forked from iovisor/bcc
-
Notifications
You must be signed in to change notification settings - Fork 2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merge pull request iovisor#4089 from davemarchevsky/davemarchevsky_fi… #4
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Hengqi Chen <[email protected]>
tools/llcstat: Add TID info support
libbpf-tools: Add tcplife
the bpf verifier would complain on program exit without initing R0 but the buggy implementation makes up one BPF_EXIT instruction only, which would be rejected by the verifier, and what's worse is that it does not log any err about the try-to-load failure, which makes all tools use this api would silently fall back to kprobe unexpectedly. this patch fixs it and also prints verbose message about the result of the try. Signed-off-by: Ze Gao <[email protected]>
Running syscount causes the following error: ... ; if (measure_latency) 103: (18) r1 = 0xffffc90000b6a002 105: (71) r1 = *(u8 *)(r1 +0) R0_w=inv(id=0,umax_value=16,var_off=(0x0; 0x1f)) R1_w=map_value(id=0,off=2,ks=4,vs=48,imm=0) R7=map_value(id=0,off=0,ks=4,vs=32,imm=0) R8=inv(id=0,smin_value=-2147483648,smax_value=2147483647) R10=fp0 fp-8=mmmmmmmm fp-16=mmmmmmmm ; if (measure_latency) 106: (15) if r1 == 0x0 goto pc+4 R0_w=inv(id=0,umax_value=16,var_off=(0x0; 0x1f)) R1_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R7=map_value(id=0,off=0,ks=4,vs=32,imm=0) R8=inv(id=0,smin_value=-2147483648,smax_value=2147483647) R10=fp0 fp-8=mmmmmmmm fp-16=mmmmmmmm ; __sync_fetch_and_add(&val->total_ns, bpf_ktime_get_ns() - *start_ts); 107: (85) call bpf_ktime_get_ns#5 ; __sync_fetch_and_add(&val->total_ns, bpf_ktime_get_ns() - *start_ts); 108: (79) r1 = *(u64 *)(r6 +0) R6 !read_ok processed 181 insns (limit 1000000) max_states_per_insn 1 total_states 19 peak_states 19 mark_read 8 -- END PROG LOAD LOG -- libbpf: failed to load program 'sys_exit' libbpf: failed to load object 'syscount_bpf' libbpf: failed to load BPF skeleton 'syscount_bpf': -13 failed to load BPF object: Permission denied Fix this by calculating the latency and store on a local variable. Signed-off-by: Hengqi Chen <[email protected]>
Running tcpconnect causes the following error: ... ; for (i = 0; i < filter_ports_len; i++) { 43: (7d) if r1 s>= r4 goto pc+96 R0=inv(id=0) R1_w=inv66 R2_w=map_value(id=0,off=280,ks=4,vs=280,imm=0) R3=map_value(id=0,off=0,ks=4,vs=280,imm=0) R4_w=inv(id=0,umin_value=67,umax_value=2147483647,var_off=(0x0; 0x7fffffff)) R6=ctx(id=0,off=0,imm=0) R7=inv(id=0) R8=inv(id=0) R9=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R10=fp0 fp-80=mmmmmm?? ; if (port == filter_ports[i]) 44: (61) r4 = *(u32 *)(r2 +0) R0=inv(id=0) R1_w=inv66 R2_w=map_value(id=0,off=280,ks=4,vs=280,imm=0) R3=map_value(id=0,off=0,ks=4,vs=280,imm=0) R4_w=inv(id=0,umin_value=67,umax_value=2147483647,var_off=(0x0; 0x7fffffff)) R6=ctx(id=0,off=0,imm=0) R7=inv(id=0) R8=inv(id=0) R9=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R10=fp0 fp-80=mmmmmm?? invalid access to map value, value_size=280 off=280 size=4 R2 min value is outside of the array range processed 783 insns (limit 1000000) max_states_per_insn 4 total_states 23 peak_states 23 mark_read 6 -- END PROG LOAD LOG -- libbpf: failed to load program 'tcp_v4_connect_ret' libbpf: failed to load object 'tcpconnect_bpf' libbpf: failed to load BPF skeleton 'tcpconnect_bpf': -13 failed to load BPF object: -13 Fix this by checking i against MAX_PORTS. Signed-off-by: Hengqi Chen <[email protected]>
tcpconnlat uses fentry in BPF programs which may failed on old kernels which don't have BPF trampline. Let's check fentry support first and fallback to kprobe if it is not available. Signed-off-by: Hengqi Chen <[email protected]>
security_inode_create does NOT exist if CONIFG_SECURITY is not set. The tool filelife attaches to security_inode_create unconditionally and result in attach error. Fix it by checking symbol existence. Signed-off-by: Hengqi Chen <[email protected]>
After kernel commit d5869fdc189f ("block: introduce block_rq_error tracepoint"), tracepoint block_rq_complete now shares the same argument struct as `struct trace_event_raw_block_rq_completion` with tracepoint block_rq_error. Because of that, now biopattern is broken because `struct trace_event_raw_block_rq_complete` is disappeared from kernel BTF. Fix it by checking type existence. Signed-off-by: Hengqi Chen <[email protected]>
Add pin support for xsk map. Signed-off-by: Y7n05h <[email protected]>
`bcc` does various conversions of "global address" to "module offset" and vice versa. Previous work (#1670) modified the "global address" -> "module offset" calculation in `ProcSyms::Module::contains` to account for differences between the file offset a section is loading bytes from and the requested start address (relative to the base address of the `.so`). Unfortunately that change didn't also modify "module offset" -> "global address" calculations, such as the one in bcc_resolve_global_addr. Update that calculation to account for the same. This calculation discrepancy was most apparent for us in production when trying to attach USDTs to a shared lib with differing requested start address and file offset. This patch also adds a test w/ comments describing our specific situation and demonstrating how the patch fixes the issue. Signed-off-by: Dave Marchevsky <[email protected]>
bcc/syms: Fix shared lib module offset <-> global addr conversion
fengjixuchui
pushed a commit
that referenced
this pull request
Nov 15, 2022
…for -v option Add additional information and change format of backtrace - add symbol base offset, dso name, dso base offset - symbol and dso info is included if it's available in target binary - changed format: INDEX ADDR [SYMBOL+OFFSET] (MODULE+OFFSET) Print backtrace of ip if it failed to get syms. Before: # offcputime -v psiginfo vscanf __snprintf_chk [unknown] [unknown] [unknown] [unknown] [unknown] sd_event_exit sd_event_dispatch sd_event_run [unknown] __libc_start_main [unknown] - systemd-journal (204) 1 xas_load xas_find filemap_map_pages __handle_mm_fault handle_mm_fault do_page_fault do_translation_fault do_mem_abort do_el0_ia_bp_hardening el0_ia xas_load -- failed to get syms - PmLogCtl (138757) 1 After: # offcputime -v #0 0xffffffc01018b7e8 __arm64_sys_clock_nanosleep+0x0 #1 0xffffffc01009a93c el0_svc_handler+0x34 #2 0xffffffc010084a08 el0_svc+0x8 #3 0xffffffc01018b7e8 __arm64_sys_clock_nanosleep+0x0 -- #4 0x0000007fa0bffd14 clock_nanosleep+0x94 (/usr/lib/libc-2.31.so+0x9ed14) #5 0x0000007fa0c0530c nanosleep+0x1c (/usr/lib/libc-2.31.so+0xa430c) #6 0x0000007fa0c051e4 sleep+0x34 (/usr/lib/libc-2.31.so+0xa41e4) #7 0x000000558a5a9608 flb_loop+0x28 (/usr/bin/fluent-bit+0x52608) #8 0x000000558a59f1c4 flb_main+0xa84 (/usr/bin/fluent-bit+0x481c4) #9 0x0000007fa0b85124 __libc_start_main+0xe4 (/usr/lib/libc-2.31.so+0x24124) #10 0x000000558a59d828 _start+0x34 (/usr/bin/fluent-bit+0x46828) - fluent-bit (1238) 1 #0 0xffffffc01027daa4 generic_copy_file_checks+0x334 #1 0xffffffc0102ba634 __handle_mm_fault+0x8dc #2 0xffffffc0102baa20 handle_mm_fault+0x168 #3 0xffffffc010ad23c0 do_page_fault+0x148 #4 0xffffffc010ad27c0 do_translation_fault+0xb0 #5 0xffffffc0100816b0 do_mem_abort+0x50 #6 0xffffffc0100843b0 el0_da+0x1c #7 0xffffffc01027daa4 generic_copy_file_checks+0x334 -- #8 0x0000007f8dc12648 [unknown] #9 0x0000007f8dc0aef8 [unknown] #10 0x0000007f8dc1c990 [unknown] #11 0x0000007f8dc08b0c [unknown] #12 0x0000007f8dc08e48 [unknown] #13 0x0000007f8dc081c8 [unknown] - PmLogCtl (2412) 1 Fixed: iovisor#3884 Signed-off-by: Eunseon Lee <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.