From mboxrd@z Thu Jan 1 00:00:00 1970 From: nathan_lynch@mentor.com (Nathan Lynch) Date: Mon, 22 Sep 2014 14:17:59 -0500 Subject: [PATCH v10 0/6] ARM: VDSO Message-ID: <1411413485-7675-1-git-send-email-nathan_lynch@mentor.com> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org Please consider this a call for review and test results. I believe this code is stable and ready for inclusion, but patches 3-6 lack explicit acks/reviews so far. Russell, I plan to add at least the sigpage changes (patches 1 and 2) to your patch system shortly after this posting, as they have Reviewed-by tags and are useful independent of the VDSO. Provide fast userspace implementations of gettimeofday and clock_gettime on systems that implement the generic timers extension defined in ARMv7. This follows the example of arm64 in conception but significantly differs in some aspects of the implementation (C vs assembly, mainly). Clocks supported: - CLOCK_REALTIME - CLOCK_MONOTONIC - CLOCK_REALTIME_COARSE - CLOCK_MONOTONIC_COARSE This also provides clock_getres (as arm64 does). getcpu support is planned but not included at this time. For applications to transparently benefit from this change, ARM-specific support code needs to be added to glibc. I hope to have that code added to glibc for the 2.21 release. The VDSO symbols are available for lookup via dlsym even with an unpatched glibc. Note that while the high-precision realtime and monotonic clock support depends on the generic timers extension, support for clock_getres and coarse clocks is independent of the timer implementation and is provided unconditionally. High-resolution clock support requires changes to the arch timer code, posted here: http://lists.infradead.org/pipermail/linux-arm-kernel/2014-September/288452.html The VDSO will function correctly without those changes, but gettimeofday and clock_gettime with CLOCK_REALTIME/CLOCK_MONOTONIC will not be accelerated. Tested on OMAP5 and i.MX6, verifying that results obtained with the vdso are consistent with those obtained from the kernel. On OMAP5 I observe a 3- to 4-fold speedup for gettimeofday / CLOCK_REALTIME, with even better (if less interesting) speedups for the coarse clock ids and clock_getres. I've been testing and benchmarking this with some custom test code which I have hosted here: https://github.com/nlynch-mentor/vdsotest Unpatched FSF GDB may complain "warning: Could not load shared library symbols for linux-vdso.so.1." This is not an ARM-specific issue. Current Fedora and Debian patch their GDB packages to prevent this warning. Changes since v9: - Update to 3.17-rc5. - Fixed minor checkpatch warnings (line length etc). - Removed useless VDSO_LBASE constant. - Added 'notrace' attributes to VDSO-internal functions. - Removed unused debug code from vdsomunge host program. Changes since v8: - Update to 3.17-rc1. - Split out arch timer changes into separate series. - Ensure that VDSO will not attempt to read the counter if access is not enabled; this check can be removed after the arch timer changes are merged. See update_vsyscall and vdso_can_use_arch_timer in patch #5. Changes since v7: - Update to next-20140801. - In arch_setup_additional_pages, fix call to get_unmapped_area - use bytes (not pages) for length argument. - As x86 does, separate data and text into two VMAs, [vvar] and [vdso] respectively. These have different permissions; [vdso] will allow debuggers to set breakpoints, but [vvar] is read-only and cannot be modified even via ptrace. - Use _install_special_mapping for signal page, vvar, and vdso mappings. - Add -DDISABLE_BRANCH_PROFILING. - Add --no-undefined -Bsymbolic to link options to cause linker to error out on unresolved references, making checkundef script unnecessary. - Specify max-page-size, common-page-size in linker options so the true alignment is reflected in program header; otherwise gdb gets confused. - Fix incremental build vs. generated auxvec.h. - Use appropriate unwind directives in __get_datapage. - Added vdso_install target and help text. Install build-id symlinks as x86 does. - Adjust update_vsyscall for changes in struct timekeeper. Changes since v6: - Update to 3.16-rc1. - Remove -lgcc from link step - need to support GCC installations without libgcc. - Force -O2 compilation to prevent GCC from emitting calls to libgcc math routines. - Use custom post-processing to clear the EF_ARM_ABI_FLOAT_SOFT flag if set in the ELF header to produce a shared object which is architecturally allowed to be used by both soft- and hard-float code. - Consolidate common arch timer code instead of duplicating it. - Prevent the VDSO from attempting CP15 access on memory-only architected timer implementations by renaming the clocksource. Changes since v5: - Update to 3.15-rc1. - Place vdso at a randomized offset above the stack along with the sigpage. - Properly export asm/auxvec.h. - Split patch into series for ease of review. Changes since v4: - Map data page at the beginning of the VMA to prevent orphan sections at the end of output invalidating the calculated offset. - Move checkundef into cmd_vdsold to avoid spurious rebuilds. - Change vdso_init message to pr_debug. - Add -fno-stack-protector to cflags. Changes since v3: - Update to 3.14-rc6. - Record vdso base in mm context before installing mapping (for the sake of perf_mmap_event). - Use a more seqcount-like API for critical sections. Using seqcount API directly, however, would leak kernel pointers to userspace when lockdep is enabled. - Trap instead of looping forever in division-by-zero stubs. Changes since v2: - Update to 3.14-rc4. - Make vDSO configurable, depending on AEABI and MMU. - Defer shifting of nanosecond component of timespec: fixes observed 1ns inconsistencies for CLOCK_REALTIME, CLOCK_MONOTONIC (see 45a7905fc48f for arm64 equivalent). - Force reload of seq_count when spinning: without a memory clobber after the load of vdata->seq_count, GCC can generate code like this: 2f8: e59c9020 ldr r9, [ip, #32] 2fc: e3190001 tst r9, #1 300: 1a000033 bne 3d4 304: f57ff05b dmb ish 308: e59c3034 ldr r3, [ip, #52] ; 0x34 ... 3d4: eafffffe b 3d4 - Build vdso.so with -lgcc: calls to __lshrdi3, __divsi3 sometimes emitted (especially with -Os). Override certain libgcc functions to prevent undefined symbols. - Do not clear PG_reserved on vdso pages. - Remove unnecessary get_page calls. - Simplify ELF signature check during init. - Use volatile for asm syscall fallbacks. - Check whether vdso_pagelist is initialized in arm_install_vdso. - Record clocksource mask in data page. - Reduce code duplication in do_realtime, do_monotonic. - Reduce calculations performed in critical sections. - Simplify coarse clock handling. - Move datapage load to its own assembly routine. - Tune vdso_data layout and tweak field names. - Check vdso shared object for undefined symbols during build. Changes since v1: - update to 3.14-rc1 - ensure cache coherency for data page - Document the kernel-to-userspace protocol for vdso data page updates, and note that the timekeeping core prevents concurrent updates. - update wall-to-monotonic fields unconditionally - move vdso_start, vdso_end declarations to vdso.h - correctly build and run when CONFIG_ARM_ARCH_TIMER=n - rearrange linker script to avoid overlapping sections when CONFIG_DEBUGINFO=n - remove use_syscall checks from coarse clock paths - crib BUG_INSTR (0xe7f001f2) from asm/bug.h for text fill Nathan Lynch (6): ARM: use _install_special_mapping for sigpage ARM: place sigpage at a random offset above stack ARM: miscellaneous vdso infrastructure, preparation ARM: add vdso user-space code ARM: vdso initialization, mapping, and synchronization ARM: add CONFIG_VDSO Kconfig and Makefile bits arch/arm/Makefile | 8 + arch/arm/include/asm/Kbuild | 1 - arch/arm/include/asm/auxvec.h | 1 + arch/arm/include/asm/elf.h | 9 + arch/arm/include/asm/mmu.h | 3 + arch/arm/include/asm/vdso.h | 32 ++++ arch/arm/include/asm/vdso_datapage.h | 60 +++++++ arch/arm/include/uapi/asm/Kbuild | 1 + arch/arm/include/uapi/asm/auxvec.h | 7 + arch/arm/kernel/Makefile | 1 + arch/arm/kernel/asm-offsets.c | 5 + arch/arm/kernel/process.c | 72 +++++++- arch/arm/kernel/vdso.c | 211 ++++++++++++++++++++++ arch/arm/mm/Kconfig | 15 ++ arch/arm/vdso/.gitignore | 1 + arch/arm/vdso/Makefile | 74 ++++++++ arch/arm/vdso/datapage.S | 15 ++ arch/arm/vdso/vdso.S | 35 ++++ arch/arm/vdso/vdso.lds.S | 88 ++++++++++ arch/arm/vdso/vdsomunge.c | 201 +++++++++++++++++++++ arch/arm/vdso/vgettimeofday.c | 328 +++++++++++++++++++++++++++++++++++ 21 files changed, 1158 insertions(+), 10 deletions(-) create mode 100644 arch/arm/include/asm/auxvec.h create mode 100644 arch/arm/include/asm/vdso.h create mode 100644 arch/arm/include/asm/vdso_datapage.h create mode 100644 arch/arm/include/uapi/asm/auxvec.h create mode 100644 arch/arm/kernel/vdso.c create mode 100644 arch/arm/vdso/.gitignore create mode 100644 arch/arm/vdso/Makefile create mode 100644 arch/arm/vdso/datapage.S create mode 100644 arch/arm/vdso/vdso.S create mode 100644 arch/arm/vdso/vdso.lds.S create mode 100644 arch/arm/vdso/vdsomunge.c create mode 100644 arch/arm/vdso/vgettimeofday.c -- 1.9.3