Home| summaryrefslogtreecommitdiff |
diff options
| author | Kernel Build Daemon <kbuild@suse.de> | 2019-03-22 07:11:04 +0100 |
|---|---|---|
| committer | Kernel Build Daemon <kbuild@suse.de> | 2019-03-22 07:11:04 +0100 |
| commit | 0360ddebe4715c0c18ddbdb75e1ca901981de6b5 (patch) | |
| tree | d7039bb6ecf6ce9b7474782a97689eb8ae32e94d | |
| parent | 994f0c0ebf61b690142f6718a01ec5adafc483f9 (diff) | |
| parent | 08b725bc137b8a136d3d1aff1c5c475bdbc4e131 (diff) | |
Merge branch 'SLE12-SP4' into SLE12-SP4-AZURErpm-4.12.14-6.9--sle12-sp4-updatesrpm-4.12.14-6.9
suse-commit: 59ee3a148edb097b48206180250d47417347e893
31 files changed, 793 insertions, 618 deletions
diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 24dce569a054..ac47b2315131 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -82,7 +82,6 @@ static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_index_mutex); -static DEFINE_MUTEX(loop_ctl_mutex); static int max_part; static int part_shift; @@ -1067,7 +1066,7 @@ static int loop_clr_fd(struct loop_device *lo) */ if (atomic_read(&lo->lo_refcnt) > 1) { lo->lo_flags |= LO_FLAGS_AUTOCLEAR; - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return 0; } @@ -1116,12 +1115,12 @@ static int loop_clr_fd(struct loop_device *lo) if (!part_shift) lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; loop_unprepare_queue(lo); - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); /* - * Need not hold loop_ctl_mutex to fput backing file. - * Calling fput holding loop_ctl_mutex triggers a circular + * Need not hold lo_ctl_mutex to fput backing file. + * Calling fput holding lo_ctl_mutex triggers a circular * lock dependency possibility warning as fput can take - * bd_mutex which is usually taken before loop_ctl_mutex. + * bd_mutex which is usually taken before lo_ctl_mutex. */ fput(filp); return 0; @@ -1273,7 +1272,7 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) int ret; if (lo->lo_state != Lo_bound) { - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return -ENXIO; } @@ -1292,9 +1291,9 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) lo->lo_encrypt_key_size); } - /* Drop loop_ctl_mutex while we call into the filesystem. */ + /* Drop lo_ctl_mutex while we call into the filesystem. */ file = get_file(lo->lo_backing_file); - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); ret = vfs_getattr(&file->f_path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { @@ -1387,7 +1386,7 @@ loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { int err; if (!arg) { - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return -EINVAL; } err = loop_get_status(lo, &info64); @@ -1405,7 +1404,7 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { int err; if (!arg) { - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return -EINVAL; } err = loop_get_status(lo, &info64); @@ -1444,7 +1443,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, struct loop_device *lo = bdev->bd_disk->private_data; int err; - mutex_lock_nested(&loop_ctl_mutex, 1); + mutex_lock_nested(&lo->lo_ctl_mutex, 1); switch (cmd) { case LOOP_SET_FD: err = loop_set_fd(lo, mode, bdev, arg); @@ -1453,7 +1452,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, err = loop_change_fd(lo, bdev, arg); break; case LOOP_CLR_FD: - /* loop_clr_fd would have unlocked loop_ctl_mutex on success */ + /* loop_clr_fd would have unlocked lo_ctl_mutex on success */ err = loop_clr_fd(lo); if (!err) goto out_unlocked; @@ -1466,7 +1465,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, break; case LOOP_GET_STATUS: err = loop_get_status_old(lo, (struct loop_info __user *) arg); - /* loop_get_status() unlocks loop_ctl_mutex */ + /* loop_get_status() unlocks lo_ctl_mutex */ goto out_unlocked; case LOOP_SET_STATUS64: err = -EPERM; @@ -1476,7 +1475,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, break; case LOOP_GET_STATUS64: err = loop_get_status64(lo, (struct loop_info64 __user *) arg); - /* loop_get_status() unlocks loop_ctl_mutex */ + /* loop_get_status() unlocks lo_ctl_mutex */ goto out_unlocked; case LOOP_SET_CAPACITY: err = -EPERM; @@ -1491,7 +1490,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); out_unlocked: return err; @@ -1608,7 +1607,7 @@ loop_get_status_compat(struct loop_device *lo, int err; if (!arg) { - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return -EINVAL; } err = loop_get_status(lo, &info64); @@ -1625,16 +1624,16 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, switch(cmd) { case LOOP_SET_STATUS: - mutex_lock(&loop_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); err = loop_set_status_compat( lo, (const struct compat_loop_info __user *) arg); - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); break; case LOOP_GET_STATUS: - mutex_lock(&loop_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); err = loop_get_status_compat( lo, (struct compat_loop_info __user *) arg); - /* loop_get_status() unlocks loop_ctl_mutex */ + /* loop_get_status() unlocks lo_ctl_mutex */ break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: @@ -1678,7 +1677,7 @@ static void __lo_release(struct loop_device *lo) if (atomic_dec_return(&lo->lo_refcnt)) return; - mutex_lock(&loop_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) { /* * In autoclear mode, stop the loop thread @@ -1695,7 +1694,7 @@ static void __lo_release(struct loop_device *lo) loop_flush(lo); } - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); } static void lo_release(struct gendisk *disk, fmode_t mode) @@ -1741,10 +1740,10 @@ static int unregister_transfer_cb(int id, void *ptr, void *data) struct loop_device *lo = ptr; struct loop_func_table *xfer = data; - mutex_lock(&loop_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_encryption == xfer) loop_release_xfer(lo); - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); return 0; } @@ -1913,6 +1912,7 @@ static int loop_add(struct loop_device **l, int i) if (!part_shift) disk->flags |= GENHD_FL_NO_PART_SCAN; disk->flags |= GENHD_FL_EXT_DEVT; + mutex_init(&lo->lo_ctl_mutex); atomic_set(&lo->lo_refcnt, 0); lo->lo_number = i; spin_lock_init(&lo->lo_lock); @@ -2025,19 +2025,19 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd, ret = loop_lookup(&lo, parm); if (ret < 0) break; - mutex_lock(&loop_ctl_mutex); + mutex_lock(&lo->lo_ctl_mutex); if (lo->lo_state != Lo_unbound) { ret = -EBUSY; - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); break; } if (atomic_read(&lo->lo_refcnt) > 0) { ret = -EBUSY; - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); break; } lo->lo_disk->private_data = NULL; - mutex_unlock(&loop_ctl_mutex); + mutex_unlock(&lo->lo_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); loop_remove(lo); break; diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c index f6308ad35b19..42ee70c23d9f 100644 --- a/drivers/message/fusion/mptsas.c +++ b/drivers/message/fusion/mptsas.c @@ -4352,11 +4352,10 @@ mptsas_hotplug_work(MPT_ADAPTER *ioc, struct fw_event_work *fw_event, return; phy_info = mptsas_refreshing_device_handles(ioc, &sas_device); - /* Only For SATA Device ADD */ - if (!phy_info && (sas_device.device_info & - MPI_SAS_DEVICE_INFO_SATA_DEVICE)) { + /* Device hot plug */ + if (!phy_info) { devtprintk(ioc, printk(MYIOC_s_DEBUG_FMT - "%s %d SATA HOT PLUG: " + "%s %d HOT PLUG: " "parent handle of device %x\n", ioc->name, __func__, __LINE__, sas_device.handle_parent)); port_info = mptsas_find_portinfo_by_handle(ioc, diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 55af04fa03a7..6c8dcb65ff03 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -1441,6 +1441,9 @@ static void nic_remove(struct pci_dev *pdev) { struct nicpf *nic = pci_get_drvdata(pdev); + if (!nic) + return; + if (nic->flags & NIC_SRIOV_ENABLED) pci_disable_sriov(pdev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 979a8fa430a4..70d046718212 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -120,6 +120,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *); static void release_crq_queue(struct ibmvnic_adapter *); static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p); static int init_crq_queue(struct ibmvnic_adapter *adapter); +static int send_query_phys_parms(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -2281,23 +2282,20 @@ static const struct net_device_ops ibmvnic_netdev_ops = { static int ibmvnic_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { - u32 supported, advertising; + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int rc; - supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | - SUPPORTED_FIBRE); - advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | - ADVERTISED_FIBRE); - cmd->base.speed = SPEED_1000; - cmd->base.duplex = DUPLEX_FULL; + rc = send_query_phys_parms(adapter); + if (rc) { + adapter->speed = SPEED_UNKNOWN; + adapter->duplex = DUPLEX_UNKNOWN; + } + cmd->base.speed = adapter->speed; + cmd->base.duplex = adapter->duplex; cmd->base.port = PORT_FIBRE; cmd->base.phy_address = 0; cmd->base.autoneg = AUTONEG_ENABLE; - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); - return 0; } @@ -4281,6 +4279,73 @@ out: } } +static int send_query_phys_parms(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + int rc; + + memset(&crq, 0, sizeof(crq)); + crq.query_phys_parms.first = IBMVNIC_CRQ_CMD; + crq.query_phys_parms.cmd = QUERY_PHYS_PARMS; + init_completion(&adapter->fw_done); + rc = ibmvnic_send_crq(adapter, &crq); + if (rc) + return rc; + wait_for_completion(&adapter->fw_done); + return adapter->fw_done_rc ? -EIO : 0; +} + +static int handle_query_phys_parms_rsp(union ibmvnic_crq *crq, + struct ibmvnic_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int rc; + + rc = crq->query_phys_parms_rsp.rc.code; + if (rc) { + netdev_err(netdev, "Error %d in QUERY_PHYS_PARMS\n", rc); + return rc; + } + switch (cpu_to_be32(crq->query_phys_parms_rsp.speed)) { + case IBMVNIC_10MBPS: + adapter->speed = SPEED_10; + break; + case IBMVNIC_100MBPS: + adapter->speed = SPEED_100; + break; + case IBMVNIC_1GBPS: + adapter->speed = SPEED_1000; + break; + case IBMVNIC_10GBP: + adapter->speed = SPEED_10000; + break; + case IBMVNIC_25GBPS: + adapter->speed = SPEED_25000; + break; + case IBMVNIC_40GBPS: + adapter->speed = SPEED_40000; + break; + case IBMVNIC_50GBPS: + adapter->speed = SPEED_50000; + break; + case IBMVNIC_100GBPS: + adapter->speed = SPEED_100000; + break; + default: + netdev_warn(netdev, "Unknown speed 0x%08x\n", + cpu_to_be32(crq->query_phys_parms_rsp.speed)); + adapter->speed = SPEED_UNKNOWN; + } + if (crq->query_phys_parms_rsp.flags1 & IBMVNIC_FULL_DUPLEX) + adapter->duplex = DUPLEX_FULL; + else if (crq->query_phys_parms_rsp.flags1 & IBMVNIC_HALF_DUPLEX) + adapter->duplex = DUPLEX_HALF; + else + adapter->duplex = DUPLEX_UNKNOWN; + + return rc; +} + static void ibmvnic_handle_crq(union ibmvnic_crq *crq, struct ibmvnic_adapter *adapter) { @@ -4429,6 +4494,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, case GET_VPD_RSP: handle_vpd_rsp(crq, adapter); break; + case QUERY_PHYS_PARMS_RSP: + adapter->fw_done_rc = handle_query_phys_parms_rsp(crq, adapter); + complete(&adapter->fw_done); + break; default: netdev_err(netdev, "Got an invalid cmd type 0x%02x\n", gen_crq->cmd); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index f2018dbebfa5..d5260a206708 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -377,11 +377,16 @@ struct ibmvnic_phys_parms { u8 flags2; #define IBMVNIC_LOGICAL_LNK_ACTIVE 0x80 __be32 speed; -#define IBMVNIC_AUTONEG 0x80 -#define IBMVNIC_10MBPS 0x40 -#define IBMVNIC_100MBPS 0x20 -#define IBMVNIC_1GBPS 0x10 -#define IBMVNIC_10GBPS 0x08 +#define IBMVNIC_AUTONEG 0x80000000 +#define IBMVNIC_10MBPS 0x40000000 +#define IBMVNIC_100MBPS 0x20000000 +#define IBMVNIC_1GBPS 0x10000000 +#define IBMVNIC_10GBP 0x08000000 +#define IBMVNIC_40GBPS 0x04000000 +#define IBMVNIC_100GBPS 0x02000000 +#define IBMVNIC_25GBPS 0x01000000 +#define IBMVNIC_50GBPS 0x00800000 +#define IBMVNIC_200GBPS 0x00400000 __be32 mtu; struct ibmvnic_rc rc; } __packed __aligned(8); @@ -999,6 +1004,9 @@ struct ibmvnic_adapter { int phys_link_state; int logical_link_state; + u32 speed; + u8 duplex; + /* login data */ struct ibmvnic_login_buffer *login_buf; dma_addr_t login_buf_token; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 5cf8a8f87a8c..f5e4fde595c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1020,7 +1020,10 @@ static ssize_t dbg_write(struct file *filp, const char __user *buf, if (!dbg->in_msg || !dbg->out_msg) return -ENOMEM; - if (copy_from_user(lbuf, buf, sizeof(lbuf))) + if (count < sizeof(lbuf) - 1) + return -EINVAL; + + if (copy_from_user(lbuf, buf, sizeof(lbuf) - 1)) return -EFAULT; lbuf[sizeof(lbuf) - 1] = 0; @@ -1224,21 +1227,12 @@ static ssize_t data_read(struct file *filp, char __user *buf, size_t count, { struct mlx5_core_dev *dev = filp->private_data; struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - int copy; - - if (*pos) - return 0; if (!dbg->out_msg) return -ENOMEM; - copy = min_t(int, count, dbg->outlen); - if (copy_to_user(buf, dbg->out_msg, copy)) - return -EFAULT; - - *pos += copy; - - return copy; + return simple_read_from_buffer(buf, count, pos, dbg->out_msg, + dbg->outlen); } static const struct file_operations dfops = { @@ -1256,19 +1250,11 @@ static ssize_t outlen_read(struct file *filp, char __user *buf, size_t count, char outlen[8]; int err; - if (*pos) - return 0; - err = snprintf(outlen, sizeof(outlen), "%d", dbg->outlen); if (err < 0) return err; - if (copy_to_user(buf, &outlen, err)) - return -EFAULT; - - *pos += err; - - return err; + return simple_read_from_buffer(buf, count, pos, outlen, err); } static ssize_t outlen_write(struct file *filp, const char __user *buf, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 7ecadb501743..8dd96fbe0d22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -150,22 +150,14 @@ static ssize_t average_read(struct file *filp, char __user *buf, size_t count, int ret; char tbuf[22]; - if (*pos) - return 0; - stats = filp->private_data; spin_lock_irq(&stats->lock); if (stats->n) field = div64_u64(stats->sum, stats->n); spin_unlock_irq(&stats->lock); ret = snprintf(tbuf, sizeof(tbuf), "%llu\n", field); - if (ret > 0) { - if (copy_to_user(buf, tbuf, ret)) - return -EFAULT; - } - *pos += ret; - return ret; + return simple_read_from_buffer(buf, count, pos, tbuf, ret); } static ssize_t average_write(struct file *filp, const char __user *buf, @@ -442,9 +434,6 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count, u64 field; int ret; - if (*pos) - return 0; - desc = filp->private_data; d = (void *)(desc - desc->i) - sizeof(*d); switch (d->type) { @@ -470,13 +459,7 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count, else ret = snprintf(tbuf, sizeof(tbuf), "0x%llx\n", field); - if (ret > 0) { - if (copy_to_user(buf, tbuf, ret)) - return -EFAULT; - } - - *pos += ret; - return ret; + return simple_read_from_buffer(buf, count, pos, tbuf, ret); } static const struct file_operations fops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index f1f16cd992d9..295bf3ffa43e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -867,8 +867,9 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { bool configure = false; bool pfc = false; + u16 thres_cells; + u16 delay_cells; bool lossy; - u16 thres; for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) { if (prio_tc[j] == i) { @@ -882,10 +883,11 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, continue; lossy = !(pfc || pause_en); - thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); - delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, - pause_en); - mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy); + thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); + delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, + pfc, pause_en); + mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres_cells + delay_cells, + thres_cells, lossy); } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index e0ef02f9503b..08458d7826be 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -238,15 +238,18 @@ static inline u64 dwmac4_get_timestamp(void *desc, u32 ats) static int dwmac4_rx_check_timestamp(void *desc) { struct dma_desc *p = (struct dma_desc *)desc; + unsigned int rdes0 = le32_to_cpu(p->des0); + unsigned int rdes1 = le32_to_cpu(p->des1); + unsigned int rdes3 = le32_to_cpu(p->des3); u32 own, ctxt; int ret = 1; - own = p->des3 & RDES3_OWN; - ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + own = rdes3 & RDES3_OWN; + ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR) >> RDES3_CONTEXT_DESCRIPTOR_SHIFT); if (likely(!own && ctxt)) { - if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff)) /* Corrupted value */ ret = -EINVAL; else diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 33efe7038cab..3bb61460b67e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -96,7 +96,7 @@ struct stmmac_priv { struct net_device *dev; struct device *device; struct mac_device_info *hw; - spinlock_t lock; + struct mutex lock; /* RX Queue */ struct stmmac_rx_queue rx_queue[MTL_MAX_RX_QUEUES]; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 743170d57f62..a2e84358a59f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -390,13 +390,13 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev, ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full); - spin_lock(&priv->lock); + mutex_lock(&priv->lock); if (priv->hw->mac->pcs_ctrl_ane) priv->hw->mac->pcs_ctrl_ane(priv->ioaddr, 1, priv->hw->ps, 0); - spin_unlock(&priv->lock); + mutex_unlock(&priv->lock); return 0; } @@ -610,12 +610,12 @@ static void stmmac_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct stmmac_priv *priv = netdev_priv(dev); - spin_lock_irq(&priv->lock); + mutex_lock(&priv->lock); if (device_can_wakeup(priv->device)) { wol->supported = WAKE_MAGIC | WAKE_UCAST; wol->wolopts = priv->wolopts; } - spin_unlock_irq(&priv->lock); + mutex_unlock(&priv->lock); } static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) @@ -644,9 +644,9 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) disable_irq_wake(priv->wol_irq); } - spin_lock_irq(&priv->lock); + mutex_lock(&priv->lock); priv->wolopts = wol->wolopts; - spin_unlock_irq(&priv->lock); + mutex_unlock(&priv->lock); return 0; } @@ -670,25 +670,27 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_eee *edata) { struct stmmac_priv *priv = netdev_priv(dev); + int ret; - priv->eee_enabled = edata->eee_enabled; - - if (!priv->eee_enabled) + if (!edata->eee_enabled) { stmmac_disable_eee_mode(priv); - else { + } else { /* We are asking for enabling the EEE but it is safe * to verify all by invoking the eee_init function. * In case of failure it will return an error. */ - priv->eee_enabled = stmmac_eee_init(priv); - if (!priv->eee_enabled) + edata->eee_enabled = stmmac_eee_init(priv); + if (!edata->eee_enabled) return -EOPNOTSUPP; - - /* Do not change tx_lpi_timer in case of failure */ - priv->tx_lpi_timer = edata->tx_lpi_timer; } - return phy_ethtool_set_eee(dev->phydev, edata); + ret = phy_ethtool_set_eee(dev->phydev, edata); + if (ret) + return ret; + + priv->eee_enabled = edata->eee_enabled; + priv->tx_lpi_timer = edata->tx_lpi_timer; + return 0; } static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1d70508db5b8..872d56167000 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -354,7 +354,6 @@ bool stmmac_eee_init(struct stmmac_priv *priv) { struct net_device *ndev = priv->dev; int interface = priv->plat->interface; - unsigned long flags; bool ret = false; if ((interface != PHY_INTERFACE_MODE_MII) && @@ -381,7 +380,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv) * changed). * In that case the driver disable own timers. */ - spin_lock_irqsave(&priv->lock, flags); + mutex_lock(&priv->lock); if (priv->eee_active) { netdev_dbg(priv->dev, "disable EEE\n"); del_timer_sync(&priv->eee_ctrl_timer); @@ -389,11 +388,11 @@ bool stmmac_eee_init(struct stmmac_priv *priv) tx_lpi_timer); } priv->eee_active = 0; - spin_unlock_irqrestore(&priv->lock, flags); + mutex_unlock(&priv->lock); goto out; } /* Activate the EEE and start timers */ - spin_lock_irqsave(&priv->lock, flags); + mutex_lock(&priv->lock); if (!priv->eee_active) { priv->eee_active = 1; setup_timer(&priv->eee_ctrl_timer, @@ -410,7 +409,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv) priv->hw->mac->set_eee_pls(priv->hw, ndev->phydev->link); ret = true; - spin_unlock_irqrestore(&priv->lock, flags); + mutex_unlock(&priv->lock); netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n"); } @@ -789,13 +788,12 @@ static void stmmac_adjust_link(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; - unsigned long flags; int new_state = 0; if (!phydev) return; - spin_lock_irqsave(&priv->lock, flags); + mutex_lock(&priv->lock); if (phydev->link) { u32 ctrl = readl(priv->ioaddr + MAC_CTRL_REG); @@ -867,7 +865,7 @@ static void stmmac_adjust_link(struct net_device *dev) if (new_state && netif_msg_link(priv)) phy_print_status(phydev); - spin_unlock_irqrestore(&priv->lock, flags); + mutex_unlock(&priv->lock); if (phydev->is_pseudo_fixed_link) /* Stop PHY layer to call the hook to adjust the link in case @@ -1989,22 +1987,60 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, static void stmmac_dma_interrupt(struct stmmac_priv *priv) { u32 tx_channel_count = priv->plat->tx_queues_to_use; - int status; + u32 rx_channel_count = priv->plat->rx_queues_to_use; + u32 channels_to_check = tx_channel_count > rx_channel_count ? + tx_channel_count : rx_channel_count; u32 chan; + bool poll_scheduled = false; + int status[channels_to_check]; + + /* Each DMA channel can be used for rx and tx simultaneously, yet + * napi_struct is embedded in struct stmmac_rx_queue rather than in a + * stmmac_channel struct. + * Because of this, stmmac_poll currently checks (and possibly wakes) + * all tx queues rather than just a single tx queue. + */ + for (chan = 0; chan < channels_to_check; chan++) + status[chan] = priv->hw->dma->dma_interrupt(priv->ioaddr, + &priv->xstats, + chan); - for (chan = 0; chan < tx_channel_count; chan++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; + for (chan = 0; chan < rx_channel_count; chan++) { + if (likely(status[chan] & handle_rx)) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; - status = priv->hw->dma->dma_interrupt(priv->ioaddr, - &priv->xstats, chan); - if (likely((status & handle_rx)) || (status & handle_tx)) { if (likely(napi_schedule_prep(&rx_q->napi))) { stmmac_disable_dma_irq(priv, chan); __napi_schedule(&rx_q->napi); + poll_scheduled = true; + } + } + } + + /* If we scheduled poll, we already know that tx queues will be checked. + * If we didn't schedule poll, see if any DMA channel (used by tx) has a + * completed transmission, if so, call stmmac_poll (once). + */ + if (!poll_scheduled) { + for (chan = 0; chan < tx_channel_count; chan++) { + if (status[chan] & handle_tx) { + /* It doesn't matter what rx queue we choose + * here. We use 0 since it always exists. + */ + struct stmmac_rx_queue *rx_q = + &priv->rx_queue[0]; + + if (likely(napi_schedule_prep(&rx_q->napi))) { + stmmac_disable_dma_irq(priv, chan); + __napi_schedule(&rx_q->napi); + } + break; } } + } - if (unlikely(status & tx_hard_error_bump_tc)) { + for (chan = 0; chan < tx_channel_count; chan++) { + if (unlikely(status[chan] & tx_hard_error_bump_tc)) { /* Try to bump up the dma threshold on this failure */ if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && (tc <= 256)) { @@ -2021,7 +2057,7 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) chan); priv->xstats.threshold = tc; } - } else if (unlikely(status == tx_hard_error)) { + } else if (unlikely(status[chan] == tx_hard_error)) { stmmac_tx_err(priv, chan); } } @@ -4202,7 +4238,7 @@ int stmmac_dvr_probe(struct device *device, (8 * priv->plat->rx_queues_to_use)); } - spin_lock_init(&priv->lock); + mutex_init(&priv->lock); /* If a specific clk_csr value is passed from the platform * this means that the CSR Clock Range selection cannot be @@ -4283,6 +4319,7 @@ int stmmac_dvr_remove(struct device *dev) priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); + mutex_destroy(&priv->lock); free_netdev(ndev); return 0; @@ -4300,7 +4337,6 @@ int stmmac_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); - unsigned long flags; if (!ndev || !netif_running(ndev)) return 0; @@ -4308,7 +4344,7 @@ int stmmac_suspend(struct device *dev) if (ndev->phydev) phy_stop(ndev->phydev); - spin_lock_irqsave(&priv->lock, flags); + mutex_lock(&priv->lock); netif_device_detach(ndev); stmmac_stop_all_queues(priv); @@ -4329,7 +4365,7 @@ int stmmac_suspend(struct device *dev) clk_disable(priv->plat->pclk); clk_disable(priv->plat->stmmac_clk); } - spin_unlock_irqrestore(&priv->lock, flags); + mutex_unlock(&priv->lock); priv->oldlink = 0; priv->speed = SPEED_UNKNOWN; @@ -4373,7 +4409,6 @@ int stmmac_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); - unsigned long flags; if (!netif_running(ndev)) return 0; @@ -4385,9 +4420,9 @@ int stmmac_resume(struct device *dev) * from another devices (e.g. serial console). */ if (device_may_wakeup(priv->device)) { - spin_lock_irqsave(&priv->lock, flags); + mutex_lock(&priv->lock); priv->hw->mac->pmt(priv->hw, 0); - spin_unlock_irqrestore(&priv->lock, flags); + mutex_unlock(&priv->lock); priv->irq_wake = 0; } else { pinctrl_pm_select_default_state(priv->device); @@ -4401,7 +4436,7 @@ int stmmac_resume(struct device *dev) netif_device_attach(ndev); - spin_lock_irqsave(&priv->lock, flags); + mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); @@ -4420,7 +4455,7 @@ int stmmac_resume(struct device *dev) stmmac_start_all_queues(priv); - spin_unlock_irqrestore(&priv->lock, flags); + mutex_unlock(&priv->lock); if (ndev->phydev) phy_start(ndev->phydev); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d9fb622512c8..222c78ec7e27 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -973,9 +973,11 @@ static inline bool nvme_read_cqe(struct nvme_queue *nvmeq, if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) { *cqe = nvmeq->cqes[nvmeq->cq_head]; - if (++nvmeq->cq_head == nvmeq->q_depth) { + if (nvmeq->cq_head == nvmeq->q_depth - 1) { nvmeq->cq_head = 0; nvmeq->cq_phase = !nvmeq->cq_phase; + } else { + nvmeq->cq_head++; } return true; } diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c index c535c52e72e5..92a4afa8272d 100644 --- a/drivers/scsi/ch.c +++ b/drivers/scsi/ch.c @@ -568,6 +568,7 @@ static void ch_destroy(struct kref *ref) { scsi_changer *ch = container_of(ref, scsi_changer, ref); + ch->device = NULL; kfree(ch->dt); kfree(ch); } @@ -577,9 +578,10 @@ ch_release(struct inode *inode, struct file *file) { scsi_changer *ch = file->private_data; + mutex_lock(&ch_mutex); scsi_device_put(ch->device); - ch->device = NULL; file->private_data = NULL; + mutex_unlock(&ch_mutex); kref_put(&ch->ref, ch_destroy); return 0; } @@ -594,14 +596,17 @@ ch_open(struct inode *inode, struct file *file) spin_lock(&ch_index_lock); ch = idr_find(&ch_index_idr, minor); - if (NULL == ch || scsi_device_get(ch->device)) { + if (NULL == ch || kref_get_unless_zero(&ch->ref)) { spin_unlock(&ch_index_lock); mutex_unlock(&ch_mutex); return -ENXIO; } - kref_get(&ch->ref); spin_unlock(&ch_index_lock); + if (!ch->device || scsi_device_get(ch->device)) { + kref_put(&ch->ref, ch_destroy); + return -ENXIO; + } file->private_data = ch; mutex_unlock(&ch_mutex); return 0; @@ -974,6 +979,7 @@ static int ch_remove(struct device *dev) spin_lock(&ch_index_lock); idr_remove(&ch_index_idr, ch->minor); + dev_set_drvdata(dev, NULL); spin_unlock(&ch_index_lock); device_destroy(ch_sysfs_class, MKDEV(SCSI_CHANGER_MAJOR,ch->minor)); diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 1deb0a9f14a6..6d2212291cf9 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -96,6 +96,7 @@ static int client_reserve = 1; static char partition_name[97] = "UNKNOWN"; static unsigned int partition_number = -1; static LIST_HEAD(ibmvscsi_head); +static DEFINE_SPINLOCK(ibmvscsi_driver_lock); static struct scsi_transport_template *ibmvscsi_transport_template; @@ -2274,7 +2275,9 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) } dev_set_drvdata(&vdev->dev, hostdata); + spin_lock(&ibmvscsi_driver_lock); list_add_tail(&hostdata->host_list, &ibmvscsi_head); + spin_unlock(&ibmvscsi_driver_lock); return 0; add_srp_port_failed: @@ -2296,15 +2299,27 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); - list_del(&hostdata->host_list); - unmap_persist_bufs(hostdata); + unsigned long flags; + + srp_remove_host(hostdata->host); + scsi_remove_host(hostdata->host); + + purge_requests(hostdata, DID_ERROR); + + spin_lock_irqsave(hostdata->host->host_lock, flags); release_event_pool(&hostdata->pool, hostdata); + spin_unlock_irqrestore(hostdata->host->host_lock, flags); + ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, max_events); kthread_stop(hostdata->work_thread); - srp_remove_host(hostdata->host); - scsi_remove_host(hostdata->host); + unmap_persist_bufs(hostdata); + + spin_lock(&ibmvscsi_driver_lock); + list_del(&hostdata->host_list); + spin_unlock(&ibmvscsi_driver_lock); + scsi_host_put(hostdata->host); return 0; diff --git a/fs/block_dev.c b/fs/block_dev.c index 7a9a14df1d82..4acd35663ae7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -256,6 +256,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, task_io_account_write(ret); } + bio_get(&bio); qc = submit_bio(&bio); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); @@ -275,7 +276,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); - + bio_put(&bio); out: if (vecs != inline_vecs) kfree(vecs); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 276249df791c..50e19d33e73e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -718,7 +718,7 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) trans = start_transaction(root, 0, TRANS_ATTACH, BTRFS_RESERVE_NO_FLUSH, true); - if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT) + if (trans == ERR_PTR(-ENOENT)) btrfs_wait_for_commit(root->fs_info, 0); return trans; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8cd571f6747b..9ba022189666 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -40,6 +40,7 @@ #define LOG_INODE_ALL 0 #define LOG_INODE_EXISTS 1 #define LOG_OTHER_INODE 2 +#define LOG_OTHER_INODE_ALL 3 /* * directory trouble cases @@ -1359,6 +1360,67 @@ out: return ret; } +static int add_link(struct btrfs_trans_handle *trans, struct btrfs_root *root, + struct inode *dir, struct inode *inode, const char *name, + int namelen, u64 ref_index) +{ + struct btrfs_dir_item *dir_item; + struct btrfs_key key; + struct btrfs_path *path; + struct inode *other_inode = NULL; + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + dir_item = btrfs_lookup_dir_item(NULL, root, path, + btrfs_ino(BTRFS_I(dir)), + name, namelen, 0); + if (!dir_item) { + btrfs_release_path(path); + goto add_link; + } else if (IS_ERR(dir_item)) { + ret = PTR_ERR(dir_item); + goto out; + } + + /* + * Our inode's dentry collides with the dentry of another inode which is + * in the log but not yet processed since it has a higher inode number. + * So delete that other dentry. + */ + btrfs_dir_item_key_to_cpu(path->nodes[0], dir_item, &key); + btrfs_release_path(path); + other_inode = read_one_inode(root, key.objectid); + if (!other_inode) { + ret = -ENOENT; + goto out; + } + ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir), BTRFS_I(other_inode), + name, namelen); + if (ret) + goto out; + /* + * If we dropped the link count to 0, bump it so that later the iput() + * on the inode will not free it. We will fixup the link count later. + */ + if (other_inode->i_nlink == 0) + inc_nlink(other_inode); + + ret = btrfs_run_delayed_items(trans, trans->fs_info); + if (ret) + goto out; +add_link: + ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), + name, namelen, 0, ref_index); +out: + iput(other_inode); + btrfs_free_path(path); + + return ret; +} + /* * replay one inode back reference item found in the log tree. * eb, slot and key refer to the buffer and key found in the log tree. @@ -1495,9 +1557,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, goto out; /* insert our name */ - ret = btrfs_add_link(trans, BTRFS_I(dir), - BTRFS_I(inode), - name, namelen, 0, ref_index); + ret = add_link(trans, root, dir, inode, name, namelen, + ref_index); if (ret) goto out; @@ -2223,7 +2284,7 @@ again: dir_key->offset, name, name_len, 0); } - if (!log_di || (IS_ERR(log_di) && PTR_ERR(log_di) == -ENOENT)) { + if (!log_di || log_di == ERR_PTR(-ENOENT)) { btrfs_dir_item_key_to_cpu(eb, di, &location); btrfs_release_path(path); btrfs_release_path(log_path); @@ -4897,7 +4958,7 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, struct btrfs_inode *inode, - u64 *other_ino) + u64 *other_ino, u64 *other_parent) { int ret; struct btrfs_path *search_path; @@ -4960,8 +5021,13 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, btrfs_dir_item_key_to_cpu(search_path->nodes[0], di, &di_key); if (di_key.type == BTRFS_INODE_ITEM_KEY) { - ret = 1; - *other_ino = di_key.objectid; + if (di_key.objectid != key->objectid) { + ret = 1; + *other_ino = di_key.objectid; + *other_parent = parent; + } else { + ret = 0; + } } else { ret = -EAGAIN; } @@ -4981,6 +5047,144 @@ out: return ret; } +struct btrfs_ino_list { + u64 ino; + u64 parent; + struct list_head list; +}; + +static int log_conflicting_inodes(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct btrfs_path *path, + struct btrfs_log_ctx *ctx, + u64 ino, u64 parent) +{ + struct btrfs_ino_list *ino_elem; + LIST_HEAD(inode_list); + int ret = 0; + + ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); + if (!ino_elem) + return -ENOMEM; + ino_elem->ino = ino; + ino_elem->parent = parent; + list_add_tail(&ino_elem->list, &inode_list); + + while (!list_empty(&inode_list)) { + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_key key; + struct inode *inode; + + ino_elem = list_first_entry(&inode_list, struct btrfs_ino_list, + list); + ino = ino_elem->ino; + parent = ino_elem->parent; + list_del(&ino_elem->list); + kfree(ino_elem); + if (ret) + continue; + + btrfs_release_path(path); + + key.objectid = ino; + key.type = BTRFS_INODE_ITEM_KEY; + key.offset = 0; + inode = btrfs_iget(fs_info->sb, &key, root, NULL); + /* + * If the other inode that had a conflicting dir entry was + * deleted in the current transaction, we need to log its parent + * directory. + */ + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + if (ret == -ENOENT) { + key.objectid = parent; + inode = btrfs_iget(fs_info->sb, &key, root, + NULL); + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + } else { + ret = btrfs_log_inode(trans, root, + BTRFS_I(inode), + LOG_OTHER_INODE_ALL, + 0, LLONG_MAX, ctx); + iput(inode); + } + } + continue; + } + /* + * We are safe logging the other inode without acquiring its + * lock as long as we log with the LOG_INODE_EXISTS mode. We + * are safe against concurrent renames of the other inode as + * well because during a rename we pin the log and update the + * log with the new name before we unpin it. + */ + ret = btrfs_log_inode(trans, root, BTRFS_I(inode), + LOG_OTHER_INODE, 0, LLONG_MAX, ctx); + if (ret) { + iput(inode); + continue; + } + + key.objectid = ino; + key.type = BTRFS_INODE_REF_KEY; + key.offset = 0; + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) { + iput(inode); + continue; + } + + while (true) { + struct extent_buffer *leaf = path->nodes[0]; + int slot = path->slots[0]; + u64 other_ino = 0; + u64 other_parent = 0; + + if (slot >= btrfs_header_nritems(leaf)) { + ret = btrfs_next_leaf(root, path); + if (ret < 0) { + break; + } else if (ret > 0) { + ret = 0; + break; + } + continue; + } + + btrfs_item_key_to_cpu(leaf, &key, slot); + if (key.objectid != ino || + (key.type != BTRFS_INODE_REF_KEY && + key.type != BTRFS_INODE_EXTREF_KEY)) { + ret = 0; + break; + } + + ret = btrfs_check_ref_name_override(leaf, slot, &key, + BTRFS_I(inode), &other_ino, + &other_parent); + if (ret < 0) + break; + if (ret > 0) { + ino_elem = kmalloc(sizeof(*ino_elem), GFP_NOFS); + if (!ino_elem) { + ret = -ENOMEM; + break; + } + ino_elem->ino = other_ino; + ino_elem->parent = other_parent; + list_add_tail(&ino_elem->list, &inode_list); + ret = 0; + } + path->slots[0]++; + } + iput(inode); + } + + return ret; +} + /* log a single inode in the tree log. * At least one parent directory for this inode must exist in the tree * or be logged already. @@ -5022,6 +5226,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, u64 logged_isize = 0; bool need_log_inode_item = true; bool xattrs_logged = false; + bool recursive_logging = false; path = btrfs_alloc_path(); if (!path) @@ -5067,8 +5272,12 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, return ret; } - if (inode_only == LOG_OTHER_INODE) { - inode_only = LOG_INODE_EXISTS; + if (inode_only == LOG_OTHER_INODE || inode_only == LOG_OTHER_INODE_ALL) { + recursive_logging = true; + if (inode_only == LOG_OTHER_INODE) + inode_only = LOG_INODE_EXISTS; + else + inode_only = LOG_INODE_ALL; mutex_lock_nested(&inode->log_mutex, SINGLE_DEPTH_NESTING); } else { mutex_lock(&inode->log_mutex); @@ -5163,20 +5372,19 @@ again: if ((min_key.type == BTRFS_INODE_REF_KEY || min_key.type == BTRFS_INODE_EXTREF_KEY) && - inode->generation == trans->transid) { + inode->generation == trans->transid && + !recursive_logging) { u64 other_ino = 0; + u64 other_parent = 0; ret = btrfs_check_ref_name_override(path->nodes[0], path->slots[0], &min_key, inode, - &other_ino); + &other_ino, &other_parent); if (ret < 0) { err = ret; goto out_unlock; } else if (ret > 0 && ctx && other_ino != btrfs_ino(BTRFS_I(ctx->inode))) { - struct btrfs_key inode_key; - struct inode *other_inode; - if (ins_nr > 0) { ins_nr++; } else { @@ -5192,44 +5400,13 @@ again: goto out_unlock; } ins_nr = 0; - btrfs_release_path(path); - inode_key.objectid = other_ino; - inode_key.type = BTRFS_INODE_ITEM_KEY; - inode_key.offset = 0; - other_inode = btrfs_iget(fs_info->sb, - &inode_key, root, - NULL); - /* - * If the other inode that had a conflicting dir - * entry was deleted in the current transaction, - * we don't need to do more work nor fallback to - * a transaction commit. - */ - if (IS_ERR(other_inode) && - PTR_ERR(other_inode) == -ENOENT) { - goto next_key; - } else if (IS_ERR(other_inode)) { - err = PTR_ERR(other_inode); - goto out_unlock; - } - /* - * We are safe logging the other inode without - * acquiring its i_mutex as long as we log with - * the LOG_INODE_EXISTS mode. We're safe against - * concurrent renames of the other inode as well - * because during a rename we pin the log and - * update the log with the new name before we - * unpin it. - */ - err = btrfs_log_inode(trans, root, - BTRFS_I(other_inode), - LOG_OTHER_INODE, 0, LLONG_MAX, - ctx); - iput(other_inode); + + err = log_conflicting_inodes(trans, root, path, + ctx, other_ino, other_parent); if (err) goto out_unlock; - else - goto next_key; + btrfs_release_path(path); + goto next_key; } } diff --git a/fs/buffer.c b/fs/buffer.c index f01b0c5f6302..07c3327ba824 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3489,6 +3489,130 @@ int bh_submit_read(struct buffer_head *bh) } EXPORT_SYMBOL(bh_submit_read); +/* + * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff. + * + * Returns the offset within the file on success, and -ENOENT otherwise. + */ +static loff_t +page_seek_hole_data(struct page *page, loff_t lastoff, int whence) +{ + loff_t offset = page_offset(page); + struct buffer_head *bh, *head; + bool seek_data = whence == SEEK_DATA; + + if (lastoff < offset) + lastoff = offset; + + bh = head = page_buffers(page); + do { + offset += bh->b_size; + if (lastoff >= offset) + continue; + + /* + * Unwritten extents that have data in the page cache covering + * them can be identified by the BH_Unwritten state flag. + * Pages with multiple buffers might have a mix of holes, data + * and unwritten extents - any buffer with valid data in it + * should have BH_Uptodate flag set on it. + */ + + if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data) + return lastoff; + + lastoff = offset; + } while ((bh = bh->b_this_page) != head); + return -ENOENT; +} + +/* + * Seek for SEEK_DATA / SEEK_HOLE in the page cache. + * + * Within unwritten extents, the page cache determines which parts are holes + * and which are data: unwritten and uptodate buffer heads count as data; + * everything else counts as a hole. + * + * Returns the resulting offset on successs, and -ENOENT otherwise. + */ +loff_t +page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, + int whence) +{ + pgoff_t index = offset >> PAGE_SHIFT; + pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE); + loff_t lastoff = offset; + struct pagevec pvec; + + if (length <= 0) + return -ENOENT; + + pagevec_init(&pvec); + + do { + unsigned want, nr_pages, i; + + want = min_t(unsigned, end - index, PAGEVEC_SIZE); + nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + /* + * At this point, the page may be truncated or + * invalidated (changing page->mapping to NULL), or + * even swizzled back from swapper_space to tmpfs file + * mapping. However, page->index will not change + * because we have a reference on the page. + * + * If current page offset is beyond where we've ended, + * we've found a hole. + */ + if (whence == SEEK_HOLE && + lastoff < page_offset(page)) + goto check_range; + + /* Searching done if the page index is out of range. */ + if (page->index >= end) + goto not_found; + + lock_page(page); + if (likely(page->mapping == inode->i_mapping) && + page_has_buffers(page)) { + lastoff = page_seek_hole_data(page, lastoff, whence); + if (lastoff >= 0) { + unlock_page(page); + goto check_range; + } + } + unlock_page(page); + lastoff = page_offset(page) + PAGE_SIZE; + } + + /* Searching done if fewer pages returned than wanted. */ + if (nr_pages < want) + break; + + index = pvec.pages[i - 1]->index + 1; + pagevec_release(&pvec); + } while (index < end); + + /* When no page at lastoff and we are not done, we found a hole. */ + if (whence != SEEK_HOLE) + goto not_found; + +check_range: + if (lastoff < offset + length) + goto out; +not_found: + lastoff = -ENOENT; +out: + pagevec_release(&pvec); + return lastoff; +} + void __init buffer_init(void) { unsigned long nrpages; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 240a90c8ffd1..bf48735494f2 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -4273,7 +4273,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, server->sec_mode, server->capabilities, server->timeAdj); if (ses->auth_key.response) { - cifs_dbg(VFS, "Free previous auth_key.response = %p\n", + cifs_dbg(FYI, "Free previous auth_key.response = %p\n", ses->auth_key.response); kfree(ses->auth_key.response); ses->auth_key.response = NULL; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index bc4045355d88..d4c312d8e416 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -286,9 +286,12 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, NULL /* no data input */, 0 /* no data input */, (char **)&out_buf, &ret_data_len); - if (rc != 0) + if (rc == -EOPNOTSUPP) { + cifs_dbg(FYI, + "server does not support query network interfaces\n"); + } else if (rc != 0) { cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc); - else if (ret_data_len < sizeof(struct network_interface_info_ioctl_rsp)) { + } else if (ret_data_len < sizeof(struct network_interface_info_ioctl_rsp)) { cifs_dbg(VFS, "server returned bad net interface info buf\n"); rc = -EINVAL; } else { diff --git a/fs/iomap.c b/fs/iomap.c index 9883e4b293d4..9523ef184dae 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -586,6 +586,100 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, } EXPORT_SYMBOL_GPL(iomap_fiemap); +static loff_t +iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, + void *data, struct iomap *iomap) +{ + switch (iomap->type) { + case IOMAP_UNWRITTEN: + offset = page_cache_seek_hole_data(inode, offset, length, + SEEK_HOLE); + if (offset < 0) + return length; + /* fall through */ + case IOMAP_HOLE: + *(loff_t *)data = offset; + return 0; + default: + return length; + } +} + +loff_t +iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) +{ + loff_t size = i_size_read(inode); + loff_t length = size - offset; + loff_t ret; + + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) + return -ENXIO; + + while (length > 0) { + ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, + &offset, iomap_seek_hole_actor); + if (ret < 0) + return ret; + if (ret == 0) + break; + + offset += ret; + length -= ret; + } + + return offset; +} +EXPORT_SYMBOL_GPL(iomap_seek_hole); + +static loff_t +iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, + void *data, struct iomap *iomap) +{ + switch (iomap->type) { + case IOMAP_HOLE: + return length; + case IOMAP_UNWRITTEN: + offset = page_cache_seek_hole_data(inode, offset, length, + SEEK_DATA); + if (offset < 0) + return length; + /*FALLTHRU*/ + default: + *(loff_t *)data = offset; + return 0; + } +} + +loff_t +iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) +{ + loff_t size = i_size_read(inode); + loff_t length = size - offset; + loff_t ret; + + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) + return -ENXIO; + + while (length > 0) { + ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, + &offset, iomap_seek_data_actor); + if (ret < 0) + return ret; + if (ret == 0) + break; + + offset += ret; + length -= ret; + } + + if (length <= 0) + return -ENXIO; + return offset; +} +EXPORT_SYMBOL_GPL(iomap_seek_data); + /* * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index e9371ba67c38..4fd84d26bc12 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -695,21 +695,18 @@ error0: */ static int xfs_dq_get_next_id( - xfs_mount_t *mp, + struct xfs_mount *mp, uint type, - xfs_dqid_t *id, - loff_t eof) + xfs_dqid_t *id) { - struct xfs_inode *quotip; + struct xfs_inode *quotip = xfs_quota_inode(mp, type); + xfs_dqid_t next_id = *id + 1; /* simple advance */ + uint lock_flags; + struct xfs_bmbt_irec got; + struct xfs_iext_cursor cur; xfs_fsblock_t start; - loff_t offset; - uint lock; - xfs_dqid_t next_id; int error = 0; - /* Simple advance */ - next_id = *id + 1; - /* If we'd wrap past the max ID, stop */ if (next_id < *id) return -ENOENT; @@ -723,23 +720,25 @@ xfs_dq_get_next_id( /* Nope, next_id is now past the current chunk, so find the next one */ start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk; - quotip = xfs_quota_inode(mp, type); - lock = xfs_ilock_data_map_shared(quotip); - - offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start), - eof, SEEK_DATA); - if (offset < 0) - error = offset; + lock_flags = xfs_ilock_data_map_shared(quotip); + if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK); + if (error) + return error; + } - xfs_iunlock(quotip, lock); + if (xfs_iext_lookup_extent(quotip, "ip->i_df, start, &cur, &got)) { + /* contiguous chunk, bump startoff for the id calculation */ + if (got.br_startoff < start) + got.br_startoff = start; + *id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk; + } else { + error = -ENOENT; + } - /* -ENXIO is essentially "no more data" */ - if (error) - return (error == -ENXIO ? -ENOENT: error); + xfs_iunlock(quotip, lock_flags); - /* Convert next data offset back to a quota id */ - *id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk; - return 0; + return error; } /* @@ -762,7 +761,6 @@ xfs_qm_dqget( struct xfs_quotainfo *qi = mp->m_quotainfo; struct radix_tree_root *tree = xfs_dquot_tree(qi, type); struct xfs_dquot *dqp; - loff_t eof = 0; int error; ASSERT(XFS_IS_QUOTA_RUNNING(mp)); @@ -790,21 +788,6 @@ xfs_qm_dqget( } #endif - /* Get the end of the quota file if we need it */ - if (flags & XFS_QMOPT_DQNEXT) { - struct xfs_inode *quotip; - xfs_fileoff_t last; - uint lock_mode; - - quotip = xfs_quota_inode(mp, type); - lock_mode = xfs_ilock_data_map_shared(quotip); - error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK); - xfs_iunlock(quotip, lock_mode); - if (error) - return error; - eof = XFS_FSB_TO_B(mp, last); - } - restart: mutex_lock(&qi->qi_tree_lock); dqp = radix_tree_lookup(tree, id); @@ -823,7 +806,7 @@ restart: if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { xfs_dqunlock(dqp); mutex_unlock(&qi->qi_tree_lock); - error = xfs_dq_get_next_id(mp, type, &id, eof); + error = xfs_dq_get_next_id(mp, type, &id); if (error) return error; goto restart; @@ -858,7 +841,7 @@ restart: /* If we are asked to find next active id, keep looking */ if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) { - error = xfs_dq_get_next_id(mp, type, &id, eof); + error = xfs_dq_get_next_id(mp, type, &id); if (!error) goto restart; } @@ -917,7 +900,7 @@ restart: if (flags & XFS_QMOPT_DQNEXT) { if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { xfs_qm_dqput(dqp); - error = xfs_dq_get_next_id(mp, type, &id, eof); + error = xfs_dq_get_next_id(mp, type, &id); if (error) return error; goto restart; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ab5c7a5325ae..2dbb9a12dae4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1041,378 +1041,31 @@ xfs_file_readdir( return xfs_readdir(ip, ctx, bufsize); } -/* - * This type is designed to indicate the type of offset we would like - * to search from page cache for xfs_seek_hole_data(). - */ -enum { - HOLE_OFF = 0, - DATA_OFF, -}; - -/* - * Lookup the desired type of offset from the given page. - * - * On success, return true and the offset argument will point to the - * start of the region that was found. Otherwise this function will - * return false and keep the offset argument unchanged. - */ -STATIC bool -xfs_lookup_buffer_offset( - struct page *page, - loff_t *offset, - unsigned int type) -{ - loff_t lastoff = page_offset(page); - bool found = false; - struct buffer_head *bh, *head; - - bh = head = page_buffers(page); - do { - /* - * Unwritten extents that have data in the page - * cache covering them can be identified by the - * BH_Unwritten state flag. Pages with multiple - * buffers might have a mix of holes, data and - * unwritten extents - any buffer with valid - * data in it should have BH_Uptodate flag set - * on it. - */ - if (buffer_unwritten(bh) || - buffer_uptodate(bh)) { - if (type == DATA_OFF) - found = true; - } else { - if (type == HOLE_OFF) - found = true; - } - - if (found) { - *offset = lastoff; - break; - } - lastoff += bh->b_size; - } while ((bh = bh->b_this_page) != head); - - return found; -} - -/* - * This routine is called to find out and return a data or hole offset - * from the page cache for unwritten extents according to the desired - * type for xfs_seek_hole_data(). - * - * The argument offset is used to tell where we start to search from the - * page cache. Map is used to figure out the end points of the range to - * lookup pages. - * - * Return true if the desired type of offset was found, and the argument - * offset is filled with that address. Otherwise, return false and keep - * offset unchanged. - */ -STATIC bool -xfs_find_get_desired_pgoff( - struct inode *inode, - struct xfs_bmbt_irec *map, - unsigned int type, - loff_t *offset) -{ - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - struct pagevec pvec; - pgoff_t index; - pgoff_t end; - loff_t endoff; - loff_t startoff = *offset; - loff_t lastoff = startoff; - bool found = false; - - pagevec_init(&pvec); - - index = startoff >> PAGE_SHIFT; - endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount); - end = (endoff - 1) >> PAGE_SHIFT; - do { - int want; - unsigned nr_pages; - unsigned int i; - - want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, - want); - if (nr_pages == 0) - break; - - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - loff_t b_offset; - - /* - * At this point, the page may be truncated or - * invalidated (changing page->mapping to NULL), - * or even swizzled back from swapper_space to tmpfs - * file mapping. However, page->index will not change - * because we have a reference on the page. - * - * If current page offset is beyond where we've ended, - * we've found a hole. - */ - if (type == HOLE_OFF && lastoff < endoff && - lastoff < page_offset(pvec.pages[i])) { - found = true; - *offset = lastoff; - goto out; - } - /* Searching done if the page index is out of range. */ - if (page->index > end) - goto out; - - lock_page(page); - /* - * Page truncated or invalidated(page->mapping == NULL). - * We can freely skip it and proceed to check the next - * page. - */ - if (unlikely(page->mapping != inode->i_mapping)) { - unlock_page(page); - continue; - } - - if (!page_has_buffers(page)) { - unlock_page(page); - continue; - } - - found = xfs_lookup_buffer_offset(page, &b_offset, type); - if (found) { - /* - * The found offset may be less than the start - * point to search if this is the first time to - * come here. - */ - *offset = max_t(loff_t, startoff, b_offset); - unlock_page(page); - goto out; - } - - /* - * We either searching data but nothing was found, or - * searching hole but found a data buffer. In either - * case, probably the next page contains the desired - * things, update the last offset to it so. - */ - lastoff = page_offset(page) + PAGE_SIZE; - unlock_page(page); - } - - /* - * The number of returned pages less than our desired, search - * done. - */ - if (nr_pages < want) - break; - - index = pvec.pages[i - 1]->index + 1; - pagevec_release(&pvec); - } while (index <= end); - - /* No page at lastoff and we are not done - we found a hole. */ - if (type == HOLE_OFF && lastoff < endoff) { - *offset = lastoff; - found = true; - } -out: - pagevec_release(&pvec); - return found; -} - -/* - * caller must lock inode with xfs_ilock_data_map_shared, - * can we craft an appropriate ASSERT? - * - * end is because the VFS-level lseek interface is defined such that any - * offset past i_size shall return -ENXIO, but we use this for quota code - * which does not maintain i_size, and we want to SEEK_DATA past i_size. - */ -loff_t -__xfs_seek_hole_data( - struct inode *inode, - loff_t start, - loff_t end, - int whence) -{ - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - loff_t uninitialized_var(offset); - xfs_fileoff_t fsbno; - xfs_filblks_t lastbno; - int error; - - if (start >= end) { - error = -ENXIO; - goto out_error; - } - - /* - * Try to read extents from the first block indicated - * by fsbno to the end block of the file. - */ - fsbno = XFS_B_TO_FSBT(mp, start); - lastbno = XFS_B_TO_FSB(mp, end); - - for (;;) { - struct xfs_bmbt_irec map[2]; - int nmap = 2; - unsigned int i; - - error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap, - XFS_BMAPI_ENTIRE); - if (error) - goto out_error; - - /* No extents at given offset, must be beyond EOF */ - if (nmap == 0) { - error = -ENXIO; - goto out_error; - } - - for (i = 0; i < nmap; i++) { - offset = max_t(loff_t, start, - XFS_FSB_TO_B(mp, map[i].br_startoff)); - - /* Landed in the hole we wanted? */ - if (whence == SEEK_HOLE && - map[i].br_startblock == HOLESTARTBLOCK) - goto out; - - /* Landed in the data extent we wanted? */ - if (whence == SEEK_DATA && - (map[i].br_startblock == DELAYSTARTBLOCK || - (map[i].br_state == XFS_EXT_NORM && - !isnullstartblock(map[i].br_startblock)))) - goto out; - - /* - * Landed in an unwritten extent, try to search - * for hole or data from page cache. - */ - if (map[i].br_state == XFS_EXT_UNWRITTEN) { - if (xfs_find_get_desired_pgoff(inode, &map[i], - whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF, - &offset)) - goto out; - } - } - - /* - * We only received one extent out of the two requested. This - * means we've hit EOF and didn't find what we are looking for. - */ - if (nmap == 1) { - /* - * If we were looking for a hole, set offset to - * the end of the file (i.e., there is an implicit - * hole at the end of any file). - */ - if (whence == SEEK_HOLE) { - offset = end; - break; - } - /* - * If we were looking for data, it's nowhere to be found - */ - ASSERT(whence == SEEK_DATA); - error = -ENXIO; - goto out_error; - } - - ASSERT(i > 1); - - /* - * Nothing was found, proceed to the next round of search - * if the next reading offset is not at or beyond EOF. - */ - fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount; - start = XFS_FSB_TO_B(mp, fsbno); - if (start >= end) { - if (whence == SEEK_HOLE) { - offset = end; - break; - } - ASSERT(whence == SEEK_DATA); - error = -ENXIO; - goto out_error; - } - } - -out: - /* - * If at this point we have found the hole we wanted, the returned - * offset may be bigger than the file size as it may be aligned to - * page boundary for unwritten extents. We need to deal with this - * situation in particular. - */ - if (whence == SEEK_HOLE) - offset = min_t(loff_t, offset, end); - - return offset; - -out_error: - return error; -} - -STATIC loff_t -xfs_seek_hole_data( - struct file *file, - loff_t start, - int whence) -{ - struct inode *inode = file->f_mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - uint lock; - loff_t offset, end; - int error = 0; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - lock = xfs_ilock_data_map_shared(ip); - - end = i_size_read(inode); - offset = __xfs_seek_hole_data(inode, start, end, whence); - if (offset < 0) { - error = offset; - goto out_unlock; - } - - offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes); - -out_unlock: - xfs_iunlock(ip, lock); - - if (error) - return error; - return offset; -} - STATIC loff_t xfs_file_llseek( struct file *file, loff_t offset, int whence) { + struct inode *inode = file->f_mapping->host; + + if (XFS_FORCED_SHUTDOWN(XFS_I(inode)->i_mount)) + return -EIO; + switch (whence) { - case SEEK_END: - case SEEK_CUR: - case SEEK_SET: + default: return generic_file_llseek(file, offset, whence); case SEEK_HOLE: + offset = iomap_seek_hole(inode, offset, &xfs_iomap_ops); + break; case SEEK_DATA: - return xfs_seek_hole_data(file, offset, whence); - default: - return -EINVAL; + offset = iomap_seek_data(inode, offset, &xfs_iomap_ops); + break; } + + if (offset < 0) + return offset; + return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } /* diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 6ccf5fb830e9..44ee56d428c0 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -459,8 +459,6 @@ int xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset, xfs_fsize_t isize, bool *did_zeroing); int xfs_zero_range(struct xfs_inode *ip, xfs_off_t pos, xfs_off_t count, bool *did_zero); -loff_t __xfs_seek_hole_data(struct inode *inode, loff_t start, - loff_t eof, int whence); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 821151ad4d36..f1689fff5196 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,6 +205,8 @@ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize); int bh_uptodate_or_lock(struct buffer_head *bh); int bh_submit_read(struct buffer_head *bh); +loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset, + loff_t length, int whence); extern int buffer_heads_over_limit; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index c4aacd3a9b6c..73e3b7085dbe 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -89,6 +89,10 @@ int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops); int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, const struct iomap_ops *ops); +loff_t iomap_seek_hole(struct inode *inode, loff_t offset, + const struct iomap_ops *ops); +loff_t iomap_seek_data(struct inode *inode, loff_t offset, + const struct iomap_ops *ops); /* * Flags for direct I/O ->end_io: diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index 49174de13eca..4a5a2548b1db 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -12,22 +12,36 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct gro_cell *cell; + int res; - if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) - return netif_rx(skb); + rcu_read_lock(); + if (unlikely(!(dev->flags & IFF_UP))) + goto drop; + + if (!gcells->cells || skb_cloned(skb) || netif_elide_gro(dev)) { + res = netif_rx(skb); + goto unlock; + } cell = this_cpu_ptr(gcells->cells); if (skb_queue_len(&cell->napi_skbs) > netdev_max_backlog) { +drop: atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); - return NET_RX_DROP; + res = NET_RX_DROP; + goto unlock; } __skb_queue_tail(&cell->napi_skbs, skb); if (skb_queue_len(&cell->napi_skbs) == 1) napi_schedule(&cell->napi); - return NET_RX_SUCCESS; + + res = NET_RX_SUCCESS; + +unlock: + rcu_read_unlock(); + return res; } EXPORT_SYMBOL(gro_cells_receive); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 5603c4a16248..9a9f7ce7438e 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -216,7 +216,12 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, atomic_set(&req->rsk_refcnt, 1); tcp_sk(child)->tsoffset = tsoff; sock_rps_save_rxhash(child, skb); - inet_csk_reqsk_queue_add(sk, req, child); + if (!inet_csk_reqsk_queue_add(sk, req, child)) { + bh_unlock_sock(child); + sock_put(child); + child = NULL; + reqsk_put(req); + } } else { reqsk_free(req); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e244dfddd39c..649931071092 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6411,7 +6411,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->send_synack(fastopen_sk, dst, &fl, req, &foc, TCP_SYNACK_FASTOPEN); /* Add the child socket directly into the accept queue */ - inet_csk_reqsk_queue_add(sk, req, fastopen_sk); + if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) { + reqsk_fastopen_remove(fastopen_sk, req, false); + bh_unlock_sock(fastopen_sk); + sock_put(fastopen_sk); + reqsk_put(req); + goto drop; + } sk->sk_data_ready(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 5f4cd03c8e4c..db32eb11d01c 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -680,9 +680,6 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (flags & MSG_OOB) goto out; - if (addr_len) - *addr_len = sizeof(*lsa); - if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); @@ -712,6 +709,7 @@ static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, lsa->l2tp_conn_id = 0; if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = inet6_iif(skb); + *addr_len = sizeof(*lsa); } if (np->rxopt.all) |