Skip to content

fix: ubsan signed overflow violations #347

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Apr 21, 2023
Merged

fix: ubsan signed overflow violations #347

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions src/ada_idna.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2632,7 +2632,9 @@ uint32_t find_range_index(uint32_t key) {
}

bool ascii_has_upper_case(char* input, size_t length) {
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you also update ada/idna repository with the relevant changes as well?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes, i can do that once we've finished this one

};
uint64_t broadcast_80 = broadcast(0x80);
uint64_t broadcast_Ap = broadcast(128 - 'A');
uint64_t broadcast_Zp = broadcast(128 - 'Z' - 1);
Expand All @@ -2654,7 +2656,9 @@ bool ascii_has_upper_case(char* input, size_t length) {
}

void ascii_map(char* input, size_t length) {
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
uint64_t broadcast_80 = broadcast(0x80);
uint64_t broadcast_Ap = broadcast(128 - 'A');
uint64_t broadcast_Zp = broadcast(128 - 'Z' - 1);
Expand Down
16 changes: 12 additions & 4 deletions src/helpers.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,9 @@ ada_really_inline size_t find_next_host_delimiter_special(
auto index_of_first_set_byte = [](uint64_t v) {
return ((((v - 1) & 0x101010101010101) * 0x101010101010101) >> 56) - 1;
};
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
size_t i = location;
uint64_t mask1 = broadcast(':');
uint64_t mask2 = broadcast('/');
Expand Down Expand Up @@ -273,7 +275,9 @@ ada_really_inline size_t find_next_host_delimiter(std::string_view view,
auto index_of_first_set_byte = [](uint64_t v) {
return ((((v - 1) & 0x101010101010101) * 0x101010101010101) >> 56) - 1;
};
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
size_t i = location;
uint64_t mask1 = broadcast(':');
uint64_t mask2 = broadcast('/');
Expand Down Expand Up @@ -599,7 +603,9 @@ find_authority_delimiter_special(std::string_view view) noexcept {
auto index_of_first_set_byte = [](uint64_t v) {
return ((((v - 1) & 0x101010101010101) * 0x101010101010101) >> 56) - 1;
};
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
size_t i = 0;
uint64_t mask1 = broadcast('@');
uint64_t mask2 = broadcast('/');
Expand Down Expand Up @@ -647,7 +653,9 @@ find_authority_delimiter(std::string_view view) noexcept {
auto index_of_first_set_byte = [](uint64_t v) {
return ((((v - 1) & 0x101010101010101) * 0x101010101010101) >> 56) - 1;
};
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
size_t i = 0;
uint64_t mask1 = broadcast('@');
uint64_t mask2 = broadcast('/');
Expand Down
8 changes: 6 additions & 2 deletions src/unicode.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,9 @@ ADA_POP_DISABLE_WARNINGS
namespace ada::unicode {

constexpr bool to_lower_ascii(char* input, size_t length) noexcept {
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
uint64_t broadcast_80 = broadcast(0x80);
uint64_t broadcast_Ap = broadcast(128 - 'A');
uint64_t broadcast_Zp = broadcast(128 - 'Z' - 1);
Expand Down Expand Up @@ -43,7 +45,9 @@ ada_really_inline constexpr bool has_tabs_or_newline(
auto has_zero_byte = [](uint64_t v) {
return ((v - 0x0101010101010101) & ~(v)&0x8080808080808080);
};
auto broadcast = [](uint8_t v) -> uint64_t { return 0x101010101010101 * v; };
auto broadcast = [](uint8_t v) -> uint64_t {
return 0x101010101010101ull * v;
};
size_t i = 0;
uint64_t mask1 = broadcast('\r');
uint64_t mask2 = broadcast('\n');
Expand Down