)]}' { "log": [ { "commit": "d94afc6ccf6690b30ae112ec8101b3f10d50114e", "tree": "f54fb1fe147861db876b99809ff1cd1a316c45c0", "parents": [ "f8bab73515ca5b392680bb033dceeb37b8463e95" ], "author": { "name": "mark gross", "email": "mgross@linux.intel.com", "time": "Fri Feb 08 04:18:39 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 08 09:22:24 2008 -0800" }, "message": "intel-iommu: fault_reason index cleanup\n\nFix an off by one bug in the fault reason string reporting function, and\nclean up some of the code around this buglet.\n\n[akpm@linux-foundation.org: cleanup]\nSigned-off-by: mark gross \u003cmgross@linux.intel.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3460a6d9cef9ac2aa997da7eff7ff1c8291b361c", "tree": "3cf7eb916456d781d2edb135f9069f7c94d10085", "parents": [ "7d3b03ce7bff9d39ebaee1bb8de1968c4434b883" ], "author": { "name": "Keshavamurthy, Anil S", "email": "anil.s.keshavamurthy@intel.com", "time": "Sun Oct 21 16:41:54 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Oct 22 08:13:19 2007 -0700" }, "message": "Intel IOMMU: DMAR fault handling support\n\nMSI interrupt handler registrations and fault handling support for Intel-IOMMU\nhadrware.\n\nThis patch enables the MSI interrupts for the DMA remapping units and in the\ninterrupt handler read the fault cause and outputs the same on to the console.\n\nSigned-off-by: Anil S Keshavamurthy \u003canil.s.keshavamurthy@intel.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Muli Ben-Yehuda \u003cmuli@il.ibm.com\u003e\nCc: \"Siddha, Suresh B\" \u003csuresh.b.siddha@intel.com\u003e\nCc: Arjan van de Ven \u003carjan@infradead.org\u003e\nCc: Ashok Raj \u003cashok.raj@intel.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Greg KH \u003cgreg@kroah.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ba39592764ed20cee09aae5352e603a27bf56b0d", "tree": "efe7ec88bbd4d6b08b639830352c68411a7ef7fb", "parents": [ "f8de50eb6b085572ea773f26e066835ea3d3028b" ], "author": { "name": "Keshavamurthy, Anil S", "email": "anil.s.keshavamurthy@intel.com", "time": "Sun Oct 21 16:41:49 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Oct 22 08:13:18 2007 -0700" }, "message": "Intel IOMMU: Intel IOMMU driver\n\nActual intel IOMMU driver. Hardware spec can be found at:\nhttp://www.intel.com/technology/virtualization\n\nThis driver sets X86_64 \u0027dma_ops\u0027, so hook into standard DMA APIs. In this\nway, PCI driver will get virtual DMA address. This change is transparent to\nPCI drivers.\n\n[akpm@linux-foundation.org: remove unneeded cast]\n[akpm@linux-foundation.org: build fix]\n[bunk@stusta.de: fix duplicate CONFIG_DMAR Makefile line]\nSigned-off-by: Anil S Keshavamurthy \u003canil.s.keshavamurthy@intel.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Muli Ben-Yehuda \u003cmuli@il.ibm.com\u003e\nCc: \"Siddha, Suresh B\" \u003csuresh.b.siddha@intel.com\u003e\nCc: Arjan van de Ven \u003carjan@infradead.org\u003e\nCc: Ashok Raj \u003cashok.raj@intel.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Greg KH \u003cgreg@kroah.com\u003e\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "10e5247f40f3bf7508a0ed2848c9cae37bddf4bc", "tree": "adca606f00ebcbdbdc5c474f012105d7e59152f6", "parents": [ "89910cccb8fec0c1140d33a743e72a712efd4f05" ], "author": { "name": "Keshavamurthy, Anil S", "email": "anil.s.keshavamurthy@intel.com", "time": "Sun Oct 21 16:41:41 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Oct 22 08:13:18 2007 -0700" }, "message": "Intel IOMMU: DMAR detection and parsing logic\n\nThis patch supports the upcomming Intel IOMMU hardware a.k.a. Intel(R)\nVirtualization Technology for Directed I/O Architecture and the hardware spec\nfor the same can be found here\nhttp://www.intel.com/technology/virtualization/index.htm\n\nFAQ! (questions from akpm, answers from ak)\n\n\u003e So... what\u0027s all this code for?\n\u003e\n\u003e I assume that the intent here is to speed things up under Xen, etc?\n\nYes in some cases, but not this code. That would be the Xen version of this\ncode that could potentially assign whole devices to guests. I expect this to\nbe only useful in some special cases though because most hardware is not\nvirtualizable and you typically want an own instance for each guest.\n\nOk at some point KVM might implement this too; i likely would use this code\nfor this.\n\n\u003e Do we\n\u003e have any benchmark results to help us to decide whether a merge would be\n\u003e justified?\n\nThe main advantage for doing it in the normal kernel is not performance, but\nmore safety. Broken devices won\u0027t be able to corrupt memory by doing random\nDMA.\n\nUnfortunately that doesn\u0027t work for graphics yet, for that need user space\ninterfaces for the X server are needed.\n\nThere are some potential performance benefits too:\n\n- When you have a device that cannot address the complete address range an\n IOMMU can remap its memory instead of bounce buffering. Remapping is likely\n cheaper than copying.\n\n- The IOMMU can merge sg lists into a single virtual block. This could\n potentially speed up SG IO when the device is slow walking SG lists. [I\n long ago benchmarked 5% on some block benchmark with an old MPT Fusion; but\n it probably depends a lot on the HBA]\n\nAnd you get better driver debugging because unexpected memory accesses from\nthe devices will cause a trappable event.\n\n\u003e\n\u003e Does it slow anything down?\n\nIt adds more overhead to each IO so yes.\n\nThis patch:\n\nAdd support for early detection and parsing of DMAR\u0027s (DMA Remapping) reported\nto OS via ACPI tables.\n\nDMA remapping(DMAR) devices support enables independent address translations\nfor Direct Memory Access(DMA) from Devices. These DMA remapping devices are\nreported via ACPI tables and includes pci device scope covered by these DMA\nremapping device.\n\nFor detailed info on the specification of \"Intel(R) Virtualization Technology\nfor Directed I/O Architecture\" please see\nhttp://www.intel.com/technology/virtualization/index.htm\n\nSigned-off-by: Anil S Keshavamurthy \u003canil.s.keshavamurthy@intel.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Muli Ben-Yehuda \u003cmuli@il.ibm.com\u003e\nCc: \"Siddha, Suresh B\" \u003csuresh.b.siddha@intel.com\u003e\nCc: Arjan van de Ven \u003carjan@infradead.org\u003e\nCc: Ashok Raj \u003cashok.raj@intel.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Greg KH \u003cgreg@kroah.com\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" } ] }