ChangeSet@1.1603.1.47, 2004-02-10 21:13:54-08:00, davidm@tiger.hpl.hp.com ia64: Correct init_task.rbs_bot value (not that it matters). ChangeSet@1.1603.1.46, 2004-02-10 21:08:10-08:00, davidm@tiger.hpl.hp.com ia64: Update defconfig ChangeSet@1.1603.1.45, 2004-02-10 18:59:35-08:00, davidm@tiger.hpl.hp.com ia64: Fix some more warnings caused by casts used as l-values. ChangeSet@1.1603.1.44, 2004-02-10 18:51:34-08:00, davidm@tiger.hpl.hp.com ia64: Based on patch by Stephane Eranian: Make fpswa version info available via /proc/efi/fpswa, rather than printing it at boot time. ChangeSet@1.1603.10.1, 2004-02-11 12:17:29+11:00, hch@sgi.com [XFS] make sure i_size_write is called under i_sem SGI Modid: xfs-linux:xfs-kern:166504a ChangeSet@1.1603.1.43, 2004-02-10 15:37:14-08:00, kaos@ocs.com.au [PATCH] ia64: Periodically forward MCA or INIT records to user-level Periodically check for outstanding MCA or INIT records and pass them to user space salinfo. ChangeSet@1.1603.1.42, 2004-02-10 15:32:28-08:00, kaos@ocs.com.au [PATCH] ia64: mca.c - Fix the "did we recover from MCA test" and move it up Correct the "did we recover from MCA test" and move it up a level to simplify interaction with debuggers. ChangeSet@1.1603.1.41, 2004-02-10 15:20:28-08:00, kenneth.w.chen@intel.com [PATCH] ia64: remove unused cpucount variable ChangeSet@1.1603.9.2, 2004-02-10 15:17:40-08:00, jun.nakajima@intel.com [PATCH] Remove the assumption that the number of the sibling is 2 Thanks to Nick's domain patch, the kernel worked fine with smp_num_siblings = 4 (in simulation). ChangeSet@1.1603.1.40, 2004-02-10 14:54:01-08:00, kaos@sgi.com [PATCH] ia64: mca.c - pass irq_safe around Patches from Ben Woodward to calculate irq_safe once and pass it around. ChangeSet@1.1603.1.39, 2004-02-10 14:14:47-08:00, kaos@sgi.com [PATCH] ia64: mca.c cleanup - Bjorn's printk cleanup ChangeSet@1.1603.1.38, 2004-02-10 14:14:04-08:00, kaos@sgi.com [PATCH] ia64: mca.c cleanup - Reorder to remove the need for forward declarations and to consolidate related code ChangeSet@1.1603.1.37, 2004-02-10 14:13:21-08:00, kaos@sgi.com [PATCH] ia64: mca.c cleanup - Delete dead variables and functions ChangeSet@1.1603.1.36, 2004-02-10 14:12:30-08:00, kaos@sgi.com [PATCH] ia64: mca.c cleanup - Mark variables and functions static where possible ChangeSet@1.1603.1.35, 2004-02-10 14:11:58-08:00, kaos@sgi.com [PATCH] ia64: mca.c cleanup - Delete all record printing code, moved to salinfo_decode in user space ChangeSet@1.1603.1.34, 2004-02-10 14:11:17-08:00, kaos@sgi.com [PATCH] ia64: Avoid deadlock when using printk() for MCA and INIT records Port the ia64 mca.c clean up patches from 2.4.25-pre8 to 2.6.2-rc2. The following 6 patches do :- 1 Avoid deadlock when using printk() for MCA and INIT records. 2 Delete all record printing code, moved to salinfo_decode in user space. 3 Mark variables and functions static where possible. 4 Delete dead variables and functions. 5 Reorder to remove the need for forward declarations and to consolidate related code. 6 Bjorn's printk cleanup. Altogether they shrink mca.c from 2432 to 1339 lines and make it much more readable. The only functional change is the removal of any attempt to print the CMC/CPE/MCA/INIT record contents in the kernel plus the addition of an info printk to ia64_mca_check_errors(), to match 2.4. Now we just get one line to say that a record has been detected, except for MCA which prints nothing at all. ChangeSet@1.1603.1.33, 2004-02-10 13:45:36-08:00, alex.williamson@hp.com [PATCH] ia64: sba_iommu perf tunning and new functionality I've been doing some performance tuning and adding some functionality to sba_iommu for zx1/sx1000 chipsets. This adds: * Long overdue consistent_dma_mask support * Long overdue ability to do large mappings in the iommu * Tightened spinlock usage for better performance/scalability * Added branch prediction hints for some of the performance paths * Added explicit data prefetching to some performance paths - perfmon shows roughly a 20% decrease in L3 misses in the bitmap search code * Increased delayed resource freeing depth and added a separate lock per ioc to avoid contention * Added code to free up queued pdir entries should we be unable to find space for new ones (not that I've ever seen the pdir anywhere close to full) * Finished cleaning out the hint support code, Grant is maintaining this separately for now * Added option to control bypass of sg mappings separately from single/coherent mappings Much like the swiotlb, sba_iommu allows devices capable of 64bit addressing to bypass the iommu and DMA directly to/from memory. Using a worst case scenario test (64bit bypass disabled, all DMA mapped through the iommu), I saw a 60% increase in sequential block input throughput using bonnie++ on a large RAID0 MD array. In fact, this patch provides the best bonnie++ performance with bypass disabled. This is likely due to benefits seen from coalescing the scatterlist, allowing better disk streaming. I assume that network performance will likely be limited by mapping latency, so I added the last bullet item to allow sg mappings to get the benefit of coalescing while keeping a low latency path for single and coherent mappings. If anyone is setup for network benchmarks, I'd be interested in a before and after with this patch. ChangeSet@1.1606, 2004-02-10 15:32:27-06:00, shaggy@kleikamp.dyn.webahead.ibm.com JFS: Threads should exit with complete_and_exit ChangeSet@1.1603.1.32, 2004-02-10 12:55:53-08:00, kenneth.w.chen@intel.com [PATCH] ia64: fix ld.a emulation This patch fixes a corner-case of ld.a emulation. ld.a should be emulated such that it always loads a misaligned value and clears the corresponding ALAT entry. The old emulation was correct for the case where ld.a was followed by ld.c/chk.a (since ALAT entry was cleared), but wrong for the case where it _wasn't_ followed by ld.c/chk.a. In that case, the misaligned value wasn't read from memory, as it should have been. ChangeSet@1.1603.1.31, 2004-02-10 12:16:10-08:00, steiner@sgi.com [PATCH] ia64: Enable cpu_vm_mask maintenance and improve SN2 TLB flushing ChangeSet@1.1603.1.30, 2004-02-10 11:19:39-08:00, torvalds@home.osdl.org Fix bogus mode bit testing by smbfs. The S_IFxxxx macros aren't bits to be tested, they are values of the S_IFMT field. ChangeSet@1.1603.8.10, 2004-02-10 18:03:26+00:00, davej@redhat.com [CPUFREQ] Fix deadlock in userspace governor. Another fix from Dominik. ChangeSet@1.1603.8.9, 2004-02-10 17:57:45+00:00, davej@redhat.com [CPUFREQ] Pentium-4-M detection fix for speedstep-lib From Dominik.. The different P-4-M steppings have different "ebx" values. Analyze it correctly to sort out Pentium-4-based Celerons. ChangeSet@1.1603.8.8, 2004-02-10 17:54:34+00:00, davej@redhat.com [CPUFREQ] powernow-k8 printk cleanups from Pavel. ChangeSet@1.1603.8.7, 2004-02-10 17:45:49+00:00, davej@redhat.com [CPUFREQ] convert powernow-k8 to use frequency tables [5/5] Move the table verification to an extra function. ChangeSet@1.1603.8.6, 2004-02-10 17:44:31+00:00, davej@redhat.com [CPUFREQ] convert powernow-k8 to use frequency tables [4/5] Remove the *ppst table, and remove an unneccessary forward-declaration ChangeSet@1.1603.8.5, 2004-02-10 17:43:28+00:00, davej@redhat.com [CPUFREQ] convert powernow-k8 to use frequency tables [3/5] Keep *ppst local to the only function which needs it any longer. ChangeSet@1.1603.8.4, 2004-02-10 17:42:30+00:00, davej@redhat.com [CPUFREQ] convert powernow-k8 to use frequency tables [2/5] Use the frequency_table for calculating the correct ->target state ChangeSet@1.1603.8.3, 2004-02-10 17:41:20+00:00, davej@redhat.com [CPUFREQ] convert powernow-k8 to use frequency tables [1/5] Add a struct cpufreq_frequency_table, fill it with content, and use it for ->verify. ChangeSet@1.1603.1.29, 2004-02-10 09:38:45-08:00, jsimmons@infradead.org [PATCH] framebuffer GPM corruption fix. This patch fixes the GPM cursor corruption people where seeing. ChangeSet@1.1603.1.28, 2004-02-10 09:24:56-08:00, thornber@redhat.com [PATCH] dm: block size bug with 64 bit devs With 32 bit sector_t the block device size _in bytes_ is also cut to 32 bit in __set_size when the block device is mount (a filesystem mounted). The argument should be cast to loff_t before expanding the sector count to a byte count and calling i_size_write. [Christophe Saout] ChangeSet@1.1603.8.2, 2004-02-10 17:17:19+00:00, davej@redhat.com [CPUFREQ] Fix an oops unloading p4-clockmod. Reverting frequency changes on unloading is uncommon for cpufreq drivers so let's remove this speciality. ChangeSet@1.1603.1.27, 2004-02-10 09:10:33-08:00, torvalds@home.osdl.org Make a bit more palatable to user program inclusion. It's still wrong to include kernel headers from user programs. Oh, well. ChangeSet@1.1603.1.26, 2004-02-10 09:00:29-08:00, B.Zolnierkiewicz@elka.pw.edu.pl [PATCH] fix build for CONFIG_BLK_DEV_IDEDMA=n Ths "fix duplication of DMA {black,white}list in icside.c" patch broke it. Noticed by Geert Uytterhoeven . ChangeSet@1.1500.29.2, 2004-02-10 16:54:06+00:00, davej@redhat.com [CPUFREQ] Geode register fixes. From: Hiroshi Miura I mistook a Geode chipset's register meanings. (-.-; ON is not 'CPU is ON' but 'cpu modulation is ON' that is stops cpu. this causes a bad freq setting. This patch fixes this and minor bug that is, if (new_khz == stock_freq) { /* if new khz == 100% of CPU speed, it is special case */ local_irq_save(flags); cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); cpufreq_notify_transition() called after local_irq_save(); this makes not update cpu_khz. ChangeSet@1.1603.1.25, 2004-02-10 08:45:59-08:00, axboe@suse.de [PATCH] DVD-R capability flag set incorrectly, /proc formatting fix From John McKell : This patch for scsi/sr.c and cdrom/cdrom.c persuades /proc/sys/dev/cdrom/info to report that connecting a drive via USB rather than ATAPI in fact does not make it able to write DVD-R. Without this patch, when sr0 and hdd are the same type of device connected via USB and ATAPI respectively, I see: $ cat /proc/sys/dev/cdrom/info: drive name: sr1 sr0 hdd ... Can write CD-R: 1 0 0 Can write CD-RW: 1 0 0 Can read DVD: 0 0 0 Can write DVD-R: 1 1 0 Can write DVD-RAM: 0 0 0 Can read MRW: 0 0 0 Can write MRW: 0 0 0 With this patch applied, instead I see: $ cat /proc/sys/dev/cdrom/info: drive name: sr1 sr0 hdd ... Can write CD-R: 1 0 0 Can write CD-RW: 1 0 0 Can read DVD: 0 0 0 Can write DVD-R: 0 0 0 Can write DVD-RAM: 0 0 0 Can read MRW: 0 0 0 Can write MRW: 0 0 0 The sr1 device in particular is an ordinary CD-RW that in fact cannot write DVD-R. While messing with this code, I also thought to tweak the /proc formatting to align the tabbed columns. ChangeSet@1.1603.1.24, 2004-02-10 08:11:44-08:00, benh@kernel.crashing.org [PATCH] Export OF device path for PCI devices Here's a new version of the patch according to our discussion. This allows the platform to add its own platform files to the sysfs PCI device node through a "pcibios_add_platform_entries()" call. I added an empty pcibios_add_platform_entries() inline to all archs that apparently have PCI and implemented the OF stuff for ppc and ppc64. The name is still "devspec" for now, I doubt it will conflict and that's consistent with our use of the "devspec" name in other places. ChangeSet@1.1603.1.23, 2004-02-09 18:59:09-08:00, torvalds@home.osdl.org Linux 2.6.3-rc2 TAG: v2.6.3-rc2