summaryrefslogtreecommitdiffstats
path: root/include
Commit message (Collapse)AuthorAgeFilesLines
* [PATCH] sched: consolidate sbe sbfNick Piggin2005-06-251-1/+1
| | | | | | | | | | | | | | | | Consolidate balance-on-exec with balance-on-fork. This is made easy by the sched-domains RCU patches. As well as the general goodness of code reduction, this allows the runqueues to be unlocked during balance-on-fork. schedstats is a problem. Maybe just have balance-on-event instead of distinguishing fork and exec? Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sched: cleanup context switch lockingNick Piggin2005-06-258-73/+23
| | | | | | | | | | | | | | | | Instead of requiring architecture code to interact with the scheduler's locking implementation, provide a couple of defines that can be used by the architecture to request runqueue unlocked context switches, and ask for interrupts to be enabled over the context switch. Also replaces the "switch_lock" used by these architectures with an oncpu flag (note, not a potentially slow bitflag). This eliminates one bus locked memory operation when context switching, and simplifies the task_running function. Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sched: sched tuningNick Piggin2005-06-254-23/+54
| | | | | | | | Do some basic initial tuning. Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sched: schedstats update for balance on forkNick Piggin2005-06-251-2/+8
| | | | | | | | Add SCHEDSTAT statistics for sched-balance-fork. Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sched: balance on forkNick Piggin2005-06-253-4/+10
| | | | | | | | | | | | | | | | | | Reimplement the balance on exec balancing to be sched-domains aware. Use this to also do balance on fork balancing. Make x86_64 do balance on fork over the NUMA domain. The problem that the non sched domains aware blancing became apparent on dual core, multi socket opterons. What we want is for the new tasks to be sent to a different socket, but more often than not, we would first load up our sibling core, or fill two cores of a single remote socket before selecting a new one. This gives large improvements to STREAM on such systems. Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sched: no aggressive idle balancingNick Piggin2005-06-253-3/+0
| | | | | | | | | | Remove the very aggressive idle stuff that has recently gone into 2.6 - it is going against the direction we are trying to go. Hopefully we can regain performance through other methods. Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sched: balance timersNick Piggin2005-06-254-1/+21
| | | | | | | | | | | | | Do CPU load averaging over a number of different intervals. Allow each interval to be chosen by sending a parameter to source_load and target_load. 0 is instantaneous, idx > 0 returns a decaying average with the most recent sample weighted at 2^(idx-1). To a maximum of 3 (could be easily increased). So generally a higher number will result in more conservative balancing. Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] RCU: clean up a few remaining synchronize_kernel() callsPaul E. McKenney2005-06-255-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 2.6.12-rc6-mm1 has a few remaining synchronize_kernel()s, some (but not all) in comments. This patch changes these synchronize_kernel() calls (and comments) to synchronize_rcu() or synchronize_sched() as follows: - arch/x86_64/kernel/mce.c mce_read(): change to synchronize_sched() to handle races with machine-check exceptions (synchronize_rcu() would not cut it given RCU implementations intended for hardcore realtime use. - drivers/input/serio/i8042.c i8042_stop(): change to synchronize_sched() to handle races with i8042_interrupt() interrupt handler. Again, synchronize_rcu() would not cut it given RCU implementations intended for hardcore realtime use. - include/*/kdebug.h comments: change to synchronize_sched() to handle races with NMIs. As before, synchronize_rcu() would not cut it... - include/linux/list.h comment: change to synchronize_rcu(), since this comment is for list_del_rcu(). - security/keys/key.c unregister_key_type(): change to synchronize_rcu(), since this is interacting with RCU read side. - security/keys/process_keys.c install_session_keyring(): change to synchronize_rcu(), since this is interacting with RCU read side. Signed-off-by: "Paul E. McKenney" <paulmck@us.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] s390: debug feature changesMichael Holzheu2005-06-251-19/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | This patch changes the memory allocation method for the s390 debug feature. Trace buffers had been allocated using the get_free_pages() function before. Therefore it was not possible to get big memory areas in a running system due to memory fragmentation. Now the trace buffers are subdivided into several subbuffers with pagesize. Therefore it is now possible to allocate more memory for the trace buffers and more trace records can be written. In addition to that, dynamic specification of the size of the trace buffers is implemented. It is now possible to change the size of a trace buffer using a new debugfs file instance. When writing a number into this file, the trace buffer size is changed to 'number * pagesize'. In the past all the traces could be obtained from userspace by accessing files in the "proc" filesystem. Now with debugfs we have a new filesystem which should be used for debugging purposes. This patch moves the debug feature from procfs to debugfs. Since the interface of debug_register() changed, all device drivers, which use the debug feature had to be adjusted. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] s390: add vmcp interfaceChristian Borntraeger2005-06-251-2/+16
| | | | | | | | Add interface to issue VM control program commands. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] s390: improved machine check handlingHeiko Carstens2005-06-255-40/+44
| | | | | | | | | | Improved machine check handling. Kernel is now able to receive machine checks while in kernel mode (system call, interrupt and program check handling). Also register validation is now performed. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] uml: add profile_pc for i386Paolo 'Blaisorblade' Giarrusso2005-06-251-0/+4
| | | | | | | | | | | Cope with a conditional i386 definition, which is wrong for UML. Before we just used that one, but it wasn't defined for CONFIG_SMP, so in that case we got link errors. Signed-off-by: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Jeff Dike <jdike@addtoit.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] swsusp: clean assembly partsPavel Machek2005-06-251-1/+1
| | | | | | | | | | | This patch fixes register saving so that each register is only saved once, and adds missing saving of %cr8 on x86-64. Some reordering so that save/restore is more logical/safer (segment registers should be restored after gdt). Signed-off-by: Pavel Machek <pavel@suse.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] properly stop devices before poweroffPavel Machek2005-06-251-12/+21
| | | | | | | | | Without this patch, Linux provokes emergency disk shutdowns and similar nastiness. It was in SuSE kernels for some time, IIRC. Signed-off-by: Pavel Machek <pavel@suse.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] suspend/resume SMP supportLi Shaohua2005-06-251-1/+1
| | | | | | | | | | Using CPU hotplug to support suspend/resume SMP. Both S3 and S4 use disable/enable_nonboot_cpus API. The S4 part is based on Pavel's original S4 SMP patch. Signed-off-by: Li Shaohua<shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] x86_64: Dont use broadcast shortcut to make it cpu hotplug safe.Ashok Raj2005-06-251-0/+2
| | | | | | | | | | | | | | | | | | | | | | | Broadcast IPI's provide un-expected behaviour for cpu hotplug. CPU's in offline state also end up receiving the IPI. Once the cpus become online they receive these stale IPI's which are bad and introduce unexpected behaviour. This is easily avoided by not sending a broadcast and addressing just the CPU's in online map. Doing prelim cycle counts it appears there is no big overhead and numbers seem around 0x3000-0x3900 on an average on x86 and x86_64 systems with CPUS running 3G, both for broadcast and mask version of the API's. The shortcuts are useful only for flat mode (where the perf shows no degradation), and in cluster mode, its unicast anyway. Its simpler to just not use broadcast anymore. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Andi Kleen <ak@muc.de> Acked-by: Zwane Mwaikambo <zwane@arm.linux.org.uk> Signed-off-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] x86_64: CPU hotplug supportAshok Raj2005-06-252-0/+7
| | | | | | | | | | | | | | | | | | | | Experimental CPU hotplug patch for x86_64 ----------------------------------------- This supports logical CPU online and offline. - Test with maxcpus=1, and then kick other cpu's off to test if init code is all cleaned up. CONFIG_SCHED_SMT works as well. - idle threads are forked on demand from keventd threads for clean startup TBD: 1. Not tested on a real NUMA machine (tested with numa=fake=2) 2. Handle ACPI pieces for physical hotplug support. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Andi Kleen <ak@muc.de> Acked-by: Zwane Mwaikambo <zwane@arm.linux.org.uk> Signed-off-by: Shaohua.li<shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] x86_64: Change init sections for CPU hotplug supportAshok Raj2005-06-251-0/+12
| | | | | | | | | | | | | | | | | | | | | This patch adds __cpuinit and __cpuinitdata sections that need to exist past boot to support cpu hotplug. Caveat: This is done *only* for EM64T CPU Hotplug support, on request from Andi Kleen. Much of the generic hotplug code in kernel, and none of the other archs that support CPU hotplug today, i386, ia64, ppc64, s390 and parisc dont mark sections with __cpuinit, but only mark them as __devinit, and __devinitdata. If someone is motivated to change generic code, we need to make sure all existing hotplug code does not break, on other arch's that dont use __cpuinit, and __cpudevinit. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Andi Kleen <ak@muc.de> Acked-by: Zwane Mwaikambo <zwane@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] make smp_prepare_cpu to a weak functionAshok Raj2005-06-252-3/+1
| | | | | | | | | | | | | | I really wish smp_prepare_cpu() would disappear eventually. In the interim this is ideally a weak function, so we dont end up changing several places to define this dummy in headers. Today since the dummy declaration is done only in drivers/base/cpu.c but the function is called in kernel/power/smp.c i get undefined reference in my cpu hotplug code for x86_64 under development. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] cpu state clean after hot removeLi Shaohua2005-06-252-0/+10
| | | | | | | | Clean CPU states in order to reuse smp boot code for CPU hotplug. Signed-off-by: Li Shaohua<shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] sep initializing reworkLi Shaohua2005-06-252-0/+4
| | | | | | | | | Make SEP init per-cpu, so it is hotplug safe. Signed-off-by: Li Shaohua<shaohua.li@intel.com> Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] i386: Dont use IPI broadcast when using cpu hotplug.Ashok Raj2005-06-251-2/+25
| | | | | | | | | | | | | | | | This patch introduces a startup parameter no_broadcast. When we enable CONFIG_HOTPLUG_CPU, we dont want to use broadcast shortcut as it has ill effects on a offline cpu. If we issue broadcast, the IPI is also delivered to offline cpus, or partially up cpu causing stale IPI's to be handled, which is a problem and can cause undesirable effects. Introduces a new startup cmdline option no_ipi_broadcast, that can be switched at cmdline if necessary. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Shaohua Li <shaohua.li@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] i386 CPU hotplugZwane Mwaikambo2005-06-253-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | (The i386 CPU hotplug patch provides infrastructure for some work which Pavel is doing as well as for ACPI S3 (suspend-to-RAM) work which Li Shaohua <shaohua.li@intel.com> is doing) The following provides i386 architecture support for safely unregistering and registering processors during runtime, updated for the current -mm tree. In order to avoid dumping cpu hotplug code into kernel/irq/* i dropped the cpu_online check in do_IRQ() by modifying fixup_irqs(). The difference being that on cpu offline, fixup_irqs() is called before we clear the cpu from cpu_online_map and a long delay in order to ensure that we never have any queued external interrupts on the APICs. There are additional changes to s390 and ppc64 to account for this change. 1) Add CONFIG_HOTPLUG_CPU 2) disable local APIC timer on dead cpus. 3) Disable preempt around irq balancing to prevent CPUs going down. 4) Print irq stats for all possible cpus. 5) Debugging check for interrupts on offline cpus. 6) Hacky fixup_irqs() to redirect irqs when cpus go off/online. 7) play_dead() for offline cpus to spin inside. 8) Handle offline cpus set in flush_tlb_others(). 9) Grab lock earlier in smp_call_function() to prevent CPUs going down. 10) Implement __cpu_disable() and __cpu_die(). 11) Enable local interrupts in cpu_enable() after fixup_irqs() 12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus. 13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline. Signed-off-by: Zwane Mwaikambo <zwane@linuxpower.ca> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] ppc32: Remove FSL OCP supportKumar Gala2005-06-252-58/+0
| | | | | | | | | | Support for the OCP device model on Freescale (FSL) PPC's is no longer used. All FSL PPC's that were using OCP have be converted to using the platform device model. Signed-off-by: Kumar Gala <kumar.gala@freescale.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] ppc32: Add support for Freescale e200 (Book-E) coreKumar Gala2005-06-255-3/+22
| | | | | | | | | | | | The e200 core is a Book-E core (similar to e500) that has a unified L1 cache and is not cache coherent on the bus. The e200 core also adds a separate exception level for debug exceptions. Part of this patch helps to cleanup a few cases that are true for all Freescale Book-E parts, not just e500. Signed-off-by: Kim Phillips <kim.phillips@freescale.com> Signed-off-by: Kumar Gala <kumar.gala@freescale.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] mips: add MIPS-specific support for flatmem/discontigmemYoichi Yuasa2005-06-253-2/+6
| | | | | | | | | 2.6.12-git6 doesn't boot on some MIPS machines. They need the support of flat memory and discontig memory. Signed-off-by: Yoichi Yuasa <yuasa@hh.iij4u.or.jp> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [PATCH] I8K: use standard DMI interfaceDmitry Torokhov2005-06-251-0/+1
| | | | | | | | | | | | I8K: Change to use stock dmi infrastructure instead of homegrown parsing code. The driver now requires box's DMI data to match list of supported models so driver can be safely compiled-in by default without fear of it poking into random SMM BIOS code. DMI checks can be ignored with i8k.ignore_dmi option. Signed-off-by: Dmitry Torokhov <dtor@mail.ru> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2005-06-254-7/+37
|\
| * [PATCH] ARM: Generic Dynamic Tick Timer support for ARM, take 4Russell King2005-06-252-0/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds support for Dynamic Tick Timer for ARM. Dynamic Tick is also known as VST (Variable Scheduling Timeouts). Dynamic Tick has been in use in the OMAP tree since last October. The patch is not intrusive, and does not do anything unless CONFIG_NO_IDLE_HZ is defined. This patch has the following fixed based on comments from RMK: - Time is updated before calling interrupt handlers. - Added new interrupt flag SA_TIMER to avoid duplicate timer interrupts - Moved struct dyn_tick_timer to time.h until we at some point probably have an arch independent dyn-tick.h - Cleaned up testing for DYN_TICK_ENABLED in irq.c I've cleaned up this patch to fix some remaining issues: - Call the timer tick handler with irqs disabled, as it would be from a normal interrupt - if we have a dyn_tick, we better implement all methods. - generic timer_dyn_reprogram() call, to be called before sleeping - added command line option - "dyntick=" to allow boot-time control of this feature -- rmk Signed-off-by: Tony Lindgren Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [PATCH] ARM: 2752/1: disable ixp2000 PCI I/O software workaround on chips ↵Lennert Buytenhek2005-06-252-7/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | that don't need it Patch from Lennert Buytenhek The later ixp2000 models don't need the PCI I/O workaround that we currently perform. Add a config option to disable the workaround, and panic on boot if a kernel without the workaround is booted on a buggy chip. As only pre-production ixp2000s need the workaround, the default is for it not to be configured in. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Deepak Saxena Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | [SPARC64]: Report any user access faults in termios accessors.David S. Miller2005-06-241-37/+41
|/ | | | Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2005-06-246-42/+100
|\
| * [PATCH] ARM: 2748/1: ixp2000 implementation of the iomap apiLennert Buytenhek2005-06-241-0/+72
| | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Lennert Buytenhek A number of ixp2000 models have a bug where the byte lanes for PCI I/O transactions are swapped. We already work around this in our versions of {in,out}{b,w,l}, but we also need to perform these workarounds in a custom implementation of the new iomap API, provided in this patch. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Deepak Saxena Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [PATCH] ARM: 2747/1: allow platforms to provide their own iomap implementationLennert Buytenhek2005-06-241-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Lennert Buytenhek This patch conditionalises the io{read,write}{8,16,32} defines and the prototypes for ioport_map/ioport_unmap in asm-arm/io.h on ioread8 not already having been defined. This is done so that platforms can provide their own implementation of the iomap API, ixp2000 for example needs this. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Deepak Saxena Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [PATCH] ARM: 2745/1: Fix IXP4xx debug macrosDeepak Saxena2005-06-242-0/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Deepak Saxena Current IXP4xx debug macros do not work in the small window between the MMU being enabled and the call to map_io() b/c the standard peripheral mapping is not properly setup for use with the low-level debug code. This patch creates a new section-aligned mapping for the UART specifically for use with the debug macros. Signed-off-by: Deepak Saxena Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [PATCH] ARM: 2744/1: ixp2000 gpio irq supportLennert Buytenhek2005-06-242-40/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Lennert Buytenhek This patch cleans up the ixp2000 gpio irq code and implements the set_irq_type method for gpio irqs so that users can select for which events (falling edge/rising edge/level low/level high) on the gpio pin they want the corresponding gpio irq to be triggered. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Deepak Saxena Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [PATCH] ARM: 2740/1: ixp2000 align{b,w} need to parenthesize their argumentsLennert Buytenhek2005-06-241-2/+2
| | | | | | | | | | | | | | | | | | | | | | Patch from Lennert Buytenhek Two macros that are used on the ixp2000 to fixup byte lane enables for I/O space accesses, align{b,w}, use their arguments without parenthesizing them. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | [PATCH] fs/qnx4/*: fix sparse warningsAlexey Dobriyan2005-06-242-17/+17
| | | | | | | | | | | | | | | | | | | | This patch fixes sparse warnings in the qnx4fs (and might even make qnx4fs work on big-endian boxes) Signed-off-by: Alexey Dobriyan <adobriyan@mail.ru> Signed-off-by: Domen Puncer <domen@coderock.org> Signed-off-by: Anders Larsen <al@alarsen.net> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | Add "memory" clobbers to the x86 inline asm of strncmp and friendsLinus Torvalds2005-06-241-10/+22
|/ | | | | | | | | | They don't actually clobber memory, but gcc doesn't even know they _read_ memory, so can apparently re-order memory accesses around them. Which obviously does the wrong thing if the memory access happens to change the memory that the compare function is accessing.. Verified to fix a strange boot problem by Jens Axboe.
* Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6Linus Torvalds2005-06-2410-13/+282
|\
| * [TCP]: Need to declare 'tcp_reno' in net/tcp.hDavid S. Miller2005-06-231-0/+1
| | | | | | | | Signed-off-by: David S. Miller <davem@davemloft.net>
| * [PKT_SCHED]: Packet classification based on textsearch (ematch)Thomas Graf2005-06-233-2/+25
| | | | | | | | | | Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [NET]: skb_find_text() - Find a text pattern in skb dataThomas Graf2005-06-231-0/+5
| | | | | | | | | | | | | | | | | | | | Finds a pattern in the skb data according to the specified textsearch configuration. Use textsearch_next() to retrieve subsequent occurrences of the pattern. Returns the offset to the first occurrence or UINT_MAX if no match was found. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [NET]: Zerocopy sequential reading of skb dataThomas Graf2005-06-231-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implements sequential reading for both linear and non-linear skb data at zerocopy cost. The data is returned in chunks of arbitary length, therefore random access is not possible. Usage: from := 0 to := 128 state := undef data := undef len := undef consumed := 0 skb_prepare_seq_read(skb, from, to, &state) while (len = skb_seq_read(consumed, &data, &state)) != 0 do /* do something with 'data' of length 'len' */ if abort then /* abort read if we don't wait for * skb_seq_read() to return 0 */ skb_abort_seq_read(&state) return endif /* not necessary to consume all of 'len' */ consumed += len done Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [LIB]: Naive finite state machine based textsearchThomas Graf2005-06-231-0/+48
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A finite state machine consists of n states (struct ts_fsm_token) representing the pattern as a finite automation. The data is read sequentially on a octet basis. Every state token specifies the number of recurrences and the type of value accepted which can be either a specific character or ctype based set of characters. The available type of recurrences include 1, (0|1), [0 n], and [1 n]. The algorithm differs between strict/non-strict mode specyfing whether the pattern has to start at the first octect. Strict mode is enabled by default and can be disabled by inserting TS_FSM_HEAD_IGNORE as the first token in the chain. The runtime performance of the algorithm should be around O(n), however while in strict mode the average runtime can be better. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [LIB]: Textsearch infrastructure.Thomas Graf2005-06-231-0/+180
| | | | | | | | | | | | | | | | | | | | The textsearch infrastructure provides text searching facitilies for both linear and non-linear data. Individual search algorithms are implemented in modules and chosen by the user. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [TCP]: Allow choosing TCP congestion control via sockopt.Stephen Hemminger2005-06-232-1/+3
| | | | | | | | | | | | | | | | Allow using setsockopt to set TCP congestion control to use on a per socket basis. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [NET]: Separate two usages of netdev_max_backlog.Stephen Hemminger2005-06-231-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | Separate out the two uses of netdev_max_backlog. One controls the upper bound on packets processed per softirq, the new name for this is netdev_budget; the other controls the limit on packets queued via netif_rx. Increase the max_backlog default to account for faster processors. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [NET]: Eliminate netif_rx massive packet drops.Stephen Hemminger2005-06-231-3/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Eliminate the throttling behaviour when the netif receive queue fills because it behaves badly when using high speed networks under load. The throttling cause multiple packet drops that cause TCP to go into slow start mode. The same effective patch has been part of BIC TCP and H-TCP as well as part of Web100. The existing code drops 100's of packets when the queue fills; this changes it to individual packet drop-tail. Signed-off-by: Stephen Hemmminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * [NET]: Remove obsolete netif_rx congestion sensing mechanism.Stephen Hemminger2005-06-231-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | Remove the congestion sensing mechanism from netif_rx, and always return either full or empty. Almost no driver checks the return value from netif_rx, and those that do only use it for debug messages. The original design of netif_rx was to do flow control based on the receive queue, but NAPI has supplanted this and no driver uses the feedback. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
OpenPOWER on IntegriCloud