aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2010-02-28virtio: fix out of range array accessMichael S. Tsirkin
I have observed the following error on virtio-net module unload: ------------[ cut here ]------------ WARNING: at kernel/irq/manage.c:858 __free_irq+0xa0/0x14c() Hardware name: Bochs Trying to free already-free IRQ 0 Modules linked in: virtio_net(-) virtio_blk virtio_pci virtio_ring virtio af_packet e1000 shpchp aacraid uhci_hcd ohci_hcd ehci_hcd [last unloaded: scsi_wait_scan] Pid: 1957, comm: rmmod Not tainted 2.6.33-rc8-vhost #24 Call Trace: [<ffffffff8103e195>] warn_slowpath_common+0x7c/0x94 [<ffffffff8103e204>] warn_slowpath_fmt+0x41/0x43 [<ffffffff810a7a36>] ? __free_pages+0x5a/0x70 [<ffffffff8107cc00>] __free_irq+0xa0/0x14c [<ffffffff8107cceb>] free_irq+0x3f/0x65 [<ffffffffa0081424>] vp_del_vqs+0x81/0xb1 [virtio_pci] [<ffffffffa0091d29>] virtnet_remove+0xda/0x10b [virtio_net] [<ffffffffa0075200>] virtio_dev_remove+0x22/0x4a [virtio] [<ffffffff812709ee>] __device_release_driver+0x66/0xac [<ffffffff81270ab7>] driver_detach+0x83/0xa9 [<ffffffff8126fc66>] bus_remove_driver+0x91/0xb4 [<ffffffff81270fcf>] driver_unregister+0x6c/0x74 [<ffffffffa0075418>] unregister_virtio_driver+0xe/0x10 [virtio] [<ffffffffa0091c4d>] fini+0x15/0x17 [virtio_net] [<ffffffff8106997b>] sys_delete_module+0x1c3/0x230 [<ffffffff81007465>] ? old_ich_force_enable_hpet+0x117/0x164 [<ffffffff813bb720>] ? do_page_fault+0x29c/0x2cc [<ffffffff81028e58>] sysenter_dispatch+0x7/0x27 ---[ end trace 15e88e4c576cc62b ]--- The bug is in virtio-pci: we use msix_vector as array index to get irq entry, but some vqs do not have a dedicated vector so this causes an out of bounds access. By chance, we seem to often get 0 value, which results in this error. Fix by verifying that vector is legal before using it as index. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Anthony Liguori <aliguori@us.ibm.com> Acked-by: Shirley Ma <xma@us.ibm.com> Acked-by: Amit Shah <amit.shah@redhat.com>
2010-02-27Merge branch 'for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k: (24 commits) m68k: Define sigcontext ABI of ColdFire m68knommu: NPTL support for uClinux m68k: Add NPTL support m68k: Eliminate unused variable in page_to_phys() m68k: Switch to generic siginfo layout macfb: fix 24-bit visual and stuff macfb: cleanup fbdev: add some missing mac modes mac68k: start CUDA early valkyriefb: various fixes fbdev: mac_var_to_mode() fix mac68k: move macsonic and macmace platform devices mac68k: move mac_esp platform device mac68k: replace mac68k SCC code with platform device pmac-zilog: add platform driver pmac-zilog: cleanup mac68k: rework SWIM platform device mac68k: cleanup ataflop: Killl warning about unused variable flags m68k: Use DIV_ROUND_CLOSEST ...
2010-02-27Merge branch 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6Linus Torvalds
* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (35 commits) [S390] time: remove unused code [S390] zcore: Add prefix registers to dump header [S390] correct vdso version string [S390] add support for compressed kernels [S390] Define new s390 ELF note sections in elf.h [S390] codepage conversion of kernel parameter line [S390] seq_file: convert drivers/s390/ [S390] add z9-ec/z10 instruction to kernel disassembler [S390] dasd: correct offline processing [S390] dasd: fix refcounting. [S390] dasd: fix online/offline race [S390] use kprobes_built_in() in mm/fault code [S390] bug: use relative pointers in bug table entries [S390] Cleanup struct _lowcore usage and defines. [S390] free_initmem: reduce code duplication [S390] Replace ENOTSUPP usage with EOPNOTSUPP [S390] spinlock: check virtual cpu running status [S390] sysinfo: fix SYSIB 3,2,2 structure [S390] add MACHINE_IS_LPAR flag [S390] qdio: optimize cache line usage of struct qdio_irq ...
2010-02-27Merge branch 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linusLinus Torvalds
* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus: (141 commits) MIPS: Alchemy: defconfig updates MIPS: Alchemy: Fix Au1100 ethernet build failure MIPS: Alchemy: Repair db1500/bosporus builds MIPS: ARC: Cleanup unused definitions from sgialib.h MIPS: Cobalt: convert legacy port addresses to GT-64111 bus addresses MIPS: Alchemy: use 36bit addresses for PCMCIA resources. MIPS: Cobalt: Fix theoretical port aliasing issue MIPS: Use ALIGN(x, bytes) instead of __ALIGN_MASK(x, bytes - 1) MIPS: Crazy spinlock speed test. MIPS: Optimize spinlocks. MIPS: Alchemy: devboard PM needs to save CPLD registers. MIPS: PowerTV: Eliminate duplicate opcode definition macros MIPS: Lemote 2F: Move printks out of port_access_lock. MIPS: PNX833x: Convert IRQ controller locks to raw spinlocks. MIPS: Octeon: Replace spinlock with raw_spinlocks in dma-octeon.c. MIPS: Octeon: Replace rwlocks in irq_chip handlers with raw_spinlocks. MIPS: Octeon: Convert octeon_irq_msi_lock to raw spinlock. MIPS: Loongson: Remove pointless sample_lock from oprofile code. MIPS: SNI: Convert sni_rm200_i8259A_lock to raw spinlock. MIPS: i8259: Convert IRQ controller lock to raw spinlock. ...
2010-02-27Merge git://git.kernel.org/pub/scm/linux/kernel/git/brodo/pcmcia-2.6Linus Torvalds
* git://git.kernel.org/pub/scm/linux/kernel/git/brodo/pcmcia-2.6: (49 commits) pcmcia: validate late-added resources pcmcia: allow for extension of resource interval pcmcia: remove useless msleep in ds.c pcmcia: use read_cis_mem return value pcmcia: handle error in serial_cs config calls pcmcia: add locking to pcmcia_{read,write}_cis_mem pcmcia: avoid prod_id memleak pcmcia: avoid sysfs-related lockup for cardbus pcmcia: use state machine for extended requery pcmcia: delay re-scanning and re-querying of PCMCIA bus pcmcia: use pccardd to handle eject, insert, suspend and resume requests pcmcia: use ops_mutex for rsrc_{mgr,nonstatic} locking pcmcia: use mutex for dynid lock pcmcia: assert locking to struct pcmcia_device pcmcia: add locking documentation pcmcia: simplify locking pcmcia: add locking to struct pcmcia_socket->pcmcia_state() pcmcia: protect s->device_count pcmcia: properly lock skt->irq, skt->irq_mask pcmcia: lock ops->set_socket ...
2010-02-27Merge branch 'next' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (88 commits) powerpc: Fix lwsync feature fixup vs. modules on 64-bit powerpc: Convert pmc_owner_lock to raw_spinlock powerpc: Convert die.lock to raw_spinlock powerpc: Convert tlbivax_lock to raw_spinlock powerpc: Convert mpic locks to raw_spinlock powerpc: Convert pmac_pic_lock to raw_spinlock powerpc: Convert big_irq_lock to raw_spinlock powerpc: Convert feature_lock to raw_spinlock powerpc: Convert i8259_lock to raw_spinlock powerpc: Convert beat_htab_lock to raw_spinlock powerpc: Convert confirm_error_lock to raw_spinlock powerpc: Convert ipic_lock to raw_spinlock powerpc: Convert native_tlbie_lock to raw_spinlock powerpc: Convert beatic_irq_mask_lock to raw_spinlock powerpc: Convert nv_lock to raw_spinlock powerpc: Convert context_lock to raw_spinlock powerpc/85xx: Add NOR, LEDs and PIB support for MPC8568E-MDS boards powerpc/86xx: Enable VME driver on the GE SBC610 powerpc/86xx: Enable VME driver on the GE PPC9A powerpc/86xx: Add MSI section to GE PPC9A DTS ...
2010-02-27m68k: Define sigcontext ABI of ColdFireMaxim Kuvyrkov
The following patch defines sigcontext ABI of ColdFire. Due to ISA restrictions ColdFire needs different rt_sigreturn trampoline. And due to ColdFire FP registers being 8-bytes instead of 12-bytes on m68k, sigcontext and fpregset structures should be updated. Regarding the sc_fpstate[16+6*8] field, it would've been enough 16 bytes to store ColdFire's FP state. To accomodate GLIBC's libSegFault it would'be been enough 6*8 bytes (room for the 6 non-call-clobbered FP registers). I set it to 16+6*8 to provide some extra space for any future changes in the ColdFire FPU. Signed-off-by: Maxim Kuvyrkov <maxim@codesourcery.com> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68knommu: NPTL support for uClinuxMaxim Kuvyrkov
Port syscalls for NPTL support to m68knommu. Signed-off-by: Maxim Kuvyrkov <maxim@codesourcery.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: Add NPTL supportMaxim Kuvyrkov
This patch adds several syscalls, that provide necessary functionality to support NPTL on m68k/ColdFire. The syscalls are get_thread_area, set_thread_area, atomic_cmpxchg_32 and atomic_barrier. The cmpxchg syscall is required for ColdFire as it doesn't support 'cas' instruction. Also a ptrace call PTRACE_GET_THREAD_AREA is added to allow debugger to inspect the TLS storage. Signed-off-by: Maxim Kuvyrkov <maxim@codesourcery.com> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: Eliminate unused variable in page_to_phys()Geert Uytterhoeven
"pgdat" is unused, so we can eliminate it and turn page_to_phys() into a single-line macro. Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: Switch to generic siginfo layoutMaxim Kuvyrkov
This patch switches m68k to generic siginfo layout. The custom layout of m68k's `struct siginfo' had several issues due to not considering aliasing of members in the union, e.g., _uid32 was at different offsets in ._kill, ._rt and ._sigchld. Signed-off-by: Maxim Kuvyrkov <maxim@codesourcery.com> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27macfb: fix 24-bit visual and stuffFinn Thain
Lots of changes. Remove volatile keywords. Take the advice in the comments and change video_slot to slot_addr. Factor out fifteen or so "channel >> 8" shifts into three shifts higher up the call graph. Make csc_setpalette() atomic, pass the correct color values. Check for ioremap() failure. Add missing break statement, thus fixing 24 bit console visual (blue background bug). Remove some uninformative printk() noise. Add a description for powerbook 140/170 graphics. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27macfb: cleanupFinn Thain
Cleanup whitespace and code style. Remove unused #includes and prototypes. Remove obsolete, redundant or misleading comments. Remove dead code and redundant initialisers. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27fbdev: add some missing mac modesFinn Thain
Add the missing mac video modes for the Portrait and 12" RGB displays. The specs come from the Mac LC III developer note. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27mac68k: start CUDA earlyFinn Thain
The valkyriefb driver needs the CUDA to work in order to set the video mode at boot. So initialise the device earlier, and bring the m68k code closer to the powermac code. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27valkyriefb: various fixesFinn Thain
Valkyriefb and macfb will adopt the same card if they get the chance, so remove valkyrie support from macfb. Also fix the "valkyriefb: can't do 832x624x8" problem reported by Raylynn Knight some time ago, by adding vmode 13 support for CONFIG_MAC. Also add vmode 11 since that works too. Make use of the monitor sense lines on 68k Macs too. Also some cleanups. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27fbdev: mac_var_to_mode() fixFinn Thain
The valkyriefb driver assumes that this logic holds: mac_vmode_to_var(X, cmode, &var); mac_var_to_vmode(&var, &vmode, &cmode); assert(vmode == X); But it doesn't hold because mac_var_to_vmode() can return a mode with a slower pixel clock, even when a match is available. So we end up with this failure: using video mode 11 and color mode 0. valkyriefb: vmode 12 not valid. valkyriefb: can't set default video mode valkyriefb: vmode 12 not valid. Rather than have mac_var_to_mode() return the first reasonable mode it finds, have it return the mode that is closest to the requested one (or the mode with the closest longer pixel clock period if there is no exact match). Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27mac68k: move macsonic and macmace platform devicesFinn Thain
Move platform device code from the drivers to the platform init function. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27mac68k: move mac_esp platform deviceFinn Thain
Move platform device code from the driver to the platform init function. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27mac68k: replace mac68k SCC code with platform deviceFinn Thain
Remove the old 68k Mac serial port code and a lot of related cruft. Add new SCC platform devices to mac 68k platform. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27pmac-zilog: add platform driverFinn Thain
Add platform driver support to the pmac-zilog driver, for m68k macs. Place the powermac-specific code inside #ifdef CONFIG_PPC_PMAC. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27pmac-zilog: cleanupFinn Thain
Whitespace cleanups and comment typo fix. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27mac68k: rework SWIM platform deviceFinn Thain
Adjust the platform device code to conform with the code style used in the rest of this patch series. No need to name resources nor to register devices which are not applicable. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27mac68k: cleanupFinn Thain
Cleanup whitespace and comments. Remove some dead code. Signed-off-by: Finn Thain <fthain@telegraphics.com.au> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27ataflop: Killl warning about unused variable flagsGeert Uytterhoeven
After commit e0c0978699a83f26f2341f7eedc1463b79e31aff ("ataflop: remove buggy/commented-out IRQ disable from do_fd_request()") the `flags' variable became unused: drivers/block/ataflop.c:1473: warning: unused variable 'flags' Hence remove it. Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: Use DIV_ROUND_CLOSESTJulia Lawall
The kernel.h macro DIV_ROUND_CLOSEST performs the computation (x + d/2)/d but is perhaps more readable. The semantic patch that makes this change is as follows: (http://www.emn.fr/x-info/coccinelle/) // <smpl> @haskernel@ @@ @depends on haskernel@ expression x,__divisor; @@ - (((x) + ((__divisor) / 2)) / (__divisor)) + DIV_ROUND_CLOSEST(x,__divisor) // </smpl> Signed-off-by: Julia Lawall <julia@diku.dk> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: vme_scc - __init annotationsPeter Huewe
Trivial patch which adds the __init macro to the module_init function and all of its helper functions of drivers/char/vme_scc.c Signed-off-by: Peter Huewe <peterhuewe@gmx.de> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k{,nommu}/h8300: Remove obsolete comment about map_chunkPhilippe De Muyter
Remove the comments referring to a function map_chunk that no longer exists. Signed-off-by: Philippe De Muyter <phdm@macqel.be> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: Allow ioremapping top of memoryPhilippe De Muyter
The test in __ioremap to reject memory ranges crossing the 0 boundary rejects also memory ranges ending at the end of the memory. Fix that. Signed-off-by: Philippe De Muyter <phdm@macqel.be> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27m68k: Fix asm/swab.h for ColdFireMaxim Kuvyrkov
Make asm/swab.h compatible with ColdFire ISA_B CPUs. Signed-off-by: Maxim Kuvyrkov <maxim@codesourcery.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
2010-02-27MIPS: Alchemy: defconfig updatesManuel Lauss
Updated, leaner defconfig for the alchemy development boards. Signed-off-by: Manuel Lauss <manuel.lauss@gmail.com> To: Linux-MIPS <linux-mips@linux-mips.org> Patchwork: http://patchwork.linux-mips.org/patch/1005/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Alchemy: Fix Au1100 ethernet build failureManuel Lauss
Don't define platform info for second mac on au1100 (which only has a single mac). Signed-off-by: Manuel Lauss <manuel.lauss@gmail.com> To: Linux-MIPS <linux-mips@linux-mips.org> Patchwork: http://patchwork.linux-mips.org/patch/1004/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Alchemy: Repair db1500/bosporus buildsManuel Lauss
A few hunks somehow ended up outside their #ifdef/endif blocks, leading to -Werror-induces build failures. Signed-off-by: Manuel Lauss <manuel.lauss@gmail.com> To: Linux-MIPS <linux-mips@linux-mips.org> Patchwork: http://patchwork.linux-mips.org/patch/1003/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: ARC: Cleanup unused definitions from sgialib.hYoichi Yuasa
Signed-off-by: Yoichi Yuasa <yuasa@linux-mips.org> Cc: linux-mips <linux-mips@linux-mips.org> Patchwork: http://patchwork.linux-mips.org/patch/979/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Cobalt: convert legacy port addresses to GT-64111 bus addressesBjorn Helgaas
The GT-64111 PCI host bridge has no address translation mechanism, so it can't generate legacy port accesses. This quirk fixes legacy device port resources to contain the bus addresses actually generated by the GT-64111. I think this is the approach Ben Herrenschmidt suggested long ago: http://marc.info/?l=linux-kernel&m=119733290624544&w=2 This allows us to remove the IORESOURCE_PCI_FIXED hack from pcibios_fixup_device_resources(), which converts bus addresses to CPU addresses. IORESOURCE_PCI_FIXED denotes resources that can't be moved; it has nothing to do with converting bus to CPU addresses. Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com> Cc: Yoichi Yuasa <yuasa@linux-mips.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: linux-mips@linux-mips.org Tested-by: Yoichi Yuasa <yuasa@linux-mips.org> Patchwork: http://patchwork.linux-mips.org/patch/998/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Alchemy: use 36bit addresses for PCMCIA resources.Manuel Lauss
On Alchemy the PCMCIA area lies at the end of the chips 36bit system bus area. Currently, addresses at the far end of the 32bit area are assumed to belong to the PCMCIA area and fixed up to the real 36bit address before being passed to ioremap(). A previous commit enabled 64 bit physical size for the resource datatype on Alchemy and this allows to use the correct 36bit addresses when registering the PCMCIA sockets. This patch removes the 32-to-36bit address fixup and registers the Alchemy demo board pcmcia socket with the correct 36bit physical addresses. Tested on DB1200, with a CF card (ide-cs driver) and a 3c589 PCMCIA ethernet card. Signed-off-by: Manuel Lauss <manuel.lauss@gmail.com> To: Linux-MIPS <linux-mips@linux-mips.org> Cc: Manuel Lauss <manuel.lauss@gmail.com> Patchwork: http://patchwork.linux-mips.org/patch/994/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Cobalt: Fix theoretical port aliasing issueRalf Baechle
Because the VIA SuperIO chip only decodes 24 bits of address space but port address space currently being configured as 32MB there is the theoretical possibility of aliases within the I/O port address range. The complicated solution is to reserve all address range that potencially could cause such aliases. But with the PCI spec limiting port allocations for devices to a maximum of 256 bytes 16MB of port address space already is way more than one would ever expect to be used so we just reduce the port space to 16MB. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> To: Yoichi Yuasa <yuasa@linux-mips.org> Cc: Bjorn Helgaas <bjorn.helgaas@hp.com> Cc: linux-mips@linux-mips.org Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Patchwork: http://patchwork.linux-mips.org/patch/995/
2010-02-27MIPS: Use ALIGN(x, bytes) instead of __ALIGN_MASK(x, bytes - 1)Matt Turner
ALIGN(x, bytes) expands to __ALIGN_MASK(x, bytes - 1), so use the one that is most clear. Signed-off-by: Matt Turner <mattst88@gmail.com> To: linux-mips@linux-mips.org Cc: David Daney <ddaney@caviumnetworks.com> Patchwork: http://patchwork.linux-mips.org/patch/999/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Crazy spinlock speed test.David Daney
This is just a test program for raw_spinlocks. The main reason I wrote it is to validate my spinlock changes that I sent in a previous patch. To use it enable CONFIG_DEBUG_FS and CONFIG_SPINLOCK_TEST then at run time do: # mount -t debugfs none /sys/kernel/debug/ # cat /sys/kernel/debug/mips/spin_single # cat /sys/kernel/debug/mips/spin_multi On my 600MHz octeon cn5860 (16 CPUs) I get spin_single spin_multi base 106885 247941 spinlock_patch 75194 219465 This shows that for uncontended locks the spinlock patch gives 41% improvement and for contended locks 12% improvement (1/time). Signed-off-by: David Daney <ddaney@caviumnetworks.com> To: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/969/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Optimize spinlocks.David Daney
The current locking mechanism uses a ll/sc sequence to release a spinlock. This is slower than a wmb() followed by a store to unlock. The branching forward to .subsection 2 on sc failure slows down the contended case. So we get rid of that part too. Since we are now working on naturally aligned u16 values, we can get rid of a masking operation as the LHU already does the right thing. The ANDI are reversed for better scheduling on multi-issue CPUs On a 12 CPU 750MHz Octeon cn5750 this patch improves ipv4 UDP packet forwarding rates from 3.58*10^6 PPS to 3.99*10^6 PPS, or about 11%. Signed-off-by: David Daney <ddaney@caviumnetworks.com> To: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/937/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Alchemy: devboard PM needs to save CPLD registers.Manuel Lauss
Save/restore CPLD registers when doing suspend-to-ram; this fixes issues with harddisk and ethernet not working correctly when resuming on DB1200. Signed-off-by: Manuel Lauss <manuel.lauss@gmail.com> To: Linux-MIPS <linux-mips@linux-mips.org> Patchwork: http://patchwork.linux-mips.org/patch/986/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: PowerTV: Eliminate duplicate opcode definition macrosDavid VomLehn
Change to different macros for assembler macros since the old names in powertv_setup.c were co-opted for use in asm/asm.h. This broken the build for the powertv platform. This patch introduces new macros based on the new macros in asm.h to take the place of the old macro values. Signed-off-by: David VomLehn <dvomlehn@cisco.com> Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/985/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Lemote 2F: Move printks out of port_access_lock.Ralf Baechle
No point in protecting them and printks are sloow. Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: PNX833x: Convert IRQ controller locks to raw spinlocks.Ralf Baechle
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Octeon: Replace spinlock with raw_spinlocks in dma-octeon.c.David Daney
Signed-off-by: David Daney <ddaney@caviumnetworks.com> Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/973/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Octeon: Replace rwlocks in irq_chip handlers with raw_spinlocks.David Daney
Signed-off-by: David Daney <ddaney@caviumnetworks.com> Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/972/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Octeon: Convert octeon_irq_msi_lock to raw spinlock.Ralf Baechle
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: Loongson: Remove pointless sample_lock from oprofile code.Ralf Baechle
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: SNI: Convert sni_rm200_i8259A_lock to raw spinlock.Ralf Baechle
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
2010-02-27MIPS: i8259: Convert IRQ controller lock to raw spinlock.Ralf Baechle
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-07 08:33:41 +0000