Index: Python/ceval.c =================================================================== --- Python/ceval.c (revision 72657) +++ Python/ceval.c (working copy) @@ -3591,12 +3591,14 @@ return result; } +/* See Objects/lnotab_notes.txt for a description of how tracing works. */ static int maybe_call_line_trace(Py_tracefunc func, PyObject *obj, PyFrameObject *frame, int *instr_lb, int *instr_ub, int *instr_prev) { int result = 0; + int line = -1; /* If the last instruction executed isn't in the current instruction window, reset the window. If the last @@ -3604,20 +3606,17 @@ represents a jump backwards, call the trace function. */ if ((frame->f_lasti < *instr_lb || frame->f_lasti >= *instr_ub)) { - int line; PyAddrPair bounds; - line = PyCode_CheckLineNumber(frame->f_code, frame->f_lasti, &bounds); - if (line >= 0) { - frame->f_lineno = line; - result = call_trace(func, obj, frame, - PyTrace_LINE, Py_None); - } *instr_lb = bounds.ap_lower; *instr_ub = bounds.ap_upper; } - else if (frame->f_lasti <= *instr_prev) { + if (line < 0 && frame->f_lasti <= *instr_prev) { + line = PyCode_Addr2Line(frame->f_code, frame->f_lasti); + } + if (line >= 0) { + frame->f_lineno = line; result = call_trace(func, obj, frame, PyTrace_LINE, Py_None); } *instr_prev = frame->f_lasti; Index: Python/compile.c =================================================================== --- Python/compile.c (revision 72657) +++ Python/compile.c (working copy) @@ -1646,9 +1646,6 @@ VISIT(c, expr, s->v.For.iter); ADDOP(c, GET_ITER); compiler_use_next_block(c, start); - /* for expressions must be traced on each iteration, - so we need to set an extra line number. */ - c->u->u_lineno_set = false; ADDOP_JREL(c, FOR_ITER, cleanup); VISIT(c, expr, s->v.For.target); VISIT_SEQ(c, stmt, s->v.For.body); @@ -1694,9 +1691,6 @@ if (!compiler_push_fblock(c, LOOP, loop)) return 0; if (constant == -1) { - /* while expressions must be traced on each iteration, - so we need to set an extra line number. */ - c->u->u_lineno_set = false; VISIT(c, expr, s->v.While.test); ADDOP_JABS(c, POP_JUMP_IF_FALSE, anchor); } @@ -3493,52 +3487,10 @@ return size; } -/* All about a_lnotab. +/* Appends a pair to the end of the line number table, a_lnotab, representing + the instruction's bytecode offset and line number. See + Objects/lnotab_notes.txt for the description of the line number table. */ -c_lnotab is an array of unsigned bytes disguised as a Python string. -It is used to map bytecode offsets to source code line #s (when needed -for tracebacks). - -The array is conceptually a list of - (bytecode offset increment, line number increment) -pairs. The details are important and delicate, best illustrated by example: - - byte code offset source code line number - 0 1 - 6 2 - 50 7 - 350 307 - 361 308 - -The first trick is that these numbers aren't stored, only the increments -from one row to the next (this doesn't really work, but it's a start): - - 0, 1, 6, 1, 44, 5, 300, 300, 11, 1 - -The second trick is that an unsigned byte can't hold negative values, or -values larger than 255, so (a) there's a deep assumption that byte code -offsets and their corresponding line #s both increase monotonically, and (b) -if at least one column jumps by more than 255 from one row to the next, more -than one pair is written to the table. In case #b, there's no way to know -from looking at the table later how many were written. That's the delicate -part. A user of c_lnotab desiring to find the source line number -corresponding to a bytecode address A should do something like this - - lineno = addr = 0 - for addr_incr, line_incr in c_lnotab: - addr += addr_incr - if addr > A: - return lineno - lineno += line_incr - -In order for this to work, when the addr field increments by more than 255, -the line # increment in each pair generated must be 0 until the remaining addr -increment is < 256. So, in the example above, assemble_lnotab (it used -to be called com_set_lineno) should not (as was actually done until 2.2) -expand 300, 300 to 255, 255, 45, 45, - but to 255, 0, 45, 255, 0, 45. -*/ - static int assemble_lnotab(struct assembler *a, struct instr *i) { Index: Include/code.h =================================================================== --- Include/code.h (revision 72657) +++ Include/code.h (working copy) @@ -23,7 +23,8 @@ PyObject *co_filename; /* string (where it was loaded from) */ PyObject *co_name; /* string (name, for reference) */ int co_firstlineno; /* first source line number */ - PyObject *co_lnotab; /* string (encoding addr<->lineno mapping) */ + PyObject *co_lnotab; /* string (encoding addr<->lineno mapping) See + Objects/lnotab_notes.txt for details. */ void *co_zombieframe; /* for optimization only (see frameobject.c) */ } PyCodeObject; Index: Objects/codeobject.c =================================================================== --- Objects/codeobject.c (revision 72657) +++ Objects/codeobject.c (working copy) @@ -507,48 +507,8 @@ code_new, /* tp_new */ }; -/* All about c_lnotab. - -c_lnotab is an array of unsigned bytes disguised as a Python string. In -O -mode, SET_LINENO opcodes aren't generated, and bytecode offsets are mapped -to source code line #s (when needed for tracebacks) via c_lnotab instead. -The array is conceptually a list of - (bytecode offset increment, line number increment) -pairs. The details are important and delicate, best illustrated by example: - - byte code offset source code line number - 0 1 - 6 2 - 50 7 - 350 307 - 361 308 - -The first trick is that these numbers aren't stored, only the increments -from one row to the next (this doesn't really work, but it's a start): - - 0, 1, 6, 1, 44, 5, 300, 300, 11, 1 - -The second trick is that an unsigned byte can't hold negative values, or -values larger than 255, so (a) there's a deep assumption that byte code -offsets and their corresponding line #s both increase monotonically, and (b) -if at least one column jumps by more than 255 from one row to the next, more -than one pair is written to the table. In case #b, there's no way to know -from looking at the table later how many were written. That's the delicate -part. A user of c_lnotab desiring to find the source line number -corresponding to a bytecode address A should do something like this - - lineno = addr = 0 - for addr_incr, line_incr in c_lnotab: - addr += addr_incr - if addr > A: - return lineno - lineno += line_incr - -In order for this to work, when the addr field increments by more than 255, -the line # increment in each pair generated must be 0 until the remaining addr -increment is < 256. So, in the example above, com_set_lineno should not (as -was actually done until 2.2) expand 300, 300 to 255, 255, 45, 45, but to -255, 0, 45, 255, 0, 45. +/* Use co_lnotab to compute the line number from a bytecode index, addrq. See + lnotab_notes.txt for the details of the lnotab representation. */ int @@ -567,84 +527,11 @@ return line; } -/* - Check whether the current instruction is at the start of a line. - +/* Update *bounds to describe the first and last instructions in the same line + as lasti. If lasti is at the beginning of its line, return that line number. + Otherwise return -1. */ - - /* The theory of SET_LINENO-less tracing. - - In a nutshell, we use the co_lnotab field of the code object - to tell when execution has moved onto a different line. - - As mentioned above, the basic idea is so set things up so - that - - *instr_lb <= frame->f_lasti < *instr_ub - - is true so long as execution does not change lines. - - This is all fairly simple. Digging the information out of - co_lnotab takes some work, but is conceptually clear. - - Somewhat harder to explain is why we don't *always* call the - line trace function when the above test fails. - - Consider this code: - - 1: def f(a): - 2: if a: - 3: print 1 - 4: else: - 5: print 2 - - which compiles to this: - - 2 0 LOAD_FAST 0 (a) - 3 JUMP_IF_FALSE 9 (to 15) - 6 POP_TOP - - 3 7 LOAD_CONST 1 (1) - 10 PRINT_ITEM - 11 PRINT_NEWLINE - 12 JUMP_FORWARD 6 (to 21) - >> 15 POP_TOP - - 5 16 LOAD_CONST 2 (2) - 19 PRINT_ITEM - 20 PRINT_NEWLINE - >> 21 LOAD_CONST 0 (None) - 24 RETURN_VALUE - - If 'a' is false, execution will jump to instruction at offset - 15 and the co_lnotab will claim that execution has moved to - line 3. This is at best misleading. In this case we could - associate the POP_TOP with line 4, but that doesn't make - sense in all cases (I think). - - What we do is only call the line trace function if the co_lnotab - indicates we have jumped to the *start* of a line, i.e. if the - current instruction offset matches the offset given for the - start of a line by the co_lnotab. - - This also takes care of the situation where 'a' is true. - Execution will jump from instruction offset 12 to offset 21. - Then the co_lnotab would imply that execution has moved to line - 5, which is again misleading. - - Why do we set f_lineno when tracing? Well, consider the code - above when 'a' is true. If stepping through this with 'n' in - pdb, you would stop at line 1 with a "call" type event, then - line events on lines 2 and 3, then a "return" type event -- but - you would be shown line 5 during this event. This is a change - from the behaviour in 2.2 and before, and I've found it - confusing in practice. By setting and using f_lineno when - tracing, one can report a line number different from that - suggested by f_lasti on this one occasion where it's desirable. - */ - - -int +int PyCode_CheckLineNumber(PyCodeObject* co, int lasti, PyAddrPair *bounds) { int size, addr, line; @@ -662,11 +549,9 @@ instr_lb -- if we stored the matching value of p somwhere we could skip the first while loop. */ - /* see comments in compile.c for the description of + /* See lnotab_notes.txt for the description of co_lnotab. A point to remember: increments to p - should come in pairs -- although we don't care about - the line increments here, treating them as byte - increments gets confusing, to say the least. */ + come in (addr, line) pairs. */ bounds->ap_lower = 0; while (size > 0) { Index: Objects/lnotab_notes.txt =================================================================== --- Objects/lnotab_notes.txt (revision 0) +++ Objects/lnotab_notes.txt (revision 0) @@ -0,0 +1,124 @@ +All about co_lnotab, the line number table. + +Code objects store a field named co_lnotab. This is an array of unsigned bytes +disguised as a Python string. It is used to map bytecode offsets to source code +line #s for tracebacks and to identify line number boundaries for line tracing. + +The array is conceptually a compressed list of + (bytecode offset increment, line number increment) +pairs. The details are important and delicate, best illustrated by example: + + byte code offset source code line number + 0 1 + 6 2 + 50 7 + 350 307 + 361 308 + +Instead of storing these numbers literally, we compress the list by storing only +the increments from one row to the next. Conceptually, the stored list might +look like: + + 0, 1, 6, 1, 44, 5, 300, 300, 11, 1 + +The above doesn't really work, but it's a start. Note that an unsigned byte +can't hold negative values, or values larger than 255, and the above example +contains two such values. So we make two tweaks: + + (a) there's a deep assumption that byte code offsets and their corresponding + line #s both increase monotonically, and + (b) if at least one column jumps by more than 255 from one row to the next, + more than one pair is written to the table. In case #b, there's no way to know + from looking at the table later how many were written. That's the delicate + part. A user of co_lnotab desiring to find the source line number + corresponding to a bytecode address A should do something like this + + lineno = addr = 0 + for addr_incr, line_incr in co_lnotab: + addr += addr_incr + if addr > A: + return lineno + lineno += line_incr + +(In C, this is implemented by PyCode_Addr2Line().) In order for this to work, +when the addr field increments by more than 255, the line # increment in each +pair generated must be 0 until the remaining addr increment is < 256. So, in +the example above, assemble_lnotab in compile.c should not (as was actually done +until 2.2) expand 300, 300 to + 255, 255, 45, 45, +but to + 255, 0, 45, 255, 0, 45. + +The above is sufficient to reconstruct line numbers for tracebacks, but not for +line tracing. Tracing is handled by PyCode_CheckLineNumber() in codeobject.c +and maybe_call_line_trace() in ceval.c. + +*** Tracing *** + +To a first approximation, we want to call the tracing function when the line +number of the current instruction changes. Re-computing the current line for +every instruction is a little slow, though, so each time we compute the line +number we save the bytecode indices where it's valid: + + *instr_lb <= frame->f_lasti < *instr_ub + +is true so long as execution does not change lines. That is, *instr_lb holds +the first bytecode index of the current line, and *instr_ub holds the first +bytecode index of the next line. As long as the above expression is true, +maybe_call_line_trace() does not need to call PyCode_CheckLineNumber(). Note +that the same line may appear multiple times in the lnotab, either because the +bytecode jumped more than 255 indices between line number changes or because +the compiler inserted the same line twice. Even in that case, *instr_ub holds +the first index of the next line. + +However, we don't *always* want to call the line trace function when the above +test fails. + +Consider this code: + +1: def f(a): +2: while a: +3: print 1, +4: break +5: else: +6: print 2, + +which compiles to this: + + 2 0 SETUP_LOOP 19 (to 22) + >> 3 LOAD_FAST 0 (a) + 6 POP_JUMP_IF_FALSE 17 + + 3 9 LOAD_CONST 1 (1) + 12 PRINT_ITEM + + 4 13 BREAK_LOOP + 14 JUMP_ABSOLUTE 3 + >> 17 POP_BLOCK + + 6 18 LOAD_CONST 2 (2) + 21 PRINT_ITEM + >> 22 LOAD_CONST 0 (None) + 25 RETURN_VALUE + +If 'a' is false, execution will jump to the POP_BLOCK instruction at offset 17 +and the co_lnotab will claim that execution has moved to line 4, which is wrong. +In this case, we could instead associate the POP_BLOCK with line 5, but that +would break jumps around loops without else clauses. + +We fix this by only calling the line trace function for a forward jump if the +co_lnotab indicates we have jumped to the *start* of a line, i.e. if the current +instruction offset matches the offset given for the start of a line by the +co_lnotab. For backward jumps, however, we always call the line trace function, +which lets a debugger stop on every evaluation of a loop guard (which usually +won't be the first opcode in a line). + +Why do we set f_lineno when tracing, and only just before calling the trace +function? Well, consider the code above when 'a' is true. If stepping through +this with 'n' in pdb, you would stop at line 1 with a "call" type event, then +line events on lines 2, 3, and 4, then a "return" type event -- but because the +code for the return actually falls in the range of the "line 6" opcodes, you +would be shown line 6 during this event. This is a change from the behaviour in +2.2 and before, and I've found it confusing in practice. By setting and using +f_lineno when tracing, one can report a line number different from that +suggested by f_lasti on this one occasion where it's desirable. Index: Doc/library/sys.rst =================================================================== --- Doc/library/sys.rst (revision 72657) +++ Doc/library/sys.rst (working copy) @@ -798,9 +798,11 @@ specifies the local trace function. ``'line'`` - The interpreter is about to execute a new line of code (sometimes multiple - line events on one line exist). The local trace function is called; *arg* - is ``None``; the return value specifies the new local trace function. + The interpreter is about to execute a new line of code or re-execute the + condition of a loop. The local trace function is called; *arg* is + ``None``; the return value specifies the new local trace function. See + :file:`Objects/lnotab_notes.txt` for a detailed explanation of how this + works. ``'return'`` A function (or other code block) is about to return. The local trace