#include "string-list.h"
/*
- * Make sure "ref" is something reasonable to have under ".git/refs/";
- * We do not like it if:
+ * How to handle various characters in refnames:
+ * This table is used by both the SIMD and non-SIMD code. It has
+ * some cases that are only useful for the SIMD; these are handled
+ * equivalently to the listed disposition in the non-SIMD code.
+ * 0: An acceptable character for refs
+ * 1: @, look for a following { to reject @{ in refs (SIMD or = 0)
+ * 2: \0: End-of-component and string
+ * 3: /: End-of-component (SIMD or = 2)
+ * 4: ., look for a preceding . to reject .. in refs
+ * 5: {, look for a preceding @ to reject @{ in refs
+ * 6: *, usually a bad character except, once as a wildcard (SIMD or = 7)
+ * 7: A bad character except * (see check_refname_component below)
+ */
+static unsigned char refname_disposition[256] = {
+ 2, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+ 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+ 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0, 0, 0, 4, 3,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 7,
+ 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 7, 0, 7, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, 0, 7, 7
+};
+
+/*
+ * Try to read one refname component from the front of refname.
+ * Return the length of the component found, or -1 if the component is
+ * not legal. It is legal if it is something reasonable to have under
+ * ".git/refs/"; We do not like it if:
*
* - any path component of it begins with ".", or
* - it has double dots "..", or
* - it has ASCII control character, "~", "^", ":" or SP, anywhere, or
- * - it ends with a "/".
- * - it ends with ".lock"
+ * - it has pattern-matching notation "*", "?", "[", anywhere, or
+ * - it ends with a "/", or
+ * - it ends with ".lock", or
* - it contains a "\" (backslash)
*/
-
-/* Return true iff ch is not allowed in reference names. */
-static inline int bad_ref_char(int ch)
-{
- if (((unsigned) ch) <= ' ' || ch == 0x7f ||
- ch == '~' || ch == '^' || ch == ':' || ch == '\\')
- return 1;
- /* 2.13 Pattern Matching Notation */
- if (ch == '*' || ch == '?' || ch == '[') /* Unsupported */
- return 1;
- return 0;
-}
-
-/*
- * Try to read one refname component from the front of refname. Return
- * the length of the component found, or -1 if the component is not
- * legal.
- */
static int check_refname_component(const char *refname, int flags)
{
const char *cp;
char last = '\0';
for (cp = refname; ; cp++) {
- char ch = *cp;
- if (ch == '\0' || ch == '/')
+ int ch = *cp & 255;
+ unsigned char disp = refname_disposition[ch];
+ switch (disp) {
+ case 2: /* fall-through */
+ case 3:
+ goto out;
+ case 4:
+ if (last == '.')
+ return -1; /* Refname contains "..". */
+ break;
+ case 5:
+ if (last == '@')
+ return -1; /* Refname contains "@{". */
break;
- if (bad_ref_char(ch))
- return -1; /* Illegal character in refname. */
- if (last == '.' && ch == '.')
- return -1; /* Refname contains "..". */
- if (last == '@' && ch == '{')
- return -1; /* Refname contains "@{". */
+ case 6: /* fall-through */
+ case 7:
+ return -1;
+ }
last = ch;
}
+out:
if (cp == refname)
return 0; /* Component has zero length. */
if (refname[0] == '.') {
return cp - refname;
}
-int check_refname_format(const char *refname, int flags)
+static int check_refname_format_bytewise(const char *refname, int flags)
{
int component_len, component_count = 0;
return 0;
}
+#if defined(__GNUC__) && defined(__x86_64__)
+#define SSE_VECTOR_BYTES 16
+
+/* Vectorized version of check_refname_format. */
+int check_refname_format(const char *refname, int flags)
+{
+ const char *cp = refname;
+
+ const __m128i dot = _mm_set1_epi8('.');
+ const __m128i at = _mm_set1_epi8('@');
+ const __m128i curly = _mm_set1_epi8('{');
+ const __m128i slash = _mm_set1_epi8('/');
+ const __m128i zero = _mm_set1_epi8('\000');
+ const __m128i el = _mm_set1_epi8('l');
+
+ /* below '*', all characters are forbidden or rare */
+ const __m128i star_ub = _mm_set1_epi8('*' + 1);
+
+ const __m128i colon = _mm_set1_epi8(':');
+ const __m128i question = _mm_set1_epi8('?');
+
+ /* '['..'^' contains 4 characters: 3 forbidden and 1 rare */
+ const __m128i bracket_lb = _mm_set1_epi8('[' - 1);
+ const __m128i caret_ub = _mm_set1_epi8('^' + 1);
+
+ /* '~' and above are forbidden */
+ const __m128i tilde_lb = _mm_set1_epi8('~' - 1);
+
+ int component_count = 0;
+ int orig_flags = flags;
+
+ if (refname[0] == 0 || refname[0] == '/') {
+ /* entirely empty ref or initial ref component */
+ return -1;
+ }
+
+ /*
+ * Initial ref component of '.'; below we look for /. so we'll
+ * miss this.
+ */
+ if (refname[0] == '.') {
+ if (refname[1] == '/' || refname[1] == '\0')
+ return -1;
+ if (!(flags & REFNAME_DOT_COMPONENT))
+ return -1;
+ }
+ while(1) {
+ __m128i tmp, tmp1, result;
+ uint64_t mask;
+
+ if ((uintptr_t) cp % PAGE_SIZE > PAGE_SIZE - SSE_VECTOR_BYTES - 1)
+ /*
+ * End-of-page; fall back to slow method for
+ * this entire ref.
+ */
+ return check_refname_format_bytewise(refname, orig_flags);
+
+ tmp = _mm_loadu_si128((__m128i *)cp);
+ tmp1 = _mm_loadu_si128((__m128i *)(cp + 1));
+
+ /*
+ * This range (note the lt) contains some
+ * permissible-but-rare characters (including all
+ * characters >= 128), which we handle later. It also
+ * includes \000.
+ */
+ result = _mm_cmplt_epi8(tmp, star_ub);
+
+ result = _mm_or_si128(result, _mm_cmpeq_epi8(tmp, question));
+ result = _mm_or_si128(result, _mm_cmpeq_epi8(tmp, colon));
+
+ /* This range contains the permissible ] as bycatch */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpgt_epi8(tmp, bracket_lb),
+ _mm_cmplt_epi8(tmp, caret_ub)));
+
+ result = _mm_or_si128(result, _mm_cmpgt_epi8(tmp, tilde_lb));
+
+ /* .. */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpeq_epi8(tmp, dot),
+ _mm_cmpeq_epi8(tmp1, dot)));
+ /* @{ */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpeq_epi8(tmp, at),
+ _mm_cmpeq_epi8(tmp1, curly)));
+ /* // */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpeq_epi8(tmp, slash),
+ _mm_cmpeq_epi8(tmp1, slash)));
+ /* trailing / */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpeq_epi8(tmp, slash),
+ _mm_cmpeq_epi8(tmp1, zero)));
+ /* .l, beginning of .lock */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpeq_epi8(tmp, dot),
+ _mm_cmpeq_epi8(tmp1, el)));
+ /*
+ * Even though /. is not necessarily an error, we flag
+ * it anyway. If we find it, we'll check if it's valid
+ * and if so we'll advance just past it.
+ */
+ result = _mm_or_si128(result, _mm_and_si128(
+ _mm_cmpeq_epi8(tmp, slash),
+ _mm_cmpeq_epi8(tmp1, dot)));
+
+ mask = _mm_movemask_epi8(result);
+ if (mask) {
+ /*
+ * We've found either end-of-string, or some
+ * probably-bad character or substring.
+ */
+ int i = __builtin_ctz(mask);
+ switch (refname_disposition[cp[i] & 255]) {
+ case 0: /* fall-through */
+ case 5:
+ /*
+ * bycatch: a good character that's in
+ * one of the ranges of mostly-forbidden
+ * characters
+ */
+ cp += i + 1;
+ break;
+ case 1:
+ if (cp[i + 1] == '{')
+ return -1;
+ cp += i + 1;
+ break;
+ case 2:
+ if (!(flags & REFNAME_ALLOW_ONELEVEL)
+ && !component_count && !strchr(refname, '/'))
+ /* Refname has only one component. */
+ return -1;
+ return 0;
+ case 3:
+ component_count ++;
+ /*
+ * Even if leading dots are allowed, don't
+ * allow "." as a component (".." is
+ * prevented by case 4 below).
+ */
+ if (cp[i + 1] == '.') {
+ if (cp[i + 2] == '\0')
+ return -1;
+ if (flags & REFNAME_DOT_COMPONENT) {
+ /* skip to just after the /. */
+ cp += i + 2;
+ break;
+ }
+ return -1;
+ } else if (cp[i + 1] == '/' || cp[i + 1] == '\0')
+ return -1;
+ break;
+ case 4:
+ if (cp[i + 1] == '.' || cp[i + 1] == '\0')
+ return -1;
+ /* .lock as end-of-component or end-of-string */
+ if ((!strncmp(cp + i, ".lock", 5))
+ && (cp[i + 5] == '/' || cp[i + 5] == 0))
+ return -1;
+ cp += 1;
+ break;
+ case 6:
+ if (((cp == refname + i) || cp[i - 1] == '/')
+ && (cp[i + 1] == '/' || cp[i + 1] == 0))
+ if (flags & REFNAME_REFSPEC_PATTERN) {
+ flags &= ~REFNAME_REFSPEC_PATTERN;
+ /* restart after the * */
+ cp += i + 1;
+ continue;
+ }
+ /* fall-through */
+ case 7:
+ return -1;
+ }
+ } else
+ cp += SSE_VECTOR_BYTES;
+ }
+}
+
+#else
+
+int check_refname_format (const char *refname, int flags)
+{
+ return check_refname_format_bytewise(refname, flags);
+}
+
+#endif
+
struct ref_entry;
/*
if (!lock) {
const char *str = "Cannot lock the ref '%s'.";
switch (onerr) {
- case MSG_ON_ERR: error(str, refname); break;
- case DIE_ON_ERR: die(str, refname); break;
- case QUIET_ON_ERR: break;
+ case UPDATE_REFS_MSG_ON_ERR: error(str, refname); break;
+ case UPDATE_REFS_DIE_ON_ERR: die(str, refname); break;
+ case UPDATE_REFS_QUIET_ON_ERR: break;
}
}
return lock;
if (write_ref_sha1(lock, sha1, action) < 0) {
const char *str = "Cannot update the ref '%s'.";
switch (onerr) {
- case MSG_ON_ERR: error(str, refname); break;
- case DIE_ON_ERR: die(str, refname); break;
- case QUIET_ON_ERR: break;
+ case UPDATE_REFS_MSG_ON_ERR: error(str, refname); break;
+ case UPDATE_REFS_DIE_ON_ERR: die(str, refname); break;
+ case UPDATE_REFS_QUIET_ON_ERR: break;
}
return 1;
}
return 0;
}
+/**
+ * Information needed for a single ref update. Set new_sha1 to the
+ * new value or to zero to delete the ref. To check the old value
+ * while locking the ref, set have_old to 1 and set old_sha1 to the
+ * value or to zero to ensure the ref does not exist before update.
+ */
+struct ref_update {
+ unsigned char new_sha1[20];
+ unsigned char old_sha1[20];
+ int flags; /* REF_NODEREF? */
+ int have_old; /* 1 if old_sha1 is valid, 0 otherwise */
+ struct ref_lock *lock;
+ int type;
+ const char refname[FLEX_ARRAY];
+};
+
+/*
+ * Data structure for holding a reference transaction, which can
+ * consist of checks and updates to multiple references, carried out
+ * as atomically as possible. This structure is opaque to callers.
+ */
+struct ref_transaction {
+ struct ref_update **updates;
+ size_t alloc;
+ size_t nr;
+};
+
+struct ref_transaction *ref_transaction_begin(void)
+{
+ return xcalloc(1, sizeof(struct ref_transaction));
+}
+
+static void ref_transaction_free(struct ref_transaction *transaction)
+{
+ int i;
+
+ for (i = 0; i < transaction->nr; i++)
+ free(transaction->updates[i]);
+
+ free(transaction->updates);
+ free(transaction);
+}
+
+void ref_transaction_rollback(struct ref_transaction *transaction)
+{
+ ref_transaction_free(transaction);
+}
+
+static struct ref_update *add_update(struct ref_transaction *transaction,
+ const char *refname)
+{
+ size_t len = strlen(refname);
+ struct ref_update *update = xcalloc(1, sizeof(*update) + len + 1);
+
+ strcpy((char *)update->refname, refname);
+ ALLOC_GROW(transaction->updates, transaction->nr + 1, transaction->alloc);
+ transaction->updates[transaction->nr++] = update;
+ return update;
+}
+
+void ref_transaction_update(struct ref_transaction *transaction,
+ const char *refname,
+ unsigned char *new_sha1, unsigned char *old_sha1,
+ int flags, int have_old)
+{
+ struct ref_update *update = add_update(transaction, refname);
+
+ hashcpy(update->new_sha1, new_sha1);
+ update->flags = flags;
+ update->have_old = have_old;
+ if (have_old)
+ hashcpy(update->old_sha1, old_sha1);
+}
+
+void ref_transaction_create(struct ref_transaction *transaction,
+ const char *refname,
+ unsigned char *new_sha1,
+ int flags)
+{
+ struct ref_update *update = add_update(transaction, refname);
+
+ assert(!is_null_sha1(new_sha1));
+ hashcpy(update->new_sha1, new_sha1);
+ hashclr(update->old_sha1);
+ update->flags = flags;
+ update->have_old = 1;
+}
+
+void ref_transaction_delete(struct ref_transaction *transaction,
+ const char *refname,
+ unsigned char *old_sha1,
+ int flags, int have_old)
+{
+ struct ref_update *update = add_update(transaction, refname);
+
+ update->flags = flags;
+ update->have_old = have_old;
+ if (have_old) {
+ assert(!is_null_sha1(old_sha1));
+ hashcpy(update->old_sha1, old_sha1);
+ }
+}
+
int update_ref(const char *action, const char *refname,
const unsigned char *sha1, const unsigned char *oldval,
int flags, enum action_on_err onerr)
{
const struct ref_update * const *u1 = r1;
const struct ref_update * const *u2 = r2;
- return strcmp((*u1)->ref_name, (*u2)->ref_name);
+ return strcmp((*u1)->refname, (*u2)->refname);
}
static int ref_update_reject_duplicates(struct ref_update **updates, int n,
{
int i;
for (i = 1; i < n; i++)
- if (!strcmp(updates[i - 1]->ref_name, updates[i]->ref_name)) {
+ if (!strcmp(updates[i - 1]->refname, updates[i]->refname)) {
const char *str =
"Multiple updates for ref '%s' not allowed.";
switch (onerr) {
- case MSG_ON_ERR:
- error(str, updates[i]->ref_name); break;
- case DIE_ON_ERR:
- die(str, updates[i]->ref_name); break;
- case QUIET_ON_ERR:
+ case UPDATE_REFS_MSG_ON_ERR:
+ error(str, updates[i]->refname); break;
+ case UPDATE_REFS_DIE_ON_ERR:
+ die(str, updates[i]->refname); break;
+ case UPDATE_REFS_QUIET_ON_ERR:
break;
}
return 1;
return 0;
}
-int update_refs(const char *action, const struct ref_update **updates_orig,
- int n, enum action_on_err onerr)
+int ref_transaction_commit(struct ref_transaction *transaction,
+ const char *msg, enum action_on_err onerr)
{
int ret = 0, delnum = 0, i;
- struct ref_update **updates;
- int *types;
- struct ref_lock **locks;
const char **delnames;
+ int n = transaction->nr;
+ struct ref_update **updates = transaction->updates;
- if (!updates_orig || !n)
+ if (!n)
return 0;
/* Allocate work space */
- updates = xmalloc(sizeof(*updates) * n);
- types = xmalloc(sizeof(*types) * n);
- locks = xcalloc(n, sizeof(*locks));
delnames = xmalloc(sizeof(*delnames) * n);
/* Copy, sort, and reject duplicate refs */
- memcpy(updates, updates_orig, sizeof(*updates) * n);
qsort(updates, n, sizeof(*updates), ref_update_compare);
ret = ref_update_reject_duplicates(updates, n, onerr);
if (ret)
/* Acquire all locks while verifying old values */
for (i = 0; i < n; i++) {
- locks[i] = update_ref_lock(updates[i]->ref_name,
- (updates[i]->have_old ?
- updates[i]->old_sha1 : NULL),
- updates[i]->flags,
- &types[i], onerr);
- if (!locks[i]) {
+ struct ref_update *update = updates[i];
+
+ update->lock = update_ref_lock(update->refname,
+ (update->have_old ?
+ update->old_sha1 : NULL),
+ update->flags,
+ &update->type, onerr);
+ if (!update->lock) {
ret = 1;
goto cleanup;
}
}
/* Perform updates first so live commits remain referenced */
- for (i = 0; i < n; i++)
- if (!is_null_sha1(updates[i]->new_sha1)) {
- ret = update_ref_write(action,
- updates[i]->ref_name,
- updates[i]->new_sha1,
- locks[i], onerr);
- locks[i] = NULL; /* freed by update_ref_write */
+ for (i = 0; i < n; i++) {
+ struct ref_update *update = updates[i];
+
+ if (!is_null_sha1(update->new_sha1)) {
+ ret = update_ref_write(msg,
+ update->refname,
+ update->new_sha1,
+ update->lock, onerr);
+ update->lock = NULL; /* freed by update_ref_write */
if (ret)
goto cleanup;
}
+ }
/* Perform deletes now that updates are safely completed */
- for (i = 0; i < n; i++)
- if (locks[i]) {
- delnames[delnum++] = locks[i]->ref_name;
- ret |= delete_ref_loose(locks[i], types[i]);
+ for (i = 0; i < n; i++) {
+ struct ref_update *update = updates[i];
+
+ if (update->lock) {
+ delnames[delnum++] = update->lock->ref_name;
+ ret |= delete_ref_loose(update->lock, update->type);
}
+ }
+
ret |= repack_without_refs(delnames, delnum);
for (i = 0; i < delnum; i++)
unlink_or_warn(git_path("logs/%s", delnames[i]));
cleanup:
for (i = 0; i < n; i++)
- if (locks[i])
- unlock_ref(locks[i]);
- free(updates);
- free(types);
- free(locks);
+ if (updates[i]->lock)
+ unlock_ref(updates[i]->lock);
free(delnames);
+ ref_transaction_free(transaction);
return ret;
}