diff --git a/[refs] b/[refs] index b42120d5b47f..480c686ca12b 100644 --- a/[refs] +++ b/[refs] @@ -1,2 +1,2 @@ --- -refs/heads/master: cf10e82bdc0d38d09dfaf46d0daf56136138ef3f +refs/heads/master: 41f81e88e01eb959f439f8537c58078e4bfc5291 diff --git a/trunk/.gitignore b/trunk/.gitignore index 22fb8fa9bc3d..8d14531846b9 100644 --- a/trunk/.gitignore +++ b/trunk/.gitignore @@ -12,6 +12,7 @@ *.s *.ko *.so +*.so.dbg *.mod.c *.i *.lst diff --git a/trunk/CREDITS b/trunk/CREDITS index 99566b1a6eeb..ee909f2cc49e 100644 --- a/trunk/CREDITS +++ b/trunk/CREDITS @@ -959,7 +959,7 @@ S: 2037 Walnut #6 S: Boulder, Colorado 80302 S: USA -N: Heiko Eissfeldt +N: Heiko Eißfeldt E: heiko@colossus.escape.de heiko@unifix.de D: verify_area stuff, generic SCSI fixes D: SCSI Programming HOWTO @@ -1988,8 +1988,8 @@ N: Volker Lendecke E: vl@kki.org D: Kernel smbfs (to mount WfW, NT and OS/2 network drives.) D: NCP filesystem support (to mount NetWare volumes) -S: Von Ossietzky Str. 12 -S: 37085 Goettingen +S: Von-Ossietzky-Str. 12 +S: 37085 Göttingen S: Germany N: Kevin Lentin @@ -2431,11 +2431,11 @@ S: 12725 SW Millikan Way, Suite 400 S: Beaverton, Oregon 97005 S: USA -N: Eberhard Moenkeberg +N: Eberhard Mönkeberg E: emoenke@gwdg.de D: CDROM driver "sbpcd" (Matsushita/Panasonic/Soundblaster) -S: Ruhstrathoehe 2 b. -S: D-37085 Goettingen +S: Ruhstrathöhe 2 b. +S: D-37085 Göttingen S: Germany N: Thomas Molina diff --git a/trunk/Documentation/00-INDEX b/trunk/Documentation/00-INDEX index 299615d821ac..c3014df066c4 100644 --- a/trunk/Documentation/00-INDEX +++ b/trunk/Documentation/00-INDEX @@ -262,6 +262,8 @@ mtrr.txt - how to use PPro Memory Type Range Registers to increase performance. mutex-design.txt - info on the generic mutex subsystem. +namespaces/ + - directory with various information about namespaces nbd.txt - info on a TCP implementation of a network block device. netlabel/ diff --git a/trunk/Documentation/DocBook/Makefile b/trunk/Documentation/DocBook/Makefile index 1a7f53068ec2..4953bc258729 100644 --- a/trunk/Documentation/DocBook/Makefile +++ b/trunk/Documentation/DocBook/Makefile @@ -11,7 +11,7 @@ DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml videobook.xml \ procfs-guide.xml writing_usb_driver.xml \ kernel-api.xml filesystems.xml lsm.xml usb.xml \ gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \ - genericirq.xml s390-drivers.xml + genericirq.xml s390-drivers.xml uio-howto.xml ### # The build process is as follows (targets): @@ -165,7 +165,7 @@ quiet_cmd_db2man = MAN $@ @touch $@ ### -# Rules to generate postscripts and PNG imgages from .fig format files +# Rules to generate postscripts and PNG images from .fig format files quiet_cmd_fig2eps = FIG2EPS $@ cmd_fig2eps = fig2dev -Leps $< $@ diff --git a/trunk/Documentation/DocBook/kernel-api.tmpl b/trunk/Documentation/DocBook/kernel-api.tmpl index d3290c46af51..aa38cc5692a0 100644 --- a/trunk/Documentation/DocBook/kernel-api.tmpl +++ b/trunk/Documentation/DocBook/kernel-api.tmpl @@ -46,7 +46,7 @@ Atomic and pointer manipulation !Iinclude/asm-x86/atomic_32.h -!Iinclude/asm-x86/unaligned_32.h +!Iinclude/asm-x86/unaligned.h Delaying, scheduling, and timer routines diff --git a/trunk/Documentation/DocBook/mtdnand.tmpl b/trunk/Documentation/DocBook/mtdnand.tmpl index 6fbc41d98c1e..957cf5c26831 100644 --- a/trunk/Documentation/DocBook/mtdnand.tmpl +++ b/trunk/Documentation/DocBook/mtdnand.tmpl @@ -282,7 +282,7 @@ int __init board_init (void) goto out; } - /* map physical adress */ + /* map physical address */ baseaddr = (unsigned long)ioremap(CHIP_PHYSICAL_ADDRESS, 1024); if(!baseaddr){ printk("Ioremap to access NAND chip failed\n"); @@ -306,7 +306,7 @@ int __init board_init (void) this->dev_ready = board_dev_ready; this->eccmode = NAND_ECC_SOFT; - /* Scan to find existance of the device */ + /* Scan to find existence of the device */ if (nand_scan (board_mtd, 1)) { err = -ENXIO; goto out_ior; @@ -340,7 +340,7 @@ static void __exit board_cleanup (void) /* Release resources, unregister device */ nand_release (board_mtd); - /* unmap physical adress */ + /* unmap physical address */ iounmap((void *)baseaddr); /* Free the MTD device structure */ diff --git a/trunk/Documentation/DocBook/uio-howto.tmpl b/trunk/Documentation/DocBook/uio-howto.tmpl index c119484258b8..fdd7f4f887b7 100644 --- a/trunk/Documentation/DocBook/uio-howto.tmpl +++ b/trunk/Documentation/DocBook/uio-howto.tmpl @@ -29,6 +29,12 @@ + + 0.4 + 2007-11-26 + hjk + Removed section about uio_dummy. + 0.3 2007-04-29 @@ -94,6 +100,26 @@ interested in translating it, please email me user space. This simplifies development and reduces the risk of serious bugs within a kernel module. + + Please note that UIO is not an universal driver interface. Devices + that are already handled well by other kernel subsystems (like + networking or serial or USB) are no candidates for an UIO driver. + Hardware that is ideally suited for an UIO driver fulfills all of + the following: + + + + The device has memory that can be mapped. The device can be + controlled completely by writing to this memory. + + + The device usually generates interrupts. + + + The device does not fit into one of the standard kernel + subsystems. + + @@ -174,8 +200,9 @@ interested in translating it, please email me For cards that don't generate interrupts but need to be polled, there is the possibility to set up a timer that triggers the interrupt handler at configurable time intervals. - See drivers/uio/uio_dummy.c for an - example of this technique. + This interrupt simulation is done by calling + uio_event_notify() + from the timer's event handler. @@ -263,63 +290,11 @@ offset = N * getpagesize(); - - -Using uio_dummy - - Well, there is no real use for uio_dummy. Its only purpose is - to test most parts of the UIO system (everything except - hardware interrupts), and to serve as an example for the - kernel module that you will have to write yourself. - - - -What uio_dummy does - - The kernel module uio_dummy.ko creates a - device that uses a timer to generate periodic interrupts. The - interrupt handler does nothing but increment a counter. The - driver adds two custom attributes, count - and freq, that appear under - /sys/devices/platform/uio_dummy/. - - - - The attribute count can be read and - written. The associated file - /sys/devices/platform/uio_dummy/count - appears as a normal text file and contains the total number of - timer interrupts. If you look at it (e.g. using - cat), you'll notice it is slowly counting - up. - - - - The attribute freq can be read and written. - The content of - /sys/devices/platform/uio_dummy/freq - represents the number of system timer ticks between two timer - interrupts. The default value of freq is - the value of the kernel variable HZ, which - gives you an interval of one second. Lower values will - increase the frequency. Try the following: - - -cd /sys/devices/platform/uio_dummy/ -echo 100 > freq - - - Use cat count to see how the interrupt - frequency changes. - - - - Writing your own kernel module - Please have a look at uio_dummy.c as an + Please have a look at uio_cif.c as an example. The following paragraphs explain the different sections of this file. @@ -354,9 +329,8 @@ See the description below for details. interrupt, it's your modules task to determine the irq number during initialization. If you don't have a hardware generated interrupt but want to trigger the interrupt handler in some other way, set -irq to UIO_IRQ_CUSTOM. The -uio_dummy module does this as it triggers the event mechanism in a timer -routine. If you had no interrupt at all, you could set +irq to UIO_IRQ_CUSTOM. +If you had no interrupt at all, you could set irq to UIO_IRQ_NONE, though this rarely makes sense. diff --git a/trunk/Documentation/Intel-IOMMU.txt b/trunk/Documentation/Intel-IOMMU.txt new file mode 100644 index 000000000000..c2321903aa09 --- /dev/null +++ b/trunk/Documentation/Intel-IOMMU.txt @@ -0,0 +1,115 @@ +Linux IOMMU Support +=================== + +The architecture spec can be obtained from the below location. + +http://www.intel.com/technology/virtualization/ + +This guide gives a quick cheat sheet for some basic understanding. + +Some Keywords + +DMAR - DMA remapping +DRHD - DMA Engine Reporting Structure +RMRR - Reserved memory Region Reporting Structure +ZLR - Zero length reads from PCI devices +IOVA - IO Virtual address. + +Basic stuff +----------- + +ACPI enumerates and lists the different DMA engines in the platform, and +device scope relationships between PCI devices and which DMA engine controls +them. + +What is RMRR? +------------- + +There are some devices the BIOS controls, for e.g USB devices to perform +PS2 emulation. The regions of memory used for these devices are marked +reserved in the e820 map. When we turn on DMA translation, DMA to those +regions will fail. Hence BIOS uses RMRR to specify these regions along with +devices that need to access these regions. OS is expected to setup +unity mappings for these regions for these devices to access these regions. + +How is IOVA generated? +--------------------- + +Well behaved drivers call pci_map_*() calls before sending command to device +that needs to perform DMA. Once DMA is completed and mapping is no longer +required, device performs a pci_unmap_*() calls to unmap the region. + +The Intel IOMMU driver allocates a virtual address per domain. Each PCIE +device has its own domain (hence protection). Devices under p2p bridges +share the virtual address with all devices under the p2p bridge due to +transaction id aliasing for p2p bridges. + +IOVA generation is pretty generic. We used the same technique as vmalloc() +but these are not global address spaces, but separate for each domain. +Different DMA engines may support different number of domains. + +We also allocate gaurd pages with each mapping, so we can attempt to catch +any overflow that might happen. + + +Graphics Problems? +------------------ +If you encounter issues with graphics devices, you can try adding +option intel_iommu=igfx_off to turn off the integrated graphics engine. + +If it happens to be a PCI device included in the INCLUDE_ALL Engine, +then try enabling CONFIG_DMAR_GFX_WA to setup a 1-1 map. We hear +graphics drivers may be in process of using DMA api's in the near +future and at that time this option can be yanked out. + +Some exceptions to IOVA +----------------------- +Interrupt ranges are not address translated, (0xfee00000 - 0xfeefffff). +The same is true for peer to peer transactions. Hence we reserve the +address from PCI MMIO ranges so they are not allocated for IOVA addresses. + + +Fault reporting +--------------- +When errors are reported, the DMA engine signals via an interrupt. The fault +reason and device that caused it with fault reason is printed on console. + +See below for sample. + + +Boot Message Sample +------------------- + +Something like this gets printed indicating presence of DMAR tables +in ACPI. + +ACPI: DMAR (v001 A M I OEMDMAR 0x00000001 MSFT 0x00000097) @ 0x000000007f5b5ef0 + +When DMAR is being processed and initialized by ACPI, prints DMAR locations +and any RMRR's processed. + +ACPI DMAR:Host address width 36 +ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000 +ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000 +ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000 +ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff +ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff + +When DMAR is enabled for use, you will notice.. + +PCI-DMA: Using DMAR IOMMU + +Fault reporting +--------------- + +DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000 +DMAR:[fault reason 05] PTE Write access is not set +DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000 +DMAR:[fault reason 05] PTE Write access is not set + +TBD +---- + +- For compatibility testing, could use unity map domain for all devices, just + provide a 1-1 for all useful memory under a single domain for all devices. +- API for paravirt ops for abstracting functionlity for VMM folks. diff --git a/trunk/Documentation/SubmitChecklist b/trunk/Documentation/SubmitChecklist index 19e7f65c269f..34e06d2f194f 100644 --- a/trunk/Documentation/SubmitChecklist +++ b/trunk/Documentation/SubmitChecklist @@ -67,7 +67,7 @@ kernel patches. 20: Check that it all passes `make headers_check'. 21: Has been checked with injection of at least slab and page-allocation - fauilures. See Documentation/fault-injection/. + failures. See Documentation/fault-injection/. If the new code is substantial, addition of subsystem-specific fault injection might be appropriate. diff --git a/trunk/Documentation/SubmittingDrivers b/trunk/Documentation/SubmittingDrivers index d7e26427e426..24f2eb40cae5 100644 --- a/trunk/Documentation/SubmittingDrivers +++ b/trunk/Documentation/SubmittingDrivers @@ -36,8 +36,7 @@ Linux 2.4: If the code area has a general maintainer then please submit it to the maintainer listed in MAINTAINERS in the kernel file. If the maintainer does not respond or you cannot find the appropriate - maintainer then please contact Marcelo Tosatti - . + maintainer then please contact Willy Tarreau . Linux 2.6: The same rules apply as 2.4 except that you should follow linux-kernel diff --git a/trunk/Documentation/SubmittingPatches b/trunk/Documentation/SubmittingPatches index a30dd4480ad4..681e2b36195c 100644 --- a/trunk/Documentation/SubmittingPatches +++ b/trunk/Documentation/SubmittingPatches @@ -464,8 +464,8 @@ section Linus Computer Science 101. Nuff said. If your code deviates too much from this, it is likely to be rejected without further review, and without comment. -Once significant exception is when moving code from one file to -another in this case you should not modify the moved code at all in +One significant exception is when moving code from one file to +another -- in this case you should not modify the moved code at all in the same patch which moves it. This clearly delineates the act of moving the code and your changes. This greatly aids review of the actual differences and allows tools to better track the history of diff --git a/trunk/Documentation/accounting/cgroupstats.txt b/trunk/Documentation/accounting/cgroupstats.txt new file mode 100644 index 000000000000..eda40fd39cad --- /dev/null +++ b/trunk/Documentation/accounting/cgroupstats.txt @@ -0,0 +1,27 @@ +Control Groupstats is inspired by the discussion at +http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics as +suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. + +Per cgroup statistics infrastructure re-uses code from the taskstats +interface. A new set of cgroup operations are registered with commands +and attributes specific to cgroups. It should be very easy to +extend per cgroup statistics, by adding members to the cgroupstats +structure. + +The current model for cgroupstats is a pull, a push model (to post +statistics on interesting events), should be very easy to add. Currently +user space requests for statistics by passing the cgroup path. +Statistics about the state of all the tasks in the cgroup is returned to +user space. + +NOTE: We currently rely on delay accounting for extracting information +about tasks blocked on I/O. If CONFIG_TASK_DELAY_ACCT is disabled, this +information will not be available. + +To extract cgroup statistics a utility very similar to getdelays.c +has been developed, the sample output of the utility is shown below + +~/balbir/cgroupstats # ./getdelays -C "/cgroup/a" +sleeping 1, blocked 0, running 1, stopped 0, uninterruptible 0 +~/balbir/cgroupstats # ./getdelays -C "/cgroup" +sleeping 155, blocked 0, running 1, stopped 0, uninterruptible 2 diff --git a/trunk/Documentation/accounting/getdelays.c b/trunk/Documentation/accounting/getdelays.c index ab82b7f53312..d6cb1a86fd61 100644 --- a/trunk/Documentation/accounting/getdelays.c +++ b/trunk/Documentation/accounting/getdelays.c @@ -25,6 +25,7 @@ #include #include +#include /* * Generic macros for dealing with netlink sockets. Might be duplicated @@ -78,6 +79,7 @@ static void usage(void) fprintf(stderr, " -i: print IO accounting (works only with -p)\n"); fprintf(stderr, " -l: listen forever\n"); fprintf(stderr, " -v: debug on\n"); + fprintf(stderr, " -C: container path\n"); } /* @@ -212,6 +214,14 @@ void task_context_switch_counts(struct taskstats *t) t->nvcsw, t->nivcsw); } +void print_cgroupstats(struct cgroupstats *c) +{ + printf("sleeping %llu, blocked %llu, running %llu, stopped %llu, " + "uninterruptible %llu\n", c->nr_sleeping, c->nr_io_wait, + c->nr_running, c->nr_stopped, c->nr_uninterruptible); +} + + void print_ioacct(struct taskstats *t) { printf("%s: read=%llu, write=%llu, cancelled_write=%llu\n", @@ -239,11 +249,14 @@ int main(int argc, char *argv[]) int maskset = 0; char *logfile = NULL; int loop = 0; + int containerset = 0; + char containerpath[1024]; + int cfd = 0; struct msgtemplate msg; while (1) { - c = getopt(argc, argv, "qdiw:r:m:t:p:vl"); + c = getopt(argc, argv, "qdiw:r:m:t:p:vlC:"); if (c < 0) break; @@ -260,6 +273,10 @@ int main(int argc, char *argv[]) printf("printing task/process context switch rates\n"); print_task_context_switch_counts = 1; break; + case 'C': + containerset = 1; + strncpy(containerpath, optarg, strlen(optarg) + 1); + break; case 'w': logfile = strdup(optarg); printf("write to file %s\n", logfile); @@ -334,6 +351,11 @@ int main(int argc, char *argv[]) } } + if (tid && containerset) { + fprintf(stderr, "Select either -t or -C, not both\n"); + goto err; + } + if (tid) { rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, cmd_type, &tid, sizeof(__u32)); @@ -344,6 +366,20 @@ int main(int argc, char *argv[]) } } + if (containerset) { + cfd = open(containerpath, O_RDONLY); + if (cfd < 0) { + perror("error opening container file"); + goto err; + } + rc = send_cmd(nl_sd, id, mypid, CGROUPSTATS_CMD_GET, + CGROUPSTATS_CMD_ATTR_FD, &cfd, sizeof(__u32)); + if (rc < 0) { + perror("error sending cgroupstats command"); + goto err; + } + } + do { int i; @@ -422,6 +458,9 @@ int main(int argc, char *argv[]) } break; + case CGROUPSTATS_TYPE_CGROUP_STATS: + print_cgroupstats(NLA_DATA(na)); + break; default: fprintf(stderr, "Unknown nla_type %d\n", na->nla_type); @@ -443,5 +482,7 @@ int main(int argc, char *argv[]) close(nl_sd); if (fd) close(fd); + if (cfd) + close(cfd); return 0; } diff --git a/trunk/Documentation/arm/Samsung-S3C24XX/DMA.txt b/trunk/Documentation/arm/Samsung-S3C24XX/DMA.txt index 37f4edcc5d87..3ed82383efea 100644 --- a/trunk/Documentation/arm/Samsung-S3C24XX/DMA.txt +++ b/trunk/Documentation/arm/Samsung-S3C24XX/DMA.txt @@ -5,7 +5,7 @@ Introduction ------------ The kernel provides an interface to manage DMA transfers - using the DMA channels in the cpu, so that the central + using the DMA channels in the CPU, so that the central duty of managing channel mappings, and programming the channel generators is in one place. @@ -17,24 +17,24 @@ DMA Channel Ordering channels to all sources, which means that some devices have a restricted number of channels that can be used. - To allow flexibilty for each cpu type and board, the - dma code can be given an dma ordering structure which + To allow flexibility for each CPU type and board, the + DMA code can be given a DMA ordering structure which allows the order of channel search to be specified, as well as allowing the prohibition of certain claims. struct s3c24xx_dma_order has a list of channels, and - each channel within has a slot for a list of dma - channel numbers. The slots are searched in order, for - the presence of a dma channel number with DMA_CH_VALID - orred in. + each channel within has a slot for a list of DMA + channel numbers. The slots are searched in order for + the presence of a DMA channel number with DMA_CH_VALID + or-ed in. If the order has the flag DMA_CH_NEVER set, then after checking the channel list, the system will return no found channel, thus denying the request. A board support file can call s3c24xx_dma_order_set() - to register an complete ordering set. The routine will - copy the data, so the original can be discared with + to register a complete ordering set. The routine will + copy the data, so the original can be discarded with __initdata. diff --git a/trunk/Documentation/cachetlb.txt b/trunk/Documentation/cachetlb.txt index 552cabac0608..da42ab414c48 100644 --- a/trunk/Documentation/cachetlb.txt +++ b/trunk/Documentation/cachetlb.txt @@ -87,30 +87,7 @@ changes occur: This is used primarily during fault processing. -5) void flush_tlb_pgtables(struct mm_struct *mm, - unsigned long start, unsigned long end) - - The software page tables for address space 'mm' for virtual - addresses in the range 'start' to 'end-1' are being torn down. - - Some platforms cache the lowest level of the software page tables - in a linear virtually mapped array, to make TLB miss processing - more efficient. On such platforms, since the TLB is caching the - software page table structure, it needs to be flushed when parts - of the software page table tree are unlinked/freed. - - Sparc64 is one example of a platform which does this. - - Usually, when munmap()'ing an area of user virtual address - space, the kernel leaves the page table parts around and just - marks the individual pte's as invalid. However, if very large - portions of the address space are unmapped, the kernel frees up - those portions of the software page tables to prevent potential - excessive kernel memory usage caused by erratic mmap/mmunmap - sequences. It is at these times that flush_tlb_pgtables will - be invoked. - -6) void update_mmu_cache(struct vm_area_struct *vma, +5) void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t pte) At the end of every page fault, this routine is invoked to @@ -123,7 +100,7 @@ changes occur: translations for software managed TLB configurations. The sparc64 port currently does this. -7) void tlb_migrate_finish(struct mm_struct *mm) +6) void tlb_migrate_finish(struct mm_struct *mm) This interface is called at the end of an explicit process migration. This interface provides a hook diff --git a/trunk/Documentation/cdrom/cdrom-standard.tex b/trunk/Documentation/cdrom/cdrom-standard.tex index 92f94e597582..c713aeb020c4 100644 --- a/trunk/Documentation/cdrom/cdrom-standard.tex +++ b/trunk/Documentation/cdrom/cdrom-standard.tex @@ -1009,7 +1009,7 @@ \subsubsection{Device dependent $ioctl$s} \cdrom-related code in the 2.1-kernel. Thanks to Scott Snyder and Gerd Knorr, who were the first to implement this interface for SCSI and IDE-CD drivers and added many ideas for extension of the data -structures relative to kernel~2.0. Further thanks to Heiko Eissfeldt, +structures relative to kernel~2.0. Further thanks to Heiko Ei{\sz}feldt, Thomas Quinot, Jon Tombs, Ken Pizzini, Eberhard M\"onkeberg and Andrew Kroll, the \linux\ \cdrom\ device driver developers who were kind enough to give suggestions and criticisms during the writing. Finally diff --git a/trunk/Documentation/cgroups.txt b/trunk/Documentation/cgroups.txt new file mode 100644 index 000000000000..98a26f81fa75 --- /dev/null +++ b/trunk/Documentation/cgroups.txt @@ -0,0 +1,545 @@ + CGROUPS + ------- + +Written by Paul Menage based on Documentation/cpusets.txt + +Original copyright statements from cpusets.txt: +Portions Copyright (C) 2004 BULL SA. +Portions Copyright (c) 2004-2006 Silicon Graphics, Inc. +Modified by Paul Jackson +Modified by Christoph Lameter + +CONTENTS: +========= + +1. Control Groups + 1.1 What are cgroups ? + 1.2 Why are cgroups needed ? + 1.3 How are cgroups implemented ? + 1.4 What does notify_on_release do ? + 1.5 How do I use cgroups ? +2. Usage Examples and Syntax + 2.1 Basic Usage + 2.2 Attaching processes +3. Kernel API + 3.1 Overview + 3.2 Synchronization + 3.3 Subsystem API +4. Questions + +1. Control Groups +========== + +1.1 What are cgroups ? +---------------------- + +Control Groups provide a mechanism for aggregating/partitioning sets of +tasks, and all their future children, into hierarchical groups with +specialized behaviour. + +Definitions: + +A *cgroup* associates a set of tasks with a set of parameters for one +or more subsystems. + +A *subsystem* is a module that makes use of the task grouping +facilities provided by cgroups to treat groups of tasks in +particular ways. A subsystem is typically a "resource controller" that +schedules a resource or applies per-cgroup limits, but it may be +anything that wants to act on a group of processes, e.g. a +virtualization subsystem. + +A *hierarchy* is a set of cgroups arranged in a tree, such that +every task in the system is in exactly one of the cgroups in the +hierarchy, and a set of subsystems; each subsystem has system-specific +state attached to each cgroup in the hierarchy. Each hierarchy has +an instance of the cgroup virtual filesystem associated with it. + +At any one time there may be multiple active hierachies of task +cgroups. Each hierarchy is a partition of all tasks in the system. + +User level code may create and destroy cgroups by name in an +instance of the cgroup virtual file system, specify and query to +which cgroup a task is assigned, and list the task pids assigned to +a cgroup. Those creations and assignments only affect the hierarchy +associated with that instance of the cgroup file system. + +On their own, the only use for cgroups is for simple job +tracking. The intention is that other subsystems hook into the generic +cgroup support to provide new attributes for cgroups, such as +accounting/limiting the resources which processes in a cgroup can +access. For example, cpusets (see Documentation/cpusets.txt) allows +you to associate a set of CPUs and a set of memory nodes with the +tasks in each cgroup. + +1.2 Why are cgroups needed ? +---------------------------- + +There are multiple efforts to provide process aggregations in the +Linux kernel, mainly for resource tracking purposes. Such efforts +include cpusets, CKRM/ResGroups, UserBeanCounters, and virtual server +namespaces. These all require the basic notion of a +grouping/partitioning of processes, with newly forked processes ending +in the same group (cgroup) as their parent process. + +The kernel cgroup patch provides the minimum essential kernel +mechanisms required to efficiently implement such groups. It has +minimal impact on the system fast paths, and provides hooks for +specific subsystems such as cpusets to provide additional behaviour as +desired. + +Multiple hierarchy support is provided to allow for situations where +the division of tasks into cgroups is distinctly different for +different subsystems - having parallel hierarchies allows each +hierarchy to be a natural division of tasks, without having to handle +complex combinations of tasks that would be present if several +unrelated subsystems needed to be forced into the same tree of +cgroups. + +At one extreme, each resource controller or subsystem could be in a +separate hierarchy; at the other extreme, all subsystems +would be attached to the same hierarchy. + +As an example of a scenario (originally proposed by vatsa@in.ibm.com) +that can benefit from multiple hierarchies, consider a large +university server with various users - students, professors, system +tasks etc. The resource planning for this server could be along the +following lines: + + CPU : Top cpuset + / \ + CPUSet1 CPUSet2 + | | + (Profs) (Students) + + In addition (system tasks) are attached to topcpuset (so + that they can run anywhere) with a limit of 20% + + Memory : Professors (50%), students (30%), system (20%) + + Disk : Prof (50%), students (30%), system (20%) + + Network : WWW browsing (20%), Network File System (60%), others (20%) + / \ + Prof (15%) students (5%) + +Browsers like firefox/lynx go into the WWW network class, while (k)nfsd go +into NFS network class. + +At the same time firefox/lynx will share an appropriate CPU/Memory class +depending on who launched it (prof/student). + +With the ability to classify tasks differently for different resources +(by putting those resource subsystems in different hierarchies) then +the admin can easily set up a script which receives exec notifications +and depending on who is launching the browser he can + + # echo browser_pid > /mnt///tasks + +With only a single hierarchy, he now would potentially have to create +a separate cgroup for every browser launched and associate it with +approp network and other resource class. This may lead to +proliferation of such cgroups. + +Also lets say that the administrator would like to give enhanced network +access temporarily to a student's browser (since it is night and the user +wants to do online gaming :) OR give one of the students simulation +apps enhanced CPU power, + +With ability to write pids directly to resource classes, its just a +matter of : + + # echo pid > /mnt/network//tasks + (after some time) + # echo pid > /mnt/network//tasks + +Without this ability, he would have to split the cgroup into +multiple separate ones and then associate the new cgroups with the +new resource classes. + + + +1.3 How are cgroups implemented ? +--------------------------------- + +Control Groups extends the kernel as follows: + + - Each task in the system has a reference-counted pointer to a + css_set. + + - A css_set contains a set of reference-counted pointers to + cgroup_subsys_state objects, one for each cgroup subsystem + registered in the system. There is no direct link from a task to + the cgroup of which it's a member in each hierarchy, but this + can be determined by following pointers through the + cgroup_subsys_state objects. This is because accessing the + subsystem state is something that's expected to happen frequently + and in performance-critical code, whereas operations that require a + task's actual cgroup assignments (in particular, moving between + cgroups) are less common. A linked list runs through the cg_list + field of each task_struct using the css_set, anchored at + css_set->tasks. + + - A cgroup hierarchy filesystem can be mounted for browsing and + manipulation from user space. + + - You can list all the tasks (by pid) attached to any cgroup. + +The implementation of cgroups requires a few, simple hooks +into the rest of the kernel, none in performance critical paths: + + - in init/main.c, to initialize the root cgroups and initial + css_set at system boot. + + - in fork and exit, to attach and detach a task from its css_set. + +In addition a new file system, of type "cgroup" may be mounted, to +enable browsing and modifying the cgroups presently known to the +kernel. When mounting a cgroup hierarchy, you may specify a +comma-separated list of subsystems to mount as the filesystem mount +options. By default, mounting the cgroup filesystem attempts to +mount a hierarchy containing all registered subsystems. + +If an active hierarchy with exactly the same set of subsystems already +exists, it will be reused for the new mount. If no existing hierarchy +matches, and any of the requested subsystems are in use in an existing +hierarchy, the mount will fail with -EBUSY. Otherwise, a new hierarchy +is activated, associated with the requested subsystems. + +It's not currently possible to bind a new subsystem to an active +cgroup hierarchy, or to unbind a subsystem from an active cgroup +hierarchy. This may be possible in future, but is fraught with nasty +error-recovery issues. + +When a cgroup filesystem is unmounted, if there are any +child cgroups created below the top-level cgroup, that hierarchy +will remain active even though unmounted; if there are no +child cgroups then the hierarchy will be deactivated. + +No new system calls are added for cgroups - all support for +querying and modifying cgroups is via this cgroup file system. + +Each task under /proc has an added file named 'cgroup' displaying, +for each active hierarchy, the subsystem names and the cgroup name +as the path relative to the root of the cgroup file system. + +Each cgroup is represented by a directory in the cgroup file system +containing the following files describing that cgroup: + + - tasks: list of tasks (by pid) attached to that cgroup + - notify_on_release flag: run /sbin/cgroup_release_agent on exit? + +Other subsystems such as cpusets may add additional files in each +cgroup dir + +New cgroups are created using the mkdir system call or shell +command. The properties of a cgroup, such as its flags, are +modified by writing to the appropriate file in that cgroups +directory, as listed above. + +The named hierarchical structure of nested cgroups allows partitioning +a large system into nested, dynamically changeable, "soft-partitions". + +The attachment of each task, automatically inherited at fork by any +children of that task, to a cgroup allows organizing the work load +on a system into related sets of tasks. A task may be re-attached to +any other cgroup, if allowed by the permissions on the necessary +cgroup file system directories. + +When a task is moved from one cgroup to another, it gets a new +css_set pointer - if there's an already existing css_set with the +desired collection of cgroups then that group is reused, else a new +css_set is allocated. Note that the current implementation uses a +linear search to locate an appropriate existing css_set, so isn't +very efficient. A future version will use a hash table for better +performance. + +To allow access from a cgroup to the css_sets (and hence tasks) +that comprise it, a set of cg_cgroup_link objects form a lattice; +each cg_cgroup_link is linked into a list of cg_cgroup_links for +a single cgroup on its cont_link_list field, and a list of +cg_cgroup_links for a single css_set on its cg_link_list. + +Thus the set of tasks in a cgroup can be listed by iterating over +each css_set that references the cgroup, and sub-iterating over +each css_set's task set. + +The use of a Linux virtual file system (vfs) to represent the +cgroup hierarchy provides for a familiar permission and name space +for cgroups, with a minimum of additional kernel code. + +1.4 What does notify_on_release do ? +------------------------------------ + +*** notify_on_release is disabled in the current patch set. It will be +*** reactivated in a future patch in a less-intrusive manner + +If the notify_on_release flag is enabled (1) in a cgroup, then +whenever the last task in the cgroup leaves (exits or attaches to +some other cgroup) and the last child cgroup of that cgroup +is removed, then the kernel runs the command specified by the contents +of the "release_agent" file in that hierarchy's root directory, +supplying the pathname (relative to the mount point of the cgroup +file system) of the abandoned cgroup. This enables automatic +removal of abandoned cgroups. The default value of +notify_on_release in the root cgroup at system boot is disabled +(0). The default value of other cgroups at creation is the current +value of their parents notify_on_release setting. The default value of +a cgroup hierarchy's release_agent path is empty. + +1.5 How do I use cgroups ? +-------------------------- + +To start a new job that is to be contained within a cgroup, using +the "cpuset" cgroup subsystem, the steps are something like: + + 1) mkdir /dev/cgroup + 2) mount -t cgroup -ocpuset cpuset /dev/cgroup + 3) Create the new cgroup by doing mkdir's and write's (or echo's) in + the /dev/cgroup virtual file system. + 4) Start a task that will be the "founding father" of the new job. + 5) Attach that task to the new cgroup by writing its pid to the + /dev/cgroup tasks file for that cgroup. + 6) fork, exec or clone the job tasks from this founding father task. + +For example, the following sequence of commands will setup a cgroup +named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, +and then start a subshell 'sh' in that cgroup: + + mount -t cgroup cpuset -ocpuset /dev/cgroup + cd /dev/cgroup + mkdir Charlie + cd Charlie + /bin/echo 2-3 > cpus + /bin/echo 1 > mems + /bin/echo $$ > tasks + sh + # The subshell 'sh' is now running in cgroup Charlie + # The next line should display '/Charlie' + cat /proc/self/cgroup + +2. Usage Examples and Syntax +============================ + +2.1 Basic Usage +--------------- + +Creating, modifying, using the cgroups can be done through the cgroup +virtual filesystem. + +To mount a cgroup hierarchy will all available subsystems, type: +# mount -t cgroup xxx /dev/cgroup + +The "xxx" is not interpreted by the cgroup code, but will appear in +/proc/mounts so may be any useful identifying string that you like. + +To mount a cgroup hierarchy with just the cpuset and numtasks +subsystems, type: +# mount -t cgroup -o cpuset,numtasks hier1 /dev/cgroup + +To change the set of subsystems bound to a mounted hierarchy, just +remount with different options: + +# mount -o remount,cpuset,ns /dev/cgroup + +Note that changing the set of subsystems is currently only supported +when the hierarchy consists of a single (root) cgroup. Supporting +the ability to arbitrarily bind/unbind subsystems from an existing +cgroup hierarchy is intended to be implemented in the future. + +Then under /dev/cgroup you can find a tree that corresponds to the +tree of the cgroups in the system. For instance, /dev/cgroup +is the cgroup that holds the whole system. + +If you want to create a new cgroup under /dev/cgroup: +# cd /dev/cgroup +# mkdir my_cgroup + +Now you want to do something with this cgroup. +# cd my_cgroup + +In this directory you can find several files: +# ls +notify_on_release release_agent tasks +(plus whatever files are added by the attached subsystems) + +Now attach your shell to this cgroup: +# /bin/echo $$ > tasks + +You can also create cgroups inside your cgroup by using mkdir in this +directory. +# mkdir my_sub_cs + +To remove a cgroup, just use rmdir: +# rmdir my_sub_cs + +This will fail if the cgroup is in use (has cgroups inside, or +has processes attached, or is held alive by other subsystem-specific +reference). + +2.2 Attaching processes +----------------------- + +# /bin/echo PID > tasks + +Note that it is PID, not PIDs. You can only attach ONE task at a time. +If you have several tasks to attach, you have to do it one after another: + +# /bin/echo PID1 > tasks +# /bin/echo PID2 > tasks + ... +# /bin/echo PIDn > tasks + +3. Kernel API +============= + +3.1 Overview +------------ + +Each kernel subsystem that wants to hook into the generic cgroup +system needs to create a cgroup_subsys object. This contains +various methods, which are callbacks from the cgroup system, along +with a subsystem id which will be assigned by the cgroup system. + +Other fields in the cgroup_subsys object include: + +- subsys_id: a unique array index for the subsystem, indicating which + entry in cgroup->subsys[] this subsystem should be + managing. Initialized by cgroup_register_subsys(); prior to this + it should be initialized to -1 + +- hierarchy: an index indicating which hierarchy, if any, this + subsystem is currently attached to. If this is -1, then the + subsystem is not attached to any hierarchy, and all tasks should be + considered to be members of the subsystem's top_cgroup. It should + be initialized to -1. + +- name: should be initialized to a unique subsystem name prior to + calling cgroup_register_subsystem. Should be no longer than + MAX_CGROUP_TYPE_NAMELEN + +Each cgroup object created by the system has an array of pointers, +indexed by subsystem id; this pointer is entirely managed by the +subsystem; the generic cgroup code will never touch this pointer. + +3.2 Synchronization +------------------- + +There is a global mutex, cgroup_mutex, used by the cgroup +system. This should be taken by anything that wants to modify a +cgroup. It may also be taken to prevent cgroups from being +modified, but more specific locks may be more appropriate in that +situation. + +See kernel/cgroup.c for more details. + +Subsystems can take/release the cgroup_mutex via the functions +cgroup_lock()/cgroup_unlock(), and can +take/release the callback_mutex via the functions +cgroup_lock()/cgroup_unlock(). + +Accessing a task's cgroup pointer may be done in the following ways: +- while holding cgroup_mutex +- while holding the task's alloc_lock (via task_lock()) +- inside an rcu_read_lock() section via rcu_dereference() + +3.3 Subsystem API +-------------------------- + +Each subsystem should: + +- add an entry in linux/cgroup_subsys.h +- define a cgroup_subsys object called _subsys + +Each subsystem may export the following methods. The only mandatory +methods are create/destroy. Any others that are null are presumed to +be successful no-ops. + +struct cgroup_subsys_state *create(struct cgroup *cont) +LL=cgroup_mutex + +Called to create a subsystem state object for a cgroup. The +subsystem should allocate its subsystem state object for the passed +cgroup, returning a pointer to the new object on success or a +negative error code. On success, the subsystem pointer should point to +a structure of type cgroup_subsys_state (typically embedded in a +larger subsystem-specific object), which will be initialized by the +cgroup system. Note that this will be called at initialization to +create the root subsystem state for this subsystem; this case can be +identified by the passed cgroup object having a NULL parent (since +it's the root of the hierarchy) and may be an appropriate place for +initialization code. + +void destroy(struct cgroup *cont) +LL=cgroup_mutex + +The cgroup system is about to destroy the passed cgroup; the +subsystem should do any necessary cleanup + +int can_attach(struct cgroup_subsys *ss, struct cgroup *cont, + struct task_struct *task) +LL=cgroup_mutex + +Called prior to moving a task into a cgroup; if the subsystem +returns an error, this will abort the attach operation. If a NULL +task is passed, then a successful result indicates that *any* +unspecified task can be moved into the cgroup. Note that this isn't +called on a fork. If this method returns 0 (success) then this should +remain valid while the caller holds cgroup_mutex. + +void attach(struct cgroup_subsys *ss, struct cgroup *cont, + struct cgroup *old_cont, struct task_struct *task) +LL=cgroup_mutex + + +Called after the task has been attached to the cgroup, to allow any +post-attachment activity that requires memory allocations or blocking. + +void fork(struct cgroup_subsy *ss, struct task_struct *task) +LL=callback_mutex, maybe read_lock(tasklist_lock) + +Called when a task is forked into a cgroup. Also called during +registration for all existing tasks. + +void exit(struct cgroup_subsys *ss, struct task_struct *task) +LL=callback_mutex + +Called during task exit + +int populate(struct cgroup_subsys *ss, struct cgroup *cont) +LL=none + +Called after creation of a cgroup to allow a subsystem to populate +the cgroup directory with file entries. The subsystem should make +calls to cgroup_add_file() with objects of type cftype (see +include/linux/cgroup.h for details). Note that although this +method can return an error code, the error code is currently not +always handled well. + +void post_clone(struct cgroup_subsys *ss, struct cgroup *cont) + +Called at the end of cgroup_clone() to do any paramater +initialization which might be required before a task could attach. For +example in cpusets, no task may attach before 'cpus' and 'mems' are set +up. + +void bind(struct cgroup_subsys *ss, struct cgroup *root) +LL=callback_mutex + +Called when a cgroup subsystem is rebound to a different hierarchy +and root cgroup. Currently this will only involve movement between +the default hierarchy (which never has sub-cgroups) and a hierarchy +that is being created/destroyed (and hence has no sub-cgroups). + +4. Questions +============ + +Q: what's up with this '/bin/echo' ? +A: bash's builtin 'echo' command does not check calls to write() against + errors. If you use it in the cgroup file system, you won't be + able to tell whether a command succeeded or failed. + +Q: When I attach processes, only the first of the line gets really attached ! +A: We can only return one error code per call to write(). So you should also + put only ONE pid. + diff --git a/trunk/Documentation/cpu-hotplug.txt b/trunk/Documentation/cpu-hotplug.txt index b6d24c22274b..a741f658a3c9 100644 --- a/trunk/Documentation/cpu-hotplug.txt +++ b/trunk/Documentation/cpu-hotplug.txt @@ -220,7 +220,9 @@ A: The following happen, listed in no particular order :-) CPU_DOWN_PREPARE or CPU_DOWN_PREPARE_FROZEN, depending on whether or not the CPU is being offlined while tasks are frozen due to a suspend operation in progress -- All process is migrated away from this outgoing CPU to a new CPU +- All processes are migrated away from this outgoing CPU to new CPUs. + The new CPU is chosen from each process' current cpuset, which may be + a subset of all online CPUs. - All interrupts targeted to this CPU is migrated to a new CPU - timers/bottom half/task lets are also migrated to a new CPU - Once all services are migrated, kernel calls an arch specific routine diff --git a/trunk/Documentation/cpusets.txt b/trunk/Documentation/cpusets.txt index ec9de6917f01..141bef1c8599 100644 --- a/trunk/Documentation/cpusets.txt +++ b/trunk/Documentation/cpusets.txt @@ -7,6 +7,7 @@ Written by Simon.Derr@bull.net Portions Copyright (c) 2004-2006 Silicon Graphics, Inc. Modified by Paul Jackson Modified by Christoph Lameter +Modified by Paul Menage CONTENTS: ========= @@ -16,9 +17,9 @@ CONTENTS: 1.2 Why are cpusets needed ? 1.3 How are cpusets implemented ? 1.4 What are exclusive cpusets ? - 1.5 What does notify_on_release do ? - 1.6 What is memory_pressure ? - 1.7 What is memory spread ? + 1.5 What is memory_pressure ? + 1.6 What is memory spread ? + 1.7 What is sched_load_balance ? 1.8 How do I use cpusets ? 2. Usage Examples and Syntax 2.1 Basic Usage @@ -44,18 +45,19 @@ hierarchy visible in a virtual file system. These are the essential hooks, beyond what is already present, required to manage dynamic job placement on large systems. -Each task has a pointer to a cpuset. Multiple tasks may reference -the same cpuset. Requests by a task, using the sched_setaffinity(2) -system call to include CPUs in its CPU affinity mask, and using the -mbind(2) and set_mempolicy(2) system calls to include Memory Nodes -in its memory policy, are both filtered through that tasks cpuset, -filtering out any CPUs or Memory Nodes not in that cpuset. The -scheduler will not schedule a task on a CPU that is not allowed in -its cpus_allowed vector, and the kernel page allocator will not -allocate a page on a node that is not allowed in the requesting tasks -mems_allowed vector. - -User level code may create and destroy cpusets by name in the cpuset +Cpusets use the generic cgroup subsystem described in +Documentation/cgroup.txt. + +Requests by a task, using the sched_setaffinity(2) system call to +include CPUs in its CPU affinity mask, and using the mbind(2) and +set_mempolicy(2) system calls to include Memory Nodes in its memory +policy, are both filtered through that tasks cpuset, filtering out any +CPUs or Memory Nodes not in that cpuset. The scheduler will not +schedule a task on a CPU that is not allowed in its cpus_allowed +vector, and the kernel page allocator will not allocate a page on a +node that is not allowed in the requesting tasks mems_allowed vector. + +User level code may create and destroy cpusets by name in the cgroup virtual file system, manage the attributes and permissions of these cpusets and which CPUs and Memory Nodes are assigned to each cpuset, specify and query to which cpuset a task is assigned, and list the @@ -115,7 +117,7 @@ Cpusets extends these two mechanisms as follows: - Cpusets are sets of allowed CPUs and Memory Nodes, known to the kernel. - Each task in the system is attached to a cpuset, via a pointer - in the task structure to a reference counted cpuset structure. + in the task structure to a reference counted cgroup structure. - Calls to sched_setaffinity are filtered to just those CPUs allowed in that tasks cpuset. - Calls to mbind and set_mempolicy are filtered to just @@ -145,15 +147,10 @@ into the rest of the kernel, none in performance critical paths: - in page_alloc.c, to restrict memory to allowed nodes. - in vmscan.c, to restrict page recovery to the current cpuset. -In addition a new file system, of type "cpuset" may be mounted, -typically at /dev/cpuset, to enable browsing and modifying the cpusets -presently known to the kernel. No new system calls are added for -cpusets - all support for querying and modifying cpusets is via -this cpuset file system. - -Each task under /proc has an added file named 'cpuset', displaying -the cpuset name, as the path relative to the root of the cpuset file -system. +You should mount the "cgroup" filesystem type in order to enable +browsing and modifying the cpusets presently known to the kernel. No +new system calls are added for cpusets - all support for querying and +modifying cpusets is via this cpuset file system. The /proc//status file for each task has two added lines, displaying the tasks cpus_allowed (on which CPUs it may be scheduled) @@ -163,16 +160,15 @@ in the format seen in the following example: Cpus_allowed: ffffffff,ffffffff,ffffffff,ffffffff Mems_allowed: ffffffff,ffffffff -Each cpuset is represented by a directory in the cpuset file system -containing the following files describing that cpuset: +Each cpuset is represented by a directory in the cgroup file system +containing (on top of the standard cgroup files) the following +files describing that cpuset: - cpus: list of CPUs in that cpuset - mems: list of Memory Nodes in that cpuset - memory_migrate flag: if set, move pages to cpusets nodes - cpu_exclusive flag: is cpu placement exclusive? - mem_exclusive flag: is memory placement exclusive? - - tasks: list of tasks (by pid) attached to that cpuset - - notify_on_release flag: run /sbin/cpuset_release_agent on exit? - memory_pressure: measure of how much paging pressure in cpuset In addition, the root cpuset only has the following file: @@ -237,21 +233,7 @@ such as requests from interrupt handlers, is allowed to be taken outside even a mem_exclusive cpuset. -1.5 What does notify_on_release do ? ------------------------------------- - -If the notify_on_release flag is enabled (1) in a cpuset, then whenever -the last task in the cpuset leaves (exits or attaches to some other -cpuset) and the last child cpuset of that cpuset is removed, then -the kernel runs the command /sbin/cpuset_release_agent, supplying the -pathname (relative to the mount point of the cpuset file system) of the -abandoned cpuset. This enables automatic removal of abandoned cpusets. -The default value of notify_on_release in the root cpuset at system -boot is disabled (0). The default value of other cpusets at creation -is the current value of their parents notify_on_release setting. - - -1.6 What is memory_pressure ? +1.5 What is memory_pressure ? ----------------------------- The memory_pressure of a cpuset provides a simple per-cpuset metric of the rate that the tasks in a cpuset are attempting to free up in @@ -308,7 +290,7 @@ the tasks in the cpuset, in units of reclaims attempted per second, times 1000. -1.7 What is memory spread ? +1.6 What is memory spread ? --------------------------- There are two boolean flag files per cpuset that control where the kernel allocates pages for the file system buffers and related in @@ -378,6 +360,142 @@ policy, especially for jobs that might have one thread reading in the data set, the memory allocation across the nodes in the jobs cpuset can become very uneven. +1.7 What is sched_load_balance ? +-------------------------------- + +The kernel scheduler (kernel/sched.c) automatically load balances +tasks. If one CPU is underutilized, kernel code running on that +CPU will look for tasks on other more overloaded CPUs and move those +tasks to itself, within the constraints of such placement mechanisms +as cpusets and sched_setaffinity. + +The algorithmic cost of load balancing and its impact on key shared +kernel data structures such as the task list increases more than +linearly with the number of CPUs being balanced. So the scheduler +has support to partition the systems CPUs into a number of sched +domains such that it only load balances within each sched domain. +Each sched domain covers some subset of the CPUs in the system; +no two sched domains overlap; some CPUs might not be in any sched +domain and hence won't be load balanced. + +Put simply, it costs less to balance between two smaller sched domains +than one big one, but doing so means that overloads in one of the +two domains won't be load balanced to the other one. + +By default, there is one sched domain covering all CPUs, except those +marked isolated using the kernel boot time "isolcpus=" argument. + +This default load balancing across all CPUs is not well suited for +the following two situations: + 1) On large systems, load balancing across many CPUs is expensive. + If the system is managed using cpusets to place independent jobs + on separate sets of CPUs, full load balancing is unnecessary. + 2) Systems supporting realtime on some CPUs need to minimize + system overhead on those CPUs, including avoiding task load + balancing if that is not needed. + +When the per-cpuset flag "sched_load_balance" is enabled (the default +setting), it requests that all the CPUs in that cpusets allowed 'cpus' +be contained in a single sched domain, ensuring that load balancing +can move a task (not otherwised pinned, as by sched_setaffinity) +from any CPU in that cpuset to any other. + +When the per-cpuset flag "sched_load_balance" is disabled, then the +scheduler will avoid load balancing across the CPUs in that cpuset, +--except-- in so far as is necessary because some overlapping cpuset +has "sched_load_balance" enabled. + +So, for example, if the top cpuset has the flag "sched_load_balance" +enabled, then the scheduler will have one sched domain covering all +CPUs, and the setting of the "sched_load_balance" flag in any other +cpusets won't matter, as we're already fully load balancing. + +Therefore in the above two situations, the top cpuset flag +"sched_load_balance" should be disabled, and only some of the smaller, +child cpusets have this flag enabled. + +When doing this, you don't usually want to leave any unpinned tasks in +the top cpuset that might use non-trivial amounts of CPU, as such tasks +may be artificially constrained to some subset of CPUs, depending on +the particulars of this flag setting in descendent cpusets. Even if +such a task could use spare CPU cycles in some other CPUs, the kernel +scheduler might not consider the possibility of load balancing that +task to that underused CPU. + +Of course, tasks pinned to a particular CPU can be left in a cpuset +that disables "sched_load_balance" as those tasks aren't going anywhere +else anyway. + +There is an impedance mismatch here, between cpusets and sched domains. +Cpusets are hierarchical and nest. Sched domains are flat; they don't +overlap and each CPU is in at most one sched domain. + +It is necessary for sched domains to be flat because load balancing +across partially overlapping sets of CPUs would risk unstable dynamics +that would be beyond our understanding. So if each of two partially +overlapping cpusets enables the flag 'sched_load_balance', then we +form a single sched domain that is a superset of both. We won't move +a task to a CPU outside it cpuset, but the scheduler load balancing +code might waste some compute cycles considering that possibility. + +This mismatch is why there is not a simple one-to-one relation +between which cpusets have the flag "sched_load_balance" enabled, +and the sched domain configuration. If a cpuset enables the flag, it +will get balancing across all its CPUs, but if it disables the flag, +it will only be assured of no load balancing if no other overlapping +cpuset enables the flag. + +If two cpusets have partially overlapping 'cpus' allowed, and only +one of them has this flag enabled, then the other may find its +tasks only partially load balanced, just on the overlapping CPUs. +This is just the general case of the top_cpuset example given a few +paragraphs above. In the general case, as in the top cpuset case, +don't leave tasks that might use non-trivial amounts of CPU in +such partially load balanced cpusets, as they may be artificially +constrained to some subset of the CPUs allowed to them, for lack of +load balancing to the other CPUs. + +1.7.1 sched_load_balance implementation details. +------------------------------------------------ + +The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary +to most cpuset flags.) When enabled for a cpuset, the kernel will +ensure that it can load balance across all the CPUs in that cpuset +(makes sure that all the CPUs in the cpus_allowed of that cpuset are +in the same sched domain.) + +If two overlapping cpusets both have 'sched_load_balance' enabled, +then they will be (must be) both in the same sched domain. + +If, as is the default, the top cpuset has 'sched_load_balance' enabled, +then by the above that means there is a single sched domain covering +the whole system, regardless of any other cpuset settings. + +The kernel commits to user space that it will avoid load balancing +where it can. It will pick as fine a granularity partition of sched +domains as it can while still providing load balancing for any set +of CPUs allowed to a cpuset having 'sched_load_balance' enabled. + +The internal kernel cpuset to scheduler interface passes from the +cpuset code to the scheduler code a partition of the load balanced +CPUs in the system. This partition is a set of subsets (represented +as an array of cpumask_t) of CPUs, pairwise disjoint, that cover all +the CPUs that must be load balanced. + +Whenever the 'sched_load_balance' flag changes, or CPUs come or go +from a cpuset with this flag enabled, or a cpuset with this flag +enabled is removed, the cpuset code builds a new such partition and +passes it to the scheduler sched domain setup code, to have the sched +domains rebuilt as necessary. + +This partition exactly defines what sched domains the scheduler should +setup - one sched domain for each element (cpumask_t) in the partition. + +The scheduler remembers the currently active sched domain partitions. +When the scheduler routine partition_sched_domains() is invoked from +the cpuset code to update these sched domains, it compares the new +partition requested with the current, and updates its sched domains, +removing the old and adding the new, for each change. 1.8 How do I use cpusets ? -------------------------- @@ -469,7 +587,7 @@ than stress the kernel. To start a new job that is to be contained within a cpuset, the steps are: 1) mkdir /dev/cpuset - 2) mount -t cpuset none /dev/cpuset + 2) mount -t cgroup -ocpuset cpuset /dev/cpuset 3) Create the new cpuset by doing mkdir's and write's (or echo's) in the /dev/cpuset virtual file system. 4) Start a task that will be the "founding father" of the new job. @@ -481,7 +599,7 @@ For example, the following sequence of commands will setup a cpuset named "Charlie", containing just CPUs 2 and 3, and Memory Node 1, and then start a subshell 'sh' in that cpuset: - mount -t cpuset none /dev/cpuset + mount -t cgroup -ocpuset cpuset /dev/cpuset cd /dev/cpuset mkdir Charlie cd Charlie @@ -513,7 +631,7 @@ Creating, modifying, using the cpusets can be done through the cpuset virtual filesystem. To mount it, type: -# mount -t cpuset none /dev/cpuset +# mount -t cgroup -o cpuset cpuset /dev/cpuset Then under /dev/cpuset you can find a tree that corresponds to the tree of the cpusets in the system. For instance, /dev/cpuset @@ -556,6 +674,18 @@ To remove a cpuset, just use rmdir: This will fail if the cpuset is in use (has cpusets inside, or has processes attached). +Note that for legacy reasons, the "cpuset" filesystem exists as a +wrapper around the cgroup filesystem. + +The command + +mount -t cpuset X /dev/cpuset + +is equivalent to + +mount -t cgroup -ocpuset X /dev/cpuset +echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent + 2.2 Adding/removing cpus ------------------------ diff --git a/trunk/Documentation/device-mapper/dm-uevent.txt b/trunk/Documentation/device-mapper/dm-uevent.txt new file mode 100644 index 000000000000..07edbd85c714 --- /dev/null +++ b/trunk/Documentation/device-mapper/dm-uevent.txt @@ -0,0 +1,97 @@ +The device-mapper uevent code adds the capability to device-mapper to create +and send kobject uevents (uevents). Previously device-mapper events were only +available through the ioctl interface. The advantage of the uevents interface +is the event contains environment attributes providing increased context for +the event avoiding the need to query the state of the device-mapper device after +the event is received. + +There are two functions currently for device-mapper events. The first function +listed creates the event and the second function sends the event(s). + +void dm_path_uevent(enum dm_uevent_type event_type, struct dm_target *ti, + const char *path, unsigned nr_valid_paths) + +void dm_send_uevents(struct list_head *events, struct kobject *kobj) + + +The variables added to the uevent environment are: + +Variable Name: DM_TARGET +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: +Value: Name of device-mapper target that generated the event. + +Variable Name: DM_ACTION +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: +Value: Device-mapper specific action that caused the uevent action. + PATH_FAILED - A path has failed. + PATH_REINSTATED - A path has been reinstated. + +Variable Name: DM_SEQNUM +Uevent Action(s): KOBJ_CHANGE +Type: unsigned integer +Description: A sequence number for this specific device-mapper device. +Value: Valid unsigned integer range. + +Variable Name: DM_PATH +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: Major and minor number of the path device pertaining to this +event. +Value: Path name in the form of "Major:Minor" + +Variable Name: DM_NR_VALID_PATHS +Uevent Action(s): KOBJ_CHANGE +Type: unsigned integer +Description: +Value: Valid unsigned integer range. + +Variable Name: DM_NAME +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: Name of the device-mapper device. +Value: Name + +Variable Name: DM_UUID +Uevent Action(s): KOBJ_CHANGE +Type: string +Description: UUID of the device-mapper device. +Value: UUID. (Empty string if there isn't one.) + +An example of the uevents generated as captured by udevmonitor is shown +below. + +1.) Path failure. +UEVENT[1192521009.711215] change@/block/dm-3 +ACTION=change +DEVPATH=/block/dm-3 +SUBSYSTEM=block +DM_TARGET=multipath +DM_ACTION=PATH_FAILED +DM_SEQNUM=1 +DM_PATH=8:32 +DM_NR_VALID_PATHS=0 +DM_NAME=mpath2 +DM_UUID=mpath-35333333000002328 +MINOR=3 +MAJOR=253 +SEQNUM=1130 + +2.) Path reinstate. +UEVENT[1192521132.989927] change@/block/dm-3 +ACTION=change +DEVPATH=/block/dm-3 +SUBSYSTEM=block +DM_TARGET=multipath +DM_ACTION=PATH_REINSTATED +DM_SEQNUM=2 +DM_PATH=8:32 +DM_NR_VALID_PATHS=1 +DM_NAME=mpath2 +DM_UUID=mpath-35333333000002328 +MINOR=3 +MAJOR=253 +SEQNUM=1131 diff --git a/trunk/Documentation/devices.txt b/trunk/Documentation/devices.txt index 6c46730c631a..e6244cde26e9 100644 --- a/trunk/Documentation/devices.txt +++ b/trunk/Documentation/devices.txt @@ -2188,7 +2188,7 @@ Your cooperation is appreciated. 136-143 char Unix98 PTY slaves 0 = /dev/pts/0 First Unix98 pseudo-TTY - 1 = /dev/pts/1 Second Unix98 pesudo-TTY + 1 = /dev/pts/1 Second Unix98 pseudo-TTY ... These device nodes are automatically generated with diff --git a/trunk/Documentation/driver-model/devres.txt b/trunk/Documentation/driver-model/devres.txt index 8569072fa387..387b8a720f4a 100644 --- a/trunk/Documentation/driver-model/devres.txt +++ b/trunk/Documentation/driver-model/devres.txt @@ -32,7 +32,7 @@ braindamaged document, if it's finally working, well, it's working. For one reason or another, low level drivers don't receive as much attention or testing as core code, and bugs on driver detach or -initilaization failure doesn't happen often enough to be noticeable. +initialization failure don't happen often enough to be noticeable. Init failure path is worse because it's much less travelled while needs to handle multiple entry points. @@ -160,7 +160,7 @@ resources on failure. For example, devres_release_group(dev, NULL); return err_code; -As resource acquision failure usually means probe failure, constructs +As resource acquisition failure usually means probe failure, constructs like above are usually useful in midlayer driver (e.g. libata core layer) where interface function shouldn't have side effect on failure. For LLDs, just returning error code suffices in most cases. diff --git a/trunk/Documentation/fb/deferred_io.txt b/trunk/Documentation/fb/deferred_io.txt index 73cf9fb7cf60..63883a892120 100644 --- a/trunk/Documentation/fb/deferred_io.txt +++ b/trunk/Documentation/fb/deferred_io.txt @@ -3,7 +3,7 @@ Deferred IO Deferred IO is a way to delay and repurpose IO. It uses host memory as a buffer and the MMU pagefault as a pretrigger for when to perform the device -IO. The following example may be a useful explaination of how one such setup +IO. The following example may be a useful explanation of how one such setup works: - userspace app like Xfbdev mmaps framebuffer @@ -28,7 +28,7 @@ a relatively more expensive operation. For some types of nonvolatile high latency displays, the desired image is the final image rather than the intermediate stages which is why it's okay -to not update for each write that is occuring. +to not update for each write that is occurring. It may be the case that this is useful in other scenarios as well. Paul Mundt has mentioned a case where it is beneficial to use the page count to decide diff --git a/trunk/Documentation/feature-removal-schedule.txt b/trunk/Documentation/feature-removal-schedule.txt index 6b0f963f5379..20c4c8bac9d7 100644 --- a/trunk/Documentation/feature-removal-schedule.txt +++ b/trunk/Documentation/feature-removal-schedule.txt @@ -14,18 +14,6 @@ Who: Jiri Slaby --------------------------- -What: V4L2 VIDIOC_G_MPEGCOMP and VIDIOC_S_MPEGCOMP -When: October 2007 -Why: Broken attempt to set MPEG compression parameters. These ioctls are - not able to implement the wide variety of parameters that can be set - by hardware MPEG encoders. A new MPEG control mechanism was created - in kernel 2.6.18 that replaces these ioctls. See the V4L2 specification - (section 1.9: Extended controls) for more information on this topic. -Who: Hans Verkuil and - Mauro Carvalho Chehab - ---------------------------- - What: dev->power.power_state When: July 2007 Why: Broken design for runtime control over driver power states, confusing @@ -49,10 +37,10 @@ Who: David Miller --------------------------- What: Video4Linux API 1 ioctls and video_decoder.h from Video devices. -When: December 2006 -Files: include/linux/video_decoder.h -Check: include/linux/video_decoder.h -Why: V4L1 AP1 was replaced by V4L2 API. during migration from 2.4 to 2.6 +When: December 2008 +Files: include/linux/video_decoder.h include/linux/videodev.h +Check: include/linux/video_decoder.h include/linux/videodev.h +Why: V4L1 AP1 was replaced by V4L2 API during migration from 2.4 to 2.6 series. The old API have lots of drawbacks and don't provide enough means to work with all video and audio standards. The newer API is already available on the main drivers and should be used instead. @@ -61,7 +49,9 @@ Why: V4L1 AP1 was replaced by V4L2 API. during migration from 2.4 to 2.6 Decoder iocts are using internally to allow video drivers to communicate with video decoders. This should also be improved to allow V4L2 calls being translated into compatible internal ioctls. -Who: Mauro Carvalho Chehab + Compatibility ioctls will be provided, for a while, via + v4l1-compat module. +Who: Mauro Carvalho Chehab --------------------------- @@ -191,15 +181,6 @@ Who: Nick Piggin --------------------------- -What: Interrupt only SA_* flags -When: September 2007 -Why: The interrupt related SA_* flags are replaced by IRQF_* to move them - out of the signal namespace. - -Who: Thomas Gleixner - ---------------------------- - What: PHYSDEVPATH, PHYSDEVBUS, PHYSDEVDRIVER in the uevent environment When: October 2008 Why: The stacking of class devices makes these values misleading and diff --git a/trunk/Documentation/filesystems/9p.txt b/trunk/Documentation/filesystems/9p.txt index d6fd6c6e4244..bf8080640eba 100644 --- a/trunk/Documentation/filesystems/9p.txt +++ b/trunk/Documentation/filesystems/9p.txt @@ -42,10 +42,12 @@ OPTIONS trans=name select an alternative transport. Valid options are currently: - unix - specifying a named pipe mount point - tcp - specifying a normal TCP/IP connection - fd - used passed file descriptors for connection + unix - specifying a named pipe mount point + tcp - specifying a normal TCP/IP connection + fd - used passed file descriptors for connection (see rfdno and wfdno) + virtio - connect to the next virtio channel available + (from lguest or KVM with trans_virtio module) uname=name user name to attempt mount as on the remote server. The server may override or ignore this value. Certain user @@ -54,7 +56,7 @@ OPTIONS aname=name aname specifies the file tree to access when the server is offering several exported file systems. - cache=mode specifies a cacheing policy. By default, no caches are used. + cache=mode specifies a caching policy. By default, no caches are used. loose = no attempts are made at consistency, intended for exclusive, read-only mounts diff --git a/trunk/Documentation/filesystems/Exporting b/trunk/Documentation/filesystems/Exporting index 31047e0fe14b..87019d2b5981 100644 --- a/trunk/Documentation/filesystems/Exporting +++ b/trunk/Documentation/filesystems/Exporting @@ -2,9 +2,12 @@ Making Filesystems Exportable ============================= -Most filesystem operations require a dentry (or two) as a starting +Overview +-------- + +All filesystem operations require a dentry (or two) as a starting point. Local applications have a reference-counted hold on suitable -dentrys via open file descriptors or cwd/root. However remote +dentries via open file descriptors or cwd/root. However remote applications that access a filesystem via a remote filesystem protocol such as NFS may not be able to hold such a reference, and so need a different way to refer to a particular dentry. As the alternative @@ -13,14 +16,14 @@ server-reboot (among other things, though these tend to be the most problematic), there is no simple answer like 'filename'. The mechanism discussed here allows each filesystem implementation to -specify how to generate an opaque (out side of the filesystem) byte +specify how to generate an opaque (outside of the filesystem) byte string for any dentry, and how to find an appropriate dentry for any given opaque byte string. This byte string will be called a "filehandle fragment" as it corresponds to part of an NFS filehandle. A filesystem which supports the mapping between filehandle fragments -and dentrys will be termed "exportable". +and dentries will be termed "exportable". @@ -89,11 +92,9 @@ For a filesystem to be exportable it must: 1/ provide the filehandle fragment routines described below. 2/ make sure that d_splice_alias is used rather than d_add when ->lookup finds an inode for a given parent and name. - Typically the ->lookup routine will end: - if (inode) - return d_splice(inode, dentry); - d_add(dentry, inode); - return NULL; + Typically the ->lookup routine will end with a: + + return d_splice_alias(inode, dentry); } @@ -101,67 +102,39 @@ For a filesystem to be exportable it must: A file system implementation declares that instances of the filesystem are exportable by setting the s_export_op field in the struct super_block. This field must point to a "struct export_operations" -struct which could potentially be full of NULLs, though normally at -least get_parent will be set. - - The primary operations are decode_fh and encode_fh. -decode_fh takes a filehandle fragment and tries to find or create a -dentry for the object referred to by the filehandle. -encode_fh takes a dentry and creates a filehandle fragment which can -later be used to find/create a dentry for the same object. - -decode_fh will probably make use of "find_exported_dentry". -This function lives in the "exportfs" module which a filesystem does -not need unless it is being exported. So rather that calling -find_exported_dentry directly, each filesystem should call it through -the find_exported_dentry pointer in it's export_operations table. -This field is set correctly by the exporting agent (e.g. nfsd) when a -filesystem is exported, and before any export operations are called. - -find_exported_dentry needs three support functions from the -filesystem: - get_name. When given a parent dentry and a child dentry, this - should find a name in the directory identified by the parent - dentry, which leads to the object identified by the child dentry. - If no get_name function is supplied, a default implementation is - provided which uses vfs_readdir to find potential names, and - matches inode numbers to find the correct match. - - get_parent. When given a dentry for a directory, this should return - a dentry for the parent. Quite possibly the parent dentry will - have been allocated by d_alloc_anon. - The default get_parent function just returns an error so any - filehandle lookup that requires finding a parent will fail. - ->lookup("..") is *not* used as a default as it can leave ".." - entries in the dcache which are too messy to work with. - - get_dentry. When given an opaque datum, this should find the - implied object and create a dentry for it (possibly with - d_alloc_anon). - The opaque datum is whatever is passed down by the decode_fh - function, and is often simply a fragment of the filehandle - fragment. - decode_fh passes two datums through find_exported_dentry. One that - should be used to identify the target object, and one that can be - used to identify the object's parent, should that be necessary. - The default get_dentry function assumes that the datum contains an - inode number and a generation number, and it attempts to get the - inode using "iget" and check it's validity by matching the - generation number. A filesystem should only depend on the default - if iget can safely be used this way. - -If decode_fh and/or encode_fh are left as NULL, then default -implementations are used. These defaults are suitable for ext2 and -extremely similar filesystems (like ext3). - -The default encode_fh creates a filehandle fragment from the inode -number and generation number of the target together with the inode -number and generation number of the parent (if the parent is -required). - -The default decode_fh extract the target and parent datums from the -filehandle assuming the format used by the default encode_fh and -passed them to find_exported_dentry. +struct which has the following members: + + encode_fh (optional) + Takes a dentry and creates a filehandle fragment which can later be used + to find or create a dentry for the same object. The default + implementation creates a filehandle fragment that encodes a 32bit inode + and generation number for the inode encoded, and if necessary the + same information for the parent. + + fh_to_dentry (mandatory) + Given a filehandle fragment, this should find the implied object and + create a dentry for it (possibly with d_alloc_anon). + + fh_to_parent (optional but strongly recommended) + Given a filehandle fragment, this should find the parent of the + implied object and create a dentry for it (possibly with d_alloc_anon). + May fail if the filehandle fragment is too small. + + get_parent (optional but strongly recommended) + When given a dentry for a directory, this should return a dentry for + the parent. Quite possibly the parent dentry will have been allocated + by d_alloc_anon. The default get_parent function just returns an error + so any filehandle lookup that requires finding a parent will fail. + ->lookup("..") is *not* used as a default as it can leave ".." entries + in the dcache which are too messy to work with. + + get_name (optional) + When given a parent dentry and a child dentry, this should find a name + in the directory identified by the parent dentry, which leads to the + object identified by the child dentry. If no get_name function is + supplied, a default implementation is provided which uses vfs_readdir + to find potential names, and matches inode numbers to find the correct + match. A filehandle fragment consists of an array of 1 or more 4byte words, @@ -172,5 +145,3 @@ generated by encode_fh, in which case it will have been padded with nuls. Rather, the encode_fh routine should choose a "type" which indicates the decode_fh how much of the filehandle is valid, and how it should be interpreted. - - diff --git a/trunk/Documentation/filesystems/Locking b/trunk/Documentation/filesystems/Locking index fe26cc978523..37c10cba7177 100644 --- a/trunk/Documentation/filesystems/Locking +++ b/trunk/Documentation/filesystems/Locking @@ -224,7 +224,7 @@ against the page the filesystem should redirty the page with redirty_page_for_writepage(), then unlock the page and return zero. This may also be done to avoid internal deadlocks, but rarely. -If the filesytem is called for sync then it must wait on any +If the filesystem is called for sync then it must wait on any in-progress I/O and then start new I/O. The filesystem should unlock the page synchronously, before returning to the diff --git a/trunk/Documentation/filesystems/ext3.txt b/trunk/Documentation/filesystems/ext3.txt index 4aecc9bdb273..b45f3c1b8b43 100644 --- a/trunk/Documentation/filesystems/ext3.txt +++ b/trunk/Documentation/filesystems/ext3.txt @@ -130,12 +130,12 @@ Device layer. Journaling Block Device layer ----------------------------- -The Journaling Block Device layer (JBD) isn't ext3 specific. It was design to -add journaling capabilities on a block device. The ext3 filesystem code will -inform the JBD of modifications it is performing (called a transaction). The -journal supports the transactions start and stop, and in case of crash, the -journal can replayed the transactions to put the partition back in a -consistent state fast. +The Journaling Block Device layer (JBD) isn't ext3 specific. It was designed +to add journaling capabilities to a block device. The ext3 filesystem code +will inform the JBD of modifications it is performing (called a transaction). +The journal supports the transactions start and stop, and in case of a crash, +the journal can replay the transactions to quickly put the partition back into +a consistent state. Handles represent a single atomic update to a filesystem. JBD can handle an external journal on a block device. @@ -164,7 +164,7 @@ written to the journal first, and then to its final location. In the event of a crash, the journal can be replayed, bringing both data and metadata into a consistent state. This mode is the slowest except when data needs to be read from and written to disk at the same time where it -outperforms all others modes. +outperforms all other modes. Compatibility ------------- diff --git a/trunk/Documentation/filesystems/files.txt b/trunk/Documentation/filesystems/files.txt index 133e213ebb72..bb0142f61084 100644 --- a/trunk/Documentation/filesystems/files.txt +++ b/trunk/Documentation/filesystems/files.txt @@ -76,13 +76,13 @@ the fdtable structure - 5. Handling of the file structures is special. Since the look-up of the fd (fget()/fget_light()) are lock-free, it is possible that look-up may race with the last put() operation on the - file structure. This is avoided using the rcuref APIs + file structure. This is avoided using atomic_inc_not_zero() on ->f_count : rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - if (rcuref_inc_lf(&file->f_count)) + if (atomic_inc_not_zero(&file->f_count)) *fput_needed = 1; else /* Didn't get the reference, someone's freed */ @@ -92,7 +92,7 @@ the fdtable structure - .... return file; - rcuref_inc_lf() detects if refcounts is already zero or + atomic_inc_not_zero() detects if refcounts is already zero or goes to zero during increment. If it does, we fail fget()/fget_light(). diff --git a/trunk/Documentation/filesystems/proc.txt b/trunk/Documentation/filesystems/proc.txt index e5c1df52a876..dec99455321f 100644 --- a/trunk/Documentation/filesystems/proc.txt +++ b/trunk/Documentation/filesystems/proc.txt @@ -813,9 +813,9 @@ Various pieces of information about kernel activity are available in the since the system first booted. For a quick look, simply cat the file: > cat /proc/stat - cpu 2255 34 2290 22625563 6290 127 456 - cpu0 1132 34 1441 11311718 3675 127 438 - cpu1 1123 0 849 11313845 2614 0 18 + cpu 2255 34 2290 22625563 6290 127 456 0 + cpu0 1132 34 1441 11311718 3675 127 438 0 + cpu1 1123 0 849 11313845 2614 0 18 0 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...] ctxt 1990473 btime 1062191376 @@ -835,6 +835,7 @@ second). The meanings of the columns are as follows, from left to right: - iowait: waiting for I/O to complete - irq: servicing interrupts - softirq: servicing softirqs +- steal: involuntary wait The "intr" line gives counts of interrupts serviced since boot time, for each of the possible system interrupts. The first column is the total of all diff --git a/trunk/Documentation/filesystems/sysfs.txt b/trunk/Documentation/filesystems/sysfs.txt index 4b5ca26e5048..4598ef7b622b 100644 --- a/trunk/Documentation/filesystems/sysfs.txt +++ b/trunk/Documentation/filesystems/sysfs.txt @@ -51,7 +51,7 @@ for the attributes, providing a means to read and write kernel attributes. Attributes should be ASCII text files, preferably with only one value -per file. It is noted that it may not be efficient to contain only +per file. It is noted that it may not be efficient to contain only one value per file, so it is socially acceptable to express an array of values of the same type. diff --git a/trunk/Documentation/filesystems/vfs.txt b/trunk/Documentation/filesystems/vfs.txt index 6f8e16e3d6c0..9d019d35728f 100644 --- a/trunk/Documentation/filesystems/vfs.txt +++ b/trunk/Documentation/filesystems/vfs.txt @@ -706,7 +706,7 @@ struct address_space_operations { wants to make it a free page. If ->releasepage succeeds, the page will be removed from the address_space and become free. - The second case if when a request has been made to invalidate + The second case is when a request has been made to invalidate some or all pages in an address_space. This can happen through the fadvice(POSIX_FADV_DONTNEED) system call or by the filesystem explicitly requesting it as nfs and 9fs do (when diff --git a/trunk/Documentation/hwmon/sysfs-interface b/trunk/Documentation/hwmon/sysfs-interface index a17b692d2679..f4a8ebc1ef1a 100644 --- a/trunk/Documentation/hwmon/sysfs-interface +++ b/trunk/Documentation/hwmon/sysfs-interface @@ -328,6 +328,37 @@ curr[1-*]_input Current input value Unit: milliampere RO +********* +* Power * +********* + +power[1-*]_average Average power use + Unit: microWatt + RO + +power[1-*]_average_highest Historical average maximum power use + Unit: microWatt + RO + +power[1-*]_average_lowest Historical average minimum power use + Unit: microWatt + RO + +power[1-*]_input Instantaneous power use + Unit: microWatt + RO + +power[1-*]_input_highest Historical maximum power use + Unit: microWatt + RO + +power[1-*]_input_lowest Historical minimum power use + Unit: microWatt + RO + +power[1-*]_reset_history Reset input_highest, input_lowest, + average_highest and average_lowest. + WO ********** * Alarms * diff --git a/trunk/Documentation/i2c/i2c-protocol b/trunk/Documentation/i2c/i2c-protocol index 579b92d5f3a3..10518dd58814 100644 --- a/trunk/Documentation/i2c/i2c-protocol +++ b/trunk/Documentation/i2c/i2c-protocol @@ -68,7 +68,7 @@ We have found some I2C devices that needs the following modifications: Flags I2C_M_IGNORE_NAK Normally message is interrupted immediately if there is [NA] from the - client. Setting this flag treats any [NA] as [A], and all of + client. Setting this flag treats any [NA] as [A], and all of message is sent. These messages may still fail to SCL lo->hi timeout. diff --git a/trunk/Documentation/i386/boot.txt b/trunk/Documentation/i386/boot.txt index 35985b34d5a6..fc49b79bc1ab 100644 --- a/trunk/Documentation/i386/boot.txt +++ b/trunk/Documentation/i386/boot.txt @@ -168,6 +168,8 @@ Offset Proto Name Meaning 0234/1 2.05+ relocatable_kernel Whether kernel is relocatable or not 0235/3 N/A pad2 Unused 0238/4 2.06+ cmdline_size Maximum size of the kernel command line +023C/4 2.07+ hardware_subarch Hardware subarchitecture +0240/8 2.07+ hardware_subarch_data Subarchitecture-specific data (1) For backwards compatibility, if the setup_sects field contains 0, the real value is 4. @@ -204,7 +206,7 @@ boot loaders can ignore those fields. The byte order of all fields is littleendian (this is x86, after all.) -Field name: setup_secs +Field name: setup_sects Type: read Offset/size: 0x1f1/1 Protocol: ALL @@ -356,6 +358,13 @@ Protocol: 2.00+ - If 0, the protected-mode code is loaded at 0x10000. - If 1, the protected-mode code is loaded at 0x100000. + Bit 6 (write): KEEP_SEGMENTS + Protocol: 2.07+ + - if 0, reload the segment registers in the 32bit entry point. + - if 1, do not reload the segment registers in the 32bit entry point. + Assume that %cs %ds %ss %es are all set to flat segments with + a base of 0 (or the equivalent for their environment). + Bit 7 (write): CAN_USE_HEAP Set this bit to 1 to indicate that the value entered in the heap_end_ptr is valid. If this field is clear, some setup code @@ -480,6 +489,29 @@ Protocol: 2.06+ cmdline_size characters. With protocol version 2.05 and earlier, the maximum size was 255. +Field name: hardware_subarch +Type: write +Offset/size: 0x23c/4 +Protocol: 2.07+ + + In a paravirtualized environment the hardware low level architectural + pieces such as interrupt handling, page table handling, and + accessing process control registers needs to be done differently. + + This field allows the bootloader to inform the kernel we are in one + one of those environments. + + 0x00000000 The default x86/PC environment + 0x00000001 lguest + 0x00000002 Xen + +Field name: hardware_subarch_data +Type: write +Offset/size: 0x240/8 +Protocol: 2.07+ + + A pointer to data that is specific to hardware subarch + **** THE KERNEL COMMAND LINE @@ -753,3 +785,41 @@ IMPORTANT: All the hooks are required to preserve %esp, %ebp, %esi and After completing your hook, you should jump to the address that was in this field before your boot loader overwrote it (relocated, if appropriate.) + + +**** 32-bit BOOT PROTOCOL + +For machine with some new BIOS other than legacy BIOS, such as EFI, +LinuxBIOS, etc, and kexec, the 16-bit real mode setup code in kernel +based on legacy BIOS can not be used, so a 32-bit boot protocol needs +to be defined. + +In 32-bit boot protocol, the first step in loading a Linux kernel +should be to setup the boot parameters (struct boot_params, +traditionally known as "zero page"). The memory for struct boot_params +should be allocated and initialized to all zero. Then the setup header +from offset 0x01f1 of kernel image on should be loaded into struct +boot_params and examined. The end of setup header can be calculated as +follow: + + 0x0202 + byte value at offset 0x0201 + +In addition to read/modify/write the setup header of the struct +boot_params as that of 16-bit boot protocol, the boot loader should +also fill the additional fields of the struct boot_params as that +described in zero-page.txt. + +After setupping the struct boot_params, the boot loader can load the +32/64-bit kernel in the same way as that of 16-bit boot protocol. + +In 32-bit boot protocol, the kernel is started by jumping to the +32-bit kernel entry point, which is the start address of loaded +32/64-bit kernel. + +At entry, the CPU must be in 32-bit protected mode with paging +disabled; a GDT must be loaded with the descriptors for selectors +__BOOT_CS(0x10) and __BOOT_DS(0x18); both descriptors must be 4G flat +segment; __BOOS_CS must have execute/read permission, and __BOOT_DS +must have read/write permission; CS must be __BOOT_CS and DS, ES, SS +must be __BOOT_DS; interrupt must be disabled; %esi must hold the base +address of the struct boot_params; %ebp, %edi and %ebx must be zero. diff --git a/trunk/Documentation/i386/zero-page.txt b/trunk/Documentation/i386/zero-page.txt index 6c0817c45683..169ad423a3d1 100644 --- a/trunk/Documentation/i386/zero-page.txt +++ b/trunk/Documentation/i386/zero-page.txt @@ -1,99 +1,31 @@ ---------------------------------------------------------------------------- -!!!!!!!!!!!!!!!WARNING!!!!!!!! -The zero page is a kernel internal data structure, not a stable ABI. It might change -without warning and the kernel has no way to detect old version of it. -If you're writing some external code like a boot loader you should only use -the stable versioned real mode boot protocol described in boot.txt. Otherwise the kernel -might break you at any time. -!!!!!!!!!!!!!WARNING!!!!!!!!!!! ----------------------------------------------------------------------------- +The additional fields in struct boot_params as a part of 32-bit boot +protocol of kernel. These should be filled by bootloader or 16-bit +real-mode setup code of the kernel. References/settings to it mainly +are in: -Summary of boot_params layout (kernel point of view) - ( collected by Hans Lermen and Martin Mares ) - -The contents of boot_params are used to pass parameters from the -16-bit realmode code of the kernel to the 32-bit part. References/settings -to it mainly are in: + include/asm-x86/bootparam.h - arch/i386/boot/setup.S - arch/i386/boot/video.S - arch/i386/kernel/head.S - arch/i386/kernel/setup.c - -Offset Type Description ------- ---- ----------- - 0 32 bytes struct screen_info, SCREEN_INFO - ATTENTION, overlaps the following !!! - 2 unsigned short EXT_MEM_K, extended memory size in Kb (from int 0x15) - 0x20 unsigned short CL_MAGIC, commandline magic number (=0xA33F) - 0x22 unsigned short CL_OFFSET, commandline offset - Address of commandline is calculated: - 0x90000 + contents of CL_OFFSET - (only taken, when CL_MAGIC = 0xA33F) - 0x40 20 bytes struct apm_bios_info, APM_BIOS_INFO - 0x60 16 bytes Intel SpeedStep (IST) BIOS support information - 0x80 16 bytes hd0-disk-parameter from intvector 0x41 - 0x90 16 bytes hd1-disk-parameter from intvector 0x46 +Offset Proto Name Meaning +/Size - 0xa0 16 bytes System description table truncated to 16 bytes. - ( struct sys_desc_table_struct ) - 0xb0 - 0x13f Free. Add more parameters here if you really need them. - 0x140- 0x1be EDID_INFO Video mode setup - -0x1c4 unsigned long EFI system table pointer -0x1c8 unsigned long EFI memory descriptor size -0x1cc unsigned long EFI memory descriptor version -0x1d0 unsigned long EFI memory descriptor map pointer -0x1d4 unsigned long EFI memory descriptor map size -0x1e0 unsigned long ALT_MEM_K, alternative mem check, in Kb -0x1e4 unsigned long Scratch field for the kernel setup code -0x1e8 char number of entries in E820MAP (below) -0x1e9 unsigned char number of entries in EDDBUF (below) -0x1ea unsigned char number of entries in EDD_MBR_SIG_BUFFER (below) -0x1f1 char size of setup.S, number of sectors -0x1f2 unsigned short MOUNT_ROOT_RDONLY (if !=0) -0x1f4 unsigned short size of compressed kernel-part in the - (b)zImage-file (in 16 byte units, rounded up) -0x1f6 unsigned short swap_dev (unused AFAIK) -0x1f8 unsigned short RAMDISK_FLAGS -0x1fa unsigned short VGA-Mode (old one) -0x1fc unsigned short ORIG_ROOT_DEV (high=Major, low=minor) -0x1ff char AUX_DEVICE_INFO - -0x200 short jump to start of setup code aka "reserved" field. -0x202 4 bytes Signature for SETUP-header, ="HdrS" -0x206 unsigned short Version number of header format - Current version is 0x0201... -0x208 8 bytes (used by setup.S for communication with boot loaders, - look there) -0x210 char LOADER_TYPE, = 0, old one - else it is set by the loader: - 0xTV: T=0 for LILO - 1 for Loadlin - 2 for bootsect-loader - 3 for SYSLINUX - 4 for ETHERBOOT - 5 for ELILO - 7 for GRuB - 8 for U-BOOT - 9 for Xen - V = version -0x211 char loadflags: - bit0 = 1: kernel is loaded high (bzImage) - bit7 = 1: Heap and pointer (see below) set by boot - loader. -0x212 unsigned short (setup.S) -0x214 unsigned long KERNEL_START, where the loader started the kernel -0x218 unsigned long INITRD_START, address of loaded ramdisk image -0x21c unsigned long INITRD_SIZE, size in bytes of ramdisk image -0x220 4 bytes (setup.S) -0x224 unsigned short setup.S heap end pointer -0x226 unsigned short zero_pad -0x228 unsigned long cmd_line_ptr -0x22c unsigned long ramdisk_max -0x230 16 bytes trampoline -0x290 - 0x2cf EDD_MBR_SIG_BUFFER (edd.S) -0x2d0 - 0xd00 E820MAP -0xd00 - 0xeff EDDBUF (edd.S) for disk signature read sector -0xd00 - 0xeeb EDDBUF (edd.S) for edd data +000/040 ALL screen_info Text mode or frame buffer information + (struct screen_info) +040/014 ALL apm_bios_info APM BIOS information (struct apm_bios_info) +060/010 ALL ist_info Intel SpeedStep (IST) BIOS support information + (struct ist_info) +080/010 ALL hd0_info hd0 disk parameter, OBSOLETE!! +090/010 ALL hd1_info hd1 disk parameter, OBSOLETE!! +0A0/010 ALL sys_desc_table System description table (struct sys_desc_table) +140/080 ALL edid_info Video mode setup (struct edid_info) +1C0/020 ALL efi_info EFI 32 information (struct efi_info) +1E0/004 ALL alk_mem_k Alternative mem check, in KB +1E4/004 ALL scratch Scratch field for the kernel setup code +1E8/001 ALL e820_entries Number of entries in e820_map (below) +1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below) +1EA/001 ALL edd_mbr_sig_buf_entries Number of entries in edd_mbr_sig_buffer + (below) +290/040 ALL edd_mbr_sig_buffer EDD MBR signatures +2D0/A00 ALL e820_map E820 memory map table + (array of struct e820entry) +D00/1EC ALL eddbuf EDD data (array of struct edd_info) diff --git a/trunk/Documentation/ia64/err_inject.txt b/trunk/Documentation/ia64/err_inject.txt index 6449a7090dbb..223e4f0582d0 100644 --- a/trunk/Documentation/ia64/err_inject.txt +++ b/trunk/Documentation/ia64/err_inject.txt @@ -21,10 +21,10 @@ software test suits to do stressful testing on IPF. Below is a sample application as part of the whole tool. The sample can be used as a working test tool. Or it can be expanded to include -more features. It also can be a integrated into a libary or other user +more features. It also can be a integrated into a library or other user application to have more thorough test. -The sample application takes err.conf as error configuation input. Gcc +The sample application takes err.conf as error configuration input. GCC compiles the code. After you install err_inject driver, you can run this sample application to inject errors. @@ -809,7 +809,7 @@ int err_inj() } /* Create semaphore: If one_lock, one semaphore for all processors. - Otherwise, one sempaphore for each processor. */ + Otherwise, one semaphore for each processor. */ if (one_lock) { if (create_sem(0)) { printf("Can not create semaphore...exit\n"); diff --git a/trunk/Documentation/input/atarikbd.txt b/trunk/Documentation/input/atarikbd.txt index ab050621e20f..f3a3ba8847ba 100644 --- a/trunk/Documentation/input/atarikbd.txt +++ b/trunk/Documentation/input/atarikbd.txt @@ -170,7 +170,7 @@ major controller faults (ROM checksum and RAM test) and such things as stuck keys. Any keys down at power-up are presumed to be stuck, and their BREAK (sic) code is returned (which without the preceding MAKE code is a flag for a keyboard error). If the controller self-test completes without error, the code -0xF0 is returned. (This code will be used to indicate the version/rlease of +0xF0 is returned. (This code will be used to indicate the version/release of the ikbd controller. The first release of the ikbd is version 0xF0, should there be a second release it will be 0xF1, and so on.) The ikbd defaults to a mouse position reporting with threshold of 1 unit in @@ -413,7 +413,7 @@ INTERROGATION MODE. %nnnnmmmm ; where m is JOYSTICK1 state ; and n is JOYSTICK0 state -Sets the ikbd to do nothing but monitor the serial command lne, maintain the +Sets the ikbd to do nothing but monitor the serial command line, maintain the time-of-day clock, and monitor the joystick. The rate sets the interval between joystick samples. N.B. The user should not set the rate higher than the serial communications @@ -446,10 +446,10 @@ The sample interval should be as constant as possible. ; until vertical cursor key is generated before RY ; has elapsed VX ; length (in tenths of seconds) of joystick closure - ; until horizontal cursor keystokes are generated + ; until horizontal cursor keystrokes are generated ; after RX has elapsed VY ; length (in tenths of seconds) of joystick closure - ; until vertical cursor keystokes are generated + ; until vertical cursor keystrokes are generated ; after RY has elapsed In this mode, joystick 0 is scanned in a way that simulates cursor keystrokes. diff --git a/trunk/Documentation/input/ff.txt b/trunk/Documentation/input/ff.txt index 085eb15b45b7..ded4d5f53109 100644 --- a/trunk/Documentation/input/ff.txt +++ b/trunk/Documentation/input/ff.txt @@ -1,5 +1,5 @@ Force feedback for Linux. -By Johann Deneux on 2001/04/22. +By Johann Deneux on 2001/04/22. Updated by Anssi Hannula on 2006/04/09. You may redistribute this file. Please remember to include shape.fig and interactive.fig as well. diff --git a/trunk/Documentation/input/iforce-protocol.txt b/trunk/Documentation/input/iforce-protocol.txt index 8777d2d321e3..3ac92413c874 100644 --- a/trunk/Documentation/input/iforce-protocol.txt +++ b/trunk/Documentation/input/iforce-protocol.txt @@ -4,10 +4,10 @@ specify force effects to I-Force 2.0 devices. None of this information comes from Immerse. That's why you should not trust what is written in this document. This document is intended to help understanding the protocol. This is not a reference. Comments and corrections are welcome. To contact me, -send an email to: deneux@ifrance.com +send an email to: johann.deneux@gmail.com ** WARNING ** -I may not be held responsible for any dammage or harm caused if you try to +I shall not be held responsible for any damage or harm caused if you try to send data to your I-Force device based on what you read in this document. ** Preliminary Notes: @@ -151,13 +151,13 @@ OP= ff Query command. Length varies according to the query type. The general format of this packet is: ff 01 QUERY [INDEX] CHECKSUM -reponses are of the same form: +responses are of the same form: FF LEN QUERY VALUE_QUERIED CHECKSUM2 where LEN = 1 + length(VALUE_QUERIED) **** Query ram size **** QUERY = 42 ('B'uffer size) -The device should reply with the same packet plus two additionnal bytes +The device should reply with the same packet plus two additional bytes containing the size of the memory: ff 03 42 03 e8 CS would mean that the device has 1000 bytes of ram available. @@ -234,19 +234,23 @@ is the amount of memory apparently needed for every set of parameters: ** Appendix: How to study the protocol ? ** -1. Generate effects using the force editor provided with the DirectX SDK, or use Immersion Studio (freely available at their web site in the developer section: www.immersion.com) -2. Start a soft spying RS232 or USB (depending on where you connected your joystick/wheel). I used ComPortSpy from fCoder (alpha version!) +1. Generate effects using the force editor provided with the DirectX SDK, or +use Immersion Studio (freely available at their web site in the developer section: +www.immersion.com) +2. Start a soft spying RS232 or USB (depending on where you connected your +joystick/wheel). I used ComPortSpy from fCoder (alpha version!) 3. Play the effect, and watch what happens on the spy screen. A few words about ComPortSpy: -At first glance, this soft seems, hum, well... buggy. In fact, data appear with a few seconds latency. Personnaly, I restart it every time I play an effect. +At first glance, this software seems, hum, well... buggy. In fact, data appear with a +few seconds latency. Personally, I restart it every time I play an effect. Remember it's free (as in free beer) and alpha! ** URLS ** Check www.immerse.com for Immersion Studio, and www.fcoder.com for ComPortSpy. ** Author of this document ** -Johann Deneux +Johann Deneux Home page at http://www.esil.univ-mrs.fr/~jdeneux/projects/ff/ Additions by Vojtech Pavlik. diff --git a/trunk/Documentation/input/input-programming.txt b/trunk/Documentation/input/input-programming.txt index d9d523099bb7..47fc86830cd7 100644 --- a/trunk/Documentation/input/input-programming.txt +++ b/trunk/Documentation/input/input-programming.txt @@ -42,8 +42,8 @@ static int __init button_init(void) goto err_free_irq; } - button_dev->evbit[0] = BIT(EV_KEY); - button_dev->keybit[LONG(BTN_0)] = BIT(BTN_0); + button_dev->evbit[0] = BIT_MASK(EV_KEY); + button_dev->keybit[BIT_WORD(BTN_0)] = BIT_MASK(BTN_0); error = input_register_device(button_dev); if (error) { @@ -79,7 +79,7 @@ In the _init function, which is called either upon module load or when booting the kernel, it grabs the required resources (it should also check for the presence of the device). -Then it allocates a new input device structure with input_aloocate_device() +Then it allocates a new input device structure with input_allocate_device() and sets up input bitfields. This way the device driver tells the other parts of the input systems what it is - what events can be generated or accepted by this input device. Our example device can only generate EV_KEY @@ -217,14 +217,15 @@ If you don't need absfuzz and absflat, you can set them to zero, which mean that the thing is precise and always returns to exactly the center position (if it has any). -1.4 NBITS(), LONG(), BIT() +1.4 BITS_TO_LONGS(), BIT_WORD(), BIT_MASK() ~~~~~~~~~~~~~~~~~~~~~~~~~~ -These three macros from input.h help some bitfield computations: +These three macros from bitops.h help some bitfield computations: - NBITS(x) - returns the length of a bitfield array in longs for x bits - LONG(x) - returns the index in the array in longs for bit x - BIT(x) - returns the index in a long for bit x + BITS_TO_LONGS(x) - returns the length of a bitfield array in longs for + x bits + BIT_WORD(x) - returns the index in the array in longs for bit x + BIT_MASK(x) - returns the index in a long for bit x 1.5 The id* and name fields ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/trunk/Documentation/isdn/CREDITS b/trunk/Documentation/isdn/CREDITS index 7c17c837064f..8cac6c2f23ee 100644 --- a/trunk/Documentation/isdn/CREDITS +++ b/trunk/Documentation/isdn/CREDITS @@ -40,7 +40,7 @@ Andreas Kool (akool@Kool.f.EUnet.de) Pedro Roque Marques (roque@di.fc.ul.pt) For lot of new ideas and the pcbit driver. -Eberhard Moenkeberg (emoenke@gwdg.de) +Eberhard Mönkeberg (emoenke@gwdg.de) For testing and help to get into kernel. Thomas Neumann (tn@ruhr.de) diff --git a/trunk/Documentation/isdn/README.concap b/trunk/Documentation/isdn/README.concap index 2f114babe4b6..a76d74845a4c 100644 --- a/trunk/Documentation/isdn/README.concap +++ b/trunk/Documentation/isdn/README.concap @@ -111,7 +111,7 @@ struct concap_proto_ops{ struct concap_proto * (*proto_new) (void); /* delete encapsulation protocol instance and free all its resources. - cprot may no loger be referenced after calling this */ + cprot may no longer be referenced after calling this */ void (*proto_del)(struct concap_proto *cprot); /* initialize the protocol's data. To be called at interface startup diff --git a/trunk/Documentation/ja_JP/SubmittingPatches b/trunk/Documentation/ja_JP/SubmittingPatches new file mode 100644 index 000000000000..a9dc1243e859 --- /dev/null +++ b/trunk/Documentation/ja_JP/SubmittingPatches @@ -0,0 +1,556 @@ +NOTE: +This is a version of Documentation/SubmittingPatches into Japanese. +This document is maintained by Keiichi KII +and the JF Project team . +If you find any difference between this document and the original file +or a problem with the translation, +please contact the maintainer of this file or JF project. + +Please also note that the purpose of this file is to be easier to read +for non English (read: Japanese) speakers and is not intended as a +fork. So if you have any comments or updates of this file, please try +to update the original English file first. + +Last Updated: 2007/10/24 +================================== +これは、 +linux-2.6.23/Documentation/SubmittingPatches の和訳 +です。 +翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ > +翻訳日： 2007/10/17 +翻訳者： Keiichi Kii +校正者： Masanari Kobayashi さん + Matsukura さん +================================== + + Linux カーネルに変更を加えるための Howto + 又は + かの Linus Torvalds の取り扱い説明書 + +Linux カーネルに変更を加えたいと思っている個人又は会社にとって、パッ +チの投稿に関連した仕組みに慣れていなければ、その過程は時々みなさんを +おじけづかせることもあります。この文章はあなたの変更を大いに受け入れ +てもらえやすくする提案を集めたものです。 + +コードを投稿する前に、Documentation/SubmitChecklist の項目リストに目 +を通してチェックしてください。もしあなたがドライバーを投稿しようとし +ているなら、Documentation/SubmittingDrivers にも目を通してください。 + +-------------------------------------------- +セクション1 パッチの作り方と送り方 +-------------------------------------------- + +1) 「 diff -up 」 +------------ + +パッチの作成には「 diff -up 」又は「 diff -uprN 」を使ってください。 + +Linux カーネルに対する全ての変更は diff(1) コマンドによるパッチの形式で +生成してください。パッチを作成するときには、diff(1) コマンドに「 -u 」引 +数を指定して、unified 形式のパッチを作成することを確認してください。また、 +変更がどの C 関数で行われたのかを表示する「 -p 」引数を使ってください。 +この引数は生成した差分をずっと読みやすくしてくれます。パッチは Linux +カーネルソースの中のサブディレクトリではなく Linux カーネルソースのルート +ディレクトリを基準にしないといけません。 + +1個のファイルについてのパッチを作成するためには、ほとんどの場合、 +以下の作業を行えば十分です。 + + SRCTREE= linux-2.6 + MYFILE= drivers/net/mydriver.c + + cd $SRCTREE + cp $MYFILE $MYFILE.orig + vi $MYFILE # make your change + cd .. + diff -up $SRCTREE/$MYFILE{.orig,} > /tmp/patch + +複数のファイルについてのパッチを作成するためには、素の( vanilla )、す +なわち変更を加えてない Linux カーネルを展開し、自分の Linux カーネル +ソースとの差分を生成しないといけません。例えば、 + + MYSRC= /devel/linux-2.6 + + tar xvfz linux-2.6.12.tar.gz + mv linux-2.6.12 linux-2.6.12-vanilla + diff -uprN -X linux-2.6.12-vanilla/Documentation/dontdiff \ + linux-2.6.12-vanilla $MYSRC > /tmp/patch + +dontdiff ファイルには Linux カーネルのビルドプロセスの過程で生成された +ファイルの一覧がのっています。そして、それらはパッチを生成する diff(1) +コマンドで無視されるべきです。dontdiff ファイルは 2.6.12 以後のバージョ +ンの Linux カーネルソースツリーに含まれています。それより前のバージョン +の Linux カーネルソースツリーに対する dontdiff ファイルは、 +から取得することができます。 + +投稿するパッチの中に関係のない余分なファイルが含まれていないことを確 +認してください。diff(1) コマンドで生成したパッチがあなたの意図したとお +りのものであることを確認してください。 + +もしあなたのパッチが多くの差分を生み出すのであれば、あなたはパッチ +を意味のあるひとまとまりごとに分けたいと思うかもしれません。 +これは他のカーネル開発者にとってレビューしやすくなるので、あなたの +パッチを受け入れてもらうためにはとても重要なことです。これを補助でき +る多くのスクリプトがあります。 + +Quilt: +http://savannah.nongnu.org/projects/quilt + +Andrew Morton's patch scripts: +http://www.zip.com.au/~akpm/linux/patches/ +このリンクの先のスクリプトの代わりとして、quilt がパッチマネジメント +ツールとして推奨されています(上のリンクを見てください)。 + +2) パッチに対する説明 + +パッチの中の変更点に対する技術的な詳細について説明してください。 + +説明はできる限り具体的に。もっとも悪い説明は「ドライバー X を更新」、 +「ドライバー X に対するバグフィックス」あるいは「このパッチはサブシス +テム X に対する更新を含んでいます。どうか取り入れてください。」などです。 + +説明が長くなりだしたのであれば、おそらくそれはパッチを分ける必要がある +という兆候です。次の #3 を見てください。 + +3) パッチの分割 + +意味のあるひとまとまりごとに変更を個々のパッチファイルに分けてください。 + +例えば、もし1つのドライバーに対するバグフィックスとパフォーマンス強 +化の両方の変更を含んでいるのであれば、その変更を2つ以上のパッチに分 +けてください。もし変更箇所に API の更新と、その新しい API を使う新たな +ドライバーが含まれているなら、2つのパッチに分けてください。 + +一方で、もしあなたが多数のファイルに対して意味的に同じ1つの変更を加え +るのであれば、その変更を1つのパッチにまとめてください。言いかえると、 +意味的に同じ1つの変更は1つのパッチの中に含まれます。 + +あるパッチが変更を完結させるために他のパッチに依存していたとしても、 +それは問題ありません。パッチの説明の中で「このパッチはパッチ X に依存 +している」と簡単に注意書きをつけてください。 + +もしパッチをより小さなパッチの集合に凝縮することができないなら、まずは +15かそこらのパッチを送り、そのレビューと統合を待って下さい。 + +4) パッチのスタイルチェック + +あなたのパッチが基本的な( Linux カーネルの)コーディングスタイルに違反し +ていないかをチェックして下さい。その詳細を Documentation/CodingStyle で +見つけることができます。コーディングスタイルの違反はレビューする人の +時間を無駄にするだけなので、恐らくあなたのパッチは読まれることすらなく +拒否されるでしょう。 + +あなたはパッチを投稿する前に最低限パッチスタイルチェッカー +( scripts/patchcheck.pl )を利用してパッチをチェックすべきです。 +もしパッチに違反がのこっているならば、それらの全てについてあなたは正当な +理由を示せるようにしておく必要があります。 + +5) 電子メールの宛先の選び方 + +MAINTAINERS ファイルとソースコードに目を通してください。そして、その変 +更がメンテナのいる特定のサブシステムに加えられるものであることが分か +れば、その人に電子メールを送ってください。 + +もし、メンテナが載っていなかったり、メンテナからの応答がないなら、 +LKML ( linux-kernel@vger.kernel.org )へパッチを送ってください。ほとんど +のカーネル開発者はこのメーリングリストに目を通しており、変更に対して +コメントを得ることができます。 + +15個より多くのパッチを同時に vger.kernel.org のメーリングリストへ送らな +いでください!!! + +Linus Torvalds は Linux カーネルに入る全ての変更に対する最終的な意思決定者 +です。電子メールアドレスは torvalds@linux-foundation.org になります。彼は +多くの電子メールを受け取っているため、できる限り彼に電子メールを送るのは +避けるべきです。 + +バグフィックスであったり、自明な変更であったり、話し合いをほとんど +必要としないパッチは Linus へ電子メールを送るか CC しなければなりません。 +話し合いを必要としたり、明確なアドバンテージがないパッチは、通常まず +は LKML へ送られるべきです。パッチが議論された後にだけ、そのパッチを +Linus へ送るべきです。 + +6) CC (カーボンコピー)先の選び方 + +特に理由がないなら、LKML にも CC してください。 + +Linus 以外のカーネル開発者は変更に気づく必要があり、その結果、彼らはそ +の変更に対してコメントをくれたり、コードに対してレビューや提案をくれ +るかもしれません。LKML とは Linux カーネル開発者にとって一番中心的なメー +リングリストです。USB やフレームバッファデバイスや VFS や SCSI サブシステ +ムなどの特定のサブシステムに関するメーリングリストもあります。あなた +の変更に、はっきりと関連のあるメーリングリストについて知りたければ +MAINTAINERS ファイルを参照してください。 + +VGER.KERNEL.ORG でホスティングされているメーリングリストの一覧が下記の +サイトに載っています。 + + +もし、変更がユーザランドのカーネルインタフェースに影響を与え +るのであれば、MAN-PAGES のメンテナ( MAINTAINERS ファイルに一覧 +があります)に man ページのパッチを送ってください。少なくとも +情報がマニュアルページの中に入ってくるように、変更が起きたという +通知を送ってください。 + +たとえ、メンテナが #4 で反応がなかったとしても、メンテナのコードに変更を +加えたときには、いつもメンテナに CC するのを忘れないようにしてください。 + +小さなパッチであれば、Adrian Bunk が管理している Trivial Patch Monkey +(ちょっとしたパッチを集めている)に CC してもいい +です。ちょっとしたパッチとは以下のルールのどれか1つを満たしていなけ +ればなりません。 + ・ドキュメントのスペルミスの修正 + ・grep(1) コマンドによる検索を困難にしているスペルの修正 + ・コンパイル時の警告の修正(無駄な警告が散乱することは好ましくないた + めです) + ・コンパイル問題の修正(それらの修正が本当に正しい場合に限る) + ・実行時の問題の修正(それらの修正が本当に問題を修正している場合に限る) + ・廃止予定の関数やマクロを使用しているコードの除去(例 check_region ) + ・問い合わせ先やドキュメントの修正 + ・移植性のないコードから移植性のあるコードへの置き換え(小さい範囲で + あればアーキテクチャ特有のことでも他の人がコピーできます) + ・作者やメンテナによる修正(すなわち patch monkey の再転送モード) +URL: + +7) MIME やリンクや圧縮ファイルや添付ファイルではなくプレインテキストのみ + +Linus や他のカーネル開発者はあなたが投稿した変更を読んで、コメントでき +る必要があります。カーネル開発者にとって、あなたが書いたコードの特定の +部分にコメントをするために、標準的な電子メールクライアントで変更が引用 +できることは重要です。 + +上記の理由で、すべてのパッチは文中に含める形式の電子メールで投稿さ +れるべきです。警告：あなたがパッチをコピー&ペーストする際には、パッ +チを改悪するエディターの折り返し機能に注意してください。 + +パッチを圧縮の有無に関わらず MIME 形式で添付しないでください。多くのポ +ピュラーな電子メールクライアントは MIME 形式の添付ファイルをプレーンテ +キストとして送信するとは限らないでしょう。そうなると、電子メールクラ +イアントがコードに対するコメントを付けることをできなくします。また、 +MIME 形式の添付ファイルは Linus に手間を取らせることになり、その変更を +受け入れてもらう可能性が低くなってしまいます。 + +例外：お使いの電子メールクライアントがパッチをめちゃくちゃにするので +あれば、誰かが MIME 形式のパッチを再送するよう求めるかもしれません。 + +警告： Mozilla のような特定の電子メールクライアントは電子メールの +ヘッダに以下のものを付加して送ります。 +---- message header ---- +Content-Type: text/plain; charset=us-ascii; format=flowed +---- message header ---- +問題は、「 format=flowed 」が付いた電子メールを特定の受信側の電子メール +クライアントがタブをスペースに置き換えるというような変更をすることです。 +したがって送られてきたパッチは壊れているように見えるでしょう。 + +これを修正するには、mozilla の defaults/pref/mailnews.js ファイルを +以下のように修正します。 +pref("mailnews.send_plaintext_flowed", false); // RFC 2646======= +pref("mailnews.display.disable_format_flowed_support", true); + +8) 電子メールのサイズ + +パッチを Linus へ送るときは常に #7 の手順に従ってください。 + +大きなパッチはメーリングリストやメンテナにとって不親切です。パッチが +未圧縮で 40KB を超えるようであるなら、インターネット上のアクセス可能な +サーバに保存し、保存場所を示す URL を伝えるほうが適切です。 + +9) カーネルバージョンの明記 + +パッチが対象とするカーネルのバージョンをパッチの概要か電子メールの +サブジェクトに付けることが重要です。 + +パッチが最新バージョンのカーネルに正しく適用できなければ、Linus は +そのパッチを採用しないでしょう。 + +10) がっかりせず再投稿 + +パッチを投稿した後は、辛抱強く待っていてください。Linus があなたのパッ +チを気に入って採用すれば、Linus がリリースする次のバージョンのカーネル +の中で姿を見せるでしょう。 + +しかし、パッチが次のバージョンのカーネルに入っていないなら、いくつもの +理由があるのでしょう。その原因を絞り込み、間違っているものを正し、更新 +したパッチを投稿するのはあなたの仕事です。 + +Linus があなたのパッチに対して何のコメントもなく不採用にすることは極め +て普通のことです。それは自然な姿です。もし、Linus があなたのパッチを受 +け取っていないのであれば、以下の理由が考えられます。 +* パッチが最新バージョンの Linux カーネルにきちんと適用できなかった +* パッチが LKML で十分に議論されていなかった +* スタイルの問題(セクション2を参照) +* 電子メールフォーマットの問題(このセクションを参照) +* パッチに対する技術的な問題 +* Linus はたくさんの電子メールを受け取っているので、どさくさに紛れて見 + 失った +* 不愉快にさせている + +判断できない場合は、LKML にコメントを頼んでください。 + +11) サブジェクトに「 PATCH 」 + +Linus や LKML への大量の電子メールのために、サブジェクトのプレフィックスに +「 [PATCH] 」を付けることが慣習となっています。これによって Linus や他の +カーネル開発者がパッチであるのか、又は、他の議論に関する電子メールであるの +かをより簡単に識別できます。 + +12) パッチへの署名 + +誰が何をしたのかを追いかけやすくするために (特に、パッチが何人かの +メンテナを経て最終的に Linux カーネルに取り込まれる場合のために)、電子 +メールでやり取りされるパッチに対して「 sign-off 」という手続きを導入し +ました。 + +「 sign-off 」とは、パッチがあなたの書いたものであるか、あるいは、 +あなたがそのパッチをオープンソースとして提供する権利を保持している、 +という証明をパッチの説明の末尾に一行記載するというものです。 +ルールはとても単純です。以下の項目を確認して下さい。 + + 原作者の証明書( DCO ) 1.1 + + このプロジェクトに寄与するものとして、以下のことを証明する。 + + (a) 本寄与は私が全体又は一部作成したものであり、私がそのファイ + ル中に明示されたオープンソースライセンスの下で公開する権利 + を持っている。もしくは、 + + (b) 本寄与は、私が知る限り、適切なオープンソースライセンスでカバ + ーされている既存の作品を元にしている。同時に、私はそのライセ + ンスの下で、私が全体又は一部作成した修正物を、ファイル中で示 + される同一のオープンソースライセンスで(異なるライセンスの下で + 投稿することが許可されている場合を除いて)投稿する権利を持って + いる。もしくは、 + + (c) 本寄与は(a)、(b)、(c)を証明する第3者から私へ直接提供された + ものであり、私はそれに変更を加えていない。 + + (d) 私はこのプロジェクトと本寄与が公のものであることに理解及び同意す + る。同時に、関与した記録(投稿の際の全ての個人情報と sign-off を + 含む)が無期限に保全されることと、当該プロジェクト又は関連する + オープンソースライセンスに沿った形で再配布されることに理解及び + 同意する。 + +もしこれに同意できるなら、以下のような1行を追加してください。 + + Signed-off-by: Random J Developer + +実名を使ってください。(残念ですが、偽名や匿名による寄与はできません。) + +人によっては sign-off の近くに追加のタグを付加しています。それらは今のところ +無視されますが、あなたはそのタグを社内の手続きに利用したり、sign-off に特別 +な情報を示したりすることができます。 + +13) いつ Acked-by: を使うのか + +「 Signed-off-by: 」タグはその署名者がパッチの開発に関わっていたことやパッチ +の伝播パスにいたことを示しています。 + +ある人が直接パッチの準備や作成に関わっていないけれど、その人のパッチに対す +る承認を記録し、示したいとします。その場合、その人を示すのに Acked-by: が使 +えます。Acked-by: はパッチのチェンジログにも追加されます。 + +パッチの影響を受けるコードのメンテナがパッチに関わっていなかったり、パッチ +の伝播パスにいなかった時にも、メンテナは Acked-by: をしばしば利用します。 + +Acked-by: は Signed-off-by: のように公式なタグではありません。それはメンテナが +少なくともパッチをレビューし、同意を示しているという記録です。そのような +ことからパッチの統合者がメンテナの「うん、良いと思うよ」という発言を +Acked-by: へ置き換えることがあります。 + +Acked-by: が必ずしもパッチ全体の承認を示しているわけではありません。例えば、 +あるパッチが複数のサブシステムへ影響を与えており、その中の1つのサブシステム +のメンテナからの Acked-by: を持っているとします。その場合、Acked-by: は通常 +そのメンテナのコードに影響を与える一部分だけに対する承認を示しています。 +この点は、ご自分で判断してください。(その Acked-by: が)疑わしい場合は、 +メーリングリストアーカイブの中の大元の議論を参照すべきです。 + +14) 標準的なパッチのフォーマット + +標準的なパッチのサブジェクトは以下のとおりです。 + + Subject: [PATCH 001/123] subsystem: summary phrase + +標準的なパッチの、電子メールのボディは以下の項目を含んでいます。 + + - パッチの作成者を明記する「 from 」行 + + - 空行 + + - 説明本体。これはこのパッチを説明するために無期限のチェンジログ + (変更履歴)にコピーされます。 + + - 上述した「 Signed-off-by: 」行。これも説明本体と同じくチェン + ジログ内にコピーされます。 + + - マーカー行は単純に「 --- 」です。 + + - 余計なコメントは、チェンジログには不適切です。 + + - 実際のパッチ(差分出力) + +サブジェクト行のフォーマットは、アルファベット順で電子メールをとても +ソートしやすいものになっています。(ほとんどの電子メールクライアント +はソートをサポートしています)パッチのサブジェクトの連番は0詰めであ +るため、数字でのソートとアルファベットでのソートは同じ結果になります。 + +電子メールのサブジェクト内のサブシステム表記は、パッチが適用される +分野またはサブシステムを識別できるようにすべきです。 + +電子メールのサブジェクトの「概要の言い回し」はそのパッチの概要を正確 +に表現しなければなりません。「概要の言い回し」をファイル名にしてはい +けません。一連のパッチ中でそれぞれのパッチは同じ「概要の言い回し」を +使ってはいけません(「一連のパッチ」とは順序付けられた関連のある複数の +パッチ群です)。 + +あなたの電子メールの「概要の言い回し」がそのパッチにとって世界で唯 +一の識別子になるように心がけてください。「概要の言い回し」は git の +チェンジログの中へずっと伝播していきます。「概要の言い回し」は、開 +発者が後でパッチを参照するために議論の中で利用するかもしれません。 +人々はそのパッチに関連した議論を読むために「概要の言い回し」を使って +google で検索したがるでしょう。 + +サブジェクトの例を二つ + + Subject: [patch 2/5] ext2: improve scalability of bitmap searching + Subject: [PATCHv2 001/207] x86: fix eflags tracking + +「 from 」行は電子メールのボディの一番最初の行でなければなりません。 +その形式は以下のとおりです。 + + From: Original Author + +「 from 」行はチェンジログの中で、そのパッチの作成者としてクレジットされ +ている人を特定するものです。「 from 」行がかけていると、電子メールのヘッ +ダーの「 From: 」が、チェンジログの中でパッチの作成者を決定するために使わ +れるでしょう。 + +説明本体は無期限のソースのチェンジログにコミットされます。なので、説明 +本体はそのパッチに至った議論の詳細を忘れているある程度の技量を持っている人 +がその詳細を思い出すことができるものでなければなりません。 + +「 --- 」マーカー行はパッチ処理ツールに対して、チェンジログメッセージの終端 +部分を認識させるという重要な役目を果たします。 + +「 --- 」マーカー行の後の追加コメントの良い使用方法の1つに diffstat コマンド +があります。diffstat コマンドとは何のファイルが変更され、1ファイル当たり何行 +追加され何行消されたかを示すものです。diffstat コマンドは特に大きなパッチに +おいて役立ちます。その時点でだけ又はメンテナにとってのみ関係のあるコメント +は無期限に保存されるチェンジログにとって適切ではありません。そのため、この +ようなコメントもマーカー行の後に書かれるべきです。ファイル名はカーネルソー +スツリーのトップディレクトリからの表記でリストされるため、横方向のスペース +をとり過ぎないように、diffstat コマンドにオプション「 -p 1 -w 70 」を指定し +てください(インデントを含めてちょうど80列に合うでしょう)。 + +適切なパッチのフォーマットの詳細についてはセクション3の参考文献を参照して +ください。 + +------------------------------------ +セクション2 - ヒントとTIPSと小技 +------------------------------------ + +このセクションは Linux カーネルに変更を適用することに関係のある一般的な +「お約束」の多くを載せています。物事には例外というものがあります。しか +し例外を適用するには、本当に妥当な理由が不可欠です。あなたは恐らくこの +セクションを Linus のコンピュータ・サイエンス101と呼ぶでしょう。 + +1) Documentation/CodingStyleを参照 + +言うまでもなく、あなたのコードがこのコーディングスタイルからあまりに +も逸脱していると、レビューやコメントなしに受け取ってもらえないかもし +れません。 + +唯一の特筆すべき例外は、コードをあるファイルから別のファイルに移動 +するときです。この場合、コードを移動するパッチでは、移動されるコード +に関して移動以外の変更を一切加えるべきではありません。これにより、 +コードの移動とあなたが行ったコードの修正を明確に区別できるようにな +ります。これは実際に何が変更されたかをレビューする際の大きな助けに +なるとともに、ツールにコードの履歴を追跡させることも容易になります。 + +投稿するより前にパッチのスタイルチェッカー( scripts/checkpatch.pl )で +あなたのパッチをチェックしてください。このスタイルチェッカーは最終結 +論としてではなく、指標としてみるべきです。もし、あなたのコードが違反 +はしているが修正するより良く見えるのであれば、おそらくそのままにする +のがベストです。 + +スタイルチェッカーによる3段階のレポート: + - エラー: 間違っている可能性が高い + - 警告：注意してレビューする必要がある + - チェック：考慮する必要がある + +あなたはパッチに残っている全ての違反について、それがなぜ必要なのか正当な +理由を示せるようにしておく必要があります。 + +2) #ifdefは見苦しい + +ifdef が散乱したコードは、読むのもメンテナンスするのも面倒です。コードの中 +で ifdef を使わないでください。代わりに、ヘッダファイルの中に ifdef を入れて、 +条件付きで、コードの中で使われる関数を「 static inline 」関数かマクロで定義し +てください。後はコンパイラが、何もしない箇所を最適化して取り去ってくれるで +しょう。 + +まずいコードの簡単な例 + + dev = alloc_etherdev (sizeof(struct funky_private)); + if (!dev) + return -ENODEV; + #ifdef CONFIG_NET_FUNKINESS + init_funky_net(dev); + #endif + +クリーンアップしたコードの例 + +(in header) + #ifndef CONFIG_NET_FUNKINESS + static inline void init_funky_net (struct net_device *d) {} + #endif + +(in the code itself) + dev = alloc_etherdev (sizeof(struct funky_private)); + if (!dev) + return -ENODEV; + init_funky_net(dev); + +3) マクロより「 static inline 」を推奨 + +「 static inline 」関数はマクロよりもずっと推奨されています。それらは、 +型安全性があり、長さにも制限が無く、フォーマットの制限もありません。 +gcc においては、マクロと同じくらい軽いです。 + +マクロは「 static inline 」が明らかに不適切であると分かる場所(高速化パスの +いくつかの特定のケース)や「 static inline 」関数を使うことができないような +場所(マクロの引数の文字列連結のような)にだけ使われるべきです。 + +「 static inline 」は「 static __inline__ 」や「 extern inline 」や +「 extern __inline__ 」よりも適切です。 + +4) 設計に凝りすぎるな + +それが有用になるかどうか分からないような不明瞭な将来を見越した設計 +をしないでください。「できる限り簡単に、そして、それ以上簡単になら +ないような設計をしてください。」 + +---------------------- +セクション3 参考文献 +---------------------- + +Andrew Morton, "The perfect patch" (tpp). + + +Jeff Garzik, "Linux kernel patch submission format". + + +Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer". + + + + + +NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people! + + +Kernel Documentation/CodingStyle: + + +Linus Torvalds's mail on the canonical patch format: + +-- diff --git a/trunk/Documentation/java.txt b/trunk/Documentation/java.txt index 3cce3fbb6644..e6a723281547 100644 --- a/trunk/Documentation/java.txt +++ b/trunk/Documentation/java.txt @@ -37,7 +37,7 @@ other program after you have done the following: or the following, if you want to be more selective: ':Applet:M:: InitThread message and retrun code +** 1. Message 0 --> InitThread message and return code ** 2. Doorbell is used for RS-232 emulation ** inDoorBell : bit0 -- data in ready ** (DRIVER DATA WRITE OK) diff --git a/trunk/Documentation/scsi/ibmmca.txt b/trunk/Documentation/scsi/ibmmca.txt index a08e225653d6..a810421f1fb3 100644 --- a/trunk/Documentation/scsi/ibmmca.txt +++ b/trunk/Documentation/scsi/ibmmca.txt @@ -21,7 +21,7 @@ versions older than 4.0 do not work with kernels 2.4.0 or later! If you try to compile your kernel with the wrong driver source, the compilation is aborted and you get a corresponding error message. This is - no bug in the driver. It prevents you from using the wrong sourcecode + no bug in the driver; it prevents you from using the wrong source code with the wrong kernel version. Authors of this Driver @@ -58,7 +58,7 @@ 5 Users' Manual 5.1 Commandline Parameters 5.2 Troubleshooting - 5.3 Bugreports + 5.3 Bug reports 5.4 Support WWW-page 6 References 7 Credits to @@ -71,13 +71,13 @@ 1 Abstract ---------- - This README-file describes the IBM SCSI-subsystem low level driver for - Linux. The descriptions which were formerly kept in the source-code have - been taken out to this file to easify the codes' readability. The driver + This README-file describes the IBM SCSI-subsystem low level driver for + Linux. The descriptions which were formerly kept in the source code have + been taken out of this file to simplify the codes readability. The driver description has been updated, as most of the former description was already - quite outdated. The history of the driver development is also kept inside - here. Multiple historical developments have been summarized to shorten the - textsize a bit. At the end of this file you can find a small manual for + quite outdated. The history of the driver development is also kept inside + here. Multiple historical developments have been summarized to shorten the + text size a bit. At the end of this file you can find a small manual for this driver and hints to get it running on your machine. 2 Driver Description @@ -186,7 +186,7 @@ between 0 and 7). The IBM SCSI-2 F/W adapter offers this on up to two busses and provides support for 30 logical devices at the same time, where in wide-addressing mode you can have 16 puns with 32 luns on each device. - This section dexribes you the handling of devices on non-F/W adapters. + This section describes the handling of devices on non-F/W adapters. Just imagine, that you can have 16 * 32 = 512 devices on a F/W adapter which means a lot of possible devices for such a small machine. @@ -209,10 +209,10 @@ -------------------------------------------------------- One consequence of information hiding is that the real (pun,lun) numbers are also hidden. The two possibilities to get around this problem - is to offer fake pun/lun combinations to the operating system or to + are to offer fake pun/lun combinations to the operating system or to delete the whole mapping of the adapter and to reassign the ldns, using the immediate assign command of the SCSI-subsystem for probing through - all possible pun/lun combinations. a ldn is a "logical device number" + all possible pun/lun combinations. An ldn is a "logical device number" which is used by IBM SCSI-subsystems to access some valid SCSI-device. At the beginning of the development of this driver, the following approach was used: @@ -251,9 +251,9 @@ lun>0 or to non-existing devices, in order to satisfy the subsystem, if there are less than 15 SCSI-devices connected. In the case of more than 15 devices, the dynamical mapping goes active. If the get_scsi[][] reports a - device to be existant, but it has no ldn assigned, it gets a ldn out of 7 - to 14. The numbers are assigned in cyclic order. Therefore it takes 8 - dynamical reassignments on the SCSI-devices, until a certain device + device to be existent, but it has no ldn assigned, it gets an ldn out of 7 + to 14. The numbers are assigned in cyclic order, therefore it takes 8 + dynamical reassignments on the SCSI-devices until a certain device loses its ldn again. This assures that dynamical remapping is avoided during intense I/O between up to 15 SCSI-devices (means pun,lun combinations). A further advantage of this method is that people who @@ -551,7 +551,7 @@ than devices are available, they are assigned to non existing pun,lun combinations to satisfy the adapter. With this, the dynamical mapping was possible to implement. (For further info see the text in the - source-code and in the description below. Read the description + source code and in the description below. Read the description below BEFORE installing this driver on your system!) 2) Changed the name IBMMCA_DRIVER_VERSION to IBMMCA_SCSI_DRIVER_VERSION. 3) The LED-display shows on PS/2-95 no longer the ldn, but the SCSI-ID @@ -762,9 +762,9 @@ - Michael Lang Apr 23, 2000 (v3.2pre1) - 1) During a very long time, I collected a huge amount of bugreports from + 1) During a very long time, I collected a huge amount of bug reports from various people, trying really quite different things on their SCSI- - PS/2s. Today, all these bugreports are taken into account and should be + PS/2s. Today, all these bug reports are taken into account and should be mostly solved. The major topics were: - Driver crashes during boottime by no obvious reason. - Driver panics while the midlevel-SCSI-driver is trying to inquire @@ -819,7 +819,7 @@ - Michael Lang July 17, 2000 (v3.2pre8) - A long period of collecting bugreports from all corners of the world + A long period of collecting bug reports from all corners of the world now lead to the following corrections to the code: 1) SCSI-2 F/W support crashed with a COMMAND ERROR. The reason for this was that it is possible to disable Fast-SCSI for the external bus. @@ -873,7 +873,7 @@ July 26, 2000 (v3.2pre11) 1) I passed a horrible weekend getting mad with NMIs on kernel 2.2.14 and a model 9595. Asking around in the community, nobody except of me has - seen such errors. Weired, but I am trying to recompile everything on + seen such errors. Weird, but I am trying to recompile everything on the model 9595. Maybe, as I use a specially modified gcc, that could cause problems. But, it was not the reason. The true background was, that the kernel was compiled for i386 and the 9595 has a 486DX-2. @@ -886,7 +886,7 @@ alive rotator during boottime. This makes sense, when no monitor is connected to the system. You can get rid of all display activity, if you do not use any parameter or just ibmmcascsi=activity, for the - harddrive activity LED, existant on all PS/2, except models 8595-XXX. + harddrive activity LED, existent on all PS/2, except models 8595-XXX. If no monitor is available, please use ibmmcascsi=display, which works fine together with the linuxinfo utility for the LED-panel. - Michael Lang @@ -1115,7 +1115,7 @@ If this really happens, do also send e-mail to the maintainer, as forced detection should be never necessary. Forced detection is in principal some flaw of the driver adapter detection and goes into - bugreports. + bug reports. Q: The driver screws up, if it starts to probe SCSI-devices, is there some way out of it? A: Yes, that was some recognition problem of the correct SCSI-adapter @@ -1172,7 +1172,7 @@ recommended version is 3.2 or later. Here, the F/W support is in a stable and reliable condition. Wide-addressing is in addition supported. - Q: I get a Ooops message and something like "killing interrupt". + Q: I get an Oops message and something like "killing interrupt". A: The reason for this is that the IBM SCSI-subsystem only sends a termination status back, if some error appeared. In former releases of the driver, it was not checked, if the termination status block @@ -1213,21 +1213,21 @@ problem. Not yet tried, but guessing that it could work. To get this, set unchecked_isa_dma argument of ibmmca.h from 0 to 1. - 5.3 Bugreports + 5.3 Bug reports -------------- - If you really find bugs in the sourcecode or the driver will successfully + If you really find bugs in the source code or the driver will successfully refuse to work on your machine, you should send a bug report to me. The best for this is to follow the instructions on the WWW-page for this driver. Fill out the bug-report form, placed on the WWW-page and ship it, so the bugs can be taken into account with maximum efforts. But, please do not send bug reports about this driver to Linus Torvalds or Leonard - Zubkoff, as Linus is burried in E-Mail and Leonard is supervising all + Zubkoff, as Linus is buried in E-Mail and Leonard is supervising all SCSI-drivers and won't have the time left to look inside every single driver to fix a bug and especially DO NOT send modified code to Linus Torvalds or Alan J. Cox which has not been checked here!!! They are both - quite burried in E-mail (as me, sometimes, too) and one should first check + quite buried in E-mail (as me, sometimes, too) and one should first check for problems on my local teststand. Recently, I got a lot of - bugreports for errors in the ibmmca.c code, which I could not imagine, but + bug reports for errors in the ibmmca.c code, which I could not imagine, but a look inside some Linux-distribution showed me quite often some modified code, which did no longer work on most other machines than the one of the modifier. Ok, so now that there is maintenance service available for this @@ -1261,7 +1261,7 @@ some e-mail directly, but at least with the same information as required by the formular. - If you have extensive bugreports, including Ooops messages and + If you have extensive bug reports, including Oops messages and screen-shots, please feel free to send it directly to the address of the maintainer, too. The current address of the maintainer is: @@ -1318,7 +1318,7 @@ detailed bug reports and ideas for this driver (and his patience ;-)). Alan J. Cox - for his bugreports and his bold activities in cross-checking + for his bug reports and his bold activities in cross-checking the driver-code with his teststand. 7.2 Sponsors & Supporters diff --git a/trunk/Documentation/scsi/link_power_management_policy.txt b/trunk/Documentation/scsi/link_power_management_policy.txt new file mode 100644 index 000000000000..d18993d01884 --- /dev/null +++ b/trunk/Documentation/scsi/link_power_management_policy.txt @@ -0,0 +1,19 @@ +This parameter allows the user to set the link (interface) power management. +There are 3 possible options: + +Value Effect +---------------------------------------------------------------------------- +min_power Tell the controller to try to make the link use the + least possible power when possible. This may + sacrifice some performance due to increased latency + when coming out of lower power states. + +max_performance Generally, this means no power management. Tell + the controller to have performance be a priority + over power management. + +medium_power Tell the controller to enter a lower power state + when possible, but do not enter the lowest power + state, thus improving latency over min_power setting. + + diff --git a/trunk/Documentation/scsi/sym53c8xx_2.txt b/trunk/Documentation/scsi/sym53c8xx_2.txt index 3d9f06bb3d00..49ea5c58c6bc 100644 --- a/trunk/Documentation/scsi/sym53c8xx_2.txt +++ b/trunk/Documentation/scsi/sym53c8xx_2.txt @@ -449,25 +449,14 @@ options as above. cmd_per_lun=#tags (#tags > 1) tagged command queuing enabled #tags will be truncated to the max queued commands configuration parameter. -10.2.2 Detailed control of tagged commands - This option allows you to specify a command queue depth for each device - that supports tagged command queueing. - Example: - tag_ctrl=10/t2t3q16-t5q24/t1u2q32 - will set devices queue depth as follow: - - controller #0 target #2 and target #3 -> 16 commands, - - controller #0 target #5 -> 24 commands, - - controller #1 target #1 logical unit #2 -> 32 commands, - - all other logical units (all targets, all controllers) -> 10 commands. - -10.2.3 Burst max +10.2.2 Burst max burst=0 burst disabled burst=255 get burst length from initial IO register settings. burst=#x burst enabled (1<<#x burst transfers max) #x is an integer value which is log base 2 of the burst transfers max. By default the driver uses the maximum value supported by the chip. -10.2.4 LED support +10.2.3 LED support led=1 enable LED support led=0 disable LED support Do not enable LED support if your scsi board does not use SDMS BIOS. @@ -560,9 +549,9 @@ Previously, the sym2 driver accepted arguments of the form sym53c8xx=tags:4,sync:10,debug:0x200 As a result of the new module parameters, this is no longer available. -Most of the options have remained the same, but tags has split into -cmd_per_lun and tag_ctrl for its two different purposes. The sample above -would be specified as: +Most of the options have remained the same, but tags has become +cmd_per_lun to reflect its different purposes. The sample above would +be specified as: modprobe sym53c8xx cmd_per_lun=4 sync=10 debug=0x200 or on the kernel boot line as: diff --git a/trunk/Documentation/sharedsubtree.txt b/trunk/Documentation/sharedsubtree.txt index ccf1cebe744f..736540045dc7 100644 --- a/trunk/Documentation/sharedsubtree.txt +++ b/trunk/Documentation/sharedsubtree.txt @@ -153,6 +153,7 @@ replicas continue to be exactly same. #include #include #include + #include #include #include diff --git a/trunk/Documentation/sound/alsa/soc/DAI.txt b/trunk/Documentation/sound/alsa/soc/DAI.txt index 58cbfd01ea8f..3feeb9ecdec4 100644 --- a/trunk/Documentation/sound/alsa/soc/DAI.txt +++ b/trunk/Documentation/sound/alsa/soc/DAI.txt @@ -20,12 +20,12 @@ I2S === I2S is a common 4 wire DAI used in HiFi, STB and portable devices. The Tx and -Rx lines are used for audio transmision, whilst the bit clock (BCLK) and +Rx lines are used for audio transmission, whilst the bit clock (BCLK) and left/right clock (LRC) synchronise the link. I2S is flexible in that either the controller or CODEC can drive (master) the BCLK and LRC clock lines. Bit clock usually varies depending on the sample rate and the master system clock (SYSCLK). LRCLK is the same as the sample rate. A few devices support separate -ADC and DAC LRCLK's, this allows for similtanious capture and playback at +ADC and DAC LRCLK's, this allows for simultaneous capture and playback at different sample rates. I2S has several different operating modes:- @@ -41,12 +41,12 @@ I2S has several different operating modes:- PCM === -PCM is another 4 wire interface, very similar to I2S, that can support a more +PCM is another 4 wire interface, very similar to I2S, which can support a more flexible protocol. It has bit clock (BCLK) and sync (SYNC) lines that are used to synchronise the link whilst the Tx and Rx lines are used to transmit and receive the audio data. Bit clock usually varies depending on sample rate whilst sync runs at the sample rate. PCM also supports Time Division -Multiplexing (TDM) in that several devices can use the bus similtaniuosly (This +Multiplexing (TDM) in that several devices can use the bus simultaneously (this is sometimes referred to as network mode). Common PCM operating modes:- diff --git a/trunk/Documentation/sound/alsa/soc/clocking.txt b/trunk/Documentation/sound/alsa/soc/clocking.txt index e93960d53a1e..14930887c25f 100644 --- a/trunk/Documentation/sound/alsa/soc/clocking.txt +++ b/trunk/Documentation/sound/alsa/soc/clocking.txt @@ -2,20 +2,20 @@ Audio Clocking ============== This text describes the audio clocking terms in ASoC and digital audio in -general. Note: Audio clocking can be complex ! +general. Note: Audio clocking can be complex! Master Clock ------------ -Every audio subsystem is driven by a master clock (sometimes refered to as MCLK +Every audio subsystem is driven by a master clock (sometimes referred to as MCLK or SYSCLK). This audio master clock can be derived from a number of sources (e.g. crystal, PLL, CPU clock) and is responsible for producing the correct audio playback and capture sample rates. -Some master clocks (e.g. PLL's and CPU based clocks) are configuarble in that +Some master clocks (e.g. PLL's and CPU based clocks) are configurable in that their speed can be altered by software (depending on the system use and to save -power). Other master clocks are fixed at at set frequency (i.e. crystals). +power). Other master clocks are fixed at a set frequency (i.e. crystals). DAI Clocks @@ -44,7 +44,7 @@ This relationship depends on the codec or SoC CPU in particular. In general it's best to configure BCLK to the lowest possible speed (depending on your rate, number of channels and wordsize) to save on power. -It's also desireable to use the codec (if possible) to drive (or master) the +It's also desirable to use the codec (if possible) to drive (or master) the audio clocks as it's usually gives more accurate sample rates than the CPU. diff --git a/trunk/Documentation/sound/alsa/soc/codec.txt b/trunk/Documentation/sound/alsa/soc/codec.txt index 48983c75aad9..1e766ad0ebd1 100644 --- a/trunk/Documentation/sound/alsa/soc/codec.txt +++ b/trunk/Documentation/sound/alsa/soc/codec.txt @@ -19,7 +19,7 @@ Optionally, codec drivers can also provide:- 6) DAPM event handler. 7) DAC Digital mute control. -It's probably best to use this guide in conjuction with the existing codec +It's probably best to use this guide in conjunction with the existing codec driver code in sound/soc/codecs/ ASoC Codec driver breakdown @@ -28,7 +28,7 @@ ASoC Codec driver breakdown 1 - Codec DAI and PCM configuration ----------------------------------- Each codec driver must have a struct snd_soc_codec_dai to define it's DAI and -PCM's capablities and operations. This struct is exported so that it can be +PCM's capabilities and operations. This struct is exported so that it can be registered with the core by your machine driver. e.g. @@ -67,7 +67,7 @@ EXPORT_SYMBOL_GPL(wm8731_dai); 2 - Codec control IO -------------------- -The codec can ususally be controlled via an I2C or SPI style interface (AC97 +The codec can usually be controlled via an I2C or SPI style interface (AC97 combines control with data in the DAI). The codec drivers will have to provide functions to read and write the codec registers along with supplying a register cache:- diff --git a/trunk/Documentation/sound/alsa/soc/dapm.txt b/trunk/Documentation/sound/alsa/soc/dapm.txt index c11877f5b4a1..ab0766fd7869 100644 --- a/trunk/Documentation/sound/alsa/soc/dapm.txt +++ b/trunk/Documentation/sound/alsa/soc/dapm.txt @@ -11,7 +11,7 @@ other PM systems. DAPM is also completely transparent to all user space applications as all power switching is done within the ASoC core. No code changes or recompiling are -required for user space applications. DAPM makes power switching descisions based +required for user space applications. DAPM makes power switching decisions based upon any audio stream (capture/playback) activity and audio mixer settings within the device. @@ -38,7 +38,7 @@ There are 4 power domains within DAPM Enabled and disabled when stream playback/capture is started and stopped respectively. e.g. aplay, arecord. -All DAPM power switching descisons are made automatically by consulting an audio +All DAPM power switching decisions are made automatically by consulting an audio routing map of the whole machine. This map is specific to each machine and consists of the interconnections between every audio component (including internal codec components). All audio components that effect power are called diff --git a/trunk/Documentation/sound/alsa/soc/overview.txt b/trunk/Documentation/sound/alsa/soc/overview.txt index 753c5cc5984a..c47ce9530677 100644 --- a/trunk/Documentation/sound/alsa/soc/overview.txt +++ b/trunk/Documentation/sound/alsa/soc/overview.txt @@ -2,18 +2,19 @@ ALSA SoC Layer ============== The overall project goal of the ALSA System on Chip (ASoC) layer is to provide -better ALSA support for embedded system on chip procesors (e.g. pxa2xx, au1x00, +better ALSA support for embedded system-on-chip processors (e.g. pxa2xx, au1x00, iMX, etc) and portable audio codecs. Currently there is some support in the kernel for SoC audio, however it has some limitations:- * Currently, codec drivers are often tightly coupled to the underlying SoC - cpu. This is not ideal and leads to code duplication i.e. Linux now has 4 + CPU. This is not ideal and leads to code duplication i.e. Linux now has 4 different wm8731 drivers for 4 different SoC platforms. - * There is no standard method to signal user initiated audio events. - e.g. Headphone/Mic insertion, Headphone/Mic detection after an insertion - event. These are quite common events on portable devices and ofter require - machine specific code to re route audio, enable amps etc after such an event. + * There is no standard method to signal user initiated audio events (e.g. + Headphone/Mic insertion, Headphone/Mic detection after an insertion + event). These are quite common events on portable devices and often require + machine specific code to re-route audio, enable amps, etc., after such an + event. * Current drivers tend to power up the entire codec when playing (or recording) audio. This is fine for a PC, but tends to waste a lot of @@ -44,7 +45,7 @@ features :- signals the codec when to change power states. * Machine specific controls: Allow machines to add controls to the sound card - e.g. volume control for speaker amp. + (e.g. volume control for speaker amp). To achieve all this, ASoC basically splits an embedded audio system into 3 components :- @@ -57,7 +58,7 @@ components :- interface drivers (e.g. I2S, AC97, PCM) for that platform. * Machine driver: The machine driver handles any machine specific controls and - audio events. i.e. turing on an amp at start of playback. + audio events (e.g. turning on an amp at start of playback). Documentation diff --git a/trunk/Documentation/sound/alsa/soc/platform.txt b/trunk/Documentation/sound/alsa/soc/platform.txt index e95b16d5a53b..d4678b4dc6c6 100644 --- a/trunk/Documentation/sound/alsa/soc/platform.txt +++ b/trunk/Documentation/sound/alsa/soc/platform.txt @@ -20,7 +20,7 @@ struct snd_soc_ops { int (*trigger)(struct snd_pcm_substream *, int); }; -The platform driver exports it's DMA functionailty via struct snd_soc_platform:- +The platform driver exports its DMA functionality via struct snd_soc_platform:- struct snd_soc_platform { char *name; diff --git a/trunk/Documentation/sound/alsa/soc/pops_clicks.txt b/trunk/Documentation/sound/alsa/soc/pops_clicks.txt index 2cf7ee5b3d74..3371bd9d7cfa 100644 --- a/trunk/Documentation/sound/alsa/soc/pops_clicks.txt +++ b/trunk/Documentation/sound/alsa/soc/pops_clicks.txt @@ -2,7 +2,7 @@ Audio Pops and Clicks ===================== Pops and clicks are unwanted audio artifacts caused by the powering up and down -of components within the audio subsystem. This is noticable on PC's when an +of components within the audio subsystem. This is noticeable on PCs when an audio module is either loaded or unloaded (at module load time the sound card is powered up and causes a popping noise on the speakers). @@ -16,7 +16,7 @@ Minimising Playback Pops and Clicks =================================== Playback pops in portable audio subsystems cannot be completely eliminated atm, -however future audio codec hardware will have better pop and click supression. +however future audio codec hardware will have better pop and click suppression. Pops can be reduced within playback by powering the audio components in a specific order. This order is different for startup and shutdown and follows some basic rules:- @@ -33,7 +33,7 @@ Minimising Capture Pops and Clicks ================================== Capture artifacts are somewhat easier to get rid as we can delay activating the -ADC until all the pops have occured. This follows similar power rules to +ADC until all the pops have occurred. This follows similar power rules to playback in that components are powered in a sequence depending upon stream startup or shutdown. diff --git a/trunk/Documentation/spi/pxa2xx b/trunk/Documentation/spi/pxa2xx index 215e3b8e7266..f3853cc37bde 100644 --- a/trunk/Documentation/spi/pxa2xx +++ b/trunk/Documentation/spi/pxa2xx @@ -1,4 +1,4 @@ -PXA2xx SPI on SSP driver HOWTO +PXA2xx SPI on SSP driver HOWTO =================================================== This a mini howto on the pxa2xx_spi driver. The driver turns a PXA2xx synchronous serial port into a SPI master controller diff --git a/trunk/Documentation/thinkpad-acpi.txt b/trunk/Documentation/thinkpad-acpi.txt index 60953d6c919d..10c041ca13c7 100644 --- a/trunk/Documentation/thinkpad-acpi.txt +++ b/trunk/Documentation/thinkpad-acpi.txt @@ -1,7 +1,7 @@ ThinkPad ACPI Extras Driver - Version 0.16 - August 2nd, 2007 + Version 0.17 + October 04th, 2007 Borislav Deianov Henrique de Moraes Holschuh @@ -105,10 +105,15 @@ The version of thinkpad-acpi's sysfs interface is exported by the driver as a driver attribute (see below). Sysfs driver attributes are on the driver's sysfs attribute space, -for 2.6.20 this is /sys/bus/platform/drivers/thinkpad_acpi/. +for 2.6.23 this is /sys/bus/platform/drivers/thinkpad_acpi/ and +/sys/bus/platform/drivers/thinkpad_hwmon/ -Sysfs device attributes are on the driver's sysfs attribute space, -for 2.6.20 this is /sys/devices/platform/thinkpad_acpi/. +Sysfs device attributes are on the thinkpad_acpi device sysfs attribute +space, for 2.6.23 this is /sys/devices/platform/thinkpad_acpi/. + +Sysfs device attributes for the sensors and fan are on the +thinkpad_hwmon device's sysfs attribute space, but you should locate it +looking for a hwmon device with the name attribute of "thinkpad". Driver version -------------- @@ -766,7 +771,7 @@ Temperature sensors ------------------- procfs: /proc/acpi/ibm/thermal -sysfs device attributes: (hwmon) temp*_input +sysfs device attributes: (hwmon "thinkpad") temp*_input Most ThinkPads include six or more separate temperature sensors but only expose the CPU temperature through the standard ACPI methods. This @@ -918,19 +923,34 @@ sysfs backlight device "thinkpad_screen" This feature allows software control of the LCD brightness on ThinkPad models which don't have a hardware brightness slider. -It has some limitations: the LCD backlight cannot be actually turned on or off -by this interface, and in many ThinkPad models, the "dim while on battery" -functionality will be enabled by the BIOS when this interface is used, and -cannot be controlled. - -The backlight control has eight levels, ranging from 0 to 7. Some of the -levels may not be distinct. - -There are two interfaces to the firmware for brightness control, EC and CMOS. -To select which one should be used, use the brightness_mode module parameter: -brightness_mode=1 selects EC mode, brightness_mode=2 selects CMOS mode, -brightness_mode=3 selects both EC and CMOS. The driver tries to autodetect -which interface to use. +It has some limitations: the LCD backlight cannot be actually turned on or +off by this interface, and in many ThinkPad models, the "dim while on +battery" functionality will be enabled by the BIOS when this interface is +used, and cannot be controlled. + +On IBM (and some of the earlier Lenovo) ThinkPads, the backlight control +has eight brightness levels, ranging from 0 to 7. Some of the levels +may not be distinct. Later Lenovo models that implement the ACPI +display backlight brightness control methods have 16 levels, ranging +from 0 to 15. + +There are two interfaces to the firmware for direct brightness control, +EC and CMOS. To select which one should be used, use the +brightness_mode module parameter: brightness_mode=1 selects EC mode, +brightness_mode=2 selects CMOS mode, brightness_mode=3 selects both EC +and CMOS. The driver tries to autodetect which interface to use. + +When display backlight brightness controls are available through the +standard ACPI interface, it is best to use it instead of this direct +ThinkPad-specific interface. The driver will disable its native +backlight brightness control interface if it detects that the standard +ACPI interface is available in the ThinkPad. + +The brightness_enable module parameter can be used to control whether +the LCD brightness control feature will be enabled when available. +brightness_enable=0 forces it to be disabled. brightness_enable=1 +forces it to be enabled when available, even if the standard ACPI +interface is also available. Procfs notes: @@ -942,11 +962,11 @@ Procfs notes: Sysfs notes: -The interface is implemented through the backlight sysfs class, which is poorly -documented at this time. +The interface is implemented through the backlight sysfs class, which is +poorly documented at this time. -Locate the thinkpad_screen device under /sys/class/backlight, and inside it -there will be the following attributes: +Locate the thinkpad_screen device under /sys/class/backlight, and inside +it there will be the following attributes: max_brightness: Reads the maximum brightness the hardware can be set to. @@ -956,17 +976,19 @@ there will be the following attributes: Reads what brightness the screen is set to at this instant. brightness: - Writes request the driver to change brightness to the given - value. Reads will tell you what brightness the driver is trying - to set the display to when "power" is set to zero and the display - has not been dimmed by a kernel power management event. + Writes request the driver to change brightness to the + given value. Reads will tell you what brightness the + driver is trying to set the display to when "power" is set + to zero and the display has not been dimmed by a kernel + power management event. power: - power management mode, where 0 is "display on", and 1 to 3 will - dim the display backlight to brightness level 0 because - thinkpad-acpi cannot really turn the backlight off. Kernel - power management events can temporarily increase the current - power management level, i.e. they can dim the display. + power management mode, where 0 is "display on", and 1 to 3 + will dim the display backlight to brightness level 0 + because thinkpad-acpi cannot really turn the backlight + off. Kernel power management events can temporarily + increase the current power management level, i.e. they can + dim the display. Volume control -- /proc/acpi/ibm/volume @@ -989,7 +1011,9 @@ Fan control and monitoring: fan speed, fan enable/disable --------------------------------------------------------- procfs: /proc/acpi/ibm/fan -sysfs device attributes: (hwmon) fan_input, pwm1, pwm1_enable +sysfs device attributes: (hwmon "thinkpad") fan1_input, pwm1, + pwm1_enable +sysfs hwmon driver attributes: fan_watchdog NOTE NOTE NOTE: fan control operations are disabled by default for safety reasons. To enable them, the module parameter "fan_control=1" @@ -1028,7 +1052,7 @@ enable it if necessary to avoid overheating. An enabled fan in level "auto" may stop spinning if the EC decides the ThinkPad is cool enough and doesn't need the extra airflow. This is -normal, and the EC will spin the fan up if the varios thermal readings +normal, and the EC will spin the fan up if the various thermal readings rise too much. On the X40, this seems to depend on the CPU and HDD temperatures. @@ -1131,7 +1155,7 @@ hwmon device attribute fan1_input: which can take up to two minutes. May return rubbish on older ThinkPads. -driver attribute fan_watchdog: +hwmon driver attribute fan_watchdog: Fan safety watchdog timer interval, in seconds. Minimum is 1 second, maximum is 120 seconds. 0 disables the watchdog. @@ -1196,7 +1220,7 @@ for example: Enabling debugging output ------------------------- -The module takes a debug paramater which can be used to selectively +The module takes a debug parameter which can be used to selectively enable various classes of debugging output, for example: modprobe ibm_acpi debug=0xffff @@ -1233,3 +1257,9 @@ Sysfs interface changelog: layer, the radio switch generates input event EV_RADIO, and the driver enables hot key handling by default in the firmware. + +0x020000: ABI fix: added a separate hwmon platform device and + driver, which must be located by name (thinkpad) + and the hwmon class for libsensors4 (lm-sensors 3) + compatibility. Moved all hwmon attributes to this + new platform device. diff --git a/trunk/Documentation/tty.txt b/trunk/Documentation/tty.txt index 048a8762cfb5..8e65c4498c52 100644 --- a/trunk/Documentation/tty.txt +++ b/trunk/Documentation/tty.txt @@ -132,6 +132,14 @@ set_termios() Notify the tty driver that the device's termios tty->termios. Previous settings should be passed in the "old" argument. + The API is defined such that the driver should return + the actual modes selected. This means that the + driver function is responsible for modifying any + bits in the request it cannot fulfill to indicate + the actual modes being used. A device with no + hardware capability for change (eg a USB dongle or + virtual port) can provide NULL for this method. + throttle() Notify the tty driver that input buffers for the line discipline are close to full, and it should somehow signal that no more characters should be diff --git a/trunk/Documentation/usb/power-management.txt b/trunk/Documentation/usb/power-management.txt index 97842deec471..b2fc4d4a9917 100644 --- a/trunk/Documentation/usb/power-management.txt +++ b/trunk/Documentation/usb/power-management.txt @@ -278,6 +278,14 @@ optional. The methods' jobs are quite simple: (although the interfaces will be in the same altsettings as before the suspend). +If the device is disconnected or powered down while it is suspended, +the disconnect method will be called instead of the resume or +reset_resume method. This is also quite likely to happen when +waking up from hibernation, as many systems do not maintain suspend +current to the USB host controllers during hibernation. (It's +possible to work around the hibernation-forces-disconnect problem by +using the USB Persist facility.) + The reset_resume method is used by the USB Persist facility (see Documentation/usb/persist.txt) and it can also be used under certain circumstances when CONFIG_USB_PERSIST is not enabled. Currently, if a diff --git a/trunk/Documentation/usb/usb-serial.txt b/trunk/Documentation/usb/usb-serial.txt index 4e0b62b8566f..8b077e43eee7 100644 --- a/trunk/Documentation/usb/usb-serial.txt +++ b/trunk/Documentation/usb/usb-serial.txt @@ -338,7 +338,7 @@ MCT USB Single Port Serial Adapter U232 This driver is for the MCT USB-RS232 Converter (25 pin, Model No. U232-P25) from Magic Control Technology Corp. (there is also a 9 pin Model No. U232-P9). More information about this device can be found at - the manufacture's web-site: http://www.mct.com.tw. + the manufacturer's web-site: http://www.mct.com.tw. The driver is generally working, though it still needs some more testing. It is derived from the Belkin USB Serial Adapter F5U103 driver and its diff --git a/trunk/Documentation/video4linux/CARDLIST.em28xx b/trunk/Documentation/video4linux/CARDLIST.em28xx index a3026689bbe6..37f0e3cedf43 100644 --- a/trunk/Documentation/video4linux/CARDLIST.em28xx +++ b/trunk/Documentation/video4linux/CARDLIST.em28xx @@ -8,4 +8,7 @@ 7 -> Leadtek Winfast USB II (em2800) 8 -> Kworld USB2800 (em2800) 9 -> Pinnacle Dazzle DVC 90 (em2820/em2840) [2304:0207] + 10 -> Hauppauge WinTV HVR 900 (em2880) + 11 -> Terratec Hybrid XS (em2880) 12 -> Kworld PVR TV 2800 RF (em2820/em2840) + 13 -> Terratec Prodigy XS (em2880) diff --git a/trunk/Documentation/watchdog/src/watchdog-simple.c b/trunk/Documentation/watchdog/src/watchdog-simple.c index 47801bc7e742..4cf72f3fa8e9 100644 --- a/trunk/Documentation/watchdog/src/watchdog-simple.c +++ b/trunk/Documentation/watchdog/src/watchdog-simple.c @@ -3,15 +3,25 @@ #include #include -int main(int argc, const char *argv[]) { +int main(void) +{ int fd = open("/dev/watchdog", O_WRONLY); + int ret = 0; if (fd == -1) { perror("watchdog"); - exit(1); + exit(EXIT_FAILURE); } while (1) { - write(fd, "\0", 1); - fsync(fd); + ret = write(fd, "\0", 1); + if (ret != 1) { + ret = -1; + break; + } + ret = fsync(fd); + if (ret) + break; sleep(10); } + close(fd); + return ret; } diff --git a/trunk/Documentation/x86_64/uefi.txt b/trunk/Documentation/x86_64/uefi.txt new file mode 100644 index 000000000000..91a98edfb588 --- /dev/null +++ b/trunk/Documentation/x86_64/uefi.txt @@ -0,0 +1,29 @@ +General note on [U]EFI x86_64 support +------------------------------------- + +The nomenclature EFI and UEFI are used interchangeably in this document. + +Although the tools below are _not_ needed for building the kernel, +the needed bootloader support and associated tools for x86_64 platforms +with EFI firmware and specifications are listed below. + +1. UEFI specification: http://www.uefi.org + +2. Booting Linux kernel on UEFI x86_64 platform requires bootloader + support. Elilo with x86_64 support can be used. + +3. x86_64 platform with EFI/UEFI firmware. + +Mechanics: +--------- +- Build the kernel with the following configuration. + CONFIG_FB_EFI=y + CONFIG_FRAMEBUFFER_CONSOLE=y +- Create a VFAT partition on the disk +- Copy the following to the VFAT partition: + elilo bootloader with x86_64 support, elilo configuration file, + kernel image built in first step and corresponding + initrd. Instructions on building elilo and its dependencies + can be found in the elilo sourceforge project. +- Boot to EFI shell and invoke elilo choosing the kernel image built + in first step. diff --git a/trunk/MAINTAINERS b/trunk/MAINTAINERS index 2534dc4aa95a..f3d7256bc74e 100644 --- a/trunk/MAINTAINERS +++ b/trunk/MAINTAINERS @@ -136,17 +136,6 @@ M: ajk@iehk.rwth-aachen.de L: linux-hams@vger.kernel.org S: Maintained -8139CP 10/100 FAST ETHERNET DRIVER -P: Jeff Garzik -M: jgarzik@pobox.com -S: Maintained - -8139TOO 10/100 FAST ETHERNET DRIVER -P: Jeff Garzik -M: jgarzik@pobox.com -W: http://sourceforge.net/projects/gkernel/ -S: Maintained - 8169 10/100/1000 GIGABIT ETHERNET DRIVER P: Francois Romieu M: romieu@fr.zoreil.com @@ -227,7 +216,7 @@ P: Len Brown M: len.brown@intel.com M: lenb@kernel.org L: linux-acpi@vger.kernel.org -W: http://acpi.sourceforge.net/ +W: http://www.lesswatts.org/projects/acpi/ T: git kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git S: Supported @@ -246,8 +235,8 @@ W: http://acpi.sourceforge.net/ S: Supported ACPI FAN DRIVER -P: Konstantin A. Karasyov -M: konstantin.a.karasyov@intel.com +P: Len Brown +M: len.brown@intel.com L: linux-acpi@vger.kernel.org W: http://acpi.sourceforge.net/ S: Supported @@ -259,15 +248,15 @@ L: pcihpd-discuss@lists.sourceforge.net S: Supported ACPI THERMAL DRIVER -P: Konstantin A. Karasyov -M: konstantin.a.karasyov@intel.com +P: Len Brown +M: len.brown@intel.com L: linux-acpi@vger.kernel.org W: http://acpi.sourceforge.net/ S: Supported ACPI VIDEO DRIVER -P: Luming Yu -M: luming.yu@intel.com +P: Rui Zhang +M: rui.zhang@intel.com L: linux-acpi@vger.kernel.org W: http://acpi.sourceforge.net/ S: Supported @@ -325,11 +314,16 @@ M: Juergen Fischer L: linux-scsi@vger.kernel.org S: Maintained +AIC7XXX / AIC79XX SCSI DRIVER +P: Hannes Reinecke +M: hare@suse.de +L: linux-scsi@vger.kernel.org +S: Maintained + ALCATEL SPEEDTOUCH USB DRIVER P: Duncan Sands M: duncan.sands@free.fr -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://www.linux-usb.org/SpeedTouch/ S: Maintained @@ -403,6 +397,12 @@ P: Arnaldo Carvalho de Melo M: acme@ghostprotocols.net S: Maintained +APPLETOUCH TOUCHPAD DRIVER +P: Johannes Berg +M: johannes@sipsolutions.net +L: linux-input@vger.kernel.org +S: Maintained + ARC FRAMEBUFFER DRIVER P: Jaya Kumar M: jayalk@intworks.biz @@ -439,7 +439,7 @@ S: Maintained ARM/ATMEL AT91RM9200 ARM ARCHITECTURE P: Andrew Victor -M: andrew@sanpeople.com +M: linux@maxim.org.za L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only) W: http://maxim.org.za/at91_26.html S: Maintained @@ -786,23 +786,25 @@ B43 WIRELESS DRIVER P: Michael Buesch M: mb@bu3sch.de P: Stefano Brivio -M: st3@riseup.net +M: stefano.brivio@polimi.it L: linux-wireless@vger.kernel.org -W: http://bcm43xx.berlios.de/ +W: http://linuxwireless.org/en/users/Drivers/b43 S: Maintained B43LEGACY WIRELESS DRIVER P: Larry Finger M: Larry.Finger@lwfinger.net +P: Stefano Brivio +M: stefano.brivio@polimi.it L: linux-wireless@vger.kernel.org -W: http://bcm43xx.berlios.de/ +W: http://linuxwireless.org/en/users/Drivers/b43 S: Maintained BCM43XX WIRELESS DRIVER (SOFTMAC BASED VERSION) P: Larry Finger M: Larry.Finger@lwfinger.net P: Stefano Brivio -M: st3@riseup.net +M: stefano.brivio@polimi.it L: linux-wireless@vger.kernel.org W: http://bcm43xx.berlios.de/ S: Maintained @@ -1037,16 +1039,10 @@ M: kernel@wantstofly.org L: netdev@vger.kernel.org S: Maintained -CIRRUS LOGIC GENERIC FBDEV DRIVER -P: Jeff Garzik -M: jgarzik@pobox.com -L: linux-fbdev-devel@lists.sourceforge.net (subscribers-only) -S: Odd Fixes - CIRRUS LOGIC EP93XX OHCI USB HOST DRIVER P: Lennert Buytenhek M: kernel@wantstofly.org -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained CIRRUS LOGIC CS4280/CS461x SOUNDDRIVER @@ -1555,7 +1551,7 @@ S: Maintained FREESCALE HIGHSPEED USB DEVICE DRIVER P: Li Yang M: leoli@freescale.com -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: linuxppc-dev@ozlabs.org S: Maintained @@ -1685,8 +1681,7 @@ S: Maintained HARMONY SOUND DRIVER P: Kyle McMartin M: kyle@parisc-linux.org -W: http://www.parisc-linux.org/~kyle/harmony/ -L: parisc-linux@lists.parisc-linux.org +L: linux-parisc@vger.kernel.org S: Maintained HAYES ESP SERIAL DRIVER @@ -1712,7 +1707,7 @@ S: Maintained HID CORE LAYER P: Jiri Kosina M: jkosina@suse.cz -L: linux-input@atrey.karlin.mff.cuni.cz +L: linux-input@vger.kernel.org T: git kernel.org:/pub/scm/linux/kernel/git/jikos/hid.git S: Maintained @@ -1917,10 +1912,8 @@ L: linux1394-devel@lists.sourceforge.net S: Maintained IMS TWINTURBO FRAMEBUFFER DRIVER -P: Paul Mundt -M: lethal@chaoticdreams.org L: linux-fbdev-devel@lists.sourceforge.net (subscribers-only) -S: Maintained +S: Orphan INFINIBAND SUBSYSTEM P: Roland Dreier @@ -1938,8 +1931,7 @@ INPUT (KEYBOARD, MOUSE, JOYSTICK, TOUCHSCREEN) DRIVERS P: Dmitry Torokhov M: dmitry.torokhov@gmail.com M: dtor@mail.ru -L: linux-input@atrey.karlin.mff.cuni.cz -L: linux-joystick@atrey.karlin.mff.cuni.cz +L: linux-input@vger.kernel.org T: git kernel.org:/pub/scm/linux/kernel/git/dtor/input.git S: Maintained @@ -1963,17 +1955,6 @@ M: adaplas@gmail.com L: linux-fbdev-devel@lists.sourceforge.net (subscribers-only) S: Maintained -INTEL APIC/IOAPIC, LOWLEVEL X86 SMP SUPPORT -P: Ingo Molnar -M: mingo@redhat.com -S: Maintained - -INTEL I8XX RANDOM NUMBER GENERATOR SUPPORT -P: Jeff Garzik -M: jgarzik@pobox.com -W: http://sourceforge.net/projects/gkernel/ -S: Maintained - INTEL IA32 MICROCODE UPDATE SUPPORT P: Tigran Aivazian M: tigran@aivazian.fsnet.co.uk @@ -2128,6 +2109,14 @@ L: irda-users@lists.sourceforge.net (subscribers-only) W: http://irda.sourceforge.net/ S: Maintained +ISCSI +P: Mike Christie +M: michaelc@cs.wisc.edu +L: open-iscsi@googlegroups.com +W: www.open-iscsi.org +T: git kernel.org:/pub/scm/linux/kernel/mnc/linux-2.6-iscsi.git +S: Maintained + ISAPNP P: Jaroslav Kysela M: perex@perex.cz @@ -2151,8 +2140,8 @@ S: Maintained JOURNALLING FLASH FILE SYSTEM V2 (JFFS2) P: David Woodhouse M: dwmw2@infradead.org -L: jffs-dev@axis.com -W: http://sources.redhat.com/jffs2/ +L: linux-mtd@lists.infradead.org +W: http://www.linux-mtd.infradead.org/doc/jffs2.html S: Maintained JFS FILESYSTEM @@ -2178,12 +2167,12 @@ S: Maintained KCONFIG P: Roman Zippel M: zippel@linux-m68k.org -L: kbuild-devel@lists.sourceforge.net +L: linux-kbuild@vger.kernel.org S: Maintained KDUMP P: Vivek Goyal -M: vgoyal@in.ibm.com +M: vgoyal@redhat.com P: Haren Myneni M: hbabu@us.ibm.com L: kexec@lists.infradead.org @@ -2207,6 +2196,7 @@ KERNEL BUILD (kbuild: Makefile, scripts/Makefile.*) P: Sam Ravnborg M: sam@ravnborg.org T: git kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git +L: linux-kbuild@vger.kernel.org S: Maintained KERNEL JANITORS @@ -2280,6 +2270,13 @@ L: legousb-devel@lists.sourceforge.net W: http://legousb.sourceforge.net/ S: Maintained +LGUEST +P: Rusty Russell +M: rusty@rustcorp.com.au +L: lguest@ozlabs.org +W: http://lguest.ozlabs.org/ +S: Maintained + LINUX FOR IBM pSERIES (RS/6000) P: Paul Mackerras M: paulus@au.ibm.com @@ -2342,6 +2339,8 @@ L: linuxppc-dev@ozlabs.org S: Maintained LINUX FOR POWERPC EMBEDDED PPC8XX +P: Vitaly Bordug +M: vitb@kernel.crashing.org P: Marcelo Tosatti M: marcelo@kvack.org W: http://www.penguinppc.org/ @@ -2451,7 +2450,7 @@ M68K ON APPLE MACINTOSH P: Joshua Thompson M: funaho@jurai.org W: http://www.mac.linux-m68k.org/ -L: linux-mac68k@mac.linux-m68k.org +L: linux-m68k@lists.linux-m68k.org S: Maintained M68K ON HP9000/300 @@ -2461,13 +2460,15 @@ W: http://www.tazenda.demon.co.uk/phil/linux-hp S: Maintained MAC80211 -P: Jiri Benc -M: jbenc@suse.cz P: Michael Wu M: flamingice@sourmilk.net +P: Johannes Berg +M: johannes@sipsolutions.net +P: Jiri Benc +M: jbenc@suse.cz L: linux-wireless@vger.kernel.org W: http://linuxwireless.org/ -T: git kernel.org:/pub/scm/linux/kernel/git/jbenc/mac80211.git +T: git kernel.org:/pub/scm/linux/kernel/git/linville/wireless-2.6.git S: Maintained MACVLAN DRIVER @@ -2554,7 +2555,7 @@ S: Supported MISCELLANEOUS MCA-SUPPORT P: James Bottomley -M: jejb@steeleye.com +M: James.Bottomley@HansenPartnership.com L: linux-kernel@vger.kernel.org S: Maintained @@ -2596,13 +2597,6 @@ L: https://tango.0pointer.de/mailman/listinfo/s270-linux W: http://0pointer.de/lennart/tchibo.html S: Maintained -MTRR AND SIMILAR SUPPORT [i386] -P: Richard Gooch -M: rgooch@atnf.csiro.au -L: linux-kernel@vger.kernel.org -W: http://www.atnf.csiro.au/~rgooch/linux/kernel-patches.html -S: Maintained - MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM P: Pierre Ossman M: drzeus-mmc@drzeus.cx @@ -2697,8 +2691,6 @@ M: Paul.Clements@steeleye.com S: Maintained NETWORK DEVICE DRIVERS -P: Andrew Morton -M: akpm@linux-foundation.org P: Jeff Garzik M: jgarzik@pobox.com L: netdev@vger.kernel.org @@ -2897,16 +2889,15 @@ W: http://www.torque.net/linux-pp.html S: Maintained PARISC ARCHITECTURE +P: Kyle McMartin +M: kyle@parisc-linux.org P: Matthew Wilcox M: matthew@wil.cx P: Grant Grundler M: grundler@parisc-linux.org -P: Kyle McMartin -M: kyle@parisc-linux.org -L: parisc-linux@parisc-linux.org +L: linux-parisc@vger.kernel.org W: http://www.parisc-linux.org/ T: git kernel.org:/pub/scm/linux/kernel/git/kyle/parisc-2.6.git -T: cvs cvs.parisc-linux.org:/var/cvs/linux-2.6 S: Maintained PARAVIRT_OPS INTERFACE @@ -3250,6 +3241,8 @@ S: Supported S390 NETWORK DRIVERS P: Ursula Braun M: ubraun@linux.vnet.ibm.com +P: Frank Blaschka +M: blaschka@linux.vnet.ibm.com M: linux390@de.ibm.com L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ @@ -3306,9 +3299,11 @@ S: Maintained SCSI SUBSYSTEM P: James E.J. Bottomley -M: James.Bottomley@SteelEye.com +M: James.Bottomley@HansenPartnership.com L: linux-scsi@vger.kernel.org T: git kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git +T: git kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-rc-fixes-2.6.git +T: git kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-pending-2.6.git S: Maintained SCSI TAPE DRIVER @@ -3455,15 +3450,10 @@ L: lm-sensors@lm-sensors.org S: Maintained SOFTMAC LAYER (IEEE 802.11) -P: Johannes Berg -M: johannes@sipsolutions.net -P: Joe Jezak -M: josejx@gentoo.org P: Daniel Drake M: dsd@gentoo.org -W: http://softmac.sipsolutions.net/ L: linux-wireless@vger.kernel.org -S: Maintained +S: Obsolete SOFTWARE RAID (Multiple Disks) SUPPORT P: Ingo Molnar @@ -3482,12 +3472,14 @@ L: linux-pm@lists.linux-foundation.org S: Supported SUSPEND TO RAM: +P: Len Brown +M: len.brown@intel.com P: Pavel Machek M: pavel@suse.cz P: Rafael J. Wysocki M: rjw@sisk.pl L: linux-pm@lists.linux-foundation.org -S: Maintained +S: Supported SONIC NETWORK DRIVER P: Thomas Bogendoerfer @@ -3640,18 +3632,12 @@ M: laredo@gnu.org W: http://www.stradis.com/ S: Maintained -SUPERH (sh) -P: Paul Mundt -M: lethal@linux-sh.org -L: linuxsh-dev@lists.sourceforge.net (subscribers-only) -W: http://www.linux-sh.org -S: Maintained - -SUPERH64 (sh64) +SUPERH P: Paul Mundt M: lethal@linux-sh.org -L: linuxsh-shmedia-dev@lists.sourceforge.net +L: linux-sh@vger.kernel.org W: http://www.linux-sh.org +T: git kernel.org:/pub/scm/linux/kernel/git/lethal/sh-2.6.git S: Maintained SUN3/3X @@ -3737,7 +3723,7 @@ S: Maintained TLAN NETWORK DRIVER P: Samuel Chessman M: chessman@tux.org -L: tlan-devel@lists.sourceforge.net +L: tlan-devel@lists.sourceforge.net (subscribers-only) W: http://sourceforge.net/projects/tlan/ S: Maintained @@ -3822,22 +3808,20 @@ S: Maintained USB ACM DRIVER P: Oliver Neukum M: oliver@neukum.name -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB BLOCK DRIVER (UB ub) P: Pete Zaitcev M: zaitcev@redhat.com L: linux-kernel@vger.kernel.org -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Supported USB CDC ETHERNET DRIVER P: Greg Kroah-Hartman M: greg@kroah.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained W: http://www.kroah.com/linux-usb/ @@ -3851,13 +3835,13 @@ S: Maintained USB EHCI DRIVER P: David Brownell M: dbrownell@users.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Odd Fixes USB ET61X[12]51 DRIVER P: Luca Risolia M: luca.risolia@studio.unibo.it -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: video4linux-list@redhat.com W: http://www.linux-projects.org S: Maintained @@ -3865,41 +3849,33 @@ S: Maintained USB GADGET/PERIPHERAL SUBSYSTEM P: David Brownell M: dbrownell@users.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://www.linux-usb.org/gadget S: Maintained USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) P: Jiri Kosina M: jkosina@suse.cz -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org T: git kernel.org:/pub/scm/linux/kernel/git/jikos/hid.git S: Maintained -USB HUB DRIVER -P: Johannes Erdfelt -M: johannes@erdfelt.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net -S: Maintained - USB ISP116X DRIVER P: Olav Kongas M: ok@artecdesign.ee -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB KAWASAKI LSI DRIVER P: Oliver Neukum M: oliver@neukum.name -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB MASS STORAGE DRIVER P: Matthew Dharm M: mdharm-usb@one-eyed-alien.net -L: linux-usb-users@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: usb-storage@lists.one-eyed-alien.net S: Maintained W: http://www.one-eyed-alien.net/~mdharm/linux-usb/ @@ -3907,28 +3883,26 @@ W: http://www.one-eyed-alien.net/~mdharm/linux-usb/ USB OHCI DRIVER P: David Brownell M: dbrownell@users.sourceforge.net -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Odd Fixes USB OPTION-CARD DRIVER P: Matthias Urlichs M: smurf@smurf.noris.de -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB OV511 DRIVER P: Mark McClelland M: mmcclell@bigfoot.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://alpha.dyndns.org/ov511/ S: Maintained USB PEGASUS DRIVER P: Petko Manolov M: petkan@users.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: netdev@vger.kernel.org W: http://pegasus2.sourceforge.net/ S: Maintained @@ -3936,14 +3910,13 @@ S: Maintained USB PRINTER DRIVER (usblp) P: Pete Zaitcev M: zaitcev@redhat.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Supported USB RTL8150 DRIVER P: Petko Manolov M: petkan@users.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: netdev@vger.kernel.org W: http://pegasus2.sourceforge.net/ S: Maintained @@ -3951,8 +3924,7 @@ S: Maintained USB SE401 DRIVER P: Jeroen Vreeken M: pe1rxq@amsat.org -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://www.chello.nl/~j.vreeken/se401/ S: Maintained @@ -3966,72 +3938,59 @@ USB SERIAL DIGI ACCELEPORT DRIVER P: Peter Berger and Al Borchers M: pberger@brimson.com M: alborchers@steinerpoint.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB SERIAL DRIVER P: Greg Kroah-Hartman M: gregkh@suse.de -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Supported USB SERIAL BELKIN F5U103 DRIVER P: William Greathouse M: wgreathouse@smva.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB SERIAL CYPRESS M8 DRIVER P: Lonnie Mendez M: dignome@gmail.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained W: http://geocities.com/i0xox0i W: http://firstlight.net/cvs -USB SERIAL CYBERJACK PINPAD/E-COM DRIVER -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net -S: Maintained - USB AUERSWALD DRIVER P: Wolfgang Muees M: wolfgang@iksw-muees.de -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB SERIAL EMPEG EMPEG-CAR MARK I/II DRIVER P: Gary Brubaker M: xavyer@ix.netcom.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB SERIAL KEYSPAN DRIVER P: Greg Kroah-Hartman M: greg@kroah.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://www.kroah.com/linux/ S: Maintained USB SERIAL WHITEHEAT DRIVER P: Support Department M: support@connecttech.com -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://www.connecttech.com S: Supported USB SN9C1xx DRIVER P: Luca Risolia M: luca.risolia@studio.unibo.it -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: video4linux-list@redhat.com W: http://www.linux-projects.org S: Maintained @@ -4039,8 +3998,7 @@ S: Maintained USB SUBSYSTEM P: Greg Kroah-Hartman M: gregkh@suse.de -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://www.linux-usb.org T: quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/ S: Supported @@ -4048,8 +4006,7 @@ S: Supported USB UHCI DRIVER P: Alan Stern M: stern@rowland.harvard.edu -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org S: Maintained USB "USBNET" DRIVER FRAMEWORK @@ -4062,7 +4019,7 @@ S: Maintained USB W996[87]CF DRIVER P: Luca Risolia M: luca.risolia@studio.unibo.it -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: video4linux-list@redhat.com W: http://www.linux-projects.org S: Maintained @@ -4070,7 +4027,7 @@ S: Maintained USB ZC0301 DRIVER P: Luca Risolia M: luca.risolia@studio.unibo.it -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: video4linux-list@redhat.com W: http://www.linux-projects.org S: Maintained @@ -4078,15 +4035,14 @@ S: Maintained USB ZD1201 DRIVER P: Jeroen Vreeken M: pe1rxq@amsat.org -L: linux-usb-users@lists.sourceforge.net -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org W: http://linux-lc100020.sourceforge.net S: Maintained USB ZR364XX DRIVER P: Antoine Jacquet M: royale@zerezo.com -L: linux-usb-devel@lists.sourceforge.net +L: linux-usb@vger.kernel.org L: video4linux-list@redhat.com W: http://royale.zerezo.com/zr364xx/ S: Maintained @@ -4105,10 +4061,6 @@ M: hirofumi@mail.parknet.co.jp L: linux-kernel@vger.kernel.org S: Maintained -VIA 82Cxxx AUDIO DRIVER (old OSS driver) -P: Jeff Garzik -S: Odd fixes - VIA RHINE NETWORK DRIVER P: Roger Luethi M: rl@hellgate.ch @@ -4164,6 +4116,12 @@ W: http://linuxtv.org T: git kernel.org:/pub/scm/linux/kernel/git/mchehab/v4l-dvb.git S: Maintained +VLAN (802.1Q) +P: Patrick McHardy +M: kaber@trash.net +L: netdev@vger.kernel.org +S: Maintained + VT1211 HARDWARE MONITOR DRIVER P: Juerg Haefliger M: juergh@gmail.com @@ -4268,9 +4226,15 @@ M: jacmet@sunsite.dk L: linux-serial@vger.kernel.org S: Maintained -X86 3-LEVEL PAGING (PAE) SUPPORT +X86 ARCHITECTURE (32-BIT AND 64-BIT) +P: Thomas Gleixner +M: tglx@linutronix.de P: Ingo Molnar M: mingo@redhat.com +P: H. Peter Anvin +M: hpa@zytor.com +L: linux-kernel@vger.kernel.org +T: git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git S: Maintained YAM DRIVER FOR AX.25 diff --git a/trunk/Makefile b/trunk/Makefile index 529b9048d97e..7fb1a2c08305 100644 --- a/trunk/Makefile +++ b/trunk/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 -SUBLEVEL = 23 -EXTRAVERSION = +SUBLEVEL = 24 +EXTRAVERSION = -rc4 NAME = Arr Matey! A Hairy Bilge Rat! # *DOCUMENTATION* @@ -108,6 +108,9 @@ endif PHONY := _all _all: +# Cancel implicit rules on top Makefile +$(CURDIR)/Makefile Makefile: ; + ifneq ($(KBUILD_OUTPUT),) # Invoke a second make in the output directory, passing relevant variables # check that the output directory actually exists @@ -115,13 +118,10 @@ saved-output := $(KBUILD_OUTPUT) KBUILD_OUTPUT := $(shell cd $(KBUILD_OUTPUT) && /bin/pwd) $(if $(KBUILD_OUTPUT),, \ $(error output directory "$(saved-output)" does not exist)) -# Check that OUTPUT directory is not the same as where we have kernel src -$(if $(filter-out $(KBUILD_OUTPUT),$(shell /bin/pwd)),, \ - $(error Output directory (O=...) specifies kernel src dir)) PHONY += $(MAKECMDGOALS) sub-make -$(filter-out _all sub-make,$(MAKECMDGOALS)) _all: sub-make +$(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make $(Q)@: sub-make: FORCE @@ -168,7 +168,8 @@ export srctree objtree VPATH TOPDIR SUBARCH := $(shell uname -m | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \ -e s/arm.*/arm/ -e s/sa110/arm/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ - -e s/ppc.*/powerpc/ -e s/mips.*/mips/ ) + -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ + -e s/sh[234].*/sh/ ) # Cross compiling and selecting different set of gcc/bin-utils # --------------------------------------------------------------------------- @@ -196,6 +197,14 @@ CROSS_COMPILE ?= UTS_MACHINE := $(ARCH) SRCARCH := $(ARCH) +# Additional ARCH settings for x86 +ifeq ($(ARCH),i386) + SRCARCH := x86 +endif +ifeq ($(ARCH),x86_64) + SRCARCH := x86 +endif + KCONFIG_CONFIG ?= .config # SHELL used by kbuild @@ -282,7 +291,8 @@ export quiet Q KBUILD_VERBOSE # Look for make include files relative to root of kernel src MAKEFLAGS += --include-dir=$(srctree) -# We need some generic definitions. +# We need some generic definitions (do not try to remake the file). +$(srctree)/scripts/Kbuild.include: ; include $(srctree)/scripts/Kbuild.include # Make variables (CC, etc...) @@ -418,7 +428,7 @@ ifeq ($(config-targets),1) # Read arch specific Makefile to set KBUILD_DEFCONFIG as needed. # KBUILD_DEFCONFIG may point out an alternative default configuration # used for 'make defconfig' -include $(srctree)/arch/$(ARCH)/Makefile +include $(srctree)/arch/$(SRCARCH)/Makefile export KBUILD_DEFCONFIG config %config: scripts_basic outputmakefile FORCE @@ -497,7 +507,7 @@ else KBUILD_CFLAGS += -O2 endif -include $(srctree)/arch/$(ARCH)/Makefile +include $(srctree)/arch/$(SRCARCH)/Makefile ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls @@ -524,9 +534,22 @@ KBUILD_CFLAGS += $(call cc-option,-Wdeclaration-after-statement,) KBUILD_CFLAGS += $(call cc-option,-Wno-pointer-sign,) # Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments -KBUILD_CPPFLAGS += $(CPPFLAGS) -KBUILD_AFLAGS += $(AFLAGS) -KBUILD_CFLAGS += $(CFLAGS) +# But warn user when we do so +warn-assign = \ +$(warning "WARNING: Appending $$K$(1) ($(K$(1))) from $(origin K$(1)) to kernel $$$(1)") + +ifneq ($(KCPPFLAGS),) + $(call warn-assign,CPPFLAGS) + KBUILD_CPPFLAGS += $(KCPPFLAGS) +endif +ifneq ($(KAFLAGS),) + $(call warn-assign,AFLAGS) + KBUILD_AFLAGS += $(KAFLAGS) +endif +ifneq ($(KCFLAGS),) + $(call warn-assign,CFLAGS) + KBUILD_CFLAGS += $(KCFLAGS) +endif # Use --build-id when available. LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\ @@ -773,6 +796,9 @@ endef vmlinux: $(vmlinux-lds) $(vmlinux-init) $(vmlinux-main) $(kallsyms.o) vmlinux.o FORCE ifdef CONFIG_HEADERS_CHECK $(Q)$(MAKE) -f $(srctree)/Makefile headers_check +endif +ifdef CONFIG_SAMPLES + $(Q)$(MAKE) $(build)=samples endif $(call vmlinux-modpost) $(call if_changed_rule,vmlinux__) @@ -884,10 +910,7 @@ prepare2: prepare3 outputmakefile prepare1: prepare2 include/linux/version.h include/linux/utsrelease.h \ include/asm include/config/auto.conf -ifneq ($(KBUILD_MODULES),) - $(Q)mkdir -p $(MODVERDIR) - $(Q)rm -f $(MODVERDIR)/* -endif + $(cmd_crmodverdir) archprepare: prepare1 scripts_basic @@ -903,14 +926,24 @@ prepare: prepare0 export CPPFLAGS_vmlinux.lds += -P -C -U$(ARCH) -# FIXME: The asm symlink changes when $(ARCH) changes. That's -# hard to detect, but I suppose "make mrproper" is a good idea -# before switching between archs anyway. - -include/asm: - @echo ' SYMLINK $@ -> include/asm-$(SRCARCH)' - $(Q)if [ ! -d include ]; then mkdir -p include; fi; - @ln -fsn asm-$(SRCARCH) $@ +# The asm symlink changes when $(ARCH) changes. +# Detect this and ask user to run make mrproper + +include/asm: FORCE + $(Q)set -e; asmlink=`readlink include/asm | cut -d '-' -f 2`; \ + if [ -L include/asm ]; then \ + if [ "$$asmlink" != "$(SRCARCH)" ]; then \ + echo "ERROR: the symlink $@ points to asm-$$asmlink but asm-$(SRCARCH) was expected"; \ + echo " set ARCH or save .config and run 'make mrproper' to fix it"; \ + exit 1; \ + fi; \ + else \ + echo ' SYMLINK $@ -> include/asm-$(SRCARCH)'; \ + if [ ! -d include ]; then \ + mkdir -p include; \ + fi; \ + ln -fsn asm-$(SRCARCH) $@; \ + fi # Generate some files # --------------------------------------------------------------------------- @@ -1020,19 +1053,12 @@ _modinst_: fi $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst -# If System.map exists, run depmod. This deliberately does not have a -# dependency on System.map since that would run the dependency tree on -# vmlinux. This depmod is only for convenience to give the initial +# This depmod is only for convenience to give the initial # boot a modules.dep even before / is mounted read-write. However the # boot script depmod is the master version. -ifeq "$(strip $(INSTALL_MOD_PATH))" "" -depmod_opts := -else -depmod_opts := -b $(INSTALL_MOD_PATH) -r -endif PHONY += _modinst_post _modinst_post: _modinst_ - if [ -r System.map -a -x $(DEPMOD) ]; then $(DEPMOD) -ae -F System.map $(depmod_opts) $(KERNELRELEASE); fi + $(call cmd,depmod) else # CONFIG_MODULES @@ -1220,8 +1246,7 @@ else # KBUILD_EXTMOD KBUILD_MODULES := 1 PHONY += crmodverdir crmodverdir: - $(Q)mkdir -p $(MODVERDIR) - $(Q)rm -f $(MODVERDIR)/* + $(cmd_crmodverdir) PHONY += $(objtree)/Module.symvers $(objtree)/Module.symvers: @@ -1249,15 +1274,6 @@ _emodinst_: $(Q)mkdir -p $(MODLIB)/$(install-dir) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst -# Run depmod only is we have System.map and depmod is executable -quiet_cmd_depmod = DEPMOD $(KERNELRELEASE) - cmd_depmod = if [ -r System.map -a -x $(DEPMOD) ]; then \ - $(DEPMOD) -ae -F System.map \ - $(if $(strip $(INSTALL_MOD_PATH)), \ - -b $(INSTALL_MOD_PATH) -r) \ - $(KERNELRELEASE); \ - fi - PHONY += _emodinst_post _emodinst_post: _emodinst_ $(call cmd,depmod) @@ -1317,12 +1333,7 @@ else ALLINCLUDE_ARCHS := $(ALLSOURCE_ARCHS) endif -# Take care of arch/x86 -ifeq ($(ARCH), $(SRCARCH)) -ALLSOURCE_ARCHS := $(ARCH) -else -ALLSOURCE_ARCHS := $(ARCH) $(SRCARCH) -endif +ALLSOURCE_ARCHS := $(SRCARCH) define find-sources ( for arch in $(ALLSOURCE_ARCHS) ; do \ @@ -1341,7 +1352,7 @@ define find-sources find $(__srctree)include/asm-generic $(RCS_FIND_IGNORE) \ -name $1 -print; \ find $(__srctree) $(RCS_FIND_IGNORE) \ - \( -name include -o -name arch \) -prune -o \ + \( -name include -o -name arch -o -name '.tmp_*' \) -prune -o \ -name $1 -print; \ ) endef @@ -1490,9 +1501,11 @@ endif # Modules / %/: prepare scripts FORCE + $(cmd_crmodverdir) $(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1) \ $(build)=$(build-dir) %.ko: prepare scripts FORCE + $(cmd_crmodverdir) $(Q)$(MAKE) KBUILD_MODULES=$(if $(CONFIG_MODULES),1) \ $(build)=$(build-dir) $(@:.ko=.o) $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost @@ -1506,6 +1519,20 @@ quiet_cmd_rmdirs = $(if $(wildcard $(rm-dirs)),CLEAN $(wildcard $(rm-dirs))) quiet_cmd_rmfiles = $(if $(wildcard $(rm-files)),CLEAN $(wildcard $(rm-files))) cmd_rmfiles = rm -f $(rm-files) +# Run depmod only is we have System.map and depmod is executable +# and we build for the host arch +quiet_cmd_depmod = DEPMOD $(KERNELRELEASE) + cmd_depmod = \ + if [ -r System.map -a -x $(DEPMOD) ]; then \ + $(DEPMOD) -ae -F System.map \ + $(if $(strip $(INSTALL_MOD_PATH)), -b $(INSTALL_MOD_PATH) -r) \ + $(KERNELRELEASE); \ + fi + +# Create temporary dir for module support files +# clean it up only when building all modules +cmd_crmodverdir = $(Q)mkdir -p $(MODVERDIR) \ + $(if $(KBUILD_MODULES),; rm -f $(MODVERDIR)/*) a_flags = -Wp,-MD,$(depfile) $(KBUILD_AFLAGS) $(AFLAGS_KERNEL) \ $(NOSTDINC_FLAGS) $(KBUILD_CPPFLAGS) \ @@ -1534,9 +1561,6 @@ endif # skip-makefile PHONY += FORCE FORCE: -# Cancel implicit rules on top Makefile, `-rR' will apply to sub-makes. -Makefile: ; - # Declare the contents of the .PHONY variable as phony. We keep that # information in a variable se we can use it in if_changed and friends. .PHONY: $(PHONY) diff --git a/trunk/arch/alpha/Kconfig b/trunk/arch/alpha/Kconfig index 2a85dc33907c..4c002ba37e50 100644 --- a/trunk/arch/alpha/Kconfig +++ b/trunk/arch/alpha/Kconfig @@ -654,7 +654,7 @@ source "drivers/Kconfig" source "fs/Kconfig" -source "arch/alpha/oprofile/Kconfig" +source "kernel/Kconfig.instrumentation" source "arch/alpha/Kconfig.debug" diff --git a/trunk/arch/alpha/kernel/err_marvel.c b/trunk/arch/alpha/kernel/err_marvel.c index f2956ac8dccc..497877bf2012 100644 --- a/trunk/arch/alpha/kernel/err_marvel.c +++ b/trunk/arch/alpha/kernel/err_marvel.c @@ -1082,7 +1082,7 @@ marvel_machine_check(u64 vector, u64 la_ptr) } /* - * A system event or error has occured, handle it here. + * A system event or error has occurred, handle it here. * * Any errors in the logout frame have already been cleared by the * PALcode, so just parse it. diff --git a/trunk/arch/alpha/kernel/err_titan.c b/trunk/arch/alpha/kernel/err_titan.c index 543d96d7fa2b..6f3867877d9e 100644 --- a/trunk/arch/alpha/kernel/err_titan.c +++ b/trunk/arch/alpha/kernel/err_titan.c @@ -591,7 +591,7 @@ privateer_process_680_frame(struct el_common *mchk_header, int print) (struct el_PRIVATEER_envdata_mcheck *) ((unsigned long)mchk_header + mchk_header->sys_offset); - /* TODO - catagorize errors, for now, no error */ + /* TODO - categorize errors, for now, no error */ if (!print) return status; diff --git a/trunk/arch/alpha/kernel/osf_sys.c b/trunk/arch/alpha/kernel/osf_sys.c index ce857158c1ea..6413c5f23226 100644 --- a/trunk/arch/alpha/kernel/osf_sys.c +++ b/trunk/arch/alpha/kernel/osf_sys.c @@ -715,7 +715,7 @@ osf_setsysinfo(unsigned long op, void __user *buffer, unsigned long nbytes, /* * Alpha Architecture Handbook 4.7.7.3: * To be fully IEEE compiant, we must track the current IEEE - * exception state in software, because spurrious bits can be + * exception state in software, because spurious bits can be * set in the trap shadow of a software-complete insn. */ diff --git a/trunk/arch/alpha/kernel/pci-noop.c b/trunk/arch/alpha/kernel/pci-noop.c index 174b729c504b..468b76ce66a1 100644 --- a/trunk/arch/alpha/kernel/pci-noop.c +++ b/trunk/arch/alpha/kernel/pci-noop.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "proto.h" @@ -172,18 +173,19 @@ dma_alloc_coherent(struct device *dev, size_t size, EXPORT_SYMBOL(dma_alloc_coherent); int -dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, +dma_map_sg(struct device *dev, struct scatterlist *sgl, int nents, enum dma_data_direction direction) { int i; + struct scatterlist *sg; - for (i = 0; i < nents; i++ ) { + for_each_sg(sgl, sg, nents, i) { void *va; - BUG_ON(!sg[i].page); - va = page_address(sg[i].page) + sg[i].offset; - sg_dma_address(sg + i) = (dma_addr_t)virt_to_bus(va); - sg_dma_len(sg + i) = sg[i].length; + BUG_ON(!sg_page(sg)); + va = sg_virt(sg); + sg_dma_address(sg) = (dma_addr_t)virt_to_bus(va); + sg_dma_len(sg) = sg->length; } return nents; diff --git a/trunk/arch/alpha/kernel/pci_iommu.c b/trunk/arch/alpha/kernel/pci_iommu.c index e1c470752ebc..2d00a08d3f08 100644 --- a/trunk/arch/alpha/kernel/pci_iommu.c +++ b/trunk/arch/alpha/kernel/pci_iommu.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -465,7 +466,7 @@ EXPORT_SYMBOL(pci_free_consistent); Write dma_length of each leader with the combined lengths of the mergable followers. */ -#define SG_ENT_VIRT_ADDRESS(SG) (page_address((SG)->page) + (SG)->offset) +#define SG_ENT_VIRT_ADDRESS(SG) (sg_virt((SG))) #define SG_ENT_PHYS_ADDRESS(SG) __pa(SG_ENT_VIRT_ADDRESS(SG)) static void diff --git a/trunk/arch/alpha/kernel/semaphore.c b/trunk/arch/alpha/kernel/semaphore.c index 8c8aaa205eae..8d2982aa1b8d 100644 --- a/trunk/arch/alpha/kernel/semaphore.c +++ b/trunk/arch/alpha/kernel/semaphore.c @@ -69,7 +69,7 @@ __down_failed(struct semaphore *sem) #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down failed(%p)\n", - tsk->comm, tsk->pid, sem); + tsk->comm, task_pid_nr(tsk), sem); #endif tsk->state = TASK_UNINTERRUPTIBLE; @@ -98,7 +98,7 @@ __down_failed(struct semaphore *sem) #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down acquired(%p)\n", - tsk->comm, tsk->pid, sem); + tsk->comm, task_pid_nr(tsk), sem); #endif } @@ -111,7 +111,7 @@ __down_failed_interruptible(struct semaphore *sem) #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down failed(%p)\n", - tsk->comm, tsk->pid, sem); + tsk->comm, task_pid_nr(tsk), sem); #endif tsk->state = TASK_INTERRUPTIBLE; @@ -139,7 +139,7 @@ __down_failed_interruptible(struct semaphore *sem) #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down %s(%p)\n", - current->comm, current->pid, + current->comm, task_pid_nr(current), (ret < 0 ? "interrupted" : "acquired"), sem); #endif return ret; @@ -168,7 +168,7 @@ down(struct semaphore *sem) #endif #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down(%p) from %p\n", - current->comm, current->pid, sem, + current->comm, task_pid_nr(current), sem, atomic_read(&sem->count), __builtin_return_address(0)); #endif __down(sem); @@ -182,7 +182,7 @@ down_interruptible(struct semaphore *sem) #endif #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down(%p) from %p\n", - current->comm, current->pid, sem, + current->comm, task_pid_nr(current), sem, atomic_read(&sem->count), __builtin_return_address(0)); #endif return __down_interruptible(sem); @@ -201,7 +201,7 @@ down_trylock(struct semaphore *sem) #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): down_trylock %s from %p\n", - current->comm, current->pid, + current->comm, task_pid_nr(current), ret ? "failed" : "acquired", __builtin_return_address(0)); #endif @@ -217,7 +217,7 @@ up(struct semaphore *sem) #endif #ifdef CONFIG_DEBUG_SEMAPHORE printk("%s(%d): up(%p) from %p\n", - current->comm, current->pid, sem, + current->comm, task_pid_nr(current), sem, atomic_read(&sem->count), __builtin_return_address(0)); #endif __up(sem); diff --git a/trunk/arch/alpha/kernel/smp.c b/trunk/arch/alpha/kernel/smp.c index ad176441be55..f4ab233201b2 100644 --- a/trunk/arch/alpha/kernel/smp.c +++ b/trunk/arch/alpha/kernel/smp.c @@ -439,7 +439,6 @@ setup_smp(void) ((char *)cpubase + i*hwrpb->processor_size); if ((cpu->flags & 0x1cc) == 0x1cc) { smp_num_probed++; - /* Assume here that "whami" == index */ cpu_set(i, cpu_present_map); cpu->pal_revision = boot_cpu_palrev; } diff --git a/trunk/arch/alpha/kernel/sys_alcor.c b/trunk/arch/alpha/kernel/sys_alcor.c index 49bedfbbd31b..d187d01d2a17 100644 --- a/trunk/arch/alpha/kernel/sys_alcor.c +++ b/trunk/arch/alpha/kernel/sys_alcor.c @@ -138,7 +138,7 @@ alcor_init_irq(void) for (i = 16; i < 48; ++i) { /* On Alcor, at least, lines 20..30 are not connected - and can generate spurrious interrupts if we turn them + and can generate spurious interrupts if we turn them on while IRQ probing. */ if (i >= 16+20 && i <= 16+30) continue; diff --git a/trunk/arch/alpha/kernel/sys_sio.c b/trunk/arch/alpha/kernel/sys_sio.c index 14b5a753aba5..ee7b9009ebb4 100644 --- a/trunk/arch/alpha/kernel/sys_sio.c +++ b/trunk/arch/alpha/kernel/sys_sio.c @@ -78,7 +78,7 @@ alphabook1_init_arch(void) * example, sound boards seem to like using IRQ 9. * * This is NOT how we should do it. PIRQ0-X should have - * their own IRQ's, the way intel uses the IO-APIC irq's. + * their own IRQs, the way intel uses the IO-APIC IRQs. */ static void __init diff --git a/trunk/arch/alpha/kernel/traps.c b/trunk/arch/alpha/kernel/traps.c index ec0f05e0d8ff..2dc7f9fed213 100644 --- a/trunk/arch/alpha/kernel/traps.c +++ b/trunk/arch/alpha/kernel/traps.c @@ -182,7 +182,7 @@ die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15) #ifdef CONFIG_SMP printk("CPU %d ", hard_smp_processor_id()); #endif - printk("%s(%d): %s %ld\n", current->comm, current->pid, str, err); + printk("%s(%d): %s %ld\n", current->comm, task_pid_nr(current), str, err); dik_show_regs(regs, r9_15); add_taint(TAINT_DIE); dik_show_trace((unsigned long *)(regs+1)); @@ -646,7 +646,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, lock_kernel(); printk("%s(%d): unhandled unaligned exception\n", - current->comm, current->pid); + current->comm, task_pid_nr(current)); printk("pc = [<%016lx>] ra = [<%016lx>] ps = %04lx\n", pc, una_reg(26), regs->ps); @@ -786,7 +786,7 @@ do_entUnaUser(void __user * va, unsigned long opcode, } if (++cnt < 5) { printk("%s(%d): unaligned trap at %016lx: %p %lx %ld\n", - current->comm, current->pid, + current->comm, task_pid_nr(current), regs->pc - 4, va, opcode, reg); } last_time = jiffies; diff --git a/trunk/arch/alpha/lib/checksum.c b/trunk/arch/alpha/lib/checksum.c index 8698e0746f9f..199f6efa83fa 100644 --- a/trunk/arch/alpha/lib/checksum.c +++ b/trunk/arch/alpha/lib/checksum.c @@ -5,7 +5,7 @@ * in an architecture-specific manner due to speed.. * Comments in other versions indicate that the algorithms are from RFC1071 * - * accellerated versions (and 21264 assembly versions ) contributed by + * accelerated versions (and 21264 assembly versions ) contributed by * Rick Gorton */ diff --git a/trunk/arch/alpha/lib/csum_partial_copy.c b/trunk/arch/alpha/lib/csum_partial_copy.c index 4ca75c74ce90..40736da9bea8 100644 --- a/trunk/arch/alpha/lib/csum_partial_copy.c +++ b/trunk/arch/alpha/lib/csum_partial_copy.c @@ -2,7 +2,7 @@ * csum_partial_copy - do IP checksumming and copy * * (C) Copyright 1996 Linus Torvalds - * accellerated versions (and 21264 assembly versions ) contributed by + * accelerated versions (and 21264 assembly versions ) contributed by * Rick Gorton * * Don't look at this too closely - you'll go mad. The things diff --git a/trunk/arch/alpha/lib/fls.c b/trunk/arch/alpha/lib/fls.c index 7ad84ea0acf8..32afaa3fa686 100644 --- a/trunk/arch/alpha/lib/fls.c +++ b/trunk/arch/alpha/lib/fls.c @@ -3,7 +3,7 @@ */ #include -#include +#include /* This is fls(x)-1, except zero is held to zero. This allows most efficent input into extbl, plus it allows easy handling of fls(0)=0. */ diff --git a/trunk/arch/alpha/mm/fault.c b/trunk/arch/alpha/mm/fault.c index 25154df3055a..4829f96585b1 100644 --- a/trunk/arch/alpha/mm/fault.c +++ b/trunk/arch/alpha/mm/fault.c @@ -188,13 +188,13 @@ do_page_fault(unsigned long address, unsigned long mmcsr, /* We ran out of memory, or some other thing happened to us that made us unable to handle the page fault gracefully. */ out_of_memory: - if (is_init(current)) { + if (is_global_init(current)) { yield(); down_read(&mm->mmap_sem); goto survive; } printk(KERN_ALERT "VM: killing process %s(%d)\n", - current->comm, current->pid); + current->comm, task_pid_nr(current)); if (!user_mode(regs)) goto no_context; do_group_exit(SIGKILL); diff --git a/trunk/arch/alpha/mm/init.c b/trunk/arch/alpha/mm/init.c index 5e6da47779a4..40c15e7301de 100644 --- a/trunk/arch/alpha/mm/init.c +++ b/trunk/arch/alpha/mm/init.c @@ -235,7 +235,7 @@ callback_init(void * kernel_end) unsigned long pfn = crb->map[i].pa >> PAGE_SHIFT; crb->map[i].va = vaddr; for (j = 0; j < crb->map[i].count; ++j) { - /* Newer console's (especially on larger + /* Newer consoles (especially on larger systems) may require more pages of PTEs. Grab additional pages as needed. */ if (pmd != pmd_offset(pgd, vaddr)) { diff --git a/trunk/arch/alpha/oprofile/Kconfig b/trunk/arch/alpha/oprofile/Kconfig deleted file mode 100644 index 5ade19801b97..000000000000 --- a/trunk/arch/alpha/oprofile/Kconfig +++ /dev/null @@ -1,23 +0,0 @@ - -menu "Profiling support" - depends on EXPERIMENTAL - -config PROFILING - bool "Profiling support (EXPERIMENTAL)" - help - Say Y here to enable the extended profiling support mechanisms used - by profilers such as OProfile. - - -config OPROFILE - tristate "OProfile system profiling (EXPERIMENTAL)" - depends on PROFILING - help - OProfile is a profiling system capable of profiling the - whole system, include the kernel, kernel modules, libraries, - and applications. - - If unsure, say N. - -endmenu - diff --git a/trunk/arch/alpha/oprofile/op_impl.h b/trunk/arch/alpha/oprofile/op_impl.h index 6b97893c1a80..b2b87ae9a353 100644 --- a/trunk/arch/alpha/oprofile/op_impl.h +++ b/trunk/arch/alpha/oprofile/op_impl.h @@ -38,7 +38,7 @@ struct op_register_config { unsigned long need_reset; }; -/* Per-architecture configury and hooks. */ +/* Per-architecture configuration and hooks. */ struct op_axp_model { void (*reg_setup) (struct op_register_config *, struct op_counter_config *, diff --git a/trunk/arch/arm/Kconfig b/trunk/arch/arm/Kconfig index 0a0c88d0039c..a7e9fea978a6 100644 --- a/trunk/arch/arm/Kconfig +++ b/trunk/arch/arm/Kconfig @@ -851,7 +851,7 @@ config KEXEC help kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot - but it is indepedent of the system firmware. And like a reboot + but it is independent of the system firmware. And like a reboot you can start any kernel with it, not just Linux. It is an ongoing process to be certain the hardware in a machine @@ -1040,6 +1040,8 @@ source "drivers/power/Kconfig" source "drivers/hwmon/Kconfig" +source "drivers/watchdog/Kconfig" + source "drivers/ssb/Kconfig" #source "drivers/l3/Kconfig" @@ -1068,7 +1070,7 @@ endmenu source "fs/Kconfig" -source "arch/arm/oprofile/Kconfig" +source "kernel/Kconfig.instrumentation" source "arch/arm/Kconfig.debug" diff --git a/trunk/arch/arm/common/dmabounce.c b/trunk/arch/arm/common/dmabounce.c index 44ab0dad4035..52fc6a883281 100644 --- a/trunk/arch/arm/common/dmabounce.c +++ b/trunk/arch/arm/common/dmabounce.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -442,7 +443,7 @@ dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, BUG_ON(dir == DMA_NONE); for (i = 0; i < nents; i++, sg++) { - struct page *page = sg->page; + struct page *page = sg_page(sg); unsigned int offset = sg->offset; unsigned int length = sg->length; void *ptr = page_address(page) + offset; diff --git a/trunk/arch/arm/common/uengine.c b/trunk/arch/arm/common/uengine.c index 95c8508c29b7..117cab30bd36 100644 --- a/trunk/arch/arm/common/uengine.c +++ b/trunk/arch/arm/common/uengine.c @@ -374,8 +374,8 @@ static int set_initial_registers(int uengine, struct ixp2000_uengine_code *c) u8 *ucode; int i; - gpr_a = kmalloc(128 * sizeof(u32), GFP_KERNEL); - gpr_b = kmalloc(128 * sizeof(u32), GFP_KERNEL); + gpr_a = kzalloc(128 * sizeof(u32), GFP_KERNEL); + gpr_b = kzalloc(128 * sizeof(u32), GFP_KERNEL); ucode = kmalloc(513 * 5, GFP_KERNEL); if (gpr_a == NULL || gpr_b == NULL || ucode == NULL) { kfree(ucode); @@ -388,8 +388,6 @@ static int set_initial_registers(int uengine, struct ixp2000_uengine_code *c) if (c->uengine_parameters & IXP2000_UENGINE_4_CONTEXTS) per_ctx_regs = 32; - memset(gpr_a, 0, sizeof(gpr_a)); - memset(gpr_b, 0, sizeof(gpr_b)); for (i = 0; i < 256; i++) { struct ixp2000_reg_value *r = c->initial_reg_values + i; u32 *bank; diff --git a/trunk/arch/arm/configs/zylonite_defconfig b/trunk/arch/arm/configs/zylonite_defconfig new file mode 100644 index 000000000000..7949d04a3602 --- /dev/null +++ b/trunk/arch/arm/configs/zylonite_defconfig @@ -0,0 +1,736 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.23 +# Tue Oct 23 13:33:20 2007 +# +CONFIG_ARM=y +CONFIG_SYS_SUPPORTS_APM_EMULATION=y +CONFIG_GENERIC_GPIO=y +CONFIG_GENERIC_TIME=y +CONFIG_GENERIC_CLOCKEVENTS=y +CONFIG_MMU=y +# CONFIG_NO_IOPORT is not set +CONFIG_GENERIC_HARDIRQS=y +CONFIG_STACKTRACE_SUPPORT=y +CONFIG_LOCKDEP_SUPPORT=y +CONFIG_TRACE_IRQFLAGS_SUPPORT=y +CONFIG_HARDIRQS_SW_RESEND=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_RWSEM_GENERIC_SPINLOCK=y +# CONFIG_ARCH_HAS_ILOG2_U32 is not set +# CONFIG_ARCH_HAS_ILOG2_U64 is not set +CONFIG_GENERIC_HWEIGHT=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_ZONE_DMA=y +CONFIG_ARCH_MTD_XIP=y +CONFIG_VECTORS_BASE=0xffff0000 +CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" + +# +# General setup +# +CONFIG_EXPERIMENTAL=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_INIT_ENV_ARG_LIMIT=32 +CONFIG_LOCALVERSION="" +CONFIG_LOCALVERSION_AUTO=y +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_SYSVIPC_SYSCTL=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +# CONFIG_TASKSTATS is not set +# CONFIG_USER_NS is not set +# CONFIG_AUDIT is not set +# CONFIG_IKCONFIG is not set +CONFIG_LOG_BUF_SHIFT=18 +# CONFIG_CGROUPS is not set +CONFIG_FAIR_GROUP_SCHED=y +CONFIG_FAIR_USER_SCHED=y +# CONFIG_FAIR_CGROUP_SCHED is not set +CONFIG_SYSFS_DEPRECATED=y +# CONFIG_RELAY is not set +# CONFIG_BLK_DEV_INITRD is not set +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set +CONFIG_SYSCTL=y +# CONFIG_EMBEDDED is not set +CONFIG_UID16=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_HOTPLUG=y +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_ANON_INODES=y +CONFIG_EPOLL=y +CONFIG_SIGNALFD=y +CONFIG_EVENTFD=y +CONFIG_SHMEM=y +CONFIG_VM_EVENT_COUNTERS=y +CONFIG_SLUB_DEBUG=y +# CONFIG_SLAB is not set +CONFIG_SLUB=y +# CONFIG_SLOB is not set +CONFIG_RT_MUTEXES=y +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 +CONFIG_MODULES=y +# CONFIG_MODULE_UNLOAD is not set +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +# CONFIG_KMOD is not set +CONFIG_BLOCK=y +# CONFIG_LBD is not set +# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LSF is not set +# CONFIG_BLK_DEV_BSG is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_DEFAULT_AS is not set +# CONFIG_DEFAULT_DEADLINE is not set +CONFIG_DEFAULT_CFQ=y +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="cfq" + +# +# System Type +# +# CONFIG_ARCH_AAEC2000 is not set +# CONFIG_ARCH_INTEGRATOR is not set +# CONFIG_ARCH_REALVIEW is not set +# CONFIG_ARCH_VERSATILE is not set +# CONFIG_ARCH_AT91 is not set +# CONFIG_ARCH_CLPS7500 is not set +# CONFIG_ARCH_CLPS711X is not set +# CONFIG_ARCH_CO285 is not set +# CONFIG_ARCH_EBSA110 is not set +# CONFIG_ARCH_EP93XX is not set +# CONFIG_ARCH_FOOTBRIDGE is not set +# CONFIG_ARCH_NETX is not set +# CONFIG_ARCH_H720X is not set +# CONFIG_ARCH_IMX is not set +# CONFIG_ARCH_IOP13XX is not set +# CONFIG_ARCH_IOP32X is not set +# CONFIG_ARCH_IOP33X is not set +# CONFIG_ARCH_IXP23XX is not set +# CONFIG_ARCH_IXP2000 is not set +# CONFIG_ARCH_IXP4XX is not set +# CONFIG_ARCH_L7200 is not set +# CONFIG_ARCH_KS8695 is not set +# CONFIG_ARCH_NS9XXX is not set +# CONFIG_ARCH_MXC is not set +# CONFIG_ARCH_PNX4008 is not set +CONFIG_ARCH_PXA=y +# CONFIG_ARCH_RPC is not set +# CONFIG_ARCH_SA1100 is not set +# CONFIG_ARCH_S3C2410 is not set +# CONFIG_ARCH_SHARK is not set +# CONFIG_ARCH_LH7A40X is not set +# CONFIG_ARCH_DAVINCI is not set +# CONFIG_ARCH_OMAP is not set + +# +# Intel PXA2xx/PXA3xx Implementations +# + +# +# Supported PXA3xx Processor Variants +# +CONFIG_CPU_PXA300=y +CONFIG_CPU_PXA310=y +CONFIG_CPU_PXA320=y +# CONFIG_ARCH_LUBBOCK is not set +# CONFIG_MACH_LOGICPD_PXA270 is not set +# CONFIG_MACH_MAINSTONE is not set +# CONFIG_ARCH_PXA_IDP is not set +# CONFIG_PXA_SHARPSL is not set +# CONFIG_MACH_TRIZEPS4 is not set +# CONFIG_MACH_EM_X270 is not set +CONFIG_MACH_ZYLONITE=y +# CONFIG_MACH_ARMCORE is not set +CONFIG_PXA3xx=y + +# +# Boot options +# + +# +# Power management +# + +# +# Processor Type +# +CONFIG_CPU_32=y +CONFIG_CPU_XSC3=y +CONFIG_CPU_32v5=y +CONFIG_CPU_ABRT_EV5T=y +CONFIG_CPU_CACHE_VIVT=y +CONFIG_CPU_TLB_V4WBI=y +CONFIG_CPU_CP15=y +CONFIG_CPU_CP15_MMU=y +CONFIG_IO_36=y + +# +# Processor Features +# +# CONFIG_ARM_THUMB is not set +# CONFIG_CPU_DCACHE_DISABLE is not set +# CONFIG_CPU_BPREDICT_DISABLE is not set +# CONFIG_OUTER_CACHE is not set +CONFIG_IWMMXT=y + +# +# Bus support +# +# CONFIG_PCI_SYSCALL is not set +# CONFIG_ARCH_SUPPORTS_MSI is not set +# CONFIG_PCCARD is not set + +# +# Kernel Features +# +# CONFIG_TICK_ONESHOT is not set +# CONFIG_NO_HZ is not set +# CONFIG_HIGH_RES_TIMERS is not set +CONFIG_GENERIC_CLOCKEVENTS_BUILD=y +# CONFIG_PREEMPT is not set +CONFIG_HZ=100 +CONFIG_AEABI=y +CONFIG_OABI_COMPAT=y +# CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set +CONFIG_FLATMEM=y +CONFIG_FLAT_NODE_MEM_MAP=y +# CONFIG_SPARSEMEM_STATIC is not set +# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set +CONFIG_SPLIT_PTLOCK_CPUS=4096 +# CONFIG_RESOURCES_64BIT is not set +CONFIG_ZONE_DMA_FLAG=1 +CONFIG_BOUNCE=y +CONFIG_VIRT_TO_BUS=y +CONFIG_ALIGNMENT_TRAP=y + +# +# Boot options +# +CONFIG_ZBOOT_ROM_TEXT=0x0 +CONFIG_ZBOOT_ROM_BSS=0x0 +CONFIG_CMDLINE="root=/dev/nfs rootfstype=nfs nfsroot=192.168.1.100:/nfs/rootfs/ ip=192.168.1.101:192.168.1.100::255.255.255.0::eth0:on console=ttyS0,38400 mem=64M debug" +# CONFIG_XIP_KERNEL is not set +# CONFIG_KEXEC is not set + +# +# Floating point emulation +# + +# +# At least one emulation must be selected +# +CONFIG_FPE_NWFPE=y +# CONFIG_FPE_NWFPE_XP is not set +# CONFIG_FPE_FASTFPE is not set + +# +# Userspace binary formats +# +CONFIG_BINFMT_ELF=y +# CONFIG_BINFMT_AOUT is not set +# CONFIG_BINFMT_MISC is not set + +# +# Power management options +# +# CONFIG_PM is not set +CONFIG_SUSPEND_UP_POSSIBLE=y + +# +# Networking +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_FIB_HASH=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set +# CONFIG_INET_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_TRANSPORT is not set +# CONFIG_INET_XFRM_MODE_TUNNEL is not set +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +# CONFIG_INET_DIAG is not set +# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_TCP_CONG_CUBIC=y +CONFIG_DEFAULT_TCP_CONG="cubic" +# CONFIG_TCP_MD5SIG is not set +# CONFIG_IPV6 is not set +# CONFIG_INET6_XFRM_TUNNEL is not set +# CONFIG_INET6_TUNNEL is not set +# CONFIG_NETWORK_SECMARK is not set +# CONFIG_NETFILTER is not set +# CONFIG_IP_DCCP is not set +# CONFIG_IP_SCTP is not set +# CONFIG_TIPC is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set +# CONFIG_NET_SCHED is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_HAMRADIO is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +# CONFIG_AF_RXRPC is not set + +# +# Wireless +# +# CONFIG_CFG80211 is not set +# CONFIG_WIRELESS_EXT is not set +# CONFIG_MAC80211 is not set +# CONFIG_IEEE80211 is not set +# CONFIG_RFKILL is not set +# CONFIG_NET_9P is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +CONFIG_FW_LOADER=y +# CONFIG_SYS_HYPERVISOR is not set +# CONFIG_CONNECTOR is not set +# CONFIG_MTD is not set +# CONFIG_PARPORT is not set +# CONFIG_BLK_DEV is not set +# CONFIG_MISC_DEVICES is not set +# CONFIG_IDE is not set + +# +# SCSI device support +# +# CONFIG_RAID_ATTRS is not set +# CONFIG_SCSI is not set +# CONFIG_SCSI_DMA is not set +# CONFIG_SCSI_NETLINK is not set +# CONFIG_ATA is not set +# CONFIG_MD is not set +CONFIG_NETDEVICES=y +# CONFIG_NETDEVICES_MULTIQUEUE is not set +# CONFIG_DUMMY is not set +# CONFIG_BONDING is not set +# CONFIG_MACVLAN is not set +# CONFIG_EQUALIZER is not set +# CONFIG_TUN is not set +# CONFIG_VETH is not set +# CONFIG_PHYLIB is not set +CONFIG_NET_ETHERNET=y +CONFIG_MII=y +# CONFIG_AX88796 is not set +CONFIG_SMC91X=y +# CONFIG_DM9000 is not set +# CONFIG_SMC911X is not set +# CONFIG_IBM_NEW_EMAC_ZMII is not set +# CONFIG_IBM_NEW_EMAC_RGMII is not set +# CONFIG_IBM_NEW_EMAC_TAH is not set +# CONFIG_IBM_NEW_EMAC_EMAC4 is not set +# CONFIG_B44 is not set +# CONFIG_NETDEV_1000 is not set +# CONFIG_NETDEV_10000 is not set + +# +# Wireless LAN +# +# CONFIG_WLAN_PRE80211 is not set +# CONFIG_WLAN_80211 is not set +# CONFIG_WAN is not set +# CONFIG_PPP is not set +# CONFIG_SLIP is not set +# CONFIG_SHAPER is not set +# CONFIG_NETCONSOLE is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set +# CONFIG_ISDN is not set + +# +# Input device support +# +CONFIG_INPUT=y +# CONFIG_INPUT_FF_MEMLESS is not set +# CONFIG_INPUT_POLLDEV is not set + +# +# Userland interfaces +# +CONFIG_INPUT_MOUSEDEV=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 +# CONFIG_INPUT_JOYDEV is not set +# CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TABLET is not set +# CONFIG_INPUT_TOUCHSCREEN is not set +# CONFIG_INPUT_MISC is not set + +# +# Hardware I/O ports +# +# CONFIG_SERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +CONFIG_VT=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +# CONFIG_VT_HW_CONSOLE_BINDING is not set +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +# CONFIG_SERIAL_8250 is not set + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_PXA=y +CONFIG_SERIAL_PXA_CONSOLE=y +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +CONFIG_UNIX98_PTYS=y +# CONFIG_LEGACY_PTYS is not set +# CONFIG_IPMI_HANDLER is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_NVRAM is not set +# CONFIG_R3964 is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_TCG_TPM is not set +# CONFIG_I2C is not set + +# +# SPI support +# +# CONFIG_SPI is not set +# CONFIG_SPI_MASTER is not set +# CONFIG_W1 is not set +# CONFIG_POWER_SUPPLY is not set +# CONFIG_HWMON is not set + +# +# Sonics Silicon Backplane +# +CONFIG_SSB_POSSIBLE=y +# CONFIG_SSB is not set + +# +# Multifunction device drivers +# +# CONFIG_MFD_SM501 is not set + +# +# Multimedia devices +# +# CONFIG_VIDEO_DEV is not set +# CONFIG_DVB_CORE is not set +# CONFIG_DAB is not set + +# +# Graphics support +# +# CONFIG_VGASTATE is not set +# CONFIG_VIDEO_OUTPUT_CONTROL is not set +CONFIG_FB=y +# CONFIG_FIRMWARE_EDID is not set +# CONFIG_FB_DDC is not set +CONFIG_FB_CFB_FILLRECT=y +CONFIG_FB_CFB_COPYAREA=y +CONFIG_FB_CFB_IMAGEBLIT=y +# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set +# CONFIG_FB_SYS_FILLRECT is not set +# CONFIG_FB_SYS_COPYAREA is not set +# CONFIG_FB_SYS_IMAGEBLIT is not set +# CONFIG_FB_SYS_FOPS is not set +CONFIG_FB_DEFERRED_IO=y +# CONFIG_FB_SVGALIB is not set +# CONFIG_FB_MACMODES is not set +# CONFIG_FB_BACKLIGHT is not set +# CONFIG_FB_MODE_HELPERS is not set +# CONFIG_FB_TILEBLITTING is not set + +# +# Frame buffer hardware drivers +# +# CONFIG_FB_S1D13XXX is not set +CONFIG_FB_PXA=y +# CONFIG_FB_PXA_PARAMETERS is not set +# CONFIG_FB_MBX is not set +# CONFIG_FB_VIRTUAL is not set +# CONFIG_BACKLIGHT_LCD_SUPPORT is not set + +# +# Display device support +# +# CONFIG_DISPLAY_SUPPORT is not set + +# +# Console display driver support +# +# CONFIG_VGA_CONSOLE is not set +CONFIG_DUMMY_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y +# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set +CONFIG_FONTS=y +# CONFIG_FONT_8x8 is not set +# CONFIG_FONT_8x16 is not set +CONFIG_FONT_6x11=y +# CONFIG_FONT_7x14 is not set +# CONFIG_FONT_PEARL_8x8 is not set +# CONFIG_FONT_ACORN_8x8 is not set +# CONFIG_FONT_MINI_4x6 is not set +# CONFIG_FONT_SUN8x16 is not set +# CONFIG_FONT_SUN12x22 is not set +# CONFIG_FONT_10x18 is not set +CONFIG_LOGO=y +CONFIG_LOGO_LINUX_MONO=y +CONFIG_LOGO_LINUX_VGA16=y +CONFIG_LOGO_LINUX_CLUT224=y + +# +# Sound +# +# CONFIG_SOUND is not set +# CONFIG_HID_SUPPORT is not set +# CONFIG_USB_SUPPORT is not set +# CONFIG_MMC is not set +# CONFIG_NEW_LEDS is not set +CONFIG_RTC_LIB=y +# CONFIG_RTC_CLASS is not set + +# +# File systems +# +# CONFIG_EXT2_FS is not set +# CONFIG_EXT3_FS is not set +# CONFIG_EXT4DEV_FS is not set +# CONFIG_REISERFS_FS is not set +# CONFIG_JFS_FS is not set +CONFIG_FS_POSIX_ACL=y +# CONFIG_XFS_FS is not set +# CONFIG_GFS2_FS is not set +# CONFIG_OCFS2_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_INOTIFY is not set +# CONFIG_QUOTA is not set +CONFIG_DNOTIFY=y +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set + +# +# CD-ROM/DVD Filesystems +# +# CONFIG_ISO9660_FS is not set +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +# CONFIG_MSDOS_FS is not set +# CONFIG_VFAT_FS is not set +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_SYSCTL=y +CONFIG_SYSFS=y +# CONFIG_TMPFS is not set +# CONFIG_HUGETLB_PAGE is not set +# CONFIG_CONFIGFS_FS is not set + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +# CONFIG_CRAMFS is not set +# CONFIG_VXFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set +CONFIG_NETWORK_FILESYSTEMS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +CONFIG_NFS_V3_ACL=y +CONFIG_NFS_V4=y +CONFIG_NFS_DIRECTIO=y +# CONFIG_NFSD is not set +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_NFS_ACL_SUPPORT=y +CONFIG_NFS_COMMON=y +CONFIG_SUNRPC=y +CONFIG_SUNRPC_GSS=y +# CONFIG_SUNRPC_BIND34 is not set +CONFIG_RPCSEC_GSS_KRB5=y +# CONFIG_RPCSEC_GSS_SPKM3 is not set +# CONFIG_SMB_FS is not set +# CONFIG_CIFS is not set +# CONFIG_NCP_FS is not set +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y +# CONFIG_NLS is not set +# CONFIG_DLM is not set +# CONFIG_INSTRUMENTATION is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_ENABLE_MUST_CHECK=y +# CONFIG_MAGIC_SYSRQ is not set +# CONFIG_UNUSED_SYMBOLS is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_HEADERS_CHECK is not set +# CONFIG_DEBUG_KERNEL is not set +# CONFIG_SLUB_DEBUG_ON is not set +CONFIG_DEBUG_BUGVERBOSE=y +CONFIG_FRAME_POINTER=y +# CONFIG_SAMPLES is not set +CONFIG_DEBUG_USER=y + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set +# CONFIG_SECURITY_FILE_CAPABILITIES is not set +CONFIG_CRYPTO=y +CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_MANAGER=y +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_XCBC is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_WP512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_ECB is not set +CONFIG_CRYPTO_CBC=y +# CONFIG_CRYPTO_PCBC is not set +# CONFIG_CRYPTO_LRW is not set +# CONFIG_CRYPTO_XTS is not set +# CONFIG_CRYPTO_CRYPTD is not set +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_TEST is not set +# CONFIG_CRYPTO_AUTHENC is not set +# CONFIG_CRYPTO_HW is not set + +# +# Library routines +# +CONFIG_BITREVERSE=y +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +# CONFIG_CRC_ITU_T is not set +CONFIG_CRC32=y +# CONFIG_CRC7 is not set +# CONFIG_LIBCRC32C is not set +CONFIG_PLIST=y +CONFIG_HAS_IOMEM=y +CONFIG_HAS_IOPORT=y +CONFIG_HAS_DMA=y diff --git a/trunk/arch/arm/kernel/entry-armv.S b/trunk/arch/arm/kernel/entry-armv.S index d645897652c2..29dec080a604 100644 --- a/trunk/arch/arm/kernel/entry-armv.S +++ b/trunk/arch/arm/kernel/entry-armv.S @@ -339,16 +339,6 @@ __pabt_svc: str r1, [sp] @ save the "real" r0 copied @ from the exception stack -#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) -#ifndef CONFIG_MMU -#warning "NPTL on non MMU needs fixing" -#else - @ make sure our user space atomic helper is aborted - cmp r2, #TASK_SIZE - bichs r3, r3, #PSR_Z_BIT -#endif -#endif - @ @ We are now ready to fill in the remaining blanks on the stack: @ @@ -372,9 +362,25 @@ __pabt_svc: zero_fp .endm + .macro kuser_cmpxchg_check +#if __LINUX_ARM_ARCH__ < 6 && !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG) +#ifndef CONFIG_MMU +#warning "NPTL on non MMU needs fixing" +#else + @ Make sure our user space atomic helper is restarted + @ if it was interrupted in a critical region. Here we + @ perform a quick test inline since it should be false + @ 99.9999% of the time. The rest is done out of line. + cmp r2, #TASK_SIZE + blhs kuser_cmpxchg_fixup +#endif +#endif + .endm + .align 5 __dabt_usr: usr_entry + kuser_cmpxchg_check @ @ Call the processor-specific abort handler: @@ -404,6 +410,7 @@ __dabt_usr: .align 5 __irq_usr: usr_entry + kuser_cmpxchg_check #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off @@ -446,9 +453,9 @@ __und_usr: @ @ r0 - instruction @ -1: ldrt r0, [r4] adr r9, ret_from_exception adr lr, __und_usr_unknown +1: ldrt r0, [r4] @ @ fallthrough to call_fpe @ @@ -669,7 +676,7 @@ __kuser_helper_start: * * Clobbered: * - * the Z flag might be lost + * none * * Definition and user space usage example: * @@ -730,9 +737,6 @@ __kuser_memory_barrier: @ 0xffff0fa0 * * - This routine already includes memory barriers as needed. * - * - A failure might be transient, i.e. it is possible, although unlikely, - * that "failure" be returned even if *ptr == oldval. - * * For example, a user space atomic_add implementation could look like this: * * #define atomic_add(ptr, val) \ @@ -769,46 +773,62 @@ __kuser_cmpxchg: @ 0xffff0fc0 #elif __LINUX_ARM_ARCH__ < 6 +#ifdef CONFIG_MMU + /* - * Theory of operation: - * - * We set the Z flag before loading oldval. If ever an exception - * occurs we can not be sure the loaded value will still be the same - * when the exception returns, therefore the user exception handler - * will clear the Z flag whenever the interrupted user code was - * actually from the kernel address space (see the usr_entry macro). - * - * The post-increment on the str is used to prevent a race with an - * exception happening just after the str instruction which would - * clear the Z flag although the exchange was done. + * The only thing that can break atomicity in this cmpxchg + * implementation is either an IRQ or a data abort exception + * causing another process/thread to be scheduled in the middle + * of the critical sequence. To prevent this, code is added to + * the IRQ and data abort exception handlers to set the pc back + * to the beginning of the critical section if it is found to be + * within that critical section (see kuser_cmpxchg_fixup). */ -#ifdef CONFIG_MMU - teq ip, ip @ set Z flag - ldr ip, [r2] @ load current val - add r3, r2, #1 @ prepare store ptr - teqeq ip, r0 @ compare with oldval if still allowed - streq r1, [r3, #-1]! @ store newval if still allowed - subs r0, r2, r3 @ if r2 == r3 the str occured +1: ldr r3, [r2] @ load current val + subs r3, r3, r0 @ compare with oldval +2: streq r1, [r2] @ store newval if eq + rsbs r0, r3, #0 @ set return val and C flag + usr_ret lr + + .text +kuser_cmpxchg_fixup: + @ Called from kuser_cmpxchg_check macro. + @ r2 = address of interrupted insn (must be preserved). + @ sp = saved regs. r7 and r8 are clobbered. + @ 1b = first critical insn, 2b = last critical insn. + @ If r2 >= 1b and r2 <= 2b then saved pc_usr is set to 1b. + mov r7, #0xffff0fff + sub r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg))) + subs r8, r2, r7 + rsbcss r8, r8, #(2b - 1b) + strcs r7, [sp, #S_PC] + mov pc, lr + .previous + #else #warning "NPTL on non MMU needs fixing" mov r0, #-1 adds r0, r0, #0 -#endif usr_ret lr +#endif #else #ifdef CONFIG_SMP mcr p15, 0, r0, c7, c10, 5 @ dmb #endif - ldrex r3, [r2] +1: ldrex r3, [r2] subs r3, r3, r0 strexeq r3, r1, [r2] + teqeq r3, #1 + beq 1b rsbs r0, r3, #0 + /* beware -- each __kuser slot must be 8 instructions max */ #ifdef CONFIG_SMP - mcr p15, 0, r0, c7, c10, 5 @ dmb -#endif + b __kuser_memory_barrier +#else usr_ret lr +#endif #endif @@ -829,7 +849,7 @@ __kuser_cmpxchg: @ 0xffff0fc0 * * Clobbered: * - * the Z flag might be lost + * none * * Definition and user space usage example: * diff --git a/trunk/arch/arm/kernel/process.c b/trunk/arch/arm/kernel/process.c index 93b7f8e22dcc..4f1a03124a74 100644 --- a/trunk/arch/arm/kernel/process.c +++ b/trunk/arch/arm/kernel/process.c @@ -265,7 +265,7 @@ void __show_regs(struct pt_regs *regs) void show_regs(struct pt_regs * regs) { printk("\n"); - printk("Pid: %d, comm: %20s\n", current->pid, current->comm); + printk("Pid: %d, comm: %20s\n", task_pid_nr(current), current->comm); __show_regs(regs); __backtrace(); } diff --git a/trunk/arch/arm/kernel/ptrace.c b/trunk/arch/arm/kernel/ptrace.c index 5feee722ea98..4b05dc5c1023 100644 --- a/trunk/arch/arm/kernel/ptrace.c +++ b/trunk/arch/arm/kernel/ptrace.c @@ -382,16 +382,16 @@ static void clear_breakpoint(struct task_struct *task, struct debug_entry *bp) if (ret != 2 || old_insn.thumb != BREAKINST_THUMB) printk(KERN_ERR "%s:%d: corrupted Thumb breakpoint at " - "0x%08lx (0x%04x)\n", task->comm, task->pid, - addr, old_insn.thumb); + "0x%08lx (0x%04x)\n", task->comm, + task_pid_nr(task), addr, old_insn.thumb); } else { ret = swap_insn(task, addr & ~3, &old_insn.arm, &bp->insn.arm, 4); if (ret != 4 || old_insn.arm != BREAKINST_ARM) printk(KERN_ERR "%s:%d: corrupted ARM breakpoint at " - "0x%08lx (0x%08x)\n", task->comm, task->pid, - addr, old_insn.arm); + "0x%08lx (0x%08x)\n", task->comm, + task_pid_nr(task), addr, old_insn.arm); } } diff --git a/trunk/arch/arm/kernel/traps.c b/trunk/arch/arm/kernel/traps.c index 8ad47619c079..c34db4e868fa 100644 --- a/trunk/arch/arm/kernel/traps.c +++ b/trunk/arch/arm/kernel/traps.c @@ -223,7 +223,7 @@ static void __die(const char *str, int err, struct thread_info *thread, struct p print_modules(); __show_regs(regs); printk("Process %s (pid: %d, stack limit = 0x%p)\n", - tsk->comm, tsk->pid, thread + 1); + tsk->comm, task_pid_nr(tsk), thread + 1); if (!user_mode(regs) || in_interrupt()) { dump_mem("Stack: ", regs->ARM_sp, @@ -327,7 +327,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if ((instr & hook->instr_mask) == hook->instr_val && (regs->ARM_cpsr & hook->cpsr_mask) == hook->cpsr_val) { if (hook->fn(regs, instr) == 0) { - spin_unlock_irq(&undef_lock); + spin_unlock_irqrestore(&undef_lock, flags); return; } } @@ -337,7 +337,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_UNDEFINED) { printk(KERN_INFO "%s (%d): undefined instruction: pc=%p\n", - current->comm, current->pid, pc); + current->comm, task_pid_nr(current), pc); dump_instr(regs); } #endif @@ -388,7 +388,7 @@ static int bad_syscall(int n, struct pt_regs *regs) #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_SYSCALL) { printk(KERN_ERR "[%d] %s: obsolete system call %08x.\n", - current->pid, current->comm, n); + task_pid_nr(current), current->comm, n); dump_instr(regs); } #endif @@ -509,7 +509,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) * existence. Don't ever use this from user code. */ case 0xfff0: - { + for (;;) { extern void do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs); unsigned long val; @@ -545,7 +545,6 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) up_read(&mm->mmap_sem); /* simulate a write access fault */ do_DataAbort(addr, 15 + (1 << 11), regs); - return -1; } #endif @@ -565,7 +564,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs) */ if (user_debug & UDBG_SYSCALL) { printk("[%d] %s: arm syscall %d\n", - current->pid, current->comm, no); + task_pid_nr(current), current->comm, no); dump_instr(regs); if (user_mode(regs)) { __show_regs(regs); @@ -642,7 +641,7 @@ baddataabort(int code, unsigned long instr, struct pt_regs *regs) #ifdef CONFIG_DEBUG_USER if (user_debug & UDBG_BADABORT) { printk(KERN_ERR "[%d] %s: bad data abort: code %d instr 0x%08lx\n", - current->pid, current->comm, code, instr); + task_pid_nr(current), current->comm, code, instr); dump_instr(regs); show_pte(current->mm, addr); } diff --git a/trunk/arch/arm/mach-at91/at91rm9200_devices.c b/trunk/arch/arm/mach-at91/at91rm9200_devices.c index 0417c165d50d..9296833f91cc 100644 --- a/trunk/arch/arm/mach-at91/at91rm9200_devices.c +++ b/trunk/arch/arm/mach-at91/at91rm9200_devices.c @@ -14,6 +14,7 @@ #include #include +#include #include #include @@ -435,7 +436,40 @@ void __init at91_add_device_nand(struct at91_nand_data *data) {} * TWI (i2c) * -------------------------------------------------------------------- */ -#if defined(CONFIG_I2C_AT91) || defined(CONFIG_I2C_AT91_MODULE) +/* + * Prefer the GPIO code since the TWI controller isn't robust + * (gets overruns and underruns under load) and can only issue + * repeated STARTs in one scenario (the driver doesn't yet handle them). + */ +#if defined(CONFIG_I2C_GPIO) || defined(CONFIG_I2C_GPIO_MODULE) + +static struct i2c_gpio_platform_data pdata = { + .sda_pin = AT91_PIN_PA25, + .sda_is_open_drain = 1, + .scl_pin = AT91_PIN_PA26, + .scl_is_open_drain = 1, + .udelay = 2, /* ~100 kHz */ +}; + +static struct platform_device at91rm9200_twi_device = { + .name = "i2c-gpio", + .id = -1, + .dev.platform_data = &pdata, +}; + +void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) +{ + at91_set_GPIO_periph(AT91_PIN_PA25, 1); /* TWD (SDA) */ + at91_set_multi_drive(AT91_PIN_PA25, 1); + + at91_set_GPIO_periph(AT91_PIN_PA26, 1); /* TWCK (SCL) */ + at91_set_multi_drive(AT91_PIN_PA26, 1); + + i2c_register_board_info(0, devices, nr_devices); + platform_device_register(&at91rm9200_twi_device); +} + +#elif defined(CONFIG_I2C_AT91) || defined(CONFIG_I2C_AT91_MODULE) static struct resource twi_resources[] = { [0] = { @@ -457,7 +491,7 @@ static struct platform_device at91rm9200_twi_device = { .num_resources = ARRAY_SIZE(twi_resources), }; -void __init at91_add_device_i2c(void) +void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) { /* pins used for TWI interface */ at91_set_A_periph(AT91_PIN_PA25, 0); /* TWD */ @@ -466,10 +500,11 @@ void __init at91_add_device_i2c(void) at91_set_A_periph(AT91_PIN_PA26, 0); /* TWCK */ at91_set_multi_drive(AT91_PIN_PA26, 1); + i2c_register_board_info(0, devices, nr_devices); platform_device_register(&at91rm9200_twi_device); } #else -void __init at91_add_device_i2c(void) {} +void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) {} #endif diff --git a/trunk/arch/arm/mach-at91/at91sam9260_devices.c b/trunk/arch/arm/mach-at91/at91sam9260_devices.c index ffd3154c1e54..3091bf47d8c9 100644 --- a/trunk/arch/arm/mach-at91/at91sam9260_devices.c +++ b/trunk/arch/arm/mach-at91/at91sam9260_devices.c @@ -13,6 +13,7 @@ #include #include +#include #include #include @@ -352,7 +353,41 @@ void __init at91_add_device_nand(struct at91_nand_data *data) {} * TWI (i2c) * -------------------------------------------------------------------- */ -#if defined(CONFIG_I2C_AT91) || defined(CONFIG_I2C_AT91_MODULE) +/* + * Prefer the GPIO code since the TWI controller isn't robust + * (gets overruns and underruns under load) and can only issue + * repeated STARTs in one scenario (the driver doesn't yet handle them). + */ + +#if defined(CONFIG_I2C_GPIO) || defined(CONFIG_I2C_GPIO_MODULE) + +static struct i2c_gpio_platform_data pdata = { + .sda_pin = AT91_PIN_PA23, + .sda_is_open_drain = 1, + .scl_pin = AT91_PIN_PA24, + .scl_is_open_drain = 1, + .udelay = 2, /* ~100 kHz */ +}; + +static struct platform_device at91sam9260_twi_device = { + .name = "i2c-gpio", + .id = -1, + .dev.platform_data = &pdata, +}; + +void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) +{ + at91_set_GPIO_periph(AT91_PIN_PA23, 1); /* TWD (SDA) */ + at91_set_multi_drive(AT91_PIN_PA23, 1); + + at91_set_GPIO_periph(AT91_PIN_PA24, 1); /* TWCK (SCL) */ + at91_set_multi_drive(AT91_PIN_PA24, 1); + + i2c_register_board_info(0, devices, nr_devices); + platform_device_register(&at91sam9260_twi_device); +} + +#elif defined(CONFIG_I2C_AT91) || defined(CONFIG_I2C_AT91_MODULE) static struct resource twi_resources[] = { [0] = { @@ -374,7 +409,7 @@ static struct platform_device at91sam9260_twi_device = { .num_resources = ARRAY_SIZE(twi_resources), }; -void __init at91_add_device_i2c(void) +void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) { /* pins used for TWI interface */ at91_set_A_periph(AT91_PIN_PA23, 0); /* TWD */ @@ -383,10 +418,11 @@ void __init at91_add_device_i2c(void) at91_set_A_periph(AT91_PIN_PA24, 0); /* TWCK */ at91_set_multi_drive(AT91_PIN_PA24, 1); + i2c_register_board_info(0, devices, nr_devices); platform_device_register(&at91sam9260_twi_device); } #else -void __init at91_add_device_i2c(void) {} +void __init at91_add_device_i2c(struct i2c_board_info *devices, int nr_devices) {} #endif diff --git a/trunk/arch/arm/mach-at91/at91sam9261_devices.c b/trunk/arch/arm/mach-at91/at91sam9261_devices.c index 3576595b4941..64979a9023c2 100644 --- a/trunk/arch/arm/mach-at91/at91sam9261_devices.c +++ b/trunk/arch/arm/mach-at91/at91sam9261_devices.c @@ -14,7 +14,9 @@ #include #include +#include +#include #include