Linux kernel documentation tree maintained by Jonathan Corbet http://mirrors.hust.edu.cn/git/lwn.git/atom?h=v3.12.52 2012-11-29T21:23:01+00:00 2012-11-29T21:23:01+00:00 H. Peter Anvin hpa@linux.intel.com 2012-11-28T19:50:24+00:00 urn:sha1:d55c5a93db2d5fa95f233ab153f594365d95b777 All 486+ CPUs support CMPXCHG, so remove the fallback 386 support code. Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Link: http://lkml.kernel.org/r/1354132230-21854-3-git-send-email-hpa@linux.intel.com 2011-07-23T00:02:24+00:00 Linus Torvalds torvalds@linux-foundation.org 2011-07-23T00:02:24+00:00 urn:sha1:eb47418dc56baaca33d270a868d8ddaa81150952 * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86: Fix write lock scalability 64-bit issue x86: Unify rwsem assembly implementation x86: Unify rwlock assembly implementation x86, asm: Fix binutils 2.16 issue with __USER32_CS x86, asm: Cleanup thunk_64.S x86, asm: Flip RESTORE_ARGS arguments logic x86, asm: Flip SAVE_ARGS arguments logic x86, asm: Thin down SAVE/RESTORE_* asm macros 2011-07-21T18:41:57+00:00 Robert Richter robert.richter@amd.com 2011-06-07T09:49:55+00:00 urn:sha1:1ac2e6ca44e13a087eb7438d284f887097ee7e84 copy_from_user_nmi() is used in oprofile and perf. Moving it to other library functions like copy_from_user(). As this is x86 code for 32 and 64 bits, create a new file usercopy.c for unified code. Signed-off-by: Robert Richter <robert.richter@amd.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110607172413.GJ20052@erda.amd.com Signed-off-by: Ingo Molnar <mingo@elte.hu> 2011-07-21T07:03:32+00:00 Jan Beulich JBeulich@novell.com 2011-07-19T12:00:19+00:00 urn:sha1:a738669464a1e0d8e7b20f631120192f9cf7cfbd Rather than having two functionally identical implementations for 32- and 64-bit configurations, use the previously extended assembly abstractions to fold the rwsem two implementations into a shared one. Signed-off-by: Jan Beulich <jbeulich@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4E258DF3020000780004E3ED@nat28.tlf.novell.com Signed-off-by: Ingo Molnar <mingo@elte.hu> 2011-07-21T07:03:31+00:00 Jan Beulich JBeulich@novell.com 2011-07-19T11:59:51+00:00 urn:sha1:4625cd637919edfb562e0d62abf94f52e9321335 Rather than having two functionally identical implementations for 32- and 64-bit configurations, extend the existing assembly abstractions enough to fold the two rwlock implementations into a shared one. Signed-off-by: Jan Beulich <jbeulich@novell.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/4E258DD7020000780004E3EA@nat28.tlf.novell.com Signed-off-by: Ingo Molnar <mingo@elte.hu> 2011-02-28T10:20:49+00:00 Christoph Lameter cl@linux.com 2011-02-28T10:02:24+00:00 urn:sha1:b9ec40af0e18fb7d02106be148036c2ea490fdf9 Support this_cpu_cmpxchg_double() using the cmpxchg16b and cmpxchg8b instructions. -tj: s/percpu_cmpxchg16b/percpu_cmpxchg16b_double/ for consistency and other cosmetic changes. Signed-off-by: Christoph Lameter <cl@linux.com> Signed-off-by: Tejun Heo <tj@kernel.org> 2010-07-28T23:53:49+00:00 H. Peter Anvin hpa@linux.intel.com 2010-07-28T23:53:49+00:00 urn:sha1:90c8f92f5c807807ca74d5f2f313794925174e6b Move cmpxchg emulation code from arch/x86/kernel/cpu (which is otherwise CPU identification) to arch/x86/lib, where other emulation code lives already. Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> LKML-Reference: <AANLkTikAmaDPji-TVDarmG1yD=fwbffcsmEU=YEuP+8r@mail.gmail.com> 2010-05-18T15:40:05+00:00 Linus Torvalds torvalds@linux-foundation.org 2010-05-18T15:40:05+00:00 urn:sha1:93c9d7f60c0cb7715890b1f9e159da6f4d1f5a65 * 'x86-atomic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86: Fix LOCK_PREFIX_HERE for uniprocessor build x86, atomic64: In selftest, distinguish x86-64 from 586+ x86-32: Fix atomic64_inc_not_zero return value convention lib: Fix atomic64_inc_not_zero test lib: Fix atomic64_add_unless return value convention x86-32: Fix atomic64_add_unless return value convention lib: Fix atomic64_add_unless test x86: Implement atomic[64]_dec_if_positive() lib: Only test atomic64_dec_if_positive on archs having it x86-32: Rewrite 32-bit atomic64 functions in assembly lib: Add self-test for atomic64_t x86-32: Allow UP/SMP lock replacement in cmpxchg64 x86: Add support for lock prefix in alternatives 2010-04-29T23:53:17+00:00 H. Peter Anvin hpa@zytor.com 2010-04-29T23:53:17+00:00 urn:sha1:d9c5841e22231e4e49fd0a1004164e6fce59b7a6 Merge reason: Conflict between LOCK_PREFIX_HERE and relative alternatives pointers Resolved Conflicts: arch/x86/include/asm/alternative.h arch/x86/kernel/alternative.c Signed-off-by: H. Peter Anvin <hpa@zytor.com> 2010-03-10T12:34:12+00:00 Ingo Molnar mingo@elte.hu 2009-06-06T11:58:12+00:00 urn:sha1:ba7e4d13fc7e25af1d167d40e6f028298dfc55ad The PEBS+LBR decoding magic needs the insn_get_length() infrastructure to be able to decode x86 instruction length. So split it out of KPROBES dependency and make it enabled when either KPROBES or PERF_EVENTS is enabled. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>