summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6Linus Torvalds2005-07-064-6/+8
|\
| * [SPARC64]: Fix enable_dma() in asm-sparc64/parport.hEddie C. Dost2005-07-061-2/+2
| | | | | | | | | | | | | | Call ebus_dma_enable() before calling ebus_dma_request(), otherwise ebus_dma_request() returns -EINVAL and enable_dma() calls BUG()... Signed-off-by: David S. Miller <davem@davemloft.net>
| * [DVB]: Do not include <linux/irq.h> from drivers.Eddie C. Dost2005-07-061-1/+0
| | | | | | | | Signed-off-by: David S. Miller <davem@davemloft.net>
| * [SPARC64]: Fix set_intr_affinity()Eddie C. Dost2005-07-061-2/+5
| | | | | | | | | | | | | | Do not cat bucket->irq_info to struct irqaction * directly, but go through struct irq_desc *. Signed-off-by: David S. Miller <davem@davemloft.net>
| * [SPARC]: Fix "Eddie C. Dost" e-mail addressEddie C. Dost2005-07-061-1/+1
| | | | | | | | Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6Linus Torvalds2005-07-0616-1349/+1845
|\ \
| * | [CRYPTO] Add faster DES code from Dag Arne OsvikDag Arne Osvik2005-07-061-1149/+854
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I've made a new implementation of DES to replace the old one in the kernel. It provides faster encryption on all tested processors apart from the original Pentium, and key setup is many times faster. Speed relative to old kernel implementation Processor des_setkey des_encrypt des3_ede_setkey des3_ede_encrypt Pentium 120Mhz 6.8 0.82 7.2 0.86 Pentium III 1.266Ghz 5.6 1.19 5.8 1.34 Pentium M 1.3Ghz 5.7 1.15 6.0 1.31 Pentium 4 2.266Ghz 5.8 1.24 6.0 1.40 Pentium 4E 3Ghz 5.4 1.27 5.5 1.48 StrongARM 1110 206Mhz 4.3 1.03 4.4 1.14 Athlon XP 2Ghz 7.8 1.44 8.1 1.61 Athlon 64 2Ghz 7.8 1.34 8.3 1.49 Signed-off-by: Dag Arne Osvik <da@osvik.no> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Remove unused iv field from context structureHerbert Xu2005-07-062-3/+0
| | | | | | | | | | | | | | | | | | | | | | | | The iv field in des_ctx/des3_ede_ctx/serpent_ctx has never been used. This was noticed by Dag Arne Osvik. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Add x86_64 asm AESAndreas Steinmetz2005-07-065-2/+543
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implementation: =============== The encrypt/decrypt code is based on an x86 implementation I did a while ago which I never published. This unpublished implementation does include an assembler based key schedule and precomputed tables. For simplicity and best acceptance, however, I took Gladman's in-kernel code for table generation and key schedule for the kernel port of my assembler code and modified this code to produce the key schedule as required by my assembler implementation. File locations and Kconfig are kept similar to the i586 AES assembler implementation. It may seem a little bit strange to use 32 bit I/O and registers in the assembler implementation but this gives the best code size. My implementation takes one instruction more per round compared to Gladman's x86 assembler but it doesn't require any stack for local variables or saved registers and it is less serialized than Gladman's code. Note that all comparisons to Gladman's code were done after my code was implemented. I did only use FIPS PUB 197 for the implementation so my implementation is independent work. If anybody has a better assembler solution for x86_64 I'll be pleased to have my code replaced with the better solution. Testing: ======== The implementation passes the in-kernel crypto testing module and I'm running it without any problems on my laptop where it is mainly used for dm-crypt. Microbenchmark: =============== The microbenchmark was done in userspace with similar compile flags as used during kernel compile. Encrypt/decrypt is about 35% faster than the generic C implementation. As the generic C as well as my assembler implementation are both table I don't really expect that there is much room for further improvements though I'll be glad to be corrected here. The key schedule is about 5% slower than the generic C implementation. This is due to the fact that some more work has to be done in the key schedule routine to fit the schedule to the assembler implementation. Code Size: ========== Encrypt and decrypt are together about 2.1 Kbytes smaller than the generic C implementation which is important with regard to L1 cache usage. The key schedule routine is about 100 bytes larger than the generic C implementation. Data Size: ========== There's no difference in data size requirements between the assembler implementation and the generic C implementation. License: ======== Gladmans's code is dual BSD/GPL whereas my assembler code is GPLv2 only (I'm not going to change the license for my code). So I had to change the module license for the x86_64 aes module from 'Dual BSD/GPL' to 'GPL' to reflect the most restrictive license within the module. Signed-off-by: Andreas Steinmetz <ast@domdv.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Add null short circuit to crypto_free_tfmJesper Juhl2005-07-061-2/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As far as I'm aware there's a general concensus that functions that are responsible for freeing resources should be able to cope with being passed a NULL pointer. This makes sense as it removes the need for all callers to check for NULL, thus elliminating the bugs that happen when some forget (safer to just check centrally in the freeing function) and it also makes for smaller code all over due to the lack of all those NULL checks. This patch makes it safe to pass the crypto_free_tfm() function a NULL pointer. Once this patch is applied we can start removing the NULL checks from the callers. Signed-off-by: Jesper Juhl <juhl-lkml@dif.dk> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Update IV correctly for Padlock CBC encryptionHerbert Xu2005-07-061-4/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When the Padlock does CBC encryption, the memory pointed to by EAX is not updated at all. Instead, it updates the value of EAX by pointing it to the last block in the output. Therefore to maintain the correct semantics we need to copy the IV. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Handle unaligned iv from encrypt_iv/decrypt_ivHerbert Xu2005-07-061-2/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Even though cit_iv is now always aligned, the user can still supply an unaligned iv through crypto_cipher_encrypt_iv/crypto_cipher_decrypt_iv. This patch will check the alignment of the user-supplied iv and copy it if necessary. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Ensure cit_iv is aligned correctlyHerbert Xu2005-07-065-11/+72
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch ensures that cit_iv is aligned according to cra_alignmask by allocating it as part of the tfm structure. As a side effect the crypto layer will also guarantee that the tfm ctx area has enough space to be aligned by cra_alignmask. This allows us to remove the extra space reservation from the Padlock driver. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Make crypto_alg_lookup staticAdrian Bunk2005-07-062-11/+9
| | | | | | | | | | | | | | | | | | | | | | | | This patch makes a needlessly global function static. Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [PADLOCK] Implement multi-block operationsHerbert Xu2005-07-061-2/+53
| | | | | | | | | | | | | | | | | | | | | | | | By operating on multiple blocks at once, we expect to extract more performance out of the VIA Padlock. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [PADLOCK] Move fast path work into aes_set_key and upper layerHerbert Xu2005-07-062-72/+52
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Most of the work done aes_padlock can be done in aes_set_key. This means that we only have to do it once when the key changes rather than every time we perform an encryption or decryption. This patch also sets cra_alignmask to let the upper layer ensure that the buffers fed to us are aligned correctly. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Add alignmask for low-level cipher implementationsHerbert Xu2005-07-064-7/+49
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The VIA Padlock device requires the input and output buffers to be aligned on 16-byte boundaries. This patch adds the alignmask attribute for low-level cipher implementations to indicate their alignment requirements. The mid-level crypt() function will copy the input/output buffers if they are not aligned correctly before they are passed to the low-level implementation. Strictly speaking, some of the software implementations require the buffers to be aligned on 4-byte boundaries as they do 32-bit loads. However, it is not clear whether it is better to copy the buffers or pay the penalty for unaligned loads/stores. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Add support for low-level multi-block operationsHerbert Xu2005-07-063-26/+45
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds hooks for cipher algorithms to implement multi-block ECB/CBC operations directly. This is expected to provide significant performance boots to the VIA Padlock. It could also be used for improving software implementations such as AES where operating on multiple blocks at a time may enable certain optimisations. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Add plumbing for multi-block operationsHerbert Xu2005-07-063-95/+161
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The VIA Padlock device is able to perform much better when multiple blocks are fed to it at once. As this device offers an exceptional throughput rate it is worthwhile to optimise the infrastructure specifically for it. We shift the existing page-sized fast path down to the CBC/ECB functions. We can then replace the CBC/ECB functions with functions provided by the underlying algorithm that performs the multi-block operations. As a side-effect this improves the performance of large cipher operations for all existing algorithm implementations. I've measured the gain to be around 5% for 3DES and 15% for AES. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [CRYPTO] Don't check for NULL before kfree()Jesper Juhl2005-07-062-4/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | Checking a pointer for NULL before calling kfree() on it is redundant. This patch removes such checks from crypto/ Signed-off-by: Jesper Juhl <juhl-lkml@dif.dk> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* | | [PATCH] yet another fix for setup-bus.c/x86 mergeIvan Kokshaysky2005-07-061-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is a slight disagreement between setup-bus.c code and traditional x86 PCI setup wrt which recourses are invalid vs resources that are free for further allocations. In particular, in the setup-bus.c, if we failed to allocate some resource, we nullify "start" and "flags" fields, but *not* the "end" one. But x86 pcibios_enable_resources() does the following check: if (!r->start && r->end) { printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev)); return -EINVAL; which means that the device owning the offending resource cannot be enabled. In particular, this breaks cardbus behind the normal decode p2p bridge - the cardbus code from setup-bus.c requests rather large IO and MEM windows, and if it fails, the socket is completely unavailable. Which is wrong, as the yenta code is capable to allocate smaller windows. Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | | Merge master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2005-07-066-17/+198
|\ \ \
| * | | [PATCH] ARM: 2792/1: IXP4xx iomap API implementationDeepak Saxena2005-07-062-3/+177
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Deepak Saxena This patch implements the iomap API for Intel IXP4xx NPU systems. We need to implement our own version of the API functions b/c of the PCI hostbridge does not provide the capability to map PCI I/O space into the CPU's physical memory space. In addition, if a system has more than 64M of PCI memory mapped BARs, PCI memory must also be accessed indirectly. This patch changes the assignment of PCI I/O resources to fall into to 0x0000:0xffff range so that we can trap I/O areas in our ioread/iowrite macros. Signed-off-by: Deepak Saxena Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * | | [PATCH] ARM: 2791/1: Add CRCs for aliased ARM symbolsTodd Poynor2005-07-061-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Todd Poynor Fix module versioning for 3 ARM symbols that do not have CRCs added, avoid "disagrees about version of symbol struct_module" errors at module load time. From David Singleton. Signed-off-by: Todd Poynor <tpoynor@mvista.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * | | [PATCH] ARM: 2790/1: Properly terminate plat_serial8250_port arrays on ↵Stefan Sorensen2005-07-062-13/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ixdp425 and coyote Patch from Stefan Sorensen On the ixdp425 and coyote platforms, the plat_serial8250_port arrays are missing the terminating entry required by serial8250_probe. Signed-off-by: Stefan Sorensen <ssoe@kirktelecom.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * | | [PATCH] ARM: 2789/1: Enable access to both CP10 and CP11 on ARMv6Catalin Marinas2005-07-061-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Catalin Marinas The VFP instructions trigger undefined exceptions because the access to CP11 is disabled (only CP10 is currently enabled by the kernel). The patch fixes this problem. Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | | | ieee1394: fix broken signed char assumption.Linus Torvalds2005-07-061-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | "ack_code" is assigned (and tested against) negative numbers, but was declared as "char". Which only works if "char" is signed - which it necessarily isn't. So make that signedness assumption specific.
* | | | [PATCH] openfirmware: implement hotplug for macio devicesJeff Mahoney2005-07-061-0/+71
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds the hotplug routine for generating hotplug events when devices are seen on the macio bus. It uses the attributed created by the sysfs nodes to generate the hotplug environment vars for userspace. Since the characters allowed inside the 'compatible' field are NUL terminated, they are exported as individual OF_COMPATIBLE_# variables, with OF_COMPATIBLE_N maintaining a count of how many there are. In order for hotplug to work with macio devices, patches to module-init-tools and hotplug must be applied. Those patches are available at: ftp://ftp.suse.com/pub/people/jeffm/linux/macio-hotplug/ Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | | | [PATCH] openfirmware: add sysfs nodes for open firmware devicesJeff Mahoney2005-07-063-1/+54
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds sysfs nodes that the hotplug userspace can use to load the appropriate modules. In order for hotplug to work with macio devices, patches to module-init-tools and hotplug must be applied. Those patches are available at: ftp://ftp.suse.com/pub/people/jeffm/linux/macio-hotplug/ Changes: The previous versions were built on 2.6.12. 2.6.13-rcX introduced a device_attribute parameter to the show functions. Since that parameter was treated as the output buffer, memory corruption would result, causing Oopsen very quickly. Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | | | [PATCH] openfirmware: generate device table for userspaceJeff Mahoney2005-07-0619-93/+91
| |_|/ |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This converts the usage of struct of_match to struct of_device_id, similar to pci_device_id. This allows a device table to be generated, which can be parsed by depmod(8) to generate a map file for module loading. In order for hotplug to work with macio devices, patches to module-init-tools and hotplug must be applied. Those patches are available at: ftp://ftp.suse.com/pub/people/jeffm/linux/macio-hotplug/ Signed-off-by: Jeff Mahoney <jeffm@suse.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | | [PATCH] Fix bt87x.c build problem for realDave Jones2005-07-061-1/+1
| | | | | | | | | | | | | | | | | | | | | Just the declaration fix wasn't enough to fix things in bt78x.c Signed-off-by: Dave Jones <davej@redhat.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | | [PATCH] Fix broken kmalloc_node in rc1/rc2Christoph Lameter2005-07-061-0/+3
| |/ |/| | | | | | | | | | | | | | | | | | | | | | | | | This patch used to be in Andrew's tree before the NUMA slab allocator went in. Either this patch or the NUMA slab allocator is needed in order for kmalloc_node to work correctly. pcibus_to_node may be used to generate the node information passed to kmalloc_node. pcibus_to_node returns -1 if it was not able to determine on which node a pcibus is located. For that case kmalloc_node must work like kmalloc. Signed-off-by: Christoph Lameter <christoph@lameter.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] Fix bt87x.c build problemGreg KH2005-07-061-0/+2
| | | | | | | | | | | | | | Missing forward declaration Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] PCI: fix !CONFIG_HOTPLUG pci build problemGreg KH2005-07-061-2/+2
|/ | | | | | | | Here's a patch to fix the build issue when CONFIG_HOTPLUG is not enabled in 2.6.13-rc2. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Linux v2.6.13-rc3v2.6.13-rc2Linus Torvalds2005-07-051-1/+1
|
* Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6Linus Torvalds2005-07-051-2/+3
|\
| * [SPARC64]: Fix UltraSPARC-III fallout from membar changes.David S. Miller2005-07-051-2/+3
| | | | | | | | | | | | | | | | The membar changes made the size of __cheetah_flush_tlb_pending grow by one instruction, but the boot-time code patching was not updated to match. Signed-off-by: David S. Miller <davem@davemloft.net>
* | [PATCH] kprobes: fix namespace problem and sparc64 buildRusty Lynch2005-07-057-6/+11
| | | | | | | | | | | | | | | | | | | | | | | | The following renames arch_init, a kprobes function for performing any architecture specific initialization, to arch_init_kprobes in order to cleanup the namespace. Also, this patch adds arch_init_kprobes to sparc64 to fix the sparc64 kprobes build from the last return probe patch. Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] ppc32: explicitly disable 440GP IRQ compatibility mode in 440GX setupEugene Surovegin2005-07-051-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | Add explicit disabling of 440GP IRQ compatibility mode when configuring 440GX interrupt controller. This helps when board firmware for some reason uses this compatibility mode and leaves it enabled. It breaks 440GX interrupt code because it assumes native 440GX IRQ mode. People seems to be continuously bitten by this. Signed-off-by: Eugene Surovegin <ebs@ebshome.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] ppc32: stop misusing NTP's time_offset valuejohn stultz2005-07-051-5/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | As part of my timeofday rework, I've been looking at the NTP code and I noticed that the PPC architecture is apparently misusing the NTP's time_offset (it is a terrible name!) value as some form of timezone offset. This could cause problems when time_offset changed by the NTP code. This patch changes the PPC code so it uses a more clear local variable: timezone_offset. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Tom Rini <trini@kernel.crashing.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] ppc32: add Freescale MPC885ADS board supportAndrei Konovalov2005-07-058-16/+1550
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds the Freescale MPC86xADS board support. The supported devices are SMC UART and 10Mbit ethernet on SCC1. The manual for the board says that it "is compatible with the MPC8xxFADS for software point of view". That's why this patch extends FADS instead of introducing a new platform. FEC is not supported as the "combined FCC/FEC ethernet driver" driver by Pantelis Antoniou should replace the current FEC driver. Signed-off-by: Gennadiy Kurtsman <gkurtsman@ru.mvista.com> Signed-off-by: Andrei Konovalov <akonovalov@ru.mvista.com> Acked-by: Tom Rini <trini@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6Linus Torvalds2005-07-0534-617/+1191
|\ \ | |/ |/|
| * [IPV4]: Add LC-Trie implementation notesRobert Olsson2005-07-051-0/+145
| | | | | | | | | | Signed-off-by: Robert Olsson <Robert.Olsson@data.slu.se> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Never TSO defer under periods of congestion.David S. Miller2005-07-051-0/+3
| | | | | | | | | | | | | | | | | | Congestion window recover after loss depends upon the fact that if we have a full MSS sized frame at the head of the send queue, we will send it. TSO deferral can defeat the ACK clocking necessary to exit cleanly from recovery. Signed-off-by: David S. Miller <davem@davemloft.net>
| * [PKT_SCHED]: Blackhole queueing disciplineThomas Graf2005-07-052-1/+55
| | | | | | | | | | | | | | | | | | | | | | | | Useful in combination with classful qdiscs to drop or temporary disable certain flows, e.g. one could block specific ds flows with dsmark. Unlike the noop qdisc it can be controlled by the user and statistic accounting is done. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Move to new TSO segmenting scheme.David S. Miller2005-07-057-240/+384
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make TSO segment transmit size decisions at send time not earlier. The basic scheme is that we try to build as large a TSO frame as possible when pulling in the user data, but the size of the TSO frame output to the card is determined at transmit time. This is guided by tp->xmit_size_goal. It is always set to a multiple of MSS and tells sendmsg/sendpage how large an SKB to try and build. Later, tcp_write_xmit() and tcp_push_one() chop up the packet if necessary and conditions warrant. These routines can also decide to "defer" in order to wait for more ACKs to arrive and thus allow larger TSO frames to be emitted. A general observation is that TSO elongates the pipe, thus requiring a larger congestion window and larger buffering especially at the sender side. Therefore, it is important that applications 1) get a large enough socket send buffer (this is accomplished by our dynamic send buffer expansion code) 2) do large enough writes. Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Break out send buffer expansion test.David S. Miller2005-07-051-4/+23
| | | | | | | | | | | | | | This makes it easier to understand, and allows easier tweaking of the heuristic later on. Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Do not call tcp_tso_acked() if no work to do.David S. Miller2005-07-051-1/+2
| | | | | | | | | | | | | | In tcp_clean_rtx_queue(), if the TSO packet is not even partially acked, do not waste time calling tcp_tso_acked(). Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Kill bogus comment above tcp_tso_acked().David S. Miller2005-07-051-9/+0
| | | | | | | | | | | | | | | | Everything stated there is out of data. tcp_trim_skb() does adjust the available socket send buffer space and skb->truesize now. Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Fix send-side cpu utiliziation regression.David S. Miller2005-07-051-2/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Only put user data purely to pages when doing TSO. The extra page allocations cause two problems: 1) Add the overhead of the page allocations themselves. 2) Make us do small user copies when we get to the end of the TCP socket cache page. It is still beneficial to purely use pages for TSO, so we will do it for that case. Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-06 05:47:01 +0000