)]}' { "log": [ { "commit": "c6622f63db86fcbd41bf6fe05ddf2e00c1e51ced", "tree": "102f3ea0a891212603a3722fece337d6a74d450c", "parents": [ "a00428f5b149e36b8225b2a0812742a6dfb07b8c" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Feb 24 10:06:59 2006 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Feb 24 14:05:56 2006 +1100" }, "message": "powerpc: Implement accurate task and CPU time accounting\n\nThis implements accurate task and cpu time accounting for 64-bit\npowerpc kernels. Instead of accounting a whole jiffy of time to a\ntask on a timer interrupt because that task happened to be running at\nthe time, we now account time in units of timebase ticks according to\nthe actual time spent by the task in user mode and kernel mode. We\nalso count the time spent processing hardware and software interrupts\naccurately. This is conditional on CONFIG_VIRT_CPU_ACCOUNTING. If\nthat is not set, we do tick-based approximate accounting as before.\n\nTo get this accurate information, we read either the PURR (processor\nutilization of resources register) on POWER5 machines, or the timebase\non other machines on\n\n* each entry to the kernel from usermode\n* each exit to usermode\n* transitions between process context, hard irq context and soft irq\n context in kernel mode\n* context switches.\n\nOn POWER5 systems with shared-processor logical partitioning we also\nread both the PURR and the timebase at each timer interrupt and\ncontext switch in order to determine how much time has been taken by\nthe hypervisor to run other partitions (\"steal\" time). Unfortunately,\nsince we need values of the PURR on both threads at the same time to\naccurately calculate the steal time, and since we can only calculate\nsteal time on a per-core basis, the apportioning of the steal time\nbetween idle time (time which we ceded to the hypervisor in the idle\nloop) and actual stolen time is somewhat approximate at the moment.\n\nThis is all based quite heavily on what s390 does, and it uses the\ngeneric interfaces that were added by the s390 developers,\ni.e. account_system_time(), account_user_time(), etc.\n\nThis patch doesn\u0027t add any new interfaces between the kernel and\nuserspace, and doesn\u0027t change the units in which time is reported to\nuserspace by things such as /proc/stat, /proc/\u003cpid\u003e/stat, getrusage(),\ntimes(), etc. Internally the various task and cpu times are stored in\ntimebase units, but they are converted to USER_HZ units (1/100th of a\nsecond) when reported to userspace. Some precision is therefore lost\nbut there should not be any accumulating error, since the internal\naccumulation is at full precision.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "3356bb9f7ba378a6e2709f9df95f4ea52111f4df", "tree": "84f370df6e58cec63132f9acce492d585226e671", "parents": [ "e58c3495e6007af59382540bb21ee941e470d88d" ], "author": { "name": "David Gibson", "email": "david@gibson.dropbear.id.au", "time": "Fri Jan 13 10:26:42 2006 +1100" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Fri Jan 13 21:17:39 2006 +1100" }, "message": "[PATCH] powerpc: Remove lppaca structure from the PACA\n\nAt present the lppaca - the structure shared with the iSeries\nhypervisor and phyp - is contained within the PACA, our own low-level\nper-cpu structure. This doesn\u0027t have to be so, the patch below\nremoves it, making a separate array of lppaca structures.\n\nThis saves approximately 500*NR_CPUS bytes of image size and kernel\nmemory, because we don\u0027t need aligning gap between the Linux and\nhypervisor portions of every PACA. On the other hand it means an\nextra level of dereference in many accesses to the lppaca.\n\nThe patch also gets rid of several places where we assign the paca\naddress to a local variable for no particular reason.\n\nSigned-off-by: David Gibson \u003cdwg@au1.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "1da44037883c0405154d53fe76da27e078456664", "tree": "db6f579831b89c55e0e0c095345b4d1e5bdd0500", "parents": [ "e2f2e58e7968f8446b1078a20a18bf8ea12b4fbc" ], "author": { "name": "Kelly Daly", "email": "kelly@au.ibm.com", "time": "Tue Nov 01 16:59:20 2005 +1100" }, "committer": { "name": "Kelly Daly", "email": "kelly@au.ibm.com", "time": "Tue Nov 01 16:59:20 2005 +1100" }, "message": "merge filename and modify references to iseries/hv_call.h\n\nSigned-off-by: Kelly Daly \u003ckelly@au.ibm.com\u003e\n" }, { "commit": "96c44507601d64f29b8ccc867637292e326c7019", "tree": "1fbdb6f4a3c2d99afaa6a244161518ec78f31048", "parents": [ "985990137e81ca9fd6561cd0f7d1a9695ec57d5a" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Sun Oct 23 17:14:56 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Sun Oct 23 17:14:56 2005 +1000" }, "message": "powerpc: Fix time code for 601 processors\n\nThe 601 doesn\u0027t have the timebase register; instead it has an RTCL\nregister that counts nanoseconds and wraps at 1000000000, and an\nRTCU register that counts seconds. This makes the necessary changes\nfor the merged time code to use the RTCL/U registers when the kernel\nis running on a 601.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "a5b518ed314bfd25ea5e433ce09f8b27080023db", "tree": "777d0f9202136dcff484121ad7673eb65d099567", "parents": [ "e2b5530698cbe8148577b24097eaefcd835ac9ca" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Sat Oct 22 14:55:23 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Sat Oct 22 14:55:23 2005 +1000" }, "message": "ppc64/powerpc: Fix time initialization on SMP systems\n\nThis moves smp_space_timers from arch/ppc64/kernel/smp.c to\narch/powerpc/kernel/time.c and makes it initialize last_jiffy[]\ninstead of paca[].next_jiffy_update_tb, since last_jiffy[] is\nnow what the time code uses. It also declares smp_space_timers\nin include/asm-powerpc/time.h and gets rid of an ifdef in\ndiv128_by_32.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "5d14a18d59b661356409e5a1f624236155a209ba", "tree": "445d21d8b1ec0e58623887f7ceb55c2d3f81f4d5", "parents": [ "17a6392d30b4ed89b88a47a318b2b6de6ae7b946" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Oct 20 22:33:06 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Oct 20 22:33:06 2005 +1000" }, "message": "powerpc: Fix some bugs in the new merged time code\n\nI had the sense of the test for when to use the old 601-style RTC\nregisters inverted. pmac_calibrate_decr and via_calibrate_decr\nweren\u0027t setting ppc_tb_freq, on which all the further calculations\ndepended. Lastly, update_gtod was losing the top 32 bits of\nthe new tb_to_xs value.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" }, { "commit": "f2783c15007468c14972e2617db51e9affc7fad9", "tree": "6c8f57ee8e5cdaeb810a3ccf7f697576a7df7615", "parents": [ "03f88e9f7145b03fd0d855918d54a3bf5342ac5e" ], "author": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Oct 20 09:23:26 2005 +1000" }, "committer": { "name": "Paul Mackerras", "email": "paulus@samba.org", "time": "Thu Oct 20 09:23:26 2005 +1000" }, "message": "powerpc: Merge time.c and asm/time.h.\n\nWe now use the merged time.c for both 32-bit and 64-bit compilation\nwith ARCH\u003dpowerpc, and for ARCH\u003dppc64, but not for ARCH\u003dppc32.\nThis removes setup_default_decr (folds its function into time_init)\nand moves wakeup_decrementer into time.c. This also makes an\nasm-powerpc/rtc.h.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n" } ] }