diff options
Diffstat (limited to 'drivers')
152 files changed, 4933 insertions, 1518 deletions
diff --git a/drivers/base/property.c b/drivers/base/property.c index 851b1b6596a4..613ba820f545 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -16,6 +16,7 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_graph.h> +#include <linux/of_irq.h> #include <linux/property.h> #include <linux/etherdevice.h> #include <linux/phy.h> @@ -997,6 +998,32 @@ fwnode_get_next_child_node(const struct fwnode_handle *fwnode, EXPORT_SYMBOL_GPL(fwnode_get_next_child_node); /** + * fwnode_get_next_available_child_node - Return the next + * available child node handle for a node + * @fwnode: Firmware node to find the next child node for. + * @child: Handle to one of the node's child nodes or a %NULL handle. + */ +struct fwnode_handle * +fwnode_get_next_available_child_node(const struct fwnode_handle *fwnode, + struct fwnode_handle *child) +{ + struct fwnode_handle *next_child = child; + + if (!fwnode) + return NULL; + + do { + next_child = fwnode_get_next_child_node(fwnode, next_child); + + if (!next_child || fwnode_device_is_available(next_child)) + break; + } while (next_child); + + return next_child; +} +EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node); + +/** * device_get_next_child_node - Return the next child node handle for a device * @dev: Device to find the next child node for. * @child: Handle to one of the device's child nodes or a null handle. @@ -1126,21 +1153,21 @@ enum dev_dma_attr device_get_dma_attr(struct device *dev) EXPORT_SYMBOL_GPL(device_get_dma_attr); /** - * device_get_phy_mode - Get phy mode for given device - * @dev: Pointer to the given device + * fwnode_get_phy_mode - Get phy mode for given firmware node + * @fwnode: Pointer to the given node * * The function gets phy interface string from property 'phy-mode' or * 'phy-connection-type', and return its index in phy_modes table, or errno in * error case. */ -int device_get_phy_mode(struct device *dev) +int fwnode_get_phy_mode(struct fwnode_handle *fwnode) { const char *pm; int err, i; - err = device_property_read_string(dev, "phy-mode", &pm); + err = fwnode_property_read_string(fwnode, "phy-mode", &pm); if (err < 0) - err = device_property_read_string(dev, + err = fwnode_property_read_string(fwnode, "phy-connection-type", &pm); if (err < 0) return err; @@ -1151,13 +1178,27 @@ int device_get_phy_mode(struct device *dev) return -ENODEV; } +EXPORT_SYMBOL_GPL(fwnode_get_phy_mode); + +/** + * device_get_phy_mode - Get phy mode for given device + * @dev: Pointer to the given device + * + * The function gets phy interface string from property 'phy-mode' or + * 'phy-connection-type', and return its index in phy_modes table, or errno in + * error case. + */ +int device_get_phy_mode(struct device *dev) +{ + return fwnode_get_phy_mode(dev_fwnode(dev)); +} EXPORT_SYMBOL_GPL(device_get_phy_mode); -static void *device_get_mac_addr(struct device *dev, +static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode, const char *name, char *addr, int alen) { - int ret = device_property_read_u8_array(dev, name, addr, alen); + int ret = fwnode_property_read_u8_array(fwnode, name, addr, alen); if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr)) return addr; @@ -1165,8 +1206,8 @@ static void *device_get_mac_addr(struct device *dev, } /** - * device_get_mac_address - Get the MAC for a given device - * @dev: Pointer to the device + * fwnode_get_mac_address - Get the MAC from the firmware node + * @fwnode: Pointer to the firmware node * @addr: Address of buffer to store the MAC in * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN * @@ -1187,23 +1228,60 @@ static void *device_get_mac_addr(struct device *dev, * In this case, the real MAC is in 'local-mac-address', and 'mac-address' * exists but is all zeros. */ -void *device_get_mac_address(struct device *dev, char *addr, int alen) +void *fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen) { char *res; - res = device_get_mac_addr(dev, "mac-address", addr, alen); + res = fwnode_get_mac_addr(fwnode, "mac-address", addr, alen); if (res) return res; - res = device_get_mac_addr(dev, "local-mac-address", addr, alen); + res = fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen); if (res) return res; - return device_get_mac_addr(dev, "address", addr, alen); + return fwnode_get_mac_addr(fwnode, "address", addr, alen); +} +EXPORT_SYMBOL(fwnode_get_mac_address); + +/** + * device_get_mac_address - Get the MAC for a given device + * @dev: Pointer to the device + * @addr: Address of buffer to store the MAC in + * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN + */ +void *device_get_mac_address(struct device *dev, char *addr, int alen) +{ + return fwnode_get_mac_address(dev_fwnode(dev), addr, alen); } EXPORT_SYMBOL(device_get_mac_address); /** + * fwnode_irq_get - Get IRQ directly from a fwnode + * @fwnode: Pointer to the firmware node + * @index: Zero-based index of the IRQ + * + * Returns Linux IRQ number on success. Other values are determined + * accordingly to acpi_/of_ irq_get() operation. + */ +int fwnode_irq_get(struct fwnode_handle *fwnode, unsigned int index) +{ + struct device_node *of_node = to_of_node(fwnode); + struct resource res; + int ret; + + if (IS_ENABLED(CONFIG_OF) && of_node) + return of_irq_get(of_node, index); + + ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); + if (ret) + return ret; + + return res.start; +} +EXPORT_SYMBOL(fwnode_irq_get); + +/** * device_graph_get_next_endpoint - Get next endpoint firmware node * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index afa4cb3b16e3..6659f113042c 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -323,6 +323,7 @@ static const struct { { 0x410e, "BCM43341B0" }, /* 002.001.014 */ { 0x4406, "BCM4324B3" }, /* 002.004.006 */ { 0x610c, "BCM4354" }, /* 003.001.012 */ + { 0x2122, "BCM4343A0" }, /* 001.001.034 */ { 0x2209, "BCM43430A1" }, /* 001.002.009 */ { 0x6119, "BCM4345C0" }, /* 003.001.025 */ { 0x230f, "BCM4356A2" }, /* 001.003.015 */ diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 07f00e422e85..5270d5513201 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -24,6 +24,7 @@ #include <linux/module.h> #include <linux/firmware.h> #include <linux/regmap.h> +#include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -569,6 +570,160 @@ struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read, } EXPORT_SYMBOL_GPL(btintel_regmap_init); +int btintel_send_intel_reset(struct hci_dev *hdev, u32 boot_param) +{ + struct intel_reset params = { 0x00, 0x01, 0x00, 0x01, 0x00000000 }; + struct sk_buff *skb; + + params.boot_param = cpu_to_le32(boot_param); + + skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(params), ¶ms, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Failed to send Intel Reset command"); + return PTR_ERR(skb); + } + + kfree_skb(skb); + + return 0; +} +EXPORT_SYMBOL_GPL(btintel_send_intel_reset); + +int btintel_read_boot_params(struct hci_dev *hdev, + struct intel_boot_params *params) +{ + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Reading Intel boot parameters failed (%ld)", + PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != sizeof(*params)) { + bt_dev_err(hdev, "Intel boot parameters size mismatch"); + kfree_skb(skb); + return -EILSEQ; + } + + memcpy(params, skb->data, sizeof(*params)); + + kfree_skb(skb); + + if (params->status) { + bt_dev_err(hdev, "Intel boot parameters command failed (%02x)", + params->status); + return -bt_to_errno(params->status); + } + + bt_dev_info(hdev, "Device revision is %u", + le16_to_cpu(params->dev_revid)); + + bt_dev_info(hdev, "Secure boot is %s", + params->secure_boot ? "enabled" : "disabled"); + + bt_dev_info(hdev, "OTP lock is %s", + params->otp_lock ? "enabled" : "disabled"); + + bt_dev_info(hdev, "API lock is %s", + params->api_lock ? "enabled" : "disabled"); + + bt_dev_info(hdev, "Debug lock is %s", + params->debug_lock ? "enabled" : "disabled"); + + bt_dev_info(hdev, "Minimum firmware build %u week %u %u", + params->min_fw_build_nn, params->min_fw_build_cw, + 2000 + params->min_fw_build_yy); + + return 0; +} +EXPORT_SYMBOL_GPL(btintel_read_boot_params); + +int btintel_download_firmware(struct hci_dev *hdev, const struct firmware *fw, + u32 *boot_param) +{ + int err; + const u8 *fw_ptr; + u32 frag_len; + + /* Start the firmware download transaction with the Init fragment + * represented by the 128 bytes of CSS header. + */ + err = btintel_secure_send(hdev, 0x00, 128, fw->data); + if (err < 0) { + bt_dev_err(hdev, "Failed to send firmware header (%d)", err); + goto done; + } + + /* Send the 256 bytes of public key information from the firmware + * as the PKey fragment. + */ + err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128); + if (err < 0) { + bt_dev_err(hdev, "Failed to send firmware pkey (%d)", err); + goto done; + } + + /* Send the 256 bytes of signature information from the firmware + * as the Sign fragment. + */ + err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388); + if (err < 0) { + bt_dev_err(hdev, "Failed to send firmware signature (%d)", err); + goto done; + } + + fw_ptr = fw->data + 644; + frag_len = 0; + + while (fw_ptr - fw->data < fw->size) { + struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len); + + /* Each SKU has a different reset parameter to use in the + * HCI_Intel_Reset command and it is embedded in the firmware + * data. So, instead of using static value per SKU, check + * the firmware data and save it for later use. + */ + if (le16_to_cpu(cmd->opcode) == 0xfc0e) { + /* The boot parameter is the first 32-bit value + * and rest of 3 octets are reserved. + */ + *boot_param = get_unaligned_le32(fw_ptr + sizeof(*cmd)); + + bt_dev_dbg(hdev, "boot_param=0x%x", *boot_param); + } + + frag_len += sizeof(*cmd) + cmd->plen; + + /* The parameter length of the secure send command requires + * a 4 byte alignment. It happens so that the firmware file + * contains proper Intel_NOP commands to align the fragments + * as needed. + * + * Send set of commands with 4 byte alignment from the + * firmware data buffer as a single Data fragement. + */ + if (!(frag_len % 4)) { + err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr); + if (err < 0) { + bt_dev_err(hdev, + "Failed to send firmware data (%d)", + err); + goto done; + } + + fw_ptr += frag_len; + frag_len = 0; + } + } + +done: + return err; +} +EXPORT_SYMBOL_GPL(btintel_download_firmware); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth support for Intel devices ver " VERSION); MODULE_VERSION(VERSION); diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index 1e8955aaafed..41c642cc523f 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -69,6 +69,14 @@ struct intel_secure_send_result { __u8 status; } __packed; +struct intel_reset { + __u8 reset_type; + __u8 patch_enable; + __u8 ddc_reload; + __u8 boot_option; + __le32 boot_param; +} __packed; + #if IS_ENABLED(CONFIG_BT_INTEL) int btintel_check_bdaddr(struct hci_dev *hdev); @@ -89,7 +97,11 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver); struct regmap *btintel_regmap_init(struct hci_dev *hdev, u16 opcode_read, u16 opcode_write); - +int btintel_send_intel_reset(struct hci_dev *hdev, u32 boot_param); +int btintel_read_boot_params(struct hci_dev *hdev, + struct intel_boot_params *params); +int btintel_download_firmware(struct hci_dev *dev, const struct firmware *fw, + u32 *boot_param); #else static inline int btintel_check_bdaddr(struct hci_dev *hdev) @@ -165,4 +177,23 @@ static inline struct regmap *btintel_regmap_init(struct hci_dev *hdev, { return ERR_PTR(-EINVAL); } + +static inline int btintel_send_intel_reset(struct hci_dev *hdev, + u32 reset_param) +{ + return -EOPNOTSUPP; +} + +static inline int btintel_read_boot_params(struct hci_dev *hdev, + struct intel_boot_params *params) +{ + return -EOPNOTSUPP; +} + +static inline int btintel_download_firmware(struct hci_dev *dev, + const struct firmware *fw, + u32 *boot_param) +{ + return -EOPNOTSUPP; +} #endif diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 29977ebfd031..2a55380ad730 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2009,15 +2009,11 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb) static int btusb_setup_intel_new(struct hci_dev *hdev) { - static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01, - 0x00, 0x08, 0x04, 0x00 }; struct btusb_data *data = hci_get_drvdata(hdev); - struct sk_buff *skb; struct intel_version ver; - struct intel_boot_params *params; + struct intel_boot_params params; const struct firmware *fw; - const u8 *fw_ptr; - u32 frag_len; + u32 boot_param; char fwname[64]; ktime_t calltime, delta, rettime; unsigned long long duration; @@ -2025,6 +2021,12 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) BT_DBG("%s", hdev->name); + /* Set the default boot parameter to 0x0 and it is updated to + * SKU specific boot parameter after reading Intel_Write_Boot_Params + * command while downloading the firmware. + */ + boot_param = 0x00000000; + calltime = ktime_get(); /* Read the Intel version information to determine if the device @@ -2095,55 +2097,24 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) /* Read the secure boot parameters to identify the operating * details of the bootloader. */ - skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s: Reading Intel boot parameters failed (%ld)", - hdev->name, PTR_ERR(skb)); - return PTR_ERR(skb); - } - - if (skb->len != sizeof(*params)) { - BT_ERR("%s: Intel boot parameters size mismatch", hdev->name); - kfree_skb(skb); - return -EILSEQ; - } - - params = (struct intel_boot_params *)skb->data; - - bt_dev_info(hdev, "Device revision is %u", - le16_to_cpu(params->dev_revid)); - - bt_dev_info(hdev, "Secure boot is %s", - params->secure_boot ? "enabled" : "disabled"); - - bt_dev_info(hdev, "OTP lock is %s", - params->otp_lock ? "enabled" : "disabled"); - - bt_dev_info(hdev, "API lock is %s", - params->api_lock ? "enabled" : "disabled"); - - bt_dev_info(hdev, "Debug lock is %s", - params->debug_lock ? "enabled" : "disabled"); - - bt_dev_info(hdev, "Minimum firmware build %u week %u %u", - params->min_fw_build_nn, params->min_fw_build_cw, - 2000 + params->min_fw_build_yy); + err = btintel_read_boot_params(hdev, ¶ms); + if (err) + return err; /* It is required that every single firmware fragment is acknowledged * with a command complete event. If the boot parameters indicate * that this bootloader does not send them, then abort the setup. */ - if (params->limited_cce != 0x00) { + if (params.limited_cce != 0x00) { BT_ERR("%s: Unsupported Intel firmware loading method (%u)", - hdev->name, params->limited_cce); - kfree_skb(skb); + hdev->name, params.limited_cce); return -EINVAL; } /* If the OTP has no valid Bluetooth device address, then there will * also be no valid address for the operational firmware. */ - if (!bacmp(¶ms->otp_bdaddr, BDADDR_ANY)) { + if (!bacmp(¶ms.otp_bdaddr, BDADDR_ANY)) { bt_dev_info(hdev, "No device address configured"); set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); } @@ -2174,7 +2145,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) case 0x0c: /* WsP */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi", le16_to_cpu(ver.hw_variant), - le16_to_cpu(params->dev_revid)); + le16_to_cpu(params.dev_revid)); break; case 0x11: /* JfP */ case 0x12: /* ThP */ @@ -2192,7 +2163,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) if (err < 0) { BT_ERR("%s: Failed to load Intel firmware file (%d)", hdev->name, err); - kfree_skb(skb); return err; } @@ -2206,7 +2176,7 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) case 0x0c: /* WsP */ snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc", le16_to_cpu(ver.hw_variant), - le16_to_cpu(params->dev_revid)); + le16_to_cpu(params.dev_revid)); break; case 0x11: /* JfP */ case 0x12: /* ThP */ @@ -2220,8 +2190,6 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) return -EINVAL; } - kfree_skb(skb); - if (fw->size < 644) { BT_ERR("%s: Invalid size of firmware file (%zu)", hdev->name, fw->size); @@ -2231,64 +2199,10 @@ static int btusb_setup_intel_new(struct hci_dev *hdev) set_bit(BTUSB_DOWNLOADING, &data->flags); - /* Start the firmware download transaction with the Init fragment - * represented by the 128 bytes of CSS header. - */ - err = btintel_secure_send(hdev, 0x00, 128, fw->data); - if (err < 0) { - BT_ERR("%s: Failed to send firmware header (%d)", - hdev->name, err); - goto done; - } - - /* Send the 256 bytes of public key information from the firmware - * as the PKey fragment. - */ - err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128); - if (err < 0) { - BT_ERR("%s: Failed to send firmware public key (%d)", - hdev->name, err); - goto done; - } - - /* Send the 256 bytes of signature information from the firmware - * as the Sign fragment. - */ - err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388); - if (err < 0) { - BT_ERR("%s: Failed to send firmware signature (%d)", - hdev->name, err); + /* Start firmware downloading and get boot parameter */ + err = btintel_download_firmware(hdev, fw, &boot_param); + if (err < 0) goto done; - } - - fw_ptr = fw->data + 644; - frag_len = 0; - - while (fw_ptr - fw->data < fw->size) { - struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len); - - frag_len += sizeof(*cmd) + cmd->plen; - - /* The parameter length of the secure send command requires - * a 4 byte alignment. It happens so that the firmware file - * contains proper Intel_NOP commands to align the fragments - * as needed. - * - * Send set of commands with 4 byte alignment from the - * firmware data buffer as a single Data fragement. - */ - if (!(frag_len % 4)) { - err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr); - if (err < 0) { - BT_ERR("%s: Failed to send firmware data (%d)", - hdev->name, err); - goto done; - } - - fw_ptr += frag_len; - frag_len = 0; - } - } set_bit(BTUSB_FIRMWARE_LOADED, &data->flags); @@ -2341,12 +2255,9 @@ done: set_bit(BTUSB_BOOTING, &data->flags); - skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param, - HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - kfree_skb(skb); + err = btintel_send_intel_reset(hdev, boot_param); + if (err) + return err; /* The bootloader will not indicate when the device is ready. This * is done by the operational firmware sending bootup notification. diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 64800cd2796c..0438a64b8185 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -412,8 +412,11 @@ out: return 0; err_unset_hu: + if (hu->serdev) + serdev_device_close(hu->serdev); #ifdef CONFIG_PM - bcm->dev->hu = NULL; + else + bcm->dev->hu = NULL; #endif err_free: mutex_unlock(&bcm_device_lock); diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index aad07e40ea4f..7c166e3b308b 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -540,18 +540,15 @@ static int intel_set_baudrate(struct hci_uart *hu, unsigned int speed) static int intel_setup(struct hci_uart *hu) { - static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01, - 0x00, 0x08, 0x04, 0x00 }; struct intel_data *intel = hu->priv; struct hci_dev *hdev = hu->hdev; struct sk_buff *skb; struct intel_version ver; - struct intel_boot_params *params; + struct intel_boot_params params; struct list_head *p; const struct firmware *fw; - const u8 *fw_ptr; char fwname[64]; - u32 frag_len; + u32 boot_param; ktime_t calltime, delta, rettime; unsigned long long duration; unsigned int init_speed, oper_speed; @@ -563,6 +560,12 @@ static int intel_setup(struct hci_uart *hu) hu->hdev->set_diag = btintel_set_diag; hu->hdev->set_bdaddr = btintel_set_bdaddr; + /* Set the default boot parameter to 0x0 and it is updated to + * SKU specific boot parameter after reading Intel_Write_Boot_Params + * command while downloading the firmware. + */ + boot_param = 0x00000000; + calltime = ktime_get(); if (hu->init_speed) @@ -656,85 +659,95 @@ static int intel_setup(struct hci_uart *hu) /* Read the secure boot parameters to identify the operating * details of the bootloader. */ - skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_CMD_TIMEOUT); - if (IS_ERR(skb)) { - bt_dev_err(hdev, "Reading Intel boot parameters failed (%ld)", - PTR_ERR(skb)); - return PTR_ERR(skb); - } - - if (skb->len != sizeof(*params)) { - bt_dev_err(hdev, "Intel boot parameters size mismatch"); - kfree_skb(skb); - return -EILSEQ; - } - - params = (struct intel_boot_params *)skb->data; - if (params->status) { - bt_dev_err(hdev, "Intel boot parameters command failure (%02x)", - params->status); - err = -bt_to_errno(params->status); - kfree_skb(skb); + err = btintel_read_boot_params(hdev, ¶ms); + if (err) return err; - } - - bt_dev_info(hdev, "Device revision is %u", - le16_to_cpu(params->dev_revid)); - - bt_dev_info(hdev, "Secure boot is %s", - params->secure_boot ? "enabled" : "disabled"); - - bt_dev_info(hdev, "Minimum firmware build %u week %u %u", - params->min_fw_build_nn, params->min_fw_build_cw, - 2000 + params->min_fw_build_yy); /* It is required that every single firmware fragment is acknowledged * with a command complete event. If the boot parameters indicate * that this bootloader does not send them, then abort the setup. */ - if (params->limited_cce != 0x00) { + if (params.limited_cce != 0x00) { bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)", - params->limited_cce); - kfree_skb(skb); + params.limited_cce); return -EINVAL; } /* If the OTP has no valid Bluetooth device address, then there will * also be no valid address for the operational firmware. */ - if (!bacmp(¶ms->otp_bdaddr, BDADDR_ANY)) { + if (!bacmp(¶ms.otp_bdaddr, BDADDR_ANY)) { bt_dev_info(hdev, "No device address configured"); set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); } /* With this Intel bootloader only the hardware variant and device - * revision information are used to select the right firmware. + * revision information are used to select the right firmware for SfP + * and WsP. * * The firmware filename is ibt-<hw_variant>-<dev_revid>.sfi. * * Currently the supported hardware variants are: * 11 (0x0b) for iBT 3.0 (LnP/SfP) + * 12 (0x0c) for iBT 3.5 (WsP) + * + * For ThP/JfP and for future SKU's, the FW name varies based on HW + * variant, HW revision and FW revision, as these are dependent on CNVi + * and RF Combination. + * + * 18 (0x12) for iBT3.5 (ThP/JfP) + * + * The firmware file name for these will be + * ibt-<hw_variant>-<hw_revision>-<fw_revision>.sfi. + * */ - snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi", - le16_to_cpu(ver.hw_variant), - le16_to_cpu(params->dev_revid)); + switch (ver.hw_variant) { + case 0x0b: /* SfP */ + case 0x0c: /* WsP */ + snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.sfi", + le16_to_cpu(ver.hw_variant), + le16_to_cpu(params.dev_revid)); + break; + case 0x12: /* ThP */ + snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.sfi", + le16_to_cpu(ver.hw_variant), + le16_to_cpu(ver.hw_revision), + le16_to_cpu(ver.fw_revision)); + break; + default: + bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)", + ver.hw_variant); + return -EINVAL; + } err = request_firmware(&fw, fwname, &hdev->dev); if (err < 0) { bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", err); - kfree_skb(skb); return err; } bt_dev_info(hdev, "Found device firmware: %s", fwname); /* Save the DDC file name for later */ - snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc", - le16_to_cpu(ver.hw_variant), - le16_to_cpu(params->dev_revid)); - - kfree_skb(skb); + switch (ver.hw_variant) { + case 0x0b: /* SfP */ + case 0x0c: /* WsP */ + snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u.ddc", + le16_to_cpu(ver.hw_variant), + le16_to_cpu(params.dev_revid)); + break; + case 0x12: /* ThP */ + snprintf(fwname, sizeof(fwname), "intel/ibt-%u-%u-%u.ddc", + le16_to_cpu(ver.hw_variant), + le16_to_cpu(ver.hw_revision), + le16_to_cpu(ver.fw_revision)); + break; + default: + bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)", + ver.hw_variant); + return -EINVAL; + } if (fw->size < 644) { bt_dev_err(hdev, "Invalid size of firmware file (%zu)", @@ -745,70 +758,10 @@ static int intel_setup(struct hci_uart *hu) set_bit(STATE_DOWNLOADING, &intel->flags); - /* Start the firmware download transaction with the Init fragment - * represented by the 128 bytes of CSS header. - */ - err = btintel_secure_send(hdev, 0x00, 128, fw->data); - if (err < 0) { - bt_dev_err(hdev, "Failed to send firmware header (%d)", err); - goto done; - } - - /* Send the 256 bytes of public key information from the firmware - * as the PKey fragment. - */ - err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128); - if (err < 0) { - bt_dev_err(hdev, "Failed to send firmware public key (%d)", - err); - goto done; - } - - /* Send the 256 bytes of signature information from the firmware - * as the Sign fragment. - */ - err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388); - if (err < 0) { - bt_dev_err(hdev, "Failed to send firmware signature (%d)", - err); + /* Start firmware downloading and get boot parameter */ + err = btintel_download_firmware(hdev, fw, &boot_param); + if (err < 0) goto done; - } - - fw_ptr = fw->data + 644; - frag_len = 0; - - while (fw_ptr - fw->data < fw->size) { - struct hci_command_hdr *cmd = (void *)(fw_ptr + frag_len); - - frag_len += sizeof(*cmd) + cmd->plen; - - bt_dev_dbg(hdev, "Patching %td/%zu", (fw_ptr - fw->data), - fw->size); - - /* The parameter length of the secure send command requires - * a 4 byte alignment. It happens so that the firmware file - * contains proper Intel_NOP commands to align the fragments - * as needed. - * - * Send set of commands with 4 byte alignment from the - * firmware data buffer as a single Data fragement. - */ - if (frag_len % 4) - continue; - - /* Send each command from the firmware data buffer as - * a single Data fragment. - */ - err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr); - if (err < 0) { - bt_dev_err(hdev, "Failed to send firmware data (%d)", - err); - goto done; - } - - fw_ptr += frag_len; - frag_len = 0; - } set_bit(STATE_FIRMWARE_LOADED, &intel->flags); @@ -869,12 +822,9 @@ done: set_bit(STATE_BOOTING, &intel->flags); - skb = __hci_cmd_sync(hdev, 0xfc01, sizeof(reset_param), reset_param, - HCI_CMD_TIMEOUT); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - kfree_skb(skb); + err = btintel_send_intel_reset(hdev, boot_param); + if (err) + return err; /* The bootloader will not indicate when the device is ready. This * is done by the operational firmware sending bootup notification. diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9fc12f556534..554d60394c06 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1954,10 +1954,15 @@ static int crypt_setkey(struct crypt_config *cc) /* Ignore extra keys (which are used for IV etc) */ subkey_size = crypt_subkey_size(cc); - if (crypt_integrity_hmac(cc)) + if (crypt_integrity_hmac(cc)) { + if (subkey_size < cc->key_mac_size) + return -EINVAL; + crypt_copy_authenckey(cc->authenc_key, cc->key, subkey_size - cc->key_mac_size, cc->key_mac_size); + } + for (i = 0; i < cc->tfms_count; i++) { if (crypt_integrity_hmac(cc)) r = crypto_aead_setkey(cc->cipher_tfm.tfms_aead[i], @@ -2053,9 +2058,6 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string ret = crypt_setkey(cc); - /* wipe the kernel key payload copy in each case */ - memset(cc->key, 0, cc->key_size * sizeof(u8)); - if (!ret) { set_bit(DM_CRYPT_KEY_VALID, &cc->flags); kzfree(cc->key_string); @@ -2523,6 +2525,10 @@ static int crypt_ctr_cipher(struct dm_target *ti, char *cipher_in, char *key) } } + /* wipe the kernel key payload copy */ + if (cc->key_string) + memset(cc->key, 0, cc->key_size * sizeof(u8)); + return ret; } @@ -2740,6 +2746,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) cc->tag_pool_max_sectors * cc->on_disk_tag_size); if (!cc->tag_pool) { ti->error = "Cannot allocate integrity tags mempool"; + ret = -ENOMEM; goto bad; } @@ -2961,6 +2968,9 @@ static int crypt_message(struct dm_target *ti, unsigned argc, char **argv) return ret; if (cc->iv_gen_ops && cc->iv_gen_ops->init) ret = cc->iv_gen_ops->init(cc); + /* wipe the kernel key payload copy */ + if (cc->key_string) + memset(cc->key, 0, cc->key_size * sizeof(u8)); return ret; } if (argc == 2 && !strcasecmp(argv[1], "wipe")) { @@ -3007,7 +3017,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type crypt_target = { .name = "crypt", - .version = {1, 18, 0}, + .version = {1, 18, 1}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 05c7bfd0c9d9..46d7c8749222 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2559,7 +2559,8 @@ static int create_journal(struct dm_integrity_c *ic, char **error) int r = 0; unsigned i; __u64 journal_pages, journal_desc_size, journal_tree_size; - unsigned char *crypt_data = NULL; + unsigned char *crypt_data = NULL, *crypt_iv = NULL; + struct skcipher_request *req = NULL; ic->commit_ids[0] = cpu_to_le64(0x1111111111111111ULL); ic->commit_ids[1] = cpu_to_le64(0x2222222222222222ULL); @@ -2617,9 +2618,20 @@ static int create_journal(struct dm_integrity_c *ic, char **error) if (blocksize == 1) { struct scatterlist *sg; - SKCIPHER_REQUEST_ON_STACK(req, ic->journal_crypt); - unsigned char iv[ivsize]; - skcipher_request_set_tfm(req, ic->journal_crypt); + + req = skcipher_request_alloc(ic->journal_crypt, GFP_KERNEL); + if (!req) { + *error = "Could not allocate crypt request"; + r = -ENOMEM; + goto bad; + } + + crypt_iv = kmalloc(ivsize, GFP_KERNEL); + if (!crypt_iv) { + *error = "Could not allocate iv"; + r = -ENOMEM; + goto bad; + } ic->journal_xor = dm_integrity_alloc_page_list(ic); if (!ic->journal_xor) { @@ -2641,9 +2653,9 @@ static int create_journal(struct dm_integrity_c *ic, char **error) sg_set_buf(&sg[i], va, PAGE_SIZE); } sg_set_buf(&sg[i], &ic->commit_ids, sizeof ic->commit_ids); - memset(iv, 0x00, ivsize); + memset(crypt_iv, 0x00, ivsize); - skcipher_request_set_crypt(req, sg, sg, PAGE_SIZE * ic->journal_pages + sizeof ic->commit_ids, iv); + skcipher_request_set_crypt(req, sg, sg, PAGE_SIZE * ic->journal_pages + sizeof ic->commit_ids, crypt_iv); init_completion(&comp.comp); comp.in_flight = (atomic_t)ATOMIC_INIT(1); if (do_crypt(true, req, &comp)) @@ -2659,10 +2671,22 @@ static int create_journal(struct dm_integrity_c *ic, char **error) crypto_free_skcipher(ic->journal_crypt); ic->journal_crypt = NULL; } else { - SKCIPHER_REQUEST_ON_STACK(req, ic->journal_crypt); - unsigned char iv[ivsize]; unsigned crypt_len = roundup(ivsize, blocksize); + req = skcipher_request_alloc(ic->journal_crypt, GFP_KERNEL); + if (!req) { + *error = "Could not allocate crypt request"; + r = -ENOMEM; + goto bad; + } + + crypt_iv = kmalloc(ivsize, GFP_KERNEL); + if (!crypt_iv) { + *error = "Could not allocate iv"; + r = -ENOMEM; + goto bad; + } + crypt_data = kmalloc(crypt_len, GFP_KERNEL); if (!crypt_data) { *error = "Unable to allocate crypt data"; @@ -2670,8 +2694,6 @@ static int create_journal(struct dm_integrity_c *ic, char **error) goto bad; } - skcipher_request_set_tfm(req, ic->journal_crypt); - ic->journal_scatterlist = dm_integrity_alloc_journal_scatterlist(ic, ic->journal); if (!ic->journal_scatterlist) { *error = "Unable to allocate sg list"; @@ -2695,12 +2717,12 @@ static int create_journal(struct dm_integrity_c *ic, char **error) struct skcipher_request *section_req; __u32 section_le = cpu_to_le32(i); - memset(iv, 0x00, ivsize); + memset(crypt_iv, 0x00, ivsize); memset(crypt_data, 0x00, crypt_len); memcpy(crypt_data, §ion_le, min((size_t)crypt_len, sizeof(section_le))); sg_init_one(&sg, crypt_data, crypt_len); - skcipher_request_set_crypt(req, &sg, &sg, crypt_len, iv); + skcipher_request_set_crypt(req, &sg, &sg, crypt_len, crypt_iv); init_completion(&comp.comp); comp.in_flight = (atomic_t)ATOMIC_INIT(1); if (do_crypt(true, req, &comp)) @@ -2758,6 +2780,9 @@ retest_commit_id: } bad: kfree(crypt_data); + kfree(crypt_iv); + skcipher_request_free(req); + return r; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index d31d18d9727c..36ef284ad086 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -80,10 +80,14 @@ #define SECTOR_TO_BLOCK_SHIFT 3 /* + * For btree insert: * 3 for btree insert + * 2 for btree lookup used within space map + * For btree remove: + * 2 for shadow spine + + * 4 for rebalance 3 child node */ -#define THIN_MAX_CONCURRENT_LOCKS 5 +#define THIN_MAX_CONCURRENT_LOCKS 6 /* This should be plenty */ #define SPACE_MAP_ROOT_SIZE 128 diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index f21ce6a3d4cf..58b319757b1e 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -683,23 +683,8 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) pn->keys[1] = rn->keys[0]; memcpy_disk(value_ptr(pn, 1), &val, sizeof(__le64)); - /* - * rejig the spine. This is ugly, since it knows too - * much about the spine - */ - if (s->nodes[0] != new_parent) { - unlock_block(s->info, s->nodes[0]); - s->nodes[0] = new_parent; - } - if (key < le64_to_cpu(rn->keys[0])) { - unlock_block(s->info, right); - s->nodes[1] = left; - } else { - unlock_block(s->info, left); - s->nodes[1] = right; - } - s->count = 2; - + unlock_block(s->info, left); + unlock_block(s->info, right); return 0; } diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c index b8029ea03307..433a14b9f731 100644 --- a/drivers/net/caif/caif_hsi.c +++ b/drivers/net/caif/caif_hsi.c @@ -264,7 +264,6 @@ static int cfhsi_tx_frm(struct cfhsi_desc *desc, struct cfhsi *cfhsi) } /* Create payload CAIF frames. */ - pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ; while (nfrms < CFHSI_MAX_PKTS) { struct caif_payload_info *info; int hpad; diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index cc94604b23e0..b1779566c5bb 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(can_change_state); * Local echo of CAN messages * * CAN network devices *should* support a local echo functionality - * (see Documentation/networking/can.txt). To test the handling of CAN + * (see Documentation/networking/can.rst). To test the handling of CAN * interfaces that do not support the local echo both driver types are * implemented. In the case that the driver does not support the echo * the IFF_ECHO remains clear in dev->flags. This causes the PF_CAN core diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index a8cb33264ff1..c2b04f505e16 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -61,7 +61,7 @@ MODULE_ALIAS_RTNL_LINK(DRV_NAME); /* * CAN test feature: * Enable the echo on driver level for testing the CAN core echo modes. - * See Documentation/networking/can.txt for details. + * See Documentation/networking/can.rst for details. */ static bool echo; /* echo testing. Default: 0 (Off) */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index f5dd5f75a40f..22889fc158f2 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -47,7 +47,7 @@ static const struct pci_device_id aq_pci_tbl[] = { {} }; -const struct aq_board_revision_s hw_atl_boards[] = { +static const struct aq_board_revision_s hw_atl_boards[] = { { AQ_DEVICE_ID_0001, AQ_HWREV_1, &hw_atl_ops_a0, &hw_atl_a0_caps_aqc107, }, { AQ_DEVICE_ID_D100, AQ_HWREV_1, &hw_atl_ops_a0, &hw_atl_a0_caps_aqc100, }, { AQ_DEVICE_ID_D107, AQ_HWREV_1, &hw_atl_ops_a0, &hw_atl_a0_caps_aqc107, }, @@ -210,8 +210,10 @@ static int aq_pci_probe(struct pci_dev *pdev, goto err_pci_func; ndev = aq_ndev_alloc(); - if (!ndev) + if (!ndev) { + err = -ENOMEM; goto err_ndev; + } self = netdev_priv(ndev); self->pdev = pdev; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 7919f6112ecf..5e34b34f7740 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -5818,8 +5818,8 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode) struct l2_fhdr *rx_hdr; int ret = -ENODEV; struct bnx2_napi *bnapi = &bp->bnx2_napi[0], *tx_napi; - struct bnx2_tx_ring_info *txr = &bnapi->tx_ring; - struct bnx2_rx_ring_info *rxr = &bnapi->rx_ring; + struct bnx2_tx_ring_info *txr; + struct bnx2_rx_ring_info *rxr; tx_napi = bnapi; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6b7e99675571..4b001d2050c2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -7778,7 +7778,8 @@ static int bnxt_setup_tc_block_cb(enum tc_setup_type type, void *type_data, { struct bnxt *bp = cb_priv; - if (!bnxt_tc_flower_enabled(bp) || !tc_can_offload(bp->dev)) + if (!bnxt_tc_flower_enabled(bp) || + !tc_cls_can_offload_and_chain0(bp->dev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 2ece1645f55d..fbe6e208e17b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1474,9 +1474,6 @@ int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid, { int rc = 0; - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: rc = bnxt_tc_add_flow(bp, src_fid, cls_flower); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index 2ca11be64182..26290403f38f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -124,7 +124,8 @@ static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type, struct bnxt *bp = vf_rep->bp; int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid; - if (!bnxt_tc_flower_enabled(vf_rep->bp) || !tc_can_offload(bp->dev)) + if (!bnxt_tc_flower_enabled(vf_rep->bp) || + !tc_cls_can_offload_and_chain0(bp->dev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig index 5713e83be08c..e2cdfa75673f 100644 --- a/drivers/net/ethernet/chelsio/Kconfig +++ b/drivers/net/ethernet/chelsio/Kconfig @@ -69,6 +69,7 @@ config CHELSIO_T4 depends on PCI && (IPV6 || IPV6=n) select FW_LOADER select MDIO + select ZLIB_DEFLATE ---help--- This driver supports Chelsio T4, T5 & T6 based gigabit, 10Gb Ethernet adapter and T5/T6 based 40Gb and T6 based 25Gb, 50Gb and 100Gb diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 6a015362c340..185fe8df7628 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3304,6 +3304,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->ethtool_ops = &cxgb_ethtool_ops; netdev->min_mtu = 81; netdev->max_mtu = ETH_MAX_MTU; + netdev->dev_port = pi->port_id; } pci_set_drvdata(pdev, adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/Makefile b/drivers/net/ethernet/chelsio/cxgb4/Makefile index 5df923798669..53b6a02c778e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/Makefile +++ b/drivers/net/ethernet/chelsio/cxgb4/Makefile @@ -8,8 +8,7 @@ obj-$(CONFIG_CHELSIO_T4) += cxgb4.o cxgb4-objs := cxgb4_main.o l2t.o smt.o t4_hw.o sge.o clip_tbl.o cxgb4_ethtool.o \ cxgb4_uld.o sched.o cxgb4_filter.o cxgb4_tc_u32.o \ cxgb4_ptp.o cxgb4_tc_flower.o cxgb4_cudbg.o \ - cudbg_common.o cudbg_lib.o + cudbg_common.o cudbg_lib.o cudbg_zlib.o cxgb4-$(CONFIG_CHELSIO_T4_DCB) += cxgb4_dcb.o cxgb4-$(CONFIG_CHELSIO_T4_FCOE) += cxgb4_fcoe.o cxgb4-$(CONFIG_DEBUG_FS) += cxgb4_debugfs.o -cxgb4-$(CONFIG_ZLIB_DEFLATE) += cudbg_zlib.o diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 8b95117c2923..557fd8bfd54e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -1567,6 +1567,12 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init, tid1->ver_hdr.size = sizeof(struct cudbg_tid_info_region_rev1) - sizeof(struct cudbg_ver_hdr); + /* If firmware is not attached/alive, use backdoor register + * access to collect dump. + */ + if (!is_fw_attached(pdbg_init)) + goto fill_tid; + #define FW_PARAM_PFVF_A(param) \ (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | \ FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_##param) | \ @@ -1604,6 +1610,9 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init, tid->nhpftids = val[1] - val[0] + 1; } +#undef FW_PARAM_PFVF_A + +fill_tid: tid->ntids = padap->tids.ntids; tid->nstids = padap->tids.nstids; tid->stid_base = padap->tids.stid_base; @@ -1623,8 +1632,6 @@ int cudbg_collect_tid(struct cudbg_init *pdbg_init, tid->ip_users = t4_read_reg(padap, LE_DB_ACT_CNT_IPV4_A); tid->ipv6_users = t4_read_reg(padap, LE_DB_ACT_CNT_IPV6_A); -#undef FW_PARAM_PFVF_A - return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff); } @@ -1866,11 +1873,18 @@ int cudbg_collect_dump_context(struct cudbg_init *pdbg_init, max_ctx_size = region_info[i].end - region_info[i].start + 1; max_ctx_qid = max_ctx_size / SGE_CTXT_SIZE; - t4_sge_ctxt_flush(padap, padap->mbox, i); - rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type[i], - region_info[i].start, max_ctx_size, - (__be32 *)ctx_buf, 1); - if (rc) { + /* If firmware is not attached/alive, use backdoor register + * access to collect dump. + */ + if (is_fw_attached(pdbg_init)) { + t4_sge_ctxt_flush(padap, padap->mbox, i); + + rc = t4_memory_rw(padap, MEMWIN_NIC, mem_type[i], + region_info[i].start, max_ctx_size, + (__be32 *)ctx_buf, 1); + } + + if (rc || !is_fw_attached(pdbg_init)) { max_ctx_qid = CUDBG_LOWMEM_MAX_CTXT_QIDS; cudbg_get_sge_ctxt_fw(pdbg_init, max_ctx_qid, i, &buff); @@ -1946,9 +1960,10 @@ static void cudbg_mps_rpl_backdoor(struct adapter *padap, mps_rplc->rplc31_0 = htonl(t4_read_reg(padap, MPS_VF_RPLCT_MAP0_A)); } -static int cudbg_collect_tcam_index(struct adapter *padap, +static int cudbg_collect_tcam_index(struct cudbg_init *pdbg_init, struct cudbg_mps_tcam *tcam, u32 idx) { + struct adapter *padap = pdbg_init->adap; u64 tcamy, tcamx, val; u32 ctl, data2; int rc = 0; @@ -2033,12 +2048,22 @@ static int cudbg_collect_tcam_index(struct adapter *padap, htons(FW_LDST_CMD_FID_V(FW_LDST_MPS_RPLC) | FW_LDST_CMD_IDX_V(idx)); - rc = t4_wr_mbox(padap, padap->mbox, &ldst_cmd, sizeof(ldst_cmd), - &ldst_cmd); - if (rc) + /* If firmware is not attached/alive, use backdoor register + * access to collect dump. + */ + if (is_fw_attached(pdbg_init)) + rc = t4_wr_mbox(padap, padap->mbox, &ldst_cmd, + sizeof(ldst_cmd), &ldst_cmd); + + if (rc || !is_fw_attached(pdbg_init)) { cudbg_mps_rpl_backdoor(padap, &mps_rplc); - else + /* Ignore error since we collected directly from + * reading registers. + */ + rc = 0; + } else { mps_rplc = ldst_cmd.u.mps.rplc; + } tcam->rplc[0] = ntohl(mps_rplc.rplc31_0); tcam->rplc[1] = ntohl(mps_rplc.rplc63_32); @@ -2075,7 +2100,7 @@ int cudbg_collect_mps_tcam(struct cudbg_init *pdbg_init, tcam = (struct cudbg_mps_tcam *)temp_buff.data; for (i = 0; i < n; i++) { - rc = cudbg_collect_tcam_index(padap, tcam, i); + rc = cudbg_collect_tcam_index(pdbg_init, tcam, i); if (rc) { cudbg_err->sys_err = rc; cudbg_put_buff(pdbg_init, &temp_buff); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c index 4c3854cbeb6c..25cc06d75cff 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.c @@ -40,8 +40,8 @@ int cudbg_compress_buff(struct cudbg_init *pdbg_init, struct cudbg_buffer *pin_buff, struct cudbg_buffer *pout_buff) { - struct z_stream_s compress_stream = { 0 }; struct cudbg_buffer temp_buff = { 0 }; + struct z_stream_s compress_stream; struct cudbg_compress_hdr *c_hdr; int rc; @@ -53,6 +53,7 @@ int cudbg_compress_buff(struct cudbg_init *pdbg_init, c_hdr = (struct cudbg_compress_hdr *)temp_buff.data; c_hdr->compress_id = CUDBG_ZLIB_COMPRESS_ID; + memset(&compress_stream, 0, sizeof(struct z_stream_s)); compress_stream.workspace = pdbg_init->workspace; rc = zlib_deflateInit2(&compress_stream, Z_DEFAULT_COMPRESSION, Z_DEFLATED, CUDBG_ZLIB_WIN_BITS, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h index 9d55c4c38c84..60d23805dfc3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_zlib.h @@ -33,24 +33,11 @@ struct cudbg_compress_hdr { static inline int cudbg_get_workspace_size(void) { -#ifdef CONFIG_ZLIB_DEFLATE return zlib_deflate_workspacesize(CUDBG_ZLIB_WIN_BITS, CUDBG_ZLIB_MEM_LVL); -#else - return 0; -#endif /* CONFIG_ZLIB_DEFLATE */ } -#ifndef CONFIG_ZLIB_DEFLATE -static inline int cudbg_compress_buff(struct cudbg_init *pdbg_init, - struct cudbg_buffer *pin_buff, - struct cudbg_buffer *pout_buff) -{ - return 0; -} -#else int cudbg_compress_buff(struct cudbg_init *pdbg_init, struct cudbg_buffer *pin_buff, struct cudbg_buffer *pout_buff); -#endif /* CONFIG_ZLIB_DEFLATE */ #endif /* __CUDBG_ZLIB_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index f05b58f74c7a..429467364219 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -820,6 +820,7 @@ struct vf_info { unsigned char vf_mac_addr[ETH_ALEN]; unsigned int tx_rate; bool pf_set_mac; + u16 vlan; }; struct mbox_list { @@ -846,6 +847,8 @@ struct adapter { int msg_enable; __be16 vxlan_port; u8 vxlan_port_cnt; + __be16 geneve_port; + u8 geneve_port_cnt; struct adapter_params params; struct cxgb4_virt_res vres; @@ -1736,4 +1739,6 @@ void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, struct sge_fl *fl); void free_tx_desc(struct adapter *adap, struct sge_txq *q, unsigned int n, bool unmap); void free_txq(struct adapter *adap, struct sge_txq *q); +int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, + u16 vlan); #endif /* __CXGB4_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 9e0a8a8186c4..30485f9a598f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -406,14 +406,15 @@ static void cudbg_free_compress_buff(struct cudbg_init *pdbg_init) int cxgb4_cudbg_collect(struct adapter *adap, void *buf, u32 *buf_size, u32 flag) { - struct cudbg_init cudbg_init = { 0 }; struct cudbg_buffer dbg_buff = { 0 }; u32 size, min_size, total_size = 0; + struct cudbg_init cudbg_init; struct cudbg_hdr *cudbg_hdr; int rc; size = *buf_size; + memset(&cudbg_init, 0, sizeof(struct cudbg_init)); cudbg_init.adap = adap; cudbg_init.outbuf = buf; cudbg_init.outbuf_size = size; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 11fe5961040a..1e3cd8abc56d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2783,7 +2783,30 @@ static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf, return 0; } -#endif +static int cxgb4_mgmt_set_vf_vlan(struct net_device *dev, int vf, + u16 vlan, u8 qos, __be16 vlan_proto) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + int ret; + + if (vf >= adap->num_vfs || vlan > 4095 || qos > 7) + return -EINVAL; + + if (vlan_proto != htons(ETH_P_8021Q) || qos != 0) + return -EPROTONOSUPPORT; + + ret = t4_set_vlan_acl(adap, adap->mbox, vf + 1, vlan); + if (!ret) { + adap->vfinfo[vf].vlan = vlan; + return 0; + } + + dev_err(adap->pdev_dev, "Err %d %s VLAN ACL for PF/VF %d/%d\n", + ret, (vlan ? "setting" : "clearing"), adap->pf, vf); + return ret; +} +#endif /* CONFIG_PCI_IOV */ static int cxgb_set_mac_addr(struct net_device *dev, void *p) { @@ -2905,9 +2928,6 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate) static int cxgb_setup_tc_flower(struct net_device *dev, struct tc_cls_flower_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: return cxgb4_tc_flower_replace(dev, cls_flower); @@ -2923,9 +2943,6 @@ static int cxgb_setup_tc_flower(struct net_device *dev, static int cxgb_setup_tc_cls_u32(struct net_device *dev, struct tc_cls_u32_offload *cls_u32) { - if (cls_u32->common.chain_index) - return -EOPNOTSUPP; - switch (cls_u32->command) { case TC_CLSU32_NEW_KNODE: case TC_CLSU32_REPLACE_KNODE: @@ -2951,7 +2968,7 @@ static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data, return -EINVAL; } - if (!tc_can_offload(dev)) + if (!tc_cls_can_offload_and_chain0(dev, type_data)) return -EOPNOTSUPP; switch (type) { @@ -3020,6 +3037,17 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev, adapter->vxlan_port = 0; t4_write_reg(adapter, MPS_RX_VXLAN_TYPE_A, 0); break; + case UDP_TUNNEL_TYPE_GENEVE: + if (!adapter->geneve_port_cnt || + adapter->geneve_port != ti->port) + return; /* Invalid GENEVE destination port */ + + adapter->geneve_port_cnt--; + if (adapter->geneve_port_cnt) + return; + + adapter->geneve_port = 0; + t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0); default: return; } @@ -3055,17 +3083,11 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, u8 match_all_mac[] = { 0, 0, 0, 0, 0, 0 }; int i, ret; - if (chip_ver < CHELSIO_T6) + if (chip_ver < CHELSIO_T6 || !adapter->rawf_cnt) return; switch (ti->type) { case UDP_TUNNEL_TYPE_VXLAN: - /* For T6 fw reserves last 2 entries for - * storing match all mac filter (config file entry). - */ - if (!adapter->rawf_cnt) - return; - /* Callback for adding vxlan port can be called with the same * port for both IPv4 and IPv6. We should not disable the * offloading when the same port for both protocols is added @@ -3091,6 +3113,26 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, t4_write_reg(adapter, MPS_RX_VXLAN_TYPE_A, VXLAN_V(be16_to_cpu(ti->port)) | VXLAN_EN_F); break; + case UDP_TUNNEL_TYPE_GENEVE: + if (adapter->geneve_port_cnt && + adapter->geneve_port == ti->port) { + adapter->geneve_port_cnt++; + return; + } + + /* We will support only one GENEVE port */ + if (adapter->geneve_port_cnt) { + netdev_info(netdev, "UDP port %d already offloaded, not adding port %d\n", + be16_to_cpu(adapter->geneve_port), + be16_to_cpu(ti->port)); + return; + } + + adapter->geneve_port = ti->port; + adapter->geneve_port_cnt = 1; + + t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, + GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F); default: return; } @@ -3101,24 +3143,22 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, * we will remove this 'match all' entry and fallback to adding * exact match filters. */ - if (adapter->rawf_cnt) { - for_each_port(adapter, i) { - pi = adap2pinfo(adapter, i); - - ret = t4_alloc_raw_mac_filt(adapter, pi->viid, - match_all_mac, - match_all_mac, - adapter->rawf_start + - pi->port_id, - 1, pi->port_id, true); - if (ret < 0) { - netdev_info(netdev, "Failed to allocate a mac filter entry, not adding port %d\n", - be16_to_cpu(ti->port)); - cxgb_del_udp_tunnel(netdev, ti); - return; - } - atomic_inc(&adapter->mps_encap[ret].refcnt); + for_each_port(adapter, i) { + pi = adap2pinfo(adapter, i); + + ret = t4_alloc_raw_mac_filt(adapter, pi->viid, + match_all_mac, + match_all_mac, + adapter->rawf_start + + pi->port_id, + 1, pi->port_id, true); + if (ret < 0) { + netdev_info(netdev, "Failed to allocate a mac filter entry, not adding port %d\n", + be16_to_cpu(ti->port)); + cxgb_del_udp_tunnel(netdev, ti); + return; } + atomic_inc(&adapter->mps_encap[ret].refcnt); } } @@ -3184,6 +3224,7 @@ static const struct net_device_ops cxgb4_mgmt_netdev_ops = { .ndo_get_vf_config = cxgb4_mgmt_get_vf_config, .ndo_set_vf_rate = cxgb4_mgmt_set_vf_rate, .ndo_get_phys_port_id = cxgb4_mgmt_get_phys_port_id, + .ndo_set_vf_vlan = cxgb4_mgmt_set_vf_vlan, }; #endif diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 9b9f3f99b39d..36563364bae7 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -43,7 +43,7 @@ #define STATS_CHECK_PERIOD (HZ / 2) -struct ch_tc_pedit_fields pedits[] = { +static struct ch_tc_pedit_fields pedits[] = { PEDIT_FIELDS(ETH_, DMAC_31_0, 4, dmac, 0), PEDIT_FIELDS(ETH_, DMAC_47_32, 2, dmac, 4), PEDIT_FIELDS(ETH_, SMAC_15_0, 2, smac, 0), @@ -111,6 +111,9 @@ static void cxgb4_process_flow_match(struct net_device *dev, ethtype_mask = 0; } + if (ethtype_key == ETH_P_IPV6) + fs->type = 1; + fs->val.ethtype = ethtype_key; fs->mask.ethtype = ethtype_mask; fs->val.proto = key->ip_proto; @@ -205,8 +208,8 @@ static void cxgb4_process_flow_match(struct net_device *dev, VLAN_PRIO_SHIFT); vlan_tci_mask = mask->vlan_id | (mask->vlan_priority << VLAN_PRIO_SHIFT); - fs->val.ivlan = cpu_to_be16(vlan_tci); - fs->mask.ivlan = cpu_to_be16(vlan_tci_mask); + fs->val.ivlan = vlan_tci; + fs->mask.ivlan = vlan_tci_mask; /* Chelsio adapters use ivlan_vld bit to match vlan packets * as 802.1Q. Also, when vlan tag is present in packets, diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index eab781fab2a8..a7af71bf14fb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1199,6 +1199,8 @@ enum cpl_tx_tnl_lso_type cxgb_encap_offload_supported(struct sk_buff *skb) case IPPROTO_UDP: if (adapter->vxlan_port == udp_hdr(skb)->dest) tnl_type = TX_TNL_TYPE_VXLAN; + else if (adapter->geneve_port == udp_hdr(skb)->dest) + tnl_type = TX_TNL_TYPE_GENEVE; break; default: return tnl_type; @@ -1238,6 +1240,7 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb, switch (tnl_type) { case TX_TNL_TYPE_VXLAN: + case TX_TNL_TYPE_GENEVE: tnl_lso->UdpLenSetOut_to_TnlHdrLen = htons(CPL_TX_TNL_LSO_UDPCHKCLROUT_F | CPL_TX_TNL_LSO_UDPLENSETOUT_F); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 6d76851a4da9..047609ef0515 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -195,9 +195,11 @@ static void t4_report_fw_error(struct adapter *adap) u32 pcie_fw; pcie_fw = t4_read_reg(adap, PCIE_FW_A); - if (pcie_fw & PCIE_FW_ERR_F) + if (pcie_fw & PCIE_FW_ERR_F) { dev_err(adap->pdev_dev, "Firmware reports adapter error: %s\n", reason[PCIE_FW_EVAL_G(pcie_fw)]); + adap->flags &= ~FW_OK; + } } /* @@ -317,9 +319,9 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, * wait [for a while] till we're at the front [or bail out with an * EBUSY] ... */ - spin_lock(&adap->mbox_lock); + spin_lock_bh(&adap->mbox_lock); list_add_tail(&entry.list, &adap->mlist.list); - spin_unlock(&adap->mbox_lock); + spin_unlock_bh(&adap->mbox_lock); delay_idx = 0; ms = delay[0]; @@ -332,9 +334,9 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, */ pcie_fw = t4_read_reg(adap, PCIE_FW_A); if (i > FW_CMD_MAX_TIMEOUT || (pcie_fw & PCIE_FW_ERR_F)) { - spin_lock(&adap->mbox_lock); + spin_lock_bh(&adap->mbox_lock); list_del(&entry.list); - spin_unlock(&adap->mbox_lock); + spin_unlock_bh(&adap->mbox_lock); ret = (pcie_fw & PCIE_FW_ERR_F) ? -ENXIO : -EBUSY; t4_record_mbox(adap, cmd, size, access, ret); return ret; @@ -365,9 +367,9 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, for (i = 0; v == MBOX_OWNER_NONE && i < 3; i++) v = MBOWNER_G(t4_read_reg(adap, ctl_reg)); if (v != MBOX_OWNER_DRV) { - spin_lock(&adap->mbox_lock); + spin_lock_bh(&adap->mbox_lock); list_del(&entry.list); - spin_unlock(&adap->mbox_lock); + spin_unlock_bh(&adap->mbox_lock); ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT; t4_record_mbox(adap, cmd, size, access, ret); return ret; @@ -418,9 +420,9 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, execute = i + ms; t4_record_mbox(adap, cmd_rpl, MBOX_LEN, access, execute); - spin_lock(&adap->mbox_lock); + spin_lock_bh(&adap->mbox_lock); list_del(&entry.list); - spin_unlock(&adap->mbox_lock); + spin_unlock_bh(&adap->mbox_lock); return -FW_CMD_RETVAL_G((int)res); } } @@ -430,9 +432,9 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n", *(const u8 *)cmd, mbox); t4_report_fw_error(adap); - spin_lock(&adap->mbox_lock); + spin_lock_bh(&adap->mbox_lock); list_del(&entry.list); - spin_unlock(&adap->mbox_lock); + spin_unlock_bh(&adap->mbox_lock); t4_fatal_err(adap); return ret; } @@ -5088,7 +5090,7 @@ int t4_read_rss(struct adapter *adapter, u16 *map) static unsigned int t4_use_ldst(struct adapter *adap) { - return (adap->flags & FW_OK) || !adap->use_bd; + return (adap->flags & FW_OK) && !adap->use_bd; } /** @@ -9899,3 +9901,35 @@ int t4_i2c_rd(struct adapter *adap, unsigned int mbox, int port, return ret; } + +/** + * t4_set_vlan_acl - Set a VLAN id for the specified VF + * @adapter: the adapter + * @mbox: mailbox to use for the FW command + * @vf: one of the VFs instantiated by the specified PF + * @vlan: The vlanid to be set + */ +int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, + u16 vlan) +{ + struct fw_acl_vlan_cmd vlan_cmd; + unsigned int enable; + + enable = (vlan ? FW_ACL_VLAN_CMD_EN_F : 0); + memset(&vlan_cmd, 0, sizeof(vlan_cmd)); + vlan_cmd.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_ACL_VLAN_CMD) | + FW_CMD_REQUEST_F | + FW_CMD_WRITE_F | + FW_CMD_EXEC_F | + FW_ACL_VLAN_CMD_PFN_V(adap->pf) | + FW_ACL_VLAN_CMD_VFN_V(vf)); + vlan_cmd.en_to_len16 = cpu_to_be32(enable | FW_LEN16(vlan_cmd)); + /* Drop all packets that donot match vlan id */ + vlan_cmd.dropnovlan_fm = FW_ACL_VLAN_CMD_FM_F; + if (enable != 0) { + vlan_cmd.nvlan = 1; + vlan_cmd.vlanid[0] = cpu_to_be16(vlan); + } + + return t4_wr_mbox(adap, adap->mbox, &vlan_cmd, sizeof(vlan_cmd), NULL); +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h index d9c06d6dc7b2..a6df73398d17 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h @@ -2522,6 +2522,17 @@ #define VXLAN_V(x) ((x) << VXLAN_S) #define VXLAN_G(x) (((x) >> VXLAN_S) & VXLAN_M) +#define MPS_RX_GENEVE_TYPE_A 0x11238 + +#define GENEVE_EN_S 16 +#define GENEVE_EN_V(x) ((x) << GENEVE_EN_S) +#define GENEVE_EN_F GENEVE_EN_V(1U) + +#define GENEVE_S 0 +#define GENEVE_M 0xffffU +#define GENEVE_V(x) ((x) << GENEVE_S) +#define GENEVE_G(x) (((x) >> GENEVE_S) & GENEVE_M) + #define MPS_CLS_TCAM_Y_L_A 0xf000 #define MPS_CLS_TCAM_DATA0_A 0xf000 #define MPS_CLS_TCAM_DATA1_A 0xf004 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index f3310d5b3c4c..f88766d2401d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -2353,14 +2353,22 @@ struct fw_acl_vlan_cmd { #define FW_ACL_VLAN_CMD_VFN_S 0 #define FW_ACL_VLAN_CMD_VFN_V(x) ((x) << FW_ACL_VLAN_CMD_VFN_S) -#define FW_ACL_VLAN_CMD_EN_S 31 -#define FW_ACL_VLAN_CMD_EN_V(x) ((x) << FW_ACL_VLAN_CMD_EN_S) +#define FW_ACL_VLAN_CMD_EN_S 31 +#define FW_ACL_VLAN_CMD_EN_M 0x1 +#define FW_ACL_VLAN_CMD_EN_V(x) ((x) << FW_ACL_VLAN_CMD_EN_S) +#define FW_ACL_VLAN_CMD_EN_G(x) \ + (((x) >> S_FW_ACL_VLAN_CMD_EN_S) & FW_ACL_VLAN_CMD_EN_M) +#define FW_ACL_VLAN_CMD_EN_F FW_ACL_VLAN_CMD_EN_V(1U) #define FW_ACL_VLAN_CMD_DROPNOVLAN_S 7 #define FW_ACL_VLAN_CMD_DROPNOVLAN_V(x) ((x) << FW_ACL_VLAN_CMD_DROPNOVLAN_S) -#define FW_ACL_VLAN_CMD_FM_S 6 -#define FW_ACL_VLAN_CMD_FM_V(x) ((x) << FW_ACL_VLAN_CMD_FM_S) +#define FW_ACL_VLAN_CMD_FM_S 6 +#define FW_ACL_VLAN_CMD_FM_M 0x1 +#define FW_ACL_VLAN_CMD_FM_V(x) ((x) << FW_ACL_VLAN_CMD_FM_S) +#define FW_ACL_VLAN_CMD_FM_G(x) \ + (((x) >> FW_ACL_VLAN_CMD_FM_S) & FW_ACL_VLAN_CMD_FM_M) +#define FW_ACL_VLAN_CMD_FM_F FW_ACL_VLAN_CMD_FM_V(1U) /* old 16-bit port capabilities bitmap (fw_port_cap16_t) */ enum fw_port_cap { diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h index 08c6ddb84a04..5883f09e3804 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h @@ -92,6 +92,7 @@ struct sge_rspq; */ struct port_info { struct adapter *adapter; /* our adapter */ + u32 vlan_id; /* vlan id for VST */ u16 viid; /* virtual interface ID */ s16 xact_addr_filt; /* index of our MAC address filter */ u16 rss_size; /* size of VI's RSS table slice */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 96f69f80dc99..b7e79e64d2ed 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -791,6 +791,8 @@ static int cxgb4vf_open(struct net_device *dev) if (err) goto err_unwind; + pi->vlan_id = t4vf_get_vf_vlan_acl(adapter); + netif_tx_start_all_queues(dev); set_bit(pi->port_id, &adapter->open_device_map); return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 129b914a434c..dfce5df7538e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -1202,6 +1202,10 @@ int t4vf_eth_xmit(struct sk_buff *skb, struct net_device *dev) BUG_ON(qidx >= pi->nqsets); txq = &adapter->sge.ethtxq[pi->first_qset + qidx]; + if (pi->vlan_id && !skb_vlan_tag_present(skb)) + __vlan_hwaccel_put_tag(skb, cpu_to_be16(ETH_P_8021Q), + pi->vlan_id); + /* * Take this opportunity to reclaim any TX Descriptors whose DMA * transfers have completed. @@ -1570,6 +1574,7 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, { struct adapter *adapter = rxq->rspq.adapter; struct sge *s = &adapter->sge; + struct port_info *pi; int ret; struct sk_buff *skb; @@ -1586,8 +1591,9 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, skb->truesize += skb->data_len; skb->ip_summed = CHECKSUM_UNNECESSARY; skb_record_rx_queue(skb, rxq->rspq.idx); + pi = netdev_priv(skb->dev); - if (pkt->vlan_ex) { + if (pkt->vlan_ex && !pi->vlan_id) { __vlan_hwaccel_put_tag(skb, cpu_to_be16(ETH_P_8021Q), be16_to_cpu(pkt->vlan)); rxq->stats.vlan_ex++; @@ -1620,6 +1626,7 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp, struct sge_eth_rxq *rxq = container_of(rspq, struct sge_eth_rxq, rspq); struct adapter *adapter = rspq->adapter; struct sge *s = &adapter->sge; + struct port_info *pi; /* * If this is a good TCP packet and we have Generic Receive Offload @@ -1644,6 +1651,7 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp, __skb_pull(skb, s->pktshift); skb->protocol = eth_type_trans(skb, rspq->netdev); skb_record_rx_queue(skb, rspq->idx); + pi = netdev_priv(skb->dev); rxq->stats.pkts++; if (csum_ok && !pkt->err_vec && @@ -1660,9 +1668,10 @@ int t4vf_ethrx_handler(struct sge_rspq *rspq, const __be64 *rsp, } else skb_checksum_none_assert(skb); - if (pkt->vlan_ex) { + if (pkt->vlan_ex && !pi->vlan_id) { rxq->stats.vlan_ex++; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(pkt->vlan)); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + be16_to_cpu(pkt->vlan)); } netif_receive_skb(skb); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index 9cf9c56b0f73..712e8f0c71b4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -413,5 +413,6 @@ int t4vf_handle_fw_rpl(struct adapter *, const __be64 *); int t4vf_prep_adapter(struct adapter *); int t4vf_get_vf_mac_acl(struct adapter *adapter, unsigned int pf, unsigned int *naddr, u8 *addr); +int t4vf_get_vf_vlan_acl(struct adapter *adapter); #endif /* __T4VF_COMMON_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index 67aec59a14e6..798695bf8678 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -2147,3 +2147,31 @@ int t4vf_get_vf_mac_acl(struct adapter *adapter, unsigned int pf, return ret; } + +/** + * t4vf_get_vf_vlan_acl - Get the VLAN ID to be set to + * the VI of this VF. + * @adapter: The adapter + * + * Find the VLAN ID to be set to the VF's VI. The requested VLAN ID + * is from the host OS via callback in the PF driver. + */ +int t4vf_get_vf_vlan_acl(struct adapter *adapter) +{ + struct fw_acl_vlan_cmd cmd; + int vlan = 0; + int ret = 0; + + cmd.op_to_vfn = htonl(FW_CMD_OP_V(FW_ACL_VLAN_CMD) | + FW_CMD_REQUEST_F | FW_CMD_READ_F); + + /* Note: Do not enable the ACL */ + cmd.en_to_len16 = cpu_to_be32((unsigned int)FW_LEN16(cmd)); + + ret = t4vf_wr_mbox(adapter, &cmd, sizeof(cmd), &cmd); + + if (!ret) + vlan = be16_to_cpu(cmd.vlanid[0]); + + return vlan; +} diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index c6e859a27ee6..c36c81959198 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4634,6 +4634,14 @@ int be_update_queues(struct be_adapter *adapter) be_schedule_worker(adapter); + /* The IF was destroyed and re-created. We need to clear + * all promiscuous flags valid for the destroyed IF. + * Without this promisc mode is not restored during + * be_open() because the driver thinks that it is + * already enabled in HW. + */ + adapter->if_flags &= ~BE_IF_FLAGS_ALL_PROMISCUOUS; + if (netif_running(netdev)) status = be_open(netdev); diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 5385074b3b7d..e7381f8ef89d 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -20,7 +20,8 @@ #include <linux/timecounter.h> #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ + defined(CONFIG_ARM64) /* * Just figures, Motorola would have to change the offsets for * registers in the same peripheral device on different models @@ -195,7 +196,7 @@ * Evidently, ARM SoCs have the FEC block generated in a * little endian mode so adjust endianness accordingly. */ -#if defined(CONFIG_ARM) +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) #define fec32_to_cpu le32_to_cpu #define fec16_to_cpu le16_to_cpu #define cpu_to_fec32 cpu_to_le32 diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 90aa69a08922..7a7f3a42b2aa 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -195,7 +195,8 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); * account when setting it. */ #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ + defined(CONFIG_ARM64) #define OPT_FRAME_SIZE (PKT_MAXBUF_SIZE << 16) #else #define OPT_FRAME_SIZE 0 @@ -2109,7 +2110,8 @@ static int fec_enet_get_regs_len(struct net_device *ndev) /* List of registers that can be safety be read to dump them with ethtool */ #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) + defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ + defined(CONFIG_ARM64) static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -3139,7 +3141,7 @@ static int fec_enet_init(struct net_device *ndev) unsigned dsize_log2 = __fls(dsize); WARN_ON(dsize != (1 << dsize_log2)); -#if defined(CONFIG_ARM) +#if defined(CONFIG_ARM) || defined(CONFIG_ARM64) fep->rx_align = 0xf; fep->tx_align = 0xf; #else diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index ca247c2cc238..acf29633ec79 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -44,12 +44,17 @@ static void dsaf_write_sub(struct dsaf_device *dsaf_dev, u32 reg, u32 val) static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg) { - u32 ret; - - if (dsaf_dev->sub_ctrl) - ret = dsaf_read_syscon(dsaf_dev->sub_ctrl, reg); - else + u32 ret = 0; + int err; + + if (dsaf_dev->sub_ctrl) { + err = dsaf_read_syscon(dsaf_dev->sub_ctrl, reg, &ret); + if (err) + dev_err(dsaf_dev->dev, "dsaf_read_syscon error %d!\n", + err); + } else { ret = dsaf_read_reg(dsaf_dev->sc_base, reg); + } return ret; } @@ -188,18 +193,23 @@ static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb) static int cpld_set_led_id(struct hns_mac_cb *mac_cb, enum hnae_led_state status) { + u32 val = 0; + int ret; + if (!mac_cb->cpld_ctrl) return 0; switch (status) { case HNAE_LED_ACTIVE: - mac_cb->cpld_led_value = - dsaf_read_syscon(mac_cb->cpld_ctrl, - mac_cb->cpld_ctrl_reg); - dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B, - CPLD_LED_ON_VALUE); + ret = dsaf_read_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg, + &val); + if (ret) + return ret; + + dsaf_set_bit(val, DSAF_LED_ANCHOR_B, CPLD_LED_ON_VALUE); dsaf_write_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg, - mac_cb->cpld_led_value); + val); + mac_cb->cpld_led_value = val; break; case HNAE_LED_INACTIVE: dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B, @@ -560,12 +570,19 @@ static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb) int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) { + u32 val = 0; + int ret; + if (!mac_cb->cpld_ctrl) return -ENODEV; - *sfp_prsnt = !dsaf_read_syscon(mac_cb->cpld_ctrl, mac_cb->cpld_ctrl_reg - + MAC_SFP_PORT_OFFSET); + ret = dsaf_read_syscon(mac_cb->cpld_ctrl, + mac_cb->cpld_ctrl_reg + MAC_SFP_PORT_OFFSET, + &val); + if (ret) + return ret; + *sfp_prsnt = !val; return 0; } @@ -615,7 +632,7 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en) #define RX_CSR(lane, reg) ((0x4080 + (reg) * 0x0002 + (lane) * 0x0200) * 2) u64 reg_offset = RX_CSR(lane_id[mac_cb->mac_id], 0); - int sfp_prsnt; + int sfp_prsnt = 0; int ret = hns_mac_get_sfp_prsnt(mac_cb, &sfp_prsnt); if (!mac_cb->phy_dev) { @@ -627,7 +644,7 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en) } if (mac_cb->serdes_ctrl) { - u32 origin; + u32 origin = 0; if (!AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver)) { #define HILINK_ACCESS_SEL_CFG 0x40008 @@ -644,7 +661,10 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en) HILINK_ACCESS_SEL_CFG, 3); } - origin = dsaf_read_syscon(mac_cb->serdes_ctrl, reg_offset); + ret = dsaf_read_syscon(mac_cb->serdes_ctrl, reg_offset, + &origin); + if (ret) + return ret; dsaf_set_field(origin, 1ull << 10, 10, en); dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index 46a52d9bb196..886cbbf25761 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -1034,12 +1034,9 @@ static inline void dsaf_write_syscon(struct regmap *base, u32 reg, u32 value) regmap_write(base, reg, value); } -static inline u32 dsaf_read_syscon(struct regmap *base, u32 reg) +static inline int dsaf_read_syscon(struct regmap *base, u32 reg, u32 *val) { - unsigned int val; - - regmap_read(base, reg, &val); - return val; + return regmap_read(base, reg, val); } #define dsaf_read_dev(a, reg) \ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 634e9327968b..fd06bc78c58e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -356,7 +356,8 @@ struct hnae3_ae_ops { u32 stringset, u8 *data); int (*get_sset_count)(struct hnae3_handle *handle, int stringset); - void (*get_regs)(struct hnae3_handle *handle, void *data); + void (*get_regs)(struct hnae3_handle *handle, u32 *version, + void *data); int (*get_regs_len)(struct hnae3_handle *handle); u32 (*get_rss_key_size)(struct hnae3_handle *handle); @@ -404,6 +405,8 @@ struct hnae3_ae_ops { int (*set_channels)(struct hnae3_handle *handle, u32 new_tqps_num); void (*get_flowctrl_adv)(struct hnae3_handle *handle, u32 *flowctrl_adv); + int (*set_led_id)(struct hnae3_handle *handle, + enum ethtool_phys_id_state status); }; struct hnae3_dcb_ops { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index ac848163ccae..601b6295d3f8 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3318,8 +3318,8 @@ static int hns3_reset_notify(struct hnae3_handle *handle, switch (type) { case HNAE3_UP_CLIENT: - ret = hns3_reset_notify_up_enet(handle); - break; + ret = hns3_reset_notify_up_enet(handle); + break; case HNAE3_DOWN_CLIENT: ret = hns3_reset_notify_down_enet(handle); break; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 358f78036941..b034c7f24eda 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1063,6 +1063,38 @@ static int hns3_set_coalesce(struct net_device *netdev, return 0; } +static int hns3_get_regs_len(struct net_device *netdev) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!h->ae_algo->ops->get_regs_len) + return -EOPNOTSUPP; + + return h->ae_algo->ops->get_regs_len(h); +} + +static void hns3_get_regs(struct net_device *netdev, + struct ethtool_regs *cmd, void *data) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!h->ae_algo->ops->get_regs) + return; + + h->ae_algo->ops->get_regs(h, &cmd->version, data); +} + +static int hns3_set_phys_id(struct net_device *netdev, + enum ethtool_phys_id_state state) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_led_id) + return -EOPNOTSUPP; + + return h->ae_algo->ops->set_led_id(h, state); +} + static const struct ethtool_ops hns3vf_ethtool_ops = { .get_drvinfo = hns3_get_drvinfo, .get_ringparam = hns3_get_ringparam, @@ -1077,6 +1109,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = { .set_rxfh = hns3_set_rss, .get_link_ksettings = hns3_get_link_ksettings, .get_channels = hns3_get_channels, + .get_coalesce = hns3_get_coalesce, + .set_coalesce = hns3_set_coalesce, }; static const struct ethtool_ops hns3_ethtool_ops = { @@ -1103,6 +1137,9 @@ static const struct ethtool_ops hns3_ethtool_ops = { .set_channels = hns3_set_channels, .get_coalesce = hns3_get_coalesce, .set_coalesce = hns3_set_coalesce, + .get_regs_len = hns3_get_regs_len, + .get_regs = hns3_get_regs, + .set_phys_id = hns3_set_phys_id, }; void hns3_ethtool_set_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 3c3159b2d3bf..3fd10a6bec53 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -102,6 +102,10 @@ enum hclge_opcode_type { HCLGE_OPC_STATS_64_BIT = 0x0030, HCLGE_OPC_STATS_32_BIT = 0x0031, HCLGE_OPC_STATS_MAC = 0x0032, + + HCLGE_OPC_QUERY_REG_NUM = 0x0040, + HCLGE_OPC_QUERY_32_BIT_REG = 0x0041, + HCLGE_OPC_QUERY_64_BIT_REG = 0x0042, /* Device management command */ /* MAC commond */ @@ -111,6 +115,7 @@ enum hclge_opcode_type { HCLGE_OPC_QUERY_LINK_STATUS = 0x0307, HCLGE_OPC_CONFIG_MAX_FRM_SIZE = 0x0308, HCLGE_OPC_CONFIG_SPEED_DUP = 0x0309, + HCLGE_OPC_STATS_MAC_TRAFFIC = 0x0314, /* MACSEC command */ /* PFC/Pause CMD*/ @@ -223,6 +228,9 @@ enum hclge_opcode_type { /* Mailbox cmd */ HCLGEVF_OPC_MBX_PF_TO_VF = 0x2000, + + /* Led command */ + HCLGE_OPC_LED_STATUS_CFG = 0xB000, }; #define HCLGE_TQP_REG_OFFSET 0x80000 @@ -601,6 +609,28 @@ struct hclge_mac_vlan_mask_entry_cmd { u8 rsv2[14]; }; +#define HCLGE_MAC_MGR_MASK_VLAN_B BIT(0) +#define HCLGE_MAC_MGR_MASK_MAC_B BIT(1) +#define HCLGE_MAC_MGR_MASK_ETHERTYPE_B BIT(2) +#define HCLGE_MAC_ETHERTYPE_LLDP 0x88cc + +struct hclge_mac_mgr_tbl_entry_cmd { + u8 flags; + u8 resp_code; + __le16 vlan_tag; + __le32 mac_addr_hi32; + __le16 mac_addr_lo16; + __le16 rsv1; + __le16 ethter_type; + __le16 egress_port; + __le16 egress_queue; + u8 sw_port_id_aware; + u8 rsv2; + u8 i_port_bitmap; + u8 i_port_direction; + u8 rsv3[2]; +}; + #define HCLGE_CFG_MTA_MAC_SEL_S 0x0 #define HCLGE_CFG_MTA_MAC_SEL_M GENMASK(1, 0) #define HCLGE_CFG_MTA_MAC_EN_B 0x7 @@ -781,6 +811,23 @@ struct hclge_reset_cmd { #define HCLGE_NIC_CMQ_DESC_NUM 1024 #define HCLGE_NIC_CMQ_DESC_NUM_S 3 +#define HCLGE_LED_PORT_SPEED_STATE_S 0 +#define HCLGE_LED_PORT_SPEED_STATE_M GENMASK(5, 0) +#define HCLGE_LED_ACTIVITY_STATE_S 0 +#define HCLGE_LED_ACTIVITY_STATE_M GENMASK(1, 0) +#define HCLGE_LED_LINK_STATE_S 0 +#define HCLGE_LED_LINK_STATE_M GENMASK(1, 0) +#define HCLGE_LED_LOCATE_STATE_S 0 +#define HCLGE_LED_LOCATE_STATE_M GENMASK(1, 0) + +struct hclge_set_led_state_cmd { + u8 port_speed_led_config; + u8 link_led_config; + u8 activity_led_config; + u8 locate_led_config; + u8 rsv[20]; +}; + int hclge_cmd_init(struct hclge_dev *hdev); static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 27f0ab695f5a..32bc6f68e297 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -39,6 +39,7 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu); static int hclge_init_vlan_config(struct hclge_dev *hdev); static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev); +static int hclge_update_led_status(struct hclge_dev *hdev); static struct hnae3_ae_algo ae_algo; @@ -392,6 +393,16 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = { HCLGE_MAC_STATS_FIELD_OFF(mac_rx_send_app_bad_pkt_num)} }; +static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = { + { + .flags = HCLGE_MAC_MGR_MASK_VLAN_B, + .ethter_type = cpu_to_le16(HCLGE_MAC_ETHERTYPE_LLDP), + .mac_addr_hi32 = cpu_to_le32(htonl(0x0180C200)), + .mac_addr_lo16 = cpu_to_le16(htons(0x000E)), + .i_port_bitmap = 0x1, + }, +}; + static int hclge_64_bit_update_stats(struct hclge_dev *hdev) { #define HCLGE_64_BIT_CMD_NUM 5 @@ -495,6 +506,38 @@ static int hclge_32_bit_update_stats(struct hclge_dev *hdev) return 0; } +static int hclge_mac_get_traffic_stats(struct hclge_dev *hdev) +{ + struct hclge_mac_stats *mac_stats = &hdev->hw_stats.mac_stats; + struct hclge_desc desc; + __le64 *desc_data; + int ret; + + /* for fiber port, need to query the total rx/tx packets statstics, + * used for data transferring checking. + */ + if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_FIBER) + return 0; + + if (test_bit(HCLGE_STATE_STATISTICS_UPDATING, &hdev->state)) + return 0; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_STATS_MAC_TRAFFIC, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get MAC total pkt stats fail, ret = %d\n", ret); + + return ret; + } + + desc_data = (__le64 *)(&desc.data[0]); + mac_stats->mac_tx_total_pkt_num += le64_to_cpu(*desc_data++); + mac_stats->mac_rx_total_pkt_num += le64_to_cpu(*desc_data); + + return 0; +} + static int hclge_mac_update_stats(struct hclge_dev *hdev) { #define HCLGE_MAC_CMD_NUM 21 @@ -2836,13 +2879,20 @@ static void hclge_service_task(struct work_struct *work) struct hclge_dev *hdev = container_of(work, struct hclge_dev, service_task); + /* The total rx/tx packets statstics are wanted to be updated + * per second. Both hclge_update_stats_for_all() and + * hclge_mac_get_traffic_stats() can do it. + */ if (hdev->hw_stats.stats_timer >= HCLGE_STATS_TIMER_INTERVAL) { hclge_update_stats_for_all(hdev); hdev->hw_stats.stats_timer = 0; + } else { + hclge_mac_get_traffic_stats(hdev); } hclge_update_speed_duplex(hdev); hclge_update_link_status(hdev); + hclge_update_led_status(hdev); hclge_service_complete(hdev); } @@ -4249,6 +4299,91 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, return status; } +static int hclge_get_mac_ethertype_cmd_status(struct hclge_dev *hdev, + u16 cmdq_resp, u8 resp_code) +{ +#define HCLGE_ETHERTYPE_SUCCESS_ADD 0 +#define HCLGE_ETHERTYPE_ALREADY_ADD 1 +#define HCLGE_ETHERTYPE_MGR_TBL_OVERFLOW 2 +#define HCLGE_ETHERTYPE_KEY_CONFLICT 3 + + int return_status; + + if (cmdq_resp) { + dev_err(&hdev->pdev->dev, + "cmdq execute failed for get_mac_ethertype_cmd_status, status=%d.\n", + cmdq_resp); + return -EIO; + } + + switch (resp_code) { + case HCLGE_ETHERTYPE_SUCCESS_ADD: + case HCLGE_ETHERTYPE_ALREADY_ADD: + return_status = 0; + break; + case HCLGE_ETHERTYPE_MGR_TBL_OVERFLOW: + dev_err(&hdev->pdev->dev, + "add mac ethertype failed for manager table overflow.\n"); + return_status = -EIO; + break; + case HCLGE_ETHERTYPE_KEY_CONFLICT: + dev_err(&hdev->pdev->dev, + "add mac ethertype failed for key conflict.\n"); + return_status = -EIO; + break; + default: + dev_err(&hdev->pdev->dev, + "add mac ethertype failed for undefined, code=%d.\n", + resp_code); + return_status = -EIO; + } + + return return_status; +} + +static int hclge_add_mgr_tbl(struct hclge_dev *hdev, + const struct hclge_mac_mgr_tbl_entry_cmd *req) +{ + struct hclge_desc desc; + u8 resp_code; + u16 retval; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_ETHTYPE_ADD, false); + memcpy(desc.data, req, sizeof(struct hclge_mac_mgr_tbl_entry_cmd)); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "add mac ethertype failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + + resp_code = (le32_to_cpu(desc.data[0]) >> 8) & 0xff; + retval = le16_to_cpu(desc.retval); + + return hclge_get_mac_ethertype_cmd_status(hdev, retval, resp_code); +} + +static int init_mgr_tbl(struct hclge_dev *hdev) +{ + int ret; + int i; + + for (i = 0; i < ARRAY_SIZE(hclge_mgr_table); i++) { + ret = hclge_add_mgr_tbl(hdev, &hclge_mgr_table[i]); + if (ret) { + dev_err(&hdev->pdev->dev, + "add mac ethertype failed, ret =%d.\n", + ret); + return ret; + } + } + + return 0; +} + static void hclge_get_mac_addr(struct hnae3_handle *handle, u8 *p) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -5271,6 +5406,12 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = init_mgr_tbl(hdev); + if (ret) { + dev_err(&pdev->dev, "manager table init fail, ret =%d\n", ret); + return ret; + } + hclge_dcb_ops_set(hdev); timer_setup(&hdev->service_timer, hclge_service_timer, 0); @@ -5544,6 +5685,318 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num) return ret; } +static int hclge_get_regs_num(struct hclge_dev *hdev, u32 *regs_num_32_bit, + u32 *regs_num_64_bit) +{ + struct hclge_desc desc; + u32 total_num; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_REG_NUM, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query register number cmd failed, ret = %d.\n", ret); + return ret; + } + + *regs_num_32_bit = le32_to_cpu(desc.data[0]); + *regs_num_64_bit = le32_to_cpu(desc.data[1]); + + total_num = *regs_num_32_bit + *regs_num_64_bit; + if (!total_num) + return -EINVAL; + + return 0; +} + +static int hclge_get_32_bit_regs(struct hclge_dev *hdev, u32 regs_num, + void *data) +{ +#define HCLGE_32_BIT_REG_RTN_DATANUM 8 + + struct hclge_desc *desc; + u32 *reg_val = data; + __le32 *desc_data; + int cmd_num; + int i, k, n; + int ret; + + if (regs_num == 0) + return 0; + + cmd_num = DIV_ROUND_UP(regs_num + 2, HCLGE_32_BIT_REG_RTN_DATANUM); + desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_32_BIT_REG, true); + ret = hclge_cmd_send(&hdev->hw, desc, cmd_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query 32 bit register cmd failed, ret = %d.\n", ret); + kfree(desc); + return ret; + } + + for (i = 0; i < cmd_num; i++) { + if (i == 0) { + desc_data = (__le32 *)(&desc[i].data[0]); + n = HCLGE_32_BIT_REG_RTN_DATANUM - 2; + } else { + desc_data = (__le32 *)(&desc[i]); + n = HCLGE_32_BIT_REG_RTN_DATANUM; + } + for (k = 0; k < n; k++) { + *reg_val++ = le32_to_cpu(*desc_data++); + + regs_num--; + if (!regs_num) + break; + } + } + + kfree(desc); + return 0; +} + +static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num, + void *data) +{ +#define HCLGE_64_BIT_REG_RTN_DATANUM 4 + + struct hclge_desc *desc; + u64 *reg_val = data; + __le64 *desc_data; + int cmd_num; + int i, k, n; + int ret; + + if (regs_num == 0) + return 0; + + cmd_num = DIV_ROUND_UP(regs_num + 1, HCLGE_64_BIT_REG_RTN_DATANUM); + desc = kcalloc(cmd_num, sizeof(struct hclge_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_64_BIT_REG, true); + ret = hclge_cmd_send(&hdev->hw, desc, cmd_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query 64 bit register cmd failed, ret = %d.\n", ret); + kfree(desc); + return ret; + } + + for (i = 0; i < cmd_num; i++) { + if (i == 0) { + desc_data = (__le64 *)(&desc[i].data[0]); + n = HCLGE_64_BIT_REG_RTN_DATANUM - 1; + } else { + desc_data = (__le64 *)(&desc[i]); + n = HCLGE_64_BIT_REG_RTN_DATANUM; + } + for (k = 0; k < n; k++) { + *reg_val++ = le64_to_cpu(*desc_data++); + + regs_num--; + if (!regs_num) + break; + } + } + + kfree(desc); + return 0; +} + +static int hclge_get_regs_len(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 regs_num_32_bit, regs_num_64_bit; + int ret; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return -EOPNOTSUPP; + } + + return regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64); +} + +static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, + void *data) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 regs_num_32_bit, regs_num_64_bit; + int ret; + + *version = hdev->fw_version; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return; + } + + ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, data); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get 32 bit register failed, ret = %d.\n", ret); + return; + } + + data = (u32 *)data + regs_num_32_bit; + ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, + data); + if (ret) + dev_err(&hdev->pdev->dev, + "Get 64 bit register failed, ret = %d.\n", ret); +} + +static int hclge_set_led_status_sfp(struct hclge_dev *hdev, u8 speed_led_status, + u8 act_led_status, u8 link_led_status, + u8 locate_led_status) +{ + struct hclge_set_led_state_cmd *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_LED_STATUS_CFG, false); + + req = (struct hclge_set_led_state_cmd *)desc.data; + hnae_set_field(req->port_speed_led_config, HCLGE_LED_PORT_SPEED_STATE_M, + HCLGE_LED_PORT_SPEED_STATE_S, speed_led_status); + hnae_set_field(req->link_led_config, HCLGE_LED_ACTIVITY_STATE_M, + HCLGE_LED_ACTIVITY_STATE_S, act_led_status); + hnae_set_field(req->activity_led_config, HCLGE_LED_LINK_STATE_M, + HCLGE_LED_LINK_STATE_S, link_led_status); + hnae_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M, + HCLGE_LED_LOCATE_STATE_S, locate_led_status); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "Send set led state cmd error, ret =%d\n", ret); + + return ret; +} + +enum hclge_led_status { + HCLGE_LED_OFF, + HCLGE_LED_ON, + HCLGE_LED_NO_CHANGE = 0xFF, +}; + +static int hclge_set_led_id(struct hnae3_handle *handle, + enum ethtool_phys_id_state status) +{ +#define BLINK_FREQUENCY 2 + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct phy_device *phydev = hdev->hw.mac.phydev; + int ret = 0; + + if (phydev || hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_FIBER) + return -EOPNOTSUPP; + + switch (status) { + case ETHTOOL_ID_ACTIVE: + ret = hclge_set_led_status_sfp(hdev, + HCLGE_LED_NO_CHANGE, + HCLGE_LED_NO_CHANGE, + HCLGE_LED_NO_CHANGE, + HCLGE_LED_ON); + break; + case ETHTOOL_ID_INACTIVE: + ret = hclge_set_led_status_sfp(hdev, + HCLGE_LED_NO_CHANGE, + HCLGE_LED_NO_CHANGE, + HCLGE_LED_NO_CHANGE, + HCLGE_LED_OFF); + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +enum hclge_led_port_speed { + HCLGE_SPEED_LED_FOR_1G, + HCLGE_SPEED_LED_FOR_10G, + HCLGE_SPEED_LED_FOR_25G, + HCLGE_SPEED_LED_FOR_40G, + HCLGE_SPEED_LED_FOR_50G, + HCLGE_SPEED_LED_FOR_100G, +}; + +static u8 hclge_led_get_speed_status(u32 speed) +{ + u8 speed_led; + + switch (speed) { + case HCLGE_MAC_SPEED_1G: + speed_led = HCLGE_SPEED_LED_FOR_1G; + break; + case HCLGE_MAC_SPEED_10G: + speed_led = HCLGE_SPEED_LED_FOR_10G; + break; + case HCLGE_MAC_SPEED_25G: + speed_led = HCLGE_SPEED_LED_FOR_25G; + break; + case HCLGE_MAC_SPEED_40G: + speed_led = HCLGE_SPEED_LED_FOR_40G; + break; + case HCLGE_MAC_SPEED_50G: + speed_led = HCLGE_SPEED_LED_FOR_50G; + break; + case HCLGE_MAC_SPEED_100G: + speed_led = HCLGE_SPEED_LED_FOR_100G; + break; + default: + speed_led = HCLGE_LED_NO_CHANGE; + } + + return speed_led; +} + +static int hclge_update_led_status(struct hclge_dev *hdev) +{ + u8 port_speed_status, link_status, activity_status; + u64 rx_pkts, tx_pkts; + + if (hdev->hw.mac.media_type != HNAE3_MEDIA_TYPE_FIBER) + return 0; + + port_speed_status = hclge_led_get_speed_status(hdev->hw.mac.speed); + + rx_pkts = hdev->hw_stats.mac_stats.mac_rx_total_pkt_num; + tx_pkts = hdev->hw_stats.mac_stats.mac_tx_total_pkt_num; + if (rx_pkts != hdev->rx_pkts_for_led || + tx_pkts != hdev->tx_pkts_for_led) + activity_status = HCLGE_LED_ON; + else + activity_status = HCLGE_LED_OFF; + hdev->rx_pkts_for_led = rx_pkts; + hdev->tx_pkts_for_led = tx_pkts; + + if (hdev->hw.mac.link) + link_status = HCLGE_LED_ON; + else + link_status = HCLGE_LED_OFF; + + return hclge_set_led_status_sfp(hdev, port_speed_status, + activity_status, link_status, + HCLGE_LED_NO_CHANGE); +} + static const struct hnae3_ae_ops hclge_ops = { .init_ae_dev = hclge_init_ae_dev, .uninit_ae_dev = hclge_uninit_ae_dev, @@ -5595,6 +6048,9 @@ static const struct hnae3_ae_ops hclge_ops = { .set_channels = hclge_set_channels, .get_channels = hclge_get_channels, .get_flowctrl_adv = hclge_get_flowctrl_adv, + .get_regs_len = hclge_get_regs_len, + .get_regs = hclge_get_regs, + .set_led_id = hclge_set_led_id, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index eeb6c8d66e4e..d99a76a9557c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -550,6 +550,9 @@ struct hclge_dev { bool accept_mta_mc; /* Whether accept mta filter multicast */ struct hclge_vlan_type_cfg vlan_type_cfg; + + u64 rx_pkts_for_led; + u64 tx_pkts_for_led; }; /* VPort level vlan tag configuration for TX direction */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 96f453ff84b5..f38fc5ce9f51 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -116,6 +116,9 @@ static int hclge_get_ring_chain_from_mbx( hnae_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]); ring_chain->tqp_index = hclge_get_queue_id(vport->nic.kinfo.tqp[req->msg[4]]); + hnae_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + req->msg[5]); cur_chain = ring_chain; @@ -133,6 +136,11 @@ static int hclge_get_ring_chain_from_mbx( [req->msg[HCLGE_RING_NODE_VARIABLE_NUM * i + HCLGE_RING_MAP_MBX_BASIC_MSG_NUM + 1]]); + hnae_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M, + HCLGE_INT_GL_IDX_S, + req->msg[HCLGE_RING_NODE_VARIABLE_NUM * i + + HCLGE_RING_MAP_MBX_BASIC_MSG_NUM + 2]); + cur_chain->next = new_chain; cur_chain = new_chain; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 3d2bc9a971fa..0d89965f7928 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -565,6 +565,11 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en, hnae_get_bit(node->flag, HNAE3_RING_TYPE_B); req->msg[HCLGEVF_RING_NODE_VARIABLE_NUM * i + 1] = node->tqp_index; + req->msg[HCLGEVF_RING_NODE_VARIABLE_NUM * i + 2] = + hnae_get_field(node->int_gl_idx, + HNAE3_RING_GL_IDX_M, + HNAE3_RING_GL_IDX_S); + if (i == (HCLGE_MBX_VF_MSG_DATA_NUM - HCLGEVF_RING_MAP_MBX_BASIC_MSG_NUM) / HCLGEVF_RING_NODE_VARIABLE_NUM) { diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 71ddad13baf4..354c0982847b 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -494,6 +494,9 @@ static u32 __emac_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_s case 16384: ret |= EMAC_MR1_RFS_16K; break; + case 8192: + ret |= EMAC4_MR1_RFS_8K; + break; case 4096: ret |= EMAC_MR1_RFS_4K; break; @@ -516,6 +519,9 @@ static u32 __emac4_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_ case 16384: ret |= EMAC4_MR1_TFS_16K; break; + case 8192: + ret |= EMAC4_MR1_TFS_8K; + break; case 4096: ret |= EMAC4_MR1_TFS_4K; break; diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h index bc14dcf27b6b..e2f80cca9bed 100644 --- a/drivers/net/ethernet/ibm/emac/emac.h +++ b/drivers/net/ethernet/ibm/emac/emac.h @@ -138,9 +138,11 @@ struct emac_regs { #define EMAC4_MR1_RFS_2K 0x00100000 #define EMAC4_MR1_RFS_4K 0x00180000 +#define EMAC4_MR1_RFS_8K 0x00200000 #define EMAC4_MR1_RFS_16K 0x00280000 #define EMAC4_MR1_TFS_2K 0x00020000 #define EMAC4_MR1_TFS_4K 0x00030000 +#define EMAC4_MR1_TFS_8K 0x00040000 #define EMAC4_MR1_TFS_16K 0x00050000 #define EMAC4_MR1_TR 0x00008000 #define EMAC4_MR1_MWSW_001 0x00001000 @@ -229,7 +231,7 @@ struct emac_regs { #define EMAC_STACR_PHYE 0x00004000 #define EMAC_STACR_STAC_MASK 0x00003000 #define EMAC_STACR_STAC_READ 0x00001000 -#define EMAC_STACR_STAC_WRITE 0x00002000 +#define EMAC_STACR_STAC_WRITE 0x00000800 #define EMAC_STACR_OPBC_MASK 0x00000C00 #define EMAC_STACR_OPBC_50 0x00000000 #define EMAC_STACR_OPBC_66 0x00000400 diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index be2ce8dece4a..8f2a77ecf4fb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -411,6 +411,10 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) struct ibmvnic_rx_pool *rx_pool; int rx_scrqs; int i, j, rc; + u64 *size_array; + + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); for (i = 0; i < rx_scrqs; i++) { @@ -418,7 +422,17 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i); - rc = reset_long_term_buff(adapter, &rx_pool->long_term_buff); + if (rx_pool->buff_size != be64_to_cpu(size_array[i])) { + free_long_term_buff(adapter, &rx_pool->long_term_buff); + rx_pool->buff_size = be64_to_cpu(size_array[i]); + alloc_long_term_buff(adapter, &rx_pool->long_term_buff, + rx_pool->size * + rx_pool->buff_size); + } else { + rc = reset_long_term_buff(adapter, + &rx_pool->long_term_buff); + } + if (rc) return rc; @@ -440,14 +454,12 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) static void release_rx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_rx_pool *rx_pool; - int rx_scrqs; int i, j; if (!adapter->rx_pool) return; - rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); - for (i = 0; i < rx_scrqs; i++) { + for (i = 0; i < adapter->num_active_rx_pools; i++) { rx_pool = &adapter->rx_pool[i]; netdev_dbg(adapter->netdev, "Releasing rx_pool[%d]\n", i); @@ -470,6 +482,7 @@ static void release_rx_pools(struct ibmvnic_adapter *adapter) kfree(adapter->rx_pool); adapter->rx_pool = NULL; + adapter->num_active_rx_pools = 0; } static int init_rx_pools(struct net_device *netdev) @@ -494,6 +507,8 @@ static int init_rx_pools(struct net_device *netdev) return -1; } + adapter->num_active_rx_pools = 0; + for (i = 0; i < rxadd_subcrqs; i++) { rx_pool = &adapter->rx_pool[i]; @@ -537,6 +552,8 @@ static int init_rx_pools(struct net_device *netdev) rx_pool->next_free = 0; } + adapter->num_active_rx_pools = rxadd_subcrqs; + return 0; } @@ -587,13 +604,12 @@ static void release_vpd_data(struct ibmvnic_adapter *adapter) static void release_tx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_tx_pool *tx_pool; - int i, tx_scrqs; + int i; if (!adapter->tx_pool) return; - tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); - for (i = 0; i < tx_scrqs; i++) { + for (i = 0; i < adapter->num_active_tx_pools; i++) { netdev_dbg(adapter->netdev, "Releasing tx_pool[%d]\n", i); tx_pool = &adapter->tx_pool[i]; kfree(tx_pool->tx_buff); @@ -604,6 +620,7 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter) kfree(adapter->tx_pool); adapter->tx_pool = NULL; + adapter->num_active_tx_pools = 0; } static int init_tx_pools(struct net_device *netdev) @@ -620,6 +637,8 @@ static int init_tx_pools(struct net_device *netdev) if (!adapter->tx_pool) return -1; + adapter->num_active_tx_pools = 0; + for (i = 0; i < tx_subcrqs; i++) { tx_pool = &adapter->tx_pool[i]; @@ -667,6 +686,8 @@ static int init_tx_pools(struct net_device *netdev) tx_pool->producer_index = 0; } + adapter->num_active_tx_pools = tx_subcrqs; + return 0; } @@ -861,7 +882,7 @@ static int ibmvnic_get_vpd(struct ibmvnic_adapter *adapter) if (adapter->vpd->buff) len = adapter->vpd->len; - reinit_completion(&adapter->fw_done); + init_completion(&adapter->fw_done); crq.get_vpd_size.first = IBMVNIC_CRQ_CMD; crq.get_vpd_size.cmd = GET_VPD_SIZE; ibmvnic_send_crq(adapter, &crq); @@ -923,6 +944,13 @@ static int init_resources(struct ibmvnic_adapter *adapter) if (!adapter->vpd) return -ENOMEM; + /* Vital Product Data (VPD) */ + rc = ibmvnic_get_vpd(adapter); + if (rc) { + netdev_err(netdev, "failed to initialize Vital Product Data (VPD)\n"); + return rc; + } + adapter->map_id = 1; adapter->napi = kcalloc(adapter->req_rx_queues, sizeof(struct napi_struct), GFP_KERNEL); @@ -996,7 +1024,7 @@ static int __ibmvnic_open(struct net_device *netdev) static int ibmvnic_open(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int rc, vpd; + int rc; mutex_lock(&adapter->reset_lock); @@ -1019,11 +1047,6 @@ static int ibmvnic_open(struct net_device *netdev) rc = __ibmvnic_open(netdev); netif_carrier_on(netdev); - /* Vital Product Data (VPD) */ - vpd = ibmvnic_get_vpd(adapter); - if (vpd) - netdev_err(netdev, "failed to initialize Vital Product Data (VPD)\n"); - mutex_unlock(&adapter->reset_lock); return rc; @@ -1553,6 +1576,7 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) static int do_reset(struct ibmvnic_adapter *adapter, struct ibmvnic_rwi *rwi, u32 reset_state) { + u64 old_num_rx_queues, old_num_tx_queues; struct net_device *netdev = adapter->netdev; int i, rc; @@ -1562,6 +1586,9 @@ static int do_reset(struct ibmvnic_adapter *adapter, netif_carrier_off(netdev); adapter->reset_reason = rwi->reset_reason; + old_num_rx_queues = adapter->req_rx_queues; + old_num_tx_queues = adapter->req_tx_queues; + if (rwi->reset_reason == VNIC_RESET_MOBILITY) { rc = ibmvnic_reenable_crq_queue(adapter); if (rc) @@ -1606,6 +1633,12 @@ static int do_reset(struct ibmvnic_adapter *adapter, rc = init_resources(adapter); if (rc) return rc; + } else if (adapter->req_rx_queues != old_num_rx_queues || + adapter->req_tx_queues != old_num_tx_queues) { + release_rx_pools(adapter); + release_tx_pools(adapter); + init_rx_pools(netdev); + init_tx_pools(netdev); } else { rc = reset_tx_pools(adapter); if (rc) @@ -3603,7 +3636,17 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, *req_value, (long int)be64_to_cpu(crq->request_capability_rsp. number), name); - *req_value = be64_to_cpu(crq->request_capability_rsp.number); + + if (be16_to_cpu(crq->request_capability_rsp.capability) == + REQ_MTU) { + pr_err("mtu of %llu is not supported. Reverting.\n", + *req_value); + *req_value = adapter->fallback.mtu; + } else { + *req_value = + be64_to_cpu(crq->request_capability_rsp.number); + } + ibmvnic_send_req_caps(adapter, 1); return; default: diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 2df79fdd800b..fe21a6e2ddae 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -1091,6 +1091,8 @@ struct ibmvnic_adapter { u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; u8 map_id; + u64 num_active_rx_pools; + u64 num_active_tx_pools; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 9f18d39bdc8f..1298b69f990b 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3303,9 +3303,11 @@ static void e1000_configure_rx(struct e1000_adapter *adapter) if (adapter->flags & FLAG_IS_ICH) { u32 rxdctl = er32(RXDCTL(0)); - ew32(RXDCTL(0), rxdctl | 0x3); + ew32(RXDCTL(0), rxdctl | 0x3 | BIT(8)); } + dev_info(&adapter->pdev->dev, + "Some CPU C-states have been disabled in order to enable jumbo frames\n"); pm_qos_update_request(&adapter->pm_qos_req, lat); } else { pm_qos_update_request(&adapter->pm_qos_req, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index ea3ab24265ee..760cfa52d02c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -353,7 +353,7 @@ int fm10k_iov_resume(struct pci_dev *pdev) struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; /* allocate all but the last GLORT to the VFs */ - if (i == ((~hw->mac.dglort_map) >> FM10K_DGLORTMAP_MASK_SHIFT)) + if (i == (~hw->mac.dglort_map >> FM10K_DGLORTMAP_MASK_SHIFT)) break; /* assign GLORT to VF, and restrict it to multicast */ @@ -511,7 +511,7 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) return err; /* allocate VFs if not already allocated */ - if (num_vfs && (num_vfs != current_vfs)) { + if (num_vfs && num_vfs != current_vfs) { /* Disable completer abort error reporting as * the VFs can trigger this any time they read a queue * that they don't own. diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index adc62fb38c49..a38ae5c54da3 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -934,8 +934,12 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) if (vid >= VLAN_N_VID) return -EINVAL; - /* Verify we have permission to add VLANs */ - if (hw->mac.vlan_override) + /* Verify that we have permission to add VLANs. If this is a request + * to remove a VLAN, we still want to allow the user to remove the + * VLAN device. In that case, we need to clear the bit in the + * active_vlans bitmask. + */ + if (set && hw->mac.vlan_override) return -EACCES; /* update active_vlans bitmask */ @@ -954,6 +958,12 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) rx_ring->vid &= ~FM10K_VLAN_CLEAR; } + /* If our VLAN has been overridden, there is no reason to send VLAN + * removal requests as they will be silently ignored. + */ + if (hw->mac.vlan_override) + return 0; + /* Do not remove default VLAN ID related entries from VLAN and MAC * tables */ @@ -1040,14 +1050,13 @@ static int __fm10k_uc_sync(struct net_device *dev, const unsigned char *addr, bool sync) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_hw *hw = &interface->hw; u16 vid, glort = interface->glort; s32 err; if (!is_valid_ether_addr(addr)) return -EADDRNOTAVAIL; - for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; + for (vid = fm10k_find_next_vlan(interface, 0); vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { err = fm10k_queue_mac_request(interface, glort, @@ -1106,14 +1115,13 @@ static int __fm10k_mc_sync(struct net_device *dev, const unsigned char *addr, bool sync) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_hw *hw = &interface->hw; u16 vid, glort = interface->glort; s32 err; if (!is_multicast_ether_addr(addr)) return -EADDRNOTAVAIL; - for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; + for (vid = fm10k_find_next_vlan(interface, 0); vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { err = fm10k_queue_mac_request(interface, glort, @@ -1157,10 +1165,12 @@ static void fm10k_set_rx_mode(struct net_device *dev) /* update xcast mode first, but only if it changed */ if (interface->xcast_mode != xcast_mode) { - /* update VLAN table */ + /* update VLAN table when entering promiscuous mode */ if (xcast_mode == FM10K_XCAST_MODE_PROMISC) fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0, true); + + /* clear VLAN table when exiting promiscuous mode */ if (interface->xcast_mode == FM10K_XCAST_MODE_PROMISC) fm10k_clear_unused_vlans(interface); @@ -1182,9 +1192,10 @@ static void fm10k_set_rx_mode(struct net_device *dev) void fm10k_restore_rx_state(struct fm10k_intfc *interface) { + struct fm10k_l2_accel *l2_accel = interface->l2_accel; struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; - int xcast_mode; + int xcast_mode, i; u16 vid, glort; /* record glort for this interface */ @@ -1211,11 +1222,8 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) fm10k_queue_vlan_request(interface, FM10K_VLAN_ALL, 0, xcast_mode == FM10K_XCAST_MODE_PROMISC); - /* Add filter for VLAN 0 */ - fm10k_queue_vlan_request(interface, 0, 0, true); - /* update table with current entries */ - for (vid = hw->mac.default_vid ? fm10k_find_next_vlan(interface, 0) : 1; + for (vid = fm10k_find_next_vlan(interface, 0); vid < VLAN_N_VID; vid = fm10k_find_next_vlan(interface, vid)) { fm10k_queue_vlan_request(interface, vid, 0, true); @@ -1234,6 +1242,24 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) __dev_uc_sync(netdev, fm10k_uc_sync, fm10k_uc_unsync); __dev_mc_sync(netdev, fm10k_mc_sync, fm10k_mc_unsync); + /* synchronize macvlan addresses */ + if (l2_accel) { + for (i = 0; i < l2_accel->size; i++) { + struct net_device *sdev = l2_accel->macvlan[i]; + + if (!sdev) + continue; + + glort = l2_accel->dglort + 1 + i; + + hw->mac.ops.update_xcast_mode(hw, glort, + FM10K_XCAST_MODE_MULTI); + fm10k_queue_mac_request(interface, glort, + sdev->dev_addr, + hw->mac.default_vid, true); + } + } + fm10k_mbx_unlock(interface); /* record updated xcast mode state */ @@ -1490,7 +1516,7 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_MULTI); fm10k_queue_mac_request(interface, glort, sdev->dev_addr, - 0, true); + hw->mac.default_vid, true); } fm10k_mbx_unlock(interface); @@ -1530,7 +1556,7 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE); fm10k_queue_mac_request(interface, glort, sdev->dev_addr, - 0, false); + hw->mac.default_vid, false); } fm10k_mbx_unlock(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 425d814aed4d..d6406fc31ffb 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -866,7 +866,7 @@ static s32 fm10k_iov_assign_default_mac_vlan_pf(struct fm10k_hw *hw, /* Determine correct default VLAN ID. The FM10K_VLAN_OVERRIDE bit is * used here to indicate to the VF that it will not have privilege to * write VLAN_TABLE. All policy is enforced on the PF but this allows - * the VF to correctly report errors to userspace rqeuests. + * the VF to correctly report errors to userspace requests. */ if (vf_info->pf_vid) vf_vid = vf_info->pf_vid | FM10K_VLAN_OVERRIDE; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index e019baa905c5..46e9f4e0a02c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -508,39 +508,40 @@ struct i40e_pf { #define I40E_HW_PORT_ID_VALID BIT(17) #define I40E_HW_RESTART_AUTONEG BIT(18) - u32 flags; -#define I40E_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40E_FLAG_MSI_ENABLED BIT(1) -#define I40E_FLAG_MSIX_ENABLED BIT(2) -#define I40E_FLAG_RSS_ENABLED BIT(3) -#define I40E_FLAG_VMDQ_ENABLED BIT(4) -#define I40E_FLAG_FILTER_SYNC BIT(5) -#define I40E_FLAG_SRIOV_ENABLED BIT(6) -#define I40E_FLAG_DCB_CAPABLE BIT(7) -#define I40E_FLAG_DCB_ENABLED BIT(8) -#define I40E_FLAG_FD_SB_ENABLED BIT(9) -#define I40E_FLAG_FD_ATR_ENABLED BIT(10) -#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT(11) -#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT(12) -#define I40E_FLAG_MFP_ENABLED BIT(13) -#define I40E_FLAG_UDP_FILTER_SYNC BIT(14) -#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT(15) -#define I40E_FLAG_VEB_MODE_ENABLED BIT(16) -#define I40E_FLAG_VEB_STATS_ENABLED BIT(17) -#define I40E_FLAG_LINK_POLLING_ENABLED BIT(18) -#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT(19) -#define I40E_FLAG_TEMP_LINK_POLLING BIT(20) -#define I40E_FLAG_LEGACY_RX BIT(21) -#define I40E_FLAG_PTP BIT(22) -#define I40E_FLAG_IWARP_ENABLED BIT(23) -#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT(24) -#define I40E_FLAG_CLIENT_L2_CHANGE BIT(25) -#define I40E_FLAG_CLIENT_RESET BIT(26) -#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT(27) -#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT(28) -#define I40E_FLAG_TC_MQPRIO BIT(29) -#define I40E_FLAG_FD_SB_INACTIVE BIT(30) -#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER BIT(31) + u64 flags; +#define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(0) +#define I40E_FLAG_MSI_ENABLED BIT_ULL(1) +#define I40E_FLAG_MSIX_ENABLED BIT_ULL(2) +#define I40E_FLAG_RSS_ENABLED BIT_ULL(3) +#define I40E_FLAG_VMDQ_ENABLED BIT_ULL(4) +#define I40E_FLAG_FILTER_SYNC BIT_ULL(5) +#define I40E_FLAG_SRIOV_ENABLED BIT_ULL(6) +#define I40E_FLAG_DCB_CAPABLE BIT_ULL(7) +#define I40E_FLAG_DCB_ENABLED BIT_ULL(8) +#define I40E_FLAG_FD_SB_ENABLED BIT_ULL(9) +#define I40E_FLAG_FD_ATR_ENABLED BIT_ULL(10) +#define I40E_FLAG_FD_SB_AUTO_DISABLED BIT_ULL(11) +#define I40E_FLAG_FD_ATR_AUTO_DISABLED BIT_ULL(12) +#define I40E_FLAG_MFP_ENABLED BIT_ULL(13) +#define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(14) +#define I40E_FLAG_HW_ATR_EVICT_ENABLED BIT_ULL(15) +#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(16) +#define I40E_FLAG_VEB_STATS_ENABLED BIT_ULL(17) +#define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(18) +#define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(19) +#define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(20) +#define I40E_FLAG_LEGACY_RX BIT_ULL(21) +#define I40E_FLAG_PTP BIT_ULL(22) +#define I40E_FLAG_IWARP_ENABLED BIT_ULL(23) +#define I40E_FLAG_SERVICE_CLIENT_REQUESTED BIT_ULL(24) +#define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(25) +#define I40E_FLAG_CLIENT_RESET BIT_ULL(26) +#define I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED BIT_ULL(27) +#define I40E_FLAG_SOURCE_PRUNING_DISABLED BIT_ULL(28) +#define I40E_FLAG_TC_MQPRIO BIT_ULL(29) +#define I40E_FLAG_FD_SB_INACTIVE BIT_ULL(30) +#define I40E_FLAG_FD_SB_TO_CLOUD_FILTER BIT_ULL(31) +#define I40E_FLAG_DISABLE_FW_LLDP BIT_ULL(32) struct i40e_client_instance *cinst; bool stat_offsets_loaded; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 9af74253c3f7..e78971605e0b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -907,10 +907,15 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw, /* update the error if time out occurred */ if ((!cmd_completed) && (!details->async && !details->postpone)) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, - "AQTX: Writeback timeout.\n"); - status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; + if (rd32(hw, hw->aq.asq.len) & I40E_GL_ATQLEN_ATQCRIT_MASK) { + i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + "AQTX: AQ Critical error.\n"); + status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR; + } else { + i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + "AQTX: Writeback timeout.\n"); + status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; + } } asq_send_command_error: @@ -971,7 +976,7 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw, } /* set next_to_use to head */ - ntu = (rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK); + ntu = rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK; if (ntu == ntc) { /* nothing to do - shouldn't need to update ring's values */ ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK; @@ -1027,7 +1032,7 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw, hw->aq.arq.next_to_clean = ntc; hw->aq.arq.next_to_use = ntu; - i40e_nvmupd_check_wait_event(hw, le16_to_cpu(e->desc.opcode)); + i40e_nvmupd_check_wait_event(hw, le16_to_cpu(e->desc.opcode), &e->desc); clean_arq_element_out: /* Set pending if needed, unlock and return */ if (pending) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index c5776340517c..a852775d3059 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -205,6 +205,7 @@ enum i40e_admin_queue_opc { /* DCB commands */ i40e_aqc_opc_dcb_ignore_pfc = 0x0301, i40e_aqc_opc_dcb_updated = 0x0302, + i40e_aqc_opc_set_dcb_parameters = 0x0303, /* TX scheduler */ i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, @@ -2231,8 +2232,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); */ struct i40e_aqc_nvm_update { u8 command_flags; -#define I40E_AQ_NVM_LAST_CMD 0x01 -#define I40E_AQ_NVM_FLASH_ONLY 0x80 +#define I40E_AQ_NVM_LAST_CMD 0x01 +#define I40E_AQ_NVM_FLASH_ONLY 0x80 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT 1 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK 0x03 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED 0x03 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_ALL 0x01 u8 module_pointer; __le16 length; __le32 offset; @@ -2492,6 +2497,17 @@ struct i40e_aqc_lldp_start { I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start); +/* Set DCB (direct 0x0303) */ +struct i40e_aqc_set_dcb_parameters { + u8 command; +#define I40E_AQ_DCB_SET_AGENT 0x1 +#define I40E_DCB_VALID 0x1 + u8 valid_flags; + u8 reserved[14]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_dcb_parameters); + /* Get CEE DCBX Oper Config (0x0A07) * uses the generic descriptor struct * returns below as indirect response diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 1b1e2acbd07f..0de9610c1d8d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -378,11 +378,11 @@ void i40e_client_subtask(struct i40e_pf *pf) if (!client || !cdev) return; - /* Here we handle client opens. If the client is down, but - * the netdev is up, then open the client. + /* Here we handle client opens. If the client is down, and + * the netdev is registered, then open the client. */ if (!test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { - if (!test_bit(__I40E_VSI_DOWN, vsi->state) && + if (vsi->netdev_registered && client->ops && client->ops->open) { set_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); ret = client->ops->open(&cdev->lan_info, client); @@ -393,17 +393,19 @@ void i40e_client_subtask(struct i40e_pf *pf) i40e_client_del_instance(pf); } } - } else { - /* Likewise for client close. If the client is up, but the netdev - * is down, then close the client. - */ - if (test_bit(__I40E_VSI_DOWN, vsi->state) && - client->ops && client->ops->close) { - clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); - client->ops->close(&cdev->lan_info, client, false); - i40e_client_release_qvlist(&cdev->lan_info); - } } + + /* enable/disable PE TCP_ENA flag based on netdev down/up + */ + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + i40e_client_update_vsi_ctxt(&cdev->lan_info, client, + 0, 0, 0, + I40E_CLIENT_VSI_FLAG_TCP_ENABLE); + else + i40e_client_update_vsi_ctxt(&cdev->lan_info, client, + 0, 0, + I40E_CLIENT_VSI_FLAG_TCP_ENABLE, + I40E_CLIENT_VSI_FLAG_TCP_ENABLE); } /** @@ -717,13 +719,13 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, return -ENOENT; } - if ((valid_flag & I40E_CLIENT_VSI_FLAG_TCP_PACKET_ENABLE) && - (flag & I40E_CLIENT_VSI_FLAG_TCP_PACKET_ENABLE)) { + if ((valid_flag & I40E_CLIENT_VSI_FLAG_TCP_ENABLE) && + (flag & I40E_CLIENT_VSI_FLAG_TCP_ENABLE)) { ctxt.info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID); ctxt.info.queueing_opt_flags |= I40E_AQ_VSI_QUE_OPT_TCP_ENA; - } else if ((valid_flag & I40E_CLIENT_VSI_FLAG_TCP_PACKET_ENABLE) && - !(flag & I40E_CLIENT_VSI_FLAG_TCP_PACKET_ENABLE)) { + } else if ((valid_flag & I40E_CLIENT_VSI_FLAG_TCP_ENABLE) && + !(flag & I40E_CLIENT_VSI_FLAG_TCP_ENABLE)) { ctxt.info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_QUEUE_OPT_VALID); ctxt.info.queueing_opt_flags &= ~I40E_AQ_VSI_QUE_OPT_TCP_ENA; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h index 15b21a5315b5..ba55c889e4c5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.h +++ b/drivers/net/ethernet/intel/i40e/i40e_client.h @@ -132,7 +132,7 @@ struct i40e_info { #define I40E_CLIENT_RESET_LEVEL_PF 1 #define I40E_CLIENT_RESET_LEVEL_CORE 2 -#define I40E_CLIENT_VSI_FLAG_TCP_PACKET_ENABLE BIT(1) +#define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) struct i40e_ops { /* setup_q_vector_list enables queues with a particular vector */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 40c5f7628aa1..ef5a868aae46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -278,6 +278,8 @@ const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err) return "I40E_NOT_SUPPORTED"; case I40E_ERR_FIRMWARE_API_VERSION: return "I40E_ERR_FIRMWARE_API_VERSION"; + case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; } snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); @@ -1486,6 +1488,7 @@ u32 i40e_led_get(struct i40e_hw *hw) case I40E_COMBINED_ACTIVITY: case I40E_FILTER_ACTIVITY: case I40E_MAC_ACTIVITY: + case I40E_LINK_ACTIVITY: continue; default: break; @@ -1534,6 +1537,7 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink) case I40E_COMBINED_ACTIVITY: case I40E_FILTER_ACTIVITY: case I40E_MAC_ACTIVITY: + case I40E_LINK_ACTIVITY: continue; default: break; @@ -1544,9 +1548,6 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink) gpio_val |= ((mode << I40E_GLGEN_GPIO_CTL_LED_MODE_SHIFT) & I40E_GLGEN_GPIO_CTL_LED_MODE_MASK); - if (mode == I40E_LINK_ACTIVITY) - blink = false; - if (blink) gpio_val |= BIT(I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT); else @@ -3465,13 +3466,14 @@ exit: * @length: length of the section to be written (in bytes from the offset) * @data: command buffer (size [bytes] = length) * @last_command: tells if this is the last command in a series + * @preservation_flags: Preservation mode flags * @cmd_details: pointer to command details structure or NULL * * Update the NVM using the admin queue commands **/ i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, u32 offset, u16 length, void *data, - bool last_command, + bool last_command, u8 preservation_flags, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; @@ -3490,6 +3492,16 @@ i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, /* If this is the last command in a series, set the proper flag. */ if (last_command) cmd->command_flags |= I40E_AQ_NVM_LAST_CMD; + if (hw->mac.type == I40E_MAC_X722) { + if (preservation_flags == I40E_NVM_PRESERVATION_FLAGS_SELECTED) + cmd->command_flags |= + (I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED << + I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT); + else if (preservation_flags == I40E_NVM_PRESERVATION_FLAGS_ALL) + cmd->command_flags |= + (I40E_AQ_NVM_PRESERVATION_FLAGS_ALL << + I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT); + } cmd->module_pointer = module_pointer; cmd->offset = cpu_to_le32(offset); cmd->length = cpu_to_le16(length); @@ -3629,7 +3641,34 @@ i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start); cmd->command = I40E_AQ_LLDP_AGENT_START; + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + return status; +} +/** + * i40e_aq_set_dcb_parameters + * @hw: pointer to the hw struct + * @cmd_details: pointer to command details structure or NULL + * @dcb_enable: True if DCB configuration needs to be applied + * + **/ +enum i40e_status_code +i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_set_dcb_parameters *cmd = + (struct i40e_aqc_set_dcb_parameters *)&desc.params.raw; + i40e_status status; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_dcb_parameters); + + if (dcb_enable) { + cmd->valid_flags = I40E_DCB_VALID; + cmd->command = I40E_AQ_DCB_SET_AGENT; + } status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); return status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 34173f821fd9..2f5bee713fef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -233,6 +233,7 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("legacy-rx", I40E_FLAG_LEGACY_RX, 0), I40E_PRIV_FLAG("disable-source-pruning", I40E_FLAG_SOURCE_PRUNING_DISABLED, 0), + I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) @@ -2305,6 +2306,8 @@ static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, struct ethtool_coalesce *ec, int queue) { + struct i40e_ring *rx_ring = vsi->rx_rings[queue]; + struct i40e_ring *tx_ring = vsi->tx_rings[queue]; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; struct i40e_q_vector *q_vector; @@ -2312,26 +2315,26 @@ static void i40e_set_itr_per_queue(struct i40e_vsi *vsi, intrl = i40e_intrl_usec_to_reg(vsi->int_rate_limit); - vsi->rx_rings[queue]->rx_itr_setting = ec->rx_coalesce_usecs; - vsi->tx_rings[queue]->tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; + tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; if (ec->use_adaptive_rx_coalesce) - vsi->rx_rings[queue]->rx_itr_setting |= I40E_ITR_DYNAMIC; + rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; else - vsi->rx_rings[queue]->rx_itr_setting &= ~I40E_ITR_DYNAMIC; + rx_ring->rx_itr_setting &= ~I40E_ITR_DYNAMIC; if (ec->use_adaptive_tx_coalesce) - vsi->tx_rings[queue]->tx_itr_setting |= I40E_ITR_DYNAMIC; + tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; else - vsi->tx_rings[queue]->tx_itr_setting &= ~I40E_ITR_DYNAMIC; + tx_ring->tx_itr_setting &= ~I40E_ITR_DYNAMIC; - q_vector = vsi->rx_rings[queue]->q_vector; - q_vector->rx.itr = ITR_TO_REG(vsi->rx_rings[queue]->rx_itr_setting); + q_vector = rx_ring->q_vector; + q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); vector = vsi->base_vector + q_vector->v_idx; wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1), q_vector->rx.itr); - q_vector = vsi->tx_rings[queue]->q_vector; - q_vector->tx.itr = ITR_TO_REG(vsi->tx_rings[queue]->tx_itr_setting); + q_vector = tx_ring->q_vector; + q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); vector = vsi->base_vector + q_vector->v_idx; wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1), q_vector->tx.itr); @@ -2746,16 +2749,16 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, no_input_set: if (input_set & I40E_L3_SRC_MASK) - fsp->m_u.tcp_ip4_spec.ip4src = htonl(0xFFFF); + fsp->m_u.tcp_ip4_spec.ip4src = htonl(0xFFFFFFFF); if (input_set & I40E_L3_DST_MASK) - fsp->m_u.tcp_ip4_spec.ip4dst = htonl(0xFFFF); + fsp->m_u.tcp_ip4_spec.ip4dst = htonl(0xFFFFFFFF); if (input_set & I40E_L4_SRC_MASK) - fsp->m_u.tcp_ip4_spec.psrc = htons(0xFFFFFFFF); + fsp->m_u.tcp_ip4_spec.psrc = htons(0xFFFF); if (input_set & I40E_L4_DST_MASK) - fsp->m_u.tcp_ip4_spec.pdst = htons(0xFFFFFFFF); + fsp->m_u.tcp_ip4_spec.pdst = htons(0xFFFF); if (rule->dest_ctl == I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET) fsp->ring_cookie = RX_CLS_FLOW_DISC; @@ -3806,6 +3809,16 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, i40e_write_fd_input_set(pf, index, new_mask); + /* IP_USER_FLOW filters match both IPv4/Other and IPv4/Fragmented + * frames. If we're programming the input set for IPv4/Other, we also + * need to program the IPv4/Fragmented input set. Since we don't have + * separate support, we'll always assume and enforce that the two flow + * types must have matching input sets. + */ + if (index == I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4, + new_mask); + /* Add the new offset and update table, if necessary */ if (new_flex_offset) { err = i40e_add_flex_offset(&pf->l4_flex_pit_list, src_offset, @@ -3828,6 +3841,87 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, } /** + * i40e_match_fdir_filter - Return true of two filters match + * @a: pointer to filter struct + * @b: pointer to filter struct + * + * Returns true if the two filters match exactly the same criteria. I.e. they + * match the same flow type and have the same parameters. We don't need to + * check any input-set since all filters of the same flow type must use the + * same input set. + **/ +static bool i40e_match_fdir_filter(struct i40e_fdir_filter *a, + struct i40e_fdir_filter *b) +{ + /* The filters do not much if any of these criteria differ. */ + if (a->dst_ip != b->dst_ip || + a->src_ip != b->src_ip || + a->dst_port != b->dst_port || + a->src_port != b->src_port || + a->flow_type != b->flow_type || + a->ip4_proto != b->ip4_proto) + return false; + + return true; +} + +/** + * i40e_disallow_matching_filters - Check that new filters differ + * @vsi: pointer to the targeted VSI + * @input: new filter to check + * + * Due to hardware limitations, it is not possible for two filters that match + * similar criteria to be programmed at the same time. This is true for a few + * reasons: + * + * (a) all filters matching a particular flow type must use the same input + * set, that is they must match the same criteria. + * (b) different flow types will never match the same packet, as the flow type + * is decided by hardware before checking which rules apply. + * (c) hardware has no way to distinguish which order filters apply in. + * + * Due to this, we can't really support using the location data to order + * filters in the hardware parsing. It is technically possible for the user to + * request two filters matching the same criteria but which select different + * queues. In this case, rather than keep both filters in the list, we reject + * the 2nd filter when the user requests adding it. + * + * This avoids needing to track location for programming the filter to + * hardware, and ensures that we avoid some strange scenarios involving + * deleting filters which match the same criteria. + **/ +static int i40e_disallow_matching_filters(struct i40e_vsi *vsi, + struct i40e_fdir_filter *input) +{ + struct i40e_pf *pf = vsi->back; + struct i40e_fdir_filter *rule; + struct hlist_node *node2; + + /* Loop through every filter, and check that it doesn't match */ + hlist_for_each_entry_safe(rule, node2, + &pf->fdir_filter_list, fdir_node) { + /* Don't check the filters match if they share the same fd_id, + * since the new filter is actually just updating the target + * of the old filter. + */ + if (rule->fd_id == input->fd_id) + continue; + + /* If any filters match, then print a warning message to the + * kernel message buffer and bail out. + */ + if (i40e_match_fdir_filter(rule, input)) { + dev_warn(&pf->pdev->dev, + "Existing user defined filter %d already matches this flow.\n", + rule->fd_id); + return -EINVAL; + } + } + + return 0; +} + +/** * i40e_add_fdir_ethtool - Add/Remove Flow Director filters * @vsi: pointer to the targeted VSI * @cmd: command to get or set RX flow classification rules @@ -3939,19 +4033,25 @@ static int i40e_add_fdir_ethtool(struct i40e_vsi *vsi, input->flex_offset = userdef.flex_offset; } - ret = i40e_add_del_fdir(vsi, input, true); + /* Avoid programming two filters with identical match criteria. */ + ret = i40e_disallow_matching_filters(vsi, input); if (ret) - goto free_input; + goto free_filter_memory; /* Add the input filter to the fdir_input_list, possibly replacing * a previous filter. Do not free the input structure after adding it * to the list as this would cause a use-after-free bug. */ i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL); - + ret = i40e_add_del_fdir(vsi, input, true); + if (ret) + goto remove_sw_rule; return 0; -free_input: +remove_sw_rule: + hlist_del(&input->fdir_node); + pf->fdir_pf_active_filters--; +free_filter_memory: kfree(input); return ret; } @@ -4264,7 +4364,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u32 orig_flags, new_flags, changed_flags; + u64 orig_flags, new_flags, changed_flags; u32 i, j; orig_flags = READ_ONCE(pf->flags); @@ -4315,13 +4415,32 @@ flags_complete: !(pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE)) return -EOPNOTSUPP; + /* Disable FW LLDP not supported if NPAR active or if FW + * API version < 1.7 + */ + if (new_flags & I40E_FLAG_DISABLE_FW_LLDP) { + if (pf->hw.func_caps.npar_enable) { + dev_warn(&pf->pdev->dev, + "Unable to stop FW LLDP if NPAR active\n"); + return -EOPNOTSUPP; + } + + if (pf->hw.aq.api_maj_ver < 1 || + (pf->hw.aq.api_maj_ver == 1 && + pf->hw.aq.api_min_ver < 7)) { + dev_warn(&pf->pdev->dev, + "FW ver does not support stopping FW LLDP\n"); + return -EOPNOTSUPP; + } + } + /* Compare and exchange the new flags into place. If we failed, that * is if cmpxchg returns anything but the old value, this means that * something else has modified the flags variable since we copied it * originally. We'll just punt with an error and log something in the * message buffer. */ - if (cmpxchg(&pf->flags, orig_flags, new_flags) != orig_flags) { + if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { dev_warn(&pf->pdev->dev, "Unable to update pf->flags as it was modified by another thread...\n"); return -EAGAIN; @@ -4360,12 +4479,37 @@ flags_complete: } } + if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { + if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) { + struct i40e_dcbx_config *dcbcfg; + int i; + + i40e_aq_stop_lldp(&pf->hw, true, NULL); + i40e_aq_set_dcb_parameters(&pf->hw, true, NULL); + /* reset local_dcbx_config to default */ + dcbcfg = &pf->hw.local_dcbx_config; + dcbcfg->etscfg.willing = 1; + dcbcfg->etscfg.maxtcs = 0; + dcbcfg->etscfg.tcbwtable[0] = 100; + for (i = 1; i < I40E_MAX_TRAFFIC_CLASS; i++) + dcbcfg->etscfg.tcbwtable[i] = 0; + for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) + dcbcfg->etscfg.prioritytable[i] = 0; + dcbcfg->etscfg.tsatable[0] = I40E_IEEE_TSA_ETS; + dcbcfg->pfc.willing = 1; + dcbcfg->pfc.pfccap = I40E_MAX_TRAFFIC_CLASS; + } else { + i40e_aq_start_lldp(&pf->hw, NULL); + } + } + /* Issue reset to cause things to take effect, as additional bits * are added we will need to create a mask of bits requiring reset */ if (changed_flags & (I40E_FLAG_VEB_STATS_ENABLED | I40E_FLAG_LEGACY_RX | - I40E_FLAG_SOURCE_PRUNING_DISABLED)) + I40E_FLAG_SOURCE_PRUNING_DISABLED | + I40E_FLAG_DISABLE_FW_LLDP)) i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED), true); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2ab22eba0c7c..f95ce9b5e4fb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1818,6 +1818,10 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, num_tc_qps = qcount / numtc; num_tc_qps = min_t(int, num_tc_qps, i40e_pf_get_max_q_per_tc(pf)); + /* Do not allow use more TC queue pairs than MSI-X vectors exist */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + num_tc_qps = min_t(int, num_tc_qps, pf->num_lan_msix); + /* Setup queue offset/count for all TCs for given VSI */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { /* See if the given TC is enabled for the given VSI */ @@ -4122,6 +4126,7 @@ static void i40e_vsi_map_rings_to_vectors(struct i40e_vsi *vsi) num_ringpairs = DIV_ROUND_UP(qp_remaining, q_vectors - v_start); q_vector->num_ringpairs = num_ringpairs; + q_vector->reg_idx = q_vector->v_idx + vsi->base_vector - 1; q_vector->rx.count = 0; q_vector->tx.count = 0; @@ -4877,104 +4882,6 @@ static int i40e_pf_wait_queues_disabled(struct i40e_pf *pf) #endif /** - * i40e_detect_recover_hung_queue - Function to detect and recover hung_queue - * @q_idx: TX queue number - * @vsi: Pointer to VSI struct - * - * This function checks specified queue for given VSI. Detects hung condition. - * We proactively detect hung TX queues by checking if interrupts are disabled - * but there are pending descriptors. If it appears hung, attempt to recover - * by triggering a SW interrupt. - **/ -static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) -{ - struct i40e_ring *tx_ring = NULL; - struct i40e_pf *pf; - u32 val, tx_pending; - int i; - - pf = vsi->back; - - /* now that we have an index, find the tx_ring struct */ - for (i = 0; i < vsi->num_queue_pairs; i++) { - if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { - if (q_idx == vsi->tx_rings[i]->queue_index) { - tx_ring = vsi->tx_rings[i]; - break; - } - } - } - - if (!tx_ring) - return; - - /* Read interrupt register */ - if (pf->flags & I40E_FLAG_MSIX_ENABLED) - val = rd32(&pf->hw, - I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx + - tx_ring->vsi->base_vector - 1)); - else - val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); - - tx_pending = i40e_get_tx_pending(tx_ring); - - /* Interrupts are disabled and TX pending is non-zero, - * trigger the SW interrupt (don't wait). Worst case - * there will be one extra interrupt which may result - * into not cleaning any queues because queues are cleaned. - */ - if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) - i40e_force_wb(vsi, tx_ring->q_vector); -} - -/** - * i40e_detect_recover_hung - Function to detect and recover hung_queues - * @pf: pointer to PF struct - * - * LAN VSI has netdev and netdev has TX queues. This function is to check - * each of those TX queues if they are hung, trigger recovery by issuing - * SW interrupt. - **/ -static void i40e_detect_recover_hung(struct i40e_pf *pf) -{ - struct net_device *netdev; - struct i40e_vsi *vsi; - unsigned int i; - - /* Only for LAN VSI */ - vsi = pf->vsi[pf->lan_vsi]; - - if (!vsi) - return; - - /* Make sure, VSI state is not DOWN/RECOVERY_PENDING */ - if (test_bit(__I40E_VSI_DOWN, vsi->back->state) || - test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state)) - return; - - /* Make sure type is MAIN VSI */ - if (vsi->type != I40E_VSI_MAIN) - return; - - netdev = vsi->netdev; - if (!netdev) - return; - - /* Bail out if netif_carrier is not OK */ - if (!netif_carrier_ok(netdev)) - return; - - /* Go thru' TX queues for netdev */ - for (i = 0; i < netdev->num_tx_queues; i++) { - struct netdev_queue *q; - - q = netdev_get_tx_queue(netdev, i); - if (q) - i40e_detect_recover_hung_queue(i, vsi); - } -} - -/** * i40e_get_iscsi_tc_map - Return TC map for iSCSI APP * @pf: pointer to PF * @@ -5342,6 +5249,8 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi, static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) { u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0}; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; struct i40e_vsi_context ctxt; int ret = 0; int i; @@ -5359,10 +5268,40 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ret = i40e_vsi_configure_bw_alloc(vsi, enabled_tc, bw_share); if (ret) { - dev_info(&vsi->back->pdev->dev, + struct i40e_aqc_query_vsi_bw_config_resp bw_config = {0}; + + dev_info(&pf->pdev->dev, "Failed configuring TC map %d for VSI %d\n", enabled_tc, vsi->seid); - goto out; + ret = i40e_aq_query_vsi_bw_config(hw, vsi->seid, + &bw_config, NULL); + if (ret) { + dev_info(&pf->pdev->dev, + "Failed querying vsi bw info, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + goto out; + } + if ((bw_config.tc_valid_bits & enabled_tc) != enabled_tc) { + u8 valid_tc = bw_config.tc_valid_bits & enabled_tc; + + if (!valid_tc) + valid_tc = bw_config.tc_valid_bits; + /* Always enable TC0, no matter what */ + valid_tc |= 1; + dev_info(&pf->pdev->dev, + "Requested tc 0x%x, but FW reports 0x%x as valid. Attempting to use 0x%x.\n", + enabled_tc, bw_config.tc_valid_bits, valid_tc); + enabled_tc = valid_tc; + } + + ret = i40e_vsi_configure_bw_alloc(vsi, enabled_tc, bw_share); + if (ret) { + dev_err(&pf->pdev->dev, + "Unable to configure TC map %d for VSI %d\n", + enabled_tc, vsi->seid); + goto out; + } } /* Update Queue Pairs Mapping for currently enabled UPs */ @@ -5402,13 +5341,12 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) /* Update the VSI after updating the VSI queue-mapping * information */ - ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); if (ret) { - dev_info(&vsi->back->pdev->dev, + dev_info(&pf->pdev->dev, "Update vsi tc config failed, err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), - i40e_aq_str(&vsi->back->hw, - vsi->back->hw.aq.asq_last_status)); + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); goto out; } /* update the local VSI info with updated queue map */ @@ -5418,11 +5356,10 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) /* Update current VSI BW information */ ret = i40e_vsi_get_bw_info(vsi); if (ret) { - dev_info(&vsi->back->pdev->dev, + dev_info(&pf->pdev->dev, "Failed updating vsi bw info, err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), - i40e_aq_str(&vsi->back->hw, - vsi->back->hw.aq.asq_last_status)); + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); goto out; } @@ -6388,8 +6325,11 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) struct i40e_hw *hw = &pf->hw; int err = 0; - /* Do not enable DCB for SW1 and SW2 images even if the FW is capable */ - if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT) + /* Do not enable DCB for SW1 and SW2 images even if the FW is capable + * Also do not enable DCBx if FW LLDP agent is disabled + */ + if ((pf->hw_features & I40E_HW_NO_DCB_SUPPORT) || + (pf->flags & I40E_FLAG_DISABLE_FW_LLDP)) goto out; /* Get the initial DCB configuration */ @@ -6416,6 +6356,9 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) dev_dbg(&pf->pdev->dev, "DCBX offload is supported for this PF.\n"); } + } else if (pf->hw.aq.asq_last_status == I40E_AQ_RC_EPERM) { + dev_info(&pf->pdev->dev, "FW LLDP disabled for this PF.\n"); + pf->flags |= I40E_FLAG_DISABLE_FW_LLDP; } else { dev_info(&pf->pdev->dev, "Query for DCB configuration failed, err %s aq_err %s\n", @@ -7505,9 +7448,6 @@ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np, { struct i40e_vsi *vsi = np->vsi; - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: return i40e_configure_clsflower(vsi, cls_flower); @@ -7525,6 +7465,9 @@ static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, { struct i40e_netdev_priv *np = cb_priv; + if (!tc_cls_can_offload_and_chain0(np->vsi->netdev, type_data)) + return -EOPNOTSUPP; + switch (type) { case TC_SETUP_CLSFLOWER: return i40e_setup_tc_cls_flower(np, type_data); @@ -7742,6 +7685,9 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf) /* Reprogram the default input set for Other/IPv4 */ i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER, I40E_L3_SRC_MASK | I40E_L3_DST_MASK); + + i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4, + I40E_L3_SRC_MASK | I40E_L3_DST_MASK); } /** @@ -9075,6 +9021,17 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi) vsi->uplink_seid); return ret; } + /* Reconfigure TX queues using QTX_CTL register */ + ret = i40e_channel_config_tx_ring(vsi->back, vsi, ch); + if (ret) { + dev_info(&vsi->back->pdev->dev, + "failed to configure TX rings for channel %u\n", + ch->seid); + return ret; + } + /* update 'next_base_queue' */ + vsi->next_base_queue = vsi->next_base_queue + + ch->num_queue_pairs; if (ch->max_tx_rate) { u64 credits = ch->max_tx_rate; @@ -9278,6 +9235,9 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) goto end_core_reset; } + /* Enable FW to write a default DCB config on link-up */ + i40e_aq_set_dcb_parameters(hw, true, NULL); + #ifdef CONFIG_I40E_DCB ret = i40e_init_pf_dcb(pf); if (ret) { @@ -9695,7 +9655,7 @@ static void i40e_service_task(struct work_struct *work) if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state)) return; - i40e_detect_recover_hung(pf); + i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]); i40e_sync_filters_subtask(pf); i40e_reset_subtask(pf); i40e_handle_mdd_event(pf); @@ -10462,10 +10422,9 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) /* set up vector assignment tracking */ size = sizeof(struct i40e_lump_tracking) + (sizeof(u16) * vectors); pf->irq_pile = kzalloc(size, GFP_KERNEL); - if (!pf->irq_pile) { - dev_err(&pf->pdev->dev, "error allocating irq_pile memory\n"); + if (!pf->irq_pile) return -ENOMEM; - } + pf->irq_pile->num_entries = vectors; pf->irq_pile->search_hint = 0; @@ -10783,8 +10742,13 @@ static int i40e_pf_config_rss(struct i40e_pf *pf) /* Determine the RSS size of the VSI */ if (!vsi->rss_size) { u16 qcount; - - qcount = vsi->num_queue_pairs / vsi->tc_config.numtc; + /* If the firmware does something weird during VSI init, we + * could end up with zero TCs. Check for that to avoid + * divide-by-zero. It probably won't pass traffic, but it also + * won't panic. + */ + qcount = vsi->num_queue_pairs / + (vsi->tc_config.numtc ? vsi->tc_config.numtc : 1); vsi->rss_size = min_t(int, pf->alloc_rss_size, qcount); } if (!vsi->rss_size) @@ -10972,7 +10936,7 @@ i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf) ret = i40e_aq_update_nvm(&pf->hw, I40E_SR_NVM_CONTROL_WORD, 0x10, sizeof(nvm_word), - &nvm_word, true, NULL); + &nvm_word, true, 0, NULL); /* Save off last admin queue command status before releasing * the NVM */ @@ -11113,13 +11077,13 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->hw.aq.fw_maj_ver >= 6) pf->hw_features |= I40E_HW_PTP_L4_CAPABLE; - if (pf->hw.func_caps.vmdq) { + if (pf->hw.func_caps.vmdq && num_online_cpus() != 1) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; pf->flags |= I40E_FLAG_VMDQ_ENABLED; pf->num_vmdq_qps = i40e_default_queues_per_vmdq(pf); } - if (pf->hw.func_caps.iwarp) { + if (pf->hw.func_caps.iwarp && num_online_cpus() != 1) { pf->flags |= I40E_FLAG_IWARP_ENABLED; /* IWARP needs one extra vector for CQP just like MISC.*/ pf->num_iwarp_msix = (int)num_online_cpus() + 1; @@ -13596,6 +13560,10 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, pf); pci_save_state(pdev); + + /* Enable FW to write default DCB config on link-up */ + i40e_aq_set_dcb_parameters(hw, true, NULL); + #ifdef CONFIG_I40E_DCB err = i40e_init_pf_dcb(pf); if (err) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 425713fb72e5..76a5cb04e4fe 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -239,8 +239,9 @@ read_nvm_exit: * * Writes a 16 bit words buffer to the Shadow RAM using the admin command. **/ -static i40e_status i40e_read_nvm_aq(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 words, void *data, +static i40e_status i40e_read_nvm_aq(struct i40e_hw *hw, + u8 module_pointer, u32 offset, + u16 words, void *data, bool last_command) { i40e_status ret_code = I40E_ERR_NVM; @@ -496,7 +497,8 @@ static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, ret_code = i40e_aq_update_nvm(hw, module_pointer, 2 * offset, /*bytes*/ 2 * words, /*bytes*/ - data, last_command, &cmd_details); + data, last_command, 0, + &cmd_details); return ret_code; } @@ -677,6 +679,9 @@ static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, struct i40e_nvm_access *cmd, u8 *bytes, int *perrno); +static i40e_status i40e_nvmupd_get_aq_event(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); static inline u8 i40e_nvmupd_get_module(u32 val) { return (u8)(val & I40E_NVM_MOD_PNT_MASK); @@ -686,6 +691,12 @@ static inline u8 i40e_nvmupd_get_transaction(u32 val) return (u8)((val & I40E_NVM_TRANS_MASK) >> I40E_NVM_TRANS_SHIFT); } +static inline u8 i40e_nvmupd_get_preservation_flags(u32 val) +{ + return (u8)((val & I40E_NVM_PRESERVATION_FLAGS_MASK) >> + I40E_NVM_PRESERVATION_FLAGS_SHIFT); +} + static const char * const i40e_nvm_update_state_str[] = { "I40E_NVMUPD_INVALID", "I40E_NVMUPD_READ_CON", @@ -703,6 +714,7 @@ static const char * const i40e_nvm_update_state_str[] = { "I40E_NVMUPD_STATUS", "I40E_NVMUPD_EXEC_AQ", "I40E_NVMUPD_GET_AQ_RESULT", + "I40E_NVMUPD_GET_AQ_EVENT", }; /** @@ -798,9 +810,9 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, * the wait info and return before doing anything else */ if (cmd->offset == 0xffff) { - i40e_nvmupd_check_wait_event(hw, hw->nvm_wait_opcode); + i40e_nvmupd_clear_wait_state(hw); status = 0; - goto exit; + break; } status = I40E_ERR_NOT_READY; @@ -815,7 +827,7 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, *perrno = -ESRCH; break; } -exit: + mutex_unlock(&hw->aq.arq_mutex); return status; } @@ -944,6 +956,10 @@ static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, status = i40e_nvmupd_get_aq_result(hw, cmd, bytes, perrno); break; + case I40E_NVMUPD_GET_AQ_EVENT: + status = i40e_nvmupd_get_aq_event(hw, cmd, bytes, perrno); + break; + default: i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: bad cmd %s in init state\n", @@ -1118,38 +1134,53 @@ retry: } /** - * i40e_nvmupd_check_wait_event - handle NVM update operation events + * i40e_nvmupd_clear_wait_state - clear wait state on hw * @hw: pointer to the hardware structure - * @opcode: the event that just happened **/ -void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode) +void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw) { - if (opcode == hw->nvm_wait_opcode) { - i40e_debug(hw, I40E_DEBUG_NVM, - "NVMUPD: clearing wait on opcode 0x%04x\n", opcode); - if (hw->nvm_release_on_done) { - i40e_release_nvm(hw); - hw->nvm_release_on_done = false; - } - hw->nvm_wait_opcode = 0; + i40e_debug(hw, I40E_DEBUG_NVM, + "NVMUPD: clearing wait on opcode 0x%04x\n", + hw->nvm_wait_opcode); - if (hw->aq.arq_last_status) { - hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR; - return; - } + if (hw->nvm_release_on_done) { + i40e_release_nvm(hw); + hw->nvm_release_on_done = false; + } + hw->nvm_wait_opcode = 0; - switch (hw->nvmupd_state) { - case I40E_NVMUPD_STATE_INIT_WAIT: - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; - break; + if (hw->aq.arq_last_status) { + hw->nvmupd_state = I40E_NVMUPD_STATE_ERROR; + return; + } - case I40E_NVMUPD_STATE_WRITE_WAIT: - hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING; - break; + switch (hw->nvmupd_state) { + case I40E_NVMUPD_STATE_INIT_WAIT: + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + break; - default: - break; - } + case I40E_NVMUPD_STATE_WRITE_WAIT: + hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING; + break; + + default: + break; + } +} + +/** + * i40e_nvmupd_check_wait_event - handle NVM update operation events + * @hw: pointer to the hardware structure + * @opcode: the event that just happened + **/ +void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, + struct i40e_aq_desc *desc) +{ + u32 aq_desc_len = sizeof(struct i40e_aq_desc); + + if (opcode == hw->nvm_wait_opcode) { + memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len); + i40e_nvmupd_clear_wait_state(hw); } } @@ -1205,6 +1236,9 @@ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, else if (module == 0) upd_cmd = I40E_NVMUPD_GET_AQ_RESULT; break; + case I40E_NVM_AQE: + upd_cmd = I40E_NVMUPD_GET_AQ_EVENT; + break; } break; @@ -1267,6 +1301,9 @@ static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, u32 aq_data_len; i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + if (cmd->offset == 0xffff) + return 0; + memset(&cmd_details, 0, sizeof(cmd_details)); cmd_details.wb_desc = &hw->nvm_wb_desc; @@ -1302,6 +1339,9 @@ static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, } } + if (cmd->offset) + memset(&hw->nvm_aq_event_desc, 0, aq_desc_len); + /* and away we go! */ status = i40e_asq_send_command(hw, aq_desc, buff, buff_size, &cmd_details); @@ -1311,6 +1351,7 @@ static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, i40e_stat_str(hw, status), i40e_aq_str(hw, hw->aq.asq_last_status)); *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + return status; } /* should we wait for a followup event? */ @@ -1392,6 +1433,40 @@ static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, } /** + * i40e_nvmupd_get_aq_event - Get the Admin Queue event from previous exec_aq + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static i40e_status i40e_nvmupd_get_aq_event(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + u32 aq_total_len; + u32 aq_desc_len; + + i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + + aq_desc_len = sizeof(struct i40e_aq_desc); + aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen); + + /* check copylength range */ + if (cmd->data_size > aq_total_len) { + i40e_debug(hw, I40E_DEBUG_NVM, + "%s: copy length %d too big, trimming to %d\n", + __func__, cmd->data_size, aq_total_len); + cmd->data_size = aq_total_len; + } + + memcpy(bytes, &hw->nvm_aq_event_desc, cmd->data_size); + + return 0; +} + +/** * i40e_nvmupd_nvm_read - Read NVM * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer @@ -1486,18 +1561,20 @@ static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, i40e_status status = 0; struct i40e_asq_cmd_details cmd_details; u8 module, transaction; + u8 preservation_flags; bool last; transaction = i40e_nvmupd_get_transaction(cmd->config); module = i40e_nvmupd_get_module(cmd->config); last = (transaction & I40E_NVM_LCB); + preservation_flags = i40e_nvmupd_get_preservation_flags(cmd->config); memset(&cmd_details, 0, sizeof(cmd_details)); cmd_details.wb_desc = &hw->nvm_wb_desc; status = i40e_aq_update_nvm(hw, module, cmd->offset, (u16)cmd->data_size, bytes, last, - &cmd_details); + preservation_flags, &cmd_details); if (status) { i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_write mod 0x%x off 0x%x len 0x%x\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index b3cc89cc3a86..83798b7841b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -214,7 +214,7 @@ i40e_status i40e_aq_discover_capabilities(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, u32 offset, u16 length, void *data, - bool last_command, + bool last_command, u8 preservation_flags, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, u8 mib_type, void *buff, u16 buff_size, @@ -225,6 +225,10 @@ i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_set_dcb_parameters(struct i40e_hw *hw, + bool dcb_enable, + struct i40e_asq_cmd_details + *cmd_details); i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, @@ -333,7 +337,9 @@ i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, i40e_status i40e_nvmupd_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd, u8 *bytes, int *); -void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode); +void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, + struct i40e_aq_desc *desc); +void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw); void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status); extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; diff --git a/drivers/net/ethernet/intel/i40e/i40e_status.h b/drivers/net/ethernet/intel/i40e/i40e_status.h index 5f9cac55aa55..afb72e711d43 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_status.h +++ b/drivers/net/ethernet/intel/i40e/i40e_status.h @@ -95,6 +95,7 @@ enum i40e_status_code { I40E_ERR_NOT_READY = -63, I40E_NOT_SUPPORTED = -64, I40E_ERR_FIRMWARE_API_VERSION = -65, + I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66, }; #endif /* _I40E_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 40edb6e5e6f6..e554aa6cf070 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -726,6 +726,59 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring) return 0; } +/** + * i40e_detect_recover_hung - Function to detect and recover hung_queues + * @vsi: pointer to vsi struct with tx queues + * + * VSI has netdev and netdev has TX queues. This function is to check each of + * those TX queues if they are hung, trigger recovery by issuing SW interrupt. + **/ +void i40e_detect_recover_hung(struct i40e_vsi *vsi) +{ + struct i40e_ring *tx_ring = NULL; + struct net_device *netdev; + unsigned int i; + int packets; + + if (!vsi) + return; + + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return; + + netdev = vsi->netdev; + if (!netdev) + return; + + if (!netif_carrier_ok(netdev)) + return; + + for (i = 0; i < vsi->num_queue_pairs; i++) { + tx_ring = vsi->tx_rings[i]; + if (tx_ring && tx_ring->desc) { + /* If packet counter has not changed the queue is + * likely stalled, so force an interrupt for this + * queue. + * + * prev_pkt_ctr would be negative if there was no + * pending work. + */ + packets = tx_ring->stats.packets & INT_MAX; + if (tx_ring->tx_stats.prev_pkt_ctr == packets) { + i40e_force_wb(vsi, tx_ring->q_vector); + continue; + } + + /* Memory barrier between read of packet count and call + * to i40e_get_tx_pending() + */ + smp_rmb(); + tx_ring->tx_stats.prev_pkt_ctr = + i40e_get_tx_pending(tx_ring) ? packets : -1; + } + } +} + #define WB_STRIDE 4 /** @@ -903,7 +956,7 @@ static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi, I40E_PFINT_DYN_CTLN_ITR_INDX_MASK; /* set noitr */ wr32(&vsi->back->hw, - I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1), + I40E_PFINT_DYN_CTLN(q_vector->reg_idx), val); } else { val = I40E_PFINT_DYN_CTL0_WB_ON_ITR_MASK | @@ -930,8 +983,7 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) /* allow 00 to be written to the index */ wr32(&vsi->back->hw, - I40E_PFINT_DYN_CTLN(q_vector->v_idx + - vsi->base_vector - 1), val); + I40E_PFINT_DYN_CTLN(q_vector->reg_idx), val); } else { u32 val = I40E_PFINT_DYN_CTL0_INTENA_MASK | I40E_PFINT_DYN_CTL0_ITR_INDX_MASK | /* set noitr */ @@ -1163,6 +1215,7 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->tx_stats.prev_pkt_ctr = -1; return 0; err: @@ -2257,7 +2310,6 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_hw *hw = &vsi->back->hw; bool rx = false, tx = false; u32 rxval, txval; - int vector; int idx = q_vector->v_idx; int rx_itr_setting, tx_itr_setting; @@ -2267,8 +2319,6 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, return; } - vector = (q_vector->v_idx + vsi->base_vector); - /* avoid dynamic calculation if in countdown mode OR if * all dynamic is disabled */ @@ -2317,12 +2367,12 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ rxval |= BIT(31); /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(vector - 1), rxval); + wr32(hw, INTREG(q_vector->reg_idx), rxval); } enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(vector - 1), txval); + wr32(hw, INTREG(q_vector->reg_idx), txval); if (q_vector->itr_countdown) q_vector->itr_countdown--; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 2d08760fc4ce..d4799b41e98a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -333,6 +333,7 @@ struct i40e_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; + int prev_pkt_ctr; }; struct i40e_rx_queue_stats { @@ -501,6 +502,7 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring); int i40e_napi_poll(struct napi_struct *napi, int budget); void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); u32 i40e_get_tx_pending(struct i40e_ring *ring); +void i40e_detect_recover_hung(struct i40e_vsi *vsi); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 5a708c363d99..cd294e6a8587 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -402,6 +402,7 @@ enum i40e_nvmupd_cmd { I40E_NVMUPD_STATUS, I40E_NVMUPD_EXEC_AQ, I40E_NVMUPD_GET_AQ_RESULT, + I40E_NVMUPD_GET_AQ_EVENT, }; enum i40e_nvmupd_state { @@ -421,15 +422,21 @@ enum i40e_nvmupd_state { #define I40E_NVM_MOD_PNT_MASK 0xFF -#define I40E_NVM_TRANS_SHIFT 8 -#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT) -#define I40E_NVM_CON 0x0 -#define I40E_NVM_SNT 0x1 -#define I40E_NVM_LCB 0x2 -#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) -#define I40E_NVM_ERA 0x4 -#define I40E_NVM_CSUM 0x8 -#define I40E_NVM_EXEC 0xf +#define I40E_NVM_TRANS_SHIFT 8 +#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT) +#define I40E_NVM_PRESERVATION_FLAGS_SHIFT 12 +#define I40E_NVM_PRESERVATION_FLAGS_MASK \ + (0x3 << I40E_NVM_PRESERVATION_FLAGS_SHIFT) +#define I40E_NVM_PRESERVATION_FLAGS_SELECTED 0x01 +#define I40E_NVM_PRESERVATION_FLAGS_ALL 0x02 +#define I40E_NVM_CON 0x0 +#define I40E_NVM_SNT 0x1 +#define I40E_NVM_LCB 0x2 +#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) +#define I40E_NVM_ERA 0x4 +#define I40E_NVM_CSUM 0x8 +#define I40E_NVM_AQE 0xe +#define I40E_NVM_EXEC 0xf #define I40E_NVM_ADAPT_SHIFT 16 #define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT) @@ -611,6 +618,7 @@ struct i40e_hw { /* state of nvm update process */ enum i40e_nvmupd_state nvmupd_state; struct i40e_aq_desc nvm_wb_desc; + struct i40e_aq_desc nvm_aq_event_desc; struct i40e_virt_mem nvm_buff; bool nvm_release_on_done; u16 nvm_wait_opcode; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 8b0d4b255dea..d1aab6b8bfb1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -837,10 +837,15 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, /* update the error if time out occurred */ if ((!cmd_completed) && (!details->async && !details->postpone)) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, - "AQTX: Writeback timeout.\n"); - status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; + if (rd32(hw, hw->aq.asq.len) & I40E_VF_ATQLEN1_ATQCRIT_MASK) { + i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + "AQTX: AQ Critical error.\n"); + status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR; + } else { + i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + "AQTX: Writeback timeout.\n"); + status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; + } } asq_send_command_error: @@ -901,7 +906,7 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, } /* set next_to_use to head */ - ntu = (rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK); + ntu = rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK; if (ntu == ntc) { /* nothing to do - shouldn't need to update ring's values */ ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 435a112d09f5..815de8d9c3fb 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -205,6 +205,7 @@ enum i40e_admin_queue_opc { /* DCB commands */ i40e_aqc_opc_dcb_ignore_pfc = 0x0301, i40e_aqc_opc_dcb_updated = 0x0302, + i40e_aqc_opc_set_dcb_parameters = 0x0303, /* TX scheduler */ i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, @@ -2196,8 +2197,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); */ struct i40e_aqc_nvm_update { u8 command_flags; -#define I40E_AQ_NVM_LAST_CMD 0x01 -#define I40E_AQ_NVM_FLASH_ONLY 0x80 +#define I40E_AQ_NVM_LAST_CMD 0x01 +#define I40E_AQ_NVM_FLASH_ONLY 0x80 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT 1 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK 0x03 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED 0x03 +#define I40E_AQ_NVM_PRESERVATION_FLAGS_ALL 0x01 u8 module_pointer; __le16 length; __le32 offset; @@ -2457,6 +2462,17 @@ struct i40e_aqc_lldp_start { I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start); +/* Set DCB (direct 0x0303) */ +struct i40e_aqc_set_dcb_parameters { + u8 command; +#define I40E_AQ_DCB_SET_AGENT 0x1 +#define I40E_DCB_VALID 0x1 + u8 valid_flags; + u8 reserved[14]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_set_dcb_parameters); + /* Apply MIB changes (0x0A07) * uses the generic struc as it contains no data */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index a94648429a5b..67bf5cebb76f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -284,6 +284,8 @@ const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err) return "I40E_NOT_SUPPORTED"; case I40E_ERR_FIRMWARE_API_VERSION: return "I40E_ERR_FIRMWARE_API_VERSION"; + case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; } snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/i40evf/i40e_status.h index 7fa7a41915c1..5b222246e08b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_status.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_status.h @@ -95,6 +95,7 @@ enum i40e_status_code { I40E_ERR_NOT_READY = -63, I40E_NOT_SUPPORTED = -64, I40E_ERR_FIRMWARE_API_VERSION = -65, + I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66, }; #endif /* _I40E_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 1ba29bb85b67..357d6051281f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -148,6 +148,59 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) return 0; } +/** + * i40evf_detect_recover_hung - Function to detect and recover hung_queues + * @vsi: pointer to vsi struct with tx queues + * + * VSI has netdev and netdev has TX queues. This function is to check each of + * those TX queues if they are hung, trigger recovery by issuing SW interrupt. + **/ +void i40evf_detect_recover_hung(struct i40e_vsi *vsi) +{ + struct i40e_ring *tx_ring = NULL; + struct net_device *netdev; + unsigned int i; + int packets; + + if (!vsi) + return; + + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return; + + netdev = vsi->netdev; + if (!netdev) + return; + + if (!netif_carrier_ok(netdev)) + return; + + for (i = 0; i < vsi->back->num_active_queues; i++) { + tx_ring = &vsi->back->tx_rings[i]; + if (tx_ring && tx_ring->desc) { + /* If packet counter has not changed the queue is + * likely stalled, so force an interrupt for this + * queue. + * + * prev_pkt_ctr would be negative if there was no + * pending work. + */ + packets = tx_ring->stats.packets & INT_MAX; + if (tx_ring->tx_stats.prev_pkt_ctr == packets) { + i40evf_force_wb(vsi, tx_ring->q_vector); + continue; + } + + /* Memory barrier between read of packet count and call + * to i40evf_get_tx_pending() + */ + smp_rmb(); + tx_ring->tx_stats.prev_pkt_ctr = + i40evf_get_tx_pending(tx_ring, false) ? packets : -1; + } + } +} + #define WB_STRIDE 4 /** @@ -316,8 +369,7 @@ static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi, I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->v_idx + - vsi->base_vector - 1), val); + I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), val); q_vector->arm_wb_state = true; } @@ -336,7 +388,7 @@ void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) /* allow 00 to be written to the index */; wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->v_idx + vsi->base_vector - 1), + I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), val); } @@ -469,6 +521,7 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->tx_stats.prev_pkt_ctr = -1; return 0; err: @@ -1444,12 +1497,9 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, struct i40e_hw *hw = &vsi->back->hw; bool rx = false, tx = false; u32 rxval, txval; - int vector; int idx = q_vector->v_idx; int rx_itr_setting, tx_itr_setting; - vector = (q_vector->v_idx + vsi->base_vector); - /* avoid dynamic calculation if in countdown mode OR if * all dynamic is disabled */ @@ -1498,12 +1548,12 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ rxval |= BIT(31); /* don't check _DOWN because interrupt isn't being enabled */ - wr32(hw, INTREG(vector - 1), rxval); + wr32(hw, INTREG(q_vector->reg_idx), rxval); } enable_int: if (!test_bit(__I40E_VSI_DOWN, vsi->state)) - wr32(hw, INTREG(vector - 1), txval); + wr32(hw, INTREG(q_vector->reg_idx), txval); if (q_vector->itr_countdown) q_vector->itr_countdown--; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 8d26c85d12e1..e72f16b4555b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -313,6 +313,7 @@ struct i40e_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; + int prev_pkt_ctr; u64 tx_lost_interrupt; }; @@ -467,6 +468,7 @@ void i40evf_free_rx_resources(struct i40e_ring *rx_ring); int i40evf_napi_poll(struct napi_struct *napi, int budget); void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw); +void i40evf_detect_recover_hung(struct i40e_vsi *vsi); int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40evf_chk_linearize(struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 6afc31616e04..54951c84a481 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -361,6 +361,7 @@ enum i40e_nvmupd_cmd { I40E_NVMUPD_STATUS, I40E_NVMUPD_EXEC_AQ, I40E_NVMUPD_GET_AQ_RESULT, + I40E_NVMUPD_GET_AQ_EVENT, }; enum i40e_nvmupd_state { @@ -380,15 +381,21 @@ enum i40e_nvmupd_state { #define I40E_NVM_MOD_PNT_MASK 0xFF -#define I40E_NVM_TRANS_SHIFT 8 -#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT) -#define I40E_NVM_CON 0x0 -#define I40E_NVM_SNT 0x1 -#define I40E_NVM_LCB 0x2 -#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) -#define I40E_NVM_ERA 0x4 -#define I40E_NVM_CSUM 0x8 -#define I40E_NVM_EXEC 0xf +#define I40E_NVM_TRANS_SHIFT 8 +#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT) +#define I40E_NVM_PRESERVATION_FLAGS_SHIFT 12 +#define I40E_NVM_PRESERVATION_FLAGS_MASK \ + (0x3 << I40E_NVM_PRESERVATION_FLAGS_SHIFT) +#define I40E_NVM_PRESERVATION_FLAGS_SELECTED 0x01 +#define I40E_NVM_PRESERVATION_FLAGS_ALL 0x02 +#define I40E_NVM_CON 0x0 +#define I40E_NVM_SNT 0x1 +#define I40E_NVM_LCB 0x2 +#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) +#define I40E_NVM_ERA 0x4 +#define I40E_NVM_CSUM 0x8 +#define I40E_NVM_AQE 0xe +#define I40E_NVM_EXEC 0xf #define I40E_NVM_ADAPT_SHIFT 16 #define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT) @@ -561,6 +568,7 @@ struct i40e_hw { /* state of nvm update process */ enum i40e_nvmupd_state nvmupd_state; struct i40e_aq_desc nvm_wb_desc; + struct i40e_aq_desc nvm_aq_event_desc; struct i40e_virt_mem nvm_buff; bool nvm_release_on_done; u16 nvm_wait_opcode; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 47040ab2e298..9690c1ea019e 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -114,14 +114,14 @@ struct i40e_q_vector { struct i40evf_adapter *adapter; struct i40e_vsi *vsi; struct napi_struct napi; - unsigned long reg_idx; struct i40e_ring_container rx; struct i40e_ring_container tx; u32 ring_mask; u8 num_ringpairs; /* total number of ring pairs in vector */ #define ITR_COUNTDOWN_START 100 u8 itr_countdown; /* when 0 or 1 update ITR */ - int v_idx; /* vector index in list */ + u16 v_idx; /* index in the vsi->q_vector array. */ + u16 reg_idx; /* register index of the interrupt */ char name[IFNAMSIZ + 15]; bool arm_wb_state; cpumask_t affinity_mask; @@ -187,6 +187,7 @@ enum i40evf_state_t { enum i40evf_critical_section_t { __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ __I40EVF_IN_CLIENT_TASK, + __I40EVF_IN_REMOVE_TASK, /* device being removed */ }; /* board specific private data structure */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index da006fa3fec1..e2d8aa19d205 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -512,31 +512,31 @@ static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter, struct ethtool_coalesce *ec, int queue) { + struct i40e_ring *rx_ring = &adapter->rx_rings[queue]; + struct i40e_ring *tx_ring = &adapter->tx_rings[queue]; struct i40e_vsi *vsi = &adapter->vsi; struct i40e_hw *hw = &adapter->hw; struct i40e_q_vector *q_vector; u16 vector; - adapter->rx_rings[queue].rx_itr_setting = ec->rx_coalesce_usecs; - adapter->tx_rings[queue].tx_itr_setting = ec->tx_coalesce_usecs; + rx_ring->rx_itr_setting = ec->rx_coalesce_usecs; + tx_ring->tx_itr_setting = ec->tx_coalesce_usecs; - if (ec->use_adaptive_rx_coalesce) - adapter->rx_rings[queue].rx_itr_setting |= I40E_ITR_DYNAMIC; - else - adapter->rx_rings[queue].rx_itr_setting &= ~I40E_ITR_DYNAMIC; + rx_ring->rx_itr_setting |= I40E_ITR_DYNAMIC; + if (!ec->use_adaptive_rx_coalesce) + rx_ring->rx_itr_setting ^= I40E_ITR_DYNAMIC; - if (ec->use_adaptive_tx_coalesce) - adapter->tx_rings[queue].tx_itr_setting |= I40E_ITR_DYNAMIC; - else - adapter->tx_rings[queue].tx_itr_setting &= ~I40E_ITR_DYNAMIC; + tx_ring->tx_itr_setting |= I40E_ITR_DYNAMIC; + if (!ec->use_adaptive_tx_coalesce) + tx_ring->tx_itr_setting ^= I40E_ITR_DYNAMIC; - q_vector = adapter->rx_rings[queue].q_vector; - q_vector->rx.itr = ITR_TO_REG(adapter->rx_rings[queue].rx_itr_setting); + q_vector = rx_ring->q_vector; + q_vector->rx.itr = ITR_TO_REG(rx_ring->rx_itr_setting); vector = vsi->base_vector + q_vector->v_idx; wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, vector - 1), q_vector->rx.itr); - q_vector = adapter->tx_rings[queue].q_vector; - q_vector->tx.itr = ITR_TO_REG(adapter->tx_rings[queue].tx_itr_setting); + q_vector = tx_ring->q_vector; + q_vector->tx.itr = ITR_TO_REG(tx_ring->tx_itr_setting); vector = vsi->base_vector + q_vector->v_idx; wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, vector - 1), q_vector->tx.itr); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f92587aba3c7..16989ad2ca90 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1387,6 +1387,7 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter) q_vector->adapter = adapter; q_vector->vsi = &adapter->vsi; q_vector->v_idx = q_idx; + q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); netif_napi_add(adapter->netdev, &q_vector->napi, i40evf_napi_poll, NAPI_POLL_WEIGHT); @@ -1716,6 +1717,8 @@ static void i40evf_watchdog_task(struct work_struct *work) if (adapter->state == __I40EVF_RUNNING) i40evf_request_stats(adapter); watchdog_done: + if (adapter->state == __I40EVF_RUNNING) + i40evf_detect_recover_hung(&adapter->vsi); clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); restart_watchdog: if (adapter->state == __I40EVF_REMOVE) @@ -1803,6 +1806,12 @@ static void i40evf_reset_task(struct work_struct *work) int i = 0, err; bool running; + /* When device is being removed it doesn't make sense to run the reset + * task, just return in such a case. + */ + if (test_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section)) + return; + while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); @@ -2336,13 +2345,19 @@ static int i40evf_set_features(struct net_device *netdev, { struct i40evf_adapter *adapter = netdev_priv(netdev); - if (!VLAN_ALLOWED(adapter)) + /* Don't allow changing VLAN_RX flag when VLAN is set for VF + * and return an error in this case + */ + if (VLAN_ALLOWED(adapter)) { + if (features & NETIF_F_HW_VLAN_CTAG_RX) + adapter->aq_required |= + I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + else + adapter->aq_required |= + I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { return -EINVAL; - - if (features & NETIF_F_HW_VLAN_CTAG_RX) - adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; - else - adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + } return 0; } @@ -3053,7 +3068,8 @@ static void i40evf_remove(struct pci_dev *pdev) struct i40evf_mac_filter *f, *ftmp; struct i40e_hw *hw = &adapter->hw; int err; - + /* Indicate we are in remove and not to run reset_task */ + set_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section); cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); cancel_delayed_work_sync(&adapter->client_task); @@ -3088,8 +3104,6 @@ static void i40evf_remove(struct pci_dev *pdev) if (adapter->watchdog_timer.function) del_timer_sync(&adapter->watchdog_timer); - flush_scheduled_work(); - i40evf_free_rss(adapter); if (hw->aq.asq.count) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index feb95b62a077..50ce0d6c09ef 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -1001,23 +1001,34 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, if (v_opcode == VIRTCHNL_OP_EVENT) { struct virtchnl_pf_event *vpe = (struct virtchnl_pf_event *)msg; + bool link_up = vpe->event_data.link_event.link_status; switch (vpe->event) { case VIRTCHNL_EVENT_LINK_CHANGE: adapter->link_speed = vpe->event_data.link_event.link_speed; - if (adapter->link_up != - vpe->event_data.link_event.link_status) { - adapter->link_up = - vpe->event_data.link_event.link_status; - if (adapter->link_up) { - netif_tx_start_all_queues(netdev); - netif_carrier_on(netdev); - } else { - netif_tx_stop_all_queues(netdev); - netif_carrier_off(netdev); - } - i40evf_print_link_message(adapter); + + /* we've already got the right link status, bail */ + if (adapter->link_up == link_up) + break; + + /* If we get link up message and start queues before + * our queues are configured it will trigger a TX hang. + * In that case, just ignore the link status message, + * we'll get another one after we enable queues and + * actually prepared to send traffic. + */ + if (link_up && adapter->state != __I40EVF_RUNNING) + break; + + adapter->link_up = link_up; + if (link_up) { + netif_tx_start_all_queues(netdev); + netif_carrier_on(netdev); + } else { + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); } + i40evf_print_link_message(adapter); break; case VIRTCHNL_EVENT_RESET_IMPENDING: dev_info(&adapter->pdev->dev, "PF reset warning received\n"); diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 92845692087a..1c6b8d9176a8 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -690,6 +690,7 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igb_set_flag_queue_pairs(struct igb_adapter *, const u32); +unsigned int igb_get_max_rss_queues(struct igb_adapter *); #ifdef CONFIG_IGB_HWMON void igb_sysfs_exit(struct igb_adapter *adapter); int igb_sysfs_init(struct igb_adapter *adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index d06a8db514d4..606e6761758f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -3338,37 +3338,7 @@ static int igb_set_rxfh(struct net_device *netdev, const u32 *indir, static unsigned int igb_max_channels(struct igb_adapter *adapter) { - struct e1000_hw *hw = &adapter->hw; - unsigned int max_combined = 0; - - switch (hw->mac.type) { - case e1000_i211: - max_combined = IGB_MAX_RX_QUEUES_I211; - break; - case e1000_82575: - case e1000_i210: - max_combined = IGB_MAX_RX_QUEUES_82575; - break; - case e1000_i350: - if (!!adapter->vfs_allocated_count) { - max_combined = 1; - break; - } - /* fall through */ - case e1000_82576: - if (!!adapter->vfs_allocated_count) { - max_combined = 2; - break; - } - /* fall through */ - case e1000_82580: - case e1000_i354: - default: - max_combined = IGB_MAX_RX_QUEUES; - break; - } - - return max_combined; + return igb_get_max_rss_queues(adapter); } static void igb_get_channels(struct net_device *netdev, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c208753ff5b7..b88fae785369 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1744,6 +1744,20 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue, * value = idleSlope * 61034 * ----------------- (E6) * 1000000 + * + * NOTE: For i210, given the above, we can see that idleslope + * is represented in 16.38431 kbps units by the value at + * the TQAVCC register (1Gbps / 61034), which reduces + * the granularity for idleslope increments. + * For instance, if you want to configure a 2576kbps + * idleslope, the value to be written on the register + * would have to be 157.23. If rounded down, you end + * up with less bandwidth available than originally + * required (~2572 kbps). If rounded up, you end up + * with a higher bandwidth (~2589 kbps). Below the + * approach we take is to always round up the + * calculated value, so the resulting bandwidth might + * be slightly higher for some configurations. */ value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000); @@ -3200,8 +3214,6 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) /* if allocation failed then we do not support SR-IOV */ if (!adapter->vf_data) { adapter->vfs_allocated_count = 0; - dev_err(&pdev->dev, - "Unable to allocate memory for VF Data Storage\n"); err = -ENOMEM; goto out; } @@ -3373,10 +3385,10 @@ static void igb_probe_vfs(struct igb_adapter *adapter) #endif /* CONFIG_PCI_IOV */ } -static void igb_init_queue_configuration(struct igb_adapter *adapter) +unsigned int igb_get_max_rss_queues(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; - u32 max_rss_queues; + unsigned int max_rss_queues; /* Determine the maximum number of RSS queues supported. */ switch (hw->mac.type) { @@ -3407,6 +3419,14 @@ static void igb_init_queue_configuration(struct igb_adapter *adapter) break; } + return max_rss_queues; +} + +static void igb_init_queue_configuration(struct igb_adapter *adapter) +{ + u32 max_rss_queues; + + max_rss_queues = igb_get_max_rss_queues(adapter); adapter->rss_queues = min_t(u32, max_rss_queues, num_online_cpus()); igb_set_flag_queue_pairs(adapter, max_rss_queues); @@ -3676,7 +3696,7 @@ static int __igb_close(struct net_device *netdev, bool suspending) int igb_close(struct net_device *netdev) { - if (netif_device_present(netdev)) + if (netif_device_present(netdev) || netdev->dismantle) return __igb_close(netdev, false); return 0; } @@ -8718,7 +8738,8 @@ static void igb_rar_set_index(struct igb_adapter *adapter, u32 index) /* Indicate to hardware the Address is Valid. */ if (adapter->mac_table[index].state & IGB_MAC_STATE_IN_USE) { - rar_high |= E1000_RAH_AV; + if (is_valid_ether_addr(addr)) + rar_high |= E1000_RAH_AV; if (hw->mac.type == e1000_82575) rar_high |= E1000_RAH_POOL_1 * @@ -8756,17 +8777,36 @@ static int igb_set_vf_mac(struct igb_adapter *adapter, static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { struct igb_adapter *adapter = netdev_priv(netdev); - if (!is_valid_ether_addr(mac) || (vf >= adapter->vfs_allocated_count)) + + if (vf >= adapter->vfs_allocated_count) + return -EINVAL; + + /* Setting the VF MAC to 0 reverts the IGB_VF_FLAG_PF_SET_MAC + * flag and allows to overwrite the MAC via VF netdev. This + * is necessary to allow libvirt a way to restore the original + * MAC after unbinding vfio-pci and reloading igbvf after shutting + * down a VM. + */ + if (is_zero_ether_addr(mac)) { + adapter->vf_data[vf].flags &= ~IGB_VF_FLAG_PF_SET_MAC; + dev_info(&adapter->pdev->dev, + "remove administratively set MAC on VF %d\n", + vf); + } else if (is_valid_ether_addr(mac)) { + adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; + dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", + mac, vf); + dev_info(&adapter->pdev->dev, + "Reload the VF driver to make this change effective."); + /* Generate additional warning if PF is down */ + if (test_bit(__IGB_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, + "The VF MAC address has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before attempting to use the VF device.\n"); + } + } else { return -EINVAL; - adapter->vf_data[vf].flags |= IGB_VF_FLAG_PF_SET_MAC; - dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", mac, vf); - dev_info(&adapter->pdev->dev, - "Reload the VF driver to make this change effective."); - if (test_bit(__IGB_DOWN, &adapter->state)) { - dev_warn(&adapter->pdev->dev, - "The VF MAC address has been set, but the PF device is not up.\n"); - dev_warn(&adapter->pdev->dev, - "Bring the PF device up before attempting to use the VF device.\n"); } return igb_set_vf_mac(adapter, vf, mac); } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 841c2a083349..0746b19ec6d3 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -643,6 +643,10 @@ static void igb_ptp_tx_work(struct work_struct *work) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); adapter->tx_hwtstamp_timeouts++; + /* Clear the tx valid bit in TSYNCTXCTL register to enable + * interrupt + */ + rd32(E1000_TXSTMPH); dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n"); return; } @@ -717,6 +721,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter) */ void igb_ptp_tx_hang(struct igb_adapter *adapter) { + struct e1000_hw *hw = &adapter->hw; bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + IGB_PTP_TX_TIMEOUT); @@ -736,6 +741,10 @@ void igb_ptp_tx_hang(struct igb_adapter *adapter) adapter->ptp_tx_skb = NULL; clear_bit_unlock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state); adapter->tx_hwtstamp_timeouts++; + /* Clear the tx valid bit in TSYNCTXCTL register to enable + * interrupt + */ + rd32(E1000_TXSTMPH); dev_warn(&adapter->pdev->dev, "clearing Tx timestamp hang\n"); } } diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 35e6fa643c7e..8319465eb38d 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -42,3 +42,4 @@ ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o +ixgbe-$(CONFIG_XFRM_OFFLOAD) += ixgbe_ipsec.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 49ab0c7a9cd5..c1e3a0039ea5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -52,6 +52,7 @@ #ifdef CONFIG_IXGBE_DCA #include <linux/dca.h> #endif +#include "ixgbe_ipsec.h" #include <net/xdp.h> #include <net/busy_poll.h> @@ -171,10 +172,11 @@ enum ixgbe_tx_flags { IXGBE_TX_FLAGS_CC = 0x08, IXGBE_TX_FLAGS_IPV4 = 0x10, IXGBE_TX_FLAGS_CSUM = 0x20, + IXGBE_TX_FLAGS_IPSEC = 0x40, /* software defined flags */ - IXGBE_TX_FLAGS_SW_VLAN = 0x40, - IXGBE_TX_FLAGS_FCOE = 0x80, + IXGBE_TX_FLAGS_SW_VLAN = 0x80, + IXGBE_TX_FLAGS_FCOE = 0x100, }; /* VLAN info */ @@ -629,15 +631,18 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_EEE_CAPABLE BIT(14) #define IXGBE_FLAG2_EEE_ENABLED BIT(15) #define IXGBE_FLAG2_RX_LEGACY BIT(16) +#define IXGBE_FLAG2_IPSEC_ENABLED BIT(17) /* Tx fast path data */ int num_tx_queues; u16 tx_itr_setting; u16 tx_work_limit; + u64 tx_ipsec; /* Rx fast path data */ int num_rx_queues; u16 rx_itr_setting; + u64 rx_ipsec; /* Port number used to identify VXLAN traffic */ __be16 vxlan_port; @@ -781,6 +786,10 @@ struct ixgbe_adapter { #define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ u32 *rss_key; + +#ifdef CONFIG_XFRM + struct ixgbe_ipsec *ipsec; +#endif /* CONFIG_XFRM */ }; static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) @@ -1011,4 +1020,24 @@ void ixgbe_store_key(struct ixgbe_adapter *adapter); void ixgbe_store_reta(struct ixgbe_adapter *adapter); s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm); +#ifdef CONFIG_XFRM_OFFLOAD +void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter); +void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter); +void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter); +void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd); +#else +static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { }; +static inline void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) { }; +static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { }; +static inline void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { }; +static inline int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd) { return 0; }; +#endif /* CONFIG_XFRM_OFFLOAD */ #endif /* _IXGBE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 7ac7ef9b37ff..61188f343955 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -4087,7 +4087,7 @@ void ixgbe_get_oem_prod_version(struct ixgbe_hw *hw, hw->eeprom.ops.read(hw, NVM_OEM_PROD_VER_PTR, &offset); /* Return is offset to OEM Product Version block is invalid */ - if (offset == 0x0 && offset == NVM_INVALID_PTR) + if (offset == 0x0 || offset == NVM_INVALID_PTR) return; /* Read product version block */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index f064099733b6..221f15803480 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -115,6 +115,8 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = { {"tx_hwtstamp_timeouts", IXGBE_STAT(tx_hwtstamp_timeouts)}, {"tx_hwtstamp_skipped", IXGBE_STAT(tx_hwtstamp_skipped)}, {"rx_hwtstamp_cleared", IXGBE_STAT(rx_hwtstamp_cleared)}, + {"tx_ipsec", IXGBE_STAT(tx_ipsec)}, + {"rx_ipsec", IXGBE_STAT(rx_ipsec)}, #ifdef IXGBE_FCOE {"fcoe_bad_fccrc", IXGBE_STAT(stats.fccrc)}, {"rx_fcoe_dropped", IXGBE_STAT(stats.fcoerpdc)}, @@ -3083,26 +3085,9 @@ static int ixgbe_get_ts_info(struct net_device *dev, case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL); - /* fallthrough */ + break; case ixgbe_mac_X540: case ixgbe_mac_82599EB: - info->so_timestamping = - SOF_TIMESTAMPING_TX_SOFTWARE | - SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE | - SOF_TIMESTAMPING_TX_HARDWARE | - SOF_TIMESTAMPING_RX_HARDWARE | - SOF_TIMESTAMPING_RAW_HARDWARE; - - if (adapter->ptp_clock) - info->phc_index = ptp_clock_index(adapter->ptp_clock); - else - info->phc_index = -1; - - info->tx_types = - BIT(HWTSTAMP_TX_OFF) | - BIT(HWTSTAMP_TX_ON); - info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | @@ -3111,6 +3096,24 @@ static int ixgbe_get_ts_info(struct net_device *dev, default: return ethtool_op_get_ts_info(dev, info); } + + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (adapter->ptp_clock) + info->phc_index = ptp_clock_index(adapter->ptp_clock); + else + info->phc_index = -1; + + info->tx_types = + BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); + return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c new file mode 100644 index 000000000000..93eacddb6704 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -0,0 +1,941 @@ +/******************************************************************************* + * + * Intel 10 Gigabit PCI Express Linux driver + * Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + ******************************************************************************/ + +#include "ixgbe.h" +#include <net/xfrm.h> +#include <crypto/aead.h> + +/** + * ixgbe_ipsec_set_tx_sa - set the Tx SA registers + * @hw: hw specific details + * @idx: register index to write + * @key: key byte array + * @salt: salt bytes + **/ +static void ixgbe_ipsec_set_tx_sa(struct ixgbe_hw *hw, u16 idx, + u32 key[], u32 salt) +{ + u32 reg; + int i; + + for (i = 0; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_IPSTXKEY(i), cpu_to_be32(key[3 - i])); + IXGBE_WRITE_REG(hw, IXGBE_IPSTXSALT, cpu_to_be32(salt)); + IXGBE_WRITE_FLUSH(hw); + + reg = IXGBE_READ_REG(hw, IXGBE_IPSTXIDX); + reg &= IXGBE_RXTXIDX_IPS_EN; + reg |= idx << IXGBE_RXTXIDX_IDX_SHIFT | IXGBE_RXTXIDX_WRITE; + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, reg); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_set_rx_item - set an Rx table item + * @hw: hw specific details + * @idx: register index to write + * @tbl: table selector + * + * Trigger the device to store into a particular Rx table the + * data that has already been loaded into the input register + **/ +static void ixgbe_ipsec_set_rx_item(struct ixgbe_hw *hw, u16 idx, + enum ixgbe_ipsec_tbl_sel tbl) +{ + u32 reg; + + reg = IXGBE_READ_REG(hw, IXGBE_IPSRXIDX); + reg &= IXGBE_RXTXIDX_IPS_EN; + reg |= tbl << IXGBE_RXIDX_TBL_SHIFT | + idx << IXGBE_RXTXIDX_IDX_SHIFT | + IXGBE_RXTXIDX_WRITE; + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, reg); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_set_rx_sa - set up the register bits to save SA info + * @hw: hw specific details + * @idx: register index to write + * @spi: security parameter index + * @key: key byte array + * @salt: salt bytes + * @mode: rx decrypt control bits + * @ip_idx: index into IP table for related IP address + **/ +static void ixgbe_ipsec_set_rx_sa(struct ixgbe_hw *hw, u16 idx, __be32 spi, + u32 key[], u32 salt, u32 mode, u32 ip_idx) +{ + int i; + + /* store the SPI (in bigendian) and IPidx */ + IXGBE_WRITE_REG(hw, IXGBE_IPSRXSPI, cpu_to_le32(spi)); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPIDX, ip_idx); + IXGBE_WRITE_FLUSH(hw); + + ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_spi_tbl); + + /* store the key, salt, and mode */ + for (i = 0; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_IPSRXKEY(i), cpu_to_be32(key[3 - i])); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXSALT, cpu_to_be32(salt)); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXMOD, mode); + IXGBE_WRITE_FLUSH(hw); + + ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_key_tbl); +} + +/** + * ixgbe_ipsec_set_rx_ip - set up the register bits to save SA IP addr info + * @hw: hw specific details + * @idx: register index to write + * @addr: IP address byte array + **/ +static void ixgbe_ipsec_set_rx_ip(struct ixgbe_hw *hw, u16 idx, __be32 addr[]) +{ + int i; + + /* store the ip address */ + for (i = 0; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPADDR(i), cpu_to_le32(addr[i])); + IXGBE_WRITE_FLUSH(hw); + + ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_ip_tbl); +} + +/** + * ixgbe_ipsec_clear_hw_tables - because some tables don't get cleared on reset + * @adapter: board private structure + **/ +static void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + u32 buf[4] = {0, 0, 0, 0}; + u16 idx; + + /* disable Rx and Tx SA lookup */ + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, 0); + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, 0); + + /* scrub the tables - split the loops for the max of the IP table */ + for (idx = 0; idx < IXGBE_IPSEC_MAX_RX_IP_COUNT; idx++) { + ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0); + ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0); + ixgbe_ipsec_set_rx_ip(hw, idx, (__be32 *)buf); + } + for (; idx < IXGBE_IPSEC_MAX_SA_COUNT; idx++) { + ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0); + ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0); + } + + ipsec->num_rx_sa = 0; + ipsec->num_tx_sa = 0; +} + +/** + * ixgbe_ipsec_stop_data + * @adapter: board private structure + **/ +static void ixgbe_ipsec_stop_data(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + bool link = adapter->link_up; + u32 t_rdy, r_rdy; + u32 limit; + u32 reg; + + /* halt data paths */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL); + reg |= IXGBE_SECTXCTRL_TX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + reg |= IXGBE_SECRXCTRL_RX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg); + + IXGBE_WRITE_FLUSH(hw); + + /* If the tx fifo doesn't have link, but still has data, + * we can't clear the tx sec block. Set the MAC loopback + * before block clear + */ + if (!link) { + reg = IXGBE_READ_REG(hw, IXGBE_MACC); + reg |= IXGBE_MACC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_MACC, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_HLREG0); + reg |= IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg); + + IXGBE_WRITE_FLUSH(hw); + mdelay(3); + } + + /* wait for the paths to empty */ + limit = 20; + do { + mdelay(10); + t_rdy = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) & + IXGBE_SECTXSTAT_SECTX_RDY; + r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) & + IXGBE_SECRXSTAT_SECRX_RDY; + } while (!t_rdy && !r_rdy && limit--); + + /* undo loopback if we played with it earlier */ + if (!link) { + reg = IXGBE_READ_REG(hw, IXGBE_MACC); + reg &= ~IXGBE_MACC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_MACC, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_HLREG0); + reg &= ~IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg); + + IXGBE_WRITE_FLUSH(hw); + } +} + +/** + * ixgbe_ipsec_stop_engine + * @adapter: board private structure + **/ +static void ixgbe_ipsec_stop_engine(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 reg; + + ixgbe_ipsec_stop_data(adapter); + + /* disable Rx and Tx SA lookup */ + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, 0); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, 0); + + /* disable the Rx and Tx engines and full packet store-n-forward */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL); + reg |= IXGBE_SECTXCTRL_SECTX_DIS; + reg &= ~IXGBE_SECTXCTRL_STORE_FORWARD; + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + reg |= IXGBE_SECRXCTRL_SECRX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg); + + /* restore the "tx security buffer almost full threshold" to 0x250 */ + IXGBE_WRITE_REG(hw, IXGBE_SECTXBUFFAF, 0x250); + + /* Set minimum IFG between packets back to the default 0x1 */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + reg = (reg & 0xfffffff0) | 0x1; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg); + + /* final set for normal (no ipsec offload) processing */ + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, IXGBE_SECTXCTRL_SECTX_DIS); + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, IXGBE_SECRXCTRL_SECRX_DIS); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_start_engine + * @adapter: board private structure + * + * NOTE: this increases power consumption whether being used or not + **/ +static void ixgbe_ipsec_start_engine(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 reg; + + ixgbe_ipsec_stop_data(adapter); + + /* Set minimum IFG between packets to 3 */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + reg = (reg & 0xfffffff0) | 0x3; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg); + + /* Set "tx security buffer almost full threshold" to 0x15 so that the + * almost full indication is generated only after buffer contains at + * least an entire jumbo packet. + */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF); + reg = (reg & 0xfffffc00) | 0x15; + IXGBE_WRITE_REG(hw, IXGBE_SECTXBUFFAF, reg); + + /* restart the data paths by clearing the DISABLE bits */ + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, 0); + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, IXGBE_SECTXCTRL_STORE_FORWARD); + + /* enable Rx and Tx SA lookup */ + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, IXGBE_RXTXIDX_IPS_EN); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, IXGBE_RXTXIDX_IPS_EN); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_restore - restore the ipsec HW settings after a reset + * @adapter: board private structure + **/ +void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (!(adapter->flags2 & IXGBE_FLAG2_IPSEC_ENABLED)) + return; + + /* clean up and restart the engine */ + ixgbe_ipsec_stop_engine(adapter); + ixgbe_ipsec_clear_hw_tables(adapter); + ixgbe_ipsec_start_engine(adapter); + + /* reload the IP addrs */ + for (i = 0; i < IXGBE_IPSEC_MAX_RX_IP_COUNT; i++) { + struct rx_ip_sa *ipsa = &ipsec->ip_tbl[i]; + + if (ipsa->used) + ixgbe_ipsec_set_rx_ip(hw, i, ipsa->ipaddr); + } + + /* reload the Rx and Tx keys */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + struct rx_sa *rsa = &ipsec->rx_tbl[i]; + struct tx_sa *tsa = &ipsec->tx_tbl[i]; + + if (rsa->used) + ixgbe_ipsec_set_rx_sa(hw, i, rsa->xs->id.spi, + rsa->key, rsa->salt, + rsa->mode, rsa->iptbl_ind); + + if (tsa->used) + ixgbe_ipsec_set_tx_sa(hw, i, tsa->key, tsa->salt); + } +} + +/** + * ixgbe_ipsec_find_empty_idx - find the first unused security parameter index + * @ipsec: pointer to ipsec struct + * @rxtable: true if we need to look in the Rx table + * + * Returns the first unused index in either the Rx or Tx SA table + **/ +static int ixgbe_ipsec_find_empty_idx(struct ixgbe_ipsec *ipsec, bool rxtable) +{ + u32 i; + + if (rxtable) { + if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search rx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->rx_tbl[i].used) + return i; + } + } else { + if (ipsec->num_tx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search tx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->tx_tbl[i].used) + return i; + } + } + + return -ENOSPC; +} + +/** + * ixgbe_ipsec_find_rx_state - find the state that matches + * @ipsec: pointer to ipsec struct + * @daddr: inbound address to match + * @proto: protocol to match + * @spi: SPI to match + * @ip4: true if using an ipv4 address + * + * Returns a pointer to the matching SA state information + **/ +static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec, + __be32 *daddr, u8 proto, + __be32 spi, bool ip4) +{ + struct rx_sa *rsa; + struct xfrm_state *ret = NULL; + + rcu_read_lock(); + hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, spi) + if (spi == rsa->xs->id.spi && + ((ip4 && *daddr == rsa->xs->id.daddr.a4) || + (!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6, + sizeof(rsa->xs->id.daddr.a6)))) && + proto == rsa->xs->id.proto) { + ret = rsa->xs; + xfrm_state_hold(ret); + break; + } + rcu_read_unlock(); + return ret; +} + +/** + * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol + * @xs: pointer to xfrm_state struct + * @mykey: pointer to key array to populate + * @mysalt: pointer to salt value to populate + * + * This copies the protocol keys and salt to our own data tables. The + * 82599 family only supports the one algorithm. + **/ +static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs, + u32 *mykey, u32 *mysalt) +{ + struct net_device *dev = xs->xso.dev; + unsigned char *key_data; + char *alg_name = NULL; + const char aes_gcm_name[] = "rfc4106(gcm(aes))"; + int key_len; + + if (xs->aead) { + key_data = &xs->aead->alg_key[0]; + key_len = xs->aead->alg_key_len; + alg_name = xs->aead->alg_name; + } else { + netdev_err(dev, "Unsupported IPsec algorithm\n"); + return -EINVAL; + } + + if (strcmp(alg_name, aes_gcm_name)) { + netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", + aes_gcm_name); + return -EINVAL; + } + + /* The key bytes come down in a bigendian array of bytes, so + * we don't need to do any byteswapping. + * 160 accounts for 16 byte key and 4 byte salt + */ + if (key_len == 160) { + *mysalt = ((u32 *)key_data)[4]; + } else if (key_len != 128) { + netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n"); + return -EINVAL; + } else { + netdev_info(dev, "IPsec hw offload parameters missing 32 bit salt value\n"); + *mysalt = 0; + } + memcpy(mykey, key_data, 16); + + return 0; +} + +/** + * ixgbe_ipsec_add_sa - program device with a security association + * @xs: pointer to transformer state struct + **/ +static int ixgbe_ipsec_add_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.dev; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + int checked, match, first; + u16 sa_idx; + int ret; + int i; + + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { + netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n", + xs->id.proto); + return -EINVAL; + } + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + struct rx_sa rsa; + + if (xs->calg) { + netdev_err(dev, "Compression offload not supported\n"); + return -EINVAL; + } + + /* find the first unused index */ + ret = ixgbe_ipsec_find_empty_idx(ipsec, true); + if (ret < 0) { + netdev_err(dev, "No space for SA in Rx table!\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&rsa, 0, sizeof(rsa)); + rsa.used = true; + rsa.xs = xs; + + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.decrypt = xs->ealg || xs->aead; + + /* get the key and salt */ + ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Rx SA table\n"); + return ret; + } + + /* get ip for rx sa table */ + if (xs->props.family == AF_INET6) + memcpy(rsa.ipaddr, &xs->id.daddr.a6, 16); + else + memcpy(&rsa.ipaddr[3], &xs->id.daddr.a4, 4); + + /* The HW does not have a 1:1 mapping from keys to IP addrs, so + * check for a matching IP addr entry in the table. If the addr + * already exists, use it; else find an unused slot and add the + * addr. If one does not exist and there are no unused table + * entries, fail the request. + */ + + /* Find an existing match or first not used, and stop looking + * after we've checked all we know we have. + */ + checked = 0; + match = -1; + first = -1; + for (i = 0; + i < IXGBE_IPSEC_MAX_RX_IP_COUNT && + (checked < ipsec->num_rx_sa || first < 0); + i++) { + if (ipsec->ip_tbl[i].used) { + if (!memcmp(ipsec->ip_tbl[i].ipaddr, + rsa.ipaddr, sizeof(rsa.ipaddr))) { + match = i; + break; + } + checked++; + } else if (first < 0) { + first = i; /* track the first empty seen */ + } + } + + if (ipsec->num_rx_sa == 0) + first = 0; + + if (match >= 0) { + /* addrs are the same, we should use this one */ + rsa.iptbl_ind = match; + ipsec->ip_tbl[match].ref_cnt++; + + } else if (first >= 0) { + /* no matches, but here's an empty slot */ + rsa.iptbl_ind = first; + + memcpy(ipsec->ip_tbl[first].ipaddr, + rsa.ipaddr, sizeof(rsa.ipaddr)); + ipsec->ip_tbl[first].ref_cnt = 1; + ipsec->ip_tbl[first].used = true; + + ixgbe_ipsec_set_rx_ip(hw, rsa.iptbl_ind, rsa.ipaddr); + + } else { + /* no match and no empty slot */ + netdev_err(dev, "No space for SA in Rx IP SA table\n"); + memset(&rsa, 0, sizeof(rsa)); + return -ENOSPC; + } + + rsa.mode = IXGBE_RXMOD_VALID; + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.mode |= IXGBE_RXMOD_PROTO_ESP; + if (rsa.decrypt) + rsa.mode |= IXGBE_RXMOD_DECRYPT; + if (rsa.xs->props.family == AF_INET6) + rsa.mode |= IXGBE_RXMOD_IPV6; + + /* the preparations worked, so save the info */ + memcpy(&ipsec->rx_tbl[sa_idx], &rsa, sizeof(rsa)); + + ixgbe_ipsec_set_rx_sa(hw, sa_idx, rsa.xs->id.spi, rsa.key, + rsa.salt, rsa.mode, rsa.iptbl_ind); + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_RX_INDEX; + + ipsec->num_rx_sa++; + + /* hash the new entry for faster search in Rx path */ + hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist, + rsa.xs->id.spi); + } else { + struct tx_sa tsa; + + /* find the first unused index */ + ret = ixgbe_ipsec_find_empty_idx(ipsec, false); + if (ret < 0) { + netdev_err(dev, "No space for SA in Tx table\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&tsa, 0, sizeof(tsa)); + tsa.used = true; + tsa.xs = xs; + + if (xs->id.proto & IPPROTO_ESP) + tsa.encrypt = xs->ealg || xs->aead; + + ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Tx SA table\n"); + memset(&tsa, 0, sizeof(tsa)); + return ret; + } + + /* the preparations worked, so save the info */ + memcpy(&ipsec->tx_tbl[sa_idx], &tsa, sizeof(tsa)); + + ixgbe_ipsec_set_tx_sa(hw, sa_idx, tsa.key, tsa.salt); + + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_TX_INDEX; + + ipsec->num_tx_sa++; + } + + /* enable the engine if not already warmed up */ + if (!(adapter->flags2 & IXGBE_FLAG2_IPSEC_ENABLED)) { + ixgbe_ipsec_start_engine(adapter); + adapter->flags2 |= IXGBE_FLAG2_IPSEC_ENABLED; + } + + return 0; +} + +/** + * ixgbe_ipsec_del_sa - clear out this specific SA + * @xs: pointer to transformer state struct + **/ +static void ixgbe_ipsec_del_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.dev; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + u32 zerobuf[4] = {0, 0, 0, 0}; + u16 sa_idx; + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + struct rx_sa *rsa; + u8 ipi; + + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX; + rsa = &ipsec->rx_tbl[sa_idx]; + + if (!rsa->used) { + netdev_err(dev, "Invalid Rx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbe_ipsec_set_rx_sa(hw, sa_idx, 0, zerobuf, 0, 0, 0); + hash_del_rcu(&rsa->hlist); + + /* if the IP table entry is referenced by only this SA, + * i.e. ref_cnt is only 1, clear the IP table entry as well + */ + ipi = rsa->iptbl_ind; + if (ipsec->ip_tbl[ipi].ref_cnt > 0) { + ipsec->ip_tbl[ipi].ref_cnt--; + + if (!ipsec->ip_tbl[ipi].ref_cnt) { + memset(&ipsec->ip_tbl[ipi], 0, + sizeof(struct rx_ip_sa)); + ixgbe_ipsec_set_rx_ip(hw, ipi, zerobuf); + } + } + + memset(rsa, 0, sizeof(struct rx_sa)); + ipsec->num_rx_sa--; + } else { + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + + if (!ipsec->tx_tbl[sa_idx].used) { + netdev_err(dev, "Invalid Tx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbe_ipsec_set_tx_sa(hw, sa_idx, zerobuf, 0); + memset(&ipsec->tx_tbl[sa_idx], 0, sizeof(struct tx_sa)); + ipsec->num_tx_sa--; + } + + /* if there are no SAs left, stop the engine to save energy */ + if (ipsec->num_rx_sa == 0 && ipsec->num_tx_sa == 0) { + adapter->flags2 &= ~IXGBE_FLAG2_IPSEC_ENABLED; + ixgbe_ipsec_stop_engine(adapter); + } +} + +/** + * ixgbe_ipsec_offload_ok - can this packet use the xfrm hw offload + * @skb: current data packet + * @xs: pointer to transformer state struct + **/ +static bool ixgbe_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) +{ + if (xs->props.family == AF_INET) { + /* Offload with IPv4 options is not supported yet */ + if (ip_hdr(skb)->ihl != 5) + return false; + } else { + /* Offload with IPv6 extension headers is not support yet */ + if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) + return false; + } + + return true; +} + +/** + * ixgbe_ipsec_free - called by xfrm garbage collections + * @xs: pointer to transformer state struct + * + * We don't have any garbage to collect, so we shouldn't bother + * implementing this function, but the XFRM code doesn't check for + * existence before calling the API callback. + **/ +static void ixgbe_ipsec_free(struct xfrm_state *xs) +{ +} + +static const struct xfrmdev_ops ixgbe_xfrmdev_ops = { + .xdo_dev_state_add = ixgbe_ipsec_add_sa, + .xdo_dev_state_delete = ixgbe_ipsec_del_sa, + .xdo_dev_offload_ok = ixgbe_ipsec_offload_ok, + .xdo_dev_state_free = ixgbe_ipsec_free, +}; + +/** + * ixgbe_ipsec_tx - setup Tx flags for ipsec offload + * @tx_ring: outgoing context + * @first: current data packet + * @itd: ipsec Tx data for later use in building context descriptor + **/ +int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd) +{ + struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_state *xs; + struct tx_sa *tsa; + + if (unlikely(!first->skb->sp->len)) { + netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n", + __func__, first->skb->sp->len); + return 0; + } + + xs = xfrm_input_state(first->skb); + if (unlikely(!xs)) { + netdev_err(tx_ring->netdev, "%s: no xfrm_input_state() xs = %p\n", + __func__, xs); + return 0; + } + + itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + if (unlikely(itd->sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) { + netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", + __func__, itd->sa_idx, xs->xso.offload_handle); + return 0; + } + + tsa = &ipsec->tx_tbl[itd->sa_idx]; + if (unlikely(!tsa->used)) { + netdev_err(tx_ring->netdev, "%s: unused sa_idx=%d\n", + __func__, itd->sa_idx); + return 0; + } + + first->tx_flags |= IXGBE_TX_FLAGS_IPSEC | IXGBE_TX_FLAGS_CC; + + itd->flags = 0; + if (xs->id.proto == IPPROTO_ESP) { + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP | + IXGBE_ADVTXD_TUCMD_L4T_TCP; + if (first->protocol == htons(ETH_P_IP)) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPV4; + itd->trailer_len = xs->props.trailer_len; + } + if (tsa->encrypt) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN; + + return 1; +} + +/** + * ixgbe_ipsec_rx - decode ipsec bits from Rx descriptor + * @rx_ring: receiving ring + * @rx_desc: receive data descriptor + * @skb: current data packet + * + * Determine if there was an ipsec encapsulation noticed, and if so set up + * the resulting status for later in the receive stack. + **/ +void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev); + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + __le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH | + IXGBE_RXDADV_PKTTYPE_IPSEC_ESP); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_offload *xo = NULL; + struct xfrm_state *xs = NULL; + struct ipv6hdr *ip6 = NULL; + struct iphdr *ip4 = NULL; + void *daddr; + __be32 spi; + u8 *c_hdr; + u8 proto; + + /* Find the ip and crypto headers in the data. + * We can assume no vlan header in the way, b/c the + * hw won't recognize the IPsec packet and anyway the + * currently vlan device doesn't support xfrm offload. + */ + if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV4)) { + ip4 = (struct iphdr *)(skb->data + ETH_HLEN); + daddr = &ip4->daddr; + c_hdr = (u8 *)ip4 + ip4->ihl * 4; + } else if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV6)) { + ip6 = (struct ipv6hdr *)(skb->data + ETH_HLEN); + daddr = &ip6->daddr; + c_hdr = (u8 *)ip6 + sizeof(struct ipv6hdr); + } else { + return; + } + + switch (pkt_info & ipsec_pkt_types) { + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH): + spi = ((struct ip_auth_hdr *)c_hdr)->spi; + proto = IPPROTO_AH; + break; + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_ESP): + spi = ((struct ip_esp_hdr *)c_hdr)->spi; + proto = IPPROTO_ESP; + break; + default: + return; + } + + xs = ixgbe_ipsec_find_rx_state(ipsec, daddr, proto, spi, !!ip4); + if (unlikely(!xs)) + return; + + skb->sp = secpath_dup(skb->sp); + if (unlikely(!skb->sp)) + return; + + skb->sp->xvec[skb->sp->len++] = xs; + skb->sp->olen++; + xo = xfrm_offload(skb); + xo->flags = CRYPTO_DONE; + xo->status = CRYPTO_SUCCESS; + + adapter->rx_ipsec++; +} + +/** + * ixgbe_init_ipsec_offload - initialize security registers for IPSec operation + * @adapter: board private structure + **/ +void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ipsec *ipsec; + size_t size; + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + return; + + ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL); + if (!ipsec) + goto err1; + hash_init(ipsec->rx_sa_list); + + size = sizeof(struct rx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->rx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->rx_tbl) + goto err2; + + size = sizeof(struct tx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->tx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->tx_tbl) + goto err2; + + size = sizeof(struct rx_ip_sa) * IXGBE_IPSEC_MAX_RX_IP_COUNT; + ipsec->ip_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->ip_tbl) + goto err2; + + ipsec->num_rx_sa = 0; + ipsec->num_tx_sa = 0; + + adapter->ipsec = ipsec; + ixgbe_ipsec_stop_engine(adapter); + ixgbe_ipsec_clear_hw_tables(adapter); + + adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops; + adapter->netdev->features |= NETIF_F_HW_ESP; + adapter->netdev->hw_enc_features |= NETIF_F_HW_ESP; + + return; + +err2: + kfree(ipsec->ip_tbl); + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); +err1: + kfree(adapter->ipsec); + netdev_err(adapter->netdev, "Unable to allocate memory for SA tables"); +} + +/** + * ixgbe_stop_ipsec_offload - tear down the ipsec offload + * @adapter: board private structure + **/ +void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + + adapter->ipsec = NULL; + if (ipsec) { + kfree(ipsec->ip_tbl); + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h new file mode 100644 index 000000000000..da3ce7849e85 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h @@ -0,0 +1,93 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program. If not, see <http://www.gnu.org/licenses/>. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + Linux NICS <linux.nics@intel.com> + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#ifndef _IXGBE_IPSEC_H_ +#define _IXGBE_IPSEC_H_ + +#define IXGBE_IPSEC_MAX_SA_COUNT 1024 +#define IXGBE_IPSEC_MAX_RX_IP_COUNT 128 +#define IXGBE_IPSEC_BASE_RX_INDEX 0 +#define IXGBE_IPSEC_BASE_TX_INDEX IXGBE_IPSEC_MAX_SA_COUNT + +#define IXGBE_RXTXIDX_IPS_EN 0x00000001 +#define IXGBE_RXIDX_TBL_SHIFT 1 +enum ixgbe_ipsec_tbl_sel { + ips_rx_ip_tbl = 0x01, + ips_rx_spi_tbl = 0x02, + ips_rx_key_tbl = 0x03, +}; + +#define IXGBE_RXTXIDX_IDX_SHIFT 3 +#define IXGBE_RXTXIDX_READ 0x40000000 +#define IXGBE_RXTXIDX_WRITE 0x80000000 + +#define IXGBE_RXMOD_VALID 0x00000001 +#define IXGBE_RXMOD_PROTO_ESP 0x00000004 +#define IXGBE_RXMOD_DECRYPT 0x00000008 +#define IXGBE_RXMOD_IPV6 0x00000010 + +struct rx_sa { + struct hlist_node hlist; + struct xfrm_state *xs; + __be32 ipaddr[4]; + u32 key[4]; + u32 salt; + u32 mode; + u8 iptbl_ind; + bool used; + bool decrypt; +}; + +struct rx_ip_sa { + __be32 ipaddr[4]; + u32 ref_cnt; + bool used; +}; + +struct tx_sa { + struct xfrm_state *xs; + u32 key[4]; + u32 salt; + bool encrypt; + bool used; +}; + +struct ixgbe_ipsec_tx_data { + u32 flags; + u16 trailer_len; + u16 sa_idx; +}; + +struct ixgbe_ipsec { + u16 num_rx_sa; + u16 num_tx_sa; + struct rx_ip_sa *ip_tbl; + struct rx_sa *rx_tbl; + struct tx_sa *tx_tbl; + DECLARE_HASHTABLE(rx_sa_list, 10); +}; +#endif /* _IXGBE_IPSEC_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index b3c282d09b18..4242f0213e46 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1282,7 +1282,7 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter) } void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens, - u32 fcoe_sof_eof, u32 type_tucmd, u32 mss_l4len_idx) + u32 fceof_saidx, u32 type_tucmd, u32 mss_l4len_idx) { struct ixgbe_adv_tx_context_desc *context_desc; u16 i = tx_ring->next_to_use; @@ -1296,7 +1296,7 @@ void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens, type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = cpu_to_le32(fcoe_sof_eof); + context_desc->fceof_saidx = cpu_to_le32(fceof_saidx); context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 4f28621b76e1..0da5aa2c8aba 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1171,7 +1171,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, struct ixgbe_adapter *adapter = q_vector->adapter; struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - unsigned int total_bytes = 0, total_packets = 0; + unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0; unsigned int budget = q_vector->tx.work_limit; unsigned int i = tx_ring->next_to_clean; @@ -1202,6 +1202,8 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, /* update the statistics for this packet */ total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; + if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC) + total_ipsec++; /* free the skb */ if (ring_is_xdp(tx_ring)) @@ -1264,6 +1266,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, u64_stats_update_end(&tx_ring->syncp); q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + adapter->tx_ipsec += total_ipsec; if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { /* schedule immediate reset if we believe we hung */ @@ -1752,6 +1755,9 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); } + if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP)) + ixgbe_ipsec_rx(rx_ring, rx_desc, skb); + skb->protocol = eth_type_trans(skb, dev); /* record Rx queue, or update MACVLAN statistics */ @@ -4127,11 +4133,15 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, rxdctl &= ~0x3FFFFF; rxdctl |= 0x080420; #if (PAGE_SIZE < 8192) - } else { + /* RXDCTL.RLPML does not work on 82599 */ + } else if (hw->mac.type != ixgbe_mac_82599EB) { rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | IXGBE_RXDCTL_RLPML_EN); - /* Limit the maximum frame size so we don't overrun the skb */ + /* Limit the maximum frame size so we don't overrun the skb. + * This can happen in SRIOV mode when the MTU of the VF is + * higher than the MTU of the PF. + */ if (ring_uses_build_skb(ring) && !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB | @@ -5425,6 +5435,7 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) ixgbe_set_rx_mode(adapter->netdev); ixgbe_restore_vlan(adapter); + ixgbe_ipsec_restore(adapter); switch (hw->mac.type) { case ixgbe_mac_82599EB: @@ -7252,6 +7263,9 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) case IXGBE_LINK_SPEED_10GB_FULL: speed_str = "10 Gbps"; break; + case IXGBE_LINK_SPEED_5GB_FULL: + speed_str = "5 Gbps"; + break; case IXGBE_LINK_SPEED_2_5GB_FULL: speed_str = "2.5 Gbps"; break; @@ -7795,10 +7809,12 @@ static inline bool ixgbe_ipv6_csum_is_sctp(struct sk_buff *skb) } static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring, - struct ixgbe_tx_buffer *first) + struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd) { struct sk_buff *skb = first->skb; u32 vlan_macip_lens = 0; + u32 fceof_saidx = 0; u32 type_tucmd = 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { @@ -7839,7 +7855,12 @@ no_csum: vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; - ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, 0, type_tucmd, 0); + if (first->tx_flags & IXGBE_TX_FLAGS_IPSEC) { + fceof_saidx |= itd->sa_idx; + type_tucmd |= itd->flags | itd->trailer_len; + } + + ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, 0); } #define IXGBE_SET_FLAG(_input, _flag, _result) \ @@ -7882,11 +7903,16 @@ static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, IXGBE_TX_FLAGS_CSUM, IXGBE_ADVTXD_POPTS_TXSM); - /* enble IPv4 checksum for TSO */ + /* enable IPv4 checksum for TSO */ olinfo_status |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_IPV4, IXGBE_ADVTXD_POPTS_IXSM); + /* enable IPsec */ + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_IPSEC, + IXGBE_ADVTXD_POPTS_IPSEC); + /* * Check Context must be set if Tx switch is enabled, which it * always is for case where virtual functions are running @@ -8350,6 +8376,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, u32 tx_flags = 0; unsigned short f; u16 count = TXD_USE_COUNT(skb_headlen(skb)); + struct ixgbe_ipsec_tx_data ipsec_tx = { 0 }; __be16 protocol = skb->protocol; u8 hdr_len = 0; @@ -8454,11 +8481,16 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, } #endif /* IXGBE_FCOE */ + +#ifdef CONFIG_XFRM_OFFLOAD + if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx)) + goto out_drop; +#endif tso = ixgbe_tso(tx_ring, first, &hdr_len); if (tso < 0) goto out_drop; else if (!tso) - ixgbe_tx_csum(tx_ring, first); + ixgbe_tx_csum(tx_ring, first, &ipsec_tx); /* add the ATR filter if ATR is on */ if (test_bit(__IXGBE_TX_FDIR_INIT_DONE, &tx_ring->state)) @@ -9278,9 +9310,6 @@ free_jump: static int ixgbe_setup_tc_cls_u32(struct ixgbe_adapter *adapter, struct tc_cls_u32_offload *cls_u32) { - if (cls_u32->common.chain_index) - return -EOPNOTSUPP; - switch (cls_u32->command) { case TC_CLSU32_NEW_KNODE: case TC_CLSU32_REPLACE_KNODE: @@ -9302,7 +9331,7 @@ static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data, { struct ixgbe_adapter *adapter = cb_priv; - if (!tc_can_offload(adapter->netdev)) + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) return -EOPNOTSUPP; switch (type) { @@ -9870,6 +9899,12 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) features &= ~NETIF_F_TSO; +#ifdef CONFIG_XFRM_OFFLOAD + /* IPsec offload doesn't get along well with others *yet* */ + if (skb->sp) + features &= ~(NETIF_F_TSO | NETIF_F_HW_CSUM); +#endif + return features; } @@ -10459,6 +10494,7 @@ skip_sriov: NETIF_F_FCOE_MTU; } #endif /* IXGBE_FCOE */ + ixgbe_init_ipsec_offload(adapter); if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) netdev->hw_features |= NETIF_F_LRO; @@ -10694,6 +10730,7 @@ static void ixgbe_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + ixgbe_stop_ipsec_offload(adapter); ixgbe_clear_interrupt_scheme(adapter); ixgbe_release_hw_control(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 21eb79ae3c30..ca45359686d3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -2360,11 +2360,6 @@ enum { #define IXGBE_TXD_CMD_VLE 0x40000000 /* Add VLAN tag */ #define IXGBE_TXD_STAT_DD 0x00000001 /* Descriptor Done */ -#define IXGBE_RXDADV_IPSEC_STATUS_SECP 0x00020000 -#define IXGBE_RXDADV_IPSEC_ERROR_INVALID_PROTOCOL 0x08000000 -#define IXGBE_RXDADV_IPSEC_ERROR_INVALID_LENGTH 0x10000000 -#define IXGBE_RXDADV_IPSEC_ERROR_AUTH_FAILED 0x18000000 -#define IXGBE_RXDADV_IPSEC_ERROR_BIT_MASK 0x18000000 /* Multiple Transmit Queue Command Register */ #define IXGBE_MTQC_RT_ENA 0x1 /* DCB Enable */ #define IXGBE_MTQC_VT_ENA 0x2 /* VMDQ2 Enable */ @@ -2416,6 +2411,9 @@ enum { #define IXGBE_RXDADV_ERR_LE 0x02000000 /* Length Error */ #define IXGBE_RXDADV_ERR_PE 0x08000000 /* Packet Error */ #define IXGBE_RXDADV_ERR_OSE 0x10000000 /* Oversize Error */ +#define IXGBE_RXDADV_ERR_IPSEC_INV_PROTOCOL 0x08000000 /* overlap ERR_PE */ +#define IXGBE_RXDADV_ERR_IPSEC_INV_LENGTH 0x10000000 /* overlap ERR_OSE */ +#define IXGBE_RXDADV_ERR_IPSEC_AUTH_FAILED 0x18000000 #define IXGBE_RXDADV_ERR_USE 0x20000000 /* Undersize Error */ #define IXGBE_RXDADV_ERR_TCPE 0x40000000 /* TCP/UDP Checksum Error */ #define IXGBE_RXDADV_ERR_IPE 0x80000000 /* IP Checksum Error */ @@ -2437,6 +2435,7 @@ enum { #define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */ #define IXGBE_RXDADV_STAT_FCSTAT_DDP 0x00000030 /* 11: Ctxt w/ DDP */ #define IXGBE_RXDADV_STAT_TS 0x00010000 /* IEEE 1588 Time Stamp */ +#define IXGBE_RXDADV_STAT_SECP 0x00020000 /* IPsec/MACsec pkt found */ /* PSRTYPE bit definitions */ #define IXGBE_PSRTYPE_TCPHDR 0x00000010 @@ -2503,13 +2502,6 @@ enum { #define IXGBE_RXDADV_PKTTYPE_ETQF_MASK 0x00000070 /* ETQF has 8 indices */ #define IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT 4 /* Right-shift 4 bits */ -/* Security Processing bit Indication */ -#define IXGBE_RXDADV_LNKSEC_STATUS_SECP 0x00020000 -#define IXGBE_RXDADV_LNKSEC_ERROR_NO_SA_MATCH 0x08000000 -#define IXGBE_RXDADV_LNKSEC_ERROR_REPLAY_ERROR 0x10000000 -#define IXGBE_RXDADV_LNKSEC_ERROR_BIT_MASK 0x18000000 -#define IXGBE_RXDADV_LNKSEC_ERROR_BAD_SIG 0x18000000 - /* Masks to determine if packets should be dropped due to frame errors */ #define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \ IXGBE_RXD_ERR_CE | \ @@ -2523,6 +2515,8 @@ enum { IXGBE_RXDADV_ERR_LE | \ IXGBE_RXDADV_ERR_PE | \ IXGBE_RXDADV_ERR_OSE | \ + IXGBE_RXDADV_ERR_IPSEC_INV_PROTOCOL | \ + IXGBE_RXDADV_ERR_IPSEC_INV_LENGTH | \ IXGBE_RXDADV_ERR_USE) /* Multicast bit mask */ @@ -2901,7 +2895,7 @@ union ixgbe_adv_rx_desc { /* Context descriptors */ struct ixgbe_adv_tx_context_desc { __le32 vlan_macip_lens; - __le32 seqnum_seed; + __le32 fceof_saidx; __le32 type_tucmd_mlhl; __le32 mss_l4len_idx; }; @@ -2932,6 +2926,7 @@ struct ixgbe_adv_tx_context_desc { IXGBE_ADVTXD_POPTS_SHIFT) #define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \ IXGBE_ADVTXD_POPTS_SHIFT) +#define IXGBE_ADVTXD_POPTS_IPSEC 0x00000400 /* IPSec offload request */ #define IXGBE_ADVTXD_POPTS_ISCO_1ST 0x00000000 /* 1st TSO of iSCSI PDU */ #define IXGBE_ADVTXD_POPTS_ISCO_MDL 0x00000800 /* Middle TSO of iSCSI PDU */ #define IXGBE_ADVTXD_POPTS_ISCO_LAST 0x00001000 /* Last TSO of iSCSI PDU */ @@ -2947,7 +2942,6 @@ struct ixgbe_adv_tx_context_desc { #define IXGBE_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 Packet TYPE of SCTP */ #define IXGBE_ADVTXD_TUCMD_L4T_RSV 0x00001800 /* RSV L4 Packet TYPE */ #define IXGBE_ADVTXD_TUCMD_MKRREQ 0x00002000 /*Req requires Markers and CRC*/ -#define IXGBE_ADVTXD_POPTS_IPSEC 0x00000400 /* IPSec offload request */ #define IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP 0x00002000 /* IPSec Type ESP */ #define IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN 0x00004000/* ESP Encrypt Enable */ #define IXGBE_ADVTXT_TUCMD_FCOE 0x00008000 /* FCoE Frame Type */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 3bce26e77090..f470d0204771 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -949,7 +949,7 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, u16 length, bufsz, i, start; u16 *local_buffer; - bufsz = sizeof(buf) / sizeof(buf[0]); + bufsz = ARRAY_SIZE(buf); /* Read a chunk at the pointer location */ if (!buffer) { diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index ff9d05f308ee..4400e49090b4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -75,6 +75,9 @@ static struct ixgbe_stats ixgbevf_gstrings_stats[] = { IXGBEVF_STAT("tx_timeout_count", tx_timeout_count), IXGBEVF_NETDEV_STAT(multicast), IXGBEVF_STAT("rx_csum_offload_errors", hw_csum_rx_error), + IXGBEVF_STAT("alloc_rx_page", alloc_rx_page), + IXGBEVF_STAT("alloc_rx_page_failed", alloc_rx_page_failed), + IXGBEVF_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed), }; #define IXGBEVF_QUEUE_STATS_LEN ( \ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 581f44bbd7b3..f6952425c87d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -62,7 +62,12 @@ struct ixgbevf_tx_buffer { struct ixgbevf_rx_buffer { dma_addr_t dma; struct page *page; - unsigned int page_offset; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; }; struct ixgbevf_stats { @@ -79,6 +84,7 @@ struct ixgbevf_tx_queue_stats { struct ixgbevf_rx_queue_stats { u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; + u64 alloc_rx_page; u64 csum_err; }; @@ -260,6 +266,9 @@ static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32 value) #define MIN_MSIX_Q_VECTORS 1 #define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS) +#define IXGBEVF_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + /* board specific private data structure */ struct ixgbevf_adapter { /* this field must be first, see ixgbevf_process_skb_fields */ @@ -287,8 +296,9 @@ struct ixgbevf_adapter { u64 hw_csum_rx_error; u64 hw_rx_no_dma_resources; int num_msix_vectors; - u32 alloc_rx_page_failed; - u32 alloc_rx_buff_failed; + u64 alloc_rx_page_failed; + u64 alloc_rx_buff_failed; + u64 alloc_rx_page; struct msix_entry *msix_entries; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index ed5c3aea7939..9b3d43d28106 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -206,28 +206,6 @@ static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction, } } -static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring, - struct ixgbevf_tx_buffer *tx_buffer) -{ - if (tx_buffer->skb) { - dev_kfree_skb_any(tx_buffer->skb); - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } else if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } - tx_buffer->next_to_watch = NULL; - tx_buffer->skb = NULL; - dma_unmap_len_set(tx_buffer, len, 0); - /* tx_buffer must be completely set up in the transmit path */ -} - static u64 ixgbevf_get_tx_completed(struct ixgbevf_ring *ring) { return ring->stats.packets; @@ -349,7 +327,6 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, DMA_TO_DEVICE); /* clear tx_buffer data */ - tx_buffer->skb = NULL; dma_unmap_len_set(tx_buffer, len, 0); /* unmap remaining buffers */ @@ -595,8 +572,8 @@ static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, } /* map page for use */ - dma = dma_map_page(rx_ring->dev, page, 0, - PAGE_SIZE, DMA_FROM_DEVICE); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, + DMA_FROM_DEVICE, IXGBEVF_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use @@ -604,13 +581,15 @@ static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, if (dma_mapping_error(rx_ring->dev, dma)) { __free_page(page); - rx_ring->rx_stats.alloc_rx_buff_failed++; + rx_ring->rx_stats.alloc_rx_page_failed++; return false; } bi->dma = dma; bi->page = page; bi->page_offset = 0; + bi->pagecnt_bias = 1; + rx_ring->rx_stats.alloc_rx_page++; return true; } @@ -639,6 +618,12 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, if (!ixgbevf_alloc_mapped_page(rx_ring, bi)) break; + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + IXGBEVF_RX_BUFSZ, + DMA_FROM_DEVICE); + /* Refresh the desc even if pkt_addr didn't change * because each write-back erases this info. */ @@ -653,8 +638,8 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, i -= rx_ring->count; } - /* clear the hdr_addr for the next_to_use descriptor */ - rx_desc->read.hdr_addr = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); @@ -741,12 +726,7 @@ static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, new_buff->page = old_buff->page; new_buff->dma = old_buff->dma; new_buff->page_offset = old_buff->page_offset; - - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma, - new_buff->page_offset, - IXGBEVF_RX_BUFSZ, - DMA_FROM_DEVICE); + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } static inline bool ixgbevf_page_is_reserved(struct page *page) @@ -754,6 +734,45 @@ static inline bool ixgbevf_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer, + struct page *page, + const unsigned int truesize) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + + /* avoid re-using remote pages */ + if (unlikely(ixgbevf_page_is_reserved(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_ref_count(page) != pagecnt_bias)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= IXGBEVF_RX_BUFSZ; + +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > (PAGE_SIZE - IXGBEVF_RX_BUFSZ)) + return false; + +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + /** * ixgbevf_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on @@ -771,12 +790,12 @@ static inline bool ixgbevf_page_is_reserved(struct page *page) **/ static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, struct ixgbevf_rx_buffer *rx_buffer, + u16 size, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { struct page *page = rx_buffer->page; unsigned char *va = page_address(page) + rx_buffer->page_offset; - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); #if (PAGE_SIZE < 8192) unsigned int truesize = IXGBEVF_RX_BUFSZ; #else @@ -795,7 +814,6 @@ static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, return true; /* this page cannot be reused so discard it */ - put_page(page); return false; } @@ -815,32 +833,7 @@ add_tail_frag: skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, (unsigned long)va & ~PAGE_MASK, size, truesize); - /* avoid re-using remote pages */ - if (unlikely(ixgbevf_page_is_reserved(page))) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely(page_count(page) != 1)) - return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IXGBEVF_RX_BUFSZ; - -#else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; - - if (rx_buffer->page_offset > (PAGE_SIZE - IXGBEVF_RX_BUFSZ)) - return false; - -#endif - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. - */ - page_ref_inc(page); - - return true; + return ixgbevf_can_reuse_rx_page(rx_buffer, page, truesize); } static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring, @@ -849,11 +842,19 @@ static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring, { struct ixgbevf_rx_buffer *rx_buffer; struct page *page; + u16 size = le16_to_cpu(rx_desc->wb.upper.length); rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; page = rx_buffer->page; prefetchw(page); + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + if (likely(!skb)) { void *page_addr = page_address(page) + rx_buffer->page_offset; @@ -879,21 +880,18 @@ static struct sk_buff *ixgbevf_fetch_rx_buffer(struct ixgbevf_ring *rx_ring, prefetchw(skb->data); } - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - IXGBEVF_RX_BUFSZ, - DMA_FROM_DEVICE); - /* pull page into skb */ - if (ixgbevf_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + if (ixgbevf_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { /* hand second half of page back to the ring */ ixgbevf_reuse_rx_page(rx_ring, rx_buffer); } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE); + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + PAGE_SIZE, DMA_FROM_DEVICE, + IXGBEVF_RX_DMA_ATTR); + __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); } /* clear contents of buffer_info */ @@ -930,7 +928,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, rx_desc = IXGBEVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - if (!ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) + if (!rx_desc->wb.upper.length) break; /* This memory barrier is needed to keep us from reading @@ -943,8 +941,10 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, skb = ixgbevf_fetch_rx_buffer(rx_ring, rx_desc, skb); /* exit if we failed to retrieve a buffer */ - if (!skb) + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; break; + } cleaned_count++; @@ -1553,6 +1553,10 @@ static void ixgbevf_configure_tx_ring(struct ixgbevf_adapter *adapter, txdctl |= (1u << 8) | /* HTHRESH = 1 */ 32; /* PTHRESH = 32 */ + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct ixgbevf_tx_buffer) * ring->count); + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &ring->state); IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), txdctl); @@ -1721,6 +1725,7 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, struct ixgbevf_ring *ring) { struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_rx_desc *rx_desc; u64 rdba = ring->dma; u32 rxdctl; u8 reg_idx = ring->reg_idx; @@ -1749,6 +1754,14 @@ static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_VFRDT(reg_idx), 0); ring->tail = adapter->io_addr + IXGBE_VFRDT(reg_idx); + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct ixgbevf_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IXGBEVF_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + /* reset ntu and ntc to place SW in sync with hardwdare */ ring->next_to_clean = 0; ring->next_to_use = 0; @@ -2103,9 +2116,7 @@ void ixgbevf_up(struct ixgbevf_adapter *adapter) **/ static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) { - struct device *dev = rx_ring->dev; - unsigned long size; - unsigned int i; + u16 i = rx_ring->next_to_clean; /* Free Rx ring sk_buff */ if (rx_ring->skb) { @@ -2113,29 +2124,39 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) rx_ring->skb = NULL; } - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_buffer_info) - return; - /* Free all the Rx ring pages */ - for (i = 0; i < rx_ring->count; i++) { + while (i != rx_ring->next_to_alloc) { struct ixgbevf_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[i]; - if (rx_buffer->dma) - dma_unmap_page(dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE); - rx_buffer->dma = 0; - if (rx_buffer->page) - __free_page(rx_buffer->page); - rx_buffer->page = NULL; - } - size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + IXGBEVF_RX_BUFSZ, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, + rx_buffer->dma, + PAGE_SIZE, + DMA_FROM_DEVICE, + IXGBEVF_RX_DMA_ATTR); + + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); + i++; + if (i == rx_ring->count) + i = 0; + } + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; } /** @@ -2144,23 +2165,57 @@ static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) **/ static void ixgbevf_clean_tx_ring(struct ixgbevf_ring *tx_ring) { - struct ixgbevf_tx_buffer *tx_buffer_info; - unsigned long size; - unsigned int i; + u16 i = tx_ring->next_to_clean; + struct ixgbevf_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (!tx_ring->tx_buffer_info) - return; + while (i != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *eop_desc, *tx_desc; - /* Free all the Tx ring sk_buffs */ - for (i = 0; i < tx_ring->count; i++) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } } - size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count; - memset(tx_ring->tx_buffer_info, 0, size); + /* reset next_to_use and next_to_clean */ + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; - memset(tx_ring->desc, 0, tx_ring->size); } /** @@ -2712,6 +2767,8 @@ out: void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; + u64 alloc_rx_page = 0, hw_csum_rx_error = 0; int i; if (test_bit(__IXGBEVF_DOWN, &adapter->state) || @@ -2732,10 +2789,18 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) adapter->stats.vfmprc); for (i = 0; i < adapter->num_rx_queues; i++) { - adapter->hw_csum_rx_error += - adapter->rx_ring[i]->hw_csum_rx_error; - adapter->rx_ring[i]->hw_csum_rx_error = 0; + struct ixgbevf_ring *rx_ring = adapter->rx_ring[i]; + + hw_csum_rx_error += rx_ring->rx_stats.csum_err; + alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; + alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; + alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; } + + adapter->hw_csum_rx_error = hw_csum_rx_error; + adapter->alloc_rx_page_failed = alloc_rx_page_failed; + adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; + adapter->alloc_rx_page = alloc_rx_page; } /** @@ -2980,7 +3045,7 @@ int ixgbevf_setup_tx_resources(struct ixgbevf_ring *tx_ring) int size; size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc(size); + tx_ring->tx_buffer_info = vmalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -3040,7 +3105,7 @@ int ixgbevf_setup_rx_resources(struct ixgbevf_ring *rx_ring) int size; size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc(size); + rx_ring->rx_buffer_info = vmalloc(size); if (!rx_ring->rx_buffer_info) goto err; @@ -3482,34 +3547,37 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, struct ixgbevf_tx_buffer *first, const u8 hdr_len) { - dma_addr_t dma; struct sk_buff *skb = first->skb; struct ixgbevf_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; - unsigned int data_len = skb->data_len; - unsigned int size = skb_headlen(skb); - unsigned int paylen = skb->len - hdr_len; + struct skb_frag_struct *frag; + dma_addr_t dma; + unsigned int data_len, size; u32 tx_flags = first->tx_flags; - __le32 cmd_type; + __le32 cmd_type = ixgbevf_tx_cmd_type(tx_flags); u16 i = tx_ring->next_to_use; tx_desc = IXGBEVF_TX_DESC(tx_ring, i); - ixgbevf_tx_olinfo_status(tx_desc, tx_flags, paylen); - cmd_type = ixgbevf_tx_cmd_type(tx_flags); + ixgbevf_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len); + + size = skb_headlen(skb); + data_len = skb->data_len; dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); - if (dma_mapping_error(tx_ring->dev, dma)) - goto dma_error; - /* record length, and DMA address */ - dma_unmap_len_set(first, len, size); - dma_unmap_addr_set(first, dma, dma); + tx_buffer = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); - tx_desc->read.buffer_addr = cpu_to_le64(dma); + tx_desc->read.buffer_addr = cpu_to_le64(dma); - for (;;) { while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) { tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(IXGBE_MAX_DATA_PER_TXD); @@ -3520,12 +3588,12 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); i = 0; } + tx_desc->read.olinfo_status = 0; dma += IXGBE_MAX_DATA_PER_TXD; size -= IXGBE_MAX_DATA_PER_TXD; tx_desc->read.buffer_addr = cpu_to_le64(dma); - tx_desc->read.olinfo_status = 0; } if (likely(!data_len)) @@ -3539,23 +3607,15 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); i = 0; } + tx_desc->read.olinfo_status = 0; size = skb_frag_size(frag); data_len -= size; dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, DMA_TO_DEVICE); - if (dma_mapping_error(tx_ring->dev, dma)) - goto dma_error; tx_buffer = &tx_ring->tx_buffer_info[i]; - dma_unmap_len_set(tx_buffer, len, size); - dma_unmap_addr_set(tx_buffer, dma, dma); - - tx_desc->read.buffer_addr = cpu_to_le64(dma); - tx_desc->read.olinfo_status = 0; - - frag++; } /* write last descriptor with RS and EOP bits */ @@ -3589,18 +3649,32 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, return; dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - for (;;) { + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i-- == 0) + i += tx_ring->count; tx_buffer = &tx_ring->tx_buffer_info[i]; - ixgbevf_unmap_and_free_tx_resource(tx_ring, tx_buffer); - if (tx_buffer == first) - break; - if (i == 0) - i = tx_ring->count; - i--; } + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + tx_ring->next_to_use = i; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 64c93e8becc6..38d3a327c1bc 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -286,7 +286,7 @@ static s32 ixgbevf_set_uc_addr_vf(struct ixgbe_hw *hw, u32 index, u8 *addr) ether_addr_copy(msg_addr, addr); ret_val = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, - sizeof(msgbuf) / sizeof(u32)); + ARRAY_SIZE(msgbuf)); if (!ret_val) { msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; @@ -456,8 +456,7 @@ static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr, ether_addr_copy(msg_addr, addr); ret_val = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, - sizeof(msgbuf) / sizeof(u32)); - + ARRAY_SIZE(msgbuf)); msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; /* if nacked the address was rejected, use "perm_addr" */ @@ -574,7 +573,7 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) msgbuf[1] = xcast_mode; err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, - sizeof(msgbuf) / sizeof(u32)); + ARRAY_SIZE(msgbuf)); if (err) return err; @@ -614,7 +613,7 @@ static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind, msgbuf[0] |= vlan_on << IXGBE_VT_MSGINFO_SHIFT; err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, - sizeof(msgbuf) / sizeof(u32)); + ARRAY_SIZE(msgbuf)); if (err) goto mbx_err; @@ -826,7 +825,7 @@ static s32 ixgbevf_set_rlpml_vf(struct ixgbe_hw *hw, u16 max_size) msgbuf[1] = max_size; ret_val = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, - sizeof(msgbuf) / sizeof(u32)); + ARRAY_SIZE(msgbuf)); if (ret_val) return ret_val; if ((msgbuf[0] & IXGBE_VF_SET_LPE) && @@ -872,8 +871,7 @@ static int ixgbevf_negotiate_api_version_vf(struct ixgbe_hw *hw, int api) msg[1] = api; msg[2] = 0; - err = ixgbevf_write_msg_read_ack(hw, msg, msg, - sizeof(msg) / sizeof(u32)); + err = ixgbevf_write_msg_read_ack(hw, msg, msg, ARRAY_SIZE(msg)); if (!err) { msg[0] &= ~IXGBE_VT_MSGTYPE_CTS; @@ -924,8 +922,7 @@ int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs, msg[0] = IXGBE_VF_GET_QUEUE; msg[1] = msg[2] = msg[3] = msg[4] = 0; - err = ixgbevf_write_msg_read_ack(hw, msg, msg, - sizeof(msg) / sizeof(u32)); + err = ixgbevf_write_msg_read_ack(hw, msg, msg, ARRAY_SIZE(msg)); if (!err) { msg[0] &= ~IXGBE_VT_MSGTYPE_CTS; diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index a19760736b71..a1d7b88cf083 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -10,6 +10,7 @@ * warranty of any kind, whether express or implied. */ +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -865,7 +866,7 @@ struct mvpp2 { /* List of pointers to port structures */ int port_count; - struct mvpp2_port **port_list; + struct mvpp2_port *port_list[MVPP2_MAX_PORTS]; /* Aggregated TXQs */ struct mvpp2_tx_queue *aggr_txqs; @@ -932,6 +933,9 @@ struct mvpp2_port { struct mvpp2 *priv; + /* Firmware node associated to the port */ + struct fwnode_handle *fwnode; + /* Per-port registers' base address */ void __iomem *base; void __iomem *stats_base; @@ -7499,7 +7503,10 @@ static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port, strncpy(irqname, "rx-shared", sizeof(irqname)); } - v->irq = of_irq_get_byname(port_node, irqname); + if (port_node) + v->irq = of_irq_get_byname(port_node, irqname); + else + v->irq = fwnode_irq_get(port->fwnode, i); if (v->irq <= 0) { ret = -EINVAL; goto err; @@ -7711,17 +7718,16 @@ static bool mvpp2_port_has_tx_irqs(struct mvpp2 *priv, } static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, - struct device_node *port_node, + struct fwnode_handle *fwnode, char **mac_from) { struct mvpp2_port *port = netdev_priv(dev); char hw_mac_addr[ETH_ALEN] = {0}; - const char *dt_mac_addr; + char fw_mac_addr[ETH_ALEN]; - dt_mac_addr = of_get_mac_address(port_node); - if (dt_mac_addr && is_valid_ether_addr(dt_mac_addr)) { - *mac_from = "device tree"; - ether_addr_copy(dev->dev_addr, dt_mac_addr); + if (fwnode_get_mac_address(fwnode, fw_mac_addr, ETH_ALEN)) { + *mac_from = "firmware node"; + ether_addr_copy(dev->dev_addr, fw_mac_addr); return; } @@ -7740,13 +7746,14 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, - struct device_node *port_node, - struct mvpp2 *priv, int index) + struct fwnode_handle *port_fwnode, + struct mvpp2 *priv) { struct device_node *phy_node; - struct phy *comphy; + struct phy *comphy = NULL; struct mvpp2_port *port; struct mvpp2_port_pcpu *port_pcpu; + struct device_node *port_node = to_of_node(port_fwnode); struct net_device *dev; struct resource *res; char *mac_from = ""; @@ -7757,7 +7764,12 @@ static int mvpp2_port_probe(struct platform_device *pdev, int phy_mode; int err, i, cpu; - has_tx_irqs = mvpp2_port_has_tx_irqs(priv, port_node); + if (port_node) { + has_tx_irqs = mvpp2_port_has_tx_irqs(priv, port_node); + } else { + has_tx_irqs = true; + queue_mode = MVPP2_QDIST_MULTI_MODE; + } if (!has_tx_irqs) queue_mode = MVPP2_QDIST_SINGLE_MODE; @@ -7772,24 +7784,30 @@ static int mvpp2_port_probe(struct platform_device *pdev, if (!dev) return -ENOMEM; - phy_node = of_parse_phandle(port_node, "phy", 0); - phy_mode = of_get_phy_mode(port_node); + if (port_node) + phy_node = of_parse_phandle(port_node, "phy", 0); + else + phy_node = NULL; + + phy_mode = fwnode_get_phy_mode(port_fwnode); if (phy_mode < 0) { dev_err(&pdev->dev, "incorrect phy mode\n"); err = phy_mode; goto err_free_netdev; } - comphy = devm_of_phy_get(&pdev->dev, port_node, NULL); - if (IS_ERR(comphy)) { - if (PTR_ERR(comphy) == -EPROBE_DEFER) { - err = -EPROBE_DEFER; - goto err_free_netdev; + if (port_node) { + comphy = devm_of_phy_get(&pdev->dev, port_node, NULL); + if (IS_ERR(comphy)) { + if (PTR_ERR(comphy) == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto err_free_netdev; + } + comphy = NULL; } - comphy = NULL; } - if (of_property_read_u32(port_node, "port-id", &id)) { + if (fwnode_property_read_u32(port_fwnode, "port-id", &id)) { err = -EINVAL; dev_err(&pdev->dev, "missing port-id value\n"); goto err_free_netdev; @@ -7802,6 +7820,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, port = netdev_priv(dev); port->dev = dev; + port->fwnode = port_fwnode; port->ntxqs = ntxqs; port->nrxqs = nrxqs; port->priv = priv; @@ -7811,7 +7830,10 @@ static int mvpp2_port_probe(struct platform_device *pdev, if (err) goto err_free_netdev; - port->link_irq = of_irq_get_byname(port_node, "link"); + if (port_node) + port->link_irq = of_irq_get_byname(port_node, "link"); + else + port->link_irq = fwnode_irq_get(port_fwnode, port->nqvecs + 1); if (port->link_irq == -EPROBE_DEFER) { err = -EPROBE_DEFER; goto err_deinit_qvecs; @@ -7820,7 +7842,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, /* the link irq is optional */ port->link_irq = 0; - if (of_property_read_bool(port_node, "marvell,loopback")) + if (fwnode_property_read_bool(port_fwnode, "marvell,loopback")) port->flags |= MVPP2_F_LOOPBACK; port->id = id; @@ -7845,8 +7867,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, MVPP21_MIB_COUNTERS_OFFSET + port->gop_id * MVPP21_MIB_COUNTERS_PORT_SZ; } else { - if (of_property_read_u32(port_node, "gop-port-id", - &port->gop_id)) { + if (fwnode_property_read_u32(port_fwnode, "gop-port-id", + &port->gop_id)) { err = -EINVAL; dev_err(&pdev->dev, "missing gop-port-id value\n"); goto err_deinit_qvecs; @@ -7876,7 +7898,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, mutex_init(&port->gather_stats_lock); INIT_DELAYED_WORK(&port->stats_work, mvpp2_gather_hw_statistics); - mvpp2_port_copy_mac_addr(dev, priv, port_node, &mac_from); + mvpp2_port_copy_mac_addr(dev, priv, port_fwnode, &mac_from); port->tx_ring_size = MVPP2_MAX_TXD_DFLT; port->rx_ring_size = MVPP2_MAX_RXD_DFLT; @@ -7934,7 +7956,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, } netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr); - priv->port_list[index] = port; + priv->port_list[priv->port_count++] = port; + return 0; err_free_port_pcpu: @@ -8193,8 +8216,9 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) static int mvpp2_probe(struct platform_device *pdev) { - struct device_node *dn = pdev->dev.of_node; - struct device_node *port_node; + const struct acpi_device_id *acpi_id; + struct fwnode_handle *fwnode = pdev->dev.fwnode; + struct fwnode_handle *port_fwnode; struct mvpp2 *priv; struct resource *res; void __iomem *base; @@ -8205,8 +8229,14 @@ static int mvpp2_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - priv->hw_version = - (unsigned long)of_device_get_match_data(&pdev->dev); + if (has_acpi_companion(&pdev->dev)) { + acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table, + &pdev->dev); + priv->hw_version = (unsigned long)acpi_id->driver_data; + } else { + priv->hw_version = + (unsigned long)of_device_get_match_data(&pdev->dev); + } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); base = devm_ioremap_resource(&pdev->dev, res); @@ -8220,10 +8250,23 @@ static int mvpp2_probe(struct platform_device *pdev) return PTR_ERR(priv->lms_base); } else { res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (has_acpi_companion(&pdev->dev)) { + /* In case the MDIO memory region is declared in + * the ACPI, it can already appear as 'in-use' + * in the OS. Because it is overlapped by second + * region of the network controller, make + * sure it is released, before requesting it again. + * The care is taken by mvpp2 driver to avoid + * concurrent access to this memory region. + */ + release_resource(res); + } priv->iface_base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(priv->iface_base)) return PTR_ERR(priv->iface_base); + } + if (priv->hw_version == MVPP22 && dev_of_node(&pdev->dev)) { priv->sysctrl_base = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "marvell,system-controller"); @@ -8249,32 +8292,34 @@ static int mvpp2_probe(struct platform_device *pdev) else priv->max_port_rxqs = 32; - priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk"); - if (IS_ERR(priv->pp_clk)) - return PTR_ERR(priv->pp_clk); - err = clk_prepare_enable(priv->pp_clk); - if (err < 0) - return err; - - priv->gop_clk = devm_clk_get(&pdev->dev, "gop_clk"); - if (IS_ERR(priv->gop_clk)) { - err = PTR_ERR(priv->gop_clk); - goto err_pp_clk; - } - err = clk_prepare_enable(priv->gop_clk); - if (err < 0) - goto err_pp_clk; + if (dev_of_node(&pdev->dev)) { + priv->pp_clk = devm_clk_get(&pdev->dev, "pp_clk"); + if (IS_ERR(priv->pp_clk)) + return PTR_ERR(priv->pp_clk); + err = clk_prepare_enable(priv->pp_clk); + if (err < 0) + return err; - if (priv->hw_version == MVPP22) { - priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk"); - if (IS_ERR(priv->mg_clk)) { - err = PTR_ERR(priv->mg_clk); - goto err_gop_clk; + priv->gop_clk = devm_clk_get(&pdev->dev, "gop_clk"); + if (IS_ERR(priv->gop_clk)) { + err = PTR_ERR(priv->gop_clk); + goto err_pp_clk; } - - err = clk_prepare_enable(priv->mg_clk); + err = clk_prepare_enable(priv->gop_clk); if (err < 0) - goto err_gop_clk; + goto err_pp_clk; + + if (priv->hw_version == MVPP22) { + priv->mg_clk = devm_clk_get(&pdev->dev, "mg_clk"); + if (IS_ERR(priv->mg_clk)) { + err = PTR_ERR(priv->mg_clk); + goto err_gop_clk; + } + + err = clk_prepare_enable(priv->mg_clk); + if (err < 0) + goto err_gop_clk; + } priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk"); if (IS_ERR(priv->axi_clk)) { @@ -8287,10 +8332,14 @@ static int mvpp2_probe(struct platform_device *pdev) if (err < 0) goto err_gop_clk; } - } - /* Get system's tclk rate */ - priv->tclk = clk_get_rate(priv->pp_clk); + /* Get system's tclk rate */ + priv->tclk = clk_get_rate(priv->pp_clk); + } else if (device_property_read_u32(&pdev->dev, "clock-frequency", + &priv->tclk)) { + dev_err(&pdev->dev, "missing clock-frequency value\n"); + return -EINVAL; + } if (priv->hw_version == MVPP22) { err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40)); @@ -8313,30 +8362,19 @@ static int mvpp2_probe(struct platform_device *pdev) goto err_mg_clk; } - priv->port_count = of_get_available_child_count(dn); + /* Initialize ports */ + fwnode_for_each_available_child_node(fwnode, port_fwnode) { + err = mvpp2_port_probe(pdev, port_fwnode, priv); + if (err < 0) + goto err_port_probe; + } + if (priv->port_count == 0) { dev_err(&pdev->dev, "no ports enabled\n"); err = -ENODEV; goto err_mg_clk; } - priv->port_list = devm_kcalloc(&pdev->dev, priv->port_count, - sizeof(*priv->port_list), - GFP_KERNEL); - if (!priv->port_list) { - err = -ENOMEM; - goto err_mg_clk; - } - - /* Initialize ports */ - i = 0; - for_each_available_child_of_node(dn, port_node) { - err = mvpp2_port_probe(pdev, port_node, priv, i); - if (err < 0) - goto err_port_probe; - i++; - } - /* Statistics must be gathered regularly because some of them (like * packets counters) are 32-bit registers and could overflow quite * quickly. For instance, a 10Gb link used at full bandwidth with the @@ -8357,7 +8395,7 @@ static int mvpp2_probe(struct platform_device *pdev) err_port_probe: i = 0; - for_each_available_child_of_node(dn, port_node) { + fwnode_for_each_available_child_node(fwnode, port_fwnode) { if (priv->port_list[i]) mvpp2_port_remove(priv->port_list[i]); i++; @@ -8376,14 +8414,14 @@ err_pp_clk: static int mvpp2_remove(struct platform_device *pdev) { struct mvpp2 *priv = platform_get_drvdata(pdev); - struct device_node *dn = pdev->dev.of_node; - struct device_node *port_node; + struct fwnode_handle *fwnode = pdev->dev.fwnode; + struct fwnode_handle *port_fwnode; int i = 0; flush_workqueue(priv->stats_queue); destroy_workqueue(priv->stats_queue); - for_each_available_child_of_node(dn, port_node) { + fwnode_for_each_available_child_node(fwnode, port_fwnode) { if (priv->port_list[i]) { mutex_destroy(&priv->port_list[i]->gather_stats_lock); mvpp2_port_remove(priv->port_list[i]); @@ -8406,6 +8444,9 @@ static int mvpp2_remove(struct platform_device *pdev) aggr_txq->descs_dma); } + if (is_acpi_node(port_fwnode)) + return 0; + clk_disable_unprepare(priv->axi_clk); clk_disable_unprepare(priv->mg_clk); clk_disable_unprepare(priv->pp_clk); @@ -8427,12 +8468,19 @@ static const struct of_device_id mvpp2_match[] = { }; MODULE_DEVICE_TABLE(of, mvpp2_match); +static const struct acpi_device_id mvpp2_acpi_match[] = { + { "MRVL0110", MVPP22 }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, mvpp2_acpi_match); + static struct platform_driver mvpp2_driver = { .probe = mvpp2_probe, .remove = mvpp2_remove, .driver = { .name = MVPP2_DRIVER_NAME, .of_match_table = mvpp2_match, + .acpi_match_table = ACPI_PTR(mvpp2_acpi_match), }, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8530c770c873..47bab842c5ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2944,9 +2944,6 @@ out: static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: return mlx5e_configure_flower(priv, cls_flower); @@ -2964,7 +2961,7 @@ int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, { struct mlx5e_priv *priv = cb_priv; - if (!tc_can_offload(priv->netdev)) + if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 10fa6a18fcf9..363d8dcb7f17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -719,9 +719,6 @@ static int mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: return mlx5e_configure_flower(priv, cls_flower); @@ -739,7 +736,7 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, { struct mlx5e_priv *priv = cb_priv; - if (!tc_can_offload(priv->netdev)) + if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 833cd0a96fd9..3dcc58d61506 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1738,9 +1738,6 @@ static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_cls_matchall_offload *f, bool ingress) { - if (f->common.chain_index) - return -EOPNOTSUPP; - switch (f->command) { case TC_CLSMATCHALL_REPLACE: return mlxsw_sp_port_add_cls_matchall(mlxsw_sp_port, f, @@ -1780,7 +1777,8 @@ static int mlxsw_sp_setup_tc_block_cb_matchall(enum tc_setup_type type, switch (type) { case TC_SETUP_CLSMATCHALL: - if (!tc_can_offload(mlxsw_sp_port->dev)) + if (!tc_cls_can_offload_and_chain0(mlxsw_sp_port->dev, + type_data)) return -EOPNOTSUPP; return mlxsw_sp_setup_tc_cls_matchall(mlxsw_sp_port, type_data, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 31891ae11c9b..f0b25baba09a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -71,6 +71,7 @@ #include "spectrum_mr_tcam.h" #include "spectrum_router.h" +struct mlxsw_sp_fib; struct mlxsw_sp_vr; struct mlxsw_sp_lpm_tree; struct mlxsw_sp_rif_ops; @@ -84,6 +85,8 @@ struct mlxsw_sp_router { struct rhashtable nexthop_ht; struct list_head nexthop_list; struct { + /* One tree for each protocol: IPv4 and IPv6 */ + struct mlxsw_sp_lpm_tree *proto_trees[2]; struct mlxsw_sp_lpm_tree *trees; unsigned int tree_count; } lpm; @@ -162,6 +165,15 @@ struct mlxsw_sp_rif_ops { struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif); }; +static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree); +static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree); +static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_fib *fib, + u8 tree_id); +static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_fib *fib); + static unsigned int * mlxsw_sp_rif_p_counter_get(struct mlxsw_sp_rif *rif, enum mlxsw_sp_rif_counter_dir dir) @@ -349,14 +361,6 @@ mlxsw_sp_prefix_usage_eq(struct mlxsw_sp_prefix_usage *prefix_usage1, return !memcmp(prefix_usage1, prefix_usage2, sizeof(*prefix_usage1)); } -static bool -mlxsw_sp_prefix_usage_none(struct mlxsw_sp_prefix_usage *prefix_usage) -{ - struct mlxsw_sp_prefix_usage prefix_usage_none = {{ 0 } }; - - return mlxsw_sp_prefix_usage_eq(prefix_usage, &prefix_usage_none); -} - static void mlxsw_sp_prefix_usage_cpy(struct mlxsw_sp_prefix_usage *prefix_usage1, struct mlxsw_sp_prefix_usage *prefix_usage2) @@ -398,7 +402,6 @@ enum mlxsw_sp_fib_entry_type { }; struct mlxsw_sp_nexthop_group; -struct mlxsw_sp_fib; struct mlxsw_sp_fib_node { struct list_head entry_list; @@ -445,6 +448,7 @@ struct mlxsw_sp_lpm_tree { u8 id; /* tree ID */ unsigned int ref_count; enum mlxsw_sp_l3proto proto; + unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; struct mlxsw_sp_prefix_usage prefix_usage; }; @@ -453,8 +457,6 @@ struct mlxsw_sp_fib { struct list_head node_list; struct mlxsw_sp_vr *vr; struct mlxsw_sp_lpm_tree *lpm_tree; - unsigned long prefix_ref_count[MLXSW_SP_PREFIX_COUNT]; - struct mlxsw_sp_prefix_usage prefix_usage; enum mlxsw_sp_l3proto proto; }; @@ -469,12 +471,15 @@ struct mlxsw_sp_vr { static const struct rhashtable_params mlxsw_sp_fib_ht_params; -static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr, +static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr, enum mlxsw_sp_l3proto proto) { + struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_fib *fib; int err; + lpm_tree = mlxsw_sp->router->lpm.proto_trees[proto]; fib = kzalloc(sizeof(*fib), GFP_KERNEL); if (!fib) return ERR_PTR(-ENOMEM); @@ -484,17 +489,26 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp_vr *vr, INIT_LIST_HEAD(&fib->node_list); fib->proto = proto; fib->vr = vr; + fib->lpm_tree = lpm_tree; + mlxsw_sp_lpm_tree_hold(lpm_tree); + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, lpm_tree->id); + if (err) + goto err_lpm_tree_bind; return fib; +err_lpm_tree_bind: + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); err_rhashtable_init: kfree(fib); return ERR_PTR(err); } -static void mlxsw_sp_fib_destroy(struct mlxsw_sp_fib *fib) +static void mlxsw_sp_fib_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib *fib) { + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); + mlxsw_sp_lpm_tree_put(mlxsw_sp, fib->lpm_tree); WARN_ON(!list_empty(&fib->node_list)); - WARN_ON(fib->lpm_tree); rhashtable_destroy(&fib->ht); kfree(fib); } @@ -581,6 +595,9 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, goto err_left_struct_set; memcpy(&lpm_tree->prefix_usage, prefix_usage, sizeof(lpm_tree->prefix_usage)); + memset(&lpm_tree->prefix_ref_count, 0, + sizeof(lpm_tree->prefix_ref_count)); + lpm_tree->ref_count = 1; return lpm_tree; err_left_struct_set: @@ -607,8 +624,10 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, if (lpm_tree->ref_count != 0 && lpm_tree->proto == proto && mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage, - prefix_usage)) + prefix_usage)) { + mlxsw_sp_lpm_tree_hold(lpm_tree); return lpm_tree; + } } return mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, proto); } @@ -629,9 +648,10 @@ static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) { + struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; struct mlxsw_sp_lpm_tree *lpm_tree; u64 max_trees; - int i; + int err, i; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_LPM_TREES)) return -EIO; @@ -649,11 +669,42 @@ static int mlxsw_sp_lpm_init(struct mlxsw_sp *mlxsw_sp) lpm_tree->id = i + MLXSW_SP_LPM_TREE_MIN; } + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + MLXSW_SP_L3_PROTO_IPV4); + if (IS_ERR(lpm_tree)) { + err = PTR_ERR(lpm_tree); + goto err_ipv4_tree_get; + } + mlxsw_sp->router->lpm.proto_trees[MLXSW_SP_L3_PROTO_IPV4] = lpm_tree; + + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + MLXSW_SP_L3_PROTO_IPV6); + if (IS_ERR(lpm_tree)) { + err = PTR_ERR(lpm_tree); + goto err_ipv6_tree_get; + } + mlxsw_sp->router->lpm.proto_trees[MLXSW_SP_L3_PROTO_IPV6] = lpm_tree; + return 0; + +err_ipv6_tree_get: + lpm_tree = mlxsw_sp->router->lpm.proto_trees[MLXSW_SP_L3_PROTO_IPV4]; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); +err_ipv4_tree_get: + kfree(mlxsw_sp->router->lpm.trees); + return err; } static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp) { + struct mlxsw_sp_lpm_tree *lpm_tree; + + lpm_tree = mlxsw_sp->router->lpm.proto_trees[MLXSW_SP_L3_PROTO_IPV6]; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + + lpm_tree = mlxsw_sp->router->lpm.proto_trees[MLXSW_SP_L3_PROTO_IPV4]; + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + kfree(mlxsw_sp->router->lpm.trees); } @@ -745,10 +796,10 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, NL_SET_ERR_MSG(extack, "spectrum: Exceeded number of supported virtual routers"); return ERR_PTR(-EBUSY); } - vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4); + vr->fib4 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); if (IS_ERR(vr->fib4)) return ERR_CAST(vr->fib4); - vr->fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6); + vr->fib6 = mlxsw_sp_fib_create(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); if (IS_ERR(vr->fib6)) { err = PTR_ERR(vr->fib6); goto err_fib6_create; @@ -763,21 +814,22 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, return vr; err_mr_table_create: - mlxsw_sp_fib_destroy(vr->fib6); + mlxsw_sp_fib_destroy(mlxsw_sp, vr->fib6); vr->fib6 = NULL; err_fib6_create: - mlxsw_sp_fib_destroy(vr->fib4); + mlxsw_sp_fib_destroy(mlxsw_sp, vr->fib4); vr->fib4 = NULL; return ERR_PTR(err); } -static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_vr *vr) { mlxsw_sp_mr_table_destroy(vr->mr4_table); vr->mr4_table = NULL; - mlxsw_sp_fib_destroy(vr->fib6); + mlxsw_sp_fib_destroy(mlxsw_sp, vr->fib6); vr->fib6 = NULL; - mlxsw_sp_fib_destroy(vr->fib4); + mlxsw_sp_fib_destroy(mlxsw_sp, vr->fib4); vr->fib4 = NULL; } @@ -793,12 +845,12 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, return vr; } -static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) +static void mlxsw_sp_vr_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr) { if (!vr->rif_count && list_empty(&vr->fib4->node_list) && list_empty(&vr->fib6->node_list) && mlxsw_sp_mr_table_empty(vr->mr4_table)) - mlxsw_sp_vr_destroy(vr); + mlxsw_sp_vr_destroy(mlxsw_sp, vr); } static bool @@ -809,7 +861,7 @@ mlxsw_sp_vr_lpm_tree_should_replace(struct mlxsw_sp_vr *vr, if (!mlxsw_sp_vr_is_used(vr)) return false; - if (fib->lpm_tree && fib->lpm_tree->id == tree_id) + if (fib->lpm_tree->id == tree_id) return true; return false; } @@ -839,14 +891,13 @@ static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, struct mlxsw_sp_lpm_tree *new_tree) { - struct mlxsw_sp_lpm_tree *old_tree = fib->lpm_tree; enum mlxsw_sp_l3proto proto = fib->proto; + struct mlxsw_sp_lpm_tree *old_tree; u8 old_id, new_id = new_tree->id; struct mlxsw_sp_vr *vr; int i, err; - if (!old_tree) - goto no_replace; + old_tree = mlxsw_sp->router->lpm.proto_trees[proto]; old_id = old_tree->id; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { @@ -860,6 +911,11 @@ static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, goto err_tree_replace; } + memcpy(new_tree->prefix_ref_count, old_tree->prefix_ref_count, + sizeof(new_tree->prefix_ref_count)); + mlxsw_sp->router->lpm.proto_trees[proto] = new_tree; + mlxsw_sp_lpm_tree_put(mlxsw_sp, old_tree); + return 0; err_tree_replace: @@ -871,36 +927,6 @@ err_tree_replace: old_tree); } return err; - -no_replace: - fib->lpm_tree = new_tree; - mlxsw_sp_lpm_tree_hold(new_tree); - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, new_tree->id); - if (err) { - mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); - fib->lpm_tree = NULL; - return err; - } - return 0; -} - -static void -mlxsw_sp_vrs_prefixes(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_sp_l3proto proto, - struct mlxsw_sp_prefix_usage *req_prefix_usage) -{ - int i; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { - struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; - struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto); - unsigned char prefix; - - if (!mlxsw_sp_vr_is_used(vr)) - continue; - mlxsw_sp_prefix_usage_for_each(prefix, &fib->prefix_usage) - mlxsw_sp_prefix_usage_set(req_prefix_usage, prefix); - } } static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) @@ -1942,11 +1968,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, dipn = htonl(dip); dev = mlxsw_sp->router->rifs[rif]->dev; n = neigh_lookup(&arp_tbl, &dipn, dev); - if (!n) { - netdev_err(dev, "Failed to find matching neighbour for IP=%pI4h\n", - &dip); + if (!n) return; - } netdev_dbg(dev, "Updating neighbour with IP=%pI4h\n", &dip); neigh_event_send(n, NULL); @@ -1973,11 +1996,8 @@ static void mlxsw_sp_router_neigh_ent_ipv6_process(struct mlxsw_sp *mlxsw_sp, dev = mlxsw_sp->router->rifs[rif]->dev; n = neigh_lookup(&nd_tbl, &dip, dev); - if (!n) { - netdev_err(dev, "Failed to find matching neighbour for IP=%pI6c\n", - &dip); + if (!n) return; - } netdev_dbg(dev, "Updating neighbour with IP=%pI6c\n", &dip); neigh_event_send(n, NULL); @@ -4201,68 +4221,66 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node, } static int mlxsw_sp_fib_lpm_tree_link(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib *fib, struct mlxsw_sp_fib_node *fib_node) { - struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; + struct mlxsw_sp_prefix_usage req_prefix_usage; + struct mlxsw_sp_fib *fib = fib_node->fib; struct mlxsw_sp_lpm_tree *lpm_tree; int err; - /* Since the tree is shared between all virtual routers we must - * make sure it contains all the required prefix lengths. This - * can be computed by either adding the new prefix length to the - * existing prefix usage of a bound tree, or by aggregating the - * prefix lengths across all virtual routers and adding the new - * one as well. - */ - if (fib->lpm_tree) - mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, - &fib->lpm_tree->prefix_usage); - else - mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); + lpm_tree = mlxsw_sp->router->lpm.proto_trees[fib->proto]; + if (lpm_tree->prefix_ref_count[fib_node->key.prefix_len] != 0) + goto out; + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &lpm_tree->prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, fib->proto); if (IS_ERR(lpm_tree)) return PTR_ERR(lpm_tree); - if (fib->lpm_tree && fib->lpm_tree->id == lpm_tree->id) - return 0; - err = mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); if (err) - return err; + goto err_lpm_tree_replace; +out: + lpm_tree->prefix_ref_count[fib_node->key.prefix_len]++; return 0; -} -static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib *fib) -{ - if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) - return; - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); - mlxsw_sp_lpm_tree_put(mlxsw_sp, fib->lpm_tree); - fib->lpm_tree = NULL; +err_lpm_tree_replace: + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); + return err; } -static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) +static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node) { - unsigned char prefix_len = fib_node->key.prefix_len; + struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree; + struct mlxsw_sp_prefix_usage req_prefix_usage; struct mlxsw_sp_fib *fib = fib_node->fib; + int err; - if (fib->prefix_ref_count[prefix_len]++ == 0) - mlxsw_sp_prefix_usage_set(&fib->prefix_usage, prefix_len); -} + if (--lpm_tree->prefix_ref_count[fib_node->key.prefix_len] != 0) + return; + /* Try to construct a new LPM tree from the current prefix usage + * minus the unused one. If we fail, continue using the old one. + */ + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &lpm_tree->prefix_usage); + mlxsw_sp_prefix_usage_clear(&req_prefix_usage, + fib_node->key.prefix_len); + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + fib->proto); + if (IS_ERR(lpm_tree)) + return; -static void mlxsw_sp_fib_node_prefix_dec(struct mlxsw_sp_fib_node *fib_node) -{ - unsigned char prefix_len = fib_node->key.prefix_len; - struct mlxsw_sp_fib *fib = fib_node->fib; + err = mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); + if (err) + goto err_lpm_tree_replace; - if (--fib->prefix_ref_count[prefix_len] == 0) - mlxsw_sp_prefix_usage_clear(&fib->prefix_usage, prefix_len); + return; + +err_lpm_tree_replace: + mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); } static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, @@ -4276,12 +4294,10 @@ static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, return err; fib_node->fib = fib; - err = mlxsw_sp_fib_lpm_tree_link(mlxsw_sp, fib, fib_node); + err = mlxsw_sp_fib_lpm_tree_link(mlxsw_sp, fib_node); if (err) goto err_fib_lpm_tree_link; - mlxsw_sp_fib_node_prefix_inc(fib_node); - return 0; err_fib_lpm_tree_link: @@ -4295,8 +4311,7 @@ static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_fib *fib = fib_node->fib; - mlxsw_sp_fib_node_prefix_dec(fib_node); - mlxsw_sp_fib_lpm_tree_unlink(mlxsw_sp, fib); + mlxsw_sp_fib_lpm_tree_unlink(mlxsw_sp, fib_node); fib_node->fib = NULL; mlxsw_sp_fib_node_remove(fib, fib_node); } @@ -4335,7 +4350,7 @@ mlxsw_sp_fib_node_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, const void *addr, err_fib_node_init: mlxsw_sp_fib_node_destroy(fib_node); err_fib_node_create: - mlxsw_sp_vr_put(vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); return ERR_PTR(err); } @@ -4348,7 +4363,7 @@ static void mlxsw_sp_fib_node_put(struct mlxsw_sp *mlxsw_sp, return; mlxsw_sp_fib_node_fini(mlxsw_sp, fib_node); mlxsw_sp_fib_node_destroy(fib_node); - mlxsw_sp_vr_put(vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); } static struct mlxsw_sp_fib4_entry * @@ -5371,7 +5386,7 @@ static void mlxsw_sp_router_fibmr_del(struct mlxsw_sp *mlxsw_sp, return; mlxsw_sp_mr_route4_del(vr->mr4_table, men_info->mfc); - mlxsw_sp_vr_put(vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); } static int @@ -5408,7 +5423,7 @@ mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp, return; mlxsw_sp_mr_vif_del(vr->mr4_table, ven_info->vif_index); - mlxsw_sp_vr_put(vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); } static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) @@ -6057,7 +6072,7 @@ err_fid_get: err_rif_alloc: err_rif_index_alloc: vr->rif_count--; - mlxsw_sp_vr_put(vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); return ERR_PTR(err); } @@ -6080,7 +6095,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) mlxsw_sp_fid_put(fid); kfree(rif); vr->rif_count--; - mlxsw_sp_vr_put(vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); } static void @@ -6870,7 +6885,7 @@ mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif) return 0; err_loopback_op: - mlxsw_sp_vr_put(ul_vr); + mlxsw_sp_vr_put(mlxsw_sp, ul_vr); return err; } @@ -6884,7 +6899,7 @@ static void mlxsw_sp_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif) mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, false); --ul_vr->rif_count; - mlxsw_sp_vr_put(ul_vr); + mlxsw_sp_vr_put(mlxsw_sp, ul_vr); } static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_ipip_lb_ops = { diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 4ee11bf2aed7..322027792fe8 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -54,7 +54,7 @@ static bool nfp_net_ebpf_capable(struct nfp_net *nn) static int nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn, - struct bpf_prog *prog) + struct bpf_prog *prog, struct netlink_ext_ack *extack) { bool running, xdp_running; int ret; @@ -70,10 +70,10 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn, if (prog && running && !xdp_running) return -EBUSY; - ret = nfp_net_bpf_offload(nn, prog, running); + ret = nfp_net_bpf_offload(nn, prog, running, extack); /* Stop offload if replace not possible */ if (ret && prog) - nfp_bpf_xdp_offload(app, nn, NULL); + nfp_bpf_xdp_offload(app, nn, NULL, extack); nn->dp.bpf_offload_xdp = prog && !ret; return ret; @@ -125,17 +125,29 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, struct nfp_bpf_vnic *bv; int err; - if (type != TC_SETUP_CLSBPF || - !tc_can_offload(nn->dp.netdev) || - !nfp_net_ebpf_capable(nn) || - cls_bpf->common.protocol != htons(ETH_P_ALL) || - cls_bpf->common.chain_index) + if (type != TC_SETUP_CLSBPF) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "only offload of BPF classifiers supported"); return -EOPNOTSUPP; + } + if (!tc_cls_can_offload_and_chain0(nn->dp.netdev, &cls_bpf->common)) + return -EOPNOTSUPP; + if (!nfp_net_ebpf_capable(nn)) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "NFP firmware does not support eBPF offload"); + return -EOPNOTSUPP; + } + if (cls_bpf->common.protocol != htons(ETH_P_ALL)) { + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "only ETH_P_ALL supported as filter protocol"); + return -EOPNOTSUPP; + } /* Only support TC direct action */ if (!cls_bpf->exts_integrated || tcf_exts_has_actions(cls_bpf->exts)) { - nn_err(nn, "only direct action with no legacy actions supported\n"); + NL_SET_ERR_MSG_MOD(cls_bpf->common.extack, + "only direct action with no legacy actions supported"); return -EOPNOTSUPP; } @@ -152,7 +164,8 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, return 0; } - err = nfp_net_bpf_offload(nn, cls_bpf->prog, oldprog); + err = nfp_net_bpf_offload(nn, cls_bpf->prog, oldprog, + cls_bpf->common.extack); if (err) return err; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index c476bca15ba4..424fe8338105 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -335,7 +335,7 @@ struct nfp_net; int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf); int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, - bool old_prog); + bool old_prog, struct netlink_ext_ack *extack); struct nfp_insn_meta * nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 1a357aacc444..0a7732385469 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -281,7 +281,9 @@ int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf) } } -static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog) +static int +nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog, + struct netlink_ext_ack *extack) { struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; unsigned int max_mtu; @@ -291,7 +293,7 @@ static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog) max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32; if (max_mtu < nn->dp.netdev->mtu) { - nn_info(nn, "BPF offload not supported with MTU larger than HW packet split boundary\n"); + NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with MTU larger than HW packet split boundary"); return -EOPNOTSUPP; } @@ -313,7 +315,8 @@ static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog) /* Load up the JITed code */ err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_BPF); if (err) - nn_err(nn, "FW command error while loading BPF: %d\n", err); + NL_SET_ERR_MSG_MOD(extack, + "FW command error while loading BPF"); dma_unmap_single(nn->dp.dev, dma_addr, nfp_prog->prog_len * sizeof(u64), DMA_TO_DEVICE); @@ -322,7 +325,8 @@ static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog) return err; } -static void nfp_net_bpf_start(struct nfp_net *nn) +static void +nfp_net_bpf_start(struct nfp_net *nn, struct netlink_ext_ack *extack) { int err; @@ -331,7 +335,8 @@ static void nfp_net_bpf_start(struct nfp_net *nn) nn_writel(nn, NFP_NET_CFG_CTRL, nn->dp.ctrl); err = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_GEN); if (err) - nn_err(nn, "FW command error while enabling BPF: %d\n", err); + NL_SET_ERR_MSG_MOD(extack, + "FW command error while enabling BPF"); } static int nfp_net_bpf_stop(struct nfp_net *nn) @@ -346,7 +351,7 @@ static int nfp_net_bpf_stop(struct nfp_net *nn) } int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, - bool old_prog) + bool old_prog, struct netlink_ext_ack *extack) { int err; @@ -364,7 +369,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, cap = nn_readb(nn, NFP_NET_CFG_BPF_CAP); if (!(cap & NFP_NET_BPF_CAP_RELO)) { - nn_err(nn, "FW does not support live reload\n"); + NL_SET_ERR_MSG_MOD(extack, + "FW does not support live reload"); return -EBUSY; } } @@ -376,12 +382,12 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, if (old_prog && !prog) return nfp_net_bpf_stop(nn); - err = nfp_net_bpf_load(nn, prog); + err = nfp_net_bpf_load(nn, prog, extack); if (err) return err; if (!old_prog) - nfp_net_bpf_start(nn); + nfp_net_bpf_start(nn, extack); return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 837134a9137c..08c4c6dc5f7f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -483,8 +483,7 @@ static int nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev, struct tc_cls_flower_offload *flower, bool egress) { - if (!eth_proto_is_802_3(flower->common.protocol) || - flower->common.chain_index) + if (!eth_proto_is_802_3(flower->common.protocol)) return -EOPNOTSUPP; switch (flower->command) { @@ -504,7 +503,7 @@ int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data, { struct nfp_repr *repr = cb_priv; - if (!tc_can_offload(repr->netdev)) + if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data)) return -EOPNOTSUPP; switch (type) { @@ -521,7 +520,7 @@ static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type, { struct nfp_repr *repr = cb_priv; - if (!tc_can_offload(repr->netdev)) + if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index 7e474df90598..437964afa8ee 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -43,6 +43,7 @@ struct bpf_prog; struct net_device; struct netdev_bpf; +struct netlink_ext_ack; struct pci_dev; struct sk_buff; struct sk_buff; @@ -138,7 +139,8 @@ struct nfp_app_type { int (*bpf)(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *xdp); int (*xdp_offload)(struct nfp_app *app, struct nfp_net *nn, - struct bpf_prog *prog); + struct bpf_prog *prog, + struct netlink_ext_ack *extack); int (*sriov_enable)(struct nfp_app *app, int num_vfs); void (*sriov_disable)(struct nfp_app *app); @@ -324,11 +326,12 @@ static inline int nfp_app_bpf(struct nfp_app *app, struct nfp_net *nn, } static inline int nfp_app_xdp_offload(struct nfp_app *app, struct nfp_net *nn, - struct bpf_prog *prog) + struct bpf_prog *prog, + struct netlink_ext_ack *extack) { if (!app || !app->type->xdp_offload) return -EOPNOTSUPP; - return app->type->xdp_offload(app, nn, prog); + return app->type->xdp_offload(app, nn, prog, extack); } static inline bool __nfp_app_ctrl_tx(struct nfp_app *app, struct sk_buff *skb) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index c5b91040b12e..cc570bb6563c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -518,6 +518,7 @@ static int nfp_pci_probe(struct pci_dev *pdev, dev_err(&pdev->dev, "Error: %d VFs already enabled, but loaded FW can only support %d\n", pf->num_vfs, pf->limit_vfs); + err = -EINVAL; goto err_fw_unload; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index cdf52421eaca..c0fd351c86b1 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3403,7 +3403,7 @@ nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags, if (err) return err; - err = nfp_app_xdp_offload(nn->app, nn, offload_prog); + err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack); if (err && flags & XDP_FLAGS_HW_MODE) return err; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c index e6f19f44b461..bb8ed460086e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c @@ -640,8 +640,8 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, struct nfp_dump_rtsym *dump_header = dump->p; struct nfp_dumpspec_cpp_isl_id cpp_params; struct nfp_rtsym_table *rtbl = pf->rtbl; + u32 header_size, total_size, sym_size; const struct nfp_rtsym *sym; - u32 header_size, total_size; u32 tl_len, key_len; int bytes_read; u32 cpp_id; @@ -657,9 +657,14 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, if (!sym) return nfp_dump_error_tlv(&spec->tl, -ENOENT, dump); + if (sym->type == NFP_RTSYM_TYPE_ABS) + sym_size = sizeof(sym->addr); + else + sym_size = sym->size; + header_size = ALIGN8(offsetof(struct nfp_dump_rtsym, rtsym) + key_len + 1); - total_size = header_size + ALIGN8(sym->size); + total_size = header_size + ALIGN8(sym_size); dest = dump->p + header_size; err = nfp_add_tlv(be32_to_cpu(spec->tl.type), total_size, dump); @@ -669,9 +674,9 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, dump_header->padded_name_length = header_size - offsetof(struct nfp_dump_rtsym, rtsym); memcpy(dump_header->rtsym, spec->rtsym, key_len + 1); + dump_header->cpp.dump_length = cpu_to_be32(sym_size); if (sym->type == NFP_RTSYM_TYPE_ABS) { - dump_header->cpp.dump_length = cpu_to_be32(sizeof(sym->addr)); *(u64 *)dest = sym->addr; } else { cpp_params.target = sym->target; @@ -681,10 +686,9 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, cpp_id = nfp_get_numeric_cpp_id(&cpp_params); dump_header->cpp.cpp_id = cpp_params; dump_header->cpp.offset = cpu_to_be32(sym->addr); - dump_header->cpp.dump_length = cpu_to_be32(sym->size); bytes_read = nfp_cpp_read(pf->cpp, cpp_id, sym->addr, dest, - sym->size); - if (bytes_read != sym->size) { + sym_size); + if (bytes_read != sym_size) { if (bytes_read >= 0) bytes_read = -EIO; dump_header->error = cpu_to_be32(bytes_read); diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index a3f6d514c0f2..66c665d0b926 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -795,7 +795,7 @@ struct fe_priv { */ union ring_type get_rx, put_rx, last_rx; struct nv_skb_map *get_rx_ctx, *put_rx_ctx; - struct nv_skb_map *first_rx_ctx, *last_rx_ctx; + struct nv_skb_map *last_rx_ctx; struct nv_skb_map *rx_skb; union ring_type rx_ring; @@ -1835,7 +1835,7 @@ static int nv_alloc_rx(struct net_device *dev) if (unlikely(np->put_rx.orig++ == np->last_rx.orig)) np->put_rx.orig = np->rx_ring.orig; if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx)) - np->put_rx_ctx = np->first_rx_ctx; + np->put_rx_ctx = np->rx_skb; } else { packet_dropped: u64_stats_update_begin(&np->swstats_rx_syncp); @@ -1877,7 +1877,7 @@ static int nv_alloc_rx_optimized(struct net_device *dev) if (unlikely(np->put_rx.ex++ == np->last_rx.ex)) np->put_rx.ex = np->rx_ring.ex; if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx)) - np->put_rx_ctx = np->first_rx_ctx; + np->put_rx_ctx = np->rx_skb; } else { packet_dropped: u64_stats_update_begin(&np->swstats_rx_syncp); @@ -1910,7 +1910,8 @@ static void nv_init_rx(struct net_device *dev) np->last_rx.orig = &np->rx_ring.orig[np->rx_ring_size-1]; else np->last_rx.ex = &np->rx_ring.ex[np->rx_ring_size-1]; - np->get_rx_ctx = np->put_rx_ctx = np->first_rx_ctx = np->rx_skb; + np->get_rx_ctx = np->rx_skb; + np->put_rx_ctx = np->rx_skb; np->last_rx_ctx = &np->rx_skb[np->rx_ring_size-1]; for (i = 0; i < np->rx_ring_size; i++) { @@ -2914,7 +2915,7 @@ next_pkt: if (unlikely(np->get_rx.orig++ == np->last_rx.orig)) np->get_rx.orig = np->rx_ring.orig; if (unlikely(np->get_rx_ctx++ == np->last_rx_ctx)) - np->get_rx_ctx = np->first_rx_ctx; + np->get_rx_ctx = np->rx_skb; rx_work++; } @@ -3003,7 +3004,7 @@ next_pkt: if (unlikely(np->get_rx.ex++ == np->last_rx.ex)) np->get_rx.ex = np->rx_ring.ex; if (unlikely(np->get_rx_ctx++ == np->last_rx_ctx)) - np->get_rx_ctx = np->first_rx_ctx; + np->get_rx_ctx = np->rx_skb; rx_work++; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index bdc46f11ce45..5d040b873137 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -358,10 +358,27 @@ static void qed_rdma_resc_free(struct qed_hwfn *p_hwfn) kfree(p_rdma_info); } +static void qed_rdma_free_tid(void *rdma_cxt, u32 itid) +{ + struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt; + + DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", itid); + + spin_lock_bh(&p_hwfn->p_rdma_info->lock); + qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->tid_map, itid); + spin_unlock_bh(&p_hwfn->p_rdma_info->lock); +} + +static void qed_rdma_free_reserved_lkey(struct qed_hwfn *p_hwfn) +{ + qed_rdma_free_tid(p_hwfn, p_hwfn->p_rdma_info->dev->reserved_lkey); +} + static void qed_rdma_free(struct qed_hwfn *p_hwfn) { DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "Freeing RDMA\n"); + qed_rdma_free_reserved_lkey(p_hwfn); qed_rdma_resc_free(p_hwfn); } @@ -615,9 +632,6 @@ static int qed_rdma_reserve_lkey(struct qed_hwfn *p_hwfn) { struct qed_rdma_device *dev = p_hwfn->p_rdma_info->dev; - /* The first DPI is reserved for the Kernel */ - __set_bit(0, p_hwfn->p_rdma_info->dpi_map.bitmap); - /* Tid 0 will be used as the key for "reserved MR". * The driver should allocate memory for it so it can be loaded but no * ramrod should be passed on it. @@ -797,17 +811,6 @@ static struct qed_rdma_device *qed_rdma_query_device(void *rdma_cxt) return p_hwfn->p_rdma_info->dev; } -static void qed_rdma_free_tid(void *rdma_cxt, u32 itid) -{ - struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt; - - DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "itid = %08x\n", itid); - - spin_lock_bh(&p_hwfn->p_rdma_info->lock); - qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->tid_map, itid); - spin_unlock_bh(&p_hwfn->p_rdma_info->lock); -} - static void qed_rdma_cnq_prod_update(void *rdma_cxt, u8 qz_offset, u16 prod) { struct qed_hwfn *p_hwfn; diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.h b/drivers/net/ethernet/qualcomm/emac/emac-mac.h index 5028fb4bec2b..4beedb8faa1e 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.h +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.h @@ -114,8 +114,9 @@ struct emac_tpd { #define TPD_INSTC_SET(tpd, val) BITS_SET((tpd)->word[3], 17, 17, val) /* High-14bit Buffer Address, So, the 64b-bit address is * {DESC_CTRL_11_TX_DATA_HIADDR[17:0],(register) BUFFER_ADDR_H, BUFFER_ADDR_L} + * Extend TPD_BUFFER_ADDR_H to [31, 18], because we never enable timestamping. */ -#define TPD_BUFFER_ADDR_H_SET(tpd, val) BITS_SET((tpd)->word[3], 18, 30, val) +#define TPD_BUFFER_ADDR_H_SET(tpd, val) BITS_SET((tpd)->word[3], 18, 31, val) /* Format D. Word offset from the 1st byte of this packet to start to calculate * the custom checksum. */ diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 38c924bdd32e..13235baf4766 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -615,8 +615,11 @@ static int emac_probe(struct platform_device *pdev) u32 reg; int ret; - /* The TPD buffer address is limited to 45 bits. */ - ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(45)); + /* The TPD buffer address is limited to: + * 1. PTP: 45bits. (Driver doesn't support yet.) + * 2. NON-PTP: 46bits. + */ + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(46)); if (ret) { dev_err(&pdev->dev, "could not set DMA mask\n"); return ret; diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 6d6fb8cf3e7c..6473cc68c2d5 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -789,7 +789,6 @@ static int ofdpa_flow_tbl_add(struct ofdpa_port *ofdpa_port, ofdpa_flags_nowait(flags), ofdpa_cmd_flow_tbl_add, found, NULL, NULL); - return 0; } static int ofdpa_flow_tbl_del(struct ofdpa_port *ofdpa_port, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 8ae467db9162..75fbf58e421c 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -322,6 +322,25 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx) return 0; } +static void efx_ef10_read_licensed_features(struct efx_nic *efx) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_LICENSING_V3_IN_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_LICENSING_V3_OUT_LEN); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + size_t outlen; + int rc; + + MCDI_SET_DWORD(inbuf, LICENSING_V3_IN_OP, + MC_CMD_LICENSING_V3_IN_OP_REPORT_LICENSE); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_LICENSING_V3, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &outlen); + if (rc || (outlen < MC_CMD_LICENSING_V3_OUT_LEN)) + return; + + nic_data->licensed_features = MCDI_QWORD(outbuf, + LICENSING_V3_OUT_LICENSED_FEATURES); +} + static int efx_ef10_get_sysclk_freq(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CLOCK_OUT_LEN); @@ -722,6 +741,8 @@ static int efx_ef10_probe(struct efx_nic *efx) if (rc < 0) goto fail5; + efx_ef10_read_licensed_features(efx); + /* We can have one VI for each vi_stride-byte region. * However, until we use TX option descriptors we need two TX queues * per channel. @@ -760,14 +781,7 @@ static int efx_ef10_probe(struct efx_nic *efx) if (rc && rc != -EPERM) goto fail5; - rc = efx_ptp_probe(efx, NULL); - /* Failure to probe PTP is not fatal. - * In the case of EPERM, efx_ptp_probe will print its own message (in - * efx_ptp_get_attributes()), so we don't need to. - */ - if (rc && rc != -EPERM) - netif_warn(efx, drv, efx->net_dev, - "Failed to probe PTP, rc=%d\n", rc); + efx_ptp_defer_probe_with_channel(efx); #ifdef CONFIG_SFC_SRIOV if ((efx->pci_dev->physfn) && (!efx->pci_dev->is_physfn)) { @@ -937,6 +951,11 @@ static int efx_ef10_link_piobufs(struct efx_nic *efx) /* Link a buffer to each TX queue */ efx_for_each_channel(channel, efx) { + /* Extra channels, even those with TXQs (PTP), do not require + * PIO resources. + */ + if (!channel->type->want_pio) + continue; efx_for_each_channel_tx_queue(tx_queue, channel) { /* We assign the PIO buffers to queues in * reverse order to allow for the following @@ -1284,7 +1303,9 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx) void __iomem *membase; int rc; - channel_vis = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES); + channel_vis = max(efx->n_channels, + (efx->n_tx_channels + efx->n_extra_tx_channels) * + EFX_TXQ_TYPES); #ifdef EFX_USE_PIO /* Try to allocate PIO buffers if wanted and if the full @@ -2408,12 +2429,25 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue) int i; BUILD_BUG_ON(MC_CMD_INIT_TXQ_OUT_LEN != 0); + /* Only attempt to enable TX timestamping if we have the license for it, + * otherwise TXQ init will fail + */ + if (!(nic_data->licensed_features & + (1 << LICENSED_V3_FEATURES_TX_TIMESTAMPS_LBN))) { + tx_queue->timestamping = false; + /* Disable sync events on this channel. */ + if (efx->type->ptp_set_ts_sync_events) + efx->type->ptp_set_ts_sync_events(efx, false, false); + } + /* TSOv2 is a limited resource that can only be configured on a limited * number of queues. TSO without checksum offload is not really a thing, * so we only enable it for those queues. + * TSOv2 cannot be used with Hardware timestamping. */ if (csum_offload && (nic_data->datapath_caps2 & - (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN))) { + (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN)) && + !tx_queue->timestamping) { tso_v2 = true; netif_dbg(efx, hw, efx->net_dev, "Using TSOv2 for channel %u\n", channel->channel); @@ -2439,14 +2473,16 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue) inlen = MC_CMD_INIT_TXQ_IN_LEN(entries); do { - MCDI_POPULATE_DWORD_3(inbuf, INIT_TXQ_IN_FLAGS, + MCDI_POPULATE_DWORD_4(inbuf, INIT_TXQ_IN_FLAGS, /* This flag was removed from mcdi_pcol.h for * the non-_EXT version of INIT_TXQ. However, * firmware still honours it. */ INIT_TXQ_EXT_IN_FLAG_TSOV2_EN, tso_v2, INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload, - INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload); + INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload, + INIT_TXQ_EXT_IN_FLAG_TIMESTAMP, + tx_queue->timestamping); rc = efx_mcdi_rpc_quiet(efx, MC_CMD_INIT_TXQ, inbuf, inlen, NULL, 0, NULL); @@ -2472,12 +2508,13 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue) tx_queue->buffer[0].flags = EFX_TX_BUF_OPTION; tx_queue->insert_count = 1; txd = efx_tx_desc(tx_queue, 0); - EFX_POPULATE_QWORD_4(*txd, + EFX_POPULATE_QWORD_5(*txd, ESF_DZ_TX_DESC_IS_OPT, true, ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_CRC_CSUM, ESF_DZ_TX_OPTION_UDP_TCP_CSUM, csum_offload, - ESF_DZ_TX_OPTION_IP_CSUM, csum_offload); + ESF_DZ_TX_OPTION_IP_CSUM, csum_offload, + ESF_DZ_TX_TIMESTAMP, tx_queue->timestamping); tx_queue->write_count = 1; if (tso_v2) { @@ -3572,31 +3609,92 @@ static int efx_ef10_handle_rx_event(struct efx_channel *channel, return n_packets; } -static int +static u32 efx_ef10_extract_event_ts(efx_qword_t *event) +{ + u32 tstamp; + + tstamp = EFX_QWORD_FIELD(*event, TX_TIMESTAMP_EVENT_TSTAMP_DATA_HI); + tstamp <<= 16; + tstamp |= EFX_QWORD_FIELD(*event, TX_TIMESTAMP_EVENT_TSTAMP_DATA_LO); + + return tstamp; +} + +static void efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) { struct efx_nic *efx = channel->efx; struct efx_tx_queue *tx_queue; unsigned int tx_ev_desc_ptr; unsigned int tx_ev_q_label; - int tx_descs = 0; + unsigned int tx_ev_type; + u64 ts_part; if (unlikely(READ_ONCE(efx->reset_pending))) - return 0; + return; if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_TX_DROP_EVENT))) - return 0; + return; - /* Transmit completion */ - tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, ESF_DZ_TX_DESCR_INDX); + /* Get the transmit queue */ tx_ev_q_label = EFX_QWORD_FIELD(*event, ESF_DZ_TX_QLABEL); tx_queue = efx_channel_get_tx_queue(channel, tx_ev_q_label % EFX_TXQ_TYPES); - tx_descs = ((tx_ev_desc_ptr + 1 - tx_queue->read_count) & - tx_queue->ptr_mask); - efx_xmit_done(tx_queue, tx_ev_desc_ptr & tx_queue->ptr_mask); - return tx_descs; + if (!tx_queue->timestamping) { + /* Transmit completion */ + tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, ESF_DZ_TX_DESCR_INDX); + efx_xmit_done(tx_queue, tx_ev_desc_ptr & tx_queue->ptr_mask); + return; + } + + /* Transmit timestamps are only available for 8XXX series. They result + * in three events per packet. These occur in order, and are: + * - the normal completion event + * - the low part of the timestamp + * - the high part of the timestamp + * + * Each part of the timestamp is itself split across two 16 bit + * fields in the event. + */ + tx_ev_type = EFX_QWORD_FIELD(*event, ESF_EZ_TX_SOFT1); + + switch (tx_ev_type) { + case TX_TIMESTAMP_EVENT_TX_EV_COMPLETION: + /* In case of Queue flush or FLR, we might have received + * the previous TX completion event but not the Timestamp + * events. + */ + if (tx_queue->completed_desc_ptr != tx_queue->ptr_mask) + efx_xmit_done(tx_queue, tx_queue->completed_desc_ptr); + + tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, + ESF_DZ_TX_DESCR_INDX); + tx_queue->completed_desc_ptr = + tx_ev_desc_ptr & tx_queue->ptr_mask; + break; + + case TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_LO: + ts_part = efx_ef10_extract_event_ts(event); + tx_queue->completed_timestamp_minor = ts_part; + break; + + case TX_TIMESTAMP_EVENT_TX_EV_TSTAMP_HI: + ts_part = efx_ef10_extract_event_ts(event); + tx_queue->completed_timestamp_major = ts_part; + + efx_xmit_done(tx_queue, tx_queue->completed_desc_ptr); + tx_queue->completed_desc_ptr = tx_queue->ptr_mask; + break; + + default: + netif_err(efx, hw, efx->net_dev, + "channel %d unknown tx event type %d (data " + EFX_QWORD_FMT ")\n", + channel->channel, tx_ev_type, + EFX_QWORD_VAL(*event)); + break; + } } static void @@ -3658,7 +3756,6 @@ static int efx_ef10_ev_process(struct efx_channel *channel, int quota) efx_qword_t event, *p_event; unsigned int read_ptr; int ev_code; - int tx_descs = 0; int spent = 0; if (quota <= 0) @@ -3698,13 +3795,7 @@ static int efx_ef10_ev_process(struct efx_channel *channel, int quota) } break; case ESE_DZ_EV_CODE_TX_EV: - tx_descs += efx_ef10_handle_tx_event(channel, &event); - if (tx_descs > efx->txq_entries) { - spent = quota; - goto out; - } else if (++spent == quota) { - goto out; - } + efx_ef10_handle_tx_event(channel, &event); break; case ESE_DZ_EV_CODE_DRIVER_EV: efx_ef10_handle_driver_event(channel, &event); @@ -6179,7 +6270,8 @@ static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en, efx_ef10_rx_enable_timestamping : efx_ef10_rx_disable_timestamping; - efx_for_each_channel(channel, efx) { + channel = efx_ptp_channel(efx); + if (channel) { int rc = set(channel, temp); if (en && rc != 0) { efx_ef10_ptp_set_ts_sync_events(efx, false, temp); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 12f0abc30cb1..16757cfc5b29 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -896,12 +896,20 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue) mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100)); } +static bool efx_default_channel_want_txqs(struct efx_channel *channel) +{ + return channel->channel - channel->efx->tx_channel_offset < + channel->efx->n_tx_channels; +} + static const struct efx_channel_type efx_default_channel_type = { .pre_probe = efx_channel_dummy_op_int, .post_remove = efx_channel_dummy_op_void, .get_name = efx_get_channel_name, .copy = efx_copy_channel, + .want_txqs = efx_default_channel_want_txqs, .keep_eventq = false, + .want_pio = true, }; int efx_channel_dummy_op_int(struct efx_channel *channel) @@ -1501,6 +1509,7 @@ static int efx_probe_interrupts(struct efx_nic *efx) } /* Assign extra channels if possible */ + efx->n_extra_tx_channels = 0; j = efx->n_channels; for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) { if (!efx->extra_channel_type[i]) @@ -1512,6 +1521,8 @@ static int efx_probe_interrupts(struct efx_nic *efx) --j; efx_get_channel(efx, j)->type = efx->extra_channel_type[i]; + if (efx_channel_has_tx_queues(efx_get_channel(efx, j))) + efx->n_extra_tx_channels++; } } diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 5334dc83d926..266b9bee1f3a 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -818,17 +818,16 @@ static void efx_farch_magic_event(struct efx_channel *channel, u32 magic) * The NIC batches TX completion events; the message we receive is of * the form "complete all TX events up to this index". */ -static int +static void efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) { unsigned int tx_ev_desc_ptr; unsigned int tx_ev_q_label; struct efx_tx_queue *tx_queue; struct efx_nic *efx = channel->efx; - int tx_packets = 0; if (unlikely(READ_ONCE(efx->reset_pending))) - return 0; + return; if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) { /* Transmit completion */ @@ -836,8 +835,6 @@ efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL); tx_queue = efx_channel_get_tx_queue( channel, tx_ev_q_label % EFX_TXQ_TYPES); - tx_packets = ((tx_ev_desc_ptr - tx_queue->read_count) & - tx_queue->ptr_mask); efx_xmit_done(tx_queue, tx_ev_desc_ptr); } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) { /* Rewrite the FIFO write pointer */ @@ -856,8 +853,6 @@ efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event) EFX_QWORD_FMT"\n", channel->channel, EFX_QWORD_VAL(*event)); } - - return tx_packets; } /* Detect errors included in the rx_evt_pkt_ok bit. */ @@ -1090,7 +1085,7 @@ efx_farch_handle_tx_flush_done(struct efx_nic *efx, efx_qword_t *event) int qid; qid = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA); - if (qid < EFX_TXQ_TYPES * efx->n_tx_channels) { + if (qid < EFX_TXQ_TYPES * (efx->n_tx_channels + efx->n_extra_tx_channels)) { tx_queue = efx_get_tx_queue(efx, qid / EFX_TXQ_TYPES, qid % EFX_TXQ_TYPES); if (atomic_cmpxchg(&tx_queue->flush_outstanding, 1, 0)) { @@ -1270,7 +1265,6 @@ int efx_farch_ev_process(struct efx_channel *channel, int budget) unsigned int read_ptr; efx_qword_t event, *p_event; int ev_code; - int tx_packets = 0; int spent = 0; if (budget <= 0) @@ -1304,12 +1298,7 @@ int efx_farch_ev_process(struct efx_channel *channel, int budget) goto out; break; case FSE_AZ_EV_CODE_TX_EV: - tx_packets += efx_farch_handle_tx_event(channel, - &event); - if (tx_packets > efx->txq_entries) { - spent = budget; - goto out; - } + efx_farch_handle_tx_event(channel, &event); break; case FSE_AZ_EV_CODE_DRV_GEN_EV: efx_farch_handle_generated_event(channel, &event); @@ -1680,20 +1669,21 @@ void efx_farch_rx_pull_indir_table(struct efx_nic *efx) */ void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw) { - unsigned vi_count, buftbl_min; + unsigned vi_count, buftbl_min, total_tx_channels; #ifdef CONFIG_SFC_SRIOV struct siena_nic_data *nic_data = efx->nic_data; #endif + total_tx_channels = efx->n_tx_channels + efx->n_extra_tx_channels; /* Account for the buffer table entries backing the datapath channels * and the descriptor caches for those channels. */ buftbl_min = ((efx->n_rx_channels * EFX_MAX_DMAQ_SIZE + - efx->n_tx_channels * EFX_TXQ_TYPES * EFX_MAX_DMAQ_SIZE + + total_tx_channels * EFX_TXQ_TYPES * EFX_MAX_DMAQ_SIZE + efx->n_channels * EFX_MAX_EVQ_SIZE) * sizeof(efx_qword_t) / EFX_BUF_SIZE); - vi_count = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES); + vi_count = max(efx->n_channels, total_tx_channels * EFX_TXQ_TYPES); #ifdef CONFIG_SFC_SRIOV if (efx->type->sriov_wanted) { diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 3dd42f3136fe..d20a8660ee48 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -191,6 +191,7 @@ struct efx_tx_buffer { * Size of the region is efx_piobuf_size. * @piobuf_offset: Buffer offset to be specified in PIO descriptors * @initialised: Has hardware queue been initialised? + * @timestamping: Is timestamping enabled for this channel? * @handle_tso: TSO xmit preparation handler. Sets up the TSO metadata and * may also map tx data, depending on the nature of the TSO implementation. * @read_count: Current read pointer. @@ -202,6 +203,10 @@ struct efx_tx_buffer { * avoid cache-line ping-pong between the xmit path and the * completion path. * @merge_events: Number of TX merged completion events + * @completed_desc_ptr: Most recent completed pointer - only used with + * timestamping. + * @completed_timestamp_major: Top part of the most recent tx timestamp. + * @completed_timestamp_minor: Low part of the most recent tx timestamp. * @insert_count: Current insert pointer * This is the number of buffers that have been added to the * software ring. @@ -247,6 +252,7 @@ struct efx_tx_queue { void __iomem *piobuf; unsigned int piobuf_offset; bool initialised; + bool timestamping; /* Function pointers used in the fast path. */ int (*handle_tso)(struct efx_tx_queue*, struct sk_buff*, bool *); @@ -257,6 +263,9 @@ struct efx_tx_queue { unsigned int merge_events; unsigned int bytes_compl; unsigned int pkts_compl; + unsigned int completed_desc_ptr; + u32 completed_timestamp_major; + u32 completed_timestamp_minor; /* Members used only on the xmit path */ unsigned int insert_count ____cacheline_aligned_in_smp; @@ -522,8 +531,12 @@ struct efx_msi_context { * @copy: Copy the channel state prior to reallocation. May be %NULL if * reallocation is not supported. * @receive_skb: Handle an skb ready to be passed to netif_receive_skb() + * @want_txqs: Determine whether this channel should have TX queues + * created. If %NULL, TX queues are not created. * @keep_eventq: Flag for whether event queue should be kept initialised * while the device is stopped + * @want_pio: Flag for whether PIO buffers should be linked to this + * channel's TX queues. */ struct efx_channel_type { void (*handle_no_channel)(struct efx_nic *); @@ -532,7 +545,9 @@ struct efx_channel_type { void (*get_name)(struct efx_channel *, char *buf, size_t len); struct efx_channel *(*copy)(const struct efx_channel *); bool (*receive_skb)(struct efx_channel *, struct sk_buff *); + bool (*want_txqs)(struct efx_channel *); bool keep_eventq; + bool want_pio; }; enum efx_led_mode { @@ -735,6 +750,7 @@ struct vfdi_status; * @n_channels: Number of channels in use * @n_rx_channels: Number of channels used for RX (= number of RX queues) * @n_tx_channels: Number of channels used for TX + * @n_extra_tx_channels: Number of extra channels with TX queues * @rx_ip_align: RX DMA address offset to have IP header aligned in * in accordance with NET_IP_ALIGN * @rx_dma_len: Current maximum RX DMA length @@ -881,6 +897,7 @@ struct efx_nic { unsigned rss_spread; unsigned tx_channel_offset; unsigned n_tx_channels; + unsigned n_extra_tx_channels; unsigned int rx_ip_align; unsigned int rx_dma_len; unsigned int rx_buffer_order; @@ -1363,8 +1380,8 @@ efx_get_tx_queue(struct efx_nic *efx, unsigned index, unsigned type) static inline bool efx_channel_has_tx_queues(struct efx_channel *channel) { - return channel->channel - channel->efx->tx_channel_offset < - channel->efx->n_tx_channels; + return channel->type && channel->type->want_txqs && + channel->type->want_txqs(channel); } static inline struct efx_tx_queue * diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 763052214525..6549fc685a48 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -440,6 +440,7 @@ struct efx_ef10_nic_data { struct efx_udp_tunnel udp_tunnels[16]; bool udp_tunnels_dirty; struct mutex udp_tunnels_lock; + u64 licensed_features; }; int efx_init_sriov(void); @@ -448,6 +449,7 @@ void efx_fini_sriov(void); struct ethtool_ts_info; int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel); void efx_ptp_defer_probe_with_channel(struct efx_nic *efx); +struct efx_channel *efx_ptp_channel(struct efx_nic *efx); void efx_ptp_remove(struct efx_nic *efx); int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr); int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr); @@ -471,6 +473,8 @@ static inline void efx_rx_skb_attach_timestamp(struct efx_channel *channel, } void efx_ptp_start_datapath(struct efx_nic *efx); void efx_ptp_stop_datapath(struct efx_nic *efx); +bool efx_ptp_use_mac_tx_timestamps(struct efx_nic *efx); +ktime_t efx_ptp_nic_to_kernel_time(struct efx_tx_queue *tx_queue); extern const struct efx_nic_type falcon_a1_nic_type; extern const struct efx_nic_type falcon_b0_nic_type; diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 3b37d7ded3c4..f21661532ed3 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -149,18 +149,14 @@ enum ptp_packet_state { /* Maximum parts-per-billion adjustment that is acceptable */ #define MAX_PPB 1000000 -/* Number of bits required to hold the above */ -#define MAX_PPB_BITS 20 - -/* Number of extra bits allowed when calculating fractional ns. - * EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS + MAX_PPB_BITS should - * be less than 63. - */ -#define PPB_EXTRA_BITS 2 - /* Precalculate scale word to avoid long long division at runtime */ -#define PPB_SCALE_WORD ((1LL << (PPB_EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS +\ - MAX_PPB_BITS)) / 1000000000LL) +/* This is equivalent to 2^66 / 10^9. */ +#define PPB_SCALE_WORD ((1LL << (57)) / 1953125LL) + +/* How much to shift down after scaling to convert to FP40 */ +#define PPB_SHIFT_FP40 26 +/* ... and FP44. */ +#define PPB_SHIFT_FP44 22 #define PTP_SYNC_ATTEMPTS 4 @@ -218,8 +214,8 @@ struct efx_ptp_timeset { * @channel: The PTP channel (Siena only) * @rx_ts_inline: Flag for whether RX timestamps are inline (else they are * separate events) - * @rxq: Receive queue (awaiting timestamps) - * @txq: Transmit queue + * @rxq: Receive SKB queue (awaiting timestamps) + * @txq: Transmit SKB queue * @evt_list: List of MC receive events awaiting packets * @evt_free_list: List of free events * @evt_lock: Lock for manipulating evt_list and evt_free_list @@ -233,19 +229,36 @@ struct efx_ptp_timeset { * @config: Current timestamp configuration * @enabled: PTP operation enabled * @mode: Mode in which PTP operating (PTP version) - * @time_format: Time format supported by this NIC * @ns_to_nic_time: Function to convert from scalar nanoseconds to NIC time * @nic_to_kernel_time: Function to convert from NIC to kernel time + * @nic_time.minor_max: Wrap point for NIC minor times + * @nic_time.sync_event_diff_min: Minimum acceptable difference between time + * in packet prefix and last MCDI time sync event i.e. how much earlier than + * the last sync event time a packet timestamp can be. + * @nic_time.sync_event_diff_max: Maximum acceptable difference between time + * in packet prefix and last MCDI time sync event i.e. how much later than + * the last sync event time a packet timestamp can be. + * @nic_time.sync_event_minor_shift: Shift required to make minor time from + * field in MCDI time sync event. * @min_synchronisation_ns: Minimum acceptable corrected sync window - * @ts_corrections.tx: Required driver correction of transmit timestamps - * @ts_corrections.rx: Required driver correction of receive timestamps + * @capabilities: Capabilities flags from the NIC + * @ts_corrections.ptp_tx: Required driver correction of PTP packet transmit + * timestamps + * @ts_corrections.ptp_rx: Required driver correction of PTP packet receive + * timestamps * @ts_corrections.pps_out: PPS output error (information only) * @ts_corrections.pps_in: Required driver correction of PPS input timestamps + * @ts_corrections.general_tx: Required driver correction of general packet + * transmit timestamps + * @ts_corrections.general_rx: Required driver correction of general packet + * receive timestamps * @evt_frags: Partly assembled PTP events * @evt_frag_idx: Current fragment number * @evt_code: Last event code * @start: Address at which MC indicates ready for synchronisation * @host_time_pps: Host time at last PPS + * @adjfreq_ppb_shift: Shift required to convert scaled parts-per-billion + * frequency adjustment into a fixed point fractional nanosecond format. * @current_adjfreq: Current ppb adjustment. * @phc_clock: Pointer to registered phc device (if primary function) * @phc_clock_info: Registration structure for phc device @@ -264,6 +277,7 @@ struct efx_ptp_timeset { * @oversize_sync_windows: Number of corrected sync windows that are too large * @rx_no_timestamp: Number of packets received without a timestamp. * @timeset: Last set of synchronisation statistics. + * @xmit_skb: Transmit SKB function. */ struct efx_ptp_data { struct efx_nic *efx; @@ -284,22 +298,31 @@ struct efx_ptp_data { struct hwtstamp_config config; bool enabled; unsigned int mode; - unsigned int time_format; void (*ns_to_nic_time)(s64 ns, u32 *nic_major, u32 *nic_minor); ktime_t (*nic_to_kernel_time)(u32 nic_major, u32 nic_minor, s32 correction); + struct { + u32 minor_max; + u32 sync_event_diff_min; + u32 sync_event_diff_max; + unsigned int sync_event_minor_shift; + } nic_time; unsigned int min_synchronisation_ns; + unsigned int capabilities; struct { - s32 tx; - s32 rx; + s32 ptp_tx; + s32 ptp_rx; s32 pps_out; s32 pps_in; + s32 general_tx; + s32 general_rx; } ts_corrections; efx_qword_t evt_frags[MAX_EVENT_FRAGS]; int evt_frag_idx; int evt_code; struct efx_buffer start; struct pps_event_time host_time_pps; + unsigned int adjfreq_ppb_shift; s64 current_adjfreq; struct ptp_clock *phc_clock; struct ptp_clock_info phc_clock_info; @@ -319,6 +342,7 @@ struct efx_ptp_data { unsigned int rx_no_timestamp; struct efx_ptp_timeset timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM]; + void (*xmit_skb)(struct efx_nic *efx, struct sk_buff *skb); }; static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); @@ -329,6 +353,24 @@ static int efx_phc_settime(struct ptp_clock_info *ptp, static int efx_phc_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); +bool efx_ptp_use_mac_tx_timestamps(struct efx_nic *efx) +{ + struct efx_ef10_nic_data *nic_data = efx->nic_data; + + return ((efx_nic_rev(efx) >= EFX_REV_HUNT_A0) && + (nic_data->datapath_caps2 & + (1 << MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_LBN) + )); +} + +/* PTP 'extra' channel is still a traffic channel, but we only create TX queues + * if PTP uses MAC TX timestamps, not if PTP uses the MC directly to transmit. + */ +static bool efx_ptp_want_txqs(struct efx_channel *channel) +{ + return efx_ptp_use_mac_tx_timestamps(channel->efx); +} + #define PTP_SW_STAT(ext_name, field_name) \ { #ext_name, 0, offsetof(struct efx_ptp_data, field_name) } #define PTP_MC_STAT(ext_name, mcdi_name) \ @@ -471,6 +513,89 @@ static ktime_t efx_ptp_s27_to_ktime_correction(u32 nic_major, u32 nic_minor, return efx_ptp_s27_to_ktime(nic_major, nic_minor); } +/* For Medford2 platforms the time is in seconds and quarter nanoseconds. */ +static void efx_ptp_ns_to_s_qns(s64 ns, u32 *nic_major, u32 *nic_minor) +{ + struct timespec64 ts = ns_to_timespec64(ns); + + *nic_major = (u32)ts.tv_sec; + *nic_minor = ts.tv_nsec * 4; +} + +static ktime_t efx_ptp_s_qns_to_ktime_correction(u32 nic_major, u32 nic_minor, + s32 correction) +{ + ktime_t kt; + + nic_minor = DIV_ROUND_CLOSEST(nic_minor, 4); + correction = DIV_ROUND_CLOSEST(correction, 4); + + kt = ktime_set(nic_major, nic_minor); + + if (correction >= 0) + kt = ktime_add_ns(kt, (u64)correction); + else + kt = ktime_sub_ns(kt, (u64)-correction); + return kt; +} + +struct efx_channel *efx_ptp_channel(struct efx_nic *efx) +{ + return efx->ptp_data ? efx->ptp_data->channel : NULL; +} + +static u32 last_sync_timestamp_major(struct efx_nic *efx) +{ + struct efx_channel *channel = efx_ptp_channel(efx); + u32 major = 0; + + if (channel) + major = channel->sync_timestamp_major; + return major; +} + +/* The 8000 series and later can provide the time from the MAC, which is only + * 48 bits long and provides meta-information in the top 2 bits. + */ +static ktime_t +efx_ptp_mac_nic_to_ktime_correction(struct efx_nic *efx, + struct efx_ptp_data *ptp, + u32 nic_major, u32 nic_minor, + s32 correction) +{ + ktime_t kt = { 0 }; + + if (!(nic_major & 0x80000000)) { + WARN_ON_ONCE(nic_major >> 16); + /* Use the top bits from the latest sync event. */ + nic_major &= 0xffff; + nic_major |= (last_sync_timestamp_major(efx) & 0xffff0000); + + kt = ptp->nic_to_kernel_time(nic_major, nic_minor, + correction); + } + return kt; +} + +ktime_t efx_ptp_nic_to_kernel_time(struct efx_tx_queue *tx_queue) +{ + struct efx_nic *efx = tx_queue->efx; + struct efx_ptp_data *ptp = efx->ptp_data; + ktime_t kt; + + if (efx_ptp_use_mac_tx_timestamps(efx)) + kt = efx_ptp_mac_nic_to_ktime_correction(efx, ptp, + tx_queue->completed_timestamp_major, + tx_queue->completed_timestamp_minor, + ptp->ts_corrections.general_tx); + else + kt = ptp->nic_to_kernel_time( + tx_queue->completed_timestamp_major, + tx_queue->completed_timestamp_minor, + ptp->ts_corrections.general_tx); + return kt; +} + /* Get PTP attributes and set up time conversions */ static int efx_ptp_get_attributes(struct efx_nic *efx) { @@ -502,31 +627,71 @@ static int efx_ptp_get_attributes(struct efx_nic *efx) return rc; } - if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION) { + switch (fmt) { + case MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION: ptp->ns_to_nic_time = efx_ptp_ns_to_s27; ptp->nic_to_kernel_time = efx_ptp_s27_to_ktime_correction; - } else if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS) { + ptp->nic_time.minor_max = 1 << 27; + ptp->nic_time.sync_event_minor_shift = 19; + break; + case MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS: ptp->ns_to_nic_time = efx_ptp_ns_to_s_ns; ptp->nic_to_kernel_time = efx_ptp_s_ns_to_ktime_correction; - } else { + ptp->nic_time.minor_max = 1000000000; + ptp->nic_time.sync_event_minor_shift = 22; + break; + case MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_QTR_NANOSECONDS: + ptp->ns_to_nic_time = efx_ptp_ns_to_s_qns; + ptp->nic_to_kernel_time = efx_ptp_s_qns_to_ktime_correction; + ptp->nic_time.minor_max = 4000000000UL; + ptp->nic_time.sync_event_minor_shift = 24; + break; + default: return -ERANGE; } - ptp->time_format = fmt; - - /* MC_CMD_PTP_OP_GET_ATTRIBUTES is an extended version of an older - * operation MC_CMD_PTP_OP_GET_TIME_FORMAT that also returns a value - * to use for the minimum acceptable corrected synchronization window. + /* Precalculate acceptable difference between the minor time in the + * packet prefix and the last MCDI time sync event. We expect the + * packet prefix timestamp to be after of sync event by up to one + * sync event interval (0.25s) but we allow it to exceed this by a + * fuzz factor of (0.1s) + */ + ptp->nic_time.sync_event_diff_min = ptp->nic_time.minor_max + - (ptp->nic_time.minor_max / 10); + ptp->nic_time.sync_event_diff_max = (ptp->nic_time.minor_max / 4) + + (ptp->nic_time.minor_max / 10); + + /* MC_CMD_PTP_OP_GET_ATTRIBUTES has been extended twice from an older + * operation MC_CMD_PTP_OP_GET_TIME_FORMAT. The function now may return + * a value to use for the minimum acceptable corrected synchronization + * window and may return further capabilities. * If we have the extra information store it. For older firmware that * does not implement the extended command use the default value. */ - if (rc == 0 && out_len >= MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN) + if (rc == 0 && + out_len >= MC_CMD_PTP_OUT_GET_ATTRIBUTES_CAPABILITIES_OFST) ptp->min_synchronisation_ns = MCDI_DWORD(outbuf, PTP_OUT_GET_ATTRIBUTES_SYNC_WINDOW_MIN); else ptp->min_synchronisation_ns = DEFAULT_MIN_SYNCHRONISATION_NS; + if (rc == 0 && + out_len >= MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN) + ptp->capabilities = MCDI_DWORD(outbuf, + PTP_OUT_GET_ATTRIBUTES_CAPABILITIES); + else + ptp->capabilities = 0; + + /* Set up the shift for conversion between frequency + * adjustments in parts-per-billion and the fixed-point + * fractional ns format that the adapter uses. + */ + if (ptp->capabilities & (1 << MC_CMD_PTP_OUT_GET_ATTRIBUTES_FP44_FREQ_ADJ_LBN)) + ptp->adjfreq_ppb_shift = PPB_SHIFT_FP44; + else + ptp->adjfreq_ppb_shift = PPB_SHIFT_FP40; + return 0; } @@ -534,8 +699,9 @@ static int efx_ptp_get_attributes(struct efx_nic *efx) static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx) { MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS_LEN); - MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_LEN); int rc; + size_t out_len; /* Get the timestamp corrections from the NIC. If this operation is * not supported (older NICs) then no correction is required. @@ -545,21 +711,37 @@ static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx) MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), - outbuf, sizeof(outbuf), NULL); + outbuf, sizeof(outbuf), &out_len); if (rc == 0) { - efx->ptp_data->ts_corrections.tx = MCDI_DWORD(outbuf, + efx->ptp_data->ts_corrections.ptp_tx = MCDI_DWORD(outbuf, PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT); - efx->ptp_data->ts_corrections.rx = MCDI_DWORD(outbuf, + efx->ptp_data->ts_corrections.ptp_rx = MCDI_DWORD(outbuf, PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE); efx->ptp_data->ts_corrections.pps_out = MCDI_DWORD(outbuf, PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT); efx->ptp_data->ts_corrections.pps_in = MCDI_DWORD(outbuf, PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN); + + if (out_len >= MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_LEN) { + efx->ptp_data->ts_corrections.general_tx = MCDI_DWORD( + outbuf, + PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_GENERAL_TX); + efx->ptp_data->ts_corrections.general_rx = MCDI_DWORD( + outbuf, + PTP_OUT_GET_TIMESTAMP_CORRECTIONS_V2_GENERAL_RX); + } else { + efx->ptp_data->ts_corrections.general_tx = + efx->ptp_data->ts_corrections.ptp_tx; + efx->ptp_data->ts_corrections.general_rx = + efx->ptp_data->ts_corrections.ptp_rx; + } } else if (rc == -EINVAL) { - efx->ptp_data->ts_corrections.tx = 0; - efx->ptp_data->ts_corrections.rx = 0; + efx->ptp_data->ts_corrections.ptp_tx = 0; + efx->ptp_data->ts_corrections.ptp_rx = 0; efx->ptp_data->ts_corrections.pps_out = 0; efx->ptp_data->ts_corrections.pps_in = 0; + efx->ptp_data->ts_corrections.general_tx = 0; + efx->ptp_data->ts_corrections.general_rx = 0; } else { efx_mcdi_display_error(efx, MC_CMD_PTP, sizeof(inbuf), outbuf, sizeof(outbuf), rc); @@ -873,8 +1055,24 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) return rc; } +/* Transmit a PTP packet via the dedicated hardware timestamped queue. */ +static void efx_ptp_xmit_skb_queue(struct efx_nic *efx, struct sk_buff *skb) +{ + struct efx_ptp_data *ptp_data = efx->ptp_data; + struct efx_tx_queue *tx_queue; + u8 type = skb->ip_summed == CHECKSUM_PARTIAL ? EFX_TXQ_TYPE_OFFLOAD : 0; + + tx_queue = &ptp_data->channel->tx_queue[type]; + if (tx_queue && tx_queue->timestamping) { + efx_enqueue_skb(tx_queue, skb); + } else { + WARN_ONCE(1, "PTP channel has no timestamped tx queue\n"); + dev_kfree_skb_any(skb); + } +} + /* Transmit a PTP packet, via the MCDI interface, to the wire. */ -static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb) +static void efx_ptp_xmit_skb_mc(struct efx_nic *efx, struct sk_buff *skb) { struct efx_ptp_data *ptp_data = efx->ptp_data; struct skb_shared_hwtstamps timestamps; @@ -910,16 +1108,16 @@ static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb) timestamps.hwtstamp = ptp_data->nic_to_kernel_time( MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_MAJOR), MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_MINOR), - ptp_data->ts_corrections.tx); + ptp_data->ts_corrections.ptp_tx); skb_tstamp_tx(skb, ×tamps); rc = 0; fail: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); - return rc; + return; } static void efx_ptp_drop_time_expired_events(struct efx_nic *efx) @@ -1189,7 +1387,7 @@ static void efx_ptp_worker(struct work_struct *work) efx_ptp_process_events(efx, &tempq); while ((skb = skb_dequeue(&ptp_data->txq))) - efx_ptp_xmit_skb(efx, skb); + ptp_data->xmit_skb(efx, skb); while ((skb = __skb_dequeue(&tempq))) efx_ptp_process_rx(efx, skb); @@ -1239,6 +1437,14 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel) goto fail2; } + if (efx_ptp_use_mac_tx_timestamps(efx)) { + ptp->xmit_skb = efx_ptp_xmit_skb_queue; + /* Request sync events on this channel. */ + channel->sync_events_state = SYNC_EVENTS_QUIESCENT; + } else { + ptp->xmit_skb = efx_ptp_xmit_skb_mc; + } + INIT_WORK(&ptp->work, efx_ptp_worker); ptp->config.flags = 0; ptp->config.tx_type = HWTSTAMP_TX_OFF; @@ -1303,11 +1509,21 @@ fail1: static int efx_ptp_probe_channel(struct efx_channel *channel) { struct efx_nic *efx = channel->efx; + int rc; channel->irq_moderation_us = 0; channel->rx_queue.core_index = 0; - return efx_ptp_probe(efx, channel); + rc = efx_ptp_probe(efx, channel); + /* Failure to probe PTP is not fatal; this channel will just not be + * used for anything. + * In the case of EPERM, efx_ptp_probe will print its own message (in + * efx_ptp_get_attributes()), so we don't need to. + */ + if (rc && rc != -EPERM) + netif_warn(efx, drv, efx->net_dev, + "Failed to probe PTP, rc=%d\n", rc); + return 0; } void efx_ptp_remove(struct efx_nic *efx) @@ -1332,6 +1548,7 @@ void efx_ptp_remove(struct efx_nic *efx) efx_nic_free_buffer(efx, &efx->ptp_data->start); kfree(efx->ptp_data); + efx->ptp_data = NULL; } static void efx_ptp_remove_channel(struct efx_channel *channel) @@ -1548,6 +1765,17 @@ void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info) ts_info->so_timestamping |= (SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE); + /* Check licensed features. If we don't have the license for TX + * timestamps, the NIC will not support them. + */ + if (efx_ptp_use_mac_tx_timestamps(efx)) { + struct efx_ef10_nic_data *nic_data = efx->nic_data; + + if (!(nic_data->licensed_features & + (1 << LICENSED_V3_FEATURES_TX_TIMESTAMPS_LBN))) + ts_info->so_timestamping &= + ~SOF_TIMESTAMPING_TX_HARDWARE; + } if (primary && primary->ptp_data && primary->ptp_data->phc_clock) ts_info->phc_index = ptp_clock_index(primary->ptp_data->phc_clock); @@ -1627,7 +1855,7 @@ static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp) evt->hwtimestamp = efx->ptp_data->nic_to_kernel_time( EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA), EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA), - ptp->ts_corrections.rx); + ptp->ts_corrections.ptp_rx); evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS); list_add_tail(&evt->link, &ptp->evt_list); @@ -1709,9 +1937,20 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev) { + struct efx_nic *efx = channel->efx; + struct efx_ptp_data *ptp = efx->ptp_data; + + /* When extracting the sync timestamp minor value, we should discard + * the least significant two bits. These are not required in order + * to reconstruct full-range timestamps and they are optionally used + * to report status depending on the options supplied when subscribing + * for sync events. + */ channel->sync_timestamp_major = MCDI_EVENT_FIELD(*ev, PTP_TIME_MAJOR); channel->sync_timestamp_minor = - MCDI_EVENT_FIELD(*ev, PTP_TIME_MINOR_26_19) << 19; + (MCDI_EVENT_FIELD(*ev, PTP_TIME_MINOR_MS_8BITS) & 0xFC) + << ptp->nic_time.sync_event_minor_shift; + /* if sync events have been disabled then we want to silently ignore * this event, so throw away result. */ @@ -1719,15 +1958,6 @@ void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev) SYNC_EVENTS_VALID); } -/* make some assumptions about the time representation rather than abstract it, - * since we currently only support one type of inline timestamping and only on - * EF10. - */ -#define MINOR_TICKS_PER_SECOND 0x8000000 -/* Fuzz factor for sync events to be out of order with RX events */ -#define FUZZ (MINOR_TICKS_PER_SECOND / 10) -#define EXPECTED_SYNC_EVENTS_PER_SECOND 4 - static inline u32 efx_rx_buf_timestamp_minor(struct efx_nic *efx, const u8 *eh) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) @@ -1745,31 +1975,33 @@ void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, struct sk_buff *skb) { struct efx_nic *efx = channel->efx; + struct efx_ptp_data *ptp = efx->ptp_data; u32 pkt_timestamp_major, pkt_timestamp_minor; u32 diff, carry; struct skb_shared_hwtstamps *timestamps; - pkt_timestamp_minor = (efx_rx_buf_timestamp_minor(efx, - skb_mac_header(skb)) + - (u32) efx->ptp_data->ts_corrections.rx) & - (MINOR_TICKS_PER_SECOND - 1); + if (channel->sync_events_state != SYNC_EVENTS_VALID) + return; + + pkt_timestamp_minor = efx_rx_buf_timestamp_minor(efx, skb_mac_header(skb)); /* get the difference between the packet and sync timestamps, * modulo one second */ - diff = (pkt_timestamp_minor - channel->sync_timestamp_minor) & - (MINOR_TICKS_PER_SECOND - 1); + diff = pkt_timestamp_minor - channel->sync_timestamp_minor; + if (pkt_timestamp_minor < channel->sync_timestamp_minor) + diff += ptp->nic_time.minor_max; + /* do we roll over a second boundary and need to carry the one? */ - carry = channel->sync_timestamp_minor + diff > MINOR_TICKS_PER_SECOND ? + carry = (channel->sync_timestamp_minor >= ptp->nic_time.minor_max - diff) ? 1 : 0; - if (diff <= MINOR_TICKS_PER_SECOND / EXPECTED_SYNC_EVENTS_PER_SECOND + - FUZZ) { + if (diff <= ptp->nic_time.sync_event_diff_max) { /* packet is ahead of the sync event by a quarter of a second or * less (allowing for fuzz) */ pkt_timestamp_major = channel->sync_timestamp_major + carry; - } else if (diff >= MINOR_TICKS_PER_SECOND - FUZZ) { + } else if (diff >= ptp->nic_time.sync_event_diff_min) { /* packet is behind the sync event but within the fuzz factor. * This means the RX packet and sync event crossed as they were * placed on the event queue, which can sometimes happen. @@ -1791,7 +2023,9 @@ void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, /* attach the timestamps to the skb */ timestamps = skb_hwtstamps(skb); timestamps->hwtstamp = - efx_ptp_s27_to_ktime(pkt_timestamp_major, pkt_timestamp_minor); + ptp->nic_to_kernel_time(pkt_timestamp_major, + pkt_timestamp_minor, + ptp->ts_corrections.general_rx); } static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) @@ -1809,9 +2043,10 @@ static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) else if (delta < -MAX_PPB) delta = -MAX_PPB; - /* Convert ppb to fixed point ns. */ - adjustment_ns = (((s64)delta * PPB_SCALE_WORD) >> - (PPB_EXTRA_BITS + MAX_PPB_BITS)); + /* Convert ppb to fixed point ns taking care to round correctly. */ + adjustment_ns = ((s64)delta * PPB_SCALE_WORD + + (1 << (ptp_data->adjfreq_ppb_shift - 1))) >> + ptp_data->adjfreq_ppb_shift; MCDI_SET_DWORD(inadj, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST); MCDI_SET_DWORD(inadj, PTP_IN_PERIPH_ID, 0); @@ -1918,6 +2153,7 @@ static const struct efx_channel_type efx_ptp_channel_type = { .get_name = efx_ptp_get_channel_name, /* no copy operation; there is no need to reallocate this channel */ .receive_skb = efx_ptp_rx, + .want_txqs = efx_ptp_want_txqs, .keep_eventq = false, }; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 9937a2450e57..cece961f2e82 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -77,9 +77,23 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, } if (buffer->flags & EFX_TX_BUF_SKB) { + struct sk_buff *skb = (struct sk_buff *)buffer->skb; + EFX_WARN_ON_PARANOID(!pkts_compl || !bytes_compl); (*pkts_compl)++; - (*bytes_compl) += buffer->skb->len; + (*bytes_compl) += skb->len; + if (tx_queue->timestamping && + (tx_queue->completed_timestamp_major || + tx_queue->completed_timestamp_minor)) { + struct skb_shared_hwtstamps hwtstamp; + + hwtstamp.hwtstamp = + efx_ptp_nic_to_kernel_time(tx_queue); + skb_tstamp_tx(skb, &hwtstamp); + + tx_queue->completed_timestamp_major = 0; + tx_queue->completed_timestamp_minor = 0; + } dev_consume_skb_any((struct sk_buff *)buffer->skb); netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev, "TX queue %d transmission id %x complete\n", @@ -828,6 +842,11 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue) tx_queue->old_read_count = 0; tx_queue->empty_read_count = 0 | EFX_EMPTY_COUNT_VALID; tx_queue->xmit_more_available = false; + tx_queue->timestamping = (efx_ptp_use_mac_tx_timestamps(efx) && + tx_queue->channel == efx_ptp_channel(efx)); + tx_queue->completed_desc_ptr = tx_queue->ptr_mask; + tx_queue->completed_timestamp_major = 0; + tx_queue->completed_timestamp_minor = 0; /* Set up default function pointers. These may get replaced by * efx_nic_init_tx() based off NIC/queue capabilities. diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ce2ea2d491ac..2ffe76c0ff74 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -474,7 +474,7 @@ struct mac_device_info; /* Helpers to program the MAC core */ struct stmmac_ops { /* MAC core initialization */ - void (*core_init)(struct mac_device_info *hw, int mtu); + void (*core_init)(struct mac_device_info *hw, struct net_device *dev); /* Enable the MAC RX/TX */ void (*set_mac)(void __iomem *ioaddr, bool enable); /* Enable and verify that the IPC module is supported */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 9eb7f65d8000..a3fa65b1ca8e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -483,7 +483,8 @@ static int sun8i_dwmac_init(struct platform_device *pdev, void *priv) return 0; } -static void sun8i_dwmac_core_init(struct mac_device_info *hw, int mtu) +static void sun8i_dwmac_core_init(struct mac_device_info *hw, + struct net_device *dev) { void __iomem *ioaddr = hw->pcsr; u32 v; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 8a86340ff2d3..540d21786a43 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -25,18 +25,28 @@ #include <linux/crc32.h> #include <linux/slab.h> #include <linux/ethtool.h> +#include <net/dsa.h> #include <asm/io.h> #include "stmmac_pcs.h" #include "dwmac1000.h" -static void dwmac1000_core_init(struct mac_device_info *hw, int mtu) +static void dwmac1000_core_init(struct mac_device_info *hw, + struct net_device *dev) { void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONTROL); + int mtu = dev->mtu; /* Configure GMAC core */ value |= GMAC_CORE_INIT; + /* Clear ACS bit because Ethernet switch tagging formats such as + * Broadcom tags can look like invalid LLC/SNAP packets and cause the + * hardware to truncate packets on reception. + */ + if (netdev_uses_dsa(dev)) + value &= ~GMAC_CONTROL_ACS; + if (mtu > 1500) value |= GMAC_CONTROL_2K; if (mtu > 2000) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index 8ef517356313..91b23f9db31a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -25,15 +25,26 @@ *******************************************************************************/ #include <linux/crc32.h> +#include <net/dsa.h> #include <asm/io.h> #include "dwmac100.h" -static void dwmac100_core_init(struct mac_device_info *hw, int mtu) +static void dwmac100_core_init(struct mac_device_info *hw, + struct net_device *dev) { void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + MAC_CONTROL); - writel((value | MAC_CORE_INIT), ioaddr + MAC_CONTROL); + value |= MAC_CORE_INIT; + + /* Clear ASTP bit because Ethernet switch tagging formats such as + * Broadcom tags can look like invalid LLC/SNAP packets and cause the + * hardware to truncate packets on reception. + */ + if (netdev_uses_dsa(dev)) + value &= ~MAC_CONTROL_ASTP; + + writel(value, ioaddr + MAC_CONTROL); #ifdef STMMAC_VLAN_TAG_USED writel(ETH_P_8021Q, ioaddr + MAC_VLAN1); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f3ed8f7853eb..ed222b20fcf1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -17,16 +17,26 @@ #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/io.h> +#include <net/dsa.h> #include "stmmac_pcs.h" #include "dwmac4.h" -static void dwmac4_core_init(struct mac_device_info *hw, int mtu) +static void dwmac4_core_init(struct mac_device_info *hw, + struct net_device *dev) { void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONFIG); + int mtu = dev->mtu; value |= GMAC_CORE_INIT; + /* Clear ACS bit because Ethernet switch tagging formats such as + * Broadcom tags can look like invalid LLC/SNAP packets and cause the + * hardware to truncate packets on reception. + */ + if (netdev_uses_dsa(dev)) + value &= ~GMAC_CONFIG_ACS; + if (mtu > 1500) value |= GMAC_CONFIG_2K; if (mtu > 2000) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 2fd8456999f6..c728ffa095de 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -334,7 +334,7 @@ static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, if (tx_own) tdes3 |= TDES3_OWN; - if (is_fs & tx_own) + if (is_fs && tx_own) /* When the own bit, for the first frame, has to be set, all * descriptors for the same frame has to be set before, to * avoid race condition. @@ -377,7 +377,7 @@ static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs, if (tx_own) tdes3 |= TDES3_OWN; - if (is_fs & tx_own) + if (is_fs && tx_own) /* When the own bit, for the first frame, has to be set, all * descriptors for the same frame has to be set before, to * avoid race condition. diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index b47cb5c4da51..6768a25b6aa0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -341,7 +341,7 @@ static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, if (tx_own) tdes0 |= ETDES0_OWN; - if (is_fs & tx_own) + if (is_fs && tx_own) /* When the own bit, for the first frame, has to be set, all * descriptors for the same frame has to be set before, to * avoid race condition. diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f99f14c35063..7ad841434ec8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2527,7 +2527,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) } /* Initialize the MAC Core */ - priv->hw->mac->core_init(priv->hw, dev->mtu); + priv->hw->mac->core_init(priv->hw, dev); /* Initialize MTL*/ if (priv->synopsys_id >= DWMAC_CORE_4_00) diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 91a67c5297f7..c3ca191fea7f 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1221,7 +1221,6 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, struct ndis_recv_scale_cap rsscap; u32 rsscap_size = sizeof(struct ndis_recv_scale_cap); u32 mtu, size; - const struct cpumask *node_cpu_mask; u32 num_possible_rss_qs; int i, ret; @@ -1290,14 +1289,8 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, if (ret || rsscap.num_recv_que < 2) goto out; - /* - * We will limit the VRSS channels to the number CPUs in the NUMA node - * the primary channel is currently bound to. - * - * This also guarantees that num_possible_rss_qs <= num_online_cpus - */ - node_cpu_mask = cpumask_of_node(cpu_to_node(dev->channel->target_cpu)); - num_possible_rss_qs = min_t(u32, cpumask_weight(node_cpu_mask), + /* This guarantees that num_possible_rss_qs <= num_online_cpus */ + num_possible_rss_qs = min_t(u32, num_online_cpus(), rsscap.num_recv_que); net_device->max_chn = min_t(u32, VRSS_CHANNEL_MAX, num_possible_rss_qs); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index f522715c6595..7de88b33d5b9 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -396,8 +396,6 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) #define MACSEC_GCM_AES_128_SAK_LEN 16 #define MACSEC_GCM_AES_256_SAK_LEN 32 -#define MAX_SAK_LEN MACSEC_GCM_AES_256_SAK_LEN - #define DEFAULT_SAK_LEN MACSEC_GCM_AES_128_SAK_LEN #define DEFAULT_SEND_SCI true #define DEFAULT_ENCRYPT false @@ -1605,7 +1603,7 @@ static const struct nla_policy macsec_genl_sa_policy[NUM_MACSEC_SA_ATTR] = { [MACSEC_SA_ATTR_KEYID] = { .type = NLA_BINARY, .len = MACSEC_KEYID_LEN, }, [MACSEC_SA_ATTR_KEY] = { .type = NLA_BINARY, - .len = MAX_SAK_LEN, }, + .len = MACSEC_MAX_KEY_LEN, }, }; static int parse_sa_config(struct nlattr **attrs, struct nlattr **tb_sa) @@ -2374,7 +2372,7 @@ static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: - csid = MACSEC_CIPHER_ID_GCM_AES_128; + csid = MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = MACSEC_CIPHER_ID_GCM_AES_256; @@ -3076,7 +3074,7 @@ static int macsec_changelink_common(struct net_device *dev, if (data[IFLA_MACSEC_CIPHER_SUITE]) { switch (nla_get_u64(data[IFLA_MACSEC_CIPHER_SUITE])) { case MACSEC_CIPHER_ID_GCM_AES_128: - case MACSEC_DEFAULT_CIPHER_ALT: + case MACSEC_DEFAULT_CIPHER_ID: secy->key_len = MACSEC_GCM_AES_128_SAK_LEN; break; case MACSEC_CIPHER_ID_GCM_AES_256: @@ -3355,7 +3353,7 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[], switch (csid) { case MACSEC_CIPHER_ID_GCM_AES_128: case MACSEC_CIPHER_ID_GCM_AES_256: - case MACSEC_DEFAULT_CIPHER_ALT: + case MACSEC_DEFAULT_CIPHER_ID: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_STD_ICV_LEN) return -EINVAL; @@ -3428,7 +3426,7 @@ static int macsec_fill_info(struct sk_buff *skb, switch (secy->key_len) { case MACSEC_GCM_AES_128_SAK_LEN: - csid = MACSEC_CIPHER_ID_GCM_AES_128; + csid = MACSEC_DEFAULT_CIPHER_ID; break; case MACSEC_GCM_AES_256_SAK_LEN: csid = MACSEC_CIPHER_ID_GCM_AES_256; diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile index 074ddebbc41d..09388c06171d 100644 --- a/drivers/net/netdevsim/Makefile +++ b/drivers/net/netdevsim/Makefile @@ -4,4 +4,8 @@ obj-$(CONFIG_NETDEVSIM) += netdevsim.o netdevsim-objs := \ netdev.o \ - bpf.o \ + +ifeq ($(CONFIG_BPF_SYSCALL),y) +netdevsim-objs += \ + bpf.o +endif diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index b3851bbefad3..de73c1ff0939 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -23,6 +23,9 @@ #include "netdevsim.h" +#define pr_vlog(env, fmt, ...) \ + bpf_verifier_log_write(env, "[netdevsim] " fmt, ##__VA_ARGS__) + struct nsim_bpf_bound_prog { struct netdevsim *ns; struct bpf_prog *prog; @@ -77,6 +80,9 @@ nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) if (state->ns->bpf_bind_verifier_delay && !insn_idx) msleep(state->ns->bpf_bind_verifier_delay); + if (insn_idx == env->prog->len - 1) + pr_vlog(env, "Hello from netdevsim!\n"); + return 0; } @@ -123,17 +129,32 @@ int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type, struct netdevsim *ns = cb_priv; struct bpf_prog *oldprog; - if (type != TC_SETUP_CLSBPF || - !tc_can_offload(ns->netdev) || - cls_bpf->common.protocol != htons(ETH_P_ALL) || - cls_bpf->common.chain_index) + if (type != TC_SETUP_CLSBPF) { + NSIM_EA(cls_bpf->common.extack, + "only offload of BPF classifiers supported"); + return -EOPNOTSUPP; + } + + if (!tc_cls_can_offload_and_chain0(ns->netdev, &cls_bpf->common)) return -EOPNOTSUPP; - if (!ns->bpf_tc_accept) + if (cls_bpf->common.protocol != htons(ETH_P_ALL)) { + NSIM_EA(cls_bpf->common.extack, + "only ETH_P_ALL supported as filter protocol"); return -EOPNOTSUPP; + } + + if (!ns->bpf_tc_accept) { + NSIM_EA(cls_bpf->common.extack, + "netdevsim configured to reject BPF TC offload"); + return -EOPNOTSUPP; + } /* Note: progs without skip_sw will probably not be dev bound */ - if (prog && !prog->aux->offload && !ns->bpf_tc_non_bound_accept) + if (prog && !prog->aux->offload && !ns->bpf_tc_non_bound_accept) { + NSIM_EA(cls_bpf->common.extack, + "netdevsim configured to reject unbound programs"); return -EOPNOTSUPP; + } if (cls_bpf->command != TC_CLSBPF_OFFLOAD) return -EOPNOTSUPP; @@ -145,8 +166,11 @@ int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type, oldprog = NULL; if (!cls_bpf->prog) return 0; - if (ns->bpf_offloaded) + if (ns->bpf_offloaded) { + NSIM_EA(cls_bpf->common.extack, + "driver and netdev offload states mismatch"); return -EBUSY; + } } return nsim_bpf_offload(ns, cls_bpf->prog, oldprog); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index b80361200302..ea081c10efb8 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -68,12 +68,40 @@ struct netdevsim { extern struct dentry *nsim_ddir; +#ifdef CONFIG_BPF_SYSCALL int nsim_bpf_init(struct netdevsim *ns); void nsim_bpf_uninit(struct netdevsim *ns); int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf); int nsim_bpf_disable_tc(struct netdevsim *ns); int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv); +#else +static inline int nsim_bpf_init(struct netdevsim *ns) +{ + return 0; +} + +static inline void nsim_bpf_uninit(struct netdevsim *ns) +{ +} + +static inline int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) +{ + return bpf->command == XDP_QUERY_PROG ? 0 : -EOPNOTSUPP; +} + +static inline int nsim_bpf_disable_tc(struct netdevsim *ns) +{ + return 0; +} + +static inline int +nsim_bpf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + return -EOPNOTSUPP; +} +#endif static inline struct netdevsim *to_nsim(struct device *ptr) { diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index bdc4bb3c8288..8961209ee949 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -441,7 +441,7 @@ EXPORT_SYMBOL_GPL(sfp_upstream_stop); /** * sfp_register_upstream() - Register the neighbouring device - * @np: device node for the SFP bus + * @fwnode: firmware node for the SFP bus * @ndev: network device associated with the interface * @upstream: the upstream private data * @ops: the upstream's &struct sfp_upstream_ops diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 4e1da1645b15..5aa59f41bf8c 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -842,6 +842,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, struct pppoe_hdr *ph; struct net_device *dev; char *start; + int hlen; lock_sock(sk); if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) { @@ -860,16 +861,16 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m, if (total_len > (dev->mtu + dev->hard_header_len)) goto end; - - skb = sock_wmalloc(sk, total_len + dev->hard_header_len + 32, - 0, GFP_KERNEL); + hlen = LL_RESERVED_SPACE(dev); + skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len + + dev->needed_tailroom, 0, GFP_KERNEL); if (!skb) { error = -ENOMEM; goto end; } /* Reserve space for headers. */ - skb_reserve(skb, dev->hard_header_len); + skb_reserve(skb, hlen); skb_reset_network_header(skb); skb->dev = dev; @@ -930,7 +931,7 @@ static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb) /* Copy the data if there is no space for the header or if it's * read-only. */ - if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len)) + if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph))) goto abort; __skb_push(skb, sizeof(*ph)); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 698874684b4e..a0c5cb1a1617 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -774,14 +774,12 @@ static void tun_detach_all(struct net_device *dev) tun_napi_del(tun, tfile); /* Drop read queue */ tun_queue_purge(tfile); - xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); tun_cleanup_tx_ring(tfile); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_enable_queue(tfile); tun_queue_purge(tfile); - xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); tun_cleanup_tx_ring(tfile); } @@ -2225,7 +2223,8 @@ static void tun_prog_free(struct rcu_head *rcu) kfree(prog); } -static int __tun_set_ebpf(struct tun_struct *tun, struct tun_prog **prog_p, +static int __tun_set_ebpf(struct tun_struct *tun, + struct tun_prog __rcu **prog_p, struct bpf_prog *prog) { struct tun_prog *old, *new = NULL; diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index d56fe32bf48d..8a22ff67b026 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -457,12 +457,10 @@ static enum skb_state defer_bh(struct usbnet *dev, struct sk_buff *skb, void usbnet_defer_kevent (struct usbnet *dev, int work) { set_bit (work, &dev->flags); - if (!schedule_work (&dev->kevent)) { - if (net_ratelimit()) - netdev_err(dev->net, "kevent %d may have been dropped\n", work); - } else { + if (!schedule_work (&dev->kevent)) + netdev_dbg(dev->net, "kevent %d may have been dropped\n", work); + else netdev_dbg(dev->net, "kevent %d scheduled\n", work); - } } EXPORT_SYMBOL_GPL(usbnet_defer_kevent); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 12dfc5fee58e..626c27352ae2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -66,16 +66,39 @@ static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_UFO }; -struct virtnet_stats { - struct u64_stats_sync tx_syncp; - struct u64_stats_sync rx_syncp; - u64 tx_bytes; - u64 tx_packets; - - u64 rx_bytes; - u64 rx_packets; +struct virtnet_stat_desc { + char desc[ETH_GSTRING_LEN]; + size_t offset; }; +struct virtnet_sq_stats { + struct u64_stats_sync syncp; + u64 packets; + u64 bytes; +}; + +struct virtnet_rq_stats { + struct u64_stats_sync syncp; + u64 packets; + u64 bytes; +}; + +#define VIRTNET_SQ_STAT(m) offsetof(struct virtnet_sq_stats, m) +#define VIRTNET_RQ_STAT(m) offsetof(struct virtnet_rq_stats, m) + +static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = { + { "packets", VIRTNET_SQ_STAT(packets) }, + { "bytes", VIRTNET_SQ_STAT(bytes) }, +}; + +static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = { + { "packets", VIRTNET_RQ_STAT(packets) }, + { "bytes", VIRTNET_RQ_STAT(bytes) }, +}; + +#define VIRTNET_SQ_STATS_LEN ARRAY_SIZE(virtnet_sq_stats_desc) +#define VIRTNET_RQ_STATS_LEN ARRAY_SIZE(virtnet_rq_stats_desc) + /* Internal representation of a send virtqueue */ struct send_queue { /* Virtqueue associated with this send _queue */ @@ -87,6 +110,8 @@ struct send_queue { /* Name of the send queue: output.$index */ char name[40]; + struct virtnet_sq_stats stats; + struct napi_struct napi; }; @@ -99,6 +124,8 @@ struct receive_queue { struct bpf_prog __rcu *xdp_prog; + struct virtnet_rq_stats stats; + /* Chain pages by the private ptr. */ struct page *pages; @@ -152,9 +179,6 @@ struct virtnet_info { /* Packet virtio header size */ u8 hdr_len; - /* Active statistics */ - struct virtnet_stats __percpu *stats; - /* Work struct for refilling if we run low on memory. */ struct delayed_work refill; @@ -1127,7 +1151,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit) struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int len, received = 0, bytes = 0; void *buf; - struct virtnet_stats *stats = this_cpu_ptr(vi->stats); if (!vi->big_packets || vi->mergeable_rx_bufs) { void *ctx; @@ -1150,10 +1173,10 @@ static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit) schedule_delayed_work(&vi->refill, 0); } - u64_stats_update_begin(&stats->rx_syncp); - stats->rx_bytes += bytes; - stats->rx_packets += received; - u64_stats_update_end(&stats->rx_syncp); + u64_stats_update_begin(&rq->stats.syncp); + rq->stats.bytes += bytes; + rq->stats.packets += received; + u64_stats_update_end(&rq->stats.syncp); return received; } @@ -1162,8 +1185,6 @@ static void free_old_xmit_skbs(struct send_queue *sq) { struct sk_buff *skb; unsigned int len; - struct virtnet_info *vi = sq->vq->vdev->priv; - struct virtnet_stats *stats = this_cpu_ptr(vi->stats); unsigned int packets = 0; unsigned int bytes = 0; @@ -1182,10 +1203,10 @@ static void free_old_xmit_skbs(struct send_queue *sq) if (!packets) return; - u64_stats_update_begin(&stats->tx_syncp); - stats->tx_bytes += bytes; - stats->tx_packets += packets; - u64_stats_update_end(&stats->tx_syncp); + u64_stats_update_begin(&sq->stats.syncp); + sq->stats.bytes += bytes; + sq->stats.packets += packets; + u64_stats_update_end(&sq->stats.syncp); } static void virtnet_poll_cleantx(struct receive_queue *rq) @@ -1474,24 +1495,25 @@ static void virtnet_stats(struct net_device *dev, struct rtnl_link_stats64 *tot) { struct virtnet_info *vi = netdev_priv(dev); - int cpu; unsigned int start; + int i; - for_each_possible_cpu(cpu) { - struct virtnet_stats *stats = per_cpu_ptr(vi->stats, cpu); + for (i = 0; i < vi->max_queue_pairs; i++) { u64 tpackets, tbytes, rpackets, rbytes; + struct receive_queue *rq = &vi->rq[i]; + struct send_queue *sq = &vi->sq[i]; do { - start = u64_stats_fetch_begin_irq(&stats->tx_syncp); - tpackets = stats->tx_packets; - tbytes = stats->tx_bytes; - } while (u64_stats_fetch_retry_irq(&stats->tx_syncp, start)); + start = u64_stats_fetch_begin_irq(&sq->stats.syncp); + tpackets = sq->stats.packets; + tbytes = sq->stats.bytes; + } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); do { - start = u64_stats_fetch_begin_irq(&stats->rx_syncp); - rpackets = stats->rx_packets; - rbytes = stats->rx_bytes; - } while (u64_stats_fetch_retry_irq(&stats->rx_syncp, start)); + start = u64_stats_fetch_begin_irq(&rq->stats.syncp); + rpackets = rq->stats.packets; + rbytes = rq->stats.bytes; + } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; @@ -1829,6 +1851,83 @@ static int virtnet_set_channels(struct net_device *dev, return err; } +static void virtnet_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + struct virtnet_info *vi = netdev_priv(dev); + char *p = (char *)data; + unsigned int i, j; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < vi->curr_queue_pairs; i++) { + for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) { + snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_%s", + i, virtnet_rq_stats_desc[j].desc); + p += ETH_GSTRING_LEN; + } + } + + for (i = 0; i < vi->curr_queue_pairs; i++) { + for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) { + snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_%s", + i, virtnet_sq_stats_desc[j].desc); + p += ETH_GSTRING_LEN; + } + } + break; + } +} + +static int virtnet_get_sset_count(struct net_device *dev, int sset) +{ + struct virtnet_info *vi = netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + return vi->curr_queue_pairs * (VIRTNET_RQ_STATS_LEN + + VIRTNET_SQ_STATS_LEN); + default: + return -EOPNOTSUPP; + } +} + +static void virtnet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct virtnet_info *vi = netdev_priv(dev); + unsigned int idx = 0, start, i, j; + const u8 *stats_base; + size_t offset; + + for (i = 0; i < vi->curr_queue_pairs; i++) { + struct receive_queue *rq = &vi->rq[i]; + + stats_base = (u8 *)&rq->stats; + do { + start = u64_stats_fetch_begin_irq(&rq->stats.syncp); + for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) { + offset = virtnet_rq_stats_desc[j].offset; + data[idx + j] = *(u64 *)(stats_base + offset); + } + } while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start)); + idx += VIRTNET_RQ_STATS_LEN; + } + + for (i = 0; i < vi->curr_queue_pairs; i++) { + struct send_queue *sq = &vi->sq[i]; + + stats_base = (u8 *)&sq->stats; + do { + start = u64_stats_fetch_begin_irq(&sq->stats.syncp); + for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) { + offset = virtnet_sq_stats_desc[j].offset; + data[idx + j] = *(u64 *)(stats_base + offset); + } + } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); + idx += VIRTNET_SQ_STATS_LEN; + } +} + static void virtnet_get_channels(struct net_device *dev, struct ethtool_channels *channels) { @@ -1928,6 +2027,9 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .get_drvinfo = virtnet_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = virtnet_get_ringparam, + .get_strings = virtnet_get_strings, + .get_sset_count = virtnet_get_sset_count, + .get_ethtool_stats = virtnet_get_ethtool_stats, .set_channels = virtnet_set_channels, .get_channels = virtnet_get_channels, .get_ts_info = ethtool_op_get_ts_info, @@ -2420,6 +2522,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg)); ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len); sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg)); + + u64_stats_init(&vi->rq[i].stats.syncp); + u64_stats_init(&vi->sq[i].stats.syncp); } return 0; @@ -2544,7 +2649,7 @@ static int virtnet_validate(struct virtio_device *vdev) static int virtnet_probe(struct virtio_device *vdev) { - int i, err; + int i, err = -ENOMEM; struct net_device *dev; struct virtnet_info *vi; u16 max_queue_pairs; @@ -2621,17 +2726,6 @@ static int virtnet_probe(struct virtio_device *vdev) vi->dev = dev; vi->vdev = vdev; vdev->priv = vi; - vi->stats = alloc_percpu(struct virtnet_stats); - err = -ENOMEM; - if (vi->stats == NULL) - goto free; - - for_each_possible_cpu(i) { - struct virtnet_stats *virtnet_stats; - virtnet_stats = per_cpu_ptr(vi->stats, i); - u64_stats_init(&virtnet_stats->tx_syncp); - u64_stats_init(&virtnet_stats->rx_syncp); - } INIT_WORK(&vi->config_work, virtnet_config_changed_work); @@ -2668,7 +2762,7 @@ static int virtnet_probe(struct virtio_device *vdev) */ dev_err(&vdev->dev, "device MTU appears to have changed " "it is now %d < %d", mtu, dev->min_mtu); - goto free_stats; + goto free; } dev->mtu = mtu; @@ -2692,7 +2786,7 @@ static int virtnet_probe(struct virtio_device *vdev) /* Allocate/initialize the rx/tx queues, and invoke find_vqs */ err = init_vqs(vi); if (err) - goto free_stats; + goto free; #ifdef CONFIG_SYSFS if (vi->mergeable_rx_bufs) @@ -2747,8 +2841,6 @@ free_vqs: cancel_delayed_work_sync(&vi->refill); free_receive_page_frags(vi); virtnet_del_vqs(vi); -free_stats: - free_percpu(vi->stats); free: free_netdev(dev); return err; @@ -2781,7 +2873,6 @@ static void virtnet_remove(struct virtio_device *vdev) remove_vq_common(vi); - free_percpu(vi->stats); free_netdev(vi->dev); } diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d1c7029ded7c..cf95290b160c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1616,7 +1616,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, rq->rx_ring[i].basePA); rq->rx_ring[i].base = NULL; } - rq->buf_info[i] = NULL; } if (rq->data_ring.base) { @@ -1638,6 +1637,7 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq, (rq->rx_ring[0].size + rq->rx_ring[1].size); dma_free_coherent(&adapter->pdev->dev, sz, rq->buf_info[0], rq->buf_info_pa); + rq->buf_info[0] = rq->buf_info[1] = NULL; } } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index e54255597fac..1cf22e62e3dd 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -32,6 +32,7 @@ #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <linux/rhashtable.h> #include "mac80211_hwsim.h" #define WARN_QUEUE 100 @@ -490,6 +491,7 @@ static const struct ieee80211_iface_combination hwsim_if_comb_p2p_dev[] = { static spinlock_t hwsim_radio_lock; static LIST_HEAD(hwsim_radios); static struct workqueue_struct *hwsim_wq; +static struct rhashtable hwsim_radios_rht; static int hwsim_radio_idx; static struct platform_driver mac80211_hwsim_driver = { @@ -500,6 +502,7 @@ static struct platform_driver mac80211_hwsim_driver = { struct mac80211_hwsim_data { struct list_head list; + struct rhash_head rht; struct ieee80211_hw *hw; struct device *dev; struct ieee80211_supported_band bands[NUM_NL80211_BANDS]; @@ -574,6 +577,13 @@ struct mac80211_hwsim_data { u64 tx_failed; }; +static const struct rhashtable_params hwsim_rht_params = { + .nelem_hint = 2, + .automatic_shrinking = true, + .key_len = ETH_ALEN, + .key_offset = offsetof(struct mac80211_hwsim_data, addresses[1]), + .head_offset = offsetof(struct mac80211_hwsim_data, rht), +}; struct hwsim_radiotap_hdr { struct ieee80211_radiotap_header hdr; @@ -1009,6 +1019,36 @@ static int hwsim_unicast_netgroup(struct mac80211_hwsim_data *data, return res; } +static inline u16 trans_tx_rate_flags_ieee2hwsim(struct ieee80211_tx_rate *rate) +{ + u16 result = 0; + + if (rate->flags & IEEE80211_TX_RC_USE_RTS_CTS) + result |= MAC80211_HWSIM_TX_RC_USE_RTS_CTS; + if (rate->flags & IEEE80211_TX_RC_USE_CTS_PROTECT) + result |= MAC80211_HWSIM_TX_RC_USE_CTS_PROTECT; + if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE) + result |= MAC80211_HWSIM_TX_RC_USE_SHORT_PREAMBLE; + if (rate->flags & IEEE80211_TX_RC_MCS) + result |= MAC80211_HWSIM_TX_RC_MCS; + if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD) + result |= MAC80211_HWSIM_TX_RC_GREEN_FIELD; + if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) + result |= MAC80211_HWSIM_TX_RC_40_MHZ_WIDTH; + if (rate->flags & IEEE80211_TX_RC_DUP_DATA) + result |= MAC80211_HWSIM_TX_RC_DUP_DATA; + if (rate->flags & IEEE80211_TX_RC_SHORT_GI) + result |= MAC80211_HWSIM_TX_RC_SHORT_GI; + if (rate->flags & IEEE80211_TX_RC_VHT_MCS) + result |= MAC80211_HWSIM_TX_RC_VHT_MCS; + if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) + result |= MAC80211_HWSIM_TX_RC_80_MHZ_WIDTH; + if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) + result |= MAC80211_HWSIM_TX_RC_160_MHZ_WIDTH; + + return result; +} + static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, struct sk_buff *my_skb, int dst_portid) @@ -1021,6 +1061,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, unsigned int hwsim_flags = 0; int i; struct hwsim_tx_rate tx_attempts[IEEE80211_TX_MAX_RATES]; + struct hwsim_tx_rate_flag tx_attempts_flags[IEEE80211_TX_MAX_RATES]; uintptr_t cookie; if (data->ps != PS_DISABLED) @@ -1072,7 +1113,11 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { tx_attempts[i].idx = info->status.rates[i].idx; + tx_attempts_flags[i].idx = info->status.rates[i].idx; tx_attempts[i].count = info->status.rates[i].count; + tx_attempts_flags[i].flags = + trans_tx_rate_flags_ieee2hwsim( + &info->status.rates[i]); } if (nla_put(skb, HWSIM_ATTR_TX_INFO, @@ -1080,6 +1125,11 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, tx_attempts)) goto nla_put_failure; + if (nla_put(skb, HWSIM_ATTR_TX_INFO_FLAGS, + sizeof(struct hwsim_tx_rate_flag) * IEEE80211_TX_MAX_RATES, + tx_attempts_flags)) + goto nla_put_failure; + /* We create a cookie to identify this skb */ data->pending_cookie++; cookie = data->pending_cookie; @@ -2732,6 +2782,15 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); spin_lock_bh(&hwsim_radio_lock); + err = rhashtable_insert_fast(&hwsim_radios_rht, &data->rht, + hwsim_rht_params); + if (err < 0) { + pr_debug("mac80211_hwsim: radio index %d already present\n", + idx); + spin_unlock_bh(&hwsim_radio_lock); + goto failed_final_insert; + } + list_add_tail(&data->list, &hwsim_radios); spin_unlock_bh(&hwsim_radio_lock); @@ -2740,6 +2799,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, return idx; +failed_final_insert: + debugfs_remove_recursive(data->debugfs); + ieee80211_unregister_hw(data->hw); failed_hw: device_release_driver(data->dev); failed_bind: @@ -2875,22 +2937,9 @@ static void hwsim_mon_setup(struct net_device *dev) static struct mac80211_hwsim_data *get_hwsim_data_ref_from_addr(const u8 *addr) { - struct mac80211_hwsim_data *data; - bool _found = false; - - spin_lock_bh(&hwsim_radio_lock); - list_for_each_entry(data, &hwsim_radios, list) { - if (memcmp(data->addresses[1].addr, addr, ETH_ALEN) == 0) { - _found = true; - break; - } - } - spin_unlock_bh(&hwsim_radio_lock); - - if (!_found) - return NULL; - - return data; + return rhashtable_lookup_fast(&hwsim_radios_rht, + addr, + hwsim_rht_params); } static void hwsim_register_wmediumd(struct net *net, u32 portid) @@ -2975,7 +3024,6 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2, for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { txi->status.rates[i].idx = tx_attempts[i].idx; txi->status.rates[i].count = tx_attempts[i].count; - /*txi->status.rates[i].flags = 0;*/ } txi->status.ack_signal = nla_get_u32(info->attrs[HWSIM_ATTR_SIGNAL]); @@ -3155,8 +3203,10 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]) { u32 idx = nla_get_u32(info->attrs[HWSIM_ATTR_REG_CUSTOM_REG]); - if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom)) + if (idx >= ARRAY_SIZE(hwsim_world_regdom_custom)) { + kfree(hwname); return -EINVAL; + } param.regd = hwsim_world_regdom_custom[idx]; } @@ -3197,6 +3247,8 @@ static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) continue; list_del(&data->list); + rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, + hwsim_rht_params); spin_unlock_bh(&hwsim_radio_lock); mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), info); @@ -3352,6 +3404,8 @@ static void remove_user_radios(u32 portid) list_for_each_entry_safe(entry, tmp, &hwsim_radios, list) { if (entry->destroy_on_close && entry->portid == portid) { list_del(&entry->list); + rhashtable_remove_fast(&hwsim_radios_rht, &entry->rht, + hwsim_rht_params); INIT_WORK(&entry->destroy_work, destroy_radio); queue_work(hwsim_wq, &entry->destroy_work); } @@ -3427,6 +3481,8 @@ static void __net_exit hwsim_exit_net(struct net *net) continue; list_del(&data->list); + rhashtable_remove_fast(&hwsim_radios_rht, &data->rht, + hwsim_rht_params); INIT_WORK(&data->destroy_work, destroy_radio); queue_work(hwsim_wq, &data->destroy_work); } @@ -3463,6 +3519,7 @@ static int __init init_mac80211_hwsim(void) hwsim_wq = alloc_workqueue("hwsim_wq",WQ_MEM_RECLAIM,0); if (!hwsim_wq) return -ENOMEM; + rhashtable_init(&hwsim_radios_rht, &hwsim_rht_params); err = register_pernet_device(&hwsim_net_ops); if (err) @@ -3604,6 +3661,7 @@ static void __exit exit_mac80211_hwsim(void) mac80211_hwsim_free(); flush_workqueue(hwsim_wq); + rhashtable_destroy(&hwsim_radios_rht); unregister_netdev(hwsim_mon); platform_driver_unregister(&mac80211_hwsim_driver); unregister_pernet_device(&hwsim_net_ops); diff --git a/drivers/net/wireless/mac80211_hwsim.h b/drivers/net/wireless/mac80211_hwsim.h index 3f5eda591dba..a96a79c1eff5 100644 --- a/drivers/net/wireless/mac80211_hwsim.h +++ b/drivers/net/wireless/mac80211_hwsim.h @@ -64,7 +64,8 @@ enum hwsim_tx_control_flags { * @HWSIM_CMD_TX_INFO_FRAME: Transmission info report from user space to * kernel, uses: * %HWSIM_ATTR_ADDR_TRANSMITTER, %HWSIM_ATTR_FLAGS, - * %HWSIM_ATTR_TX_INFO, %HWSIM_ATTR_SIGNAL, %HWSIM_ATTR_COOKIE + * %HWSIM_ATTR_TX_INFO, %WSIM_ATTR_TX_INFO_FLAGS, + * %HWSIM_ATTR_SIGNAL, %HWSIM_ATTR_COOKIE * @HWSIM_CMD_NEW_RADIO: create a new radio with the given parameters, * returns the radio ID (>= 0) or negative on errors, if successful * then multicast the result @@ -123,6 +124,8 @@ enum { * @HWSIM_ATTR_RADIO_NAME: Name of radio, e.g. phy666 * @HWSIM_ATTR_NO_VIF: Do not create vif (wlanX) when creating radio. * @HWSIM_ATTR_FREQ: Frequency at which packet is transmitted or received. + * @HWSIM_ATTR_TX_INFO_FLAGS: additional flags for corresponding + * rates of %HWSIM_ATTR_TX_INFO * @__HWSIM_ATTR_MAX: enum limit */ @@ -149,6 +152,7 @@ enum { HWSIM_ATTR_NO_VIF, HWSIM_ATTR_FREQ, HWSIM_ATTR_PAD, + HWSIM_ATTR_TX_INFO_FLAGS, __HWSIM_ATTR_MAX, }; #define HWSIM_ATTR_MAX (__HWSIM_ATTR_MAX - 1) @@ -171,4 +175,66 @@ struct hwsim_tx_rate { u8 count; } __packed; +/** + * enum hwsim_tx_rate_flags - per-rate flags set by the rate control algorithm. + * Inspired by structure mac80211_rate_control_flags. New flags may be + * appended, but old flags not deleted, to keep compatibility for + * userspace. + * + * These flags are set by the Rate control algorithm for each rate during tx, + * in the @flags member of struct ieee80211_tx_rate. + * + * @MAC80211_HWSIM_TX_RC_USE_RTS_CTS: Use RTS/CTS exchange for this rate. + * @MAC80211_HWSIM_TX_RC_USE_CTS_PROTECT: CTS-to-self protection is required. + * This is set if the current BSS requires ERP protection. + * @MAC80211_HWSIM_TX_RC_USE_SHORT_PREAMBLE: Use short preamble. + * @MAC80211_HWSIM_TX_RC_MCS: HT rate. + * @MAC80211_HWSIM_TX_RC_VHT_MCS: VHT MCS rate, in this case the idx field is + * split into a higher 4 bits (Nss) and lower 4 bits (MCS number) + * @MAC80211_HWSIM_TX_RC_GREEN_FIELD: Indicates whether this rate should be used + * in Greenfield mode. + * @MAC80211_HWSIM_TX_RC_40_MHZ_WIDTH: Indicates if the Channel Width should be + * 40 MHz. + * @MAC80211_HWSIM_TX_RC_80_MHZ_WIDTH: Indicates 80 MHz transmission + * @MAC80211_HWSIM_TX_RC_160_MHZ_WIDTH: Indicates 160 MHz transmission + * (80+80 isn't supported yet) + * @MAC80211_HWSIM_TX_RC_DUP_DATA: The frame should be transmitted on both of + * the adjacent 20 MHz channels, if the current channel type is + * NL80211_CHAN_HT40MINUS or NL80211_CHAN_HT40PLUS. + * @MAC80211_HWSIM_TX_RC_SHORT_GI: Short Guard interval should be used for this + * rate. + */ +enum hwsim_tx_rate_flags { + MAC80211_HWSIM_TX_RC_USE_RTS_CTS = BIT(0), + MAC80211_HWSIM_TX_RC_USE_CTS_PROTECT = BIT(1), + MAC80211_HWSIM_TX_RC_USE_SHORT_PREAMBLE = BIT(2), + + /* rate index is an HT/VHT MCS instead of an index */ + MAC80211_HWSIM_TX_RC_MCS = BIT(3), + MAC80211_HWSIM_TX_RC_GREEN_FIELD = BIT(4), + MAC80211_HWSIM_TX_RC_40_MHZ_WIDTH = BIT(5), + MAC80211_HWSIM_TX_RC_DUP_DATA = BIT(6), + MAC80211_HWSIM_TX_RC_SHORT_GI = BIT(7), + MAC80211_HWSIM_TX_RC_VHT_MCS = BIT(8), + MAC80211_HWSIM_TX_RC_80_MHZ_WIDTH = BIT(9), + MAC80211_HWSIM_TX_RC_160_MHZ_WIDTH = BIT(10), +}; + +/** + * struct hwsim_tx_rate - rate selection/status + * + * @idx: rate index to attempt to send with + * @count: number of tries in this rate before going to the next rate + * + * A value of -1 for @idx indicates an invalid rate and, if used + * in an array of retry rates, that no more rates should be tried. + * + * When used for transmit status reporting, the driver should + * always report the rate and number of retries used. + * + */ +struct hwsim_tx_rate_flag { + s8 idx; + u16 flags; +} __packed; #endif /* __MAC80211_HWSIM_H */ diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c index 58476b728c57..c9406852c3e9 100644 --- a/drivers/scsi/libsas/sas_scsi_host.c +++ b/drivers/scsi/libsas/sas_scsi_host.c @@ -486,15 +486,28 @@ static int sas_queue_reset(struct domain_device *dev, int reset_type, int sas_eh_abort_handler(struct scsi_cmnd *cmd) { - int res; + int res = TMF_RESP_FUNC_FAILED; struct sas_task *task = TO_SAS_TASK(cmd); struct Scsi_Host *host = cmd->device->host; + struct domain_device *dev = cmd_to_domain_dev(cmd); struct sas_internal *i = to_sas_internal(host->transportt); + unsigned long flags; if (!i->dft->lldd_abort_task) return FAILED; - res = i->dft->lldd_abort_task(task); + spin_lock_irqsave(host->host_lock, flags); + /* We cannot do async aborts for SATA devices */ + if (dev_is_sata(dev) && !host->host_eh_scheduled) { + spin_unlock_irqrestore(host->host_lock, flags); + return FAILED; + } + spin_unlock_irqrestore(host->host_lock, flags); + + if (task) + res = i->dft->lldd_abort_task(task); + else + SAS_DPRINTK("no task to abort\n"); if (res == TMF_RESP_FUNC_SUCC || res == TMF_RESP_FUNC_COMPLETE) return SUCCESS; diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 1bef39828ca7..3c573a8caa80 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -225,6 +225,18 @@ void serdev_device_set_flow_control(struct serdev_device *serdev, bool enable) } EXPORT_SYMBOL_GPL(serdev_device_set_flow_control); +int serdev_device_set_parity(struct serdev_device *serdev, + enum serdev_parity parity) +{ + struct serdev_controller *ctrl = serdev->ctrl; + + if (!ctrl || !ctrl->ops->set_parity) + return -ENOTSUPP; + + return ctrl->ops->set_parity(ctrl, parity); +} +EXPORT_SYMBOL_GPL(serdev_device_set_parity); + void serdev_device_wait_until_sent(struct serdev_device *serdev, long timeout) { struct serdev_controller *ctrl = serdev->ctrl; diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c index 247788a16f0b..1bdf2959ac5c 100644 --- a/drivers/tty/serdev/serdev-ttyport.c +++ b/drivers/tty/serdev/serdev-ttyport.c @@ -190,6 +190,29 @@ static void ttyport_set_flow_control(struct serdev_controller *ctrl, bool enable tty_set_termios(tty, &ktermios); } +static int ttyport_set_parity(struct serdev_controller *ctrl, + enum serdev_parity parity) +{ + struct serport *serport = serdev_controller_get_drvdata(ctrl); + struct tty_struct *tty = serport->tty; + struct ktermios ktermios = tty->termios; + + ktermios.c_cflag &= ~(PARENB | PARODD | CMSPAR); + if (parity != SERDEV_PARITY_NONE) { + ktermios.c_cflag |= PARENB; + if (parity == SERDEV_PARITY_ODD) + ktermios.c_cflag |= PARODD; + } + + tty_set_termios(tty, &ktermios); + + if ((tty->termios.c_cflag & (PARENB | PARODD | CMSPAR)) != + (ktermios.c_cflag & (PARENB | PARODD | CMSPAR))) + return -EINVAL; + + return 0; +} + static void ttyport_wait_until_sent(struct serdev_controller *ctrl, long timeout) { struct serport *serport = serdev_controller_get_drvdata(ctrl); @@ -227,6 +250,7 @@ static const struct serdev_controller_ops ctrl_ops = { .open = ttyport_open, .close = ttyport_close, .set_flow_control = ttyport_set_flow_control, + .set_parity = ttyport_set_parity, .set_baudrate = ttyport_set_baudrate, .wait_until_sent = ttyport_wait_until_sent, .get_tiocm = ttyport_get_tiocm, diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 33ac2b186b85..5727b186b3ca 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -904,7 +904,7 @@ static void vhost_dev_lock_vqs(struct vhost_dev *d) { int i = 0; for (i = 0; i < d->nvqs; ++i) - mutex_lock(&d->vqs[i]->mutex); + mutex_lock_nested(&d->vqs[i]->mutex, i); } static void vhost_dev_unlock_vqs(struct vhost_dev *d) @@ -1015,6 +1015,10 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev, vhost_iotlb_notify_vq(dev, msg); break; case VHOST_IOTLB_INVALIDATE: + if (!dev->iotlb) { + ret = -EFAULT; + break; + } vhost_vq_meta_reset(dev); vhost_del_umem_range(dev->iotlb, msg->iova, msg->iova + msg->size - 1); |