Consider -fanalyzer on: #include <stdint.h>
int32_t arr[10]; void int_arr_write_element_after_end_off_by_one(int32_t x) { arr[10] = x; } Trunk x86_64: https://godbolt.org/z/17zn3qYY4 Currently we emit: <source>: In function 'int_arr_write_element_after_end_off_by_one': <source>:7:11: warning: buffer overflow [CWE-787] [-Wanalyzer-out-of-bounds] 7 | arr[10] = x; | ~~~~~~~~^~~ event 1 | | 3 | int32_t arr[10]; | | ^~~ | | | | | (1) capacity is 40 bytes | +--> 'int_arr_write_element_after_end_off_by_one': events 2-3 | | 5 | void int_arr_write_element_after_end_off_by_one(int32_t x) | | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ | | | | | (2) entry to 'int_arr_write_element_after_end_off_by_one' | 6 | { | 7 | arr[10] = x; | | ~~~~~~~~~~~ | | | | | (3) out-of-bounds write from byte 40 till byte 43 but 'arr' ends at byte 40 | <source>:7:11: note: write of 4 bytes to beyond the end of 'arr' 7 | arr[10] = x; | ~~~~~~~~^~~ This is worded in terms of bytes, due to the way -Wanalyzer-out-of-bounds is implemented, but this isn't what the user wrote. This patch tries to get closer to the user's code by adding a note about array bounds when we're referring to an array. In the above example it adds this trailing note: note: valid subscripts for 'arr' are '[0]' to '[9]' Successfully bootstrapped & regrtested on x86_64-pc-linux-gnu. Pushed to trunk as r13-4427-g7c655699ed51b0. gcc/analyzer/ChangeLog: PR analyzer/106626 * bounds-checking.cc (out_of_bounds::maybe_describe_array_bounds): New. (buffer_overflow::emit): Call maybe_describe_array_bounds. (buffer_overread::emit): Likewise. (buffer_underflow::emit): Likewise. (buffer_underread::emit): Likewise. gcc/testsuite/ChangeLog: PR analyzer/106626 * gcc.dg/analyzer/call-summaries-2.c: Add dg-message for expected note about valid indexes. * gcc.dg/analyzer/out-of-bounds-1.c: Likewise, fixing up existing dg-message directives. * gcc.dg/analyzer/out-of-bounds-write-char-arr.c: Likewise. * gcc.dg/analyzer/out-of-bounds-write-int-arr.c: Likewise. Signed-off-by: David Malcolm <dmalc...@redhat.com> --- gcc/analyzer/bounds-checking.cc | 46 +++++++++++++++++-- .../gcc.dg/analyzer/call-summaries-2.c | 1 + .../gcc.dg/analyzer/out-of-bounds-1.c | 16 ++++--- .../analyzer/out-of-bounds-write-char-arr.c | 6 +++ .../analyzer/out-of-bounds-write-int-arr.c | 6 +++ 5 files changed, 64 insertions(+), 11 deletions(-) diff --git a/gcc/analyzer/bounds-checking.cc b/gcc/analyzer/bounds-checking.cc index ad7f431ea2f..b02bc79a926 100644 --- a/gcc/analyzer/bounds-checking.cc +++ b/gcc/analyzer/bounds-checking.cc @@ -71,6 +71,34 @@ public: } protected: + /* Potentially add a note about valid ways to index this array, such + as (given "int arr[10];"): + note: valid subscripts for 'arr' are '[0]' to '[9]' + We print the '[' and ']' characters so as to express the valid + subscripts using C syntax, rather than just as byte ranges, + which hopefully is more clear to the user. */ + void + maybe_describe_array_bounds (location_t loc) const + { + if (!m_diag_arg) + return; + tree t = TREE_TYPE (m_diag_arg); + if (!t) + return; + if (TREE_CODE (t) != ARRAY_TYPE) + return; + tree domain = TYPE_DOMAIN (t); + if (!domain) + return; + tree max_idx = TYPE_MAX_VALUE (domain); + if (!max_idx) + return; + tree min_idx = TYPE_MIN_VALUE (domain); + inform (loc, + "valid subscripts for %qE are %<[%E]%> to %<[%E]%>", + m_diag_arg, min_idx, max_idx); + } + const region *m_reg; tree m_diag_arg; byte_range m_out_of_bounds_range; @@ -165,6 +193,8 @@ public: inform (rich_loc->get_loc (), "write to beyond the end of %qE", m_diag_arg); + + maybe_describe_array_bounds (rich_loc->get_loc ()); } return warned; @@ -245,6 +275,8 @@ public: inform (rich_loc->get_loc (), "read from after the end of %qE", m_diag_arg); + + maybe_describe_array_bounds (rich_loc->get_loc ()); } return warned; @@ -297,8 +329,11 @@ public: { diagnostic_metadata m; m.add_cwe (124); - return warning_meta (rich_loc, m, get_controlling_option (), - "buffer underflow"); + bool warned = warning_meta (rich_loc, m, get_controlling_option (), + "buffer underflow"); + if (warned) + maybe_describe_array_bounds (rich_loc->get_loc ()); + return warned; } label_text describe_final_event (const evdesc::final_event &ev) @@ -346,8 +381,11 @@ public: { diagnostic_metadata m; m.add_cwe (127); - return warning_meta (rich_loc, m, get_controlling_option (), - "buffer underread"); + bool warned = warning_meta (rich_loc, m, get_controlling_option (), + "buffer underread"); + if (warned) + maybe_describe_array_bounds (rich_loc->get_loc ()); + return warned; } label_text describe_final_event (const evdesc::final_event &ev) diff --git a/gcc/testsuite/gcc.dg/analyzer/call-summaries-2.c b/gcc/testsuite/gcc.dg/analyzer/call-summaries-2.c index 953cbd32f5a..a7a17dbd358 100644 --- a/gcc/testsuite/gcc.dg/analyzer/call-summaries-2.c +++ b/gcc/testsuite/gcc.dg/analyzer/call-summaries-2.c @@ -330,6 +330,7 @@ int test_returns_element_ptr (int j) __analyzer_eval (*returns_element_ptr (1) == 8); /* { dg-warning "TRUE" } */ __analyzer_eval (*returns_element_ptr (2) == 9); /* { dg-warning "TRUE" } */ return *returns_element_ptr (3); /* { dg-warning "buffer overread" } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[2\\\]'" "valid subscript note" { target *-*-* } .-1 } */ } int returns_offset (int arr[3], int i) diff --git a/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-1.c b/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-1.c index 9f3cda6e02b..dc4de9b28a6 100644 --- a/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-1.c +++ b/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-1.c @@ -25,8 +25,9 @@ void test1 (void) id_sequence[2] = 345; id_sequence[3] = 456; /* { dg-line test1 } */ - /* { dg-warning "overflow" "warning" { target *-*-* } test1 } */ - /* { dg-message "" "note" { target *-*-* } test1 } */ + /* { dg-warning "stack-based buffer overflow" "warning" { target *-*-* } test1 } */ + /* { dg-message "write of 4 bytes to beyond the end of 'id_sequence'" "num bad bytes note" { target *-*-* } test1 } */ + /* { dg-message "valid subscripts for 'id_sequence' are '\\\[0\\\]' to '\\\[2\\\]'" "valid subscript note" { target *-*-* } test1 } */ } void test2 (void) @@ -46,8 +47,9 @@ void test3 (void) for (int i = n; i >= 0; i--) arr[i] = i; /* { dg-line test3 } */ - /* { dg-warning "overflow" "warning" { target *-*-* } test3 } */ - /* { dg-message "" "note" { target *-*-* } test3 } */ + /* { dg-warning "stack-based buffer overflow" "warning" { target *-*-* } test3 } */ + /* { dg-message "write of 4 bytes to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } test3 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[3\\\]'" "valid subscript note" { target *-*-* } test3 } */ } void test4 (void) @@ -72,7 +74,7 @@ void test5 (void) *last_el = 4; /* { dg-line test5 } */ free (arr); - /* { dg-warning "overflow" "warning" { target *-*-* } test5 } */ + /* { dg-warning "heap-based buffer overflow" "warning" { target *-*-* } test5 } */ /* { dg-message "" "note" { target *-*-* } test5 } */ } @@ -89,9 +91,9 @@ void test6 (void) printf ("x=%d y=%d *p=%d *q=%d\n" , x, y, *p, *q); /* { dg-line test6c } */ } - /* { dg-warning "overflow" "warning" { target *-*-* } test6b } */ + /* { dg-warning "buffer overflow" "warning" { target *-*-* } test6b } */ /* { dg-message "" "note" { target *-*-* } test6b } */ - /* { dg-warning "overread" "warning" { target *-*-* } test6c } */ + /* { dg-warning "buffer overread" "warning" { target *-*-* } test6c } */ /* { dg-message "" "note" { target *-*-* } test6c } */ } diff --git a/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-char-arr.c b/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-char-arr.c index 3564476c322..739ebb11590 100644 --- a/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-char-arr.c +++ b/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-char-arr.c @@ -4,18 +4,21 @@ void int_arr_write_element_before_start_far(char x) { arr[-100] = x; /* { dg-warning "buffer underflow" "warning" } */ /* { dg-message "out-of-bounds write at byte -100 but 'arr' starts at byte 0" "final event" { target *-*-* } .-1 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-2 } */ } void int_arr_write_element_before_start_near(char x) { arr[-2] = x; /* { dg-warning "buffer underflow" "warning" } */ /* { dg-message "out-of-bounds write at byte -2 but 'arr' starts at byte 0" "final event" { target *-*-* } .-1 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-2 } */ } void int_arr_write_element_before_start_off_by_one(char x) { arr[-1] = x; /* { dg-warning "buffer underflow" "warning" } */ /* { dg-message "out-of-bounds write at byte -1 but 'arr' starts at byte 0" "final event" { target *-*-* } .-1 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-2 } */ } void int_arr_write_element_at_start(char x) @@ -33,6 +36,7 @@ void int_arr_write_element_after_end_off_by_one(char x) arr[10] = x; /* { dg-warning "buffer overflow" "warning" } */ /* { dg-message "out-of-bounds write at byte 10 but 'arr' ends at byte 10" "final event" { target *-*-* } .-1 } */ /* { dg-message "write of 1 byte to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } .-2 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-3 } */ } void int_arr_write_element_after_end_near(char x) @@ -40,6 +44,7 @@ void int_arr_write_element_after_end_near(char x) arr[11] = x; /* { dg-warning "buffer overflow" "warning" } */ /* { dg-message "out-of-bounds write at byte 11 but 'arr' ends at byte 10" "final event" { target *-*-* } .-1 } */ /* { dg-message "write of 1 byte to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } .-2 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-3 } */ } void int_arr_write_element_after_end_far(char x) @@ -47,4 +52,5 @@ void int_arr_write_element_after_end_far(char x) arr[100] = x; /* { dg-warning "buffer overflow" "warning" } */ /* { dg-message "out-of-bounds write at byte 100 but 'arr' ends at byte 10" "final event" { target *-*-* } .-1 } */ /* { dg-message "write of 1 byte to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } .-2 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-3 } */ } diff --git a/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-int-arr.c b/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-int-arr.c index 24a9a6bfa18..b2b37b92e01 100644 --- a/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-int-arr.c +++ b/gcc/testsuite/gcc.dg/analyzer/out-of-bounds-write-int-arr.c @@ -6,18 +6,21 @@ void int_arr_write_element_before_start_far(int32_t x) { arr[-100] = x; /* { dg-warning "buffer underflow" "warning" } */ /* { dg-message "out-of-bounds write from byte -400 till byte -397 but 'arr' starts at byte 0" "final event" { target *-*-* } .-1 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-2 } */ } void int_arr_write_element_before_start_near(int32_t x) { arr[-2] = x; /* { dg-warning "buffer underflow" "warning" } */ /* { dg-message "out-of-bounds write from byte -8 till byte -5 but 'arr' starts at byte 0" "final event" { target *-*-* } .-1 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-2 } */ } void int_arr_write_element_before_start_off_by_one(int32_t x) { arr[-1] = x; /* { dg-warning "buffer underflow" "warning" } */ /* { dg-message "out-of-bounds write from byte -4 till byte -1 but 'arr' starts at byte 0" "final event" { target *-*-* } .-1 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-2 } */ } void int_arr_write_element_at_start(int32_t x) @@ -35,6 +38,7 @@ void int_arr_write_element_after_end_off_by_one(int32_t x) arr[10] = x; /* { dg-warning "buffer overflow" "warning" } */ /* { dg-message "out-of-bounds write from byte 40 till byte 43 but 'arr' ends at byte 40" "final event" { target *-*-* } .-1 } */ /* { dg-message "write of 4 bytes to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } .-2 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-3 } */ } void int_arr_write_element_after_end_near(int32_t x) @@ -42,6 +46,7 @@ void int_arr_write_element_after_end_near(int32_t x) arr[11] = x; /* { dg-warning "buffer overflow" "warning" } */ /* { dg-message "out-of-bounds write from byte 44 till byte 47 but 'arr' ends at byte 40" "final event" { target *-*-* } .-1 } */ /* { dg-message "write of 4 bytes to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } .-2 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-3 } */ } void int_arr_write_element_after_end_far(int32_t x) @@ -49,4 +54,5 @@ void int_arr_write_element_after_end_far(int32_t x) arr[100] = x; /* { dg-warning "buffer overflow" "warning" } */ /* { dg-message "out-of-bounds write from byte 400 till byte 403 but 'arr' ends at byte 40" "final event" { target *-*-* } .-1 } */ /* { dg-message "write of 4 bytes to beyond the end of 'arr'" "num bad bytes note" { target *-*-* } .-2 } */ + /* { dg-message "valid subscripts for 'arr' are '\\\[0\\\]' to '\\\[9\\\]'" "valid subscript note" { target *-*-* } .-3 } */ } -- 2.26.3