aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAge
* Merge git://git.infradead.org/~dhowells/irq-2.6Linus Torvalds2006-10-05
|\ | | | | | | | | | | | | * git://git.infradead.org/~dhowells/irq-2.6: IRQ: Maintain regs pointer globally rather than passing to IRQ handlers IRQ: Typedef the IRQ handler function type IRQ: Typedef the IRQ flow handler function type
| * IRQ: Maintain regs pointer globally rather than passing to IRQ handlersDavid Howells2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
| * IRQ: Typedef the IRQ handler function typeDavid Howells2006-10-05
| | | | | | | | | | | | | | Typedef the IRQ handler function type. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1356d1e5fd256997e3d3dce0777ab787d0515c7a commit)
| * IRQ: Typedef the IRQ flow handler function typeDavid Howells2006-10-05
| | | | | | | | | | | | | | Typedef the IRQ flow handler function type. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 8e973fbdf5716b93a0a8c0365be33a31ca0fa351 commit)
* | [PATCH] UDF: Fix mounting read-writePeter Osterlund2006-10-05
| | | | | | | | | | | | | | | | | | The UDF filesystem can't be mounted in read-write mode any more, because of forgotten braces. Signed-off-by: Peter Osterlund <petero2@telia.com> [ Duh! ] Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] x86-64: Fix compilation without CONFIG_KALLSYMSRandy Dunlap2006-10-05
| | | | | | | | | | | | | | | | Include linux/kallsyms.h unconditionally for print_symbol(). Signed-off-by: Randy Dunlap <rdunlap@xenotime.net> Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6Linus Torvalds2006-10-05
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: [PATCH] i386: fix rwsem build bug on CONFIG_M386=y [PATCH] x86-64: Annotate interrupt frame backlink in interrupt handlers [PATCH] x86-64: Fix FPU corruption [PATCH] x86: Terminate the kernel stacks for the unwinder [PATCH] i386: Fix PCI BIOS config space access [PATCH] x86-64: Calgary IOMMU: print PCI bus numbers in hex [PATCH] x86-64: Calgary IOMMU: Update Jon's contact info [PATCH] x86-64: Calgary IOMMU: Fix off by one when calculating register space location [PATCH] x86-64: Calgary IOMMU: deobfuscate calgary_init [PATCH] i386: Update defconfig [PATCH] x86-64: Update defconfig [ Manually skipped commits that incorrectly ignored AC in kernel space. The alignment fault is defined to only happen for CPL3 anyway - Linus ]
| * | [PATCH] i386: fix rwsem build bug on CONFIG_M386=yIngo Molnar2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | CONFIG_M386 turns on spinlock-based generic rwsems - which surprises the semaphore.S rwsem stubs. Tested both with and without CONFIG_M386. Reported-by: Klaus Knopper <knopper@knopper.net> Triaged-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Annotate interrupt frame backlink in interrupt handlersAndi Kleen2006-10-05
| | | | | | | | | | | | | | | | | | Add correct CFI annotation to the backlink on top of the interrupt stack. Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Fix FPU corruptionAndi Kleen2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts an earlier patch that was found to cause FPU state corruption. I think the corruption happens because unlazy_fpu() can cause FPU exceptions and when it happens after the current switch some processing would affect the state in the wrong process. Thanks to Douglas Crosher and Tom Hughes for testing. Cc: jbeulich@novell.com Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86: Terminate the kernel stacks for the unwinderAndi Kleen2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Always make sure RIP/EIP is 0 in the registers stored on the top of the stack of a kernel thread. This makes sure the unwinder code won't try a fallback but knows the stack has ended. AK: this patch is a bit mysterious. in theory they should be terminated anyways, but it seems to fix at least one crash. Anyways double termination probably doesn't hurt. Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] i386: Fix PCI BIOS config space accessAndi Kleen2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Got broken by a earlier change. Also add a printk when no pci config method could be found. Cc: gregkh@suse.de Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Calgary IOMMU: print PCI bus numbers in hexJon Mason2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | Make the references to the bus number in hex instead of decimal, as that is the way that lspci prints out the bus numbers. Signed-off-by: Jon Mason <jdmason@kudzu.us> Signed-off-by: Muli Ben-Yehuda <muli@il.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Calgary IOMMU: Update Jon's contact infoJon Mason2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | Also add copyright for work done after leaving IBM. Signed-off-by: Jon Mason <jdmason@kudzu.us> Signed-off-by: Muli Ben-Yehuda <muli@il.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Calgary IOMMU: Fix off by one when calculating register ↵Jon Mason2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | space location The purpose of the code being modified is to determine the location of the calgary chip address space. This is done by a magical formula of FE0MB-8MB*OneBasedChassisNumber+1MB*(RioNodeId-ChassisBase) to find the offset where BIOS puts it. In this formula, OneBasedChassisNumber corresponds to the NUMA node, and rionodeid is always 2 or 3 depending on which chip in the system it is. The problem was that we had an off by one error that caused us to account some busses to the wrong chip and thus give them the wrong address space. Fixes RH bugzilla #203971. Signed-off-by: Jon Mason <jdmason@kudzu.us> Signed-off-bu: Muli Ben-Yehuda <muli@il.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Calgary IOMMU: deobfuscate calgary_initJon Mason2006-10-05
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | calgary_init's for loop does not correspond to the actual device being checked, which makes its upperbound check for array overflow useless. Changing this to a do-while loop is the correct way of doing this. There should be no possibility of spinning forever in this loop, as pci_get_device states that it will go through all iterations, then return NULL (thus breaking the loop). Signed-off-by: Jon Mason <jdmason@kudzu.us> Signed-off-by: Muli Ben-Yehuda <muli@il.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] i386: Update defconfigAndi Kleen2006-10-05
| | | | | | | | | | | | Signed-off-by: Andi Kleen <ak@suse.de>
| * | [PATCH] x86-64: Update defconfigAndi Kleen2006-10-05
| |/ | | | | | | Signed-off-by: Andi Kleen <ak@suse.de>
* / [PATCH] fix qla{2,4} build errorFrederik Deweerdt2006-10-05
|/ | | | | | | | | | | | | | | | | | | | | | | commit 0181944fe647cae18d545ac1167df3d15d393701 adds a 'extended_error_logging' global variable to qla2xxx which is defined by qla4xxx too. Trying to build both drivers results in the following error: LD drivers/scsi/built-in.o drivers/scsi/qla4xxx/built-in.o: In function `qla4xxx_slave_configure': drivers/scsi/qla4xxx/ql4_os.c:1433: multiple definition of `extended_error_logging' drivers/scsi/qla2xxx/built-in.o:drivers/scsi/qla2xxx/qla_os.c:2166: first defined here make[2]: *** [drivers/scsi/built-in.o] Error 1 make[1]: *** [drivers/scsi] Error 2 make: *** [drivers] Error 2 The following patch simply adds a qla2_ (qla4_ respectively) prefix to the variable name. Signed-off-by: Frederik Deweerdt <frederik.deweerdt@gmail.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Linux 2.6.19-rc1v2.6.19-rc1Linus Torvalds2006-10-04
| | | | Merge window closed..
* [PATCH] itmtouch: fix inverted flag to indicate touch location correctly, ↵Mark Assad2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | correct white space There is a bug in the current version of the itmtouch USB touchscreen driver. The if statment that checks if pressure is being applied to the touch screen is now missing a ! (not), so events are no longer being reported correctly. The original source code for this line was as follows: #define UCP(x) ((unsigned char*)(x)) #define UCOM(x,y,z) ((UCP((x)->transfer_buffer)[y]) & (z)) ... if (!UCOM(urb, 7, 0x20)) { And was cleaned to: unsigned char *data = urb->transfer_buffer; .... if (data[7] & 0x20) { (note the lack of '!') This has been tested on an LG L1510BF and an LG1510SF touch screen. Signed-off-by: Mark Assad <massad@gmail.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge master.kernel.org:/pub/scm/linux/kernel/git/willy/parisc-2.6Linus Torvalds2006-10-04
|\ | | | | | | | | | | | | | | | | | | | | * master.kernel.org:/pub/scm/linux/kernel/git/willy/parisc-2.6: [PA-RISC] Fix time.c for new do_timer() calling convention [PA-RISC] Fix must_check warnings in drivers.c [PA-RISC] Fix parisc_newuname() [PA-RISC] Remove warning from pci.c [PA-RISC] Fix filldir warnings [PA-RISC] Fix sys32_sysctl [PA-RISC] Fix sba_iommu compilation
| * [PA-RISC] Fix time.c for new do_timer() calling conventionMatthew Wilcox2006-10-04
| | | | | | | | | | | | | | | | | | do_timer now wants to know how many ticks have elapsed. Now that we have to calculate that, we can eliminate some of the clever code that avoided having to calculate that. Also add some more documentation. I'd like to thank Grant Grundler for helping me with this. Signed-off-by: Matthew Wilcox <willy@parisc-linux.org>
| * [PA-RISC] Fix must_check warnings in drivers.cMatthew Wilcox2006-10-04
| | | | | | | | | | | | | | | | | | Panic if we can't register the parisc bus or the root parisc device. There's no way we can boot without them, so let the user know ASAP. If we can't register a parisc device, handle the failure gracefully. Signed-off-by: Matthew Wilcox <willy@parisc-linux.org>
| * [PA-RISC] Fix parisc_newuname()Matthew Wilcox2006-10-04
| | | | | | | | | | | | | | The utsname virtualisation broke parisc_newuname compilation. Rewrite the implementation to call sys_newuname() like sparc64 does. Signed-off-by: Matthew Wilcox <willy@parisc-linux.org>
| * [PA-RISC] Remove warning from pci.cMatthew Wilcox2006-10-04
| | | | | | | | | | | | | | max() doesn't like comparing an unsigned long and a resource_size_t, so make the local variables resource_size_t too. Signed-off-by: Matthew Wilcox <willy@parisc-linux.org>
| * [PA-RISC] Fix filldir warningsMatthew Wilcox2006-10-04
| | | | | | | | | | | | filldir_t now takes a u64, not an ino_t. Signed-off-by: Matthew Wilcox <matthew@wil.cx>
| * [PA-RISC] Fix sys32_sysctlMatthew Wilcox2006-10-04
| | | | | | | | | | | | | | | | When CONFIG_SYSCTL_SYSCALL isn't defined, do_sysctl doesn't exist and we fail to link. Fix with an ifdef, the same way sparc64 did. Also add some minor changes to be more like sparc64. Signed-off-by: Matthew Wilcox <matthew@wil.cx>
| * [PA-RISC] Fix sba_iommu compilationMatthew Wilcox2006-10-04
| | | | | | | | | | | | | | klist_iter_exit() only takes one parameter. Also fix warning by adding additional brackets. Signed-off-by: Matthew Wilcox <matthew@wil.cx>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpcLinus Torvalds2006-10-04
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: [POWERPC] cell: fix bugs found by sparse [POWERPC] spiderpic: enable new style devtree support [POWERPC] Update cell_defconfig [POWERPC] spufs: add infrastructure for finding elf objects [POWERPC] spufs: support new OF device tree format [POWERPC] spufs: add support for read/write on cntl [POWERPC] spufs: remove support for ancient firmware [POWERPC] spufs: make mailbox functions handle multiple elements [POWERPC] spufs: use correct pg_prot for mapping SPU local store [POWERPC] spufs: Add infrastructure needed for gang scheduling [POWERPC] spufs: implement error event delivery to user space [POWERPC] spufs: fix context switch during page fault [POWERPC] spufs: scheduler support for NUMA. [POWERPC] spufs: cell spu problem state mapping updates
| * | [POWERPC] cell: fix bugs found by sparseArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - Some long constants should be marked 'ul'. - When using desc->handler_data to pass an __iomem register area, we need to add casts to and from __iomem. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spiderpic: enable new style devtree supportArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | This enables support for new firmware test releases. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] Update cell_defconfigArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | This adds defaults for new configuration options added since 2.6.18 and it enables the option for 64kb pages by default. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: add infrastructure for finding elf objectsArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This adds an 'object-id' file that the spe library can use to store a pointer to its ELF object. This was originally meant for use by oprofile, but is now also used by the GNU debugger, if available. In order for oprofile to find the location in an spu-elf binary where an event counter triggered, we need a way to identify the binary in the first place. Unfortunately, that binary itself can be embedded in a powerpc ELF binary. Since we can assume it is mapped into the effective address space of the running process, have that one write the pointer value into a new spufs file. When a context switch occurs, pass the user value to the profiler so that can look at the mapped file (with some care). Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: support new OF device tree formatArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The properties we used traditionally in the device tree are somewhat nonstandard. This adds support for a more conventional format using 'interrupts' and 'reg' properties. The interrupts are specified in three cells (class 0, 1 and 2) and registered at the interrupt-parent. The reg property contains either three or four register areas in the order 'local-store', 'problem', 'priv2', and 'priv1', so the priv1 one can be left out in case of hypervisor driven systems that access these through hcalls. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: add support for read/write on cntlArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Writing to cntl can be used to stop execution on the spu and to restart it, reading from cntl gives the contents of the current status register. The access is always in ascii, as for most other files. This was always meant to be there, but we had a little problem with writing to runctl so it was left out so far. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: remove support for ancient firmwareArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | Any firmware that still uses the 'spc' nodes already stopped running for other reasons, so let's get rid of this. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: make mailbox functions handle multiple elementsArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Since libspe2 will provide a function that can read/write multiple mailbox elements at once, the kernel should handle that efficiently. read/write on the three mailbox files can now access the spe context multiple times to operate on any number of mailbox data elements. If the spu application keeps writing to its outbound mailbox, the read call will pick up all the data in a single system call. Unfortunately, if the user passes an invalid pointer, we may lose a mailbox element on read, since we can't put it back. This probably impossible to solve, if the user also accesses the mailbox through direct register access. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: use correct pg_prot for mapping SPU local storeArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This hopefully fixes a long-standing bug in the spu file system. An spu context comes with local memory that can be either saved in kernel pages or point directly to a physical SPE. When mapping the physical SPE, that mapping needs to be cache-inhibited. For simplicity, we used to map the kernel backing memory that way too, but unfortunately that was not only inefficient, but also incorrect because the same page could then be accessed simultaneously through a cacheable and a cache-inhibited mapping, which is not allowed by the powerpc specification and in our case caused data inconsistency for which we did a really ugly workaround in user space. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: Add infrastructure needed for gang schedulingArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add the concept of a gang to spufs as a new type of object. So far, this has no impact whatsover on scheduling, but makes it possible to add that later. A new type of object in spufs is now a spu_gang. It is created with the spu_create system call with the flags argument set to SPU_CREATE_GANG (0x2). Inside of a spu_gang, it is then possible to create spu_context objects, which until now was only possible at the root of spufs. There is a new member in struct spu_context pointing to the spu_gang it belongs to, if any. The spu_gang maintains a list of spu_context structures that are its children. This information can then be used in the scheduler in the future. There is still a bug that needs to be resolved in this basic infrastructure regarding the order in which objects are removed. When the spu_gang file descriptor is closed before the spu_context descriptors, we leak the dentry and inode for the gang. Any ideas how to cleanly solve this are appreciated. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: implement error event delivery to user spaceArnd Bergmann2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This tries to fix spufs so we have an interface closer to what is specified in the man page for events returned in the third argument of spu_run. Fortunately, libspe has never been using the returned contents of that register, as they were the same as the return code of spu_run (duh!). Unlike the specification that we never implemented correctly, we now require a SPU_CREATE_EVENTS_ENABLED flag passed to spu_create, in order to get the new behavior. When this flag is not passed, spu_run will simply ignore the third argument now. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: fix context switch during page faultHyeonSeung Jang2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | For better explanation, I break down the page fault handling into steps: 1) There is a page fault caused by DMA operation initiated by SPU and DMA is suspended. 2) The interrupt handler 'spu_irq_class_1()/__spu_trap_data_map()' is called and it just wakes up the sleeping spe-manager thread. 3) by PPE scheduler, the corresponding bottom half, spu_irq_class_1_bottom() is called in process context and DMA is restarted. There can be a quite large time gap between 2) and 3) and I found the following problem: Between 2) and 3) If the context becomes unbound, 3) is not executed because when the spe-manager thread is awaken, the context is already saved. (This situation can happen, for example, when a high priority spe thread newly started in that time gap) But the actual problem is that the corresponding SPU context does not work even if it is bound again to a SPU. Besides I can see the following warning in mambo simulator when the context becomes unbound(in save_mfc_cmd()), i.e. when unbind() is called for the context after step 2) before 3) : 'WARNING: 61392752237: SPE2: MFC_CMD_QUEUE channel count of 15 is inconsistent with number of available DMA queue entries of 16' After I go through available documents, I found that the problem is because the suspended DMA is not restarted when it is bound again. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: scheduler support for NUMA.Mark Nutter2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds NUMA support to the the spufs scheduler. The new arch/powerpc/platforms/cell/spufs/sched.c is greatly simplified, in an attempt to reduce complexity while adding support for NUMA scheduler domains. SPUs are allocated starting from the calling thread's node, moving to others as supported by current->cpus_allowed. Preemption is gone as it was buggy, but should be re-enabled in another patch when stable. The new arch/powerpc/platforms/cell/spu_base.c maintains idle lists on a per-node basis, and allows caller to specify which node(s) an SPU should be allocated from, while passing -1 tells spu_alloc() that any node is allowed. Since the patch removes the currently implemented preemptive scheduling, it is technically a regression, but practically all users have since migrated to this version, as it is part of the IBM SDK and the yellowdog distribution, so there is not much point holding it back while the new preemptive scheduling patch gets delayed further. Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * | [POWERPC] spufs: cell spu problem state mapping updatesBenjamin Herrenschmidt2006-10-04
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds a new "psmap" file to spufs that allows mmap of all of the problem state mapping of SPEs. It is compatible with 64k pages. In addition, it removes mmap ability of individual files when using 64k pages, with the exception of signal1 and signal2 which will both map the entire 64k page holding both registers. It also removes CONFIG_SPUFS_MMAP as there is no point in not building mmap support in spufs. It goes along a separate patch to libspe implementing usage of that new file to access problem state registers. Another patch will follow up to fix races opened up by accessing the 'runcntl' register directly, which is made possible with this patch. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | Merge master.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6Linus Torvalds2006-10-04
|\ \ | |/ |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * master.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6: (54 commits) [SCSI] Initial Commit of qla4xxx [SCSI] raid class: handle component-add errors [SCSI] SCSI megaraid_sas: handle thrown errors [SCSI] SCSI aic94xx: handle sysfs errors [SCSI] SCSI st: fix error handling in module init, sysfs [SCSI] SCSI sd: fix module init/exit error handling [SCSI] SCSI osst: add error handling to module init, sysfs [SCSI] scsi: remove hosts.h [SCSI] scsi: Scsi_Cmnd convertion in aic7xxx_old.c [SCSI] megaraid_sas: sets ioctl timeout and updates version,changelog [SCSI] megaraid_sas: adds tasklet for cmd completion [SCSI] megaraid_sas: prints pending cmds before setting hw_crit_error [SCSI] megaraid_sas: function pointer for disable interrupt [SCSI] megaraid_sas: frame count optimization [SCSI] megaraid_sas: FW transition and q size changes [SCSI] qla2xxx: Update version number to 8.01.07-k2. [SCSI] qla2xxx: Stall mid-layer error handlers while rport is blocked. [SCSI] qla2xxx: Add MODULE_FIRMWARE tags. [SCSI] qla2xxx: Add support for host port state FC transport attribute. [SCSI] qla2xxx: Add support for fabric name FC transport attribute. ...
| * [SCSI] Initial Commit of qla4xxxDavid Somayajulu2006-10-04
| | | | | | | | | | | | | | | | | | | | open-iSCSI driver for Qlogic Corporation's iSCSI HBAs Signed-off-by: Ravi Anand <ravi.anand@qlogic.com> Signed-off-by: David Somayajulu <david.somayajulu@qlogic.com> Signed-off-by: Doug Maxey <dwm@bubba.enoyolf.org> Signed-off-by: Mike Christie <michaelc@cs.wisc.edu> Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
| * [SCSI] raid class: handle component-add errorsJeff Garzik2006-10-04
| | | | | | | | | | Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
| * [SCSI] SCSI megaraid_sas: handle thrown errorsJeff Garzik2006-10-04
| | | | | | | | | | | | | | | | | | | | | | | | | | | | - handle clear_user() error - handle and properly unwind from sysfs errors thrown during mod init - adjust order of calls in megasas_exit() to precisely match registration order in megasas_init() Signed-off-by: Jeff Garzik <jeff@garzik.org> Updated for extra attribute and Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
| * [SCSI] SCSI aic94xx: handle sysfs errorsJeff Garzik2006-10-04
| | | | | | | | | | | | | | Handle and unwind from errors returned by driver model functions. Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
| * [SCSI] SCSI st: fix error handling in module init, sysfsJeff Garzik2006-10-04
| | | | | | | | | | | | | | | | | | | | | | - Notice and handle sysfs errors in module init, tape init - Properly unwind errors in module init - Remove bogus st_sysfs_class==NULL test, it is guaranteed !NULL at that point Signed-off-by: Jeff Garzik <jeff@garzik.org> Signed-off-by: James Bottomley <James.Bottomley@SteelEye.com>
generated by cgit v1.2.2 (git 2.25.0) at 2024-12-29 10:29:59 -0500