)]}' { "log": [ { "commit": "c44e3ed539e4fc17d6bcb5eaecb894a94de4cc5f", "tree": "dbc31370fbc5196e090708341f3ca4c4dca7f41e", "parents": [ "7dc3ca39cb1e22eedbf1207ff9ac7bf682fc0f6d", "5095f59bda6793a7b8f0856096d6893fe98e0e51" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:51:15 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:51:15 2009 -0700" }, "message": "Merge branch \u0027x86-cpu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-cpu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86: cpu_debug: Remove model information to reduce encoding-decoding\n x86: fixup numa_node information for AMD CPU northbridge functions\n x86: k8 convert node_to_k8_nb_misc() from a macro to an inline function\n x86: cacheinfo: complete L2/L3 Cache and TLB associativity field definitions\n x86/docs: add description for cache_disable sysfs interface\n x86: cacheinfo: disable L3 ECC scrubbing when L3 cache index is disabled\n x86: cacheinfo: replace sysfs interface for cache_disable feature\n x86: cacheinfo: use cached K8 NB_MISC devices instead of scanning for it\n x86: cacheinfo: correct return value when cache_disable feature is not active\n x86: cacheinfo: use L3 cache index disable feature only for CPUs that support it\n" }, { "commit": "7dc3ca39cb1e22eedbf1207ff9ac7bf682fc0f6d", "tree": "6303897c21de6d7c39e14160b5c0d5f5548d2cee", "parents": [ "aa98936e4f423dc2706771368598b04870059d14", "a4046f8d299e00e9855ae292527c2d66a42670eb" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:49:36 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:49:36 2009 -0700" }, "message": "Merge branch \u0027x86-cleanups-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-cleanups-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86, nmi: Use predefined numbers instead of hardcoded one\n x86: asm/processor.h: remove double declaration\n x86, mtrr: replace MTRRdefType_MSR with msr-index\u0027s MSR_MTRRdefType\n x86, mtrr: replace MTRRfix4K_C0000_MSR with msr-index\u0027s MSR_MTRRfix4K_C0000\n x86, mtrr: remove mtrr MSRs double declaration\n x86, mtrr: replace MTRRfix16K_80000_MSR with msr-index\u0027s MSR_MTRRfix16K_80000\n x86, mtrr: replace MTRRfix64K_00000_MSR with msr-index\u0027s MSR_MTRRfix64K_00000\n x86, mtrr: replace MTRRcap_MSR with msr-index\u0027s MSR_MTRRcap\n x86: mce: remove duplicated #include\n x86: msr-index.h remove duplicate MSR C001_0015 declaration\n x86: clean up arch/x86/kernel/tsc_sync.c a bit\n x86: use symbolic name for VM86_SIGNAL when used as vm86 default return\n x86: added \u0027ifndef _ASM_X86_IOMAP_H\u0027 to iomap.h\n x86: avoid multiple declaration of kstack_depth_to_print\n x86: vdso/vma.c declare vdso_enabled and arch_setup_additional_pages before they get used\n x86: clean up declarations and variables\n x86: apic/x2apic_cluster.c x86_cpu_to_logical_apicid should be static\n x86 early quirks: eliminate unused function\n" }, { "commit": "aa98936e4f423dc2706771368598b04870059d14", "tree": "5b503225ee28f4b9648354db54eb29f4c097c140", "parents": [ "082b63ae45e7d14e15995dedd782ec7344596fb2", "0c23590f00f85467b318ad0c20c36796a5bd4c60" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:49:10 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:49:10 2009 -0700" }, "message": "Merge branch \u0027x86-asm-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-asm-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86, 64-bit: ifdef out struct thread_struct::ip\n x86, 32-bit: ifdef out struct thread_struct::fs\n x86: clean up alternative.h\n" }, { "commit": "99e97b860e14c64760855198e91d1166697131a7", "tree": "fadc8368c3f784bff92fba82d983e7861559cf9d", "parents": [ "82782ca77d1bfb32b0334cce40a25b91bd8ec016", "f04d82b7e0c63d0251f9952a537a4bc4d73aa1a9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:32:59 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:32:59 2009 -0700" }, "message": "Merge branch \u0027sched-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027sched-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n sched: fix typo in sched-rt-group.txt file\n ftrace: fix typo about map of kernel priority in ftrace.txt file.\n sched: properly define the sched_group::cpumask and sched_domain::span fields\n sched, timers: cleanup avenrun users\n sched, timers: move calc_load() to scheduler\n sched: Don\u0027t export sched_mc_power_savings on multi-socket single core system\n sched: emit thread info flags with stack trace\n sched: rt: document the risk of small values in the bandwidth settings\n sched: Replace first_cpu() with cpumask_first() in ILB nomination code\n sched: remove extra call overhead for schedule()\n sched: use group_first_cpu() instead of cpumask_first(sched_group_cpus())\n wait: don\u0027t use __wake_up_common()\n sched: Nominate a power-efficient ilb in select_nohz_balancer()\n sched: Nominate idle load balancer from a semi-idle package.\n sched: remove redundant hierarchy walk in check_preempt_wakeup\n" }, { "commit": "82782ca77d1bfb32b0334cce40a25b91bd8ec016", "tree": "d8c73212af80ed9aa314612e2b8b9e6cf74c47f7", "parents": [ "f0d5e12bd42b7173ebbbf59279c867605f859814", "6799687a53a28536fd027ccb644833f66a778925" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:30:41 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:30:41 2009 -0700" }, "message": "Merge branch \u0027x86-kbuild-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-kbuild-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (46 commits)\n x86, boot: add new generated files to the appropriate .gitignore files\n x86, boot: correct the calculation of ZO_INIT_SIZE\n x86-64: align __PHYSICAL_START, remove __KERNEL_ALIGN\n x86, boot: correct sanity checks in boot/compressed/misc.c\n x86: add extension fields for bootloader type and version\n x86, defconfig: update kernel position parameters\n x86, defconfig: update to current, no material changes\n x86: make CONFIG_RELOCATABLE the default\n x86: default CONFIG_PHYSICAL_START and CONFIG_PHYSICAL_ALIGN to 16 MB\n x86: document new bzImage fields\n x86, boot: make kernel_alignment adjustable; new bzImage fields\n x86, boot: remove dead code from boot/compressed/head_*.S\n x86, boot: use LOAD_PHYSICAL_ADDR on 64 bits\n x86, boot: make symbols from the main vmlinux available\n x86, boot: determine compressed code offset at compile time\n x86, boot: use appropriate rep string for move and clear\n x86, boot: zero EFLAGS on 32 bits\n x86, boot: set up the decompression stack as early as possible\n x86, boot: straighten out ranges to copy/zero in compressed/head*.S\n x86, boot: stylistic cleanups for boot/compressed/head_64.S\n ...\n\nFixed trivial conflict in arch/x86/configs/x86_64_defconfig manually\n" }, { "commit": "f0d5e12bd42b7173ebbbf59279c867605f859814", "tree": "f4018a726ecd2cf520afdf27210bfec1f3181718", "parents": [ "0fea615e526b4b7eff0363ee02d5753e5f924089", "103428e57be323c3c5545db8ad12667099bc6005" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:25:41 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:25:41 2009 -0700" }, "message": "Merge branch \u0027irq-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027irq-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (76 commits)\n x86, apic: Fix dummy apic read operation together with broken MP handling\n x86, apic: Restore irqs on fail paths\n x86: Print real IOAPIC version for x86-64\n x86: enable_update_mptable should be a macro\n sparseirq: Allow early irq_desc allocation\n x86, io-apic: Don\u0027t mark pin_programmed early\n x86, irq: don\u0027t call mp_config_acpi_gsi() if update_mptable is not enabled\n x86, irq: update_mptable needs pci_routeirq\n x86: don\u0027t call read_apic_id if !cpu_has_apic\n x86, apic: introduce io_apic_irq_attr\n x86/pci: add 4 more return parameters to IO_APIC_get_PCI_irq_vector(), fix\n x86: read apic ID in the !acpi_lapic case\n x86: apic: Fixmap apic address even if apic disabled\n x86: display extended apic registers with print_local_APIC and cpu_debug code\n x86: read apic ID in the !acpi_lapic case\n x86: clean up and fix setup_clear/force_cpu_cap handling\n x86: apic: Check rev 3 fadt correctly for physical_apic bit\n x86/pci: update pirq_enable_irq() to setup io apic routing\n x86/acpi: move setup io apic routing out of CONFIG_ACPI scope\n x86/pci: add 4 more return parameters to IO_APIC_get_PCI_irq_vector()\n ...\n" }, { "commit": "0fea615e526b4b7eff0363ee02d5753e5f924089", "tree": "306e87e03c0529eec05b6a481241057edf18b0ff", "parents": [ "0de51088e6a82bc8413d3ca9e28bbca2788b5b53" ], "author": { "name": "Harald Welte", "email": "HaraldWelte@viatech.com", "time": "Mon Jun 08 18:29:36 2009 +0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:22:44 2009 -0700" }, "message": "CPUFREQ: Mark e_powersaver driver as EXPERIMENTAL and DANGEROUS\n\nThe e_powersaver driver for VIA\u0027s C7 CPU\u0027s needs to be marked as\nDANGEROUS as it configures the CPU to power states that are out\nof specification.\n\nAccording to Centaur, all systems with C7 and Nano CPU\u0027s support\nthe ACPI p-state method. Thus, the acpi-cpufreq driver should\nbe used instead.\n\nSigned-off-by: Harald Welte \u003cHaraldWelte@viatech.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0de51088e6a82bc8413d3ca9e28bbca2788b5b53", "tree": "3003393dd3e60639b61200feefc13fc6bf5d28e0", "parents": [ "2b83868723d090078ac0e2120e06a1cc94dbaef0" ], "author": { "name": "Harald Welte", "email": "HaraldWelte@viatech.com", "time": "Mon Jun 08 18:27:54 2009 +0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jun 10 15:22:44 2009 -0700" }, "message": "CPUFREQ: Enable acpi-cpufreq driver for VIA/Centaur CPUs\n\nThe VIA/Centaur C7, C7-M and Nano CPU\u0027s all support ACPI based cpu p-states\nusing a MSR interface. The Linux driver just never made use of it, since in\naddition to the check for the EST flag it also checked if the vendor is Intel.\n\nSigned-off-by: Harald Welte \u003cHaraldWelte@viatech.com\u003e\n[ Removed the vendor checks entirely - Linus ]\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "eaa958402ea40851097d051f52ba1bb7a885efe9", "tree": "9187f59ff0ee6ac138b5c81a2212bc10f46d04a5", "parents": [ "0281b5dc0350cbf6dd21ed558a33cccce77abc02" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Sat Jun 06 14:51:36 2009 -0700" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Tue Jun 09 22:30:27 2009 +0930" }, "message": "cpumask: alloc zeroed cpumask for static cpumask_var_ts\n\nThese are defined as static cpumask_var_t so if MAXSMP is not used,\nthey are cleared already. Avoid surprises when MAXSMP is enabled.\n\nSigned-off-by: Yinghai Lu \u003cyinghai.lu@kernel.org\u003e\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\n" }, { "commit": "a4046f8d299e00e9855ae292527c2d66a42670eb", "tree": "c795507c475a133fd66fe995938b6e55e6d5dbde", "parents": [ "4aee2ad461889132bfb5a1518a9580d00e17008c" ], "author": { "name": "Cyrill Gorcunov", "email": "gorcunov@openvz.org", "time": "Sun Jun 07 12:19:37 2009 +0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jun 07 16:22:02 2009 +0200" }, "message": "x86, nmi: Use predefined numbers instead of hardcoded one\n\n[ Impact: cleanup ]\n\nSigned-off-by: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nLKML-Reference: \u003c20090607081937.GC4547@lenovo\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "103428e57be323c3c5545db8ad12667099bc6005", "tree": "8f8275235b7ef7ff13bf3a2a7c9e13035ec61052", "parents": [ "3d58829b0510244596079c1d2f1762c53aef2e97" ], "author": { "name": "Cyrill Gorcunov", "email": "gorcunov@openvz.org", "time": "Sun Jun 07 16:48:40 2009 +0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jun 07 16:08:05 2009 +0200" }, "message": "x86, apic: Fix dummy apic read operation together with broken MP handling\n\nIngo Molnar reported that read_apic is buggy novadays:\n\n[ 0.000000] Using APIC driver default\n[ 0.000000] SMP: Allowing 1 CPUs, 0 hotplug CPUs\n[ 0.000000] Local APIC disabled by BIOS -- you can enable it with \"lapic\"\n[ 0.000000] APIC: disable apic facility\n[ 0.000000] ------------[ cut here ]------------\n[ 0.000000] WARNING: at arch/x86/kernel/apic/apic.c:254 native_apic_read_dummy+0x2d/0x3b()\n[ 0.000000] Hardware name: HP OmniBook PC\n\nIndeed we still rely on apic-\u003eread operation for SMP compiled\nkernel. And instead of disfigure the SMP code with #ifdef we\nallow to call apic-\u003eread. To capture any unexpected results\nwe check for apic-\u003eread being called for sane reason via\nWARN_ON_ONCE but(!) instead of OR we should use AND logical\noperation (thanks Yinghai for spotting the root of the problem).\n\nAlong with that we could be have bad MP table and we are\nto fix it that way no SMP started and no complains about\nBIOS bug if apic was just disabled via command line.\n\nSigned-off-by: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nCc: Yinghai Lu \u003cyinghai@kernel.org\u003e\nLKML-Reference: \u003c20090607124840.GD4547@lenovo\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5095f59bda6793a7b8f0856096d6893fe98e0e51", "tree": "07678e9f4dbe337e3dd5b588fceda22af24fb5ca", "parents": [ "5f4457a4f62cc9d78e04c0eb12ff0540899aad89" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinder@kernel.org", "time": "Fri Jun 05 23:27:17 2009 +0530" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jun 07 12:22:56 2009 +0200" }, "message": "x86: cpu_debug: Remove model information to reduce encoding-decoding\n\nRemove model information, encoding/decoding and reduce bookkeeping.\n\nThis, besides removing a lot of code and cleaning up the code, also\nenables these features on many more CPUs that were enumerated before.\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nCc: Alan Cox \u003calan@lxorguk.ukuu.org.uk\u003e\nLKML-Reference: \u003c1244224637.8212.6.camel@ht.satnam\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5f4457a4f62cc9d78e04c0eb12ff0540899aad89", "tree": "0b973d527ea6b2ae31e08da0746b4965a3c5a6d8", "parents": [ "9b94b3a19b13e094c10f65f24bc358f6ffe4eacd", "b87297fb405ef13cac375f202d114323b076a56d" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jun 07 12:22:15 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Jun 07 12:22:15 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into x86/cpu\n" }, { "commit": "ccc0d38ec13d4649d4168c1db590137df53ad783", "tree": "8512448edfcaeb7a0604a4872a380ff233c1f50a", "parents": [ "f07502dae230a2c3b65381fd1b06e8a18b2c7525", "75e613cdc7bb2ba3795b1bc3ddf19476c767ba68" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jun 06 14:33:54 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jun 06 14:33:54 2009 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6:\n x86/pci: fix mmconfig detection with 32bit near 4g\n PCI: use fixed-up device class when configuring device\n" }, { "commit": "2c701b10283b58937201004276319ef9d9051b5d", "tree": "20ff3bbfd1f791ac356bc0c8d043f04b0d14cd47", "parents": [ "edaba2c5334492f82d39ec35637c6dea5176a977" ], "author": { "name": "Dave Jones", "email": "davej@codemonkey.org.uk", "time": "Fri Jun 05 12:37:07 2009 -0400" }, "committer": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Fri Jun 05 13:25:25 2009 -0400" }, "message": "[CPUFREQ] powernow-k8: check space_id of _PCT registers to be FFH\n\nThe powernow-k8 driver checks to see that the Performance Control/Status\nRegisters are declared as FFH (functional fixed hardware) by the BIOS.\nHowever, this check got broken in the commit:\n 0e64a0c982c06a6b8f5e2a7f29eb108fdf257b2f\n [CPUFREQ] checkpatch cleanups for powernow-k8\n\nFix based on an original patch from Naga Chumbalkar.\n\nSigned-off-by: Naga Chumbalkar \u003cnagananda.chumbalkar@hp.com\u003e\nCc: Mark Langsdorf \u003cmark.langsdorf@amd.com\u003e\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\n" }, { "commit": "2cb7878a3a4341d1faa208de962d66f0817d3e7a", "tree": "6639c4dcce9f213a58144e0c0431a339b69c42b2", "parents": [ "9fa7eb283c5cdc2b0f4a8cfe6387ed82e5e9a3d3" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Wed Jun 03 14:52:24 2009 +0930" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jun 04 11:50:06 2009 -0700" }, "message": "lguest: fix \u0027unhandled trap 13\u0027 with CONFIG_CC_STACKPROTECTOR\n\nWe don\u0027t set up the canary; let\u0027s disable stack protector on boot.c so\nwe can get into lguest_init, then set it up. As a side effect,\nswitch_to_new_gdt() sets up %fs for us properly too.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nAcked-by: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "75e613cdc7bb2ba3795b1bc3ddf19476c767ba68", "tree": "14864c1ad72554fa1061dbefd2e97b549d0a2507", "parents": [ "f79b1b146b52765ee38bfb91bb14eb850fa98017" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed Jun 03 00:13:13 2009 -0700" }, "committer": { "name": "Jesse Barnes", "email": "jbarnes@virtuousgeek.org", "time": "Thu Jun 04 11:31:13 2009 +0100" }, "message": "x86/pci: fix mmconfig detection with 32bit near 4g\n\nPascal reported and bisected a commit:\n|\tx86/PCI: don\u0027t call e820_all_mapped with -1 in the mmconfig case\n\nwhich broke one system system.\n\nACPI: Using IOAPIC for interrupt routing\nPCI: MCFG configuration 0: base f0000000 segment 0 buses 0 - 255\nPCI: MCFG area at f0000000 reserved in ACPI motherboard resources\nPCI: Using MMCONFIG for extended config space\n\nit didn\u0027t have\nPCI: updated MCFG configuration 0: base f0000000 segment 0 buses 0 - 63\nanymore, and try to use 0xf000000 - 0xffffffff for mmconfig\n\nFor 32bit, mcfg_res-\u003eend could be 32bit only (if 64 resources aren\u0027t used)\nSo use end - 1 to pass the value in mcfg-\u003eend to avoid overflow.\n\nWe don\u0027t need to worry about the e820 path, they are always 64 bit.\n\nReported-by: Pascal Terjan \u003cpterjan@mandriva.com\u003e\nBisected-by: Pascal Terjan \u003cpterjan@mandriva.com\u003e\nTested-by: Pascal Terjan \u003cpterjan@mandriva.com\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: stable@kernel.org\nSigned-off-by: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\n" }, { "commit": "6799687a53a28536fd027ccb644833f66a778925", "tree": "fc7bcab7ac90ce1a23b6f83b57c0a31e96859783", "parents": [ "c6ac4c18fbc92a26df71ece609b082bc3099676b" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Tue Jun 02 08:23:58 2009 +0200" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Tue Jun 02 21:13:30 2009 -0700" }, "message": "x86, boot: add new generated files to the appropriate .gitignore files\n\ngit status complains of untracked (generated) files in arch/x86/boot..\n\n# Untracked files:\n# (use \"git add \u003cfile\u003e...\" to include in what will be committed)\n#\n# ../../arch/x86/boot/compressed/mkpiggy\n# ../../arch/x86/boot/compressed/piggy.S\n# ../../arch/x86/boot/compressed/vmlinux.lds\n# ../../arch/x86/boot/voffset.h\n# ../../arch/x86/boot/zoffset.h\n\n..so adjust .gitignore files accordingly.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "3d58829b0510244596079c1d2f1762c53aef2e97", "tree": "ab80e980013ca517351abb3ee601d7d5ae66f124", "parents": [ "58f892e022e88438183c48661dcdc6a2997dab99" ], "author": { "name": "Jiri Slaby", "email": "jirislaby@gmail.com", "time": "Thu May 28 09:54:47 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jun 02 02:48:59 2009 +0200" }, "message": "x86, apic: Restore irqs on fail paths\n\nlapic_resume forgets to restore interrupts on fail paths.\nFix that.\n\nSigned-off-by: Jiri Slaby \u003cjirislaby@gmail.com\u003e\nAcked-by: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nLKML-Reference: \u003c1243497289-18591-1-git-send-email-jirislaby@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "58f892e022e88438183c48661dcdc6a2997dab99", "tree": "faaa745b6c1bf160e873a924395d1231c109def6", "parents": [ "ee4c24a5c9b530481394132c8dbc10572d57c075" ], "author": { "name": "Naga Chumbalkar", "email": "nagananda.chumbalkar@hp.com", "time": "Tue May 26 21:48:07 2009 +0000" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jun 02 02:03:18 2009 +0200" }, "message": "x86: Print real IOAPIC version for x86-64\n\nFix the fact that the IOAPIC version number in the x86_64 code path always\ngets assigned to 0, instead of the correct value.\n\nBefore the patch: (from \"dmesg\" output):\n\n ACPI: IOAPIC (id[0x08] address[0xfec00000] gsi_base[0])\n IOAPIC[0]: apic_id 8, version 0, address 0xfec00000, GSI 0-23 \u003c---\n\n After the patch:\n ACPI: IOAPIC (id[0x08] address[0xfec00000] gsi_base[0])\n IOAPIC[0]: apic_id 8, version 32, address 0xfec00000, GSI 0-23 \u003c---\n\nHistory:\n\nio_apic_get_version() was compiled out of the x86_64 code path in the commit\nf2c2cca3acef8b253a36381d9b469ad4fb08563a:\n\nAuthor: Andi Kleen \u003cak@suse.de\u003e\nDate: Tue Sep 26 10:52:37 2006 +0200\n\n [PATCH] Remove APIC version/cpu capability mpparse checking/printing\n\n ACPI went to great trouble to get the APIC version and CPU capabilities\n of different CPUs before passing them to the mpparser. But all\n that data was used was to print it out. Actually it even faked some data\n based on the boot cpu, not on the actual CPU being booted.\n\n Remove all this code because it\u0027s not needed.\n\n Cc: len.brown@intel.com\n\nAt the time, the IOAPIC version number was deliberately not printed\nin the x86_64 code path. However, after the x86 and x86_64 files were\nmerged, the net result is that the IOAPIC version is printed incorrectly\nin the x86_64 code path.\n\nThe patch below provides a fix. I have tested it with acpi, and with\nacpi\u003doff, and did not see any problems.\n\nSigned-off-by: Naga Chumbalkar \u003cnagananda.chumbalkar@hp.com\u003e\nAcked-by: Yinghai Lu \u003cyhlu.kernel@gmail.com\u003e\nLKML-Reference: \u003c20090416014230.4885.94926.sendpatchset@localhost.localdomain\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n*************************\n" }, { "commit": "ee4c24a5c9b530481394132c8dbc10572d57c075", "tree": "91c580724b9de9f2ae09bb375fc33f4df24b55c0", "parents": [ "3d58f48ba05caed9118bce62b3047f8683438835", "3e0c373749d7eb5b354ac0b043f2b2cdf84eefef" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jun 01 22:29:35 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jun 01 22:30:01 2009 +0200" }, "message": "Merge branch \u0027x86/cpufeature\u0027 into irq/numa\n\nMerge reason: irq/numa didnt build because this commit:\n\n 2759c32: x86: don\u0027t call read_apic_id if !cpu_has_apic\n\nHad a dependency on x86/cpufeature changes. Pull in that\n(small) branch to fix the dependency.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3d58f48ba05caed9118bce62b3047f8683438835", "tree": "94c911034f0e14ded73d3e9e6e9f8e22b6cad822", "parents": [ "abfe0af9813153bae8c85d9bac966bafcb8ddab1", "d9244b5d2fbfe9fa540024b410047af13ceec90f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jun 01 21:06:21 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Jun 01 21:06:21 2009 +0200" }, "message": "Merge branch \u0027linus\u0027 into irq/numa\n\nConflicts:\n\tarch/mips/sibyte/bcm1480/irq.c\n\tarch/mips/sibyte/sb1250/irq.c\n\nMerge reason: we gathered a few conflicts plus update to latest upstream fixes.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "61c8c67e3ad67ea1d1360f2e88688bd942834756", "tree": "600aef70bb6ca109b98fa00db04ee6b2959bda0c", "parents": [ "21671b88be331fb9c95891d5ee7d2e940e6b024c" ], "author": { "name": "Joe Perches", "email": "joe@perches.com", "time": "Tue May 26 14:58:39 2009 -0700" }, "committer": { "name": "Len Brown", "email": "len.brown@intel.com", "time": "Fri May 29 21:26:26 2009 -0400" }, "message": "acpi-cpufreq: fix printk typo and indentation\n\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Len Brown \u003clen.brown@intel.com\u003e\n" }, { "commit": "32b154c0b0bae2879bf4e549d861caf1759a3546", "tree": "dbd2c6df9511ee400c5460ef714955d15b689cf4", "parents": [ "53b7479bbdaedcc7846c66fd608fe66f1b5aa35b" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Thu May 28 14:34:37 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 29 08:40:03 2009 -0700" }, "message": "x86: ignore VM_LOCKED when determining if hugetlb-backed page tables can be shared or not\n\nAddresses http://bugzilla.kernel.org/show_bug.cgi?id\u003d13302\n\nOn x86 and x86-64, it is possible that page tables are shared beween\nshared mappings backed by hugetlbfs. As part of this,\npage_table_shareable() checks a pair of vma-\u003evm_flags and they must match\nif they are to be shared. All VMA flags are taken into account, including\nVM_LOCKED.\n\nThe problem is that VM_LOCKED is cleared on fork(). When a process with a\nshared memory segment forks() to exec() a helper, there will be shared\nVMAs with different flags. The impact is that the shared segment is\nsometimes considered shareable and other times not, depending on what\nprocess is checking.\n\nWhat happens is that the segment page tables are being shared but the\ncount is inaccurate depending on the ordering of events. As the page\ntables are freed with put_page(), bad pmd\u0027s are found when some of the\nchildren exit. The hugepage counters also get corrupted and the Total and\nFree count will no longer match even when all the hugepage-backed regions\nare freed. This requires a reboot of the machine to \"fix\".\n\nThis patch addresses the problem by comparing all flags except VM_LOCKED\nwhen deciding if pagetables should be shared or not for hugetlbfs-backed\nmapping.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: \u003cstable@kernel.org\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: \u003cstarlight@binnacle.cx\u003e\nCc: Eric B Munson \u003cebmunson@us.ibm.com\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Andy Whitcroft \u003capw@canonical.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "abfe0af9813153bae8c85d9bac966bafcb8ddab1", "tree": "a19a364e427c0db6dad4f2245522ab8afda9e4c9", "parents": [ "948cd52906baf1f92aeea2f9b5c515db1b2e592a" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 20 00:37:40 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu May 28 01:59:05 2009 +0200" }, "message": "x86: enable_update_mptable should be a macro\n\ninstead of declaring one variant as an inline function...\nbecause other case is a variable\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nLKML-Reference: \u003c4A13B344.7030307@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cd86a536c81e9300d984327517548ca0652eebf9", "tree": "a9c197a9f9bb4f615b0fe19134f40ccc77ff8dd8", "parents": [ "ebd4c994d2f917dffec882e7a77c28c6b28758ac", "2171787be2e71ff71159857bfeb21398b61eb615" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 26 15:06:12 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 26 15:06:12 2009 -0700" }, "message": "Merge branch \u0027x86-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86: avoid back to back on_each_cpu in cpa_flush_array\n x86, relocs: ignore R_386_NONE in kernel relocation entries\n" }, { "commit": "2171787be2e71ff71159857bfeb21398b61eb615", "tree": "671bde892ae47316d9fbf2b5f105d6c365d07b60", "parents": [ "46176b4f6bac19454b7b5c35f68594b85850a600" ], "author": { "name": "Pallipadi, Venkatesh", "email": "venkatesh.pallipadi@intel.com", "time": "Tue May 26 10:33:35 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Tue May 26 13:12:12 2009 -0700" }, "message": "x86: avoid back to back on_each_cpu in cpa_flush_array\n\nCleanup cpa_flush_array() to avoid back to back on_each_cpu() calls.\n\n[ Impact: optimizes fix 0af48f42df15b97080b450d24219dd95db7b929a ]\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "ca446d06351992e4f1a7c1e5e99870ab4ec5188f", "tree": "fedb65e1059aa04f199d3d306c664674b1217971", "parents": [ "df1829770db415dc5a5ed5ada3bd70176c6f0a01" ], "author": { "name": "Andreas Herrmann", "email": "andreas.herrmann3@amd.com", "time": "Wed Apr 22 13:48:33 2009 +0200" }, "committer": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Tue May 26 12:04:51 2009 -0400" }, "message": "[CPUFREQ] powernow-k8: determine exact CPU frequency for HW Pstates\n\nSlightly modified by trenn@suse.de -\u003e only do this on fam 10h and fam 11h.\n\nCurrently powernow-k8 determines CPU frequency from ACPI PSS objects, but\naccording to AMD family 11h BKDG this frequency is just a rounded value:\n\n \"CoreFreq (MHz) \u003d The CPU COF specified by MSRC001_00[6B:64][CpuFid]\n rounded to the nearest 100 Mhz.\"\n\nAs a consequnce powernow-k8 reports wrong CPU frequency on some systems,\ne.g. on Turion X2 Ultra:\n\n powernow-k8: Found 1 AMD Turion(tm)X2 Ultra DualCore Mobile ZM-82\n processors (2 cpu cores) (version 2.20.00)\n powernow-k8: 0 : pstate 0 (2200 MHz)\n powernow-k8: 1 : pstate 1 (1100 MHz)\n powernow-k8: 2 : pstate 2 (600 MHz)\n\nBut this is wrong as frequency for Pstate2 is 550 MHz. x86info reports it\ncorrectly:\n\n #x86info -a |grep Pstate\n ...\n Pstate-0: fid\u003de, did\u003d0, vid\u003d24 (2200MHz)\n Pstate-1: fid\u003de, did\u003d1, vid\u003d30 (1100MHz)\n Pstate-2: fid\u003de, did\u003d2, vid\u003d3c (550MHz) (current)\n\nSolution is to determine the frequency directly from Pstate MSRs instead\nof using rounded values from ACPI table.\n\nSigned-off-by: Andreas Herrmann \u003candreas.herrmann3@amd.com\u003e\nSigned-off-by: Thomas Renninger \u003ctrenn@suse.de\u003e\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\n" }, { "commit": "df1829770db415dc5a5ed5ada3bd70176c6f0a01", "tree": "6c9862b0c5dc58ab8d0093985a4fc56b820c0a69", "parents": [ "b14893a62c73af0eca414cfed505b8c09efc613c" ], "author": { "name": "Thomas Renninger", "email": "trenn@suse.de", "time": "Wed Apr 22 13:48:32 2009 +0200" }, "committer": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Tue May 26 12:04:51 2009 -0400" }, "message": "[CPUFREQ] powernow-k8 cleanup msg if BIOS does not export ACPI _PSS cpufreq data\n\n- Make the message shorter and easier to grep for\n- Use printk_once instead of WARN_ONCE (functionality of these was mixed)\n\nSigned-off-by: Thomas Renninger \u003ctrenn@suse.de\u003e\nCc: Langsdorf, Mark \u003cmark.langsdorf@amd.com\u003e\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\n" }, { "commit": "d38e73e8dad454a5916f446b0d3523c1161ae95a", "tree": "52d2f4e2e2a04929c6fff29268b2db7c41214701", "parents": [ "4319503779060120fa5de9b8fde056603bb6e0fd" ], "author": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Thu Apr 23 13:36:12 2009 -0400" }, "committer": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Tue May 26 12:04:50 2009 -0400" }, "message": "[CPUFREQ] powernow-k7 build fix when ACPI\u003dn\n\narch/x86/kernel/cpu/cpufreq/powernow-k7.c:172: warning: \u0027invalidate_entry\u0027 defined but not used\n\nReported-by: Toralf Förster \u003ctoralf.foerster@gmx.de\u003e\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\n" }, { "commit": "4319503779060120fa5de9b8fde056603bb6e0fd", "tree": "d4e39fa9efd04be2aadb5eb30edb556759c8657d", "parents": [ "b18f1e21993f73f072b1e0859f942fb11afddcb1" ], "author": { "name": "Jarod Wilson", "email": "jwilson@fedoraproject.org", "time": "Fri Mar 06 20:24:57 2009 +0000" }, "committer": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Tue May 26 12:04:50 2009 -0400" }, "message": "[CPUFREQ] add atom family to p4-clockmod\n\nSome atom procs don\u0027t do freq scaling (such as the atom 330 on my own\nlittlefalls2 board). By adding the atom family here, we at least get\nthe benefit of passive cooling in a thermal emergency. Not sure how\nto see that its actually helping any, but the driver does bind and\nclaim its functioning on my atom 330.\n\nSigned-off-by: Jarod Wilson \u003cjarod@redhat.com\u003e\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\n" }, { "commit": "46176b4f6bac19454b7b5c35f68594b85850a600", "tree": "c67571802f614aa361726d513e9a8fcaee603fb1", "parents": [ "71c9d8b68b299bef614afc7907393564a9f1476f" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue May 26 14:42:40 2009 +0900" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 25 22:52:49 2009 -0700" }, "message": "x86, relocs: ignore R_386_NONE in kernel relocation entries\n\nFor relocatable 32bit kernels, boot/compressed/relocs.c processes\nrelocation entries in the kernel image and appends it to the kernel\nimage such that boot/compressed/head_32.S can relocate the kernel.\nThe kernel image is one statically linked object and only uses two\nrelocation types - R_386_PC32 and R_386_32, of the two only the latter\nneeds massaging during kernel relocation and thus handled by relocs.\nR_386_PC32 is ignored and all other relocation types are considered\nerror.\n\nWhen the target of a relocation resides in a discarded section,\nbinutils doesn\u0027t throw away the relocation record but nullifies it by\nchanging it to R_386_NONE, which unfortunately makes relocs fail.\n\nThe problem was triggered by yet out-of-tree x86 stack unwind patches\nbut given the binutils behavior, ignoring R_386_NONE is the right\nthing to do.\n\nThe problem has been tracked down to binutils behavior by Jan Beulich.\n\n[ Impact: fix build with certain binutils by ignoring R_386_NONE ]\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Jan Beulich \u003cJBeulich@novell.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c4A1B8150.40702@kernel.org\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "b18f1e21993f73f072b1e0859f942fb11afddcb1", "tree": "50c8a36a1518d43a4198afb304a05727609b24f7", "parents": [ "a0c1af135a93ee25b07cbc61762fb957fd2f3733", "a2edf57f510cce6a389cc14e58c6ad0a4296d6f9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon May 25 15:51:27 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon May 25 15:51:27 2009 -0700" }, "message": "Merge branch \u0027kvm-updates/2.6.30\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm\n\n* \u0027kvm-updates/2.6.30\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm:\n KVM: Fix PDPTR reloading on CR4 writes\n KVM: Make paravirt tlb flush also reload the PAE PDPTRs\n" }, { "commit": "a2edf57f510cce6a389cc14e58c6ad0a4296d6f9", "tree": "77fd1e5a86c32d483323c9dc64cdc30eaa3b349e", "parents": [ "a8cd0244e9cebcf9b358d24c7e7410062f3665cb" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun May 24 22:19:00 2009 +0300" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 25 20:00:53 2009 +0300" }, "message": "KVM: Fix PDPTR reloading on CR4 writes\n\nThe processor is documented to reload the PDPTRs while in PAE mode if any\nof the CR4 bits PSE, PGE, or PAE change. Linux relies on this\nbehaviour when zapping the low mappings of PAE kernels during boot.\n\nThe code already handled changes to CR4.PAE; augment it to also notice changes\nto PSE and PGE.\n\nThis triggered while booting an F11 PAE kernel; the futex initialization code\nruns before any CR3 reloads and writes to a NULL pointer; the futex subsystem\nended up uninitialized, killing PI futexes and pulseaudio which uses them.\n\nCc: stable@kernel.org\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "a8cd0244e9cebcf9b358d24c7e7410062f3665cb", "tree": "8e7da98d9fbcb5f86abfab5b1d6ab8b97294f801", "parents": [ "59a3759d0fe8d969888c741bb33f4946e4d3750d" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun May 24 22:15:25 2009 +0300" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 25 20:00:50 2009 +0300" }, "message": "KVM: Make paravirt tlb flush also reload the PAE PDPTRs\n\nThe paravirt tlb flush may be used not only to flush TLBs, but also\nto reload the four page-directory-pointer-table entries, as it is used\nas a replacement for reloading CR3. Change the code to do the entire\nCR3 reloading dance instead of simply flushing the TLB.\n\nCc: stable@kernel.org\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "71c9d8b68b299bef614afc7907393564a9f1476f", "tree": "ad92b85c7e8e6542391e5dbef4be71efc4d2a20d", "parents": [ "0af48f42df15b97080b450d24219dd95db7b929a" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Mon May 25 12:01:59 2009 +0900" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 25 05:37:55 2009 +0200" }, "message": "x86: Remove remap percpu allocator for the time being\n\nRemap percpu allocator has subtle bug when combined with page\nattribute changing. Remap percpu allocator aliases PMD pages for the\nfirst chunk and as pageattr doesn\u0027t know about the alias it ends up\nupdating page attributes of the original mapping thus leaving the\nalises in inconsistent state which might lead to subtle data\ncorruption. Please read the following threads for more information:\n\n http://thread.gmane.org/gmane.linux.kernel/835783\n\nThe following is the proposed fix which teaches pageattr about percpu\naliases.\n\n http://thread.gmane.org/gmane.linux.kernel/837157\n\nHowever, the above changes are deemed too pervasive for upstream\ninclusion for 2.6.30 release, so this patch essentially disables\nthe remap allocator for the time being.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nLKML-Reference: \u003c4A1A0A27.4050301@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "0af48f42df15b97080b450d24219dd95db7b929a", "tree": "f1746198024b2e93250c1b14855026ba0d769117", "parents": [ "0b827537e339c084ac9384df588969d400be9e0d" ], "author": { "name": "venkatesh.pallipadi@intel.com", "email": "venkatesh.pallipadi@intel.com", "time": "Fri May 22 13:23:38 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 22 13:33:59 2009 -0700" }, "message": "x86: cpa_flush_array wbinvd should be done on all CPUs\n\ncpa_flush_array seems to prefer wbinvd() over clflush at 4M threshold.\nclflush needs to be done on only one CPU as per instruction definition.\nwbinvd() however, should be done on all CPUs.\n\n[ Impact: fix missing flush which could cause data corruption ]\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: Suresh Siddha \u003csuresh.b.siddha@intel.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "0b827537e339c084ac9384df588969d400be9e0d", "tree": "26ae170ba3fd7077c28613f8cc7aba7d1b133430", "parents": [ "0c752a93353d9b17dbe148312d732fbe06d235e1" ], "author": { "name": "venkatesh.pallipadi@intel.com", "email": "venkatesh.pallipadi@intel.com", "time": "Fri May 22 13:23:37 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 22 13:33:27 2009 -0700" }, "message": "x86: bugfix wbinvd() model check instead of family check\n\nwbinvd is supported on all CPUs 486 or later. But,\npageattr.c is checking x86_model \u003e\u003d 4 before wbinvd(), which looks like\nan oversight bug. It was first introduced at one place by changeset\nd7c8f21a8cad0228c7c5ce2bb6dbd95d1ee49d13 and got copied over to second\nplace in the same file later.\n\n[ Impact: fix missing cache flush on early-model CPUs, potential data corruption ]\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "0c752a93353d9b17dbe148312d732fbe06d235e1", "tree": "944b37d214dd478abc1c5d2b51573ec87be59c63", "parents": [ "bca23dba760d6705c013f89113c46570378fb626" ], "author": { "name": "Suresh Siddha", "email": "suresh.b.siddha@intel.com", "time": "Fri May 22 12:17:45 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 22 13:10:54 2009 -0700" }, "message": "x86: introduce noxsave boot parameter\n\nIntroduce \"noxsave\" boot parameter which will disable the cpu\u0027s xsave/xrstor\ncapabilities. Useful for debugging and working around xsave related issues.\n\n[ Impact: make it possible to debug problems in the field ]\n\nSigned-off-by: Suresh Siddha \u003csuresh.b.siddha@intel.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "bca23dba760d6705c013f89113c46570378fb626", "tree": "31f52293a54d418ff347e7de20ffc702acf554be", "parents": [ "88dff4936c0a5fa53080cca68dc963a8a2a674b0" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Thu May 21 11:46:16 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 22 11:14:02 2009 -0700" }, "message": "x86, setup: revert ACPI 3 E820 extended attributes support\n\nRemove ACPI 3 E820 extended memory attributes support. At least one\nvendor actively set all the flags to zero, but left ECX on return at\n24. This bug may be present in other BIOSes.\n\nThe breakage functionally means the ACPI 3 flags are probably\ncompletely useless, and that no OS any time soon is going to rely on\ntheir existence. Therefore, drop support completely. We may want to\nrevisit this question in the future, if we find ourselves actually\nneeding the flags.\n\nThis reverts all or part of the following checkins:\n\n cd670599b7b00d9263f6f11a05c0edeb9cbedaf3\n c549e71d073a6e9a4847497344db28a784061455\n\nHowever, retain the part from the latter commit that copies e820 into\na temporary buffer; that is an unrelated BIOS workaround. Put in a\ncomment to explain that part.\n\nSee https://bugzilla.redhat.com/show_bug.cgi?id\u003d499396 for some\nadditional information.\n\n[ Impact: detect all memory on affected machines ]\n\nReported-by: Thomas J. Baker \u003ctjb@unh.edu\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\nAcked-by: Len Brown \u003clen.brown@intel.com\u003e\nCc: Chuck Ebbert \u003ccebbert@redhat.com\u003e\nCc: Kyle McMartin \u003ckmcmartin@redhat.com\u003e\nCc: Matt Domsch \u003cmatt_domsch@dell.com\u003e\n" }, { "commit": "88dff4936c0a5fa53080cca68dc963a8a2a674b0", "tree": "699318cdd98daf4773cab5a27d432f11078faace", "parents": [ "279e677faa775ad16e75c32e1bf4a37f8158bc61" ], "author": { "name": "Zhang Rui", "email": "rui.zhang@intel.com", "time": "Fri May 22 11:35:50 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 22 09:11:30 2009 +0200" }, "message": "x86: DMI match for the Sony VGN-Z540N as it needs BIOS reboot\n\nx86: DMI match for the Sony VGN-Z540N as it needs BIOS reboot,\nsee:\n\n http://bugzilla.kernel.org/show_bug.cgi?id\u003d12901\n\n[ Impact: fix hung reboot on certain systems ]\n\nSigned-off-by: Zhang Rui \u003crui.zhang@intel.com\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c1242963350.32574.53.camel@rzhang-dt\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c6ac4c18fbc92a26df71ece609b082bc3099676b", "tree": "577533e27b1217800b44ee43d7d4870f46be3e8e", "parents": [ "c4f68236e41641494f9c8a418ccc0678c335bbb5" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Wed May 20 11:26:09 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Wed May 20 11:26:09 2009 -0700" }, "message": "x86, boot: correct the calculation of ZO_INIT_SIZE\n\nCorrect the calculation of ZO_INIT_SIZE (the amount of memory we need\nduring decompression). One symbol (ZO_startup_32) was missing from\nzoffset.h, and another (ZO_z_extract_offset) was misspelled.\n\n[ Impact: build fix ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "4c6f18fc81565967da20f2d4a3922cdba33f8e2b", "tree": "f9d801323a84f6a77eaec35840d08d1714c1ddae", "parents": [ "f1bdb523880c7f6990e9e8e50b0fc972ca475e84" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Mon May 18 10:23:28 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 19 14:26:51 2009 +0200" }, "message": "x86, io-apic: Don\u0027t mark pin_programmed early\n\nPeter bisected that:\n\n| commit b9c61b70075c87a8612624736faf4a2de5b1ed30\n| Date: Wed May 6 10:10:06 2009 -0700\n|\n| x86/pci: update pirq_enable_irq() to setup io apic routing\n|\n| So we can set io apic routing only when enabling the device irq.\n\nwrecked his opteron box, ata1 interrupts fail to get through.\n\nata1 is using irq 11:\n\n[ 1.451839] sata_svw 0000:01:0e.0: version 2.3\n[ 1.456333] sata_svw 0000:01:0e.0: PCI INT A -\u003e GSI 11 (level, low) -\u003e IRQ 11\n[ 1.463639] scsi0 : sata_svw\n[ 1.466949] scsi1 : sata_svw\n[ 1.470022] scsi2 : sata_svw\n[ 1.473090] scsi3 : sata_svw\n[ 1.476112] ata1: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe000 irq 11\n[ 1.483490] ata2: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe100 irq 11\n[ 1.490870] ata3: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe200 irq 11\n[ 1.498247] ata4: SATA max UDMA/133 mmio m8192@0xff3fe000 port 0xff3fe300 irq 11\n\nthat pin is overlapped with pin with legacy ones.\n\nWe should not set bits in pin_programmed here, so that those bit could\nbe set later via io_apic_set_pci_routing().\n\n[ Impact: fix boot hang on certain systems ]\n\nReported-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai.lu@kernel.org\u003e\nTested-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nLKML-Reference: \u003c4A119990.9020606@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "4aee2ad461889132bfb5a1518a9580d00e17008c", "tree": "87cfb8bbe0ad78f6f01c4ac0fed477c492e30680", "parents": [ "52650257ea06bb15c2e2bbe854cbdf463726141a" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinder@kernel.org", "time": "Tue May 19 17:07:01 2009 +0530" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 19 14:16:24 2009 +0200" }, "message": "x86: asm/processor.h: remove double declaration\n\nRemove double declaration of:\n\n extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);\n extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);\n extern unsigned short num_cache_leaves;\n\nthey are already defined in the same file.\n\n[ Impact: cleanup ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nLKML-Reference: \u003c1242733021.3377.1.camel@localhost.localdomain\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "13bba6fda98fe03a955665c9d4bf63c8fd9c19c0", "tree": "f0058f8b307eab6da6106cda02b4edd0245977e3", "parents": [ "0130b2d7010fe8e046b7a6c44911a1d3d0d16c96", "b4ecc126991b30fe5f9a59dfacda046aeac124b2" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon May 18 09:17:37 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon May 18 09:17:37 2009 -0700" }, "message": "Merge branch \u0027x86-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86: Fix performance regression caused by paravirt_ops on native kernels\n xen: use header for EXPORT_SYMBOL_GPL\n x86, 32-bit: fix kernel_trap_sp()\n x86: fix percpu_{to,from}_op()\n x86: mtrr: Fix high_width computation when phys-addr is \u003e\u003d 44bit\n x86: Fix false positive section mismatch warnings in the apic code\n" }, { "commit": "0130b2d7010fe8e046b7a6c44911a1d3d0d16c96", "tree": "e4fb22c311a2ca8da64528538646d1e2579f4447", "parents": [ "80193195f87ebca6d7417516d6edeb3969631c15", "88fc86c283d9c3854e67e4155808027bc2519eb6" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon May 18 09:15:41 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon May 18 09:15:41 2009 -0700" }, "message": "Merge branch \u0027tracing-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027tracing-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n tracing: Append prompt in /debug/tracing/README file\n x86/function-graph: fix constraint for recording old return value\n" }, { "commit": "f1bdb523880c7f6990e9e8e50b0fc972ca475e84", "tree": "bf46a5a0f06b5b1a28cc392ee0aab0d454951915", "parents": [ "629e15d245f46bef9d26199b450f882f9437a8fe" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Fri May 15 13:05:16 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 09:33:29 2009 +0200" }, "message": "x86, irq: don\u0027t call mp_config_acpi_gsi() if update_mptable is not enabled\n\nLen expressed concern that the update_mptable feature has\nside-effects on the ACPI code.\n\nMake it sure explicitly that the code only ever gets called if\nthe (default disabled) update_mptable boot quirk option is\ndisabled.\n\n[ Impact: isolate the update_mptable feature from ACPI code more ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A0DC832.5090200@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "629e15d245f46bef9d26199b450f882f9437a8fe", "tree": "8acc02c159e6b1a62753db4ba508932358ae5457", "parents": [ "2759c3287de27266e06f1f4e82cbd2d65f6a044c" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Fri May 15 13:05:16 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 09:33:17 2009 +0200" }, "message": "x86, irq: update_mptable needs pci_routeirq\n\nTo get all device irq routing and to save them.\n\nThis is basically an implicit pci\u003drouteirq enablement if (and on if)\nthe update_mptable boot option (which is off by default) has been\nspecified.\n\n[ Impact: extend the update_mptable boot opion\u0027s scope ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nLKML-Reference: \u003c4A0DB7B4.4060702@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2759c3287de27266e06f1f4e82cbd2d65f6a044c", "tree": "78fa6a205d2e1c5f010f62e2ad50a181df1e5f47", "parents": [ "e5198075c67a22ec9a09565b1ce88d3d3f5ba855" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Fri May 15 13:05:16 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 08:43:25 2009 +0200" }, "message": "x86: don\u0027t call read_apic_id if !cpu_has_apic\n\nshould not call that if apic is disabled.\n\n[ Impact: fix crash on certain UP configs ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Cyrill Gorcunov \u003cgorcunov@gmail.com\u003e\nLKML-Reference: \u003c4A09CCBB.2000306@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e5198075c67a22ec9a09565b1ce88d3d3f5ba855", "tree": "3d4ea0efd8575e677509b022e649c62d4786ed55", "parents": [ "b5710ce92a8cf8e3fc0ffc230cfdbfa23463f1c8" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Fri May 15 13:05:16 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 18 08:38:55 2009 +0200" }, "message": "x86, apic: introduce io_apic_irq_attr\n\naccording to Ingo, io_apic irq-setup related functions have too many\nparameters with a repetitive signature.\n\nSo reduce related funcs to get less params by passing a pointer\nto a newly defined io_apic_irq_attr structure.\n\nv2: io_apic_irq \u003d\u003d\u003e irq_attr\n triggering \u003d\u003d\u003e trigger\n\nv3: add set_io_apic_irq_attr\n\n[ Impact: cleanup ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A08ACD3.2070401@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b4ecc126991b30fe5f9a59dfacda046aeac124b2", "tree": "ecde1569068bbe6e941658e385a1e44671752a7b", "parents": [ "44408ad7368906c84000e87a99c14a16dbb867fd" ], "author": { "name": "Jeremy Fitzhardinge", "email": "jeremy@goop.org", "time": "Wed May 13 17:16:55 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri May 15 20:07:42 2009 +0200" }, "message": "x86: Fix performance regression caused by paravirt_ops on native kernels\n\nXiaohui Xin and some other folks at Intel have been looking into what\u0027s\nbehind the performance hit of paravirt_ops when running native.\n\nIt appears that the hit is entirely due to the paravirtualized\nspinlocks introduced by:\n\n | commit 8efcbab674de2bee45a2e4cdf97de16b8e609ac8\n | Date: Mon Jul 7 12:07:51 2008 -0700\n |\n | paravirt: introduce a \"lock-byte\" spinlock implementation\n\nThe extra call/return in the spinlock path is somehow\ncausing an increase in the cycles/instruction of somewhere around 2-7%\n(seems to vary quite a lot from test to test). The working theory is\nthat the CPU\u0027s pipeline is getting upset about the\ncall-\u003ecall-\u003elocked-op-\u003ereturn-\u003ereturn, and seems to be failing to\nspeculate (though I haven\u0027t seen anything definitive about the precise\nreasons). This doesn\u0027t entirely make sense, because the performance\nhit is also visible on unlock and other operations which don\u0027t involve\nlocked instructions. But spinlock operations clearly swamp all the\nother pvops operations, even though I can\u0027t imagine that they\u0027re\nnearly as common (there\u0027s only a .05% increase in instructions\nexecuted).\n\nIf I disable just the pv-spinlock calls, my tests show that pvops is\nidentical to non-pvops performance on native (my measurements show that\nit is actually about .1% faster, but Xiaohui shows a .05% slowdown).\n\nSummary of results, averaging 10 runs of the \"mmperf\" test, using a\nno-pvops build as baseline:\n\n\t\tnopv\t\tPv-nospin\tPv-spin\nCPU cycles\t100.00%\t\t99.89%\t\t102.18%\ninstructions\t100.00%\t\t100.10%\t\t100.15%\nCPI\t\t100.00%\t\t99.79%\t\t102.03%\ncache ref\t100.00%\t\t100.84%\t\t100.28%\ncache miss\t100.00%\t\t90.47%\t\t88.56%\ncache miss rate\t100.00%\t\t89.72%\t\t88.31%\nbranches\t100.00%\t\t99.93%\t\t100.04%\nbranch miss\t100.00%\t\t103.66%\t\t107.72%\nbranch miss rt\t100.00%\t\t103.73%\t\t107.67%\nwallclock\t100.00%\t\t99.90%\t\t102.20%\n\nThe clear effect here is that the 2% increase in CPI is\ndirectly reflected in the final wallclock time.\n\n(The other interesting effect is that the more ops are\nout of line calls via pvops, the lower the cache access\nand miss rates. Not too surprising, but it suggests that\nthe non-pvops kernel is over-inlined. On the flipside,\nthe branch misses go up correspondingly...)\n\nSo, what\u0027s the fix?\n\nParavirt patching turns all the pvops calls into direct calls, so\n_spin_lock etc do end up having direct calls. For example, the compiler\ngenerated code for paravirtualized _spin_lock is:\n\n\u003c_spin_lock+0\u003e:\t\tmov %gs:0xb4c8,%rax\n\u003c_spin_lock+9\u003e:\t\tincl 0xffffffffffffe044(%rax)\n\u003c_spin_lock+15\u003e:\tcallq *0xffffffff805a5b30\n\u003c_spin_lock+22\u003e:\tretq\n\nThe indirect call will get patched to:\n\u003c_spin_lock+0\u003e:\t\tmov %gs:0xb4c8,%rax\n\u003c_spin_lock+9\u003e:\t\tincl 0xffffffffffffe044(%rax)\n\u003c_spin_lock+15\u003e:\tcallq \u003c__ticket_spin_lock\u003e\n\u003c_spin_lock+20\u003e:\tnop; nop\t\t/* or whatever 2-byte nop */\n\u003c_spin_lock+22\u003e:\tretq\n\nOne possibility is to inline _spin_lock, etc, when building an\noptimised kernel (ie, when there\u0027s no spinlock/preempt\ninstrumentation/debugging enabled). That will remove the outer\ncall/return pair, returning the instruction stream to a single\ncall/return, which will presumably execute the same as the non-pvops\ncase. The downsides arel 1) it will replicate the\npreempt_disable/enable code at eack lock/unlock callsite; this code is\nfairly small, but not nothing; and 2) the spinlock definitions are\nalready a very heavily tangled mass of #ifdefs and other preprocessor\nmagic, and making any changes will be non-trivial.\n\nThe other obvious answer is to disable pv-spinlocks. Making them a\nseparate config option is fairly easy, and it would be trivial to\nenable them only when Xen is enabled (as the only non-default user).\nBut it doesn\u0027t really address the common case of a distro build which\nis going to have Xen support enabled, and leaves the open question of\nwhether the native performance cost of pv-spinlocks is worth the\nperformance improvement on a loaded Xen system (10% saving of overall\nsystem CPU when guests block rather than spin). Still it is a\nreasonable short-term workaround.\n\n[ Impact: fix pvops performance regression when running native ]\n\nAnalysed-by: \"Xin Xiaohui\" \u003cxiaohui.xin@intel.com\u003e\nAnalysed-by: \"Li Xin\" \u003cxin.li@intel.com\u003e\nAnalysed-by: \"Nakajima Jun\" \u003cjun.nakajima@intel.com\u003e\nSigned-off-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nAcked-by: H. Peter Anvin \u003chpa@zytor.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Xen-devel \u003cxen-devel@lists.xensource.com\u003e\nLKML-Reference: \u003c4A0B62F7.5030802@goop.org\u003e\n[ fixed the help text ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "52650257ea06bb15c2e2bbe854cbdf463726141a", "tree": "bf376e12e33a84582a06b7176f9c928700474b28", "parents": [ "ba5673ff1ff5f428256db4cedd4b05b7be008bb6" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Thu May 14 12:35:46 2009 +0530" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 15 07:49:01 2009 -0700" }, "message": "x86, mtrr: replace MTRRdefType_MSR with msr-index\u0027s MSR_MTRRdefType\n\nUse standard msr-index.h\u0027s MSR declaration and no need to declare again.\n\n[ Impact: cleanup, no object code change ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "ba5673ff1ff5f428256db4cedd4b05b7be008bb6", "tree": "8f57573cc395c64c147629f95b0e202cc43dd21f", "parents": [ "654ac05801ae806661c8fdeb3b5c420a31cbc5b1" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Thu May 14 12:29:25 2009 +0530" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 15 07:49:01 2009 -0700" }, "message": "x86, mtrr: replace MTRRfix4K_C0000_MSR with msr-index\u0027s MSR_MTRRfix4K_C0000\n\nUse standard msr-index.h\u0027s MSR declaration and no need to declare again.\n\n[ Impact: cleanup, no object code change ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "654ac05801ae806661c8fdeb3b5c420a31cbc5b1", "tree": "558e452d83b9c02b5b0b9ab86eb5024c4f0ec9f5", "parents": [ "7d9d55e449089df8463bca2045d702ae6cda64a2" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Thu May 14 12:21:54 2009 +0530" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 15 07:49:01 2009 -0700" }, "message": "x86, mtrr: remove mtrr MSRs double declaration\n\nRemoved MTRR MSR from mtrr/mtrr.h as these are already declared in\nmsr-index.h and nobody is using them:\n MTRRfix16K_A0000_MSR\n MTRRfix4K_C8000_MSR\n MTRRfix4K_D0000_MSR\n MTRRfix4K_D8000_MSR\n MTRRfix4K_E0000_MSR\n MTRRfix4K_E8000_MSR\n MTRRfix4K_F0000_MSR\n MTRRfix4K_F8000_MSR\n\nUse standard msr-index.h\u0027s MSR declaration and no need to declare again\n\n[ Impact: cleanup, no object code change ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "7d9d55e449089df8463bca2045d702ae6cda64a2", "tree": "40a11d1ca0aeddc49378d8955be4a147a421cff3", "parents": [ "a036c7a358cc9d7ed28a188480b9a4d709e09b24" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Thu May 14 12:15:32 2009 +0530" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 15 07:49:00 2009 -0700" }, "message": "x86, mtrr: replace MTRRfix16K_80000_MSR with msr-index\u0027s MSR_MTRRfix16K_80000\n\nUse standard msr-index.h\u0027s MSR declaration and no need to declare again\n\n[ Impact: cleanup, no object code change ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "a036c7a358cc9d7ed28a188480b9a4d709e09b24", "tree": "0e8bf833e93888d4f35cec4b06769f715569db56", "parents": [ "d9bcc01d58d18ed287091707b0b45c6ac888a11a" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Thu May 14 12:10:43 2009 +0530" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 15 07:49:00 2009 -0700" }, "message": "x86, mtrr: replace MTRRfix64K_00000_MSR with msr-index\u0027s MSR_MTRRfix64K_00000\n\nUse standard msr-index.h\u0027s MSR declaration and no need to declare again.\n\n[ Impact: cleanup, no object code change ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "d9bcc01d58d18ed287091707b0b45c6ac888a11a", "tree": "e845b49eeaa85c19427dac03e9603f108e62d7d7", "parents": [ "778dedae0cb76a441145f3a0c5d59fcb3ba296d5" ], "author": { "name": "Jaswinder Singh Rajput", "email": "jaswinderrajput@gmail.com", "time": "Thu May 14 12:06:12 2009 +0530" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 15 07:49:00 2009 -0700" }, "message": "x86, mtrr: replace MTRRcap_MSR with msr-index\u0027s MSR_MTRRcap\n\nUse standard msr-index.h\u0027s MSR declaration and no need to declare again.\n\n[ Impact: cleanup, no object code change ]\n\nSigned-off-by: Jaswinder Singh Rajput \u003cjaswinderrajput@gmail.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "33ab1979bc9f719213bc3f392c8fd9d012e4f4e9", "tree": "4bec72fadd446a86c7ffc96269a9f83fc4a9f456", "parents": [ "364b5b7b1d793a7f98be55b6b154716dcae78dfc" ], "author": { "name": "Jason Wessel", "email": "jason.wessel@windriver.com", "time": "Wed Feb 11 18:46:32 2009 -0600" }, "committer": { "name": "Jason Wessel", "email": "jason.wessel@windriver.com", "time": "Fri May 15 07:56:25 2009 -0500" }, "message": "kgdb,i386: use address that SP register points to in the exception frame\n\nThe treatment of the SP register is different on x86_64 and i386.\nThis is a regression fix that lived outside the mainline kernel from\n2.6.27 to now. The regression was a result of the original merge\nconsolidation of the i386 and x86_64 archs to x86.\n\nThe incorrectly reported SP on i386 prevented stack tracebacks from\nworking correctly in gdb.\n\nSigned-off-by: Jason Wessel \u003cjason.wessel@windriver.com\u003e\n" }, { "commit": "aa512a27e9e8ed32f31b15eec67ab1ceca33839b", "tree": "b9f4c0e65027d2501eb08f4661d7aa95c4d5d74d", "parents": [ "091bf7624d1c90cec9e578a18529f615213ff847" ], "author": { "name": "Steven Rostedt", "email": "srostedt@redhat.com", "time": "Wed May 13 13:52:19 2009 -0400" }, "committer": { "name": "Steven Rostedt", "email": "rostedt@goodmis.org", "time": "Wed May 13 13:52:19 2009 -0400" }, "message": "x86/function-graph: fix constraint for recording old return value\n\nAfter upgrading from gcc 4.2.2 to 4.4.0, the function graph tracer broke.\nInvestigating, I found that in the asm that replaces the return value,\ngcc was using the same register for the old value as it was for the\nnew value.\n\n\tmov\t(addr), old\n\tmov\tnew, (addr)\n\nBut if old and new are the same register, we clobber new with old!\nI first thought this was a bug in gcc 4.4.0 and reported it:\n\n http://gcc.gnu.org/bugzilla/show_bug.cgi?id\u003d40132\n\nAndrew Pinski responded (quickly), saying that it was correct gcc behavior\nand the code needed to denote old as an \"early clobber\".\n\nInstead of \"\u003dr\"(old), we need \"\u003d\u0026r\"(old).\n\n[Impact: keep function graph tracer from breaking with gcc 4.4.0 ]\n\nSigned-off-by: Steven Rostedt \u003crostedt@goodmis.org\u003e\n" }, { "commit": "44408ad7368906c84000e87a99c14a16dbb867fd", "tree": "409ea6a4cab12a68d5a71abe97ed59277e4a412d", "parents": [ "7b6c6c77732ca1d2498eda7eabb64f9648896e96" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Tue May 12 13:31:40 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed May 13 15:43:55 2009 +0200" }, "message": "xen: use header for EXPORT_SYMBOL_GPL\n\nmmu.c needs to #include module.h to prevent these warnings:\n\n arch/x86/xen/mmu.c:239: warning: data definition has no type or storage class\n arch/x86/xen/mmu.c:239: warning: type defaults to \u0027int\u0027 in declaration of \u0027EXPORT_SYMBOL_GPL\u0027\n arch/x86/xen/mmu.c:239: warning: parameter names (without types) in function declaration\n\n[ Impact: cleanup ]\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nAcked-by: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c4f68236e41641494f9c8a418ccc0678c335bbb5", "tree": "0af5a0ce1331a0270bd4e01fe836a86967d9054c", "parents": [ "7ed42a28b269f8682eefae27f5c11187eb56e63b" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Tue May 12 11:37:34 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Tue May 12 11:41:42 2009 -0700" }, "message": "x86-64: align __PHYSICAL_START, remove __KERNEL_ALIGN\n\nHandle the misconfiguration where CONFIG_PHYSICAL_START is\nincompatible with CONFIG_PHYSICAL_ALIGN. This is a configuration\nerror, but one which arises easily since Kconfig doesn\u0027t have the\nsmarts to express the true relationship between these two variables.\nHence, align __PHYSICAL_START the same way we align LOAD_PHYSICAL_ADDR\nin \u003casm/boot.h\u003e.\n\nFor non-relocatable kernels, this would cause the boot to fail.\n\n[ Impact: fix boot failures for non-relocatable kernels ]\n\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "7ed42a28b269f8682eefae27f5c11187eb56e63b", "tree": "62bfe9cdb017524630d2b6c8f66a8db00d278a38", "parents": [ "5031296c57024a78ddad4edfc993367dbf4abb98" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Tue May 12 11:33:08 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Tue May 12 11:33:08 2009 -0700" }, "message": "x86, boot: correct sanity checks in boot/compressed/misc.c\n\narch/x86/boot/compressed/misc.c contains several sanity checks on the\noutput address. Correct constraints that are no longer correct:\n\n- the alignment test should be MIN_KERNEL_ALIGN on both 32 and 64\n bits.\n- the 64 bit maximum address was set to 2^40, which was the limit of\n one specific x86-64 implementation. Change the test to 2^46, the\n current Linux limit, and at least try to test the end rather than\n the beginning.\n- for non-relocatable kernels, test against LOAD_PHYSICAL_ADDR on both\n 32 and 64 bits.\n\n[ Impact: fix potential boot failure due to invalid tests ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "4797f6b021a3fa399942245d07a1feb30df81bb8", "tree": "aea4f0aec80786f8e5b4d55c9140add997a9a348", "parents": [ "6cda3eb62ef42aa5acd649bf99c8db544e0f4051" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Sat May 02 10:40:57 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 12 12:22:06 2009 +0200" }, "message": "x86: read apic ID in the !acpi_lapic case\n\nEd found that on 32-bit, boot_cpu_physical_apicid is not read right,\nwhen the mptable is broken.\n\nInterestingly, actually three paths use/set it:\n\n 1. acpi: at that time that is already read from reg\n 2. mptable: only read from mptable\n 3. no madt, and no mptable, that use default apic id 0 for 64-bit, -1 for 32-bit\n\nso we could read the apic id for the 2/3 path. We trust the hardware\nregister more than we trust a BIOS data structure (the mptable).\n\nWe can also avoid the double set_fixmap() when acpi_lapic\nis used, and also need to move cpu_has_apic earlier and\ncall apic_disable().\n\nAlso when need to update the apic id, we\u0027d better read and\nset the apic version as well - so that quirks are applied precisely.\n\nv2: make path 3 with 64bit, use -1 as apic id, so could read it later.\nv3: fix whitespace problem pointed out by Ed Swierk\nv5: fix boot crash\n\n[ Impact: get correct apic id for bsp other than acpi path ]\n\nReported-by: Ed Swierk \u003ceswierk@aristanetworks.com\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nAcked-by: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nLKML-Reference: \u003c49FC85A9.2070702@kernel.org\u003e\n[ v4: sanity-check in the ACPI case too ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6cda3eb62ef42aa5acd649bf99c8db544e0f4051", "tree": "93f74ca002f5756c8e157611174f9540b5cf41c0", "parents": [ "b9c61b70075c87a8612624736faf4a2de5b1ed30", "cec6be6d1069d697beb490bbb40a290d5ff554a2" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 12 12:17:30 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 12 12:17:36 2009 +0200" }, "message": "Merge branch \u0027x86/apic\u0027 into irq/numa\n\nMerge reason: both topics modify the APIC code but were able to do it in\n parallel so far. An upcoming patch generates a conflict so\n merge them to avoid the conflict.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5031296c57024a78ddad4edfc993367dbf4abb98", "tree": "7506daf7aabf25a5ec567fcd2e644fe22cd91eca", "parents": [ "fe83fcc0a14dcf71996de5eb84771b2369ba7abc" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Thu May 07 16:54:11 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 17:45:06 2009 -0700" }, "message": "x86: add extension fields for bootloader type and version\n\nA long ago, in days of yore, it all began with a god named Thor.\nThere were vikings and boats and some plans for a Linux kernel\nheader. Unfortunately, a single 8-bit field was used for bootloader\ntype and version. This has generally worked without *too* much pain,\nbut we\u0027re getting close to flat running out of ID fields.\n\nAdd extension fields for both type and version. The type will be\nextended if it the old field is 0xE; the version is a simple MSB\nextension.\n\nKeep /proc/sys/kernel/bootloader_type containing\n(type \u003c\u003c 4) + (ver \u0026 0xf) for backwards compatiblity, but also add\n/proc/sys/kernel/bootloader_version which contains the full version\nnumber.\n\n[ Impact: new feature to support more bootloaders ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "fe83fcc0a14dcf71996de5eb84771b2369ba7abc", "tree": "40af2bc6fc3dcad082b2b6bf22d3b8e0017be50a", "parents": [ "c4a994645d04d5fa6bfa52a3204af87dd92168d5" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 16:23:16 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 17:45:06 2009 -0700" }, "message": "x86, defconfig: update kernel position parameters\n\nUpdate CONFIG_RELOCATABLE, CONFIG_PHYSICAL_START and\nCONFIG_PHYSICAL_ALIGN to reflect the current defaults.\n\n[ Impact: make defconfig match Kconfig defaults ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "c4a994645d04d5fa6bfa52a3204af87dd92168d5", "tree": "b47514d7683af99e514f2038aa42a4b509236a43", "parents": [ "26717808f93a27c22d4853c4fb17fa225f4ccc68" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 16:20:12 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 17:45:06 2009 -0700" }, "message": "x86, defconfig: update to current, no material changes\n\nUpdate defconfigs to reflect current configuration files. No other\nchanges.\n\n[ Impact: updates defconfigs to match what \"make defconfig\" generates ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "26717808f93a27c22d4853c4fb17fa225f4ccc68", "tree": "f260903b5ee426813aca4f1203b003eab449e731", "parents": [ "ceefccc93932b920a8ec6f35f596db05202a12fe" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Thu May 07 14:19:34 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 17:45:06 2009 -0700" }, "message": "x86: make CONFIG_RELOCATABLE the default\n\nRemove the EXPERIMENTAL tag from CONFIG_RELOCATABLE and make it the\ndefault. Relocatable kernels have been used for a while now, and\nshould now have identical semantics to non-relocatable kernels when\nloaded by a non-relocating bootloader.\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "ceefccc93932b920a8ec6f35f596db05202a12fe", "tree": "5def2c91f78186e944c23ba1d1b3e0741382b180", "parents": [ "d297366ba692faf1f0384811a6ff0b20c3470b1b" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 16:12:16 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 17:45:05 2009 -0700" }, "message": "x86: default CONFIG_PHYSICAL_START and CONFIG_PHYSICAL_ALIGN to 16 MB\n\nDefault CONFIG_PHYSICAL_START and CONFIG_PHYSICAL_ALIGN each to 16 MB,\nso that both non-relocatable and relocatable kernels are loaded at\n16 MB by a non-relocating bootloader. This is somewhat hacky, but it\nappears to be the only way to do this that does not break some some\nset of existing bootloaders.\n\nWe want to avoid the bottom 16 MB because of large page breakup,\nmemory holes, and ZONE_DMA. Embedded systems may need to reduce this,\nor update their bootloaders to be aware of the new min_alignment field.\n\n[ Impact: performance improvement, avoids problems on some systems ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "37ba7ab5e33cebc25c68fffe33e9f21e7c2014e8", "tree": "006ba60fcd29b8fdee844ee6d90b85104a254d0d", "parents": [ "99aa45595f45603526513d5e29fc00f8afbf3913" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 15:56:08 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 17:44:39 2009 -0700" }, "message": "x86, boot: make kernel_alignment adjustable; new bzImage fields\n\nMake the kernel_alignment field adjustable; this allows us to set it\nto a large value (intended to be 16 MB to avoid ZONE_DMA contention,\nmemory holes and other weirdness) while a smart bootloader can still\nforce a loading at a lesser alignment if absolutely necessary.\n\nAlso export pref_address (preferred loading address, corresponding to\nthe link-time address) and init_size, the total amount of linear\nmemory the kernel will require during initialization.\n\n[ Impact: allows better kernel placement, gives bootloader more info ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "99aa45595f45603526513d5e29fc00f8afbf3913", "tree": "6c78891c04c10f6af014891fbbaf63c7276a5c24", "parents": [ "40b387a8a9a821878ecdf9fb117958c426fc1385" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 16:02:10 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 16:17:05 2009 -0700" }, "message": "x86, boot: remove dead code from boot/compressed/head_*.S\n\nRemove a couple of lines of dead code from\narch/x86/boot/compressed/head_*.S; all of these update registers that\nare dead in the current code.\n\n[ Impact: cleanup ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "7b6c6c77732ca1d2498eda7eabb64f9648896e96", "tree": "f5eccbffc028d396e454898db1edc66e7e6a4666", "parents": [ "3c598766a2bae1b208470e7cc934ac462561e3cb" ], "author": { "name": "Masami Hiramatsu", "email": "mhiramat@redhat.com", "time": "Mon May 11 17:03:00 2009 -0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue May 12 00:39:52 2009 +0200" }, "message": "x86, 32-bit: fix kernel_trap_sp()\n\nUse \u0026regs-\u003esp instead of regs for getting the top of stack in kernel mode.\n(on x86-64, regs-\u003esp always points the top of stack)\n\n[ Impact: Oprofile decodes only stack for backtracing on i386 ]\n\nSigned-off-by: Masami Hiramatsu \u003cmhiramat@redhat.com\u003e\n[ v2: rename the API to kernel_stack_pointer(), move variable inside ]\nAcked-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nCc: systemtap@sources.redhat.com\nCc: Harvey Harrison \u003charvey.harrison@gmail.com\u003e\nCc: Jan Blunck \u003cjblunck@suse.de\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nLKML-Reference: \u003c20090511210300.17332.67549.stgit@localhost.localdomain\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2ff799d3cff1ecb274049378b28120ee5c1c5e5f", "tree": "4658ce8c196b4625297d22131a204ba9946f6d29", "parents": [ "7961386fe9596e6bf03d09948a73c5df9653325b" ], "author": { "name": "Vaidyanathan Srinivasan", "email": "svaidy@linux.vnet.ibm.com", "time": "Mon May 11 20:09:14 2009 +0530" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 23:57:56 2009 +0200" }, "message": "sched: Don\u0027t export sched_mc_power_savings on multi-socket single core system\n\nFix to prevent sched_mc_power_saving from being exported through sysfs\nfor multi-scoket single core system. Max cores should be always greater than\none (1). My earlier patch that introduced fix for not exporting\n\u0027sched_mc_power_saving\u0027 on laptops broke it on multi-socket single core\nsystem. This fix addresses issue on both laptop and multi-socket single\ncore system.\nBelow are the Test results:\n\n1. Single socket - multi-core\n Before Patch: Does not export \u0027sched_mc_power_saving\u0027\n After Patch: Does not export \u0027sched_mc_power_saving\u0027\n Result: Pass\n\n2. Multi Socket - single core\n Before Patch: exports \u0027sched_mc_power_saving\u0027\n After Patch: Does not export \u0027sched_mc_power_saving\u0027\n Result: Pass\n\n3. Multi Socket - Multi core\n Before Patch: exports \u0027sched_mc_power_saving\u0027\n After Patch: exports \u0027sched_mc_power_saving\u0027\n\n[ Impact: make the sched_mc_power_saving control available more consistently ]\n\nSigned-off-by: Mahesh Salgaonkar \u003cmahesh@linux.vnet.ibm.com\u003e\nCc: Suresh B Siddha \u003csuresh.b.siddha@intel.com\u003e\nCc: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLKML-Reference: \u003c20090511143914.GB4853@dirshya.in.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "40b387a8a9a821878ecdf9fb117958c426fc1385", "tree": "28a8886b89faa4da5cfce32a5115e0a10f49c04e", "parents": [ "77d1a4999502c260df0eb2de437d320bf8c64b36" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 14:41:55 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 14:41:55 2009 -0700" }, "message": "x86, boot: use LOAD_PHYSICAL_ADDR on 64 bits\n\nUse LOAD_PHYSICAL_ADDR instead of CONFIG_PHYSICAL_START in the 64-bit\ndecompression code, for equivalence with the 32-bit code.\n\n[ Impact: cleanup, increases code similarity ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "77d1a4999502c260df0eb2de437d320bf8c64b36", "tree": "d479843ccd9ffdd0e89548753c391950adb664a4", "parents": [ "02a884c0fe7ec8459d00d34b7d4101af21fc4a86" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 14:21:12 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 14:40:50 2009 -0700" }, "message": "x86, boot: make symbols from the main vmlinux available\n\nMake symbols from the main vmlinux, as opposed to just\ncompressed/vmlinux, available to header.S. Also, export a few\nadditional symbols.\n\nThis will be used in a subsequent patch to export the total memory\nfootprint of the kernel.\n\n[ Impact: enable future enhancement ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "3c598766a2bae1b208470e7cc934ac462561e3cb", "tree": "3119bfbff3966146843b407eefc793db0da89064", "parents": [ "917a0153621572e88aeb2d5df025ad2e81027287" ], "author": { "name": "Jan Beulich", "email": "JBeulich@novell.com", "time": "Mon May 11 16:49:28 2009 +0100" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Mon May 11 08:54:33 2009 -0700" }, "message": "x86: fix percpu_{to,from}_op()\n\n- the byte operand constraints were wrong for 32-bit\n- the to-op\u0027s input operands weren\u0027t properly parenthesized\n\n[ Impact: fix possible miscompilation or build failure ]\n\nSigned-off-by: Jan Beulich \u003cjbeulich@novell.com\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "0c23590f00f85467b318ad0c20c36796a5bd4c60", "tree": "bc04b3fbe0394b49e580fd68dca8e96331ac3eab", "parents": [ "d756f4adb9d8a86e347a2d5435bb5cc95744733e" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Mon May 04 03:30:15 2009 +0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 16:23:54 2009 +0200" }, "message": "x86, 64-bit: ifdef out struct thread_struct::ip\n\nstruct thread_struct::ip isn\u0027t used on x86_64, struct pt_regs::ip is used\ninstead.\n\nkgdb should be reading 0 always, but I can\u0027t check it.\n\n[ Impact: (potentially) reduce thread_struct size on 64-bit ]\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: containers@lists.linux-foundation.org\nLKML-Reference: \u003c20090503233015.GJ16631@x200.localdomain\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d756f4adb9d8a86e347a2d5435bb5cc95744733e", "tree": "beeb3c4304241b139feec51e21affd0a788b8a99", "parents": [ "edc953fa4ebc0265ef3b1754fe116a9fd4264e15" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Mon May 04 03:29:52 2009 +0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 16:23:54 2009 +0200" }, "message": "x86, 32-bit: ifdef out struct thread_struct::fs\n\nAfter commit 464d1a78fbf8cf6c7fd970e7b3e2db50a320ce28 aka\n\"[PATCH] i386: Convert i386 PDA code to use %fs\"\n%fs saved during context switch moved from thread_struct to pt_regs\nand value on thread_struct became unused.\n\n[ Impact: reduce thread_struct size on 32-bit ]\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: containers@lists.linux-foundation.org\nLKML-Reference: \u003c20090503232952.GI16631@x200.localdomain\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cec6be6d1069d697beb490bbb40a290d5ff554a2", "tree": "43ef99d950545909d8dbc87cddb14e29789aa060", "parents": [ "97a52714658cd959a3cfa35c5b6f489859f0204b" ], "author": { "name": "Cyrill Gorcunov", "email": "gorcunov@gmail.com", "time": "Mon May 11 17:41:40 2009 +0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 15:50:58 2009 +0200" }, "message": "x86: apic: Fixmap apic address even if apic disabled\n\nIn case if apic were disabled by boot option\nwe still need read_apic operation. So fixmap\na fake apic area if needed.\n\n[ Impact: fix boot crash ]\n\nSigned-off-by: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nCc: yinghai@kernel.org\nCc: eswierk@aristanetworks.com\nLKML-Reference: \u003c20090511134140.GH4624@lenovo\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "97a52714658cd959a3cfa35c5b6f489859f0204b", "tree": "462708be716e7e1e5216f305dbf243f7c9db1382", "parents": [ "4401da6111ac58f94234417427d06a72c4048c74" ], "author": { "name": "Andreas Herrmann", "email": "andreas.herrmann3@amd.com", "time": "Fri May 08 18:23:50 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 14:37:36 2009 +0200" }, "message": "x86: display extended apic registers with print_local_APIC and cpu_debug code\n\nBoth print_local_APIC (used when apic\u003ddebug kernel param is set) and\ncpu_debug code missed support for some extended APIC registers that\nI\u0027d like to see.\n\nThis adds support to show:\n\n - extended APIC feature register\n - extended APIC control register\n - extended LVT registers\n\n[ Impact: print more debug info ]\n\nSigned-off-by: Andreas Herrmann \u003candreas.herrmann3@amd.com\u003e\nCc: Jaswinder Singh Rajput \u003cjaswinder@kernel.org\u003e\nCc: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nLKML-Reference: \u003c20090508162350.GO29045@alberich.amd.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "99f85a28a78e96d28907fe036e1671a218fee597", "tree": "7d24df5b4d27d6801b1c372297adffb2334d9a97", "parents": [ "e286e86e6d2042d67d09244aa0e05ffef75c9d54" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 11 14:21:10 2009 +0300" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 11 14:40:51 2009 +0300" }, "message": "KVM: SVM: Remove port 80 passthrough\n\nKVM optimizes guest port 80 accesses by passthing them through to the host.\nSome AMD machines die on port 80 writes, allowing the guest to hard-lock the\nhost.\n\nRemove the port passthrough to avoid the problem.\n\nCc: stable@kernel.org\nReported-by: Piotr Jaroszyński \u003cp.jaroszynski@gmail.com\u003e\nTested-by: Piotr Jaroszyński \u003cp.jaroszynski@gmail.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "917a0153621572e88aeb2d5df025ad2e81027287", "tree": "4a1f06f9820f10d714814a9fa86f2094e8eb9c4a", "parents": [ "b74d446f1f337e3fe906169a3266cb65ffa4179e" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 21:36:16 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 11:40:43 2009 +0200" }, "message": "x86: mtrr: Fix high_width computation when phys-addr is \u003e\u003d 44bit\n\nfound one system where cpu address line is 44bits, mtrr printout\nis not right:\n\n [ 0.000000] MTRR variable ranges enabled:\n [ 0.000000] 0 base 0 00000000 mask FF0 00000000 write-back\n [ 0.000000] 1 base 10 00000000 mask FFF 80000000 write-back\n [ 0.000000] 2 base 0 80000000 mask FFF 80000000 uncachable\n [ 0.000000] 3 base 0 7F800000 mask FFF FF800000 uncachable\n\nLi Zefan and Frederic pointed out the high_width could be -4 some how.\n\nIt turns out when phys_addr is 44bit, size_or_mask will be\nffffffff,00000000 so ffs(size_or_mask) will be 0.\n\nTry to check low 32 bit, to get correct high_width.\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kerne.org\u003e\nAlso-analyzed-by: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nAlso-analyzed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Jeremy Fitzhardinge \u003cjeremy@goop.org\u003e\nCc: Zhaolei \u003czhaolei@cn.fujitsu.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Vegard Nossum \u003cvegard.nossum@gmail.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nLKML-Reference: \u003c4A026540.8060504@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "4401da6111ac58f94234417427d06a72c4048c74", "tree": "8e42dbef7e8dcc9a82cc43971cdfb68f1a35e6fc", "parents": [ "61fe91e1319556f32bebfd7ed2c68ef02e2c17f7" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Sat May 02 10:40:57 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 11:29:23 2009 +0200" }, "message": "x86: read apic ID in the !acpi_lapic case\n\nEd found that on 32-bit, boot_cpu_physical_apicid is not read right,\nwhen the mptable is broken.\n\nInterestingly, actually three paths use/set it:\n\n 1. acpi: at that time that is already read from reg\n 2. mptable: only read from mptable\n 3. no madt, and no mptable, that use default apic id 0 for 64-bit, -1 for 32-bit\n\nso we could read the apic id for the 2/3 path. We trust the hardware\nregister more than we trust a BIOS data structure (the mptable).\n\nWe can also avoid the double set_fixmap() when acpi_lapic\nis used, and also need to move cpu_has_apic earlier and\ncall apic_disable().\n\nAlso when need to update the apic id, we\u0027d better read and\nset the apic version as well - so that quirks are applied precisely.\n\nv2: make path 3 with 64bit, use -1 as apic id, so could read it later.\nv3: fix whitespace problem pointed out by Ed Swierk\n\n[ Impact: get correct apic id for bsp other than acpi path ]\n\nReported-by: Ed Swierk \u003ceswierk@aristanetworks.com\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nAcked-by: Cyrill Gorcunov \u003cgorcunov@openvz.org\u003e\nLKML-Reference: \u003c49FC85A9.2070702@kernel.org\u003e\n[ v4: sanity-check in the ACPI case too ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3e0c373749d7eb5b354ac0b043f2b2cdf84eefef", "tree": "473870b2f527ce227cb729db35dbe226ce95a7d1", "parents": [ "3969c52d4d2fef5a4b9e3ab0e51b3901e1cc8b83" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Sat May 09 23:47:42 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:57:24 2009 +0200" }, "message": "x86: clean up and fix setup_clear/force_cpu_cap handling\n\nsetup_force_cpu_cap() only have one user (Xen guest code),\nbut it should not reuse cleared_cpu_cpus, otherwise it\nwill have problems on SMP.\n\nNeed to have a separate cpu_cpus_set array too, for forced-on\nflags, beyond the forced-off flags.\n\nAlso need to setup handling before all cpus caps are combined.\n\n[ Impact: fix the forced-set CPU feature flag logic ]\n\nCc: H. Peter Anvin \u003chpa@linux.intel.com\u003e\nCc: Jeremy Fitzhardinge \u003cjeremy.fitzhardinge@citrix.com\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai.lu@kernel.org\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "61fe91e1319556f32bebfd7ed2c68ef02e2c17f7", "tree": "70af8a1972cc0aa274412eb606a2551859ee03a7", "parents": [ "7a309490da98981558a07183786201f02a6341e2" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Sat May 09 23:47:42 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:52:40 2009 +0200" }, "message": "x86: apic: Check rev 3 fadt correctly for physical_apic bit\n\nImpact: fix fadt version checking\n\nFADT2_REVISION_ID has value 3 aka rev 3 FADT. So need to use \u003e\u003d instead\nof \u003e, as other places in the code do.\n\n[ Impact: extend scope of APIC boot quirk ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b9c61b70075c87a8612624736faf4a2de5b1ed30", "tree": "40f4ae74461d20be77b4b260e5384fe937bc5bec", "parents": [ "5ef2183768bb7d64b85eccbfa1537a61cbefa97c" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:10:06 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:10 2009 +0200" }, "message": "x86/pci: update pirq_enable_irq() to setup io apic routing\n\nSo we can set io apic routing only when enabling the device irq.\n\nThis is advantageous for IRQ descriptor allocation affinity: if we set up\nthe IO-APIC entry later, we have a chance to allocate the IRQ descriptor\nlater and know which device it is on and can set affinity accordingly.\n\n[ Impact: standardize/enhance irq-enabling sequence for mptable irqs ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nAcked-by: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nLKML-Reference: \u003c4A01C46E.8000501@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5ef2183768bb7d64b85eccbfa1537a61cbefa97c", "tree": "b2fc0ccee203c8690660eab9ee5f45d7857a93d5", "parents": [ "e20c06fd6950265a899edd96a02dc2e6ae2d1ce5" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:08:50 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:09 2009 +0200" }, "message": "x86/acpi: move setup io apic routing out of CONFIG_ACPI scope\n\nSo we could set io apic routing when ACPI is not enabled.\n\n[ Impact: prepare for new functionality ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A01C422.5070400@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e20c06fd6950265a899edd96a02dc2e6ae2d1ce5", "tree": "851deab98ff271debe6efb76443fb5fdc3d0be0c", "parents": [ "bdfe8ac153546537ed24de69610ea781a734f785" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:08:22 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:09 2009 +0200" }, "message": "x86/pci: add 4 more return parameters to IO_APIC_get_PCI_irq_vector()\n\nTo prepare those params for pcibios_irq_enable() to call setup_io_apic_routing().\n\n[ Impact: extend function call API to prepare for new functionality ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nAcked-by: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nLKML-Reference: \u003c4A01C406.2040303@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "bdfe8ac153546537ed24de69610ea781a734f785", "tree": "cad38765f6c27fe26408a536f2bcb596641e8c0c", "parents": [ "a31f82057ce6f7ced578d64c07a72ccbdc7336e4" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:07:41 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:08 2009 +0200" }, "message": "x86/acpi: move pin_programmed bit map to io_apic.c\n\nPrepare to call setup_io_apic_routing() in pcibios_irq_enable()\nalso remove not needed member apic_id.\n\n[ Impact: clean up, prepare for future change ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A01C3DD.3050104@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a31f82057ce6f7ced578d64c07a72ccbdc7336e4", "tree": "0dbe94d15a6a32640b0f86094d3ecf2b60b43f73", "parents": [ "ee214558c2e959781a406e76c5b34364da638e1d" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:06:15 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:08 2009 +0200" }, "message": "x86/acpi: call mp_config_acpi_gsi() in mp_register_gsi()\n\nThe patch to call mp_config_acpi_gsi() from the ACPI IRQ registration\ncode never got mainline because there were open discussions about it.\n\nThis call is needed to properly update the kernel\u0027s copy of the mptable,\nwhen the update_mptable boot parameter is needed.\n\nNow that the dust has settled with the APIC unification, and since there\nwere no objections when the patch was re-submitted, try this again.\n\n[ Impact: fix the update_mptable boot parameter ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A01C387.7090103@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ee214558c2e959781a406e76c5b34364da638e1d", "tree": "5fc0218815773b7eba93c91dc9e1972bf4f43954", "parents": [ "b9e0353fc85dab4ef5ebcef2bd09ebc4ce6d5a7b" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:07:07 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:07 2009 +0200" }, "message": "x86: fix alloc_mptable()\n\nFix the conditions when we stop updating the mptable due to\nrunning out of slots.\n\n[ Impact: fix memory corruption / non-working update_mptable boot parameter ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A01C3BB.1000609@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b9e0353fc85dab4ef5ebcef2bd09ebc4ce6d5a7b", "tree": "541981e91f5e18118570fd64ce3fb94473794e53", "parents": [ "b2e5d8588de0b5341eddad87dbe48d2185eaa3dd" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Wed May 06 10:05:32 2009 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 10:35:06 2009 +0200" }, "message": "x86/acpi: remove irq-compression trick on 32-bit\n\nWe already have a per cpu vector on 32-bit via recent changes, and\ndon\u0027t need this trick any more (which trick obfuscates the real GSI\nmappings and which only triggers on larger systems to begin with):\n\nOn 3 ioapic system (24 per ioapic) before patch I got:\n\nACPI: PCI Interrupt Link [ILSB] enabled at IRQ 71\nIOAPIC[2]: Set routing entry (10-23 -\u003e 0xa9 -\u003e IRQ 64 Mode:1 Active:1)\npci 0000:80:01.1: PCI INT A -\u003e Link[ILSB] -\u003e GSI 71 (level, low) -\u003e IRQ 64\nACPI: PCI Interrupt Link [LE5B] enabled at IRQ 67\nIOAPIC[2]: Set routing entry (10-19 -\u003e 0xb1 -\u003e IRQ 65 Mode:1 Active:1)\npci 0000:83:00.0: PCI INT B -\u003e Link[LE5B] -\u003e GSI 67 (level, low) -\u003e IRQ 65\nACPI: PCI Interrupt Link [LE5A] enabled at IRQ 66\nIOAPIC[2]: Set routing entry (10-18 -\u003e 0xb9 -\u003e IRQ 66 Mode:1 Active:1)\npci 0000:83:00.1: PCI INT A -\u003e Link[LE5A] -\u003e GSI 66 (level, low) -\u003e IRQ 66\nACPI: PCI Interrupt Link [LE5D] enabled at IRQ 65\nIOAPIC[2]: Set routing entry (10-17 -\u003e 0xc1 -\u003e IRQ 67 Mode:1 Active:1)\npci 0000:84:00.0: PCI INT B -\u003e Link[LE5D] -\u003e GSI 65 (level, low) -\u003e IRQ 67\nACPI: PCI Interrupt Link [LE5C] enabled at IRQ 64\nIOAPIC[2]: Set routing entry (10-16 -\u003e 0xc9 -\u003e IRQ 68 Mode:1 Active:1)\npci 0000:84:00.1: PCI INT A -\u003e Link[LE5C] -\u003e GSI 64 (level, low) -\u003e IRQ 68\npci 0000:87:00.0: PCI INT B -\u003e Link[LE5A] -\u003e GSI 66 (level, low) -\u003e IRQ 66\npci 0000:87:00.1: PCI INT A -\u003e Link[LE5D] -\u003e GSI 65 (level, low) -\u003e IRQ 67\npci 0000:88:00.0: PCI INT B -\u003e Link[LE5C] -\u003e GSI 64 (level, low) -\u003e IRQ 68\npci 0000:88:00.1: PCI INT A -\u003e Link[LE5B] -\u003e GSI 67 (level, low) -\u003e IRQ 65\npci 0000:8b:00.0: PCI INT B -\u003e Link[LE5A] -\u003e GSI 66 (level, low) -\u003e IRQ 66\npci 0000:8b:00.1: PCI INT A -\u003e Link[LE5D] -\u003e GSI 65 (level, low) -\u003e IRQ 67\npci 0000:8c:00.0: PCI INT B -\u003e Link[LE5C] -\u003e GSI 64 (level, low) -\u003e IRQ 68\npci 0000:8c:00.1: PCI INT A -\u003e Link[LE5B] -\u003e GSI 67 (level, low) -\u003e IRQ 65\n\nafter the patch we get:\n\nACPI: PCI Interrupt Link [ILSB] enabled at IRQ 71\nIOAPIC[2]: Set routing entry (10-23 -\u003e 0xa9 -\u003e IRQ 71 Mode:1 Active:1)\npci 0000:80:01.1: PCI INT A -\u003e Link[ILSB] -\u003e GSI 71 (level, low) -\u003e IRQ 71\nACPI: PCI Interrupt Link [LE5B] enabled at IRQ 67\nIOAPIC[2]: Set routing entry (10-19 -\u003e 0xb1 -\u003e IRQ 67 Mode:1 Active:1)\npci 0000:83:00.0: PCI INT B -\u003e Link[LE5B] -\u003e GSI 67 (level, low) -\u003e IRQ 67\nACPI: PCI Interrupt Link [LE5A] enabled at IRQ 66\nIOAPIC[2]: Set routing entry (10-18 -\u003e 0xb9 -\u003e IRQ 66 Mode:1 Active:1)\npci 0000:83:00.1: PCI INT A -\u003e Link[LE5A] -\u003e GSI 66 (level, low) -\u003e IRQ 66\nACPI: PCI Interrupt Link [LE5D] enabled at IRQ 65\nIOAPIC[2]: Set routing entry (10-17 -\u003e 0xc1 -\u003e IRQ 65 Mode:1 Active:1)\npci 0000:84:00.0: PCI INT B -\u003e Link[LE5D] -\u003e GSI 65 (level, low) -\u003e IRQ 65\nACPI: PCI Interrupt Link [LE5C] enabled at IRQ 64\nIOAPIC[2]: Set routing entry (10-16 -\u003e 0xc9 -\u003e IRQ 64 Mode:1 Active:1)\npci 0000:84:00.1: PCI INT A -\u003e Link[LE5C] -\u003e GSI 64 (level, low) -\u003e IRQ 64\npci 0000:87:00.0: PCI INT B -\u003e Link[LE5A] -\u003e GSI 66 (level, low) -\u003e IRQ 66\npci 0000:87:00.1: PCI INT A -\u003e Link[LE5D] -\u003e GSI 65 (level, low) -\u003e IRQ 65\npci 0000:88:00.0: PCI INT B -\u003e Link[LE5C] -\u003e GSI 64 (level, low) -\u003e IRQ 64\npci 0000:88:00.1: PCI INT A -\u003e Link[LE5B] -\u003e GSI 67 (level, low) -\u003e IRQ 67\npci 0000:8b:00.0: PCI INT B -\u003e Link[LE5A] -\u003e GSI 66 (level, low) -\u003e IRQ 66\npci 0000:8b:00.1: PCI INT A -\u003e Link[LE5D] -\u003e GSI 65 (level, low) -\u003e IRQ 65\npci 0000:8c:00.0: PCI INT B -\u003e Link[LE5C] -\u003e GSI 64 (level, low) -\u003e IRQ 64\npci 0000:8c:00.1: PCI INT A -\u003e Link[LE5B] -\u003e GSI 67 (level, low) -\u003e IRQ 67\n\nAs it can be seen that GSIs now get mapped lineary.\n\n[ Impact: simplify irq number mapping on bigger 32-bit systems ]\n\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Jesse Barnes \u003cjbarnes@virtuousgeek.org\u003e\nCc: Len Brown \u003clenb@kernel.org\u003e\nLKML-Reference: \u003c4A01C35C.7060207@kernel.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e286e86e6d2042d67d09244aa0e05ffef75c9d54", "tree": "6fbabd149ba7e0b2fa06a03f39cebe268de9dc8b", "parents": [ "334b8ad7b182fc14d720acd7729afda3ab4c7e3a" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun May 03 18:50:55 2009 +0300" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 11 11:19:00 2009 +0300" }, "message": "KVM: Make EFER reads safe when EFER does not exist\n\nSome processors don\u0027t have EFER; don\u0027t oops if userspace wants us to\nread EFER when we check NX.\n\nCc: stable@kernel.org\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "334b8ad7b182fc14d720acd7729afda3ab4c7e3a", "tree": "695c1cd225be64cba2690c3e07371d5b1847556f", "parents": [ "19bca6ab75d8118ae970fcc656359ddb467ac763" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun May 03 16:34:21 2009 +0300" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 11 11:18:48 2009 +0300" }, "message": "KVM: Fix NX support reporting\n\nNX support is bit 20, not bit 1.\n\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "19bca6ab75d8118ae970fcc656359ddb467ac763", "tree": "3f63eba121f3dd7994330087d65ad085c7e79f3a", "parents": [ "a4d7749be5de4a7261bcbe3c7d96c748792ec455" ], "author": { "name": "Andre Przywara", "email": "andre.przywara@amd.com", "time": "Tue Apr 28 12:45:30 2009 +0200" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Mon May 11 11:18:04 2009 +0300" }, "message": "KVM: SVM: Fix cross vendor migration issue with unusable bit\n\nAMDs VMCB does not have an explicit unusable segment descriptor field,\nso we emulate it by using \"not present\". This has to be setup before\nthe fixups, because this field is used there.\n\nSigned-off-by: Andre Przywara \u003candre.przywara@amd.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "7a309490da98981558a07183786201f02a6341e2", "tree": "204bfd3bc344dbb02be0b1eac29b956f6722e661", "parents": [ "9a8709d44139748fe2e0ab56d20d8c384c8b65ad", "091bf7624d1c90cec9e578a18529f615213ff847" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 09:33:06 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon May 11 09:50:02 2009 +0200" }, "message": "Merge commit \u0027v2.6.30-rc5\u0027 into x86/apic\n\nMerge reason: this branch was on a .30-rc2 base - sync it up with\n all the latest fixes.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b74d446f1f337e3fe906169a3266cb65ffa4179e", "tree": "c17305fcfd9015fe2b8d5bf3526e6935cbea43d7", "parents": [ "091bf7624d1c90cec9e578a18529f615213ff847" ], "author": { "name": "Sam Ravnborg", "email": "sam@ravnborg.org", "time": "Sat May 09 15:35:10 2009 +0600" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun May 10 09:26:54 2009 +0200" }, "message": "x86: Fix false positive section mismatch warnings in the apic code\n\n[ Impact: reduce kernel image size a bit, annotate away warnings ]\n\nSigned-off-by: Sam Ravnborg \u003csam@ravnborg.org\u003e\n[ modified and tested it ]\nSigned-off-by: Rakib Mullick \u003crakib.mullick@gmail.com\u003e\nCc: Marcin Slusarz \u003cmarcin.slusarz@gmail.com\u003e\nLKML-Reference: \u003cb9df5fa10905090235s4bfd26a8o979f93809c9727ad@mail.gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "778dedae0cb76a441145f3a0c5d59fcb3ba296d5", "tree": "37d8393458c6f51f1e50d8610de36d974700849c", "parents": [ "bf8b9a63c18a1a7777571650de0c9f4fd4368ca0" ], "author": { "name": "Huang Weiyi", "email": "weiyi.huang@gmail.com", "time": "Sat May 09 12:54:34 2009 +0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat May 09 07:06:26 2009 +0200" }, "message": "x86: mce: remove duplicated #include\n\nRemove duplicated #include in arch/x86/kernel/cpu/mcheck/mce_intel_64.c.\n\n[ Impact: cleanup ]\n\nSigned-off-by: Huang Weiyi \u003cweiyi.huang@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "02a884c0fe7ec8459d00d34b7d4101af21fc4a86", "tree": "164783f84130482e52290af03d96ff8e887f8605", "parents": [ "36d3793c947f1ef7ba3d24eeeddc1be41adc5ab4" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 08 17:42:16 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 08 17:46:34 2009 -0700" }, "message": "x86, boot: determine compressed code offset at compile time\n\nDetermine the compressed code offset (from the kernel runtime address)\nat compile time. This allows some minor optimizations in\narch/x86/boot/compressed/head_*.S, but more importantly it makes this\nvalue available to the build process, which will enable a future patch\nto export the necessary linear memory footprint into the bzImage\nheader.\n\n[ Impact: cleanup, future patch enabling ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "36d3793c947f1ef7ba3d24eeeddc1be41adc5ab4", "tree": "bf5987e4caacb7aab5a78ca683a3179bd8eba717", "parents": [ "97541912785369925723b6255438ad9fce2ddf04" ], "author": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 08 16:45:15 2009 -0700" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Fri May 08 17:34:52 2009 -0700" }, "message": "x86, boot: use appropriate rep string for move and clear\n\nIn the pre-decompression code, use the appropriate largest possible\nrep movs and rep stos to move code and clear bss, respectively. For\nreverse copy, do note that the initial values are supposed to be the\naddress of the first (highest) copy datum, not one byte beyond the end\nof the buffer.\n\nrep strings are not necessarily the fastest way to perform these\noperations on all current processors, but are likely to be in the\nfuture, and perhaps more importantly, we want to encourage the\narchitecturally right thing to do here.\n\nThis also fixes a couple of trivial inefficiencies on 64 bits.\n\n[ Impact: trivial performance enhancement, increase code similarity ]\n\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" } ], "next": "97541912785369925723b6255438ad9fce2ddf04" }