diff options
| -rw-r--r-- | block/io.c | 10 | ||||
| -rw-r--r-- | include/qemu/uri.h | 4 | ||||
| -rw-r--r-- | linux-user/elfload.c | 10 | ||||
| -rwxr-xr-x | linux-user/riscv/vdso-32.so | bin | 2900 -> 2980 bytes | |||
| -rwxr-xr-x | linux-user/riscv/vdso-64.so | bin | 3856 -> 3944 bytes | |||
| -rw-r--r-- | linux-user/riscv/vdso.S | 8 | ||||
| -rw-r--r-- | linux-user/signal.c | 5 | ||||
| -rw-r--r-- | tcg/arm/tcg-target.c.inc | 3 | ||||
| -rw-r--r-- | tcg/region.c | 10 | ||||
| -rw-r--r-- | tcg/s390x/tcg-target.c.inc | 6 | ||||
| -rw-r--r-- | tests/qtest/meson.build | 8 | ||||
| -rw-r--r-- | tests/unit/test-iov.c | 20 | ||||
| -rw-r--r-- | util/coroutine-ucontext.c | 35 | ||||
| -rw-r--r-- | util/uri.c | 869 |
14 files changed, 88 insertions, 900 deletions
diff --git a/block/io.c b/block/io.c index 8fa7670571..33150c0359 100644 --- a/block/io.c +++ b/block/io.c @@ -2584,6 +2584,16 @@ bdrv_co_do_block_status(BlockDriverState *bs, bool want_zero, ret |= (ret2 & BDRV_BLOCK_ZERO); } } + + /* + * Now that the recursive search was done, clear the flag. Otherwise, + * with more complicated block graphs like snapshot-access -> + * copy-before-write -> qcow2, where the return value will be propagated + * further up to a parent bdrv_co_do_block_status() call, both the + * BDRV_BLOCK_RECURSE and BDRV_BLOCK_ZERO flags would be set, which is + * not allowed. + */ + ret &= ~BDRV_BLOCK_RECURSE; } out: diff --git a/include/qemu/uri.h b/include/qemu/uri.h index 1855b764f2..255e61f452 100644 --- a/include/qemu/uri.h +++ b/include/qemu/uri.h @@ -72,14 +72,10 @@ typedef struct URI { } URI; URI *uri_new(void); -char *uri_resolve(const char *URI, const char *base); -char *uri_resolve_relative(const char *URI, const char *base); URI *uri_parse(const char *str); URI *uri_parse_raw(const char *str, int raw); int uri_parse_into(URI *uri, const char *str); char *uri_to_string(URI *uri); -char *uri_string_escape(const char *str, const char *list); -char *uri_string_unescape(const char *str, int len, char *target); void uri_free(URI *uri); /* Single web service query parameter 'name=value'. */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index cf9e74468b..daf7ef8435 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -2,6 +2,7 @@ #include "qemu/osdep.h" #include <sys/param.h> +#include <sys/prctl.h> #include <sys/resource.h> #include <sys/shm.h> @@ -4667,9 +4668,14 @@ static int elf_core_dump(int signr, const CPUArchState *env) init_note_info(&info); errno = 0; - getrlimit(RLIMIT_CORE, &dumpsize); - if (dumpsize.rlim_cur == 0) + + if (prctl(PR_GET_DUMPABLE) == 0) { + return 0; + } + + if (getrlimit(RLIMIT_CORE, &dumpsize) == 0 && dumpsize.rlim_cur == 0) { return 0; + } corefile = core_dump_filename(ts); diff --git a/linux-user/riscv/vdso-32.so b/linux-user/riscv/vdso-32.so index 1ad1e5cbbb..c2ce2a4757 100755 --- a/linux-user/riscv/vdso-32.so +++ b/linux-user/riscv/vdso-32.so Binary files differdiff --git a/linux-user/riscv/vdso-64.so b/linux-user/riscv/vdso-64.so index 83992bebe6..ae49f5b043 100755 --- a/linux-user/riscv/vdso-64.so +++ b/linux-user/riscv/vdso-64.so Binary files differdiff --git a/linux-user/riscv/vdso.S b/linux-user/riscv/vdso.S index a86d8fc488..c37275233a 100644 --- a/linux-user/riscv/vdso.S +++ b/linux-user/riscv/vdso.S @@ -101,12 +101,12 @@ endf __vdso_flush_icache .cfi_startproc simple .cfi_signal_frame -#define sizeof_reg (__riscv_xlen / 4) +#define sizeof_reg (__riscv_xlen / 8) #define sizeof_freg 8 -#define B_GR (offsetof_uc_mcontext - sizeof_rt_sigframe) -#define B_FR (offsetof_uc_mcontext - sizeof_rt_sigframe + offsetof_freg0) +#define B_GR 0 +#define B_FR offsetof_freg0 - .cfi_def_cfa 2, sizeof_rt_sigframe + .cfi_def_cfa 2, offsetof_uc_mcontext /* Return address */ .cfi_return_column 64 diff --git a/linux-user/signal.c b/linux-user/signal.c index b35d1e512f..c9527adfa3 100644 --- a/linux-user/signal.c +++ b/linux-user/signal.c @@ -925,7 +925,7 @@ static void host_sigsegv_handler(CPUState *cpu, siginfo_t *info, cpu_loop_exit_sigsegv(cpu, guest_addr, access_type, maperr, pc); } -static void host_sigbus_handler(CPUState *cpu, siginfo_t *info, +static uintptr_t host_sigbus_handler(CPUState *cpu, siginfo_t *info, host_sigcontext *uc) { uintptr_t pc = host_signal_pc(uc); @@ -947,6 +947,7 @@ static void host_sigbus_handler(CPUState *cpu, siginfo_t *info, sigprocmask(SIG_SETMASK, host_signal_mask(uc), NULL); cpu_loop_exit_sigbus(cpu, guest_addr, access_type, pc); } + return pc; } static void host_signal_handler(int host_sig, siginfo_t *info, void *puc) @@ -974,7 +975,7 @@ static void host_signal_handler(int host_sig, siginfo_t *info, void *puc) host_sigsegv_handler(cpu, info, uc); return; case SIGBUS: - host_sigbus_handler(cpu, info, uc); + pc = host_sigbus_handler(cpu, info, uc); sync_sig = true; break; case SIGILL: diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index fc78566494..a9aa8aa91c 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -1662,6 +1662,9 @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, TCGReg datalo, } else { tcg_out_strd_r(s, h.cond, datalo, h.base, h.index); } + } else if (h.index < 0) { + tcg_out_st32_12(s, h.cond, datalo, h.base, 0); + tcg_out_st32_12(s, h.cond, datahi, h.base, 4); } else if (h.index_scratch) { tcg_out_st32_rwb(s, h.cond, datalo, h.index, h.base); tcg_out_st32_12(s, h.cond, datahi, h.index, 4); diff --git a/tcg/region.c b/tcg/region.c index 86692455c0..478ec051c4 100644 --- a/tcg/region.c +++ b/tcg/region.c @@ -584,7 +584,9 @@ static int alloc_code_gen_buffer_splitwx_memfd(size_t size, Error **errp) buf_rx = mmap(NULL, size, host_prot_read_exec(), MAP_SHARED, fd, 0); if (buf_rx == MAP_FAILED) { - goto fail_rx; + error_setg_errno(errp, errno, + "failed to map shared memory for execute"); + goto fail; } close(fd); @@ -594,12 +596,8 @@ static int alloc_code_gen_buffer_splitwx_memfd(size_t size, Error **errp) return PROT_READ | PROT_WRITE; - fail_rx: - error_setg_errno(errp, errno, "failed to map shared memory for execute"); fail: - if (buf_rx != MAP_FAILED) { - munmap(buf_rx, size); - } + /* buf_rx is always equal to MAP_FAILED here and does not require cleanup */ if (buf_rw) { munmap(buf_rw, size); } diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc index fbee43d3b0..7f6b84aa2c 100644 --- a/tcg/s390x/tcg-target.c.inc +++ b/tcg/s390x/tcg-target.c.inc @@ -683,7 +683,7 @@ static void tcg_out_insn_VRIc(TCGContext *s, S390Opcode op, tcg_debug_assert(is_vector_reg(v3)); tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v3 & 0xf)); tcg_out16(s, i2); - tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, v3, 0) | (m4 << 12)); + tcg_out16(s, (op & 0x00ff) | RXB(v1, v3, 0, 0) | (m4 << 12)); } static void tcg_out_insn_VRRa(TCGContext *s, S390Opcode op, @@ -738,7 +738,7 @@ static void tcg_out_insn_VRSa(TCGContext *s, S390Opcode op, TCGReg v1, tcg_debug_assert(is_vector_reg(v3)); tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v3 & 0xf)); tcg_out16(s, b2 << 12 | d2); - tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, v3, 0) | (m4 << 12)); + tcg_out16(s, (op & 0x00ff) | RXB(v1, v3, 0, 0) | (m4 << 12)); } static void tcg_out_insn_VRSb(TCGContext *s, S390Opcode op, TCGReg v1, @@ -762,7 +762,7 @@ static void tcg_out_insn_VRSc(TCGContext *s, S390Opcode op, TCGReg r1, tcg_debug_assert(is_vector_reg(v3)); tcg_out16(s, (op & 0xff00) | (r1 << 4) | (v3 & 0xf)); tcg_out16(s, b2 << 12 | d2); - tcg_out16(s, (op & 0x00ff) | RXB(0, 0, v3, 0) | (m4 << 12)); + tcg_out16(s, (op & 0x00ff) | RXB(0, v3, 0, 0) | (m4 << 12)); } static void tcg_out_insn_VRX(TCGContext *s, S390Opcode op, TCGReg v1, diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index d22434b14e..84a055a7d9 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -1,16 +1,18 @@ slow_qtests = { 'aspeed_smc-test': 360, - 'bios-tables-test' : 540, + 'bios-tables-test' : 610, + 'cdrom-test' : 610, 'device-introspect-test' : 720, 'migration-test' : 480, 'npcm7xx_pwm-test': 300, 'npcm7xx_watchdog_timer-test': 120, 'qom-test' : 900, 'test-hmp' : 240, - 'pxe-test': 600, + 'pxe-test': 610, 'prom-env-test': 360, - 'boot-serial-test': 240, + 'boot-serial-test': 360, 'qos-test': 120, + 'vmgenid-test': 610, } qtests_generic = [ diff --git a/tests/unit/test-iov.c b/tests/unit/test-iov.c index 6f7623d310..75bc3be005 100644 --- a/tests/unit/test-iov.c +++ b/tests/unit/test-iov.c @@ -197,15 +197,17 @@ static void test_io(void) s = g_test_rand_int_range(0, j - k + 1); r = iov_send(sv[1], iov, niov, k, s); g_assert(memcmp(iov, siov, sizeof(*iov)*niov) == 0); - if (r >= 0) { - k += r; - usleep(g_test_rand_int_range(0, 30)); - } else if (errno == EAGAIN) { - select(sv[1]+1, NULL, &fds, NULL, NULL); - continue; - } else { - perror("send"); - exit(1); + if (r < 0) { + if (errno == EAGAIN) { + r = 0; + } else { + perror("send"); + exit(1); + } + } + k += r; + if (k < j) { + select(sv[1] + 1, NULL, &fds, NULL, NULL); } } while(k < j); } diff --git a/util/coroutine-ucontext.c b/util/coroutine-ucontext.c index 7b304c79d9..8ef603d081 100644 --- a/util/coroutine-ucontext.c +++ b/util/coroutine-ucontext.c @@ -119,13 +119,11 @@ void finish_switch_fiber(void *fake_stack_save) /* always_inline is required to avoid TSan runtime fatal errors. */ static inline __attribute__((always_inline)) -void start_switch_fiber_asan(CoroutineAction action, void **fake_stack_save, +void start_switch_fiber_asan(void **fake_stack_save, const void *bottom, size_t size) { #ifdef CONFIG_ASAN - __sanitizer_start_switch_fiber( - action == COROUTINE_TERMINATE ? NULL : fake_stack_save, - bottom, size); + __sanitizer_start_switch_fiber(fake_stack_save, bottom, size); #endif } @@ -165,7 +163,7 @@ static void coroutine_trampoline(int i0, int i1) if (!sigsetjmp(self->env, 0)) { CoroutineUContext *leaderp = get_ptr_leader(); - start_switch_fiber_asan(COROUTINE_YIELD, &fake_stack_save, + start_switch_fiber_asan(&fake_stack_save, leaderp->stack, leaderp->stack_size); start_switch_fiber_tsan(&fake_stack_save, self, true); /* true=caller */ siglongjmp(*(sigjmp_buf *)co->entry_arg, 1); @@ -226,8 +224,7 @@ Coroutine *qemu_coroutine_new(void) /* swapcontext() in, siglongjmp() back out */ if (!sigsetjmp(old_env, 0)) { - start_switch_fiber_asan(COROUTINE_YIELD, &fake_stack_save, co->stack, - co->stack_size); + start_switch_fiber_asan(&fake_stack_save, co->stack, co->stack_size); start_switch_fiber_tsan(&fake_stack_save, co, false); /* false=not caller */ @@ -269,10 +266,28 @@ static inline void valgrind_stack_deregister(CoroutineUContext *co) #endif #endif +#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL) +static void coroutine_fn terminate_asan(void *opaque) +{ + CoroutineUContext *to = DO_UPCAST(CoroutineUContext, base, opaque); + + set_current(opaque); + start_switch_fiber_asan(NULL, to->stack, to->stack_size); + G_STATIC_ASSERT(!IS_ENABLED(CONFIG_TSAN)); + siglongjmp(to->env, COROUTINE_ENTER); +} +#endif + void qemu_coroutine_delete(Coroutine *co_) { CoroutineUContext *co = DO_UPCAST(CoroutineUContext, base, co_); +#if defined(CONFIG_ASAN) && defined(CONFIG_COROUTINE_POOL) + co_->entry_arg = qemu_coroutine_self(); + co_->entry = terminate_asan; + qemu_coroutine_switch(co_->entry_arg, co_, COROUTINE_ENTER); +#endif + #ifdef CONFIG_VALGRIND_H valgrind_stack_deregister(co); #endif @@ -305,8 +320,10 @@ qemu_coroutine_switch(Coroutine *from_, Coroutine *to_, ret = sigsetjmp(from->env, 0); if (ret == 0) { - start_switch_fiber_asan(action, &fake_stack_save, to->stack, - to->stack_size); + start_switch_fiber_asan(IS_ENABLED(CONFIG_COROUTINE_POOL) || + action != COROUTINE_TERMINATE ? + &fake_stack_save : NULL, + to->stack, to->stack_size); start_switch_fiber_tsan(&fake_stack_save, to, false); /* false=not caller */ siglongjmp(to->env, action); diff --git a/util/uri.c b/util/uri.c index dcb3305236..573174bf47 100644 --- a/util/uri.c +++ b/util/uri.c @@ -164,19 +164,6 @@ static void uri_clean(URI *uri); ((*(p) == '=')) || ((*(p) == '\''))) /* - * gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@" - */ -#define ISA_GEN_DELIM(p) \ - (((*(p) == ':')) || ((*(p) == '/')) || ((*(p) == '?')) || \ - ((*(p) == '#')) || ((*(p) == '[')) || ((*(p) == ']')) || \ - ((*(p) == '@'))) - -/* - * reserved = gen-delims / sub-delims - */ -#define ISA_RESERVED(p) (ISA_GEN_DELIM(p) || (ISA_SUB_DELIM(p))) - -/* * unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" */ #define ISA_UNRESERVED(p) \ @@ -267,7 +254,7 @@ static int rfc3986_parse_fragment(URI *uri, const char **str) if (uri->cleanup & 2) { uri->fragment = g_strndup(*str, cur - *str); } else { - uri->fragment = uri_string_unescape(*str, cur - *str, NULL); + uri->fragment = g_uri_unescape_segment(*str, cur, NULL); } } *str = cur; @@ -368,7 +355,7 @@ static int rfc3986_parse_user_info(URI *uri, const char **str) if (uri->cleanup & 2) { uri->user = g_strndup(*str, cur - *str); } else { - uri->user = uri_string_unescape(*str, cur - *str, NULL); + uri->user = g_uri_unescape_segment(*str, cur, NULL); } } *str = cur; @@ -496,7 +483,7 @@ found: if (uri->cleanup & 2) { uri->server = g_strndup(host, cur - host); } else { - uri->server = uri_string_unescape(host, cur - host, NULL); + uri->server = g_uri_unescape_segment(host, cur, NULL); } } else { uri->server = NULL; @@ -614,7 +601,7 @@ static int rfc3986_parse_path_ab_empty(URI *uri, const char **str) if (uri->cleanup & 2) { uri->path = g_strndup(*str, cur - *str); } else { - uri->path = uri_string_unescape(*str, cur - *str, NULL); + uri->path = g_uri_unescape_segment(*str, cur, NULL); } } else { uri->path = NULL; @@ -663,7 +650,7 @@ static int rfc3986_parse_path_absolute(URI *uri, const char **str) if (uri->cleanup & 2) { uri->path = g_strndup(*str, cur - *str); } else { - uri->path = uri_string_unescape(*str, cur - *str, NULL); + uri->path = g_uri_unescape_segment(*str, cur, NULL); } } else { uri->path = NULL; @@ -709,7 +696,7 @@ static int rfc3986_parse_path_rootless(URI *uri, const char **str) if (uri->cleanup & 2) { uri->path = g_strndup(*str, cur - *str); } else { - uri->path = uri_string_unescape(*str, cur - *str, NULL); + uri->path = g_uri_unescape_segment(*str, cur, NULL); } } else { uri->path = NULL; @@ -755,7 +742,7 @@ static int rfc3986_parse_path_no_scheme(URI *uri, const char **str) if (uri->cleanup & 2) { uri->path = g_strndup(*str, cur - *str); } else { - uri->path = uri_string_unescape(*str, cur - *str, NULL); + uri->path = g_uri_unescape_segment(*str, cur, NULL); } } else { uri->path = NULL; @@ -1351,844 +1338,10 @@ void uri_free(URI *uri) /************************************************************************ * * - * Helper functions * - * * - ************************************************************************/ - -/** - * normalize_uri_path: - * @path: pointer to the path string - * - * Applies the 5 normalization steps to a path string--that is, RFC 2396 - * Section 5.2, steps 6.c through 6.g. - * - * Normalization occurs directly on the string, no new allocation is done - * - * Returns 0 or an error code - */ -static int normalize_uri_path(char *path) -{ - char *cur, *out; - - if (path == NULL) { - return -1; - } - - /* Skip all initial "/" chars. We want to get to the beginning of the - * first non-empty segment. - */ - cur = path; - while (cur[0] == '/') { - ++cur; - } - if (cur[0] == '\0') { - return 0; - } - - /* Keep everything we've seen so far. */ - out = cur; - - /* - * Analyze each segment in sequence for cases (c) and (d). - */ - while (cur[0] != '\0') { - /* - * c) All occurrences of "./", where "." is a complete path segment, - * are removed from the buffer string. - */ - if ((cur[0] == '.') && (cur[1] == '/')) { - cur += 2; - /* '//' normalization should be done at this point too */ - while (cur[0] == '/') { - cur++; - } - continue; - } - - /* - * d) If the buffer string ends with "." as a complete path segment, - * that "." is removed. - */ - if ((cur[0] == '.') && (cur[1] == '\0')) { - break; - } - - /* Otherwise keep the segment. */ - while (cur[0] != '/') { - if (cur[0] == '\0') { - goto done_cd; - } - (out++)[0] = (cur++)[0]; - } - /* nomalize // */ - while ((cur[0] == '/') && (cur[1] == '/')) { - cur++; - } - - (out++)[0] = (cur++)[0]; - } -done_cd: - out[0] = '\0'; - - /* Reset to the beginning of the first segment for the next sequence. */ - cur = path; - while (cur[0] == '/') { - ++cur; - } - if (cur[0] == '\0') { - return 0; - } - - /* - * Analyze each segment in sequence for cases (e) and (f). - * - * e) All occurrences of "<segment>/../", where <segment> is a - * complete path segment not equal to "..", are removed from the - * buffer string. Removal of these path segments is performed - * iteratively, removing the leftmost matching pattern on each - * iteration, until no matching pattern remains. - * - * f) If the buffer string ends with "<segment>/..", where <segment> - * is a complete path segment not equal to "..", that - * "<segment>/.." is removed. - * - * To satisfy the "iterative" clause in (e), we need to collapse the - * string every time we find something that needs to be removed. Thus, - * we don't need to keep two pointers into the string: we only need a - * "current position" pointer. - */ - while (1) { - char *segp, *tmp; - - /* At the beginning of each iteration of this loop, "cur" points to - * the first character of the segment we want to examine. - */ - - /* Find the end of the current segment. */ - segp = cur; - while ((segp[0] != '/') && (segp[0] != '\0')) { - ++segp; - } - - /* If this is the last segment, we're done (we need at least two - * segments to meet the criteria for the (e) and (f) cases). - */ - if (segp[0] == '\0') { - break; - } - - /* If the first segment is "..", or if the next segment _isn't_ "..", - * keep this segment and try the next one. - */ - ++segp; - if (((cur[0] == '.') && (cur[1] == '.') && (segp == cur + 3)) || - ((segp[0] != '.') || (segp[1] != '.') || - ((segp[2] != '/') && (segp[2] != '\0')))) { - cur = segp; - continue; - } - - /* If we get here, remove this segment and the next one and back up - * to the previous segment (if there is one), to implement the - * "iteratively" clause. It's pretty much impossible to back up - * while maintaining two pointers into the buffer, so just compact - * the whole buffer now. - */ - - /* If this is the end of the buffer, we're done. */ - if (segp[2] == '\0') { - cur[0] = '\0'; - break; - } - /* Valgrind complained, strcpy(cur, segp + 3); */ - /* string will overlap, do not use strcpy */ - tmp = cur; - segp += 3; - while ((*tmp++ = *segp++) != 0) { - /* No further work */ - } - - /* If there are no previous segments, then keep going from here. */ - segp = cur; - while ((segp > path) && ((--segp)[0] == '/')) { - /* No further work */ - } - if (segp == path) { - continue; - } - - /* "segp" is pointing to the end of a previous segment; find it's - * start. We need to back up to the previous segment and start - * over with that to handle things like "foo/bar/../..". If we - * don't do this, then on the first pass we'll remove the "bar/..", - * but be pointing at the second ".." so we won't realize we can also - * remove the "foo/..". - */ - cur = segp; - while ((cur > path) && (cur[-1] != '/')) { - --cur; - } - } - out[0] = '\0'; - - /* - * g) If the resulting buffer string still begins with one or more - * complete path segments of "..", then the reference is - * considered to be in error. Implementations may handle this - * error by retaining these components in the resolved path (i.e., - * treating them as part of the final URI), by removing them from - * the resolved path (i.e., discarding relative levels above the - * root), or by avoiding traversal of the reference. - * - * We discard them from the final path. - */ - if (path[0] == '/') { - cur = path; - while ((cur[0] == '/') && (cur[1] == '.') && (cur[2] == '.') && - ((cur[3] == '/') || (cur[3] == '\0'))) { - cur += 3; - } - - if (cur != path) { - out = path; - while (cur[0] != '\0') { - (out++)[0] = (cur++)[0]; - } - out[0] = 0; - } - } - - return 0; -} - -static int is_hex(char c) -{ - if (((c >= '0') && (c <= '9')) || ((c >= 'a') && (c <= 'f')) || - ((c >= 'A') && (c <= 'F'))) { - return 1; - } - return 0; -} - -/** - * uri_string_unescape: - * @str: the string to unescape - * @len: the length in bytes to unescape (or <= 0 to indicate full string) - * @target: optional destination buffer - * - * Unescaping routine, but does not check that the string is an URI. The - * output is a direct unsigned char translation of %XX values (no encoding) - * Note that the length of the result can only be smaller or same size as - * the input string. - * - * Returns a copy of the string, but unescaped, will return NULL only in case - * of error - */ -char *uri_string_unescape(const char *str, int len, char *target) -{ - char *ret, *out; - const char *in; - - if (str == NULL) { - return NULL; - } - if (len <= 0) { - len = strlen(str); - } - if (len < 0) { - return NULL; - } - - if (target == NULL) { - ret = g_malloc(len + 1); - } else { - ret = target; - } - in = str; - out = ret; - while (len > 0) { - if ((len > 2) && (*in == '%') && (is_hex(in[1])) && (is_hex(in[2]))) { - in++; - if ((*in >= '0') && (*in <= '9')) { - *out = (*in - '0'); - } else if ((*in >= 'a') && (*in <= 'f')) { - *out = (*in - 'a') + 10; - } else if ((*in >= 'A') && (*in <= 'F')) { - *out = (*in - 'A') + 10; - } - in++; - if ((*in >= '0') && (*in <= '9')) { - *out = *out * 16 + (*in - '0'); - } else if ((*in >= 'a') && (*in <= 'f')) { - *out = *out * 16 + (*in - 'a') + 10; - } else if ((*in >= 'A') && (*in <= 'F')) { - *out = *out * 16 + (*in - 'A') + 10; - } - in++; - len -= 3; - out++; - } else { - *out++ = *in++; - len--; - } - } - *out = 0; - return ret; -} - -/** - * uri_string_escape: - * @str: string to escape - * @list: exception list string of chars not to escape - * - * This routine escapes a string to hex, ignoring reserved characters (a-z) - * and the characters in the exception list. - * - * Returns a new escaped string or NULL in case of error. - */ -char *uri_string_escape(const char *str, const char *list) -{ - char *ret, ch; - char *temp; - const char *in; - int len, out; - - if (str == NULL) { - return NULL; - } - if (str[0] == 0) { - return g_strdup(str); - } - len = strlen(str); - if (!(len > 0)) { - return NULL; - } - - len += 20; - ret = g_malloc(len); - in = str; - out = 0; - while (*in != 0) { - if (len - out <= 3) { - temp = realloc2n(ret, &len); - ret = temp; - } - - ch = *in; - - if ((ch != '@') && (!IS_UNRESERVED(ch)) && (!strchr(list, ch))) { - unsigned char val; - ret[out++] = '%'; - val = ch >> 4; - if (val <= 9) { - ret[out++] = '0' + val; - } else { - ret[out++] = 'A' + val - 0xA; - } - val = ch & 0xF; - if (val <= 9) { - ret[out++] = '0' + val; - } else { - ret[out++] = 'A' + val - 0xA; - } - in++; - } else { - ret[out++] = *in++; - } - } - ret[out] = 0; - return ret; -} - -/************************************************************************ - * * * Public functions * * * ************************************************************************/ -/** - * uri_resolve: - * @URI: the URI instance found in the document - * @base: the base value - * - * Computes he final URI of the reference done by checking that - * the given URI is valid, and building the final URI using the - * base URI. This is processed according to section 5.2 of the - * RFC 2396 - * - * 5.2. Resolving Relative References to Absolute Form - * - * Returns a new URI string (to be freed by the caller) or NULL in case - * of error. - */ -char *uri_resolve(const char *uri, const char *base) -{ - char *val = NULL; - int ret, len, indx, cur, out; - URI *ref = NULL; - URI *bas = NULL; - URI *res = NULL; - - /* - * 1) The URI reference is parsed into the potential four components and - * fragment identifier, as described in Section 4.3. - * - * NOTE that a completely empty URI is treated by modern browsers - * as a reference to "." rather than as a synonym for the current - * URI. Should we do that here? - */ - if (uri == NULL) { - ret = -1; - } else { - if (*uri) { - ref = uri_new(); - ret = uri_parse_into(ref, uri); - } else { - ret = 0; - } - } - if (ret != 0) { - goto done; - } - if ((ref != NULL) && (ref->scheme != NULL)) { - /* - * The URI is absolute don't modify. - */ - val = g_strdup(uri); - goto done; - } - if (base == NULL) { - ret = -1; - } else { - bas = uri_new(); - ret = uri_parse_into(bas, base); - } - if (ret != 0) { - if (ref) { - val = uri_to_string(ref); - } - goto done; - } - if (ref == NULL) { - /* - * the base fragment must be ignored - */ - g_free(bas->fragment); - bas->fragment = NULL; - val = uri_to_string(bas); - goto done; - } - - /* - * 2) If the path component is empty and the scheme, authority, and - * query components are undefined, then it is a reference to the - * current document and we are done. Otherwise, the reference URI's - * query and fragment components are defined as found (or not found) - * within the URI reference and not inherited from the base URI. - * - * NOTE that in modern browsers, the parsing differs from the above - * in the following aspect: the query component is allowed to be - * defined while still treating this as a reference to the current - * document. - */ - res = uri_new(); - if ((ref->scheme == NULL) && (ref->path == NULL) && - ((ref->authority == NULL) && (ref->server == NULL))) { - res->scheme = g_strdup(bas->scheme); - if (bas->authority != NULL) { - res->authority = g_strdup(bas->authority); - } else if (bas->server != NULL) { - res->server = g_strdup(bas->server); - res->user = g_strdup(bas->user); - res->port = bas->port; - } - res->path = g_strdup(bas->path); - if (ref->query != NULL) { - res->query = g_strdup(ref->query); - } else { - res->query = g_strdup(bas->query); - } - res->fragment = g_strdup(ref->fragment); - goto step_7; - } - - /* - * 3) If the scheme component is defined, indicating that the reference - * starts with a scheme name, then the reference is interpreted as an - * absolute URI and we are done. Otherwise, the reference URI's - * scheme is inherited from the base URI's scheme component. - */ - if (ref->scheme != NULL) { - val = uri_to_string(ref); - goto done; - } - res->scheme = g_strdup(bas->scheme); - - res->query = g_strdup(ref->query); - res->fragment = g_strdup(ref->fragment); - - /* - * 4) If the authority component is defined, then the reference is a - * network-path and we skip to step 7. Otherwise, the reference - * URI's authority is inherited from the base URI's authority - * component, which will also be undefined if the URI scheme does not - * use an authority component. - */ - if ((ref->authority != NULL) || (ref->server != NULL)) { - if (ref->authority != NULL) { - res->authority = g_strdup(ref->authority); - } else { - res->server = g_strdup(ref->server); - res->user = g_strdup(ref->user); - res->port = ref->port; - } - res->path = g_strdup(ref->path); - goto step_7; - } - if (bas->authority != NULL) { - res->authority = g_strdup(bas->authority); - } else if (bas->server != NULL) { - res->server = g_strdup(bas->server); - res->user = g_strdup(bas->user); - res->port = bas->port; - } - - /* - * 5) If the path component begins with a slash character ("/"), then - * the reference is an absolute-path and we skip to step 7. - */ - if ((ref->path != NULL) && (ref->path[0] == '/')) { - res->path = g_strdup(ref->path); - goto step_7; - } - - /* - * 6) If this step is reached, then we are resolving a relative-path - * reference. The relative path needs to be merged with the base - * URI's path. Although there are many ways to do this, we will - * describe a simple method using a separate string buffer. - * - * Allocate a buffer large enough for the result string. - */ - len = 2; /* extra / and 0 */ - if (ref->path != NULL) { - len += strlen(ref->path); - } - if (bas->path != NULL) { - len += strlen(bas->path); - } - res->path = g_malloc(len); - res->path[0] = 0; - - /* - * a) All but the last segment of the base URI's path component is - * copied to the buffer. In other words, any characters after the - * last (right-most) slash character, if any, are excluded. - */ - cur = 0; - out = 0; - if (bas->path != NULL) { - while (bas->path[cur] != 0) { - while ((bas->path[cur] != 0) && (bas->path[cur] != '/')) { - cur++; - } - if (bas->path[cur] == 0) { - break; - } - - cur++; - while (out < cur) { - res->path[out] = bas->path[out]; - out++; - } - } - } - res->path[out] = 0; - - /* - * b) The reference's path component is appended to the buffer - * string. - */ - if (ref->path != NULL && ref->path[0] != 0) { - indx = 0; - /* - * Ensure the path includes a '/' - */ - if ((out == 0) && (bas->server != NULL)) { - res->path[out++] = '/'; - } - while (ref->path[indx] != 0) { - res->path[out++] = ref->path[indx++]; - } - } - res->path[out] = 0; - - /* - * Steps c) to h) are really path normalization steps - */ - normalize_uri_path(res->path); - -step_7: - - /* - * 7) The resulting URI components, including any inherited from the - * base URI, are recombined to give the absolute form of the URI - * reference. - */ - val = uri_to_string(res); - -done: - uri_free(ref); - uri_free(bas); - uri_free(res); - return val; -} - -/** - * uri_resolve_relative: - * @URI: the URI reference under consideration - * @base: the base value - * - * Expresses the URI of the reference in terms relative to the - * base. Some examples of this operation include: - * base = "http://site1.com/docs/book1.html" - * URI input URI returned - * docs/pic1.gif pic1.gif - * docs/img/pic1.gif img/pic1.gif - * img/pic1.gif ../img/pic1.gif - * http://site1.com/docs/pic1.gif pic1.gif - * http://site2.com/docs/pic1.gif http://site2.com/docs/pic1.gif - * - * base = "docs/book1.html" - * URI input URI returned - * docs/pic1.gif pic1.gif - * docs/img/pic1.gif img/pic1.gif - * img/pic1.gif ../img/pic1.gif - * http://site1.com/docs/pic1.gif http://site1.com/docs/pic1.gif - * - * - * Note: if the URI reference is really weird or complicated, it may be - * worthwhile to first convert it into a "nice" one by calling - * uri_resolve (using 'base') before calling this routine, - * since this routine (for reasonable efficiency) assumes URI has - * already been through some validation. - * - * Returns a new URI string (to be freed by the caller) or NULL in case - * error. - */ -char *uri_resolve_relative(const char *uri, const char *base) -{ - char *val = NULL; - int ret; - int ix; - int pos = 0; - int nbslash = 0; - int len; - URI *ref = NULL; - URI *bas = NULL; - char *bptr, *uptr, *vptr; - int remove_path = 0; - - if ((uri == NULL) || (*uri == 0)) { - return NULL; - } - - /* - * First parse URI into a standard form - */ - ref = uri_new(); - /* If URI not already in "relative" form */ - if (uri[0] != '.') { - ret = uri_parse_into(ref, uri); - if (ret != 0) { - goto done; /* Error in URI, return NULL */ - } - } else { - ref->path = g_strdup(uri); - } - - /* - * Next parse base into the same standard form - */ - if ((base == NULL) || (*base == 0)) { - val = g_strdup(uri); - goto done; - } - bas = uri_new(); - if (base[0] != '.') { - ret = uri_parse_into(bas, base); - if (ret != 0) { - goto done; /* Error in base, return NULL */ - } - } else { - bas->path = g_strdup(base); - } - - /* - * If the scheme / server on the URI differs from the base, - * just return the URI - */ - if ((ref->scheme != NULL) && - ((bas->scheme == NULL) || (strcmp(bas->scheme, ref->scheme)) || - (strcmp(bas->server, ref->server)))) { - val = g_strdup(uri); - goto done; - } - if (bas->path == ref->path || - (bas->path && ref->path && !strcmp(bas->path, ref->path))) { - val = g_strdup(""); - goto done; - } - if (bas->path == NULL) { - val = g_strdup(ref->path); - goto done; - } - if (ref->path == NULL) { - ref->path = (char *)"/"; - remove_path = 1; - } - - /* - * At this point (at last!) we can compare the two paths - * - * First we take care of the special case where either of the - * two path components may be missing (bug 316224) - */ - if (bas->path == NULL) { - if (ref->path != NULL) { - uptr = ref->path; - if (*uptr == '/') { - uptr++; - } - /* exception characters from uri_to_string */ - val = uri_string_escape(uptr, "/;&=+$,"); - } - goto done; - } - bptr = bas->path; - if (ref->path == NULL) { - for (ix = 0; bptr[ix] != 0; ix++) { - if (bptr[ix] == '/') { - nbslash++; - } - } - uptr = NULL; - len = 1; /* this is for a string terminator only */ - } else { - /* - * Next we compare the two strings and find where they first differ - */ - if ((ref->path[pos] == '.') && (ref->path[pos + 1] == '/')) { - pos += 2; - } - if ((*bptr == '.') && (bptr[1] == '/')) { - bptr += 2; - } else if ((*bptr == '/') && (ref->path[pos] != '/')) { - bptr++; - } - while ((bptr[pos] == ref->path[pos]) && (bptr[pos] != 0)) { - pos++; - } - - if (bptr[pos] == ref->path[pos]) { - val = g_strdup(""); - goto done; /* (I can't imagine why anyone would do this) */ - } - - /* - * In URI, "back up" to the last '/' encountered. This will be the - * beginning of the "unique" suffix of URI - */ - ix = pos; - if ((ref->path[ix] == '/') && (ix > 0)) { - ix--; - } else if ((ref->path[ix] == 0) && (ix > 1) - && (ref->path[ix - 1] == '/')) { - ix -= 2; - } - for (; ix > 0; ix--) { - if (ref->path[ix] == '/') { - break; - } - } - if (ix == 0) { - uptr = ref->path; - } else { - ix++; - uptr = &ref->path[ix]; - } - - /* - * In base, count the number of '/' from the differing point - */ - if (bptr[pos] != ref->path[pos]) { /* check for trivial URI == base */ - for (; bptr[ix] != 0; ix++) { - if (bptr[ix] == '/') { - nbslash++; - } - } - } - len = strlen(uptr) + 1; - } - - if (nbslash == 0) { - if (uptr != NULL) { - /* exception characters from uri_to_string */ - val = uri_string_escape(uptr, "/;&=+$,"); - } - goto done; - } - - /* - * Allocate just enough space for the returned string - - * length of the remainder of the URI, plus enough space - * for the "../" groups, plus one for the terminator - */ - val = g_malloc(len + 3 * nbslash); - vptr = val; - /* - * Put in as many "../" as needed - */ - for (; nbslash > 0; nbslash--) { - *vptr++ = '.'; - *vptr++ = '.'; - *vptr++ = '/'; - } - /* - * Finish up with the end of the URI - */ - if (uptr != NULL) { - if ((vptr > val) && (len > 0) && (uptr[0] == '/') && - (vptr[-1] == '/')) { - memcpy(vptr, uptr + 1, len - 1); - vptr[len - 2] = 0; - } else { - memcpy(vptr, uptr, len); - vptr[len - 1] = 0; - } - } else { - vptr[len - 1] = 0; - } - - /* escape the freshly-built path */ - vptr = val; - /* exception characters from uri_to_string */ - val = uri_string_escape(vptr, "/;&=+$,"); - g_free(vptr); - -done: - /* - * Free the working variables - */ - if (remove_path != 0) { - ref->path = NULL; - } - uri_free(ref); - uri_free(bas); - - return val; -} - /* * Utility functions to help parse and assemble query strings. */ @@ -2274,14 +1427,14 @@ struct QueryParams *query_params_parse(const char *query) * and consistent with CGI.pm we assume value is "". */ else if (!eq) { - name = uri_string_unescape(query, end - query, NULL); + name = g_uri_unescape_segment(query, end, NULL); value = NULL; } /* Or if we have "name=" here (works around annoying * problem when calling uri_string_unescape with len = 0). */ else if (eq + 1 == end) { - name = uri_string_unescape(query, eq - query, NULL); + name = g_uri_unescape_segment(query, eq, NULL); value = g_new0(char, 1); } /* If the '=' character is at the beginning then we have @@ -2293,8 +1446,8 @@ struct QueryParams *query_params_parse(const char *query) /* Otherwise it's "name=value". */ else { - name = uri_string_unescape(query, eq - query, NULL); - value = uri_string_unescape(eq + 1, end - (eq + 1), NULL); + name = g_uri_unescape_segment(query, eq, NULL); + value = g_uri_unescape_segment(eq + 1, end, NULL); } /* Append to the parameter set. */ |