From: Yuanhan Liu Date: Tue, 2 Feb 2016 13:48:19 +0000 (+0800) Subject: virtio: support specification 1.0 X-Git-Tag: spdx-start~7657 X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=6ba1f63b5ab0d6115c0fb74283e3a16512f56255;p=dpdk.git virtio: support specification 1.0 Modern (v1.0) virtio pci device defines several pci capabilities. Each cap has a configure structure corresponding to it, and the cap.bar and cap.offset fields tell us where to find it. Firstly, we map the pci resources by rte_eal_pci_map_device(). We then could easily locate a cfg structure by: cfg_addr = dev->mem_resources[cap.bar].addr + cap.offset; Therefore, the entrance of enabling modern (v1.0) pci device support is to iterate the pci capability lists, and to locate some configs we care; and they are: - common cfg For generic virtio and virtqueue configuration, such as setting/getting features, enabling a specific queue, and so on. - nofity cfg Combining with `queue_notify_off' from common cfg, we could use it to notify a specific virt queue. - device cfg Where virtio_net_config structure is located. - isr cfg Where to read isr (interrupt status). If any of above cap is not found, we fallback to the legacy virtio handling. If succeed, hw->vtpci_ops is assigned to modern_ops, where all operations are implemented by reading/writing a (or few) specific configuration space from above 4 cfg structures. And that's basically how this patch works. Besides those changes, virtio 1.0 introduces a new status field: FEATURES_OK, which is set after features negotiation is done. Last, set the VIRTIO_F_VERSION_1 feature flag. Signed-off-by: Yuanhan Liu Tested-by: Qian Xu Reviewed-by: Tetsuya Mukawa Tested-by: Tetsuya Mukawa Acked-by: Huawei Xie --- diff --git a/doc/guides/rel_notes/release_2_3.rst b/doc/guides/rel_notes/release_2_3.rst index 53d048d2a1..7945694b5f 100644 --- a/doc/guides/rel_notes/release_2_3.rst +++ b/doc/guides/rel_notes/release_2_3.rst @@ -35,6 +35,10 @@ This section should contain new features added in this release. Sample format: Refer to the previous release notes for examples. +* **Virtio 1.0.** + + Enabled virtio 1.0 support for virtio pmd driver. + Resolved Issues --------------- diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virtio_ethdev.c index 4f8475785a..755503ded3 100644 --- a/drivers/net/virtio/virtio_ethdev.c +++ b/drivers/net/virtio/virtio_ethdev.c @@ -927,7 +927,7 @@ virtio_vlan_filter_set(struct rte_eth_dev *dev, uint16_t vlan_id, int on) return virtio_send_command(hw->cvq, &ctrl, &len, 1); } -static void +static int virtio_negotiate_features(struct virtio_hw *hw) { uint64_t host_features; @@ -949,6 +949,22 @@ virtio_negotiate_features(struct virtio_hw *hw) hw->guest_features = vtpci_negotiate_features(hw, host_features); PMD_INIT_LOG(DEBUG, "features after negotiate = %" PRIx64, hw->guest_features); + + if (hw->modern) { + if (!vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) { + PMD_INIT_LOG(ERR, + "VIRTIO_F_VERSION_1 features is not enabled."); + return -1; + } + vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_FEATURES_OK); + if (!(vtpci_get_status(hw) & VIRTIO_CONFIG_STATUS_FEATURES_OK)) { + PMD_INIT_LOG(ERR, + "failed to set FEATURES_OK status!"); + return -1; + } + } + + return 0; } /* @@ -1032,7 +1048,8 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) /* Tell the host we've known how to drive the device. */ vtpci_set_status(hw, VIRTIO_CONFIG_STATUS_DRIVER); - virtio_negotiate_features(hw); + if (virtio_negotiate_features(hw) < 0) + return -1; /* If host does not support status then disable LSC */ if (!vtpci_with_feature(hw, VIRTIO_NET_F_STATUS)) @@ -1043,7 +1060,8 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) rx_func_get(eth_dev); /* Setting up rx_header size for the device */ - if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF)) + if (vtpci_with_feature(hw, VIRTIO_NET_F_MRG_RXBUF) || + vtpci_with_feature(hw, VIRTIO_F_VERSION_1)) hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr_mrg_rxbuf); else hw->vtnet_hdr_size = sizeof(struct virtio_net_hdr); @@ -1159,6 +1177,7 @@ eth_virtio_dev_uninit(struct rte_eth_dev *eth_dev) rte_intr_callback_unregister(&pci_dev->intr_handle, virtio_interrupt_handler, eth_dev); + rte_eal_pci_unmap_device(pci_dev); PMD_INIT_LOG(DEBUG, "dev_uninit completed"); diff --git a/drivers/net/virtio/virtio_ethdev.h b/drivers/net/virtio/virtio_ethdev.h index ae2d47de7b..fed9571ce8 100644 --- a/drivers/net/virtio/virtio_ethdev.h +++ b/drivers/net/virtio/virtio_ethdev.h @@ -64,7 +64,8 @@ 1u << VIRTIO_NET_F_CTRL_VQ | \ 1u << VIRTIO_NET_F_CTRL_RX | \ 1u << VIRTIO_NET_F_CTRL_VLAN | \ - 1u << VIRTIO_NET_F_MRG_RXBUF) + 1u << VIRTIO_NET_F_MRG_RXBUF | \ + 1ULL << VIRTIO_F_VERSION_1) /* * CQ function prototype diff --git a/drivers/net/virtio/virtio_pci.c b/drivers/net/virtio/virtio_pci.c index 39610775d6..7c7621a0bf 100644 --- a/drivers/net/virtio/virtio_pci.c +++ b/drivers/net/virtio/virtio_pci.c @@ -41,6 +41,14 @@ #include "virtio_logs.h" #include "virtqueue.h" +/* + * Following macros are derived from linux/pci_regs.h, however, + * we can't simply include that header here, as there is no such + * file for non-Linux platform. + */ +#define PCI_CAPABILITY_LIST 0x34 +#define PCI_CAP_ID_VNDR 0x09 + static void legacy_read_dev_config(struct virtio_hw *hw, size_t offset, void *dst, int length) @@ -444,6 +452,217 @@ static const struct virtio_pci_ops legacy_ops = { }; +static inline uint8_t +io_read8(uint8_t *addr) +{ + return *(volatile uint8_t *)addr; +} + +static inline void +io_write8(uint8_t val, uint8_t *addr) +{ + *(volatile uint8_t *)addr = val; +} + +static inline uint16_t +io_read16(uint16_t *addr) +{ + return *(volatile uint16_t *)addr; +} + +static inline void +io_write16(uint16_t val, uint16_t *addr) +{ + *(volatile uint16_t *)addr = val; +} + +static inline uint32_t +io_read32(uint32_t *addr) +{ + return *(volatile uint32_t *)addr; +} + +static inline void +io_write32(uint32_t val, uint32_t *addr) +{ + *(volatile uint32_t *)addr = val; +} + +static inline void +io_write64_twopart(uint64_t val, uint32_t *lo, uint32_t *hi) +{ + io_write32(val & ((1ULL << 32) - 1), lo); + io_write32(val >> 32, hi); +} + +static void +modern_read_dev_config(struct virtio_hw *hw, size_t offset, + void *dst, int length) +{ + int i; + uint8_t *p; + uint8_t old_gen, new_gen; + + do { + old_gen = io_read8(&hw->common_cfg->config_generation); + + p = dst; + for (i = 0; i < length; i++) + *p++ = io_read8((uint8_t *)hw->dev_cfg + offset + i); + + new_gen = io_read8(&hw->common_cfg->config_generation); + } while (old_gen != new_gen); +} + +static void +modern_write_dev_config(struct virtio_hw *hw, size_t offset, + const void *src, int length) +{ + int i; + const uint8_t *p = src; + + for (i = 0; i < length; i++) + io_write8(*p++, (uint8_t *)hw->dev_cfg + offset + i); +} + +static uint64_t +modern_get_features(struct virtio_hw *hw) +{ + uint32_t features_lo, features_hi; + + io_write32(0, &hw->common_cfg->device_feature_select); + features_lo = io_read32(&hw->common_cfg->device_feature); + + io_write32(1, &hw->common_cfg->device_feature_select); + features_hi = io_read32(&hw->common_cfg->device_feature); + + return ((uint64_t)features_hi << 32) | features_lo; +} + +static void +modern_set_features(struct virtio_hw *hw, uint64_t features) +{ + io_write32(0, &hw->common_cfg->guest_feature_select); + io_write32(features & ((1ULL << 32) - 1), + &hw->common_cfg->guest_feature); + + io_write32(1, &hw->common_cfg->guest_feature_select); + io_write32(features >> 32, + &hw->common_cfg->guest_feature); +} + +static uint8_t +modern_get_status(struct virtio_hw *hw) +{ + return io_read8(&hw->common_cfg->device_status); +} + +static void +modern_set_status(struct virtio_hw *hw, uint8_t status) +{ + io_write8(status, &hw->common_cfg->device_status); +} + +static void +modern_reset(struct virtio_hw *hw) +{ + modern_set_status(hw, VIRTIO_CONFIG_STATUS_RESET); + modern_get_status(hw); +} + +static uint8_t +modern_get_isr(struct virtio_hw *hw) +{ + return io_read8(hw->isr); +} + +static uint16_t +modern_set_config_irq(struct virtio_hw *hw, uint16_t vec) +{ + io_write16(vec, &hw->common_cfg->msix_config); + return io_read16(&hw->common_cfg->msix_config); +} + +static uint16_t +modern_get_queue_num(struct virtio_hw *hw, uint16_t queue_id) +{ + io_write16(queue_id, &hw->common_cfg->queue_select); + return io_read16(&hw->common_cfg->queue_size); +} + +static void +modern_setup_queue(struct virtio_hw *hw, struct virtqueue *vq) +{ + uint64_t desc_addr, avail_addr, used_addr; + uint16_t notify_off; + + desc_addr = vq->mz->phys_addr; + avail_addr = desc_addr + vq->vq_nentries * sizeof(struct vring_desc); + used_addr = RTE_ALIGN_CEIL(avail_addr + offsetof(struct vring_avail, + ring[vq->vq_nentries]), + VIRTIO_PCI_VRING_ALIGN); + + io_write16(vq->vq_queue_index, &hw->common_cfg->queue_select); + + io_write64_twopart(desc_addr, &hw->common_cfg->queue_desc_lo, + &hw->common_cfg->queue_desc_hi); + io_write64_twopart(avail_addr, &hw->common_cfg->queue_avail_lo, + &hw->common_cfg->queue_avail_hi); + io_write64_twopart(used_addr, &hw->common_cfg->queue_used_lo, + &hw->common_cfg->queue_used_hi); + + notify_off = io_read16(&hw->common_cfg->queue_notify_off); + vq->notify_addr = (void *)((uint8_t *)hw->notify_base + + notify_off * hw->notify_off_multiplier); + + io_write16(1, &hw->common_cfg->queue_enable); + + PMD_INIT_LOG(DEBUG, "queue %u addresses:", vq->vq_queue_index); + PMD_INIT_LOG(DEBUG, "\t desc_addr: %" PRIx64, desc_addr); + PMD_INIT_LOG(DEBUG, "\t aval_addr: %" PRIx64, avail_addr); + PMD_INIT_LOG(DEBUG, "\t used_addr: %" PRIx64, used_addr); + PMD_INIT_LOG(DEBUG, "\t notify addr: %p (notify offset: %u)", + vq->notify_addr, notify_off); +} + +static void +modern_del_queue(struct virtio_hw *hw, struct virtqueue *vq) +{ + io_write16(vq->vq_queue_index, &hw->common_cfg->queue_select); + + io_write64_twopart(0, &hw->common_cfg->queue_desc_lo, + &hw->common_cfg->queue_desc_hi); + io_write64_twopart(0, &hw->common_cfg->queue_avail_lo, + &hw->common_cfg->queue_avail_hi); + io_write64_twopart(0, &hw->common_cfg->queue_used_lo, + &hw->common_cfg->queue_used_hi); + + io_write16(0, &hw->common_cfg->queue_enable); +} + +static void +modern_notify_queue(struct virtio_hw *hw __rte_unused, struct virtqueue *vq) +{ + io_write16(1, vq->notify_addr); +} + +static const struct virtio_pci_ops modern_ops = { + .read_dev_cfg = modern_read_dev_config, + .write_dev_cfg = modern_write_dev_config, + .reset = modern_reset, + .get_status = modern_get_status, + .set_status = modern_set_status, + .get_features = modern_get_features, + .set_features = modern_set_features, + .get_isr = modern_get_isr, + .set_config_irq = modern_set_config_irq, + .get_queue_num = modern_get_queue_num, + .setup_queue = modern_setup_queue, + .del_queue = modern_del_queue, + .notify_queue = modern_notify_queue, +}; + + void vtpci_read_dev_config(struct virtio_hw *hw, size_t offset, void *dst, int length) @@ -496,6 +715,12 @@ vtpci_set_status(struct virtio_hw *hw, uint8_t status) hw->vtpci_ops->set_status(hw, status); } +uint8_t +vtpci_get_status(struct virtio_hw *hw) +{ + return hw->vtpci_ops->get_status(hw); +} + uint8_t vtpci_isr(struct virtio_hw *hw) { @@ -510,15 +735,142 @@ vtpci_irq_config(struct virtio_hw *hw, uint16_t vec) return hw->vtpci_ops->set_config_irq(hw, vec); } +static void * +get_cfg_addr(struct rte_pci_device *dev, struct virtio_pci_cap *cap) +{ + uint8_t bar = cap->bar; + uint32_t length = cap->length; + uint32_t offset = cap->offset; + uint8_t *base; + + if (bar > 5) { + PMD_INIT_LOG(ERR, "invalid bar: %u", bar); + return NULL; + } + + if (offset + length < offset) { + PMD_INIT_LOG(ERR, "offset(%u) + length(%u) overflows", + offset, length); + return NULL; + } + + if (offset + length > dev->mem_resource[bar].len) { + PMD_INIT_LOG(ERR, + "invalid cap: overflows bar space: %u > %" PRIu64, + offset + length, dev->mem_resource[bar].len); + return NULL; + } + + base = dev->mem_resource[bar].addr; + if (base == NULL) { + PMD_INIT_LOG(ERR, "bar %u base addr is NULL", bar); + return NULL; + } + + return base + offset; +} + +static int +virtio_read_caps(struct rte_pci_device *dev, struct virtio_hw *hw) +{ + uint8_t pos; + struct virtio_pci_cap cap; + int ret; + + if (rte_eal_pci_map_device(dev) < 0) { + PMD_INIT_LOG(DEBUG, "failed to map pci device!"); + return -1; + } + + ret = rte_eal_pci_read_config(dev, &pos, 1, PCI_CAPABILITY_LIST); + if (ret < 0) { + PMD_INIT_LOG(DEBUG, "failed to read pci capability list"); + return -1; + } + + while (pos) { + ret = rte_eal_pci_read_config(dev, &cap, sizeof(cap), pos); + if (ret < 0) { + PMD_INIT_LOG(ERR, + "failed to read pci cap at pos: %x", pos); + break; + } + + if (cap.cap_vndr != PCI_CAP_ID_VNDR) { + PMD_INIT_LOG(DEBUG, + "[%2x] skipping non VNDR cap id: %02x", + pos, cap.cap_vndr); + goto next; + } + + PMD_INIT_LOG(DEBUG, + "[%2x] cfg type: %u, bar: %u, offset: %04x, len: %u", + pos, cap.cfg_type, cap.bar, cap.offset, cap.length); + + switch (cap.cfg_type) { + case VIRTIO_PCI_CAP_COMMON_CFG: + hw->common_cfg = get_cfg_addr(dev, &cap); + break; + case VIRTIO_PCI_CAP_NOTIFY_CFG: + rte_eal_pci_read_config(dev, &hw->notify_off_multiplier, + 4, pos + sizeof(cap)); + hw->notify_base = get_cfg_addr(dev, &cap); + break; + case VIRTIO_PCI_CAP_DEVICE_CFG: + hw->dev_cfg = get_cfg_addr(dev, &cap); + break; + case VIRTIO_PCI_CAP_ISR_CFG: + hw->isr = get_cfg_addr(dev, &cap); + break; + } + +next: + pos = cap.cap_next; + } + + if (hw->common_cfg == NULL || hw->notify_base == NULL || + hw->dev_cfg == NULL || hw->isr == NULL) { + PMD_INIT_LOG(INFO, "no modern virtio pci device found."); + return -1; + } + + PMD_INIT_LOG(INFO, "found modern virtio pci device."); + + PMD_INIT_LOG(DEBUG, "common cfg mapped at: %p", hw->common_cfg); + PMD_INIT_LOG(DEBUG, "device cfg mapped at: %p", hw->dev_cfg); + PMD_INIT_LOG(DEBUG, "isr cfg mapped at: %p", hw->isr); + PMD_INIT_LOG(DEBUG, "notify base: %p, notify off multiplier: %u", + hw->notify_base, hw->notify_off_multiplier); + + return 0; +} + int vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw) { - hw->vtpci_ops = &legacy_ops; + hw->dev = dev; + /* + * Try if we can succeed reading virtio pci caps, which exists + * only on modern pci device. If failed, we fallback to legacy + * virtio handling. + */ + if (virtio_read_caps(dev, hw) == 0) { + PMD_INIT_LOG(INFO, "modern virtio pci detected."); + hw->vtpci_ops = &modern_ops; + hw->modern = 1; + dev->driver->drv_flags |= RTE_PCI_DRV_INTR_LSC; + return 0; + } + + PMD_INIT_LOG(INFO, "trying with legacy virtio pci."); if (legacy_virtio_resource_init(dev) < 0) return -1; + + hw->vtpci_ops = &legacy_ops; hw->use_msix = legacy_virtio_has_msix(&dev->addr); hw->io_base = (uint32_t)(uintptr_t)dev->mem_resource[0].addr; + hw->modern = 0; return 0; } diff --git a/drivers/net/virtio/virtio_pci.h b/drivers/net/virtio/virtio_pci.h index d7bc6bb033..fcac660e91 100644 --- a/drivers/net/virtio/virtio_pci.h +++ b/drivers/net/virtio/virtio_pci.h @@ -93,6 +93,7 @@ struct virtqueue; #define VIRTIO_CONFIG_STATUS_ACK 0x01 #define VIRTIO_CONFIG_STATUS_DRIVER 0x02 #define VIRTIO_CONFIG_STATUS_DRIVER_OK 0x04 +#define VIRTIO_CONFIG_STATUS_FEATURES_OK 0x08 #define VIRTIO_CONFIG_STATUS_FAILED 0x80 /* @@ -141,6 +142,8 @@ struct virtqueue; /* We support indirect buffer descriptors */ #define VIRTIO_RING_F_INDIRECT_DESC 28 +#define VIRTIO_F_VERSION_1 32 + /* * Some VirtIO feature bits (currently bits 28 through 31) are * reserved for the transport being used (eg. virtio_ring), the @@ -163,6 +166,60 @@ struct virtqueue; */ #define VIRTIO_MAX_VIRTQUEUES 8 +/* Common configuration */ +#define VIRTIO_PCI_CAP_COMMON_CFG 1 +/* Notifications */ +#define VIRTIO_PCI_CAP_NOTIFY_CFG 2 +/* ISR Status */ +#define VIRTIO_PCI_CAP_ISR_CFG 3 +/* Device specific configuration */ +#define VIRTIO_PCI_CAP_DEVICE_CFG 4 +/* PCI configuration access */ +#define VIRTIO_PCI_CAP_PCI_CFG 5 + +/* This is the PCI capability header: */ +struct virtio_pci_cap { + uint8_t cap_vndr; /* Generic PCI field: PCI_CAP_ID_VNDR */ + uint8_t cap_next; /* Generic PCI field: next ptr. */ + uint8_t cap_len; /* Generic PCI field: capability length */ + uint8_t cfg_type; /* Identifies the structure. */ + uint8_t bar; /* Where to find it. */ + uint8_t padding[3]; /* Pad to full dword. */ + uint32_t offset; /* Offset within bar. */ + uint32_t length; /* Length of the structure, in bytes. */ +}; + +struct virtio_pci_notify_cap { + struct virtio_pci_cap cap; + uint32_t notify_off_multiplier; /* Multiplier for queue_notify_off. */ +}; + +/* Fields in VIRTIO_PCI_CAP_COMMON_CFG: */ +struct virtio_pci_common_cfg { + /* About the whole device. */ + uint32_t device_feature_select; /* read-write */ + uint32_t device_feature; /* read-only */ + uint32_t guest_feature_select; /* read-write */ + uint32_t guest_feature; /* read-write */ + uint16_t msix_config; /* read-write */ + uint16_t num_queues; /* read-only */ + uint8_t device_status; /* read-write */ + uint8_t config_generation; /* read-only */ + + /* About a specific virtqueue. */ + uint16_t queue_select; /* read-write */ + uint16_t queue_size; /* read-write, power of 2. */ + uint16_t queue_msix_vector; /* read-write */ + uint16_t queue_enable; /* read-write */ + uint16_t queue_notify_off; /* read-only */ + uint32_t queue_desc_lo; /* read-write */ + uint32_t queue_desc_hi; /* read-write */ + uint32_t queue_avail_lo; /* read-write */ + uint32_t queue_avail_hi; /* read-write */ + uint32_t queue_used_lo; /* read-write */ + uint32_t queue_used_hi; /* read-write */ +}; + struct virtio_hw; struct virtio_pci_ops { @@ -188,6 +245,8 @@ struct virtio_pci_ops { void (*notify_queue)(struct virtio_hw *hw, struct virtqueue *vq); }; +struct virtio_net_config; + struct virtio_hw { struct virtqueue *cvq; uint32_t io_base; @@ -198,7 +257,14 @@ struct virtio_hw { uint8_t vlan_strip; uint8_t use_msix; uint8_t started; + uint8_t modern; uint8_t mac_addr[ETHER_ADDR_LEN]; + uint32_t notify_off_multiplier; + uint8_t *isr; + uint16_t *notify_base; + struct rte_pci_device *dev; + struct virtio_pci_common_cfg *common_cfg; + struct virtio_net_config *dev_cfg; const struct virtio_pci_ops *vtpci_ops; }; @@ -284,6 +350,7 @@ void vtpci_reset(struct virtio_hw *); void vtpci_reinit_complete(struct virtio_hw *); +uint8_t vtpci_get_status(struct virtio_hw *); void vtpci_set_status(struct virtio_hw *, uint8_t); uint64_t vtpci_negotiate_features(struct virtio_hw *, uint64_t); diff --git a/drivers/net/virtio/virtqueue.h b/drivers/net/virtio/virtqueue.h index d7fb450562..99d4fa91e8 100644 --- a/drivers/net/virtio/virtqueue.h +++ b/drivers/net/virtio/virtqueue.h @@ -202,6 +202,8 @@ struct virtqueue { /* Size bins in array as RFC 2819, undersized [0], 64 [1], etc */ uint64_t size_bins[8]; + uint16_t *notify_addr; + struct vq_desc_extra { void *cookie; uint16_t ndescs;