linux/include/asm-generic/vmlinux.lds.h

442 lines
14 KiB
C
Raw Normal View History

#ifndef LOAD_OFFSET
#define LOAD_OFFSET 0
#endif
#ifndef VMLINUX_SYMBOL
#define VMLINUX_SYMBOL(_sym_) _sym_
#endif
/* Align . to a 8 byte boundary equals to maximum function alignment. */
#define ALIGN_FUNCTION() . = ALIGN(8)
/* The actual configuration determine if the init/exit sections
* are handled as text/data or they can be discarded (which
* often happens at runtime)
*/
#ifdef CONFIG_HOTPLUG
#define DEV_KEEP(sec) *(.dev##sec)
#define DEV_DISCARD(sec)
#else
#define DEV_KEEP(sec)
#define DEV_DISCARD(sec) *(.dev##sec)
#endif
#ifdef CONFIG_HOTPLUG_CPU
#define CPU_KEEP(sec) *(.cpu##sec)
#define CPU_DISCARD(sec)
#else
#define CPU_KEEP(sec)
#define CPU_DISCARD(sec) *(.cpu##sec)
#endif
#if defined(CONFIG_MEMORY_HOTPLUG)
#define MEM_KEEP(sec) *(.mem##sec)
#define MEM_DISCARD(sec)
#else
#define MEM_KEEP(sec)
#define MEM_DISCARD(sec) *(.mem##sec)
#endif
ftrace: create __mcount_loc section This patch creates a section in the kernel called "__mcount_loc". This will hold a list of pointers to the mcount relocation for each call site of mcount. For example: objdump -dr init/main.o [...] Disassembly of section .text: 0000000000000000 <do_one_initcall>: 0: 55 push %rbp [...] 000000000000017b <init_post>: 17b: 55 push %rbp 17c: 48 89 e5 mov %rsp,%rbp 17f: 53 push %rbx 180: 48 83 ec 08 sub $0x8,%rsp 184: e8 00 00 00 00 callq 189 <init_post+0xe> 185: R_X86_64_PC32 mcount+0xfffffffffffffffc [...] We will add a section to point to each function call. .section __mcount_loc,"a",@progbits [...] .quad .text + 0x185 [...] The offset to of the mcount call site in init_post is an offset from the start of the section, and not the start of the function init_post. The mcount relocation is at the call site 0x185 from the start of the .text section. .text + 0x185 == init_post + 0xa We need a way to add this __mcount_loc section in a way that we do not lose the relocations after final link. The .text section here will be attached to all other .text sections after final link and the offsets will be meaningless. We need to keep track of where these .text sections are. To do this, we use the start of the first function in the section. do_one_initcall. We can make a tmp.s file with this function as a reference to the start of the .text section. .section __mcount_loc,"a",@progbits [...] .quad do_one_initcall + 0x185 [...] Then we can compile the tmp.s into a tmp.o gcc -c tmp.s -o tmp.o And link it into back into main.o. ld -r main.o tmp.o -o tmp_main.o mv tmp_main.o main.o But we have a problem. What happens if the first function in a section is not exported, and is a static function. The linker will not let the tmp.o use it. This case exists in main.o as well. Disassembly of section .init.text: 0000000000000000 <set_reset_devices>: 0: 55 push %rbp 1: 48 89 e5 mov %rsp,%rbp 4: e8 00 00 00 00 callq 9 <set_reset_devices+0x9> 5: R_X86_64_PC32 mcount+0xfffffffffffffffc The first function in .init.text is a static function. 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 t set_reset_devices The lowercase 't' means that set_reset_devices is local and is not exported. If we simply try to link the tmp.o with the set_reset_devices we end up with two symbols: one local and one global. .section __mcount_loc,"a",@progbits .quad set_reset_devices + 0x10 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 t set_reset_devices U set_reset_devices We still have an undefined reference to set_reset_devices, and if we try to compile the kernel, we will end up with an undefined reference to set_reset_devices, or even worst, it could be exported someplace else, and then we will have a reference to the wrong location. To handle this case, we make an intermediate step using objcopy. We convert set_reset_devices into a global exported symbol before linking it with tmp.o and set it back afterwards. 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 T set_reset_devices 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 T set_reset_devices 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 t set_reset_devices Now we have a section in main.o called __mcount_loc that we can place somewhere in the kernel using vmlinux.ld.S and access it to convert all these locations that call mcount into nops before starting SMP and thus, eliminating the need to do this with kstop_machine. Note, A well documented perl script (scripts/recordmcount.pl) is used to do all this in one location. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-14 19:45:07 +00:00
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
#define MCOUNT_REC() VMLINUX_SYMBOL(__start_mcount_loc) = .; \
*(__mcount_loc) \
VMLINUX_SYMBOL(__stop_mcount_loc) = .;
#else
#define MCOUNT_REC()
#endif
#ifdef CONFIG_TRACE_BRANCH_PROFILING
#define LIKELY_PROFILE() VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \
*(_ftrace_annotated_branch) \
VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .;
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 05:14:39 +00:00
#else
#define LIKELY_PROFILE()
#endif
#ifdef CONFIG_PROFILE_ALL_BRANCHES
#define BRANCH_PROFILE() VMLINUX_SYMBOL(__start_branch_profile) = .; \
*(_ftrace_branch) \
VMLINUX_SYMBOL(__stop_branch_profile) = .;
#else
#define BRANCH_PROFILE()
#endif
/* .data section */
#define DATA_DATA \
*(.data) \
*(.data.init.refok) \
Introduce new section reference annotations tags: __ref, __refdata, __refconst Today we have the following annotations for functions/data referencing __init/__exit functions / data: __init_refok => for init functions __initdata_refok => for init data __exit_refok => for exit functions There is really no difference between the __init and __exit versions and simplify it and to introduce a shorter annotation the following new annotations are introduced: __ref => for functions (code) that references __*init / __*exit __refdata => for variables __refconst => for const variables Whit this annotation is it more obvious what the annotation is for and there is no longer the arbitary division between __init and __exit code. The mechanishm is the same as before - a special section is created which is made part of the usual sections in the linker script. We will start to see annotations like this: -static struct pci_serial_quirk pci_serial_quirks[] = { +static const struct pci_serial_quirk pci_serial_quirks[] __refconst = { ----------------- -static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier = +static struct notifier_block cpuid_class_cpu_notifier __refdata = ---------------- -static int threshold_cpu_callback(struct notifier_block *nfb, +static int __ref threshold_cpu_callback(struct notifier_block *nfb, [The above is just random samples]. Note: No modifications were needed in modpost to support the new sections due to the newly introduced blacklisting. Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
2008-01-28 19:21:15 +00:00
*(.ref.data) \
DEV_KEEP(init.data) \
DEV_KEEP(exit.data) \
CPU_KEEP(init.data) \
CPU_KEEP(exit.data) \
MEM_KEEP(init.data) \
MEM_KEEP(exit.data) \
. = ALIGN(8); \
VMLINUX_SYMBOL(__start___markers) = .; \
*(__markers) \
tracing: Kernel Tracepoints Implementation of kernel tracepoints. Inspired from the Linux Kernel Markers. Allows complete typing verification by declaring both tracing statement inline functions and probe registration/unregistration static inline functions within the same macro "DEFINE_TRACE". No format string is required. See the tracepoint Documentation and Samples patches for usage examples. Taken from the documentation patch : "A tracepoint placed in code provides a hook to call a function (probe) that you can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or "off" (no probe is attached). When a tracepoint is "off" it has no effect, except for adding a tiny time penalty (checking a condition for a branch) and space penalty (adding a few bytes for the function call at the end of the instrumented function and adds a data structure in a separate section). When a tracepoint is "on", the function you provide is called each time the tracepoint is executed, in the execution context of the caller. When the function provided ends its execution, it returns to the caller (continuing from the tracepoint site). You can put tracepoints at important locations in the code. They are lightweight hooks that can pass an arbitrary number of parameters, which prototypes are described in a tracepoint declaration placed in a header file." Addition and removal of tracepoints is synchronized by RCU using the scheduler (and preempt_disable) as guarantees to find a quiescent state (this is really RCU "classic"). The update side uses rcu_barrier_sched() with call_rcu_sched() and the read/execute side uses "preempt_disable()/preempt_enable()". We make sure the previous array containing probes, which has been scheduled for deletion by the rcu callback, is indeed freed before we proceed to the next update. It therefore limits the rate of modification of a single tracepoint to one update per RCU period. The objective here is to permit fast batch add/removal of probes on _different_ tracepoints. Changelog : - Use #name ":" #proto as string to identify the tracepoint in the tracepoint table. This will make sure not type mismatch happens due to connexion of a probe with the wrong type to a tracepoint declared with the same name in a different header. - Add tracepoint_entry_free_old. - Change __TO_TRACE to get rid of the 'i' iterator. Masami Hiramatsu <mhiramat@redhat.com> : Tested on x86-64. Performance impact of a tracepoint : same as markers, except that it adds about 70 bytes of instructions in an unlikely branch of each instrumented function (the for loop, the stack setup and the function call). It currently adds a memory read, a test and a conditional branch at the instrumentation site (in the hot path). Immediate values will eventually change this into a load immediate, test and branch, which removes the memory read which will make the i-cache impact smaller (changing the memory read for a load immediate removes 3-4 bytes per site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it also saves the d-cache hit). About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. Quoting Hideo Aoki about Markers : I evaluated overhead of kernel marker using linux-2.6-sched-fixes git tree, which includes several markers for LTTng, using an ia64 server. While the immediate trace mark feature isn't implemented on ia64, there is no major performance regression. So, I think that we don't have any issues to propose merging marker point patches into Linus's tree from the viewpoint of performance impact. I prepared two kernels to evaluate. The first one was compiled without CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS. I downloaded the original hackbench from the following URL: http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c I ran hackbench 5 times in each condition and calculated the average and difference between the kernels. The parameter of hackbench: every 50 from 50 to 800 The number of CPUs of the server: 2, 4, and 8 Below is the results. As you can see, major performance regression wasn't found in any case. Even if number of processes increases, differences between marker-enabled kernel and marker- disabled kernel doesn't increase. Moreover, if number of CPUs increases, the differences doesn't increase either. Curiously, marker-enabled kernel is better than marker-disabled kernel in more than half cases, although I guess it comes from the difference of memory access pattern. * 2 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 4.811 | 4.872 | +0.061 | +1.27 | 100 | 9.854 | 10.309 | +0.454 | +4.61 | 150 | 15.602 | 15.040 | -0.562 | -3.6 | 200 | 20.489 | 20.380 | -0.109 | -0.53 | 250 | 25.798 | 25.652 | -0.146 | -0.56 | 300 | 31.260 | 30.797 | -0.463 | -1.48 | 350 | 36.121 | 35.770 | -0.351 | -0.97 | 400 | 42.288 | 42.102 | -0.186 | -0.44 | 450 | 47.778 | 47.253 | -0.526 | -1.1 | 500 | 51.953 | 52.278 | +0.325 | +0.63 | 550 | 58.401 | 57.700 | -0.701 | -1.2 | 600 | 63.334 | 63.222 | -0.112 | -0.18 | 650 | 68.816 | 68.511 | -0.306 | -0.44 | 700 | 74.667 | 74.088 | -0.579 | -0.78 | 750 | 78.612 | 79.582 | +0.970 | +1.23 | 800 | 85.431 | 85.263 | -0.168 | -0.2 | -------------------------------------------------------------- * 4 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.586 | 2.584 | -0.003 | -0.1 | 100 | 5.254 | 5.283 | +0.030 | +0.56 | 150 | 8.012 | 8.074 | +0.061 | +0.76 | 200 | 11.172 | 11.000 | -0.172 | -1.54 | 250 | 13.917 | 14.036 | +0.119 | +0.86 | 300 | 16.905 | 16.543 | -0.362 | -2.14 | 350 | 19.901 | 20.036 | +0.135 | +0.68 | 400 | 22.908 | 23.094 | +0.186 | +0.81 | 450 | 26.273 | 26.101 | -0.172 | -0.66 | 500 | 29.554 | 29.092 | -0.461 | -1.56 | 550 | 32.377 | 32.274 | -0.103 | -0.32 | 600 | 35.855 | 35.322 | -0.533 | -1.49 | 650 | 39.192 | 38.388 | -0.804 | -2.05 | 700 | 41.744 | 41.719 | -0.025 | -0.06 | 750 | 45.016 | 44.496 | -0.520 | -1.16 | 800 | 48.212 | 47.603 | -0.609 | -1.26 | -------------------------------------------------------------- * 8 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.094 | 2.072 | -0.022 | -1.07 | 100 | 4.162 | 4.273 | +0.111 | +2.66 | 150 | 6.485 | 6.540 | +0.055 | +0.84 | 200 | 8.556 | 8.478 | -0.078 | -0.91 | 250 | 10.458 | 10.258 | -0.200 | -1.91 | 300 | 12.425 | 12.750 | +0.325 | +2.62 | 350 | 14.807 | 14.839 | +0.032 | +0.22 | 400 | 16.801 | 16.959 | +0.158 | +0.94 | 450 | 19.478 | 19.009 | -0.470 | -2.41 | 500 | 21.296 | 21.504 | +0.208 | +0.98 | 550 | 23.842 | 23.979 | +0.137 | +0.57 | 600 | 26.309 | 26.111 | -0.198 | -0.75 | 650 | 28.705 | 28.446 | -0.259 | -0.9 | 700 | 31.233 | 31.394 | +0.161 | +0.52 | 750 | 34.064 | 33.720 | -0.344 | -1.01 | 800 | 36.320 | 36.114 | -0.206 | -0.57 | -------------------------------------------------------------- Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: 'Peter Zijlstra' <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-18 16:16:16 +00:00
VMLINUX_SYMBOL(__stop___markers) = .; \
. = ALIGN(32); \
tracing: Kernel Tracepoints Implementation of kernel tracepoints. Inspired from the Linux Kernel Markers. Allows complete typing verification by declaring both tracing statement inline functions and probe registration/unregistration static inline functions within the same macro "DEFINE_TRACE". No format string is required. See the tracepoint Documentation and Samples patches for usage examples. Taken from the documentation patch : "A tracepoint placed in code provides a hook to call a function (probe) that you can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or "off" (no probe is attached). When a tracepoint is "off" it has no effect, except for adding a tiny time penalty (checking a condition for a branch) and space penalty (adding a few bytes for the function call at the end of the instrumented function and adds a data structure in a separate section). When a tracepoint is "on", the function you provide is called each time the tracepoint is executed, in the execution context of the caller. When the function provided ends its execution, it returns to the caller (continuing from the tracepoint site). You can put tracepoints at important locations in the code. They are lightweight hooks that can pass an arbitrary number of parameters, which prototypes are described in a tracepoint declaration placed in a header file." Addition and removal of tracepoints is synchronized by RCU using the scheduler (and preempt_disable) as guarantees to find a quiescent state (this is really RCU "classic"). The update side uses rcu_barrier_sched() with call_rcu_sched() and the read/execute side uses "preempt_disable()/preempt_enable()". We make sure the previous array containing probes, which has been scheduled for deletion by the rcu callback, is indeed freed before we proceed to the next update. It therefore limits the rate of modification of a single tracepoint to one update per RCU period. The objective here is to permit fast batch add/removal of probes on _different_ tracepoints. Changelog : - Use #name ":" #proto as string to identify the tracepoint in the tracepoint table. This will make sure not type mismatch happens due to connexion of a probe with the wrong type to a tracepoint declared with the same name in a different header. - Add tracepoint_entry_free_old. - Change __TO_TRACE to get rid of the 'i' iterator. Masami Hiramatsu <mhiramat@redhat.com> : Tested on x86-64. Performance impact of a tracepoint : same as markers, except that it adds about 70 bytes of instructions in an unlikely branch of each instrumented function (the for loop, the stack setup and the function call). It currently adds a memory read, a test and a conditional branch at the instrumentation site (in the hot path). Immediate values will eventually change this into a load immediate, test and branch, which removes the memory read which will make the i-cache impact smaller (changing the memory read for a load immediate removes 3-4 bytes per site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it also saves the d-cache hit). About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. Quoting Hideo Aoki about Markers : I evaluated overhead of kernel marker using linux-2.6-sched-fixes git tree, which includes several markers for LTTng, using an ia64 server. While the immediate trace mark feature isn't implemented on ia64, there is no major performance regression. So, I think that we don't have any issues to propose merging marker point patches into Linus's tree from the viewpoint of performance impact. I prepared two kernels to evaluate. The first one was compiled without CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS. I downloaded the original hackbench from the following URL: http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c I ran hackbench 5 times in each condition and calculated the average and difference between the kernels. The parameter of hackbench: every 50 from 50 to 800 The number of CPUs of the server: 2, 4, and 8 Below is the results. As you can see, major performance regression wasn't found in any case. Even if number of processes increases, differences between marker-enabled kernel and marker- disabled kernel doesn't increase. Moreover, if number of CPUs increases, the differences doesn't increase either. Curiously, marker-enabled kernel is better than marker-disabled kernel in more than half cases, although I guess it comes from the difference of memory access pattern. * 2 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 4.811 | 4.872 | +0.061 | +1.27 | 100 | 9.854 | 10.309 | +0.454 | +4.61 | 150 | 15.602 | 15.040 | -0.562 | -3.6 | 200 | 20.489 | 20.380 | -0.109 | -0.53 | 250 | 25.798 | 25.652 | -0.146 | -0.56 | 300 | 31.260 | 30.797 | -0.463 | -1.48 | 350 | 36.121 | 35.770 | -0.351 | -0.97 | 400 | 42.288 | 42.102 | -0.186 | -0.44 | 450 | 47.778 | 47.253 | -0.526 | -1.1 | 500 | 51.953 | 52.278 | +0.325 | +0.63 | 550 | 58.401 | 57.700 | -0.701 | -1.2 | 600 | 63.334 | 63.222 | -0.112 | -0.18 | 650 | 68.816 | 68.511 | -0.306 | -0.44 | 700 | 74.667 | 74.088 | -0.579 | -0.78 | 750 | 78.612 | 79.582 | +0.970 | +1.23 | 800 | 85.431 | 85.263 | -0.168 | -0.2 | -------------------------------------------------------------- * 4 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.586 | 2.584 | -0.003 | -0.1 | 100 | 5.254 | 5.283 | +0.030 | +0.56 | 150 | 8.012 | 8.074 | +0.061 | +0.76 | 200 | 11.172 | 11.000 | -0.172 | -1.54 | 250 | 13.917 | 14.036 | +0.119 | +0.86 | 300 | 16.905 | 16.543 | -0.362 | -2.14 | 350 | 19.901 | 20.036 | +0.135 | +0.68 | 400 | 22.908 | 23.094 | +0.186 | +0.81 | 450 | 26.273 | 26.101 | -0.172 | -0.66 | 500 | 29.554 | 29.092 | -0.461 | -1.56 | 550 | 32.377 | 32.274 | -0.103 | -0.32 | 600 | 35.855 | 35.322 | -0.533 | -1.49 | 650 | 39.192 | 38.388 | -0.804 | -2.05 | 700 | 41.744 | 41.719 | -0.025 | -0.06 | 750 | 45.016 | 44.496 | -0.520 | -1.16 | 800 | 48.212 | 47.603 | -0.609 | -1.26 | -------------------------------------------------------------- * 8 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.094 | 2.072 | -0.022 | -1.07 | 100 | 4.162 | 4.273 | +0.111 | +2.66 | 150 | 6.485 | 6.540 | +0.055 | +0.84 | 200 | 8.556 | 8.478 | -0.078 | -0.91 | 250 | 10.458 | 10.258 | -0.200 | -1.91 | 300 | 12.425 | 12.750 | +0.325 | +2.62 | 350 | 14.807 | 14.839 | +0.032 | +0.22 | 400 | 16.801 | 16.959 | +0.158 | +0.94 | 450 | 19.478 | 19.009 | -0.470 | -2.41 | 500 | 21.296 | 21.504 | +0.208 | +0.98 | 550 | 23.842 | 23.979 | +0.137 | +0.57 | 600 | 26.309 | 26.111 | -0.198 | -0.75 | 650 | 28.705 | 28.446 | -0.259 | -0.9 | 700 | 31.233 | 31.394 | +0.161 | +0.52 | 750 | 34.064 | 33.720 | -0.344 | -1.01 | 800 | 36.320 | 36.114 | -0.206 | -0.57 | -------------------------------------------------------------- Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: 'Peter Zijlstra' <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-18 16:16:16 +00:00
VMLINUX_SYMBOL(__start___tracepoints) = .; \
*(__tracepoints) \
tracing: profile likely and unlikely annotations Impact: new unlikely/likely profiler Andrew Morton recently suggested having an in-kernel way to profile likely and unlikely macros. This patch achieves that goal. When configured, every(*) likely and unlikely macro gets a counter attached to it. When the condition is hit, the hit and misses of that condition are recorded. These numbers can later be retrieved by: /debugfs/tracing/profile_likely - All likely markers /debugfs/tracing/profile_unlikely - All unlikely markers. # cat /debug/tracing/profile_unlikely | head correct incorrect % Function File Line ------- --------- - -------- ---- ---- 2167 0 0 do_arch_prctl process_64.c 832 0 0 0 do_arch_prctl process_64.c 804 2670 0 0 IS_ERR err.h 34 71230 5693 7 __switch_to process_64.c 673 76919 0 0 __switch_to process_64.c 639 43184 33743 43 __switch_to process_64.c 624 12740 64181 83 __switch_to process_64.c 594 12740 64174 83 __switch_to process_64.c 590 # cat /debug/tracing/profile_unlikely | \ awk '{ if ($3 > 25) print $0; }' |head -20 44963 35259 43 __switch_to process_64.c 624 12762 67454 84 __switch_to process_64.c 594 12762 67447 84 __switch_to process_64.c 590 1478 595 28 syscall_get_error syscall.h 51 0 2821 100 syscall_trace_leave ptrace.c 1567 0 1 100 native_smp_prepare_cpus smpboot.c 1237 86338 265881 75 calc_delta_fair sched_fair.c 408 210410 108540 34 calc_delta_mine sched.c 1267 0 54550 100 sched_info_queued sched_stats.h 222 51899 66435 56 pick_next_task_fair sched_fair.c 1422 6 10 62 yield_task_fair sched_fair.c 982 7325 2692 26 rt_policy sched.c 144 0 1270 100 pre_schedule_rt sched_rt.c 1261 1268 48073 97 pick_next_task_rt sched_rt.c 884 0 45181 100 sched_info_dequeued sched_stats.h 177 0 15 100 sched_move_task sched.c 8700 0 15 100 sched_move_task sched.c 8690 53167 33217 38 schedule sched.c 4457 0 80208 100 sched_info_switch sched_stats.h 270 30585 49631 61 context_switch sched.c 2619 # cat /debug/tracing/profile_likely | awk '{ if ($3 > 25) print $0; }' 39900 36577 47 pick_next_task sched.c 4397 20824 15233 42 switch_mm mmu_context_64.h 18 0 7 100 __cancel_work_timer workqueue.c 560 617 66484 99 clocksource_adjust timekeeping.c 456 0 346340 100 audit_syscall_exit auditsc.c 1570 38 347350 99 audit_get_context auditsc.c 732 0 345244 100 audit_syscall_entry auditsc.c 1541 38 1017 96 audit_free auditsc.c 1446 0 1090 100 audit_alloc auditsc.c 862 2618 1090 29 audit_alloc auditsc.c 858 0 6 100 move_masked_irq migration.c 9 1 198 99 probe_sched_wakeup trace_sched_switch.c 58 2 2 50 probe_wakeup trace_sched_wakeup.c 227 0 2 100 probe_wakeup_sched_switch trace_sched_wakeup.c 144 4514 2090 31 __grab_cache_page filemap.c 2149 12882 228786 94 mapping_unevictable pagemap.h 50 4 11 73 __flush_cpu_slab slub.c 1466 627757 330451 34 slab_free slub.c 1731 2959 61245 95 dentry_lru_del_init dcache.c 153 946 1217 56 load_elf_binary binfmt_elf.c 904 102 82 44 disk_put_part genhd.h 206 1 1 50 dst_gc_task dst.c 82 0 19 100 tcp_mss_split_point tcp_output.c 1126 As you can see by the above, there's a bit of work to do in rethinking the use of some unlikelys and likelys. Note: the unlikely case had 71 hits that were more than 25%. Note: After submitting my first version of this patch, Andrew Morton showed me a version written by Daniel Walker, where I picked up the following ideas from: 1) Using __builtin_constant_p to avoid profiling fixed values. 2) Using __FILE__ instead of instruction pointers. 3) Using the preprocessor to stop all profiling of likely annotations from vsyscall_64.c. Thanks to Andrew Morton, Arjan van de Ven, Theodore Tso and Ingo Molnar for their feed back on this patch. (*) Not ever unlikely is recorded, those that are used by vsyscalls (a few of them) had to have profiling disabled. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Theodore Tso <tytso@mit.edu> Cc: Arjan van de Ven <arjan@infradead.org> Cc: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-12 05:14:39 +00:00
VMLINUX_SYMBOL(__stop___tracepoints) = .; \
LIKELY_PROFILE() \
BRANCH_PROFILE()
#define RO_DATA(align) \
. = ALIGN((align)); \
.rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \
[PATCH] i386: Distinguish absolute symbols Ld knows about 2 kinds of symbols, absolute and section relative. Section relative symbols symbols change value when a section is moved and absolute symbols do not. Currently in the linker script we have several labels marking the beginning and ending of sections that are outside of sections, making them absolute symbols. Having a mixture of absolute and section relative symbols refereing to the same data is currently harmless but it is confusing. This must be done carefully as newer revs of ld do not place symbols that appear in sections without data and instead ld makes those symbols global :( My ultimate goal is to build a relocatable kernel. The safest and least intrusive technique is to generate relocation entries so the kernel can be relocated at load time. The only penalty would be an increase in the size of the kernel binary. The problem is that if absolute and relocatable symbols are not properly specified absolute symbols will be relocated or section relative symbols won't be, which is fatal. The practical motivation is that when generating kernels that will run from a reserved area for analyzing what caused a kernel panic, it is simpler if you don't need to hard code the physical memory location they will run at, especially for the distributions. [AK: and merged:] o Also put a message so that in future people can be aware of it and avoid introducing absolute symbols. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-12-07 01:14:03 +00:00
VMLINUX_SYMBOL(__start_rodata) = .; \
*(.rodata) *(.rodata.*) \
*(__vermagic) /* Kernel version magic */ \
*(__markers_strings) /* Markers: strings */ \
tracing: Kernel Tracepoints Implementation of kernel tracepoints. Inspired from the Linux Kernel Markers. Allows complete typing verification by declaring both tracing statement inline functions and probe registration/unregistration static inline functions within the same macro "DEFINE_TRACE". No format string is required. See the tracepoint Documentation and Samples patches for usage examples. Taken from the documentation patch : "A tracepoint placed in code provides a hook to call a function (probe) that you can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or "off" (no probe is attached). When a tracepoint is "off" it has no effect, except for adding a tiny time penalty (checking a condition for a branch) and space penalty (adding a few bytes for the function call at the end of the instrumented function and adds a data structure in a separate section). When a tracepoint is "on", the function you provide is called each time the tracepoint is executed, in the execution context of the caller. When the function provided ends its execution, it returns to the caller (continuing from the tracepoint site). You can put tracepoints at important locations in the code. They are lightweight hooks that can pass an arbitrary number of parameters, which prototypes are described in a tracepoint declaration placed in a header file." Addition and removal of tracepoints is synchronized by RCU using the scheduler (and preempt_disable) as guarantees to find a quiescent state (this is really RCU "classic"). The update side uses rcu_barrier_sched() with call_rcu_sched() and the read/execute side uses "preempt_disable()/preempt_enable()". We make sure the previous array containing probes, which has been scheduled for deletion by the rcu callback, is indeed freed before we proceed to the next update. It therefore limits the rate of modification of a single tracepoint to one update per RCU period. The objective here is to permit fast batch add/removal of probes on _different_ tracepoints. Changelog : - Use #name ":" #proto as string to identify the tracepoint in the tracepoint table. This will make sure not type mismatch happens due to connexion of a probe with the wrong type to a tracepoint declared with the same name in a different header. - Add tracepoint_entry_free_old. - Change __TO_TRACE to get rid of the 'i' iterator. Masami Hiramatsu <mhiramat@redhat.com> : Tested on x86-64. Performance impact of a tracepoint : same as markers, except that it adds about 70 bytes of instructions in an unlikely branch of each instrumented function (the for loop, the stack setup and the function call). It currently adds a memory read, a test and a conditional branch at the instrumentation site (in the hot path). Immediate values will eventually change this into a load immediate, test and branch, which removes the memory read which will make the i-cache impact smaller (changing the memory read for a load immediate removes 3-4 bytes per site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it also saves the d-cache hit). About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. Quoting Hideo Aoki about Markers : I evaluated overhead of kernel marker using linux-2.6-sched-fixes git tree, which includes several markers for LTTng, using an ia64 server. While the immediate trace mark feature isn't implemented on ia64, there is no major performance regression. So, I think that we don't have any issues to propose merging marker point patches into Linus's tree from the viewpoint of performance impact. I prepared two kernels to evaluate. The first one was compiled without CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS. I downloaded the original hackbench from the following URL: http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c I ran hackbench 5 times in each condition and calculated the average and difference between the kernels. The parameter of hackbench: every 50 from 50 to 800 The number of CPUs of the server: 2, 4, and 8 Below is the results. As you can see, major performance regression wasn't found in any case. Even if number of processes increases, differences between marker-enabled kernel and marker- disabled kernel doesn't increase. Moreover, if number of CPUs increases, the differences doesn't increase either. Curiously, marker-enabled kernel is better than marker-disabled kernel in more than half cases, although I guess it comes from the difference of memory access pattern. * 2 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 4.811 | 4.872 | +0.061 | +1.27 | 100 | 9.854 | 10.309 | +0.454 | +4.61 | 150 | 15.602 | 15.040 | -0.562 | -3.6 | 200 | 20.489 | 20.380 | -0.109 | -0.53 | 250 | 25.798 | 25.652 | -0.146 | -0.56 | 300 | 31.260 | 30.797 | -0.463 | -1.48 | 350 | 36.121 | 35.770 | -0.351 | -0.97 | 400 | 42.288 | 42.102 | -0.186 | -0.44 | 450 | 47.778 | 47.253 | -0.526 | -1.1 | 500 | 51.953 | 52.278 | +0.325 | +0.63 | 550 | 58.401 | 57.700 | -0.701 | -1.2 | 600 | 63.334 | 63.222 | -0.112 | -0.18 | 650 | 68.816 | 68.511 | -0.306 | -0.44 | 700 | 74.667 | 74.088 | -0.579 | -0.78 | 750 | 78.612 | 79.582 | +0.970 | +1.23 | 800 | 85.431 | 85.263 | -0.168 | -0.2 | -------------------------------------------------------------- * 4 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.586 | 2.584 | -0.003 | -0.1 | 100 | 5.254 | 5.283 | +0.030 | +0.56 | 150 | 8.012 | 8.074 | +0.061 | +0.76 | 200 | 11.172 | 11.000 | -0.172 | -1.54 | 250 | 13.917 | 14.036 | +0.119 | +0.86 | 300 | 16.905 | 16.543 | -0.362 | -2.14 | 350 | 19.901 | 20.036 | +0.135 | +0.68 | 400 | 22.908 | 23.094 | +0.186 | +0.81 | 450 | 26.273 | 26.101 | -0.172 | -0.66 | 500 | 29.554 | 29.092 | -0.461 | -1.56 | 550 | 32.377 | 32.274 | -0.103 | -0.32 | 600 | 35.855 | 35.322 | -0.533 | -1.49 | 650 | 39.192 | 38.388 | -0.804 | -2.05 | 700 | 41.744 | 41.719 | -0.025 | -0.06 | 750 | 45.016 | 44.496 | -0.520 | -1.16 | 800 | 48.212 | 47.603 | -0.609 | -1.26 | -------------------------------------------------------------- * 8 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.094 | 2.072 | -0.022 | -1.07 | 100 | 4.162 | 4.273 | +0.111 | +2.66 | 150 | 6.485 | 6.540 | +0.055 | +0.84 | 200 | 8.556 | 8.478 | -0.078 | -0.91 | 250 | 10.458 | 10.258 | -0.200 | -1.91 | 300 | 12.425 | 12.750 | +0.325 | +2.62 | 350 | 14.807 | 14.839 | +0.032 | +0.22 | 400 | 16.801 | 16.959 | +0.158 | +0.94 | 450 | 19.478 | 19.009 | -0.470 | -2.41 | 500 | 21.296 | 21.504 | +0.208 | +0.98 | 550 | 23.842 | 23.979 | +0.137 | +0.57 | 600 | 26.309 | 26.111 | -0.198 | -0.75 | 650 | 28.705 | 28.446 | -0.259 | -0.9 | 700 | 31.233 | 31.394 | +0.161 | +0.52 | 750 | 34.064 | 33.720 | -0.344 | -1.01 | 800 | 36.320 | 36.114 | -0.206 | -0.57 | -------------------------------------------------------------- Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: 'Peter Zijlstra' <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-18 16:16:16 +00:00
*(__tracepoints_strings)/* Tracepoints: strings */ \
} \
\
.rodata1 : AT(ADDR(.rodata1) - LOAD_OFFSET) { \
*(.rodata1) \
} \
\
BUG_TABLE \
\
/* PCI quirks */ \
.pci_fixup : AT(ADDR(.pci_fixup) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start_pci_fixups_early) = .; \
*(.pci_fixup_early) \
VMLINUX_SYMBOL(__end_pci_fixups_early) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_header) = .; \
*(.pci_fixup_header) \
VMLINUX_SYMBOL(__end_pci_fixups_header) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_final) = .; \
*(.pci_fixup_final) \
VMLINUX_SYMBOL(__end_pci_fixups_final) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_enable) = .; \
*(.pci_fixup_enable) \
VMLINUX_SYMBOL(__end_pci_fixups_enable) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_resume) = .; \
*(.pci_fixup_resume) \
VMLINUX_SYMBOL(__end_pci_fixups_resume) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_resume_early) = .; \
*(.pci_fixup_resume_early) \
VMLINUX_SYMBOL(__end_pci_fixups_resume_early) = .; \
VMLINUX_SYMBOL(__start_pci_fixups_suspend) = .; \
*(.pci_fixup_suspend) \
VMLINUX_SYMBOL(__end_pci_fixups_suspend) = .; \
} \
\
/* Built-in firmware blobs */ \
.builtin_fw : AT(ADDR(.builtin_fw) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start_builtin_fw) = .; \
*(.builtin_fw) \
VMLINUX_SYMBOL(__end_builtin_fw) = .; \
} \
\
/* RapidIO route ops */ \
.rio_route : AT(ADDR(.rio_route) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start_rio_route_ops) = .; \
*(.rio_route_ops) \
VMLINUX_SYMBOL(__end_rio_route_ops) = .; \
} \
\
TRACEDATA \
\
/* Kernel symbol table: Normal symbols */ \
__ksymtab : AT(ADDR(__ksymtab) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab) = .; \
*(__ksymtab) \
VMLINUX_SYMBOL(__stop___ksymtab) = .; \
} \
\
/* Kernel symbol table: GPL-only symbols */ \
__ksymtab_gpl : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_gpl) = .; \
*(__ksymtab_gpl) \
VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .; \
} \
\
/* Kernel symbol table: Normal unused symbols */ \
__ksymtab_unused : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_unused) = .; \
*(__ksymtab_unused) \
VMLINUX_SYMBOL(__stop___ksymtab_unused) = .; \
} \
\
/* Kernel symbol table: GPL-only unused symbols */ \
__ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .; \
*(__ksymtab_unused_gpl) \
VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .; \
} \
\
/* Kernel symbol table: GPL-future-only symbols */ \
__ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .; \
*(__ksymtab_gpl_future) \
VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .; \
} \
\
/* Kernel symbol table: Normal symbols */ \
__kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab) = .; \
*(__kcrctab) \
VMLINUX_SYMBOL(__stop___kcrctab) = .; \
} \
\
/* Kernel symbol table: GPL-only symbols */ \
__kcrctab_gpl : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_gpl) = .; \
*(__kcrctab_gpl) \
VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .; \
} \
\
/* Kernel symbol table: Normal unused symbols */ \
__kcrctab_unused : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_unused) = .; \
*(__kcrctab_unused) \
VMLINUX_SYMBOL(__stop___kcrctab_unused) = .; \
} \
\
/* Kernel symbol table: GPL-only unused symbols */ \
__kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .; \
*(__kcrctab_unused_gpl) \
VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .; \
} \
\
/* Kernel symbol table: GPL-future-only symbols */ \
__kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .; \
*(__kcrctab_gpl_future) \
VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .; \
} \
\
/* Kernel symbol table: strings */ \
__ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) { \
*(__ksymtab_strings) \
} \
\
/* __*init sections */ \
__init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) { \
Introduce new section reference annotations tags: __ref, __refdata, __refconst Today we have the following annotations for functions/data referencing __init/__exit functions / data: __init_refok => for init functions __initdata_refok => for init data __exit_refok => for exit functions There is really no difference between the __init and __exit versions and simplify it and to introduce a shorter annotation the following new annotations are introduced: __ref => for functions (code) that references __*init / __*exit __refdata => for variables __refconst => for const variables Whit this annotation is it more obvious what the annotation is for and there is no longer the arbitary division between __init and __exit code. The mechanishm is the same as before - a special section is created which is made part of the usual sections in the linker script. We will start to see annotations like this: -static struct pci_serial_quirk pci_serial_quirks[] = { +static const struct pci_serial_quirk pci_serial_quirks[] __refconst = { ----------------- -static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier = +static struct notifier_block cpuid_class_cpu_notifier __refdata = ---------------- -static int threshold_cpu_callback(struct notifier_block *nfb, +static int __ref threshold_cpu_callback(struct notifier_block *nfb, [The above is just random samples]. Note: No modifications were needed in modpost to support the new sections due to the newly introduced blacklisting. Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
2008-01-28 19:21:15 +00:00
*(.ref.rodata) \
ftrace: create __mcount_loc section This patch creates a section in the kernel called "__mcount_loc". This will hold a list of pointers to the mcount relocation for each call site of mcount. For example: objdump -dr init/main.o [...] Disassembly of section .text: 0000000000000000 <do_one_initcall>: 0: 55 push %rbp [...] 000000000000017b <init_post>: 17b: 55 push %rbp 17c: 48 89 e5 mov %rsp,%rbp 17f: 53 push %rbx 180: 48 83 ec 08 sub $0x8,%rsp 184: e8 00 00 00 00 callq 189 <init_post+0xe> 185: R_X86_64_PC32 mcount+0xfffffffffffffffc [...] We will add a section to point to each function call. .section __mcount_loc,"a",@progbits [...] .quad .text + 0x185 [...] The offset to of the mcount call site in init_post is an offset from the start of the section, and not the start of the function init_post. The mcount relocation is at the call site 0x185 from the start of the .text section. .text + 0x185 == init_post + 0xa We need a way to add this __mcount_loc section in a way that we do not lose the relocations after final link. The .text section here will be attached to all other .text sections after final link and the offsets will be meaningless. We need to keep track of where these .text sections are. To do this, we use the start of the first function in the section. do_one_initcall. We can make a tmp.s file with this function as a reference to the start of the .text section. .section __mcount_loc,"a",@progbits [...] .quad do_one_initcall + 0x185 [...] Then we can compile the tmp.s into a tmp.o gcc -c tmp.s -o tmp.o And link it into back into main.o. ld -r main.o tmp.o -o tmp_main.o mv tmp_main.o main.o But we have a problem. What happens if the first function in a section is not exported, and is a static function. The linker will not let the tmp.o use it. This case exists in main.o as well. Disassembly of section .init.text: 0000000000000000 <set_reset_devices>: 0: 55 push %rbp 1: 48 89 e5 mov %rsp,%rbp 4: e8 00 00 00 00 callq 9 <set_reset_devices+0x9> 5: R_X86_64_PC32 mcount+0xfffffffffffffffc The first function in .init.text is a static function. 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 t set_reset_devices The lowercase 't' means that set_reset_devices is local and is not exported. If we simply try to link the tmp.o with the set_reset_devices we end up with two symbols: one local and one global. .section __mcount_loc,"a",@progbits .quad set_reset_devices + 0x10 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 t set_reset_devices U set_reset_devices We still have an undefined reference to set_reset_devices, and if we try to compile the kernel, we will end up with an undefined reference to set_reset_devices, or even worst, it could be exported someplace else, and then we will have a reference to the wrong location. To handle this case, we make an intermediate step using objcopy. We convert set_reset_devices into a global exported symbol before linking it with tmp.o and set it back afterwards. 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 T set_reset_devices 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 T set_reset_devices 00000000000000a8 t __setup_set_reset_devices 000000000000105f t __setup_str_set_reset_devices 0000000000000000 t set_reset_devices Now we have a section in main.o called __mcount_loc that we can place somewhere in the kernel using vmlinux.ld.S and access it to convert all these locations that call mcount into nops before starting SMP and thus, eliminating the need to do this with kstop_machine. Note, A well documented perl script (scripts/recordmcount.pl) is used to do all this in one location. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-08-14 19:45:07 +00:00
MCOUNT_REC() \
DEV_KEEP(init.rodata) \
DEV_KEEP(exit.rodata) \
CPU_KEEP(init.rodata) \
CPU_KEEP(exit.rodata) \
MEM_KEEP(init.rodata) \
MEM_KEEP(exit.rodata) \
} \
\
/* Built-in module parameters. */ \
__param : AT(ADDR(__param) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___param) = .; \
*(__param) \
VMLINUX_SYMBOL(__stop___param) = .; \
. = ALIGN((align)); \
[PATCH] i386: Distinguish absolute symbols Ld knows about 2 kinds of symbols, absolute and section relative. Section relative symbols symbols change value when a section is moved and absolute symbols do not. Currently in the linker script we have several labels marking the beginning and ending of sections that are outside of sections, making them absolute symbols. Having a mixture of absolute and section relative symbols refereing to the same data is currently harmless but it is confusing. This must be done carefully as newer revs of ld do not place symbols that appear in sections without data and instead ld makes those symbols global :( My ultimate goal is to build a relocatable kernel. The safest and least intrusive technique is to generate relocation entries so the kernel can be relocated at load time. The only penalty would be an increase in the size of the kernel binary. The problem is that if absolute and relocatable symbols are not properly specified absolute symbols will be relocated or section relative symbols won't be, which is fatal. The practical motivation is that when generating kernels that will run from a reserved area for analyzing what caused a kernel panic, it is simpler if you don't need to hard code the physical memory location they will run at, especially for the distributions. [AK: and merged:] o Also put a message so that in future people can be aware of it and avoid introducing absolute symbols. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com> Signed-off-by: Andi Kleen <ak@suse.de>
2006-12-07 01:14:03 +00:00
VMLINUX_SYMBOL(__end_rodata) = .; \
} \
. = ALIGN((align));
/* RODATA provided for backward compatibility.
* All archs are supposed to use RO_DATA() */
#define RODATA RO_DATA(4096)
#define SECURITY_INIT \
.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__security_initcall_start) = .; \
*(.security_initcall.init) \
VMLINUX_SYMBOL(__security_initcall_end) = .; \
}
/* .text section. Map to function alignment to avoid address changes
* during second ld run in second ld pass when generating System.map */
#define TEXT_TEXT \
ALIGN_FUNCTION(); \
*(.text.hot) \
*(.text) \
Introduce new section reference annotations tags: __ref, __refdata, __refconst Today we have the following annotations for functions/data referencing __init/__exit functions / data: __init_refok => for init functions __initdata_refok => for init data __exit_refok => for exit functions There is really no difference between the __init and __exit versions and simplify it and to introduce a shorter annotation the following new annotations are introduced: __ref => for functions (code) that references __*init / __*exit __refdata => for variables __refconst => for const variables Whit this annotation is it more obvious what the annotation is for and there is no longer the arbitary division between __init and __exit code. The mechanishm is the same as before - a special section is created which is made part of the usual sections in the linker script. We will start to see annotations like this: -static struct pci_serial_quirk pci_serial_quirks[] = { +static const struct pci_serial_quirk pci_serial_quirks[] __refconst = { ----------------- -static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier = +static struct notifier_block cpuid_class_cpu_notifier __refdata = ---------------- -static int threshold_cpu_callback(struct notifier_block *nfb, +static int __ref threshold_cpu_callback(struct notifier_block *nfb, [The above is just random samples]. Note: No modifications were needed in modpost to support the new sections due to the newly introduced blacklisting. Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
2008-01-28 19:21:15 +00:00
*(.ref.text) \
*(.text.init.refok) \
*(.exit.text.refok) \
DEV_KEEP(init.text) \
DEV_KEEP(exit.text) \
CPU_KEEP(init.text) \
CPU_KEEP(exit.text) \
MEM_KEEP(init.text) \
MEM_KEEP(exit.text) \
*(.text.unlikely)
/* sched.text is aling to function alignment to secure we have same
* address even at second ld pass when generating System.map */
#define SCHED_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__sched_text_start) = .; \
*(.sched.text) \
VMLINUX_SYMBOL(__sched_text_end) = .;
/* spinlock.text is aling to function alignment to secure we have same
* address even at second ld pass when generating System.map */
#define LOCK_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__lock_text_start) = .; \
*(.spinlock.text) \
VMLINUX_SYMBOL(__lock_text_end) = .;
#define KPROBES_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__kprobes_text_start) = .; \
*(.kprobes.text) \
VMLINUX_SYMBOL(__kprobes_text_end) = .;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
#define IRQENTRY_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__irqentry_text_start) = .; \
*(.irqentry.text) \
VMLINUX_SYMBOL(__irqentry_text_end) = .;
#else
#define IRQENTRY_TEXT
#endif
/* Section used for early init (in .S files) */
#define HEAD_TEXT *(.head.text)
/* init and exit section handling */
#define INIT_DATA \
*(.init.data) \
DEV_DISCARD(init.data) \
DEV_DISCARD(init.rodata) \
CPU_DISCARD(init.data) \
CPU_DISCARD(init.rodata) \
MEM_DISCARD(init.data) \
driver core: basic infrastructure for per-module dynamic debug messages Base infrastructure to enable per-module debug messages. I've introduced CONFIG_DYNAMIC_PRINTK_DEBUG, which when enabled centralizes control of debugging statements on a per-module basis in one /proc file, currently, <debugfs>/dynamic_printk/modules. When, CONFIG_DYNAMIC_PRINTK_DEBUG, is not set, debugging statements can still be enabled as before, often by defining 'DEBUG' for the proper compilation unit. Thus, this patch set has no affect when CONFIG_DYNAMIC_PRINTK_DEBUG is not set. The infrastructure currently ties into all pr_debug() and dev_dbg() calls. That is, if CONFIG_DYNAMIC_PRINTK_DEBUG is set, all pr_debug() and dev_dbg() calls can be dynamically enabled/disabled on a per-module basis. Future plans include extending this functionality to subsystems, that define their own debug levels and flags. Usage: Dynamic debugging is controlled by the debugfs file, <debugfs>/dynamic_printk/modules. This file contains a list of the modules that can be enabled. The format of the file is as follows: <module_name> <enabled=0/1> . . . <module_name> : Name of the module in which the debug call resides <enabled=0/1> : whether the messages are enabled or not For example: snd_hda_intel enabled=0 fixup enabled=1 driver enabled=0 Enable a module: $echo "set enabled=1 <module_name>" > dynamic_printk/modules Disable a module: $echo "set enabled=0 <module_name>" > dynamic_printk/modules Enable all modules: $echo "set enabled=1 all" > dynamic_printk/modules Disable all modules: $echo "set enabled=0 all" > dynamic_printk/modules Finally, passing "dynamic_printk" at the command line enables debugging for all modules. This mode can be turned off via the above disable command. [gkh: minor cleanups and tweaks to make the build work quietly] Signed-off-by: Jason Baron <jbaron@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-08-12 20:46:19 +00:00
MEM_DISCARD(init.rodata) \
/* implement dynamic printk debug */ \
VMLINUX_SYMBOL(__start___verbose_strings) = .; \
*(__verbose_strings) \
VMLINUX_SYMBOL(__stop___verbose_strings) = .; \
. = ALIGN(8); \
VMLINUX_SYMBOL(__start___verbose) = .; \
*(__verbose) \
VMLINUX_SYMBOL(__stop___verbose) = .;
#define INIT_TEXT \
*(.init.text) \
DEV_DISCARD(init.text) \
CPU_DISCARD(init.text) \
MEM_DISCARD(init.text)
#define EXIT_DATA \
*(.exit.data) \
DEV_DISCARD(exit.data) \
DEV_DISCARD(exit.rodata) \
CPU_DISCARD(exit.data) \
CPU_DISCARD(exit.rodata) \
MEM_DISCARD(exit.data) \
MEM_DISCARD(exit.rodata)
#define EXIT_TEXT \
*(.exit.text) \
DEV_DISCARD(exit.text) \
CPU_DISCARD(exit.text) \
MEM_DISCARD(exit.text)
/* DWARF debug sections.
Symbols in the DWARF debugging sections are relative to
the beginning of the section so we begin them at 0. */
#define DWARF_DEBUG \
/* DWARF 1 */ \
.debug 0 : { *(.debug) } \
.line 0 : { *(.line) } \
/* GNU DWARF 1 extensions */ \
.debug_srcinfo 0 : { *(.debug_srcinfo) } \
.debug_sfnames 0 : { *(.debug_sfnames) } \
/* DWARF 1.1 and DWARF 2 */ \
.debug_aranges 0 : { *(.debug_aranges) } \
.debug_pubnames 0 : { *(.debug_pubnames) } \
/* DWARF 2 */ \
.debug_info 0 : { *(.debug_info \
.gnu.linkonce.wi.*) } \
.debug_abbrev 0 : { *(.debug_abbrev) } \
.debug_line 0 : { *(.debug_line) } \
.debug_frame 0 : { *(.debug_frame) } \
.debug_str 0 : { *(.debug_str) } \
.debug_loc 0 : { *(.debug_loc) } \
.debug_macinfo 0 : { *(.debug_macinfo) } \
/* SGI/MIPS DWARF 2 extensions */ \
.debug_weaknames 0 : { *(.debug_weaknames) } \
.debug_funcnames 0 : { *(.debug_funcnames) } \
.debug_typenames 0 : { *(.debug_typenames) } \
.debug_varnames 0 : { *(.debug_varnames) } \
/* Stabs debugging sections. */
#define STABS_DEBUG \
.stab 0 : { *(.stab) } \
.stabstr 0 : { *(.stabstr) } \
.stab.excl 0 : { *(.stab.excl) } \
.stab.exclstr 0 : { *(.stab.exclstr) } \
.stab.index 0 : { *(.stab.index) } \
.stab.indexstr 0 : { *(.stab.indexstr) } \
.comment 0 : { *(.comment) }
#ifdef CONFIG_GENERIC_BUG
[PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h] Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andi Kleen <ak@muc.de> Cc: Hugh Dickens <hugh@veritas.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 10:36:19 +00:00
#define BUG_TABLE \
. = ALIGN(8); \
__bug_table : AT(ADDR(__bug_table) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start___bug_table) = .; \
[PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h] Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andi Kleen <ak@muc.de> Cc: Hugh Dickens <hugh@veritas.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 10:36:19 +00:00
*(__bug_table) \
VMLINUX_SYMBOL(__stop___bug_table) = .; \
[PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h] Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andi Kleen <ak@muc.de> Cc: Hugh Dickens <hugh@veritas.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 10:36:19 +00:00
}
#else
#define BUG_TABLE
#endif
[PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h] Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andi Kleen <ak@muc.de> Cc: Hugh Dickens <hugh@veritas.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 10:36:19 +00:00
#ifdef CONFIG_PM_TRACE
#define TRACEDATA \
. = ALIGN(4); \
.tracedata : AT(ADDR(.tracedata) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__tracedata_start) = .; \
*(.tracedata) \
VMLINUX_SYMBOL(__tracedata_end) = .; \
}
#else
#define TRACEDATA
#endif
#define NOTES \
.notes : AT(ADDR(.notes) - LOAD_OFFSET) { \
VMLINUX_SYMBOL(__start_notes) = .; \
*(.note.*) \
VMLINUX_SYMBOL(__stop_notes) = .; \
}
#define INITCALLS \
*(.initcallearly.init) \
VMLINUX_SYMBOL(__early_initcall_end) = .; \
*(.initcall0.init) \
*(.initcall0s.init) \
*(.initcall1.init) \
*(.initcall1s.init) \
*(.initcall2.init) \
*(.initcall2s.init) \
*(.initcall3.init) \
*(.initcall3s.init) \
*(.initcall4.init) \
*(.initcall4s.init) \
*(.initcall5.init) \
*(.initcall5s.init) \
*(.initcallrootfs.init) \
*(.initcall6.init) \
*(.initcall6s.init) \
*(.initcall7.init) \
*(.initcall7s.init)
#define PERCPU(align) \
. = ALIGN(align); \
VMLINUX_SYMBOL(__per_cpu_start) = .; \
.data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { \
*(.data.percpu.page_aligned) \
*(.data.percpu) \
*(.data.percpu.shared_aligned) \
} \
VMLINUX_SYMBOL(__per_cpu_end) = .;