JIT fault #11127
Labels
Comments
|
Just for clarification, are the two files missing, or are they empty? |
|
Sorry, my first post here. |
|
I can reproduce this with the
1.php, for convenience. <?php
include('2.php');
for($a=1;$a<100;$a++){
echo _f('1');
echo _f('1');
echo _f('1');
}
touch('2.php');
?> |
|
@dstogov Can you help here? This is beyond my expertise. Disassembled JIT code
|
|
Thanks for the report. I reproduced and understood the problem. It's a tracing JIT bug. The crash is caused by incorrect "function guard" that bypass execution of the "old" inlined version of function _f(). On second request, the "old" version of function wasn't initialized correctly, EX(run_time_cache) got invalid value, and we crash... The real problem caused by incorrect function guard. The current JIT code: TRACE-3$/home/dmitry/php/php-master/CGI-DEBUG-64/1.php$4: ; (unknown)
....
.L1:
cmpq $0, EG(exception)
jne JIT$$exception_handler
movq 0x40(%r14), %rdx ; func = EX(run_time_cache)[1]
movq 8(%rdx), %rax
testq %rax, %rax ; if (func)
je .L15
.L2:
...
.L15:
movq $0x7e64620, %rdi
leaq 8(%rdx), %rsi
movabsq $zend_jit_find_func_helper, %rax
callq *%rax
cmpq $0x84d4fa0, %rax ; if (finc == OLD_INLINED_FUNC)
je .L2
jmp jit$$trace_exit_1Should be converted to a more accurate check: TRACE-3$/home/dmitry/php/php-master/CGI-DEBUG-64/1.php$4: ; (unknown)
....
.L1:
cmpq $0, EG(exception)
jne JIT$$exception_handler
movq 0x40(%r14), %rdx ; func = EX(run_time_cache)[1]
movq 8(%rdx), %rax
.L2:
cmpq $0x84d4fa0, %rax ; if (func == OLD_INLINED_FUNC)
jne .L15
...
.L15:
test %rax, %rax ; if (func)
jne jit$$trace_exit_1
movq $0x7e64620, %rdi
leaq 8(%rdx), %rsi
movabsq $zend_jit_find_func_helper, %rax
callq *%rax
: jmp .L2The old code assumed, that the function cached in EX(run_time_case) was already properly guarded before. The fix will take some time. |
|
I'm afraid this exceeds my knowledge on JITs 🙁 I'm hoping to learn more soon so I can help out with these. @arnaud-lb Maybe you're more qualified? |
|
Not sure I'm more qualified, but I can not find a more efficient way to implement this guard. The happy path does not seem to be affected a lot, as we just swap a testq/je with a cmpq/jne (albeit cmpq/jne probably generates larger code, and if the function does not have a 32bit address, we also add an additional movq). Maybe we could elide guards when the same guard has been executed in a dominator? I guess that IR does that / will do that? |
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
May 2, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
May 2, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
May 15, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
May 31, 2023
|
I seem to be experiencing a similar bug but I can't confirm if it is the same one, especially since the opcache.jit=1205 workaround also results in the 503 error. The server is temporarily unable to service your request due to maintenance downtime or capacity problems. Please try again later. cat /var/log/php8.2-fpm.log shows: [pool www] child 1926 exited on signal 11 (SIGSEGV) after 3277.669446 seconds from start in cat /var/log/php8.2-fpm.log Should i report this a different bug or wait for the next version of php? |
|
@sysadminpower2019 the fix for this issue will be in 8.1.20, which will be released on June 8. Maybe your issue is the same one, maybe it is different. You could check if it reproduces with the new version and if it does you can open a report. You can already test this with the release candidate. |
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Jun 13, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Jun 15, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Jul 4, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Jul 26, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Aug 1, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Aug 29, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Aug 31, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Sep 1, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Sep 4, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Sep 5, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Sep 5, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Sep 8, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Sep 14, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Oct 11, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Oct 18, 2023
dstogov
added a commit
to dstogov/php-src
that referenced
this issue
Oct 20, 2023
dstogov
added a commit
that referenced
this issue
Oct 23, 2023
* IR update * Use folding to allow constant folding and common subexpression elimination * Implement IR JIT for INIT_FCALL, INIT_FCALL_BY_NAME and INIT_NS_FCALL_BY_NAME * Implement IR JIT for SEND_VAL and SEND_VAL_EX * Implement IR JIT for SEND_REF * Implement IR JIT for SEND_VAR* instructions (incompltere - few tests failures) * Implement IR JIT for CHECK_FUNC_ARG * Implement IR JIT for CHECK_UNDEF_ARGS * Implement IR JIT for ROPE_INIT, ROPE_ADD and ROPE_END * Implement IR JIT for FREE, FE_FREE, ECHO, STRLEN and COUNT * Implement IR JIT for IN_ARRAY * Implement IR JIT support for separate VM stack overflow check * Implement IR JIT for INIT_DYNAMIC_CALL * Implemenr IR JIT for INIT_METHOD_CALL * Fix IR JIT for IN_ARRAY and COUNT * Implement IR JIT for VERIFY_RETURN_TYPE * Force C compiler to store preserved registers to allow JIT using them * Implement IR JIT for DO_FCALL, DO_UCALL, DO_ICALL and DO_FCALL_BY_NAME * Implement IR JIT for FETCH_CONSTANT * Fix (reverse) guard conditions * Implement IR JIT for RECV and RECV_INIT * Implement IR JIT for RETURN * Implement IR JIT for BIND_GLOBAL * Fix guard for: int++ => double * Fix exception handling * Allow deoptimization of zval type only (if some register is spilled by the IR engine) * Fix overflow handling * Implement IR JIT for FE_RESET_R and FE_FETCH_R * Eliminate extra temporary register * Better registers usage * Implement IR JIT for FETCH_DIM_* and ISSET_DIM * Implement IR JIT for ASSIGN_DIM and ASSIGN_DIM_OP * cleanup * Generae IR that produces a better x86[_64] code * Allow trace register allocation for live ranges terminated before entering a called function * Remove following END->BEGIN nodes during IR construction * Remove useless (duplicate) guard * Avoid useless exception check * Prevent duplicate store * Eliminate repatable re-assignment of stack zval types * Enable combination of some instructions with the following SEND_VAL for IR JIT * Avoid generation of useless RLOADs * Eliminatare refcouting in a sequence of FETCH_DIM_R * Fix assertion * Remove ZREG_ZVAL_ADDREF flag from an element of abstract stack * Implement IR JIT for FETCH_OBJ_* * Implement IR JIT for ASSIGN_OBJ * Implement IR JIT for ASSIGN_OBJ_OP * cleanup * Implement IR JIT for (PRE/POST)_(INC/DEC)_OBJ * ws * cleanup * Fix IR JIT for constructor call * Fix opcache.jit=1201 IR JIT. With opcache.jit=1201 we still have to generate code for follow and target basic blocks with single exiting VM instruction. We mat just omit the entry point. * Fix IR construction for the case when both IF targets are the same * Avoid PHP LEAVE code duplication in function IR JIT. * Reload operands from memeory when overflow (this improves hot code) * Implement IR JIT for SWITCH_LONG, SWITCH_STRING and MATCH * Initialize result to IS_UNDEF * Fix JIT integraion with observer (Zend/tests/gh10346.phpt failure) * Fix incorrect compilation of FE_FETCH with predicted empty array * Fix register allocation * Use sign extension inxted of zero * Fix trace register allocator * cleanp * Fix address sanitizer warning * Calculate JIT trace prologue sixe on startup (to avoid magic constants). * Add cgecks for merge arrays overflow (this should be refactored using lists) * Cache TLS access to perform corresponding read once per basic block * cleanup unused variable * Fix IR JIT support for CLANG build (CALL VM without global register variables) * Fix IR JIT for CALL VM with global register variables * Allow %rpb ysage in JIT for CALL VM (we save and restore it in prologue/epilogue anyway) * cleanup * Allocate enough fixed stack to keep preserved registers * We don't have to care about x29 and x30 * cleanup (JMPZ/NZ_EX work fine) * Revert "cleanup (JMPZ/NZ_EX work fine)" This reverts commit cf8dd74. * Don't allocate register for PHP variables that are loaded from memory and used once * Eliminate redundand deoptimization stores * cleanup * cleanup * cleanup * Optimization for constant comparison * Cleanup and elimination of dead deoptimization stores * Eliminate duplicate constant loading * Set proper initial SP offset info for GDB backtraces This doesn't take into account the following SP/FP modifications * Add spill stores * Remove low limit on number of deoptimization constants * Emit dead code only when it's really necessary for IR graph * cleanup * cleanup * Prefer loading long constants from memory (instead of loading immediate value) * Regiter disasm labels using macros (add missing helpers) * Make IR franework to care about GUARD JMP reordering * Avoid reloading * Improve register allocation for IR tracing JIT * Add comment * Fix deoptimization on result type guard of FETCH_DIM_R and FETCH_OBJ_R * If HYBRID VM can't provide some stack space for JIT code in "red zone" then JIT has to reserve stack space itself * Dump IR for stubs only if disassembling of stubs is requested * Revert "Dump IR for stubs only if disassembling of stubs is requested" This reverts commit d8b56be. * Dump IR for stubs only if disassembling of stubs is requested (another approach) * Improve overflow deoptimization for ADD(_,1) and SUB(_,1) Now we deoptimize to the next instruction, load constant result, and remove op1 from SNAPSHOT * Switch to IR Builder API * Switch to new IR builder macros * Fix jit_set_Z_TYPE_INFO() call. op3 is a simple constant (not a ir_ref). * Generate better code * Enable empty ENTRY block merging * Improve code generated for array separation/creation before an update (ASSIGN_DIM, ASSING_DIM_OP, etc) * Fix incorrect deleteion of PHI source (op1 is used for control link) * Load constant once * cleanup * Improve control-flow to avoid two IS_ARRAY checks for REFERENCEs * Update comments * cleanup * Clenup comments * Fix AAarch 64 build (disable stack adjustment auto-detection) * Add filename and line number to closure names * Reserve stack for parameter passing * Increase size of CPU stack reserved for JIT-ed code * Fix addess sanitizer warnings * Clenup: introduce OPTIMIZE_FOR_SIZE macro (disabled by default) * Port 08e7591 to IR JIT Fix (at lease part of the) #GH-10635: ARM64 function JIT causes impossible assertion * cleanup * Preload constant and use tests that may be compiled into better code * Convert helpers to stubs * Introduce a helper data structure (ir_refs) to collect references for the following use in (MERGE/PHI)_N * Use ir_refs * Improve code generated by zend_jit_zval_copy_deref() * Use "cold" attribute to influence IR block scheduler and achieve better code layout * Keep info collected by recursion analyzer * Use HTTPS URL to allow fetching without a SSH key * Update IR * Update IR * Add IR JIT support for Wondows (Win64 support is incomplete) * Update IR * Update IR * Fix support for Windows ZTS build * Fix stack alignment * Cleanup ir_ctx.control usage * Fixed support for irreducable (incomplete) and merged loops * Revert "Fixed support for irreducable (incomplete) and merged loops" This reverts commit 672b5b8. * Generate better code for RECV_ENTRies * Use simpler and more efficient checks * Switch to new ENTRY node concept * Limit register usage across the OSR ENTRY point * Upate MEM type only if we write to memory * Use LOOP_END without a reference edge * Use new ir_init() prototype * Delay LOAD for better LOAD fusion * Fix RECV/RECV_INIT compilation with opcache.jit=1235 * iPtoperly compile fake closures (they mau be called as regular functions) * Fix reabase * Fix rebase and add --with-capstone support for IR JIT * Replace zend_uchar -> uint8_t * IR JIT support for delayed destructor for zend_assign_to_typed_ref/prop * Handle zend_execute_internal in IR JIT * Fix readonly+clone IR JIT issues * Switch to ir_ctx.mflags * Ckeanup "inputs_count" access * Disable CSE for nodes bound to PHP local varibles The stack slots for temporaty variables may be reused and in case of spilling this may cause clobbering of the value. (ext/standard/tests/strings/htmlentities20.phpt on x86 with tracing JIT) * Fix deoptimization code when link traces See ext/zlib/tests/bug75273.phpt failure * Fix missing type store This fixes ext/openssl/tests/openssl_error_string_basic_openssl3.phpt * Fix tracing JIT for overflowing INC/DEC Fixes tests/lang/operators/preinc_basiclong_64bit.phpt * Remove ir_remove_unreachable_blocks() call. Now it's called by ir_build_cfg(), when necessary. * IR JIT: Fixed inaccurate range inference usage for UNDEF/NULL/FALSE * IR JIT: Fixed GH-11127 (JIT fault) * Avoid allocation of unused exit point * Don't record already stored PHP variables in SNAPSHOTs * Delay variable load * Disable CSE across ENTRY * Fixed disabling CSE * Fix deoptimization * Fixed deoptimization * Disable incorrect register allocation * Fix JIT for INDENTICAL+JMPZ_EX * Add comments * Fixed missed type stores * IR JIT: added support for CLDEMOTE * Fixed incorrect constant usage * Disable compilation of PHP functions with irreducible CGF * Fixed liveness check * Fixed code for constant conditional jump * Add type store to avoid use-after-free * Fixed liveness analyses * Gnerate SNAPSHOT for virtual method calls * More accurate search for staticaly inferred info about a trace SSA vaiable * Fix incorrect result use type_info * Fix JMPZ/NZ_EX support and missing type store * Fixed trace type inference and missing type store * Store type of unused CV to prevent possible following use after free * Fixed deoptimizaton info * Fixed stack layout * Implemented support for veneers on AArch64 * Dsable CSE to avoid over-optimization * Don't bind nodes for TMP PHP variables * Re-enable CSE for temporary variables as we don't bind them anymore * Switch to CPU stack spill slots * Add codegen info dump * Initialize CV variables through FP (this enables some folding optimizatios) * Use zero-extension that can be eliminated * Avoid generation of dead PHIs * Increase preallocated spill stack size * Enable IR based JIT by default * Fixed build with -disable-opcache-jit * Use explicit type conversion & force load values to registerts * Fix IR build * Checkout submodules in github actions * Fixed Windows build * Fixed Windows build * Fixed reattach to IR JIT SHM * Update IR * Checkout submodules in nightly CI * Fix MACOS ZTS in IR JIT * Update ir * Fixed incorrect register allocation * Fixed incorect code generation * Fixed tracing jit for BIND_INIT_STATIC_OR_JMP * Update README * Typos * Revert JIT disabling for run-tests.php workers * Fixed code review issues * Update IR * Update IR * Update IR * Allow exit_point duplication, when the deoptimization info differs because of spilling * Use bound spill slots for CV (once again) * Improve error handling * Removed IR submodule * Remove IR submodule from workflows * Embed IR IR commit: 8977307f4e96ee03847d7f2eb809b3080f9ed662 * Add .gitignore * Fixed according to feedback * Force C saving preserved registers only for HYBRID VM * Update IR IR commit: a2f8452b3d35a756cba38924f5c51a48a7207494 * cleanup * Replace ZEND_ASSERT(0) by ZEND_UNREACHABLE() * Update IR and remove unused IR files IR commit: 399a38771393c202a741336643118991290b4b1b * Fixed inconsistency between IR code-generation and register-allocation * Update IR IR commit: 86685504274b0c71d9985b3c926dccaca2cacf9b * Update ir_PHI*() according to IR construction API changes * Fixed 32-bit build * Update IR IR commit: d0686408e20cd8c8640e37ed52ab81403a2383cb * Support for ir_TAILCALL() prototype changes * Update IR IR commit: d72ae866e09d17e879378767aceb91d51894818c * Fixed incorrect extension (ZEXT->SEXT) * Fix SSA dominance * Update IR IR commit: d60d92516dc5f89b93cdf1df7a54141e83226b07 * Fixed support ir_ctx.ret_type
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Description
This bug was accidentally noticed in complex production scripts and was very hard to manually reproduce in a simple example. But nevermind, here's a working example below.
I use two files:
1.php:
2.php:
In short: the script is using multiple times a function, that is located in another php script file.
Under php 8.2, 8.1 and 8.0 - same results.
Under php-fpm and under apache/mod_php - same result.
Under php-cli - bug not reproducible
Steps to do:
upstream prematurely closed connection while reading response header from upstream
Apache error log empty.
Php-fpm error log says something like:
[24-Apr-2023 18:21:07] WARNING: [pool u10] child 71477 exited on signal 11 (SIGSEGV) after 20.735545 seconds from start
[24-Apr-2023 18:21:07] NOTICE: [pool u10] child 71484 started
php.ini:
opcache.jit_buffer_size=128M
When only i add:
opcache.jit=1205
The bug disappear, but php performance become a bit slower.
And also setting opcache.jit_buffer_size=0 solves the bug as well as slowing down the performance of course.
I have no clue what's going on, but something is clearly becomes wrong causing the executing process to crash.
PHP Version
php 8.2.5 8.1.18 8.0.28
Operating System
Debian 11
The text was updated successfully, but these errors were encountered: