aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86
Commit message (Collapse)AuthorAgeFilesLines
* x86: gart: Clean up the code a bitIngo Molnar2009-11-171-55/+61
| | | | | | | | | | | | Clean up various small stylistic details in the GART code. No functionality changed. Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: muli@il.ibm.com Cc: joerg.roedel@amd.com LKML-Reference: <1258287594-8777-2-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: Calgary: Remove unnecessary DMA_ERROR_CODE usageFUJITA Tomonori2009-11-171-9/+6
| | | | | | | | | | | | This cleans up iommu_alloc() a bit and removes unnecessary DMA_ERROR_CODE usage. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: muli@il.ibm.com Cc: joerg.roedel@amd.com LKML-Reference: <1258287594-8777-4-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: Kill bad_dma_address variableFUJITA Tomonori2009-11-175-29/+24
| | | | | | | | | | | | | | | | | | | | | | | | This kills bad_dma_address variable, the old mechanism to enable IOMMU drivers to make dma_mapping_error() work in IOMMU's specific way. bad_dma_address variable was introduced to enable IOMMU drivers to make dma_mapping_error() work in IOMMU's specific way. However, it can't handle systems that use both swiotlb and HW IOMMU. SO we introduced dma_map_ops->mapping_error to solve that case. Intel VT-d, GART, and swiotlb already use dma_map_ops->mapping_error. Calgary, AMD IOMMU, and nommu use zero for an error dma address. This adds DMA_ERROR_CODE and converts them to use it (as SPARC and POWER does). Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: muli@il.ibm.com Cc: joerg.roedel@amd.com LKML-Reference: <1258287594-8777-3-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* x86: gart: Add own dma_mapping_error functionFUJITA Tomonori2009-11-171-5/+13
| | | | | | | | | | | | | | | GART IOMMU is the only user of bad_dma_address variable. This patch converts GART to use the newer mechanism, fill in ->mapping_error() in struct dma_map_ops, to make dma_mapping_error() work in IOMMU specific way. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org> Cc: muli@il.ibm.com Cc: joerg.roedel@amd.com LKML-Reference: <1258287594-8777-2-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Merge commit 'v2.6.32-rc7' into core/iommuIngo Molnar2009-11-175-20/+33
|\ | | | | | | | | | | Merge reason: Add fixes we'll depend on. Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * Merge branch 'for-linus' of ↵Linus Torvalds2009-11-112-7/+9
| |\ | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6 * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6: x86/PCI: Adjust GFP mask handling for coherent allocations PCI ASPM: fix oops on root port removal
| | * x86/PCI: Adjust GFP mask handling for coherent allocationsJan Beulich2009-11-082-7/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rather than forcing GFP flags and DMA mask to be inconsistent, GFP flags should be determined even for the fallback device through dma_alloc_coherent_mask()/dma_alloc_coherent_gfp_flags(). This restores 64-bit behavior as it was prior to commits 8965eb19386fdf5ccd0ef8b02593eb8560aa3416 and 4a367f3a9dbf2e7ffcee4702203479809236ee6e (not sure why there are two of them), where GFP_DMA was forced on for 32-bit, but not for 64-bit, with the slight adjustment that afaict even 32-bit doesn't need this without CONFIG_ISA. Signed-off-by: Jan Beulich <jbeulich@novell.com> Acked-by: Takashi Iwai <tiwai@suse.de> LKML-Reference: <4AF18187020000780001D8AA@vpn.id2.novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
| * | Merge branch 'x86-fixes-for-linus' of ↵Linus Torvalds2009-11-113-13/+24
| |\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86, amd-ucode: Check UCODE_MAGIC before loading the container file x86: Fix error return sequence in __ioremap_caller() x86: Add Phoenix/MSC BIOSes to lowmem corruption list
| | * | x86, amd-ucode: Check UCODE_MAGIC before loading the container fileBorislav Petkov2009-11-101-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Borislav Petkov <borislav.petkov@amd.com> Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com> LKML-Reference: <20091029134552.GC30802@alberich.amd.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * | x86: Fix error return sequence in __ioremap_caller()Xiaotian Feng2009-11-081-13/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | kernel missed to free memtype if get_vm_area_caller failed in __ioremap_caller. This patch introduces error path to fix this and cleans up the repetitive error return sequences that contributed to the creation of the bug. Signed-off-by: Xiaotian Feng <dfeng@redhat.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> LKML-Reference: <1257389031-20429-1-git-send-email-dfeng@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| | * | x86: Add Phoenix/MSC BIOSes to lowmem corruption listSimon Kagstrom2009-11-061-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We have a board with a Phoenix/MSC BIOS which also corrupts the low 64KB of RAM, so add an entry to the table. Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net> LKML-Reference: <20091106154404.002648d9@marrow.netinsight.se> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
* | | | x86: Don't put iommu_shutdown_noop() in init sectionHiroshi Shimamoto2009-11-161-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It causes kernel panic on shutdown or reboot. Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com> Acked-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> LKML-Reference: <4B00BC8E.50801@ct.jp.nec.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Make calgary_iommu_init() staticFUJITA Tomonori2009-11-151-20/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This makes calgary_iommu_init() static and moves it to remove the forward declaration. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: muli@il.ibm.com LKML-Reference: <20091114212603U.fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | swiotlb: Remove duplicate swiotlb_force extern declarationsFUJITA Tomonori2009-11-151-4/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: tony.luck@intel.com LKML-Reference: <1258199198-16657-4-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Move iommu_shutdown_noop to x86_init.cFUJITA Tomonori2009-11-152-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | iommu_init_noop() is in arch/x86/kernel/x86_init.c but iommu_shutdown_noop() in arch/x86/include/asm/iommu.h. This moves iommu_shutdown_noop() to x86_init.c for consistency. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> LKML-Reference: <1258199198-16657-3-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Set dma_ops to nommu_dma_ops by defaultFUJITA Tomonori2009-11-152-5/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We set dma_ops to nommu_dma_ops at two different places for x86_32 and x86_64. This unifies them by setting dma_ops to nommu_dma_ops by default. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> LKML-Reference: <1258199198-16657-2-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | swiotlb: Remove the swiotlb variable usageFUJITA Tomonori2009-11-113-7/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | POWERPC doesn't expect it to be used. This fixes the linux-next build failure reported by Stephen Rothwell: lib/swiotlb.c: In function 'setup_io_tlb_npages': lib/swiotlb.c:114: error: 'swiotlb' undeclared (first use in this function) Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: peterz@infradead.org LKML-Reference: <20091112000258F.fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Add iommu_init to x86_init_ops, fix buildIngo Molnar2009-11-101-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Most of the time x86_init.h is included in pci-dma.c - but not always, leading to this rare build failure: arch/x86/kernel/pci-dma.c:296: error: 'x86_init' undeclared (first use in this function) So include asm/x86_init.h explicitly. Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-2-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86, 32-bit: Fix swiotlb boot crashFUJITA Tomonori2009-11-101-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Ingo Molnar reported this boot crash: [ 8.655620] pata_amd 0000:00:06.0: version 0.4.1 [ 8.660286] BUG: unable to handle kernel NULL pointer dereference at 00000034 [ 8.663572] IP: [<c100617b>] dma_supported+0x3b/0xa4 [ 8.663572] *pde = 00000000 Initialize dma_ops properly in the 32-bit case. Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Handle HW IOMMU initialization failure gracefullyFUJITA Tomonori2009-11-109-34/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If HW IOMMU initialization fails (Intel VT-d often does this, typically due to BIOS bugs), we fall back to nommu. It doesn't work for the majority since nowadays we have more than 4GB memory so we must use swiotlb instead of nommu. The problem is that it's too late to initialize swiotlb when HW IOMMU initialization fails. We need to allocate swiotlb memory earlier from bootmem allocator. Chris explained the issue in detail: http://marc.info/?l=linux-kernel&m=125657444317079&w=2 The current x86 IOMMU initialization sequence is too complicated and handling the above issue makes it more hacky. This patch changes x86 IOMMU initialization sequence to handle the above issue cleanly. The new x86 IOMMU initialization sequence are: 1. we initialize the swiotlb (and setting swiotlb to 1) in the case of (max_pfn > MAX_DMA32_PFN && !no_iommu). dma_ops is set to swiotlb_dma_ops or nommu_dma_ops. if swiotlb usage is forced by the boot option, we finish here. 2. we call the detection functions of all the IOMMUs 3. the detection function sets x86_init.iommu.iommu_init to the IOMMU initialization function (so we can avoid calling the initialization functions of all the IOMMUs needlessly). 4. if the IOMMU initialization function doesn't need to swiotlb then sets swiotlb to zero (e.g. the initialization is sucessful). 5. if we find that swiotlb is set to zero, we free swiotlb resource. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-10-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | swiotlb: Defer swiotlb init printing, export swiotlb_print_info()FUJITA Tomonori2009-11-101-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This enables us to avoid printing swiotlb memory info when we initialize swiotlb. After swiotlb initialization, we could find that we don't need swiotlb. This patch removes the code to print swiotlb memory info in swiotlb_init() and exports the function to do that. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com Cc: tony.luck@intel.com Cc: benh@kernel.crashing.org LKML-Reference: <1257849980-22640-9-git-send-email-fujita.tomonori@lab.ntt.co.jp> [ -v2: merge up conflict ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: intel-iommu: Convert detect_intel_iommu to use iommu_init hookFUJITA Tomonori2009-11-101-2/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This changes detect_intel_iommu() to set intel_iommu_init() to iommu_init hook if detect_intel_iommu() finds the IOMMU. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-6-git-send-email-fujita.tomonori@lab.ntt.co.jp> [ -v2: build fix for the !CONFIG_DMAR case ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: amd_iommu: Convert amd_iommu_detect() to use iommu_init hookFUJITA Tomonori2009-11-103-18/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This changes amd_iommu_detect() to set amd_iommu_init to iommu_init hook if amd_iommu_detect() finds the AMD IOMMU. We can kill the code to check if we found the IOMMU in amd_iommu_init() since amd_iommu_detect() sets amd_iommu_init() only when it found the IOMMU. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-5-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: GART: Convert gart_iommu_hole_init() to use iommu_init hookFUJITA Tomonori2009-11-104-16/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This changes gart_iommu_hole_init() to set gart_iommu_init() to iommu_init hook if gart_iommu_hole_init() finds the GART IOMMU. We can kill the code to check if we found the IOMMU in gart_iommu_init() since gart_iommu_hole_init() sets gart_iommu_init() only when it found the IOMMU. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-4-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Calgary: Convert detect_calgary() to use iommu_init hookFUJITA Tomonori2009-11-103-10/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This changes detect_calgary() to set init_calgary() to iommu_init hook if detect_calgary() finds the Calgary IOMMU. We can kill the code to check if we found the IOMMU in init_calgary() since detect_calgary() sets init_calgary() only when it found the IOMMU. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by: Muli Ben-Yehuda <muli@il.ibm.com> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com LKML-Reference: <1257849980-22640-3-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Add iommu_init to x86_init_opsFUJITA Tomonori2009-11-103-0/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We call the detections functions of all the IOMMUs then all their initialization functions. The latter is pointless since we don't detect multiple different IOMMUs. What we need to do is calling the initialization function of the detected IOMMU. This adds iommu_init hook to x86_init_ops so if an IOMMU detection function can set its initialization function to the hook. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: chrisw@sous-sol.org Cc: dwmw2@infradead.org Cc: joerg.roedel@amd.com Cc: muli@il.ibm.com LKML-Reference: <1257849980-22640-2-git-send-email-fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: GART: pci-gart_64.c: Use correct length in strncmpJoe Perches2009-11-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Joe Perches <joe@perches.com> Cc: <stable@kernel.org> # .3x.x LKML-Reference: <1257818330.12852.72.camel@Joe-Laptop.home> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Fix iommu=nodac parameter handlingTejun Heo2009-11-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | iommu=nodac should forbid dac instead of enabling it. Fix it. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Matteo Frigo <athena@fftw.org> Cc: <stable@kernel.org> # .32.x and older LKML-Reference: <4AE5B52A.4050408@kernel.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | x86: Use x86_platform for iommu_shutdownFUJITA Tomonori2009-11-0810-26/+13
|/ / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch cleans up pci_iommu_shutdown() a bit to use x86_platform (similar to how IA64 initializes an IOMMU driver). This adds iommu_shutdown() to x86_platform to avoid calling every IOMMUs' shutdown functions in pci_iommu_shutdown() in order. The IOMMU shutdown functions are platform specific (we don't have multiple different IOMMU hardware) so the current way is pointless. An IOMMU driver sets x86_platform.iommu_shutdown to the shutdown function if necessary. Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: joerg.roedel@amd.com LKML-Reference: <20091027163358F.fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | Merge branch 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvmLinus Torvalds2009-11-051-2/+2
|\ \ \ | | | | | | | | | | | | | | | | | | | | * 'kvm-updates/2.6.32' of git://git.kernel.org/pub/scm/virt/kvm/kvm: KVM: get_tss_base_addr() should return a gpa_t KVM: x86: Catch potential overrun in MCE setup
| * | | KVM: get_tss_base_addr() should return a gpa_tGleb Natapov2009-11-041-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If TSS we are switching to resides in high memory task switch will fail since address will be truncated. Windows2k3 does this sometimes when running with more then 4G Cc: stable@kernel.org Signed-off-by: Gleb Natapov <gleb@redhat.com> Signed-off-by: Avi Kivity <avi@redhat.com>
| * | | KVM: x86: Catch potential overrun in MCE setupJan Kiszka2009-11-041-1/+1
| | |/ | |/| | | | | | | | | | | | | | | | | | | | | | We only allocate memory for 32 MCE banks (KVM_MAX_MCE_BANKS) but we allow user space to fill up to 255 on setup (mcg_cap & 0xff), corrupting kernel memory. Catch these overflows. Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
* | | x86: Make sure get_user_desc() doesn't sign extend.Chris Lalancette2009-11-051-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current implementation of get_user_desc() sign extends the return value because of integer promotion rules. For the most part, this doesn't matter, because the top bit of base2 is usually 0. If, however, that bit is 1, then the entire value will be 0xffff... which is probably not what the caller intended. This patch casts the entire thing to unsigned before returning, which generates almost the same assembly as the current code but replaces the final "cltq" (sign extend) with a "mov %eax %eax" (zero-extend). This fixes booting certain guests under KVM. Signed-off-by: Chris Lalancette <clalance@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* | | Merge branch 'bugfix' of ↵Linus Torvalds2009-11-051-1/+10
|\ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen * 'bugfix' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen: xen: mask extended topology info in cpuid xen/hvc: make sure console output is always emitted, with explicit polling
| * | | xen: mask extended topology info in cpuidJeremy Fitzhardinge2009-11-031-1/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A Xen guest never needs to know about extended topology, and knowing would just confuse it. This patch just zeros ebx in leaf 0xb which indicates no topology info, preventing a crash under Xen on cpus which support this leaf. Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Cc: Stable Kernel <stable@kernel.org>
* | | | Merge branch 'sched-fixes-for-linus' of ↵Linus Torvalds2009-11-051-1/+1
|\ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: sched: Fix kthread_bind() by moving the body of kthread_bind() to sched.c sched: Disable SD_PREFER_LOCAL at node level sched: Fix boot crash by zalloc()ing most of the cpu masks sched: Strengthen buddies and mitigate buddy induced latencies
| * | | | sched: Disable SD_PREFER_LOCAL at node levelMike Galbraith2009-11-031-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Yanmin Zhang reported that SD_PREFER_LOCAL induces an order of magnitude increase in select_task_rq_fair() overhead while running heavy wakeup benchmarks (tbench and vmark). Since SD_BALANCE_WAKE is off at node level, turn SD_PREFER_LOCAL off as well pending further investigation. Reported-by: Zhang, Yanmin <yanmin_zhang@linux.intel.com> Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | | Merge branch 'x86-fixes-for-linus' of ↵Linus Torvalds2009-11-057-3/+41
|\ \ \ \ \ | |_|_|/ / |/| | | / | | |_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86, fs: Fix x86 procfs stack information for threads on 64-bit x86: Add reboot quirk for 3 series Mac mini x86: Fix printk message typo in mtrr cleanup code dma-debug: Fix compile warning with PAE enabled x86/amd-iommu: Un__init function required on shutdown x86/amd-iommu: Workaround for erratum 63
| * | | x86, fs: Fix x86 procfs stack information for threads on 64-bitStefani Seibold2009-11-042-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes two issues in the procfs stack information on x86-64 linux. The 32 bit loader compat_do_execve did not store stack start. (this was figured out by Alexey Dobriyan). The stack information on a x64_64 kernel always shows 0 kbyte stack usage, because of a missing implementation of the KSTK_ESP macro which always returned -1. The new implementation now returns the right value. Signed-off-by: Stefani Seibold <stefani@seibold.net> Cc: Americo Wang <xiyou.wangcong@gmail.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1257240160.4889.24.camel@wall-e> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | Merge branch 'iommu/fixes' of ↵Ingo Molnar2009-11-033-1/+26
| |\ \ \ | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/joro/linux-2.6-iommu into x86/urgent
| | | \ \
| | | \ \
| | *-. \ \ Merge branches 'amd-iommu/fixes' and 'dma-debug/fixes' into iommu/fixesJoerg Roedel2009-11-033-1/+26
| | |\ \ \ \
| | | * | | | x86/amd-iommu: Un__init function required on shutdownJoerg Roedel2009-10-281-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The function iommu_feature_disable is required on system shutdown to disable the IOMMU but it is marked as __init. This may result in a panic if the memory is reused. This patch fixes this bug. Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
| | | * | | | x86/amd-iommu: Workaround for erratum 63Joerg Roedel2009-10-093-0/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is an erratum for IOMMU hardware which documents undefined behavior when forwarding SMI requests from peripherals and the DTE of that peripheral has a sysmgt value of 01b. This problem caused weird IO_PAGE_FAULTS in my case. This patch implements the suggested workaround for that erratum into the AMD IOMMU driver. The erratum is documented with number 63. Cc: stable@kernel.org Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
| * | | | | | x86: Add reboot quirk for 3 series Mac miniGottfried Haider2009-11-021-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Reboot does not work out of the box on my "Early 2009" Mac mini (3,1). Detect this machine via DMI as we do for recent MacBooks. Signed-off-by: Gottfried Haider <gottfried.haider@gmail.com> Cc: Ozan Çağlayan <ozan@pardus.org.tr> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | | | x86: Fix printk message typo in mtrr cleanup codeDave Jones2009-11-021-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Trivial typo. Signed-off-by: Dave Jones <davej@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
* | | | | | | Merge branch 'x86-fixes-for-linus' of ↵Linus Torvalds2009-11-026-9/+24
|\ \ \ \ \ \ \ | |/ / / / / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86: Make EFI RTC function depend on 32bit again x86-64: Fix register leak in 32-bit syscall audting x86: crash_dump: Fix non-pae kdump kernel memory accesses x86: Side-step lguest problem by only building cmpxchg8b_emu for pre-Pentium x86: Remove STACKPROTECTOR_ALL
| * | | | | | x86: Make EFI RTC function depend on 32bit againFeng Tang2009-10-271-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The EFI RTC functions are only available on 32 bit. commit 7bd867df (x86: Move get/set_wallclock to x86_platform_ops) removed the 32bit dependency which leads to boot crashes on 64bit EFI systems. Add the dependency back. Solves: http://bugzilla.kernel.org/show_bug.cgi?id=14466 Tested-by: Matthew Garrett <mjg59@srcf.ucam.org> Signed-off-by: Feng Tang <feng.tang@intel.com> LKML-Reference: <20091020125402.028d66d5@feng-desktop> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
| * | | | | | x86-64: Fix register leak in 32-bit syscall audtingJan Beulich2009-10-261-3/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Restoring %ebp after the call to audit_syscall_exit() is not only unnecessary (because the register didn't get clobbered), but in the sysenter case wasn't even doing the right thing: It loaded %ebp from a location below the top of stack (RBP < ARGOFFSET), i.e. arbitrary kernel data got passed back to user mode in the register. Signed-off-by: Jan Beulich <jbeulich@novell.com> Acked-by: Roland McGrath <roland@redhat.com> Cc: <stable@kernel.org> LKML-Reference: <4AE5CC4D020000780001BD13@vpn.id2.novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | | | x86: crash_dump: Fix non-pae kdump kernel memory accessesJiri Slaby2009-10-261-0/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Non-PAE 32-bit dump kernels may wrap an address around 4G and poke unwanted space. ptes there are 32-bit long, and since pfn << PAGE_SIZE may exceed this limit, high pfn bits are cropped and wrong address mapped by kmap_atomic_pfn in copy_oldmem_page. Don't allow this behavior in non-PAE kdump kernels by checking pfns passed into copy_oldmem_page. In the case of failure, userspace process gets EFAULT. [v2] - fix comments - move ifdefs inside the function Signed-off-by: Jiri Slaby <jirislaby@gmail.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Simon Horman <horms@verge.net.au> Cc: Paul Mundt <lethal@linux-sh.org> LKML-Reference: <1256551903-30567-1-git-send-email-jirislaby@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
| * | | | | | x86: Side-step lguest problem by only building cmpxchg8b_emu for pre-PentiumRusty Russell2009-10-261-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 79e1dd05d1a22 "x86: Provide an alternative() based cmpxchg64()" broke lguest, even on systems which have cmpxchg8b support. The emulation code gets used until alternatives get run, but it contains native instructions, not their paravirt alternatives. The simplest fix is to turn this code off except for 386 and 486 builds. Reported-by: Johannes Stezenbach <js@sig21.net> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> Acked-by: H. Peter Anvin <hpa@zytor.com> Cc: lguest@ozlabs.org Cc: Arjan van de Ven <arjan@infradead.org> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <200910261426.05769.rusty@rustcorp.com.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
generated by cgit v1.1 at 2025-02-07 09:07:53 +0000