Issue #6042:
lnotab-based tracing is very complicated and isn't documented very well. There
were at least 3 comment blocks purporting to document co_lnotab, and none did a
very good job. This patch unifies them into Objects/lnotab_notes.txt which
tries to completely capture the current state of affairs.
I also discovered that we've attached 2 layers of patches to the basic tracing
scheme. The first layer avoids jumping to instructions that don't start a line,
to avoid problems in if statements and while loops. The second layer
discovered that jumps backward do need to trace at instructions that don't
start a line, so it added extra lnotab entries for 'while' and 'for' loops, and
added a special case for backward jumps within the same line. I replaced these
patches by just treating forward and backward jumps differently.
diff --git a/Python/ceval.c b/Python/ceval.c
index 474a885..4f0877b 100644
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -3591,33 +3591,30 @@
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 = frame->f_lineno;
/* If the last instruction executed isn't in the current
- instruction window, reset the window. If the last
- instruction happens to fall at the start of a line or if it
- represents a jump backwards, call the trace function.
+ instruction window, reset the window.
*/
- if ((frame->f_lasti < *instr_lb || frame->f_lasti >= *instr_ub)) {
- int line;
+ if (frame->f_lasti < *instr_lb || frame->f_lasti >= *instr_ub) {
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);
- }
+ line = _PyCode_CheckLineNumber(frame->f_code, frame->f_lasti,
+ &bounds);
*instr_lb = bounds.ap_lower;
*instr_ub = bounds.ap_upper;
}
- else if (frame->f_lasti <= *instr_prev) {
+ /* If the last instruction falls at the start of a line or if
+ it represents a jump backwards, update the frame's line
+ number and call the trace function. */
+ if (frame->f_lasti == *instr_lb || frame->f_lasti < *instr_prev) {
+ frame->f_lineno = line;
result = call_trace(func, obj, frame, PyTrace_LINE, Py_None);
}
*instr_prev = frame->f_lasti;
diff --git a/Python/compile.c b/Python/compile.c
index 69321ae..8c85306 100644
--- a/Python/compile.c
+++ b/Python/compile.c
@@ -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);
}
@@ -3493,51 +3487,9 @@
return size;
}
-/* All about a_lnotab.
-
-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.
-*/
+/* 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. */
static int
assemble_lnotab(struct assembler *a, struct instr *i)