)]}' { "log": [ { "commit": "5047f09b56d0bc3c21aec9cb16de60283da645c6", "tree": "09a07554b933c3bb912ce3bfc0ea7c7e1f16041c", "parents": [ "c0f1fe00c3923135b2c2f443448585482da8a53e", "5528e568a760442e0ec8fd2dea1f0791875a066b" ], "author": { "name": "David Woodhouse", "email": "dwmw2@infradead.org", "time": "Sat May 06 19:59:18 2006 +0100" }, "committer": { "name": "David Woodhouse", "email": "dwmw2@infradead.org", "time": "Sat May 06 19:59:18 2006 +0100" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6\n\nSigned-off-by: David Woodhouse \u003cdwmw2@infradead.org\u003e\n" }, { "commit": "568cb09b9d889b6f2852ede19772b8e9eed36c1e", "tree": "7ae4d5289c9f20ae323291fe3a5337cc1c3096f7", "parents": [ "99532559dc7a8e686b2cef14c780a7ad5dbd4a31" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Fri May 05 22:35:05 2006 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Fri May 05 22:35:05 2006 +0100" }, "message": "[ARM] 3495/1: EABI: undefine removed syscalls, but...\n\nPatch from Nicolas Pitre\n\n... but only for user space.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "cd95842ca0ffb0e3df3b459832a60f9f4544ed9e", "tree": "ac05eb43e6e3449bcb6dd9357069f795e64d3e9f", "parents": [ "e0a515bc6a2188f02916e976f419a8640312e32a" ], "author": { "name": "Markus Gutschke", "email": "markus@google.com", "time": "Sun Apr 30 15:34:29 2006 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sun Apr 30 15:34:29 2006 +0100" }, "message": "[ARM] 3486/1: Mark memory as clobbered by the ARM _syscallX() macros\n\nPatch from Markus Gutschke\n\nIn order to prevent gcc from making incorrect optimizations, all asm()\nstatements that define system calls should report memory as\nclobbered. Recent versions of the headers for i386 have been changed\naccordingly, but the ARM headers are still defective.\n\nThis patch fixes the bug tracked at\nhttp://bugzilla.kernel.org/show_bug.cgi?id\u003d6205\n\nSigned-off-by: Markus Gutschke \u003cmarkus@google.com\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "56142536868a2be34f261ed8fdca1610f8a73fbd", "tree": "0bd66166b318d8403b1881285f6813ece2acced1", "parents": [ "34c278d3913a15b64943e8c40a16b4f732cc7c59" ], "author": { "name": "David Woodhouse", "email": "dwmw2@shinybook.infradead.org", "time": "Sat Apr 29 01:51:47 2006 +0100" }, "committer": { "name": "David Woodhouse", "email": "dwmw2@infradead.org", "time": "Sat Apr 29 01:51:47 2006 +0100" }, "message": "Remove unneeded _syscallX macros from user view in asm-*/unistd.h\n\nThese aren\u0027t needed by glibc or klibc, and they\u0027re broken in some cases\nanyway. The uClibc folks are apparently switching over to stop using\nthem too (now that we agreed that they should be dropped, at least).\n\nSigned-off-by: David Woodhouse \u003cdwmw2@infradead.org\u003e\n" }, { "commit": "463b158aab247b600e4e93614b7b8f42a66331c9", "tree": "9e5d7b6704e82478c0129f0c94f814cf35b93a4d", "parents": [ "f6835543440c85f20c86c5b006e8404fe6a78109" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Sat Apr 15 16:10:43 2006 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sat Apr 15 16:10:43 2006 +0100" }, "message": "[ARM] 3477/1: ARM EABI: undefine removed syscalls\n\nPatch from Nicolas Pitre\n\nAvoid confusion for libraries assuming that a given syscall is available\nwhen corresponding symbol is defined.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "d53ace70052b5c0a08a4f92993c0614f84920abf", "tree": "1ac610aced6be5dd09433a04114bf842c2326799", "parents": [ "6896eec0296c400db95e4382095fd4d6cf59800c" ], "author": { "name": "Russell King", "email": "rmk@dyn-67.arm.linux.org.uk", "time": "Wed Mar 29 09:42:43 2006 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Thu Mar 30 10:22:01 2006 +0100" }, "message": "[ARM] Allow un-muxed syscalls to be available for everyone\n\nIt\u0027s been a while since the un-muxed socket and ipc syscalls were\nintroduced, so make the unistd.h number definitions visible for\nnon-EABI as well as EABI.\n\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "d9db950cfa3d674ee834d980c329efdf8e4a0568", "tree": "e30c8ce04b2de5d01df22bb30b25276eaa81d365", "parents": [ "6c0fa49b18b09ba9e69c0999f89bc38fad95d8a6" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Thu Feb 16 22:36:15 2006 +0000" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Thu Feb 16 22:36:15 2006 +0000" }, "message": "[ARM] 3339/1: ARM EABI: make unmuxed syscalls visible\n\nPatch from Nicolas Pitre\n\nWith EABI the multiplex sys_ipc and sys_socketcall syscalls are\nunavailable and their support code even removed from the compiled\nkernel, and the new unmuxed syscalls must be used instead.\n\nMake those syscall numbers visible.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "dd35afc22b76766e827c9e67ebc4b7bf6e31ecab", "tree": "3336355470c2d57a2b11a47f8d9bcc1e86546735", "parents": [ "687ad0191488a067b3b3cc94f670cc21f93811e1" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Sat Jan 14 16:36:12 2006 +0000" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sat Jan 14 16:36:12 2006 +0000" }, "message": "[ARM] 3110/5: old ABI compat: multi-ABI syscall entry support\n\nPatch from Nicolas Pitre\n\nThis patch adds the required code to support both user space ABIs at\nthe same time. A second syscall table is created to include legacy ABI\nsyscalls that need an ABI compat wrapper.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "3f2829a31573e3e502b874c8d69a765f7a778793", "tree": "40f64826c0d2964c56c366f770e2d3959123eb59", "parents": [ "ba95e4e4a0a8a3c6aba363d45f78d5f2e2d111eb" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Sat Jan 14 16:31:29 2006 +0000" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Sat Jan 14 16:31:29 2006 +0000" }, "message": "[ARM] 3105/4: ARM EABI: new syscall entry convention\n\nPatch from Nicolas Pitre\n\nFor a while we wanted to change the way syscalls were called on ARM.\nInstead of encoding the syscall number in the swi instruction which\nrequires reading back the instruction from memory to extract that number\nand polluting the data cache, it was decided that simply storing the\nsyscall number into r7 would be more efficient. Since this represents\nan ABI change then making that change at the same time as EABI support\nis the right thing to do.\n\nIt is now expected that EABI user space binaries put the syscall number\ninto r7 and use \"swi 0\" to call the kernel. Syscall register argument\nare also expected to have \"EABI arrangement\" i.e. 64-bit arguments\nshould be put in a pair of registers from an even register number.\n\nExample with long ftruncate64(unsigned int fd, loff_t length):\n\n\tlegacy ABI:\n\t- put fd into r0\n\t- put length into r1-r2\n\t- use \"swi #(0x900000 + 194)\" to call the kernel\n\n\tnew ARM EABI:\n\t- put fd into r0\n\t- put length into r2-r3 (skipping over r1)\n\t- put 194 into r7\n\t- use \"swi 0\" to call the kernel\n\nNote that it is important to use 0 for the swi argument as backward\ncompatibility with legacy ABI user space relies on this.\nThe syscall macros in asm-arm/unistd.h were also updated to support\nboth ABIs and implement the right call method automatically.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "dfb7dac3af623a68262536437af008ed6aba4d88", "tree": "fdc8a61c73257dcf8866cf7b9213ce78d2422e7f", "parents": [ "7024a9b884ed7657fb873e655cd124d85ae792a4" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Sun Oct 30 15:02:22 2005 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@g5.osdl.org", "time": "Sun Oct 30 17:37:20 2005 -0800" }, "message": "[PATCH] unify sys_ptrace prototype\n\nMake sure we always return, as all syscalls should. Also move the common\nprototype to \u003clinux/syscalls.h\u003e\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Miklos Szeredi \u003cmiklos@szeredi.hu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "9c2c389307c03a35672c80725ccf7968656d87ef", "tree": "bbd28f14f72591ff42a8a1f12e3827a73bba1e7b", "parents": [ "5f5024130287a9467a41b9f94ec170958ae45cbd" ], "author": { "name": "Russell King", "email": "rmk@dyn-67.arm.linux.org.uk", "time": "Fri Sep 09 11:12:51 2005 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Fri Sep 09 11:12:51 2005 +0100" }, "message": "[ARM] Add memory type based allocation syscalls\n\nAdd syscall numbers and syscall table entries for mbind,\nset_mempolicy and get_mempolicy.\n\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "68d9102f76de7a923fb81c8b6de4764f8f50ed17", "tree": "635711b71ef8aca704638b01bb2f58902b93d04a", "parents": [ "147056fb84150966d736fe21fa01d5e0f08e0980" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Thu Sep 01 12:37:13 2005 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Thu Sep 01 12:37:13 2005 +0100" }, "message": "[ARM] 2865/2: fix fadvise64_64 syscall argument passing\n\nPatch from Nicolas Pitre\n\nThe prototype for sys_fadvise64_64() is:\n long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)\nThe argument list is therefore as follows on legacy ABI:\n\tfd: type int (r0)\n\toffset: type long long (r1-r2)\n\tlen: type long long (r3-sp[0])\n\tadvice: type int (sp[4])\nWith EABI this becomes:\n\tfd: type int (r0)\n\toffset: type long long (r2-r3)\n\tlen: type long long (sp[0]-sp[4])\n\tadvice: type int (sp[8])\nNot only do we have ABI differences here, but the EABI version requires\none additional word on the syscall stack.\nTo avoid the ABI mismatch and the extra stack space required with EABI\nthis syscall is now defined with a different argument ordering\non ARM as follows:\n long sys_arm_fadvise64_64(int fd, int advice, loff_t offset, loff_t len)\nThis gives us the following ABI independent argument distribution:\n\tfd: type int (r0)\n\tadvice: type int (r1)\n\toffset: type long long (r2-r3)\n\tlen: type long long (sp[0]-sp[4])\nNow, since the syscall entry code takes care of 5 registers only by\ndefault including the store of r4 to the stack, we need a wrapper to\nstore r5 to the stack as well. Because that wrapper was missing and was\nalways required this means that sys_fadvise64_64 never worked on ARM and\ntherefore we can safely reuse its syscall number for our new\nsys_arm_fadvise64_64 interface.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "cb85a502e0c2019d8bc302b011150bd62ecf70ab", "tree": "727e8342c862c09c89cc719a432d70e1e634d043", "parents": [ "01b9c414828d951148a3792237ff3bf6e6debc85" ], "author": { "name": "Nicolas Pitre", "email": "nico@cam.org", "time": "Mon Aug 29 22:46:32 2005 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Mon Aug 29 22:46:32 2005 +0100" }, "message": "[ARM] 2858/1: ARM has sys_fadvise64_64 only\n\nPatch from Nicolas Pitre\n\nThere is no need to define __ARCH_WANT_SYS_FADVISE64 on ARM since it\nonly serves to compile in a compatibility wrapper for sys_fadvise64\nwhich never was tied to any syscall number.\n\nSigned-off-by: Nicolas Pitre \u003cnico@cam.org\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "498de0cc5ea3009af762dc968a46d6f5df96b67a", "tree": "3f9161c9c2f31c35dff635f3c4b75deaaf910c77", "parents": [ "2ba84684e8cf6f980e4e95a2300f53a505eb794e" ], "author": { "name": "Robert Love", "email": "rml@novell.com", "time": "Mon Aug 15 10:57:08 2005 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Mon Aug 15 10:57:08 2005 +0100" }, "message": "[ARM] Add syscall stubs for inotify and ioprio system calls\n\nSigned-off-by: Robert Love \u003crml@novell.com\u003e\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "2d2669b62984b8d76b05a6a045390a3250317d21", "tree": "822f62adf59f2e6302a16289cc99b0f9b873cfb4", "parents": [ "3a1e501511a1e2c665c566939047794dcf86466b" ], "author": { "name": "Nicolas Pitre", "email": "nico@org.rmk.(none)", "time": "Fri Apr 29 22:08:33 2005 +0100" }, "committer": { "name": "Russell King", "email": "rmk+kernel@arm.linux.org.uk", "time": "Fri Apr 29 22:08:33 2005 +0100" }, "message": "[PATCH] ARM: 2651/3: kernel helpers for NPTL support\n\nPatch from Nicolas Pitre\n\nThis patch entirely reworks the kernel assistance for NPTL on ARM.\nIn particular this provides an efficient way to retrieve the TLS\nvalue and perform atomic operations without any instruction emulation\nnor special system call. This even allows for pre ARMv6 binaries to\nbe forward compatible with SMP systems without any penalty.\nThe problematic and performance critical operations are performed\nthrough segment of kernel provided user code reachable from user space\nat a fixed address in kernel memory. Those fixed entry points are\nwithin the vector page so we basically get it for free as no extra\nmemory page is required and nothing else may be mapped at that\nlocation anyway.\nThis is different from (but doesn\u0027t preclude) a full blown VDSO\nimplementation, however a VDSO would prevent some assembly tricks with\nconstants that allows for efficient branching to those code segments.\nAnd since those code segments only use a few cycles before returning to\nuser code, the overhead of a VDSO far call would add a significant\noverhead to such minimalistic operations.\nThe ARM_NR_set_tls syscall also changed number. This is done for two\nreasons:\n1) this patch changes the way the TLS value was previously meant to be\n retrieved, therefore we ensure whatever library using the old way\n gets fixed (they only exist in private tree at the moment since the\n NPTL work is still progressing).\n2) the previous number was allocated in a range causing an undefined\n instruction trap on kernels not supporting that syscall and it was\n determined that allocating it in a range returning -ENOSYS would be\n much nicer for libraries trying to determine if the feature is\n present or not.\n\nSigned-off-by: Nicolas Pitre\nSigned-off-by: Russell King \u003crmk+kernel@arm.linux.org.uk\u003e\n" }, { "commit": "1da177e4c3f41524e886b7f1b8a0c1fc7321cac2", "tree": "0bba044c4ce775e45a88a51686b5d9f90697ea9d", "parents": [], "author": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@ppc970.osdl.org", "time": "Sat Apr 16 15:20:36 2005 -0700" }, "message": "Linux-2.6.12-rc2\n\nInitial git repository build. I\u0027m not bothering with the full history,\neven though we have it. We can create a separate \"historical\" git\narchive of that later if we want to, and in the meantime it\u0027s about\n3.2GB when imported into git - space that would just make the early\ngit days unnecessarily complicated, when we don\u0027t have a lot of good\ninfrastructure for it.\n\nLet it rip!\n" } ] }