summaryrefslogtreecommitdiffstats
path: root/arch
AgeCommit message (Expand)AuthorFilesLines
2011-02-22x86-64, NUMA: Seperate out numa_alloc_distance() from numa_set_distance()Yinghai Lu1-35/+40
2011-02-22x86-64, NUMA: Add proper function comments to global functionsTejun Heo2-10/+69
2011-02-22x86-64, NUMA: Move NUMA emulation into numa_emulation.cTejun Heo4-476/+488
2011-02-22x86-64, NUMA: Prepare numa_emulation() for moving NUMA emulation into a separ...Tejun Heo1-23/+33
2011-02-21x86-64, NUMA: Do not scan two times for setup_node_bootmem()Yinghai Lu1-20/+12
2011-02-17x86-64, NUMA: Put dummy_numa_init() in the init sectionYinghai Lu1-1/+1
2011-02-17x86-64, NUMA: Don't call __pa() with invalid address in numa_reset_distance()Yinghai Lu1-4/+6
2011-02-16x86-64, NUMA: Unify emulated distance mappingTejun Heo6-176/+40
2011-02-16x86-64, NUMA: Unify emulated apicid -> node mapping transformationTejun Heo3-33/+16
2011-02-16x86-64, NUMA: Emulate directly from numa_meminfoTejun Heo1-100/+71
2011-02-16x86-64, NUMA: Wrap node ID during emulationTejun Heo1-10/+2
2011-02-16x86-64, NUMA: Make emulation code build numa_meminfo and share the registrati...Tejun Heo1-87/+86
2011-02-16x86-64, NUMA: Build and use direct emulated nid -> phys nid mappingTejun Heo1-29/+35
2011-02-16x86-64, NUMA: Trivial changes to prepare for emulation updatesTejun Heo1-16/+18
2011-02-16x86-64, NUMA: Implement generic node distance handlingTejun Heo5-17/+109
2011-02-16x86-64, NUMA: Kill mem_nodes_parsedTejun Heo4-13/+20
2011-02-16x86-64, NUMA: Rename cpu_nodes_parsed to numa_nodes_parsedTejun Heo4-10/+10
2011-02-16x86-64, NUMA: Kill numa_nodes[]Tejun Heo4-58/+53
2011-02-16x86-64, NUMA: Add common find_node_by_addr()Tejun Heo4-31/+20
2011-02-16x86-64, NUMA: consolidate and improve memblk sanity checksTejun Heo1-50/+49
2011-02-16x86-64, NUMA: make numa_cleanup_meminfo() prettierTejun Heo1-17/+19
2011-02-16x86-64, NUMA: Separate out numa_cleanup_meminfo()Tejun Heo1-37/+46
2011-02-16x86-64, NUMA: Introduce struct numa_meminfoTejun Heo1-70/+75
2011-02-16x86-64, NUMA: Remove %NULL @nodeids handling from compute_hash_shift()Tejun Heo1-7/+7
2011-02-16x86-64, NUMA: Kill {acpi|amd|dummy}_scan_nodes()Tejun Heo5-26/+0
2011-02-16x86-64, NUMA: Unify the rest of memblk registrationTejun Heo3-74/+68
2011-02-16x86-64, NUMA: Unify use of memblk in all init methodsTejun Heo4-29/+8
2011-02-16x86-64, NUMA: Factor out memblk handling into numa_{add|register}_memblk()Tejun Heo5-94/+117
2011-02-16x86-64, NUMA: Kill {acpi|amd}_get_nodes()Tejun Heo5-39/+10
2011-02-16x86-64, NUMA: Use common numa_nodes[]Tejun Heo4-42/+45
2011-02-16x86-64, NUMA: Move apicid to numa mapping initialization from amd_scan_nodes(...Tejun Heo1-20/+23
2011-02-16x86-64, NUMA: Remove local variable found from amd_numa_init()Tejun Heo1-4/+2
2011-02-16x86-64, NUMA: Use common {cpu|mem}_nodes_parsedTejun Heo4-24/+31
2011-02-16x86-64, NUMA: Restructure initmem_init()Tejun Heo2-46/+52
2011-02-16x86, NUMA: Move *_numa_init() invocations into initmem_init()Tejun Heo6-20/+20
2011-02-16x86-64, NUMA: Wrap acpi_numa_init() so that failure can be indicated by retur...Tejun Heo3-1/+12
2011-02-16x86-64, NUMA: Unify {acpi|amd}_{numa_init|scan_nodes}() arguments and return ...Tejun Heo6-16/+16
2011-02-16x86, NUMA: Drop @start/last_pfn from initmem_init()Tejun Heo6-23/+14
2011-02-16x86-64, NUMA: Simplify hotplug node handling in acpi_numa_memory_affinity_init()Tejun Heo1-18/+13
2011-02-16x86-64, NUMA: Make dummy node initialization path similar to non-dummy onesTejun Heo1-2/+3
2011-02-16Merge branch 'x86/amd-nb' into x86/mmIngo Molnar6-25/+154
2011-02-16Merge branch 'x86/numa' into x86/mmIngo Molnar34-488/+504
2011-02-16Merge branch 'x86/bootmem' into x86/mmIngo Molnar8-108/+145
2011-02-15x86, amd: Initialize variable properlyBorislav Petkov1-3/+3
2011-02-14x86, numa: Add error handling for bad cpu-to-node mappingsDavid Rientjes2-0/+8
2011-02-14Merge commit 'v2.6.38-rc4' into x86/numaIngo Molnar57-266/+385
2011-02-14x86: Emit "mem=nopentium ignored" warning when not supportedKamal Mostafa1-2/+5
2011-02-14x86: Fix panic when handling "mem={invalid}" paramKamal Mostafa1-0/+3
2011-02-14x86: Avoid tlbstate lock if not enough cpusShaohua Li1-7/+4
2011-02-14x86: Scale up the number of TLB invalidate vectors with NR_CPUs, up to 32Shaohua Li1-4/+9