Messages in this thread | | | From | Denys Vlasenko <> | Subject | [PATCH v4 0/17] x86: entry.S optimizations | Date | Fri, 8 Aug 2014 19:44:23 +0200 |
| |
Version 4 of the patchset.
Please consider applying at least two first patches, they are definitely safe, and the second one fixes a latent bug.
Changes since v3: = simplified iret stack handling on SYSCALL64 fastpath: got rid of FIXUP_TOP_OF_STACK and RESTORE_TOP_OF_STACK, got rid of thread_struct::usersp. = save_paranoid cleaned up. = folded test_in_nmi and IA32_ARG_FIXUP macros into their users. = got rid of KERNEL_STACK_OFFSET. = other small optimizations. = fixed comments about SYSCALL from 32bit mode.
Changes since v2: = fixed pre-existing latent bug: wrong symbolic constant usage: R11->ARGOFFSET = per Oleg's request, added comments about various syscall instructions
Changes since v1 (mainly in patch 4/6): = Reverted changes to "partial pt_regs saving" on interrupt path. = Folded PARTIAL_FRAME macro into DEFAULT_FRAME. Patch v1 had a bug (incorrect dwarf debug info generation). = Corrected more comments. = Added use of SAVE_* macros to error_entry and save_paranoid. = Added another cleanup rename patch.
TODO: = "idtentry" macro uses a subroutine to factor out a largish common code block. "interrupt" macro inlines a similar block every time (~20 instances). Maybe factor it out?
CC: Linus Torvalds <torvalds@linux-foundation.org> CC: Oleg Nesterov <oleg@redhat.com> CC: "H. Peter Anvin" <hpa@zytor.com> CC: Andy Lutomirski <luto@amacapital.net> CC: Frederic Weisbecker <fweisbec@gmail.com> CC: X86 ML <x86@kernel.org> CC: Alexei Starovoitov <ast@plumgrid.com> CC: Will Drewry <wad@chromium.org> CC: Kees Cook <keescook@chromium.org> CC: linux-kernel@vger.kernel.org
Denys Vlasenko (17): x86: entry_64.S: delete unused code x86: ia32entry.S: fix wrong symbolic constant usage: R11->ARGOFFSET x86: open-code register save/restore in trace_hardirqs thunks x86: entry_64.S: fold SAVE_ARGS_IRQ macro into its sole user x86: entry_64.S: always allocate complete "struct pt_regs" x86: mass removal of ARGOFFSET x86: rename some macros and labels, no code changes x86: add comments about various syscall instructions, no code changes x86: entry_64.S: move save_paranoid and ret_from_fork closer to their users x86: entry_64.S: rename save_paranoid to paranoid_entry, no code changes x86: entry_64.S: fold test_in_nmi macro into its only user x86: get rid of KERNEL_STACK_OFFSET x86: ia32entry.S: fold IA32_ARG_FIXUP macro into its callers x86: ia32entry.S: use mov instead of push/pop where possible x86: code shrink in paranoid_exit x86: entry_64.S: trivial optimization for ENOSYS x86: simplify iret stack handling on SYSCALL64 fastpath
arch/x86/ia32/ia32entry.S | 366 +++++++++-------- arch/x86/include/asm/calling.h | 226 +++++------ arch/x86/include/asm/compat.h | 2 +- arch/x86/include/asm/irqflags.h | 4 +- arch/x86/include/asm/processor.h | 1 - arch/x86/include/asm/ptrace.h | 21 +- arch/x86/include/asm/thread_info.h | 8 +- arch/x86/include/uapi/asm/ptrace-abi.h | 16 +- arch/x86/include/uapi/asm/ptrace.h | 13 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/entry_64.S | 708 ++++++++++++++------------------- arch/x86/kernel/preempt.S | 16 +- arch/x86/kernel/process_32.c | 3 +- arch/x86/kernel/process_64.c | 11 +- arch/x86/kernel/smpboot.c | 3 +- arch/x86/lib/thunk_64.S | 29 +- arch/x86/syscalls/syscall_64.tbl | 2 +- arch/x86/um/sys_call_table_64.c | 2 +- arch/x86/xen/smp.c | 3 +- 19 files changed, 699 insertions(+), 737 deletions(-)
-- 1.8.1.4
| |