| /linux/tools/testing/selftests/ftrace/test.d/kprobe/ |
| H A D | kprobe_opt_types.tc | 19 DEFAULT=$(cat /proc/sys/debug/kprobes-optimization)
20 echo 1 > /proc/sys/debug/kprobes-optimization
29 echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization
33 echo "$DEFAULT" > /proc/sys/debug/kprobes-optimization
|
| /linux/Documentation/trace/ |
| H A D | kprobes.rst | 54 probes work and how jump optimization works. They explain certain
169 How Does Jump Optimization Work?
181 When a probe is registered, before attempting this optimization,
221 Pre-optimization
242 Optimization subsection
251 of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
262 the optimization is complete, the kprobe is just dequeued from the
263 optimized list. If the optimization has been done, the jump is
273 .. [4] This optimization-safety checking may be replaced with the
278 The jump optimization changes the kprobe's pre_handler behavior.
[all …]
|
| /linux/Documentation/process/ |
| H A D | volatile-considered-harmful.rst | 15 to suppress optimization, which is almost never what one really wants to
19 all optimization-related problems in a more efficient way.
23 unwanted optimization. If they are being used properly, there will be no
42 forget anything it knows. There will be no optimization problems with
59 optimization, so, once again, volatile is unnecessary.
|
| /linux/tools/perf/pmu-events/arch/x86/amdzen2/ |
| H A D | floating-point.json | 71 …ful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
77 …optimization (have Z-bit either set or pass). This is a dispatch based speculative event, and is u…
83 …ful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
89 …ful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
|
| /linux/tools/perf/pmu-events/arch/x86/amdzen3/ |
| H A D | floating-point.json | 70 …ful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
76 …optimization (have Z-bit either set or pass). This is a dispatch based speculative event, and is u…
82 …ful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
88 …ful for measuring the effectiveness of the Move elimination and Scalar code optimization schemes.",
|
| /linux/Documentation/dev-tools/ |
| H A D | propeller.rst | 8 compiler. Propeller is a profile-guided optimization (PGO) method used
15 A few important notes about adopting Propeller optimization:
17 #. Although it can be used as a standalone optimization step, it is
34 The Propeller optimization process involves the following steps:
|
| /linux/arch/x86/ |
| H A D | Kconfig.cpu | 2 # Put here option for CPU selection and depending optimization
99 copy optimization, compiles the kernel with optimization flags
148 some extended instructions, and passes appropriate optimization
156 some extended instructions, and passes appropriate optimization
164 like a 586 with TSC, and sets some GCC optimization flags (like a
254 # LLVM 19 introduces an optimization that resolves some high stack
|
| /linux/tools/power/acpi/ |
| H A D | Makefile.config | 61 # use '-Os' optimization if available, else use -O2
62 OPTIMIZATION := $(call cc-supports,-Os,-O2)
87 CFLAGS += $(OPTIMIZATION) -fomit-frame-pointer
|
| /linux/arch/powerpc/purgatory/ |
| H A D | Makefile | 5 # When profile-guided optimization is enabled, llvm emits two different
7 # optimization flags.
|
| /linux/tools/perf/pmu-events/arch/x86/amdzen1/ |
| H A D | floating-point.json | 172 …r measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number…
178 …"BriefDescription": "Number of Ops that are candidates for optimization (have Z-bit either set or …
179 …of the Move elimination and Scalar code optimization schemes. Number of Ops that are candidates fo…
186 …r measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number…
193 …r measuring the effectiveness of the Move elimination and Scalar code optimization schemes. Number…
|
| /linux/include/drm/ |
| H A D | drm_cache.h | 55 * only, but permits an optimization to be enabled in some cases, where in drm_arch_can_wc_memory()
63 * case. However, on ARM and arm64, enabling this optimization on a in drm_arch_can_wc_memory()
67 * optimization entirely for ARM and arm64. in drm_arch_can_wc_memory()
|
| /linux/arch/alpha/include/asm/ |
| H A D | elf.h | 20 #define R_ALPHA_LITERAL 4 /* GP relative 16 bit w/optimization */
21 #define R_ALPHA_LITUSE 5 /* Optimization hint for LITERAL */
130 specific libraries for optimization. This is more specific in
|
| /linux/Documentation/staging/ |
| H A D | static-keys.rst | 91 optimization.
100 In order to make use of this optimization you must first define a key::
184 to take advantage of this optimization. If there is no architecture support, we
248 Without the jump label optimization it looks like::
327 this optimization is about reducing the number of branches. In addition, we've
|
| /linux/arch/x86/purgatory/ |
| H A D | Makefile | 16 # When profile-guided optimization is enabled, llvm emits two different
18 # optimization flags.
|
| /linux/lib/crypto/mpi/ |
| H A D | mpih-div.c | 73 /* Possible optimization: in mpihelp_mod_1()
132 /* Possible optimization: in mpihelp_mod_1()
350 /* Possible optimization: We already have (q * n0) and (1 * n1) in mpihelp_divrem()
422 /* Possible optimization: in mpihelp_divmod_1()
480 /* Possible optimization: in mpihelp_divmod_1()
|
| /linux/arch/riscv/purgatory/ |
| H A D | Makefile | 39 # When profile-guided optimization is enabled, llvm emits two different
41 # optimization flags.
|
| /linux/drivers/pci/ |
| H A D | Kconfig | 202 TPH allows endpoint devices to provide optimization hints, such as
262 prompt "PCI Express hierarchy optimization setting"
270 The following choices set the MPS and MRRS optimization strategy
|
| /linux/arch/powerpc/math-emu/ |
| H A D | udivmodti4.c | 83 This special case is necessary, not an optimization. in _fp_udivmodti4()
140 This special case is necessary, not an optimization. */ in _fp_udivmodti4()
|
| /linux/lib/raid6/ |
| H A D | sse2.c | 94 z0 = stop; /* P/Q right side optimization */ in raid6_sse21_xor_syndrome()
117 /* P/Q left side optimization */ in raid6_sse21_xor_syndrome()
205 z0 = stop; /* P/Q right side optimization */ in raid6_sse22_xor_syndrome()
239 /* P/Q left side optimization */ in raid6_sse22_xor_syndrome()
371 z0 = stop; /* P/Q right side optimization */ in raid6_sse24_xor_syndrome()
431 /* P/Q left side optimization */ in raid6_sse24_xor_syndrome()
|
| H A D | s390vx.uc | 87 z0 = stop; /* P/Q right side optimization */
107 /* P/Q left side optimization */
|
| H A D | int.uc | 112 z0 = stop; /* P/Q right side optimization */
128 /* P/Q left side optimization */
|
| H A D | avx2.c | 89 z0 = stop; /* P/Q right side optimization */ in raid6_avx21_xor_syndrome()
112 /* P/Q left side optimization */ in raid6_avx21_xor_syndrome()
199 z0 = stop; /* P/Q right side optimization */ in raid6_avx22_xor_syndrome()
234 /* P/Q left side optimization */ in raid6_avx22_xor_syndrome()
360 z0 = stop; /* P/Q right side optimization */ in raid6_avx24_xor_syndrome()
423 /* P/Q left side optimization */ in raid6_avx24_xor_syndrome()
|
| /linux/kernel/ |
| H A D | kprobes.c | 449 /* Return true if the kprobe is ready for optimization. */
512 /* Optimization staging list, protected by 'kprobe_mutex' */
529 * The optimization/unoptimization refers 'online_cpus' via in do_optimize_kprobes()
540 /* Optimization never be done when disarmed */ in do_optimize_kprobes()
659 /* Wait for completing optimization and unoptimization */
684 /* Check if the kprobe is disabled or not ready for optimization. */ in optimize_kprobe()
797 /* Dequeue from the (un)optimization queue */ in kill_optimized_kprobe()
862 /* For preparing optimization, jump_label_text_reserved() is called. */ in try_to_optimize_kprobe()
890 /* If optimization is already allowed, just return. */ in optimize_all_kprobes()
903 pr_info("kprobe jump-optimization is enabled. All kprobes are optimized if possible.\n"); in optimize_all_kprobes()
[all …]
|
| /linux/tools/perf/tests/ |
| H A D | dwarf-unwind.c | 25 * the frame of the caller. Clang can disable this optimization on a called
150 * prevent potential optimization, which may expand in test_dwarf_unwind__krava_3()
|
| /linux/include/linux/generic_pt/ |
| H A D | common.h | 124 * contained by the range. The optimization objective is to minimize the
131 * the optimization objective is to only flush IOVA that has been
|