- 15 Nov, 2005 4 commits
-
-
Andi Kleen authored
The code should deal with an additional empty zone, so fix up the #error. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-
Andi Kleen authored
IA64 traditionally had a 4GB DMA32 zone. Set the compatibility flag to keep old drivers working. For new drivers it would be better to use ZONE_DMA32 now. Cc: tony.luck@intel.com Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-
Andi Kleen authored
Add a new 4GB GFP_DMA32 zone between the GFP_DMA and GFP_NORMAL zones. As a bit of historical background: when the x86-64 port was originally designed we had some discussion if we should use a 16MB DMA zone like i386 or a 4GB DMA zone like IA64 or both. Both was ruled out at this point because it was in early 2.4 when VM is still quite shakey and had bad troubles even dealing with one DMA zone. We settled on the 16MB DMA zone mainly because we worried about older soundcards and the floppy. But this has always caused problems since then because device drivers had trouble getting enough DMA able memory. These days the VM works much better and the wide use of NUMA has proven it can deal with many zones successfully. So this patch adds both zones. This helps drivers who need a lot of memory below 4GB because their hardware is not accessing more (graphic drivers - proprietary and free ones, video frame buffer drivers, sound drivers etc.). Previously they could only use IOMMU+16MB GFP_DMA, which was not enough memory. Another common problem is that hardware who has full memory addressing for >4GB misses it for some control structures in memory (like transmit rings or other metadata). They tended to allocate memory in the 16MB GFP_DMA or the IOMMU/swiotlb then using pci_alloc_consistent, but that can tie up a lot of precious 16MB GFPDMA/IOMMU/swiotlb memory (even on AMD systems the IOMMU tends to be quite small) especially if you have many devices. With the new zone pci_alloc_consistent can just put this stuff into memory below 4GB which works better. One argument was still if the zone should be 4GB or 2GB. The main motivation for 2GB would be an unnamed not so unpopular hardware raid controller (mostly found in older machines from a particular four letter company) who has a strange 2GB restriction in firmware. But that one works ok with swiotlb/IOMMU anyways, so it doesn't really need GFP_DMA32. I chose 4GB to be compatible with IA64 and because it seems to be the most common restriction. The new zone is so far added only for x86-64. For other architectures who don't set up this new zone nothing changes. Architectures can set a compatibility define in Kconfig CONFIG_DMA_IS_DMA32 that will define GFP_DMA32 as GFP_DMA. Otherwise it's a nop because on 32bit architectures it's normally not needed because GFP_NORMAL (=0) is DMA able enough. One problem is still that GFP_DMA means different things on different architectures. e.g. some drivers used to have #ifdef ia64 use GFP_DMA (trusting it to be 4GB) #elif __x86_64__ (use other hacks like the swiotlb because 16MB is not enough) ... . This was quite ugly and is now obsolete. These should be now converted to use GFP_DMA32 unconditionally. I haven't done this yet. Or best only use pci_alloc_consistent/dma_alloc_coherent which will use GFP_DMA32 transparently. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-
Andi Kleen authored
Rerun and enable autofs 4, relayfs and softdog Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-
- 05 Nov, 2005 6 commits
-
-
Jeff Garzik authored
Use ata_pad_{alloc,free} in two drivers, to factor out common code. Add ata_pad_{alloc,free} to two other drivers, which needed the padding but had not been updated.
-
Jeff Garzik authored
-
Calin A. Culianu authored
This adds support for the Nvidia Geforce 7800 series of cards to the nvidiafb framebuffer driver. All it does is add the PCI device id for the 7800, 7800 GTX, 7800 GO, and 7800 GTX GO cards to the module device table for the nvidiafb.ko driver, so that nvidiafb.ko will actually work on these cards. I also added the relevant PCI device ids to linux/pci_ids.h I tested it on my 7800 GTX here and it works like a charm. I now can get framebuffer support on this card! Woo hoo!! Nothing like 200x75 text mode to make your eyes BLEED. ;) Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-
Linus Torvalds authored
-
Linus Torvalds authored
-
Linus Torvalds authored
-
- 04 Nov, 2005 30 commits
-
-
Paul Mackerras authored
We can't currently use asm-ppc/page.h in vmlinux.lds.S, so until we have a merged page.h, define PAGE_SIZE and KERNELBASE locally. Also gets rid of some dynamic executable cruft that we had for 32-bit. With -Ttext=$(KERNELBASE) this didn't cause any problem, but when we changed to putting . = KERNELBASE in the vmlinux.lds.S this cruft caused the text to get linked at 0xa0 instead of 0xc0000000. Oops. Signed-off-by: Paul Mackerras <paulus@samba.org>
-
Paul Mackerras authored
This also moves setup_cpu_maps to setup-common.c (calling it smp_setup_cpu_maps) and uses it on both 32-bit and 64-bit. Signed-off-by: Paul Mackerras <paulus@samba.org>
-
Chuck Lever authored
Fix some dprintk's so that NLM, NFS client, and RPC client compile cleanly if CONFIG_SYSCTL is disabled. Test plan: Compile kernel with CONFIG_NFS enabled and CONFIG_SYSCTL disabled. Signed-off-by: Chuck Lever <cel@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Chuck Lever authored
The sunrpc module should build properly even when CONFIG_SYSCTL is disabled. Reported by Jan-Benedict Glaw. Test plan: Compile kernel with CONFIG_NFS as a module and built-in, and CONFIG_SYSCTL enabled and disabled. Signed-off-by: Chuck Lever <cel@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
Now that we have a method of dealing with delegation recalls, actually enable the caching of posix and BSD locks. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
Delegations allow us to cache posix and BSD locks, however when the delegation is recalled, we need to "flush the cache" and send the cached LOCK requests to the server. This patch sets up the mechanism for doing so. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
I missed this one... Any form of rename will result in a delegation recall, so it is more efficient to return the one we hold before trying the rename. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
Ensure that we retry the failed operation... Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
RFC 3530 states that for OPEN_DOWNGRADE "The share_access and share_deny bits specified must be exactly equal to the union of the share_access and share_deny bits specified for some subset of the OPENs in effect for current openowner on the current file. Setattr is currently violating the NFSv4 rules for OPEN_DOWNGRADE in that it may cause a downgrade from OPEN4_SHARE_ACCESS_BOTH to OPEN4_SHARE_ACCESS_WRITE despite the fact that there exists no open file with O_WRONLY access mode. Fix the problem by replacing nfs4_find_state() with a modified version of nfs_find_open_context(). Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
Trond Myklebust authored
We must not remove the nfs4_state structure from the inode open lists before we are in sequence lock. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
-
David S. Miller authored
At header fixup time, it is not yet legal to ioremap() PCI device registers, yet that is what this quirk code needs to do. Signed-off-by: David S. Miller <davem@davemloft.net>
-
Oleg Nesterov authored
Do not transfer remaining time slice to another cpu on process exit. Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-
Linus Torvalds authored
-
Linus Torvalds authored
-
Linus Torvalds authored
-
Russell King authored
No longer maintained
-
Russell King authored
No longer maintained
-
Russell King authored
No longer maintained
-
Nicolas Pitre authored
Patch from Nicolas Pitre We have an optimized sha1 routine (arch/arm/lib/sha1.S) meant to override the generic one in lib/sha1.c. Unfortunately lib/lib.a is listed _before_ arch/arm/lib/lib.a in the link argument list and therefore the architecture specific lib functions are not picked up before the generic versions. This patch is a quick fix to change that ordering for ARM. Here's what the kbuild maintainer had to say about it (was also CC'd on lkml): On Wed, 2 Nov 2005, Sam Ravnborg wrote: > This looks like an obvious way to achive correct ordering. > We could change it so arch defines always took precedence but > the above is so simple that it is not worth the effort. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-
Todd Poynor authored
Patch from Todd Poynor Add platform devices for flash to Lubbock and Mainstone board files. Once in place, the two existing mtd map drivers for the boards will be converted to use a single pxa2xx map driver in the linux-mtd tree. Take 4: flash_platform_data .map_name vs. .name cleaned up, resync with merged irda patch context. Signed-off-by: Todd Poynor <tpoynor@mvista.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-
Dave Jiang authored
Patch from Dave Jiang This provides support for IXP2xxx error interrupt handling. Previously there was a patch to remove this (although the original stuff was broken). Well, now the error bits are needed again. These are used extensively by the micro-engine drivers according to Deepak and also we will need it for the new EDAC code that Alan Cox is trying to push into the main kernel. Re-submit of 3072/1, generated against git tree pulled today. AFAICT, this git tree pulled in all the ARM changes that's in arm.diff. Please let me know if there are additional changes. Thx! Signed-off-by: Dave Jiang <djiang@mvista.com> Signed-off-by: Deepak Saxena <dsaxena@plexity.net> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-
Nicolas Pitre authored
Patch from Nicolas Pitre ARM processors that have pld instructions are not using those copy_user implementation anymore. Let's remove the useless PLD lines which were half wrong anyway. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
-
-
Stephen Rothwell authored
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
-
-
Paul Mackerras authored
Signed-off-by: Paul Mackerras <paulus@samba.org>
-
Michael Ellerman authored
-
Michael Ellerman authored
The merged verison of ELF_CORE_COPY_REGS is basically the PPC64 version, with a memset that came from PPC and a few types abstracted out into #defines. But it's not _quite_ right. The first problem is we calculate the number of registers with: nregs = sizeof(struct pt_regs) / sizeof(ELF_GREG_TYPE) For a 32-bit process on a 64-bit kernel that's bogus because the registers are 64 bits, but ELF_GREG_TYPE is u32, so nregs == 88 which is wrong. The other problem is the memset, which assumes a struct pt_regs is smaller than a struct elf_regs. For a 32-bit process on a 64-bit kernel that's false. The fix is to calculate the number of regs using sizeof(unsigned long), which should always be right, and just memset the whole damn thing _before_ copying the registers in. Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
-
Michael Ellerman authored
There's no reason for smp_release_cpus() to be asm, and most people can make more sense of C code. Add an extern declaration to smp.h and remove the custom one in machine_kexec.c Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
-