#include "qapi/error.h"
#include "qemu/error-report.h"
#include "qemu/iov.h"
+#include "qemu/main-loop.h"
#include "qemu/sockets.h"
#include "virtio-9p.h"
#include "fsdev/qemu-fsdev.h"
#include "trace.h"
#include "migration/blocker.h"
#include "sysemu/qtest.h"
+#include "qemu/xxhash.h"
+#include <math.h>
+#include <linux/limits.h>
int open_fd_hw;
int total_open_fd;
f->next = s->fid_list;
s->fid_list = f;
- v9fs_readdir_init(&f->fs.dir);
- v9fs_readdir_init(&f->fs_reclaim.dir);
+ v9fs_readdir_init(s->proto_version, &f->fs.dir);
+ v9fs_readdir_init(s->proto_version, &f->fs_reclaim.dir);
return f;
}
P9_STAT_MODE_NAMED_PIPE | \
P9_STAT_MODE_SOCKET)
-/* This is the algorithm from ufs in spfs */
-static void stat_to_qid(const struct stat *stbuf, V9fsQID *qidp)
+/* Mirrors all bits of a byte. So e.g. binary 10100000 would become 00000101. */
+static inline uint8_t mirror8bit(uint8_t byte)
{
+ return (byte * 0x0202020202ULL & 0x010884422010ULL) % 1023;
+}
+
+/* Same as mirror8bit() just for a 64 bit data type instead for a byte. */
+static inline uint64_t mirror64bit(uint64_t value)
+{
+ return ((uint64_t)mirror8bit(value & 0xff) << 56) |
+ ((uint64_t)mirror8bit((value >> 8) & 0xff) << 48) |
+ ((uint64_t)mirror8bit((value >> 16) & 0xff) << 40) |
+ ((uint64_t)mirror8bit((value >> 24) & 0xff) << 32) |
+ ((uint64_t)mirror8bit((value >> 32) & 0xff) << 24) |
+ ((uint64_t)mirror8bit((value >> 40) & 0xff) << 16) |
+ ((uint64_t)mirror8bit((value >> 48) & 0xff) << 8) |
+ ((uint64_t)mirror8bit((value >> 56) & 0xff));
+}
+
+/**
+ * @brief Parameter k for the Exponential Golomb algorihm to be used.
+ *
+ * The smaller this value, the smaller the minimum bit count for the Exp.
+ * Golomb generated affixes will be (at lowest index) however for the
+ * price of having higher maximum bit count of generated affixes (at highest
+ * index). Likewise increasing this parameter yields in smaller maximum bit
+ * count for the price of having higher minimum bit count.
+ *
+ * In practice that means: a good value for k depends on the expected amount
+ * of devices to be exposed by one export. For a small amount of devices k
+ * should be small, for a large amount of devices k might be increased
+ * instead. The default of k=0 should be fine for most users though.
+ *
+ * @b IMPORTANT: In case this ever becomes a runtime parameter; the value of
+ * k should not change as long as guest is still running! Because that would
+ * cause completely different inode numbers to be generated on guest.
+ */
+#define EXP_GOLOMB_K 0
+
+/**
+ * @brief Exponential Golomb algorithm for arbitrary k (including k=0).
+ *
+ * The Exponential Golomb algorithm generates @b prefixes (@b not suffixes!)
+ * with growing length and with the mathematical property of being
+ * "prefix-free". The latter means the generated prefixes can be prepended
+ * in front of arbitrary numbers and the resulting concatenated numbers are
+ * guaranteed to be always unique.
+ *
+ * This is a minor adjustment to the original Exp. Golomb algorithm in the
+ * sense that lowest allowed index (@param n) starts with 1, not with zero.
+ *
+ * @param n - natural number (or index) of the prefix to be generated
+ * (1, 2, 3, ...)
+ * @param k - parameter k of Exp. Golomb algorithm to be used
+ * (see comment on EXP_GOLOMB_K macro for details about k)
+ */
+static VariLenAffix expGolombEncode(uint64_t n, int k)
+{
+ const uint64_t value = n + (1 << k) - 1;
+ const int bits = (int) log2(value) + 1;
+ return (VariLenAffix) {
+ .type = AffixType_Prefix,
+ .value = value,
+ .bits = bits + MAX((bits - 1 - k), 0)
+ };
+}
+
+/**
+ * @brief Converts a suffix into a prefix, or a prefix into a suffix.
+ *
+ * Simply mirror all bits of the affix value, for the purpose to preserve
+ * respectively the mathematical "prefix-free" or "suffix-free" property
+ * after the conversion.
+ *
+ * If a passed prefix is suitable to create unique numbers, then the
+ * returned suffix is suitable to create unique numbers as well (and vice
+ * versa).
+ */
+static VariLenAffix invertAffix(const VariLenAffix *affix)
+{
+ return (VariLenAffix) {
+ .type =
+ (affix->type == AffixType_Suffix) ?
+ AffixType_Prefix : AffixType_Suffix,
+ .value =
+ mirror64bit(affix->value) >>
+ ((sizeof(affix->value) * 8) - affix->bits),
+ .bits = affix->bits
+ };
+}
+
+/**
+ * @brief Generates suffix numbers with "suffix-free" property.
+ *
+ * This is just a wrapper function on top of the Exp. Golomb algorithm.
+ *
+ * Since the Exp. Golomb algorithm generates prefixes, but we need suffixes,
+ * this function converts the Exp. Golomb prefixes into appropriate suffixes
+ * which are still suitable for generating unique numbers.
+ *
+ * @param n - natural number (or index) of the suffix to be generated
+ * (1, 2, 3, ...)
+ */
+static VariLenAffix affixForIndex(uint64_t index)
+{
+ VariLenAffix prefix;
+ prefix = expGolombEncode(index, EXP_GOLOMB_K);
+ return invertAffix(&prefix); /* convert prefix to suffix */
+}
+
+/* creative abuse of tb_hash_func7, which is based on xxhash */
+static uint32_t qpp_hash(QppEntry e)
+{
+ return qemu_xxhash7(e.ino_prefix, e.dev, 0, 0, 0);
+}
+
+static uint32_t qpf_hash(QpfEntry e)
+{
+ return qemu_xxhash7(e.ino, e.dev, 0, 0, 0);
+}
+
+static bool qpd_cmp_func(const void *obj, const void *userp)
+{
+ const QpdEntry *e1 = obj, *e2 = userp;
+ return e1->dev == e2->dev;
+}
+
+static bool qpp_cmp_func(const void *obj, const void *userp)
+{
+ const QppEntry *e1 = obj, *e2 = userp;
+ return e1->dev == e2->dev && e1->ino_prefix == e2->ino_prefix;
+}
+
+static bool qpf_cmp_func(const void *obj, const void *userp)
+{
+ const QpfEntry *e1 = obj, *e2 = userp;
+ return e1->dev == e2->dev && e1->ino == e2->ino;
+}
+
+static void qp_table_remove(void *p, uint32_t h, void *up)
+{
+ g_free(p);
+}
+
+static void qp_table_destroy(struct qht *ht)
+{
+ if (!ht || !ht->map) {
+ return;
+ }
+ qht_iter(ht, qp_table_remove, NULL);
+ qht_destroy(ht);
+}
+
+static void qpd_table_init(struct qht *ht)
+{
+ qht_init(ht, qpd_cmp_func, 1, QHT_MODE_AUTO_RESIZE);
+}
+
+static void qpp_table_init(struct qht *ht)
+{
+ qht_init(ht, qpp_cmp_func, 1, QHT_MODE_AUTO_RESIZE);
+}
+
+static void qpf_table_init(struct qht *ht)
+{
+ qht_init(ht, qpf_cmp_func, 1 << 16, QHT_MODE_AUTO_RESIZE);
+}
+
+/*
+ * Returns how many (high end) bits of inode numbers of the passed fs
+ * device shall be used (in combination with the device number) to
+ * generate hash values for qpp_table entries.
+ *
+ * This function is required if variable length suffixes are used for inode
+ * number mapping on guest level. Since a device may end up having multiple
+ * entries in qpp_table, each entry most probably with a different suffix
+ * length, we thus need this function in conjunction with qpd_table to
+ * "agree" about a fix amount of bits (per device) to be always used for
+ * generating hash values for the purpose of accessing qpp_table in order
+ * get consistent behaviour when accessing qpp_table.
+ */
+static int qid_inode_prefix_hash_bits(V9fsPDU *pdu, dev_t dev)
+{
+ QpdEntry lookup = {
+ .dev = dev
+ }, *val;
+ uint32_t hash = dev;
+ VariLenAffix affix;
+
+ val = qht_lookup(&pdu->s->qpd_table, &lookup, hash);
+ if (!val) {
+ val = g_malloc0(sizeof(QpdEntry));
+ *val = lookup;
+ affix = affixForIndex(pdu->s->qp_affix_next);
+ val->prefix_bits = affix.bits;
+ qht_insert(&pdu->s->qpd_table, val, hash, NULL);
+ pdu->s->qp_ndevices++;
+ }
+ return val->prefix_bits;
+}
+
+/**
+ * @brief Slow / full mapping host inode nr -> guest inode nr.
+ *
+ * This function performs a slower and much more costly remapping of an
+ * original file inode number on host to an appropriate different inode
+ * number on guest. For every (dev, inode) combination on host a new
+ * sequential number is generated, cached and exposed as inode number on
+ * guest.
+ *
+ * This is just a "last resort" fallback solution if the much faster/cheaper
+ * qid_path_suffixmap() failed. In practice this slow / full mapping is not
+ * expected ever to be used at all though.
+ *
+ * @see qid_path_suffixmap() for details
+ *
+ */
+static int qid_path_fullmap(V9fsPDU *pdu, const struct stat *stbuf,
+ uint64_t *path)
+{
+ QpfEntry lookup = {
+ .dev = stbuf->st_dev,
+ .ino = stbuf->st_ino
+ }, *val;
+ uint32_t hash = qpf_hash(lookup);
+ VariLenAffix affix;
+
+ val = qht_lookup(&pdu->s->qpf_table, &lookup, hash);
+
+ if (!val) {
+ if (pdu->s->qp_fullpath_next == 0) {
+ /* no more files can be mapped :'( */
+ error_report_once(
+ "9p: No more prefixes available for remapping inodes from "
+ "host to guest."
+ );
+ return -ENFILE;
+ }
+
+ val = g_malloc0(sizeof(QppEntry));
+ *val = lookup;
+
+ /* new unique inode and device combo */
+ affix = affixForIndex(
+ 1ULL << (sizeof(pdu->s->qp_affix_next) * 8)
+ );
+ val->path = (pdu->s->qp_fullpath_next++ << affix.bits) | affix.value;
+ pdu->s->qp_fullpath_next &= ((1ULL << (64 - affix.bits)) - 1);
+ qht_insert(&pdu->s->qpf_table, val, hash, NULL);
+ }
+
+ *path = val->path;
+ return 0;
+}
+
+/**
+ * @brief Quick mapping host inode nr -> guest inode nr.
+ *
+ * This function performs quick remapping of an original file inode number
+ * on host to an appropriate different inode number on guest. This remapping
+ * of inodes is required to avoid inode nr collisions on guest which would
+ * happen if the 9p export contains more than 1 exported file system (or
+ * more than 1 file system data set), because unlike on host level where the
+ * files would have different device nrs, all files exported by 9p would
+ * share the same device nr on guest (the device nr of the virtual 9p device
+ * that is).
+ *
+ * Inode remapping is performed by chopping off high end bits of the original
+ * inode number from host, shifting the result upwards and then assigning a
+ * generated suffix number for the low end bits, where the same suffix number
+ * will be shared by all inodes with the same device id AND the same high end
+ * bits that have been chopped off. That approach utilizes the fact that inode
+ * numbers very likely share the same high end bits (i.e. due to their common
+ * sequential generation by file systems) and hence we only have to generate
+ * and track a very limited amount of suffixes in practice due to that.
+ *
+ * We generate variable size suffixes for that purpose. The 1st generated
+ * suffix will only have 1 bit and hence we only need to chop off 1 bit from
+ * the original inode number. The subsequent suffixes being generated will
+ * grow in (bit) size subsequently, i.e. the 2nd and 3rd suffix being
+ * generated will have 3 bits and hence we have to chop off 3 bits from their
+ * original inodes, and so on. That approach of using variable length suffixes
+ * (i.e. over fixed size ones) utilizes the fact that in practice only a very
+ * limited amount of devices are shared by the same export (e.g. typically
+ * less than 2 dozen devices per 9p export), so in practice we need to chop
+ * off less bits than with fixed size prefixes and yet are flexible to add
+ * new devices at runtime below host's export directory at any time without
+ * having to reboot guest nor requiring to reconfigure guest for that. And due
+ * to the very limited amount of original high end bits that we chop off that
+ * way, the total amount of suffixes we need to generate is less than by using
+ * fixed size prefixes and hence it also improves performance of the inode
+ * remapping algorithm, and finally has the nice side effect that the inode
+ * numbers on guest will be much smaller & human friendly. ;-)
+ */
+static int qid_path_suffixmap(V9fsPDU *pdu, const struct stat *stbuf,
+ uint64_t *path)
+{
+ const int ino_hash_bits = qid_inode_prefix_hash_bits(pdu, stbuf->st_dev);
+ QppEntry lookup = {
+ .dev = stbuf->st_dev,
+ .ino_prefix = (uint16_t) (stbuf->st_ino >> (64 - ino_hash_bits))
+ }, *val;
+ uint32_t hash = qpp_hash(lookup);
+
+ val = qht_lookup(&pdu->s->qpp_table, &lookup, hash);
+
+ if (!val) {
+ if (pdu->s->qp_affix_next == 0) {
+ /* we ran out of affixes */
+ warn_report_once(
+ "9p: Potential degraded performance of inode remapping"
+ );
+ return -ENFILE;
+ }
+
+ val = g_malloc0(sizeof(QppEntry));
+ *val = lookup;
+
+ /* new unique inode affix and device combo */
+ val->qp_affix_index = pdu->s->qp_affix_next++;
+ val->qp_affix = affixForIndex(val->qp_affix_index);
+ qht_insert(&pdu->s->qpp_table, val, hash, NULL);
+ }
+ /* assuming generated affix to be suffix type, not prefix */
+ *path = (stbuf->st_ino << val->qp_affix.bits) | val->qp_affix.value;
+ return 0;
+}
+
+static int stat_to_qid(V9fsPDU *pdu, const struct stat *stbuf, V9fsQID *qidp)
+{
+ int err;
size_t size;
- memset(&qidp->path, 0, sizeof(qidp->path));
- size = MIN(sizeof(stbuf->st_ino), sizeof(qidp->path));
- memcpy(&qidp->path, &stbuf->st_ino, size);
+ if (pdu->s->ctx.export_flags & V9FS_REMAP_INODES) {
+ /* map inode+device to qid path (fast path) */
+ err = qid_path_suffixmap(pdu, stbuf, &qidp->path);
+ if (err == -ENFILE) {
+ /* fast path didn't work, fall back to full map */
+ err = qid_path_fullmap(pdu, stbuf, &qidp->path);
+ }
+ if (err) {
+ return err;
+ }
+ } else {
+ if (pdu->s->dev_id != stbuf->st_dev) {
+ if (pdu->s->ctx.export_flags & V9FS_FORBID_MULTIDEVS) {
+ error_report_once(
+ "9p: Multiple devices detected in same VirtFS export. "
+ "Access of guest to additional devices is (partly) "
+ "denied due to virtfs option 'multidevs=forbid' being "
+ "effective."
+ );
+ return -ENODEV;
+ } else {
+ warn_report_once(
+ "9p: Multiple devices detected in same VirtFS export, "
+ "which might lead to file ID collisions and severe "
+ "misbehaviours on guest! You should either use a "
+ "separate export for each device shared from host or "
+ "use virtfs option 'multidevs=remap'!"
+ );
+ }
+ }
+ memset(&qidp->path, 0, sizeof(qidp->path));
+ size = MIN(sizeof(stbuf->st_ino), sizeof(qidp->path));
+ memcpy(&qidp->path, &stbuf->st_ino, size);
+ }
+
qidp->version = stbuf->st_mtime ^ (stbuf->st_size << 8);
qidp->type = 0;
if (S_ISDIR(stbuf->st_mode)) {
if (S_ISLNK(stbuf->st_mode)) {
qidp->type |= P9_QID_TYPE_SYMLINK;
}
+
+ return 0;
}
static int coroutine_fn fid_to_qid(V9fsPDU *pdu, V9fsFidState *fidp,
if (err < 0) {
return err;
}
- stat_to_qid(&stbuf, qidp);
+ err = stat_to_qid(pdu, &stbuf, qidp);
+ if (err < 0) {
+ return err;
+ }
return 0;
}
{
if (stat->type == -1 &&
stat->dev == -1 &&
- stat->qid.type == -1 &&
- stat->qid.version == -1 &&
- stat->qid.path == -1 &&
+ stat->qid.type == 0xff &&
+ stat->qid.version == (uint32_t) -1 &&
+ stat->qid.path == (uint64_t) -1 &&
stat->mode == -1 &&
stat->atime == -1 &&
stat->mtime == -1 &&
memset(v9stat, 0, sizeof(*v9stat));
- stat_to_qid(stbuf, &v9stat->qid);
+ err = stat_to_qid(pdu, stbuf, &v9stat->qid);
+ if (err < 0) {
+ return err;
+ }
v9stat->mode = stat_to_v9mode(stbuf);
v9stat->atime = stbuf->st_atime;
v9stat->mtime = stbuf->st_mtime;
#define P9_STATS_ALL 0x00003fffULL /* Mask for All fields above */
-static void stat_to_v9stat_dotl(V9fsState *s, const struct stat *stbuf,
+static int stat_to_v9stat_dotl(V9fsPDU *pdu, const struct stat *stbuf,
V9fsStatDotl *v9lstat)
{
memset(v9lstat, 0, sizeof(*v9lstat));
/* Currently we only support BASIC fields in stat */
v9lstat->st_result_mask = P9_STATS_BASIC;
- stat_to_qid(stbuf, &v9lstat->qid);
+ return stat_to_qid(pdu, stbuf, &v9lstat->qid);
}
static void print_sg(struct iovec *sg, int cnt)
s->proto_version = V9FS_PROTO_2000L;
} else {
v9fs_string_sprintf(&version, "unknown");
+ /* skip min. msize check, reporting invalid version has priority */
+ goto marshal;
+ }
+
+ if (s->msize < P9_MIN_MSIZE) {
+ err = -EMSGSIZE;
+ error_report(
+ "9pfs: Client requested msize < minimum msize ("
+ stringify(P9_MIN_MSIZE) ") supported by this server."
+ );
+ goto out;
}
+ /* 8192 is the default msize of Linux clients */
+ if (s->msize <= 8192 && !(s->ctx.export_flags & V9FS_NO_PERF_WARN)) {
+ warn_report_once(
+ "9p: degraded performance: a reasonable high msize should be "
+ "chosen on client/guest side (chosen msize is <= 8192). See "
+ "https://wiki.qemu.org/Documentation/9psetup#msize for details."
+ );
+ }
+
+marshal:
err = pdu_marshal(pdu, offset, "ds", s->msize, &version);
if (err < 0) {
goto out;
size_t offset = 7;
V9fsQID qid;
ssize_t err;
- Error *local_err = NULL;
v9fs_string_init(&uname);
v9fs_string_init(&aname);
error_setg(&s->migration_blocker,
"Migration is disabled when VirtFS export path '%s' is mounted in the guest using mount_tag '%s'",
s->ctx.fs_root ? s->ctx.fs_root : "NULL", s->tag);
- err = migrate_add_blocker(s->migration_blocker, &local_err);
- if (local_err) {
- error_free(local_err);
+ err = migrate_add_blocker(s->migration_blocker, NULL);
+ if (err < 0) {
error_free(s->migration_blocker);
s->migration_blocker = NULL;
clunk_fid(s, fid);
uint64_t request_mask;
V9fsStatDotl v9stat_dotl;
V9fsPDU *pdu = opaque;
- V9fsState *s = pdu->s;
retval = pdu_unmarshal(pdu, offset, "dq", &fid, &request_mask);
if (retval < 0) {
if (retval < 0) {
goto out;
}
- stat_to_v9stat_dotl(s, &stbuf, &v9stat_dotl);
+ retval = stat_to_v9stat_dotl(pdu, &stbuf, &v9stat_dotl);
+ if (retval < 0) {
+ goto out;
+ }
/* fill st_gen if requested and supported by underlying fs */
if (request_mask & P9_STATS_GEN) {
if (err < 0) {
goto out;
}
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
v9fs_path_copy(&dpath, &path);
}
memcpy(&qids[name_idx], &qid, sizeof(qid));
* and as well as less than (client msize - P9_IOHDRSZ))
*/
if (!v9fs_co_statfs(pdu, path, &stbuf)) {
- iounit = stbuf.f_bsize;
- iounit *= (s->msize - P9_IOHDRSZ)/stbuf.f_bsize;
+ if (stbuf.f_bsize) {
+ iounit = stbuf.f_bsize;
+ iounit *= (s->msize - P9_IOHDRSZ) / stbuf.f_bsize;
+ }
}
if (!iounit) {
iounit = s->msize - P9_IOHDRSZ;
if (err < 0) {
goto out;
}
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
if (S_ISDIR(stbuf.st_mode)) {
err = v9fs_co_opendir(pdu, fidp);
if (err < 0) {
fidp->flags |= FID_NON_RECLAIMABLE;
}
iounit = get_iounit(pdu, &fidp->path);
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
err = pdu_marshal(pdu, offset, "Qd", &qid, iounit);
if (err < 0) {
goto out;
goto out_nofid;
}
if (fidp->fid_type == P9_FID_DIR) {
-
+ if (s->proto_version != V9FS_PROTO_2000U) {
+ warn_report_once(
+ "9p: bad client: T_read request on directory only expected "
+ "with 9P2000.u protocol version"
+ );
+ err = -EOPNOTSUPP;
+ goto out;
+ }
if (off == 0) {
v9fs_co_rewinddir(pdu, fidp);
}
pdu_complete(pdu, err);
}
-static size_t v9fs_readdir_data_size(V9fsString *name)
+/**
+ * Returns size required in Rreaddir response for the passed dirent @p name.
+ *
+ * @param name - directory entry's name (i.e. file name, directory name)
+ * @returns required size in bytes
+ */
+size_t v9fs_readdir_response_size(V9fsString *name)
{
/*
* Size of each dirent on the wire: size of qid (13) + size of offset (8)
return 24 + v9fs_string_size(name);
}
+static void v9fs_free_dirents(struct V9fsDirEnt *e)
+{
+ struct V9fsDirEnt *next = NULL;
+
+ for (; e; e = next) {
+ next = e->next;
+ g_free(e->dent);
+ g_free(e->st);
+ g_free(e);
+ }
+}
+
static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
- int32_t max_count)
+ off_t offset, int32_t max_count)
{
size_t size;
V9fsQID qid;
V9fsString name;
int len, err = 0;
int32_t count = 0;
- off_t saved_dir_pos;
struct dirent *dent;
+ struct stat *st;
+ struct V9fsDirEnt *entries = NULL;
- /* save the directory position */
- saved_dir_pos = v9fs_co_telldir(pdu, fidp);
- if (saved_dir_pos < 0) {
- return saved_dir_pos;
+ /*
+ * inode remapping requires the device id, which in turn might be
+ * different for different directory entries, so if inode remapping is
+ * enabled we have to make a full stat for each directory entry
+ */
+ const bool dostat = pdu->s->ctx.export_flags & V9FS_REMAP_INODES;
+
+ /*
+ * Fetch all required directory entries altogether on a background IO
+ * thread from fs driver. We don't want to do that for each entry
+ * individually, because hopping between threads (this main IO thread
+ * and background IO driver thread) would sum up to huge latencies.
+ */
+ count = v9fs_co_readdir_many(pdu, fidp, &entries, offset, max_count,
+ dostat);
+ if (count < 0) {
+ err = count;
+ count = 0;
+ goto out;
}
+ count = 0;
- while (1) {
- v9fs_readdir_lock(&fidp->fs.dir);
+ for (struct V9fsDirEnt *e = entries; e; e = e->next) {
+ dent = e->dent;
- err = v9fs_co_readdir(pdu, fidp, &dent);
- if (err || !dent) {
- break;
+ if (pdu->s->ctx.export_flags & V9FS_REMAP_INODES) {
+ st = e->st;
+ /* e->st should never be NULL, but just to be sure */
+ if (!st) {
+ err = -1;
+ break;
+ }
+
+ /* remap inode */
+ err = stat_to_qid(pdu, st, &qid);
+ if (err < 0) {
+ break;
+ }
+ } else {
+ /*
+ * Fill up just the path field of qid because the client uses
+ * only that. To fill the entire qid structure we will have
+ * to stat each dirent found, which is expensive. For the
+ * latter reason we don't call stat_to_qid() here. Only drawback
+ * is that no multi-device export detection of stat_to_qid()
+ * would be done and provided as error to the user here. But
+ * user would get that error anyway when accessing those
+ * files/dirs through other ways.
+ */
+ size = MIN(sizeof(dent->d_ino), sizeof(qid.path));
+ memcpy(&qid.path, &dent->d_ino, size);
+ /* Fill the other fields with dummy values */
+ qid.type = 0;
+ qid.version = 0;
}
+
v9fs_string_init(&name);
v9fs_string_sprintf(&name, "%s", dent->d_name);
- if ((count + v9fs_readdir_data_size(&name)) > max_count) {
- v9fs_readdir_unlock(&fidp->fs.dir);
-
- /* Ran out of buffer. Set dir back to old position and return */
- v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
- v9fs_string_free(&name);
- return count;
- }
- /*
- * Fill up just the path field of qid because the client uses
- * only that. To fill the entire qid structure we will have
- * to stat each dirent found, which is expensive
- */
- size = MIN(sizeof(dent->d_ino), sizeof(qid.path));
- memcpy(&qid.path, &dent->d_ino, size);
- /* Fill the other fields with dummy values */
- qid.type = 0;
- qid.version = 0;
/* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */
len = pdu_marshal(pdu, 11 + count, "Qqbs",
&qid, dent->d_off,
dent->d_type, &name);
- v9fs_readdir_unlock(&fidp->fs.dir);
+ v9fs_string_free(&name);
if (len < 0) {
- v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
- v9fs_string_free(&name);
- return len;
+ err = len;
+ break;
}
+
count += len;
- v9fs_string_free(&name);
- saved_dir_pos = dent->d_off;
}
- v9fs_readdir_unlock(&fidp->fs.dir);
-
+out:
+ v9fs_free_dirents(entries);
if (err < 0) {
return err;
}
int32_t count;
uint32_t max_count;
V9fsPDU *pdu = opaque;
+ V9fsState *s = pdu->s;
retval = pdu_unmarshal(pdu, offset, "dqd", &fid,
&initial_offset, &max_count);
}
trace_v9fs_readdir(pdu->tag, pdu->id, fid, initial_offset, max_count);
+ /* Enough space for a R_readdir header: size[4] Rreaddir tag[2] count[4] */
+ if (max_count > s->msize - 11) {
+ max_count = s->msize - 11;
+ warn_report_once(
+ "9p: bad client: T_readdir with count > msize - 11"
+ );
+ }
+
fidp = get_fid(pdu, fid);
if (fidp == NULL) {
retval = -EINVAL;
retval = -EINVAL;
goto out;
}
- if (initial_offset == 0) {
- v9fs_co_rewinddir(pdu, fidp);
- } else {
- v9fs_co_seekdir(pdu, fidp, initial_offset);
+ if (s->proto_version != V9FS_PROTO_2000L) {
+ warn_report_once(
+ "9p: bad client: T_readdir request only expected with 9P2000.L "
+ "protocol version"
+ );
+ retval = -EOPNOTSUPP;
+ goto out;
}
- count = v9fs_do_readdir(pdu, fidp, max_count);
+ count = v9fs_do_readdir(pdu, fidp, (off_t) initial_offset, max_count);
if (count < 0) {
retval = count;
goto out;
if (fidp->fs.xattr.len < off) {
- err = -ENOSPC;
- goto out;
+ return -ENOSPC;
}
write_count = fidp->fs.xattr.len - off;
if (write_count > count) {
off += to_copy;
write_count -= to_copy;
}
-out:
+
return err;
}
}
}
iounit = get_iounit(pdu, &fidp->path);
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
err = pdu_marshal(pdu, offset, "Qd", &qid, iounit);
if (err < 0) {
goto out;
if (err < 0) {
goto out;
}
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
err = pdu_marshal(pdu, offset, "Q", &qid);
if (err < 0) {
goto out;
if (newdirfid != -1) {
dirfidp = get_fid(pdu, newdirfid);
if (dirfidp == NULL) {
- err = -ENOENT;
- goto out_nofid;
+ return -ENOENT;
}
if (fidp->fid_type != P9_FID_NONE) {
err = -EINVAL;
put_fid(pdu, dirfidp);
}
v9fs_path_free(&new_path);
-out_nofid:
return err;
}
if (err < 0) {
goto out;
}
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
err = pdu_marshal(pdu, offset, "Q", &qid);
if (err < 0) {
goto out;
if (err < 0) {
goto out;
}
- stat_to_qid(&stbuf, &qid);
+ err = stat_to_qid(pdu, &stbuf, &qid);
+ if (err < 0) {
+ goto out;
+ }
err = pdu_marshal(pdu, offset, "Q", &qid);
if (err < 0) {
goto out;
int v9fs_device_realize_common(V9fsState *s, const V9fsTransport *t,
Error **errp)
{
+ ERRP_GUARD();
int i, len;
struct stat stat;
FsDriverEntry *fse;
goto out;
}
+ s->dev_id = stat.st_dev;
+
+ /* init inode remapping : */
+ /* hash table for variable length inode suffixes */
+ qpd_table_init(&s->qpd_table);
+ /* hash table for slow/full inode remapping (most users won't need it) */
+ qpf_table_init(&s->qpf_table);
+ /* hash table for quick inode remapping */
+ qpp_table_init(&s->qpp_table);
+ s->qp_ndevices = 0;
+ s->qp_affix_next = 1; /* reserve 0 to detect overflow */
+ s->qp_fullpath_next = 1;
+
s->ctx.fst = &fse->fst;
fsdev_throttle_init(s->ctx.fst);
- v9fs_path_free(&path);
-
rc = 0;
out:
if (rc) {
- if (s->ops && s->ops->cleanup && s->ctx.private) {
- s->ops->cleanup(&s->ctx);
- }
- g_free(s->tag);
- g_free(s->ctx.fs_root);
- v9fs_path_free(&path);
+ v9fs_device_unrealize_common(s);
}
+ v9fs_path_free(&path);
return rc;
}
-void v9fs_device_unrealize_common(V9fsState *s, Error **errp)
+void v9fs_device_unrealize_common(V9fsState *s)
{
- if (s->ops->cleanup) {
+ if (s->ops && s->ops->cleanup) {
s->ops->cleanup(&s->ctx);
}
- fsdev_throttle_cleanup(s->ctx.fst);
+ if (s->ctx.fst) {
+ fsdev_throttle_cleanup(s->ctx.fst);
+ }
g_free(s->tag);
+ qp_table_destroy(&s->qpd_table);
+ qp_table_destroy(&s->qpp_table);
+ qp_table_destroy(&s->qpf_table);
g_free(s->ctx.fs_root);
}
projects / mirror_qemu.git / blobdiff