diff options
Diffstat (limited to 'kernel/drivers/vhost')
| -rw-r--r-- | kernel/drivers/vhost/Kconfig | 15 | ||||
| -rw-r--r-- | kernel/drivers/vhost/net.c | 3 | ||||
| -rw-r--r-- | kernel/drivers/vhost/scsi.c | 272 | ||||
| -rw-r--r-- | kernel/drivers/vhost/test.c | 3 | ||||
| -rw-r--r-- | kernel/drivers/vhost/vhost.c | 157 | ||||
| -rw-r--r-- | kernel/drivers/vhost/vhost.h | 36 |
6 files changed, 212 insertions, 274 deletions
diff --git a/kernel/drivers/vhost/Kconfig b/kernel/drivers/vhost/Kconfig index 017a1e8a8..533eaf04f 100644 --- a/kernel/drivers/vhost/Kconfig +++ b/kernel/drivers/vhost/Kconfig @@ -32,3 +32,18 @@ config VHOST ---help--- This option is selected by any driver which needs to access the core of vhost. + +config VHOST_CROSS_ENDIAN_LEGACY + bool "Cross-endian support for vhost" + default n + ---help--- + This option allows vhost to support guests with a different byte + ordering from host while using legacy virtio. + + Userspace programs can control the feature using the + VHOST_SET_VRING_ENDIAN and VHOST_GET_VRING_ENDIAN ioctls. + + This is only useful on a few platforms (ppc64 and arm64). Since it + adds some overhead, it is disabled by default. + + If unsure, say "N". diff --git a/kernel/drivers/vhost/net.c b/kernel/drivers/vhost/net.c index 7d137a43c..9eda69e40 100644 --- a/kernel/drivers/vhost/net.c +++ b/kernel/drivers/vhost/net.c @@ -61,8 +61,7 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" enum { VHOST_NET_FEATURES = VHOST_FEATURES | (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) | - (1ULL << VIRTIO_NET_F_MRG_RXBUF) | - (1ULL << VIRTIO_F_VERSION_1), + (1ULL << VIRTIO_NET_F_MRG_RXBUF) }; enum { diff --git a/kernel/drivers/vhost/scsi.c b/kernel/drivers/vhost/scsi.c index ea32b3867..29cfc57d4 100644 --- a/kernel/drivers/vhost/scsi.c +++ b/kernel/drivers/vhost/scsi.c @@ -35,14 +35,13 @@ #include <linux/compat.h> #include <linux/eventfd.h> #include <linux/fs.h> +#include <linux/vmalloc.h> #include <linux/miscdevice.h> #include <asm/unaligned.h> -#include <scsi/scsi.h> +#include <scsi/scsi_common.h> +#include <scsi/scsi_proto.h> #include <target/target_core_base.h> #include <target/target_core_fabric.h> -#include <target/target_core_fabric_configfs.h> -#include <target/target_core_configfs.h> -#include <target/configfs_macros.h> #include <linux/vhost.h> #include <linux/virtio_scsi.h> #include <linux/llist.h> @@ -115,15 +114,6 @@ struct vhost_scsi_nexus { struct se_session *tvn_se_sess; }; -struct vhost_scsi_nacl { - /* Binary World Wide unique Port Name for Vhost Initiator port */ - u64 iport_wwpn; - /* ASCII formatted WWPN for Sas Initiator port */ - char iport_name[VHOST_SCSI_NAMELEN]; - /* Returned by vhost_scsi_make_nodeacl() */ - struct se_node_acl se_node_acl; -}; - struct vhost_scsi_tpg { /* Vhost port target portal group tag for TCM */ u16 tport_tpgt; @@ -174,9 +164,7 @@ enum { /* Note: can't set VIRTIO_F_VERSION_1 yet, since that implies ANY_LAYOUT. */ enum { VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG) | - (1ULL << VIRTIO_SCSI_F_T10_PI) | - (1ULL << VIRTIO_F_ANY_LAYOUT) | - (1ULL << VIRTIO_F_VERSION_1) + (1ULL << VIRTIO_SCSI_F_T10_PI) }; #define VHOST_SCSI_MAX_TARGET 256 @@ -216,7 +204,6 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; -static struct target_core_fabric_ops vhost_scsi_ops; static struct workqueue_struct *vhost_scsi_workqueue; /* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */ @@ -297,28 +284,6 @@ static char *vhost_scsi_get_fabric_name(void) return "vhost"; } -static u8 vhost_scsi_get_fabric_proto_ident(struct se_portal_group *se_tpg) -{ - struct vhost_scsi_tpg *tpg = container_of(se_tpg, - struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tport *tport = tpg->tport; - - switch (tport->tport_proto_id) { - case SCSI_PROTOCOL_SAS: - return sas_get_fabric_proto_ident(se_tpg); - case SCSI_PROTOCOL_FCP: - return fc_get_fabric_proto_ident(se_tpg); - case SCSI_PROTOCOL_ISCSI: - return iscsi_get_fabric_proto_ident(se_tpg); - default: - pr_err("Unknown tport_proto_id: 0x%02x, using" - " SAS emulation\n", tport->tport_proto_id); - break; - } - - return sas_get_fabric_proto_ident(se_tpg); -} - static char *vhost_scsi_get_fabric_wwn(struct se_portal_group *se_tpg) { struct vhost_scsi_tpg *tpg = container_of(se_tpg, @@ -335,102 +300,6 @@ static u16 vhost_scsi_get_tpgt(struct se_portal_group *se_tpg) return tpg->tport_tpgt; } -static u32 vhost_scsi_get_default_depth(struct se_portal_group *se_tpg) -{ - return 1; -} - -static u32 -vhost_scsi_get_pr_transport_id(struct se_portal_group *se_tpg, - struct se_node_acl *se_nacl, - struct t10_pr_registration *pr_reg, - int *format_code, - unsigned char *buf) -{ - struct vhost_scsi_tpg *tpg = container_of(se_tpg, - struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tport *tport = tpg->tport; - - switch (tport->tport_proto_id) { - case SCSI_PROTOCOL_SAS: - return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg, - format_code, buf); - case SCSI_PROTOCOL_FCP: - return fc_get_pr_transport_id(se_tpg, se_nacl, pr_reg, - format_code, buf); - case SCSI_PROTOCOL_ISCSI: - return iscsi_get_pr_transport_id(se_tpg, se_nacl, pr_reg, - format_code, buf); - default: - pr_err("Unknown tport_proto_id: 0x%02x, using" - " SAS emulation\n", tport->tport_proto_id); - break; - } - - return sas_get_pr_transport_id(se_tpg, se_nacl, pr_reg, - format_code, buf); -} - -static u32 -vhost_scsi_get_pr_transport_id_len(struct se_portal_group *se_tpg, - struct se_node_acl *se_nacl, - struct t10_pr_registration *pr_reg, - int *format_code) -{ - struct vhost_scsi_tpg *tpg = container_of(se_tpg, - struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tport *tport = tpg->tport; - - switch (tport->tport_proto_id) { - case SCSI_PROTOCOL_SAS: - return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg, - format_code); - case SCSI_PROTOCOL_FCP: - return fc_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg, - format_code); - case SCSI_PROTOCOL_ISCSI: - return iscsi_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg, - format_code); - default: - pr_err("Unknown tport_proto_id: 0x%02x, using" - " SAS emulation\n", tport->tport_proto_id); - break; - } - - return sas_get_pr_transport_id_len(se_tpg, se_nacl, pr_reg, - format_code); -} - -static char * -vhost_scsi_parse_pr_out_transport_id(struct se_portal_group *se_tpg, - const char *buf, - u32 *out_tid_len, - char **port_nexus_ptr) -{ - struct vhost_scsi_tpg *tpg = container_of(se_tpg, - struct vhost_scsi_tpg, se_tpg); - struct vhost_scsi_tport *tport = tpg->tport; - - switch (tport->tport_proto_id) { - case SCSI_PROTOCOL_SAS: - return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len, - port_nexus_ptr); - case SCSI_PROTOCOL_FCP: - return fc_parse_pr_out_transport_id(se_tpg, buf, out_tid_len, - port_nexus_ptr); - case SCSI_PROTOCOL_ISCSI: - return iscsi_parse_pr_out_transport_id(se_tpg, buf, out_tid_len, - port_nexus_ptr); - default: - pr_err("Unknown tport_proto_id: 0x%02x, using" - " SAS emulation\n", tport->tport_proto_id); - break; - } - - return sas_parse_pr_out_transport_id(se_tpg, buf, out_tid_len, - port_nexus_ptr); -} - static int vhost_scsi_check_prot_fabric_only(struct se_portal_group *se_tpg) { struct vhost_scsi_tpg *tpg = container_of(se_tpg, @@ -439,29 +308,6 @@ static int vhost_scsi_check_prot_fabric_only(struct se_portal_group *se_tpg) return tpg->tv_fabric_prot_type; } -static struct se_node_acl * -vhost_scsi_alloc_fabric_acl(struct se_portal_group *se_tpg) -{ - struct vhost_scsi_nacl *nacl; - - nacl = kzalloc(sizeof(struct vhost_scsi_nacl), GFP_KERNEL); - if (!nacl) { - pr_err("Unable to allocate struct vhost_scsi_nacl\n"); - return NULL; - } - - return &nacl->se_node_acl; -} - -static void -vhost_scsi_release_fabric_acl(struct se_portal_group *se_tpg, - struct se_node_acl *se_nacl) -{ - struct vhost_scsi_nacl *nacl = container_of(se_nacl, - struct vhost_scsi_nacl, se_node_acl); - kfree(nacl); -} - static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg) { return 1; @@ -519,11 +365,6 @@ static void vhost_scsi_set_default_node_attrs(struct se_node_acl *nacl) return; } -static u32 vhost_scsi_get_task_tag(struct se_cmd *se_cmd) -{ - return 0; -} - static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd) { return 0; @@ -607,7 +448,7 @@ static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd) static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd) { - return target_put_sess_cmd(se_cmd->se_sess, se_cmd); + return target_put_sess_cmd(se_cmd); } static void @@ -968,6 +809,7 @@ static void vhost_scsi_submission_work(struct work_struct *work) } tv_nexus = cmd->tvc_nexus; + se_cmd->tag = 0; rc = target_submit_cmd_map_sgls(se_cmd, tv_nexus->tvn_se_sess, cmd->tvc_cdb, &cmd->tvc_sense_buf[0], cmd->tvc_lun, cmd->tvc_exp_data_len, @@ -1727,9 +1569,9 @@ static int __init vhost_scsi_register(void) return misc_register(&vhost_scsi_misc); } -static int vhost_scsi_deregister(void) +static void vhost_scsi_deregister(void) { - return misc_deregister(&vhost_scsi_misc); + misc_deregister(&vhost_scsi_misc); } static char *vhost_scsi_dump_proto_id(struct vhost_scsi_tport *tport) @@ -1822,50 +1664,6 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, mutex_unlock(&vhost_scsi_mutex); } -static struct se_node_acl * -vhost_scsi_make_nodeacl(struct se_portal_group *se_tpg, - struct config_group *group, - const char *name) -{ - struct se_node_acl *se_nacl, *se_nacl_new; - struct vhost_scsi_nacl *nacl; - u64 wwpn = 0; - u32 nexus_depth; - - /* vhost_scsi_parse_wwn(name, &wwpn, 1) < 0) - return ERR_PTR(-EINVAL); */ - se_nacl_new = vhost_scsi_alloc_fabric_acl(se_tpg); - if (!se_nacl_new) - return ERR_PTR(-ENOMEM); - - nexus_depth = 1; - /* - * se_nacl_new may be released by core_tpg_add_initiator_node_acl() - * when converting a NodeACL from demo mode -> explict - */ - se_nacl = core_tpg_add_initiator_node_acl(se_tpg, se_nacl_new, - name, nexus_depth); - if (IS_ERR(se_nacl)) { - vhost_scsi_release_fabric_acl(se_tpg, se_nacl_new); - return se_nacl; - } - /* - * Locate our struct vhost_scsi_nacl and set the FC Nport WWPN - */ - nacl = container_of(se_nacl, struct vhost_scsi_nacl, se_node_acl); - nacl->iport_wwpn = wwpn; - - return se_nacl; -} - -static void vhost_scsi_drop_nodeacl(struct se_node_acl *se_acl) -{ - struct vhost_scsi_nacl *nacl = container_of(se_acl, - struct vhost_scsi_nacl, se_node_acl); - core_tpg_del_initiator_node_acl(se_acl->se_tpg, se_acl, 1); - kfree(nacl); -} - static void vhost_scsi_free_cmd_map_res(struct vhost_scsi_nexus *nexus, struct se_session *se_sess) { @@ -1884,11 +1682,10 @@ static void vhost_scsi_free_cmd_map_res(struct vhost_scsi_nexus *nexus, } } -static ssize_t vhost_scsi_tpg_attrib_store_fabric_prot_type( - struct se_portal_group *se_tpg, - const char *page, - size_t count) +static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( + struct config_item *item, const char *page, size_t count) { + struct se_portal_group *se_tpg = attrib_to_tpg(item); struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); unsigned long val; @@ -1907,19 +1704,20 @@ static ssize_t vhost_scsi_tpg_attrib_store_fabric_prot_type( return count; } -static ssize_t vhost_scsi_tpg_attrib_show_fabric_prot_type( - struct se_portal_group *se_tpg, - char *page) +static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_show( + struct config_item *item, char *page) { + struct se_portal_group *se_tpg = attrib_to_tpg(item); struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); return sprintf(page, "%d\n", tpg->tv_fabric_prot_type); } -TF_TPG_ATTRIB_ATTR(vhost_scsi, fabric_prot_type, S_IRUGO | S_IWUSR); + +CONFIGFS_ATTR(vhost_scsi_tpg_attrib_, fabric_prot_type); static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = { - &vhost_scsi_tpg_attrib_fabric_prot_type.attr, + &vhost_scsi_tpg_attrib_attr_fabric_prot_type, NULL, }; @@ -2067,9 +1865,9 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg) return 0; } -static ssize_t vhost_scsi_tpg_show_nexus(struct se_portal_group *se_tpg, - char *page) +static ssize_t vhost_scsi_tpg_nexus_show(struct config_item *item, char *page) { + struct se_portal_group *se_tpg = to_tpg(item); struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); struct vhost_scsi_nexus *tv_nexus; @@ -2088,10 +1886,10 @@ static ssize_t vhost_scsi_tpg_show_nexus(struct se_portal_group *se_tpg, return ret; } -static ssize_t vhost_scsi_tpg_store_nexus(struct se_portal_group *se_tpg, - const char *page, - size_t count) +static ssize_t vhost_scsi_tpg_nexus_store(struct config_item *item, + const char *page, size_t count) { + struct se_portal_group *se_tpg = to_tpg(item); struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); struct vhost_scsi_tport *tport_wwn = tpg->tport; @@ -2166,10 +1964,10 @@ check_newline: return count; } -TF_TPG_BASE_ATTR(vhost_scsi, nexus, S_IRUGO | S_IWUSR); +CONFIGFS_ATTR(vhost_scsi_tpg_, nexus); static struct configfs_attribute *vhost_scsi_tpg_attrs[] = { - &vhost_scsi_tpg_nexus.attr, + &vhost_scsi_tpg_attr_nexus, NULL, }; @@ -2200,8 +1998,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, tpg->tport = tport; tpg->tport_tpgt = tpgt; - ret = core_tpg_register(&vhost_scsi_ops, wwn, - &tpg->se_tpg, tpg, TRANSPORT_TPG_TYPE_NORMAL); + ret = core_tpg_register(wwn, &tpg->se_tpg, tport->tport_proto_id); if (ret < 0) { kfree(tpg); return NULL; @@ -2306,18 +2103,17 @@ static void vhost_scsi_drop_tport(struct se_wwn *wwn) } static ssize_t -vhost_scsi_wwn_show_attr_version(struct target_fabric_configfs *tf, - char *page) +vhost_scsi_wwn_version_show(struct config_item *item, char *page) { return sprintf(page, "TCM_VHOST fabric module %s on %s/%s" "on "UTS_RELEASE"\n", VHOST_SCSI_VERSION, utsname()->sysname, utsname()->machine); } -TF_WWN_ATTR_RO(vhost_scsi, version); +CONFIGFS_ATTR_RO(vhost_scsi_wwn_, version); static struct configfs_attribute *vhost_scsi_wwn_attrs[] = { - &vhost_scsi_wwn_version.attr, + &vhost_scsi_wwn_attr_version, NULL, }; @@ -2325,20 +2121,13 @@ static struct target_core_fabric_ops vhost_scsi_ops = { .module = THIS_MODULE, .name = "vhost", .get_fabric_name = vhost_scsi_get_fabric_name, - .get_fabric_proto_ident = vhost_scsi_get_fabric_proto_ident, .tpg_get_wwn = vhost_scsi_get_fabric_wwn, .tpg_get_tag = vhost_scsi_get_tpgt, - .tpg_get_default_depth = vhost_scsi_get_default_depth, - .tpg_get_pr_transport_id = vhost_scsi_get_pr_transport_id, - .tpg_get_pr_transport_id_len = vhost_scsi_get_pr_transport_id_len, - .tpg_parse_pr_out_transport_id = vhost_scsi_parse_pr_out_transport_id, .tpg_check_demo_mode = vhost_scsi_check_true, .tpg_check_demo_mode_cache = vhost_scsi_check_true, .tpg_check_demo_mode_write_protect = vhost_scsi_check_false, .tpg_check_prod_mode_write_protect = vhost_scsi_check_false, .tpg_check_prot_fabric_only = vhost_scsi_check_prot_fabric_only, - .tpg_alloc_fabric_acl = vhost_scsi_alloc_fabric_acl, - .tpg_release_fabric_acl = vhost_scsi_release_fabric_acl, .tpg_get_inst_index = vhost_scsi_tpg_get_inst_index, .release_cmd = vhost_scsi_release_cmd, .check_stop_free = vhost_scsi_check_stop_free, @@ -2349,7 +2138,6 @@ static struct target_core_fabric_ops vhost_scsi_ops = { .write_pending = vhost_scsi_write_pending, .write_pending_status = vhost_scsi_write_pending_status, .set_default_node_attributes = vhost_scsi_set_default_node_attrs, - .get_task_tag = vhost_scsi_get_task_tag, .get_cmd_state = vhost_scsi_get_cmd_state, .queue_data_in = vhost_scsi_queue_data_in, .queue_status = vhost_scsi_queue_status, @@ -2364,10 +2152,6 @@ static struct target_core_fabric_ops vhost_scsi_ops = { .fabric_drop_tpg = vhost_scsi_drop_tpg, .fabric_post_link = vhost_scsi_port_link, .fabric_pre_unlink = vhost_scsi_port_unlink, - .fabric_make_np = NULL, - .fabric_drop_np = NULL, - .fabric_make_nodeacl = vhost_scsi_make_nodeacl, - .fabric_drop_nodeacl = vhost_scsi_drop_nodeacl, .tfc_wwn_attrs = vhost_scsi_wwn_attrs, .tfc_tpg_base_attrs = vhost_scsi_tpg_attrs, diff --git a/kernel/drivers/vhost/test.c b/kernel/drivers/vhost/test.c index d9c501eaa..f2882ac98 100644 --- a/kernel/drivers/vhost/test.c +++ b/kernel/drivers/vhost/test.c @@ -277,10 +277,13 @@ static long vhost_test_ioctl(struct file *f, unsigned int ioctl, return -EFAULT; return 0; case VHOST_SET_FEATURES: + printk(KERN_ERR "1\n"); if (copy_from_user(&features, featurep, sizeof features)) return -EFAULT; + printk(KERN_ERR "2\n"); if (features & ~VHOST_FEATURES) return -EOPNOTSUPP; + printk(KERN_ERR "3\n"); return vhost_test_set_features(n, features); case VHOST_RESET_OWNER: return vhost_test_reset_owner(n); diff --git a/kernel/drivers/vhost/vhost.c b/kernel/drivers/vhost/vhost.c index fa49d3294..ad2146a9a 100644 --- a/kernel/drivers/vhost/vhost.c +++ b/kernel/drivers/vhost/vhost.c @@ -22,20 +22,97 @@ #include <linux/file.h> #include <linux/highmem.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <linux/kthread.h> #include <linux/cgroup.h> #include <linux/module.h> +#include <linux/sort.h> #include "vhost.h" +static ushort max_mem_regions = 64; +module_param(max_mem_regions, ushort, 0444); +MODULE_PARM_DESC(max_mem_regions, + "Maximum number of memory regions in memory map. (default: 64)"); + enum { - VHOST_MEMORY_MAX_NREGIONS = 64, VHOST_MEMORY_F_LOG = 0x1, }; #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num]) #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num]) +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY +static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq) +{ + vq->user_be = !virtio_legacy_is_little_endian(); +} + +static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp) +{ + struct vhost_vring_state s; + + if (vq->private_data) + return -EBUSY; + + if (copy_from_user(&s, argp, sizeof(s))) + return -EFAULT; + + if (s.num != VHOST_VRING_LITTLE_ENDIAN && + s.num != VHOST_VRING_BIG_ENDIAN) + return -EINVAL; + + vq->user_be = s.num; + + return 0; +} + +static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, + int __user *argp) +{ + struct vhost_vring_state s = { + .index = idx, + .num = vq->user_be + }; + + if (copy_to_user(argp, &s, sizeof(s))) + return -EFAULT; + + return 0; +} + +static void vhost_init_is_le(struct vhost_virtqueue *vq) +{ + /* Note for legacy virtio: user_be is initialized at reset time + * according to the host endianness. If userspace does not set an + * explicit endianness, the default behavior is native endian, as + * expected by legacy virtio. + */ + vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be; +} +#else +static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq) +{ +} + +static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp) +{ + return -ENOIOCTLCMD; +} + +static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, + int __user *argp) +{ + return -ENOIOCTLCMD; +} + +static void vhost_init_is_le(struct vhost_virtqueue *vq) +{ + if (vhost_has_feature(vq, VIRTIO_F_VERSION_1)) + vq->is_le = true; +} +#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */ + static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh, poll_table *pt) { @@ -199,6 +276,8 @@ static void vhost_vq_reset(struct vhost_dev *dev, vq->call = NULL; vq->log_ctx = NULL; vq->memory = NULL; + vq->is_le = virtio_legacy_is_little_endian(); + vhost_vq_reset_user_be(vq); } static int vhost_worker(void *data) @@ -470,7 +549,7 @@ void vhost_dev_cleanup(struct vhost_dev *dev, bool locked) fput(dev->log_file); dev->log_file = NULL; /* No one will access memory at this point */ - kfree(dev->memory); + kvfree(dev->memory); dev->memory = NULL; WARN_ON(!list_empty(&dev->work_list)); if (dev->worker) { @@ -590,6 +669,25 @@ int vhost_vq_access_ok(struct vhost_virtqueue *vq) } EXPORT_SYMBOL_GPL(vhost_vq_access_ok); +static int vhost_memory_reg_sort_cmp(const void *p1, const void *p2) +{ + const struct vhost_memory_region *r1 = p1, *r2 = p2; + if (r1->guest_phys_addr < r2->guest_phys_addr) + return 1; + if (r1->guest_phys_addr > r2->guest_phys_addr) + return -1; + return 0; +} + +static void *vhost_kvzalloc(unsigned long size) +{ + void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + + if (!n) + n = vzalloc(size); + return n; +} + static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) { struct vhost_memory mem, *newmem, *oldmem; @@ -600,21 +698,23 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) return -EFAULT; if (mem.padding) return -EOPNOTSUPP; - if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS) + if (mem.nregions > max_mem_regions) return -E2BIG; - newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL); + newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions)); if (!newmem) return -ENOMEM; memcpy(newmem, &mem, size); if (copy_from_user(newmem->regions, m->regions, mem.nregions * sizeof *m->regions)) { - kfree(newmem); + kvfree(newmem); return -EFAULT; } + sort(newmem->regions, newmem->nregions, sizeof(*newmem->regions), + vhost_memory_reg_sort_cmp, NULL); if (!memory_access_ok(d, newmem, 0)) { - kfree(newmem); + kvfree(newmem); return -EFAULT; } oldmem = d->memory; @@ -626,7 +726,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) d->vqs[i]->memory = newmem; mutex_unlock(&d->vqs[i]->mutex); } - kfree(oldmem); + kvfree(oldmem); return 0; } @@ -719,7 +819,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE); if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) || (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) || - (a.log_guest_addr & (sizeof(u64) - 1))) { + (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) { r = -EINVAL; break; } @@ -806,6 +906,12 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp) } else filep = eventfp; break; + case VHOST_SET_VRING_ENDIAN: + r = vhost_set_vring_endian(vq, argp); + break; + case VHOST_GET_VRING_ENDIAN: + r = vhost_get_vring_endian(vq, idx, argp); + break; default: r = -ENOIOCTLCMD; } @@ -914,17 +1020,22 @@ EXPORT_SYMBOL_GPL(vhost_dev_ioctl); static const struct vhost_memory_region *find_region(struct vhost_memory *mem, __u64 addr, __u32 len) { - struct vhost_memory_region *reg; - int i; + const struct vhost_memory_region *reg; + int start = 0, end = mem->nregions; - /* linear search is not brilliant, but we really have on the order of 6 - * regions in practice */ - for (i = 0; i < mem->nregions; ++i) { - reg = mem->regions + i; - if (reg->guest_phys_addr <= addr && - reg->guest_phys_addr + reg->memory_size - 1 >= addr) - return reg; + while (start < end) { + int slot = start + (end - start) / 2; + reg = mem->regions + slot; + if (addr >= reg->guest_phys_addr) + end = slot; + else + start = slot + 1; } + + reg = mem->regions + start; + if (addr >= reg->guest_phys_addr && + reg->guest_phys_addr + reg->memory_size > addr) + return reg; return NULL; } @@ -1045,8 +1156,12 @@ int vhost_init_used(struct vhost_virtqueue *vq) { __virtio16 last_used_idx; int r; - if (!vq->private_data) + if (!vq->private_data) { + vq->is_le = virtio_legacy_is_little_endian(); return 0; + } + + vhost_init_is_le(vq); r = vhost_update_used_flags(vq); if (r) @@ -1254,7 +1369,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ if (unlikely(__get_user(ring_head, - &vq->avail->ring[last_avail_idx % vq->num]))) { + &vq->avail->ring[last_avail_idx & (vq->num - 1)]))) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); @@ -1374,7 +1489,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq, u16 old, new; int start; - start = vq->last_used_idx % vq->num; + start = vq->last_used_idx & (vq->num - 1); used = vq->used->ring + start; if (count == 1) { if (__put_user(heads[0].id, &used->id)) { @@ -1416,7 +1531,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, { int start, n, r; - start = vq->last_used_idx % vq->num; + start = vq->last_used_idx & (vq->num - 1); n = vq->num - start; if (n < count) { r = __vhost_add_used_n(vq, heads, n); diff --git a/kernel/drivers/vhost/vhost.h b/kernel/drivers/vhost/vhost.h index 8c1c79290..d3f767448 100644 --- a/kernel/drivers/vhost/vhost.h +++ b/kernel/drivers/vhost/vhost.h @@ -106,6 +106,14 @@ struct vhost_virtqueue { /* Log write descriptors */ void __user *log_base; struct vhost_log *log; + + /* Ring endianness. Defaults to legacy native endianness. + * Set to true when starting a modern virtio device. */ + bool is_le; +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY + /* Ring endianness requested by userspace for cross-endian support. */ + bool user_be; +#endif }; struct vhost_dev { @@ -165,7 +173,9 @@ enum { VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) | (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | (1ULL << VIRTIO_RING_F_EVENT_IDX) | - (1ULL << VHOST_F_LOG_ALL), + (1ULL << VHOST_F_LOG_ALL) | + (1ULL << VIRTIO_F_ANY_LAYOUT) | + (1ULL << VIRTIO_F_VERSION_1) }; static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) @@ -173,34 +183,46 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit) return vq->acked_features & (1ULL << bit); } +#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY +static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) +{ + return vq->is_le; +} +#else +static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq) +{ + return virtio_legacy_is_little_endian() || vq->is_le; +} +#endif + /* Memory accessors */ static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val) { - return __virtio16_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __virtio16_to_cpu(vhost_is_little_endian(vq), val); } static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val) { - return __cpu_to_virtio16(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio16(vhost_is_little_endian(vq), val); } static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val) { - return __virtio32_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __virtio32_to_cpu(vhost_is_little_endian(vq), val); } static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val) { - return __cpu_to_virtio32(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio32(vhost_is_little_endian(vq), val); } static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val) { - return __virtio64_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __virtio64_to_cpu(vhost_is_little_endian(vq), val); } static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val) { - return __cpu_to_virtio64(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val); + return __cpu_to_virtio64(vhost_is_little_endian(vq), val); } #endif |