+ cp->iscsi_l2_cid = BNX2X_ISCSI_ETH_CID(bp);
+
+ if (NO_ISCSI_OOO(bp))
+ cp->drv_state |= CNIC_DRV_STATE_NO_ISCSI_OOO;
+}
+
static int bnx2x_register_cnic(struct net_device *dev, struct cnic_ops *ops,
void *data)
{
cp->drv_ctl = bnx2x_drv_ctl;
cp->drv_register_cnic = bnx2x_register_cnic;
cp->drv_unregister_cnic = bnx2x_unregister_cnic;
- cp->fcoe_init_cid = BNX2X_FCOE_ETH_CID;
+ cp->fcoe_init_cid = BNX2X_FCOE_ETH_CID(bp);
cp->iscsi_l2_client_id =
bnx2x_cnic_eth_cl_id(bp, BNX2X_ISCSI_ETH_CL_ID_IDX);
- cp->iscsi_l2_cid = BNX2X_ISCSI_ETH_CID;
+ cp->iscsi_l2_cid = BNX2X_ISCSI_ETH_CID(bp);
if (NO_ISCSI_OOO(bp))
cp->drv_state |= CNIC_DRV_STATE_NO_ISCSI_OOO;
#define MISC_REGISTERS_SPIO_OUTPUT_LOW 0
#define MISC_REGISTERS_SPIO_SET_POS 8
#define HW_LOCK_MAX_RESOURCE_VALUE 31
+#define HW_LOCK_RESOURCE_DCBX_ADMIN_MIB 13
#define HW_LOCK_RESOURCE_DRV_FLAGS 10
#define HW_LOCK_RESOURCE_GPIO 1
#define HW_LOCK_RESOURCE_MDIO 0
data->capabilities |=
ETH_RSS_UPDATE_RAMROD_DATA_IPV4_TCP_CAPABILITY;
+ if (test_bit(BNX2X_RSS_IPV4_UDP, &p->rss_flags))
+ data->capabilities |=
+ ETH_RSS_UPDATE_RAMROD_DATA_IPV4_UDP_CAPABILITY;
+
if (test_bit(BNX2X_RSS_IPV6, &p->rss_flags))
data->capabilities |=
ETH_RSS_UPDATE_RAMROD_DATA_IPV6_CAPABILITY;
data->capabilities |=
ETH_RSS_UPDATE_RAMROD_DATA_IPV6_TCP_CAPABILITY;
+ if (test_bit(BNX2X_RSS_IPV6_UDP, &p->rss_flags))
+ data->capabilities |=
+ ETH_RSS_UPDATE_RAMROD_DATA_IPV6_UDP_CAPABILITY;
+
/* Hashing mask */
data->rss_result_mask = p->rss_result_mask;
BNX2X_RSS_IPV4,
BNX2X_RSS_IPV4_TCP,
+ BNX2X_RSS_IPV4_UDP,
BNX2X_RSS_IPV6,
BNX2X_RSS_IPV6_TCP,
+ BNX2X_RSS_IPV6_UDP,
};
struct bnx2x_config_rss_params {
/* Last configured indirection table */
u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE];
+ /* flags for enabling 4-tupple hash on UDP */
+ u8 udp_rss_v4;
+ u8 udp_rss_v6;
+
int (*config_rss)(struct bnx2x *bp,
struct bnx2x_config_rss_params *p);
};
struct tstorm_per_queue_stats *tclient =
&bp->fw_stats_data->queue_stats[i].
tstorm_queue_statistics;
- struct tstorm_per_queue_stats *old_tclient = &fp->old_tclient;
+ struct tstorm_per_queue_stats *old_tclient =
+ &bnx2x_fp_stats(bp, fp)->old_tclient;
struct ustorm_per_queue_stats *uclient =
&bp->fw_stats_data->queue_stats[i].
ustorm_queue_statistics;
- struct ustorm_per_queue_stats *old_uclient = &fp->old_uclient;
+ struct ustorm_per_queue_stats *old_uclient =
+ &bnx2x_fp_stats(bp, fp)->old_uclient;
struct xstorm_per_queue_stats *xclient =
&bp->fw_stats_data->queue_stats[i].
xstorm_queue_statistics;
- struct xstorm_per_queue_stats *old_xclient = &fp->old_xclient;
- struct bnx2x_eth_q_stats *qstats = &fp->eth_q_stats;
- struct bnx2x_eth_q_stats_old *qstats_old = &fp->eth_q_stats_old;
+ struct xstorm_per_queue_stats *old_xclient =
+ &bnx2x_fp_stats(bp, fp)->old_xclient;
+ struct bnx2x_eth_q_stats *qstats =
+ &bnx2x_fp_stats(bp, fp)->eth_q_stats;
+ struct bnx2x_eth_q_stats_old *qstats_old =
+ &bnx2x_fp_stats(bp, fp)->eth_q_stats_old;
u32 diff;
nstats->tx_bytes = bnx2x_hilo(&estats->total_bytes_transmitted_hi);
tmp = estats->mac_discard;
- for_each_rx_queue(bp, i)
- tmp += le32_to_cpu(bp->fp[i].old_tclient.checksum_discard);
+ for_each_rx_queue(bp, i) {
+ struct tstorm_per_queue_stats *old_tclient =
+ &bp->fp_stats[i].old_tclient;
+ tmp += le32_to_cpu(old_tclient->checksum_discard);
+ }
nstats->rx_dropped = tmp + bp->net_stats_old.rx_dropped;
nstats->tx_dropped = 0;
int i;
for_each_queue(bp, i) {
- struct bnx2x_eth_q_stats *qstats = &bp->fp[i].eth_q_stats;
+ struct bnx2x_eth_q_stats *qstats = &bp->fp_stats[i].eth_q_stats;
struct bnx2x_eth_q_stats_old *qstats_old =
- &bp->fp[i].eth_q_stats_old;
+ &bp->fp_stats[i].eth_q_stats_old;
UPDATE_ESTAT_QSTAT(driver_xoff);
UPDATE_ESTAT_QSTAT(rx_err_discard_pkt);
query[first_queue_query_index + i];
cur_query_entry->kind = STATS_TYPE_QUEUE;
- cur_query_entry->index = bnx2x_stats_id(&bp->fp[FCOE_IDX]);
+ cur_query_entry->index = bnx2x_stats_id(&bp->fp[FCOE_IDX(bp)]);
cur_query_entry->funcID = cpu_to_le16(BP_FUNC(bp));
cur_query_entry->address.hi =
cpu_to_le32(U64_HI(cur_data_offset));
/* function stats */
for_each_queue(bp, i) {
- struct bnx2x_fastpath *fp = &bp->fp[i];
-
- memset(&fp->old_tclient, 0, sizeof(fp->old_tclient));
- memset(&fp->old_uclient, 0, sizeof(fp->old_uclient));
- memset(&fp->old_xclient, 0, sizeof(fp->old_xclient));
+ struct bnx2x_fp_stats *fp_stats = &bp->fp_stats[i];
+
+ memset(&fp_stats->old_tclient, 0,
+ sizeof(fp_stats->old_tclient));
+ memset(&fp_stats->old_uclient, 0,
+ sizeof(fp_stats->old_uclient));
+ memset(&fp_stats->old_xclient, 0,
+ sizeof(fp_stats->old_xclient));
if (bp->stats_init) {
- memset(&fp->eth_q_stats, 0, sizeof(fp->eth_q_stats));
- memset(&fp->eth_q_stats_old, 0,
- sizeof(fp->eth_q_stats_old));
+ memset(&fp_stats->eth_q_stats, 0,
+ sizeof(fp_stats->eth_q_stats));
+ memset(&fp_stats->eth_q_stats_old, 0,
+ sizeof(fp_stats->eth_q_stats_old));
}
}
/* save queue statistics */
for_each_eth_queue(bp, i) {
struct bnx2x_fastpath *fp = &bp->fp[i];
- struct bnx2x_eth_q_stats *qstats = &fp->eth_q_stats;
- struct bnx2x_eth_q_stats_old *qstats_old = &fp->eth_q_stats_old;
+ struct bnx2x_eth_q_stats *qstats =
+ &bnx2x_fp_stats(bp, fp)->eth_q_stats;
+ struct bnx2x_eth_q_stats_old *qstats_old =
+ &bnx2x_fp_stats(bp, fp)->eth_q_stats_old;
UPDATE_QSTAT_OLD(total_unicast_bytes_received_hi);
UPDATE_QSTAT_OLD(total_unicast_bytes_received_lo);
struct afex_stats *afex_stats = (struct afex_stats *)void_afex_stats;
struct bnx2x_eth_stats *estats = &bp->eth_stats;
struct per_queue_stats *fcoe_q_stats =
- &bp->fw_stats_data->queue_stats[FCOE_IDX];
+ &bp->fw_stats_data->queue_stats[FCOE_IDX(bp)];
struct tstorm_per_queue_stats *fcoe_q_tstorm_stats =
&fcoe_q_stats->tstorm_queue_statistics;
memset(afex_stats, 0, sizeof(struct afex_stats));
for_each_eth_queue(bp, i) {
- struct bnx2x_fastpath *fp = &bp->fp[i];
- struct bnx2x_eth_q_stats *qstats = &fp->eth_q_stats;
+ struct bnx2x_eth_q_stats *qstats = &bp->fp_stats[i].eth_q_stats;
ADD_64(afex_stats->rx_unicast_bytes_hi,
qstats->total_unicast_bytes_received_hi,
}
if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw))
- e_info("PHY reset is blocked due to SOL/IDER session.\n");
+ dev_info(&pdev->dev,
+ "PHY reset is blocked due to SOL/IDER session.\n");
/* Set initial default active device features */
netdev->features = (NETIF_F_SG |
if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
break;
if (i == 2) {
- e_err("The NVM Checksum Is Not Valid\n");
+ dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
err = -EIO;
goto err_eeprom;
}
/* copy the MAC address */
if (e1000e_read_mac_addr(&adapter->hw))
- e_err("NVM Read Error while reading MAC address\n");
+ dev_err(&pdev->dev,
+ "NVM Read Error while reading MAC address\n");
memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len);
memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);
if (!is_valid_ether_addr(netdev->perm_addr)) {
- e_err("Invalid MAC Address: %pM\n", netdev->perm_addr);
+ dev_err(&pdev->dev, "Invalid MAC Address: %pM\n",
+ netdev->perm_addr);
err = -EIO;
goto err_eeprom;
}
case enable_option:
switch (*value) {
case OPTION_ENABLED:
- e_info("%s Enabled\n", opt->name);
+ dev_info(&adapter->pdev->dev, "%s Enabled\n",
+ opt->name);
return 0;
case OPTION_DISABLED:
- e_info("%s Disabled\n", opt->name);
+ dev_info(&adapter->pdev->dev, "%s Disabled\n",
+ opt->name);
return 0;
}
break;
case range_option:
if (*value >= opt->arg.r.min && *value <= opt->arg.r.max) {
- e_info("%s set to %i\n", opt->name, *value);
+ dev_info(&adapter->pdev->dev, "%s set to %i\n",
+ opt->name, *value);
return 0;
}
break;
ent = &opt->arg.l.p[i];
if (*value == ent->i) {
if (ent->str[0] != '\0')
- e_info("%s\n", ent->str);
+ dev_info(&adapter->pdev->dev, "%s\n",
+ ent->str);
return 0;
}
}
BUG();
}
- e_info("Invalid %s value specified (%i) %s\n", opt->name, *value,
- opt->err);
+ dev_info(&adapter->pdev->dev, "Invalid %s value specified (%i) %s\n",
+ opt->name, *value, opt->err);
*value = opt->def;
return -1;
}
int bd = adapter->bd_number;
if (bd >= E1000_MAX_NIC) {
- e_notice("Warning: no configuration for board #%i\n", bd);
- e_notice("Using defaults for all values\n");
+ dev_notice(&adapter->pdev->dev,
+ "Warning: no configuration for board #%i\n", bd);
+ dev_notice(&adapter->pdev->dev,
+ "Using defaults for all values\n");
}
{ /* Transmit Interrupt Delay */
* default values
*/
if (adapter->itr > 4)
- e_info("%s set to default %d\n", opt.name,
- adapter->itr);
+ dev_info(&adapter->pdev->dev,
+ "%s set to default %d\n", opt.name,
+ adapter->itr);
}
adapter->itr_setting = adapter->itr;
switch (adapter->itr) {
case 0:
- e_info("%s turned off\n", opt.name);
+ dev_info(&adapter->pdev->dev, "%s turned off\n",
+ opt.name);
break;
case 1:
- e_info("%s set to dynamic mode\n", opt.name);
+ dev_info(&adapter->pdev->dev,
+ "%s set to dynamic mode\n", opt.name);
adapter->itr = 20000;
break;
case 3:
- e_info("%s set to dynamic conservative mode\n",
- opt.name);
+ dev_info(&adapter->pdev->dev,
+ "%s set to dynamic conservative mode\n",
+ opt.name);
adapter->itr = 20000;
break;
case 4:
- e_info("%s set to simplified (2000-8000 ints) mode\n",
- opt.name);
+ dev_info(&adapter->pdev->dev,
+ "%s set to simplified (2000-8000 ints) mode\n",
+ opt.name);
break;
default:
/*
ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \
ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
- ixgbe_mbx.o ixgbe_x540.o ixgbe_sysfs.o ixgbe_lib.o
+ ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o
ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \
ixgbe_dcb_82599.o ixgbe_dcb_nl.o
ixgbe-$(CONFIG_IXGBE_PTP) += ixgbe_ptp.o
-
+ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o
ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o
spinlock_t tmreg_lock;
struct cyclecounter cc;
struct timecounter tc;
+ int rx_hwtstamp_filter;
u32 base_incval;
u32 cycle_speed;
#endif /* CONFIG_IXGBE_PTP */
extern void ixgbe_ptp_tx_hwtstamp(struct ixgbe_q_vector *q_vector,
struct sk_buff *skb);
extern void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
+ union ixgbe_adv_rx_desc *rx_desc,
struct sk_buff *skb);
extern int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
struct ifreq *ifr, int cmd);
total_packets += tx_buffer->gso_segs;
#ifdef CONFIG_IXGBE_PTP
- if (unlikely(tx_buffer->tx_flags &
- IXGBE_TX_FLAGS_TSTAMP))
- ixgbe_ptp_tx_hwtstamp(q_vector,
- tx_buffer->skb);
-
+ if (unlikely(tx_buffer->tx_flags & IXGBE_TX_FLAGS_TSTAMP))
+ ixgbe_ptp_tx_hwtstamp(q_vector, tx_buffer->skb);
#endif
+
/* free the skb */
dev_kfree_skb_any(tx_buffer->skb);
ixgbe_rx_checksum(rx_ring, rx_desc, skb);
#ifdef CONFIG_IXGBE_PTP
- if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS))
- ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, skb);
+ ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);
#endif
if ((dev->features & NETIF_F_HW_VLAN_RX) &&
*******************************************************************************/
#include "ixgbe.h"
#include <linux/export.h>
+#include <linux/ptp_classify.h>
/*
* The 82599 and the X540 do not have true 64bit nanosecond scale
#define NSECS_PER_SEC 1000000000ULL
#endif
+static struct sock_filter ptp_filter[] = {
+ PTP_FILTER
+};
+
/**
* ixgbe_ptp_read - read raw cycle counter (to be used by time counter)
* @cc - the cyclecounter structure
!(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED))
return;
- switch (hw->mac.type) {
- case ixgbe_mac_X540:
- if (eicr & IXGBE_EICR_TIMESYNC)
+ if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) {
+ switch (hw->mac.type) {
+ case ixgbe_mac_X540:
ptp_clock_event(adapter->ptp_clock, &event);
- break;
- default:
- break;
+ break;
+ default:
+ break;
+ }
}
}
}
}
+/**
+ * ixgbe_ptp_match - determine if this skb matches a ptp packet
+ * @skb: pointer to the skb
+ * @hwtstamp: pointer to the hwtstamp_config to check
+ *
+ * Determine whether the skb should have been timestamped, assuming the
+ * hwtstamp was set via the hwtstamp ioctl. Returns non-zero when the packet
+ * should have a timestamp waiting in the registers, and 0 otherwise.
+ *
+ * V1 packets have to check the version type to determine whether they are
+ * correct. However, we can't directly access the data because it might be
+ * fragmented in the SKB, in paged memory. In order to work around this, we
+ * use skb_copy_bits which will properly copy the data whether it is in the
+ * paged memory fragments or not. We have to copy the IP header as well as the
+ * message type.
+ */
+static int ixgbe_ptp_match(struct sk_buff *skb, int rx_filter)
+{
+ struct iphdr iph;
+ u8 msgtype;
+ unsigned int type, offset;
+
+ if (rx_filter == HWTSTAMP_FILTER_NONE)
+ return 0;
+
+ type = sk_run_filter(skb, ptp_filter);
+
+ if (likely(rx_filter == HWTSTAMP_FILTER_PTP_V2_EVENT))
+ return type & PTP_CLASS_V2;
+
+ /* For the remaining cases actually check message type */
+ switch (type) {
+ case PTP_CLASS_V1_IPV4:
+ skb_copy_bits(skb, OFF_IHL, &iph, sizeof(iph));
+ offset = ETH_HLEN + (iph.ihl << 2) + UDP_HLEN + OFF_PTP_CONTROL;
+ break;
+ case PTP_CLASS_V1_IPV6:
+ offset = OFF_PTP6 + OFF_PTP_CONTROL;
+ break;
+ default:
+ /* other cases invalid or handled above */
+ return 0;
+ }
+
+ /* Make sure our buffer is long enough */
+ if (skb->len < offset)
+ return 0;
+
+ skb_copy_bits(skb, offset, &msgtype, sizeof(msgtype));
+
+ switch (rx_filter) {
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ return (msgtype == IXGBE_RXMTRL_V1_SYNC_MSG);
+ break;
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ return (msgtype == IXGBE_RXMTRL_V1_DELAY_REQ_MSG);
+ break;
+ default:
+ return 0;
+ }
+}
+
/**
* ixgbe_ptp_tx_hwtstamp - utility function which checks for TX time stamp
* @q_vector: structure containing interrupt and ring information
/**
* ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp
* @q_vector: structure containing interrupt and ring information
+ * @rx_desc: the rx descriptor
* @skb: particular skb to send timestamp with
*
* if the timestamp is valid, we convert it into the timecounter ns
* is passed up the network stack
*/
void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
+ union ixgbe_adv_rx_desc *rx_desc,
struct sk_buff *skb)
{
struct ixgbe_adapter *adapter;
hw = &adapter->hw;
tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL);
+
+ /* Check if we have a valid timestamp and make sure the skb should
+ * have been timestamped */
+ if (likely(!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID) ||
+ !ixgbe_ptp_match(skb, adapter->rx_hwtstamp_filter)))
+ return;
+
+ /*
+ * Always read the registers, in order to clear a possible fault
+ * because of stagnant RX timestamp values for a packet that never
+ * reached the queue.
+ */
regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL);
regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32;
/*
- * If this bit is set, then the RX registers contain the time stamp. No
- * other packet will be time stamped until we read these registers, so
- * read the registers to make them available again. Because only one
- * packet can be time stamped at a time, we know that the register
- * values must belong to this one here and therefore we don't need to
- * compare any of the additional attributes stored for it.
+ * If the timestamp bit is set in the packet's descriptor, we know the
+ * timestamp belongs to this packet. No other packet can be
+ * timestamped until the registers for timestamping have been read.
+ * Therefor only one packet with this bit can be in the queue at a
+ * time, and the rx timestamp values that were in the registers belong
+ * to this packet.
*
* If nothing went wrong, then it should have a skb_shared_tx that we
* can turn into a skb_shared_hwtstamps.
*/
- if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID))
+ if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS)))
return;
spin_lock_irqsave(&adapter->tmreg_lock, flags);
* type has to be specified. Matching the kind of event packet is
* not supported, with the exception of "all V2 events regardless of
* level 2 or 4".
+ *
+ * Since hardware always timestamps Path delay packets when timestamping V2
+ * packets, regardless of the type specified in the register, only use V2
+ * Event mode. This more accurately tells the user what the hardware is going
+ * to do anyways.
*/
int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter,
struct ifreq *ifr, int cmd)
tsync_rx_mtrl = IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
is_l4 = true;
break;
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
- tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2;
- tsync_rx_mtrl = IXGBE_RXMTRL_V2_SYNC_MSG;
- is_l2 = true;
- is_l4 = true;
- config.rx_filter = HWTSTAMP_FILTER_SOME;
- break;
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
- tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2;
- tsync_rx_mtrl = IXGBE_RXMTRL_V2_DELAY_REQ_MSG;
- is_l2 = true;
- is_l4 = true;
- config.rx_filter = HWTSTAMP_FILTER_SOME;
- break;
- case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
- case HWTSTAMP_FILTER_PTP_V2_EVENT:
tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2;
- config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
is_l2 = true;
is_l4 = true;
+ config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
break;
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_ALL:
default:
/*
- * register RXMTRL must be set, therefore it is not
- * possible to time stamp both V1 Sync and Delay_Req messages
- * and hardware does not support timestamping all packets
- * => return error
+ * register RXMTRL must be set in order to do V1 packets,
+ * therefore it is not possible to time stamp both V1 Sync and
+ * Delay_Req messages and hardware does not support
+ * timestamping all packets => return error
*/
+ config.rx_filter = HWTSTAMP_FILTER_NONE;
return -ERANGE;
}
return 0;
}
+ /* Store filter value for later use */
+ adapter->rx_hwtstamp_filter = config.rx_filter;
+
/* define ethertype filter for timestamped packets */
if (is_l2)
IXGBE_WRITE_REG(hw, IXGBE_ETQF(3),
return;
}
+ /* initialize the ptp filter */
+ if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter)))
+ e_dev_warn("ptp_filter_init failed\n");
+
spin_lock_init(&adapter->tmreg_lock);
ixgbe_ptp_start_cyclecounter(adapter);
#include <linux/netdevice.h>
#include <linux/hwmon.h>
-#ifdef CONFIG_IXGBE_HWMON
/* hwmon callback functions */
static ssize_t ixgbe_hwmon_show_location(struct device *dev,
struct device_attribute *attr,
exit:
return rc;
}
-#endif /* CONFIG_IXGBE_HWMON */
*/
/* BitTimes (BT) conversion */
-#define IXGBE_BT2KB(BT) ((BT + 1023) / (8 * 1024))
+#define IXGBE_BT2KB(BT) ((BT + (8 * 1024 - 1)) / (8 * 1024))
#define IXGBE_B2BT(BT) (BT * 8)
/* Calculate Delay to respond to PFC */
#define IXGBE_PCI_DELAY 10000
/* Calculate X540 delay value in bit times */
-#define IXGBE_FILL_RATE (36 / 25)
-
-#define IXGBE_DV_X540(LINK, TC) (IXGBE_FILL_RATE * \
- (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \
- (2 * IXGBE_CABLE_DC) + \
- (2 * IXGBE_ID_X540) + \
- IXGBE_HD + IXGBE_B2BT(TC)))
+#define IXGBE_DV_X540(_max_frame_link, _max_frame_tc) \
+ ((36 * \
+ (IXGBE_B2BT(_max_frame_link) + \
+ IXGBE_PFC_D + \
+ (2 * IXGBE_CABLE_DC) + \
+ (2 * IXGBE_ID_X540) + \
+ IXGBE_HD) / 25 + 1) + \
+ 2 * IXGBE_B2BT(_max_frame_tc))
/* Calculate 82599, 82598 delay value in bit times */
-#define IXGBE_DV(LINK, TC) (IXGBE_FILL_RATE * \
- (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \
- (2 * IXGBE_CABLE_DC) + (2 * IXGBE_ID) + \
- IXGBE_HD + IXGBE_B2BT(TC)))
+#define IXGBE_DV(_max_frame_link, _max_frame_tc) \
+ ((36 * \
+ (IXGBE_B2BT(_max_frame_link) + \
+ IXGBE_PFC_D + \
+ (2 * IXGBE_CABLE_DC) + \
+ (2 * IXGBE_ID) + \
+ IXGBE_HD) / 25 + 1) + \
+ 2 * IXGBE_B2BT(_max_frame_tc))
/* Calculate low threshold delay values */
-#define IXGBE_LOW_DV_X540(TC) (2 * IXGBE_B2BT(TC) + \
- (IXGBE_FILL_RATE * IXGBE_PCI_DELAY))
-#define IXGBE_LOW_DV(TC) (2 * IXGBE_LOW_DV_X540(TC))
+#define IXGBE_LOW_DV_X540(_max_frame_tc) \
+ (2 * IXGBE_B2BT(_max_frame_tc) + \
+ (36 * IXGBE_PCI_DELAY / 25) + 1)
+#define IXGBE_LOW_DV(_max_frame_tc) \
+ (2 * IXGBE_LOW_DV_X540(_max_frame_tc))
/* Software ATR hash keys */
#define IXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2
if (slave != dev->caps.function)
memset(inbox->buf, 0, 256);
if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
- *(u8 *) inbox->buf = !!reset_qkey_viols << 6;
+ *(u8 *) inbox->buf |= !!reset_qkey_viols << 6;
((__be32 *) inbox->buf)[2] = agg_cap_mask;
} else {
- ((u8 *) inbox->buf)[3] = !!reset_qkey_viols;
+ ((u8 *) inbox->buf)[3] |= !!reset_qkey_viols;
((__be32 *) inbox->buf)[1] = agg_cap_mask;
}
#define MODNAME "lpc-eth"
#define DRV_VERSION "1.00"
-#define PHYDEF_ADDR 0x00
#define ENET_MAXF_SIZE 1536
#define ENET_RX_DESC 48
#define TXDESC_CONTROL_LAST (1 << 30)
#define TXDESC_CONTROL_INT (1 << 31)
-static int lpc_eth_hard_start_xmit(struct sk_buff *skb,
- struct net_device *ndev);
-
/*
* Structure of a TX/RX descriptors and RX status
*/
spinlock_t lock;
void __iomem *net_base;
u32 msg_enable;
- struct sk_buff *skb[ENET_TX_DESC];
+ unsigned int skblen[ENET_TX_DESC];
unsigned int last_tx_idx;
unsigned int num_used_tx_buffs;
struct mii_bus *mii_bus;
static void __lpc_handle_xmit(struct net_device *ndev)
{
struct netdata_local *pldat = netdev_priv(ndev);
- struct sk_buff *skb;
u32 txcidx, *ptxstat, txstat;
txcidx = readl(LPC_ENET_TXCONSUMEINDEX(pldat->net_base));
while (pldat->last_tx_idx != txcidx) {
- skb = pldat->skb[pldat->last_tx_idx];
+ unsigned int skblen = pldat->skblen[pldat->last_tx_idx];
/* A buffer is available, get buffer status */
ptxstat = &pldat->tx_stat_v[pldat->last_tx_idx];
} else {
/* Update stats */
ndev->stats.tx_packets++;
- ndev->stats.tx_bytes += skb->len;
+ ndev->stats.tx_bytes += skblen;
}
- dev_kfree_skb_irq(skb);
txcidx = readl(LPC_ENET_TXCONSUMEINDEX(pldat->net_base));
}
memcpy(pldat->tx_buff_v + txidx * ENET_MAXF_SIZE, skb->data, len);
/* Save the buffer and increment the buffer counter */
- pldat->skb[txidx] = skb;
+ pldat->skblen[txidx] = len;
pldat->num_used_tx_buffs++;
/* Start transmit */
spin_unlock_irq(&pldat->lock);
+ dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
res->start);
netdev_dbg(ndev, "IO address size :%d\n",
res->end - res->start + 1);
- netdev_err(ndev, "IO address (mapped) :0x%p\n",
+ netdev_dbg(ndev, "IO address (mapped) :0x%p\n",
pldat->net_base);
netdev_dbg(ndev, "IRQ number :%d\n", ndev->irq);
netdev_dbg(ndev, "DMA buffer size :%d\n", pldat->dma_buff_size);
for (i = 0; i < QLCNIC_MAX_PCI_FUNC; i++) {
pfn = pci_info[i].id;
- if (pfn > QLCNIC_MAX_PCI_FUNC) {
+ if (pfn >= QLCNIC_MAX_PCI_FUNC) {
ret = QL_STATUS_INVALID_PARAM;
goto err_eswitch;
}
list_for_each_entry(_maps_node_, &pinctrl_maps, node) \
for (_i_ = 0, _map_ = &_maps_node_->maps[_i_]; \
_i_ < _maps_node_->num_maps; \
- i++, _map_ = &_maps_node_->maps[_i_])
+ _i_++, _map_ = &_maps_node_->maps[_i_])
/**
* pinctrl_provide_dummies() - indicate if pinctrl provides dummy state support
#include "core.h"
#include "pinctrl-imx.h"
-#define IMX_PMX_DUMP(info, p, m, c, n) \
-{ \
- int i, j; \
- printk("Format: Pin Mux Config\n"); \
- for (i = 0; i < n; i++) { \
- j = p[i]; \
- printk("%s %d 0x%lx\n", \
- info->pins[j].name, \
- m[i], c[i]); \
- } \
+#define IMX_PMX_DUMP(info, p, m, c, n) \
+{ \
+ int i, j; \
+ printk(KERN_DEBUG "Format: Pin Mux Config\n"); \
+ for (i = 0; i < n; i++) { \
+ j = p[i]; \
+ printk(KERN_DEBUG "%s %d 0x%lx\n", \
+ info->pins[j].name, \
+ m[i], c[i]); \
+ } \
}
/* The bits in CONFIG cell defined in binding doc*/
/* create mux map */
parent = of_get_parent(np);
- if (!parent)
+ if (!parent) {
+ kfree(new_map);
return -EINVAL;
+ }
new_map[0].type = PIN_MAP_TYPE_MUX_GROUP;
new_map[0].data.mux.function = parent->name;
new_map[0].data.mux.group = np->name;
}
dev_dbg(pctldev->dev, "maps: function %s group %s num %d\n",
- new_map->data.mux.function, new_map->data.mux.group, map_num);
+ (*map)->data.mux.function, (*map)->data.mux.group, map_num);
return 0;
}
static void imx_dt_free_map(struct pinctrl_dev *pctldev,
struct pinctrl_map *map, unsigned num_maps)
{
- int i;
-
- for (i = 0; i < num_maps; i++)
- kfree(map);
+ kfree(map);
}
static struct pinctrl_ops imx_pctrl_ops = {
grp->configs[j] = config & ~IMX_PAD_SION;
}
-#ifdef DEBUG
IMX_PMX_DUMP(info, grp->pins, grp->mux_mode, grp->configs, grp->npins);
-#endif
+
return 0;
}
/* Compose group name */
group = kzalloc(length, GFP_KERNEL);
- if (!group)
- return -ENOMEM;
+ if (!group) {
+ ret = -ENOMEM;
+ goto free;
+ }
snprintf(group, length, "%s.%d", np->name, reg);
new_map[i].data.mux.group = group;
i++;
pconfig = kmemdup(&config, sizeof(config), GFP_KERNEL);
if (!pconfig) {
ret = -ENOMEM;
- goto free;
+ goto free_group;
}
new_map[i].type = PIN_MAP_TYPE_CONFIGS_GROUP;
return 0;
+free_group:
+ if (!purecfg)
+ free(group);
free:
kfree(new_map);
return ret;
return 0;
err:
+ platform_set_drvdata(pdev, NULL);
iounmap(d->base);
return ret;
}
{
struct mxs_pinctrl_data *d = platform_get_drvdata(pdev);
+ platform_set_drvdata(pdev, NULL);
pinctrl_unregister(d->pctl);
iounmap(d->base);
* wakeup is anyhow controlled by the RIMSC and FIMSC registers.
*/
if (nmk_chip->sleepmode && on) {
- __nmk_gpio_set_slpm(nmk_chip, gpio % nmk_chip->chip.base,
+ __nmk_gpio_set_slpm(nmk_chip, gpio % NMK_GPIO_PER_CHIP,
NMK_GPIO_SLPM_WAKEUP_ENABLE);
}
ret = PTR_ERR(clk);
goto out_unmap;
}
+ clk_prepare(clk);
nmk_chip = kzalloc(sizeof(*nmk_chip), GFP_KERNEL);
if (!nmk_chip) {
return ret;
}
-static const struct of_device_id pinmux_ids[] = {
+static const struct of_device_id pinmux_ids[] __devinitconst = {
{ .compatible = "sirf,prima2-gpio-pinmux" },
{}
};
*
* (C) 2009 - Peter Feuerer peter (a) piie.net
* http://piie.net
- * 2009 Borislav Petkov <petkovbb@gmail.com>
+ * 2009 Borislav Petkov bp (a) alien8.de
*
* Inspired by and many thanks to:
* o acerfand - Rachel Greenham
.of_match_table = of_anatop_regulator_match_tbl,
},
.probe = anatop_regulator_probe,
- .remove = anatop_regulator_remove,
+ .remove = __devexit_p(anatop_regulator_remove),
};
static int __init anatop_regulator_init(void)
return -EINVAL;
}
+ if (min_uV < rdev->desc->min_uV)
+ min_uV = rdev->desc->min_uV;
+
ret = DIV_ROUND_UP(min_uV - rdev->desc->min_uV, rdev->desc->uV_step);
if (ret < 0)
return ret;
}
static int gpio_regulator_set_value(struct regulator_dev *dev,
- int min, int max)
+ int min, int max, unsigned *selector)
{
struct gpio_regulator_data *data = rdev_get_drvdata(dev);
- int ptr, target, state, best_val = INT_MAX;
+ int ptr, target = 0, state, best_val = INT_MAX;
for (ptr = 0; ptr < data->nr_states; ptr++)
if (data->states[ptr].value < best_val &&
data->states[ptr].value >= min &&
- data->states[ptr].value <= max)
+ data->states[ptr].value <= max) {
target = data->states[ptr].gpios;
+ best_val = data->states[ptr].value;
+ if (selector)
+ *selector = ptr;
+ }
if (best_val == INT_MAX)
return -EINVAL;
int min_uV, int max_uV,
unsigned *selector)
{
- return gpio_regulator_set_value(dev, min_uV, max_uV);
+ return gpio_regulator_set_value(dev, min_uV, max_uV, selector);
}
static int gpio_regulator_list_voltage(struct regulator_dev *dev,
static int gpio_regulator_set_current_limit(struct regulator_dev *dev,
int min_uA, int max_uA)
{
- return gpio_regulator_set_value(dev, min_uA, max_uA);
+ return gpio_regulator_set_value(dev, min_uA, max_uA, NULL);
}
static struct regulator_ops gpio_regulator_voltage_ops = {
cfg.dev = &pdev->dev;
cfg.init_data = config->init_data;
- cfg.driver_data = &drvdata;
+ cfg.driver_data = drvdata;
drvdata->dev = regulator_register(&drvdata->desc, &cfg);
if (IS_ERR(drvdata->dev)) {
config.dev = &client->dev;
config.init_data = pdata->regulator;
config.driver_data = info;
+ config.regmap = info->regmap;
info->regulator = regulator_register(&dcdc_desc, &config);
if (IS_ERR(info->regulator)) {
err_unregister_regulator:
while (--id >= 0)
regulator_unregister(pmic->rdev[id]);
- kfree(pmic->rdev);
- kfree(pmic->desc);
- kfree(pmic);
return ret;
}
for (id = 0; id < PALMAS_NUM_REGS; id++)
regulator_unregister(pmic->rdev[id]);
-
- kfree(pmic->rdev);
- kfree(pmic->desc);
- kfree(pmic);
return 0;
}
static u32 rtc_handler(void *context)
{
+ struct device *dev = context;
+
+ pm_wakeup_event(dev, 0);
acpi_clear_event(ACPI_EVENT_RTC);
acpi_disable_event(ACPI_EVENT_RTC, 0);
return ACPI_INTERRUPT_HANDLED;
}
-static inline void rtc_wake_setup(void)
+static inline void rtc_wake_setup(struct device *dev)
{
- acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, NULL);
+ acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev);
/*
* After the RTC handler is installed, the Fixed_RTC event should
* be disabled. Only when the RTC alarm is set will it be enabled.
if (acpi_disabled)
return;
- rtc_wake_setup();
+ rtc_wake_setup(dev);
acpi_rtc_info.wake_on = rtc_wake_on;
acpi_rtc_info.wake_off = rtc_wake_off;
return oid;
}
-static int zcache_frontswap_put_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
/* returns 0 if the page was successfully gotten from frontswap, -1 if
* was not present (should never happen!) */
-static int zcache_frontswap_get_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
}
static struct frontswap_ops zcache_frontswap_ops = {
- .put_page = zcache_frontswap_put_page,
- .get_page = zcache_frontswap_get_page,
+ .store = zcache_frontswap_store,
+ .load = zcache_frontswap_load,
.invalidate_page = zcache_frontswap_flush_page,
.invalidate_area = zcache_frontswap_flush_area,
.init = zcache_frontswap_init
* Swizzling increases objects per swaptype, increasing tmem concurrency
* for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS
* Setting SWIZ_BITS to 27 basically reconstructs the swap entry from
- * frontswap_get_page(), but has side-effects. Hence using 8.
+ * frontswap_load(), but has side-effects. Hence using 8.
*/
#define SWIZ_BITS 8
#define SWIZ_MASK ((1 << SWIZ_BITS) - 1)
return oid;
}
-static int zcache_frontswap_put_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
/* returns 0 if the page was successfully gotten from frontswap, -1 if
* was not present (should never happen!) */
-static int zcache_frontswap_get_page(unsigned type, pgoff_t offset,
+static int zcache_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
}
static struct frontswap_ops zcache_frontswap_ops = {
- .put_page = zcache_frontswap_put_page,
- .get_page = zcache_frontswap_get_page,
+ .store = zcache_frontswap_store,
+ .load = zcache_frontswap_load,
.invalidate_page = zcache_frontswap_flush_page,
.invalidate_area = zcache_frontswap_flush_area,
.init = zcache_frontswap_init
{
struct sbp_tport *tport = agent->tport;
struct sbp_tpg *tpg = tport->tpg;
- int login_id;
+ int id;
struct sbp_login_descriptor *login;
- login_id = LOGOUT_ORB_LOGIN_ID(be32_to_cpu(req->orb.misc));
+ id = LOGOUT_ORB_LOGIN_ID(be32_to_cpu(req->orb.misc));
- login = sbp_login_find_by_id(tpg, login_id);
+ login = sbp_login_find_by_id(tpg, id);
if (!login) {
- pr_warn("cannot find login: %d\n", login_id);
+ pr_warn("cannot find login: %d\n", id);
req->status.status = cpu_to_be32(
STATUS_BLOCK_RESP(STATUS_RESP_REQUEST_COMPLETE) |
ret = PTR_ERR(dev_p);
goto fail;
}
-
- /* O_DIRECT too? */
- flags = O_RDWR | O_CREAT | O_LARGEFILE;
-
/*
- * If fd_buffered_io=1 has not been set explicitly (the default),
- * use O_SYNC to force FILEIO writes to disk.
+ * Use O_DSYNC by default instead of O_SYNC to forgo syncing
+ * of pure timestamp updates.
*/
- if (!(fd_dev->fbd_flags & FDBD_USE_BUFFERED_IO))
- flags |= O_SYNC;
+ flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
file = filp_open(dev_p, flags, 0600);
if (IS_ERR(file)) {
}
}
-static void fd_emulate_write_fua(struct se_cmd *cmd)
-{
- struct se_device *dev = cmd->se_dev;
- struct fd_dev *fd_dev = dev->dev_ptr;
- loff_t start = cmd->t_task_lba *
- dev->se_sub_dev->se_dev_attrib.block_size;
- loff_t end = start + cmd->data_length;
- int ret;
-
- pr_debug("FILEIO: FUA WRITE LBA: %llu, bytes: %u\n",
- cmd->t_task_lba, cmd->data_length);
-
- ret = vfs_fsync_range(fd_dev->fd_file, start, end, 1);
- if (ret != 0)
- pr_err("FILEIO: vfs_fsync_range() failed: %d\n", ret);
-}
-
static int fd_execute_cmd(struct se_cmd *cmd, struct scatterlist *sgl,
u32 sgl_nents, enum dma_data_direction data_direction)
{
ret = fd_do_readv(cmd, sgl, sgl_nents);
} else {
ret = fd_do_writev(cmd, sgl, sgl_nents);
-
+ /*
+ * Perform implict vfs_fsync_range() for fd_do_writev() ops
+ * for SCSI WRITEs with Forced Unit Access (FUA) set.
+ * Allow this to happen independent of WCE=0 setting.
+ */
if (ret > 0 &&
- dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0 &&
dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
(cmd->se_cmd_flags & SCF_FUA)) {
- /*
- * We might need to be a bit smarter here
- * and return some sense data to let the initiator
- * know the FUA WRITE cache sync failed..?
- */
- fd_emulate_write_fua(cmd);
- }
+ struct fd_dev *fd_dev = dev->dev_ptr;
+ loff_t start = cmd->t_task_lba *
+ dev->se_sub_dev->se_dev_attrib.block_size;
+ loff_t end = start + cmd->data_length;
+ vfs_fsync_range(fd_dev->fd_file, start, end, 1);
+ }
}
if (ret < 0) {
static match_table_t tokens = {
{Opt_fd_dev_name, "fd_dev_name=%s"},
{Opt_fd_dev_size, "fd_dev_size=%s"},
- {Opt_fd_buffered_io, "fd_buffered_io=%d"},
{Opt_err, NULL}
};
struct fd_dev *fd_dev = se_dev->se_dev_su_ptr;
char *orig, *ptr, *arg_p, *opts;
substring_t args[MAX_OPT_ARGS];
- int ret = 0, arg, token;
+ int ret = 0, token;
opts = kstrdup(page, GFP_KERNEL);
if (!opts)
" bytes\n", fd_dev->fd_dev_size);
fd_dev->fbd_flags |= FBDF_HAS_SIZE;
break;
- case Opt_fd_buffered_io:
- match_int(args, &arg);
- if (arg != 1) {
- pr_err("bogus fd_buffered_io=%d value\n", arg);
- ret = -EINVAL;
- goto out;
- }
-
- pr_debug("FILEIO: Using buffered I/O"
- " operations for struct fd_dev\n");
-
- fd_dev->fbd_flags |= FDBD_USE_BUFFERED_IO;
- break;
default:
break;
}
ssize_t bl = 0;
bl = sprintf(b + bl, "TCM FILEIO ID: %u", fd_dev->fd_dev_id);
- bl += sprintf(b + bl, " File: %s Size: %llu Mode: %s\n",
- fd_dev->fd_dev_name, fd_dev->fd_dev_size,
- (fd_dev->fbd_flags & FDBD_USE_BUFFERED_IO) ?
- "Buffered" : "Synchronous");
+ bl += sprintf(b + bl, " File: %s Size: %llu Mode: O_DSYNC\n",
+ fd_dev->fd_dev_name, fd_dev->fd_dev_size);
return bl;
}
#define FBDF_HAS_PATH 0x01
#define FBDF_HAS_SIZE 0x02
-#define FDBD_USE_BUFFERED_IO 0x04
struct fd_dev {
u32 fbd_flags;
return 0;
}
+static void sci_cleanup_single(struct sci_port *port)
+{
+ sci_free_gpios(port);
+
+ clk_put(port->iclk);
+ clk_put(port->fclk);
+
+ pm_runtime_disable(port->port.dev);
+}
+
#ifdef CONFIG_SERIAL_SH_SCI_CONSOLE
static void serial_console_putchar(struct uart_port *port, int ch)
{
cpufreq_unregister_notifier(&port->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
- sci_free_gpios(port);
-
uart_remove_one_port(&sci_uart_driver, &port->port);
- clk_put(port->iclk);
- clk_put(port->fclk);
+ sci_cleanup_single(port);
- pm_runtime_disable(&dev->dev);
return 0;
}
index+1, SCI_NPORTS);
dev_notice(&dev->dev, "Consider bumping "
"CONFIG_SERIAL_SH_SCI_NR_UARTS!\n");
- return 0;
+ return -EINVAL;
}
ret = sci_init_single(dev, sciport, index, p);
if (ret)
return ret;
- return uart_add_one_port(&sci_uart_driver, &sciport->port);
+ ret = uart_add_one_port(&sci_uart_driver, &sciport->port);
+ if (ret) {
+ sci_cleanup_single(sciport);
+ return ret;
+ }
+
+ return 0;
}
static int __devinit sci_probe(struct platform_device *dev)
ret = sci_probe_single(dev, dev->id, p, sp);
if (ret)
- goto err_unreg;
+ return ret;
sp->freq_transition.notifier_call = sci_notifier;
ret = cpufreq_register_notifier(&sp->freq_transition,
CPUFREQ_TRANSITION_NOTIFIER);
- if (unlikely(ret < 0))
- goto err_unreg;
+ if (unlikely(ret < 0)) {
+ sci_cleanup_single(sp);
+ return ret;
+ }
#ifdef CONFIG_SH_STANDARD_BIOS
sh_bios_gdb_detach();
#endif
return 0;
-
-err_unreg:
- sci_remove(dev);
- return ret;
}
static int sci_suspend(struct device *dev)
{
struct omap_dss_device *dssdev = to_dss_device(dev);
struct taal_data *td = dev_get_drvdata(&dssdev->dev);
- u8 errors;
+ u8 errors = 0;
int r;
mutex_lock(&td->lock);
static inline void dss_uninitialize_debugfs(void)
{
}
-static inline int dss_debugfs_create_file(const char *name,
- void (*write)(struct seq_file *))
+int dss_debugfs_create_file(const char *name, void (*write)(struct seq_file *))
{
return 0;
}
/* CLKIN4DDR = 16 * TXBYTECLKHS */
tlp_avail = thsbyte_clk * (blank - trans_lp);
- ttxclkesc = tdsi_fclk / lp_clk_div;
+ ttxclkesc = tdsi_fclk * lp_clk_div;
lp_inter = ((tlp_avail - 8 * thsbyte_clk - 5 * tdsi_fclk) / ttxclkesc -
26) / 16;
DSSDBG("dss_runtime_put\n");
r = pm_runtime_put_sync(&dss.pdev->dev);
- WARN_ON(r < 0);
+ WARN_ON(r < 0 && r != -EBUSY);
}
/* DEBUGFS */
}
/* returns 0 if the page was successfully put into frontswap, -1 if not */
-static int tmem_frontswap_put_page(unsigned type, pgoff_t offset,
+static int tmem_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
* returns 0 if the page was successfully gotten from frontswap, -1 if
* was not present (should never happen!)
*/
-static int tmem_frontswap_get_page(unsigned type, pgoff_t offset,
+static int tmem_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
u64 ind64 = (u64)offset;
__setup("nofrontswap", no_frontswap);
static struct frontswap_ops __initdata tmem_frontswap_ops = {
- .put_page = tmem_frontswap_put_page,
- .get_page = tmem_frontswap_get_page,
+ .store = tmem_frontswap_store,
+ .load = tmem_frontswap_load,
.invalidate_page = tmem_frontswap_flush_page,
.invalidate_area = tmem_frontswap_flush_area,
.init = tmem_frontswap_init
void (*add_credits)(struct TCP_Server_Info *, const unsigned int);
void (*set_credits)(struct TCP_Server_Info *, const int);
int * (*get_credits_field)(struct TCP_Server_Info *);
+ __u64 (*get_next_mid)(struct TCP_Server_Info *);
/* data offset from read response message */
unsigned int (*read_data_offset)(char *);
/* data length from read response message */
server->ops->set_credits(server, val);
}
+static inline __u64
+get_next_mid(struct TCP_Server_Info *server)
+{
+ return server->ops->get_next_mid(server);
+}
+
/*
* Macros to allow the TCP_Server_Info->net field and related code to drop out
* when CONFIG_NET_NS isn't set.
void **request_buf);
extern int CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses,
const struct nls_table *nls_cp);
-extern __u64 GetNextMid(struct TCP_Server_Info *server);
extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
extern u64 cifs_UnixTimeToNT(struct timespec);
extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
return rc;
buffer = (struct smb_hdr *)*request_buf;
- buffer->Mid = GetNextMid(ses->server);
+ buffer->Mid = get_next_mid(ses->server);
if (ses->capabilities & CAP_UNICODE)
buffer->Flags2 |= SMBFLG2_UNICODE;
if (ses->capabilities & CAP_STATUS32)
cFYI(1, "secFlags 0x%x", secFlags);
- pSMB->hdr.Mid = GetNextMid(server);
+ pSMB->hdr.Mid = get_next_mid(server);
pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS);
if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
return rc;
}
- pSMB->hdr.Mid = GetNextMid(ses->server);
+ pSMB->hdr.Mid = get_next_mid(ses->server);
if (ses->server->sec_mode &
(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
/* server pointer checked in called function,
but should never be null here anyway */
- pSMB->hdr.Mid = GetNextMid(ses->server);
+ pSMB->hdr.Mid = get_next_mid(ses->server);
pSMB->hdr.Tid = ses->ipc_tid;
pSMB->hdr.Uid = ses->Suid;
if (ses->capabilities & CAP_STATUS32)
if (mid_entry != NULL) {
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
- } else if (!server->ops->is_oplock_break(buf, server)) {
+ } else if (!server->ops->is_oplock_break ||
+ !server->ops->is_oplock_break(buf, server)) {
cERROR(1, "No task to wake, unknown frame received! "
"NumMids %d", atomic_read(&midCount));
cifs_dump_mem("Received Data is: ", buf,
HEADER_SIZE(server));
#ifdef CONFIG_CIFS_DEBUG2
- server->ops->dump_detail(buf);
+ if (server->ops->dump_detail)
+ server->ops->dump_detail(buf);
cifs_dump_mids(server);
#endif /* CIFS_DEBUG2 */
header_assemble(smb_buffer, SMB_COM_TREE_CONNECT_ANDX,
NULL /*no tid */ , 4 /*wct */ );
- smb_buffer->Mid = GetNextMid(ses->server);
+ smb_buffer->Mid = get_next_mid(ses->server);
smb_buffer->Uid = ses->Suid;
pSMB = (TCONX_REQ *) smb_buffer;
pSMBr = (TCONX_RSP *) smb_buffer_response;
struct cifsLockInfo *li, *tmp;
struct cifs_tcon *tcon;
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
- unsigned int num, max_num;
+ unsigned int num, max_num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
int types[] = {LOCKING_ANDX_LARGE_FILES,
LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
return rc;
}
- max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) /
- sizeof(LOCKING_ANDX_RANGE);
+ /*
+ * Accessing maxBuf is racy with cifs_reconnect - need to store value
+ * and check it for zero before using.
+ */
+ max_buf = tcon->ses->server->maxBuf;
+ if (!max_buf) {
+ mutex_unlock(&cinode->lock_mutex);
+ FreeXid(xid);
+ return -EINVAL;
+ }
+
+ max_num = (max_buf - sizeof(struct smb_hdr)) /
+ sizeof(LOCKING_ANDX_RANGE);
buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf) {
mutex_unlock(&cinode->lock_mutex);
int types[] = {LOCKING_ANDX_LARGE_FILES,
LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
unsigned int i;
- unsigned int max_num, num;
+ unsigned int max_num, num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
INIT_LIST_HEAD(&tmp_llist);
- max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) /
- sizeof(LOCKING_ANDX_RANGE);
+ /*
+ * Accessing maxBuf is racy with cifs_reconnect - need to store value
+ * and check it for zero before using.
+ */
+ max_buf = tcon->ses->server->maxBuf;
+ if (!max_buf)
+ return -EINVAL;
+
+ max_num = (max_buf - sizeof(struct smb_hdr)) /
+ sizeof(LOCKING_ANDX_RANGE);
buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
if (!buf)
return -ENOMEM;
continue;
if (types[i] != li->type)
continue;
- if (!cinode->can_cache_brlcks) {
- cur->Pid = cpu_to_le16(li->pid);
- cur->LengthLow = cpu_to_le32((u32)li->length);
- cur->LengthHigh =
- cpu_to_le32((u32)(li->length>>32));
- cur->OffsetLow = cpu_to_le32((u32)li->offset);
- cur->OffsetHigh =
- cpu_to_le32((u32)(li->offset>>32));
- /*
- * We need to save a lock here to let us add
- * it again to the file's list if the unlock
- * range request fails on the server.
- */
- list_move(&li->llist, &tmp_llist);
- if (++num == max_num) {
- stored_rc = cifs_lockv(xid, tcon,
- cfile->netfid,
- li->type, num,
- 0, buf);
- if (stored_rc) {
- /*
- * We failed on the unlock range
- * request - add all locks from
- * the tmp list to the head of
- * the file's list.
- */
- cifs_move_llist(&tmp_llist,
- &cfile->llist);
- rc = stored_rc;
- } else
- /*
- * The unlock range request
- * succeed - free the tmp list.
- */
- cifs_free_llist(&tmp_llist);
- cur = buf;
- num = 0;
- } else
- cur++;
- } else {
+ if (cinode->can_cache_brlcks) {
/*
* We can cache brlock requests - simply remove
* a lock from the file's list.
list_del(&li->llist);
cifs_del_lock_waiters(li);
kfree(li);
+ continue;
}
+ cur->Pid = cpu_to_le16(li->pid);
+ cur->LengthLow = cpu_to_le32((u32)li->length);
+ cur->LengthHigh = cpu_to_le32((u32)(li->length>>32));
+ cur->OffsetLow = cpu_to_le32((u32)li->offset);
+ cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32));
+ /*
+ * We need to save a lock here to let us add it again to
+ * the file's list if the unlock range request fails on
+ * the server.
+ */
+ list_move(&li->llist, &tmp_llist);
+ if (++num == max_num) {
+ stored_rc = cifs_lockv(xid, tcon, cfile->netfid,
+ li->type, num, 0, buf);
+ if (stored_rc) {
+ /*
+ * We failed on the unlock range
+ * request - add all locks from the tmp
+ * list to the head of the file's list.
+ */
+ cifs_move_llist(&tmp_llist,
+ &cfile->llist);
+ rc = stored_rc;
+ } else
+ /*
+ * The unlock range request succeed -
+ * free the tmp list.
+ */
+ cifs_free_llist(&tmp_llist);
+ cur = buf;
+ num = 0;
+ } else
+ cur++;
}
if (num) {
stored_rc = cifs_lockv(xid, tcon, cfile->netfid,
return;
}
-/*
- * Find a free multiplex id (SMB mid). Otherwise there could be
- * mid collisions which might cause problems, demultiplexing the
- * wrong response to this request. Multiplex ids could collide if
- * one of a series requests takes much longer than the others, or
- * if a very large number of long lived requests (byte range
- * locks or FindNotify requests) are pending. No more than
- * 64K-1 requests can be outstanding at one time. If no
- * mids are available, return zero. A future optimization
- * could make the combination of mids and uid the key we use
- * to demultiplex on (rather than mid alone).
- * In addition to the above check, the cifs demultiplex
- * code already used the command code as a secondary
- * check of the frame and if signing is negotiated the
- * response would be discarded if the mid were the same
- * but the signature was wrong. Since the mid is not put in the
- * pending queue until later (when it is about to be dispatched)
- * we do have to limit the number of outstanding requests
- * to somewhat less than 64K-1 although it is hard to imagine
- * so many threads being in the vfs at one time.
- */
-__u64 GetNextMid(struct TCP_Server_Info *server)
-{
- __u64 mid = 0;
- __u16 last_mid, cur_mid;
- bool collision;
-
- spin_lock(&GlobalMid_Lock);
-
- /* mid is 16 bit only for CIFS/SMB */
- cur_mid = (__u16)((server->CurrentMid) & 0xffff);
- /* we do not want to loop forever */
- last_mid = cur_mid;
- cur_mid++;
-
- /*
- * This nested loop looks more expensive than it is.
- * In practice the list of pending requests is short,
- * fewer than 50, and the mids are likely to be unique
- * on the first pass through the loop unless some request
- * takes longer than the 64 thousand requests before it
- * (and it would also have to have been a request that
- * did not time out).
- */
- while (cur_mid != last_mid) {
- struct mid_q_entry *mid_entry;
- unsigned int num_mids;
-
- collision = false;
- if (cur_mid == 0)
- cur_mid++;
-
- num_mids = 0;
- list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
- ++num_mids;
- if (mid_entry->mid == cur_mid &&
- mid_entry->mid_state == MID_REQUEST_SUBMITTED) {
- /* This mid is in use, try a different one */
- collision = true;
- break;
- }
- }
-
- /*
- * if we have more than 32k mids in the list, then something
- * is very wrong. Possibly a local user is trying to DoS the
- * box by issuing long-running calls and SIGKILL'ing them. If
- * we get to 2^16 mids then we're in big trouble as this
- * function could loop forever.
- *
- * Go ahead and assign out the mid in this situation, but force
- * an eventual reconnect to clean out the pending_mid_q.
- */
- if (num_mids > 32768)
- server->tcpStatus = CifsNeedReconnect;
-
- if (!collision) {
- mid = (__u64)cur_mid;
- server->CurrentMid = mid;
- break;
- }
- cur_mid++;
- }
- spin_unlock(&GlobalMid_Lock);
- return mid;
-}
-
/* NB: MID can not be set if treeCon not passed in, in that
case it is responsbility of caller to set the mid */
void
/* Uid is not converted */
buffer->Uid = treeCon->ses->Suid;
- buffer->Mid = GetNextMid(treeCon->ses->server);
+ buffer->Mid = get_next_mid(treeCon->ses->server);
}
if (treeCon->Flags & SMB_SHARE_IS_IN_DFS)
buffer->Flags2 |= SMBFLG2_DFS;
return &server->credits;
}
+/*
+ * Find a free multiplex id (SMB mid). Otherwise there could be
+ * mid collisions which might cause problems, demultiplexing the
+ * wrong response to this request. Multiplex ids could collide if
+ * one of a series requests takes much longer than the others, or
+ * if a very large number of long lived requests (byte range
+ * locks or FindNotify requests) are pending. No more than
+ * 64K-1 requests can be outstanding at one time. If no
+ * mids are available, return zero. A future optimization
+ * could make the combination of mids and uid the key we use
+ * to demultiplex on (rather than mid alone).
+ * In addition to the above check, the cifs demultiplex
+ * code already used the command code as a secondary
+ * check of the frame and if signing is negotiated the
+ * response would be discarded if the mid were the same
+ * but the signature was wrong. Since the mid is not put in the
+ * pending queue until later (when it is about to be dispatched)
+ * we do have to limit the number of outstanding requests
+ * to somewhat less than 64K-1 although it is hard to imagine
+ * so many threads being in the vfs at one time.
+ */
+static __u64
+cifs_get_next_mid(struct TCP_Server_Info *server)
+{
+ __u64 mid = 0;
+ __u16 last_mid, cur_mid;
+ bool collision;
+
+ spin_lock(&GlobalMid_Lock);
+
+ /* mid is 16 bit only for CIFS/SMB */
+ cur_mid = (__u16)((server->CurrentMid) & 0xffff);
+ /* we do not want to loop forever */
+ last_mid = cur_mid;
+ cur_mid++;
+
+ /*
+ * This nested loop looks more expensive than it is.
+ * In practice the list of pending requests is short,
+ * fewer than 50, and the mids are likely to be unique
+ * on the first pass through the loop unless some request
+ * takes longer than the 64 thousand requests before it
+ * (and it would also have to have been a request that
+ * did not time out).
+ */
+ while (cur_mid != last_mid) {
+ struct mid_q_entry *mid_entry;
+ unsigned int num_mids;
+
+ collision = false;
+ if (cur_mid == 0)
+ cur_mid++;
+
+ num_mids = 0;
+ list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
+ ++num_mids;
+ if (mid_entry->mid == cur_mid &&
+ mid_entry->mid_state == MID_REQUEST_SUBMITTED) {
+ /* This mid is in use, try a different one */
+ collision = true;
+ break;
+ }
+ }
+
+ /*
+ * if we have more than 32k mids in the list, then something
+ * is very wrong. Possibly a local user is trying to DoS the
+ * box by issuing long-running calls and SIGKILL'ing them. If
+ * we get to 2^16 mids then we're in big trouble as this
+ * function could loop forever.
+ *
+ * Go ahead and assign out the mid in this situation, but force
+ * an eventual reconnect to clean out the pending_mid_q.
+ */
+ if (num_mids > 32768)
+ server->tcpStatus = CifsNeedReconnect;
+
+ if (!collision) {
+ mid = (__u64)cur_mid;
+ server->CurrentMid = mid;
+ break;
+ }
+ cur_mid++;
+ }
+ spin_unlock(&GlobalMid_Lock);
+ return mid;
+}
+
struct smb_version_operations smb1_operations = {
.send_cancel = send_nt_cancel,
.compare_fids = cifs_compare_fids,
.add_credits = cifs_add_credits,
.set_credits = cifs_set_credits,
.get_credits_field = cifs_get_credits_field,
+ .get_next_mid = cifs_get_next_mid,
.read_data_offset = cifs_read_data_offset,
.read_data_length = cifs_read_data_length,
.map_error = map_smb_to_linux_error,
pSMB->LockType = LOCKING_ANDX_CANCEL_LOCK|LOCKING_ANDX_LARGE_FILES;
pSMB->Timeout = 0;
- pSMB->hdr.Mid = GetNextMid(ses->server);
+ pSMB->hdr.Mid = get_next_mid(ses->server);
return SendReceive(xid, ses, in_buf, out_buf,
&bytes_returned, 0);
/**
* d_find_alias - grab a hashed alias of inode
* @inode: inode in question
+ * @want_discon: flag, used by d_splice_alias, to request
+ * that only a DISCONNECTED alias be returned.
*
* If inode has a hashed alias, or is a directory and has any alias,
* acquire the reference to alias and return it. Otherwise return NULL.
* of a filesystem.
*
* If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
- * any other hashed alias over that.
+ * any other hashed alias over that one unless @want_discon is set,
+ * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
*/
-static struct dentry *__d_find_alias(struct inode *inode)
+static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
struct dentry *alias, *discon_alias;
if (IS_ROOT(alias) &&
(alias->d_flags & DCACHE_DISCONNECTED)) {
discon_alias = alias;
- } else {
+ } else if (!want_discon) {
__dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
if (!list_empty(&inode->i_dentry)) {
spin_lock(&inode->i_lock);
- de = __d_find_alias(inode);
+ de = __d_find_alias(inode, 0);
spin_unlock(&inode->i_lock);
}
return de;
if (inode && S_ISDIR(inode->i_mode)) {
spin_lock(&inode->i_lock);
- new = __d_find_any_alias(inode);
+ new = __d_find_alias(inode, 1);
if (new) {
+ BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
d_move(new, dentry);
struct dentry *alias;
/* Does an aliased dentry already exist? */
- alias = __d_find_alias(inode);
+ alias = __d_find_alias(inode, 0);
if (alias) {
actual = alias;
write_seqlock(&rename_lock);
static struct kobj_type uuid_ktype = {
};
-void exofs_sysfs_dbg_print()
+void exofs_sysfs_dbg_print(void)
{
#ifdef CONFIG_EXOFS_DEBUG
struct kobject *k_name, *k_tmp;
* unusual file system layouts.
*/
if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) {
- block_cluster = EXT4_B2C(sbi, (start -
- ext4_block_bitmap(sb, gdp)));
+ block_cluster = EXT4_B2C(sbi,
+ ext4_block_bitmap(sb, gdp) - start);
if (block_cluster < num_clusters)
block_cluster = -1;
else if (block_cluster == num_clusters) {
if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) {
inode_cluster = EXT4_B2C(sbi,
- start - ext4_inode_bitmap(sb, gdp));
+ ext4_inode_bitmap(sb, gdp) - start);
if (inode_cluster < num_clusters)
inode_cluster = -1;
else if (inode_cluster == num_clusters) {
itbl_blk = ext4_inode_table(sb, gdp);
for (i = 0; i < sbi->s_itb_per_group; i++) {
if (ext4_block_in_group(sb, itbl_blk + i, block_group)) {
- c = EXT4_B2C(sbi, start - itbl_blk + i);
+ c = EXT4_B2C(sbi, itbl_blk + i - start);
if ((c < num_clusters) || (c == inode_cluster) ||
(c == block_cluster) || (c == itbl_cluster))
continue;
else
ext4_clear_inode_flag(inode, i);
}
- ei->i_flags = flags;
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
/* Wait for I_SYNC. This function drops i_lock... */
inode_sleep_on_writeback(inode);
/* Inode may be gone, start again */
+ spin_lock(&wb->list_lock);
continue;
}
inode->i_state |= I_SYNC;
unsigned global_limit)
{
unsigned long t;
- char tmp[32];
unsigned limit = (1 << 16) - 1;
int err;
- if (*ppos || count >= sizeof(tmp) - 1)
- return -EINVAL;
-
- if (copy_from_user(tmp, buf, count))
+ if (*ppos)
return -EINVAL;
- tmp[count] = '\0';
-
- err = strict_strtoul(tmp, 0, &t);
+ err = kstrtoul_from_user(buf, count, 0, &t);
if (err)
return err;
static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr,
struct kstat *stat)
{
+ unsigned int blkbits;
+
stat->dev = inode->i_sb->s_dev;
stat->ino = attr->ino;
stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
stat->ctime.tv_nsec = attr->ctimensec;
stat->size = attr->size;
stat->blocks = attr->blocks;
- stat->blksize = (1 << inode->i_blkbits);
+
+ if (attr->blksize != 0)
+ blkbits = ilog2(attr->blksize);
+ else
+ blkbits = inode->i_sb->s_blocksize_bits;
+
+ stat->blksize = 1 << blkbits;
}
static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
if (stat) {
generic_fillattr(inode, stat);
stat->mode = fi->orig_i_mode;
+ stat->ino = fi->orig_ino;
}
}
return ret;
}
+long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
+ loff_t length)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fc;
+ struct fuse_req *req;
+ struct fuse_fallocate_in inarg = {
+ .fh = ff->fh,
+ .offset = offset,
+ .length = length,
+ .mode = mode
+ };
+ int err;
+
+ if (fc->no_fallocate)
+ return -EOPNOTSUPP;
+
+ req = fuse_get_req(fc);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ req->in.h.opcode = FUSE_FALLOCATE;
+ req->in.h.nodeid = ff->nodeid;
+ req->in.numargs = 1;
+ req->in.args[0].size = sizeof(inarg);
+ req->in.args[0].value = &inarg;
+ fuse_request_send(fc, req);
+ err = req->out.h.error;
+ if (err == -ENOSYS) {
+ fc->no_fallocate = 1;
+ err = -EOPNOTSUPP;
+ }
+ fuse_put_request(fc, req);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(fuse_file_fallocate);
+
static const struct file_operations fuse_file_operations = {
.llseek = fuse_file_llseek,
.read = do_sync_read,
.unlocked_ioctl = fuse_file_ioctl,
.compat_ioctl = fuse_file_compat_ioctl,
.poll = fuse_file_poll,
+ .fallocate = fuse_file_fallocate,
};
static const struct file_operations fuse_direct_io_file_operations = {
.unlocked_ioctl = fuse_file_ioctl,
.compat_ioctl = fuse_file_compat_ioctl,
.poll = fuse_file_poll,
+ .fallocate = fuse_file_fallocate,
/* no splice_read */
};
preserve the original mode */
umode_t orig_i_mode;
+ /** 64 bit inode number */
+ u64 orig_ino;
+
/** Version of last attribute change */
u64 attr_version;
/** Are BSD file locking primitives not implemented by fs? */
unsigned no_flock:1;
+ /** Is fallocate not implemented by fs? */
+ unsigned no_fallocate:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
fi->nlookup = 0;
fi->attr_version = 0;
fi->writectr = 0;
+ fi->orig_ino = 0;
INIT_LIST_HEAD(&fi->write_files);
INIT_LIST_HEAD(&fi->queued_writes);
INIT_LIST_HEAD(&fi->writepages);
return 0;
}
+/*
+ * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down
+ * so that it will fit.
+ */
+static ino_t fuse_squash_ino(u64 ino64)
+{
+ ino_t ino = (ino_t) ino64;
+ if (sizeof(ino_t) < sizeof(u64))
+ ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8;
+ return ino;
+}
+
void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
u64 attr_valid)
{
fi->attr_version = ++fc->attr_version;
fi->i_time = attr_valid;
- inode->i_ino = attr->ino;
+ inode->i_ino = fuse_squash_ino(attr->ino);
inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
set_nlink(inode, attr->nlink);
inode->i_uid = attr->uid;
fi->orig_i_mode = inode->i_mode;
if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
inode->i_mode &= ~S_ISVTX;
+
+ fi->orig_ino = attr->ino;
}
void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
- unsigned i_mode, f_mode = file->f_mode;
+ unsigned f_mode = file->f_mode;
rcu_read_unlock();
put_files_struct(files);
inode->i_gid = GLOBAL_ROOT_GID;
}
- i_mode = S_IFLNK;
- if (f_mode & FMODE_READ)
- i_mode |= S_IRUSR | S_IXUSR;
- if (f_mode & FMODE_WRITE)
- i_mode |= S_IWUSR | S_IXUSR;
- inode->i_mode = i_mode;
+ if (S_ISLNK(inode->i_mode)) {
+ unsigned i_mode = S_IFLNK;
+ if (f_mode & FMODE_READ)
+ i_mode |= S_IRUSR | S_IXUSR;
+ if (f_mode & FMODE_WRITE)
+ i_mode |= S_IWUSR | S_IXUSR;
+ inode->i_mode = i_mode;
+ }
security_task_to_inode(task, inode);
put_task_struct(task);
ei = PROC_I(inode);
ei->fd = fd;
+ inode->i_mode = S_IFLNK;
inode->i_op = &proc_pid_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
struct dentry *dent;
struct ubifs_debug_info *d = c->dbg;
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME,
c->vi.ubi_num, c->vi.vol_id);
if (n == UBIFS_DFS_DIR_LEN) {
*/
void dbg_debugfs_exit_fs(struct ubifs_info *c)
{
- debugfs_remove_recursive(c->dbg->dfs_dir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove_recursive(c->dbg->dfs_dir);
}
struct ubifs_global_debug_info ubifs_dbg;
const char *fname;
struct dentry *dent;
+ if (!IS_ENABLED(DEBUG_FS))
+ return 0;
+
fname = "ubifs";
dent = debugfs_create_dir(fname, NULL);
if (IS_ERR_OR_NULL(dent))
*/
void dbg_debugfs_exit(void)
{
- debugfs_remove_recursive(dfs_rootdir);
+ if (IS_ENABLED(DEBUG_FS))
+ debugfs_remove_recursive(dfs_rootdir);
}
/**
#else /* CONFIG_ACPI */
-static int register_acpi_bus_type(struct acpi_bus_type *bus) { return 0; }
-static int unregister_acpi_bus_type(struct acpi_bus_type *bus) { return 0; }
+static inline int register_acpi_bus_type(void *bus) { return 0; }
+static inline int unregister_acpi_bus_type(void *bus) { return 0; }
#endif /* CONFIG_ACPI */
#define _ASM_GENERIC_BUG_H
#include <linux/compiler.h>
+#include <linux/kernel.h>
#ifdef CONFIG_BUG
struct drm_object_properties *properties;
};
-#define DRM_OBJECT_MAX_PROPERTY 16
+#define DRM_OBJECT_MAX_PROPERTY 24
struct drm_object_properties {
int count;
uint32_t ids[DRM_OBJECT_MAX_PROPERTY];
{0x1002, 0x6747, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6748, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6749, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x674A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6751, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6771, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6772, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6827, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6828, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
- {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
- {0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6831, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6837, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6838, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6839, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+ {0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9807, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x980A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9909, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x990A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x990F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9910, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9913, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9917, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9918, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9919, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9990, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9991, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9992, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9993, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9994, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x99A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x99A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x99A4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0, 0, 0}
#define r128_PCI_IDS \
* A structure for mapping buffer.
*
* @handle: a handle to gem object created.
+ * @pad: just padding to be 64-bit aligned.
* @size: memory size to be mapped.
* @mapped: having user virtual address mmaped.
* - this variable would be filled by exynos gem module
*/
struct drm_exynos_gem_mmap {
unsigned int handle;
- unsigned int size;
+ unsigned int pad;
+ uint64_t size;
uint64_t mapped;
};
struct clock_event_device *evt);
extern void clockevents_register_device(struct clock_event_device *dev);
+extern void clockevents_config(struct clock_event_device *dev, u32 freq);
extern void clockevents_config_and_register(struct clock_event_device *dev,
u32 freq, unsigned long min_delta,
unsigned long max_delta);
#ifndef _LINUX_COMPACTION_H
#define _LINUX_COMPACTION_H
-#include <linux/node.h>
-
/* Return values for compact_zone() and try_to_compact_pages() */
/* compaction didn't start as it was not possible or direct reclaim was more suitable */
#define COMPACT_SKIPPED 0
/* The full zone was compacted */
#define COMPACT_COMPLETE 3
-/*
- * compaction supports three modes
- *
- * COMPACT_ASYNC_MOVABLE uses asynchronous migration and only scans
- * MIGRATE_MOVABLE pageblocks as migration sources and targets.
- * COMPACT_ASYNC_UNMOVABLE uses asynchronous migration and only scans
- * MIGRATE_MOVABLE pageblocks as migration sources.
- * MIGRATE_UNMOVABLE pageblocks are scanned as potential migration
- * targets and convers them to MIGRATE_MOVABLE if possible
- * COMPACT_SYNC uses synchronous migration and scans all pageblocks
- */
-enum compact_mode {
- COMPACT_ASYNC_MOVABLE,
- COMPACT_ASYNC_UNMOVABLE,
- COMPACT_SYNC,
-};
-
#ifdef CONFIG_COMPACTION
extern int sysctl_compact_memory;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
--- /dev/null
+#ifndef _LINUX_FRONTSWAP_H
+#define _LINUX_FRONTSWAP_H
+
+#include <linux/swap.h>
+#include <linux/mm.h>
+#include <linux/bitops.h>
+
+struct frontswap_ops {
+ void (*init)(unsigned);
+ int (*store)(unsigned, pgoff_t, struct page *);
+ int (*load)(unsigned, pgoff_t, struct page *);
+ void (*invalidate_page)(unsigned, pgoff_t);
+ void (*invalidate_area)(unsigned);
+};
+
+extern bool frontswap_enabled;
+extern struct frontswap_ops
+ frontswap_register_ops(struct frontswap_ops *ops);
+extern void frontswap_shrink(unsigned long);
+extern unsigned long frontswap_curr_pages(void);
+extern void frontswap_writethrough(bool);
+
+extern void __frontswap_init(unsigned type);
+extern int __frontswap_store(struct page *page);
+extern int __frontswap_load(struct page *page);
+extern void __frontswap_invalidate_page(unsigned, pgoff_t);
+extern void __frontswap_invalidate_area(unsigned);
+
+#ifdef CONFIG_FRONTSWAP
+
+static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset)
+{
+ bool ret = false;
+
+ if (frontswap_enabled && sis->frontswap_map)
+ ret = test_bit(offset, sis->frontswap_map);
+ return ret;
+}
+
+static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset)
+{
+ if (frontswap_enabled && sis->frontswap_map)
+ set_bit(offset, sis->frontswap_map);
+}
+
+static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset)
+{
+ if (frontswap_enabled && sis->frontswap_map)
+ clear_bit(offset, sis->frontswap_map);
+}
+
+static inline void frontswap_map_set(struct swap_info_struct *p,
+ unsigned long *map)
+{
+ p->frontswap_map = map;
+}
+
+static inline unsigned long *frontswap_map_get(struct swap_info_struct *p)
+{
+ return p->frontswap_map;
+}
+#else
+/* all inline routines become no-ops and all externs are ignored */
+
+#define frontswap_enabled (0)
+
+static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset)
+{
+ return false;
+}
+
+static inline void frontswap_set(struct swap_info_struct *sis, pgoff_t offset)
+{
+}
+
+static inline void frontswap_clear(struct swap_info_struct *sis, pgoff_t offset)
+{
+}
+
+static inline void frontswap_map_set(struct swap_info_struct *p,
+ unsigned long *map)
+{
+}
+
+static inline unsigned long *frontswap_map_get(struct swap_info_struct *p)
+{
+ return NULL;
+}
+#endif
+
+static inline int frontswap_store(struct page *page)
+{
+ int ret = -1;
+
+ if (frontswap_enabled)
+ ret = __frontswap_store(page);
+ return ret;
+}
+
+static inline int frontswap_load(struct page *page)
+{
+ int ret = -1;
+
+ if (frontswap_enabled)
+ ret = __frontswap_load(page);
+ return ret;
+}
+
+static inline void frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+ if (frontswap_enabled)
+ __frontswap_invalidate_page(type, offset);
+}
+
+static inline void frontswap_invalidate_area(unsigned type)
+{
+ if (frontswap_enabled)
+ __frontswap_invalidate_area(type);
+}
+
+static inline void frontswap_init(unsigned type)
+{
+ if (frontswap_enabled)
+ __frontswap_init(type);
+}
+
+#endif /* _LINUX_FRONTSWAP_H */
unsigned int __i_nlink;
};
dev_t i_rdev;
+ loff_t i_size;
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
+ unsigned int i_blkbits;
blkcnt_t i_blocks;
- loff_t i_size;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
struct list_head i_dentry;
struct rcu_head i_rcu;
};
- atomic_t i_count;
- unsigned int i_blkbits;
u64 i_version;
+ atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
* 7.18
* - add FUSE_IOCTL_DIR flag
* - add FUSE_NOTIFY_DELETE
+ *
+ * 7.19
+ * - add FUSE_FALLOCATE
*/
#ifndef _LINUX_FUSE_H
#define FUSE_KERNEL_VERSION 7
/** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 18
+#define FUSE_KERNEL_MINOR_VERSION 19
/** The node ID of the root inode */
#define FUSE_ROOT_ID 1
FUSE_POLL = 40,
FUSE_NOTIFY_REPLY = 41,
FUSE_BATCH_FORGET = 42,
+ FUSE_FALLOCATE = 43,
/* CUSE specific operations */
CUSE_INIT = 4096,
__u64 kh;
};
+struct fuse_fallocate_in {
+ __u64 fh;
+ __u64 offset;
+ __u64 length;
+ __u32 mode;
+ __u32 padding;
+};
+
struct fuse_in_header {
__u32 len;
__u32 opcode;
--- /dev/null
+/*
+ * i2c-mux-pinctrl platform data
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _LINUX_I2C_MUX_PINCTRL_H
+#define _LINUX_I2C_MUX_PINCTRL_H
+
+/**
+ * struct i2c_mux_pinctrl_platform_data - Platform data for i2c-mux-pinctrl
+ * @parent_bus_num: Parent I2C bus number
+ * @base_bus_num: Base I2C bus number for the child busses. 0 for dynamic.
+ * @bus_count: Number of child busses. Also the number of elements in
+ * @pinctrl_states
+ * @pinctrl_states: The names of the pinctrl state to select for each child bus
+ * @pinctrl_state_idle: The pinctrl state to select when no child bus is being
+ * accessed. If NULL, the most recently used pinctrl state will be left
+ * selected.
+ */
+struct i2c_mux_pinctrl_platform_data {
+ int parent_bus_num;
+ int base_bus_num;
+ int bus_count;
+ const char **pinctrl_states;
+ const char *pinctrl_state_idle;
+};
+
+#endif
.normal_prio = MAX_PRIO-20, \
.policy = SCHED_NORMAL, \
.cpus_allowed = CPU_MASK_ALL, \
+ .nr_cpus_allowed= NR_CPUS, \
.mm = NULL, \
.active_mm = &init_mm, \
.se = { \
.rt = { \
.run_list = LIST_HEAD_INIT(tsk.rt.run_list), \
.time_slice = RR_TIMESLICE, \
- .nr_cpus_allowed = NR_CPUS, \
}, \
.tasks = LIST_HEAD_INIT(tsk.tasks), \
INIT_PUSHABLE_TASKS(tsk) \
* The ops can have NULL set or get functions.
*/
#define module_param_cb(name, ops, arg, perm) \
- __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, 0)
+ __module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1)
/**
* <level>_param_cb - general callback for a module/cmdline parameter
{ (void *)set, (void *)get }; \
__module_param_call(MODULE_PARAM_PREFIX, \
name, &__param_ops_##name, arg, \
- (perm) + sizeof(__check_old_set_param(set))*0, 0)
+ (perm) + sizeof(__check_old_set_param(set))*0, -1)
/* We don't get oldget: it's often a new-style param_get_uint, etc. */
static inline int
*/
#define core_param(name, var, type, perm) \
param_check_##type(name, &(var)); \
- __module_param_call("", name, ¶m_ops_##type, &var, perm, 0)
+ __module_param_call("", name, ¶m_ops_##type, &var, perm, -1)
#endif /* !MODULE */
/**
= { len, string }; \
__module_param_call(MODULE_PARAM_PREFIX, name, \
¶m_ops_string, \
- .str = &__param_string_##name, perm, 0); \
+ .str = &__param_string_##name, perm, -1); \
__MODULE_PARM_TYPE(name, "string")
/**
__module_param_call(MODULE_PARAM_PREFIX, name, \
¶m_array_ops, \
.arr = &__param_arr_##name, \
- perm, 0); \
+ perm, -1); \
__MODULE_PARM_TYPE(name, "array of " #type)
extern struct kernel_param_ops param_array_ops;
extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu;
extern void nf_ct_attach(struct sk_buff *, struct sk_buff *);
extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
+
+struct nf_conn;
+struct nlattr;
+
+struct nfq_ct_hook {
+ size_t (*build_size)(const struct nf_conn *ct);
+ int (*build)(struct sk_buff *skb, struct nf_conn *ct);
+ int (*parse)(const struct nlattr *attr, struct nf_conn *ct);
+ void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct,
+ u32 ctinfo, int off);
+};
+extern struct nfq_ct_hook *nfq_ct_hook;
#else
static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
#endif
header-y += nfnetlink_acct.h
header-y += nfnetlink_compat.h
header-y += nfnetlink_conntrack.h
+header-y += nfnetlink_cthelper.h
header-y += nfnetlink_cttimeout.h
header-y += nfnetlink_log.h
header-y += nfnetlink_queue.h
#define __NF_CONNTRACK_SIP_H__
#ifdef __KERNEL__
+#include <net/netfilter/nf_conntrack_expect.h>
+
#define SIP_PORT 5060
#define SIP_TIMEOUT 3600
#define NFNL_SUBSYS_IPSET 6
#define NFNL_SUBSYS_ACCT 7
#define NFNL_SUBSYS_CTNETLINK_TIMEOUT 8
-#define NFNL_SUBSYS_COUNT 9
+#define NFNL_SUBSYS_CTHELPER 9
+#define NFNL_SUBSYS_COUNT 10
#ifdef __KERNEL__
enum ctattr_help {
CTA_HELP_UNSPEC,
CTA_HELP_NAME,
+ CTA_HELP_INFO,
__CTA_HELP_MAX
};
#define CTA_HELP_MAX (__CTA_HELP_MAX - 1)
--- /dev/null
+#ifndef _NFNL_CTHELPER_H_
+#define _NFNL_CTHELPER_H_
+
+#define NFCT_HELPER_STATUS_DISABLED 0
+#define NFCT_HELPER_STATUS_ENABLED 1
+
+enum nfnl_acct_msg_types {
+ NFNL_MSG_CTHELPER_NEW,
+ NFNL_MSG_CTHELPER_GET,
+ NFNL_MSG_CTHELPER_DEL,
+ NFNL_MSG_CTHELPER_MAX
+};
+
+enum nfnl_cthelper_type {
+ NFCTH_UNSPEC,
+ NFCTH_NAME,
+ NFCTH_TUPLE,
+ NFCTH_QUEUE_NUM,
+ NFCTH_POLICY,
+ NFCTH_PRIV_DATA_LEN,
+ NFCTH_STATUS,
+ __NFCTH_MAX
+};
+#define NFCTH_MAX (__NFCTH_MAX - 1)
+
+enum nfnl_cthelper_policy_type {
+ NFCTH_POLICY_SET_UNSPEC,
+ NFCTH_POLICY_SET_NUM,
+ NFCTH_POLICY_SET,
+ NFCTH_POLICY_SET1 = NFCTH_POLICY_SET,
+ NFCTH_POLICY_SET2,
+ NFCTH_POLICY_SET3,
+ NFCTH_POLICY_SET4,
+ __NFCTH_POLICY_SET_MAX
+};
+#define NFCTH_POLICY_SET_MAX (__NFCTH_POLICY_SET_MAX - 1)
+
+enum nfnl_cthelper_pol_type {
+ NFCTH_POLICY_UNSPEC,
+ NFCTH_POLICY_NAME,
+ NFCTH_POLICY_EXPECT_MAX,
+ NFCTH_POLICY_EXPECT_TIMEOUT,
+ __NFCTH_POLICY_MAX
+};
+#define NFCTH_POLICY_MAX (__NFCTH_POLICY_MAX - 1)
+
+enum nfnl_cthelper_tuple_type {
+ NFCTH_TUPLE_UNSPEC,
+ NFCTH_TUPLE_L3PROTONUM,
+ NFCTH_TUPLE_L4PROTONUM,
+ __NFCTH_TUPLE_MAX,
+};
+#define NFCTH_TUPLE_MAX (__NFCTH_TUPLE_MAX - 1)
+
+#endif /* _NFNL_CTHELPER_H */
NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */
NFQA_HWADDR, /* nfqnl_msg_packet_hw */
NFQA_PAYLOAD, /* opaque data payload */
+ NFQA_CT, /* nf_conntrack_netlink.h */
+ NFQA_CT_INFO, /* enum ip_conntrack_info */
__NFQA_MAX
};
/* Flags for NFQA_CFG_FLAGS */
#define NFQA_CFG_F_FAIL_OPEN (1 << 0)
+#define NFQA_CFG_F_CONNTRACK (1 << 1)
#endif /* _NFNETLINK_QUEUE_H */
NF_IP_PRI_SECURITY = 50,
NF_IP_PRI_NAT_SRC = 100,
NF_IP_PRI_SELINUX_LAST = 225,
+ NF_IP_PRI_CONNTRACK_HELPER = 300,
NF_IP_PRI_CONNTRACK_CONFIRM = INT_MAX,
NF_IP_PRI_LAST = INT_MAX,
};
NF_IP6_PRI_SECURITY = 50,
NF_IP6_PRI_NAT_SRC = 100,
NF_IP6_PRI_SELINUX_LAST = 225,
+ NF_IP6_PRI_CONNTRACK_HELPER = 300,
NF_IP6_PRI_LAST = INT_MAX,
};
PERF_RECORD_MAX, /* non-ABI */
};
+#define PERF_MAX_STACK_DEPTH 127
+
enum perf_callchain_context {
PERF_CONTEXT_HV = (__u64)-32,
PERF_CONTEXT_KERNEL = (__u64)-128,
#include <linux/sysfs.h>
#include <asm/local.h>
-#define PERF_MAX_STACK_DEPTH 255
-
struct perf_callchain_entry {
__u64 nr;
__u64 ip[PERF_MAX_STACK_DEPTH];
#define PR_SET_PTRACER 0x59616d61
# define PR_SET_PTRACER_ANY ((unsigned long)-1)
-#define PR_SET_CHILD_SUBREAPER 36
-#define PR_GET_CHILD_SUBREAPER 37
+#define PR_SET_CHILD_SUBREAPER 36
+#define PR_GET_CHILD_SUBREAPER 37
/*
* If no_new_privs is set, then operations that grant new privileges (i.e.
* asking selinux for a specific new context (e.g. with runcon) will result
* in execve returning -EPERM.
*/
-#define PR_SET_NO_NEW_PRIVS 38
-#define PR_GET_NO_NEW_PRIVS 39
+#define PR_SET_NO_NEW_PRIVS 38
+#define PR_GET_NO_NEW_PRIVS 39
+
+#define PR_GET_TID_ADDRESS 40
#endif /* _LINUX_PRCTL_H */
iter->index++;
if (likely(*slot))
return slot;
- if (flags & RADIX_TREE_ITER_CONTIG)
+ if (flags & RADIX_TREE_ITER_CONTIG) {
+ /* forbid switching to the next chunk */
+ iter->next_index = 0;
break;
+ }
}
}
return NULL;
extern void calc_global_load(unsigned long ticks);
+extern void update_cpu_load_nohz(void);
extern unsigned long get_parent_ip(unsigned long addr);
/* leave room for more dump flags */
#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */
+#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
* Number of busy cpus in this group.
*/
atomic_t nr_busy_cpus;
+
+ unsigned long cpumask[0]; /* iteration mask */
};
struct sched_group {
return to_cpumask(sg->cpumask);
}
+/*
+ * cpumask masking which cpus in the group are allowed to iterate up the domain
+ * tree.
+ */
+static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+{
+ return to_cpumask(sg->sgp->cpumask);
+}
+
/**
* group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
* @group: The group whose first cpu is to be returned.
struct list_head run_list;
unsigned long timeout;
unsigned int time_slice;
- int nr_cpus_allowed;
struct sched_rt_entity *back;
#ifdef CONFIG_RT_GROUP_SCHED
#endif
unsigned int policy;
+ int nr_cpus_allowed;
cpumask_t cpus_allowed;
#ifdef CONFIG_PREEMPT_RCU
/* device driver is going to provide hardware time stamp */
SKBTX_IN_PROGRESS = 1 << 2,
- /* ensure the originating sk reference is available on driver level */
- SKBTX_DRV_NEEDS_SK_REF = 1 << 3,
-
/* device driver supports TX zero-copy buffers */
- SKBTX_DEV_ZEROCOPY = 1 << 4,
+ SKBTX_DEV_ZEROCOPY = 1 << 3,
/* generate wifi status information (where possible) */
- SKBTX_WIFI_STATUS = 1 << 5,
+ SKBTX_WIFI_STATUS = 1 << 4,
};
/*
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
+#ifdef CONFIG_FRONTSWAP
+ unsigned long *frontswap_map; /* frontswap in-use, one bit per page */
+ atomic_t frontswap_pages; /* frontswap pages in-use counter */
+#endif
};
struct swap_list_t {
--- /dev/null
+#ifndef _LINUX_SWAPFILE_H
+#define _LINUX_SWAPFILE_H
+
+/*
+ * these were static in swapfile.c but frontswap.c needs them and we don't
+ * want to expose them to the dozens of source files that include swap.h
+ */
+extern spinlock_t swap_lock;
+extern struct swap_list_t swap_list;
+extern struct swap_info_struct *swap_info[];
+extern int try_to_unuse(unsigned int, bool, unsigned long);
+
+#endif /* _LINUX_SWAPFILE_H */
enum vga_switcheroo_state {
VGA_SWITCHEROO_OFF,
VGA_SWITCHEROO_ON,
+ /* below are referred only from vga_switcheroo_get_client_state() */
+ VGA_SWITCHEROO_INIT,
+ VGA_SWITCHEROO_NOT_FOUND,
};
enum vga_switcheroo_client_id {
int vga_switcheroo_process_delayed_switch(void);
+int vga_switcheroo_get_client_state(struct pci_dev *dev);
+
#else
static inline void vga_switcheroo_unregister_client(struct pci_dev *dev) {}
int id, bool active) { return 0; }
static inline void vga_switcheroo_unregister_handler(void) {}
static inline int vga_switcheroo_process_delayed_switch(void) { return 0; }
+static inline int vga_switcheroo_get_client_state(struct pci_dev *dev) { return VGA_SWITCHEROO_ON; }
+
#endif
#else
void *__pad1;
#endif
- int (*input)(struct sk_buff*);
- int (*output)(struct sk_buff*);
+ int (*input)(struct sk_buff *);
+ int (*output)(struct sk_buff *);
int flags;
#define DST_HOST 0x0001
return dst_metric(dst, RTAX_LOCK) & (1<<metric);
}
-static inline void dst_hold(struct dst_entry * dst)
+static inline void dst_hold(struct dst_entry *dst)
{
/*
* If your kernel compilation stops here, please check
dst->lastuse = time;
}
-static inline
-struct dst_entry * dst_clone(struct dst_entry * dst)
+static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
if (dst)
atomic_inc(&dst->__refcnt);
}
extern int dst_discard(struct sk_buff *skb);
-extern void *dst_alloc(struct dst_ops * ops, struct net_device *dev,
+extern void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
int initial_ref, int initial_obsolete, int flags);
-extern void __dst_free(struct dst_entry * dst);
-extern struct dst_entry *dst_destroy(struct dst_entry * dst);
+extern void __dst_free(struct dst_entry *dst);
+extern struct dst_entry *dst_destroy(struct dst_entry *dst);
-static inline void dst_free(struct dst_entry * dst)
+static inline void dst_free(struct dst_entry *dst)
{
if (dst->obsolete > 1)
return;
u8 *lladdr,
int on_link);
-extern void rt6_pmtu_discovery(const struct in6_addr *daddr,
- const struct in6_addr *saddr,
- struct net_device *dev,
- u32 pmtu);
+extern void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
+ int oif, u32 mark);
+extern void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk,
+ __be32 mtu);
struct netlink_callback;
/* insert expect proto private data here */
};
-/* Add protocol helper include file here */
-#include <linux/netfilter/nf_conntrack_ftp.h>
-#include <linux/netfilter/nf_conntrack_pptp.h>
-#include <linux/netfilter/nf_conntrack_h323.h>
-#include <linux/netfilter/nf_conntrack_sane.h>
-#include <linux/netfilter/nf_conntrack_sip.h>
-
-/* per conntrack: application helper private data */
-union nf_conntrack_help {
- /* insert conntrack helper private data (master) here */
-#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE)
- struct nf_ct_ftp_master ct_ftp_info;
-#endif
-#if defined(CONFIG_NF_CONNTRACK_PPTP) || \
- defined(CONFIG_NF_CONNTRACK_PPTP_MODULE)
- struct nf_ct_pptp_master ct_pptp_info;
-#endif
-#if defined(CONFIG_NF_CONNTRACK_H323) || \
- defined(CONFIG_NF_CONNTRACK_H323_MODULE)
- struct nf_ct_h323_master ct_h323_info;
-#endif
-#if defined(CONFIG_NF_CONNTRACK_SANE) || \
- defined(CONFIG_NF_CONNTRACK_SANE_MODULE)
- struct nf_ct_sane_master ct_sane_info;
-#endif
-#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE)
- struct nf_ct_sip_master ct_sip_info;
-#endif
-};
-
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/timer.h>
/* Helper. if any */
struct nf_conntrack_helper __rcu *helper;
- union nf_conntrack_help help;
-
struct hlist_head expectations;
/* Current number of expected connections */
u8 expecting[NF_CT_MAX_EXPECT_CLASSES];
+
+ /* private helper information. */
+ char data[];
};
#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
return nf_ct_net(exp->master);
}
+#define NF_CT_EXP_POLICY_NAME_LEN 16
+
struct nf_conntrack_expect_policy {
unsigned int max_expected;
unsigned int timeout;
- const char *name;
+ char name[NF_CT_EXP_POLICY_NAME_LEN];
};
#define NF_CT_EXPECT_CLASS_DEFAULT 0
}
/* Add this type, returns pointer to data or NULL. */
-void *
-__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp);
+void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
+ size_t var_alloc_len, gfp_t gfp);
+
#define nf_ct_ext_add(ct, id, gfp) \
- ((id##_TYPE *)__nf_ct_ext_add((ct), (id), (gfp)))
+ ((id##_TYPE *)__nf_ct_ext_add_length((ct), (id), 0, (gfp)))
+#define nf_ct_ext_add_length(ct, id, len, gfp) \
+ ((id##_TYPE *)__nf_ct_ext_add_length((ct), (id), (len), (gfp)))
#define NF_CT_EXT_F_PREALLOC 0x0001
#define _NF_CONNTRACK_HELPER_H
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_expect.h>
struct module;
+enum nf_ct_helper_flags {
+ NF_CT_HELPER_F_USERSPACE = (1 << 0),
+ NF_CT_HELPER_F_CONFIGURED = (1 << 1),
+};
+
#define NF_CT_HELPER_NAME_LEN 16
struct nf_conntrack_helper {
struct hlist_node hnode; /* Internal use. */
- const char *name; /* name of the module */
+ char name[NF_CT_HELPER_NAME_LEN]; /* name of the module */
struct module *me; /* pointer to self */
const struct nf_conntrack_expect_policy *expect_policy;
+ /* length of internal data, ie. sizeof(struct nf_ct_*_master) */
+ size_t data_len;
+
/* Tuple of things we will help (compared against server response) */
struct nf_conntrack_tuple tuple;
void (*destroy)(struct nf_conn *ct);
+ int (*from_nlattr)(struct nlattr *attr, struct nf_conn *ct);
int (*to_nlattr)(struct sk_buff *skb, const struct nf_conn *ct);
unsigned int expect_class_max;
+
+ unsigned int flags;
+ unsigned int queue_num; /* For user-space helpers. */
};
extern struct nf_conntrack_helper *
extern int nf_conntrack_helper_register(struct nf_conntrack_helper *);
extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
-extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp);
+extern struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp);
extern int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
gfp_t flags);
return nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
}
+static inline void *nfct_help_data(const struct nf_conn *ct)
+{
+ struct nf_conn_help *help;
+
+ help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
+
+ return (void *)help->data;
+}
+
extern int nf_conntrack_helper_init(struct net *net);
extern void nf_conntrack_helper_fini(struct net *net);
struct nf_ct_helper_expectfn *
nf_ct_helper_expectfn_find_by_symbol(const void *symbol);
+extern struct hlist_head *nf_ct_helper_hash;
+extern unsigned int nf_ct_helper_hsize;
+
#endif /*_NF_CONNTRACK_HELPER_H*/
extern s16 nf_nat_get_offset(const struct nf_conn *ct,
enum ip_conntrack_dir dir,
u32 seq);
+
+extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
+ u32 dir, int off);
+
#endif
--- /dev/null
+#ifndef _NET_NFNL_QUEUE_H_
+#define _NET_NFNL_QUEUE_H_
+
+#include <linux/netfilter/nf_conntrack_common.h>
+
+struct nf_conn;
+
+#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT
+struct nf_conn *nfqnl_ct_get(struct sk_buff *entskb, size_t *size,
+ enum ip_conntrack_info *ctinfo);
+struct nf_conn *nfqnl_ct_parse(const struct sk_buff *skb,
+ const struct nlattr *attr,
+ enum ip_conntrack_info *ctinfo);
+int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo);
+void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo, int diff);
+#else
+inline struct nf_conn *
+nfqnl_ct_get(struct sk_buff *entskb, size_t *size, enum ip_conntrack_info *ctinfo)
+{
+ return NULL;
+}
+
+inline struct nf_conn *nfqnl_ct_parse(const struct sk_buff *skb,
+ const struct nlattr *attr,
+ enum ip_conntrack_info *ctinfo)
+{
+ return NULL;
+}
+
+inline int
+nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+ return 0;
+}
+
+inline void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo, int diff)
+{
+}
+#endif /* NF_CONNTRACK */
+#endif
return ip_route_input_common(skb, dst, src, tos, devin, true);
}
-extern void ip_rt_send_redirect(struct sk_buff *skb);
+extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
+ int oif, u32 mark, u8 protocol, int flow_flags);
+extern void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu);
+extern void ip_rt_send_redirect(struct sk_buff *skb);
extern unsigned int inet_addr_type(struct net *net, __be32 addr);
extern unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr);
parse_early_param();
parse_args("Booting kernel", static_command_line, __start___param,
__stop___param - __start___param,
- 0, 0, &unknown_bootoption);
+ -1, -1, &unknown_bootoption);
jump_label_init();
{
int level;
- for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++) {
- pr_info("initlevel:%d=%s, %d registered initcalls\n",
- level, initcall_level_names[level],
- (int) (initcall_levels[level+1]
- - initcall_levels[level]));
+ for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++)
do_initcall_level(level);
- }
}
/*
return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
}
+static long shm_fallocate(struct file *file, int mode, loff_t offset,
+ loff_t len)
+{
+ struct shm_file_data *sfd = shm_file_data(file);
+
+ if (!sfd->file->f_op->fallocate)
+ return -EOPNOTSUPP;
+ return sfd->file->f_op->fallocate(file, mode, offset, len);
+}
+
static unsigned long shm_get_unmapped_area(struct file *file,
unsigned long addr, unsigned long len, unsigned long pgoff,
unsigned long flags)
.get_unmapped_area = shm_get_unmapped_area,
#endif
.llseek = noop_llseek,
+ .fallocate = shm_fallocate,
};
static const struct file_operations shm_file_operations_huge = {
.release = shm_release,
.get_unmapped_area = shm_get_unmapped_area,
.llseek = noop_llseek,
+ .fallocate = shm_fallocate,
};
int is_file_shm_hugepages(struct file *file)
mutex_unlock(&cgroup_mutex);
/*
- * Drop the active superblock reference that we took when we
- * created the cgroup
+ * We want to drop the active superblock reference from the
+ * cgroup creation after all the dentry refs are gone -
+ * kill_sb gets mighty unhappy otherwise. Mark
+ * dentry->d_fsdata with cgroup_diput() to tell
+ * cgroup_d_release() to call deactivate_super().
*/
- deactivate_super(cgrp->root->sb);
+ dentry->d_fsdata = cgroup_diput;
/*
* if we're getting rid of the cgroup, refcount should ensure
return 1;
}
+static void cgroup_d_release(struct dentry *dentry)
+{
+ /* did cgroup_diput() tell me to deactivate super? */
+ if (dentry->d_fsdata == cgroup_diput)
+ deactivate_super(dentry->d_sb);
+}
+
static void remove_dir(struct dentry *d)
{
struct dentry *parent = dget(d->d_parent);
static const struct dentry_operations cgroup_dops = {
.d_iput = cgroup_diput,
.d_delete = cgroup_delete,
+ .d_release = cgroup_d_release,
};
struct inode *inode =
event = event->group_leader;
perf_event_for_each_child(event, func);
- func(event);
list_for_each_entry(sibling, &event->sibling_list, group_entry)
perf_event_for_each_child(sibling, func);
mutex_unlock(&ctx->mutex);
kstat_incr_irqs_this_cpu(irq, desc);
action = desc->action;
- if (unlikely(!action || irqd_irq_disabled(&desc->irq_data)))
+ if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
+ desc->istate |= IRQS_PENDING;
goto out_unlock;
+ }
irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
raw_spin_unlock_irq(&desc->lock);
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
- if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data)))
+ if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+ desc->istate |= IRQS_PENDING;
goto out_unlock;
+ }
handle_irq_event(desc);
extern void irq_set_thread_affinity(struct irq_desc *desc);
+extern int irq_do_set_affinity(struct irq_data *data,
+ const struct cpumask *dest, bool force);
+
/* Inline functions for support of irq chips on slow busses */
static inline void chip_bus_lock(struct irq_desc *desc)
{
irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
#endif
+int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_desc *desc = irq_data_to_desc(data);
+ struct irq_chip *chip = irq_data_get_irq_chip(data);
+ int ret;
+
+ ret = chip->irq_set_affinity(data, mask, false);
+ switch (ret) {
+ case IRQ_SET_MASK_OK:
+ cpumask_copy(data->affinity, mask);
+ case IRQ_SET_MASK_OK_NOCOPY:
+ irq_set_thread_affinity(desc);
+ ret = 0;
+ }
+
+ return ret;
+}
+
int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
{
struct irq_chip *chip = irq_data_get_irq_chip(data);
return -EINVAL;
if (irq_can_move_pcntxt(data)) {
- ret = chip->irq_set_affinity(data, mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(data->affinity, mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- ret = 0;
- }
+ ret = irq_do_set_affinity(data, mask, false);
} else {
irqd_set_move_pending(data);
irq_copy_pending(desc, mask);
static int
setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
{
- struct irq_chip *chip = irq_desc_get_chip(desc);
struct cpumask *set = irq_default_affinity;
- int ret, node = desc->irq_data.node;
+ int node = desc->irq_data.node;
/* Excludes PER_CPU and NO_BALANCE interrupts */
if (!irq_can_set_affinity(irq))
if (cpumask_intersects(mask, nodemask))
cpumask_and(mask, mask, nodemask);
}
- ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(desc->irq_data.affinity, mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- }
+ irq_do_set_affinity(&desc->irq_data, mask, false);
return 0;
}
#else
* For correct operation this depends on the caller
* masking the irqs.
*/
- if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
- < nr_cpu_ids)) {
- int ret = chip->irq_set_affinity(&desc->irq_data,
- desc->pending_mask, false);
- switch (ret) {
- case IRQ_SET_MASK_OK:
- cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
- case IRQ_SET_MASK_OK_NOCOPY:
- irq_set_thread_affinity(desc);
- }
- }
+ if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
+ irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
cpumask_clear(desc->pending_mask);
}
#define SCHED_FEAT(name, enabled) \
#name ,
-static __read_mostly char *sched_feat_names[] = {
+static const char * const sched_feat_names[] = {
#include "features.h"
- NULL
};
#undef SCHED_FEAT
sched_avg_update(this_rq);
}
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
/*
* Called from nohz_idle_balance() to update the load ratings before doing the
* idle balance.
*/
void update_idle_cpu_load(struct rq *this_rq)
{
- unsigned long curr_jiffies = jiffies;
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
unsigned long load = this_rq->load.weight;
unsigned long pending_updates;
/*
- * Bloody broken means of dealing with nohz, but better than nothing..
- * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
- * update and see 0 difference the one time and 2 the next, even though
- * we ticked at roughtly the same rate.
- *
- * Hence we only use this from nohz_idle_balance() and skip this
- * nonsense when called from the scheduler_tick() since that's
- * guaranteed a stable rate.
+ * bail if there's load or we're actually up-to-date.
*/
if (load || curr_jiffies == this_rq->last_load_update_tick)
return;
__update_cpu_load(this_rq, load, pending_updates);
}
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+ struct rq *this_rq = this_rq();
+ unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+ unsigned long pending_updates;
+
+ if (curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ raw_spin_lock(&this_rq->lock);
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ if (pending_updates) {
+ this_rq->last_load_update_tick = curr_jiffies;
+ /*
+ * We were idle, this means load 0, the current load might be
+ * !0 due to remote wakeups and the sort.
+ */
+ __update_cpu_load(this_rq, 0, pending_updates);
+ }
+ raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
/*
* Called from scheduler_tick()
*/
static void update_cpu_load_active(struct rq *this_rq)
{
/*
- * See the mess in update_idle_cpu_load().
+ * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
*/
this_rq->last_load_update_tick = jiffies;
__update_cpu_load(this_rq, this_rq->load.weight, 1);
p->sched_class->set_cpus_allowed(p, new_mask);
cpumask_copy(&p->cpus_allowed, new_mask);
- p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+ p->nr_cpus_allowed = cpumask_weight(new_mask);
}
/*
#ifdef CONFIG_SCHED_DEBUG
-static __read_mostly int sched_domain_debug_enabled;
+static __read_mostly int sched_debug_enabled;
-static int __init sched_domain_debug_setup(char *str)
+static int __init sched_debug_setup(char *str)
{
- sched_domain_debug_enabled = 1;
+ sched_debug_enabled = 1;
return 0;
}
-early_param("sched_debug", sched_domain_debug_setup);
+early_param("sched_debug", sched_debug_setup);
+
+static inline bool sched_debug(void)
+{
+ return sched_debug_enabled;
+}
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
break;
}
- if (!group->sgp->power) {
+ /*
+ * Even though we initialize ->power to something semi-sane,
+ * we leave power_orig unset. This allows us to detect if
+ * domain iteration is still funny without causing /0 traps.
+ */
+ if (!group->sgp->power_orig) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
{
int level = 0;
- if (!sched_domain_debug_enabled)
+ if (!sched_debug_enabled)
return;
if (!sd) {
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
+static inline bool sched_debug(void)
+{
+ return false;
+}
#endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd)
struct sd_data data;
};
+/*
+ * Build an iteration mask that can exclude certain CPUs from the upwards
+ * domain traversal.
+ *
+ * Asymmetric node setups can result in situations where the domain tree is of
+ * unequal depth, make sure to skip domains that already cover the entire
+ * range.
+ *
+ * In that case build_sched_domains() will have terminated the iteration early
+ * and our sibling sd spans will be empty. Domains should always include the
+ * cpu they're built on, so check that.
+ *
+ */
+static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+{
+ const struct cpumask *span = sched_domain_span(sd);
+ struct sd_data *sdd = sd->private;
+ struct sched_domain *sibling;
+ int i;
+
+ for_each_cpu(i, span) {
+ sibling = *per_cpu_ptr(sdd->sd, i);
+ if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+ continue;
+
+ cpumask_set_cpu(i, sched_group_mask(sg));
+ }
+}
+
+/*
+ * Return the canonical balance cpu for this group, this is the first cpu
+ * of this group that's also in the iteration mask.
+ */
+int group_balance_cpu(struct sched_group *sg)
+{
+ return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+}
+
static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
if (cpumask_test_cpu(i, covered))
continue;
+ child = *per_cpu_ptr(sdd->sd, i);
+
+ /* See the comment near build_group_mask(). */
+ if (!cpumask_test_cpu(i, sched_domain_span(child)))
+ continue;
+
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, cpu_to_node(cpu));
goto fail;
sg_span = sched_group_cpus(sg);
-
- child = *per_cpu_ptr(sdd->sd, i);
if (child->child) {
child = child->child;
cpumask_copy(sg_span, sched_domain_span(child));
cpumask_or(covered, covered, sg_span);
- sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
- atomic_inc(&sg->sgp->ref);
+ sg->sgp = *per_cpu_ptr(sdd->sgp, i);
+ if (atomic_inc_return(&sg->sgp->ref) == 1)
+ build_group_mask(sd, sg);
- if (cpumask_test_cpu(cpu, sg_span))
+ /*
+ * Initialize sgp->power such that even if we mess up the
+ * domains and no possible iteration will get us here, we won't
+ * die on a /0 trap.
+ */
+ sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+
+ /*
+ * Make sure the first group of this domain contains the
+ * canonical balance cpu. Otherwise the sched_domain iteration
+ * breaks. See update_sg_lb_stats().
+ */
+ if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+ group_balance_cpu(sg) == cpu)
groups = sg;
if (!first)
cpumask_clear(sched_group_cpus(sg));
sg->sgp->power = 0;
+ cpumask_setall(sched_group_mask(sg));
for_each_cpu(j, span) {
if (get_group(j, sdd, NULL) != group)
sg = sg->next;
} while (sg != sd->groups);
- if (cpu != group_first_cpu(sg))
+ if (cpu != group_balance_cpu(sg))
return;
update_group_power(sd, cpu);
static int __init setup_relax_domain_level(char *str)
{
- unsigned long val;
-
- val = simple_strtoul(str, NULL, 0);
- if (val < sched_domain_level_max)
- default_relax_domain_level = val;
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+ pr_warn("Unable to set relax_domain_level\n");
return 1;
}
#ifdef CONFIG_NUMA
static int sched_domains_numa_levels;
-static int sched_domains_numa_scale;
static int *sched_domains_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
static int sched_domains_curr_level;
static inline int sd_local_flags(int level)
{
- if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+ if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
return 0;
return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
}
+static void sched_numa_warn(const char *str)
+{
+ static int done = false;
+ int i,j;
+
+ if (done)
+ return;
+
+ done = true;
+
+ printk(KERN_WARNING "ERROR: %s\n\n", str);
+
+ for (i = 0; i < nr_node_ids; i++) {
+ printk(KERN_WARNING " ");
+ for (j = 0; j < nr_node_ids; j++)
+ printk(KERN_CONT "%02d ", node_distance(i,j));
+ printk(KERN_CONT "\n");
+ }
+ printk(KERN_WARNING "\n");
+}
+
+static bool find_numa_distance(int distance)
+{
+ int i;
+
+ if (distance == node_distance(0, 0))
+ return true;
+
+ for (i = 0; i < sched_domains_numa_levels; i++) {
+ if (sched_domains_numa_distance[i] == distance)
+ return true;
+ }
+
+ return false;
+}
+
static void sched_init_numa(void)
{
int next_distance, curr_distance = node_distance(0, 0);
int level = 0;
int i, j, k;
- sched_domains_numa_scale = curr_distance;
sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
if (!sched_domains_numa_distance)
return;
*
* Assumes node_distance(0,j) includes all distances in
* node_distance(i,j) in order to avoid cubic time.
- *
- * XXX: could be optimized to O(n log n) by using sort()
*/
next_distance = curr_distance;
for (i = 0; i < nr_node_ids; i++) {
for (j = 0; j < nr_node_ids; j++) {
- int distance = node_distance(0, j);
- if (distance > curr_distance &&
- (distance < next_distance ||
- next_distance == curr_distance))
- next_distance = distance;
+ for (k = 0; k < nr_node_ids; k++) {
+ int distance = node_distance(i, k);
+
+ if (distance > curr_distance &&
+ (distance < next_distance ||
+ next_distance == curr_distance))
+ next_distance = distance;
+
+ /*
+ * While not a strong assumption it would be nice to know
+ * about cases where if node A is connected to B, B is not
+ * equally connected to A.
+ */
+ if (sched_debug() && node_distance(k, i) != distance)
+ sched_numa_warn("Node-distance not symmetric");
+
+ if (sched_debug() && i && !find_numa_distance(distance))
+ sched_numa_warn("Node-0 not representative");
+ }
+ if (next_distance != curr_distance) {
+ sched_domains_numa_distance[level++] = next_distance;
+ sched_domains_numa_levels = level;
+ curr_distance = next_distance;
+ } else break;
}
- if (next_distance != curr_distance) {
- sched_domains_numa_distance[level++] = next_distance;
- sched_domains_numa_levels = level;
- curr_distance = next_distance;
- } else break;
+
+ /*
+ * In case of sched_debug() we verify the above assumption.
+ */
+ if (!sched_debug())
+ break;
}
/*
* 'level' contains the number of unique distances, excluding the
return;
for (j = 0; j < nr_node_ids; j++) {
- struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+ struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
if (!mask)
return;
*per_cpu_ptr(sdd->sg, j) = sg;
- sgp = kzalloc_node(sizeof(struct sched_group_power),
+ sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sgp)
return -ENOMEM;
if (!sd)
return child;
- set_domain_attribute(sd, attr);
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
child->parent = sd;
}
sd->child = child;
+ set_domain_attribute(sd, attr);
return sd;
}
if (!doms_cur)
doms_cur = &fallback_doms;
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
- dattr_cur = NULL;
err = build_sched_domains(doms_cur[0], NULL);
register_sched_domain_sysctl();
int want_sd = 1;
int sync = wake_flags & WF_SYNC;
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
return prev_cpu;
if (sd_flag & SD_BALANCE_WAKE) {
unsigned long scale_rt_power(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, available;
+ u64 total, available, age_stamp, avg;
- total = sched_avg_period() + (rq->clock - rq->age_stamp);
+ /*
+ * Since we're reading these variables without serialization make sure
+ * we read them once before doing sanity checks on them.
+ */
+ age_stamp = ACCESS_ONCE(rq->age_stamp);
+ avg = ACCESS_ONCE(rq->rt_avg);
+
+ total = sched_avg_period() + (rq->clock - age_stamp);
- if (unlikely(total < rq->rt_avg)) {
+ if (unlikely(total < avg)) {
/* Ensures that power won't end up being negative */
available = 0;
} else {
- available = total - rq->rt_avg;
+ available = total - avg;
}
if (unlikely((s64)total < SCHED_POWER_SCALE))
power = 0;
- group = child->groups;
- do {
- power += group->sgp->power;
- group = group->next;
- } while (group != child->groups);
+ if (child->flags & SD_OVERLAP) {
+ /*
+ * SD_OVERLAP domains cannot assume that child groups
+ * span the current group.
+ */
- sdg->sgp->power = power;
+ for_each_cpu(cpu, sched_group_cpus(sdg))
+ power += power_of(cpu);
+ } else {
+ /*
+ * !SD_OVERLAP domains can assume that child groups
+ * span the current group.
+ */
+
+ group = child->groups;
+ do {
+ power += group->sgp->power;
+ group = group->next;
+ } while (group != child->groups);
+ }
+
+ sdg->sgp->power_orig = sdg->sgp->power = power;
}
/*
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
+ * @env: The load balancing environment.
* @group: sched_group whose statistics are to be updated.
* @load_idx: Load index of sched_domain of this_cpu for load calc.
* @local_group: Does group contain this_cpu.
int i;
if (local_group)
- balance_cpu = group_first_cpu(group);
+ balance_cpu = group_balance_cpu(group);
/* Tally up the load of all CPUs in the group */
max_cpu_load = 0;
/* Bias balancing toward cpus of our domain */
if (local_group) {
- if (idle_cpu(i) && !first_idle_cpu) {
+ if (idle_cpu(i) && !first_idle_cpu &&
+ cpumask_test_cpu(i, sched_group_mask(group))) {
first_idle_cpu = 1;
balance_cpu = i;
}
/**
* update_sd_pick_busiest - return 1 on busiest group
- * @sd: sched_domain whose statistics are to be checked
+ * @env: The load balancing environment.
* @sds: sched_domain statistics
* @sg: sched_group candidate to be checked for being the busiest
* @sgs: sched_group statistics
- * @this_cpu: the current cpu
*
* Determine if @sg is a busier group than the previously selected
* busiest group.
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
+ * @env: The load balancing environment.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
* Returns 1 when packing is required and a task should be moved to
* this CPU. The amount of the imbalance is returned in *imbalance.
*
- * @sd: The sched_domain whose packing is to be checked.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain which is to be packed
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: returns amount of imbalanced due to packing.
*/
static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
{
* fix_small_imbalance - Calculate the minor imbalance that exists
* amongst the groups of a sched_domain, during
* load balancing.
+ * @env: The load balancing environment.
* @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: Variable to store the imbalance.
*/
static inline
void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
* Also calculates the amount of weighted load which should be moved
* to restore balance.
*
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- * be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
+ * @env: The load balancing environment.
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total++;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory++;
update_rt_migration(rt_rq);
static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
+ struct task_struct *p;
+
if (!rt_entity_is_task(rt_se))
return;
+ p = rt_task_of(rt_se);
rt_rq = &rq_of_rt_rq(rt_rq)->rt;
rt_rq->rt_nr_total--;
- if (rt_se->nr_cpus_allowed > 1)
+ if (p->nr_cpus_allowed > 1)
rt_rq->rt_nr_migratory--;
update_rt_migration(rt_rq);
enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
- if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+ if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
inc_nr_running(rq);
cpu = task_cpu(p);
- if (p->rt.nr_cpus_allowed == 1)
+ if (p->nr_cpus_allowed == 1)
goto out;
/* For anything but wake ups, just return the task_cpu */
* will have to sort it out.
*/
if (curr && unlikely(rt_task(curr)) &&
- (curr->rt.nr_cpus_allowed < 2 ||
+ (curr->nr_cpus_allowed < 2 ||
curr->prio <= p->prio) &&
- (p->rt.nr_cpus_allowed > 1)) {
+ (p->nr_cpus_allowed > 1)) {
int target = find_lowest_rq(p);
if (target != -1)
static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
- if (rq->curr->rt.nr_cpus_allowed == 1)
+ if (rq->curr->nr_cpus_allowed == 1)
return;
- if (p->rt.nr_cpus_allowed != 1
+ if (p->nr_cpus_allowed != 1
&& cpupri_find(&rq->rd->cpupri, p, NULL))
return;
* The previous task needs to be made eligible for pushing
* if it is still active
*/
- if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
+ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
}
{
if (!task_running(rq, p) &&
(cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
- (p->rt.nr_cpus_allowed > 1))
+ (p->nr_cpus_allowed > 1))
return 1;
return 0;
}
if (unlikely(!lowest_mask))
return -1;
- if (task->rt.nr_cpus_allowed == 1)
+ if (task->nr_cpus_allowed == 1)
return -1; /* No other targets possible */
if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
task_running(rq, task) ||
!task->on_rq)) {
- raw_spin_unlock(&lowest_rq->lock);
+ double_unlock_balance(rq, lowest_rq);
lowest_rq = NULL;
break;
}
BUG_ON(rq->cpu != task_cpu(p));
BUG_ON(task_current(rq, p));
- BUG_ON(p->rt.nr_cpus_allowed <= 1);
+ BUG_ON(p->nr_cpus_allowed <= 1);
BUG_ON(!p->on_rq);
BUG_ON(!rt_task(p));
if (!task_running(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
- p->rt.nr_cpus_allowed > 1 &&
+ p->nr_cpus_allowed > 1 &&
rt_task(rq->curr) &&
- (rq->curr->rt.nr_cpus_allowed < 2 ||
+ (rq->curr->nr_cpus_allowed < 2 ||
rq->curr->prio <= p->prio))
push_rt_tasks(rq);
}
* Only update if the process changes its state from whether it
* can migrate or not.
*/
- if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+ if ((p->nr_cpus_allowed > 1) == (weight > 1))
return;
rq = task_rq(p);
static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
+ struct sched_rt_entity *rt_se = &p->rt;
+
update_curr_rt(rq);
watchdog(rq, p);
p->rt.time_slice = RR_TIMESLICE;
/*
- * Requeue to the end of queue if we are not the only element
- * on the queue:
+ * Requeue to the end of queue if we (and all of our ancestors) are the
+ * only element on the queue
*/
- if (p->rt.run_list.prev != p->rt.run_list.next) {
- requeue_task_rt(rq, p, 0);
- set_tsk_need_resched(p);
+ for_each_sched_rt_entity(rt_se) {
+ if (rt_se->run_list.prev != rt_se->run_list.next) {
+ requeue_task_rt(rq, p, 0);
+ set_tsk_need_resched(p);
+ return;
+ }
}
}
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_id);
+extern int group_balance_cpu(struct sched_group *sg);
+
#endif /* CONFIG_SMP */
#include "stats.h"
per_cpu(idle_threads, smp_processor_id()) = current;
}
+/**
+ * idle_init - Initialize the idle thread for a cpu
+ * @cpu: The cpu for which the idle thread should be initialized
+ *
+ * Creates the thread if it does not exist.
+ */
static inline void idle_init(unsigned int cpu)
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
}
/**
- * idle_thread_init - Initialize the idle thread for a cpu
- * @cpu: The cpu for which the idle thread should be initialized
- *
- * Creates the thread if it does not exist.
+ * idle_threads_init - Initialize idle threads for all cpus
*/
void __init idle_threads_init(void)
{
- unsigned int cpu;
+ unsigned int cpu, boot_cpu;
+
+ boot_cpu = smp_processor_id();
for_each_possible_cpu(cpu) {
- if (cpu != smp_processor_id())
+ if (cpu != boot_cpu)
idle_init(cpu);
}
}
}
#ifdef CONFIG_CHECKPOINT_RESTORE
-static bool vma_flags_mismatch(struct vm_area_struct *vma,
- unsigned long required,
- unsigned long banned)
-{
- return (vma->vm_flags & required) != required ||
- (vma->vm_flags & banned);
-}
-
static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
{
+ struct vm_area_struct *vma;
struct file *exe_file;
struct dentry *dentry;
int err;
- /*
- * Setting new mm::exe_file is only allowed when no VM_EXECUTABLE vma's
- * remain. So perform a quick test first.
- */
- if (mm->num_exe_file_vmas)
- return -EBUSY;
-
exe_file = fget(fd);
if (!exe_file)
return -EBADF;
if (err)
goto exit;
+ down_write(&mm->mmap_sem);
+
+ /*
+ * Forbid mm->exe_file change if there are mapped other files.
+ */
+ err = -EBUSY;
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma->vm_file && !path_equal(&vma->vm_file->f_path,
+ &exe_file->f_path))
+ goto exit_unlock;
+ }
+
/*
* The symlink can be changed only once, just to disallow arbitrary
* transitions malicious software might bring in. This means one
* could make a snapshot over all processes running and monitor
* /proc/pid/exe changes to notice unusual activity if needed.
*/
- down_write(&mm->mmap_sem);
- if (likely(!mm->exe_file))
- set_mm_exe_file(mm, exe_file);
- else
- err = -EBUSY;
+ err = -EPERM;
+ if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
+ goto exit_unlock;
+
+ set_mm_exe_file(mm, exe_file);
+exit_unlock:
up_write(&mm->mmap_sem);
exit:
if (opt == PR_SET_MM_EXE_FILE)
return prctl_set_mm_exe_file(mm, (unsigned int)addr);
- if (addr >= TASK_SIZE)
+ if (addr >= TASK_SIZE || addr < mmap_min_addr)
return -EINVAL;
error = -EINVAL;
error = -EFAULT;
goto out;
}
-#ifdef CONFIG_STACK_GROWSUP
- if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSUP, 0))
-#else
- if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSDOWN, 0))
-#endif
- goto out;
if (opt == PR_SET_MM_START_STACK)
mm->start_stack = addr;
else if (opt == PR_SET_MM_ARG_START)
up_read(&mm->mmap_sem);
return error;
}
+
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return put_user(me->clear_child_tid, tid_addr);
+}
+
#else /* CONFIG_CHECKPOINT_RESTORE */
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
return -EINVAL;
}
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+ return -EINVAL;
+}
#endif
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
else
return -EINVAL;
break;
+ case PR_GET_TID_ADDRESS:
+ error = prctl_get_tid_address(me, (int __user **)arg2);
+ break;
default:
return -EINVAL;
}
}
EXPORT_SYMBOL_GPL(clockevents_register_device);
-static void clockevents_config(struct clock_event_device *dev,
- u32 freq)
+void clockevents_config(struct clock_event_device *dev, u32 freq)
{
u64 sec;
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
+ update_cpu_load_nohz();
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
return HRTIMER_RESTART;
}
+static int sched_skew_tick;
+
+static int __init skew_tick(char *str)
+{
+ get_option(&str, &sched_skew_tick);
+
+ return 0;
+}
+early_param("skew_tick", skew_tick);
+
/**
* tick_setup_sched_timer - setup the tick emulation timer
*/
/* Get the next period (per cpu) */
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
+ /* Offset the tick to avert xtime_lock contention. */
+ if (sched_skew_tick) {
+ u64 offset = ktime_to_ns(tick_period) >> 1;
+ do_div(offset, num_possible_cpus());
+ offset *= smp_processor_id();
+ hrtimer_add_expires_ns(&ts->sched_timer, offset);
+ }
+
for (;;) {
hrtimer_forward(&ts->sched_timer, now, tick_period);
hrtimer_start_expires(&ts->sched_timer,
timekeeper.xtime.tv_sec++;
leap = second_overflow(timekeeper.xtime.tv_sec);
timekeeper.xtime.tv_sec += leap;
+ timekeeper.wall_to_monotonic.tv_sec -= leap;
}
/* Accumulate raw time */
timekeeper.xtime.tv_sec++;
leap = second_overflow(timekeeper.xtime.tv_sec);
timekeeper.xtime.tv_sec += leap;
+ timekeeper.wall_to_monotonic.tv_sec -= leap;
}
timekeeping_update(false);
if (head->height == 0)
return NULL;
-retry:
longcpy(key, __key, geo->keylen);
+retry:
dec_key(geo, key);
node = head->node;
}
miss:
if (retry_key) {
- __key = retry_key;
+ longcpy(key, retry_key, geo->keylen);
retry_key = NULL;
goto retry;
}
int btree_insert(struct btree_head *head, struct btree_geo *geo,
unsigned long *key, void *val, gfp_t gfp)
{
+ BUG_ON(!val);
return btree_insert_level(head, geo, key, val, 1, gfp);
}
EXPORT_SYMBOL_GPL(btree_insert);
* during iterating; it can be zero only at the beginning.
* And we cannot overflow iter->next_index in a single step,
* because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+ *
+ * This condition also used by radix_tree_next_slot() to stop
+ * contiguous iterating, and forbid swithing to the next chunk.
*/
index = iter->next_index;
if (!index && iter->index)
#include <linux/raid/pq.h>
/* Recover two failed data blocks. */
-void raid6_2data_recov_intx1(int disks, size_t bytes, int faila, int failb,
- void **ptrs)
+static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila,
+ int failb, void **ptrs)
{
u8 *p, *q, *dp, *dq;
u8 px, qx, db;
}
/* Recover failure of one data block plus the P block */
-void raid6_datap_recov_intx1(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila,
+ void **ptrs)
{
u8 *p, *q, *dq;
const u8 *qmul; /* Q multiplier table */
boot_cpu_has(X86_FEATURE_SSSE3);
}
-void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila, int failb,
- void **ptrs)
+static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
+ int failb, void **ptrs)
{
u8 *p, *q, *dp, *dq;
const u8 *pbmul; /* P multiplier table for B data */
}
-void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
+ void **ptrs)
{
u8 *p, *q, *dq;
const u8 *qmul; /* Q multiplier table */
in a negligible performance hit.
If unsure, say Y to enable cleancache
+
+config FRONTSWAP
+ bool "Enable frontswap to cache swap pages if tmem is present"
+ depends on SWAP
+ default n
+ help
+ Frontswap is so named because it can be thought of as the opposite
+ of a "backing" store for a swap device. The data is stored into
+ "transcendent memory", memory that is not directly accessible or
+ addressable by the kernel and is of unknown and possibly
+ time-varying size. When space in transcendent memory is available,
+ a significant swap I/O reduction may be achieved. When none is
+ available, all frontswap calls are reduced to a single pointer-
+ compare-against-NULL resulting in a negligible performance hit
+ and swap data is stored as normal on the matching swap device.
+
+ If unsure, say Y to enable frontswap.
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o
+obj-$(CONFIG_FRONTSWAP) += frontswap.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
obj-$(CONFIG_HUGETLBFS) += hugetlb.o
obj-$(CONFIG_NUMA) += mempolicy.o
*/
while (unlikely(too_many_isolated(zone))) {
/* async migration should just abort */
- if (cc->mode != COMPACT_SYNC)
+ if (!cc->sync)
return 0;
congestion_wait(BLK_RW_ASYNC, HZ/10);
* satisfies the allocation
*/
pageblock_nr = low_pfn >> pageblock_order;
- if (cc->mode != COMPACT_SYNC &&
- last_pageblock_nr != pageblock_nr &&
+ if (!cc->sync && last_pageblock_nr != pageblock_nr &&
!migrate_async_suitable(get_pageblock_migratetype(page))) {
low_pfn += pageblock_nr_pages;
low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
continue;
}
- if (cc->mode != COMPACT_SYNC)
+ if (!cc->sync)
mode |= ISOLATE_ASYNC_MIGRATE;
lruvec = mem_cgroup_page_lruvec(page, zone);
#endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION
-/*
- * Returns true if MIGRATE_UNMOVABLE pageblock was successfully
- * converted to MIGRATE_MOVABLE type, false otherwise.
- */
-static bool rescue_unmovable_pageblock(struct page *page)
-{
- unsigned long pfn, start_pfn, end_pfn;
- struct page *start_page, *end_page;
-
- pfn = page_to_pfn(page);
- start_pfn = pfn & ~(pageblock_nr_pages - 1);
- end_pfn = start_pfn + pageblock_nr_pages;
-
- start_page = pfn_to_page(start_pfn);
- end_page = pfn_to_page(end_pfn);
-
- /* Do not deal with pageblocks that overlap zones */
- if (page_zone(start_page) != page_zone(end_page))
- return false;
-
- for (page = start_page, pfn = start_pfn; page < end_page; pfn++,
- page++) {
- if (!pfn_valid_within(pfn))
- continue;
-
- if (PageBuddy(page)) {
- int order = page_order(page);
-
- pfn += (1 << order) - 1;
- page += (1 << order) - 1;
-
- continue;
- } else if (page_count(page) == 0 || PageLRU(page))
- continue;
-
- return false;
- }
-
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE);
- return true;
-}
-enum smt_result {
- GOOD_AS_MIGRATION_TARGET,
- FAIL_UNMOVABLE_TARGET,
- FAIL_BAD_TARGET,
-};
-
-/*
- * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block
- * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page
- * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise.
- */
-static enum smt_result suitable_migration_target(struct page *page,
- struct compact_control *cc)
+/* Returns true if the page is within a block suitable for migration to */
+static bool suitable_migration_target(struct page *page)
{
int migratetype = get_pageblock_migratetype(page);
/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
- return FAIL_BAD_TARGET;
+ return false;
/* If the page is a large free page, then allow migration */
if (PageBuddy(page) && page_order(page) >= pageblock_order)
- return GOOD_AS_MIGRATION_TARGET;
+ return true;
/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
- if (cc->mode != COMPACT_ASYNC_UNMOVABLE &&
- migrate_async_suitable(migratetype))
- return GOOD_AS_MIGRATION_TARGET;
-
- if (cc->mode == COMPACT_ASYNC_MOVABLE &&
- migratetype == MIGRATE_UNMOVABLE)
- return FAIL_UNMOVABLE_TARGET;
-
- if (cc->mode != COMPACT_ASYNC_MOVABLE &&
- migratetype == MIGRATE_UNMOVABLE &&
- rescue_unmovable_pageblock(page))
- return GOOD_AS_MIGRATION_TARGET;
+ if (migrate_async_suitable(migratetype))
+ return true;
/* Otherwise skip the block */
- return FAIL_BAD_TARGET;
+ return false;
}
/*
zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
- /*
- * isolate_freepages() may be called more than once during
- * compact_zone_order() run and we want only the most recent
- * count.
- */
- cc->nr_pageblocks_skipped = 0;
-
/*
* Isolate free pages until enough are available to migrate the
* pages on cc->migratepages. We stop searching if the migrate
for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
pfn -= pageblock_nr_pages) {
unsigned long isolated;
- enum smt_result ret;
if (!pfn_valid(pfn))
continue;
continue;
/* Check the block is suitable for migration */
- ret = suitable_migration_target(page, cc);
- if (ret != GOOD_AS_MIGRATION_TARGET) {
- if (ret == FAIL_UNMOVABLE_TARGET)
- cc->nr_pageblocks_skipped++;
+ if (!suitable_migration_target(page))
continue;
- }
+
/*
* Found a block suitable for isolating free pages from. Now
* we disabled interrupts, double check things are ok and
*/
isolated = 0;
spin_lock_irqsave(&zone->lock, flags);
- ret = suitable_migration_target(page, cc);
- if (ret == GOOD_AS_MIGRATION_TARGET) {
+ if (suitable_migration_target(page)) {
end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
isolated = isolate_freepages_block(pfn, end_pfn,
freelist, false);
nr_freepages += isolated;
- } else if (ret == FAIL_UNMOVABLE_TARGET)
- cc->nr_pageblocks_skipped++;
+ }
spin_unlock_irqrestore(&zone->lock, flags);
/*
nr_migrate = cc->nr_migratepages;
err = migrate_pages(&cc->migratepages, compaction_alloc,
- (unsigned long)&cc->freepages, false,
- (cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT
- : MIGRATE_ASYNC);
+ (unsigned long)cc, false,
+ cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
update_nr_listpages(cc);
nr_remaining = cc->nr_migratepages;
static unsigned long compact_zone_order(struct zone *zone,
int order, gfp_t gfp_mask,
- enum compact_mode mode,
- unsigned long *nr_pageblocks_skipped)
+ bool sync)
{
struct compact_control cc = {
.nr_freepages = 0,
.order = order,
.migratetype = allocflags_to_migratetype(gfp_mask),
.zone = zone,
- .mode = mode,
+ .sync = sync,
};
- unsigned long rc;
-
INIT_LIST_HEAD(&cc.freepages);
INIT_LIST_HEAD(&cc.migratepages);
- rc = compact_zone(zone, &cc);
- *nr_pageblocks_skipped = cc.nr_pageblocks_skipped;
-
- return rc;
+ return compact_zone(zone, &cc);
}
int sysctl_extfrag_threshold = 500;
struct zoneref *z;
struct zone *zone;
int rc = COMPACT_SKIPPED;
- unsigned long nr_pageblocks_skipped;
- enum compact_mode mode;
/*
* Check whether it is worth even starting compaction. The order check is
nodemask) {
int status;
- mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE;
-retry:
- status = compact_zone_order(zone, order, gfp_mask, mode,
- &nr_pageblocks_skipped);
+ status = compact_zone_order(zone, order, gfp_mask, sync);
rc = max(status, rc);
/* If a normal allocation would succeed, stop compacting */
if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
break;
-
- if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) {
- if (nr_pageblocks_skipped) {
- mode = COMPACT_ASYNC_UNMOVABLE;
- goto retry;
- }
- }
}
return rc;
if (ok && cc->order > zone->compact_order_failed)
zone->compact_order_failed = cc->order + 1;
/* Currently async compaction is never deferred. */
- else if (!ok && cc->mode == COMPACT_SYNC)
+ else if (!ok && cc->sync)
defer_compaction(zone, cc->order);
}
{
struct compact_control cc = {
.order = order,
- .mode = COMPACT_ASYNC_MOVABLE,
+ .sync = false,
};
return __compact_pgdat(pgdat, &cc);
{
struct compact_control cc = {
.order = -1,
- .mode = COMPACT_SYNC,
+ .sync = true,
};
return __compact_pgdat(NODE_DATA(nid), &cc);
--- /dev/null
+/*
+ * Frontswap frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of frontswap. See
+ * Documentation/vm/frontswap.txt for more information.
+ *
+ * Copyright (C) 2009-2012 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/proc_fs.h>
+#include <linux/security.h>
+#include <linux/capability.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
+
+/*
+ * frontswap_ops is set by frontswap_register_ops to contain the pointers
+ * to the frontswap "backend" implementation functions.
+ */
+static struct frontswap_ops frontswap_ops __read_mostly;
+
+/*
+ * This global enablement flag reduces overhead on systems where frontswap_ops
+ * has not been registered, so is preferred to the slower alternative: a
+ * function call that checks a non-global.
+ */
+bool frontswap_enabled __read_mostly;
+EXPORT_SYMBOL(frontswap_enabled);
+
+/*
+ * If enabled, frontswap_store will return failure even on success. As
+ * a result, the swap subsystem will always write the page to swap, in
+ * effect converting frontswap into a writethrough cache. In this mode,
+ * there is no direct reduction in swap writes, but a frontswap backend
+ * can unilaterally "reclaim" any pages in use with no data loss, thus
+ * providing increases control over maximum memory usage due to frontswap.
+ */
+static bool frontswap_writethrough_enabled __read_mostly;
+
+#ifdef CONFIG_DEBUG_FS
+/*
+ * Counters available via /sys/kernel/debug/frontswap (if debugfs is
+ * properly configured). These are for information only so are not protected
+ * against increment races.
+ */
+static u64 frontswap_loads;
+static u64 frontswap_succ_stores;
+static u64 frontswap_failed_stores;
+static u64 frontswap_invalidates;
+
+static inline void inc_frontswap_loads(void) {
+ frontswap_loads++;
+}
+static inline void inc_frontswap_succ_stores(void) {
+ frontswap_succ_stores++;
+}
+static inline void inc_frontswap_failed_stores(void) {
+ frontswap_failed_stores++;
+}
+static inline void inc_frontswap_invalidates(void) {
+ frontswap_invalidates++;
+}
+#else
+static inline void inc_frontswap_loads(void) { }
+static inline void inc_frontswap_succ_stores(void) { }
+static inline void inc_frontswap_failed_stores(void) { }
+static inline void inc_frontswap_invalidates(void) { }
+#endif
+/*
+ * Register operations for frontswap, returning previous thus allowing
+ * detection of multiple backends and possible nesting.
+ */
+struct frontswap_ops frontswap_register_ops(struct frontswap_ops *ops)
+{
+ struct frontswap_ops old = frontswap_ops;
+
+ frontswap_ops = *ops;
+ frontswap_enabled = true;
+ return old;
+}
+EXPORT_SYMBOL(frontswap_register_ops);
+
+/*
+ * Enable/disable frontswap writethrough (see above).
+ */
+void frontswap_writethrough(bool enable)
+{
+ frontswap_writethrough_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_writethrough);
+
+/*
+ * Called when a swap device is swapon'd.
+ */
+void __frontswap_init(unsigned type)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ if (frontswap_enabled)
+ (*frontswap_ops.init)(type);
+}
+EXPORT_SYMBOL(__frontswap_init);
+
+/*
+ * "Store" data from a page to frontswap and associate it with the page's
+ * swaptype and offset. Page must be locked and in the swap cache.
+ * If frontswap already contains a page with matching swaptype and
+ * offset, the frontswap implmentation may either overwrite the data and
+ * return success or invalidate the page from frontswap and return failure.
+ */
+int __frontswap_store(struct page *page)
+{
+ int ret = -1, dup = 0;
+ swp_entry_t entry = { .val = page_private(page), };
+ int type = swp_type(entry);
+ struct swap_info_struct *sis = swap_info[type];
+ pgoff_t offset = swp_offset(entry);
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset))
+ dup = 1;
+ ret = (*frontswap_ops.store)(type, offset, page);
+ if (ret == 0) {
+ frontswap_set(sis, offset);
+ inc_frontswap_succ_stores();
+ if (!dup)
+ atomic_inc(&sis->frontswap_pages);
+ } else if (dup) {
+ /*
+ failed dup always results in automatic invalidate of
+ the (older) page from frontswap
+ */
+ frontswap_clear(sis, offset);
+ atomic_dec(&sis->frontswap_pages);
+ inc_frontswap_failed_stores();
+ } else
+ inc_frontswap_failed_stores();
+ if (frontswap_writethrough_enabled)
+ /* report failure so swap also writes to swap device */
+ ret = -1;
+ return ret;
+}
+EXPORT_SYMBOL(__frontswap_store);
+
+/*
+ * "Get" data from frontswap associated with swaptype and offset that were
+ * specified when the data was put to frontswap and use it to fill the
+ * specified page with data. Page must be locked and in the swap cache.
+ */
+int __frontswap_load(struct page *page)
+{
+ int ret = -1;
+ swp_entry_t entry = { .val = page_private(page), };
+ int type = swp_type(entry);
+ struct swap_info_struct *sis = swap_info[type];
+ pgoff_t offset = swp_offset(entry);
+
+ BUG_ON(!PageLocked(page));
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset))
+ ret = (*frontswap_ops.load)(type, offset, page);
+ if (ret == 0)
+ inc_frontswap_loads();
+ return ret;
+}
+EXPORT_SYMBOL(__frontswap_load);
+
+/*
+ * Invalidate any data from frontswap associated with the specified swaptype
+ * and offset so that a subsequent "get" will fail.
+ */
+void __frontswap_invalidate_page(unsigned type, pgoff_t offset)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (frontswap_test(sis, offset)) {
+ (*frontswap_ops.invalidate_page)(type, offset);
+ atomic_dec(&sis->frontswap_pages);
+ frontswap_clear(sis, offset);
+ inc_frontswap_invalidates();
+ }
+}
+EXPORT_SYMBOL(__frontswap_invalidate_page);
+
+/*
+ * Invalidate all data from frontswap associated with all offsets for the
+ * specified swaptype.
+ */
+void __frontswap_invalidate_area(unsigned type)
+{
+ struct swap_info_struct *sis = swap_info[type];
+
+ BUG_ON(sis == NULL);
+ if (sis->frontswap_map == NULL)
+ return;
+ (*frontswap_ops.invalidate_area)(type);
+ atomic_set(&sis->frontswap_pages, 0);
+ memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+}
+EXPORT_SYMBOL(__frontswap_invalidate_area);
+
+/*
+ * Frontswap, like a true swap device, may unnecessarily retain pages
+ * under certain circumstances; "shrink" frontswap is essentially a
+ * "partial swapoff" and works by calling try_to_unuse to attempt to
+ * unuse enough frontswap pages to attempt to -- subject to memory
+ * constraints -- reduce the number of pages in frontswap to the
+ * number given in the parameter target_pages.
+ */
+void frontswap_shrink(unsigned long target_pages)
+{
+ struct swap_info_struct *si = NULL;
+ int si_frontswap_pages;
+ unsigned long total_pages = 0, total_pages_to_unuse;
+ unsigned long pages = 0, pages_to_unuse = 0;
+ int type;
+ bool locked = false;
+
+ /*
+ * we don't want to hold swap_lock while doing a very
+ * lengthy try_to_unuse, but swap_list may change
+ * so restart scan from swap_list.head each time
+ */
+ spin_lock(&swap_lock);
+ locked = true;
+ total_pages = 0;
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ total_pages += atomic_read(&si->frontswap_pages);
+ }
+ if (total_pages <= target_pages)
+ goto out;
+ total_pages_to_unuse = total_pages - target_pages;
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ si_frontswap_pages = atomic_read(&si->frontswap_pages);
+ if (total_pages_to_unuse < si_frontswap_pages)
+ pages = pages_to_unuse = total_pages_to_unuse;
+ else {
+ pages = si_frontswap_pages;
+ pages_to_unuse = 0; /* unuse all */
+ }
+ /* ensure there is enough RAM to fetch pages from frontswap */
+ if (security_vm_enough_memory_mm(current->mm, pages))
+ continue;
+ vm_unacct_memory(pages);
+ break;
+ }
+ if (type < 0)
+ goto out;
+ locked = false;
+ spin_unlock(&swap_lock);
+ try_to_unuse(type, true, pages_to_unuse);
+out:
+ if (locked)
+ spin_unlock(&swap_lock);
+ return;
+}
+EXPORT_SYMBOL(frontswap_shrink);
+
+/*
+ * Count and return the number of frontswap pages across all
+ * swap devices. This is exported so that backend drivers can
+ * determine current usage without reading debugfs.
+ */
+unsigned long frontswap_curr_pages(void)
+{
+ int type;
+ unsigned long totalpages = 0;
+ struct swap_info_struct *si = NULL;
+
+ spin_lock(&swap_lock);
+ for (type = swap_list.head; type >= 0; type = si->next) {
+ si = swap_info[type];
+ totalpages += atomic_read(&si->frontswap_pages);
+ }
+ spin_unlock(&swap_lock);
+ return totalpages;
+}
+EXPORT_SYMBOL(frontswap_curr_pages);
+
+static int __init init_frontswap(void)
+{
+#ifdef CONFIG_DEBUG_FS
+ struct dentry *root = debugfs_create_dir("frontswap", NULL);
+ if (root == NULL)
+ return -ENXIO;
+ debugfs_create_u64("loads", S_IRUGO, root, &frontswap_loads);
+ debugfs_create_u64("succ_stores", S_IRUGO, root, &frontswap_succ_stores);
+ debugfs_create_u64("failed_stores", S_IRUGO, root,
+ &frontswap_failed_stores);
+ debugfs_create_u64("invalidates", S_IRUGO,
+ root, &frontswap_invalidates);
+#endif
+ return 0;
+}
+
+module_init(init_frontswap);
/*
* in mm/page_alloc.c
*/
-extern void set_pageblock_migratetype(struct page *page, int migratetype);
-extern int move_freepages_block(struct zone *zone, struct page *page,
- int migratetype);
extern void __free_pages_bootmem(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned long order);
#ifdef CONFIG_MEMORY_FAILURE
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
-#include <linux/compaction.h>
/*
* in mm/compaction.c
unsigned long nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
unsigned long migrate_pfn; /* isolate_migratepages search base */
- enum compact_mode mode; /* Compaction mode */
+ bool sync; /* Synchronous migration */
int order; /* order a direct compactor needs */
int migratetype; /* MOVABLE, RECLAIMABLE etc */
struct zone *zone;
-
- /* Number of UNMOVABLE destination pageblocks skipped during scan */
- unsigned long nr_pageblocks_skipped;
};
unsigned long
* is actually a signal that all of the page has become dirty.
* Whereas only part of our page may be dirty.
*/
- __set_page_dirty_nobuffers(newpage);
+ if (PageSwapBacked(page))
+ SetPageDirty(newpage);
+ else
+ __set_page_dirty_nobuffers(newpage);
}
mlock_migrate_page(newpage, page);
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
- ret = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+ retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
if (file)
fput(file);
unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
- unsigned long points;
+ long points;
if (oom_unkillable_task(p, memcg, nodemask))
return 0;
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
- return points ? points : 1;
+ return points > 0 ? points : 1;
}
/*
int page_group_by_mobility_disabled __read_mostly;
-void set_pageblock_migratetype(struct page *page, int migratetype)
+static void set_pageblock_migratetype(struct page *page, int migratetype)
{
if (unlikely(page_group_by_mobility_disabled))
return pages_moved;
}
-int move_freepages_block(struct zone *zone, struct page *page,
- int migratetype)
+static int move_freepages_block(struct zone *zone, struct page *page,
+ int migratetype)
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
- .mode = COMPACT_SYNC,
+ .sync = true,
};
INIT_LIST_HEAD(&cc.migratepages);
#include <linux/bio.h>
#include <linux/swapops.h>
#include <linux/writeback.h>
+#include <linux/frontswap.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags,
unlock_page(page);
goto out;
}
+ if (frontswap_store(page) == 0) {
+ set_page_writeback(page);
+ unlock_page(page);
+ end_page_writeback(page);
+ goto out;
+ }
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(PageUptodate(page));
+ if (frontswap_load(page) == 0) {
+ SetPageUptodate(page);
+ unlock_page(page);
+ goto out;
+ }
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
mutex_lock(&shmem_swaplist_mutex);
/*
* We needed to drop mutex to make that restrictive page
- * allocation; but the inode might already be freed by now,
- * and we cannot refer to inode or mapping or info to check.
- * However, we do hold page lock on the PageSwapCache page,
- * so can check if that still has our reference remaining.
+ * allocation, but the inode might have been freed while we
+ * dropped it: although a racing shmem_evict_inode() cannot
+ * complete without emptying the radix_tree, our page lock
+ * on this swapcache page is not enough to prevent that -
+ * free_swap_and_cache() of our swap entry will only
+ * trylock_page(), removing swap from radix_tree whatever.
+ *
+ * We must not proceed to shmem_add_to_page_cache() if the
+ * inode has been freed, but of course we cannot rely on
+ * inode or mapping or info to check that. However, we can
+ * safely check if our swap entry is still in use (and here
+ * it can't have got reused for another page): if it's still
+ * in use, then the inode cannot have been freed yet, and we
+ * can safely proceed (if it's no longer in use, that tells
+ * nothing about the inode, but we don't need to unuse swap).
*/
if (!page_swapcount(*pagep))
error = -ENOENT;
/*
* There's a faint possibility that swap page was replaced before
- * caller locked it: it will come back later with the right page.
+ * caller locked it: caller will come back later with the right page.
*/
- if (unlikely(!PageSwapCache(page)))
+ if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val))
goto out;
/*
newpage = shmem_alloc_page(gfp, info, index);
if (!newpage)
return -ENOMEM;
- VM_BUG_ON(shmem_should_replace_page(newpage, gfp));
- *pagep = newpage;
page_cache_get(newpage);
copy_highpage(newpage, oldpage);
+ flush_dcache_page(newpage);
- VM_BUG_ON(!PageLocked(oldpage));
__set_page_locked(newpage);
- VM_BUG_ON(!PageUptodate(oldpage));
SetPageUptodate(newpage);
- VM_BUG_ON(!PageSwapBacked(oldpage));
SetPageSwapBacked(newpage);
- VM_BUG_ON(!swap_index);
set_page_private(newpage, swap_index);
- VM_BUG_ON(!PageSwapCache(oldpage));
SetPageSwapCache(newpage);
/*
spin_lock_irq(&swap_mapping->tree_lock);
error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
newpage);
- __inc_zone_page_state(newpage, NR_FILE_PAGES);
- __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ if (!error) {
+ __inc_zone_page_state(newpage, NR_FILE_PAGES);
+ __dec_zone_page_state(oldpage, NR_FILE_PAGES);
+ }
spin_unlock_irq(&swap_mapping->tree_lock);
- BUG_ON(error);
- mem_cgroup_replace_page_cache(oldpage, newpage);
- lru_cache_add_anon(newpage);
+ if (unlikely(error)) {
+ /*
+ * Is this possible? I think not, now that our callers check
+ * both PageSwapCache and page_private after getting page lock;
+ * but be defensive. Reverse old to newpage for clear and free.
+ */
+ oldpage = newpage;
+ } else {
+ mem_cgroup_replace_page_cache(oldpage, newpage);
+ lru_cache_add_anon(newpage);
+ *pagep = newpage;
+ }
ClearPageSwapCache(oldpage);
set_page_private(oldpage, 0);
unlock_page(oldpage);
page_cache_release(oldpage);
page_cache_release(oldpage);
- return 0;
+ return error;
}
/*
/* We have to do this with page locked to prevent races */
lock_page(page);
- if (!PageSwapCache(page) || page->mapping) {
+ if (!PageSwapCache(page) || page_private(page) != swap.val ||
+ page->mapping) {
error = -EEXIST; /* try again */
goto failed;
}
#include <linux/memcontrol.h>
#include <linux/poll.h>
#include <linux/oom.h>
+#include <linux/frontswap.h>
+#include <linux/swapfile.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
static void free_swap_count_continuations(struct swap_info_struct *);
static sector_t map_swap_entry(swp_entry_t, struct block_device**);
-static DEFINE_SPINLOCK(swap_lock);
+DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
long nr_swap_pages;
long total_swap_pages;
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
-static struct swap_list_t swap_list = {-1, -1};
+struct swap_list_t swap_list = {-1, -1};
-static struct swap_info_struct *swap_info[MAX_SWAPFILES];
+struct swap_info_struct *swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
swap_list.next = p->type;
nr_swap_pages++;
p->inuse_pages--;
+ frontswap_invalidate_page(p->type, offset);
if ((p->flags & SWP_BLKDEV) &&
disk->fops->swap_slot_free_notify)
disk->fops->swap_slot_free_notify(p->bdev, offset);
}
/*
- * Scan swap_map from current position to next entry still in use.
+ * Scan swap_map (or frontswap_map if frontswap parameter is true)
+ * from current position to next entry still in use.
* Recycle to start on reaching the end, returning 0 when empty.
*/
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
- unsigned int prev)
+ unsigned int prev, bool frontswap)
{
unsigned int max = si->max;
unsigned int i = prev;
prev = 0;
i = 1;
}
+ if (frontswap) {
+ if (frontswap_test(si, i))
+ break;
+ else
+ continue;
+ }
count = si->swap_map[i];
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
* We completely avoid races by reading each swap page in advance,
* and then search for the process using it. All the necessary
* page table adjustments can then be made atomically.
+ *
+ * if the boolean frontswap is true, only unuse pages_to_unuse pages;
+ * pages_to_unuse==0 means all pages; ignored if frontswap is false
*/
-static int try_to_unuse(unsigned int type)
+int try_to_unuse(unsigned int type, bool frontswap,
+ unsigned long pages_to_unuse)
{
struct swap_info_struct *si = swap_info[type];
struct mm_struct *start_mm;
* one pass through swap_map is enough, but not necessarily:
* there are races when an instance of an entry might be missed.
*/
- while ((i = find_next_to_unuse(si, i)) != 0) {
+ while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
* interactive performance.
*/
cond_resched();
+ if (frontswap && pages_to_unuse > 0) {
+ if (!--pages_to_unuse)
+ break;
+ }
}
mmput(start_mm);
}
static void enable_swap_info(struct swap_info_struct *p, int prio,
- unsigned char *swap_map)
+ unsigned char *swap_map,
+ unsigned long *frontswap_map)
{
int i, prev;
else
p->prio = --least_priority;
p->swap_map = swap_map;
+ frontswap_map_set(p, frontswap_map);
p->flags |= SWP_WRITEOK;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
swap_list.head = swap_list.next = p->type;
else
swap_info[prev]->next = p->type;
+ frontswap_init(p->type);
spin_unlock(&swap_lock);
}
spin_unlock(&swap_lock);
oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
- err = try_to_unuse(type);
+ err = try_to_unuse(type, false, 0); /* force all pages to be unused */
compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
if (err) {
* sys_swapoff for this swap_info_struct at this point.
*/
/* re-insert swap space back into swap_list */
- enable_swap_info(p, p->prio, p->swap_map);
+ enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
goto out_dput;
}
swap_map = p->swap_map;
p->swap_map = NULL;
p->flags = 0;
+ frontswap_invalidate_area(type);
spin_unlock(&swap_lock);
mutex_unlock(&swapon_mutex);
vfree(swap_map);
+ vfree(frontswap_map_get(p));
/* Destroy swap account informatin */
swap_cgroup_swapoff(type);
sector_t span;
unsigned long maxpages;
unsigned char *swap_map = NULL;
+ unsigned long *frontswap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
error = nr_extents;
goto bad_swap;
}
+ /* frontswap enabled? set up bit-per-page map for frontswap */
+ if (frontswap_enabled)
+ frontswap_map = vzalloc(maxpages / sizeof(long));
if (p->bdev) {
if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
if (swap_flags & SWAP_FLAG_PREFER)
prio =
(swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
- enable_swap_info(p, prio, swap_map);
+ enable_swap_info(p, prio, swap_map, frontswap_map);
printk(KERN_INFO "Adding %uk swap on %s. "
- "Priority:%d extents:%d across:%lluk %s%s\n",
+ "Priority:%d extents:%d across:%lluk %s%s%s\n",
p->pages<<(PAGE_SHIFT-10), name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
- (p->flags & SWP_DISCARDABLE) ? "D" : "");
+ (p->flags & SWP_DISCARDABLE) ? "D" : "",
+ (frontswap_map) ? "FS" : "");
mutex_unlock(&swapon_mutex);
atomic_inc(&proc_poll_event);
d = debugfs_create_file("log", S_IFREG | S_IRUSR,
bat_priv->debug_dir, bat_priv, &log_fops);
- if (d)
+ if (!d)
goto err;
return 0;
err:
- return 1;
+ return -ENOMEM;
}
static void debug_log_cleanup(struct bat_priv *bat_priv)
if (!bat_priv->debug_dir)
goto out;
- bat_socket_setup(bat_priv);
- debug_log_setup(bat_priv);
+ if (bat_socket_setup(bat_priv) < 0)
+ goto rem_attr;
+
+ if (debug_log_setup(bat_priv) < 0)
+ goto rem_attr;
for (bat_debug = mesh_debuginfos; *bat_debug; ++bat_debug) {
file = debugfs_create_file(((*bat_debug)->attr).name,
const uint8_t *neigh_addr,
struct orig_node *orig_node,
struct orig_node *orig_neigh,
- uint32_t seqno)
+ __be32 seqno)
{
struct neigh_node *neigh_node;
- neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, seqno);
+ neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr,
+ ntohl(seqno));
if (!neigh_node)
goto out;
{
struct batman_ogm_packet *batman_ogm_packet;
uint32_t random_seqno;
- int res = -1;
+ int res = -ENOMEM;
/* randomize initial seqno to avoid collision */
get_random_bytes(&random_seqno, sizeof(random_seqno));
/* create clone because function is called more than once */
skb = skb_clone(forw_packet->skb, GFP_ATOMIC);
- if (skb)
+ if (skb) {
+ batadv_inc_counter(bat_priv, BAT_CNT_MGMT_TX);
+ batadv_add_counter(bat_priv, BAT_CNT_MGMT_TX_BYTES,
+ skb->len + ETH_HLEN);
send_skb_packet(skb, hard_iface, broadcast_addr);
+ }
}
/* send a batman ogm packet */
"Forwarding packet: tq: %i, ttl: %i\n",
batman_ogm_packet->tq, batman_ogm_packet->header.ttl);
- batman_ogm_packet->seqno = htonl(batman_ogm_packet->seqno);
- batman_ogm_packet->tt_crc = htons(batman_ogm_packet->tt_crc);
-
/* switch of primaries first hop flag when forwarding */
batman_ogm_packet->flags &= ~PRIMARIES_FIRST_HOP;
if (is_single_hop_neigh)
if_incoming, 0, bat_iv_ogm_fwd_send_time());
}
-static void bat_iv_ogm_schedule(struct hard_iface *hard_iface,
- int tt_num_changes)
+static void bat_iv_ogm_schedule(struct hard_iface *hard_iface)
{
struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
struct batman_ogm_packet *batman_ogm_packet;
struct hard_iface *primary_if;
- int vis_server;
+ int vis_server, tt_num_changes = 0;
vis_server = atomic_read(&bat_priv->vis_mode);
primary_if = primary_if_get_selected(bat_priv);
+ if (hard_iface == primary_if)
+ tt_num_changes = batadv_tt_append_diff(bat_priv,
+ &hard_iface->packet_buff,
+ &hard_iface->packet_len,
+ BATMAN_OGM_HLEN);
+
batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff;
/* change sequence number to network order */
batman_ogm_packet->seqno =
htonl((uint32_t)atomic_read(&hard_iface->seqno));
+ atomic_inc(&hard_iface->seqno);
batman_ogm_packet->ttvn = atomic_read(&bat_priv->ttvn);
- batman_ogm_packet->tt_crc = htons((uint16_t)
- atomic_read(&bat_priv->tt_crc));
+ batman_ogm_packet->tt_crc = htons(bat_priv->tt_crc);
if (tt_num_changes >= 0)
batman_ogm_packet->tt_num_changes = tt_num_changes;
else
batman_ogm_packet->gw_flags = NO_FLAGS;
- atomic_inc(&hard_iface->seqno);
-
slide_own_bcast_window(hard_iface);
bat_iv_ogm_queue_add(bat_priv, hard_iface->packet_buff,
hard_iface->packet_len, hard_iface, 1,
tt_update_orig(bat_priv, orig_node, tt_buff,
batman_ogm_packet->tt_num_changes,
batman_ogm_packet->ttvn,
- batman_ogm_packet->tt_crc);
+ ntohs(batman_ogm_packet->tt_crc));
if (orig_node->gw_flags != batman_ogm_packet->gw_flags)
gw_node_update(bat_priv, orig_node,
int32_t seq_diff;
int need_update = 0;
int set_mark, ret = -1;
+ uint32_t seqno = ntohl(batman_ogm_packet->seqno);
orig_node = get_orig_node(bat_priv, batman_ogm_packet->orig);
if (!orig_node)
return 0;
spin_lock_bh(&orig_node->ogm_cnt_lock);
- seq_diff = batman_ogm_packet->seqno - orig_node->last_real_seqno;
+ seq_diff = seqno - orig_node->last_real_seqno;
/* signalize caller that the packet is to be dropped. */
if (!hlist_empty(&orig_node->neigh_list) &&
is_duplicate |= bat_test_bit(tmp_neigh_node->real_bits,
orig_node->last_real_seqno,
- batman_ogm_packet->seqno);
+ seqno);
if (compare_eth(tmp_neigh_node->addr, ethhdr->h_source) &&
(tmp_neigh_node->if_incoming == if_incoming))
if (need_update) {
bat_dbg(DBG_BATMAN, bat_priv,
"updating last_seqno: old %u, new %u\n",
- orig_node->last_real_seqno, batman_ogm_packet->seqno);
- orig_node->last_real_seqno = batman_ogm_packet->seqno;
+ orig_node->last_real_seqno, seqno);
+ orig_node->last_real_seqno = seqno;
}
ret = is_duplicate;
"Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n",
ethhdr->h_source, if_incoming->net_dev->name,
if_incoming->net_dev->dev_addr, batman_ogm_packet->orig,
- batman_ogm_packet->prev_sender, batman_ogm_packet->seqno,
- batman_ogm_packet->ttvn, batman_ogm_packet->tt_crc,
+ batman_ogm_packet->prev_sender, ntohl(batman_ogm_packet->seqno),
+ batman_ogm_packet->ttvn, ntohs(batman_ogm_packet->tt_crc),
batman_ogm_packet->tt_num_changes, batman_ogm_packet->tq,
batman_ogm_packet->header.ttl,
batman_ogm_packet->header.version, has_directlink_flag);
word = &(orig_neigh_node->bcast_own[offset]);
bat_set_bit(word,
if_incoming_seqno -
- batman_ogm_packet->seqno - 2);
+ ntohl(batman_ogm_packet->seqno) - 2);
orig_neigh_node->bcast_own_sum[if_incoming->if_num] =
bitmap_weight(word, TQ_LOCAL_WINDOW_SIZE);
spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock);
* seqno and similar ttl as the non-duplicate */
if (is_bidirectional &&
(!is_duplicate ||
- ((orig_node->last_real_seqno == batman_ogm_packet->seqno) &&
+ ((orig_node->last_real_seqno == ntohl(batman_ogm_packet->seqno)) &&
(orig_node->last_ttl - 3 <= batman_ogm_packet->header.ttl))))
bat_iv_ogm_orig_update(bat_priv, orig_node, ethhdr,
batman_ogm_packet, if_incoming,
if (bat_priv->bat_algo_ops->bat_ogm_emit != bat_iv_ogm_emit)
return NET_RX_DROP;
+ batadv_inc_counter(bat_priv, BAT_CNT_MGMT_RX);
+ batadv_add_counter(bat_priv, BAT_CNT_MGMT_RX_BYTES,
+ skb->len + ETH_HLEN);
+
packet_len = skb_headlen(skb);
ethhdr = (struct ethhdr *)skb_mac_header(skb);
packet_buff = skb->data;
/* unpack the aggregated packets and process them one by one */
do {
- /* network to host order for our 32bit seqno and the
- orig_interval */
- batman_ogm_packet->seqno = ntohl(batman_ogm_packet->seqno);
- batman_ogm_packet->tt_crc = ntohs(batman_ogm_packet->tt_crc);
-
tt_buff = packet_buff + buff_pos + BATMAN_OGM_HLEN;
bat_iv_ogm_process(ethhdr, batman_ogm_packet,
}
static struct bat_algo_ops batman_iv __read_mostly = {
- .name = "BATMAN IV",
+ .name = "BATMAN_IV",
.bat_iface_enable = bat_iv_ogm_iface_enable,
.bat_iface_disable = bat_iv_ogm_iface_disable,
.bat_iface_update_mac = bat_iv_ogm_iface_update_mac,
static BAT_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, show_gw_bwidth,
store_gw_bwidth);
#ifdef CONFIG_BATMAN_ADV_DEBUG
-BAT_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, 15, NULL);
+BAT_ATTR_SIF_UINT(log_level, S_IRUGO | S_IWUSR, 0, DBG_ALL, NULL);
#endif
static struct bat_attribute *mesh_attrs[] = {
int throw_uevent(struct bat_priv *bat_priv, enum uev_type type,
enum uev_action action, const char *data)
{
- int ret = -1;
+ int ret = -ENOMEM;
struct hard_iface *primary_if = NULL;
struct kobject *bat_kobj;
char *uevent_env[4] = { NULL, NULL, NULL, NULL };
struct net_device *soft_iface;
uint8_t *hw_src;
struct bla_claim_dst local_claim_dest;
- uint32_t zeroip = 0;
+ __be32 zeroip = 0;
primary_if = primary_if_get_selected(bat_priv);
if (!primary_if)
struct backbone_gw *backbone_gw)
{
uint8_t mac[ETH_ALEN];
- uint16_t crc;
+ __be16 crc;
memcpy(mac, announce_mac, 4);
crc = htons(backbone_gw->crc);
- memcpy(&mac[4], (uint8_t *)&crc, 2);
+ memcpy(&mac[4], &crc, 2);
bla_send_claim(bat_priv, mac, backbone_gw->vid, CLAIM_TYPE_ANNOUNCE);
/* handle as ANNOUNCE frame */
backbone_gw->lasttime = jiffies;
- crc = ntohs(*((uint16_t *)(&an_addr[4])));
+ crc = ntohs(*((__be16 *)(&an_addr[4])));
bat_dbg(DBG_BLA, bat_priv,
"handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %04x\n",
bla_start_timer(bat_priv);
}
+/* The hash for claim and backbone hash receive the same key because they
+ * are getting initialized by hash_new with the same key. Reinitializing
+ * them with to different keys to allow nested locking without generating
+ * lockdep warnings
+ */
+static struct lock_class_key claim_hash_lock_class_key;
+static struct lock_class_key backbone_hash_lock_class_key;
+
/* initialize all bla structures */
int bla_init(struct bat_priv *bat_priv)
{
bat_priv->bcast_duplist_curr = 0;
if (bat_priv->claim_hash)
- return 1;
+ return 0;
bat_priv->claim_hash = hash_new(128);
bat_priv->backbone_hash = hash_new(32);
if (!bat_priv->claim_hash || !bat_priv->backbone_hash)
- return -1;
+ return -ENOMEM;
+
+ batadv_hash_set_lock_class(bat_priv->claim_hash,
+ &claim_hash_lock_class_key);
+ batadv_hash_set_lock_class(bat_priv->backbone_hash,
+ &backbone_hash_lock_class_key);
bat_dbg(DBG_BLA, bat_priv, "bla hashes initialized\n");
bla_start_timer(bat_priv);
- return 1;
+ return 0;
}
/**
**/
gw_bandwidth_to_kbit((uint8_t)gw_bandwidth_tmp, &down, &up);
+ if (atomic_read(&bat_priv->gw_bandwidth) == gw_bandwidth_tmp)
+ return count;
+
gw_deselect(bat_priv);
bat_info(net_dev,
"Changing gateway bandwidth from: '%i' to: '%ld' (propagating: %d%s/%d%s)\n",
bat_priv = netdev_priv(hard_iface->soft_iface);
ret = bat_priv->bat_algo_ops->bat_iface_enable(hard_iface);
- if (ret < 0) {
- ret = -ENOMEM;
+ if (ret < 0)
goto err_dev;
- }
hard_iface->if_num = bat_priv->num_ifaces;
bat_priv->num_ifaces++;
kfree(hash);
return NULL;
}
+
+void batadv_hash_set_lock_class(struct hashtable_t *hash,
+ struct lock_class_key *key)
+{
+ uint32_t i;
+
+ for (i = 0; i < hash->size; i++)
+ lockdep_set_class(&hash->list_locks[i], key);
+}
/* allocates and clears the hash */
struct hashtable_t *hash_new(uint32_t size);
+/* set class key for all locks */
+void batadv_hash_set_lock_class(struct hashtable_t *hash,
+ struct lock_class_key *key);
+
/* free only the hashtable and the hash itself. */
void hash_destroy(struct hashtable_t *hash);
head = &hash->table[index];
list_lock = &hash->list_locks[index];
- rcu_read_lock();
- __hlist_for_each_rcu(node, head) {
+ spin_lock_bh(list_lock);
+
+ hlist_for_each(node, head) {
if (!compare(node, data))
continue;
ret = 1;
- goto err_unlock;
+ goto unlock;
}
- rcu_read_unlock();
/* no duplicate found in list, add new element */
- spin_lock_bh(list_lock);
hlist_add_head_rcu(data_node, head);
- spin_unlock_bh(list_lock);
ret = 0;
- goto out;
-err_unlock:
- rcu_read_unlock();
+unlock:
+ spin_unlock_bh(list_lock);
out:
return ret;
}
d = debugfs_create_file(ICMP_SOCKET, S_IFREG | S_IWUSR | S_IRUSR,
bat_priv->debug_dir, bat_priv, &fops);
- if (d)
+ if (!d)
goto err;
return 0;
err:
- return 1;
+ return -ENOMEM;
}
static void bat_socket_add_packet(struct socket_client *socket_client,
* list traversals just rcu-locked */
struct list_head hardif_list;
static int (*recv_packet_handler[256])(struct sk_buff *, struct hard_iface *);
-char bat_routing_algo[20] = "BATMAN IV";
+char bat_routing_algo[20] = "BATMAN_IV";
static struct hlist_head bat_algo_list;
unsigned char broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
int mesh_init(struct net_device *soft_iface)
{
struct bat_priv *bat_priv = netdev_priv(soft_iface);
+ int ret;
spin_lock_init(&bat_priv->forw_bat_list_lock);
spin_lock_init(&bat_priv->forw_bcast_list_lock);
INIT_LIST_HEAD(&bat_priv->tt_req_list);
INIT_LIST_HEAD(&bat_priv->tt_roam_list);
- if (originator_init(bat_priv) < 1)
+ ret = originator_init(bat_priv);
+ if (ret < 0)
goto err;
- if (tt_init(bat_priv) < 1)
+ ret = tt_init(bat_priv);
+ if (ret < 0)
goto err;
tt_local_add(soft_iface, soft_iface->dev_addr, NULL_IFINDEX);
- if (vis_init(bat_priv) < 1)
+ ret = vis_init(bat_priv);
+ if (ret < 0)
goto err;
- if (bla_init(bat_priv) < 1)
+ ret = bla_init(bat_priv);
+ if (ret < 0)
goto err;
atomic_set(&bat_priv->gw_reselect, 0);
atomic_set(&bat_priv->mesh_state, MESH_ACTIVE);
- goto end;
+
+ return 0;
err:
mesh_free(soft_iface);
- return -1;
-
-end:
- return 0;
+ return ret;
}
void mesh_free(struct net_device *soft_iface)
bla_free(bat_priv);
+ free_percpu(bat_priv->bat_counters);
+
atomic_set(&bat_priv->mesh_state, MESH_INACTIVE);
}
int bat_algo_register(struct bat_algo_ops *bat_algo_ops)
{
struct bat_algo_ops *bat_algo_ops_tmp;
- int ret = -1;
+ int ret;
bat_algo_ops_tmp = bat_algo_get(bat_algo_ops->name);
if (bat_algo_ops_tmp) {
pr_info("Trying to register already registered routing algorithm: %s\n",
bat_algo_ops->name);
+ ret = -EEXIST;
goto out;
}
!bat_algo_ops->bat_ogm_emit) {
pr_info("Routing algo '%s' does not implement required ops\n",
bat_algo_ops->name);
+ ret = -EINVAL;
goto out;
}
int bat_algo_select(struct bat_priv *bat_priv, char *name)
{
struct bat_algo_ops *bat_algo_ops;
- int ret = -1;
+ int ret = -EINVAL;
bat_algo_ops = bat_algo_get(name);
if (!bat_algo_ops)
static int param_set_ra(const char *val, const struct kernel_param *kp)
{
struct bat_algo_ops *bat_algo_ops;
+ char *algo_name = (char *)val;
+ size_t name_len = strlen(algo_name);
+
+ if (algo_name[name_len - 1] == '\n')
+ algo_name[name_len - 1] = '\0';
- bat_algo_ops = bat_algo_get((char *)val);
+ bat_algo_ops = bat_algo_get(algo_name);
if (!bat_algo_ops) {
- pr_err("Routing algorithm '%s' is not supported\n", val);
+ pr_err("Routing algorithm '%s' is not supported\n", algo_name);
return -EINVAL;
}
- return param_set_copystring(val, kp);
+ return param_set_copystring(algo_name, kp);
}
static const struct kernel_param_ops param_ops_ra = {
#define DRIVER_DEVICE "batman-adv"
#ifndef SOURCE_VERSION
-#define SOURCE_VERSION "2012.2.0"
+#define SOURCE_VERSION "2012.3.0"
#endif
/* B.A.T.M.A.N. parameters */
#include <linux/kthread.h> /* kernel threads */
#include <linux/pkt_sched.h> /* schedule types */
#include <linux/workqueue.h> /* workqueue */
+#include <linux/percpu.h>
#include <linux/slab.h>
#include <net/sock.h> /* struct sock */
#include <linux/jiffies.h>
_dummy > smallest_signed_int(_dummy); })
#define seq_after(x, y) seq_before(y, x)
+/* Stop preemption on local cpu while incrementing the counter */
+static inline void batadv_add_counter(struct bat_priv *bat_priv, size_t idx,
+ size_t count)
+{
+ int cpu = get_cpu();
+ per_cpu_ptr(bat_priv->bat_counters, cpu)[idx] += count;
+ put_cpu();
+}
+
+#define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1)
+
+/* Sum and return the cpu-local counters for index 'idx' */
+static inline uint64_t batadv_sum_counter(struct bat_priv *bat_priv, size_t idx)
+{
+ uint64_t *counters;
+ int cpu;
+ int sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ counters = per_cpu_ptr(bat_priv->bat_counters, cpu);
+ sum += counters[idx];
+ }
+
+ return sum;
+}
+
#endif /* _NET_BATMAN_ADV_MAIN_H_ */
int originator_init(struct bat_priv *bat_priv)
{
if (bat_priv->orig_hash)
- return 1;
+ return 0;
bat_priv->orig_hash = hash_new(1024);
goto err;
start_purge_timer(bat_priv);
- return 1;
+ return 0;
err:
- return 0;
+ return -ENOMEM;
}
void neigh_node_free_ref(struct neigh_node *neigh_node)
data_ptr = kmalloc(max_if_num * sizeof(unsigned long) * NUM_WORDS,
GFP_ATOMIC);
if (!data_ptr)
- return -1;
+ return -ENOMEM;
memcpy(data_ptr, orig_node->bcast_own,
(max_if_num - 1) * sizeof(unsigned long) * NUM_WORDS);
data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC);
if (!data_ptr)
- return -1;
+ return -ENOMEM;
memcpy(data_ptr, orig_node->bcast_own_sum,
(max_if_num - 1) * sizeof(uint8_t));
ret = orig_node_add_if(orig_node, max_if_num);
spin_unlock_bh(&orig_node->ogm_cnt_lock);
- if (ret == -1)
+ if (ret == -ENOMEM)
goto err;
}
rcu_read_unlock();
chunk_size = sizeof(unsigned long) * NUM_WORDS;
data_ptr = kmalloc(max_if_num * chunk_size, GFP_ATOMIC);
if (!data_ptr)
- return -1;
+ return -ENOMEM;
/* copy first part */
memcpy(data_ptr, orig_node->bcast_own, del_if_num * chunk_size);
data_ptr = kmalloc(max_if_num * sizeof(uint8_t), GFP_ATOMIC);
if (!data_ptr)
- return -1;
+ return -ENOMEM;
memcpy(data_ptr, orig_node->bcast_own_sum,
del_if_num * sizeof(uint8_t));
hard_iface->if_num);
spin_unlock_bh(&orig_node->ogm_cnt_lock);
- if (ret == -1)
+ if (ret == -ENOMEM)
goto err;
}
rcu_read_unlock();
struct bla_claim_dst {
uint8_t magic[3]; /* FF:43:05 */
uint8_t type; /* bla_claimframe */
- uint16_t group; /* group id */
+ __be16 group; /* group id */
} __packed;
struct batman_header {
struct batman_ogm_packet {
struct batman_header header;
uint8_t flags; /* 0x40: DIRECTLINK flag, 0x20 VIS_SERVER flag... */
- uint32_t seqno;
+ __be32 seqno;
uint8_t orig[ETH_ALEN];
uint8_t prev_sender[ETH_ALEN];
uint8_t gw_flags; /* flags related to gateway class */
uint8_t tq;
uint8_t tt_num_changes;
uint8_t ttvn; /* translation table version number */
- uint16_t tt_crc;
+ __be16 tt_crc;
} __packed;
#define BATMAN_OGM_HLEN sizeof(struct batman_ogm_packet)
uint8_t msg_type; /* see ICMP message types above */
uint8_t dst[ETH_ALEN];
uint8_t orig[ETH_ALEN];
- uint16_t seqno;
+ __be16 seqno;
uint8_t uid;
uint8_t reserved;
} __packed;
uint8_t msg_type; /* see ICMP message types above */
uint8_t dst[ETH_ALEN];
uint8_t orig[ETH_ALEN];
- uint16_t seqno;
+ __be16 seqno;
uint8_t uid;
uint8_t rr_cur;
uint8_t rr[BAT_RR_LEN][ETH_ALEN];
uint8_t flags;
uint8_t align;
uint8_t orig[ETH_ALEN];
- uint16_t seqno;
+ __be16 seqno;
} __packed;
struct bcast_packet {
struct batman_header header;
uint8_t reserved;
- uint32_t seqno;
+ __be32 seqno;
uint8_t orig[ETH_ALEN];
} __packed;
struct vis_packet {
struct batman_header header;
uint8_t vis_type; /* which type of vis-participant sent this? */
- uint32_t seqno; /* sequence number */
+ __be32 seqno; /* sequence number */
uint8_t entries; /* number of entries behind this struct */
uint8_t reserved;
uint8_t vis_orig[ETH_ALEN]; /* originator reporting its neighbors */
* if TT_REQUEST: crc associated with the
* ttvn
* if TT_RESPONSE: table_size */
- uint16_t tt_data;
+ __be16 tt_data;
} __packed;
struct roam_adv_packet {
{
struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface);
struct tt_query_packet *tt_query;
- uint16_t tt_len;
+ uint16_t tt_size;
struct ethhdr *ethhdr;
/* drop packet if it has not necessary minimum size */
tt_query = (struct tt_query_packet *)skb->data;
- tt_query->tt_data = ntohs(tt_query->tt_data);
-
switch (tt_query->flags & TT_QUERY_TYPE_MASK) {
case TT_REQUEST:
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_REQUEST_RX);
+
/* If we cannot provide an answer the tt_request is
* forwarded */
if (!send_tt_response(bat_priv, tt_query)) {
"Routing TT_REQUEST to %pM [%c]\n",
tt_query->dst,
(tt_query->flags & TT_FULL_TABLE ? 'F' : '.'));
- tt_query->tt_data = htons(tt_query->tt_data);
return route_unicast_packet(skb, recv_if);
}
break;
case TT_RESPONSE:
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_RESPONSE_RX);
+
if (is_my_mac(tt_query->dst)) {
/* packet needs to be linearized to access the TT
* changes */
if (skb_linearize(skb) < 0)
goto out;
+ /* skb_linearize() possibly changed skb->data */
+ tt_query = (struct tt_query_packet *)skb->data;
- tt_len = tt_query->tt_data * sizeof(struct tt_change);
+ tt_size = tt_len(ntohs(tt_query->tt_data));
/* Ensure we have all the claimed data */
if (unlikely(skb_headlen(skb) <
- sizeof(struct tt_query_packet) + tt_len))
+ sizeof(struct tt_query_packet) + tt_size))
goto out;
handle_tt_response(bat_priv, tt_query);
"Routing TT_RESPONSE to %pM [%c]\n",
tt_query->dst,
(tt_query->flags & TT_FULL_TABLE ? 'F' : '.'));
- tt_query->tt_data = htons(tt_query->tt_data);
return route_unicast_packet(skb, recv_if);
}
break;
if (is_broadcast_ether_addr(ethhdr->h_source))
goto out;
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_ROAM_ADV_RX);
+
roam_adv_packet = (struct roam_adv_packet *)skb->data;
if (!is_my_mac(roam_adv_packet->dst))
/* decrement ttl */
unicast_packet->header.ttl--;
+ /* Update stats counter */
+ batadv_inc_counter(bat_priv, BAT_CNT_FORWARD);
+ batadv_add_counter(bat_priv, BAT_CNT_FORWARD_BYTES,
+ skb->len + ETH_HLEN);
+
/* route it */
send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
ret = NET_RX_SUCCESS;
return NET_XMIT_DROP;
}
-static void realloc_packet_buffer(struct hard_iface *hard_iface,
- int new_len)
-{
- unsigned char *new_buff;
-
- new_buff = kmalloc(new_len, GFP_ATOMIC);
-
- /* keep old buffer if kmalloc should fail */
- if (new_buff) {
- memcpy(new_buff, hard_iface->packet_buff,
- BATMAN_OGM_HLEN);
-
- kfree(hard_iface->packet_buff);
- hard_iface->packet_buff = new_buff;
- hard_iface->packet_len = new_len;
- }
-}
-
-/* when calling this function (hard_iface == primary_if) has to be true */
-static int prepare_packet_buffer(struct bat_priv *bat_priv,
- struct hard_iface *hard_iface)
-{
- int new_len;
-
- new_len = BATMAN_OGM_HLEN +
- tt_len((uint8_t)atomic_read(&bat_priv->tt_local_changes));
-
- /* if we have too many changes for one packet don't send any
- * and wait for the tt table request which will be fragmented */
- if (new_len > hard_iface->soft_iface->mtu)
- new_len = BATMAN_OGM_HLEN;
-
- realloc_packet_buffer(hard_iface, new_len);
-
- atomic_set(&bat_priv->tt_crc, tt_local_crc(bat_priv));
-
- /* reset the sending counter */
- atomic_set(&bat_priv->tt_ogm_append_cnt, TT_OGM_APPEND_MAX);
-
- return tt_changes_fill_buffer(bat_priv,
- hard_iface->packet_buff + BATMAN_OGM_HLEN,
- hard_iface->packet_len - BATMAN_OGM_HLEN);
-}
-
-static int reset_packet_buffer(struct bat_priv *bat_priv,
- struct hard_iface *hard_iface)
-{
- realloc_packet_buffer(hard_iface, BATMAN_OGM_HLEN);
- return 0;
-}
-
void schedule_bat_ogm(struct hard_iface *hard_iface)
{
struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
- struct hard_iface *primary_if;
- int tt_num_changes = -1;
if ((hard_iface->if_status == IF_NOT_IN_USE) ||
(hard_iface->if_status == IF_TO_BE_REMOVED))
if (hard_iface->if_status == IF_TO_BE_ACTIVATED)
hard_iface->if_status = IF_ACTIVE;
- primary_if = primary_if_get_selected(bat_priv);
-
- if (hard_iface == primary_if) {
- /* if at least one change happened */
- if (atomic_read(&bat_priv->tt_local_changes) > 0) {
- tt_commit_changes(bat_priv);
- tt_num_changes = prepare_packet_buffer(bat_priv,
- hard_iface);
- }
-
- /* if the changes have been sent often enough */
- if (!atomic_dec_not_zero(&bat_priv->tt_ogm_append_cnt))
- tt_num_changes = reset_packet_buffer(bat_priv,
- hard_iface);
- }
-
- if (primary_if)
- hardif_free_ref(primary_if);
-
- bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface, tt_num_changes);
+ bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface);
}
static void forw_packet_free(struct forw_packet *forw_packet)
static u32 bat_get_msglevel(struct net_device *dev);
static void bat_set_msglevel(struct net_device *dev, u32 value);
static u32 bat_get_link(struct net_device *dev);
+static void batadv_get_strings(struct net_device *dev, u32 stringset, u8 *data);
+static void batadv_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats, u64 *data);
+static int batadv_get_sset_count(struct net_device *dev, int stringset);
static const struct ethtool_ops bat_ethtool_ops = {
.get_settings = bat_get_settings,
.get_msglevel = bat_get_msglevel,
.set_msglevel = bat_set_msglevel,
.get_link = bat_get_link,
+ .get_strings = batadv_get_strings,
+ .get_ethtool_stats = batadv_get_ethtool_stats,
+ .get_sset_count = batadv_get_sset_count,
};
int my_skb_head_push(struct sk_buff *skb, unsigned int len)
bat_priv->primary_if = NULL;
bat_priv->num_ifaces = 0;
+ bat_priv->bat_counters = __alloc_percpu(sizeof(uint64_t) * BAT_CNT_NUM,
+ __alignof__(uint64_t));
+ if (!bat_priv->bat_counters)
+ goto unreg_soft_iface;
+
ret = bat_algo_select(bat_priv, bat_routing_algo);
if (ret < 0)
- goto unreg_soft_iface;
+ goto free_bat_counters;
ret = sysfs_add_meshif(soft_iface);
if (ret < 0)
- goto unreg_soft_iface;
+ goto free_bat_counters;
ret = debugfs_add_meshif(soft_iface);
if (ret < 0)
debugfs_del_meshif(soft_iface);
unreg_sysfs:
sysfs_del_meshif(soft_iface);
+free_bat_counters:
+ free_percpu(bat_priv->bat_counters);
unreg_soft_iface:
unregister_netdevice(soft_iface);
return NULL;
{
return 1;
}
+
+/* Inspired by drivers/net/ethernet/dlink/sundance.c:1702
+ * Declare each description string in struct.name[] to get fixed sized buffer
+ * and compile time checking for strings longer than ETH_GSTRING_LEN.
+ */
+static const struct {
+ const char name[ETH_GSTRING_LEN];
+} bat_counters_strings[] = {
+ { "forward" },
+ { "forward_bytes" },
+ { "mgmt_tx" },
+ { "mgmt_tx_bytes" },
+ { "mgmt_rx" },
+ { "mgmt_rx_bytes" },
+ { "tt_request_tx" },
+ { "tt_request_rx" },
+ { "tt_response_tx" },
+ { "tt_response_rx" },
+ { "tt_roam_adv_tx" },
+ { "tt_roam_adv_rx" },
+};
+
+static void batadv_get_strings(struct net_device *dev, uint32_t stringset,
+ uint8_t *data)
+{
+ if (stringset == ETH_SS_STATS)
+ memcpy(data, bat_counters_strings,
+ sizeof(bat_counters_strings));
+}
+
+static void batadv_get_ethtool_stats(struct net_device *dev,
+ struct ethtool_stats *stats,
+ uint64_t *data)
+{
+ struct bat_priv *bat_priv = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < BAT_CNT_NUM; i++)
+ data[i] = batadv_sum_counter(bat_priv, i);
+}
+
+static int batadv_get_sset_count(struct net_device *dev, int stringset)
+{
+ if (stringset == ETH_SS_STATS)
+ return BAT_CNT_NUM;
+
+ return -EOPNOTSUPP;
+}
static int tt_local_init(struct bat_priv *bat_priv)
{
if (bat_priv->tt_local_hash)
- return 1;
+ return 0;
bat_priv->tt_local_hash = hash_new(1024);
if (!bat_priv->tt_local_hash)
- return 0;
+ return -ENOMEM;
- return 1;
+ return 0;
}
void tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
tt_global_entry_free_ref(tt_global_entry);
}
-int tt_changes_fill_buffer(struct bat_priv *bat_priv,
- unsigned char *buff, int buff_len)
+static void tt_realloc_packet_buff(unsigned char **packet_buff,
+ int *packet_buff_len, int min_packet_len,
+ int new_packet_len)
+{
+ unsigned char *new_buff;
+
+ new_buff = kmalloc(new_packet_len, GFP_ATOMIC);
+
+ /* keep old buffer if kmalloc should fail */
+ if (new_buff) {
+ memcpy(new_buff, *packet_buff, min_packet_len);
+ kfree(*packet_buff);
+ *packet_buff = new_buff;
+ *packet_buff_len = new_packet_len;
+ }
+}
+
+static void tt_prepare_packet_buff(struct bat_priv *bat_priv,
+ unsigned char **packet_buff,
+ int *packet_buff_len, int min_packet_len)
+{
+ struct hard_iface *primary_if;
+ int req_len;
+
+ primary_if = primary_if_get_selected(bat_priv);
+
+ req_len = min_packet_len;
+ req_len += tt_len(atomic_read(&bat_priv->tt_local_changes));
+
+ /* if we have too many changes for one packet don't send any
+ * and wait for the tt table request which will be fragmented
+ */
+ if ((!primary_if) || (req_len > primary_if->soft_iface->mtu))
+ req_len = min_packet_len;
+
+ tt_realloc_packet_buff(packet_buff, packet_buff_len,
+ min_packet_len, req_len);
+
+ if (primary_if)
+ hardif_free_ref(primary_if);
+}
+
+static int tt_changes_fill_buff(struct bat_priv *bat_priv,
+ unsigned char **packet_buff,
+ int *packet_buff_len, int min_packet_len)
{
- int count = 0, tot_changes = 0;
struct tt_change_node *entry, *safe;
+ int count = 0, tot_changes = 0, new_len;
+ unsigned char *tt_buff;
+
+ tt_prepare_packet_buff(bat_priv, packet_buff,
+ packet_buff_len, min_packet_len);
- if (buff_len > 0)
- tot_changes = buff_len / tt_len(1);
+ new_len = *packet_buff_len - min_packet_len;
+ tt_buff = *packet_buff + min_packet_len;
+
+ if (new_len > 0)
+ tot_changes = new_len / tt_len(1);
spin_lock_bh(&bat_priv->tt_changes_list_lock);
atomic_set(&bat_priv->tt_local_changes, 0);
list_for_each_entry_safe(entry, safe, &bat_priv->tt_changes_list,
list) {
if (count < tot_changes) {
- memcpy(buff + tt_len(count),
+ memcpy(tt_buff + tt_len(count),
&entry->change, sizeof(struct tt_change));
count++;
}
kfree(bat_priv->tt_buff);
bat_priv->tt_buff_len = 0;
bat_priv->tt_buff = NULL;
- /* We check whether this new OGM has no changes due to size
- * problems */
- if (buff_len > 0) {
- /**
- * if kmalloc() fails we will reply with the full table
+ /* check whether this new OGM has no changes due to size problems */
+ if (new_len > 0) {
+ /* if kmalloc() fails we will reply with the full table
* instead of providing the diff
*/
- bat_priv->tt_buff = kmalloc(buff_len, GFP_ATOMIC);
+ bat_priv->tt_buff = kmalloc(new_len, GFP_ATOMIC);
if (bat_priv->tt_buff) {
- memcpy(bat_priv->tt_buff, buff, buff_len);
- bat_priv->tt_buff_len = buff_len;
+ memcpy(bat_priv->tt_buff, tt_buff, new_len);
+ bat_priv->tt_buff_len = new_len;
}
}
spin_unlock_bh(&bat_priv->tt_buff_lock);
- return tot_changes;
+ return count;
}
int tt_local_seq_print_text(struct seq_file *seq, void *offset)
static int tt_global_init(struct bat_priv *bat_priv)
{
if (bat_priv->tt_global_hash)
- return 1;
+ return 0;
bat_priv->tt_global_hash = hash_new(1024);
if (!bat_priv->tt_global_hash)
- return 0;
+ return -ENOMEM;
- return 1;
+ return 0;
}
static void tt_changes_list_free(struct bat_priv *bat_priv)
}
/* Calculates the checksum of the local table */
-uint16_t tt_local_crc(struct bat_priv *bat_priv)
+static uint16_t batadv_tt_local_crc(struct bat_priv *bat_priv)
{
uint16_t total = 0, total_one;
struct hashtable_t *hash = bat_priv->tt_local_hash;
dst_orig_node->orig, neigh_node->addr,
(full_table ? 'F' : '.'));
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_REQUEST_TX);
+
send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
ret = 0;
/* I don't have the requested data */
if (orig_ttvn != req_ttvn ||
- tt_request->tt_data != req_dst_orig_node->tt_crc)
+ tt_request->tt_data != htons(req_dst_orig_node->tt_crc))
goto out;
/* If the full table has been explicitly requested */
res_dst_orig_node->orig, neigh_node->addr,
req_dst_orig_node->orig, req_ttvn);
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_RESPONSE_TX);
+
send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
ret = true;
goto out;
orig_node->orig, neigh_node->addr,
(tt_response->flags & TT_FULL_TABLE ? 'F' : '.'));
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_RESPONSE_TX);
+
send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
ret = true;
goto out;
_tt_update_changes(bat_priv, orig_node,
(struct tt_change *)(tt_response + 1),
- tt_response->tt_data, tt_response->ttvn);
+ ntohs(tt_response->tt_data), tt_response->ttvn);
spin_lock_bh(&orig_node->tt_buff_lock);
kfree(orig_node->tt_buff);
bat_dbg(DBG_TT, bat_priv,
"Received TT_RESPONSE from %pM for ttvn %d t_size: %d [%c]\n",
- tt_response->src, tt_response->ttvn, tt_response->tt_data,
+ tt_response->src, tt_response->ttvn,
+ ntohs(tt_response->tt_data),
(tt_response->flags & TT_FULL_TABLE ? 'F' : '.'));
/* we should have never asked a backbone gw */
if (tt_response->flags & TT_FULL_TABLE)
tt_fill_gtable(bat_priv, tt_response);
else
- tt_update_changes(bat_priv, orig_node, tt_response->tt_data,
+ tt_update_changes(bat_priv, orig_node,
+ ntohs(tt_response->tt_data),
tt_response->ttvn,
(struct tt_change *)(tt_response + 1));
int tt_init(struct bat_priv *bat_priv)
{
- if (!tt_local_init(bat_priv))
- return 0;
+ int ret;
- if (!tt_global_init(bat_priv))
- return 0;
+ ret = tt_local_init(bat_priv);
+ if (ret < 0)
+ return ret;
+
+ ret = tt_global_init(bat_priv);
+ if (ret < 0)
+ return ret;
tt_start_timer(bat_priv);
"Sending ROAMING_ADV to %pM (client %pM) via %pM\n",
orig_node->orig, client, neigh_node->addr);
+ batadv_inc_counter(bat_priv, BAT_CNT_TT_ROAM_ADV_TX);
+
send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
ret = 0;
}
-void tt_commit_changes(struct bat_priv *bat_priv)
+static int tt_commit_changes(struct bat_priv *bat_priv,
+ unsigned char **packet_buff, int *packet_buff_len,
+ int packet_min_len)
{
- uint16_t changed_num = tt_set_flags(bat_priv->tt_local_hash,
- TT_CLIENT_NEW, false);
- /* all the reset entries have now to be effectively counted as local
- * entries */
+ uint16_t changed_num = 0;
+
+ if (atomic_read(&bat_priv->tt_local_changes) < 1)
+ return -ENOENT;
+
+ changed_num = tt_set_flags(bat_priv->tt_local_hash,
+ TT_CLIENT_NEW, false);
+
+ /* all reset entries have to be counted as local entries */
atomic_add(changed_num, &bat_priv->num_local_tt);
tt_local_purge_pending_clients(bat_priv);
+ bat_priv->tt_crc = batadv_tt_local_crc(bat_priv);
/* Increment the TTVN only once per OGM interval */
atomic_inc(&bat_priv->ttvn);
bat_dbg(DBG_TT, bat_priv, "Local changes committed, updating to ttvn %u\n",
(uint8_t)atomic_read(&bat_priv->ttvn));
bat_priv->tt_poss_change = false;
+
+ /* reset the sending counter */
+ atomic_set(&bat_priv->tt_ogm_append_cnt, TT_OGM_APPEND_MAX);
+
+ return tt_changes_fill_buff(bat_priv, packet_buff,
+ packet_buff_len, packet_min_len);
+}
+
+/* when calling this function (hard_iface == primary_if) has to be true */
+int batadv_tt_append_diff(struct bat_priv *bat_priv,
+ unsigned char **packet_buff, int *packet_buff_len,
+ int packet_min_len)
+{
+ int tt_num_changes;
+
+ /* if at least one change happened */
+ tt_num_changes = tt_commit_changes(bat_priv, packet_buff,
+ packet_buff_len, packet_min_len);
+
+ /* if the changes have been sent often enough */
+ if ((tt_num_changes < 0) &&
+ (!atomic_dec_not_zero(&bat_priv->tt_ogm_append_cnt))) {
+ tt_realloc_packet_buff(packet_buff, packet_buff_len,
+ packet_min_len, packet_min_len);
+ tt_num_changes = 0;
+ }
+
+ return tt_num_changes;
}
bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst)
#define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_
int tt_len(int changes_num);
-int tt_changes_fill_buffer(struct bat_priv *bat_priv,
- unsigned char *buff, int buff_len);
int tt_init(struct bat_priv *bat_priv);
void tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
int ifindex);
struct orig_node *orig_node, const char *message);
struct orig_node *transtable_search(struct bat_priv *bat_priv,
const uint8_t *src, const uint8_t *addr);
-uint16_t tt_local_crc(struct bat_priv *bat_priv);
void tt_free(struct bat_priv *bat_priv);
bool send_tt_response(struct bat_priv *bat_priv,
struct tt_query_packet *tt_request);
bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr);
void handle_tt_response(struct bat_priv *bat_priv,
struct tt_query_packet *tt_response);
-void tt_commit_changes(struct bat_priv *bat_priv);
bool is_ap_isolated(struct bat_priv *bat_priv, uint8_t *src, uint8_t *dst);
void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node,
const unsigned char *tt_buff, uint8_t tt_num_changes,
uint8_t ttvn, uint16_t tt_crc);
+int batadv_tt_append_diff(struct bat_priv *bat_priv,
+ unsigned char **packet_buff, int *packet_buff_len,
+ int packet_min_len);
bool tt_global_client_is_roaming(struct bat_priv *bat_priv, uint8_t *addr);
};
#endif
+enum bat_counters {
+ BAT_CNT_FORWARD,
+ BAT_CNT_FORWARD_BYTES,
+ BAT_CNT_MGMT_TX,
+ BAT_CNT_MGMT_TX_BYTES,
+ BAT_CNT_MGMT_RX,
+ BAT_CNT_MGMT_RX_BYTES,
+ BAT_CNT_TT_REQUEST_TX,
+ BAT_CNT_TT_REQUEST_RX,
+ BAT_CNT_TT_RESPONSE_TX,
+ BAT_CNT_TT_RESPONSE_RX,
+ BAT_CNT_TT_ROAM_ADV_TX,
+ BAT_CNT_TT_ROAM_ADV_RX,
+ BAT_CNT_NUM,
+};
+
struct bat_priv {
atomic_t mesh_state;
struct net_device_stats stats;
+ uint64_t __percpu *bat_counters; /* Per cpu counters */
atomic_t aggregated_ogms; /* boolean */
atomic_t bonding; /* boolean */
atomic_t fragmentation; /* boolean */
spinlock_t vis_list_lock; /* protects vis_info::recv_list */
atomic_t num_local_tt;
/* Checksum of the local table, recomputed before sending a new OGM */
- atomic_t tt_crc;
+ uint16_t tt_crc;
unsigned char *tt_buff;
int16_t tt_buff_len;
spinlock_t tt_buff_lock; /* protects tt_buff */
/* called when primary interface is selected / changed */
void (*bat_primary_iface_set)(struct hard_iface *hard_iface);
/* prepare a new outgoing OGM for the send queue */
- void (*bat_ogm_schedule)(struct hard_iface *hard_iface,
- int tt_num_changes);
+ void (*bat_ogm_schedule)(struct hard_iface *hard_iface);
/* send scheduled OGM */
void (*bat_ogm_emit)(struct forw_packet *forw_packet);
};
int vis_server = atomic_read(&bat_priv->vis_mode);
size_t buff_pos, buf_size;
char *buff;
- int compare;
primary_if = primary_if_get_selected(bat_priv);
if (!primary_if)
entries = (struct vis_info_entry *)
((char *)packet + sizeof(*packet));
+ vis_data_insert_interface(packet->vis_orig,
+ &vis_if_list, true);
+
for (j = 0; j < packet->entries; j++) {
if (entries[j].quality == 0)
continue;
- compare =
- compare_eth(entries[j].src, packet->vis_orig);
+ if (compare_eth(entries[j].src,
+ packet->vis_orig))
+ continue;
vis_data_insert_interface(entries[j].src,
&vis_if_list,
- compare);
+ false);
}
hlist_for_each_entry(entry, pos, &vis_if_list, list) {
entries = (struct vis_info_entry *)
((char *)packet + sizeof(*packet));
+ vis_data_insert_interface(packet->vis_orig,
+ &vis_if_list, true);
+
for (j = 0; j < packet->entries; j++) {
if (entries[j].quality == 0)
continue;
- compare =
- compare_eth(entries[j].src, packet->vis_orig);
+ if (compare_eth(entries[j].src,
+ packet->vis_orig))
+ continue;
vis_data_insert_interface(entries[j].src,
&vis_if_list,
- compare);
+ false);
}
hlist_for_each_entry(entry, pos, &vis_if_list, list) {
best_tq = find_best_vis_server(bat_priv, info);
if (best_tq < 0)
- return -1;
+ return best_tq;
}
for (i = 0; i < hash->size; i++) {
int hash_added;
if (bat_priv->vis_hash)
- return 1;
+ return 0;
spin_lock_bh(&bat_priv->vis_hash_lock);
spin_unlock_bh(&bat_priv->vis_hash_lock);
start_vis_timer(bat_priv);
- return 1;
+ return 0;
free_info:
kfree(bat_priv->my_vis_info);
err:
spin_unlock_bh(&bat_priv->vis_hash_lock);
vis_quit(bat_priv);
- return 0;
+ return -ENOMEM;
}
/* Decrease the reference count on a hash item info */
if (err < 0)
goto free_skb;
- /* to be able to check the received tx sock reference in raw_rcv() */
- skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF;
-
skb->dev = dev;
skb->sk = sk;
return 0;
}
-/*
- * Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested or the sk-reference
- * is needed on driver level for other reasons, e.g. see net/can/raw.c
- */
-static inline void skb_orphan_try(struct sk_buff *skb)
-{
- struct sock *sk = skb->sk;
-
- if (sk && !skb_shinfo(skb)->tx_flags) {
- /* skb_tx_hash() wont be able to get sk.
- * We copy sk_hash into skb->rxhash
- */
- if (!skb->rxhash)
- skb->rxhash = sk->sk_hash;
- skb_orphan(skb);
- }
-}
-
static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
{
return ((features & NETIF_F_GEN_CSUM) ||
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
- skb_orphan_try(skb);
-
features = netif_skb_features(skb);
if (vlan_tx_tag_present(skb) &&
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
- hash = (__force u16) skb->protocol ^ skb->rxhash;
+ hash = (__force u16) skb->protocol;
hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * qcount) >> 32) + qoffset;
void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
{
- int total_len, eth_len, ip_len, udp_len;
+ int total_len, ip_len, udp_len;
struct sk_buff *skb;
struct udphdr *udph;
struct iphdr *iph;
struct ethhdr *eth;
udp_len = len + sizeof(*udph);
- ip_len = eth_len = udp_len + sizeof(*iph);
- total_len = eth_len + ETH_HLEN + NET_IP_ALIGN;
+ ip_len = udp_len + sizeof(*iph);
+ total_len = ip_len + LL_RESERVED_SPACE(np->dev);
- skb = find_skb(np, total_len, total_len - len);
+ skb = find_skb(np, total_len + np->dev->needed_tailroom,
+ total_len - len);
if (!skb)
return;
skb_copy_to_linear_data(skb, msg, len);
- skb->len += len;
+ skb_put(skb, len);
skb_push(skb, sizeof(*udph));
skb_reset_transport_header(skb);
static LIST_HEAD(dcb_app_list);
static DEFINE_SPINLOCK(dcb_lock);
-/* standard netlink reply call */
-static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
- u32 seq, u16 flags)
+static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq,
+ u32 flags, struct nlmsghdr **nlhp)
{
- struct sk_buff *dcbnl_skb;
+ struct sk_buff *skb;
struct dcbmsg *dcb;
struct nlmsghdr *nlh;
- int ret = -EINVAL;
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- return ret;
+ skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!skb)
+ return NULL;
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, event, sizeof(*dcb), flags);
+ nlh = nlmsg_put(skb, port, seq, type, sizeof(*dcb), flags);
+ BUG_ON(!nlh);
- dcb = NLMSG_DATA(nlh);
+ dcb = nlmsg_data(nlh);
dcb->dcb_family = AF_UNSPEC;
dcb->cmd = cmd;
dcb->dcb_pad = 0;
- ret = nla_put_u8(dcbnl_skb, attr, value);
- if (ret)
- goto err;
+ if (nlhp)
+ *nlhp = nlh;
- /* end the message, assign the nlmsg_len. */
- nlmsg_end(dcbnl_skb, nlh);
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- return -EINVAL;
-
- return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
- return ret;
+ return skb;
}
-static int dcbnl_getstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
-
/* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */
if (!netdev->dcbnl_ops->getstate)
- return ret;
-
- ret = dcbnl_reply(netdev->dcbnl_ops->getstate(netdev), RTM_GETDCB,
- DCB_CMD_GSTATE, DCB_ATTR_STATE, pid, seq, flags);
+ return -EOPNOTSUPP;
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_STATE,
+ netdev->dcbnl_ops->getstate(netdev));
}
-static int dcbnl_getpfccfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest;
u8 value;
- int ret = -EINVAL;
+ int ret;
int i;
int getall = 0;
- if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->getpfccfg)
- return ret;
+ if (!tb[DCB_ATTR_PFC_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getpfccfg)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
tb[DCB_ATTR_PFC_CFG],
dcbnl_pfc_up_nest);
if (ret)
- goto err_out;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_PFC_GCFG;
+ return ret;
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PFC_CFG);
+ nest = nla_nest_start(skb, DCB_ATTR_PFC_CFG);
if (!nest)
- goto err;
+ return -EMSGSIZE;
if (data[DCB_PFC_UP_ATTR_ALL])
getall = 1;
netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0,
&value);
- ret = nla_put_u8(dcbnl_skb, i, value);
-
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
- goto err;
+ nla_nest_cancel(skb, nest);
+ return ret;
}
}
- nla_nest_end(dcbnl_skb, nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, nest);
return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- return -EINVAL;
}
-static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
u8 perm_addr[MAX_ADDR_LEN];
- int ret = -EINVAL;
if (!netdev->dcbnl_ops->getpermhwaddr)
- return ret;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GPERM_HWADDR;
+ return -EOPNOTSUPP;
netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr);
- ret = nla_put(dcbnl_skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr),
- perm_addr);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
-
- return 0;
-
-nlmsg_failure:
- kfree_skb(dcbnl_skb);
-err_out:
- return -EINVAL;
+ return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr);
}
-static int dcbnl_getcap(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest;
u8 value;
- int ret = -EINVAL;
+ int ret;
int i;
int getall = 0;
- if (!tb[DCB_ATTR_CAP] || !netdev->dcbnl_ops->getcap)
- return ret;
+ if (!tb[DCB_ATTR_CAP])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getcap)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP],
dcbnl_cap_nest);
if (ret)
- goto err_out;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GCAP;
+ return ret;
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_CAP);
+ nest = nla_nest_start(skb, DCB_ATTR_CAP);
if (!nest)
- goto err;
+ return -EMSGSIZE;
if (data[DCB_CAP_ATTR_ALL])
getall = 1;
continue;
if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) {
- ret = nla_put_u8(dcbnl_skb, i, value);
-
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
- goto err;
+ nla_nest_cancel(skb, nest);
+ return ret;
}
}
}
- nla_nest_end(dcbnl_skb, nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, nest);
return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- return -EINVAL;
}
-static int dcbnl_getnumtcs(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest;
u8 value;
- int ret = -EINVAL;
+ int ret;
int i;
int getall = 0;
- if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->getnumtcs)
- return ret;
+ if (!tb[DCB_ATTR_NUMTCS])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getnumtcs)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
dcbnl_numtcs_nest);
- if (ret) {
- ret = -EINVAL;
- goto err_out;
- }
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb) {
- ret = -EINVAL;
- goto err_out;
- }
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GNUMTCS;
+ if (ret)
+ return ret;
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_NUMTCS);
- if (!nest) {
- ret = -EINVAL;
- goto err;
- }
+ nest = nla_nest_start(skb, DCB_ATTR_NUMTCS);
+ if (!nest)
+ return -EMSGSIZE;
if (data[DCB_NUMTCS_ATTR_ALL])
getall = 1;
ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value);
if (!ret) {
- ret = nla_put_u8(dcbnl_skb, i, value);
-
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
- ret = -EINVAL;
- goto err;
+ nla_nest_cancel(skb, nest);
+ return ret;
}
- } else {
- goto err;
- }
- }
- nla_nest_end(dcbnl_skb, nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret) {
- ret = -EINVAL;
- goto err_out;
+ } else
+ return -EINVAL;
}
+ nla_nest_end(skb, nest);
return 0;
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- return ret;
}
-static int dcbnl_setnumtcs(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1];
- int ret = -EINVAL;
+ int ret;
u8 value;
int i;
- if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->setnumtcs)
- return ret;
+ if (!tb[DCB_ATTR_NUMTCS])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setnumtcs)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
dcbnl_numtcs_nest);
-
- if (ret) {
- ret = -EINVAL;
- goto err;
- }
+ if (ret)
+ return ret;
for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) {
if (data[i] == NULL)
value = nla_get_u8(data[i]);
ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value);
-
if (ret)
- goto operr;
+ break;
}
-operr:
- ret = dcbnl_reply(!!ret, RTM_SETDCB, DCB_CMD_SNUMTCS,
- DCB_ATTR_NUMTCS, pid, seq, flags);
-
-err:
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_NUMTCS, !!ret);
}
-static int dcbnl_getpfcstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getpfcstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
-
if (!netdev->dcbnl_ops->getpfcstate)
- return ret;
-
- ret = dcbnl_reply(netdev->dcbnl_ops->getpfcstate(netdev), RTM_GETDCB,
- DCB_CMD_PFC_GSTATE, DCB_ATTR_PFC_STATE,
- pid, seq, flags);
+ return -EOPNOTSUPP;
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_PFC_STATE,
+ netdev->dcbnl_ops->getpfcstate(netdev));
}
-static int dcbnl_setpfcstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setpfcstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
u8 value;
- if (!tb[DCB_ATTR_PFC_STATE] || !netdev->dcbnl_ops->setpfcstate)
- return ret;
+ if (!tb[DCB_ATTR_PFC_STATE])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setpfcstate)
+ return -EOPNOTSUPP;
value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]);
netdev->dcbnl_ops->setpfcstate(netdev, value);
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SSTATE, DCB_ATTR_PFC_STATE,
- pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_PFC_STATE, 0);
}
-static int dcbnl_getapp(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *app_nest;
struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1];
u16 id;
u8 up, idtype;
- int ret = -EINVAL;
+ int ret;
if (!tb[DCB_ATTR_APP])
- goto out;
+ return -EINVAL;
ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
dcbnl_app_nest);
if (ret)
- goto out;
+ return ret;
- ret = -EINVAL;
/* all must be non-null */
if ((!app_tb[DCB_APP_ATTR_IDTYPE]) ||
(!app_tb[DCB_APP_ATTR_ID]))
- goto out;
+ return -EINVAL;
/* either by eth type or by socket number */
idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]);
if ((idtype != DCB_APP_IDTYPE_ETHTYPE) &&
(idtype != DCB_APP_IDTYPE_PORTNUM))
- goto out;
+ return -EINVAL;
id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]);
up = dcb_getapp(netdev, &app);
}
- /* send this back */
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GAPP;
-
- app_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_APP);
+ app_nest = nla_nest_start(skb, DCB_ATTR_APP);
if (!app_nest)
- goto out_cancel;
+ return -EMSGSIZE;
- ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_IDTYPE, idtype);
+ ret = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, idtype);
if (ret)
goto out_cancel;
- ret = nla_put_u16(dcbnl_skb, DCB_APP_ATTR_ID, id);
+ ret = nla_put_u16(skb, DCB_APP_ATTR_ID, id);
if (ret)
goto out_cancel;
- ret = nla_put_u8(dcbnl_skb, DCB_APP_ATTR_PRIORITY, up);
+ ret = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, up);
if (ret)
goto out_cancel;
- nla_nest_end(dcbnl_skb, app_nest);
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto nlmsg_failure;
+ nla_nest_end(skb, app_nest);
- goto out;
+ return 0;
out_cancel:
- nla_nest_cancel(dcbnl_skb, app_nest);
-nlmsg_failure:
- kfree_skb(dcbnl_skb);
-out:
+ nla_nest_cancel(skb, app_nest);
return ret;
}
-static int dcbnl_setapp(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int err, ret = -EINVAL;
+ int ret;
u16 id;
u8 up, idtype;
struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1];
if (!tb[DCB_ATTR_APP])
- goto out;
+ return -EINVAL;
ret = nla_parse_nested(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP],
dcbnl_app_nest);
if (ret)
- goto out;
+ return ret;
- ret = -EINVAL;
/* all must be non-null */
if ((!app_tb[DCB_APP_ATTR_IDTYPE]) ||
(!app_tb[DCB_APP_ATTR_ID]) ||
(!app_tb[DCB_APP_ATTR_PRIORITY]))
- goto out;
+ return -EINVAL;
/* either by eth type or by socket number */
idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]);
if ((idtype != DCB_APP_IDTYPE_ETHTYPE) &&
(idtype != DCB_APP_IDTYPE_PORTNUM))
- goto out;
+ return -EINVAL;
id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]);
up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]);
if (netdev->dcbnl_ops->setapp) {
- err = netdev->dcbnl_ops->setapp(netdev, idtype, id, up);
+ ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up);
} else {
struct dcb_app app;
app.selector = idtype;
app.protocol = id;
app.priority = up;
- err = dcb_setapp(netdev, &app);
+ ret = dcb_setapp(netdev, &app);
}
- ret = dcbnl_reply(err, RTM_SETDCB, DCB_CMD_SAPP, DCB_ATTR_APP,
- pid, seq, flags);
+ ret = nla_put_u8(skb, DCB_ATTR_APP, ret);
dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0);
-out:
+
return ret;
}
-static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags, int dir)
+static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ struct nlattr **tb, struct sk_buff *skb, int dir)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *pg_nest, *param_nest, *data;
struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1];
struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1];
u8 prio, pgid, tc_pct, up_map;
- int ret = -EINVAL;
+ int ret;
int getall = 0;
int i;
- if (!tb[DCB_ATTR_PG_CFG] ||
- !netdev->dcbnl_ops->getpgtccfgtx ||
+ if (!tb[DCB_ATTR_PG_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getpgtccfgtx ||
!netdev->dcbnl_ops->getpgtccfgrx ||
!netdev->dcbnl_ops->getpgbwgcfgtx ||
!netdev->dcbnl_ops->getpgbwgcfgrx)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
-
if (ret)
- goto err_out;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = (dir) ? DCB_CMD_PGRX_GCFG : DCB_CMD_PGTX_GCFG;
+ return ret;
- pg_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PG_CFG);
+ pg_nest = nla_nest_start(skb, DCB_ATTR_PG_CFG);
if (!pg_nest)
- goto err;
+ return -EMSGSIZE;
if (pg_tb[DCB_PG_ATTR_TC_ALL])
getall = 1;
if (ret)
goto err_pg;
- param_nest = nla_nest_start(dcbnl_skb, i);
+ param_nest = nla_nest_start(skb, i);
if (!param_nest)
goto err_pg;
if (param_tb[DCB_TC_ATTR_PARAM_PGID] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb,
+ ret = nla_put_u8(skb,
DCB_TC_ATTR_PARAM_PGID, pgid);
if (ret)
goto err_param;
}
if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb,
+ ret = nla_put_u8(skb,
DCB_TC_ATTR_PARAM_UP_MAPPING, up_map);
if (ret)
goto err_param;
}
if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb,
+ ret = nla_put_u8(skb,
DCB_TC_ATTR_PARAM_STRICT_PRIO, prio);
if (ret)
goto err_param;
}
if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] ||
param_tb[DCB_TC_ATTR_PARAM_ALL]) {
- ret = nla_put_u8(dcbnl_skb, DCB_TC_ATTR_PARAM_BW_PCT,
+ ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT,
tc_pct);
if (ret)
goto err_param;
}
- nla_nest_end(dcbnl_skb, param_nest);
+ nla_nest_end(skb, param_nest);
}
if (pg_tb[DCB_PG_ATTR_BW_ID_ALL])
netdev->dcbnl_ops->getpgbwgcfgtx(netdev,
i - DCB_PG_ATTR_BW_ID_0, &tc_pct);
}
- ret = nla_put_u8(dcbnl_skb, i, tc_pct);
-
+ ret = nla_put_u8(skb, i, tc_pct);
if (ret)
goto err_pg;
}
- nla_nest_end(dcbnl_skb, pg_nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, pg_nest);
return 0;
err_param:
- nla_nest_cancel(dcbnl_skb, param_nest);
+ nla_nest_cancel(skb, param_nest);
err_pg:
- nla_nest_cancel(dcbnl_skb, pg_nest);
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- ret = -EINVAL;
- return ret;
+ nla_nest_cancel(skb, pg_nest);
+
+ return -EMSGSIZE;
}
-static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 0);
+ return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 0);
}
-static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 1);
+ return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 1);
}
-static int dcbnl_setstate(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setstate(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
u8 value;
- if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->setstate)
- return ret;
+ if (!tb[DCB_ATTR_STATE])
+ return -EINVAL;
- value = nla_get_u8(tb[DCB_ATTR_STATE]);
+ if (!netdev->dcbnl_ops->setstate)
+ return -EOPNOTSUPP;
- ret = dcbnl_reply(netdev->dcbnl_ops->setstate(netdev, value),
- RTM_SETDCB, DCB_CMD_SSTATE, DCB_ATTR_STATE,
- pid, seq, flags);
+ value = nla_get_u8(tb[DCB_ATTR_STATE]);
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_STATE,
+ netdev->dcbnl_ops->setstate(netdev, value));
}
-static int dcbnl_setpfccfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1];
int i;
- int ret = -EINVAL;
+ int ret;
u8 value;
- if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->setpfccfg)
- return ret;
+ if (!tb[DCB_ATTR_PFC_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setpfccfg)
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
tb[DCB_ATTR_PFC_CFG],
dcbnl_pfc_up_nest);
if (ret)
- goto err;
+ return ret;
for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) {
if (data[i] == NULL)
data[i]->nla_type - DCB_PFC_UP_ATTR_0, value);
}
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SCFG, DCB_ATTR_PFC_CFG,
- pid, seq, flags);
-err:
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_PFC_CFG, 0);
}
-static int dcbnl_setall(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setall(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret = -EINVAL;
+ int ret;
- if (!tb[DCB_ATTR_SET_ALL] || !netdev->dcbnl_ops->setall)
- return ret;
+ if (!tb[DCB_ATTR_SET_ALL])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setall)
+ return -EOPNOTSUPP;
- ret = dcbnl_reply(netdev->dcbnl_ops->setall(netdev), RTM_SETDCB,
- DCB_CMD_SET_ALL, DCB_ATTR_SET_ALL, pid, seq, flags);
+ ret = nla_put_u8(skb, DCB_ATTR_SET_ALL,
+ netdev->dcbnl_ops->setall(netdev));
dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0);
return ret;
}
-static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags, int dir)
+static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb,
+ int dir)
{
struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1];
struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1];
- int ret = -EINVAL;
+ int ret;
int i;
u8 pgid;
u8 up_map;
u8 prio;
u8 tc_pct;
- if (!tb[DCB_ATTR_PG_CFG] ||
- !netdev->dcbnl_ops->setpgtccfgtx ||
+ if (!tb[DCB_ATTR_PG_CFG])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setpgtccfgtx ||
!netdev->dcbnl_ops->setpgtccfgrx ||
!netdev->dcbnl_ops->setpgbwgcfgtx ||
!netdev->dcbnl_ops->setpgbwgcfgrx)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
if (ret)
- goto err;
+ return ret;
for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
if (!pg_tb[i])
ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
pg_tb[i], dcbnl_tc_param_nest);
if (ret)
- goto err;
+ return ret;
pgid = DCB_ATTR_VALUE_UNDEFINED;
prio = DCB_ATTR_VALUE_UNDEFINED;
}
}
- ret = dcbnl_reply(0, RTM_SETDCB,
- (dir ? DCB_CMD_PGRX_SCFG : DCB_CMD_PGTX_SCFG),
- DCB_ATTR_PG_CFG, pid, seq, flags);
-
-err:
- return ret;
+ return nla_put_u8(skb,
+ (dir ? DCB_CMD_PGRX_SCFG : DCB_CMD_PGTX_SCFG), 0);
}
-static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 0);
+ return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 0);
}
-static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 1);
+ return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 1);
}
-static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *bcn_nest;
struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1];
u8 value_byte;
u32 value_integer;
- int ret = -EINVAL;
+ int ret;
bool getall = false;
int i;
- if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->getbcnrp ||
+ if (!tb[DCB_ATTR_BCN])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->getbcnrp ||
!netdev->dcbnl_ops->getbcncfg)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX,
tb[DCB_ATTR_BCN], dcbnl_bcn_nest);
-
if (ret)
- goto err_out;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb)
- goto err_out;
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_BCN_GCFG;
+ return ret;
- bcn_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_BCN);
+ bcn_nest = nla_nest_start(skb, DCB_ATTR_BCN);
if (!bcn_nest)
- goto err;
+ return -EMSGSIZE;
if (bcn_tb[DCB_BCN_ATTR_ALL])
getall = true;
netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0,
&value_byte);
- ret = nla_put_u8(dcbnl_skb, i, value_byte);
+ ret = nla_put_u8(skb, i, value_byte);
if (ret)
goto err_bcn;
}
netdev->dcbnl_ops->getbcncfg(netdev, i,
&value_integer);
- ret = nla_put_u32(dcbnl_skb, i, value_integer);
+ ret = nla_put_u32(skb, i, value_integer);
if (ret)
goto err_bcn;
}
- nla_nest_end(dcbnl_skb, bcn_nest);
-
- nlmsg_end(dcbnl_skb, nlh);
-
- ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
- if (ret)
- goto err_out;
+ nla_nest_end(skb, bcn_nest);
return 0;
err_bcn:
- nla_nest_cancel(dcbnl_skb, bcn_nest);
-nlmsg_failure:
-err:
- kfree_skb(dcbnl_skb);
-err_out:
- ret = -EINVAL;
+ nla_nest_cancel(skb, bcn_nest);
return ret;
}
-static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_BCN_ATTR_MAX + 1];
int i;
- int ret = -EINVAL;
+ int ret;
u8 value_byte;
u32 value_int;
- if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg ||
+ if (!tb[DCB_ATTR_BCN])
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops->setbcncfg ||
!netdev->dcbnl_ops->setbcnrp)
- return ret;
+ return -EOPNOTSUPP;
ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX,
tb[DCB_ATTR_BCN],
dcbnl_pfc_up_nest);
if (ret)
- goto err;
+ return ret;
for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) {
if (data[i] == NULL)
i, value_int);
}
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_BCN_SCFG, DCB_ATTR_BCN,
- pid, seq, flags);
-err:
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_BCN, 0);
}
static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb,
struct dcb_app_type *itr;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
int dcbx;
- int err = -EMSGSIZE;
+ int err;
if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name))
- goto nla_put_failure;
+ return -EMSGSIZE;
+
ieee = nla_nest_start(skb, DCB_ATTR_IEEE);
if (!ieee)
- goto nla_put_failure;
+ return -EMSGSIZE;
if (ops->ieee_getets) {
struct ieee_ets ets;
err = ops->ieee_getets(netdev, &ets);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
if (ops->ieee_getmaxrate) {
err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE,
sizeof(maxrate), &maxrate);
if (err)
- goto nla_put_failure;
+ return -EMSGSIZE;
}
}
err = ops->ieee_getpfc(netdev, &pfc);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
app = nla_nest_start(skb, DCB_ATTR_IEEE_APP_TABLE);
if (!app)
- goto nla_put_failure;
+ return -EMSGSIZE;
spin_lock(&dcb_lock);
list_for_each_entry(itr, &dcb_app_list, list) {
&itr->app);
if (err) {
spin_unlock(&dcb_lock);
- goto nla_put_failure;
+ return -EMSGSIZE;
}
}
}
err = ops->ieee_peer_getets(netdev, &ets);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
if (ops->ieee_peer_getpfc) {
err = ops->ieee_peer_getpfc(netdev, &pfc);
if (!err &&
nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
if (ops->peer_getappinfo && ops->peer_getapptable) {
DCB_ATTR_IEEE_APP_UNSPEC,
DCB_ATTR_IEEE_APP);
if (err)
- goto nla_put_failure;
+ return -EMSGSIZE;
}
nla_nest_end(skb, ieee);
if (dcbx >= 0) {
err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx);
if (err)
- goto nla_put_failure;
+ return -EMSGSIZE;
}
return 0;
-
-nla_put_failure:
- return err;
}
static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev,
struct nlattr *pg = nla_nest_start(skb, i);
if (!pg)
- goto nla_put_failure;
+ return -EMSGSIZE;
for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
struct nlattr *tc_nest = nla_nest_start(skb, i);
if (!tc_nest)
- goto nla_put_failure;
+ return -EMSGSIZE;
pgid = DCB_ATTR_VALUE_UNDEFINED;
prio = DCB_ATTR_VALUE_UNDEFINED;
nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) ||
nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) ||
nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct))
- goto nla_put_failure;
+ return -EMSGSIZE;
nla_nest_end(skb, tc_nest);
}
ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0,
&tc_pct);
if (nla_put_u8(skb, i, tc_pct))
- goto nla_put_failure;
+ return -EMSGSIZE;
}
nla_nest_end(skb, pg);
return 0;
-
-nla_put_failure:
- return -EMSGSIZE;
}
static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev)
struct net *net = dev_net(dev);
struct sk_buff *skb;
struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops;
int err;
if (!ops)
return -EOPNOTSUPP;
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ skb = dcbnl_newmsg(event, cmd, pid, seq, 0, &nlh);
if (!skb)
return -ENOBUFS;
- nlh = nlmsg_put(skb, pid, 0, event, sizeof(*dcb), 0);
- if (nlh == NULL) {
- nlmsg_free(skb);
- return -EMSGSIZE;
- }
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = cmd;
-
if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE)
err = dcbnl_ieee_fill(skb, dev);
else
if (err < 0) {
/* Report error to broadcast listeners */
- nlmsg_cancel(skb, nlh);
- kfree_skb(skb);
+ nlmsg_free(skb);
rtnl_set_sk_err(net, RTNLGRP_DCB, err);
} else {
/* End nlmsg and notify broadcast listeners */
* No attempt is made to reconcile the case where only part of the
* cmd can be completed.
*/
-static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
- int err = -EOPNOTSUPP;
+ int err;
if (!ops)
- return err;
+ return -EOPNOTSUPP;
if (!tb[DCB_ATTR_IEEE])
return -EINVAL;
}
err:
- dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE,
- pid, seq, flags);
+ err = nla_put_u8(skb, DCB_ATTR_IEEE, err);
dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0);
return err;
}
-static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_ieee_get(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct net *net = dev_net(netdev);
- struct sk_buff *skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
- int err;
if (!ops)
return -EOPNOTSUPP;
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!skb)
- return -ENOBUFS;
-
- nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
- if (nlh == NULL) {
- nlmsg_free(skb);
- return -EMSGSIZE;
- }
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_IEEE_GET;
-
- err = dcbnl_ieee_fill(skb, netdev);
-
- if (err < 0) {
- nlmsg_cancel(skb, nlh);
- kfree_skb(skb);
- } else {
- nlmsg_end(skb, nlh);
- err = rtnl_unicast(skb, net, pid);
- }
-
- return err;
+ return dcbnl_ieee_fill(skb, netdev);
}
-static int dcbnl_ieee_del(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1];
- int err = -EOPNOTSUPP;
+ int err;
if (!ops)
return -EOPNOTSUPP;
}
err:
- dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_DEL, DCB_ATTR_IEEE,
- pid, seq, flags);
+ err = nla_put_u8(skb, DCB_ATTR_IEEE, err);
dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0);
return err;
}
/* DCBX configuration */
-static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getdcbx(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret;
-
if (!netdev->dcbnl_ops->getdcbx)
return -EOPNOTSUPP;
- ret = dcbnl_reply(netdev->dcbnl_ops->getdcbx(netdev), RTM_GETDCB,
- DCB_CMD_GDCBX, DCB_ATTR_DCBX, pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_DCBX,
+ netdev->dcbnl_ops->getdcbx(netdev));
}
-static int dcbnl_setdcbx(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setdcbx(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- int ret;
u8 value;
if (!netdev->dcbnl_ops->setdcbx)
value = nla_get_u8(tb[DCB_ATTR_DCBX]);
- ret = dcbnl_reply(netdev->dcbnl_ops->setdcbx(netdev, value),
- RTM_SETDCB, DCB_CMD_SDCBX, DCB_ATTR_DCBX,
- pid, seq, flags);
-
- return ret;
+ return nla_put_u8(skb, DCB_ATTR_DCBX,
+ netdev->dcbnl_ops->setdcbx(netdev, value));
}
-static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct sk_buff *dcbnl_skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest;
u8 value;
int ret, i;
ret = nla_parse_nested(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG],
dcbnl_featcfg_nest);
if (ret)
- goto err_out;
-
- dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!dcbnl_skb) {
- ret = -ENOBUFS;
- goto err_out;
- }
-
- nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
-
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_GFEATCFG;
+ return ret;
- nest = nla_nest_start(dcbnl_skb, DCB_ATTR_FEATCFG);
- if (!nest) {
- ret = -EMSGSIZE;
- goto nla_put_failure;
- }
+ nest = nla_nest_start(skb, DCB_ATTR_FEATCFG);
+ if (!nest)
+ return -EMSGSIZE;
if (data[DCB_FEATCFG_ATTR_ALL])
getall = 1;
ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value);
if (!ret)
- ret = nla_put_u8(dcbnl_skb, i, value);
+ ret = nla_put_u8(skb, i, value);
if (ret) {
- nla_nest_cancel(dcbnl_skb, nest);
+ nla_nest_cancel(skb, nest);
goto nla_put_failure;
}
}
- nla_nest_end(dcbnl_skb, nest);
+ nla_nest_end(skb, nest);
- nlmsg_end(dcbnl_skb, nlh);
-
- return rtnl_unicast(dcbnl_skb, &init_net, pid);
nla_put_failure:
- nlmsg_cancel(dcbnl_skb, nlh);
-nlmsg_failure:
- kfree_skb(dcbnl_skb);
-err_out:
return ret;
}
-static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1];
int ret, i;
goto err;
}
err:
- dcbnl_reply(ret, RTM_SETDCB, DCB_CMD_SFEATCFG, DCB_ATTR_FEATCFG,
- pid, seq, flags);
+ ret = nla_put_u8(skb, DCB_ATTR_FEATCFG, ret);
return ret;
}
/* Handle CEE DCBX GET commands. */
-static int dcbnl_cee_get(struct net_device *netdev, struct nlattr **tb,
- u32 pid, u32 seq, u16 flags)
+static int dcbnl_cee_get(struct net_device *netdev, struct nlmsghdr *nlh,
+ u32 seq, struct nlattr **tb, struct sk_buff *skb)
{
- struct net *net = dev_net(netdev);
- struct sk_buff *skb;
- struct nlmsghdr *nlh;
- struct dcbmsg *dcb;
const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops;
- int err;
if (!ops)
return -EOPNOTSUPP;
- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (!skb)
- return -ENOBUFS;
-
- nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
- if (nlh == NULL) {
- nlmsg_free(skb);
- return -EMSGSIZE;
- }
+ return dcbnl_cee_fill(skb, netdev);
+}
- dcb = NLMSG_DATA(nlh);
- dcb->dcb_family = AF_UNSPEC;
- dcb->cmd = DCB_CMD_CEE_GET;
+struct reply_func {
+ /* reply netlink message type */
+ int type;
- err = dcbnl_cee_fill(skb, netdev);
+ /* function to fill message contents */
+ int (*cb)(struct net_device *, struct nlmsghdr *, u32,
+ struct nlattr **, struct sk_buff *);
+};
- if (err < 0) {
- nlmsg_cancel(skb, nlh);
- nlmsg_free(skb);
- } else {
- nlmsg_end(skb, nlh);
- err = rtnl_unicast(skb, net, pid);
- }
- return err;
-}
+static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = {
+ [DCB_CMD_GSTATE] = { RTM_GETDCB, dcbnl_getstate },
+ [DCB_CMD_SSTATE] = { RTM_SETDCB, dcbnl_setstate },
+ [DCB_CMD_PFC_GCFG] = { RTM_GETDCB, dcbnl_getpfccfg },
+ [DCB_CMD_PFC_SCFG] = { RTM_SETDCB, dcbnl_setpfccfg },
+ [DCB_CMD_GPERM_HWADDR] = { RTM_GETDCB, dcbnl_getperm_hwaddr },
+ [DCB_CMD_GCAP] = { RTM_GETDCB, dcbnl_getcap },
+ [DCB_CMD_GNUMTCS] = { RTM_GETDCB, dcbnl_getnumtcs },
+ [DCB_CMD_SNUMTCS] = { RTM_SETDCB, dcbnl_setnumtcs },
+ [DCB_CMD_PFC_GSTATE] = { RTM_GETDCB, dcbnl_getpfcstate },
+ [DCB_CMD_PFC_SSTATE] = { RTM_SETDCB, dcbnl_setpfcstate },
+ [DCB_CMD_GAPP] = { RTM_GETDCB, dcbnl_getapp },
+ [DCB_CMD_SAPP] = { RTM_SETDCB, dcbnl_setapp },
+ [DCB_CMD_PGTX_GCFG] = { RTM_GETDCB, dcbnl_pgtx_getcfg },
+ [DCB_CMD_PGTX_SCFG] = { RTM_SETDCB, dcbnl_pgtx_setcfg },
+ [DCB_CMD_PGRX_GCFG] = { RTM_GETDCB, dcbnl_pgrx_getcfg },
+ [DCB_CMD_PGRX_SCFG] = { RTM_SETDCB, dcbnl_pgrx_setcfg },
+ [DCB_CMD_SET_ALL] = { RTM_SETDCB, dcbnl_setall },
+ [DCB_CMD_BCN_GCFG] = { RTM_GETDCB, dcbnl_bcn_getcfg },
+ [DCB_CMD_BCN_SCFG] = { RTM_SETDCB, dcbnl_bcn_setcfg },
+ [DCB_CMD_IEEE_GET] = { RTM_GETDCB, dcbnl_ieee_get },
+ [DCB_CMD_IEEE_SET] = { RTM_SETDCB, dcbnl_ieee_set },
+ [DCB_CMD_IEEE_DEL] = { RTM_SETDCB, dcbnl_ieee_del },
+ [DCB_CMD_GDCBX] = { RTM_GETDCB, dcbnl_getdcbx },
+ [DCB_CMD_SDCBX] = { RTM_SETDCB, dcbnl_setdcbx },
+ [DCB_CMD_GFEATCFG] = { RTM_GETDCB, dcbnl_getfeatcfg },
+ [DCB_CMD_SFEATCFG] = { RTM_SETDCB, dcbnl_setfeatcfg },
+ [DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get },
+};
static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct net_device *netdev;
- struct dcbmsg *dcb = (struct dcbmsg *)NLMSG_DATA(nlh);
+ struct dcbmsg *dcb = nlmsg_data(nlh);
struct nlattr *tb[DCB_ATTR_MAX + 1];
u32 pid = skb ? NETLINK_CB(skb).pid : 0;
int ret = -EINVAL;
+ struct sk_buff *reply_skb;
+ struct nlmsghdr *reply_nlh = NULL;
+ const struct reply_func *fn;
if (!net_eq(net, &init_net))
return -EINVAL;
if (ret < 0)
return ret;
+ if (dcb->cmd > DCB_CMD_MAX)
+ return -EINVAL;
+
+ /* check if a reply function has been defined for the command */
+ fn = &reply_funcs[dcb->cmd];
+ if (!fn->cb)
+ return -EOPNOTSUPP;
+
if (!tb[DCB_ATTR_IFNAME])
return -EINVAL;
netdev = dev_get_by_name(&init_net, nla_data(tb[DCB_ATTR_IFNAME]));
if (!netdev)
- return -EINVAL;
+ return -ENODEV;
- if (!netdev->dcbnl_ops)
- goto errout;
-
- switch (dcb->cmd) {
- case DCB_CMD_GSTATE:
- ret = dcbnl_getstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_GCFG:
- ret = dcbnl_getpfccfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GPERM_HWADDR:
- ret = dcbnl_getperm_hwaddr(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGTX_GCFG:
- ret = dcbnl_pgtx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGRX_GCFG:
- ret = dcbnl_pgrx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_BCN_GCFG:
- ret = dcbnl_bcn_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SSTATE:
- ret = dcbnl_setstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_SCFG:
- ret = dcbnl_setpfccfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
+ if (!netdev->dcbnl_ops) {
+ ret = -EOPNOTSUPP;
goto out;
+ }
- case DCB_CMD_SET_ALL:
- ret = dcbnl_setall(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGTX_SCFG:
- ret = dcbnl_pgtx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PGRX_SCFG:
- ret = dcbnl_pgrx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GCAP:
- ret = dcbnl_getcap(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GNUMTCS:
- ret = dcbnl_getnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SNUMTCS:
- ret = dcbnl_setnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_GSTATE:
- ret = dcbnl_getpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_PFC_SSTATE:
- ret = dcbnl_setpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_BCN_SCFG:
- ret = dcbnl_bcn_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GAPP:
- ret = dcbnl_getapp(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SAPP:
- ret = dcbnl_setapp(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_IEEE_SET:
- ret = dcbnl_ieee_set(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_IEEE_GET:
- ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_IEEE_DEL:
- ret = dcbnl_ieee_del(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GDCBX:
- ret = dcbnl_getdcbx(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SDCBX:
- ret = dcbnl_setdcbx(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_GFEATCFG:
- ret = dcbnl_getfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
- goto out;
- case DCB_CMD_SFEATCFG:
- ret = dcbnl_setfeatcfg(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
+ reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags, &reply_nlh);
+ if (!reply_skb) {
+ ret = -ENOBUFS;
goto out;
- case DCB_CMD_CEE_GET:
- ret = dcbnl_cee_get(netdev, tb, pid, nlh->nlmsg_seq,
- nlh->nlmsg_flags);
+ }
+
+ ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb);
+ if (ret < 0) {
+ nlmsg_free(reply_skb);
goto out;
- default:
- goto errout;
}
-errout:
- ret = -EINVAL;
+
+ nlmsg_end(reply_skb, reply_nlh);
+
+ ret = rtnl_unicast(reply_skb, &init_net, pid);
out:
dev_put(netdev);
return ret;
}
+static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app,
+ int ifindex, int prio)
+{
+ struct dcb_app_type *itr;
+
+ list_for_each_entry(itr, &dcb_app_list, list) {
+ if (itr->app.selector == app->selector &&
+ itr->app.protocol == app->protocol &&
+ itr->ifindex == ifindex &&
+ (!prio || itr->app.priority == prio))
+ return itr;
+ }
+
+ return NULL;
+}
+
+static int dcb_app_add(const struct dcb_app *app, int ifindex)
+{
+ struct dcb_app_type *entry;
+
+ entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ return -ENOMEM;
+
+ memcpy(&entry->app, app, sizeof(*app));
+ entry->ifindex = ifindex;
+ list_add(&entry->list, &dcb_app_list);
+
+ return 0;
+}
+
/**
* dcb_getapp - retrieve the DCBX application user priority
*
u8 prio = 0;
spin_lock(&dcb_lock);
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == app->selector &&
- itr->app.protocol == app->protocol &&
- itr->ifindex == dev->ifindex) {
- prio = itr->app.priority;
- break;
- }
- }
+ if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
+ prio = itr->app.priority;
spin_unlock(&dcb_lock);
return prio;
{
struct dcb_app_type *itr;
struct dcb_app_type event;
+ int err = 0;
event.ifindex = dev->ifindex;
memcpy(&event.app, new, sizeof(event.app));
spin_lock(&dcb_lock);
/* Search for existing match and replace */
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == new->selector &&
- itr->app.protocol == new->protocol &&
- itr->ifindex == dev->ifindex) {
- if (new->priority)
- itr->app.priority = new->priority;
- else {
- list_del(&itr->list);
- kfree(itr);
- }
- goto out;
+ if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) {
+ if (new->priority)
+ itr->app.priority = new->priority;
+ else {
+ list_del(&itr->list);
+ kfree(itr);
}
+ goto out;
}
/* App type does not exist add new application type */
- if (new->priority) {
- struct dcb_app_type *entry;
- entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
- if (!entry) {
- spin_unlock(&dcb_lock);
- return -ENOMEM;
- }
-
- memcpy(&entry->app, new, sizeof(*new));
- entry->ifindex = dev->ifindex;
- list_add(&entry->list, &dcb_app_list);
- }
+ if (new->priority)
+ err = dcb_app_add(new, dev->ifindex);
out:
spin_unlock(&dcb_lock);
- call_dcbevent_notifiers(DCB_APP_EVENT, &event);
- return 0;
+ if (!err)
+ call_dcbevent_notifiers(DCB_APP_EVENT, &event);
+ return err;
}
EXPORT_SYMBOL(dcb_setapp);
u8 prio = 0;
spin_lock(&dcb_lock);
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == app->selector &&
- itr->app.protocol == app->protocol &&
- itr->ifindex == dev->ifindex) {
- prio |= 1 << itr->app.priority;
- }
- }
+ if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
+ prio |= 1 << itr->app.priority;
spin_unlock(&dcb_lock);
return prio;
*/
int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new)
{
- struct dcb_app_type *itr, *entry;
struct dcb_app_type event;
int err = 0;
spin_lock(&dcb_lock);
/* Search for existing match and abort if found */
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == new->selector &&
- itr->app.protocol == new->protocol &&
- itr->app.priority == new->priority &&
- itr->ifindex == dev->ifindex) {
- err = -EEXIST;
- goto out;
- }
- }
-
- /* App entry does not exist add new entry */
- entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC);
- if (!entry) {
- err = -ENOMEM;
+ if (dcb_app_lookup(new, dev->ifindex, new->priority)) {
+ err = -EEXIST;
goto out;
}
- memcpy(&entry->app, new, sizeof(*new));
- entry->ifindex = dev->ifindex;
- list_add(&entry->list, &dcb_app_list);
+ err = dcb_app_add(new, dev->ifindex);
out:
spin_unlock(&dcb_lock);
if (!err)
spin_lock(&dcb_lock);
/* Search for existing match and remove it. */
- list_for_each_entry(itr, &dcb_app_list, list) {
- if (itr->app.selector == del->selector &&
- itr->app.protocol == del->protocol &&
- itr->app.priority == del->priority &&
- itr->ifindex == dev->ifindex) {
- list_del(&itr->list);
- kfree(itr);
- err = 0;
- goto out;
- }
+ if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) {
+ list_del(&itr->list);
+ kfree(itr);
+ err = 0;
}
-out:
spin_unlock(&dcb_lock);
if (!err)
call_dcbevent_notifiers(DCB_APP_EVENT, &event);
} else
dst_hold(dst);
+ dst->ops->update_pmtu(dst, ntohl(info));
+
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
dccp_sync_mss(sk, dst_mtu(dst));
} /* else let the usual retransmit timer handle it */
return;
pr_debug("pmtu discovery on SA AH/%08x/%08x\n",
ntohl(ah->spi), ntohl(iph->daddr));
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
}
return;
NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n",
ntohl(esph->spi), ntohl(iph->daddr));
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
}
int type = nla_type(nla);
if (type) {
+ u32 val;
+
if (type > RTAX_MAX)
goto err_inval;
- fi->fib_metrics[type - 1] = nla_get_u32(nla);
+ val = nla_get_u32(nla);
+ if (type == RTAX_ADVMSS && val > 65535 - 40)
+ val = 65535 - 40;
+ fi->fib_metrics[type - 1] = val;
}
}
}
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
flags & GRE_KEY ?
*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
p[1]);
- if (t == NULL || t->parms.iph.daddr == 0 ||
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->parms.link, 0, IPPROTO_GRE, 0);
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0 ||
ipv4_is_multicast(t->parms.iph.daddr))
goto out;
return;
NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI4\n",
spi, &iph->daddr);
+ ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
}
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
rcu_read_lock();
t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
- if (t == NULL || t->parms.iph.daddr == 0)
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->dev->ifindex, 0, IPPROTO_IPIP, 0);
+ err = 0;
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0)
goto out;
err = 0;
return NF_ACCEPT;
}
-static unsigned int ipv4_confirm(unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+static unsigned int ipv4_helper(unsigned int hooknum,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
- goto out;
+ return NF_ACCEPT;
help = nfct_help(ct);
if (!help)
- goto out;
+ return NF_ACCEPT;
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
- goto out;
+ return NF_ACCEPT;
ret = helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
ct, ctinfo);
- if (ret != NF_ACCEPT) {
+ if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) {
nf_log_packet(NFPROTO_IPV4, hooknum, skb, in, out, NULL,
"nf_ct_%s: dropping packet", helper->name);
- return ret;
}
+ return ret;
+}
+
+static unsigned int ipv4_confirm(unsigned int hooknum,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ struct nf_conn *ct;
+ enum ip_conntrack_info ctinfo;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+ goto out;
/* adjust seqs for loopback traffic only in outgoing direction */
if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP_PRI_CONNTRACK,
},
+ {
+ .hook = ipv4_helper,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_POST_ROUTING,
+ .priority = NF_IP_PRI_CONNTRACK_HELPER,
+ },
{
.hook = ipv4_confirm,
.owner = THIS_MODULE,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP_PRI_CONNTRACK_CONFIRM,
},
+ {
+ .hook = ipv4_helper,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = NF_IP_PRI_CONNTRACK_HELPER,
+ },
{
.hook = ipv4_confirm,
.owner = THIS_MODULE,
#include <linux/skbuff.h>
#include <linux/udp.h>
-#include <net/netfilter/nf_nat_helper.h>
-#include <net/netfilter/nf_nat_rule.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat_helper.h>
+#include <net/netfilter/nf_nat_rule.h>
#include <linux/netfilter/nf_conntrack_amanda.h>
MODULE_AUTHOR("Brian J. Murrell <netfilter@interlinx.bc.ca>");
unsigned char **data,
TransportAddress *taddr, int count)
{
- const struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ const struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int i;
__be16 port;
struct nf_conntrack_expect *rtp_exp,
struct nf_conntrack_expect *rtcp_exp)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int i;
u_int16_t nated_port;
TransportAddress *taddr, __be16 port,
struct nf_conntrack_expect *exp)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
u_int16_t nated_port = ntohs(port);
unsigned char **data, TransportAddress *taddr, int idx,
__be16 port, struct nf_conntrack_expect *exp)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
u_int16_t nated_port = ntohs(port);
union nf_inet_addr addr;
}
EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust);
+void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
+ u32 ctinfo, int off)
+{
+ const struct tcphdr *th;
+
+ if (nf_ct_protonum(ct) != IPPROTO_TCP)
+ return;
+
+ th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb));
+ nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off);
+}
+EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust);
+
static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data,
int datalen, __sum16 *check, int oldlen)
{
const struct nf_nat_pptp *nat_pptp_info;
struct nf_nat_ipv4_range range;
- ct_pptp_info = &nfct_help(master)->help.ct_pptp_info;
+ ct_pptp_info = nfct_help_data(master);
nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info;
/* And here goes the grand finale of corrosion... */
__be16 new_callid;
unsigned int cid_off;
- ct_pptp_info = &nfct_help(ct)->help.ct_pptp_info;
+ ct_pptp_info = nfct_help_data(ct);
nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info;
new_callid = ct_pptp_info->pns_call_id;
struct nf_ct_pptp_master *ct_pptp_info;
struct nf_nat_pptp *nat_pptp_info;
- ct_pptp_info = &nfct_help(ct)->help.ct_pptp_info;
+ ct_pptp_info = nfct_help_data(ct);
nat_pptp_info = &nfct_nat(ct)->help.nat_pptp_info;
/* save original PAC call ID in nat_info */
#include <linux/module.h>
#include <linux/udp.h>
-#include <net/netfilter/nf_nat_helper.h>
-#include <net/netfilter/nf_nat_rule.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat_helper.h>
+#include <net/netfilter/nf_nat_rule.h>
#include <linux/netfilter/nf_conntrack_tftp.h>
MODULE_AUTHOR("Magnus Boden <mb@ozaba.mine.nu>");
break;
case ICMP_DEST_UNREACH:
if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
err = EMSGSIZE;
harderr = 1;
int err = 0;
int harderr = 0;
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+ ipv4_sk_update_pmtu(skb, sk, info);
+
/* Report error on raw socket, if:
1. User requested ip_recverr.
2. Socket is connected (otherwise the error indication
}
}
+void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
+ int oif, u32 mark, u8 protocol, int flow_flags)
+{
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
+ struct flowi4 fl4;
+ struct rtable *rt;
+
+ flowi4_init_output(&fl4, oif, mark, RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
+ protocol, flow_flags | FLOWI_FLAG_PRECOW_METRICS,
+ iph->daddr, iph->saddr, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
+ if (!IS_ERR(rt)) {
+ ip_rt_update_pmtu(&rt->dst, mtu);
+ ip_rt_put(rt);
+ }
+}
+EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
+
+void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
+{
+ const struct inet_sock *inet = inet_sk(sk);
+
+ return ipv4_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark,
+ inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ inet_sk_flowi_flags(sk));
+}
+EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
static void ipv4_validate_peer(struct rtable *rt)
{
if (dst_mtu(dst) > IP_MAX_MTU)
dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU);
- if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40)
- dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40);
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
break;
case ICMP_DEST_UNREACH:
if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
if (inet->pmtudisc != IP_PMTUDISC_DONT) {
err = EMSGSIZE;
harderr = 1;
#include <linux/pfkeyv2.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/%pI6\n",
ntohl(ah->spi), &iph->daddr);
-
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
return;
pr_debug("pmtu discovery on SA ESP/%08x/%pI6\n",
ntohl(esph->spi), &iph->daddr);
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
struct net_device *dev = skb->dev;
struct inet6_dev *idev = __in6_dev_get(dev);
const struct in6_addr *saddr, *daddr;
- const struct ipv6hdr *orig_hdr;
struct icmp6hdr *hdr;
u8 type;
XFRM_STATE_ICMP))
goto drop_no_count;
- if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(*orig_hdr)))
+ if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
goto drop_no_count;
nh = skb_network_offset(skb);
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto discard_it;
hdr = icmp6_hdr(skb);
- orig_hdr = (struct ipv6hdr *) (hdr + 1);
- rt6_pmtu_discovery(&orig_hdr->daddr, &orig_hdr->saddr, dev,
- ntohl(hdr->icmp6_mtu));
/*
* Drop through to notify
#include <linux/list.h>
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
+#include <net/ip6_route.h>
#include <net/icmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
pr_debug("pmtu discovery on SA IPCOMP/%08x/%pI6\n",
spi, &iph->daddr);
+ ip6_update_pmtu(skb, net, info, 0, 0);
xfrm_state_put(x);
}
return NF_ACCEPT;
}
-static unsigned int ipv6_confirm(unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
+static unsigned int ipv6_helper(unsigned int hooknum,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
{
struct nf_conn *ct;
const struct nf_conn_help *help;
/* This is where we call the helper: as the packet goes out. */
ct = nf_ct_get(skb, &ctinfo);
if (!ct || ctinfo == IP_CT_RELATED_REPLY)
- goto out;
+ return NF_ACCEPT;
help = nfct_help(ct);
if (!help)
- goto out;
+ return NF_ACCEPT;
/* rcu_read_lock()ed by nf_hook_slow */
helper = rcu_dereference(help->helper);
if (!helper)
- goto out;
+ return NF_ACCEPT;
protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum,
skb->len - extoff);
}
ret = helper->help(skb, protoff, ct, ctinfo);
- if (ret != NF_ACCEPT) {
+ if (ret != NF_ACCEPT && (ret & NF_VERDICT_MASK) != NF_QUEUE) {
nf_log_packet(NFPROTO_IPV6, hooknum, skb, in, out, NULL,
"nf_ct_%s: dropping packet", helper->name);
- return ret;
}
-out:
+ return ret;
+}
+
+static unsigned int ipv6_confirm(unsigned int hooknum,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
/* We've seen it coming out the other side: confirm it */
return nf_conntrack_confirm(skb);
}
.hooknum = NF_INET_LOCAL_OUT,
.priority = NF_IP6_PRI_CONNTRACK,
},
+ {
+ .hook = ipv6_helper,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV6,
+ .hooknum = NF_INET_POST_ROUTING,
+ .priority = NF_IP6_PRI_CONNTRACK_HELPER,
+ },
{
.hook = ipv6_confirm,
.owner = THIS_MODULE,
.hooknum = NF_INET_POST_ROUTING,
.priority = NF_IP6_PRI_LAST,
},
+ {
+ .hook = ipv6_helper,
+ .owner = THIS_MODULE,
+ .pf = NFPROTO_IPV6,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = NF_IP6_PRI_CONNTRACK_HELPER,
+ },
{
.hook = ipv6_confirm,
.owner = THIS_MODULE,
return;
harderr = icmpv6_err_convert(type, code, &err);
- if (type == ICMPV6_PKT_TOOBIG)
+ if (type == ICMPV6_PKT_TOOBIG) {
+ ip6_sk_update_pmtu(skb, sk, info);
harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
-
+ }
if (np->recverr) {
u8 *payload = skb->data;
if (!inet->hdrincl)
{
struct rt6_info *rt6 = (struct rt6_info*)dst;
+ dst_confirm(dst);
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
+ struct net *net = dev_net(dst->dev);
+
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU) {
u32 features = dst_metric(dst, RTAX_FEATURES);
dst_metric_set(dst, RTAX_FEATURES, features);
}
dst_metric_set(dst, RTAX_MTU, mtu);
+ rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
}
+void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
+ int oif, u32 mark)
+{
+ const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data;
+ struct dst_entry *dst;
+ struct flowi6 fl6;
+
+ memset(&fl6, 0, sizeof(fl6));
+ fl6.flowi6_oif = oif;
+ fl6.flowi6_mark = mark;
+ fl6.flowi6_flags = FLOWI_FLAG_PRECOW_METRICS;
+ fl6.daddr = iph->daddr;
+ fl6.saddr = iph->saddr;
+ fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK;
+
+ dst = ip6_route_output(net, NULL, &fl6);
+ if (!dst->error)
+ ip6_rt_update_pmtu(dst, ntohl(mtu));
+ dst_release(dst);
+}
+EXPORT_SYMBOL_GPL(ip6_update_pmtu);
+
+void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
+{
+ ip6_update_pmtu(skb, sock_net(sk), mtu,
+ sk->sk_bound_dev_if, sk->sk_mark);
+}
+EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
+
static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
struct net_device *dev = dst->dev;
dst_release(&rt->dst);
}
-/*
- * Handle ICMP "packet too big" messages
- * i.e. Path MTU discovery
- */
-
-static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net *net, u32 pmtu, int ifindex)
-{
- struct rt6_info *rt, *nrt;
- int allfrag = 0;
-again:
- rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
- if (!rt)
- return;
-
- if (rt6_check_expired(rt)) {
- ip6_del_rt(rt);
- goto again;
- }
-
- if (pmtu >= dst_mtu(&rt->dst))
- goto out;
-
- if (pmtu < IPV6_MIN_MTU) {
- /*
- * According to RFC2460, PMTU is set to the IPv6 Minimum Link
- * MTU (1280) and a fragment header should always be included
- * after a node receiving Too Big message reporting PMTU is
- * less than the IPv6 Minimum Link MTU.
- */
- pmtu = IPV6_MIN_MTU;
- allfrag = 1;
- }
-
- /* New mtu received -> path was valid.
- They are sent only in response to data packets,
- so that this nexthop apparently is reachable. --ANK
- */
- dst_confirm(&rt->dst);
-
- /* Host route. If it is static, it would be better
- not to override it, but add new one, so that
- when cache entry will expire old pmtu
- would return automatically.
- */
- if (rt->rt6i_flags & RTF_CACHE) {
- dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&rt->dst, RTAX_FEATURES, features);
- }
- rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
- rt->rt6i_flags |= RTF_MODIFIED;
- goto out;
- }
-
- /* Network route.
- Two cases are possible:
- 1. It is connected route. Action: COW
- 2. It is gatewayed route or NONEXTHOP route. Action: clone it.
- */
- if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
- nrt = rt6_alloc_cow(rt, daddr, saddr);
- else
- nrt = rt6_alloc_clone(rt, daddr);
-
- if (nrt) {
- dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
- if (allfrag) {
- u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
- features |= RTAX_FEATURE_ALLFRAG;
- dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
- }
-
- /* According to RFC 1981, detecting PMTU increase shouldn't be
- * happened within 5 mins, the recommended timer is 10 mins.
- * Here this route expiration time is set to ip6_rt_mtu_expires
- * which is 10 mins. After 10 mins the decreased pmtu is expired
- * and detecting PMTU increase will be automatically happened.
- */
- rt6_update_expires(nrt, net->ipv6.sysctl.ip6_rt_mtu_expires);
- nrt->rt6i_flags |= RTF_DYNAMIC;
- ip6_ins_rt(nrt);
- }
-out:
- dst_release(&rt->dst);
-}
-
-void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
- struct net_device *dev, u32 pmtu)
-{
- struct net *net = dev_net(dev);
-
- /*
- * RFC 1981 states that a node "MUST reduce the size of the packets it
- * is sending along the path" that caused the Packet Too Big message.
- * Since it's not possible in the general case to determine which
- * interface was used to send the original packet, we update the MTU
- * on the interface that will be used to send future packets. We also
- * update the MTU on the interface that received the Packet Too Big in
- * case the original packet was forced out that interface with
- * SO_BINDTODEVICE or similar. This is the next best thing to the
- * correct behaviour, which would be to update the MTU on all
- * interfaces.
- */
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
- rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
-}
-
/*
* Misc support functions
*/
if (ret)
goto out_kmem_cache;
- ret = register_pernet_subsys(&ip6_route_net_ops);
+ ret = register_pernet_subsys(&ipv6_inetpeer_ops);
if (ret)
goto out_dst_entries;
- ret = register_pernet_subsys(&ipv6_inetpeer_ops);
+ ret = register_pernet_subsys(&ip6_route_net_ops);
if (ret)
- goto out_register_subsys;
+ goto out_register_inetpeer;
ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
#endif
ret = fib6_init();
if (ret)
- goto out_register_inetpeer;
+ goto out_register_subsys;
ret = xfrm6_init();
if (ret)
xfrm6_fini();
out_fib6_init:
fib6_gc_cleanup();
-out_register_inetpeer:
- unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_register_subsys:
unregister_pernet_subsys(&ip6_route_net_ops);
+out_register_inetpeer:
+ unregister_pernet_subsys(&ipv6_inetpeer_ops);
out_dst_entries:
dst_entries_destroy(&ip6_dst_blackhole_ops);
out_kmem_cache:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
skb->dev,
iph->daddr,
iph->saddr);
- if (t == NULL || t->parms.iph.daddr == 0)
+ if (t == NULL)
+ goto out;
+
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
+ ipv4_update_pmtu(skb, dev_net(skb->dev), info,
+ t->dev->ifindex, 0, IPPROTO_IPV6, 0);
+ err = 0;
+ goto out;
+ }
+
+ if (t->parms.iph.daddr == 0)
goto out;
err = 0;
} else
dst_hold(dst);
+ dst->ops->update_pmtu(dst, ntohl(info));
+
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
if (sk == NULL)
return;
+ if (type == ICMPV6_PKT_TOOBIG)
+ ip6_sk_update_pmtu(skb, sk, info);
+
np = inet6_sk(sk);
if (!icmpv6_err_convert(type, code, &err) && !np->recverr)
skb_trim(skb, skb->dev->mtu);
}
skb->protocol = ETH_P_AF_IUCV;
- skb_shinfo(skb)->tx_flags |= SKBTX_DRV_NEEDS_SK_REF;
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
return -ENOMEM;
If unsure, say `N'.
+config NF_CT_NETLINK_HELPER
+ tristate 'Connection tracking helpers in user-space via Netlink'
+ select NETFILTER_NETLINK
+ depends on NF_CT_NETLINK
+ depends on NETFILTER_NETLINK_QUEUE
+ depends on NETFILTER_NETLINK_QUEUE_CT
+ depends on NETFILTER_ADVANCED
+ help
+ This option enables the user-space connection tracking helpers
+ infrastructure.
+
+ If unsure, say `N'.
+
+config NETFILTER_NETLINK_QUEUE_CT
+ bool "NFQUEUE integration with Connection Tracking"
+ default n
+ depends on NETFILTER_NETLINK_QUEUE
+ help
+ If this option is enabled, NFQUEUE can include Connection Tracking
+ information together with the packet is the enqueued via NFNETLINK.
+
endif # NF_CONNTRACK
# transparent proxy support
obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
+nfnetlink_queue-y := nfnetlink_queue_core.o
+nfnetlink_queue-$(CONFIG_NETFILTER_NETLINK_QUEUE_CT) += nfnetlink_queue_ct.o
obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
# netlink interface for nf_conntrack
obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o
obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o
+obj-$(CONFIG_NF_CT_NETLINK_HELPER) += nfnetlink_cthelper.o
# connection tracking helpers
nf_conntrack_h323-objs := nf_conntrack_h323_main.o nf_conntrack_h323_asn1.o
rcu_read_unlock();
}
EXPORT_SYMBOL(nf_conntrack_destroy);
+
+struct nfq_ct_hook *nfq_ct_hook;
+EXPORT_SYMBOL_GPL(nfq_ct_hook);
+
#endif /* CONFIG_NF_CONNTRACK */
#ifdef CONFIG_PROC_FS
__set_bit(IPS_EXPECTED_BIT, &ct->status);
ct->master = exp->master;
if (exp->helper) {
- help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
+ help = nf_ct_helper_ext_add(ct, exp->helper,
+ GFP_ATOMIC);
if (help)
rcu_assign_pointer(help->helper, exp->helper);
}
EXPORT_SYMBOL(__nf_ct_ext_destroy);
static void *
-nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp)
+nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id,
+ size_t var_alloc_len, gfp_t gfp)
{
unsigned int off, len;
struct nf_ct_ext_type *t;
t = rcu_dereference(nf_ct_ext_types[id]);
BUG_ON(t == NULL);
off = ALIGN(sizeof(struct nf_ct_ext), t->align);
- len = off + t->len;
- alloc_size = t->alloc_size;
+ len = off + t->len + var_alloc_len;
+ alloc_size = t->alloc_size + var_alloc_len;
rcu_read_unlock();
*ext = kzalloc(alloc_size, gfp);
return (void *)(*ext) + off;
}
-void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
+void *__nf_ct_ext_add_length(struct nf_conn *ct, enum nf_ct_ext_id id,
+ size_t var_alloc_len, gfp_t gfp)
{
struct nf_ct_ext *old, *new;
int i, newlen, newoff;
old = ct->ext;
if (!old)
- return nf_ct_ext_create(&ct->ext, id, gfp);
+ return nf_ct_ext_create(&ct->ext, id, var_alloc_len, gfp);
if (__nf_ct_ext_exist(old, id))
return NULL;
BUG_ON(t == NULL);
newoff = ALIGN(old->len, t->align);
- newlen = newoff + t->len;
+ newlen = newoff + t->len + var_alloc_len;
rcu_read_unlock();
new = __krealloc(old, newlen, gfp);
memset((void *)new + newoff, 0, newlen - newoff);
return (void *)new + newoff;
}
-EXPORT_SYMBOL(__nf_ct_ext_add);
+EXPORT_SYMBOL(__nf_ct_ext_add_length);
static void update_alloc_size(struct nf_ct_ext_type *type)
{
u32 seq;
int dir = CTINFO2DIR(ctinfo);
unsigned int uninitialized_var(matchlen), uninitialized_var(matchoff);
- struct nf_ct_ftp_master *ct_ftp_info = &nfct_help(ct)->help.ct_ftp_info;
+ struct nf_ct_ftp_master *ct_ftp_info = nfct_help_data(ct);
struct nf_conntrack_expect *exp;
union nf_inet_addr *daddr;
struct nf_conntrack_man cmd = {};
}
static struct nf_conntrack_helper ftp[MAX_PORTS][2] __read_mostly;
-static char ftp_names[MAX_PORTS][2][sizeof("ftp-65535")] __read_mostly;
static const struct nf_conntrack_expect_policy ftp_exp_policy = {
.max_expected = 1,
static int __init nf_conntrack_ftp_init(void)
{
int i, j = -1, ret = 0;
- char *tmpname;
ftp_buffer = kmalloc(65536, GFP_KERNEL);
if (!ftp_buffer)
ftp[i][0].tuple.src.l3num = PF_INET;
ftp[i][1].tuple.src.l3num = PF_INET6;
for (j = 0; j < 2; j++) {
+ ftp[i][j].data_len = sizeof(struct nf_ct_ftp_master);
ftp[i][j].tuple.src.u.tcp.port = htons(ports[i]);
ftp[i][j].tuple.dst.protonum = IPPROTO_TCP;
ftp[i][j].expect_policy = &ftp_exp_policy;
ftp[i][j].me = THIS_MODULE;
ftp[i][j].help = help;
- tmpname = &ftp_names[i][j][0];
if (ports[i] == FTP_PORT)
- sprintf(tmpname, "ftp");
+ sprintf(ftp[i][j].name, "ftp");
else
- sprintf(tmpname, "ftp-%d", ports[i]);
- ftp[i][j].name = tmpname;
+ sprintf(ftp[i][j].name, "ftp-%d", ports[i]);
pr_debug("nf_ct_ftp: registering helper for pf: %d "
"port: %d\n",
struct nf_conn *ct, enum ip_conntrack_info ctinfo,
unsigned char **data, int *datalen, int *dataoff)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
const struct tcphdr *th;
struct tcphdr _tcph;
static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = {
.name = "H.245",
.me = THIS_MODULE,
+ .data_len = sizeof(struct nf_ct_h323_master),
.tuple.src.l3num = AF_UNSPEC,
.tuple.dst.protonum = IPPROTO_UDP,
.help = h245_help,
{
.name = "Q.931",
.me = THIS_MODULE,
+ .data_len = sizeof(struct nf_ct_h323_master),
.tuple.src.l3num = AF_INET,
.tuple.src.u.tcp.port = cpu_to_be16(Q931_PORT),
.tuple.dst.protonum = IPPROTO_TCP,
unsigned char **data,
TransportAddress *taddr, int count)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int ret = 0;
int i;
enum ip_conntrack_info ctinfo,
unsigned char **data, RegistrationRequest *rrq)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int ret;
typeof(set_ras_addr_hook) set_ras_addr;
enum ip_conntrack_info ctinfo,
unsigned char **data, RegistrationConfirm *rcf)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int ret;
struct nf_conntrack_expect *exp;
enum ip_conntrack_info ctinfo,
unsigned char **data, UnregistrationRequest *urq)
{
- struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
int ret;
typeof(set_sig_addr_hook) set_sig_addr;
enum ip_conntrack_info ctinfo,
unsigned char **data, AdmissionRequest *arq)
{
- const struct nf_ct_h323_master *info = &nfct_help(ct)->help.ct_h323_info;
+ const struct nf_ct_h323_master *info = nfct_help_data(ct);
int dir = CTINFO2DIR(ctinfo);
__be16 port;
union nf_inet_addr addr;
{
.name = "RAS",
.me = THIS_MODULE,
+ .data_len = sizeof(struct nf_ct_h323_master),
.tuple.src.l3num = AF_INET,
.tuple.src.u.udp.port = cpu_to_be16(RAS_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
{
.name = "RAS",
.me = THIS_MODULE,
+ .data_len = sizeof(struct nf_ct_h323_master),
.tuple.src.l3num = AF_INET6,
.tuple.src.u.udp.port = cpu_to_be16(RAS_PORT),
.tuple.dst.protonum = IPPROTO_UDP,
#include <net/netfilter/nf_conntrack_extend.h>
static DEFINE_MUTEX(nf_ct_helper_mutex);
-static struct hlist_head *nf_ct_helper_hash __read_mostly;
-static unsigned int nf_ct_helper_hsize __read_mostly;
+struct hlist_head *nf_ct_helper_hash __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ct_helper_hash);
+unsigned int nf_ct_helper_hsize __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ct_helper_hsize);
static unsigned int nf_ct_helper_count __read_mostly;
static bool nf_ct_auto_assign_helper __read_mostly = true;
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get);
-struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp)
+struct nf_conn_help *
+nf_ct_helper_ext_add(struct nf_conn *ct,
+ struct nf_conntrack_helper *helper, gfp_t gfp)
{
struct nf_conn_help *help;
- help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp);
+ help = nf_ct_ext_add_length(ct, NF_CT_EXT_HELPER,
+ helper->data_len, gfp);
if (help)
INIT_HLIST_HEAD(&help->expectations);
else
}
if (help == NULL) {
- help = nf_ct_helper_ext_add(ct, flags);
+ help = nf_ct_helper_ext_add(ct, helper, flags);
if (help == NULL) {
ret = -ENOMEM;
goto out;
}
} else {
- memset(&help->help, 0, sizeof(help->help));
+ /* We only allow helper re-assignment of the same sort since
+ * we cannot reallocate the helper extension area.
+ */
+ if (help->helper != helper) {
+ RCU_INIT_POINTER(help->helper, NULL);
+ goto out;
+ }
}
rcu_assign_pointer(help->helper, helper);
int nf_conntrack_helper_register(struct nf_conntrack_helper *me)
{
+ int ret = 0;
+ struct nf_conntrack_helper *cur;
+ struct hlist_node *n;
unsigned int h = helper_hash(&me->tuple);
BUG_ON(me->expect_policy == NULL);
BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1);
mutex_lock(&nf_ct_helper_mutex);
+ hlist_for_each_entry(cur, n, &nf_ct_helper_hash[h], hnode) {
+ if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 &&
+ cur->tuple.src.l3num == me->tuple.src.l3num &&
+ cur->tuple.dst.protonum == me->tuple.dst.protonum) {
+ ret = -EEXIST;
+ goto out;
+ }
+ }
hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]);
nf_ct_helper_count++;
+out:
mutex_unlock(&nf_ct_helper_mutex);
-
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(nf_conntrack_helper_register);
}
static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly;
-static char irc_names[MAX_PORTS][sizeof("irc-65535")] __read_mostly;
static struct nf_conntrack_expect_policy irc_exp_policy;
static void nf_conntrack_irc_fini(void);
static int __init nf_conntrack_irc_init(void)
{
int i, ret;
- char *tmpname;
if (max_dcc_channels < 1) {
printk(KERN_ERR "nf_ct_irc: max_dcc_channels must not be zero\n");
irc[i].me = THIS_MODULE;
irc[i].help = help;
- tmpname = &irc_names[i][0];
if (ports[i] == IRC_PORT)
- sprintf(tmpname, "irc");
+ sprintf(irc[i].name, "irc");
else
- sprintf(tmpname, "irc-%u", i);
- irc[i].name = tmpname;
+ sprintf(irc[i].name, "irc-%u", i);
ret = nf_conntrack_helper_register(&irc[i]);
if (ret) {
#ifdef CONFIG_NF_NAT_NEEDED
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_protocol.h>
+#include <net/netfilter/nf_nat_helper.h>
#endif
#include <linux/netfilter/nfnetlink.h>
};
static inline int
-ctnetlink_parse_help(const struct nlattr *attr, char **helper_name)
+ctnetlink_parse_help(const struct nlattr *attr, char **helper_name,
+ struct nlattr **helpinfo)
{
struct nlattr *tb[CTA_HELP_MAX+1];
*helper_name = nla_data(tb[CTA_HELP_NAME]);
+ if (tb[CTA_HELP_INFO])
+ *helpinfo = tb[CTA_HELP_INFO];
+
return 0;
}
struct nf_conntrack_helper *helper;
struct nf_conn_help *help = nfct_help(ct);
char *helpname = NULL;
+ struct nlattr *helpinfo = NULL;
int err;
/* don't change helper of sibling connections */
if (ct->master)
return -EBUSY;
- err = ctnetlink_parse_help(cda[CTA_HELP], &helpname);
+ err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo);
if (err < 0)
return err;
}
if (help) {
- if (help->helper == helper)
+ if (help->helper == helper) {
+ /* update private helper data if allowed. */
+ if (helper->from_nlattr && helpinfo)
+ helper->from_nlattr(helpinfo, ct);
return 0;
- if (help->helper)
+ } else
return -EBUSY;
- /* need to zero data of old helper */
- memset(&help->help, 0, sizeof(help->help));
- } else {
- /* we cannot set a helper for an existing conntrack */
- return -EOPNOTSUPP;
}
- rcu_assign_pointer(help->helper, helper);
-
- return 0;
+ /* we cannot set a helper for an existing conntrack */
+ return -EOPNOTSUPP;
}
static inline int
rcu_read_lock();
if (cda[CTA_HELP]) {
char *helpname = NULL;
-
- err = ctnetlink_parse_help(cda[CTA_HELP], &helpname);
+ struct nlattr *helpinfo = NULL;
+
+ err = ctnetlink_parse_help(cda[CTA_HELP], &helpname, &helpinfo);
if (err < 0)
goto err2;
} else {
struct nf_conn_help *help;
- help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
+ help = nf_ct_helper_ext_add(ct, helper, GFP_ATOMIC);
if (help == NULL) {
err = -ENOMEM;
goto err2;
}
+ /* set private helper data if allowed. */
+ if (helper->from_nlattr && helpinfo)
+ helper->from_nlattr(helpinfo, ct);
/* not in hash table yet so not strictly necessary */
RCU_INIT_POINTER(help->helper, helper);
return err;
}
+#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT
+static size_t
+ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
+{
+ return 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */
+ + 3 * nla_total_size(0) /* CTA_TUPLE_IP */
+ + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */
+ + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
+ + nla_total_size(0) /* CTA_PROTOINFO */
+ + nla_total_size(0) /* CTA_HELP */
+ + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
+ + ctnetlink_secctx_size(ct)
+#ifdef CONFIG_NF_NAT_NEEDED
+ + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+ + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
+#endif
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
+#endif
+ + ctnetlink_proto_size(ct)
+ ;
+}
+
+static int
+ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct)
+{
+ struct nlattr *nest_parms;
+
+ rcu_read_lock();
+ nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
+ if (!nest_parms)
+ goto nla_put_failure;
+ if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+ goto nla_put_failure;
+ nla_nest_end(skb, nest_parms);
+
+ nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
+ if (!nest_parms)
+ goto nla_put_failure;
+ if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
+ goto nla_put_failure;
+ nla_nest_end(skb, nest_parms);
+
+ if (nf_ct_zone(ct)) {
+ if (nla_put_be16(skb, CTA_ZONE, htons(nf_ct_zone(ct))))
+ goto nla_put_failure;
+ }
+
+ if (ctnetlink_dump_id(skb, ct) < 0)
+ goto nla_put_failure;
+
+ if (ctnetlink_dump_status(skb, ct) < 0)
+ goto nla_put_failure;
+
+ if (ctnetlink_dump_timeout(skb, ct) < 0)
+ goto nla_put_failure;
+
+ if (ctnetlink_dump_protoinfo(skb, ct) < 0)
+ goto nla_put_failure;
+
+ if (ctnetlink_dump_helpinfo(skb, ct) < 0)
+ goto nla_put_failure;
+
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+ if (ct->secmark && ctnetlink_dump_secctx(skb, ct) < 0)
+ goto nla_put_failure;
+#endif
+ if (ct->master && ctnetlink_dump_master(skb, ct) < 0)
+ goto nla_put_failure;
+
+ if ((ct->status & IPS_SEQ_ADJUST) &&
+ ctnetlink_dump_nat_seq_adj(skb, ct) < 0)
+ goto nla_put_failure;
+
+#ifdef CONFIG_NF_CONNTRACK_MARK
+ if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0)
+ goto nla_put_failure;
+#endif
+ rcu_read_unlock();
+ return 0;
+
+nla_put_failure:
+ rcu_read_unlock();
+ return -ENOSPC;
+}
+
+static int
+ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct)
+{
+ int err;
+
+ if (cda[CTA_TIMEOUT]) {
+ err = ctnetlink_change_timeout(ct, cda);
+ if (err < 0)
+ return err;
+ }
+ if (cda[CTA_STATUS]) {
+ err = ctnetlink_change_status(ct, cda);
+ if (err < 0)
+ return err;
+ }
+ if (cda[CTA_HELP]) {
+ err = ctnetlink_change_helper(ct, cda);
+ if (err < 0)
+ return err;
+ }
+#if defined(CONFIG_NF_CONNTRACK_MARK)
+ if (cda[CTA_MARK])
+ ct->mark = ntohl(nla_get_be32(cda[CTA_MARK]));
+#endif
+ return 0;
+}
+
+static int
+ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct)
+{
+ struct nlattr *cda[CTA_MAX+1];
+
+ nla_parse_nested(cda, CTA_MAX, attr, ct_nla_policy);
+
+ return ctnetlink_nfqueue_parse_ct((const struct nlattr **)cda, ct);
+}
+
+static struct nfq_ct_hook ctnetlink_nfqueue_hook = {
+ .build_size = ctnetlink_nfqueue_build_size,
+ .build = ctnetlink_nfqueue_build,
+ .parse = ctnetlink_nfqueue_parse,
+#ifdef CONFIG_NF_NAT_NEEDED
+ .seq_adjust = nf_nat_tcp_seq_adjust,
+#endif
+};
+#endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */
+
/***********************************************************************
* EXPECT
***********************************************************************/
pr_err("ctnetlink_init: cannot register pernet operations\n");
goto err_unreg_exp_subsys;
}
-
+#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT
+ /* setup interaction between nf_queue and nf_conntrack_netlink. */
+ RCU_INIT_POINTER(nfq_ct_hook, &ctnetlink_nfqueue_hook);
+#endif
return 0;
err_unreg_exp_subsys:
unregister_pernet_subsys(&ctnetlink_net_ops);
nfnetlink_subsys_unregister(&ctnl_exp_subsys);
nfnetlink_subsys_unregister(&ctnl_subsys);
+#ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT
+ RCU_INIT_POINTER(nfq_ct_hook, NULL);
+#endif
}
module_init(ctnetlink_init);
static void pptp_destroy_siblings(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
- const struct nf_conn_help *help = nfct_help(ct);
+ const struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
struct nf_conntrack_tuple t;
nf_ct_gre_keymap_destroy(ct);
/* try original (pns->pac) tuple */
memcpy(&t, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, sizeof(t));
t.dst.protonum = IPPROTO_GRE;
- t.src.u.gre.key = help->help.ct_pptp_info.pns_call_id;
- t.dst.u.gre.key = help->help.ct_pptp_info.pac_call_id;
+ t.src.u.gre.key = ct_pptp_info->pns_call_id;
+ t.dst.u.gre.key = ct_pptp_info->pac_call_id;
if (!destroy_sibling_or_exp(net, ct, &t))
pr_debug("failed to timeout original pns->pac ct/exp\n");
/* try reply (pac->pns) tuple */
memcpy(&t, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, sizeof(t));
t.dst.protonum = IPPROTO_GRE;
- t.src.u.gre.key = help->help.ct_pptp_info.pac_call_id;
- t.dst.u.gre.key = help->help.ct_pptp_info.pns_call_id;
+ t.src.u.gre.key = ct_pptp_info->pac_call_id;
+ t.dst.u.gre.key = ct_pptp_info->pns_call_id;
if (!destroy_sibling_or_exp(net, ct, &t))
pr_debug("failed to timeout reply pac->pns ct/exp\n");
}
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
- struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info;
+ struct nf_ct_pptp_master *info = nfct_help_data(ct);
u_int16_t msg;
__be16 cid = 0, pcid = 0;
typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound;
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
- struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info;
+ struct nf_ct_pptp_master *info = nfct_help_data(ct);
u_int16_t msg;
__be16 cid = 0, pcid = 0;
typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound;
{
int dir = CTINFO2DIR(ctinfo);
- const struct nf_ct_pptp_master *info = &nfct_help(ct)->help.ct_pptp_info;
+ const struct nf_ct_pptp_master *info = nfct_help_data(ct);
const struct tcphdr *tcph;
struct tcphdr _tcph;
const struct pptp_pkt_hdr *pptph;
static struct nf_conntrack_helper pptp __read_mostly = {
.name = "pptp",
.me = THIS_MODULE,
+ .data_len = sizeof(struct nf_ct_pptp_master),
.tuple.src.l3num = AF_INET,
.tuple.src.u.tcp.port = cpu_to_be16(PPTP_CONTROL_PORT),
.tuple.dst.protonum = IPPROTO_TCP,
{
struct net *net = nf_ct_net(ct);
struct netns_proto_gre *net_gre = gre_pernet(net);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
struct nf_ct_gre_keymap **kmp, *km;
- kmp = &help->help.ct_pptp_info.keymap[dir];
+ kmp = &ct_pptp_info->keymap[dir];
if (*kmp) {
/* check whether it's a retransmission */
read_lock_bh(&net_gre->keymap_lock);
{
struct net *net = nf_ct_net(ct);
struct netns_proto_gre *net_gre = gre_pernet(net);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct);
enum ip_conntrack_dir dir;
pr_debug("entering for ct %p\n", ct);
write_lock_bh(&net_gre->keymap_lock);
for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) {
- if (help->help.ct_pptp_info.keymap[dir]) {
+ if (ct_pptp_info->keymap[dir]) {
pr_debug("removing %p from list\n",
- help->help.ct_pptp_info.keymap[dir]);
- list_del(&help->help.ct_pptp_info.keymap[dir]->list);
- kfree(help->help.ct_pptp_info.keymap[dir]);
- help->help.ct_pptp_info.keymap[dir] = NULL;
+ ct_pptp_info->keymap[dir]);
+ list_del(&ct_pptp_info->keymap[dir]->list);
+ kfree(ct_pptp_info->keymap[dir]);
+ ct_pptp_info->keymap[dir] = NULL;
}
}
write_unlock_bh(&net_gre->keymap_lock);
void *sb_ptr;
int ret = NF_ACCEPT;
int dir = CTINFO2DIR(ctinfo);
- struct nf_ct_sane_master *ct_sane_info;
+ struct nf_ct_sane_master *ct_sane_info = nfct_help_data(ct);
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
struct sane_request *req;
struct sane_reply_net_start *reply;
- ct_sane_info = &nfct_help(ct)->help.ct_sane_info;
/* Until there's been traffic both ways, don't look in packets. */
if (ctinfo != IP_CT_ESTABLISHED &&
ctinfo != IP_CT_ESTABLISHED_REPLY)
}
static struct nf_conntrack_helper sane[MAX_PORTS][2] __read_mostly;
-static char sane_names[MAX_PORTS][2][sizeof("sane-65535")] __read_mostly;
static const struct nf_conntrack_expect_policy sane_exp_policy = {
.max_expected = 1,
static int __init nf_conntrack_sane_init(void)
{
int i, j = -1, ret = 0;
- char *tmpname;
sane_buffer = kmalloc(65536, GFP_KERNEL);
if (!sane_buffer)
sane[i][0].tuple.src.l3num = PF_INET;
sane[i][1].tuple.src.l3num = PF_INET6;
for (j = 0; j < 2; j++) {
+ sane[i][j].data_len = sizeof(struct nf_ct_sane_master);
sane[i][j].tuple.src.u.tcp.port = htons(ports[i]);
sane[i][j].tuple.dst.protonum = IPPROTO_TCP;
sane[i][j].expect_policy = &sane_exp_policy;
sane[i][j].me = THIS_MODULE;
sane[i][j].help = help;
- tmpname = &sane_names[i][j][0];
if (ports[i] == SANE_PORT)
- sprintf(tmpname, "sane");
+ sprintf(sane[i][j].name, "sane");
else
- sprintf(tmpname, "sane-%d", ports[i]);
- sane[i][j].name = tmpname;
+ sprintf(sane[i][j].name, "sane-%d", ports[i]);
pr_debug("nf_ct_sane: registering helper for pf: %d "
"port: %d\n",
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
if ((code >= 100 && code <= 199) ||
(code >= 200 && code <= 299))
return process_sdp(skb, dataoff, dptr, datalen, cseq);
- else if (help->help.ct_sip_info.invite_cseq == cseq)
+ else if (ct_sip_info->invite_cseq == cseq)
flush_expectations(ct, true);
return NF_ACCEPT;
}
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
if ((code >= 100 && code <= 199) ||
(code >= 200 && code <= 299))
return process_sdp(skb, dataoff, dptr, datalen, cseq);
- else if (help->help.ct_sip_info.invite_cseq == cseq)
+ else if (ct_sip_info->invite_cseq == cseq)
flush_expectations(ct, true);
return NF_ACCEPT;
}
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
if ((code >= 100 && code <= 199) ||
(code >= 200 && code <= 299))
return process_sdp(skb, dataoff, dptr, datalen, cseq);
- else if (help->help.ct_sip_info.invite_cseq == cseq)
+ else if (ct_sip_info->invite_cseq == cseq)
flush_expectations(ct, true);
return NF_ACCEPT;
}
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
unsigned int ret;
flush_expectations(ct, true);
ret = process_sdp(skb, dataoff, dptr, datalen, cseq);
if (ret == NF_ACCEPT)
- help->help.ct_sip_info.invite_cseq = cseq;
+ ct_sip_info->invite_cseq = cseq;
return ret;
}
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
unsigned int matchoff, matchlen;
struct nf_conntrack_expect *exp;
store_cseq:
if (ret == NF_ACCEPT)
- help->help.ct_sip_info.register_cseq = cseq;
+ ct_sip_info->register_cseq = cseq;
return ret;
}
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- struct nf_conn_help *help = nfct_help(ct);
+ struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct);
enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
union nf_inet_addr addr;
__be16 port;
* responses, so we store the sequence number of the last valid
* request and compare it here.
*/
- if (help->help.ct_sip_info.register_cseq != cseq)
+ if (ct_sip_info->register_cseq != cseq)
return NF_ACCEPT;
if (code >= 100 && code <= 199)
static int __init nf_conntrack_sip_init(void)
{
int i, j, ret;
- char *tmpname;
if (ports_c == 0)
ports[ports_c++] = SIP_PORT;
sip[i][3].help = sip_help_tcp;
for (j = 0; j < ARRAY_SIZE(sip[i]); j++) {
+ sip[i][j].data_len = sizeof(struct nf_ct_sip_master);
sip[i][j].tuple.src.u.udp.port = htons(ports[i]);
sip[i][j].expect_policy = sip_exp_policy;
sip[i][j].expect_class_max = SIP_EXPECT_MAX;
sip[i][j].me = THIS_MODULE;
- tmpname = &sip_names[i][j][0];
if (ports[i] == SIP_PORT)
- sprintf(tmpname, "sip");
+ sprintf(sip_names[i][j], "sip");
else
- sprintf(tmpname, "sip-%u", i);
- sip[i][j].name = tmpname;
+ sprintf(sip_names[i][j], "sip-%u", i);
pr_debug("port #%u: %u\n", i, ports[i]);
}
static struct nf_conntrack_helper tftp[MAX_PORTS][2] __read_mostly;
-static char tftp_names[MAX_PORTS][2][sizeof("tftp-65535")] __read_mostly;
static const struct nf_conntrack_expect_policy tftp_exp_policy = {
.max_expected = 1,
static int __init nf_conntrack_tftp_init(void)
{
int i, j, ret;
- char *tmpname;
if (ports_c == 0)
ports[ports_c++] = TFTP_PORT;
tftp[i][j].me = THIS_MODULE;
tftp[i][j].help = tftp_help;
- tmpname = &tftp_names[i][j][0];
if (ports[i] == TFTP_PORT)
- sprintf(tmpname, "tftp");
+ sprintf(tftp[i][j].name, "tftp");
else
- sprintf(tmpname, "tftp-%u", i);
- tftp[i][j].name = tmpname;
+ sprintf(tftp[i][j].name, "tftp-%u", i);
ret = nf_conntrack_helper_register(&tftp[i][j]);
if (ret) {
--- /dev/null
+/*
+ * (C) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation (or any later at your option).
+ *
+ * This software has been sponsored by Vyatta Inc. <http://www.vyatta.com>
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <net/netlink.h>
+#include <net/sock.h>
+
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+#include <linux/netfilter/nfnetlink_cthelper.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
+
+static int
+nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
+ struct nf_conn *ct, enum ip_conntrack_info ctinfo)
+{
+ const struct nf_conn_help *help;
+ struct nf_conntrack_helper *helper;
+
+ help = nfct_help(ct);
+ if (help == NULL)
+ return NF_DROP;
+
+ /* rcu_read_lock()ed by nf_hook_slow */
+ helper = rcu_dereference(help->helper);
+ if (helper == NULL)
+ return NF_DROP;
+
+ /* This is an user-space helper not yet configured, skip. */
+ if ((helper->flags &
+ (NF_CT_HELPER_F_USERSPACE | NF_CT_HELPER_F_CONFIGURED)) ==
+ NF_CT_HELPER_F_USERSPACE)
+ return NF_ACCEPT;
+
+ /* If the user-space helper is not available, don't block traffic. */
+ return NF_QUEUE_NR(helper->queue_num) | NF_VERDICT_FLAG_QUEUE_BYPASS;
+}
+
+static const struct nla_policy nfnl_cthelper_tuple_pol[NFCTH_TUPLE_MAX+1] = {
+ [NFCTH_TUPLE_L3PROTONUM] = { .type = NLA_U16, },
+ [NFCTH_TUPLE_L4PROTONUM] = { .type = NLA_U8, },
+};
+
+static int
+nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_TUPLE_MAX+1];
+
+ nla_parse_nested(tb, NFCTH_TUPLE_MAX, attr, nfnl_cthelper_tuple_pol);
+
+ if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
+ return -EINVAL;
+
+ tuple->src.l3num = ntohs(nla_get_u16(tb[NFCTH_TUPLE_L3PROTONUM]));
+ tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
+
+ return 0;
+}
+
+static int
+nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
+{
+ const struct nf_conn_help *help = nfct_help(ct);
+
+ if (help->helper->data_len == 0)
+ return -EINVAL;
+
+ memcpy(&help->data, nla_data(attr), help->helper->data_len);
+ return 0;
+}
+
+static int
+nfnl_cthelper_to_nlattr(struct sk_buff *skb, const struct nf_conn *ct)
+{
+ const struct nf_conn_help *help = nfct_help(ct);
+
+ if (help->helper->data_len &&
+ nla_put(skb, CTA_HELP_INFO, help->helper->data_len, &help->data))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -ENOSPC;
+}
+
+static const struct nla_policy nfnl_cthelper_expect_pol[NFCTH_POLICY_MAX+1] = {
+ [NFCTH_POLICY_NAME] = { .type = NLA_NUL_STRING,
+ .len = NF_CT_HELPER_NAME_LEN-1 },
+ [NFCTH_POLICY_EXPECT_MAX] = { .type = NLA_U32, },
+ [NFCTH_POLICY_EXPECT_TIMEOUT] = { .type = NLA_U32, },
+};
+
+static int
+nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_MAX+1];
+
+ nla_parse_nested(tb, NFCTH_POLICY_MAX, attr, nfnl_cthelper_expect_pol);
+
+ if (!tb[NFCTH_POLICY_NAME] ||
+ !tb[NFCTH_POLICY_EXPECT_MAX] ||
+ !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
+ return -EINVAL;
+
+ strncpy(expect_policy->name,
+ nla_data(tb[NFCTH_POLICY_NAME]), NF_CT_HELPER_NAME_LEN);
+ expect_policy->max_expected =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+ expect_policy->timeout =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
+
+ return 0;
+}
+
+static const struct nla_policy
+nfnl_cthelper_expect_policy_set[NFCTH_POLICY_SET_MAX+1] = {
+ [NFCTH_POLICY_SET_NUM] = { .type = NLA_U32, },
+};
+
+static int
+nfnl_cthelper_parse_expect_policy(struct nf_conntrack_helper *helper,
+ const struct nlattr *attr)
+{
+ int i, ret;
+ struct nf_conntrack_expect_policy *expect_policy;
+ struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
+
+ nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
+ nfnl_cthelper_expect_policy_set);
+
+ if (!tb[NFCTH_POLICY_SET_NUM])
+ return -EINVAL;
+
+ helper->expect_class_max =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+
+ if (helper->expect_class_max != 0 &&
+ helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES)
+ return -EOVERFLOW;
+
+ expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) *
+ helper->expect_class_max, GFP_KERNEL);
+ if (expect_policy == NULL)
+ return -ENOMEM;
+
+ for (i=0; i<helper->expect_class_max; i++) {
+ if (!tb[NFCTH_POLICY_SET+i])
+ goto err;
+
+ ret = nfnl_cthelper_expect_policy(&expect_policy[i],
+ tb[NFCTH_POLICY_SET+i]);
+ if (ret < 0)
+ goto err;
+ }
+ helper->expect_policy = expect_policy;
+ return 0;
+err:
+ kfree(expect_policy);
+ return -EINVAL;
+}
+
+static int
+nfnl_cthelper_create(const struct nlattr * const tb[],
+ struct nf_conntrack_tuple *tuple)
+{
+ struct nf_conntrack_helper *helper;
+ int ret;
+
+ if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
+ return -EINVAL;
+
+ helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL);
+ if (helper == NULL)
+ return -ENOMEM;
+
+ ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
+ if (ret < 0)
+ goto err;
+
+ strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
+ helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
+ helper->flags |= NF_CT_HELPER_F_USERSPACE;
+ memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple));
+
+ helper->me = THIS_MODULE;
+ helper->help = nfnl_userspace_cthelper;
+ helper->from_nlattr = nfnl_cthelper_from_nlattr;
+ helper->to_nlattr = nfnl_cthelper_to_nlattr;
+
+ /* Default to queue number zero, this can be updated at any time. */
+ if (tb[NFCTH_QUEUE_NUM])
+ helper->queue_num = ntohl(nla_get_be32(tb[NFCTH_QUEUE_NUM]));
+
+ if (tb[NFCTH_STATUS]) {
+ int status = ntohl(nla_get_be32(tb[NFCTH_STATUS]));
+
+ switch(status) {
+ case NFCT_HELPER_STATUS_ENABLED:
+ helper->flags |= NF_CT_HELPER_F_CONFIGURED;
+ break;
+ case NFCT_HELPER_STATUS_DISABLED:
+ helper->flags &= ~NF_CT_HELPER_F_CONFIGURED;
+ break;
+ }
+ }
+
+ ret = nf_conntrack_helper_register(helper);
+ if (ret < 0)
+ goto err;
+
+ return 0;
+err:
+ kfree(helper);
+ return ret;
+}
+
+static int
+nfnl_cthelper_update(const struct nlattr * const tb[],
+ struct nf_conntrack_helper *helper)
+{
+ int ret;
+
+ if (tb[NFCTH_PRIV_DATA_LEN])
+ return -EBUSY;
+
+ if (tb[NFCTH_POLICY]) {
+ ret = nfnl_cthelper_parse_expect_policy(helper,
+ tb[NFCTH_POLICY]);
+ if (ret < 0)
+ return ret;
+ }
+ if (tb[NFCTH_QUEUE_NUM])
+ helper->queue_num = ntohl(nla_get_be32(tb[NFCTH_QUEUE_NUM]));
+
+ if (tb[NFCTH_STATUS]) {
+ int status = ntohl(nla_get_be32(tb[NFCTH_STATUS]));
+
+ switch(status) {
+ case NFCT_HELPER_STATUS_ENABLED:
+ helper->flags |= NF_CT_HELPER_F_CONFIGURED;
+ break;
+ case NFCT_HELPER_STATUS_DISABLED:
+ helper->flags &= ~NF_CT_HELPER_F_CONFIGURED;
+ break;
+ }
+ }
+ return 0;
+}
+
+static int
+nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ const char *helper_name;
+ struct nf_conntrack_helper *cur, *helper = NULL;
+ struct nf_conntrack_tuple tuple;
+ struct hlist_node *n;
+ int ret = 0, i;
+
+ if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
+ return -EINVAL;
+
+ helper_name = nla_data(tb[NFCTH_NAME]);
+
+ ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]);
+ if (ret < 0)
+ return ret;
+
+ rcu_read_lock();
+ for (i = 0; i < nf_ct_helper_hsize && !helper; i++) {
+ hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) {
+
+ /* skip non-userspace conntrack helpers. */
+ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+ continue;
+
+ if (strncmp(cur->name, helper_name,
+ NF_CT_HELPER_NAME_LEN) != 0)
+ continue;
+
+ if ((tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
+
+ if (nlh->nlmsg_flags & NLM_F_EXCL) {
+ ret = -EEXIST;
+ goto err;
+ }
+ helper = cur;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ if (helper == NULL)
+ ret = nfnl_cthelper_create(tb, &tuple);
+ else
+ ret = nfnl_cthelper_update(tb, helper);
+
+ return ret;
+err:
+ rcu_read_unlock();
+ return ret;
+}
+
+static int
+nfnl_cthelper_dump_tuple(struct sk_buff *skb,
+ struct nf_conntrack_helper *helper)
+{
+ struct nlattr *nest_parms;
+
+ nest_parms = nla_nest_start(skb, NFCTH_TUPLE | NLA_F_NESTED);
+ if (nest_parms == NULL)
+ goto nla_put_failure;
+
+ if (nla_put_be16(skb, NFCTH_TUPLE_L3PROTONUM,
+ htons(helper->tuple.src.l3num)))
+ goto nla_put_failure;
+
+ if (nla_put_u8(skb, NFCTH_TUPLE_L4PROTONUM, helper->tuple.dst.protonum))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest_parms);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static int
+nfnl_cthelper_dump_policy(struct sk_buff *skb,
+ struct nf_conntrack_helper *helper)
+{
+ int i;
+ struct nlattr *nest_parms1, *nest_parms2;
+
+ nest_parms1 = nla_nest_start(skb, NFCTH_POLICY | NLA_F_NESTED);
+ if (nest_parms1 == NULL)
+ goto nla_put_failure;
+
+ if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM,
+ htonl(helper->expect_class_max)))
+ goto nla_put_failure;
+
+ for (i=0; i<helper->expect_class_max; i++) {
+ nest_parms2 = nla_nest_start(skb,
+ (NFCTH_POLICY_SET+i) | NLA_F_NESTED);
+ if (nest_parms2 == NULL)
+ goto nla_put_failure;
+
+ if (nla_put_string(skb, NFCTH_POLICY_NAME,
+ helper->expect_policy[i].name))
+ goto nla_put_failure;
+
+ if (nla_put_be32(skb, NFCTH_POLICY_EXPECT_MAX,
+ htonl(helper->expect_policy[i].max_expected)))
+ goto nla_put_failure;
+
+ if (nla_put_be32(skb, NFCTH_POLICY_EXPECT_TIMEOUT,
+ htonl(helper->expect_policy[i].timeout)))
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest_parms2);
+ }
+ nla_nest_end(skb, nest_parms1);
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+static int
+nfnl_cthelper_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type,
+ int event, struct nf_conntrack_helper *helper)
+{
+ struct nlmsghdr *nlh;
+ struct nfgenmsg *nfmsg;
+ unsigned int flags = pid ? NLM_F_MULTI : 0;
+ int status;
+
+ event |= NFNL_SUBSYS_CTHELPER << 8;
+ nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+ if (nlh == NULL)
+ goto nlmsg_failure;
+
+ nfmsg = nlmsg_data(nlh);
+ nfmsg->nfgen_family = AF_UNSPEC;
+ nfmsg->version = NFNETLINK_V0;
+ nfmsg->res_id = 0;
+
+ if (nla_put_string(skb, NFCTH_NAME, helper->name))
+ goto nla_put_failure;
+
+ if (nla_put_be32(skb, NFCTH_QUEUE_NUM, htonl(helper->queue_num)))
+ goto nla_put_failure;
+
+ if (nfnl_cthelper_dump_tuple(skb, helper) < 0)
+ goto nla_put_failure;
+
+ if (nfnl_cthelper_dump_policy(skb, helper) < 0)
+ goto nla_put_failure;
+
+ if (nla_put_be32(skb, NFCTH_PRIV_DATA_LEN, htonl(helper->data_len)))
+ goto nla_put_failure;
+
+ if (helper->flags & NF_CT_HELPER_F_CONFIGURED)
+ status = NFCT_HELPER_STATUS_ENABLED;
+ else
+ status = NFCT_HELPER_STATUS_DISABLED;
+
+ if (nla_put_be32(skb, NFCTH_STATUS, htonl(status)))
+ goto nla_put_failure;
+
+ nlmsg_end(skb, nlh);
+ return skb->len;
+
+nlmsg_failure:
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -1;
+}
+
+static int
+nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct nf_conntrack_helper *cur, *last;
+ struct hlist_node *n;
+
+ rcu_read_lock();
+ last = (struct nf_conntrack_helper *)cb->args[1];
+ for (; cb->args[0] < nf_ct_helper_hsize; cb->args[0]++) {
+restart:
+ hlist_for_each_entry_rcu(cur, n,
+ &nf_ct_helper_hash[cb->args[0]], hnode) {
+
+ /* skip non-userspace conntrack helpers. */
+ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+ continue;
+
+ if (cb->args[1]) {
+ if (cur != last)
+ continue;
+ cb->args[1] = 0;
+ }
+ if (nfnl_cthelper_fill_info(skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
+ NFNL_MSG_CTHELPER_NEW, cur) < 0) {
+ cb->args[1] = (unsigned long)cur;
+ goto out;
+ }
+ }
+ }
+ if (cb->args[1]) {
+ cb->args[1] = 0;
+ goto restart;
+ }
+out:
+ rcu_read_unlock();
+ return skb->len;
+}
+
+static int
+nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ int ret = -ENOENT, i;
+ struct nf_conntrack_helper *cur;
+ struct hlist_node *n;
+ struct sk_buff *skb2;
+ char *helper_name = NULL;
+ struct nf_conntrack_tuple tuple;
+ bool tuple_set = false;
+
+ if (nlh->nlmsg_flags & NLM_F_DUMP) {
+ struct netlink_dump_control c = {
+ .dump = nfnl_cthelper_dump_table,
+ };
+ return netlink_dump_start(nfnl, skb, nlh, &c);
+ }
+
+ if (tb[NFCTH_NAME])
+ helper_name = nla_data(tb[NFCTH_NAME]);
+
+ if (tb[NFCTH_TUPLE]) {
+ ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]);
+ if (ret < 0)
+ return ret;
+
+ tuple_set = true;
+ }
+
+ for (i = 0; i < nf_ct_helper_hsize; i++) {
+ hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) {
+
+ /* skip non-userspace conntrack helpers. */
+ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+ continue;
+
+ if (helper_name && strncmp(cur->name, helper_name,
+ NF_CT_HELPER_NAME_LEN) != 0) {
+ continue;
+ }
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
+
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).pid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ NFNL_MSG_CTHELPER_NEW, cur);
+ if (ret <= 0) {
+ kfree_skb(skb2);
+ break;
+ }
+
+ ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid,
+ MSG_DONTWAIT);
+ if (ret > 0)
+ ret = 0;
+
+ /* this avoids a loop in nfnetlink. */
+ return ret == -EAGAIN ? -ENOBUFS : ret;
+ }
+ }
+ return ret;
+}
+
+static int
+nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb,
+ const struct nlmsghdr *nlh, const struct nlattr * const tb[])
+{
+ char *helper_name = NULL;
+ struct nf_conntrack_helper *cur;
+ struct hlist_node *n, *tmp;
+ struct nf_conntrack_tuple tuple;
+ bool tuple_set = false, found = false;
+ int i, j = 0, ret;
+
+ if (tb[NFCTH_NAME])
+ helper_name = nla_data(tb[NFCTH_NAME]);
+
+ if (tb[NFCTH_TUPLE]) {
+ ret = nfnl_cthelper_parse_tuple(&tuple, tb[NFCTH_TUPLE]);
+ if (ret < 0)
+ return ret;
+
+ tuple_set = true;
+ }
+
+ for (i = 0; i < nf_ct_helper_hsize; i++) {
+ hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i],
+ hnode) {
+ /* skip non-userspace conntrack helpers. */
+ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+ continue;
+
+ j++;
+
+ if (helper_name && strncmp(cur->name, helper_name,
+ NF_CT_HELPER_NAME_LEN) != 0) {
+ continue;
+ }
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
+
+ found = true;
+ nf_conntrack_helper_unregister(cur);
+ }
+ }
+ /* Make sure we return success if we flush and there is no helpers */
+ return (found || j == 0) ? 0 : -ENOENT;
+}
+
+static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = {
+ [NFCTH_NAME] = { .type = NLA_NUL_STRING,
+ .len = NF_CT_HELPER_NAME_LEN-1 },
+ [NFCTH_QUEUE_NUM] = { .type = NLA_U32, },
+};
+
+static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = {
+ [NFNL_MSG_CTHELPER_NEW] = { .call = nfnl_cthelper_new,
+ .attr_count = NFCTH_MAX,
+ .policy = nfnl_cthelper_policy },
+ [NFNL_MSG_CTHELPER_GET] = { .call = nfnl_cthelper_get,
+ .attr_count = NFCTH_MAX,
+ .policy = nfnl_cthelper_policy },
+ [NFNL_MSG_CTHELPER_DEL] = { .call = nfnl_cthelper_del,
+ .attr_count = NFCTH_MAX,
+ .policy = nfnl_cthelper_policy },
+};
+
+static const struct nfnetlink_subsystem nfnl_cthelper_subsys = {
+ .name = "cthelper",
+ .subsys_id = NFNL_SUBSYS_CTHELPER,
+ .cb_count = NFNL_MSG_CTHELPER_MAX,
+ .cb = nfnl_cthelper_cb,
+};
+
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTHELPER);
+
+static int __init nfnl_cthelper_init(void)
+{
+ int ret;
+
+ ret = nfnetlink_subsys_register(&nfnl_cthelper_subsys);
+ if (ret < 0) {
+ pr_err("nfnl_cthelper: cannot register with nfnetlink.\n");
+ goto err_out;
+ }
+ return 0;
+err_out:
+ return ret;
+}
+
+static void __exit nfnl_cthelper_exit(void)
+{
+ struct nf_conntrack_helper *cur;
+ struct hlist_node *n, *tmp;
+ int i;
+
+ nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
+
+ for (i=0; i<nf_ct_helper_hsize; i++) {
+ hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i],
+ hnode) {
+ /* skip non-userspace conntrack helpers. */
+ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
+ continue;
+
+ nf_conntrack_helper_unregister(cur);
+ }
+ }
+}
+
+module_init(nfnl_cthelper_init);
+module_exit(nfnl_cthelper_exit);
#include <linux/list.h>
#include <net/sock.h>
#include <net/netfilter/nf_queue.h>
+#include <net/netfilter/nfnetlink_queue.h>
#include <linux/atomic.h>
struct sk_buff *entskb = entry->skb;
struct net_device *indev;
struct net_device *outdev;
+ struct nf_conn *ct = NULL;
+ enum ip_conntrack_info uninitialized_var(ctinfo);
size = NLMSG_SPACE(sizeof(struct nfgenmsg))
+ nla_total_size(sizeof(struct nfqnl_msg_packet_hdr))
break;
}
+ if (queue->flags & NFQA_CFG_F_CONNTRACK)
+ ct = nfqnl_ct_get(entskb, &size, &ctinfo);
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
BUG();
}
+ if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
+ goto nla_put_failure;
+
nlh->nlmsg_len = skb->tail - old_tail;
return skb;
}
static int
-nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e)
+nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
{
struct sk_buff *nskb;
- int diff;
- diff = data_len - e->skb->len;
if (diff < 0) {
if (pskb_trim(e->skb, data_len))
return -ENOMEM;
[NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) },
[NFQA_MARK] = { .type = NLA_U32 },
[NFQA_PAYLOAD] = { .type = NLA_UNSPEC },
+ [NFQA_CT] = { .type = NLA_UNSPEC },
};
static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = {
struct nfqnl_instance *queue;
unsigned int verdict;
struct nf_queue_entry *entry;
+ enum ip_conntrack_info uninitialized_var(ctinfo);
+ struct nf_conn *ct = NULL;
queue = instance_lookup(queue_num);
if (!queue)
if (entry == NULL)
return -ENOENT;
+ rcu_read_lock();
+ if (nfqa[NFQA_CT] && (queue->flags & NFQA_CFG_F_CONNTRACK))
+ ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo);
+
if (nfqa[NFQA_PAYLOAD]) {
+ u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]);
+ int diff = payload_len - entry->skb->len;
+
if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]),
- nla_len(nfqa[NFQA_PAYLOAD]), entry) < 0)
+ payload_len, entry, diff) < 0)
verdict = NF_DROP;
+
+ if (ct)
+ nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff);
}
+ rcu_read_unlock();
if (nfqa[NFQA_MARK])
entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));
--- /dev/null
+/*
+ * (C) 2012 by Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/skbuff.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_queue.h>
+#include <net/netfilter/nf_conntrack.h>
+
+struct nf_conn *nfqnl_ct_get(struct sk_buff *entskb, size_t *size,
+ enum ip_conntrack_info *ctinfo)
+{
+ struct nfq_ct_hook *nfq_ct;
+ struct nf_conn *ct;
+
+ /* rcu_read_lock()ed by __nf_queue already. */
+ nfq_ct = rcu_dereference(nfq_ct_hook);
+ if (nfq_ct == NULL)
+ return NULL;
+
+ ct = nf_ct_get(entskb, ctinfo);
+ if (ct) {
+ if (!nf_ct_is_untracked(ct))
+ *size += nfq_ct->build_size(ct);
+ else
+ ct = NULL;
+ }
+ return ct;
+}
+
+struct nf_conn *
+nfqnl_ct_parse(const struct sk_buff *skb, const struct nlattr *attr,
+ enum ip_conntrack_info *ctinfo)
+{
+ struct nfq_ct_hook *nfq_ct;
+ struct nf_conn *ct;
+
+ /* rcu_read_lock()ed by __nf_queue already. */
+ nfq_ct = rcu_dereference(nfq_ct_hook);
+ if (nfq_ct == NULL)
+ return NULL;
+
+ ct = nf_ct_get(skb, ctinfo);
+ if (ct && !nf_ct_is_untracked(ct))
+ nfq_ct->parse(attr, ct);
+
+ return ct;
+}
+
+int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo)
+{
+ struct nfq_ct_hook *nfq_ct;
+ struct nlattr *nest_parms;
+ u_int32_t tmp;
+
+ nfq_ct = rcu_dereference(nfq_ct_hook);
+ if (nfq_ct == NULL)
+ return 0;
+
+ nest_parms = nla_nest_start(skb, NFQA_CT | NLA_F_NESTED);
+ if (!nest_parms)
+ goto nla_put_failure;
+
+ if (nfq_ct->build(skb, ct) < 0)
+ goto nla_put_failure;
+
+ nla_nest_end(skb, nest_parms);
+
+ tmp = ctinfo;
+ if (nla_put_be32(skb, NFQA_CT_INFO, htonl(tmp)))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -1;
+}
+
+void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo, int diff)
+{
+ struct nfq_ct_hook *nfq_ct;
+
+ nfq_ct = rcu_dereference(nfq_ct_hook);
+ if (nfq_ct == NULL)
+ return;
+
+ if ((ct->status & IPS_NAT_MASK) && diff)
+ nfq_ct->seq_adjust(skb, ct, ctinfo, diff);
+}
goto err3;
if (info->helper[0]) {
+ struct nf_conntrack_helper *helper;
+
ret = -ENOENT;
proto = xt_ct_find_proto(par);
if (!proto) {
goto err3;
}
- ret = -ENOMEM;
- help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
- if (help == NULL)
- goto err3;
-
ret = -ENOENT;
- help->helper = nf_conntrack_helper_try_module_get(info->helper,
- par->family,
- proto);
- if (help->helper == NULL) {
+ helper = nf_conntrack_helper_try_module_get(info->helper,
+ par->family,
+ proto);
+ if (helper == NULL) {
pr_info("No such helper \"%s\"\n", info->helper);
goto err3;
}
+
+ ret = -ENOMEM;
+ help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL);
+ if (help == NULL)
+ goto err3;
+
+ help->helper = helper;
}
__set_bit(IPS_TEMPLATE_BIT, &ct->status);
goto err3;
if (info->helper[0]) {
+ struct nf_conntrack_helper *helper;
+
ret = -ENOENT;
proto = xt_ct_find_proto(par);
if (!proto) {
goto err3;
}
- ret = -ENOMEM;
- help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
- if (help == NULL)
- goto err3;
-
ret = -ENOENT;
- help->helper = nf_conntrack_helper_try_module_get(info->helper,
- par->family,
- proto);
- if (help->helper == NULL) {
+ helper = nf_conntrack_helper_try_module_get(info->helper,
+ par->family,
+ proto);
+ if (helper == NULL) {
pr_info("No such helper \"%s\"\n", info->helper);
goto err3;
}
+
+ ret = -ENOMEM;
+ help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL);
+ if (help == NULL)
+ goto err3;
+
+ help->helper = helper;
}
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING)
return -EPERM;
retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_PAUSE_PUSH);
- if (!retval) {
+ if (!retval)
stream->runtime->state = SNDRV_PCM_STATE_PAUSED;
- wake_up(&stream->runtime->sleep);
- }
return retval;
}
if (!retval) {
stream->runtime->state = SNDRV_PCM_STATE_SETUP;
wake_up(&stream->runtime->sleep);
+ stream->runtime->hw_pointer = 0;
+ stream->runtime->app_pointer = 0;
+ stream->runtime->total_bytes_available = 0;
+ stream->runtime->total_bytes_transferred = 0;
}
return retval;
}
static int DELAYED_INIT_MARK azx_first_init(struct azx *chip);
static int DELAYED_INIT_MARK azx_probe_continue(struct azx *chip);
+#ifdef SUPPORT_VGA_SWITCHEROO
static struct pci_dev __devinit *get_bound_vga(struct pci_dev *pci);
-#ifdef SUPPORT_VGA_SWITCHEROO
static void azx_vs_set_state(struct pci_dev *pci,
enum vga_switcheroo_state state)
{
#else
#define init_vga_switcheroo(chip) /* NOP */
#define register_vga_switcheroo(chip) 0
+#define check_hdmi_disabled(pci) false
#endif /* SUPPORT_VGA_SWITCHER */
/*
return azx_free(device->device_data);
}
+#ifdef SUPPORT_VGA_SWITCHEROO
/*
* Check of disabled HDMI controller by vga-switcheroo
*/
struct pci_dev *p = get_bound_vga(pci);
if (p) {
- if (vga_default_device() && p != vga_default_device())
+ if (vga_switcheroo_get_client_state(p) == VGA_SWITCHEROO_OFF)
vga_inactive = true;
pci_dev_put(p);
}
return vga_inactive;
}
+#endif /* SUPPORT_VGA_SWITCHEROO */
/*
* white/black-listing for position_fix
{ PCI_DEVICE(0x6549, 0x1200),
.driver_data = AZX_DRIVER_TERA | AZX_DCAPS_NO_64BIT },
/* Creative X-Fi (CA0110-IBG) */
+ /* CTHDA chips */
+ { PCI_DEVICE(0x1102, 0x0010),
+ .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
+ { PCI_DEVICE(0x1102, 0x0012),
+ .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
#if !defined(CONFIG_SND_CTXFI) && !defined(CONFIG_SND_CTXFI_MODULE)
/* the following entry conflicts with snd-ctxfi driver,
* as ctxfi driver mutates from HD-audio to native mode with
.driver_data = AZX_DRIVER_CTX | AZX_DCAPS_CTX_WORKAROUND |
AZX_DCAPS_RIRB_PRE_DELAY | AZX_DCAPS_POSFIX_LPIB },
#endif
- /* CTHDA chips */
- { PCI_DEVICE(0x1102, 0x0010),
- .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
- { PCI_DEVICE(0x1102, 0x0012),
- .driver_data = AZX_DRIVER_CTHDA | AZX_DCAPS_PRESET_CTHDA },
/* Vortex86MX */
{ PCI_DEVICE(0x17f3, 0x3010), .driver_data = AZX_DRIVER_GENERIC },
/* VMware HDAudio */
static int cx_auto_init(struct hda_codec *codec)
{
struct conexant_spec *spec = codec->spec;
- /*snd_hda_sequence_write(codec, cx_auto_init_verbs);*/
+ snd_hda_gen_apply_verbs(codec);
cx_auto_init_output(codec);
cx_auto_init_input(codec);
cx_auto_init_digital(codec);
alc_fix_pll(codec);
alc_auto_init_amp(codec, spec->init_amp);
+ snd_hda_gen_apply_verbs(codec);
alc_init_special_input_src(codec);
alc_auto_init_std(codec);
ALC662_FIXUP_ASUS_MODE7,
ALC662_FIXUP_ASUS_MODE8,
ALC662_FIXUP_NO_JACK_DETECT,
+ ALC662_FIXUP_ZOTAC_Z68,
};
static const struct alc_fixup alc662_fixups[] = {
.type = ALC_FIXUP_FUNC,
.v.func = alc_fixup_no_jack_detect,
},
+ [ALC662_FIXUP_ZOTAC_Z68] = {
+ .type = ALC_FIXUP_PINS,
+ .v.pins = (const struct alc_pincfg[]) {
+ { 0x1b, 0x02214020 }, /* Front HP */
+ { }
+ }
+ },
};
static const struct snd_pci_quirk alc662_fixup_tbl[] = {
SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
+ SND_PCI_QUIRK(0x19da, 0xa130, "Zotac Z68", ALC662_FIXUP_ZOTAC_Z68),
SND_PCI_QUIRK(0x1b35, 0x2206, "CZC P10T", ALC662_FIXUP_CZC_P10T),
#if 0
}
static int wm2000_poll_bit(struct i2c_client *i2c,
- unsigned int reg, u8 mask, int timeout)
+ unsigned int reg, u8 mask)
{
+ int timeout = 4000;
int val;
val = wm2000_read(i2c, reg);
static int wm2000_power_up(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int ret, timeout;
+ int ret;
BUG_ON(wm2000->anc_mode != ANC_OFF);
/* Wait for ANC engine to become ready */
if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT,
- WM2000_ANC_ENG_IDLE, 1)) {
+ WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev, "ANC engine failed to reset\n");
return -ETIMEDOUT;
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_BOOT_COMPLETE, 1)) {
+ WM2000_STATUS_BOOT_COMPLETE)) {
dev_err(&i2c->dev, "ANC engine failed to initialise\n");
return -ETIMEDOUT;
}
dev_dbg(&i2c->dev, "Download complete\n");
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_MOUSE_ENABLE |
WM2000_MODE_THERMAL_ENABLE);
} else {
- timeout = 10;
-
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_MOUSE_ENABLE |
WM2000_MODE_THERMAL_ENABLE);
wm2000_write(i2c, WM2000_REG_SYS_CTL2, WM2000_ANC_INT_N_CLR);
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_MOUSE_ACTIVE, timeout)) {
- dev_err(&i2c->dev, "Timed out waiting for device after %dms\n",
- timeout * 10);
+ WM2000_STATUS_MOUSE_ACTIVE)) {
+ dev_err(&i2c->dev, "Timed out waiting for device\n");
return -ETIMEDOUT;
}
static int wm2000_power_down(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int timeout;
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_POWER_DOWN);
} else {
- timeout = 10;
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_POWER_DOWN);
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_POWER_DOWN_COMPLETE, timeout)) {
+ WM2000_STATUS_POWER_DOWN_COMPLETE)) {
dev_err(&i2c->dev, "Timeout waiting for ANC power down\n");
return -ETIMEDOUT;
}
if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT,
- WM2000_ANC_ENG_IDLE, 1)) {
+ WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev, "Timeout waiting for ANC engine idle\n");
return -ETIMEDOUT;
}
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_ANC_DISABLED, 10)) {
+ WM2000_STATUS_ANC_DISABLED)) {
dev_err(&i2c->dev, "Timeout waiting for ANC disable\n");
return -ETIMEDOUT;
}
if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT,
- WM2000_ANC_ENG_IDLE, 1)) {
+ WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev, "Timeout waiting for ANC engine idle\n");
return -ETIMEDOUT;
}
wm2000_write(i2c, WM2000_REG_SYS_CTL2, WM2000_ANC_INT_N_CLR);
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_MOUSE_ACTIVE, 10)) {
+ WM2000_STATUS_MOUSE_ACTIVE)) {
dev_err(&i2c->dev, "Timed out waiting for MOUSE\n");
return -ETIMEDOUT;
}
static int wm2000_enter_standby(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int timeout;
BUG_ON(wm2000->anc_mode != ANC_ACTIVE);
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PD_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_STANDBY_ENTRY);
} else {
- timeout = 10;
-
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_STANDBY_ENTRY);
}
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_ANC_DISABLED, timeout)) {
+ WM2000_STATUS_ANC_DISABLED)) {
dev_err(&i2c->dev,
"Timed out waiting for ANC disable after 1ms\n");
return -ETIMEDOUT;
}
- if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT, WM2000_ANC_ENG_IDLE,
- 1)) {
+ if (!wm2000_poll_bit(i2c, WM2000_REG_ANC_STAT, WM2000_ANC_ENG_IDLE)) {
dev_err(&i2c->dev,
- "Timed out waiting for standby after %dms\n",
- timeout * 10);
+ "Timed out waiting for standby\n");
return -ETIMEDOUT;
}
static int wm2000_exit_standby(struct i2c_client *i2c, int analogue)
{
struct wm2000_priv *wm2000 = dev_get_drvdata(&i2c->dev);
- int timeout;
BUG_ON(wm2000->anc_mode != ANC_STANDBY);
wm2000_write(i2c, WM2000_REG_SYS_CTL1, 0);
if (analogue) {
- timeout = 248;
- wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, timeout / 4);
+ wm2000_write(i2c, WM2000_REG_ANA_VMID_PU_TIME, 248 / 4);
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_ANA_SEQ_INCLUDE |
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_MOUSE_ENABLE);
} else {
- timeout = 10;
-
wm2000_write(i2c, WM2000_REG_SYS_MODE_CNTRL,
WM2000_MODE_THERMAL_ENABLE |
WM2000_MODE_MOUSE_ENABLE);
wm2000_write(i2c, WM2000_REG_SYS_CTL2, WM2000_ANC_INT_N_CLR);
if (!wm2000_poll_bit(i2c, WM2000_REG_SYS_STATUS,
- WM2000_STATUS_MOUSE_ACTIVE, timeout)) {
- dev_err(&i2c->dev, "Timed out waiting for MOUSE after %dms\n",
- timeout * 10);
+ WM2000_STATUS_MOUSE_ACTIVE)) {
+ dev_err(&i2c->dev, "Timed out waiting for MOUSE\n");
return -ETIMEDOUT;
}
#define WM8994_NUM_DRC 3
#define WM8994_NUM_EQ 3
+static struct {
+ unsigned int reg;
+ unsigned int mask;
+} wm8994_vu_bits[] = {
+ { WM8994_LEFT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU },
+ { WM8994_RIGHT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU },
+ { WM8994_LEFT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU },
+ { WM8994_RIGHT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU },
+ { WM8994_SPEAKER_VOLUME_LEFT, WM8994_SPKOUT_VU },
+ { WM8994_SPEAKER_VOLUME_RIGHT, WM8994_SPKOUT_VU },
+ { WM8994_LEFT_OUTPUT_VOLUME, WM8994_HPOUT1_VU },
+ { WM8994_RIGHT_OUTPUT_VOLUME, WM8994_HPOUT1_VU },
+ { WM8994_LEFT_OPGA_VOLUME, WM8994_MIXOUT_VU },
+ { WM8994_RIGHT_OPGA_VOLUME, WM8994_MIXOUT_VU },
+
+ { WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1DAC1_VU },
+ { WM8994_AIF1_DAC1_RIGHT_VOLUME, WM8994_AIF1DAC1_VU },
+ { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU },
+ { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU },
+ { WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2DAC_VU },
+ { WM8994_AIF2_DAC_RIGHT_VOLUME, WM8994_AIF2DAC_VU },
+ { WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1ADC1_VU },
+ { WM8994_AIF1_ADC1_RIGHT_VOLUME, WM8994_AIF1ADC1_VU },
+ { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU },
+ { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
+ { WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2ADC_VU },
+ { WM8994_AIF2_ADC_RIGHT_VOLUME, WM8994_AIF1ADC2_VU },
+ { WM8994_DAC1_LEFT_VOLUME, WM8994_DAC1_VU },
+ { WM8994_DAC1_RIGHT_VOLUME, WM8994_DAC1_VU },
+ { WM8994_DAC2_LEFT_VOLUME, WM8994_DAC2_VU },
+ { WM8994_DAC2_RIGHT_VOLUME, WM8994_DAC2_VU },
+};
+
static int wm8994_drc_base[] = {
WM8994_AIF1_DRC1_1,
WM8994_AIF1_DRC2_1,
struct snd_soc_codec *codec = w->codec;
struct wm8994 *control = codec->control_data;
int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA;
+ int i;
int dac;
int adc;
int val;
WM8994_AIF1DAC2L_ENA);
break;
+ case SND_SOC_DAPM_POST_PMU:
+ for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+ snd_soc_write(codec, wm8994_vu_bits[i].reg,
+ snd_soc_read(codec,
+ wm8994_vu_bits[i].reg));
+ break;
+
case SND_SOC_DAPM_PRE_PMD:
case SND_SOC_DAPM_POST_PMD:
snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5,
struct snd_kcontrol *kcontrol, int event)
{
struct snd_soc_codec *codec = w->codec;
+ int i;
int dac;
int adc;
int val;
WM8994_AIF2DACR_ENA);
break;
+ case SND_SOC_DAPM_POST_PMU:
+ for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+ snd_soc_write(codec, wm8994_vu_bits[i].reg,
+ snd_soc_read(codec,
+ wm8994_vu_bits[i].reg));
+ break;
+
case SND_SOC_DAPM_PRE_PMD:
case SND_SOC_DAPM_POST_PMD:
snd_soc_update_bits(codec, WM8994_POWER_MANAGEMENT_5,
switch (event) {
case SND_SOC_DAPM_PRE_PMU:
if (wm8994->aif1clk_enable) {
- aif1clk_ev(w, kcontrol, event);
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMU);
snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1,
WM8994_AIF1CLK_ENA_MASK,
WM8994_AIF1CLK_ENA);
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMU);
wm8994->aif1clk_enable = 0;
}
if (wm8994->aif2clk_enable) {
- aif2clk_ev(w, kcontrol, event);
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMU);
snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1,
WM8994_AIF2CLK_ENA_MASK,
WM8994_AIF2CLK_ENA);
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMU);
wm8994->aif2clk_enable = 0;
}
break;
switch (event) {
case SND_SOC_DAPM_POST_PMD:
if (wm8994->aif1clk_disable) {
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMD);
snd_soc_update_bits(codec, WM8994_AIF1_CLOCKING_1,
WM8994_AIF1CLK_ENA_MASK, 0);
- aif1clk_ev(w, kcontrol, event);
+ aif1clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMD);
wm8994->aif1clk_disable = 0;
}
if (wm8994->aif2clk_disable) {
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_PRE_PMD);
snd_soc_update_bits(codec, WM8994_AIF2_CLOCKING_1,
WM8994_AIF2CLK_ENA_MASK, 0);
- aif2clk_ev(w, kcontrol, event);
+ aif2clk_ev(w, kcontrol, SND_SOC_DAPM_POST_PMD);
wm8994->aif2clk_disable = 0;
}
break;
static const struct snd_soc_dapm_widget wm8994_lateclk_widgets[] = {
SND_SOC_DAPM_SUPPLY("AIF1CLK", WM8994_AIF1_CLOCKING_1, 0, 0, aif1clk_ev,
- SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
+ SND_SOC_DAPM_PRE_PMD),
SND_SOC_DAPM_SUPPLY("AIF2CLK", WM8994_AIF2_CLOCKING_1, 0, 0, aif2clk_ev,
- SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD),
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU |
+ SND_SOC_DAPM_PRE_PMD),
SND_SOC_DAPM_PGA("Direct Voice", SND_SOC_NOPM, 0, 0, NULL, 0),
SND_SOC_DAPM_MIXER("SPKL", WM8994_POWER_MANAGEMENT_3, 8, 0,
left_speaker_mixer, ARRAY_SIZE(left_speaker_mixer)),
pm_runtime_put(codec->dev);
- /* Latch volume updates (right only; we always do left then right). */
- snd_soc_update_bits(codec, WM8994_AIF1_DAC1_LEFT_VOLUME,
- WM8994_AIF1DAC1_VU, WM8994_AIF1DAC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_DAC1_RIGHT_VOLUME,
- WM8994_AIF1DAC1_VU, WM8994_AIF1DAC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_DAC2_LEFT_VOLUME,
- WM8994_AIF1DAC2_VU, WM8994_AIF1DAC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_DAC2_RIGHT_VOLUME,
- WM8994_AIF1DAC2_VU, WM8994_AIF1DAC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_DAC_LEFT_VOLUME,
- WM8994_AIF2DAC_VU, WM8994_AIF2DAC_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_DAC_RIGHT_VOLUME,
- WM8994_AIF2DAC_VU, WM8994_AIF2DAC_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC1_LEFT_VOLUME,
- WM8994_AIF1ADC1_VU, WM8994_AIF1ADC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC1_RIGHT_VOLUME,
- WM8994_AIF1ADC1_VU, WM8994_AIF1ADC1_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC2_LEFT_VOLUME,
- WM8994_AIF1ADC2_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF1_ADC2_RIGHT_VOLUME,
- WM8994_AIF1ADC2_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_ADC_LEFT_VOLUME,
- WM8994_AIF2ADC_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_AIF2_ADC_RIGHT_VOLUME,
- WM8994_AIF2ADC_VU, WM8994_AIF1ADC2_VU);
- snd_soc_update_bits(codec, WM8994_DAC1_LEFT_VOLUME,
- WM8994_DAC1_VU, WM8994_DAC1_VU);
- snd_soc_update_bits(codec, WM8994_DAC1_RIGHT_VOLUME,
- WM8994_DAC1_VU, WM8994_DAC1_VU);
- snd_soc_update_bits(codec, WM8994_DAC2_LEFT_VOLUME,
- WM8994_DAC2_VU, WM8994_DAC2_VU);
- snd_soc_update_bits(codec, WM8994_DAC2_RIGHT_VOLUME,
- WM8994_DAC2_VU, WM8994_DAC2_VU);
+ /* Latch volume update bits */
+ for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++)
+ snd_soc_update_bits(codec, wm8994_vu_bits[i].reg,
+ wm8994_vu_bits[i].mask,
+ wm8994_vu_bits[i].mask);
/* Set the low bit of the 3D stereo depth so TLV matches */
snd_soc_update_bits(codec, WM8994_AIF1_DAC1_FILTERS_2,
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/pinctrl/consumer.h>
#include "imx-audmux.h"
static int __devinit imx_audmux_probe(struct platform_device *pdev)
{
struct resource *res;
+ struct pinctrl *pinctrl;
const struct of_device_id *of_id =
of_match_device(imx_audmux_dt_ids, &pdev->dev);
if (!audmux_base)
return -EADDRNOTAVAIL;
+ pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
+ if (IS_ERR(pinctrl)) {
+ dev_err(&pdev->dev, "setup pinctrl failed!");
+ return PTR_ERR(pinctrl);
+ }
+
audmux_clk = clk_get(&pdev->dev, "audmux");
if (IS_ERR(audmux_clk)) {
dev_dbg(&pdev->dev, "cannot get clock: %ld\n",
/* do we need to add this widget to the list ? */
if (list) {
int err;
- err = dapm_list_add_widget(list, path->sink);
+ err = dapm_list_add_widget(list, path->source);
if (err < 0) {
dev_err(widget->dapm->dev, "could not add widget %s\n",
widget->name);
if (stream == SNDRV_PCM_STREAM_PLAYBACK)
paths = is_connected_output_ep(dai->playback_widget, list);
else
- paths = is_connected_input_ep(dai->playback_widget, list);
+ paths = is_connected_input_ep(dai->capture_widget, list);
trace_snd_soc_dapm_connected(paths, stream);
dapm_clear_walk(&card->dapm);
for (i = 0; i < card->num_links; i++) {
be = &card->rtd[i];
+ if (!be->dai_link->no_pcm)
+ continue;
+
if (be->cpu_dai->playback_widget == widget ||
be->codec_dai->playback_widget == widget)
return be;
for (i = 0; i < card->num_links; i++) {
be = &card->rtd[i];
+ if (!be->dai_link->no_pcm)
+ continue;
+
if (be->cpu_dai->capture_widget == widget ||
be->codec_dai->capture_widget == widget)
return be;
MODULE_DESCRIPTION("Tegra30 AHUB driver");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_DEVICE_TABLE(of, tegra30_ahub_of_match);
unsigned long unlink_mask; /* bitmask of unlinked urbs */
/* data and sync endpoints for this stream */
+ unsigned int ep_num; /* the endpoint number */
struct snd_usb_endpoint *data_endpoint;
struct snd_usb_endpoint *sync_endpoint;
unsigned long flags;
subs->formats |= fp->formats;
subs->num_formats++;
subs->fmt_type = fp->fmt_type;
+ subs->ep_num = fp->endpoint;
}
/*
if (as->fmt_type != fp->fmt_type)
continue;
subs = &as->substream[stream];
- if (!subs->data_endpoint)
- continue;
- if (subs->data_endpoint->ep_num == fp->endpoint) {
+ if (subs->ep_num == fp->endpoint) {
list_add_tail(&fp->list, &subs->fmt_list);
subs->num_formats++;
subs->formats |= fp->formats;
if (as->fmt_type != fp->fmt_type)
continue;
subs = &as->substream[stream];
- if (subs->data_endpoint)
+ if (subs->ep_num)
continue;
err = snd_pcm_new_stream(as->pcm, stream, 1);
if (err < 0)
tools/perf
+tools/scripts
+tools/lib/traceevent
include/linux/const.h
include/linux/perf_event.h
include/linux/rbtree.h
if (symbol_conf.use_callchain) {
err = callchain_append(he->callchain,
- &evsel->hists.callchain_cursor,
+ &callchain_cursor,
sample->period);
if (err)
return err;
* so we don't allocated the extra space needed because the stdio
* code will not use it.
*/
- if (al->sym != NULL && use_browser > 0) {
+ if (he->ms.sym != NULL && use_browser > 0) {
struct annotation *notes = symbol__annotation(he->ms.sym);
assert(evsel != NULL);
return 0;
if (!evsel_list->nr_entries) {
- if (perf_evlist__add_attrs_array(evsel_list, default_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
return -1;
}
return 0;
/* Append detailed run extra attributes: */
- if (perf_evlist__add_attrs_array(evsel_list, detailed_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, detailed_attrs) < 0)
return -1;
if (detailed_run < 2)
return 0;
/* Append very detailed run extra attributes: */
- if (perf_evlist__add_attrs_array(evsel_list, very_detailed_attrs) < 0)
+ if (perf_evlist__add_default_attrs(evsel_list, very_detailed_attrs) < 0)
return -1;
if (detailed_run < 3)
return 0;
/* Append very, very detailed run extra attributes: */
- return perf_evlist__add_attrs_array(evsel_list, very_very_detailed_attrs);
+ return perf_evlist__add_default_attrs(evsel_list, very_very_detailed_attrs);
}
int cmd_stat(int argc, const char **argv, const char *prefix __used)
}
if (symbol_conf.use_callchain) {
- err = callchain_append(he->callchain, &evsel->hists.callchain_cursor,
+ err = callchain_append(he->callchain, &callchain_cursor,
sample->period);
if (err)
return;
prctl. When a counter is disabled, it doesn't count or generate
events but does continue to exist and maintain its count value.
-An individual counter or counter group can be enabled with
+An individual counter can be enabled with
- ioctl(fd, PERF_EVENT_IOC_ENABLE);
+ ioctl(fd, PERF_EVENT_IOC_ENABLE, 0);
or disabled with
- ioctl(fd, PERF_EVENT_IOC_DISABLE);
+ ioctl(fd, PERF_EVENT_IOC_DISABLE, 0);
+For a counter group, pass PERF_IOC_FLAG_GROUP as the third argument.
Enabling or disabling the leader of a group enables or disables the
whole group; that is, while the group leader is disabled, none of the
counters in the group will count. Enabling or disabling a member of a
"q/ESC/CTRL+C Exit\n\n"
"-> Go to target\n"
"<- Exit\n"
- "h Cycle thru hottest instructions\n"
+ "H Cycle thru hottest instructions\n"
"j Toggle showing jump to target arrows\n"
"J Toggle showing number of jump sources on targets\n"
"n Search next string\n"
# First check if there is a .git to get the version from git describe
# otherwise try to get the version from the kernel makefile
if test -d ../../.git -o -f ../../.git &&
- VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+ VN=$(git describe --match 'v[0-9].[0-9]*' --abbrev=4 HEAD 2>/dev/null) &&
case "$VN" in
*$LF*) (exit 1) ;;
v[0-9]*)
#include "util.h"
#include "callchain.h"
+__thread struct callchain_cursor callchain_cursor;
+
bool ip_callchain__valid(struct ip_callchain *chain,
const union perf_event *event)
{
struct callchain_cursor_node *curr;
};
+extern __thread struct callchain_cursor callchain_cursor;
+
static inline void callchain_init(struct callchain_root *root)
{
INIT_LIST_HEAD(&root->node.siblings);
return -1;
}
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs)
+{
+ size_t i;
+
+ for (i = 0; i < nr_attrs; i++)
+ event_attr_init(attrs + i);
+
+ return perf_evlist__add_attrs(evlist, attrs, nr_attrs);
+}
+
static int trace_event__id(const char *evname)
{
char *filename, *colon;
for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
list_for_each_entry(pos, &evlist->entries, node) {
for (thread = 0; thread < evlist->threads->nr; thread++)
- ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_DISABLE);
+ ioctl(FD(pos, cpu, thread),
+ PERF_EVENT_IOC_DISABLE, 0);
}
}
}
for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
list_for_each_entry(pos, &evlist->entries, node) {
for (thread = 0; thread < evlist->threads->nr; thread++)
- ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+ ioctl(FD(pos, cpu, thread),
+ PERF_EVENT_IOC_ENABLE, 0);
}
}
}
int perf_evlist__add_default(struct perf_evlist *evlist);
int perf_evlist__add_attrs(struct perf_evlist *evlist,
struct perf_event_attr *attrs, size_t nr_attrs);
+int __perf_evlist__add_default_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs);
int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
const char *tracepoints[], size_t nr_tracepoints);
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
#define perf_evlist__add_attrs_array(evlist, array) \
perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
+#define perf_evlist__add_default_attrs(evlist, array) \
+ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
#define perf_evlist__add_tracepoints_array(evlist, array) \
perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
}
static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
- struct perf_sample *sample)
+ struct perf_sample *sample,
+ bool swapped)
{
const u64 *array = event->sample.array;
+ union u64_swap u;
array += ((event->header.size -
sizeof(event->header)) / sizeof(u64)) - 1;
if (type & PERF_SAMPLE_CPU) {
- u32 *p = (u32 *)array;
- sample->cpu = *p;
+ u.val64 = *array;
+ if (swapped) {
+ /* undo swap of u64, then swap on individual u32s */
+ u.val64 = bswap_64(u.val64);
+ u.val32[0] = bswap_32(u.val32[0]);
+ }
+
+ sample->cpu = u.val32[0];
array--;
}
}
if (type & PERF_SAMPLE_TID) {
- u32 *p = (u32 *)array;
- sample->pid = p[0];
- sample->tid = p[1];
+ u.val64 = *array;
+ if (swapped) {
+ /* undo swap of u64, then swap on individual u32s */
+ u.val64 = bswap_64(u.val64);
+ u.val32[0] = bswap_32(u.val32[0]);
+ u.val32[1] = bswap_32(u.val32[1]);
+ }
+
+ sample->pid = u.val32[0];
+ sample->tid = u.val32[1];
}
return 0;
if (event->header.type != PERF_RECORD_SAMPLE) {
if (!sample_id_all)
return 0;
- return perf_event__parse_id_sample(event, type, data);
+ return perf_event__parse_id_sample(event, type, data, swapped);
}
array = event->sample.array;
* collapse the histogram
*/
-static bool hists__collapse_insert_entry(struct hists *hists,
+static bool hists__collapse_insert_entry(struct hists *hists __used,
struct rb_root *root,
struct hist_entry *he)
{
iter->period += he->period;
iter->nr_events += he->nr_events;
if (symbol_conf.use_callchain) {
- callchain_cursor_reset(&hists->callchain_cursor);
- callchain_merge(&hists->callchain_cursor, iter->callchain,
+ callchain_cursor_reset(&callchain_cursor);
+ callchain_merge(&callchain_cursor,
+ iter->callchain,
he->callchain);
}
hist_entry__free(he);
struct events_stats stats;
u64 event_stream;
u16 col_len[HISTC_NR_COLS];
- /* Best would be to reuse the session callchain cursor */
- struct callchain_cursor callchain_cursor;
};
struct hist_entry *__hists__add_entry(struct hists *self,
}
if (!pager)
pager = getenv("PAGER");
+ if (!pager) {
+ if (!access("/usr/bin/pager", X_OK))
+ pager = "/usr/bin/pager";
+ }
if (!pager)
pager = "less";
else if (!*pager || !strcmp(pager, "cat"))
error:
if (kfd >= 0) {
- if (namelist)
- strlist__delete(namelist);
-
+ strlist__delete(namelist);
close(kfd);
}
if (ufd >= 0) {
- if (unamelist)
- strlist__delete(unamelist);
-
+ strlist__delete(unamelist);
close(ufd);
}
return bi;
}
-int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
+int machine__resolve_callchain(struct machine *self,
+ struct perf_evsel *evsel __used,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent)
unsigned int i;
int err;
- callchain_cursor_reset(&evsel->hists.callchain_cursor);
+ callchain_cursor_reset(&callchain_cursor);
+
+ if (chain->nr > PERF_MAX_STACK_DEPTH) {
+ pr_warning("corrupted callchain. skipping...\n");
+ return 0;
+ }
for (i = 0; i < chain->nr; i++) {
u64 ip;
case PERF_CONTEXT_USER:
cpumode = PERF_RECORD_MISC_USER; break;
default:
- break;
+ pr_debug("invalid callchain context: "
+ "%"PRId64"\n", (s64) ip);
+ /*
+ * It seems the callchain is corrupted.
+ * Discard all.
+ */
+ callchain_cursor_reset(&callchain_cursor);
+ return 0;
}
continue;
}
break;
}
- err = callchain_cursor_append(&evsel->hists.callchain_cursor,
+ err = callchain_cursor_append(&callchain_cursor,
ip, al.map, al.sym);
if (err)
return err;
}
}
-static void perf_event__all64_swap(union perf_event *event)
+static void swap_sample_id_all(union perf_event *event, void *data)
+{
+ void *end = (void *) event + event->header.size;
+ int size = end - data;
+
+ BUG_ON(size % sizeof(u64));
+ mem_bswap_64(data, size);
+}
+
+static void perf_event__all64_swap(union perf_event *event,
+ bool sample_id_all __used)
{
struct perf_event_header *hdr = &event->header;
mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
}
-static void perf_event__comm_swap(union perf_event *event)
+static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
{
event->comm.pid = bswap_32(event->comm.pid);
event->comm.tid = bswap_32(event->comm.tid);
+
+ if (sample_id_all) {
+ void *data = &event->comm.comm;
+
+ data += ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
}
-static void perf_event__mmap_swap(union perf_event *event)
+static void perf_event__mmap_swap(union perf_event *event,
+ bool sample_id_all)
{
event->mmap.pid = bswap_32(event->mmap.pid);
event->mmap.tid = bswap_32(event->mmap.tid);
event->mmap.start = bswap_64(event->mmap.start);
event->mmap.len = bswap_64(event->mmap.len);
event->mmap.pgoff = bswap_64(event->mmap.pgoff);
+
+ if (sample_id_all) {
+ void *data = &event->mmap.filename;
+
+ data += ALIGN(strlen(data) + 1, sizeof(u64));
+ swap_sample_id_all(event, data);
+ }
}
-static void perf_event__task_swap(union perf_event *event)
+static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
{
event->fork.pid = bswap_32(event->fork.pid);
event->fork.tid = bswap_32(event->fork.tid);
event->fork.ppid = bswap_32(event->fork.ppid);
event->fork.ptid = bswap_32(event->fork.ptid);
event->fork.time = bswap_64(event->fork.time);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->fork + 1);
}
-static void perf_event__read_swap(union perf_event *event)
+static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
{
event->read.pid = bswap_32(event->read.pid);
event->read.tid = bswap_32(event->read.tid);
event->read.time_enabled = bswap_64(event->read.time_enabled);
event->read.time_running = bswap_64(event->read.time_running);
event->read.id = bswap_64(event->read.id);
+
+ if (sample_id_all)
+ swap_sample_id_all(event, &event->read + 1);
}
static u8 revbyte(u8 b)
swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}
-static void perf_event__hdr_attr_swap(union perf_event *event)
+static void perf_event__hdr_attr_swap(union perf_event *event,
+ bool sample_id_all __used)
{
size_t size;
mem_bswap_64(event->attr.id, size);
}
-static void perf_event__event_type_swap(union perf_event *event)
+static void perf_event__event_type_swap(union perf_event *event,
+ bool sample_id_all __used)
{
event->event_type.event_type.event_id =
bswap_64(event->event_type.event_type.event_id);
}
-static void perf_event__tracing_data_swap(union perf_event *event)
+static void perf_event__tracing_data_swap(union perf_event *event,
+ bool sample_id_all __used)
{
event->tracing_data.size = bswap_32(event->tracing_data.size);
}
-typedef void (*perf_event__swap_op)(union perf_event *event);
+typedef void (*perf_event__swap_op)(union perf_event *event,
+ bool sample_id_all);
static perf_event__swap_op perf_event__swap_ops[] = {
[PERF_RECORD_MMAP] = perf_event__mmap_swap,
}
}
+static void event_swap(union perf_event *event, bool sample_id_all)
+{
+ perf_event__swap_op swap;
+
+ swap = perf_event__swap_ops[event->header.type];
+ if (swap)
+ swap(event, sample_id_all);
+}
+
static int perf_session__process_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool,
struct perf_sample sample;
int ret;
- if (session->header.needs_swap &&
- perf_event__swap_ops[event->header.type])
- perf_event__swap_ops[event->header.type](event);
+ if (session->header.needs_swap)
+ event_swap(event, session->sample_id_all);
if (event->header.type >= PERF_RECORD_HEADER_MAX)
return -EINVAL;
int print_sym, int print_dso, int print_symoffset)
{
struct addr_location al;
- struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
struct callchain_cursor_node *node;
if (perf_event__preprocess_sample(event, machine, &al, sample,
error("Failed to resolve callchain. Skipping\n");
return;
}
- callchain_cursor_commit(cursor);
+ callchain_cursor_commit(&callchain_cursor);
while (1) {
- node = callchain_cursor_current(cursor);
+ node = callchain_cursor_current(&callchain_cursor);
if (!node)
break;
}
if (print_dso) {
printf(" (");
- map__fprintf_dsoname(al.map, stdout);
+ map__fprintf_dsoname(node->map, stdout);
printf(")");
}
printf("\n");
- callchain_cursor_advance(cursor);
+ callchain_cursor_advance(&callchain_cursor);
}
} else {
dso->sorted_by_name = 0;
dso->has_build_id = 0;
dso->kernel = DSO_TYPE_USER;
+ dso->needs_swap = DSO_SWAP__UNSET;
INIT_LIST_HEAD(&dso->node);
}
return -1;
}
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+ static unsigned int const endian = 1;
+
+ dso->needs_swap = DSO_SWAP__NO;
+
+ switch (eidata) {
+ case ELFDATA2LSB:
+ /* We are big endian, DSO is little endian. */
+ if (*(unsigned char const *)&endian != 1)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ case ELFDATA2MSB:
+ /* We are little endian, DSO is big endian. */
+ if (*(unsigned char const *)&endian != 0)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ default:
+ pr_err("unrecognized DSO data encoding %d\n", eidata);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
int fd, symbol_filter_t filter, int kmodule,
int want_symtab)
goto out_elf_end;
}
+ if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+ goto out_elf_end;
+
/* Always reject images with a mismatched build-id: */
if (dso->has_build_id) {
u8 build_id[BUILD_ID_SIZE];
if (opdsec && sym.st_shndx == opdidx) {
u32 offset = sym.st_value - opdshdr.sh_addr;
u64 *opd = opddata->d_buf + offset;
- sym.st_value = *opd;
+ sym.st_value = DSO__SWAP(dso, u64, *opd);
sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
}
struct map *dso__new_map(const char *name)
{
+ struct map *map = NULL;
struct dso *dso = dso__new(name);
- struct map *map = map__new2(0, dso, MAP__FUNCTION);
+
+ if (dso)
+ map = map__new2(0, dso, MAP__FUNCTION);
return map;
}
#include <linux/list.h>
#include <linux/rbtree.h>
#include <stdio.h>
+#include <byteswap.h>
#ifdef HAVE_CPLUS_DEMANGLE
extern char *cplus_demangle(const char *, int);
DSO_TYPE_GUEST_KERNEL
};
+enum dso_swap_type {
+ DSO_SWAP__UNSET,
+ DSO_SWAP__NO,
+ DSO_SWAP__YES,
+};
+
struct dso {
struct list_head node;
struct rb_root symbols[MAP__NR_TYPES];
struct rb_root symbol_names[MAP__NR_TYPES];
enum dso_kernel_type kernel;
+ enum dso_swap_type needs_swap;
u8 adjust_symbols:1;
u8 has_build_id:1;
u8 hit:1;
char name[0];
};
+#define DSO__SWAP(dso, type, val) \
+({ \
+ type ____r = val; \
+ BUG_ON(dso->needs_swap == DSO_SWAP__UNSET); \
+ if (dso->needs_swap == DSO_SWAP__YES) { \
+ switch (sizeof(____r)) { \
+ case 2: \
+ ____r = bswap_16(val); \
+ break; \
+ case 4: \
+ ____r = bswap_32(val); \
+ break; \
+ case 8: \
+ ____r = bswap_64(val); \
+ break; \
+ default: \
+ BUG_ON(1); \
+ } \
+ } \
+ ____r; \
+})
+
struct dso *dso__new(const char *name);
void dso__delete(struct dso *dso);
char *progname;
int num_cpus;
-cpu_set_t *cpu_mask;
-size_t cpu_mask_size;
+cpu_set_t *cpu_present_set, *cpu_mask;
+size_t cpu_present_setsize, cpu_mask_size;
struct counters {
unsigned long long tsc; /* per thread */
struct timeval tv_odd;
struct timeval tv_delta;
+int mark_cpu_present(int pkg, int core, int cpu)
+{
+ CPU_SET_S(cpu, cpu_present_setsize, cpu_present_set);
+ return 0;
+}
+
/*
* cpu_mask_init(ncpus)
*
}
cpu_mask_size = CPU_ALLOC_SIZE(ncpus);
CPU_ZERO_S(cpu_mask_size, cpu_mask);
+
+ /*
+ * Allocate and initialize cpu_present_set
+ */
+ cpu_present_set = CPU_ALLOC(ncpus);
+ if (cpu_present_set == NULL) {
+ perror("CPU_ALLOC");
+ exit(3);
+ }
+ cpu_present_setsize = CPU_ALLOC_SIZE(ncpus);
+ CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
+ for_all_cpus(mark_cpu_present);
}
void cpu_mask_uninit()
CPU_FREE(cpu_mask);
cpu_mask = NULL;
cpu_mask_size = 0;
+ CPU_FREE(cpu_present_set);
+ cpu_present_set = NULL;
+ cpu_present_setsize = 0;
}
int cpu_migrate(int cpu)
switch (model) {
case 0x2A:
case 0x2D:
+ case 0x3A: /* IVB */
+ case 0x3D: /* IVB Xeon */
return 1;
}
return 0;
int retval;
pid_t child_pid;
get_counters(cnt_even);
+
+ /* clear affinity side-effect of get_counters() */
+ sched_setaffinity(0, cpu_present_setsize, cpu_present_set);
gettimeofday(&tv_even, (struct timezone *)NULL);
child_pid = fork();
*/
hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link)
if (ei->type == KVM_IRQ_ROUTING_MSI ||
+ ue->type == KVM_IRQ_ROUTING_MSI ||
ue->u.irqchip.irqchip == ei->irqchip.irqchip)
return r;