summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* [ARM] 3572/1: netX: framebuffer driver for Hilscher netXSascha Hauer2006-06-192-0/+138
| | | | | | | | | | | Patch from Sascha Hauer This patch adds framebuffer support for Hilscher's netX network processors. Signed-off-by: Robert Schwebel <r.schwebel@pengutronix.de> Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3566/1: netX: register definitionsSascha Hauer2006-06-191-0/+410
| | | | | | | | | | | Patch from Sascha Hauer This patch adds the register definitions for Hilscher's netX network processors. Signed-off-by: Robert Schwebel <r.schwebel@pengutronix.de> Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3578/1: AT91RM9200 Clock updateAndrew Victor2006-06-191-20/+101
| | | | | | | | | | | | | | | | | Patch from Andrew Victor Some updates to the clock infrastructure for the AT91RM9200. 1. Hard-coded values replaced with names defined in at91rm9200_sys.h. 2. Added the four PIO clocks, which are enabled at startup. 3. At startup, disable all unused clocks. 4. Minor bugfix for usage counts associated with MCK. [Patch from David Brownell] 5. Added at91_clock_associate() function to associate device & function with a particular clock. [Patch from David Brownell] Signed-off-by: Andrew Victor <andrew@sanpeople.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3563/1: LED: Set the LOCOMO LED driver default triggersRichard Purdie2006-06-191-0/+2
| | | | | | | | | Patch from Richard Purdie Set the default triggers for the LOCOMO LED driver. Signed-off-by: Richard Purdie <rpurdie@rpsys.net> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3559/1: S3C2442: core and serial portBen Dooks2006-06-1817-225/+664
| | | | | | | | | | | Patch from Ben Dooks Core support for the Samsung S3C2442, and the serial port driver update to allow the serial port blocks to be used. Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3557/1: S3C24XX: centralise and cleanup uart registrationBen Dooks2006-06-1815-185/+154
| | | | | | | | | | | | | Patch from Ben Dooks All the S3C24XX based devices currently have similar uart blocks, in the same location. Make the process of adding new uart blocks easier by commonising the device definitions and adding a new init function for the cpu code. Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3558/1: SMDK24XX: LED platform devicesBen Dooks2006-06-181-0/+65
| | | | | | | | | Patch from Ben Dooks Platform devices for the LEDs on all the SMDK24XX boards Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3534/1: add spi support to lubbock platformDavid Brownell2006-06-181-0/+84
| | | | | | | | | | | | | | | | Patch from David Brownell This adds the platform device for SSP/SPI controller, and declares the ads7846 device hooked up to it. Not all Lubbock boards appear to populate the connector needed to use this instead of the ucb1400 chip, but it can always be used as a temperature sensor. In short, this is probably most useful as an example of how to provide the configuration data used by the pxa2xx_spi driver. (Last tested against a slightly earlier version of that driver.) Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3554/1: ARM: Fix dyntick lockingTony Lindgren2006-06-183-9/+20
| | | | | | | | | | Patch from Tony Lindgren This patch fixes some dyntick locking issues on ARM as pointed out by Russell King. Signed-off-by: Tony Lindgren <tony@atomide.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3553/1: S3C24XX: earlier print of cpu idcode infoBen Dooks2006-06-181-2/+2
| | | | | | | | | | | Patch from Ben Dooks Move the printk of the CPU information and IDCODE before the checking of the table entry validity to aide in debugging new cpu entries. Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3552/1: S3C24XX: Move VA of GPIO for low-level debugBen Dooks2006-06-181-1/+10
| | | | | | | | | | | | | | | | Patch from Ben Dooks Using the low-level debug routines early in the kernel debug cause the 1:1 mapping to get into the TLB, which is not flushed until after the CPU detection process (which needs the GPIO VA). This patch moves the VA for the GPIO to the same offset as the physical offset of the UART to the GPIO. Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3551/1: S3C24XX: PM code failes to compile with CONFIG_DCACHE_WRITETHROUGHBen Dooks2006-06-182-0/+6
| | | | | | | | | | | | | | Patch from Ben Dooks If CONFIG_CPU_DCACHE_WRITETHOUGH is set, then the S3C24XX PM code fails to compile, as there is no need to flush the D-cache, the flush function arm920_flush_kern_cache_all() is not compiled. Fix the code to not use this if the config is set. Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3550/1: OSIRIS: fix serial port map for 1:1Ben Dooks2006-06-181-1/+1
| | | | | | | | | | | Patch from Ben Dooks The default serial port-mapping for the Osiris has the port 2 mapped onto the first serial port, and no port1. Correct this so port 1 is port. Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3548/1: Fix the ARMv6 CPU id in compressed/head.SCatalin Marinas2006-06-181-2/+2
| | | | | | | | | | | Patch from Catalin Marinas This code was still using the old format for the ARMv6 CPU id and it wasn't flushing the caches on the MPCore CPU (and other ARM1176 cores). The patch changes the mask bits to cope with the new id format. Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3335/1: Old-abi Thumb sys_syscall brokenPaul Brook2006-06-181-1/+1
| | | | | | | | | | | | | | | | Patch from Paul Brook The old-abi sys_syscall syscall is broken when called from Thumb mode. It assumes the syscall number is an Arm syscall number (ie. starts from __NR_OABI_SYSCALL_BASE). In thumb mode syscall numbers start from zero. The patch below fixes this by clearing the nigh bits of the syscall number instead of inverting them. Technically this means we accept some invalid syscall numbers, but I can't see how that could be a problem. The two sets of numbers far apart that unimplemented syscalls should still be rejected. Signed-off-by: Paul Brook <paul@codesourcery.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3467/1: [3/3] Support for Philips PNX4008 platform: defconfigVitaly Wool2006-06-181-0/+2072
| | | | | | | | | | | Patch from Vitaly Wool This patch adds default configuration file PNX4008 ARM platform. It\'s basically the same as the previos one. Signed-off-by: Vitaly Wool <vwool@ru.mvista.com> Signed-off-by: Dmitry Pervushin <dpervushin@gmail.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3466/1: [2/3] Support for Philips PNX4008 platform: chip supportVitaly Wool2006-06-1815-2/+3434
| | | | | | | | | | | | Patch from Vitaly Wool This patch adds basic chip support for PNX4008 ARM platform. It's basically the same as the previous one, but with the rmk's comments taken into account. Signed-off-by: Vitaly Wool <vwool@ru.mvista.com> Signed-off-by: Dmitry Pervushin <dpervushin@gmail.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3465/1: [1/3] Support for Philips PNX4008 platform: headersVitaly Wool2006-06-1817-0/+1173
| | | | | | | | | | | Patch from Vitaly Wool This patch adds kernel headers for PNX4008 ARM platform. It's basically the same as the previos one, but with the rmk's comments taken into account. Signed-off-by: Vitaly Wool <vwool@ru.mvista.com> Signed-off-by: Dmitry Pervushin <dpervushin@gmail.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3407/1: lpd7x: documetation updateMarc Singer2006-06-182-0/+120
| | | | | | | | | Patch from Marc Singer New documentation for the touchscreen controllers and LCD panels. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3406/1: lpd7x: compilation fix for smc91xMarc Singer2006-06-181-16/+28
| | | | | | | | | | | Patch from Marc Singer Reworking of the adaptation macros to allow driver to compile again for the lpd7x's. Also, support added for the lh79520 so it may use the smc91x. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3405/1: lpd7a40x: CPLD ssp driverMarc Singer2006-06-182-0/+348
| | | | | | | | | | Patch from Marc Singer Driver for operating SSP devices through LPD7A40X CPLD chip. This driver is used by the audio codecs. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3404/1: lpd7a40x: AMBA CLCD supportMarc Singer2006-06-182-0/+304
| | | | | | | | | | Patch from Marc Singer Board support and LCD panel configurations to integrate lh7a40x's with the amba clcd driver. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3403/1: lpd7a40x: updated default configurationsMarc Singer2006-06-182-127/+438
| | | | | | | | | Patch from Marc Singer Revised default configuration files. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3402/1: lpd7a40x: serial driver bug fixMarc Singer2006-06-181-4/+9
| | | | | | | | | Patch from Marc Singer The serial driver now sets up the third UART when it is to be used. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3401/1: lpd7a40x: platform updateMarc Singer2006-06-186-76/+433
| | | | | | | | | | Patch from Marc Singer Updates to the lpd7a40x_platform files. Includes support for new architecture, lpd7a400. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3400/1: lpd7a40x: platform headers updateMarc Singer2006-06-1810-21/+581
| | | | | | | | | | Patch from Marc Singer Updates to the lpd7a40x platform headers. Includes support for new architecture, lpd7a400. Signed-off-by: Marc Singer <elf@buici.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* Linux v2.6.17v2.6.17Linus Torvalds2006-06-171-1/+1
| | | | | Being named "Crazed Snow-Weasel" instills a lot of confidence in this release, so I'm sure this will be one of the better ones.
* [PATCH] powerpc: enable CPU_FTR_CI_LARGE_PAGE for cellArnd Bergmann2006-06-171-1/+1
| | | | | | | | Reflect the fact that the Cell Broadband Engine supports 64k pages by adding the bit to the CPU features. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] powerpc: Fix 64k pages on non-partitioned machinesArnd Bergmann2006-06-171-2/+2
| | | | | | | | | | | | | The page size encoding passed to tlbie is incorrect for new-style large pages. This fixes it. This doesn't affect anything on older machines because mmu_psize_defs[psize].penc (the page size encoding) is 0 for 4k and 16M pages (the two are distinguished by a separate "is a large page" bit). Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] arm_timer: remove a racy and obsolete PF_EXITING checkOleg Nesterov2006-06-171-3/+0
| | | | | | | | | | | | | | | | | | arm_timer() checks PF_EXITING to prevent BUG_ON(->exit_state) in run_posix_cpu_timers(). However, for some reason it does so only for CPUCLOCK_PERTHREAD case (which is imho wrong). Also, this check is not reliable, PF_EXITING could be set on another cpu without any locks/barriers just after the check, so it can't prevent from attaching the timer to the exiting task. The previous patch makes this check unneeded. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] run_posix_cpu_timers: remove a bogus BUG_ON()Oleg Nesterov2006-06-172-26/+18
| | | | | | | | | | | | | | | | | | | | | | | do_exit() clears ->it_##clock##_expires, but nothing prevents another cpu to attach the timer to exiting process after that. arm_timer() tries to protect against this race, but the check is racy. After exit_notify() does 'write_unlock_irq(&tasklist_lock)' and before do_exit() calls 'schedule() local timer interrupt can find tsk->exit_state != 0. If that state was EXIT_DEAD (or another cpu does sys_wait4) interrupted task has ->signal == NULL. At this moment exiting task has no pending cpu timers, they were cleanuped in __exit_signal()->posix_cpu_timers_exit{,_group}(), so we can just return from irq. John Stultz recently confirmed this bug, see http://marc.theaimsgroup.com/?l=linux-kernel&m=115015841413687 Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] check_process_timers: fix possible lockupOleg Nesterov2006-06-171-5/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | If the local timer interrupt happens just after do_exit() sets PF_EXITING (and before it clears ->it_xxx_expires) run_posix_cpu_timers() will call check_process_timers() with tasklist_lock + ->siglock held and check_process_timers: t = tsk; do { .... do { t = next_thread(t); } while (unlikely(t->flags & PF_EXITING)); } while (t != tsk); the outer loop will never stop. Actually, the window is bigger. Another process can attach the timer after ->it_xxx_expires was cleared (see the next commit) and the 'if (PF_EXITING)' check in arm_timer() is racy (see the one after that). Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sky2: netconsole suspend/resume interactionStephen Hemminger2006-06-171-1/+6
| | | | | | | | | | | | | A couple of fixes that should prevent crashes when using netconsole and suspend/resume. First, netconsole poll routine shouldn't run unless the device is up; second, the NAPI poll should be disabled during suspend. This is only an issue on sky2, because it has to have one NAPI poll routine for both ports on dual port boards. Normal drivers use netif_rx_schedule_prep and that checks for netif_running. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] Fix missing ret assignment in __bio_map_user() error pathJens Axboe2006-06-171-2/+3
| | | | | | | | | | | | If get_user_pages() returns less pages than what we asked for, we jump to out_unmap which will return ERR_PTR(ret). But ret can contain a positive number just smaller than local_nr_pages, so be sure to set it to -EFAULT always. Problem found and diagnosed by Damien Le Moal <damien@sdl.hitachi.co.jp> Signed-off-by: Jens Axboe <axboe@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] fix cdrom openJens Axboe2006-06-171-2/+4
| | | | | | | | | | | | | | | | Some time ago the cdrom open routine was changed so that we call the driver's open routine before checking to see if it is read only. However, if we discovered that a read write open was not possible and the open flags required a writable open, we just returned -EROFS without calling the driver's release routine. This seems to work for most cdrom drivers, but breaks the Powerpc iSeries virtual cdrom rather badly. This just inserts the release call in the error path to balance the call to "->open()" done by "open_for_data()". Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Jens Axboe <axboe@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] cfq-iosched: fix crash in do_div()Jens Axboe2006-06-141-8/+3
| | | | | | | | | | | | | We don't clear the seek stat values in cfq_alloc_io_context(), and if ->seek_mean is unlucky enough to be set to -36 by chance, the first invocation of cfq_update_io_seektime() will oops with a divide by zero in do_div(). Just memset the entire cic instead of filling invididual values independently. Signed-off-by: Jens Axboe <axboe@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] Return error in case flock_lock_file failureKirill Korotaev2006-06-141-0/+2
| | | | | | | | | If flock_lock_file() failed to allocate flock with locks_alloc_lock() then "error = 0" is returned. Need to return some non-zero. Signed-off-by: Pavel Emelianov <xemul@openvz.org> Signed-off-by: Kirill Korotaev <dev@openvz.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sky2: stop/start hardware idle timer on suspend/resumeStephen Hemminger2006-06-131-4/+13
| | | | | | | | | The resume bug was caused not by an early interrupt but because the idle timeout was not being stopped on suspend. Also disable hardware IRQ's on suspend. Will need to revisit this with hotplug? Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sky2: save/restore base hardware irq during suspend/resumeStephen Hemminger2006-06-131-0/+3
| | | | | | | | The hardware should be fully shut off during suspend, and the base irq mask restored during resume. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sky2: fix hotplug detect during pollStephen Hemminger2006-06-131-2/+2
| | | | | | | | If the poll routine detects no hardware available, it needs to dequeue it self from the network poll list. Linus didn't understand NAPI. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sky2: don't hard code number of portsStephen Hemminger2006-06-131-2/+2
| | | | | | | It is cleaner, to not loop over both ports if only one exists. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sky2: set_power_state should be voidStephen Hemminger2006-06-131-8/+8
| | | | | | | | | The set power state function is cleaner if it doesn't return anything. The only caller that could fail is in suspend() and it can check the argument there. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] alpha: generic hweight build fixRandy Dunlap2006-06-121-1/+1
| | | | | | | | | | | | | | From: Randy Dunlap <rdunlap@xenotime.net> According to include/asm-alpha/bitops.h, only ALPHA_EV67 has hardware hweight support, so ALPHA_EV6 needs to use GENERIC_HWEIGHT. Signed-off-by: Randy Dunlap <rdunlap@xenotime.net> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Ernst Herzberg <earny@net4u.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] tmpfs: Decrement i_nlink correctly in shmem_rmdir()Sergey Vlasov2006-06-121-0/+1
| | | | | | | | | | shmem_rmdir() must undo the increment of i_nlink done in shmem_get_inode() for directories, otherwise at least IN_DELETE_SELF inotify event generation is broken. Signed-off-by: Sergey Vlasov <vsu@altlinux.ru> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] tmpfs: time granularity fix for [acm]time going backwardsRobin H. Johnson2006-06-121-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | I noticed a strange behavior in a tmpfs file system the other day, while building packages - occasionally, and seemingly at random, make decided to rebuild a target. However, only on tmpfs. A file would be created, and if checked, it had a sub-second timestamp. However, after an utimes related call where sub-seconds should be set, they were zeroed instead. In the case that a file was created, and utimes(...,NULL) was used on it in the same second, the timestamp on the file moved backwards. After some digging, I found that this was being caused by tmpfs not having a time granularity set, thus inheriting the default 1 second granularity. Hugh adds: yes, we missed tmpfs when the s_time_gran mods went into 2.6.11. Unfortunately, the granularity of CURRENT_TIME, often used in filesystems, does not match the default granularity set by alloc_super. A few more such discrepancies have been found, but this is the most important to fix now. Signed-off-by: Robin H. Johnson <robbat2@gentoo.org> Acked-by: Andi Kleen <ak@suse.de> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6Linus Torvalds2006-06-121-1/+0
|\ | | | | | | | | * master.kernel.org:/pub/scm/linux/kernel/git/davem/sparc-2.6: [SPARC64]: Do not double-export sys_close() when CONFIG_SOLARIS_EMUL_MODULE
| * [SPARC64]: Do not double-export sys_close() when CONFIG_SOLARIS_EMUL_MODULEDavid S. Miller2006-06-111-1/+0
| | | | | | | | | | | | | | | | It is already exported by fs/open.c Noticed by Ben Collins. Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6Linus Torvalds2006-06-123-3/+3
|\ \ | | | | | | | | | | | | | | | | | | * master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: [IPV4]: Increment ipInHdrErrors when TTL expires. [TCP]: continued: reno sacked_out count fix [DCCP] Ackvec: fix soft lockup in ackvec handling code
| * | [IPV4]: Increment ipInHdrErrors when TTL expires.Weidong2006-06-121-0/+1
| | | | | | | | | | | | | | | | | | Signed-off-by: Weidong <weid@nanjing-fnst.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | [TCP]: continued: reno sacked_out count fixAki M Nyrhinen2006-06-111-3/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | From: Aki M Nyrhinen <anyrhine@cs.helsinki.fi> IMHO the current fix to the problem (in_flight underflow in reno) is incorrect. it treats the symptons but ignores the problem. the problem is timing out packets other than the head packet when we don't have sack. i try to explain (sorry if explaining the obvious). with sack, scanning the retransmit queue for timed out packets is fine because we know which packets in our retransmit queue have been acked by the receiver. without sack, we know only how many packets in our retransmit queue the receiver has acknowledged, but no idea which packets. think of a "typical" slow-start overshoot case, where for example every third packet in a window get lost because a router buffer gets full. with sack, we check for timeouts on those every third packet (as the rest have been sacked). the packet counting works out and if there is no reordering, we'll retransmit exactly the packets that were lost. without sack, however, we check for timeout on every packet and end up retransmitting consecutive packets in the retransmit queue. in our slow-start example, 2/3 of those retransmissions are unnecessary. these unnecessary retransmissions eat the congestion window and evetually prevent fast recovery from continuing, if enough packets were lost. Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.25.1) at 2024-08-25 08:57:07 +0000