return !strncmp(name, buf, len) ? buf + len : NULL;
}
+static ssize_t iwl_dbgfs_os_device_timediff_read(struct file *file,
+ char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct ieee80211_vif *vif = file->private_data;
+ struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+ struct iwl_mvm *mvm = mvmvif->mvm;
+ u32 curr_gp2;
+ u64 curr_os;
+ s64 diff;
+ char buf[64];
+ const size_t bufsz = sizeof(buf);
+ int pos = 0;
+
+ iwl_mvm_get_sync_time(mvm, &curr_gp2, &curr_os);
+ do_div(curr_os, NSEC_PER_USEC);
+ diff = curr_os - curr_gp2;
+ pos += scnprintf(buf + pos, bufsz - pos, "diff=%lld\n", diff);
+
+ return simple_read_from_buffer(user_buf, count, ppos, buf, pos);
+}
+
static ssize_t iwl_dbgfs_tof_enable_write(struct ieee80211_vif *vif,
char *buf,
size_t count, loff_t *ppos)
MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_responder_params, 32);
MVM_DEBUGFS_READ_WRITE_FILE_OPS(quota_min, 32);
MVM_DEBUGFS_WRITE_FILE_OPS(lqm_send_cmd, 64);
+MVM_DEBUGFS_READ_FILE_OPS(os_device_timediff);
+
void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
{
mvmvif->dbgfs_dir = debugfs_create_dir("iwlmvm", dbgfs_dir);
if (!mvmvif->dbgfs_dir) {
- IWL_ERR(mvm, "Failed to create debugfs directory under %s\n",
- dbgfs_dir->d_name.name);
+ IWL_ERR(mvm, "Failed to create debugfs directory under %pd\n",
+ dbgfs_dir);
return;
}
if (iwlmvm_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
((vif->type == NL80211_IFTYPE_STATION && !vif->p2p) ||
- (vif->type == NL80211_IFTYPE_STATION && vif->p2p &&
- mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_BSS_P2P_PS_DCM)))
+ (vif->type == NL80211_IFTYPE_STATION && vif->p2p)))
MVM_DEBUGFS_ADD_FILE_VIF(pm_params, mvmvif->dbgfs_dir, S_IWUSR |
S_IRUSR);
MVM_DEBUGFS_ADD_FILE_VIF(quota_min, mvmvif->dbgfs_dir,
S_IRUSR | S_IWUSR);
MVM_DEBUGFS_ADD_FILE_VIF(lqm_send_cmd, mvmvif->dbgfs_dir, S_IWUSR);
+ MVM_DEBUGFS_ADD_FILE_VIF(os_device_timediff,
+ mvmvif->dbgfs_dir, S_IRUSR);
if (vif->type == NL80211_IFTYPE_STATION && !vif->p2p &&
mvmvif == mvm->bf_allowed_vif)
* find
* netdev:wlan0 -> ../../../ieee80211/phy0/netdev:wlan0/iwlmvm/
*/
- snprintf(buf, 100, "../../../%s/%s/%s/%s",
- dbgfs_dir->d_parent->d_parent->d_name.name,
- dbgfs_dir->d_parent->d_name.name,
- dbgfs_dir->d_name.name,
- mvmvif->dbgfs_dir->d_name.name);
+ snprintf(buf, 100, "../../../%pd3/%pd",
+ dbgfs_dir,
+ mvmvif->dbgfs_dir);
mvmvif->dbgfs_slink = debugfs_create_symlink(dbgfs_dir->d_name.name,
mvm->debugfs_dir, buf);
if (!mvmvif->dbgfs_slink)
- IWL_ERR(mvm, "Can't create debugfs symbolic link under %s\n",
- dbgfs_dir->d_name.name);
+ IWL_ERR(mvm, "Can't create debugfs symbolic link under %pd\n",
+ dbgfs_dir);
return;
err:
IWL_ERR(mvm, "Can't create debugfs entity\n");
return ret ?: count;
}
+static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
+ char *buf, size_t count,
+ loff_t *ppos)
+{
+ struct iwl_rx_cmd_buffer rxb = {
+ ._rx_page_order = 0,
+ .truesize = 0, /* not used */
+ ._offset = 0,
+ };
+ struct iwl_rx_packet *pkt;
+ struct iwl_rx_mpdu_desc *desc;
+ int bin_len = count / 2;
+ int ret = -EINVAL;
+
+ /* supporting only 9000 descriptor */
+ if (!mvm->trans->cfg->mq_rx_supported)
+ return -ENOTSUPP;
+
+ rxb._page = alloc_pages(GFP_ATOMIC, 0);
+ if (!rxb._page)
+ return -ENOMEM;
+ pkt = rxb_addr(&rxb);
+
+ ret = hex2bin(page_address(rxb._page), buf, bin_len);
+ if (ret)
+ goto out;
+
+ /* avoid invalid memory access */
+ if (bin_len < sizeof(*pkt) + sizeof(*desc))
+ goto out;
+
+ /* check this is RX packet */
+ if (WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd) !=
+ WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD))
+ goto out;
+
+ /* check the length in metadata matches actual received length */
+ desc = (void *)pkt->data;
+ if (le16_to_cpu(desc->mpdu_len) !=
+ (bin_len - sizeof(*desc) - sizeof(*pkt)))
+ goto out;
+
+ local_bh_disable();
+ iwl_mvm_rx_mpdu_mq(mvm, NULL, &rxb, 0);
+ local_bh_enable();
+ ret = 0;
+
+out:
+ iwl_free_rxb(&rxb);
+
+ return ret ?: count;
+}
+
static ssize_t iwl_dbgfs_fw_dbg_conf_read(struct file *file,
char __user *user_buf,
size_t count, loff_t *ppos)
MVM_DEBUGFS_WRITE_FILE_OPS(max_amsdu_len, 8);
MVM_DEBUGFS_WRITE_FILE_OPS(indirection_tbl,
(IWL_RSS_INDIRECTION_TABLE_SIZE * 2));
+MVM_DEBUGFS_WRITE_FILE_OPS(inject_packet, 512);
#ifdef CONFIG_IWLWIFI_BCAST_FILTERING
MVM_DEBUGFS_READ_WRITE_FILE_OPS(bcast_filters, 256);
MVM_DEBUGFS_READ_WRITE_FILE_OPS(d3_sram, 8);
#endif
+static ssize_t iwl_dbgfs_mem_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct iwl_mvm *mvm = file->private_data;
+ struct iwl_dbg_mem_access_cmd cmd = {};
+ struct iwl_dbg_mem_access_rsp *rsp;
+ struct iwl_host_cmd hcmd = {
+ .flags = CMD_WANT_SKB | CMD_SEND_IN_RFKILL,
+ .data = { &cmd, },
+ .len = { sizeof(cmd) },
+ };
+ size_t delta, len;
+ ssize_t ret;
+
+ hcmd.id = iwl_cmd_id(*ppos >> 24 ? UMAC_RD_WR : LMAC_RD_WR,
+ DEBUG_GROUP, 0);
+ cmd.op = cpu_to_le32(DEBUG_MEM_OP_READ);
+
+ /* Take care of alignment of both the position and the length */
+ delta = *ppos & 0x3;
+ cmd.addr = cpu_to_le32(*ppos - delta);
+ cmd.len = cpu_to_le32(min(ALIGN(count + delta, 4) / 4,
+ (size_t)DEBUG_MEM_MAX_SIZE_DWORDS));
+
+ mutex_lock(&mvm->mutex);
+ ret = iwl_mvm_send_cmd(mvm, &hcmd);
+ mutex_unlock(&mvm->mutex);
+
+ if (ret < 0)
+ return ret;
+
+ rsp = (void *)hcmd.resp_pkt->data;
+ if (le32_to_cpu(rsp->status) != DEBUG_MEM_STATUS_SUCCESS) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ len = min((size_t)le32_to_cpu(rsp->len) << 2,
+ iwl_rx_packet_payload_len(hcmd.resp_pkt) - sizeof(*rsp));
+ len = min(len - delta, count);
+ if (len < 0) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret = len - copy_to_user(user_buf, (void *)rsp->data + delta, len);
+ *ppos += ret;
+
+out:
+ iwl_free_resp(&hcmd);
+ return ret;
+}
+
+static ssize_t iwl_dbgfs_mem_write(struct file *file,
+ const char __user *user_buf, size_t count,
+ loff_t *ppos)
+{
+ struct iwl_mvm *mvm = file->private_data;
+ struct iwl_dbg_mem_access_cmd *cmd;
+ struct iwl_dbg_mem_access_rsp *rsp;
+ struct iwl_host_cmd hcmd = {};
+ size_t cmd_size;
+ size_t data_size;
+ u32 op, len;
+ ssize_t ret;
+
+ hcmd.id = iwl_cmd_id(*ppos >> 24 ? UMAC_RD_WR : LMAC_RD_WR,
+ DEBUG_GROUP, 0);
+
+ if (*ppos & 0x3 || count < 4) {
+ op = DEBUG_MEM_OP_WRITE_BYTES;
+ len = min(count, (size_t)(4 - (*ppos & 0x3)));
+ data_size = len;
+ } else {
+ op = DEBUG_MEM_OP_WRITE;
+ len = min(count >> 2, (size_t)DEBUG_MEM_MAX_SIZE_DWORDS);
+ data_size = len << 2;
+ }
+
+ cmd_size = sizeof(*cmd) + ALIGN(data_size, 4);
+ cmd = kzalloc(cmd_size, GFP_KERNEL);
+ if (!cmd)
+ return -ENOMEM;
+
+ cmd->op = cpu_to_le32(op);
+ cmd->len = cpu_to_le32(len);
+ cmd->addr = cpu_to_le32(*ppos);
+ if (copy_from_user((void *)cmd->data, user_buf, data_size)) {
+ kfree(cmd);
+ return -EFAULT;
+ }
+
+ hcmd.flags = CMD_WANT_SKB | CMD_SEND_IN_RFKILL,
+ hcmd.data[0] = (void *)cmd;
+ hcmd.len[0] = cmd_size;
+
+ mutex_lock(&mvm->mutex);
+ ret = iwl_mvm_send_cmd(mvm, &hcmd);
+ mutex_unlock(&mvm->mutex);
+
+ kfree(cmd);
+
+ if (ret < 0)
+ return ret;
+
+ rsp = (void *)hcmd.resp_pkt->data;
+ if (rsp->status != DEBUG_MEM_STATUS_SUCCESS) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ ret = data_size;
+ *ppos += ret;
+
+out:
+ iwl_free_resp(&hcmd);
+ return ret;
+}
+
+static const struct file_operations iwl_dbgfs_mem_ops = {
+ .read = iwl_dbgfs_mem_read,
+ .write = iwl_dbgfs_mem_write,
+ .open = simple_open,
+ .llseek = default_llseek,
+};
+
int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir)
{
struct dentry *bcast_dir __maybe_unused;
MVM_DEBUGFS_ADD_FILE(send_echo_cmd, mvm->debugfs_dir, S_IWUSR);
MVM_DEBUGFS_ADD_FILE(cont_recording, mvm->debugfs_dir, S_IWUSR);
MVM_DEBUGFS_ADD_FILE(indirection_tbl, mvm->debugfs_dir, S_IWUSR);
+ MVM_DEBUGFS_ADD_FILE(inject_packet, mvm->debugfs_dir, S_IWUSR);
if (!debugfs_create_bool("enable_scan_iteration_notif",
S_IRUSR | S_IWUSR,
mvm->debugfs_dir,
mvm->debugfs_dir, &mvm->nvm_phy_sku_blob))
goto err;
+ debugfs_create_file("mem", S_IRUSR | S_IWUSR, dbgfs_dir, mvm,
+ &iwl_dbgfs_mem_ops);
+
/*
* Create a symlink with mac80211. It will be removed when mac80211
* exists (before the opmode exists which removes the target.)
*/
- snprintf(buf, 100, "../../%s/%s",
- dbgfs_dir->d_parent->d_parent->d_name.name,
- dbgfs_dir->d_parent->d_name.name);
+ snprintf(buf, 100, "../../%pd2", dbgfs_dir->d_parent);
if (!debugfs_create_symlink("iwlwifi", mvm->hw->wiphy->debugfsdir, buf))
goto err;
#define DEBUG_SUBSYSTEM S_LLITE
#include "../include/lustre_dlm.h"
-#include "../include/lustre_lite.h"
#include <linux/pagemap.h>
#include <linux/file.h>
+#include <linux/sched.h>
#include <linux/mount.h>
-#include "llite_internal.h"
#include "../include/lustre/ll_fiemap.h"
+#include "../include/lustre/lustre_ioctl.h"
#include "../include/cl_object.h"
+#include "llite_internal.h"
static int
ll_put_grouplock(struct inode *inode, struct file *file, unsigned long arg);
spin_unlock(&lli->lli_lock);
}
- if (rc == 0) {
- rc = ll_objects_destroy(req, inode);
- if (rc)
- CERROR("inode %lu ll_objects destroy: rc = %d\n",
- inode->i_ino, rc);
- }
if (rc == 0 && op_data->op_bias & MDS_HSM_RELEASE) {
struct mdt_body *body;
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- if (!(body->valid & OBD_MD_FLRELEASED))
+ if (!(body->mbo_valid & OBD_MD_FLRELEASED))
rc = -EBUSY;
}
fd = LUSTRE_FPRIVATE(file);
LASSERT(fd);
- /* The last ref on @file, maybe not be the owner pid of statahead.
- * Different processes can open the same dir, "ll_opendir_key" means:
- * it is me that should stop the statahead thread.
+ /* The last ref on @file, maybe not be the owner pid of statahead,
+ * because parent and child process can share the same file handle.
*/
- if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd &&
- lli->lli_opendir_pid != 0)
- ll_stop_statahead(inode, lli->lli_opendir_key);
+ if (S_ISDIR(inode->i_mode) && lli->lli_opendir_key == fd)
+ ll_deauthorize_statahead(inode, fd);
if (is_root_inode(inode)) {
LUSTRE_FPRIVATE(file) = NULL;
}
if (!S_ISDIR(inode->i_mode)) {
- lov_read_and_clear_async_rc(lli->lli_clob);
+ if (lli->lli_clob)
+ lov_read_and_clear_async_rc(lli->lli_clob);
lli->lli_async_rc = 0;
}
return rc;
}
-static int ll_intent_file_open(struct dentry *dentry, void *lmm,
- int lmmsize, struct lookup_intent *itp)
+static int ll_intent_file_open(struct dentry *de, void *lmm, int lmmsize,
+ struct lookup_intent *itp)
{
- struct inode *inode = d_inode(dentry);
+ struct inode *inode = d_inode(de);
struct ll_sb_info *sbi = ll_i2sbi(inode);
- struct dentry *parent = dentry->d_parent;
- const char *name = dentry->d_name.name;
- const int len = dentry->d_name.len;
+ struct dentry *parent = de->d_parent;
+ const char *name = NULL;
struct md_op_data *op_data;
- struct ptlrpc_request *req;
- __u32 opc = LUSTRE_OPC_ANY;
- int rc;
+ struct ptlrpc_request *req = NULL;
+ int len = 0, rc;
- /* Usually we come here only for NFSD, and we want open lock. */
- /* We can also get here if there was cached open handle in revalidate_it
- * but it disappeared while we were getting from there to ll_file_open.
- * But this means this file was closed and immediately opened which
- * makes a good candidate for using OPEN lock
- */
- /* If lmmsize & lmm are not 0, we are just setting stripe info
- * parameters. No need for the open lock
+ LASSERT(parent);
+ LASSERT(itp->it_flags & MDS_OPEN_BY_FID);
+
+ /*
+ * if server supports open-by-fid, or file name is invalid, don't pack
+ * name in open request
*/
- if (!lmm && lmmsize == 0) {
- struct ll_dentry_data *ldd = ll_d2d(dentry);
- /*
- * If we came via ll_iget_for_nfs, then we need to request
- * struct ll_dentry_data *ldd = ll_d2d(file->f_dentry);
- *
- * NB: when ldd is NULL, it must have come via normal
- * lookup path only, since ll_iget_for_nfs always calls
- * ll_d_init().
- */
- if (ldd && ldd->lld_nfs_dentry) {
- ldd->lld_nfs_dentry = 0;
- itp->it_flags |= MDS_OPEN_LOCK;
- }
- if (itp->it_flags & FMODE_WRITE)
- opc = LUSTRE_OPC_CREATE;
+ if (!(exp_connect_flags(sbi->ll_md_exp) & OBD_CONNECT_OPEN_BY_FID) &&
+ lu_name_is_valid_2(de->d_name.name, de->d_name.len)) {
+ name = de->d_name.name;
+ len = de->d_name.len;
}
- op_data = ll_prep_md_op_data(NULL, d_inode(parent),
- inode, name, len,
- O_RDWR, opc, NULL);
+ op_data = ll_prep_md_op_data(NULL, d_inode(parent), inode, name, len,
+ O_RDWR, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
+ op_data->op_data = lmm;
+ op_data->op_data_size = lmmsize;
- itp->it_flags |= MDS_OPEN_BY_FID;
- rc = md_intent_lock(sbi->ll_md_exp, op_data, lmm, lmmsize, itp,
- 0 /*unused */, &req, ll_md_blocking_ast, 0);
+ rc = md_intent_lock(sbi->ll_md_exp, op_data, itp, &req,
+ &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
if (rc == -ESTALE) {
/* reason for keep own exit path - don`t flood log
struct mdt_body *body;
body = req_capsule_server_get(&it->it_request->rq_pill, &RMF_MDT_BODY);
- och->och_fh = body->handle;
- och->och_fid = body->fid1;
+ och->och_fh = body->mbo_handle;
+ och->och_fid = body->mbo_fid1;
och->och_lease_handle.cookie = it->it_lock_handle;
och->och_magic = OBD_CLIENT_HANDLE_MAGIC;
och->och_flags = it->it_flags;
body = req_capsule_server_get(&it->it_request->rq_pill,
&RMF_MDT_BODY);
- ll_ioepoch_open(lli, body->ioepoch);
+ ll_ioepoch_open(lli, body->mbo_ioepoch);
}
LUSTRE_FPRIVATE(file) = fd;
struct obd_client_handle **och_p = NULL;
__u64 *och_usecount = NULL;
struct ll_file_data *fd;
- int rc = 0, opendir_set = 0;
+ int rc = 0;
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), flags %o\n",
PFID(ll_inode2fid(inode)), inode, file->f_flags);
}
fd->fd_file = file;
- if (S_ISDIR(inode->i_mode)) {
- spin_lock(&lli->lli_sa_lock);
- if (!lli->lli_opendir_key && !lli->lli_sai &&
- lli->lli_opendir_pid == 0) {
- lli->lli_opendir_key = fd;
- lli->lli_opendir_pid = current_pid();
- opendir_set = 1;
- }
- spin_unlock(&lli->lli_sa_lock);
- }
+ if (S_ISDIR(inode->i_mode))
+ ll_authorize_statahead(inode, fd);
if (is_root_inode(inode)) {
LUSTRE_FPRIVATE(file) = fd;
} else if (it->it_flags & FMODE_EXEC) {
och_p = &lli->lli_mds_exec_och;
och_usecount = &lli->lli_open_fd_exec_count;
- } else {
+ } else {
och_p = &lli->lli_mds_read_och;
och_usecount = &lli->lli_open_fd_read_count;
}
* result in a deadlock
*/
mutex_unlock(&lli->lli_och_mutex);
- it->it_create_mode |= M_CHECK_STALE;
+ /*
+ * Normally called under two situations:
+ * 1. NFS export.
+ * 2. revalidate with IT_OPEN (revalidate doesn't
+ * execute this intent any more).
+ *
+ * Always fetch MDS_OPEN_LOCK if this is not setstripe.
+ *
+ * Always specify MDS_OPEN_BY_FID because we don't want
+ * to get file with different fid.
+ */
+ it->it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID;
rc = ll_intent_file_open(file->f_path.dentry, NULL, 0, it);
- it->it_create_mode &= ~M_CHECK_STALE;
if (rc)
goto out_openerr;
mutex_unlock(&lli->lli_och_mutex);
out_openerr:
- if (opendir_set != 0)
- ll_stop_statahead(inode, lli->lli_opendir_key);
- ll_file_data_put(fd);
+ if (lli->lli_opendir_key == fd)
+ ll_deauthorize_statahead(inode, fd);
+ if (fd)
+ ll_file_data_put(fd);
} else {
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_OPEN, 1);
}
struct lookup_intent it = { .it_op = IT_OPEN };
struct ll_sb_info *sbi = ll_i2sbi(inode);
struct md_op_data *op_data;
- struct ptlrpc_request *req;
+ struct ptlrpc_request *req = NULL;
struct lustre_handle old_handle = { 0 };
struct obd_client_handle *och = NULL;
int rc;
it.it_flags = fmode | open_flags;
it.it_flags |= MDS_OPEN_LOCK | MDS_OPEN_BY_FID | MDS_OPEN_LEASE;
- rc = md_intent_lock(sbi->ll_md_exp, op_data, NULL, 0, &it, 0, &req,
- ll_md_blocking_lease_ast,
+ rc = md_intent_lock(sbi->ll_md_exp, op_data, &it, &req,
+ &ll_md_blocking_lease_ast,
/* LDLM_FL_NO_LRU: To not put the lease lock into LRU list, otherwise
* it can be cancelled which may mislead applications that the lease is
* broken;
* open in ll_md_blocking_ast(). Otherwise as ll_md_blocking_lease_ast
* doesn't deal with openhandle, so normal openhandle will be leaked.
*/
- LDLM_FL_NO_LRU | LDLM_FL_EXCL);
+ LDLM_FL_NO_LRU | LDLM_FL_EXCL);
ll_finish_md_op_data(op_data);
ptlrpc_req_finished(req);
if (rc < 0)
{
struct ldlm_lock *lock;
bool cancelled = true;
- int rc;
lock = ldlm_handle2lock(&och->och_lease_handle);
if (lock) {
if (lease_broken)
*lease_broken = cancelled;
- rc = ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp, inode, och,
- NULL);
- return rc;
+ return ll_close_inode_openhandle(ll_i2sbi(inode)->ll_md_exp,
+ inode, och, NULL);
}
/* Fills the obdo with the attributes for the lsm */
{
struct ll_inode_info *lli = ll_i2info(file_inode(file));
struct ll_file_data *fd = LUSTRE_FPRIVATE(file);
+ struct range_lock range;
struct cl_io *io;
ssize_t result;
- CDEBUG(D_VFSTRACE, "file: %s, type: %d ppos: %llu, count: %zu\n",
- file->f_path.dentry->d_name.name, iot, *ppos, count);
- CDEBUG(D_VFSTRACE, "file: %pD, type: %d ppos: %llu, count: %zd\n",
++ CDEBUG(D_VFSTRACE, "file: %pD, type: %d ppos: %llu, count: %zu\n",
+ file, iot, *ppos, count);
restart:
io = vvp_env_thread_io(env);
if (cl_io_rw_init(env, io, iot, *ppos, count) == 0) {
struct vvp_io *vio = vvp_env_io(env);
- int write_mutex_locked = 0;
+ bool range_locked = false;
+
+ if (file->f_flags & O_APPEND)
+ range_lock_init(&range, 0, LUSTRE_EOF);
+ else
+ range_lock_init(&range, *ppos, *ppos + count - 1);
vio->vui_fd = LUSTRE_FPRIVATE(file);
- vio->vui_io_subtype = args->via_io_subtype;
-
- switch (vio->vui_io_subtype) {
- case IO_NORMAL:
- vio->vui_iter = args->u.normal.via_iter;
- vio->vui_iocb = args->u.normal.via_iocb;
- if ((iot == CIT_WRITE) &&
- !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
- if (mutex_lock_interruptible(&lli->
- lli_write_mutex)) {
- result = -ERESTARTSYS;
- goto out;
- }
- write_mutex_locked = 1;
- }
- down_read(&lli->lli_trunc_sem);
- break;
- case IO_SPLICE:
- vio->u.splice.vui_pipe = args->u.splice.via_pipe;
- vio->u.splice.vui_flags = args->u.splice.via_flags;
- break;
- default:
- CERROR("Unknown IO type - %u\n", vio->vui_io_subtype);
- LBUG();
+ vio->vui_iter = args->u.normal.via_iter;
+ vio->vui_iocb = args->u.normal.via_iocb;
+ /*
+ * Direct IO reads must also take range lock,
+ * or multiple reads will try to work on the same pages
+ * See LU-6227 for details.
+ */
+ if (((iot == CIT_WRITE) ||
+ (iot == CIT_READ && (file->f_flags & O_DIRECT))) &&
+ !(vio->vui_fd->fd_flags & LL_FILE_GROUP_LOCKED)) {
+ CDEBUG(D_VFSTRACE, "Range lock [%llu, %llu]\n",
+ range.rl_node.in_extent.start,
+ range.rl_node.in_extent.end);
+ result = range_lock(&lli->lli_write_tree,
+ &range);
+ if (result < 0)
+ goto out;
+
+ range_locked = true;
}
+ down_read(&lli->lli_trunc_sem);
ll_cl_add(file, env, io);
result = cl_io_loop(env, io);
ll_cl_remove(file, env);
- if (args->via_io_subtype == IO_NORMAL)
- up_read(&lli->lli_trunc_sem);
- if (write_mutex_locked)
- mutex_unlock(&lli->lli_write_mutex);
+ up_read(&lli->lli_trunc_sem);
+ if (range_locked) {
+ CDEBUG(D_VFSTRACE, "Range unlock [%llu, %llu]\n",
+ range.rl_node.in_extent.start,
+ range.rl_node.in_extent.end);
+ range_unlock(&lli->lli_write_tree, &range);
+ }
} else {
/* cl_io_rw_init() handled IO */
result = io->ci_result;
* short read/write instead of restart io.
*/
if ((result == 0 || result == -ENODATA) && io->ci_need_restart) {
- CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zd\n",
+ CDEBUG(D_VFSTRACE, "Restart %s on %pD from %lld, count:%zu\n",
iot == CIT_READ ? "read" : "write",
file, *ppos, count);
LASSERTF(io->ci_nob == 0, "%zd\n", io->ci_nob);
if (IS_ERR(env))
return PTR_ERR(env);
- args = ll_env_args(env, IO_NORMAL);
+ args = ll_env_args(env);
args->u.normal.via_iter = to;
args->u.normal.via_iocb = iocb;
if (IS_ERR(env))
return PTR_ERR(env);
- args = ll_env_args(env, IO_NORMAL);
+ args = ll_env_args(env);
args->u.normal.via_iter = from;
args->u.normal.via_iocb = iocb;
return result;
}
-/*
- * Send file content (through pagecache) somewhere with helper
- */
-static ssize_t ll_file_splice_read(struct file *in_file, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t count,
- unsigned int flags)
-{
- struct lu_env *env;
- struct vvp_io_args *args;
- ssize_t result;
- int refcheck;
-
- env = cl_env_get(&refcheck);
- if (IS_ERR(env))
- return PTR_ERR(env);
-
- args = ll_env_args(env, IO_SPLICE);
- args->u.splice.via_pipe = pipe;
- args->u.splice.via_flags = flags;
-
- result = ll_file_io_generic(env, args, in_file, CIT_READ, ppos, count);
- cl_env_put(env, &refcheck);
- return result;
-}
-
-static int ll_lov_recreate(struct inode *inode, struct ost_id *oi, u32 ost_idx)
-{
- struct obd_export *exp = ll_i2dtexp(inode);
- struct obd_trans_info oti = { 0 };
- struct obdo *oa = NULL;
- int lsm_size;
- int rc = 0;
- struct lov_stripe_md *lsm = NULL, *lsm2;
-
- oa = kmem_cache_zalloc(obdo_cachep, GFP_NOFS);
- if (!oa)
- return -ENOMEM;
-
- lsm = ccc_inode_lsm_get(inode);
- if (!lsm_has_objects(lsm)) {
- rc = -ENOENT;
- goto out;
- }
-
- lsm_size = sizeof(*lsm) + (sizeof(struct lov_oinfo) *
- (lsm->lsm_stripe_count));
-
- lsm2 = libcfs_kvzalloc(lsm_size, GFP_NOFS);
- if (!lsm2) {
- rc = -ENOMEM;
- goto out;
- }
-
- oa->o_oi = *oi;
- oa->o_nlink = ost_idx;
- oa->o_flags |= OBD_FL_RECREATE_OBJS;
- oa->o_valid = OBD_MD_FLID | OBD_MD_FLFLAGS | OBD_MD_FLGROUP;
- obdo_from_inode(oa, inode, OBD_MD_FLTYPE | OBD_MD_FLATIME |
- OBD_MD_FLMTIME | OBD_MD_FLCTIME);
- obdo_set_parent_fid(oa, &ll_i2info(inode)->lli_fid);
- memcpy(lsm2, lsm, lsm_size);
- ll_inode_size_lock(inode);
- rc = obd_create(NULL, exp, oa, &lsm2, &oti);
- ll_inode_size_unlock(inode);
-
- kvfree(lsm2);
- goto out;
-out:
- ccc_inode_lsm_put(inode, lsm);
- kmem_cache_free(obdo_cachep, oa);
- return rc;
-}
-
-static int ll_lov_recreate_obj(struct inode *inode, unsigned long arg)
-{
- struct ll_recreate_obj ucreat;
- struct ost_id oi;
-
- if (!capable(CFS_CAP_SYS_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&ucreat, (struct ll_recreate_obj __user *)arg,
- sizeof(ucreat)))
- return -EFAULT;
-
- ostid_set_seq_mdt0(&oi);
- ostid_set_id(&oi, ucreat.lrc_id);
- return ll_lov_recreate(inode, &oi, ucreat.lrc_ost_idx);
-}
-
-static int ll_lov_recreate_fid(struct inode *inode, unsigned long arg)
-{
- struct lu_fid fid;
- struct ost_id oi;
- u32 ost_idx;
-
- if (!capable(CFS_CAP_SYS_ADMIN))
- return -EPERM;
-
- if (copy_from_user(&fid, (struct lu_fid __user *)arg, sizeof(fid)))
- return -EFAULT;
-
- fid_to_ostid(&fid, &oi);
- ost_idx = (fid_seq(&fid) >> 16) & 0xffff;
- return ll_lov_recreate(inode, &oi, ost_idx);
-}
-
int ll_lov_setstripe_ea_info(struct inode *inode, struct dentry *dentry,
__u64 flags, struct lov_user_md *lum,
int lum_size)
{
struct lov_stripe_md *lsm = NULL;
- struct lookup_intent oit = {.it_op = IT_OPEN, .it_flags = flags};
+ struct lookup_intent oit = {
+ .it_op = IT_OPEN,
+ .it_flags = flags | MDS_OPEN_BY_FID,
+ };
int rc = 0;
lsm = ccc_inode_lsm_get(inode);
ll_inode_size_lock(inode);
rc = ll_intent_file_open(dentry, lum, lum_size, &oit);
- if (rc)
+ if (rc < 0)
goto out_unlock;
rc = oit.it_status;
if (rc < 0)
- goto out_req_free;
+ goto out_unlock;
ll_release_openhandle(inode, &oit);
ccc_inode_lsm_put(inode, lsm);
out:
return rc;
-out_req_free:
- ptlrpc_req_finished((struct ptlrpc_request *)oit.it_request);
- goto out;
}
int ll_lov_getstripe_ea_info(struct inode *inode, const char *filename,
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- lmmsize = body->eadatasize;
+ lmmsize = body->mbo_eadatasize;
- if (!(body->valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
+ if (!(body->mbo_valid & (OBD_MD_FLEASIZE | OBD_MD_FLDIREA)) ||
lmmsize == 0) {
rc = -ENODATA;
goto out;
*/
if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V1)) {
lustre_swab_lov_user_md_v1((struct lov_user_md_v1 *)lmm);
- if (S_ISREG(body->mode))
+ if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v1 *)lmm)->lmm_objects,
stripe_count);
} else if (lmm->lmm_magic == cpu_to_le32(LOV_MAGIC_V3)) {
lustre_swab_lov_user_md_v3((struct lov_user_md_v3 *)lmm);
- if (S_ISREG(body->mode))
+ if (S_ISREG(body->mbo_mode))
lustre_swab_lov_user_md_objects(
((struct lov_user_md_v3 *)lmm)->lmm_objects,
stripe_count);
return rc;
}
+static int ll_file_getstripe(struct inode *inode,
+ struct lov_user_md __user *lum)
+{
+ struct lu_env *env;
+ int refcheck;
+ int rc;
+
+ env = cl_env_get(&refcheck);
+ if (IS_ERR(env))
+ return PTR_ERR(env);
+
+ rc = cl_object_getstripe(env, ll_i2info(inode)->lli_clob, lum);
+ cl_env_put(env, &refcheck);
+ return rc;
+}
+
static int ll_lov_setstripe(struct inode *inode, struct file *file,
unsigned long arg)
{
- struct lov_user_md_v3 lumv3;
- struct lov_user_md_v1 *lumv1 = (struct lov_user_md_v1 *)&lumv3;
- struct lov_user_md_v1 __user *lumv1p = (void __user *)arg;
- struct lov_user_md_v3 __user *lumv3p = (void __user *)arg;
+ struct lov_user_md __user *lum = (struct lov_user_md __user *)arg;
+ struct lov_user_md *klum;
int lum_size, rc;
__u64 flags = FMODE_WRITE;
- /* first try with v1 which is smaller than v3 */
- lum_size = sizeof(struct lov_user_md_v1);
- if (copy_from_user(lumv1, lumv1p, lum_size))
- return -EFAULT;
-
- if (lumv1->lmm_magic == LOV_USER_MAGIC_V3) {
- lum_size = sizeof(struct lov_user_md_v3);
- if (copy_from_user(&lumv3, lumv3p, lum_size))
- return -EFAULT;
- }
+ rc = ll_copy_user_md(lum, &klum);
+ if (rc < 0)
+ return rc;
- rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, lumv1,
+ lum_size = rc;
+ rc = ll_lov_setstripe_ea_info(inode, file->f_path.dentry, flags, klum,
lum_size);
cl_lov_delay_create_clear(&file->f_flags);
if (rc == 0) {
- struct lov_stripe_md *lsm;
__u32 gen;
- put_user(0, &lumv1p->lmm_stripe_count);
+ put_user(0, &lum->lmm_stripe_count);
ll_layout_refresh(inode, &gen);
- lsm = ccc_inode_lsm_get(inode);
- rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode),
- 0, lsm, (void __user *)arg);
- ccc_inode_lsm_put(inode, lsm);
+ rc = ll_file_getstripe(inode, (struct lov_user_md __user *)arg);
}
- return rc;
-}
-static int ll_lov_getstripe(struct inode *inode, unsigned long arg)
-{
- struct lov_stripe_md *lsm;
- int rc = -ENODATA;
-
- lsm = ccc_inode_lsm_get(inode);
- if (lsm)
- rc = obd_iocontrol(LL_IOC_LOV_GETSTRIPE, ll_i2dtexp(inode), 0,
- lsm, (void __user *)arg);
- ccc_inode_lsm_put(inode, lsm);
+ kfree(klum);
return rc;
}
return rc;
}
+static inline long ll_lease_type_from_fmode(fmode_t fmode)
+{
+ return ((fmode & FMODE_READ) ? LL_LEASE_RDLCK : 0) |
+ ((fmode & FMODE_WRITE) ? LL_LEASE_WRLCK : 0);
+}
+
static long
ll_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
return rc;
}
case LL_IOC_LOV_GETSTRIPE:
- return ll_lov_getstripe(inode, arg);
- case LL_IOC_RECREATE_OBJ:
- return ll_lov_recreate_obj(inode, arg);
- case LL_IOC_RECREATE_FID:
- return ll_lov_recreate_fid(inode, arg);
+ return ll_file_getstripe(inode,
+ (struct lov_user_md __user *)arg);
case FSFILT_IOC_FIEMAP:
return ll_ioctl_fiemap(inode, arg);
case FSFILT_IOC_GETFLAGS:
return 0;
}
+ case LL_IOC_GETPARENT:
+ return ll_getparent(file, (struct getparent __user *)arg);
case OBD_IOC_FID2PATH:
return ll_fid2path(inode, (void __user *)arg);
case LL_IOC_DATA_VERSION: {
struct ll_inode_info *lli = ll_i2info(inode);
struct obd_client_handle *och = NULL;
bool lease_broken;
- fmode_t mode = 0;
+ fmode_t fmode;
switch (arg) {
- case F_WRLCK:
+ case LL_LEASE_WRLCK:
if (!(file->f_mode & FMODE_WRITE))
return -EPERM;
- mode = FMODE_WRITE;
+ fmode = FMODE_WRITE;
break;
- case F_RDLCK:
+ case LL_LEASE_RDLCK:
if (!(file->f_mode & FMODE_READ))
return -EPERM;
- mode = FMODE_READ;
+ fmode = FMODE_READ;
break;
- case F_UNLCK:
+ case LL_LEASE_UNLCK:
mutex_lock(&lli->lli_och_mutex);
if (fd->fd_lease_och) {
och = fd->fd_lease_och;
}
mutex_unlock(&lli->lli_och_mutex);
- if (och) {
- mode = och->och_flags &
- (FMODE_READ|FMODE_WRITE);
- rc = ll_lease_close(och, inode, &lease_broken);
- if (rc == 0 && lease_broken)
- mode = 0;
- } else {
- rc = -ENOLCK;
- }
+ if (!och)
+ return -ENOLCK;
+
+ fmode = och->och_flags;
+ rc = ll_lease_close(och, inode, &lease_broken);
+ if (rc < 0)
+ return rc;
+
+ if (lease_broken)
+ fmode = 0;
- /* return the type of lease or error */
- return rc < 0 ? rc : (int)mode;
+ return ll_lease_type_from_fmode(fmode);
default:
return -EINVAL;
}
- CDEBUG(D_INODE, "Set lease with mode %d\n", mode);
+ CDEBUG(D_INODE, "Set lease with mode %u\n", fmode);
/* apply for lease */
- och = ll_lease_open(inode, file, mode, 0);
+ och = ll_lease_open(inode, file, fmode, 0);
if (IS_ERR(och))
return PTR_ERR(och);
case LL_IOC_GET_LEASE: {
struct ll_inode_info *lli = ll_i2info(inode);
struct ldlm_lock *lock = NULL;
+ fmode_t fmode = 0;
- rc = 0;
mutex_lock(&lli->lli_och_mutex);
if (fd->fd_lease_och) {
struct obd_client_handle *och = fd->fd_lease_och;
if (lock) {
lock_res_and_lock(lock);
if (!ldlm_is_cancel(lock))
- rc = och->och_flags &
- (FMODE_READ | FMODE_WRITE);
+ fmode = och->och_flags;
unlock_res_and_lock(lock);
LDLM_LOCK_PUT(lock);
}
}
mutex_unlock(&lli->lli_och_mutex);
- return rc;
+ return ll_lease_type_from_fmode(fmode);
}
case LL_IOC_HSM_IMPORT: {
struct hsm_user_import *hui;
eof = i_size_read(inode);
}
- retval = generic_file_llseek_size(file, offset, origin,
- ll_file_maxbytes(inode), eof);
- return retval;
+ return generic_file_llseek_size(file, offset, origin,
+ ll_file_maxbytes(inode), eof);
}
static int ll_flush(struct file *file, fl_owner_t id)
*/
rc = lli->lli_async_rc;
lli->lli_async_rc = 0;
- err = lov_read_and_clear_async_rc(lli->lli_clob);
- if (rc == 0)
- rc = err;
+ if (lli->lli_clob) {
+ err = lov_read_and_clear_async_rc(lli->lli_clob);
+ if (!rc)
+ rc = err;
+ }
/* The application has been told about write failure already.
* Do not report failure again.
struct md_op_data *op_data;
struct lustre_handle lockh = {0};
ldlm_policy_data_t flock = { {0} };
+ int fl_type = file_lock->fl_type;
__u64 flags = 0;
int rc;
int rc2 = 0;
if (file_lock->fl_lmops && file_lock->fl_lmops->lm_compare_owner)
flock.l_flock.owner = (unsigned long)file_lock->fl_pid;
- switch (file_lock->fl_type) {
+ switch (fl_type) {
case F_RDLCK:
einfo.ei_mode = LCK_PR;
break;
einfo.ei_mode = LCK_PW;
break;
default:
- CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n",
- file_lock->fl_type);
+ CDEBUG(D_INFO, "Unknown fcntl lock type: %d\n", fl_type);
return -ENOTSUPP;
}
case F_GETLK64:
#endif
flags = LDLM_FL_TEST_LOCK;
- /* Save the old mode so that if the mode in the lock changes we
- * can decrement the appropriate reader or writer refcount.
- */
- file_lock->fl_type = einfo.ei_mode;
break;
default:
CERROR("unknown fcntl lock command: %d\n", cmd);
return -EINVAL;
}
+ /*
+ * Save the old mode so that if the mode in the lock changes we
+ * can decrement the appropriate reader or writer refcount.
+ */
+ file_lock->fl_type = einfo.ei_mode;
+
op_data = ll_prep_md_op_data(NULL, inode, NULL, NULL, 0, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
PFID(ll_inode2fid(inode)), flock.l_flock.pid, flags,
einfo.ei_mode, flock.l_flock.start, flock.l_flock.end);
- rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL,
- op_data, &lockh, &flock, 0, NULL /* req */, flags);
+ rc = md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data, &lockh,
+ flags);
+
+ /* Restore the file lock type if not TEST lock. */
+ if (!(flags & LDLM_FL_TEST_LOCK))
+ file_lock->fl_type = fl_type;
if ((rc == 0 || file_lock->fl_type == F_UNLCK) &&
!(flags & LDLM_FL_TEST_LOCK))
if (rc2 && file_lock->fl_type != F_UNLCK) {
einfo.ei_mode = LCK_NL;
- md_enqueue(sbi->ll_md_exp, &einfo, NULL,
- op_data, &lockh, &flock, 0, NULL /* req */, flags);
+ md_enqueue(sbi->ll_md_exp, &einfo, &flock, NULL, op_data,
+ &lockh, flags);
rc = rc2;
}
return rc;
}
+int ll_get_fid_by_name(struct inode *parent, const char *name,
+ int namelen, struct lu_fid *fid)
+{
+ struct md_op_data *op_data = NULL;
+ struct ptlrpc_request *req;
+ struct mdt_body *body;
+ int rc;
+
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen, 0,
+ LUSTRE_OPC_ANY, NULL);
+ if (IS_ERR(op_data))
+ return PTR_ERR(op_data);
+
+ op_data->op_valid = OBD_MD_FLID;
+ rc = md_getattr_name(ll_i2sbi(parent)->ll_md_exp, op_data, &req);
+ ll_finish_md_op_data(op_data);
+ if (rc < 0)
+ return rc;
+
+ body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
+ if (!body) {
+ rc = -EFAULT;
+ goto out_req;
+ }
+ if (fid)
+ *fid = body->mbo_fid1;
+out_req:
+ ptlrpc_req_finished(req);
+ return rc;
+}
+
+int ll_migrate(struct inode *parent, struct file *file, int mdtidx,
+ const char *name, int namelen)
+{
+ struct ptlrpc_request *request = NULL;
+ struct inode *child_inode = NULL;
+ struct dentry *dchild = NULL;
+ struct md_op_data *op_data;
+ struct qstr qstr;
+ int rc;
+
+ CDEBUG(D_VFSTRACE, "migrate %s under "DFID" to MDT%d\n",
+ name, PFID(ll_inode2fid(parent)), mdtidx);
+
+ op_data = ll_prep_md_op_data(NULL, parent, NULL, name, namelen,
+ 0, LUSTRE_OPC_ANY, NULL);
+ if (IS_ERR(op_data))
+ return PTR_ERR(op_data);
+
+ /* Get child FID first */
+ qstr.hash = full_name_hash(parent, name, namelen);
+ qstr.name = name;
+ qstr.len = namelen;
+ dchild = d_lookup(file_dentry(file), &qstr);
+ if (dchild) {
+ op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
+ if (dchild->d_inode) {
+ child_inode = igrab(dchild->d_inode);
+ if (child_inode) {
+ inode_lock(child_inode);
+ op_data->op_fid3 = *ll_inode2fid(child_inode);
+ ll_invalidate_aliases(child_inode);
+ }
+ }
+ dput(dchild);
+ } else {
+ rc = ll_get_fid_by_name(parent, name, namelen,
+ &op_data->op_fid3);
+ if (rc)
+ goto out_free;
+ }
+
+ if (!fid_is_sane(&op_data->op_fid3)) {
+ CERROR("%s: migrate %s, but fid "DFID" is insane\n",
+ ll_get_fsname(parent->i_sb, NULL, 0), name,
+ PFID(&op_data->op_fid3));
+ rc = -EINVAL;
+ goto out_free;
+ }
+
+ rc = ll_get_mdt_idx_by_fid(ll_i2sbi(parent), &op_data->op_fid3);
+ if (rc < 0)
+ goto out_free;
+
+ if (rc == mdtidx) {
+ CDEBUG(D_INFO, "%s:"DFID" is already on MDT%d.\n", name,
+ PFID(&op_data->op_fid3), mdtidx);
+ rc = 0;
+ goto out_free;
+ }
+
+ op_data->op_mds = mdtidx;
+ op_data->op_cli_flags = CLI_MIGRATE;
+ rc = md_rename(ll_i2sbi(parent)->ll_md_exp, op_data, name,
+ namelen, name, namelen, &request);
+ if (!rc)
+ ll_update_times(request, parent);
+
+ ptlrpc_req_finished(request);
+
+out_free:
+ if (child_inode) {
+ clear_nlink(child_inode);
+ inode_unlock(child_inode);
+ iput(child_inode);
+ }
+
+ ll_finish_md_op_data(op_data);
+ return rc;
+}
+
static int
ll_file_noflock(struct file *file, int cmd, struct file_lock *file_lock)
{
struct lustre_handle lockh;
ldlm_policy_data_t policy;
enum ldlm_mode mode = (l_req_mode == LCK_MINMODE) ?
- (LCK_CR|LCK_CW|LCK_PR|LCK_PW) : l_req_mode;
+ (LCK_CR | LCK_CW | LCK_PR | LCK_PW) : l_req_mode;
struct lu_fid *fid;
__u64 flags;
int i;
{
ldlm_policy_data_t policy = { .l_inodebits = {bits} };
struct lu_fid *fid;
- enum ldlm_mode rc;
fid = &ll_i2info(inode)->lli_fid;
CDEBUG(D_INFO, "trying to match res "DFID"\n", PFID(fid));
- rc = md_lock_match(ll_i2mdexp(inode), flags | LDLM_FL_BLOCK_GRANTED,
- fid, LDLM_IBITS, &policy, mode, lockh);
-
- return rc;
+ return md_lock_match(ll_i2mdexp(inode), flags | LDLM_FL_BLOCK_GRANTED,
+ fid, LDLM_IBITS, &policy, mode, lockh);
}
static int ll_inode_revalidate_fini(struct inode *inode, int rc)
if (IS_ERR(op_data))
return PTR_ERR(op_data);
- oit.it_create_mode |= M_CHECK_STALE;
- rc = md_intent_lock(exp, op_data, NULL, 0,
- /* we are not interested in name
- * based lookup
- */
- &oit, 0, &req,
- ll_md_blocking_ast, 0);
+ rc = md_intent_lock(exp, op_data, &oit, &req,
+ &ll_md_blocking_ast, 0);
ll_finish_md_op_data(op_data);
- oit.it_create_mode &= ~M_CHECK_STALE;
if (rc < 0) {
rc = ll_inode_revalidate_fini(inode, rc);
goto out;
op_data->op_valid = valid;
rc = md_getattr(sbi->ll_md_exp, op_data, &req);
ll_finish_md_op_data(op_data);
- if (rc) {
- rc = ll_inode_revalidate_fini(inode, rc);
- return rc;
- }
+ if (rc)
+ return ll_inode_revalidate_fini(inode, rc);
rc = ll_prep_inode(&inode, req, NULL, NULL);
}
return rc;
}
+static int ll_merge_md_attr(struct inode *inode)
+{
+ struct cl_attr attr = { 0 };
+ int rc;
+
+ LASSERT(ll_i2info(inode)->lli_lsm_md);
+ rc = md_merge_attr(ll_i2mdexp(inode), ll_i2info(inode)->lli_lsm_md,
+ &attr, ll_md_blocking_ast);
+ if (rc)
+ return rc;
+
+ set_nlink(inode, attr.cat_nlink);
+ inode->i_blocks = attr.cat_blocks;
+ i_size_write(inode, attr.cat_size);
+
+ ll_i2info(inode)->lli_atime = attr.cat_atime;
+ ll_i2info(inode)->lli_mtime = attr.cat_mtime;
+ ll_i2info(inode)->lli_ctime = attr.cat_ctime;
+
+ return 0;
+}
+
static int ll_inode_revalidate(struct dentry *dentry, __u64 ibits)
{
struct inode *inode = d_inode(dentry);
/* if object isn't regular file, don't validate size */
if (!S_ISREG(inode->i_mode)) {
+ if (S_ISDIR(inode->i_mode) &&
+ ll_i2info(inode)->lli_lsm_md) {
+ rc = ll_merge_md_attr(inode);
+ if (rc)
+ return rc;
+ }
+
LTIME_S(inode->i_atime) = ll_i2info(inode)->lli_atime;
LTIME_S(inode->i_mtime) = ll_i2info(inode)->lli_mtime;
LTIME_S(inode->i_ctime) = ll_i2info(inode)->lli_ctime;
if (res)
return res;
+ OBD_FAIL_TIMEOUT(OBD_FAIL_GETATTR_DELAY, 30);
+
stat->dev = inode->i_sb->s_dev;
if (ll_need_32bit_api(sbi))
stat->ino = cl_fid_build_ino(&lli->lli_fid, 1);
else
stat->ino = inode->i_ino;
stat->mode = inode->i_mode;
- stat->nlink = inode->i_nlink;
stat->uid = inode->i_uid;
stat->gid = inode->i_gid;
stat->rdev = inode->i_rdev;
stat->ctime = inode->i_ctime;
stat->blksize = 1 << inode->i_blkbits;
+ stat->nlink = inode->i_nlink;
stat->size = i_size_read(inode);
stat->blocks = inode->i_blocks;
int ll_inode_permission(struct inode *inode, int mask)
{
+ struct ll_sb_info *sbi;
+ struct root_squash_info *squash;
+ const struct cred *old_cred = NULL;
+ struct cred *cred = NULL;
+ bool squash_id = false;
+ cfs_cap_t cap;
int rc = 0;
if (mask & MAY_NOT_BLOCK)
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p), inode mode %x mask %o\n",
PFID(ll_inode2fid(inode)), inode, inode->i_mode, mask);
+ /* squash fsuid/fsgid if needed */
+ sbi = ll_i2sbi(inode);
+ squash = &sbi->ll_squash;
+ if (unlikely(squash->rsi_uid &&
+ uid_eq(current_fsuid(), GLOBAL_ROOT_UID) &&
+ !(sbi->ll_flags & LL_SBI_NOROOTSQUASH))) {
+ squash_id = true;
+ }
+
+ if (squash_id) {
+ CDEBUG(D_OTHER, "squash creds (%d:%d)=>(%d:%d)\n",
+ __kuid_val(current_fsuid()), __kgid_val(current_fsgid()),
+ squash->rsi_uid, squash->rsi_gid);
+
+ /*
+ * update current process's credentials
+ * and FS capability
+ */
+ cred = prepare_creds();
+ if (!cred)
+ return -ENOMEM;
+
+ cred->fsuid = make_kuid(&init_user_ns, squash->rsi_uid);
+ cred->fsgid = make_kgid(&init_user_ns, squash->rsi_gid);
+ for (cap = 0; cap < sizeof(cfs_cap_t) * 8; cap++) {
+ if ((1 << cap) & CFS_CAP_FS_MASK)
+ cap_lower(cred->cap_effective, cap);
+ }
+ old_cred = override_creds(cred);
+ }
+
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_INODE_PERM, 1);
rc = generic_permission(inode, mask);
+ /* restore current process's credentials and FS capability */
+ if (squash_id) {
+ revert_creds(old_cred);
+ put_cred(cred);
+ }
+
return rc;
}
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush
};
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_flock,
.release = ll_file_release,
.mmap = ll_file_mmap,
.llseek = ll_file_seek,
- .splice_read = ll_file_splice_read,
+ .splice_read = generic_file_splice_read,
.fsync = ll_fsync,
.flush = ll_flush,
.flock = ll_file_noflock,
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
- .setxattr = ll_setxattr,
- .getxattr = ll_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = ll_listxattr,
- .removexattr = ll_removexattr,
+ .removexattr = generic_removexattr,
.fiemap = ll_fiemap,
.get_acl = ll_get_acl,
};
if (!in_data)
return NULL;
- memset(in_data, 0, sizeof(*in_data));
in_data->iocd_size = size;
in_data->iocd_cb = cb;
in_data->iocd_count = count;
goto out;
}
- lmmsize = body->eadatasize;
+ lmmsize = body->mbo_eadatasize;
if (lmmsize == 0) /* empty layout */ {
rc = 0;
goto out;
PFID(&lli->lli_fid), inode, reconf);
/* in case this is a caching lock and reinstate with new inode */
- md_set_lock_data(sbi->ll_md_exp, &lockh->cookie, inode, NULL);
+ md_set_lock_data(sbi->ll_md_exp, lockh, inode, NULL);
lock_res_and_lock(lock);
lvb_ready = ldlm_is_lvb_ready(lock);
struct ldlm_enqueue_info einfo = {
.ei_type = LDLM_IBITS,
.ei_mode = LCK_CR,
- .ei_cb_bl = ll_md_blocking_ast,
- .ei_cb_cp = ldlm_completion_ast,
+ .ei_cb_bl = &ll_md_blocking_ast,
+ .ei_cb_cp = &ldlm_completion_ast,
};
int rc;
ll_get_fsname(inode->i_sb, NULL, 0),
PFID(&lli->lli_fid), inode);
- rc = md_enqueue(sbi->ll_md_exp, &einfo, &it, op_data, &lockh,
- NULL, 0, NULL, 0);
+ rc = md_enqueue(sbi->ll_md_exp, &einfo, NULL, &it, op_data, &lockh, 0);
ptlrpc_req_finished(it.it_request);
it.it_request = NULL;
#include <linux/types.h>
#include <linux/mm.h>
-#include "../include/lustre_lite.h"
+#include "../include/lustre/lustre_ioctl.h"
#include "../include/lustre_ha.h"
#include "../include/lustre_dlm.h"
#include "../include/lprocfs_status.h"
sbi->ll_sa_max = LL_SA_RPC_DEF;
atomic_set(&sbi->ll_sa_total, 0);
atomic_set(&sbi->ll_sa_wrong, 0);
+ atomic_set(&sbi->ll_sa_running, 0);
atomic_set(&sbi->ll_agl_total, 0);
sbi->ll_flags |= LL_SBI_AGL_ENABLED;
+ /* root squash */
+ sbi->ll_squash.rsi_uid = 0;
+ sbi->ll_squash.rsi_gid = 0;
+ INIT_LIST_HEAD(&sbi->ll_squash.rsi_nosquash_nids);
+ init_rwsem(&sbi->ll_squash.rsi_sem);
+
sbi->ll_sb = sb;
return sbi;
struct ll_sb_info *sbi = ll_s2sbi(sb);
if (sbi->ll_cache) {
+ if (!list_empty(&sbi->ll_squash.rsi_nosquash_nids))
+ cfs_free_nidlist(&sbi->ll_squash.rsi_nosquash_nids);
cl_cache_decref(sbi->ll_cache);
sbi->ll_cache = NULL;
}
OBD_CONNECT_PINGLESS |
OBD_CONNECT_MAX_EASIZE |
OBD_CONNECT_FLOCK_DEAD |
- OBD_CONNECT_DISP_STRIPE;
+ OBD_CONNECT_DISP_STRIPE | OBD_CONNECT_LFSCK |
+ OBD_CONNECT_OPEN_BY_FID |
+ OBD_CONNECT_DIR_STRIPE;
if (sbi->ll_flags & LL_SBI_SOM_PREVIEW)
data->ocd_connect_flags |= OBD_CONNECT_SOM;
sbi->ll_flags |= LL_SBI_64BIT_HASH;
if (data->ocd_connect_flags & OBD_CONNECT_BRW_SIZE)
- sbi->ll_md_brw_size = data->ocd_brw_size;
+ sbi->ll_md_brw_pages = data->ocd_brw_size >> PAGE_SHIFT;
else
- sbi->ll_md_brw_size = PAGE_SIZE;
+ sbi->ll_md_brw_pages = 1;
if (data->ocd_connect_flags & OBD_CONNECT_LAYOUTLOCK)
sbi->ll_flags |= LL_SBI_LAYOUT_LOCK;
CDEBUG(D_SUPER, "rootfid "DFID"\n", PFID(&sbi->ll_root_fid));
sb->s_op = &lustre_super_operations;
+ sb->s_xattr = ll_xattr_handlers;
#if THREAD_SIZE >= 8192 /*b=17630*/
sb->s_export_op = &lustre_export_operations;
#endif
md_free_lustre_md(sbi->ll_md_exp, &lmd);
ptlrpc_req_finished(request);
- if (!(root)) {
+ if (IS_ERR(root)) {
if (lmd.lsm)
obd_free_memmd(sbi->ll_dt_exp, &lmd.lsm);
#ifdef CONFIG_FS_POSIX_ACL
err = obd_set_info_async(NULL, sbi->ll_dt_exp, sizeof(KEY_CHECKSUM),
KEY_CHECKSUM, sizeof(checksum), &checksum,
NULL);
+ if (err) {
+ CERROR("%s: Set checksum failed: rc = %d\n",
+ sbi->ll_dt_exp->exp_obd->obd_name, err);
+ goto out_root;
+ }
cl_sb_init(sb);
err = obd_set_info_async(NULL, sbi->ll_dt_exp, sizeof(KEY_CACHE_SET),
KEY_CACHE_SET, sizeof(*sbi->ll_cache),
sbi->ll_cache, NULL);
+ if (err) {
+ CERROR("%s: Set cache_set failed: rc = %d\n",
+ sbi->ll_dt_exp->exp_obd->obd_name, err);
+ goto out_root;
+ }
sb->s_root = d_make_root(root);
if (!sb->s_root) {
return rc;
}
+/**
+ * Get the value of the default_easize parameter.
+ *
+ * \see client_obd::cl_default_mds_easize
+ *
+ * \param[in] sbi superblock info for this filesystem
+ * \param[out] lmmsize pointer to storage location for value
+ *
+ * \retval 0 on success
+ * \retval negative negated errno on failure
+ */
int ll_get_default_mdsize(struct ll_sb_info *sbi, int *lmmsize)
{
int size, rc;
return rc;
}
+/**
+ * Set the default_easize parameter to the given value.
+ *
+ * \see client_obd::cl_default_mds_easize
+ *
+ * \param[in] sbi superblock info for this filesystem
+ * \param[in] lmmsize the size to set
+ *
+ * \retval 0 on success
+ * \retval negative negated errno on failure
+ */
+int ll_set_default_mdsize(struct ll_sb_info *sbi, int lmmsize)
+{
+ if (lmmsize < sizeof(struct lov_mds_md) ||
+ lmmsize > OBD_MAX_DEFAULT_EA_SIZE)
+ return -EINVAL;
+
+ return obd_set_info_async(NULL, sbi->ll_md_exp,
+ sizeof(KEY_DEFAULT_EASIZE),
+ KEY_DEFAULT_EASIZE,
+ sizeof(int), &lmmsize, NULL);
+}
+
static void client_common_put_super(struct super_block *sb)
{
struct ll_sb_info *sbi = ll_s2sbi(sb);
if (sbi) {
sb->s_dev = sbi->ll_sdev_orig;
sbi->ll_umounting = 1;
+
+ /* wait running statahead threads to quit */
+ while (atomic_read(&sbi->ll_sa_running) > 0) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(msecs_to_jiffies(MSEC_PER_SEC >> 3));
+ }
}
}
*flags |= tmp;
goto next;
}
- tmp = ll_set_opt("noflock", s1, LL_SBI_FLOCK|LL_SBI_LOCALFLOCK);
+ tmp = ll_set_opt("noflock", s1,
+ LL_SBI_FLOCK | LL_SBI_LOCALFLOCK);
if (tmp) {
*flags &= ~tmp;
goto next;
lli->lli_sai = NULL;
spin_lock_init(&lli->lli_sa_lock);
lli->lli_opendir_pid = 0;
+ lli->lli_sa_enabled = 0;
+ lli->lli_def_stripe_offset = -1;
} else {
mutex_init(&lli->lli_size_mutex);
lli->lli_symlink_name = NULL;
init_rwsem(&lli->lli_trunc_sem);
- mutex_init(&lli->lli_write_mutex);
+ range_lock_tree_init(&lli->lli_write_tree);
init_rwsem(&lli->lli_glimpse_sem);
lli->lli_glimpse_time = 0;
INIT_LIST_HEAD(&lli->lli_agl_list);
struct lustre_sb_info *lsi = s2lsi(sb);
struct ll_sb_info *sbi = ll_s2sbi(sb);
char *profilenm = get_profile_name(sb);
- int ccc_count, next, force = 1, rc = 0;
+ int next, force = 1, rc = 0;
+ long ccc_count;
CDEBUG(D_VFSTRACE, "VFS Op: sb %p - %s\n", sb, profilenm);
struct l_wait_info lwi = LWI_INTR(LWI_ON_SIGNAL_NOOP, NULL);
rc = l_wait_event(sbi->ll_cache->ccc_unstable_waitq,
- !atomic_read(&sbi->ll_cache->ccc_unstable_nr),
+ !atomic_long_read(&sbi->ll_cache->ccc_unstable_nr),
&lwi);
}
- ccc_count = atomic_read(&sbi->ll_cache->ccc_unstable_nr);
+ ccc_count = atomic_long_read(&sbi->ll_cache->ccc_unstable_nr);
if (!force && rc != -EINTR)
- LASSERTF(!ccc_count, "count: %i\n", ccc_count);
+ LASSERTF(!ccc_count, "count: %li\n", ccc_count);
/* We need to set force before the lov_disconnect in
* lustre_common_put_super, since l_d cleans up osc's as well.
return inode;
}
+static void ll_dir_clear_lsm_md(struct inode *inode)
+{
+ struct ll_inode_info *lli = ll_i2info(inode);
+
+ LASSERT(S_ISDIR(inode->i_mode));
+
+ if (lli->lli_lsm_md) {
+ lmv_free_memmd(lli->lli_lsm_md);
+ lli->lli_lsm_md = NULL;
+ }
+}
+
+static struct inode *ll_iget_anon_dir(struct super_block *sb,
+ const struct lu_fid *fid,
+ struct lustre_md *md)
+{
+ struct ll_sb_info *sbi = ll_s2sbi(sb);
+ struct mdt_body *body = md->body;
+ struct inode *inode;
+ ino_t ino;
+
+ ino = cl_fid_build_ino(fid, sbi->ll_flags & LL_SBI_32BIT_API);
+ inode = iget_locked(sb, ino);
+ if (!inode) {
+ CERROR("%s: failed get simple inode "DFID": rc = -ENOENT\n",
+ ll_get_fsname(sb, NULL, 0), PFID(fid));
+ return ERR_PTR(-ENOENT);
+ }
+
+ if (inode->i_state & I_NEW) {
+ struct ll_inode_info *lli = ll_i2info(inode);
+ struct lmv_stripe_md *lsm = md->lmv;
+
+ inode->i_mode = (inode->i_mode & ~S_IFMT) |
+ (body->mbo_mode & S_IFMT);
+ LASSERTF(S_ISDIR(inode->i_mode), "Not slave inode "DFID"\n",
+ PFID(fid));
+
+ LTIME_S(inode->i_mtime) = 0;
+ LTIME_S(inode->i_atime) = 0;
+ LTIME_S(inode->i_ctime) = 0;
+ inode->i_rdev = 0;
+
+ inode->i_op = &ll_dir_inode_operations;
+ inode->i_fop = &ll_dir_operations;
+ lli->lli_fid = *fid;
+ ll_lli_init(lli);
+
+ LASSERT(lsm);
+ /* master object FID */
+ lli->lli_pfid = body->mbo_fid1;
+ CDEBUG(D_INODE, "lli %p slave "DFID" master "DFID"\n",
+ lli, PFID(fid), PFID(&lli->lli_pfid));
+ unlock_new_inode(inode);
+ }
+
+ return inode;
+}
+
+static int ll_init_lsm_md(struct inode *inode, struct lustre_md *md)
+{
+ struct lmv_stripe_md *lsm = md->lmv;
+ struct lu_fid *fid;
+ int i;
+
+ LASSERT(lsm);
+ /*
+ * XXX sigh, this lsm_root initialization should be in
+ * LMV layer, but it needs ll_iget right now, so we
+ * put this here right now.
+ */
+ for (i = 0; i < lsm->lsm_md_stripe_count; i++) {
+ fid = &lsm->lsm_md_oinfo[i].lmo_fid;
+ LASSERT(!lsm->lsm_md_oinfo[i].lmo_root);
+ /* Unfortunately ll_iget will call ll_update_inode,
+ * where the initialization of slave inode is slightly
+ * different, so it reset lsm_md to NULL to avoid
+ * initializing lsm for slave inode.
+ */
+ /* For migrating inode, master stripe and master object will
+ * be same, so we only need assign this inode
+ */
+ if (lsm->lsm_md_hash_type & LMV_HASH_FLAG_MIGRATION && !i)
+ lsm->lsm_md_oinfo[i].lmo_root = inode;
+ else
+ lsm->lsm_md_oinfo[i].lmo_root =
+ ll_iget_anon_dir(inode->i_sb, fid, md);
+ if (IS_ERR(lsm->lsm_md_oinfo[i].lmo_root)) {
+ int rc = PTR_ERR(lsm->lsm_md_oinfo[i].lmo_root);
+
+ lsm->lsm_md_oinfo[i].lmo_root = NULL;
+ return rc;
+ }
+ }
+
+ return 0;
+}
+
+static inline int lli_lsm_md_eq(const struct lmv_stripe_md *lsm_md1,
+ const struct lmv_stripe_md *lsm_md2)
+{
+ return lsm_md1->lsm_md_magic == lsm_md2->lsm_md_magic &&
+ lsm_md1->lsm_md_stripe_count == lsm_md2->lsm_md_stripe_count &&
+ lsm_md1->lsm_md_master_mdt_index ==
+ lsm_md2->lsm_md_master_mdt_index &&
+ lsm_md1->lsm_md_hash_type == lsm_md2->lsm_md_hash_type &&
+ lsm_md1->lsm_md_layout_version ==
+ lsm_md2->lsm_md_layout_version &&
+ !strcmp(lsm_md1->lsm_md_pool_name,
+ lsm_md2->lsm_md_pool_name);
+}
+
+static int ll_update_lsm_md(struct inode *inode, struct lustre_md *md)
+{
+ struct ll_inode_info *lli = ll_i2info(inode);
+ struct lmv_stripe_md *lsm = md->lmv;
+ int rc;
+
+ LASSERT(S_ISDIR(inode->i_mode));
+ CDEBUG(D_INODE, "update lsm %p of "DFID"\n", lli->lli_lsm_md,
+ PFID(ll_inode2fid(inode)));
+
+ /* no striped information from request. */
+ if (!lsm) {
+ if (!lli->lli_lsm_md) {
+ return 0;
+ } else if (lli->lli_lsm_md->lsm_md_hash_type &
+ LMV_HASH_FLAG_MIGRATION) {
+ /*
+ * migration is done, the temporay MIGRATE layout has
+ * been removed
+ */
+ CDEBUG(D_INODE, DFID" finish migration.\n",
+ PFID(ll_inode2fid(inode)));
+ lmv_free_memmd(lli->lli_lsm_md);
+ lli->lli_lsm_md = NULL;
+ return 0;
+ } else {
+ /*
+ * The lustre_md from req does not include stripeEA,
+ * see ll_md_setattr
+ */
+ return 0;
+ }
+ }
+
+ /* set the directory layout */
+ if (!lli->lli_lsm_md) {
+ rc = ll_init_lsm_md(inode, md);
+ if (rc)
+ return rc;
+
+ lli->lli_lsm_md = lsm;
+ /*
+ * set lsm_md to NULL, so the following free lustre_md
+ * will not free this lsm
+ */
+ md->lmv = NULL;
+ CDEBUG(D_INODE, "Set lsm %p magic %x to "DFID"\n", lsm,
+ lsm->lsm_md_magic, PFID(ll_inode2fid(inode)));
+ return 0;
+ }
+
+ /* Compare the old and new stripe information */
+ if (!lsm_md_eq(lli->lli_lsm_md, lsm)) {
+ struct lmv_stripe_md *old_lsm = lli->lli_lsm_md;
+ int idx;
+
+ CERROR("%s: inode "DFID"(%p)'s lmv layout mismatch (%p)/(%p) magic:0x%x/0x%x stripe count: %d/%d master_mdt: %d/%d hash_type:0x%x/0x%x layout: 0x%x/0x%x pool:%s/%s\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), PFID(&lli->lli_fid),
+ inode, lsm, old_lsm,
+ lsm->lsm_md_magic, old_lsm->lsm_md_magic,
+ lsm->lsm_md_stripe_count,
+ old_lsm->lsm_md_stripe_count,
+ lsm->lsm_md_master_mdt_index,
+ old_lsm->lsm_md_master_mdt_index,
+ lsm->lsm_md_hash_type, old_lsm->lsm_md_hash_type,
+ lsm->lsm_md_layout_version,
+ old_lsm->lsm_md_layout_version,
+ lsm->lsm_md_pool_name,
+ old_lsm->lsm_md_pool_name);
+
+ for (idx = 0; idx < old_lsm->lsm_md_stripe_count; idx++) {
+ CERROR("%s: sub FIDs in old lsm idx %d, old: "DFID"\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), idx,
+ PFID(&old_lsm->lsm_md_oinfo[idx].lmo_fid));
+ }
+
+ for (idx = 0; idx < lsm->lsm_md_stripe_count; idx++) {
+ CERROR("%s: sub FIDs in new lsm idx %d, new: "DFID"\n",
+ ll_get_fsname(inode->i_sb, NULL, 0), idx,
+ PFID(&lsm->lsm_md_oinfo[idx].lmo_fid));
+ }
+
+ return -EIO;
+ }
+
+ return 0;
+}
+
void ll_clear_inode(struct inode *inode)
{
struct ll_inode_info *lli = ll_i2info(inode);
#ifdef CONFIG_FS_POSIX_ACL
if (lli->lli_posix_acl) {
- LASSERT(atomic_read(&lli->lli_posix_acl->a_refcount) == 1);
posix_acl_release(lli->lli_posix_acl);
lli->lli_posix_acl = NULL;
}
#endif
lli->lli_inode_magic = LLI_INODE_DEAD;
- if (!S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode))
+ ll_dir_clear_lsm_md(inode);
+ if (S_ISREG(inode->i_mode) && !is_bad_inode(inode))
LASSERT(list_empty(&lli->lli_agl_list));
/*
op_data->op_attr.ia_valid = ia_valid;
/* Extract epoch data if obtained. */
- op_data->op_handle = md.body->handle;
- op_data->op_ioepoch = md.body->ioepoch;
+ op_data->op_handle = md.body->mbo_handle;
+ op_data->op_ioepoch = md.body->mbo_ioepoch;
- ll_update_inode(inode, &md);
+ rc = ll_update_inode(inode, &md);
ptlrpc_req_finished(request);
return rc;
rc = ll_som_update(inode, op_data);
else if (rc) {
CERROR("%s: inode "DFID" mdc truncate failed: rc = %d\n",
- ll_i2sbi(inode)->ll_md_exp->exp_obd->obd_name,
- PFID(ll_inode2fid(inode)), rc);
+ ll_i2sbi(inode)->ll_md_exp->exp_obd->obd_name,
+ PFID(ll_inode2fid(inode)), rc);
}
return rc;
}
attr->ia_valid |= ATTR_MTIME | ATTR_CTIME;
}
- /* POSIX: check before ATTR_*TIME_SET set (from inode_change_ok) */
+ /* POSIX: check before ATTR_*TIME_SET set (from setattr_prepare) */
if (attr->ia_valid & TIMES_SET_FLAGS) {
if ((!uid_eq(current_fsuid(), inode->i_uid)) &&
!capable(CFS_CAP_FOWNER))
{
int mode = d_inode(de)->i_mode;
- if ((attr->ia_valid & (ATTR_CTIME|ATTR_SIZE|ATTR_MODE)) ==
- (ATTR_CTIME|ATTR_SIZE|ATTR_MODE))
+ if ((attr->ia_valid & (ATTR_CTIME | ATTR_SIZE | ATTR_MODE)) ==
+ (ATTR_CTIME | ATTR_SIZE | ATTR_MODE))
attr->ia_valid |= MDS_OPEN_OWNEROVERRIDE;
- if (((attr->ia_valid & (ATTR_MODE|ATTR_FORCE|ATTR_SIZE)) ==
- (ATTR_SIZE|ATTR_MODE)) &&
+ if (((attr->ia_valid & (ATTR_MODE | ATTR_FORCE | ATTR_SIZE)) ==
+ (ATTR_SIZE | ATTR_MODE)) &&
(((mode & S_ISUID) && !(attr->ia_mode & S_ISUID)) ||
- (((mode & (S_ISGID|S_IXGRP)) == (S_ISGID|S_IXGRP)) &&
+ (((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) &&
!(attr->ia_mode & S_ISGID))))
attr->ia_valid |= ATTR_FORCE;
attr->ia_valid |= ATTR_KILL_SUID;
if ((attr->ia_valid & ATTR_MODE) &&
- ((mode & (S_ISGID|S_IXGRP)) == (S_ISGID|S_IXGRP)) &&
+ ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) &&
!(attr->ia_mode & S_ISGID) &&
!(attr->ia_valid & ATTR_KILL_SGID))
attr->ia_valid |= ATTR_KILL_SGID;
mutex_unlock(&lli->lli_size_mutex);
}
-void ll_update_inode(struct inode *inode, struct lustre_md *md)
+int ll_update_inode(struct inode *inode, struct lustre_md *md)
{
struct ll_inode_info *lli = ll_i2info(inode);
struct mdt_body *body = md->body;
struct lov_stripe_md *lsm = md->lsm;
struct ll_sb_info *sbi = ll_i2sbi(inode);
- LASSERT((lsm != NULL) == ((body->valid & OBD_MD_FLEASIZE) != 0));
+ LASSERT((lsm != NULL) == ((body->mbo_valid & OBD_MD_FLEASIZE) != 0));
if (lsm) {
if (!lli->lli_has_smd &&
!(sbi->ll_flags & LL_SBI_LAYOUT_LOCK))
lli->lli_maxbytes = MAX_LFS_FILESIZE;
}
+ if (S_ISDIR(inode->i_mode)) {
+ int rc;
+
+ rc = ll_update_lsm_md(inode, md);
+ if (rc)
+ return rc;
+ }
+
#ifdef CONFIG_FS_POSIX_ACL
- if (body->valid & OBD_MD_FLACL) {
+ if (body->mbo_valid & OBD_MD_FLACL) {
spin_lock(&lli->lli_lock);
if (lli->lli_posix_acl)
posix_acl_release(lli->lli_posix_acl);
spin_unlock(&lli->lli_lock);
}
#endif
- inode->i_ino = cl_fid_build_ino(&body->fid1,
+ inode->i_ino = cl_fid_build_ino(&body->mbo_fid1,
sbi->ll_flags & LL_SBI_32BIT_API);
- inode->i_generation = cl_fid_build_gen(&body->fid1);
+ inode->i_generation = cl_fid_build_gen(&body->mbo_fid1);
- if (body->valid & OBD_MD_FLATIME) {
- if (body->atime > LTIME_S(inode->i_atime))
- LTIME_S(inode->i_atime) = body->atime;
- lli->lli_atime = body->atime;
+ if (body->mbo_valid & OBD_MD_FLATIME) {
+ if (body->mbo_atime > LTIME_S(inode->i_atime))
+ LTIME_S(inode->i_atime) = body->mbo_atime;
+ lli->lli_atime = body->mbo_atime;
}
- if (body->valid & OBD_MD_FLMTIME) {
- if (body->mtime > LTIME_S(inode->i_mtime)) {
+ if (body->mbo_valid & OBD_MD_FLMTIME) {
+ if (body->mbo_mtime > LTIME_S(inode->i_mtime)) {
CDEBUG(D_INODE, "setting ino %lu mtime from %lu to %llu\n",
inode->i_ino, LTIME_S(inode->i_mtime),
- body->mtime);
- LTIME_S(inode->i_mtime) = body->mtime;
+ body->mbo_mtime);
+ LTIME_S(inode->i_mtime) = body->mbo_mtime;
}
- lli->lli_mtime = body->mtime;
- }
- if (body->valid & OBD_MD_FLCTIME) {
- if (body->ctime > LTIME_S(inode->i_ctime))
- LTIME_S(inode->i_ctime) = body->ctime;
- lli->lli_ctime = body->ctime;
- }
- if (body->valid & OBD_MD_FLMODE)
- inode->i_mode = (inode->i_mode & S_IFMT)|(body->mode & ~S_IFMT);
- if (body->valid & OBD_MD_FLTYPE)
- inode->i_mode = (inode->i_mode & ~S_IFMT)|(body->mode & S_IFMT);
+ lli->lli_mtime = body->mbo_mtime;
+ }
+ if (body->mbo_valid & OBD_MD_FLCTIME) {
+ if (body->mbo_ctime > LTIME_S(inode->i_ctime))
+ LTIME_S(inode->i_ctime) = body->mbo_ctime;
+ lli->lli_ctime = body->mbo_ctime;
+ }
+ if (body->mbo_valid & OBD_MD_FLMODE)
+ inode->i_mode = (inode->i_mode & S_IFMT) |
+ (body->mbo_mode & ~S_IFMT);
+ if (body->mbo_valid & OBD_MD_FLTYPE)
+ inode->i_mode = (inode->i_mode & ~S_IFMT) |
+ (body->mbo_mode & S_IFMT);
LASSERT(inode->i_mode != 0);
if (S_ISREG(inode->i_mode))
inode->i_blkbits = min(PTLRPC_MAX_BRW_BITS + 1,
LL_MAX_BLKSIZE_BITS);
else
inode->i_blkbits = inode->i_sb->s_blocksize_bits;
- if (body->valid & OBD_MD_FLUID)
- inode->i_uid = make_kuid(&init_user_ns, body->uid);
- if (body->valid & OBD_MD_FLGID)
- inode->i_gid = make_kgid(&init_user_ns, body->gid);
- if (body->valid & OBD_MD_FLFLAGS)
- inode->i_flags = ll_ext_to_inode_flags(body->flags);
- if (body->valid & OBD_MD_FLNLINK)
- set_nlink(inode, body->nlink);
- if (body->valid & OBD_MD_FLRDEV)
- inode->i_rdev = old_decode_dev(body->rdev);
-
- if (body->valid & OBD_MD_FLID) {
+ if (body->mbo_valid & OBD_MD_FLUID)
+ inode->i_uid = make_kuid(&init_user_ns, body->mbo_uid);
+ if (body->mbo_valid & OBD_MD_FLGID)
+ inode->i_gid = make_kgid(&init_user_ns, body->mbo_gid);
+ if (body->mbo_valid & OBD_MD_FLFLAGS)
+ inode->i_flags = ll_ext_to_inode_flags(body->mbo_flags);
+ if (body->mbo_valid & OBD_MD_FLNLINK)
+ set_nlink(inode, body->mbo_nlink);
+ if (body->mbo_valid & OBD_MD_FLRDEV)
+ inode->i_rdev = old_decode_dev(body->mbo_rdev);
+
+ if (body->mbo_valid & OBD_MD_FLID) {
/* FID shouldn't be changed! */
if (fid_is_sane(&lli->lli_fid)) {
- LASSERTF(lu_fid_eq(&lli->lli_fid, &body->fid1),
+ LASSERTF(lu_fid_eq(&lli->lli_fid, &body->mbo_fid1),
"Trying to change FID "DFID" to the "DFID", inode "DFID"(%p)\n",
- PFID(&lli->lli_fid), PFID(&body->fid1),
+ PFID(&lli->lli_fid), PFID(&body->mbo_fid1),
PFID(ll_inode2fid(inode)), inode);
} else {
- lli->lli_fid = body->fid1;
+ lli->lli_fid = body->mbo_fid1;
}
}
LASSERT(fid_seq(&lli->lli_fid) != 0);
- if (body->valid & OBD_MD_FLSIZE) {
+ if (body->mbo_valid & OBD_MD_FLSIZE) {
if (exp_connect_som(ll_i2mdexp(inode)) &&
S_ISREG(inode->i_mode)) {
struct lustre_handle lockh;
/* Use old size assignment to avoid
* deadlock bz14138 & bz14326
*/
- i_size_write(inode, body->size);
+ i_size_write(inode, body->mbo_size);
spin_lock(&lli->lli_lock);
lli->lli_flags |= LLIF_MDS_SIZE_LOCK;
spin_unlock(&lli->lli_lock);
/* Use old size assignment to avoid
* deadlock bz14138 & bz14326
*/
- i_size_write(inode, body->size);
+ i_size_write(inode, body->mbo_size);
CDEBUG(D_VFSTRACE, "inode=%lu, updating i_size %llu\n",
- inode->i_ino, (unsigned long long)body->size);
+ inode->i_ino, (unsigned long long)body->mbo_size);
}
- if (body->valid & OBD_MD_FLBLOCKS)
- inode->i_blocks = body->blocks;
+ if (body->mbo_valid & OBD_MD_FLBLOCKS)
+ inode->i_blocks = body->mbo_blocks;
}
- if (body->valid & OBD_MD_TSTATE) {
- if (body->t_state & MS_RESTORE)
+ if (body->mbo_valid & OBD_MD_TSTATE) {
+ if (body->mbo_t_state & MS_RESTORE)
lli->lli_flags |= LLIF_FILE_RESTORING;
}
+
+ return 0;
}
-void ll_read_inode2(struct inode *inode, void *opaque)
+int ll_read_inode2(struct inode *inode, void *opaque)
{
struct lustre_md *md = opaque;
struct ll_inode_info *lli = ll_i2info(inode);
+ int rc;
CDEBUG(D_VFSTRACE, "VFS Op:inode="DFID"(%p)\n",
PFID(&lli->lli_fid), inode);
LTIME_S(inode->i_atime) = 0;
LTIME_S(inode->i_ctime) = 0;
inode->i_rdev = 0;
- ll_update_inode(inode, md);
+ rc = ll_update_inode(inode, md);
+ if (rc)
+ return rc;
/* OIDEBUG(inode); */
init_special_inode(inode, inode->i_mode,
inode->i_rdev);
}
+
+ return 0;
}
void ll_delete_inode(struct inode *inode)
* osc_extent implementation at LU-1030.
*/
cl_sync_file_range(inode, 0, OBD_OBJECT_EOF,
- CL_FSYNC_DISCARD, 1);
+ CL_FSYNC_LOCAL, 1);
truncate_inode_pages_final(&inode->i_data);
- /* Workaround for LU-118 */
- if (inode->i_data.nrpages) {
- spin_lock_irq(&inode->i_data.tree_lock);
- spin_unlock_irq(&inode->i_data.tree_lock);
- LASSERTF(inode->i_data.nrpages == 0,
- "inode="DFID"(%p) nrpages=%lu, see http://jira.whamcloud.com/browse/LU-118\n",
- PFID(ll_inode2fid(inode)), inode,
- inode->i_data.nrpages);
- }
- /* Workaround end */
+ LASSERTF(!inode->i_data.nrpages,
+ "inode=" DFID "(%p) nrpages=%lu, see http://jira.whamcloud.com/browse/LU-118\n",
+ PFID(ll_inode2fid(inode)), inode, inode->i_data.nrpages);
ll_clear_inode(inode);
clear_inode(inode);
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
- flags = body->flags;
+ flags = body->mbo_flags;
ptlrpc_req_finished(req);
if (!op_data)
return;
- op_data->op_fid1 = body->fid1;
- op_data->op_ioepoch = body->ioepoch;
- op_data->op_handle = body->handle;
+ op_data->op_fid1 = body->mbo_fid1;
+ op_data->op_ioepoch = body->mbo_ioepoch;
+ op_data->op_handle = body->mbo_handle;
op_data->op_mod_time = get_seconds();
md_close(exp, op_data, NULL, &close_req);
ptlrpc_req_finished(close_req);
goto cleanup;
if (*inode) {
- ll_update_inode(*inode, &md);
+ rc = ll_update_inode(*inode, &md);
+ if (rc)
+ goto out;
} else {
LASSERT(sb);
* At this point server returns to client's same fid as client
* generated for creating. So using ->fid1 is okay here.
*/
- if (!fid_is_sane(&md.body->fid1)) {
+ if (!fid_is_sane(&md.body->mbo_fid1)) {
CERROR("%s: Fid is insane " DFID "\n",
ll_get_fsname(sb, NULL, 0),
- PFID(&md.body->fid1));
+ PFID(&md.body->mbo_fid1));
rc = -EINVAL;
goto out;
}
- *inode = ll_iget(sb, cl_fid_build_ino(&md.body->fid1,
+ *inode = ll_iget(sb, cl_fid_build_ino(&md.body->mbo_fid1,
sbi->ll_flags & LL_SBI_32BIT_API),
&md);
- if (!*inode) {
+ if (IS_ERR(*inode)) {
#ifdef CONFIG_FS_POSIX_ACL
if (md.posix_acl) {
posix_acl_release(md.posix_acl);
/* this function prepares md_op_data hint for passing ot down to MD stack. */
struct md_op_data *ll_prep_md_op_data(struct md_op_data *op_data,
struct inode *i1, struct inode *i2,
- const char *name, int namelen,
- int mode, __u32 opc, void *data)
+ const char *name, size_t namelen,
+ u32 mode, __u32 opc, void *data)
{
- if (namelen > ll_i2sbi(i1)->ll_namelen)
- return ERR_PTR(-ENAMETOOLONG);
+ if (!name) {
+ /* Do not reuse namelen for something else. */
+ if (namelen)
+ return ERR_PTR(-EINVAL);
+ } else {
+ if (namelen > ll_i2sbi(i1)->ll_namelen)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ if (!lu_name_is_valid_2(name, namelen))
+ return ERR_PTR(-EINVAL);
+ }
if (!op_data)
op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
ll_i2gids(op_data->op_suppgids, i1, i2);
op_data->op_fid1 = *ll_inode2fid(i1);
+ op_data->op_default_stripe_offset = -1;
+ if (S_ISDIR(i1->i_mode)) {
+ op_data->op_mea1 = ll_i2info(i1)->lli_lsm_md;
+ op_data->op_default_stripe_offset =
+ ll_i2info(i1)->lli_def_stripe_offset;
+ }
- if (i2)
+ if (i2) {
op_data->op_fid2 = *ll_inode2fid(i2);
- else
+ if (S_ISDIR(i2->i_mode))
+ op_data->op_mea2 = ll_i2info(i2)->lli_lsm_md;
+ } else {
fid_zero(&op_data->op_fid2);
+ }
+
+ if (ll_i2sbi(i1)->ll_flags & LL_SBI_64BIT_HASH)
+ op_data->op_cli_flags |= CLI_HASH64;
+
+ if (ll_need_32bit_api(ll_i2sbi(i1)))
+ op_data->op_cli_flags |= CLI_API32;
op_data->op_name = name;
op_data->op_namelen = namelen;
op_data->op_bias = 0;
op_data->op_cli_flags = 0;
if ((opc == LUSTRE_OPC_CREATE) && name &&
- filename_is_volatile(name, namelen, NULL))
+ filename_is_volatile(name, namelen, &op_data->op_mds))
op_data->op_bias |= MDS_CREATE_VOLATILE;
- op_data->op_opc = opc;
- op_data->op_mds = 0;
+ else
+ op_data->op_mds = 0;
op_data->op_data = data;
- /* If the file is being opened after mknod() (normally due to NFS)
- * try to use the default stripe data from parent directory for
- * allocating OST objects. Try to pass the parent FID to MDS.
- */
- if (opc == LUSTRE_OPC_CREATE && i1 == i2 && S_ISREG(i2->i_mode) &&
- !ll_i2info(i2)->lli_has_smd) {
- struct ll_inode_info *lli = ll_i2info(i2);
-
- spin_lock(&lli->lli_lock);
- if (likely(!lli->lli_has_smd && !fid_is_zero(&lli->lli_pfid)))
- op_data->op_fid1 = lli->lli_pfid;
- spin_unlock(&lli->lli_lock);
- }
-
/* When called by ll_setattr_raw, file is i1. */
if (ll_i2info(i1)->lli_flags & LLIF_DATA_MODIFIED)
op_data->op_bias |= MDS_DATA_MODIFIED;
if (buf)
free_page((unsigned long)buf);
}
+
+ssize_t ll_copy_user_md(const struct lov_user_md __user *md,
+ struct lov_user_md **kbuf)
+{
+ struct lov_user_md lum;
+ ssize_t lum_size;
+
+ if (copy_from_user(&lum, md, sizeof(lum))) {
+ lum_size = -EFAULT;
+ goto no_kbuf;
+ }
+
+ lum_size = ll_lov_user_md_size(&lum);
+ if (lum_size < 0)
+ goto no_kbuf;
+
+ *kbuf = kzalloc(lum_size, GFP_NOFS);
+ if (!*kbuf) {
+ lum_size = -ENOMEM;
+ goto no_kbuf;
+ }
+
+ if (copy_from_user(*kbuf, md, lum_size) != 0) {
+ kfree(*kbuf);
+ *kbuf = NULL;
+ lum_size = -EFAULT;
+ }
+no_kbuf:
+ return lum_size;
+}
+
+/*
+ * Compute llite root squash state after a change of root squash
+ * configuration setting or add/remove of a lnet nid
+ */
+void ll_compute_rootsquash_state(struct ll_sb_info *sbi)
+{
+ struct root_squash_info *squash = &sbi->ll_squash;
+ lnet_process_id_t id;
+ bool matched;
+ int i;
+
+ /* Update norootsquash flag */
+ down_write(&squash->rsi_sem);
+ if (list_empty(&squash->rsi_nosquash_nids)) {
+ sbi->ll_flags &= ~LL_SBI_NOROOTSQUASH;
+ } else {
+ /*
+ * Do not apply root squash as soon as one of our NIDs is
+ * in the nosquash_nids list
+ */
+ matched = false;
+ i = 0;
+
+ while (LNetGetId(i++, &id) != -ENOENT) {
+ if (LNET_NETTYP(LNET_NIDNET(id.nid)) == LOLND)
+ continue;
+ if (cfs_match_nid(id.nid, &squash->rsi_nosquash_nids)) {
+ matched = true;
+ break;
+ }
+ }
+ if (matched)
+ sbi->ll_flags |= LL_SBI_NOROOTSQUASH;
+ else
+ sbi->ll_flags &= ~LL_SBI_NOROOTSQUASH;
+ }
+ up_write(&squash->rsi_sem);
+}
+
+/**
+ * Parse linkea content to extract information about a given hardlink
+ *
+ * \param[in] ldata - Initialized linkea data
+ * \param[in] linkno - Link identifier
+ * \param[out] parent_fid - The entry's parent FID
+ * \param[in] size - Entry name destination buffer
+ *
+ * \retval 0 on success
+ * \retval Appropriate negative error code on failure
+ */
+static int ll_linkea_decode(struct linkea_data *ldata, unsigned int linkno,
+ struct lu_fid *parent_fid, struct lu_name *ln)
+{
+ unsigned int idx;
+ int rc;
+
+ rc = linkea_init(ldata);
+ if (rc < 0)
+ return rc;
+
+ if (linkno >= ldata->ld_leh->leh_reccount)
+ /* beyond last link */
+ return -ENODATA;
+
+ linkea_first_entry(ldata);
+ for (idx = 0; ldata->ld_lee; idx++) {
+ linkea_entry_unpack(ldata->ld_lee, &ldata->ld_reclen, ln,
+ parent_fid);
+ if (idx == linkno)
+ break;
+
+ linkea_next_entry(ldata);
+ }
+
+ if (idx < linkno)
+ return -ENODATA;
+
+ return 0;
+}
+
+/**
+ * Get parent FID and name of an identified link. Operation is performed for
+ * a given link number, letting the caller iterate over linkno to list one or
+ * all links of an entry.
+ *
+ * \param[in] file - File descriptor against which to perform the operation
+ * \param[in,out] arg - User-filled structure containing the linkno to operate
+ * on and the available size. It is eventually filled with
+ * the requested information or left untouched on error
+ *
+ * \retval - 0 on success
+ * \retval - Appropriate negative error code on failure
+ */
+int ll_getparent(struct file *file, struct getparent __user *arg)
+{
+ struct inode *inode = file_inode(file);
+ struct linkea_data *ldata;
+ struct lu_fid parent_fid;
+ struct lu_buf buf = {
+ .lb_buf = NULL,
+ .lb_len = 0
+ };
+ struct lu_name ln;
+ u32 name_size;
+ u32 linkno;
+ int rc;
+
+ if (!capable(CFS_CAP_DAC_READ_SEARCH) &&
+ !(ll_i2sbi(inode)->ll_flags & LL_SBI_USER_FID2PATH))
+ return -EPERM;
+
+ if (get_user(name_size, &arg->gp_name_size))
+ return -EFAULT;
+
+ if (get_user(linkno, &arg->gp_linkno))
+ return -EFAULT;
+
+ if (name_size > PATH_MAX)
+ return -EINVAL;
+
+ ldata = kzalloc(sizeof(*ldata), GFP_NOFS);
+ if (!ldata)
+ return -ENOMEM;
+
+ rc = linkea_data_new(ldata, &buf);
+ if (rc < 0)
+ goto ldata_free;
+
+ rc = ll_xattr_list(inode, XATTR_NAME_LINK, XATTR_TRUSTED_T, buf.lb_buf,
+ buf.lb_len, OBD_MD_FLXATTR);
+ if (rc < 0)
+ goto lb_free;
+
+ rc = ll_linkea_decode(ldata, linkno, &parent_fid, &ln);
+ if (rc < 0)
+ goto lb_free;
+
+ if (ln.ln_namelen >= name_size) {
+ rc = -EOVERFLOW;
+ goto lb_free;
+ }
+
+ if (copy_to_user(&arg->gp_fid, &parent_fid, sizeof(arg->gp_fid))) {
+ rc = -EFAULT;
+ goto lb_free;
+ }
+
+ if (copy_to_user(&arg->gp_name, ln.ln_name, ln.ln_namelen)) {
+ rc = -EFAULT;
+ goto lb_free;
+ }
+
+ if (put_user('\0', arg->gp_name + ln.ln_namelen)) {
+ rc = -EFAULT;
+ goto lb_free;
+ }
+
+lb_free:
+ lu_buf_free(&buf);
+ldata_free:
+ kfree(ldata);
+ return rc;
+}
(long long)REINT_SETXATTR);
LASSERTF(REINT_RMENTRY == 8, "found %lld\n",
(long long)REINT_RMENTRY);
- LASSERTF(REINT_MAX == 9, "found %lld\n",
+ LASSERTF(REINT_MIGRATE == 9, "found %lld\n",
+ (long long)REINT_MIGRATE);
+ LASSERTF(REINT_MAX == 10, "found %lld\n",
(long long)REINT_MAX);
LASSERTF(DISP_IT_EXECD == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)DISP_IT_EXECD);
+ (unsigned)DISP_IT_EXECD);
LASSERTF(DISP_LOOKUP_EXECD == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)DISP_LOOKUP_EXECD);
+ (unsigned)DISP_LOOKUP_EXECD);
LASSERTF(DISP_LOOKUP_NEG == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)DISP_LOOKUP_NEG);
+ (unsigned)DISP_LOOKUP_NEG);
LASSERTF(DISP_LOOKUP_POS == 0x00000008UL, "found 0x%.8xUL\n",
- (unsigned)DISP_LOOKUP_POS);
+ (unsigned)DISP_LOOKUP_POS);
LASSERTF(DISP_OPEN_CREATE == 0x00000010UL, "found 0x%.8xUL\n",
- (unsigned)DISP_OPEN_CREATE);
+ (unsigned)DISP_OPEN_CREATE);
LASSERTF(DISP_OPEN_OPEN == 0x00000020UL, "found 0x%.8xUL\n",
- (unsigned)DISP_OPEN_OPEN);
+ (unsigned)DISP_OPEN_OPEN);
LASSERTF(DISP_ENQ_COMPLETE == 0x00400000UL, "found 0x%.8xUL\n",
- (unsigned)DISP_ENQ_COMPLETE);
+ (unsigned)DISP_ENQ_COMPLETE);
LASSERTF(DISP_ENQ_OPEN_REF == 0x00800000UL, "found 0x%.8xUL\n",
- (unsigned)DISP_ENQ_OPEN_REF);
+ (unsigned)DISP_ENQ_OPEN_REF);
LASSERTF(DISP_ENQ_CREATE_REF == 0x01000000UL, "found 0x%.8xUL\n",
- (unsigned)DISP_ENQ_CREATE_REF);
+ (unsigned)DISP_ENQ_CREATE_REF);
LASSERTF(DISP_OPEN_LOCK == 0x02000000UL, "found 0x%.8xUL\n",
- (unsigned)DISP_OPEN_LOCK);
+ (unsigned)DISP_OPEN_LOCK);
LASSERTF(MDS_STATUS_CONN == 1, "found %lld\n",
(long long)MDS_STATUS_CONN);
LASSERTF(MDS_STATUS_LOV == 2, "found %lld\n",
LASSERTF(LUSTRE_BFLAG_UNCOMMITTED_WRITES == 1, "found %lld\n",
(long long)LUSTRE_BFLAG_UNCOMMITTED_WRITES);
LASSERTF(MF_SOM_CHANGE == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)MF_SOM_CHANGE);
+ (unsigned)MF_SOM_CHANGE);
LASSERTF(MF_EPOCH_OPEN == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)MF_EPOCH_OPEN);
+ (unsigned)MF_EPOCH_OPEN);
LASSERTF(MF_EPOCH_CLOSE == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)MF_EPOCH_CLOSE);
+ (unsigned)MF_EPOCH_CLOSE);
LASSERTF(MF_MDC_CANCEL_FID1 == 0x00000008UL, "found 0x%.8xUL\n",
- (unsigned)MF_MDC_CANCEL_FID1);
+ (unsigned)MF_MDC_CANCEL_FID1);
LASSERTF(MF_MDC_CANCEL_FID2 == 0x00000010UL, "found 0x%.8xUL\n",
- (unsigned)MF_MDC_CANCEL_FID2);
+ (unsigned)MF_MDC_CANCEL_FID2);
LASSERTF(MF_MDC_CANCEL_FID3 == 0x00000020UL, "found 0x%.8xUL\n",
- (unsigned)MF_MDC_CANCEL_FID3);
+ (unsigned)MF_MDC_CANCEL_FID3);
LASSERTF(MF_MDC_CANCEL_FID4 == 0x00000040UL, "found 0x%.8xUL\n",
- (unsigned)MF_MDC_CANCEL_FID4);
+ (unsigned)MF_MDC_CANCEL_FID4);
LASSERTF(MF_SOM_AU == 0x00000080UL, "found 0x%.8xUL\n",
- (unsigned)MF_SOM_AU);
+ (unsigned)MF_SOM_AU);
LASSERTF(MF_GETATTR_LOCK == 0x00000100UL, "found 0x%.8xUL\n",
- (unsigned)MF_GETATTR_LOCK);
+ (unsigned)MF_GETATTR_LOCK);
LASSERTF(MDS_ATTR_MODE == 0x0000000000000001ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_MODE);
+ (long long)MDS_ATTR_MODE);
LASSERTF(MDS_ATTR_UID == 0x0000000000000002ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_UID);
+ (long long)MDS_ATTR_UID);
LASSERTF(MDS_ATTR_GID == 0x0000000000000004ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_GID);
+ (long long)MDS_ATTR_GID);
LASSERTF(MDS_ATTR_SIZE == 0x0000000000000008ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_SIZE);
+ (long long)MDS_ATTR_SIZE);
LASSERTF(MDS_ATTR_ATIME == 0x0000000000000010ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_ATIME);
+ (long long)MDS_ATTR_ATIME);
LASSERTF(MDS_ATTR_MTIME == 0x0000000000000020ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_MTIME);
+ (long long)MDS_ATTR_MTIME);
LASSERTF(MDS_ATTR_CTIME == 0x0000000000000040ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_CTIME);
+ (long long)MDS_ATTR_CTIME);
LASSERTF(MDS_ATTR_ATIME_SET == 0x0000000000000080ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_ATIME_SET);
+ (long long)MDS_ATTR_ATIME_SET);
LASSERTF(MDS_ATTR_MTIME_SET == 0x0000000000000100ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_MTIME_SET);
+ (long long)MDS_ATTR_MTIME_SET);
LASSERTF(MDS_ATTR_FORCE == 0x0000000000000200ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_FORCE);
+ (long long)MDS_ATTR_FORCE);
LASSERTF(MDS_ATTR_ATTR_FLAG == 0x0000000000000400ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_ATTR_FLAG);
+ (long long)MDS_ATTR_ATTR_FLAG);
LASSERTF(MDS_ATTR_KILL_SUID == 0x0000000000000800ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_KILL_SUID);
+ (long long)MDS_ATTR_KILL_SUID);
LASSERTF(MDS_ATTR_KILL_SGID == 0x0000000000001000ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_KILL_SGID);
+ (long long)MDS_ATTR_KILL_SGID);
LASSERTF(MDS_ATTR_CTIME_SET == 0x0000000000002000ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_CTIME_SET);
+ (long long)MDS_ATTR_CTIME_SET);
LASSERTF(MDS_ATTR_FROM_OPEN == 0x0000000000004000ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_FROM_OPEN);
+ (long long)MDS_ATTR_FROM_OPEN);
LASSERTF(MDS_ATTR_BLOCKS == 0x0000000000008000ULL, "found 0x%.16llxULL\n",
- (long long)MDS_ATTR_BLOCKS);
+ (long long)MDS_ATTR_BLOCKS);
LASSERTF(FLD_QUERY == 900, "found %lld\n",
(long long)FLD_QUERY);
LASSERTF(FLD_FIRST_OPC == 900, "found %lld\n",
LASSERTF((int)sizeof(((struct lustre_mdt_attrs *)0)->lma_self_fid) == 16, "found %lld\n",
(long long)(int)sizeof(((struct lustre_mdt_attrs *)0)->lma_self_fid));
LASSERTF(LMAI_RELEASED == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)LMAI_RELEASED);
+ (unsigned)LMAI_RELEASED);
LASSERTF(LMAC_HSM == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)LMAC_HSM);
+ (unsigned)LMAC_HSM);
LASSERTF(LMAC_SOM == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)LMAC_SOM);
+ (unsigned)LMAC_SOM);
LASSERTF(LMAC_NOT_IN_OI == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)LMAC_NOT_IN_OI);
+ (unsigned)LMAC_NOT_IN_OI);
LASSERTF(LMAC_FID_ON_OST == 0x00000008UL, "found 0x%.8xUL\n",
- (unsigned)LMAC_FID_ON_OST);
+ (unsigned)LMAC_FID_ON_OST);
/* Checks for struct ost_id */
LASSERTF((int)sizeof(struct ost_id) == 16, "found %lld\n",
LASSERTF(FID_SEQ_IGIF == 12, "found %lld\n",
(long long)FID_SEQ_IGIF);
LASSERTF(FID_SEQ_IGIF_MAX == 0x00000000ffffffffULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_IGIF_MAX);
+ (long long)FID_SEQ_IGIF_MAX);
LASSERTF(FID_SEQ_IDIF == 0x0000000100000000ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_IDIF);
+ (long long)FID_SEQ_IDIF);
LASSERTF(FID_SEQ_IDIF_MAX == 0x00000001ffffffffULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_IDIF_MAX);
+ (long long)FID_SEQ_IDIF_MAX);
LASSERTF(FID_SEQ_START == 0x0000000200000000ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_START);
+ (long long)FID_SEQ_START);
LASSERTF(FID_SEQ_LOCAL_FILE == 0x0000000200000001ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_LOCAL_FILE);
+ (long long)FID_SEQ_LOCAL_FILE);
LASSERTF(FID_SEQ_DOT_LUSTRE == 0x0000000200000002ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_DOT_LUSTRE);
+ (long long)FID_SEQ_DOT_LUSTRE);
LASSERTF(FID_SEQ_SPECIAL == 0x0000000200000004ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_SPECIAL);
+ (long long)FID_SEQ_SPECIAL);
LASSERTF(FID_SEQ_QUOTA == 0x0000000200000005ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_QUOTA);
+ (long long)FID_SEQ_QUOTA);
LASSERTF(FID_SEQ_QUOTA_GLB == 0x0000000200000006ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_QUOTA_GLB);
+ (long long)FID_SEQ_QUOTA_GLB);
LASSERTF(FID_SEQ_ROOT == 0x0000000200000007ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_ROOT);
+ (long long)FID_SEQ_ROOT);
LASSERTF(FID_SEQ_NORMAL == 0x0000000200000400ULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_NORMAL);
+ (long long)FID_SEQ_NORMAL);
LASSERTF(FID_SEQ_LOV_DEFAULT == 0xffffffffffffffffULL, "found 0x%.16llxULL\n",
- (long long)FID_SEQ_LOV_DEFAULT);
+ (long long)FID_SEQ_LOV_DEFAULT);
LASSERTF(FID_OID_SPECIAL_BFL == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)FID_OID_SPECIAL_BFL);
+ (unsigned)FID_OID_SPECIAL_BFL);
LASSERTF(FID_OID_DOT_LUSTRE == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)FID_OID_DOT_LUSTRE);
+ (unsigned)FID_OID_DOT_LUSTRE);
LASSERTF(FID_OID_DOT_LUSTRE_OBF == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)FID_OID_DOT_LUSTRE_OBF);
+ (unsigned)FID_OID_DOT_LUSTRE_OBF);
/* Checks for struct lu_dirent */
LASSERTF((int)sizeof(struct lu_dirent) == 32, "found %lld\n",
LASSERTF((int)sizeof(((struct lu_dirent *)0)->lde_name[0]) == 1, "found %lld\n",
(long long)(int)sizeof(((struct lu_dirent *)0)->lde_name[0]));
LASSERTF(LUDA_FID == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)LUDA_FID);
+ (unsigned)LUDA_FID);
LASSERTF(LUDA_TYPE == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)LUDA_TYPE);
+ (unsigned)LUDA_TYPE);
LASSERTF(LUDA_64BITHASH == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)LUDA_64BITHASH);
+ (unsigned)LUDA_64BITHASH);
/* Checks for struct luda_type */
LASSERTF((int)sizeof(struct luda_type) == 2, "found %lld\n",
LASSERTF((int)sizeof(((struct lustre_msg_v2 *)0)->lm_buflens[0]) == 4, "found %lld\n",
(long long)(int)sizeof(((struct lustre_msg_v2 *)0)->lm_buflens[0]));
LASSERTF(LUSTRE_MSG_MAGIC_V2 == 0x0BD00BD3, "found 0x%.8x\n",
- LUSTRE_MSG_MAGIC_V2);
+ LUSTRE_MSG_MAGIC_V2);
LASSERTF(LUSTRE_MSG_MAGIC_V2_SWABBED == 0xD30BD00B, "found 0x%.8x\n",
- LUSTRE_MSG_MAGIC_V2_SWABBED);
+ LUSTRE_MSG_MAGIC_V2_SWABBED);
/* Checks for struct ptlrpc_body */
LASSERTF((int)sizeof(struct ptlrpc_body_v3) == 184, "found %lld\n",
(long long)(int)offsetof(struct ptlrpc_body_v3, pb_padding));
LASSERTF((int)sizeof(((struct ptlrpc_body_v3 *)0)->pb_padding) == 32, "found %lld\n",
(long long)(int)sizeof(((struct ptlrpc_body_v3 *)0)->pb_padding));
- CLASSERT(JOBSTATS_JOBID_SIZE == 32);
+ CLASSERT(LUSTRE_JOBID_SIZE == 32);
LASSERTF((int)offsetof(struct ptlrpc_body_v3, pb_jobid) == 152, "found %lld\n",
(long long)(int)offsetof(struct ptlrpc_body_v3, pb_jobid));
LASSERTF((int)sizeof(((struct ptlrpc_body_v3 *)0)->pb_jobid) == 32, "found %lld\n",
LASSERTF(MSG_PTLRPC_HEADER_OFF == 31, "found %lld\n",
(long long)MSG_PTLRPC_HEADER_OFF);
LASSERTF(PTLRPC_MSG_VERSION == 0x00000003, "found 0x%.8x\n",
- PTLRPC_MSG_VERSION);
+ PTLRPC_MSG_VERSION);
LASSERTF(LUSTRE_VERSION_MASK == 0xffff0000, "found 0x%.8x\n",
- LUSTRE_VERSION_MASK);
+ LUSTRE_VERSION_MASK);
LASSERTF(LUSTRE_OBD_VERSION == 0x00010000, "found 0x%.8x\n",
- LUSTRE_OBD_VERSION);
+ LUSTRE_OBD_VERSION);
LASSERTF(LUSTRE_MDS_VERSION == 0x00020000, "found 0x%.8x\n",
- LUSTRE_MDS_VERSION);
+ LUSTRE_MDS_VERSION);
LASSERTF(LUSTRE_OST_VERSION == 0x00030000, "found 0x%.8x\n",
- LUSTRE_OST_VERSION);
+ LUSTRE_OST_VERSION);
LASSERTF(LUSTRE_DLM_VERSION == 0x00040000, "found 0x%.8x\n",
- LUSTRE_DLM_VERSION);
+ LUSTRE_DLM_VERSION);
LASSERTF(LUSTRE_LOG_VERSION == 0x00050000, "found 0x%.8x\n",
- LUSTRE_LOG_VERSION);
+ LUSTRE_LOG_VERSION);
LASSERTF(LUSTRE_MGS_VERSION == 0x00060000, "found 0x%.8x\n",
- LUSTRE_MGS_VERSION);
+ LUSTRE_MGS_VERSION);
LASSERTF(MSGHDR_AT_SUPPORT == 1, "found %lld\n",
(long long)MSGHDR_AT_SUPPORT);
LASSERTF(MSGHDR_CKSUM_INCOMPAT18 == 2, "found %lld\n",
(long long)MSGHDR_CKSUM_INCOMPAT18);
LASSERTF(MSG_OP_FLAG_MASK == 0xffff0000UL, "found 0x%.8xUL\n",
- (unsigned)MSG_OP_FLAG_MASK);
+ (unsigned)MSG_OP_FLAG_MASK);
LASSERTF(MSG_OP_FLAG_SHIFT == 16, "found %lld\n",
(long long)MSG_OP_FLAG_SHIFT);
LASSERTF(MSG_GEN_FLAG_MASK == 0x0000ffffUL, "found 0x%.8xUL\n",
- (unsigned)MSG_GEN_FLAG_MASK);
+ (unsigned)MSG_GEN_FLAG_MASK);
LASSERTF(MSG_LAST_REPLAY == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)MSG_LAST_REPLAY);
+ (unsigned)MSG_LAST_REPLAY);
LASSERTF(MSG_RESENT == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)MSG_RESENT);
+ (unsigned)MSG_RESENT);
LASSERTF(MSG_REPLAY == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)MSG_REPLAY);
+ (unsigned)MSG_REPLAY);
LASSERTF(MSG_DELAY_REPLAY == 0x00000010UL, "found 0x%.8xUL\n",
- (unsigned)MSG_DELAY_REPLAY);
+ (unsigned)MSG_DELAY_REPLAY);
LASSERTF(MSG_VERSION_REPLAY == 0x00000020UL, "found 0x%.8xUL\n",
- (unsigned)MSG_VERSION_REPLAY);
+ (unsigned)MSG_VERSION_REPLAY);
LASSERTF(MSG_REQ_REPLAY_DONE == 0x00000040UL, "found 0x%.8xUL\n",
- (unsigned)MSG_REQ_REPLAY_DONE);
+ (unsigned)MSG_REQ_REPLAY_DONE);
LASSERTF(MSG_LOCK_REPLAY_DONE == 0x00000080UL, "found 0x%.8xUL\n",
- (unsigned)MSG_LOCK_REPLAY_DONE);
+ (unsigned)MSG_LOCK_REPLAY_DONE);
LASSERTF(MSG_CONNECT_RECOVERING == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_RECOVERING);
+ (unsigned)MSG_CONNECT_RECOVERING);
LASSERTF(MSG_CONNECT_RECONNECT == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_RECONNECT);
+ (unsigned)MSG_CONNECT_RECONNECT);
LASSERTF(MSG_CONNECT_REPLAYABLE == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_REPLAYABLE);
+ (unsigned)MSG_CONNECT_REPLAYABLE);
LASSERTF(MSG_CONNECT_LIBCLIENT == 0x00000010UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_LIBCLIENT);
+ (unsigned)MSG_CONNECT_LIBCLIENT);
LASSERTF(MSG_CONNECT_INITIAL == 0x00000020UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_INITIAL);
+ (unsigned)MSG_CONNECT_INITIAL);
LASSERTF(MSG_CONNECT_ASYNC == 0x00000040UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_ASYNC);
+ (unsigned)MSG_CONNECT_ASYNC);
LASSERTF(MSG_CONNECT_NEXT_VER == 0x00000080UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_NEXT_VER);
+ (unsigned)MSG_CONNECT_NEXT_VER);
LASSERTF(MSG_CONNECT_TRANSNO == 0x00000100UL, "found 0x%.8xUL\n",
- (unsigned)MSG_CONNECT_TRANSNO);
+ (unsigned)MSG_CONNECT_TRANSNO);
/* Checks for struct obd_connect_data */
LASSERTF((int)sizeof(struct obd_connect_data) == 192, "found %lld\n",
"found 0x%.16llxULL\n", OBD_CONNECT_FLOCK_DEAD);
LASSERTF(OBD_CONNECT_OPEN_BY_FID == 0x20000000000000ULL,
"found 0x%.16llxULL\n", OBD_CONNECT_OPEN_BY_FID);
+ LASSERTF(OBD_CONNECT_LFSCK == 0x40000000000000ULL, "found 0x%.16llxULL\n",
+ OBD_CONNECT_LFSCK);
+ LASSERTF(OBD_CONNECT_UNLINK_CLOSE == 0x100000000000000ULL, "found 0x%.16llxULL\n",
+ OBD_CONNECT_UNLINK_CLOSE);
+ LASSERTF(OBD_CONNECT_DIR_STRIPE == 0x400000000000000ULL, "found 0x%.16llxULL\n",
+ OBD_CONNECT_DIR_STRIPE);
LASSERTF(OBD_CKSUM_CRC32 == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)OBD_CKSUM_CRC32);
+ (unsigned)OBD_CKSUM_CRC32);
LASSERTF(OBD_CKSUM_ADLER == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)OBD_CKSUM_ADLER);
+ (unsigned)OBD_CKSUM_ADLER);
LASSERTF(OBD_CKSUM_CRC32C == 0x00000004UL, "found 0x%.8xUL\n",
- (unsigned)OBD_CKSUM_CRC32C);
+ (unsigned)OBD_CKSUM_CRC32C);
/* Checks for struct obdo */
LASSERTF((int)sizeof(struct obdo) == 208, "found %lld\n",
(long long)(int)offsetof(struct lov_mds_md_v1, lmm_objects[0]));
LASSERTF((int)sizeof(((struct lov_mds_md_v1 *)0)->lmm_objects[0]) == 24, "found %lld\n",
(long long)(int)sizeof(((struct lov_mds_md_v1 *)0)->lmm_objects[0]));
- CLASSERT(LOV_MAGIC_V1 == 0x0BD10BD0);
+ CLASSERT(LOV_MAGIC_V1 == (0x0BD10000 | 0x0BD0));
/* Checks for struct lov_mds_md_v3 */
LASSERTF((int)sizeof(struct lov_mds_md_v3) == 48, "found %lld\n",
(long long)(int)offsetof(struct lov_mds_md_v3, lmm_layout_gen));
LASSERTF((int)sizeof(((struct lov_mds_md_v3 *)0)->lmm_layout_gen) == 2, "found %lld\n",
(long long)(int)sizeof(((struct lov_mds_md_v3 *)0)->lmm_layout_gen));
- CLASSERT(LOV_MAXPOOLNAME == 16);
+ CLASSERT(LOV_MAXPOOLNAME == 15);
LASSERTF((int)offsetof(struct lov_mds_md_v3, lmm_pool_name[16]) == 48, "found %lld\n",
(long long)(int)offsetof(struct lov_mds_md_v3, lmm_pool_name[16]));
LASSERTF((int)sizeof(((struct lov_mds_md_v3 *)0)->lmm_pool_name[16]) == 1, "found %lld\n",
(long long)(int)offsetof(struct lov_mds_md_v3, lmm_objects[0]));
LASSERTF((int)sizeof(((struct lov_mds_md_v3 *)0)->lmm_objects[0]) == 24, "found %lld\n",
(long long)(int)sizeof(((struct lov_mds_md_v3 *)0)->lmm_objects[0]));
- CLASSERT(LOV_MAGIC_V3 == 0x0BD30BD0);
+ CLASSERT(LOV_MAGIC_V3 == (0x0BD30000 | 0x0BD0));
LASSERTF(LOV_PATTERN_RAID0 == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)LOV_PATTERN_RAID0);
+ (unsigned)LOV_PATTERN_RAID0);
LASSERTF(LOV_PATTERN_RAID1 == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)LOV_PATTERN_RAID1);
+ (unsigned)LOV_PATTERN_RAID1);
LASSERTF(LOV_PATTERN_FIRST == 0x00000100UL, "found 0x%.8xUL\n",
- (unsigned)LOV_PATTERN_FIRST);
+ (unsigned)LOV_PATTERN_FIRST);
LASSERTF(LOV_PATTERN_CMOBD == 0x00000200UL, "found 0x%.8xUL\n",
- (unsigned)LOV_PATTERN_CMOBD);
+ (unsigned)LOV_PATTERN_CMOBD);
+
+ /* Checks for struct lmv_mds_md_v1 */
+ LASSERTF((int)sizeof(struct lmv_mds_md_v1) == 56, "found %lld\n",
+ (long long)(int)sizeof(struct lmv_mds_md_v1));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_magic) == 0, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_magic));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_magic) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_magic));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_stripe_count) == 4, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_stripe_count));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_stripe_count) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_stripe_count));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_master_mdt_index) == 8, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_master_mdt_index));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_master_mdt_index) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_master_mdt_index));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_hash_type) == 12, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_hash_type));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_hash_type) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_hash_type));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_layout_version) == 16, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_layout_version));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_layout_version) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_layout_version));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_padding1) == 20, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_padding1));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_padding1) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_padding1));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_padding2) == 24, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_padding2));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_padding2) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_padding2));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_padding3) == 32, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_padding3));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_padding3) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_padding3));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_pool_name[16]) == 56, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_pool_name[16]));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_pool_name[16]) == 1, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_pool_name[16]));
+ LASSERTF((int)offsetof(struct lmv_mds_md_v1, lmv_stripe_fids[0]) == 56, "found %lld\n",
+ (long long)(int)offsetof(struct lmv_mds_md_v1, lmv_stripe_fids[0]));
+ LASSERTF((int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_stripe_fids[0]) == 16, "found %lld\n",
+ (long long)(int)sizeof(((struct lmv_mds_md_v1 *)0)->lmv_stripe_fids[0]));
+ CLASSERT(LMV_MAGIC_V1 == 0x0CD20CD0);
+ CLASSERT(LMV_MAGIC_STRIPE == 0x0CD40CD0);
+ CLASSERT(LMV_HASH_TYPE_MASK == 0x0000ffff);
+ CLASSERT(LMV_HASH_FLAG_MIGRATION == 0x80000000);
+ CLASSERT(LMV_HASH_FLAG_DEAD == 0x40000000);
/* Checks for struct obd_statfs */
LASSERTF((int)sizeof(struct obd_statfs) == 144, "found %lld\n",
LASSERTF((int)sizeof(((struct obd_dqblk *)0)->dqb_padding) == 4, "found %lld\n",
(long long)(int)sizeof(((struct obd_dqblk *)0)->dqb_padding));
LASSERTF(Q_QUOTACHECK == 0x800100, "found 0x%.8x\n",
- Q_QUOTACHECK);
+ Q_QUOTACHECK);
LASSERTF(Q_INITQUOTA == 0x800101, "found 0x%.8x\n",
- Q_INITQUOTA);
+ Q_INITQUOTA);
LASSERTF(Q_GETOINFO == 0x800102, "found 0x%.8x\n",
- Q_GETOINFO);
+ Q_GETOINFO);
LASSERTF(Q_GETOQUOTA == 0x800103, "found 0x%.8x\n",
- Q_GETOQUOTA);
+ Q_GETOQUOTA);
LASSERTF(Q_FINVALIDATE == 0x800104, "found 0x%.8x\n",
- Q_FINVALIDATE);
+ Q_FINVALIDATE);
/* Checks for struct niobuf_remote */
LASSERTF((int)sizeof(struct niobuf_remote) == 16, "found %lld\n",
(long long)(int)sizeof(struct niobuf_remote));
- LASSERTF((int)offsetof(struct niobuf_remote, offset) == 0, "found %lld\n",
- (long long)(int)offsetof(struct niobuf_remote, offset));
- LASSERTF((int)sizeof(((struct niobuf_remote *)0)->offset) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct niobuf_remote *)0)->offset));
- LASSERTF((int)offsetof(struct niobuf_remote, len) == 8, "found %lld\n",
- (long long)(int)offsetof(struct niobuf_remote, len));
- LASSERTF((int)sizeof(((struct niobuf_remote *)0)->len) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct niobuf_remote *)0)->len));
- LASSERTF((int)offsetof(struct niobuf_remote, flags) == 12, "found %lld\n",
- (long long)(int)offsetof(struct niobuf_remote, flags));
- LASSERTF((int)sizeof(((struct niobuf_remote *)0)->flags) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct niobuf_remote *)0)->flags));
+ LASSERTF((int)offsetof(struct niobuf_remote, rnb_offset) == 0, "found %lld\n",
+ (long long)(int)offsetof(struct niobuf_remote, rnb_offset));
+ LASSERTF((int)sizeof(((struct niobuf_remote *)0)->rnb_offset) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct niobuf_remote *)0)->rnb_offset));
+ LASSERTF((int)offsetof(struct niobuf_remote, rnb_len) == 8, "found %lld\n",
+ (long long)(int)offsetof(struct niobuf_remote, rnb_len));
+ LASSERTF((int)sizeof(((struct niobuf_remote *)0)->rnb_len) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct niobuf_remote *)0)->rnb_len));
+ LASSERTF((int)offsetof(struct niobuf_remote, rnb_flags) == 12, "found %lld\n",
+ (long long)(int)offsetof(struct niobuf_remote, rnb_flags));
+ LASSERTF((int)sizeof(((struct niobuf_remote *)0)->rnb_flags) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct niobuf_remote *)0)->rnb_flags));
LASSERTF(OBD_BRW_READ == 0x01, "found 0x%.8x\n",
- OBD_BRW_READ);
+ OBD_BRW_READ);
LASSERTF(OBD_BRW_WRITE == 0x02, "found 0x%.8x\n",
- OBD_BRW_WRITE);
+ OBD_BRW_WRITE);
LASSERTF(OBD_BRW_SYNC == 0x08, "found 0x%.8x\n",
- OBD_BRW_SYNC);
+ OBD_BRW_SYNC);
LASSERTF(OBD_BRW_CHECK == 0x10, "found 0x%.8x\n",
- OBD_BRW_CHECK);
+ OBD_BRW_CHECK);
LASSERTF(OBD_BRW_FROM_GRANT == 0x20, "found 0x%.8x\n",
- OBD_BRW_FROM_GRANT);
+ OBD_BRW_FROM_GRANT);
LASSERTF(OBD_BRW_GRANTED == 0x40, "found 0x%.8x\n",
- OBD_BRW_GRANTED);
+ OBD_BRW_GRANTED);
LASSERTF(OBD_BRW_NOCACHE == 0x80, "found 0x%.8x\n",
- OBD_BRW_NOCACHE);
+ OBD_BRW_NOCACHE);
LASSERTF(OBD_BRW_NOQUOTA == 0x100, "found 0x%.8x\n",
- OBD_BRW_NOQUOTA);
+ OBD_BRW_NOQUOTA);
LASSERTF(OBD_BRW_SRVLOCK == 0x200, "found 0x%.8x\n",
- OBD_BRW_SRVLOCK);
+ OBD_BRW_SRVLOCK);
LASSERTF(OBD_BRW_ASYNC == 0x400, "found 0x%.8x\n",
- OBD_BRW_ASYNC);
+ OBD_BRW_ASYNC);
LASSERTF(OBD_BRW_MEMALLOC == 0x800, "found 0x%.8x\n",
- OBD_BRW_MEMALLOC);
+ OBD_BRW_MEMALLOC);
LASSERTF(OBD_BRW_OVER_USRQUOTA == 0x1000, "found 0x%.8x\n",
OBD_BRW_OVER_USRQUOTA);
LASSERTF(OBD_BRW_OVER_GRPQUOTA == 0x2000, "found 0x%.8x\n",
/* Checks for struct mdt_body */
LASSERTF((int)sizeof(struct mdt_body) == 216, "found %lld\n",
(long long)(int)sizeof(struct mdt_body));
- LASSERTF((int)offsetof(struct mdt_body, fid1) == 0, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, fid1));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->fid1) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->fid1));
- LASSERTF((int)offsetof(struct mdt_body, fid2) == 16, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, fid2));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->fid2) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->fid2));
- LASSERTF((int)offsetof(struct mdt_body, handle) == 32, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, handle));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->handle) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->handle));
- LASSERTF((int)offsetof(struct mdt_body, valid) == 40, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, valid));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->valid) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->valid));
- LASSERTF((int)offsetof(struct mdt_body, size) == 48, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, size));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->size) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->size));
- LASSERTF((int)offsetof(struct mdt_body, mtime) == 56, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, mtime));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->mtime) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->mtime));
- LASSERTF((int)offsetof(struct mdt_body, atime) == 64, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, atime));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->atime) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->atime));
- LASSERTF((int)offsetof(struct mdt_body, ctime) == 72, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, ctime));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->ctime) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->ctime));
- LASSERTF((int)offsetof(struct mdt_body, blocks) == 80, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, blocks));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->blocks) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->blocks));
- LASSERTF((int)offsetof(struct mdt_body, t_state) == 96, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, t_state));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->t_state) == 8,
+ LASSERTF((int)offsetof(struct mdt_body, mbo_fid1) == 0, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_fid1));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_fid1) == 16, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_fid1));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_fid2) == 16, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_fid2));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_fid2) == 16, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_fid2));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_handle) == 32, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_handle));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_handle) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_handle));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_valid) == 40, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_valid));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_valid) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_valid));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_size) == 48, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_size));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_size) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_size));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_mtime) == 56, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_mtime));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_mtime) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_mtime));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_atime) == 64, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_atime));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_atime) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_atime));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_ctime) == 72, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_ctime));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_ctime) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_ctime));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_blocks) == 80, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_blocks));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_blocks) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_blocks));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_t_state) == 96, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_t_state));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_t_state) == 8,
"found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->t_state));
- LASSERTF((int)offsetof(struct mdt_body, fsuid) == 104, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, fsuid));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->fsuid) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->fsuid));
- LASSERTF((int)offsetof(struct mdt_body, fsgid) == 108, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, fsgid));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->fsgid) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->fsgid));
- LASSERTF((int)offsetof(struct mdt_body, capability) == 112, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, capability));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->capability) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->capability));
- LASSERTF((int)offsetof(struct mdt_body, mode) == 116, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, mode));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->mode) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->mode));
- LASSERTF((int)offsetof(struct mdt_body, uid) == 120, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, uid));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->uid) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->uid));
- LASSERTF((int)offsetof(struct mdt_body, gid) == 124, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, gid));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->gid) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->gid));
- LASSERTF((int)offsetof(struct mdt_body, flags) == 128, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, flags));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->flags) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->flags));
- LASSERTF((int)offsetof(struct mdt_body, rdev) == 132, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, rdev));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->rdev) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->rdev));
- LASSERTF((int)offsetof(struct mdt_body, nlink) == 136, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, nlink));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->nlink) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->nlink));
- LASSERTF((int)offsetof(struct mdt_body, unused2) == 140, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, unused2));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->unused2) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->unused2));
- LASSERTF((int)offsetof(struct mdt_body, suppgid) == 144, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, suppgid));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->suppgid) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->suppgid));
- LASSERTF((int)offsetof(struct mdt_body, eadatasize) == 148, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, eadatasize));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->eadatasize) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->eadatasize));
- LASSERTF((int)offsetof(struct mdt_body, aclsize) == 152, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, aclsize));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->aclsize) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->aclsize));
- LASSERTF((int)offsetof(struct mdt_body, max_mdsize) == 156, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, max_mdsize));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->max_mdsize) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->max_mdsize));
- LASSERTF((int)offsetof(struct mdt_body, max_cookiesize) == 160, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, max_cookiesize));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->max_cookiesize) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->max_cookiesize));
- LASSERTF((int)offsetof(struct mdt_body, uid_h) == 164, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, uid_h));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->uid_h) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->uid_h));
- LASSERTF((int)offsetof(struct mdt_body, gid_h) == 168, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, gid_h));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->gid_h) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->gid_h));
- LASSERTF((int)offsetof(struct mdt_body, padding_5) == 172, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, padding_5));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->padding_5) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->padding_5));
- LASSERTF((int)offsetof(struct mdt_body, padding_6) == 176, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, padding_6));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->padding_6) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->padding_6));
- LASSERTF((int)offsetof(struct mdt_body, padding_7) == 184, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, padding_7));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->padding_7) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->padding_7));
- LASSERTF((int)offsetof(struct mdt_body, padding_8) == 192, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, padding_8));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->padding_8) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->padding_8));
- LASSERTF((int)offsetof(struct mdt_body, padding_9) == 200, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, padding_9));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->padding_9) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->padding_9));
- LASSERTF((int)offsetof(struct mdt_body, padding_10) == 208, "found %lld\n",
- (long long)(int)offsetof(struct mdt_body, padding_10));
- LASSERTF((int)sizeof(((struct mdt_body *)0)->padding_10) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct mdt_body *)0)->padding_10));
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_t_state));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_fsuid) == 104, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_fsuid));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_fsuid) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_fsuid));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_fsgid) == 108, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_fsgid));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_fsgid) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_fsgid));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_capability) == 112, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_capability));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_capability) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_capability));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_mode) == 116, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_mode));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_mode) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_mode));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_uid) == 120, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_uid));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_uid) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_uid));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_gid) == 124, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_gid));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_gid) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_gid));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_flags) == 128, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_flags));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_flags) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_flags));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_rdev) == 132, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_rdev));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_rdev) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_rdev));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_nlink) == 136, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_nlink));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_nlink) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_nlink));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_unused2) == 140, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_unused2));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_unused2) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_unused2));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_suppgid) == 144, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_suppgid));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_suppgid) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_suppgid));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_eadatasize) == 148, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_eadatasize));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_eadatasize) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_eadatasize));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_aclsize) == 152, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_aclsize));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_aclsize) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_aclsize));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_max_mdsize) == 156, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_max_mdsize));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_max_mdsize) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_max_mdsize));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_max_cookiesize) == 160, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_max_cookiesize));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_max_cookiesize) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_max_cookiesize));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_uid_h) == 164, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_uid_h));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_uid_h) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_uid_h));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_gid_h) == 168, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_gid_h));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_gid_h) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_gid_h));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_padding_5) == 172, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_padding_5));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_padding_5) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_padding_5));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_padding_6) == 176, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_padding_6));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_padding_6) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_padding_6));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_padding_7) == 184, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_padding_7));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_padding_7) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_padding_7));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_padding_8) == 192, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_padding_8));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_padding_8) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_padding_8));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_padding_9) == 200, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_padding_9));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_padding_9) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_padding_9));
+ LASSERTF((int)offsetof(struct mdt_body, mbo_padding_10) == 208, "found %lld\n",
+ (long long)(int)offsetof(struct mdt_body, mbo_padding_10));
+ LASSERTF((int)sizeof(((struct mdt_body *)0)->mbo_padding_10) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct mdt_body *)0)->mbo_padding_10));
LASSERTF(MDS_FMODE_CLOSED == 000000000000UL, "found 0%.11oUL\n",
- MDS_FMODE_CLOSED);
+ MDS_FMODE_CLOSED);
LASSERTF(MDS_FMODE_EXEC == 000000000004UL, "found 0%.11oUL\n",
- MDS_FMODE_EXEC);
+ MDS_FMODE_EXEC);
LASSERTF(MDS_FMODE_EPOCH == 000001000000UL, "found 0%.11oUL\n",
- MDS_FMODE_EPOCH);
+ MDS_FMODE_EPOCH);
LASSERTF(MDS_FMODE_TRUNC == 000002000000UL, "found 0%.11oUL\n",
- MDS_FMODE_TRUNC);
+ MDS_FMODE_TRUNC);
LASSERTF(MDS_FMODE_SOM == 000004000000UL, "found 0%.11oUL\n",
- MDS_FMODE_SOM);
+ MDS_FMODE_SOM);
LASSERTF(MDS_OPEN_CREATED == 000000000010UL, "found 0%.11oUL\n",
- MDS_OPEN_CREATED);
+ MDS_OPEN_CREATED);
LASSERTF(MDS_OPEN_CROSS == 000000000020UL, "found 0%.11oUL\n",
- MDS_OPEN_CROSS);
+ MDS_OPEN_CROSS);
LASSERTF(MDS_OPEN_CREAT == 000000000100UL, "found 0%.11oUL\n",
- MDS_OPEN_CREAT);
+ MDS_OPEN_CREAT);
LASSERTF(MDS_OPEN_EXCL == 000000000200UL, "found 0%.11oUL\n",
- MDS_OPEN_EXCL);
+ MDS_OPEN_EXCL);
LASSERTF(MDS_OPEN_TRUNC == 000000001000UL, "found 0%.11oUL\n",
- MDS_OPEN_TRUNC);
+ MDS_OPEN_TRUNC);
LASSERTF(MDS_OPEN_APPEND == 000000002000UL, "found 0%.11oUL\n",
- MDS_OPEN_APPEND);
+ MDS_OPEN_APPEND);
LASSERTF(MDS_OPEN_SYNC == 000000010000UL, "found 0%.11oUL\n",
- MDS_OPEN_SYNC);
+ MDS_OPEN_SYNC);
LASSERTF(MDS_OPEN_DIRECTORY == 000000200000UL, "found 0%.11oUL\n",
- MDS_OPEN_DIRECTORY);
+ MDS_OPEN_DIRECTORY);
LASSERTF(MDS_OPEN_BY_FID == 000040000000UL, "found 0%.11oUL\n",
- MDS_OPEN_BY_FID);
+ MDS_OPEN_BY_FID);
LASSERTF(MDS_OPEN_DELAY_CREATE == 000100000000UL, "found 0%.11oUL\n",
- MDS_OPEN_DELAY_CREATE);
+ MDS_OPEN_DELAY_CREATE);
LASSERTF(MDS_OPEN_OWNEROVERRIDE == 000200000000UL, "found 0%.11oUL\n",
- MDS_OPEN_OWNEROVERRIDE);
+ MDS_OPEN_OWNEROVERRIDE);
LASSERTF(MDS_OPEN_JOIN_FILE == 000400000000UL, "found 0%.11oUL\n",
- MDS_OPEN_JOIN_FILE);
+ MDS_OPEN_JOIN_FILE);
LASSERTF(MDS_OPEN_LOCK == 004000000000UL, "found 0%.11oUL\n",
- MDS_OPEN_LOCK);
+ MDS_OPEN_LOCK);
LASSERTF(MDS_OPEN_HAS_EA == 010000000000UL, "found 0%.11oUL\n",
- MDS_OPEN_HAS_EA);
+ MDS_OPEN_HAS_EA);
LASSERTF(MDS_OPEN_HAS_OBJS == 020000000000UL, "found 0%.11oUL\n",
- MDS_OPEN_HAS_OBJS);
+ MDS_OPEN_HAS_OBJS);
LASSERTF(MDS_OPEN_NORESTORE == 00000000000100000000000ULL, "found 0%.22lloULL\n",
- (long long)MDS_OPEN_NORESTORE);
+ (long long)MDS_OPEN_NORESTORE);
LASSERTF(MDS_OPEN_NEWSTRIPE == 00000000000200000000000ULL, "found 0%.22lloULL\n",
- (long long)MDS_OPEN_NEWSTRIPE);
+ (long long)MDS_OPEN_NEWSTRIPE);
LASSERTF(MDS_OPEN_VOLATILE == 00000000000400000000000ULL, "found 0%.22lloULL\n",
- (long long)MDS_OPEN_VOLATILE);
+ (long long)MDS_OPEN_VOLATILE);
LASSERTF(LUSTRE_SYNC_FL == 0x00000008, "found 0x%.8x\n",
- LUSTRE_SYNC_FL);
+ LUSTRE_SYNC_FL);
LASSERTF(LUSTRE_IMMUTABLE_FL == 0x00000010, "found 0x%.8x\n",
- LUSTRE_IMMUTABLE_FL);
+ LUSTRE_IMMUTABLE_FL);
LASSERTF(LUSTRE_APPEND_FL == 0x00000020, "found 0x%.8x\n",
- LUSTRE_APPEND_FL);
+ LUSTRE_APPEND_FL);
LASSERTF(LUSTRE_NOATIME_FL == 0x00000080, "found 0x%.8x\n",
- LUSTRE_NOATIME_FL);
+ LUSTRE_NOATIME_FL);
LASSERTF(LUSTRE_DIRSYNC_FL == 0x00010000, "found 0x%.8x\n",
- LUSTRE_DIRSYNC_FL);
+ LUSTRE_DIRSYNC_FL);
LASSERTF(MDS_INODELOCK_LOOKUP == 0x000001, "found 0x%.8x\n",
- MDS_INODELOCK_LOOKUP);
+ MDS_INODELOCK_LOOKUP);
LASSERTF(MDS_INODELOCK_UPDATE == 0x000002, "found 0x%.8x\n",
- MDS_INODELOCK_UPDATE);
+ MDS_INODELOCK_UPDATE);
LASSERTF(MDS_INODELOCK_OPEN == 0x000004, "found 0x%.8x\n",
- MDS_INODELOCK_OPEN);
+ MDS_INODELOCK_OPEN);
LASSERTF(MDS_INODELOCK_LAYOUT == 0x000008, "found 0x%.8x\n",
- MDS_INODELOCK_LAYOUT);
+ MDS_INODELOCK_LAYOUT);
/* Checks for struct mdt_ioepoch */
LASSERTF((int)sizeof(struct mdt_ioepoch) == 24, "found %lld\n",
LASSERTF((int)sizeof(((struct lmv_desc *)0)->ld_uuid) == 40, "found %lld\n",
(long long)(int)sizeof(((struct lmv_desc *)0)->ld_uuid));
- /* Checks for struct lmv_stripe_md */
- LASSERTF((int)sizeof(struct lmv_stripe_md) == 32, "found %lld\n",
- (long long)(int)sizeof(struct lmv_stripe_md));
- LASSERTF((int)offsetof(struct lmv_stripe_md, mea_magic) == 0, "found %lld\n",
- (long long)(int)offsetof(struct lmv_stripe_md, mea_magic));
- LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_magic) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_magic));
- LASSERTF((int)offsetof(struct lmv_stripe_md, mea_count) == 4, "found %lld\n",
- (long long)(int)offsetof(struct lmv_stripe_md, mea_count));
- LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_count) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_count));
- LASSERTF((int)offsetof(struct lmv_stripe_md, mea_master) == 8, "found %lld\n",
- (long long)(int)offsetof(struct lmv_stripe_md, mea_master));
- LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_master) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_master));
- LASSERTF((int)offsetof(struct lmv_stripe_md, mea_padding) == 12, "found %lld\n",
- (long long)(int)offsetof(struct lmv_stripe_md, mea_padding));
- LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_padding) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_padding));
- CLASSERT(LOV_MAXPOOLNAME == 16);
- LASSERTF((int)offsetof(struct lmv_stripe_md, mea_pool_name[16]) == 32, "found %lld\n",
- (long long)(int)offsetof(struct lmv_stripe_md, mea_pool_name[16]));
- LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_pool_name[16]) == 1, "found %lld\n",
- (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_pool_name[16]));
- LASSERTF((int)offsetof(struct lmv_stripe_md, mea_ids[0]) == 32, "found %lld\n",
- (long long)(int)offsetof(struct lmv_stripe_md, mea_ids[0]));
- LASSERTF((int)sizeof(((struct lmv_stripe_md *)0)->mea_ids[0]) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct lmv_stripe_md *)0)->mea_ids[0]));
-
/* Checks for struct lov_desc */
LASSERTF((int)sizeof(struct lov_desc) == 88, "found %lld\n",
(long long)(int)sizeof(struct lov_desc));
(long long)(int)offsetof(struct llog_setattr64_rec, lsr_gid_h));
LASSERTF((int)sizeof(((struct llog_setattr64_rec *)0)->lsr_gid_h) == 4, "found %lld\n",
(long long)(int)sizeof(((struct llog_setattr64_rec *)0)->lsr_gid_h));
- LASSERTF((int)offsetof(struct llog_setattr64_rec, lsr_padding) == 48, "found %lld\n",
- (long long)(int)offsetof(struct llog_setattr64_rec, lsr_padding));
- LASSERTF((int)sizeof(((struct llog_setattr64_rec *)0)->lsr_padding) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct llog_setattr64_rec *)0)->lsr_padding));
+ LASSERTF((int)offsetof(struct llog_setattr64_rec, lsr_valid) == 48, "found %lld\n",
+ (long long)(int)offsetof(struct llog_setattr64_rec, lsr_valid));
+ LASSERTF((int)sizeof(((struct llog_setattr64_rec *)0)->lsr_valid) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct llog_setattr64_rec *)0)->lsr_valid));
LASSERTF((int)offsetof(struct llog_setattr64_rec, lsr_tail) == 56, "found %lld\n",
(long long)(int)offsetof(struct llog_setattr64_rec, lsr_tail));
LASSERTF((int)sizeof(((struct llog_setattr64_rec *)0)->lsr_tail) == 8, "found %lld\n",
LASSERTF((int)sizeof(((struct changelog_rec *)0)->cr_pfid) == 16, "found %lld\n",
(long long)(int)sizeof(((struct changelog_rec *)0)->cr_pfid));
- /* Checks for struct changelog_ext_rec */
- LASSERTF((int)sizeof(struct changelog_ext_rec) == 96, "found %lld\n",
- (long long)(int)sizeof(struct changelog_ext_rec));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_namelen) == 0, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_namelen));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_namelen) == 2, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_namelen));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_flags) == 2, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_flags));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_flags) == 2, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_flags));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_type) == 4, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_type));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_type) == 4, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_type));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_index) == 8, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_index));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_index) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_index));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_prev) == 16, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_prev));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_prev) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_prev));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_time) == 24, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_time));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_time) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_time));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_tfid) == 32, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_tfid));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_tfid) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_tfid));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_pfid) == 48, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_pfid));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_pfid) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_pfid));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_sfid) == 64, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_sfid));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_sfid) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_sfid));
- LASSERTF((int)offsetof(struct changelog_ext_rec, cr_spfid) == 80, "found %lld\n",
- (long long)(int)offsetof(struct changelog_ext_rec, cr_spfid));
- LASSERTF((int)sizeof(((struct changelog_ext_rec *)0)->cr_spfid) == 16, "found %lld\n",
- (long long)(int)sizeof(((struct changelog_ext_rec *)0)->cr_spfid));
-
/* Checks for struct changelog_setinfo */
LASSERTF((int)sizeof(struct changelog_setinfo) == 12, "found %lld\n",
(long long)(int)sizeof(struct changelog_setinfo));
(long long)(int)offsetof(struct llog_changelog_rec, cr));
LASSERTF((int)sizeof(((struct llog_changelog_rec *)0)->cr) == 64, "found %lld\n",
(long long)(int)sizeof(((struct llog_changelog_rec *)0)->cr));
- LASSERTF((int)offsetof(struct llog_changelog_rec, cr_tail) == 80, "found %lld\n",
- (long long)(int)offsetof(struct llog_changelog_rec, cr_tail));
- LASSERTF((int)sizeof(((struct llog_changelog_rec *)0)->cr_tail) == 8, "found %lld\n",
- (long long)(int)sizeof(((struct llog_changelog_rec *)0)->cr_tail));
+ LASSERTF((int)offsetof(struct llog_changelog_rec, cr_do_not_use) == 80, "found %lld\n",
+ (long long)(int)offsetof(struct llog_changelog_rec, cr_do_not_use));
+ LASSERTF((int)sizeof(((struct llog_changelog_rec *)0)->cr_do_not_use) == 8, "found %lld\n",
+ (long long)(int)sizeof(((struct llog_changelog_rec *)0)->cr_do_not_use));
/* Checks for struct llog_changelog_user_rec */
LASSERTF((int)sizeof(struct llog_changelog_user_rec) == 40, "found %lld\n",
CLASSERT(LLOG_ORIGIN_HANDLE_DESTROY == 509);
CLASSERT(LLOG_FIRST_OPC == 501);
CLASSERT(LLOG_LAST_OPC == 510);
+ CLASSERT(LLOG_CONFIG_ORIG_CTXT == 0);
+ CLASSERT(LLOG_CONFIG_REPL_CTXT == 1);
+ CLASSERT(LLOG_MDS_OST_ORIG_CTXT == 2);
+ CLASSERT(LLOG_MDS_OST_REPL_CTXT == 3);
+ CLASSERT(LLOG_SIZE_ORIG_CTXT == 4);
+ CLASSERT(LLOG_SIZE_REPL_CTXT == 5);
+ CLASSERT(LLOG_TEST_ORIG_CTXT == 8);
+ CLASSERT(LLOG_TEST_REPL_CTXT == 9);
+ CLASSERT(LLOG_CHANGELOG_ORIG_CTXT == 12);
+ CLASSERT(LLOG_CHANGELOG_REPL_CTXT == 13);
+ CLASSERT(LLOG_CHANGELOG_USER_ORIG_CTXT == 14);
+ CLASSERT(LLOG_AGENT_ORIG_CTXT == 15);
+ CLASSERT(LLOG_MAX_CTXTS == 16);
/* Checks for struct llogd_conn_body */
LASSERTF((int)sizeof(struct llogd_conn_body) == 40, "found %lld\n",
CLASSERT(FIEMAP_EXTENT_NET == 0x80000000);
/* Checks for type posix_acl_xattr_entry */
- LASSERTF((int)sizeof(posix_acl_xattr_entry) == 8, "found %lld\n",
- (long long)(int)sizeof(posix_acl_xattr_entry));
- LASSERTF((int)offsetof(posix_acl_xattr_entry, e_tag) == 0, "found %lld\n",
- (long long)(int)offsetof(posix_acl_xattr_entry, e_tag));
- LASSERTF((int)sizeof(((posix_acl_xattr_entry *)0)->e_tag) == 2, "found %lld\n",
- (long long)(int)sizeof(((posix_acl_xattr_entry *)0)->e_tag));
- LASSERTF((int)offsetof(posix_acl_xattr_entry, e_perm) == 2, "found %lld\n",
- (long long)(int)offsetof(posix_acl_xattr_entry, e_perm));
- LASSERTF((int)sizeof(((posix_acl_xattr_entry *)0)->e_perm) == 2, "found %lld\n",
- (long long)(int)sizeof(((posix_acl_xattr_entry *)0)->e_perm));
- LASSERTF((int)offsetof(posix_acl_xattr_entry, e_id) == 4, "found %lld\n",
- (long long)(int)offsetof(posix_acl_xattr_entry, e_id));
- LASSERTF((int)sizeof(((posix_acl_xattr_entry *)0)->e_id) == 4, "found %lld\n",
- (long long)(int)sizeof(((posix_acl_xattr_entry *)0)->e_id));
+ LASSERTF((int)sizeof(struct posix_acl_xattr_entry) == 8, "found %lld\n",
+ (long long)(int)sizeof(struct posix_acl_xattr_entry));
+ LASSERTF((int)offsetof(struct posix_acl_xattr_entry, e_tag) == 0, "found %lld\n",
+ (long long)(int)offsetof(struct posix_acl_xattr_entry, e_tag));
+ LASSERTF((int)sizeof(((struct posix_acl_xattr_entry *)0)->e_tag) == 2, "found %lld\n",
+ (long long)(int)sizeof(((struct posix_acl_xattr_entry *)0)->e_tag));
+ LASSERTF((int)offsetof(struct posix_acl_xattr_entry, e_perm) == 2, "found %lld\n",
+ (long long)(int)offsetof(struct posix_acl_xattr_entry, e_perm));
+ LASSERTF((int)sizeof(((struct posix_acl_xattr_entry *)0)->e_perm) == 2, "found %lld\n",
+ (long long)(int)sizeof(((struct posix_acl_xattr_entry *)0)->e_perm));
+ LASSERTF((int)offsetof(struct posix_acl_xattr_entry, e_id) == 4, "found %lld\n",
+ (long long)(int)offsetof(struct posix_acl_xattr_entry, e_id));
+ LASSERTF((int)sizeof(((struct posix_acl_xattr_entry *)0)->e_id) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct posix_acl_xattr_entry *)0)->e_id));
/* Checks for type posix_acl_xattr_header */
- LASSERTF((int)sizeof(posix_acl_xattr_header) == 4, "found %lld\n",
- (long long)(int)sizeof(posix_acl_xattr_header));
- LASSERTF((int)offsetof(posix_acl_xattr_header, a_version) == 0, "found %lld\n",
- (long long)(int)offsetof(posix_acl_xattr_header, a_version));
- LASSERTF((int)sizeof(((posix_acl_xattr_header *)0)->a_version) == 4, "found %lld\n",
- (long long)(int)sizeof(((posix_acl_xattr_header *)0)->a_version));
- LASSERTF((int)offsetof(posix_acl_xattr_header, a_entries) == 4, "found %lld\n",
- (long long)(int)offsetof(posix_acl_xattr_header, a_entries));
- LASSERTF((int)sizeof(((posix_acl_xattr_header *)0)->a_entries) == 0, "found %lld\n",
- (long long)(int)sizeof(((posix_acl_xattr_header *)0)->a_entries));
+ LASSERTF((int)sizeof(struct posix_acl_xattr_header) == 4, "found %lld\n",
+ (long long)(int)sizeof(struct posix_acl_xattr_header));
+ LASSERTF((int)offsetof(struct posix_acl_xattr_header, a_version) == 0, "found %lld\n",
+ (long long)(int)offsetof(struct posix_acl_xattr_header, a_version));
+ LASSERTF((int)sizeof(((struct posix_acl_xattr_header *)0)->a_version) == 4, "found %lld\n",
+ (long long)(int)sizeof(((struct posix_acl_xattr_header *)0)->a_version));
/* Checks for struct link_ea_header */
LASSERTF((int)sizeof(struct link_ea_header) == 24, "found %lld\n",
LASSERTF((int)sizeof(((struct hsm_progress *)0)->padding) == 4, "found %lld\n",
(long long)(int)sizeof(((struct hsm_progress *)0)->padding));
LASSERTF(HP_FLAG_COMPLETED == 0x01, "found 0x%.8x\n",
- HP_FLAG_COMPLETED);
+ HP_FLAG_COMPLETED);
LASSERTF(HP_FLAG_RETRY == 0x02, "found 0x%.8x\n",
- HP_FLAG_RETRY);
+ HP_FLAG_RETRY);
LASSERTF((int)offsetof(struct hsm_copy, hc_data_version) == 0, "found %lld\n",
(long long)(int)offsetof(struct hsm_copy, hc_data_version));
LASSERTF((int)sizeof(((struct hsm_request *)0)->hr_data_len) == 4, "found %lld\n",
(long long)(int)sizeof(((struct hsm_request *)0)->hr_data_len));
LASSERTF(HSM_FORCE_ACTION == 0x00000001UL, "found 0x%.8xUL\n",
- (unsigned)HSM_FORCE_ACTION);
+ (unsigned)HSM_FORCE_ACTION);
LASSERTF(HSM_GHOST_COPY == 0x00000002UL, "found 0x%.8xUL\n",
- (unsigned)HSM_GHOST_COPY);
+ (unsigned)HSM_GHOST_COPY);
/* Checks for struct hsm_user_request */
LASSERTF((int)sizeof(struct hsm_user_request) == 24, "found %lld\n",
if (btrfs_root_readonly(root))
return -EROFS;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
if (!bio)
return -ENOMEM;
- bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_opf);
+ bio_set_op_attrs(bio, bio_op(orig_bio), bio_flags(orig_bio));
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
start_sector, GFP_NOFS);
if (!bio)
goto out_err;
- bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_opf);
+ bio_set_op_attrs(bio, bio_op(orig_bio),
+ bio_flags(orig_bio));
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
}
- /* Inspired by filemap_check_errors() */
- int btrfs_inode_check_errors(struct inode *inode)
- {
- int ret = 0;
-
- if (test_bit(AS_ENOSPC, &inode->i_mapping->flags) &&
- test_and_clear_bit(AS_ENOSPC, &inode->i_mapping->flags))
- ret = -ENOSPC;
- if (test_bit(AS_EIO, &inode->i_mapping->flags) &&
- test_and_clear_bit(AS_EIO, &inode->i_mapping->flags))
- ret = -EIO;
-
- return ret;
- }
-
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/fiemap.h>
+#include <linux/iomap.h>
#include <linux/namei.h>
#include <linux/uio.h>
#include "ext2.h"
*/
static int ext2_get_blocks(struct inode *inode,
sector_t iblock, unsigned long maxblocks,
- struct buffer_head *bh_result,
+ u32 *bno, bool *new, bool *boundary,
int create)
{
int err = -EIO;
/* Simplest case - block found, no allocation needed */
if (!partial) {
first_block = le32_to_cpu(chain[depth - 1].key);
- clear_buffer_new(bh_result); /* What's this do? */
count++;
/*map more blocks*/
while (count < maxblocks && count <= blocks_to_boundary) {
mutex_unlock(&ei->truncate_mutex);
if (err)
goto cleanup;
- clear_buffer_new(bh_result);
goto got_it;
}
}
}
if (IS_DAX(inode)) {
+ int i;
+
+ /*
+ * We must unmap blocks before zeroing so that writeback cannot
+ * overwrite zeros with stale data from block device page cache.
+ */
+ for (i = 0; i < count; i++) {
+ unmap_underlying_metadata(inode->i_sb->s_bdev,
+ le32_to_cpu(chain[depth-1].key) + i);
+ }
/*
* block must be initialised before we put it in the tree
* so that it's not found by another thread before it's
mutex_unlock(&ei->truncate_mutex);
goto cleanup;
}
- } else
- set_buffer_new(bh_result);
+ } else {
+ *new = true;
+ }
ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
mutex_unlock(&ei->truncate_mutex);
got_it:
- map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
+ *bno = le32_to_cpu(chain[depth-1].key);
if (count > blocks_to_boundary)
- set_buffer_boundary(bh_result);
+ *boundary = true;
err = count;
/* Clean up and exit */
partial = chain + depth - 1; /* the whole chain */
return err;
}
-int ext2_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
+int ext2_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- int ret = ext2_get_blocks(inode, iblock, max_blocks,
- bh_result, create);
- if (ret > 0) {
- bh_result->b_size = (ret << inode->i_blkbits);
- ret = 0;
+ bool new = false, boundary = false;
+ u32 bno;
+ int ret;
+
+ ret = ext2_get_blocks(inode, iblock, max_blocks, &bno, &new, &boundary,
+ create);
+ if (ret <= 0)
+ return ret;
+
+ map_bh(bh_result, inode->i_sb, bno);
+ bh_result->b_size = (ret << inode->i_blkbits);
+ if (new)
+ set_buffer_new(bh_result);
+ if (boundary)
+ set_buffer_boundary(bh_result);
+ return 0;
+
+}
+
+#ifdef CONFIG_FS_DAX
+static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned flags, struct iomap *iomap)
+{
+ unsigned int blkbits = inode->i_blkbits;
+ unsigned long first_block = offset >> blkbits;
+ unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits;
+ bool new = false, boundary = false;
+ u32 bno;
+ int ret;
+
+ ret = ext2_get_blocks(inode, first_block, max_blocks,
+ &bno, &new, &boundary, flags & IOMAP_WRITE);
+ if (ret < 0)
+ return ret;
+
+ iomap->flags = 0;
+ iomap->bdev = inode->i_sb->s_bdev;
+ iomap->offset = (u64)first_block << blkbits;
+
+ if (ret == 0) {
+ iomap->type = IOMAP_HOLE;
+ iomap->blkno = IOMAP_NULL_BLOCK;
+ iomap->length = 1 << blkbits;
+ } else {
+ iomap->type = IOMAP_MAPPED;
+ iomap->blkno = (sector_t)bno << (blkbits - 9);
+ iomap->length = (u64)ret << blkbits;
+ iomap->flags |= IOMAP_F_MERGED;
}
- return ret;
+ if (new)
+ iomap->flags |= IOMAP_F_NEW;
+ return 0;
+}
+
+static int
+ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
+ ssize_t written, unsigned flags, struct iomap *iomap)
+{
+ if (iomap->type == IOMAP_MAPPED &&
+ written < length &&
+ (flags & IOMAP_WRITE))
+ ext2_write_failed(inode->i_mapping, offset + length);
+ return 0;
}
+struct iomap_ops ext2_iomap_ops = {
+ .iomap_begin = ext2_iomap_begin,
+ .iomap_end = ext2_iomap_end,
+};
+#endif /* CONFIG_FS_DAX */
+
int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
loff_t offset = iocb->ki_pos;
ssize_t ret;
- if (IS_DAX(inode))
- ret = dax_do_io(iocb, inode, iter, ext2_get_block, NULL,
- DIO_LOCKING);
- else
- ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
+ if (WARN_ON_ONCE(IS_DAX(inode)))
+ return -EIO;
+
+ ret = blockdev_direct_IO(iocb, inode, iter, ext2_get_block);
if (ret < 0 && iov_iter_rw(iter) == WRITE)
ext2_write_failed(mapping, offset + count);
return ret;
struct inode *inode = d_inode(dentry);
int error;
- error = inode_change_ok(inode, iattr);
+ error = setattr_prepare(dentry, iattr);
if (error)
return error;
/*
* We have to zeroout blocks before inserting them into extent
* status tree. Otherwise someone could look them up there and
- * use them before they are really zeroed.
+ * use them before they are really zeroed. We also have to
+ * unmap metadata before zeroing as otherwise writeback can
+ * overwrite zeros with stale data from block device.
*/
if (flags & EXT4_GET_BLOCKS_ZERO &&
map->m_flags & EXT4_MAP_MAPPED &&
map->m_flags & EXT4_MAP_NEW) {
+ ext4_lblk_t i;
+
+ for (i = 0; i < map->m_len; i++) {
+ unmap_underlying_metadata(inode->i_sb->s_bdev,
+ map->m_pblk + i);
+ }
ret = ext4_issue_zeroout(inode, map->m_lblk,
map->m_pblk, map->m_len);
if (ret) {
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
if (invalidate) {
+ if (page_mapped(page))
+ clear_page_dirty_for_io(page);
block_invalidatepage(page, 0, PAGE_SIZE);
ClearPageUptodate(page);
}
static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
{
- int unlocked = 0;
- struct inode *inode = iocb->ki_filp->f_mapping->host;
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+ struct inode *inode = mapping->host;
ssize_t ret;
- if (ext4_should_dioread_nolock(inode)) {
- /*
- * Nolock dioread optimization may be dynamically disabled
- * via ext4_inode_block_unlocked_dio(). Check inode's state
- * while holding extra i_dio_count ref.
- */
- inode_dio_begin(inode);
- smp_mb();
- if (unlikely(ext4_test_inode_state(inode,
- EXT4_STATE_DIOREAD_LOCK)))
- inode_dio_end(inode);
- else
- unlocked = 1;
- }
+ /*
+ * Shared inode_lock is enough for us - it protects against concurrent
+ * writes & truncates and since we take care of writing back page cache,
+ * we are protected against page writeback as well.
+ */
+ inode_lock_shared(inode);
if (IS_DAX(inode)) {
- ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block,
- NULL, unlocked ? 0 : DIO_LOCKING);
+ ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0);
} else {
+ size_t count = iov_iter_count(iter);
+
+ ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
+ iocb->ki_pos + count);
+ if (ret)
+ goto out_unlock;
ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
iter, ext4_dio_get_block,
- NULL, NULL,
- unlocked ? 0 : DIO_LOCKING);
+ NULL, NULL, 0);
}
- if (unlocked)
- inode_dio_end(inode);
+out_unlock:
+ inode_unlock_shared(inode);
return ret;
}
}
/*
- * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
*
* @inode: File inode
* Write out all dirty pages to avoid race conditions
* Then release them.
*/
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
ret = filemap_write_and_wait_range(mapping, offset,
offset + length - 1);
if (ret)
int ext4_get_projid(struct inode *inode, kprojid_t *projid)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT))
+ if (!ext4_has_feature_project(inode->i_sb))
return -EOPNOTSUPP;
*projid = EXT4_I(inode)->i_projid;
return 0;
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+ if (ext4_has_feature_project(sb) &&
EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
- if (!ei->i_dtime) {
+ if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+ raw_inode->i_uid_high = 0;
+ raw_inode->i_gid_high = 0;
+ } else {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(i_gid));
- } else {
- raw_inode->i_uid_high = 0;
- raw_inode->i_gid_high = 0;
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
}
}
- BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+ BUG_ON(!ext4_has_feature_project(inode->i_sb) &&
i_projid != EXT4_DEF_PROJID);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
return ERR_PTR(-EINVAL);
}
-static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
+static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
+ const struct posix_acl *acl, size_t *size)
{
struct f2fs_acl_header *f2fs_acl;
struct f2fs_acl_entry *entry;
int i;
- f2fs_acl = f2fs_kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
- sizeof(struct f2fs_acl_entry), GFP_NOFS);
+ f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) +
+ acl->a_count * sizeof(struct f2fs_acl_entry),
+ GFP_NOFS);
if (!f2fs_acl)
return ERR_PTR(-ENOMEM);
retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
if (retval > 0) {
- value = f2fs_kmalloc(retval, GFP_F2FS_ZERO);
+ value = f2fs_kmalloc(F2FS_I_SB(inode), retval, GFP_F2FS_ZERO);
if (!value)
return ERR_PTR(-ENOMEM);
retval = f2fs_getxattr(inode, name_index, "", value,
case ACL_TYPE_ACCESS:
name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl) {
- error = posix_acl_equiv_mode(acl, &inode->i_mode);
- if (error < 0)
+ error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+ if (error)
return error;
set_acl_inode(inode, inode->i_mode);
- if (error == 0)
- acl = NULL;
}
break;
}
if (acl) {
- value = f2fs_acl_to_disk(acl, &size);
+ value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size);
if (IS_ERR(value)) {
clear_inode_flag(inode, FI_ACL_MODE);
return (int)PTR_ERR(value);
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
- else if (file_enc_name(inode) && need_dentry_mark(sbi, inode->i_ino))
+ else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
need_cp = true;
else if (file_wrong_pino(inode))
need_cp = true;
return 0;
if (cache_only) {
- page = f2fs_grab_cache_page(mapping, index, false);
+ page = find_lock_page(mapping, index);
if (page && PageUptodate(page))
goto truncate_out;
f2fs_put_page(page, 1);
struct inode *inode = d_inode(dentry);
int err;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int flags;
unsigned int oldflags;
int ret;
* avoid defragment running in SSR mode when free section are allocated
* intensively
*/
- if (has_not_enough_free_secs(sbi, sec_num)) {
+ if (has_not_enough_free_secs(sbi, 0, sec_num)) {
err = -EAGAIN;
goto out;
}
if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
return -EOPNOTSUPP;
+ if (src == dst) {
+ if (pos_in == pos_out)
+ return 0;
+ if (pos_out > pos_in && pos_out < pos_in + len)
+ return -EINVAL;
+ }
+
inode_lock(src);
if (src != dst) {
if (!inode_trylock(dst)) {
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
- ret = __exchange_data_block(src, dst, pos_in,
- pos_out, len >> F2FS_BLKSIZE_BITS, false);
+ ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
+ pos_out >> F2FS_BLKSIZE_BITS,
+ len >> F2FS_BLKSIZE_BITS, false);
if (!ret) {
if (dst_max_i_size)
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
if (excess_cached_nats(sbi))
res = false;
- if (nm_i->nat_cnt > DEF_NAT_CACHE_THRESHOLD)
- res = false;
} else if (type == DIRTY_DENTS) {
if (sbi->sb->s_bdi->wb.dirty_exceeded)
return false;
struct page *last_page = NULL;
bool marked = false;
nid_t ino = inode->i_ino;
+ int nwritten = 0;
if (atomic) {
last_page = last_fsync_dnode(sbi, ino);
unlock_page(page);
f2fs_put_page(last_page, 0);
break;
+ } else {
+ nwritten++;
}
+
if (page == last_page) {
f2fs_put_page(page, 0);
marked = true;
unlock_page(last_page);
goto retry;
}
+
+ if (nwritten)
+ f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE);
return ret ? -EIO: 0;
}
struct pagevec pvec;
int step = 0;
int nwritten = 0;
+ int ret = 0;
pagevec_init(&pvec, 0);
if (unlikely(f2fs_cp_error(sbi))) {
pagevec_release(&pvec);
- return -EIO;
+ ret = -EIO;
+ goto out;
}
/*
if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
unlock_page(page);
+ else
+ nwritten++;
if (--wbc->nr_to_write == 0)
break;
step++;
goto next_step;
}
- return nwritten;
+out:
+ if (nwritten)
+ f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ return ret;
}
int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
{
pgoff_t index = 0, end = ULONG_MAX;
struct pagevec pvec;
- int ret2 = 0, ret = 0;
+ int ret2, ret = 0;
pagevec_init(&pvec, 0);
cond_resched();
}
- if (unlikely(test_and_clear_bit(AS_ENOSPC, &NODE_MAPPING(sbi)->flags)))
- ret2 = -ENOSPC;
- if (unlikely(test_and_clear_bit(AS_EIO, &NODE_MAPPING(sbi)->flags)))
- ret2 = -EIO;
+ ret2 = filemap_check_errors(NODE_MAPPING(sbi));
if (!ret)
ret = ret2;
return ret;
.set_page_dirty = f2fs_set_node_page_dirty,
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
+#ifdef CONFIG_MIGRATION
+ .migratepage = f2fs_migrate_page,
+#endif
};
static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
struct free_nid *i = NULL;
retry:
#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (time_to_inject(FAULT_ALLOC_NID))
+ if (time_to_inject(sbi, FAULT_ALLOC_NID))
return false;
#endif
if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
if (unlikely(old_ni.blk_addr != NULL_ADDR))
return -EINVAL;
-
+retry:
ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
- if (!ipage)
- return -ENOMEM;
+ if (!ipage) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
/* Should not use this inode from free nid list */
remove_free_nid(NM_I(sbi), ino);
#include <linux/sched.h>
#include <linux/namei.h>
#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx)
{
set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
}
-#if BITS_PER_LONG >= 64
+union fuse_dentry {
+ u64 time;
+ struct rcu_head rcu;
+};
+
static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
{
- entry->d_time = time;
+ ((union fuse_dentry *) entry->d_fsdata)->time = time;
}
static inline u64 fuse_dentry_time(struct dentry *entry)
{
- return entry->d_time;
-}
-#else
-/*
- * On 32 bit archs store the high 32 bits of time in d_fsdata
- */
-static void fuse_dentry_settime(struct dentry *entry, u64 time)
-{
- entry->d_time = time;
- entry->d_fsdata = (void *) (unsigned long) (time >> 32);
-}
-
-static u64 fuse_dentry_time(struct dentry *entry)
-{
- return (u64) entry->d_time +
- ((u64) (unsigned long) entry->d_fsdata << 32);
+ return ((union fuse_dentry *) entry->d_fsdata)->time;
}
-#endif
/*
* FUSE caches dentries and attributes with separate timeout. The
* time in jiffies until the dentry/attributes are valid is stored in
- * dentry->d_time and fuse_inode->i_time respectively.
+ * dentry->d_fsdata and fuse_inode->i_time respectively.
*/
/*
* Calculate the time in jiffies until a dentry/attributes are valid
*/
-static u64 time_to_jiffies(unsigned long sec, unsigned long nsec)
+static u64 time_to_jiffies(u64 sec, u32 nsec)
{
if (sec || nsec) {
- struct timespec ts = {sec, nsec};
- return get_jiffies_64() + timespec_to_jiffies(&ts);
+ struct timespec64 ts = {
+ sec,
+ max_t(u32, nsec, NSEC_PER_SEC - 1)
+ };
+
+ return get_jiffies_64() + timespec64_to_jiffies(&ts);
} else
return 0;
}
if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
+ forget_all_cached_acls(inode);
fuse_change_attributes(inode, &outarg.attr,
entry_attr_timeout(&outarg),
attr_version);
return !nodeid || nodeid == FUSE_ROOT_ID;
}
+static int fuse_dentry_init(struct dentry *dentry)
+{
+ dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry), GFP_KERNEL);
+
+ return dentry->d_fsdata ? 0 : -ENOMEM;
+}
+static void fuse_dentry_release(struct dentry *dentry)
+{
+ union fuse_dentry *fd = dentry->d_fsdata;
+
+ kfree_rcu(fd, rcu);
+}
+
const struct dentry_operations fuse_dentry_operations = {
.d_revalidate = fuse_dentry_revalidate,
+ .d_init = fuse_dentry_init,
+ .d_release = fuse_dentry_release,
};
int fuse_valid_type(int m)
return create_new_entry(fc, &args, dir, entry, S_IFLNK);
}
-static inline void fuse_update_ctime(struct inode *inode)
+void fuse_update_ctime(struct inode *inode)
{
if (!IS_NOCMTIME(inode)) {
inode->i_ctime = current_fs_time(inode->i_sb);
if (time_before64(fi->i_time, get_jiffies_64())) {
r = true;
+ forget_all_cached_acls(inode);
err = fuse_do_getattr(inode, stat, file);
} else {
r = false;
{
const struct cred *cred;
- if (fc->flags & FUSE_ALLOW_OTHER)
+ if (fc->allow_other)
return 1;
cred = current_cred();
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
+ forget_all_cached_acls(inode);
return fuse_do_getattr(inode, NULL, NULL);
}
/*
* If attributes are needed, refresh them before proceeding
*/
- if ((fc->flags & FUSE_DEFAULT_PERMISSIONS) ||
+ if (fc->default_permissions ||
((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) {
struct fuse_inode *fi = get_fuse_inode(inode);
}
}
- if (fc->flags & FUSE_DEFAULT_PERMISSIONS) {
+ if (fc->default_permissions) {
err = generic_permission(inode, mask);
/* If permission is denied, try to refresh file
fi->nlookup++;
spin_unlock(&fc->lock);
+ forget_all_cached_acls(inode);
fuse_change_attributes(inode, &o->attr,
entry_attr_timeout(o),
attr_version);
* vmtruncate() doesn't allow for this case, so do the rlimit checking
* and the actual truncation by hand.
*/
- int fuse_do_setattr(struct inode *inode, struct iattr *attr,
+ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
struct file *file)
{
+ struct inode *inode = d_inode(dentry);
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
FUSE_ARGS(args);
int err;
bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode);
- if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS))
+ if (!fc->default_permissions)
attr->ia_valid |= ATTR_FORCE;
- err = inode_change_ok(inode, attr);
+ err = setattr_prepare(dentry, attr);
if (err)
return err;
}
static int fuse_setattr(struct dentry *entry, struct iattr *attr)
-{
- struct inode *inode = d_inode(entry);
-
- if (!fuse_allow_current_process(get_fuse_conn(inode)))
- return -EACCES;
-
- if (attr->ia_valid & ATTR_FILE)
- return fuse_do_setattr(entry, attr, attr->ia_file);
- else
- return fuse_do_setattr(entry, attr, NULL);
-}
-
-static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
- struct kstat *stat)
{
struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
+ struct file *file = (attr->ia_valid & ATTR_FILE) ? attr->ia_file : NULL;
+ int ret;
- if (!fuse_allow_current_process(fc))
+ if (!fuse_allow_current_process(get_fuse_conn(inode)))
return -EACCES;
- return fuse_update_attributes(inode, stat, NULL, NULL);
-}
-
-static int fuse_setxattr(struct dentry *unused, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
-{
- struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- struct fuse_setxattr_in inarg;
- int err;
-
- if (fc->no_setxattr)
- return -EOPNOTSUPP;
+ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) {
+ attr->ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID |
+ ATTR_MODE);
- memset(&inarg, 0, sizeof(inarg));
- inarg.size = size;
- inarg.flags = flags;
- args.in.h.opcode = FUSE_SETXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 3;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- args.in.args[1].size = strlen(name) + 1;
- args.in.args[1].value = name;
- args.in.args[2].size = size;
- args.in.args[2].value = value;
- err = fuse_simple_request(fc, &args);
- if (err == -ENOSYS) {
- fc->no_setxattr = 1;
- err = -EOPNOTSUPP;
- }
- if (!err) {
- fuse_invalidate_attr(inode);
- fuse_update_ctime(inode);
+ /*
+ * The only sane way to reliably kill suid/sgid is to do it in
+ * the userspace filesystem
+ *
+ * This should be done on write(), truncate() and chown().
+ */
+ if (!fc->handle_killpriv) {
+ int kill;
+
+ /*
+ * ia_mode calculation may have used stale i_mode.
+ * Refresh and recalculate.
+ */
+ ret = fuse_do_getattr(inode, NULL, file);
+ if (ret)
+ return ret;
+
+ attr->ia_mode = inode->i_mode;
+ kill = should_remove_suid(entry);
+ if (kill & ATTR_KILL_SUID) {
+ attr->ia_valid |= ATTR_MODE;
+ attr->ia_mode &= ~S_ISUID;
+ }
+ if (kill & ATTR_KILL_SGID) {
+ attr->ia_valid |= ATTR_MODE;
+ attr->ia_mode &= ~S_ISGID;
+ }
+ }
}
- return err;
-}
-
-static ssize_t fuse_getxattr(struct dentry *entry, struct inode *inode,
- const char *name, void *value, size_t size)
-{
- struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- struct fuse_getxattr_in inarg;
- struct fuse_getxattr_out outarg;
- ssize_t ret;
+ if (!attr->ia_valid)
+ return 0;
- ret = fuse_do_setattr(inode, attr, file);
- if (fc->no_getxattr)
- return -EOPNOTSUPP;
++ ret = fuse_do_setattr(entry, attr, file);
+ if (!ret) {
+ /*
+ * If filesystem supports acls it may have updated acl xattrs in
+ * the filesystem, so forget cached acls for the inode.
+ */
+ if (fc->posix_acl)
+ forget_all_cached_acls(inode);
- memset(&inarg, 0, sizeof(inarg));
- inarg.size = size;
- args.in.h.opcode = FUSE_GETXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 2;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- args.in.args[1].size = strlen(name) + 1;
- args.in.args[1].value = name;
- /* This is really two different operations rolled into one */
- args.out.numargs = 1;
- if (size) {
- args.out.argvar = 1;
- args.out.args[0].size = size;
- args.out.args[0].value = value;
- } else {
- args.out.args[0].size = sizeof(outarg);
- args.out.args[0].value = &outarg;
- }
- ret = fuse_simple_request(fc, &args);
- if (!ret && !size)
- ret = outarg.size;
- if (ret == -ENOSYS) {
- fc->no_getxattr = 1;
- ret = -EOPNOTSUPP;
+ /* Directory mode changed, may need to revalidate access */
+ if (d_is_dir(entry) && (attr->ia_valid & ATTR_MODE))
+ fuse_invalidate_entry_cache(entry);
}
return ret;
}
-static ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
+static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
+ struct kstat *stat)
{
struct inode *inode = d_inode(entry);
struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- struct fuse_getxattr_in inarg;
- struct fuse_getxattr_out outarg;
- ssize_t ret;
if (!fuse_allow_current_process(fc))
return -EACCES;
- if (fc->no_listxattr)
- return -EOPNOTSUPP;
-
- memset(&inarg, 0, sizeof(inarg));
- inarg.size = size;
- args.in.h.opcode = FUSE_LISTXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 1;
- args.in.args[0].size = sizeof(inarg);
- args.in.args[0].value = &inarg;
- /* This is really two different operations rolled into one */
- args.out.numargs = 1;
- if (size) {
- args.out.argvar = 1;
- args.out.args[0].size = size;
- args.out.args[0].value = list;
- } else {
- args.out.args[0].size = sizeof(outarg);
- args.out.args[0].value = &outarg;
- }
- ret = fuse_simple_request(fc, &args);
- if (!ret && !size)
- ret = outarg.size;
- if (ret == -ENOSYS) {
- fc->no_listxattr = 1;
- ret = -EOPNOTSUPP;
- }
- return ret;
-}
-
-static int fuse_removexattr(struct dentry *entry, const char *name)
-{
- struct inode *inode = d_inode(entry);
- struct fuse_conn *fc = get_fuse_conn(inode);
- FUSE_ARGS(args);
- int err;
-
- if (fc->no_removexattr)
- return -EOPNOTSUPP;
-
- args.in.h.opcode = FUSE_REMOVEXATTR;
- args.in.h.nodeid = get_node_id(inode);
- args.in.numargs = 1;
- args.in.args[0].size = strlen(name) + 1;
- args.in.args[0].value = name;
- err = fuse_simple_request(fc, &args);
- if (err == -ENOSYS) {
- fc->no_removexattr = 1;
- err = -EOPNOTSUPP;
- }
- if (!err) {
- fuse_invalidate_attr(inode);
- fuse_update_ctime(inode);
- }
- return err;
+ return fuse_update_attributes(inode, stat, NULL, NULL);
}
static const struct inode_operations fuse_dir_inode_operations = {
.mknod = fuse_mknod,
.permission = fuse_permission,
.getattr = fuse_getattr,
- .setxattr = fuse_setxattr,
- .getxattr = fuse_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = fuse_removexattr,
+ .removexattr = generic_removexattr,
+ .get_acl = fuse_get_acl,
+ .set_acl = fuse_set_acl,
};
static const struct file_operations fuse_dir_operations = {
.setattr = fuse_setattr,
.permission = fuse_permission,
.getattr = fuse_getattr,
- .setxattr = fuse_setxattr,
- .getxattr = fuse_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = fuse_removexattr,
+ .removexattr = generic_removexattr,
+ .get_acl = fuse_get_acl,
+ .set_acl = fuse_set_acl,
};
static const struct inode_operations fuse_symlink_inode_operations = {
.get_link = fuse_get_link,
.readlink = generic_readlink,
.getattr = fuse_getattr,
- .setxattr = fuse_setxattr,
- .getxattr = fuse_getxattr,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
.listxattr = fuse_listxattr,
- .removexattr = fuse_removexattr,
+ .removexattr = generic_removexattr,
};
void fuse_init_common(struct inode *inode)
return retval;
}
-static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov,
- unsigned int nr_segs, size_t bytes, bool to_user)
-{
- struct iov_iter ii;
- int page_idx = 0;
-
- if (!bytes)
- return 0;
-
- iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes);
-
- while (iov_iter_count(&ii)) {
- struct page *page = pages[page_idx++];
- size_t todo = min_t(size_t, PAGE_SIZE, iov_iter_count(&ii));
- void *kaddr;
-
- kaddr = kmap(page);
-
- while (todo) {
- char __user *uaddr = ii.iov->iov_base + ii.iov_offset;
- size_t iov_len = ii.iov->iov_len - ii.iov_offset;
- size_t copy = min(todo, iov_len);
- size_t left;
-
- if (!to_user)
- left = copy_from_user(kaddr, uaddr, copy);
- else
- left = copy_to_user(uaddr, kaddr, copy);
-
- if (unlikely(left))
- return -EFAULT;
-
- iov_iter_advance(&ii, copy);
- todo -= copy;
- kaddr += copy;
- }
-
- kunmap(page);
- }
-
- return 0;
-}
-
/*
* CUSE servers compiled on 32bit broke on 64bit kernels because the
* ABI was defined to be 'struct iovec' which is different on 32bit
struct iovec *iov_page = NULL;
struct iovec *in_iov = NULL, *out_iov = NULL;
unsigned int in_iovs = 0, out_iovs = 0, num_pages = 0, max_pages;
- size_t in_size, out_size, transferred;
- int err;
+ size_t in_size, out_size, transferred, c;
+ int err, i;
+ struct iov_iter ii;
#if BITS_PER_LONG == 32
inarg.flags |= FUSE_IOCTL_32BIT;
req->in.args[1].size = in_size;
req->in.argpages = 1;
- err = fuse_ioctl_copy_user(pages, in_iov, in_iovs, in_size,
- false);
- if (err)
- goto out;
+ err = -EFAULT;
+ iov_iter_init(&ii, WRITE, in_iov, in_iovs, in_size);
+ for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= num_pages); i++) {
+ c = copy_page_from_iter(pages[i], 0, PAGE_SIZE, &ii);
+ if (c != PAGE_SIZE && iov_iter_count(&ii))
+ goto out;
+ }
}
req->out.numargs = 2;
if (transferred > inarg.out_size)
goto out;
- err = fuse_ioctl_copy_user(pages, out_iov, out_iovs, transferred, true);
+ err = -EFAULT;
+ iov_iter_init(&ii, READ, out_iov, out_iovs, transferred);
+ for (i = 0; iov_iter_count(&ii) && !WARN_ON(i >= num_pages); i++) {
+ c = copy_page_to_iter(pages[i], 0, PAGE_SIZE, &ii);
+ if (c != PAGE_SIZE && iov_iter_count(&ii))
+ goto out;
+ }
+ err = 0;
out:
if (req)
fuse_put_request(fc, req);
attr.ia_file = file;
attr.ia_valid |= ATTR_FILE;
- fuse_do_setattr(inode, &attr, file);
+ fuse_do_setattr(file_dentry(file), &attr, file);
}
static inline loff_t fuse_round_up(loff_t off)
#include <linux/poll.h>
#include <linux/workqueue.h>
#include <linux/kref.h>
+#include <linux/xattr.h>
/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
/** Number of dentries for each connection in the control filesystem */
#define FUSE_CTL_NUM_DENTRIES 5
-/** If the FUSE_DEFAULT_PERMISSIONS flag is given, the filesystem
- module will check permissions based on the file mode. Otherwise no
- permission checking is done in the kernel */
-#define FUSE_DEFAULT_PERMISSIONS (1 << 0)
-
-/** If the FUSE_ALLOW_OTHER flag is given, then not only the user
- doing the mount will be allowed to access the filesystem */
-#define FUSE_ALLOW_OTHER (1 << 1)
-
/** Number of page pointers embedded in fuse_req */
#define FUSE_REQ_INLINE_PAGES 1
/** The group id for this mount */
kgid_t group_id;
- /** The fuse mount flags for this mount */
- unsigned flags;
-
/** Maximum read size */
unsigned max_read;
/** allow parallel lookups and readdir (default is serialized) */
unsigned parallel_dirops:1;
+ /** handle fs handles killing suid/sgid/cap on write/chown/trunc */
+ unsigned handle_killpriv:1;
+
/*
* The following bitfields are only for optimization purposes
* and hence races in setting them will not cause malfunction
/** Is lseek not implemented by fs? */
unsigned no_lseek:1;
+ /** Does the filesystem support posix acls? */
+ unsigned posix_acl:1;
+
+ /** Check permissions based on the file mode or not? */
+ unsigned default_permissions:1;
+
+ /** Allow other than the mounter user to access the filesystem ? */
+ unsigned allow_other:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id);
+void fuse_update_ctime(struct inode *inode);
+
int fuse_update_attributes(struct inode *inode, struct kstat *stat,
struct file *file, bool *refreshed);
int fuse_flush_times(struct inode *inode, struct fuse_file *ff);
int fuse_write_inode(struct inode *inode, struct writeback_control *wbc);
- int fuse_do_setattr(struct inode *inode, struct iattr *attr,
+ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
struct file *file);
void fuse_set_initialized(struct fuse_conn *fc);
void fuse_unlock_inode(struct inode *inode);
void fuse_lock_inode(struct inode *inode);
+int fuse_setxattr(struct inode *inode, const char *name, const void *value,
+ size_t size, int flags);
+ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
+ size_t size);
+ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size);
+int fuse_removexattr(struct inode *inode, const char *name);
+extern const struct xattr_handler *fuse_xattr_handlers[];
+extern const struct xattr_handler *fuse_acl_xattr_handlers[];
+
+struct posix_acl;
+struct posix_acl *fuse_get_acl(struct inode *inode, int type);
+int fuse_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+
#endif /* _FS_FUSE_I_H */
}
gfs2_set_iop(inode);
+
+ inode->i_atime.tv_sec = 0;
+ inode->i_atime.tv_nsec = 0;
+
unlock_new_inode(inode);
}
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
goto out;
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
- bool rsv_on_error;
u32 hash;
/*
* cache (remove_huge_page) BEFORE removing the
* region/reserve map (hugetlb_unreserve_pages). In
* rare out of memory conditions, removal of the
- * region/reserve map could fail. Before free'ing
- * the page, note PagePrivate which is used in case
- * of error.
+ * region/reserve map could fail. Correspondingly,
+ * the subpool and global reserve usage count can need
+ * to be adjusted.
*/
- rsv_on_error = !PagePrivate(page);
+ VM_BUG_ON(PagePrivate(page));
remove_huge_page(page);
freed++;
if (!truncate_op) {
if (unlikely(hugetlb_unreserve_pages(inode,
next, next + 1, 1)))
- hugetlb_fix_reserve_counts(inode,
- rsv_on_error);
+ hugetlb_fix_reserve_counts(inode);
}
unlock_page(page);
BUG_ON(!inode);
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
struct super_block;
struct file_system_type;
struct iomap;
+struct iomap_ops;
struct linux_binprm;
struct path;
struct mount;
extern void inode_add_lru(struct inode *inode);
extern int dentry_needs_remove_privs(struct dentry *dentry);
+ extern bool __atime_needs_update(const struct path *, struct inode *, bool);
+ static inline bool atime_needs_update_rcu(const struct path *path,
+ struct inode *inode)
+ {
+ return __atime_needs_update(path, inode, true);
+ }
+
+ extern bool atime_needs_update_rcu(const struct path *, struct inode *);
+
/*
* fs-writeback.c
*/
/*
* fs/nsfs.c
*/
- extern struct dentry_operations ns_dentry_operations;
+ extern const struct dentry_operations ns_dentry_operations;
/*
* fs/ioctl.c
extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd,
unsigned long arg);
extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
+/*
+ * iomap support:
+ */
+typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
+ void *data, struct iomap *iomap);
+
+loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
+ unsigned flags, struct iomap_ops *ops, void *data,
+ iomap_actor_t actor);
#include <linux/pid_namespace.h>
#include <linux/hashtable.h>
#include <linux/percpu.h>
-#include <linux/lglock.h>
#define CREATE_TRACE_POINTS
#include <trace/events/filelock.h>
#define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
#define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK)
+ static inline bool is_remote_lock(struct file *filp)
+ {
+ return likely(!(filp->f_path.dentry->d_sb->s_flags & MS_NOREMOTELOCK));
+ }
+
static bool lease_breaking(struct file_lock *fl)
{
return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING);
/*
* The global file_lock_list is only used for displaying /proc/locks, so we
- * keep a list on each CPU, with each list protected by its own spinlock via
- * the file_lock_lglock. Note that alterations to the list also require that
- * the relevant flc_lock is held.
+ * keep a list on each CPU, with each list protected by its own spinlock.
+ * Global serialization is done using file_rwsem.
+ *
+ * Note that alterations to the list also require that the relevant flc_lock is
+ * held.
*/
-DEFINE_STATIC_LGLOCK(file_lock_lglock);
-static DEFINE_PER_CPU(struct hlist_head, file_lock_list);
+struct file_lock_list_struct {
+ spinlock_t lock;
+ struct hlist_head hlist;
+};
+static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list);
+DEFINE_STATIC_PERCPU_RWSEM(file_rwsem);
/*
* The blocked_hash is used to find POSIX lock loops for deadlock detection.
/* Must be called with the flc_lock held! */
static void locks_insert_global_locks(struct file_lock *fl)
{
- lg_local_lock(&file_lock_lglock);
+ struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list);
+
+ percpu_rwsem_assert_held(&file_rwsem);
+
+ spin_lock(&fll->lock);
fl->fl_link_cpu = smp_processor_id();
- hlist_add_head(&fl->fl_link, this_cpu_ptr(&file_lock_list));
- lg_local_unlock(&file_lock_lglock);
+ hlist_add_head(&fl->fl_link, &fll->hlist);
+ spin_unlock(&fll->lock);
}
/* Must be called with the flc_lock held! */
static void locks_delete_global_locks(struct file_lock *fl)
{
+ struct file_lock_list_struct *fll;
+
+ percpu_rwsem_assert_held(&file_rwsem);
+
/*
* Avoid taking lock if already unhashed. This is safe since this check
* is done while holding the flc_lock, and new insertions into the list
*/
if (hlist_unhashed(&fl->fl_link))
return;
- lg_local_lock_cpu(&file_lock_lglock, fl->fl_link_cpu);
+
+ fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu);
+ spin_lock(&fll->lock);
hlist_del_init(&fl->fl_link);
- lg_local_unlock_cpu(&file_lock_lglock, fl->fl_link_cpu);
+ spin_unlock(&fll->lock);
}
static unsigned long
{
struct file_lock *cfl;
struct file_lock_context *ctx;
- struct inode *inode = file_inode(filp);
+ struct inode *inode = locks_inode(filp);
ctx = smp_load_acquire(&inode->i_flctx);
if (!ctx || list_empty_careful(&ctx->flc_posix)) {
return -ENOMEM;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
if (request->fl_flags & FL_ACCESS)
goto find_conflict;
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
if (new_fl)
locks_free_lock(new_fl);
locks_dispose_list(&dispose);
new_fl2 = locks_alloc_lock();
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
/*
* New lock request. Walk all POSIX locks and look for conflicts. If
}
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
/*
* Free any unused locks.
*/
int posix_lock_file(struct file *filp, struct file_lock *fl,
struct file_lock *conflock)
{
- return posix_lock_inode(file_inode(filp), fl, conflock);
+ return posix_lock_inode(locks_inode(filp), fl, conflock);
}
EXPORT_SYMBOL(posix_lock_file);
int locks_mandatory_locked(struct file *file)
{
int ret;
- struct inode *inode = file_inode(file);
+ struct inode *inode = locks_inode(file);
struct file_lock_context *ctx;
struct file_lock *fl;
return error;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
locks_insert_block(fl, new_fl);
trace_break_lease_block(inode, new_fl);
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
+
locks_dispose_list(&dispose);
error = wait_event_interruptible_timeout(new_fl->fl_wait,
!new_fl->fl_next, break_time);
+
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
trace_break_lease_unblock(inode, new_fl);
locks_delete_block(new_fl);
}
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
locks_dispose_list(&dispose);
locks_free_lock(new_fl);
return error;
int fcntl_getlease(struct file *filp)
{
struct file_lock *fl;
- struct inode *inode = file_inode(filp);
+ struct inode *inode = locks_inode(filp);
struct file_lock_context *ctx;
int type = F_UNLCK;
LIST_HEAD(dispose);
ctx = smp_load_acquire(&inode->i_flctx);
if (ctx && !list_empty_careful(&ctx->flc_lease)) {
spin_lock(&ctx->flc_lock);
- time_out_leases(file_inode(filp), &dispose);
+ time_out_leases(inode, &dispose);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (fl->fl_file != filp)
continue;
if (flags & FL_LAYOUT)
return 0;
- if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
+ if ((arg == F_RDLCK) &&
+ (atomic_read(&d_real_inode(dentry)->i_writecount) > 0))
return -EAGAIN;
if ((arg == F_WRLCK) && ((d_count(dentry) > 1) ||
{
struct file_lock *fl, *my_fl = NULL, *lease;
struct dentry *dentry = filp->f_path.dentry;
- struct inode *inode = file_inode(filp);
+ struct inode *inode = dentry->d_inode;
struct file_lock_context *ctx;
bool is_deleg = (*flp)->fl_flags & FL_DELEG;
int error;
return -EINVAL;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
time_out_leases(inode, &dispose);
error = check_conflicting_open(dentry, arg, lease->fl_flags);
lease->fl_lmops->lm_setup(lease, priv);
out:
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
locks_dispose_list(&dispose);
if (is_deleg)
inode_unlock(inode);
{
int error = -EAGAIN;
struct file_lock *fl, *victim = NULL;
- struct inode *inode = file_inode(filp);
+ struct inode *inode = locks_inode(filp);
struct file_lock_context *ctx;
LIST_HEAD(dispose);
return error;
}
+ percpu_down_read_preempt_disable(&file_rwsem);
spin_lock(&ctx->flc_lock);
list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
if (fl->fl_file == filp &&
if (victim)
error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
spin_unlock(&ctx->flc_lock);
+ percpu_up_read_preempt_enable(&file_rwsem);
locks_dispose_list(&dispose);
return error;
}
int generic_setlease(struct file *filp, long arg, struct file_lock **flp,
void **priv)
{
- struct inode *inode = file_inode(filp);
+ struct inode *inode = locks_inode(filp);
int error;
if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE))
int
vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv)
{
- if (filp->f_op->setlease)
+ if (filp->f_op->setlease && is_remote_lock(filp))
return filp->f_op->setlease(filp, arg, lease, priv);
else
return generic_setlease(filp, arg, lease, priv);
if (error)
goto out_free;
- if (f.file->f_op->flock)
+ if (f.file->f_op->flock && is_remote_lock(f.file))
error = f.file->f_op->flock(f.file,
(can_sleep) ? F_SETLKW : F_SETLK,
lock);
*/
int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
- if (filp->f_op->lock)
+ if (filp->f_op->lock && is_remote_lock(filp))
return filp->f_op->lock(filp, F_GETLK, fl);
posix_test_lock(filp, fl);
return 0;
*/
int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf)
{
- if (filp->f_op->lock)
+ if (filp->f_op->lock && is_remote_lock(filp))
return filp->f_op->lock(filp, cmd, fl);
else
return posix_lock_file(filp, fl, conf);
if (file_lock == NULL)
return -ENOLCK;
- inode = file_inode(filp);
+ inode = locks_inode(filp);
/*
* This might block, so we do it before checking the inode.
if (copy_from_user(&flock, l, sizeof(flock)))
goto out;
- inode = file_inode(filp);
+ inode = locks_inode(filp);
/* Don't allow mandatory locks on files that may be memory mapped
* and shared.
void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
int error;
+ struct inode *inode = locks_inode(filp);
struct file_lock lock;
struct file_lock_context *ctx;
* posix_lock_file(). Another process could be setting a lock on this
* file at the same time, but we wouldn't remove that lock anyway.
*/
- ctx = smp_load_acquire(&file_inode(filp)->i_flctx);
+ ctx = smp_load_acquire(&inode->i_flctx);
if (!ctx || list_empty(&ctx->flc_posix))
return;
if (lock.fl_ops && lock.fl_ops->fl_release_private)
lock.fl_ops->fl_release_private(&lock);
- trace_locks_remove_posix(file_inode(filp), &lock, error);
+ trace_locks_remove_posix(inode, &lock, error);
}
EXPORT_SYMBOL(locks_remove_posix);
.fl_type = F_UNLCK,
.fl_end = OFFSET_MAX,
};
- struct inode *inode = file_inode(filp);
+ struct inode *inode = locks_inode(filp);
if (list_empty(&flctx->flc_flock))
return;
- if (filp->f_op->flock)
+ if (filp->f_op->flock && is_remote_lock(filp))
filp->f_op->flock(filp, F_SETLKW, &fl);
else
flock_lock_inode(inode, &fl);
{
struct file_lock_context *ctx;
- ctx = smp_load_acquire(&file_inode(filp)->i_flctx);
+ ctx = smp_load_acquire(&locks_inode(filp)->i_flctx);
if (!ctx)
return;
*/
int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
- if (filp->f_op->lock)
+ if (filp->f_op->lock && is_remote_lock(filp))
return filp->f_op->lock(filp, F_CANCELLK, fl);
return 0;
}
struct inode *inode = NULL;
unsigned int fl_pid;
- if (fl->fl_nspid)
- fl_pid = pid_vnr(fl->fl_nspid);
- else
+ if (fl->fl_nspid) {
+ struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
+
+ /* Don't let fl_pid change based on who is reading the file */
+ fl_pid = pid_nr_ns(fl->fl_nspid, proc_pidns);
+
+ /*
+ * If there isn't a fl_pid don't display who is waiting on
+ * the lock if we are called from locks_show, or if we are
+ * called from __show_fd_info - skip lock entirely
+ */
+ if (fl_pid == 0)
+ return;
+ } else
fl_pid = fl->fl_pid;
if (fl->fl_file != NULL)
- inode = file_inode(fl->fl_file);
+ inode = locks_inode(fl->fl_file);
seq_printf(f, "%lld:%s ", id, pfx);
if (IS_POSIX(fl)) {
{
struct locks_iterator *iter = f->private;
struct file_lock *fl, *bfl;
+ struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
fl = hlist_entry(v, struct file_lock, fl_link);
+ if (fl->fl_nspid && !pid_nr_ns(fl->fl_nspid, proc_pidns))
+ return 0;
+
lock_get_status(f, fl, iter->li_pos, "");
list_for_each_entry(bfl, &fl->fl_block, fl_block)
void show_fd_locks(struct seq_file *f,
struct file *filp, struct files_struct *files)
{
- struct inode *inode = file_inode(filp);
+ struct inode *inode = locks_inode(filp);
struct file_lock_context *ctx;
int id = 0;
struct locks_iterator *iter = f->private;
iter->li_pos = *pos + 1;
- lg_global_lock(&file_lock_lglock);
+ percpu_down_write(&file_rwsem);
spin_lock(&blocked_lock_lock);
- return seq_hlist_start_percpu(&file_lock_list, &iter->li_cpu, *pos);
+ return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos);
}
static void *locks_next(struct seq_file *f, void *v, loff_t *pos)
struct locks_iterator *iter = f->private;
++iter->li_pos;
- return seq_hlist_next_percpu(v, &file_lock_list, &iter->li_cpu, pos);
+ return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos);
}
static void locks_stop(struct seq_file *f, void *v)
__releases(&blocked_lock_lock)
{
spin_unlock(&blocked_lock_lock);
- lg_global_unlock(&file_lock_lglock);
+ percpu_up_write(&file_rwsem);
}
static const struct seq_operations locks_seq_operations = {
filelock_cache = kmem_cache_create("file_lock_cache",
sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
- lg_lock_init(&file_lock_lglock, "file_lock_lglock");
- for_each_possible_cpu(i)
- INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i));
+ for_each_possible_cpu(i) {
+ struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i);
+
+ spin_lock_init(&fll->lock);
+ INIT_HLIST_HEAD(&fll->hlist);
+ }
return 0;
}
#include "pnode.h"
#include "internal.h"
+/* Maximum number of mounts in a mount namespace */
+unsigned int sysctl_mount_max __read_mostly = 100000;
+
static unsigned int m_hash_mask __read_mostly;
static unsigned int m_hash_shift __read_mostly;
static unsigned int mp_hash_mask __read_mostly;
list_splice(&head, n->list.prev);
+ n->mounts += n->pending_mounts;
+ n->pending_mounts = 0;
+
attach_shadowed(mnt, parent, shadows);
touch_mnt_namespace(n);
}
propagate_umount(&tmp_list);
while (!list_empty(&tmp_list)) {
+ struct mnt_namespace *ns;
bool disconnect;
p = list_first_entry(&tmp_list, struct mount, mnt_list);
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
- __touch_mnt_namespace(p->mnt_ns);
+ ns = p->mnt_ns;
+ if (ns) {
+ ns->mounts--;
+ __touch_mnt_namespace(ns);
+ }
p->mnt_ns = NULL;
if (how & UMOUNT_SYNC)
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
return 0;
}
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
+{
+ unsigned int max = READ_ONCE(sysctl_mount_max);
+ unsigned int mounts = 0, old, pending, sum;
+ struct mount *p;
+
+ for (p = mnt; p; p = next_mnt(p, mnt))
+ mounts++;
+
+ old = ns->mounts;
+ pending = ns->pending_mounts;
+ sum = old + pending;
+ if ((old > sum) ||
+ (pending > sum) ||
+ (max < sum) ||
+ (mounts > (max - sum)))
+ return -ENOSPC;
+
+ ns->pending_mounts = pending + mounts;
+ return 0;
+}
+
/*
* @source_mnt : mount tree to be attached
* @nd : place the mount tree @source_mnt is attached
struct path *parent_path)
{
HLIST_HEAD(tree_list);
+ struct mnt_namespace *ns = dest_mnt->mnt_ns;
struct mount *child, *p;
struct hlist_node *n;
int err;
+ /* Is there space to add these mounts to the mount namespace? */
+ if (!parent_path) {
+ err = count_mounts(ns, source_mnt);
+ if (err)
+ goto out;
+ }
+
if (IS_MNT_SHARED(dest_mnt)) {
err = invent_group_ids(source_mnt, true);
if (err)
out_cleanup_ids:
while (!hlist_empty(&tree_list)) {
child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+ child->mnt_parent->mnt_ns->pending_mounts = 0;
umount_tree(child, UMOUNT_SYNC);
}
unlock_mount_hash();
cleanup_group_ids(source_mnt, NULL);
out:
+ ns->pending_mounts = 0;
return err;
}
flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
- MS_STRICTATIME);
+ MS_STRICTATIME | MS_NOREMOTELOCK);
if (flags & MS_REMOUNT)
retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
return retval;
}
+static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns)
+{
+ return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES);
+}
+
+static void dec_mnt_namespaces(struct ucounts *ucounts)
+{
+ dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES);
+}
+
static void free_mnt_ns(struct mnt_namespace *ns)
{
ns_free_inum(&ns->ns);
+ dec_mnt_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
kfree(ns);
}
static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
{
struct mnt_namespace *new_ns;
+ struct ucounts *ucounts;
int ret;
+ ucounts = inc_mnt_namespaces(user_ns);
+ if (!ucounts)
+ return ERR_PTR(-ENOSPC);
+
new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
- if (!new_ns)
+ if (!new_ns) {
+ dec_mnt_namespaces(ucounts);
return ERR_PTR(-ENOMEM);
+ }
ret = ns_alloc_inum(&new_ns->ns);
if (ret) {
kfree(new_ns);
+ dec_mnt_namespaces(ucounts);
return ERR_PTR(ret);
}
new_ns->ns.ops = &mntns_operations;
init_waitqueue_head(&new_ns->poll);
new_ns->event = 0;
new_ns->user_ns = get_user_ns(user_ns);
+ new_ns->ucounts = ucounts;
+ new_ns->mounts = 0;
+ new_ns->pending_mounts = 0;
return new_ns;
}
q = new;
while (p) {
q->mnt_ns = new_ns;
+ new_ns->mounts++;
if (new_fs) {
if (&p->mnt == new_fs->root.mnt) {
new_fs->root.mnt = mntget(&q->mnt);
struct mount *mnt = real_mount(m);
mnt->mnt_ns = new_ns;
new_ns->root = mnt;
+ new_ns->mounts++;
list_add(&mnt->mnt_list, &new_ns->list);
} else {
mntput(m);
return 0;
}
+static struct user_namespace *mntns_owner(struct ns_common *ns)
+{
+ return to_mnt_ns(ns)->user_ns;
+}
+
const struct proc_ns_operations mntns_operations = {
.name = "mnt",
.type = CLONE_NEWNS,
.get = mntns_get,
.put = mntns_put,
.install = mntns_install,
+ .owner = mntns_owner,
};
struct inode *inode = d_inode(dentry);
attr->ia_valid &= ~ATTR_SIZE;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
}
cleanup_inode = 1;
- user_dlm_worker = create_singlethread_workqueue("user_dlm");
+ user_dlm_worker = alloc_workqueue("user_dlm", WQ_MEM_RECLAIM, 0);
if (!user_dlm_worker) {
status = -ENOMEM;
goto bail;
if (!(attr->ia_valid & OCFS2_VALID_ATTRS))
return 0;
- status = inode_change_ok(inode, attr);
+ status = setattr_prepare(dentry, attr);
if (status)
return status;
return ret;
}
-static ssize_t ocfs2_file_splice_read(struct file *in,
- loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len,
- unsigned int flags)
-{
- int ret = 0, lock_level = 0;
- struct inode *inode = file_inode(in);
-
- trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- in->f_path.dentry->d_name.len,
- in->f_path.dentry->d_name.name, len);
-
- /*
- * See the comment in ocfs2_file_read_iter()
- */
- ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level);
- if (ret < 0) {
- mlog_errno(ret);
- goto bail;
- }
- ocfs2_inode_unlock(inode, lock_level);
-
- ret = generic_file_splice_read(in, ppos, pipe, len, flags);
-
-bail:
- return ret;
-}
-
static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
struct iov_iter *to)
{
#endif
.lock = ocfs2_lock,
.flock = ocfs2_flock,
- .splice_read = ocfs2_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
.compat_ioctl = ocfs2_compat_ioctl,
#endif
.flock = ocfs2_flock,
- .splice_read = ocfs2_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ocfs2_fallocate,
};
#include <linux/fs.h>
#include <linux/pagemap.h>
+static int flush_racache(struct inode *inode)
+{
+ struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+ struct orangefs_kernel_op_s *new_op;
+ int ret;
+
+ gossip_debug(GOSSIP_UTILS_DEBUG,
+ "%s: %pU: Handle is %pU | fs_id %d\n", __func__,
+ get_khandle_from_ino(inode), &orangefs_inode->refn.khandle,
+ orangefs_inode->refn.fs_id);
+
+ new_op = op_alloc(ORANGEFS_VFS_OP_RA_FLUSH);
+ if (!new_op)
+ return -ENOMEM;
+ new_op->upcall.req.ra_cache_flush.refn = orangefs_inode->refn;
+
+ ret = service_operation(new_op, "orangefs_flush_racache",
+ get_interruptible_flag(inode));
+
+ gossip_debug(GOSSIP_UTILS_DEBUG, "%s: got return value of %d\n",
+ __func__, ret);
+
+ op_release(new_op);
+ return ret;
+}
+
/*
* Copy to client-core's address space from the buffers specified
* by the iovec upto total_size bytes.
size_t bufmap_size;
ssize_t ret = -EINVAL;
- g_orangefs_stats.reads++;
+ orangefs_stats.reads++;
bufmap_size = orangefs_bufmap_size_query();
if (count > bufmap_size) {
gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n");
- g_orangefs_stats.reads++;
+ orangefs_stats.reads++;
rc = do_readv_writev(ORANGEFS_IO_READ, file, &pos, iter);
iocb->ki_pos = pos;
}
iocb->ki_pos = pos;
- g_orangefs_stats.writes++;
+ orangefs_stats.writes++;
out:
static int orangefs_file_release(struct inode *inode, struct file *file)
{
gossip_debug(GOSSIP_FILE_DEBUG,
- "orangefs_file_release: called on %s\n",
- file->f_path.dentry->d_name.name);
+ "orangefs_file_release: called on %pD\n",
+ file);
orangefs_flush_inode(inode);
/*
- * remove all associated inode pages from the page cache and mmap
+ * remove all associated inode pages from the page cache and
* readahead cache (if any); this forces an expensive refresh of
* data for the next caller of mmap (or 'get_block' accesses)
*/
if (file->f_path.dentry->d_inode &&
file->f_path.dentry->d_inode->i_mapping &&
- mapping_nrpages(&file->f_path.dentry->d_inode->i_data))
+ mapping_nrpages(&file->f_path.dentry->d_inode->i_data)) {
+ if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) {
+ gossip_debug(GOSSIP_INODE_DEBUG,
+ "calling flush_racache on %pU\n",
+ get_khandle_from_ino(inode));
+ flush_racache(inode);
+ gossip_debug(GOSSIP_INODE_DEBUG,
+ "flush_racache finished\n");
+ }
truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping,
0);
+ }
return 0;
}
struct inode *inode;
int ret;
- gossip_debug(GOSSIP_NAME_DEBUG, "%s: %s\n",
+ gossip_debug(GOSSIP_NAME_DEBUG, "%s: %pd\n",
__func__,
- dentry->d_name.name);
+ dentry);
new_op = op_alloc(ORANGEFS_VFS_OP_CREATE);
if (!new_op)
ret = service_operation(new_op, __func__, get_interruptible_flag(dir));
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: %s: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
+ "%s: %pd: handle:%pU: fsid:%d: new_op:%p: ret:%d:\n",
__func__,
- dentry->d_name.name,
+ dentry,
&new_op->downcall.resp.create.refn.khandle,
new_op->downcall.resp.create.refn.fs_id,
new_op,
inode = orangefs_new_inode(dir->i_sb, dir, S_IFREG | mode, 0,
&new_op->downcall.resp.create.refn);
if (IS_ERR(inode)) {
- gossip_err("%s: Failed to allocate inode for file :%s:\n",
+ gossip_err("%s: Failed to allocate inode for file :%pd:\n",
__func__,
- dentry->d_name.name);
+ dentry);
ret = PTR_ERR(inode);
goto out;
}
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: Assigned inode :%pU: for file :%s:\n",
+ "%s: Assigned inode :%pU: for file :%pd:\n",
__func__,
get_khandle_from_ino(inode),
- dentry->d_name.name);
+ dentry);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: dentry instantiated for %s\n",
+ "%s: dentry instantiated for %pd\n",
__func__,
- dentry->d_name.name);
+ dentry);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
out:
op_release(new_op);
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: %s: returning %d\n",
+ "%s: %pd: returning %d\n",
__func__,
- dentry->d_name.name,
+ dentry,
ret);
return ret;
}
* -EEXIST on O_EXCL opens, which is broken if we skip this lookup
* in the create path)
*/
- gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %s\n",
- __func__, dentry->d_name.name);
+ gossip_debug(GOSSIP_NAME_DEBUG, "%s called on %pd\n",
+ __func__, dentry);
if (dentry->d_name.len > (ORANGEFS_NAME_MAX - 1))
return ERR_PTR(-ENAMETOOLONG);
gossip_debug(GOSSIP_NAME_DEBUG,
"orangefs_lookup: Adding *negative* dentry "
- "%p for %s\n",
+ "%p for %pd\n",
dentry,
- dentry->d_name.name);
+ dentry);
d_add(dentry, NULL);
res = NULL;
goto out;
}
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn);
if (IS_ERR(inode)) {
int ret;
gossip_debug(GOSSIP_NAME_DEBUG,
- "%s: called on %s\n"
+ "%s: called on %pd\n"
" (inode %pU): Parent is %pU | fs_id %d\n",
__func__,
- dentry->d_name.name,
+ dentry,
get_khandle_from_ino(inode),
&parent->refn.khandle,
parent->refn.fs_id);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
- "Inode (Symlink) %pU -> %s\n",
+ "Inode (Symlink) %pU -> %pd\n",
get_khandle_from_ino(inode),
- dentry->d_name.name);
+ dentry);
SetMtimeFlag(parent);
dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
d_instantiate(dentry, inode);
unlock_new_inode(inode);
- dentry->d_time = jiffies + dcache_timeout_msecs*HZ/1000;
+ dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000;
ORANGEFS_I(inode)->getattr_time = jiffies - 1;
gossip_debug(GOSSIP_NAME_DEBUG,
- "Inode (Directory) %pU -> %s\n",
+ "Inode (Directory) %pU -> %pd\n",
get_khandle_from_ino(inode),
- dentry->d_name.name);
+ dentry);
/*
* NOTE: we have no good way to keep nlink consistent for directories
#include "protocol.h"
#include "orangefs-kernel.h"
-static int orangefs_debug_disabled = 1;
-
-static int orangefs_debug_help_open(struct inode *, struct file *);
+#define DEBUG_HELP_STRING_SIZE 4096
+#define HELP_STRING_UNINITIALIZED \
+ "Client Debug Keywords are unknown until the first time\n" \
+ "the client is started after boot.\n"
+#define ORANGEFS_KMOD_DEBUG_HELP_FILE "debug-help"
+#define ORANGEFS_KMOD_DEBUG_FILE "kernel-debug"
+#define ORANGEFS_CLIENT_DEBUG_FILE "client-debug"
+#define ORANGEFS_VERBOSE "verbose"
+#define ORANGEFS_ALL "all"
-const struct file_operations debug_help_fops = {
- .open = orangefs_debug_help_open,
- .read = seq_read,
- .release = seq_release,
- .llseek = seq_lseek,
+/*
+ * An array of client_debug_mask will be built to hold debug keyword/mask
+ * values fetched from userspace.
+ */
+struct client_debug_mask {
+ char *keyword;
+ __u64 mask1;
+ __u64 mask2;
};
+static int orangefs_kernel_debug_init(void);
+
+static int orangefs_debug_help_open(struct inode *, struct file *);
static void *help_start(struct seq_file *, loff_t *);
static void *help_next(struct seq_file *, void *, loff_t *);
static void help_stop(struct seq_file *, void *);
static int help_show(struct seq_file *, void *);
-static const struct seq_operations help_debug_ops = {
- .start = help_start,
- .next = help_next,
- .stop = help_stop,
- .show = help_show,
-};
-
-/*
- * Used to protect data in ORANGEFS_KMOD_DEBUG_FILE and
- * ORANGEFS_KMOD_DEBUG_FILE.
- */
-static DEFINE_MUTEX(orangefs_debug_lock);
-
-int orangefs_debug_open(struct inode *, struct file *);
+static int orangefs_debug_open(struct inode *, struct file *);
static ssize_t orangefs_debug_read(struct file *,
char __user *,
size_t,
loff_t *);
+static int orangefs_prepare_cdm_array(char *);
+static void debug_mask_to_string(void *, int);
+static void do_k_string(void *, int);
+static void do_c_string(void *, int);
+static int keyword_is_amalgam(char *);
+static int check_amalgam_keyword(void *, int);
+static void debug_string_to_mask(char *, void *, int);
+static void do_c_mask(int, char *, struct client_debug_mask **);
+static void do_k_mask(int, char *, __u64 **);
+
+static char kernel_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN] = "none";
+static char *debug_help_string;
+static char client_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+static char client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN];
+
+static struct dentry *help_file_dentry;
+static struct dentry *client_debug_dentry;
+static struct dentry *debug_dir;
+
+static unsigned int kernel_mask_set_mod_init;
+static int orangefs_debug_disabled = 1;
+static int help_string_initialized;
+
+static const struct seq_operations help_debug_ops = {
+ .start = help_start,
+ .next = help_next,
+ .stop = help_stop,
+ .show = help_show,
+};
+
+const struct file_operations debug_help_fops = {
+ .open = orangefs_debug_help_open,
+ .read = seq_read,
+ .release = seq_release,
+ .llseek = seq_lseek,
+};
+
static const struct file_operations kernel_debug_fops = {
.open = orangefs_debug_open,
.read = orangefs_debug_read,
.llseek = generic_file_llseek,
};
+static int client_all_index;
+static int client_verbose_index;
+
+static struct client_debug_mask *cdm_array;
+static int cdm_element_count;
+
+static struct client_debug_mask client_debug_mask;
+
+/*
+ * Used to protect data in ORANGEFS_KMOD_DEBUG_FILE and
+ * ORANGEFS_KMOD_DEBUG_FILE.
+ */
+static DEFINE_MUTEX(orangefs_debug_lock);
+
/*
* initialize kmod debug operations, create orangefs debugfs dir and
* ORANGEFS_KMOD_DEBUG_HELP_FILE.
*/
-int orangefs_debugfs_init(void)
+int orangefs_debugfs_init(int debug_mask)
{
-
int rc = -ENOMEM;
+ /* convert input debug mask to a 64-bit unsigned integer */
+ orangefs_gossip_debug_mask = (unsigned long long)debug_mask;
+
+ /*
+ * set the kernel's gossip debug string; invalid mask values will
+ * be ignored.
+ */
+ debug_mask_to_string(&orangefs_gossip_debug_mask, 0);
+
+ /* remove any invalid values from the mask */
+ debug_string_to_mask(kernel_debug_string, &orangefs_gossip_debug_mask,
+ 0);
+
+ /*
+ * if the mask has a non-zero value, then indicate that the mask
+ * was set when the kernel module was loaded. The orangefs dev ioctl
+ * command will look at this boolean to determine if the kernel's
+ * debug mask should be overwritten when the client-core is started.
+ */
+ if (orangefs_gossip_debug_mask != 0)
+ kernel_mask_set_mod_init = true;
+
+ pr_info("%s: called with debug mask: :%s: :%llx:\n",
+ __func__,
+ kernel_debug_string,
+ (unsigned long long)orangefs_gossip_debug_mask);
+
debug_dir = debugfs_create_dir("orangefs", NULL);
if (!debug_dir) {
pr_info("%s: debugfs_create_dir failed.\n", __func__);
}
orangefs_debug_disabled = 0;
+
+ rc = orangefs_kernel_debug_init();
+
+out:
+
+ return rc;
+}
+
+/*
+ * initialize the kernel-debug file.
+ */
+static int orangefs_kernel_debug_init(void)
+{
+ int rc = -ENOMEM;
+ struct dentry *ret;
+ char *k_buffer = NULL;
+
+ gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
+
+ k_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
+ if (!k_buffer)
+ goto out;
+
+ if (strlen(kernel_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
+ strcpy(k_buffer, kernel_debug_string);
+ strcat(k_buffer, "\n");
+ } else {
+ strcpy(k_buffer, "none\n");
+ pr_info("%s: overflow 1!\n", __func__);
+ }
+
+ ret = debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE,
+ 0444,
+ debug_dir,
+ k_buffer,
+ &kernel_debug_fops);
+ if (!ret) {
+ pr_info("%s: failed to create %s.\n",
+ __func__,
+ ORANGEFS_KMOD_DEBUG_FILE);
+ goto out;
+ }
+
rc = 0;
out:
+ gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
return rc;
}
+
void orangefs_debugfs_cleanup(void)
{
debugfs_remove_recursive(debug_dir);
return 0;
}
-/*
- * initialize the kernel-debug file.
- */
-int orangefs_kernel_debug_init(void)
-{
- int rc = -ENOMEM;
- struct dentry *ret;
- char *k_buffer = NULL;
-
- gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__);
-
- k_buffer = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL);
- if (!k_buffer)
- goto out;
-
- if (strlen(kernel_debug_string) + 1 < ORANGEFS_MAX_DEBUG_STRING_LEN) {
- strcpy(k_buffer, kernel_debug_string);
- strcat(k_buffer, "\n");
- } else {
- strcpy(k_buffer, "none\n");
- pr_info("%s: overflow 1!\n", __func__);
- }
-
- ret = debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE,
- 0444,
- debug_dir,
- k_buffer,
- &kernel_debug_fops);
- if (!ret) {
- pr_info("%s: failed to create %s.\n",
- __func__,
- ORANGEFS_KMOD_DEBUG_FILE);
- goto out;
- }
-
- rc = 0;
-
-out:
-
- gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc);
- return rc;
-}
-
/*
* initialize the client-debug file.
*/
}
/* open ORANGEFS_KMOD_DEBUG_FILE or ORANGEFS_CLIENT_DEBUG_FILE.*/
-int orangefs_debug_open(struct inode *inode, struct file *file)
+static int orangefs_debug_open(struct inode *inode, struct file *file)
{
int rc = -ENODEV;
struct client_debug_mask c_mask = { NULL, 0, 0 };
gossip_debug(GOSSIP_DEBUGFS_DEBUG,
- "orangefs_debug_write: %s\n",
- file->f_path.dentry->d_name.name);
+ "orangefs_debug_write: %pD\n",
+ file);
/*
* Thwart users who try to jamb a ridiculous number
*/
if (!strcmp(file->f_path.dentry->d_name.name,
ORANGEFS_KMOD_DEBUG_FILE)) {
- debug_string_to_mask(buf, &gossip_debug_mask, 0);
- debug_mask_to_string(&gossip_debug_mask, 0);
+ debug_string_to_mask(buf, &orangefs_gossip_debug_mask, 0);
+ debug_mask_to_string(&orangefs_gossip_debug_mask, 0);
debug_string = kernel_debug_string;
gossip_debug(GOSSIP_DEBUGFS_DEBUG,
"New kernel debug string is %s\n",
kfree(buf);
return rc;
}
+
+/*
+ * After obtaining a string representation of the client's debug
+ * keywords and their associated masks, this function is called to build an
+ * array of these values.
+ */
+static int orangefs_prepare_cdm_array(char *debug_array_string)
+{
+ int i;
+ int rc = -EINVAL;
+ char *cds_head = NULL;
+ char *cds_delimiter = NULL;
+ int keyword_len = 0;
+
+ gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+ /*
+ * figure out how many elements the cdm_array needs.
+ */
+ for (i = 0; i < strlen(debug_array_string); i++)
+ if (debug_array_string[i] == '\n')
+ cdm_element_count++;
+
+ if (!cdm_element_count) {
+ pr_info("No elements in client debug array string!\n");
+ goto out;
+ }
+
+ cdm_array =
+ kzalloc(cdm_element_count * sizeof(struct client_debug_mask),
+ GFP_KERNEL);
+ if (!cdm_array) {
+ pr_info("malloc failed for cdm_array!\n");
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ cds_head = debug_array_string;
+
+ for (i = 0; i < cdm_element_count; i++) {
+ cds_delimiter = strchr(cds_head, '\n');
+ *cds_delimiter = '\0';
+
+ keyword_len = strcspn(cds_head, " ");
+
+ cdm_array[i].keyword = kzalloc(keyword_len + 1, GFP_KERNEL);
+ if (!cdm_array[i].keyword) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ sscanf(cds_head,
+ "%s %llx %llx",
+ cdm_array[i].keyword,
+ (unsigned long long *)&(cdm_array[i].mask1),
+ (unsigned long long *)&(cdm_array[i].mask2));
+
+ if (!strcmp(cdm_array[i].keyword, ORANGEFS_VERBOSE))
+ client_verbose_index = i;
+
+ if (!strcmp(cdm_array[i].keyword, ORANGEFS_ALL))
+ client_all_index = i;
+
+ cds_head = cds_delimiter + 1;
+ }
+
+ rc = cdm_element_count;
+
+ gossip_debug(GOSSIP_UTILS_DEBUG, "%s: rc:%d:\n", __func__, rc);
+
+out:
+
+ return rc;
+
+}
+
+/*
+ * /sys/kernel/debug/orangefs/debug-help can be catted to
+ * see all the available kernel and client debug keywords.
+ *
+ * When the kernel boots, we have no idea what keywords the
+ * client supports, nor their associated masks.
+ *
+ * We pass through this function once at boot and stamp a
+ * boilerplate "we don't know" message for the client in the
+ * debug-help file. We pass through here again when the client
+ * starts and then we can fill out the debug-help file fully.
+ *
+ * The client might be restarted any number of times between
+ * reboots, we only build the debug-help file the first time.
+ */
+int orangefs_prepare_debugfs_help_string(int at_boot)
+{
+ int rc = -EINVAL;
+ int i;
+ int byte_count = 0;
+ char *client_title = "Client Debug Keywords:\n";
+ char *kernel_title = "Kernel Debug Keywords:\n";
+
+ gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+ if (at_boot) {
+ byte_count += strlen(HELP_STRING_UNINITIALIZED);
+ client_title = HELP_STRING_UNINITIALIZED;
+ } else {
+ /*
+ * fill the client keyword/mask array and remember
+ * how many elements there were.
+ */
+ cdm_element_count =
+ orangefs_prepare_cdm_array(client_debug_array_string);
+ if (cdm_element_count <= 0)
+ goto out;
+
+ /* Count the bytes destined for debug_help_string. */
+ byte_count += strlen(client_title);
+
+ for (i = 0; i < cdm_element_count; i++) {
+ byte_count += strlen(cdm_array[i].keyword + 2);
+ if (byte_count >= DEBUG_HELP_STRING_SIZE) {
+ pr_info("%s: overflow 1!\n", __func__);
+ goto out;
+ }
+ }
+
+ gossip_debug(GOSSIP_UTILS_DEBUG,
+ "%s: cdm_element_count:%d:\n",
+ __func__,
+ cdm_element_count);
+ }
+
+ byte_count += strlen(kernel_title);
+ for (i = 0; i < num_kmod_keyword_mask_map; i++) {
+ byte_count +=
+ strlen(s_kmod_keyword_mask_map[i].keyword + 2);
+ if (byte_count >= DEBUG_HELP_STRING_SIZE) {
+ pr_info("%s: overflow 2!\n", __func__);
+ goto out;
+ }
+ }
+
+ /* build debug_help_string. */
+ debug_help_string = kzalloc(DEBUG_HELP_STRING_SIZE, GFP_KERNEL);
+ if (!debug_help_string) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ strcat(debug_help_string, client_title);
+
+ if (!at_boot) {
+ for (i = 0; i < cdm_element_count; i++) {
+ strcat(debug_help_string, "\t");
+ strcat(debug_help_string, cdm_array[i].keyword);
+ strcat(debug_help_string, "\n");
+ }
+ }
+
+ strcat(debug_help_string, "\n");
+ strcat(debug_help_string, kernel_title);
+
+ for (i = 0; i < num_kmod_keyword_mask_map; i++) {
+ strcat(debug_help_string, "\t");
+ strcat(debug_help_string, s_kmod_keyword_mask_map[i].keyword);
+ strcat(debug_help_string, "\n");
+ }
+
+ rc = 0;
+
+out:
+
+ return rc;
+
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ */
+static void debug_mask_to_string(void *mask, int type)
+{
+ int i;
+ int len = 0;
+ char *debug_string;
+ int element_count = 0;
+
+ gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+ if (type) {
+ debug_string = client_debug_string;
+ element_count = cdm_element_count;
+ } else {
+ debug_string = kernel_debug_string;
+ element_count = num_kmod_keyword_mask_map;
+ }
+
+ memset(debug_string, 0, ORANGEFS_MAX_DEBUG_STRING_LEN);
+
+ /*
+ * Some keywords, like "all" or "verbose", are amalgams of
+ * numerous other keywords. Make a special check for those
+ * before grinding through the whole mask only to find out
+ * later...
+ */
+ if (check_amalgam_keyword(mask, type))
+ goto out;
+
+ /* Build the debug string. */
+ for (i = 0; i < element_count; i++)
+ if (type)
+ do_c_string(mask, i);
+ else
+ do_k_string(mask, i);
+
+ len = strlen(debug_string);
+
+ if ((len) && (type))
+ client_debug_string[len - 1] = '\0';
+ else if (len)
+ kernel_debug_string[len - 1] = '\0';
+ else if (type)
+ strcpy(client_debug_string, "none");
+ else
+ strcpy(kernel_debug_string, "none");
+
+out:
+gossip_debug(GOSSIP_UTILS_DEBUG, "%s: string:%s:\n", __func__, debug_string);
+
+ return;
+
+}
+
+static void do_k_string(void *k_mask, int index)
+{
+ __u64 *mask = (__u64 *) k_mask;
+
+ if (keyword_is_amalgam((char *) s_kmod_keyword_mask_map[index].keyword))
+ goto out;
+
+ if (*mask & s_kmod_keyword_mask_map[index].mask_val) {
+ if ((strlen(kernel_debug_string) +
+ strlen(s_kmod_keyword_mask_map[index].keyword))
+ < ORANGEFS_MAX_DEBUG_STRING_LEN - 1) {
+ strcat(kernel_debug_string,
+ s_kmod_keyword_mask_map[index].keyword);
+ strcat(kernel_debug_string, ",");
+ } else {
+ gossip_err("%s: overflow!\n", __func__);
+ strcpy(kernel_debug_string, ORANGEFS_ALL);
+ goto out;
+ }
+ }
+
+out:
+
+ return;
+}
+
+static void do_c_string(void *c_mask, int index)
+{
+ struct client_debug_mask *mask = (struct client_debug_mask *) c_mask;
+
+ if (keyword_is_amalgam(cdm_array[index].keyword))
+ goto out;
+
+ if ((mask->mask1 & cdm_array[index].mask1) ||
+ (mask->mask2 & cdm_array[index].mask2)) {
+ if ((strlen(client_debug_string) +
+ strlen(cdm_array[index].keyword) + 1)
+ < ORANGEFS_MAX_DEBUG_STRING_LEN - 2) {
+ strcat(client_debug_string,
+ cdm_array[index].keyword);
+ strcat(client_debug_string, ",");
+ } else {
+ gossip_err("%s: overflow!\n", __func__);
+ strcpy(client_debug_string, ORANGEFS_ALL);
+ goto out;
+ }
+ }
+out:
+ return;
+}
+
+static int keyword_is_amalgam(char *keyword)
+{
+ int rc = 0;
+
+ if ((!strcmp(keyword, ORANGEFS_ALL)) || (!strcmp(keyword, ORANGEFS_VERBOSE)))
+ rc = 1;
+
+ return rc;
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ *
+ * return 1 if we found an amalgam.
+ */
+static int check_amalgam_keyword(void *mask, int type)
+{
+ __u64 *k_mask;
+ struct client_debug_mask *c_mask;
+ int k_all_index = num_kmod_keyword_mask_map - 1;
+ int rc = 0;
+
+ if (type) {
+ c_mask = (struct client_debug_mask *) mask;
+
+ if ((c_mask->mask1 == cdm_array[client_all_index].mask1) &&
+ (c_mask->mask2 == cdm_array[client_all_index].mask2)) {
+ strcpy(client_debug_string, ORANGEFS_ALL);
+ rc = 1;
+ goto out;
+ }
+
+ if ((c_mask->mask1 == cdm_array[client_verbose_index].mask1) &&
+ (c_mask->mask2 == cdm_array[client_verbose_index].mask2)) {
+ strcpy(client_debug_string, ORANGEFS_VERBOSE);
+ rc = 1;
+ goto out;
+ }
+
+ } else {
+ k_mask = (__u64 *) mask;
+
+ if (*k_mask >= s_kmod_keyword_mask_map[k_all_index].mask_val) {
+ strcpy(kernel_debug_string, ORANGEFS_ALL);
+ rc = 1;
+ goto out;
+ }
+ }
+
+out:
+
+ return rc;
+}
+
+/*
+ * kernel = type 0
+ * client = type 1
+ */
+static void debug_string_to_mask(char *debug_string, void *mask, int type)
+{
+ char *unchecked_keyword;
+ int i;
+ char *strsep_fodder = kstrdup(debug_string, GFP_KERNEL);
+ char *original_pointer;
+ int element_count = 0;
+ struct client_debug_mask *c_mask = NULL;
+ __u64 *k_mask = NULL;
+
+ gossip_debug(GOSSIP_UTILS_DEBUG, "%s: start\n", __func__);
+
+ if (type) {
+ c_mask = (struct client_debug_mask *)mask;
+ element_count = cdm_element_count;
+ } else {
+ k_mask = (__u64 *)mask;
+ *k_mask = 0;
+ element_count = num_kmod_keyword_mask_map;
+ }
+
+ original_pointer = strsep_fodder;
+ while ((unchecked_keyword = strsep(&strsep_fodder, ",")))
+ if (strlen(unchecked_keyword)) {
+ for (i = 0; i < element_count; i++)
+ if (type)
+ do_c_mask(i,
+ unchecked_keyword,
+ &c_mask);
+ else
+ do_k_mask(i,
+ unchecked_keyword,
+ &k_mask);
+ }
+
+ kfree(original_pointer);
+}
+
+static void do_c_mask(int i, char *unchecked_keyword,
+ struct client_debug_mask **sane_mask)
+{
+
+ if (!strcmp(cdm_array[i].keyword, unchecked_keyword)) {
+ (**sane_mask).mask1 = (**sane_mask).mask1 | cdm_array[i].mask1;
+ (**sane_mask).mask2 = (**sane_mask).mask2 | cdm_array[i].mask2;
+ }
+}
+
+static void do_k_mask(int i, char *unchecked_keyword, __u64 **sane_mask)
+{
+
+ if (!strcmp(s_kmod_keyword_mask_map[i].keyword, unchecked_keyword))
+ **sane_mask = (**sane_mask) |
+ s_kmod_keyword_mask_map[i].mask_val;
+}
+
+int orangefs_debugfs_new_client_mask(void __user *arg)
+{
+ struct dev_mask2_info_s mask2_info = {0};
+ int ret;
+
+ ret = copy_from_user(&mask2_info,
+ (void __user *)arg,
+ sizeof(struct dev_mask2_info_s));
+
+ if (ret != 0)
+ return -EIO;
+
+ client_debug_mask.mask1 = mask2_info.mask1_value;
+ client_debug_mask.mask2 = mask2_info.mask2_value;
+
+ pr_info("%s: client debug mask has been been received "
+ ":%llx: :%llx:\n",
+ __func__,
+ (unsigned long long)client_debug_mask.mask1,
+ (unsigned long long)client_debug_mask.mask2);
+
+ return ret;
+}
+
+int orangefs_debugfs_new_client_string(void __user *arg)
+{
+ int ret;
+
+ ret = copy_from_user(&client_debug_array_string,
+ (void __user *)arg,
+ ORANGEFS_MAX_DEBUG_STRING_LEN);
+ if (ret != 0)
+ return -EIO;
+
+ /*
+ * The real client-core makes an effort to ensure
+ * that actual strings that aren't too long to fit in
+ * this buffer is what we get here. We're going to use
+ * string functions on the stuff we got, so we'll make
+ * this extra effort to try and keep from
+ * flowing out of this buffer when we use the string
+ * functions, even if somehow the stuff we end up
+ * with here is garbage.
+ */
+ client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
+ '\0';
+
+ if (ret != 0) {
+ pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
+ __func__);
+ return -EIO;
+ }
+
+ pr_info("%s: client debug array string has been received.\n",
+ __func__);
+
+ if (!help_string_initialized) {
+
+ /* Free the "we don't know yet" default string... */
+ kfree(debug_help_string);
+
+ /* build a proper debug help string */
+ if (orangefs_prepare_debugfs_help_string(0)) {
+ gossip_err("%s: no debug help string \n",
+ __func__);
+ return -EIO;
+ }
+
+ /* Replace the boilerplate boot-time debug-help file. */
+ debugfs_remove(help_file_dentry);
+
+ help_file_dentry =
+ debugfs_create_file(
+ ORANGEFS_KMOD_DEBUG_HELP_FILE,
+ 0444,
+ debug_dir,
+ debug_help_string,
+ &debug_help_fops);
+
+ if (!help_file_dentry) {
+ gossip_err("%s: debugfs_create_file failed for"
+ " :%s:!\n",
+ __func__,
+ ORANGEFS_KMOD_DEBUG_HELP_FILE);
+ return -EIO;
+ }
+ }
+
+ debug_mask_to_string(&client_debug_mask, 1);
+
+ debugfs_remove(client_debug_dentry);
+
+ orangefs_client_debug_init();
+
+ help_string_initialized++;
+
+ return ret;
+}
+
+int orangefs_debugfs_new_debug(void __user *arg)
+{
+ struct dev_mask_info_s mask_info = {0};
+ int ret;
+
+ ret = copy_from_user(&mask_info,
+ (void __user *)arg,
+ sizeof(mask_info));
+
+ if (ret != 0)
+ return -EIO;
+
+ if (mask_info.mask_type == KERNEL_MASK) {
+ if ((mask_info.mask_value == 0)
+ && (kernel_mask_set_mod_init)) {
+ /*
+ * the kernel debug mask was set when the
+ * kernel module was loaded; don't override
+ * it if the client-core was started without
+ * a value for ORANGEFS_KMODMASK.
+ */
+ return 0;
+ }
+ debug_mask_to_string(&mask_info.mask_value,
+ mask_info.mask_type);
+ orangefs_gossip_debug_mask = mask_info.mask_value;
+ pr_info("%s: kernel debug mask has been modified to "
+ ":%s: :%llx:\n",
+ __func__,
+ kernel_debug_string,
+ (unsigned long long)orangefs_gossip_debug_mask);
+ } else if (mask_info.mask_type == CLIENT_MASK) {
+ debug_mask_to_string(&mask_info.mask_value,
+ mask_info.mask_type);
+ pr_info("%s: client debug mask has been modified to"
+ ":%s: :%llx:\n",
+ __func__,
+ client_debug_string,
+ llu(mask_info.mask_value));
+ } else {
+ gossip_lerr("Invalid mask type....\n");
+ return -EINVAL;
+ }
+
+ return ret;
+}
.llseek = generic_file_llseek,
};
- static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task)
- {
- struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
- if (mm && !IS_ERR(mm)) {
- unsigned int nwords = 0;
- do {
- nwords += 2;
- } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
- seq_write(m, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0]));
- mmput(mm);
- return 0;
- } else
- return PTR_ERR(mm);
- }
-
-
#ifdef CONFIG_KALLSYMS
/*
* Provides a wchan file via kallsyms in a proper one-value-per-file format.
save_stack_trace_tsk(task, &trace);
for (i = 0; i < trace.nr_entries; i++) {
- seq_printf(m, "[<%pK>] %pS\n",
+ seq_printf(m, "[<%pK>] %pB\n",
(void *)entries[i], (void *)entries[i]);
}
unlock_trace(task);
if (attr->ia_valid & ATTR_MODE)
return -EPERM;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
.release = mem_release,
};
+ static int auxv_open(struct inode *inode, struct file *file)
+ {
+ return __mem_open(inode, file, PTRACE_MODE_READ_FSCREDS);
+ }
+
+ static ssize_t auxv_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+ {
+ struct mm_struct *mm = file->private_data;
+ unsigned int nwords = 0;
+ do {
+ nwords += 2;
+ } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
+ return simple_read_from_buffer(buf, count, ppos, mm->saved_auxv,
+ nwords * sizeof(mm->saved_auxv[0]));
+ }
+
+ static const struct file_operations proc_auxv_operations = {
+ .open = auxv_open,
+ .read = auxv_read,
+ .llseek = generic_file_llseek,
+ .release = mem_release,
+ };
+
static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
if (!p)
return -ESRCH;
- if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
- task_lock(p);
- if (slack_ns == 0)
- p->timer_slack_ns = p->default_timer_slack_ns;
- else
- p->timer_slack_ns = slack_ns;
- task_unlock(p);
- } else
- count = -EPERM;
+ if (p != current) {
+ if (!capable(CAP_SYS_NICE)) {
+ count = -EPERM;
+ goto out;
+ }
+
+ err = security_task_setscheduler(p);
+ if (err) {
+ count = err;
+ goto out;
+ }
+ }
+
+ task_lock(p);
+ if (slack_ns == 0)
+ p->timer_slack_ns = p->default_timer_slack_ns;
+ else
+ p->timer_slack_ns = slack_ns;
+ task_unlock(p);
+out:
put_task_struct(p);
return count;
{
struct inode *inode = m->private;
struct task_struct *p;
- int err = 0;
+ int err = 0;
p = get_proc_task(inode);
if (!p)
return -ESRCH;
- if (ptrace_may_access(p, PTRACE_MODE_ATTACH_FSCREDS)) {
- task_lock(p);
- seq_printf(m, "%llu\n", p->timer_slack_ns);
- task_unlock(p);
- } else
- err = -EPERM;
+ if (p != current) {
+
+ if (!capable(CAP_SYS_NICE)) {
+ err = -EPERM;
+ goto out;
+ }
+ err = security_task_getscheduler(p);
+ if (err)
+ goto out;
+ }
+ task_lock(p);
+ seq_printf(m, "%llu\n", p->timer_slack_ns);
+ task_unlock(p);
+
+out:
put_task_struct(p);
return err;
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
#endif
REG("environ", S_IRUSR, proc_environ_operations),
- ONE("auxv", S_IRUSR, proc_pid_auxv),
+ REG("auxv", S_IRUSR, proc_auxv_operations),
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
ONE("limits", S_IRUGO, proc_pid_limits),
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
#endif
REG("environ", S_IRUSR, proc_environ_operations),
- ONE("auxv", S_IRUSR, proc_pid_auxv),
+ REG("auxv", S_IRUSR, proc_auxv_operations),
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
ONE("limits", S_IRUGO, proc_pid_limits),
struct proc_dir_entry *de = PDE(inode);
int error;
- error = inode_change_ok(inode, iattr);
+ error = setattr_prepare(dentry, iattr);
if (error)
return error;
atomic_set(&ent->count, 1);
spin_lock_init(&ent->pde_unload_lock);
INIT_LIST_HEAD(&ent->pde_openers);
+ proc_set_user(ent, (*parent)->uid, (*parent)->gid);
+
out:
return ent;
}
static void drop_sysctl_table(struct ctl_table_header *header);
static int sysctl_follow_link(struct ctl_table_header **phead,
- struct ctl_table **pentry, struct nsproxy *namespaces);
+ struct ctl_table **pentry);
static int insert_links(struct ctl_table_header *head);
static void put_links(struct ctl_table_header *header);
}
static struct ctl_table_set *
-lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+lookup_header_set(struct ctl_table_root *root)
{
struct ctl_table_set *set = &root->default_set;
if (root->lookup)
- set = root->lookup(root, namespaces);
+ set = root->lookup(root);
return set;
}
static struct inode *proc_sys_make_inode(struct super_block *sb,
struct ctl_table_header *head, struct ctl_table *table)
{
+ struct ctl_table_root *root = head->root;
struct inode *inode;
struct proc_inode *ei;
if (is_empty_dir(head))
make_empty_dir_inode(inode);
}
+
+ if (root->set_ownership)
+ root->set_ownership(head, table, &inode->i_uid, &inode->i_gid);
+
out:
return inode;
}
goto out;
if (S_ISLNK(p->mode)) {
- ret = sysctl_follow_link(&h, &p, current->nsproxy);
+ ret = sysctl_follow_link(&h, &p);
err = ERR_PTR(ret);
if (ret)
goto out;
if (S_ISLNK(table->mode)) {
/* It is not an error if we can not follow the link ignore it */
- int err = sysctl_follow_link(&head, &table, current->nsproxy);
+ int err = sysctl_follow_link(&head, &table);
if (err)
goto out;
}
if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
return -EPERM;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
}
static int sysctl_follow_link(struct ctl_table_header **phead,
- struct ctl_table **pentry, struct nsproxy *namespaces)
+ struct ctl_table **pentry)
{
struct ctl_table_header *head;
struct ctl_table_root *root;
ret = 0;
spin_lock(&sysctl_lock);
root = (*pentry)->data;
- set = lookup_header_set(root, namespaces);
+ set = lookup_header_set(root);
dir = xlate_dir(set, (*phead)->parent);
if (IS_ERR(dir))
ret = PTR_ERR(dir);
return -EINVAL;
}
+ file_accessed(iocb->ki_filp);
+
/*
* Locking is a bit tricky here. If we take an exclusive lock for direct
* IO, we effectively serialise all new concurrent read IO to this file
}
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
- file_accessed(iocb->ki_filp);
return ret;
}
struct kiocb *iocb,
struct iov_iter *to)
{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- struct inode *inode = mapping->host;
- struct xfs_inode *ip = XFS_I(inode);
- struct iov_iter data = *to;
+ struct xfs_inode *ip = XFS_I(iocb->ki_filp->f_mapping->host);
size_t count = iov_iter_count(to);
ssize_t ret = 0;
return 0; /* skip atime */
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
- ret = dax_do_io(iocb, inode, &data, xfs_get_blocks_direct, NULL, 0);
- if (ret > 0) {
- iocb->ki_pos += ret;
- iov_iter_advance(to, ret);
- }
+ ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
file_accessed(iocb->ki_filp);
return ret;
}
-STATIC ssize_t
-xfs_file_splice_read(
- struct file *infilp,
- loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t count,
- unsigned int flags)
-{
- struct xfs_inode *ip = XFS_I(infilp->f_mapping->host);
- ssize_t ret;
-
- XFS_STATS_INC(ip->i_mount, xs_read_calls);
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- return -EIO;
-
- trace_xfs_file_splice_read(ip, count, *ppos);
-
- /*
- * DAX inodes cannot ues the page cache for splice, so we have to push
- * them through the VFS IO path. This means it goes through
- * ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we
- * cannot lock the splice operation at this level for DAX inodes.
- */
- if (IS_DAX(VFS_I(ip))) {
- ret = default_file_splice_read(infilp, ppos, pipe, count,
- flags);
- goto out;
- }
-
- xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
- ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
- xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-out:
- if (ret > 0)
- XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
- return ret;
-}
-
/*
* Zero any on disk space between the current EOF and the new, larger EOF.
*
struct kiocb *iocb,
struct iov_iter *from)
{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- struct inode *inode = mapping->host;
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
- struct xfs_mount *mp = ip->i_mount;
- ssize_t ret = 0;
- int unaligned_io = 0;
- int iolock;
- struct iov_iter data;
+ int iolock = XFS_IOLOCK_EXCL;
+ ssize_t ret, error = 0;
+ size_t count;
+ loff_t pos;
- /* "unaligned" here means not aligned to a filesystem block */
- if ((iocb->ki_pos & mp->m_blockmask) ||
- ((iocb->ki_pos + iov_iter_count(from)) & mp->m_blockmask)) {
- unaligned_io = 1;
- iolock = XFS_IOLOCK_EXCL;
- } else if (mapping->nrpages) {
- iolock = XFS_IOLOCK_EXCL;
- } else {
- iolock = XFS_IOLOCK_SHARED;
- }
xfs_rw_ilock(ip, iolock);
-
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
- /*
- * Yes, even DAX files can have page cache attached to them: A zeroed
- * page is inserted into the pagecache when we have to serve a write
- * fault on a hole. It should never be dirtied and can simply be
- * dropped from the pagecache once we get real data for the page.
- *
- * XXX: This is racy against mmap, and there's nothing we can do about
- * it. dax_do_io() should really do this invalidation internally as
- * it will know if we've allocated over a holei for this specific IO and
- * if so it needs to update the mapping tree and invalidate existing
- * PTEs over the newly allocated range. Remove this invalidation when
- * dax_do_io() is fixed up.
- */
- if (mapping->nrpages) {
- loff_t end = iocb->ki_pos + iov_iter_count(from) - 1;
+ pos = iocb->ki_pos;
+ count = iov_iter_count(from);
- ret = invalidate_inode_pages2_range(mapping,
- iocb->ki_pos >> PAGE_SHIFT,
- end >> PAGE_SHIFT);
- WARN_ON_ONCE(ret);
- }
+ trace_xfs_file_dax_write(ip, count, pos);
- if (iolock == XFS_IOLOCK_EXCL && !unaligned_io) {
- xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
- iolock = XFS_IOLOCK_SHARED;
+ ret = iomap_dax_rw(iocb, from, &xfs_iomap_ops);
+ if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
+ i_size_write(inode, iocb->ki_pos);
+ error = xfs_setfilesize(ip, pos, ret);
}
- trace_xfs_file_dax_write(ip, iov_iter_count(from), iocb->ki_pos);
-
- data = *from;
- ret = dax_do_io(iocb, inode, &data, xfs_get_blocks_direct,
- xfs_end_io_direct_write, 0);
- if (ret > 0) {
- iocb->ki_pos += ret;
- iov_iter_advance(from, ret);
- }
out:
xfs_rw_iunlock(ip, iolock);
- return ret;
+ return error ? error : ret;
}
STATIC ssize_t
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
- error = xfs_setattr_size(ip, &iattr);
+ error = xfs_vn_setattr_size(file_dentry(file), &iattr);
if (error)
goto out_unlock;
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
- ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
+ ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
} else {
ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
ret = block_page_mkwrite_return(ret);
* changes to xfs_get_blocks_direct() to map unwritten extent
* ioend for conversion on read-only mappings.
*/
- ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
+ ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
} else
ret = filemap_fault(vma, vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
.llseek = xfs_file_llseek,
.read_iter = xfs_file_read_iter,
.write_iter = xfs_file_write_iter,
- .splice_read = xfs_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
.open = xfs_file_open,
.release = xfs_file_release,
.fsync = xfs_file_fsync,
+ .get_unmapped_area = thp_get_unmapped_area,
.fallocate = xfs_file_fallocate,
};
extern struct files_stat_struct files_stat;
extern unsigned long get_max_files(void);
- extern int sysctl_nr_open;
+ extern unsigned int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
extern int sysctl_protected_symlinks;
#define ATTR_KILL_PRIV (1 << 14)
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
+ #define ATTR_TOUCH (1 << 17)
/*
* Whiteout is represented by a char device. The following constants define the
extern void send_sigio(struct fown_struct *fown, int fd, int band);
+ /*
+ * Return the inode to use for locking
+ *
+ * For overlayfs this should be the overlay inode, not the real inode returned
+ * by file_inode(). For any other fs file_inode(filp) and locks_inode(filp) are
+ * equal.
+ */
+ static inline struct inode *locks_inode(const struct file *f)
+ {
+ return f->f_path.dentry->d_inode;
+ }
+
#ifdef CONFIG_FILE_LOCKING
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
- return locks_lock_inode_wait(file_inode(filp), fl);
+ return locks_lock_inode_wait(locks_inode(filp), fl);
}
struct fasync_struct {
S_VERSION = 8,
};
- extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
static inline void file_accessed(struct file *file)
{
static inline int locks_verify_locked(struct file *file)
{
- if (mandatory_lock(file_inode(file)))
+ if (mandatory_lock(locks_inode(file)))
return locks_mandatory_locked(file);
return 0;
}
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
-extern ssize_t default_file_splice_read(struct file *, loff_t *,
- struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
#define buffer_migrate_page NULL
#endif
- extern int inode_change_ok(const struct inode *, struct iattr *);
+ extern int setattr_prepare(struct dentry *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */
AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */
AS_EXITING = __GFP_BITS_SHIFT + 4, /* final truncate in progress */
+ /* writeback related tags are not used */
+ AS_NO_WRITEBACK_TAGS = __GFP_BITS_SHIFT + 5,
};
static inline void mapping_set_error(struct address_space *mapping, int error)
return test_bit(AS_EXITING, &mapping->flags);
}
+static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
+{
+ set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
+}
+
+static inline int mapping_use_writeback_tags(struct address_space *mapping)
+{
+ return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
+}
+
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
static inline loff_t page_file_offset(struct page *page)
{
- return ((loff_t)page_file_index(page)) << PAGE_SHIFT;
+ return ((loff_t)page_index(page)) << PAGE_SHIFT;
}
extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
/*
- * Fault one or two userspace pages into pagetables.
- * Return -EINVAL if more than two pages would be needed.
- * Return non-zero on a fault.
+ * Fault everything in given userspace address range in.
*/
static inline int fault_in_pages_writeable(char __user *uaddr, int size)
- {
- int span, ret;
-
- if (unlikely(size == 0))
- return 0;
-
- span = offset_in_page(uaddr) + size;
- if (span > 2 * PAGE_SIZE)
- return -EINVAL;
- /*
- * Writing zeroes into userspace here is OK, because we know that if
- * the zero gets there, we'll be overwriting it.
- */
- ret = __put_user(0, uaddr);
- if (ret == 0 && span > PAGE_SIZE)
- ret = __put_user(0, uaddr + size - 1);
- return ret;
- }
-
- static inline int fault_in_pages_readable(const char __user *uaddr, int size)
- {
- volatile char c;
- int ret;
-
- if (unlikely(size == 0))
- return 0;
-
- ret = __get_user(c, uaddr);
- if (ret == 0) {
- const char __user *end = uaddr + size - 1;
-
- if (((unsigned long)uaddr & PAGE_MASK) !=
- ((unsigned long)end & PAGE_MASK)) {
- ret = __get_user(c, end);
- (void)c;
- }
- }
- return ret;
- }
-
- /*
- * Multipage variants of the above prefault helpers, useful if more than
- * PAGE_SIZE of data needs to be prefaulted. These are separate from the above
- * functions (which only handle up to PAGE_SIZE) to avoid clobbering the
- * filemap.c hotpaths.
- */
- static inline int fault_in_multipages_writeable(char __user *uaddr, int size)
{
char __user *end = uaddr + size - 1;
return 0;
}
- static inline int fault_in_multipages_readable(const char __user *uaddr,
- int size)
+ static inline int fault_in_pages_readable(const char __user *uaddr, int size)
{
volatile char c;
const char __user *end = uaddr + size - 1;
#include <uapi/linux/uio.h>
struct page;
+struct pipe_inode_info;
struct kvec {
void *iov_base; /* and that should *never* hold a userland pointer */
ITER_IOVEC = 0,
ITER_KVEC = 2,
ITER_BVEC = 4,
+ ITER_PIPE = 8,
};
struct iov_iter {
const struct iovec *iov;
const struct kvec *kvec;
const struct bio_vec *bvec;
+ struct pipe_inode_info *pipe;
+ };
+ union {
+ unsigned long nr_segs;
+ int idx;
};
- unsigned long nr_segs;
};
/*
}
#define iov_for_each(iov, iter, start) \
- if (!((start).type & ITER_BVEC)) \
+ if (!((start).type & (ITER_BVEC | ITER_PIPE))) \
for (iter = (start); \
(iter).count && \
((iov = iov_iter_iovec(&(iter))), 1); \
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
- #define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
unsigned long nr_segs, size_t count);
void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec,
unsigned long nr_segs, size_t count);
+void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe,
+ size_t count);
ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
size_t maxsize, unsigned maxpages, size_t *start);
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
static inline bool iter_is_iovec(struct iov_iter *i)
{
- return !(i->type & (ITER_BVEC | ITER_KVEC));
+ return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE));
}
/*
header-y += blkpg.h
header-y += blktrace_api.h
header-y += bpf_common.h
+header-y += bpf_perf_event.h
header-y += bpf.h
header-y += bpqether.h
header-y += bsg.h
header-y += pkt_sched.h
header-y += pmu.h
header-y += poll.h
+ header-y += posix_acl.h
+ header-y += posix_acl_xattr.h
header-y += posix_types.h
header-y += ppdev.h
header-y += ppp-comp.h
#include <linux/sched/sysctl.h>
#include <linux/kexec.h>
#include <linux/bpf.h>
+#include <linux/mount.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
extern int pid_max;
extern int pid_max_min, pid_max_max;
extern int percpu_pagelist_fraction;
- extern int compat_log;
extern int latencytop_enabled;
- extern int sysctl_nr_open_min, sysctl_nr_open_max;
+ extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max;
#ifndef CONFIG_MMU
extern int sysctl_nr_trim_pages;
#endif
.extra1 = &neg_one,
},
#endif
- #ifdef CONFIG_COMPAT
- {
- .procname = "compat-log",
- .data = &compat_log,
- .maxlen = sizeof (int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- #endif
#ifdef CONFIG_RT_MUTEXES
{
.procname = "max_lock_depth",
{
.procname = "nr_open",
.data = &sysctl_nr_open,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &sysctl_nr_open_min,
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
+ {
+ .procname = "mount-max",
+ .data = &sysctl_mount_max,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ },
{ }
};
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
+#include <linux/splice.h>
#include <net/checksum.h>
+#define PIPE_PARANOIA /* for now */
+
#define iterate_iovec(i, n, __v, __p, skip, STEP) { \
size_t left; \
size_t wanted = n; \
return wanted - bytes;
}
+#ifdef PIPE_PARANOIA
+static bool sanity(const struct iov_iter *i)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ int idx = i->idx;
+ int next = pipe->curbuf + pipe->nrbufs;
+ if (i->iov_offset) {
+ struct pipe_buffer *p;
+ if (unlikely(!pipe->nrbufs))
+ goto Bad; // pipe must be non-empty
+ if (unlikely(idx != ((next - 1) & (pipe->buffers - 1))))
+ goto Bad; // must be at the last buffer...
+
+ p = &pipe->bufs[idx];
+ if (unlikely(p->offset + p->len != i->iov_offset))
+ goto Bad; // ... at the end of segment
+ } else {
+ if (idx != (next & (pipe->buffers - 1)))
+ goto Bad; // must be right after the last buffer
+ }
+ return true;
+Bad:
+ printk(KERN_ERR "idx = %d, offset = %zd\n", i->idx, i->iov_offset);
+ printk(KERN_ERR "curbuf = %d, nrbufs = %d, buffers = %d\n",
+ pipe->curbuf, pipe->nrbufs, pipe->buffers);
+ for (idx = 0; idx < pipe->buffers; idx++)
+ printk(KERN_ERR "[%p %p %d %d]\n",
+ pipe->bufs[idx].ops,
+ pipe->bufs[idx].page,
+ pipe->bufs[idx].offset,
+ pipe->bufs[idx].len);
+ WARN_ON(1);
+ return false;
+}
+#else
+#define sanity(i) true
+#endif
+
+static inline int next_idx(int idx, struct pipe_inode_info *pipe)
+{
+ return (idx + 1) & (pipe->buffers - 1);
+}
+
+static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes,
+ struct iov_iter *i)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ struct pipe_buffer *buf;
+ size_t off;
+ int idx;
+
+ if (unlikely(bytes > i->count))
+ bytes = i->count;
+
+ if (unlikely(!bytes))
+ return 0;
+
+ if (!sanity(i))
+ return 0;
+
+ off = i->iov_offset;
+ idx = i->idx;
+ buf = &pipe->bufs[idx];
+ if (off) {
+ if (offset == off && buf->page == page) {
+ /* merge with the last one */
+ buf->len += bytes;
+ i->iov_offset += bytes;
+ goto out;
+ }
+ idx = next_idx(idx, pipe);
+ buf = &pipe->bufs[idx];
+ }
+ if (idx == pipe->curbuf && pipe->nrbufs)
+ return 0;
+ pipe->nrbufs++;
+ buf->ops = &page_cache_pipe_buf_ops;
+ get_page(buf->page = page);
+ buf->offset = offset;
+ buf->len = bytes;
+ i->iov_offset = offset + bytes;
+ i->idx = idx;
+out:
+ i->count -= bytes;
+ return bytes;
+}
+
/*
* Fault in one or more iovecs of the given iov_iter, to a maximum length of
* bytes. For each iovec, fault in each page that constitutes the iovec.
if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
iterate_iovec(i, bytes, v, iov, skip, ({
- err = fault_in_multipages_readable(v.iov_base,
- v.iov_len);
+ err = fault_in_pages_readable(v.iov_base, v.iov_len);
if (unlikely(err))
return err;
0;}))
kunmap_atomic(addr);
}
+static inline bool allocated(struct pipe_buffer *buf)
+{
+ return buf->ops == &default_pipe_buf_ops;
+}
+
+static inline void data_start(const struct iov_iter *i, int *idxp, size_t *offp)
+{
+ size_t off = i->iov_offset;
+ int idx = i->idx;
+ if (off && (!allocated(&i->pipe->bufs[idx]) || off == PAGE_SIZE)) {
+ idx = next_idx(idx, i->pipe);
+ off = 0;
+ }
+ *idxp = idx;
+ *offp = off;
+}
+
+static size_t push_pipe(struct iov_iter *i, size_t size,
+ int *idxp, size_t *offp)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ size_t off;
+ int idx;
+ ssize_t left;
+
+ if (unlikely(size > i->count))
+ size = i->count;
+ if (unlikely(!size))
+ return 0;
+
+ left = size;
+ data_start(i, &idx, &off);
+ *idxp = idx;
+ *offp = off;
+ if (off) {
+ left -= PAGE_SIZE - off;
+ if (left <= 0) {
+ pipe->bufs[idx].len += size;
+ return size;
+ }
+ pipe->bufs[idx].len = PAGE_SIZE;
+ idx = next_idx(idx, pipe);
+ }
+ while (idx != pipe->curbuf || !pipe->nrbufs) {
+ struct page *page = alloc_page(GFP_USER);
+ if (!page)
+ break;
+ pipe->nrbufs++;
+ pipe->bufs[idx].ops = &default_pipe_buf_ops;
+ pipe->bufs[idx].page = page;
+ pipe->bufs[idx].offset = 0;
+ if (left <= PAGE_SIZE) {
+ pipe->bufs[idx].len = left;
+ return size;
+ }
+ pipe->bufs[idx].len = PAGE_SIZE;
+ left -= PAGE_SIZE;
+ idx = next_idx(idx, pipe);
+ }
+ return size - left;
+}
+
+static size_t copy_pipe_to_iter(const void *addr, size_t bytes,
+ struct iov_iter *i)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ size_t n, off;
+ int idx;
+
+ if (!sanity(i))
+ return 0;
+
+ bytes = n = push_pipe(i, bytes, &idx, &off);
+ if (unlikely(!n))
+ return 0;
+ for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+ size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+ memcpy_to_page(pipe->bufs[idx].page, off, addr, chunk);
+ i->idx = idx;
+ i->iov_offset = off + chunk;
+ n -= chunk;
+ addr += chunk;
+ }
+ i->count -= bytes;
+ return bytes;
+}
+
size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
const char *from = addr;
+ if (unlikely(i->type & ITER_PIPE))
+ return copy_pipe_to_iter(addr, bytes, i);
iterate_and_advance(i, bytes, v,
__copy_to_user(v.iov_base, (from += v.iov_len) - v.iov_len,
v.iov_len),
size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return 0;
+ }
iterate_and_advance(i, bytes, v,
__copy_from_user((to += v.iov_len) - v.iov_len, v.iov_base,
v.iov_len),
size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
char *to = addr;
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return 0;
+ }
iterate_and_advance(i, bytes, v,
__copy_from_user_nocache((to += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len),
size_t wanted = copy_to_iter(kaddr + offset, bytes, i);
kunmap_atomic(kaddr);
return wanted;
- } else
+ } else if (likely(!(i->type & ITER_PIPE)))
return copy_page_to_iter_iovec(page, offset, bytes, i);
+ else
+ return copy_page_to_iter_pipe(page, offset, bytes, i);
}
EXPORT_SYMBOL(copy_page_to_iter);
size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i)
{
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return 0;
+ }
if (i->type & (ITER_BVEC|ITER_KVEC)) {
void *kaddr = kmap_atomic(page);
size_t wanted = copy_from_iter(kaddr + offset, bytes, i);
}
EXPORT_SYMBOL(copy_page_from_iter);
+static size_t pipe_zero(size_t bytes, struct iov_iter *i)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ size_t n, off;
+ int idx;
+
+ if (!sanity(i))
+ return 0;
+
+ bytes = n = push_pipe(i, bytes, &idx, &off);
+ if (unlikely(!n))
+ return 0;
+
+ for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+ size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+ memzero_page(pipe->bufs[idx].page, off, chunk);
+ i->idx = idx;
+ i->iov_offset = off + chunk;
+ n -= chunk;
+ }
+ i->count -= bytes;
+ return bytes;
+}
+
size_t iov_iter_zero(size_t bytes, struct iov_iter *i)
{
+ if (unlikely(i->type & ITER_PIPE))
+ return pipe_zero(bytes, i);
iterate_and_advance(i, bytes, v,
__clear_user(v.iov_base, v.iov_len),
memzero_page(v.bv_page, v.bv_offset, v.bv_len),
struct iov_iter *i, unsigned long offset, size_t bytes)
{
char *kaddr = kmap_atomic(page), *p = kaddr + offset;
+ if (unlikely(i->type & ITER_PIPE)) {
+ kunmap_atomic(kaddr);
+ WARN_ON(1);
+ return 0;
+ }
iterate_all_kinds(i, bytes, v,
__copy_from_user_inatomic((p += v.iov_len) - v.iov_len,
v.iov_base, v.iov_len),
}
EXPORT_SYMBOL(iov_iter_copy_from_user_atomic);
+static void pipe_advance(struct iov_iter *i, size_t size)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ struct pipe_buffer *buf;
+ int idx = i->idx;
+ size_t off = i->iov_offset;
+
+ if (unlikely(i->count < size))
+ size = i->count;
+
+ if (size) {
+ if (off) /* make it relative to the beginning of buffer */
+ size += off - pipe->bufs[idx].offset;
+ while (1) {
+ buf = &pipe->bufs[idx];
+ if (size <= buf->len)
+ break;
+ size -= buf->len;
+ idx = next_idx(idx, pipe);
+ }
+ buf->len = size;
+ i->idx = idx;
+ off = i->iov_offset = buf->offset + size;
+ }
+ if (off)
+ idx = next_idx(idx, pipe);
+ if (pipe->nrbufs) {
+ int unused = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
+ /* [curbuf,unused) is in use. Free [idx,unused) */
+ while (idx != unused) {
+ pipe_buf_release(pipe, &pipe->bufs[idx]);
+ idx = next_idx(idx, pipe);
+ pipe->nrbufs--;
+ }
+ }
+}
+
void iov_iter_advance(struct iov_iter *i, size_t size)
{
+ if (unlikely(i->type & ITER_PIPE)) {
+ pipe_advance(i, size);
+ return;
+ }
iterate_and_advance(i, size, v, 0, 0, 0)
}
EXPORT_SYMBOL(iov_iter_advance);
*/
size_t iov_iter_single_seg_count(const struct iov_iter *i)
{
+ if (unlikely(i->type & ITER_PIPE))
+ return i->count; // it is a silly place, anyway
if (i->nr_segs == 1)
return i->count;
else if (i->type & ITER_BVEC)
}
EXPORT_SYMBOL(iov_iter_bvec);
+void iov_iter_pipe(struct iov_iter *i, int direction,
+ struct pipe_inode_info *pipe,
+ size_t count)
+{
+ BUG_ON(direction != ITER_PIPE);
+ i->type = direction;
+ i->pipe = pipe;
+ i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1);
+ i->iov_offset = 0;
+ i->count = count;
+}
+EXPORT_SYMBOL(iov_iter_pipe);
+
unsigned long iov_iter_alignment(const struct iov_iter *i)
{
unsigned long res = 0;
if (!size)
return 0;
+ if (unlikely(i->type & ITER_PIPE)) {
+ if (i->iov_offset && allocated(&i->pipe->bufs[i->idx]))
+ return size | i->iov_offset;
+ return size;
+ }
iterate_all_kinds(i, size, v,
(res |= (unsigned long)v.iov_base | v.iov_len, 0),
res |= v.bv_offset | v.bv_len,
if (!size)
return 0;
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return ~0U;
+ }
+
iterate_all_kinds(i, size, v,
(res |= (!res ? 0 : (unsigned long)v.iov_base) |
(size != v.iov_len ? size : 0), 0),
}
EXPORT_SYMBOL(iov_iter_gap_alignment);
+static inline size_t __pipe_get_pages(struct iov_iter *i,
+ size_t maxsize,
+ struct page **pages,
+ int idx,
+ size_t *start)
+{
+ struct pipe_inode_info *pipe = i->pipe;
+ size_t n = push_pipe(i, maxsize, &idx, start);
+ if (!n)
+ return -EFAULT;
+
+ maxsize = n;
+ n += *start;
+ while (n >= PAGE_SIZE) {
+ get_page(*pages++ = pipe->bufs[idx].page);
+ idx = next_idx(idx, pipe);
+ n -= PAGE_SIZE;
+ }
+
+ return maxsize;
+}
+
+static ssize_t pipe_get_pages(struct iov_iter *i,
+ struct page **pages, size_t maxsize, unsigned maxpages,
+ size_t *start)
+{
+ unsigned npages;
+ size_t capacity;
+ int idx;
+
+ if (!sanity(i))
+ return -EFAULT;
+
+ data_start(i, &idx, start);
+ /* some of this one + all after this one */
+ npages = ((i->pipe->curbuf - idx - 1) & (i->pipe->buffers - 1)) + 1;
+ capacity = min(npages,maxpages) * PAGE_SIZE - *start;
+
+ return __pipe_get_pages(i, min(maxsize, capacity), pages, idx, start);
+}
+
ssize_t iov_iter_get_pages(struct iov_iter *i,
struct page **pages, size_t maxsize, unsigned maxpages,
size_t *start)
if (!maxsize)
return 0;
+ if (unlikely(i->type & ITER_PIPE))
+ return pipe_get_pages(i, pages, maxsize, maxpages, start);
iterate_all_kinds(i, maxsize, v, ({
unsigned long addr = (unsigned long)v.iov_base;
size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
return p;
}
+static ssize_t pipe_get_pages_alloc(struct iov_iter *i,
+ struct page ***pages, size_t maxsize,
+ size_t *start)
+{
+ struct page **p;
+ size_t n;
+ int idx;
+ int npages;
+
+ if (!sanity(i))
+ return -EFAULT;
+
+ data_start(i, &idx, start);
+ /* some of this one + all after this one */
+ npages = ((i->pipe->curbuf - idx - 1) & (i->pipe->buffers - 1)) + 1;
+ n = npages * PAGE_SIZE - *start;
+ if (maxsize > n)
+ maxsize = n;
+ else
+ npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE);
+ p = get_pages_array(npages);
+ if (!p)
+ return -ENOMEM;
+ n = __pipe_get_pages(i, maxsize, p, idx, start);
+ if (n > 0)
+ *pages = p;
+ else
+ kvfree(p);
+ return n;
+}
+
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
struct page ***pages, size_t maxsize,
size_t *start)
if (!maxsize)
return 0;
+ if (unlikely(i->type & ITER_PIPE))
+ return pipe_get_pages_alloc(i, pages, maxsize, start);
iterate_all_kinds(i, maxsize, v, ({
unsigned long addr = (unsigned long)v.iov_base;
size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1));
__wsum sum, next;
size_t off = 0;
sum = *csum;
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return 0;
+ }
iterate_and_advance(i, bytes, v, ({
int err = 0;
next = csum_and_copy_from_user(v.iov_base,
__wsum sum, next;
size_t off = 0;
sum = *csum;
+ if (unlikely(i->type & ITER_PIPE)) {
+ WARN_ON(1); /* for now */
+ return 0;
+ }
iterate_and_advance(i, bytes, v, ({
int err = 0;
next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len,
if (!size)
return 0;
- iterate_all_kinds(i, size, v, ({
+ if (unlikely(i->type & ITER_PIPE)) {
+ struct pipe_inode_info *pipe = i->pipe;
+ size_t off;
+ int idx;
+
+ if (!sanity(i))
+ return 0;
+
+ data_start(i, &idx, &off);
+ /* some of this one + all after this one */
+ npages = ((pipe->curbuf - idx - 1) & (pipe->buffers - 1)) + 1;
+ if (npages >= maxpages)
+ return maxpages;
+ } else iterate_all_kinds(i, size, v, ({
unsigned long p = (unsigned long)v.iov_base;
npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE)
- p / PAGE_SIZE;
const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags)
{
*new = *old;
+ if (unlikely(new->type & ITER_PIPE)) {
+ WARN_ON(1);
+ return NULL;
+ }
if (new->type & ITER_BVEC)
return new->bvec = kmemdup(new->bvec,
new->nr_segs * sizeof(struct bio_vec),
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
- error = inode_change_ok(inode, attr);
+ error = setattr_prepare(dentry, attr);
if (error)
return error;
return retval ? retval : error;
}
-static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe, size_t len,
- unsigned int flags)
-{
- struct address_space *mapping = in->f_mapping;
- struct inode *inode = mapping->host;
- unsigned int loff, nr_pages, req_pages;
- struct page *pages[PIPE_DEF_BUFFERS];
- struct partial_page partial[PIPE_DEF_BUFFERS];
- struct page *page;
- pgoff_t index, end_index;
- loff_t isize, left;
- int error, page_nr;
- struct splice_pipe_desc spd = {
- .pages = pages,
- .partial = partial,
- .nr_pages_max = PIPE_DEF_BUFFERS,
- .flags = flags,
- .ops = &page_cache_pipe_buf_ops,
- .spd_release = spd_release_page,
- };
-
- isize = i_size_read(inode);
- if (unlikely(*ppos >= isize))
- return 0;
-
- left = isize - *ppos;
- if (unlikely(left < len))
- len = left;
-
- if (splice_grow_spd(pipe, &spd))
- return -ENOMEM;
-
- index = *ppos >> PAGE_SHIFT;
- loff = *ppos & ~PAGE_MASK;
- req_pages = (len + loff + PAGE_SIZE - 1) >> PAGE_SHIFT;
- nr_pages = min(req_pages, spd.nr_pages_max);
-
- spd.nr_pages = find_get_pages_contig(mapping, index,
- nr_pages, spd.pages);
- index += spd.nr_pages;
- error = 0;
-
- while (spd.nr_pages < nr_pages) {
- error = shmem_getpage(inode, index, &page, SGP_CACHE);
- if (error)
- break;
- unlock_page(page);
- spd.pages[spd.nr_pages++] = page;
- index++;
- }
-
- index = *ppos >> PAGE_SHIFT;
- nr_pages = spd.nr_pages;
- spd.nr_pages = 0;
-
- for (page_nr = 0; page_nr < nr_pages; page_nr++) {
- unsigned int this_len;
-
- if (!len)
- break;
-
- this_len = min_t(unsigned long, len, PAGE_SIZE - loff);
- page = spd.pages[page_nr];
-
- if (!PageUptodate(page) || page->mapping != mapping) {
- error = shmem_getpage(inode, index, &page, SGP_CACHE);
- if (error)
- break;
- unlock_page(page);
- put_page(spd.pages[page_nr]);
- spd.pages[page_nr] = page;
- }
-
- isize = i_size_read(inode);
- end_index = (isize - 1) >> PAGE_SHIFT;
- if (unlikely(!isize || index > end_index))
- break;
-
- if (end_index == index) {
- unsigned int plen;
-
- plen = ((isize - 1) & ~PAGE_MASK) + 1;
- if (plen <= loff)
- break;
-
- this_len = min(this_len, plen - loff);
- len = this_len;
- }
-
- spd.partial[page_nr].offset = loff;
- spd.partial[page_nr].len = this_len;
- len -= this_len;
- loff = 0;
- spd.nr_pages++;
- index++;
- }
-
- while (page_nr < nr_pages)
- put_page(spd.pages[page_nr++]);
-
- if (spd.nr_pages)
- error = splice_to_pipe(pipe, &spd);
-
- splice_shrink_spd(&spd);
-
- if (error > 0) {
- *ppos += error;
- file_accessed(in);
- }
- return error;
-}
-
/*
* llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
*/
.read_iter = shmem_file_read_iter,
.write_iter = generic_file_write_iter,
.fsync = noop_fsync,
- .splice_read = shmem_file_splice_read,
+ .splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = shmem_fallocate,
#endif
/* common code */
-static struct dentry_operations anon_ops = {
+static const struct dentry_operations anon_ops = {
.d_dname = simple_dname
};