No conflicts.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Default : 0 (for compatibility reasons)
+txrehash
+--------
+
+Controls default hash rethink behaviour on listening socket when SO_TXREHASH
+option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt).
+
+If set to 1 (default), hash rethink is performed on listening socket.
+If set to 0, hash rethink is not performed.
+
2. /proc/sys/net/unix - Parameters for Unix domain sockets
----------------------------------------------------------
In libbpf, the map can be defined with extra annotation like below:
::
- struct bpf_map_def SEC("maps") btf_map = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(struct ipv_counts),
- .max_entries = 4,
- };
- BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
+ struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, int);
+ __type(value, struct ipv_counts);
+ __uint(max_entries, 4);
+ } btf_map SEC(".maps");
-Here, the parameters for macro BPF_ANNOTATE_KV_PAIR are map name, key and
-value types for the map. During ELF parsing, libbpf is able to extract
-key/value type_id's and assign them to BPF_MAP_CREATE attributes
-automatically.
+During ELF parsing, libbpf is able to extract key/value type_id's and assign
+them to BPF_MAP_CREATE attributes automatically.
.. _BPF_Prog_Load:
___A b1:4;
enum A b2:4;
};
- struct bpf_map_def SEC("maps") tmpmap = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(struct tmp_t),
- .max_entries = 1,
- };
- BPF_ANNOTATE_KV_PAIR(tmpmap, int, struct tmp_t);
+ struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, int);
+ __type(value, struct tmp_t);
+ __uint(max_entries, 1);
+ } tmpmap SEC(".maps");
bpftool is able to pretty print like below:
::
phy-handle: true
+ phys:
+ maxItems: 1
+
+ phy-names:
+ const: sgmii-phy
+ description:
+ Required with ZynqMP SoC when in SGMII mode.
+ Should reference PS-GTR generic PHY device for this controller
+ instance. See ZynqMP example.
+
+ resets:
+ maxItems: 1
+ description:
+ Recommended with ZynqMP, specify reset control for this
+ controller instance with zynqmp-reset driver.
+
+ reset-names:
+ maxItems: 1
+
fixed-link: true
iommus:
reset-gpios = <&pioE 6 1>;
};
};
+
+ - |
+ #include <dt-bindings/clock/xlnx-zynqmp-clk.h>
+ #include <dt-bindings/power/xlnx-zynqmp-power.h>
+ #include <dt-bindings/reset/xlnx-zynqmp-resets.h>
+ #include <dt-bindings/phy/phy.h>
+
+ bus {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ gem1: ethernet@ff0c0000 {
+ compatible = "cdns,zynqmp-gem", "cdns,gem";
+ interrupt-parent = <&gic>;
+ interrupts = <0 59 4>, <0 59 4>;
+ reg = <0x0 0xff0c0000 0x0 0x1000>;
+ clocks = <&zynqmp_clk LPD_LSBUS>, <&zynqmp_clk GEM1_REF>,
+ <&zynqmp_clk GEM1_TX>, <&zynqmp_clk GEM1_RX>,
+ <&zynqmp_clk GEM_TSU>;
+ clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ #stream-id-cells = <1>;
+ iommus = <&smmu 0x875>;
+ power-domains = <&zynqmp_firmware PD_ETH_1>;
+ resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>;
+ reset-names = "gem1_rst";
+ status = "okay";
+ phy-mode = "sgmii";
+ phy-names = "sgmii-phy";
+ phys = <&psgtr 1 PHY_TYPE_SGMII 1 1>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ pause;
+ };
+ };
+ };
description:
Set if the output SYNCLKO frequency should be set to 125MHz instead of 25MHz.
+ microchip,synclko-disable:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Set if the output SYNCLKO clock should be disabled. Do not mix with
+ microchip,synclko-125.
+
required:
- compatible
- reg
Value type: <prop-encoded-array>
Definition: A standard property.
-- bus-frequency
+- clocks
+ Usage: optional
+ Value type: <phandle>
+ Definition: A reference to the input clock of the controller
+ from which the MDC frequency is derived.
+
+- clock-frequency
Usage: optional
Value type: <u32>
- Definition: Specifies the external MDIO bus clock speed to
- be used, if different from the standard 2.5 MHz.
- This may be due to the standard speed being unsupported (e.g.
- due to a hardware problem), or to advertise that all relevant
- components in the system support a faster speed.
+ Definition: Specifies the external MDC frequency, in Hertz, to
+ be used. Requires that the input clock is specified in the
+ "clocks" property. See also: mdio.yaml.
+
+- suppress-preamble
+ Usage: optional
+ Value type: <boolean>
+ Definition: Disable generation of preamble bits. See also:
+ mdio.yaml.
- interrupts
Usage: required for external MDIO
- description: register based extraction
- description: frame dma based extraction
- description: analyzer interrupt
+ - description: ptp interrupt
interrupt-names:
minItems: 1
- const: xtr
- const: fdma
- const: ana
+ - const: ptp
resets:
items:
``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring
``ETHTOOL_A_RINGS_TX`` u32 size of TX ring
``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring
+ ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split
==================================== ====== ===========================
+``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with
+page-flipping TCP zero-copy receive (``getsockopt(TCP_ZEROCOPY_RECEIVE)``).
+If enabled the device is configured to place frame headers and data into
+separate buffers. The device configuration must make it possible to receive
+full memory pages of data, for example because MTU is high enough or through
+HW-GRO.
+
RINGS_SET
=========
M: Linus Walleij <linus.walleij@linaro.org>
S: Maintained
F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt
-F: drivers/net/dsa/realtek-smi*
-F: drivers/net/dsa/rtl83*
+F: drivers/net/dsa/realtek/*
REALTEK WIRELESS DRIVER (rtlwifi family)
M: Ping-Ke Shih <pkshih@realtek.com>
#define SO_RESERVE_MEM 73
+#define SO_TXREHASH 74
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64
#stream-id-cells = <1>;
iommus = <&smmu 0x874>;
power-domains = <&zynqmp_firmware PD_ETH_0>;
+ resets = <&zynqmp_reset ZYNQMP_RESET_GEM0>;
+ reset-names = "gem0_rst";
};
gem1: ethernet@ff0c0000 {
#stream-id-cells = <1>;
iommus = <&smmu 0x875>;
power-domains = <&zynqmp_firmware PD_ETH_1>;
+ resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>;
+ reset-names = "gem1_rst";
};
gem2: ethernet@ff0d0000 {
#stream-id-cells = <1>;
iommus = <&smmu 0x876>;
power-domains = <&zynqmp_firmware PD_ETH_2>;
+ resets = <&zynqmp_reset ZYNQMP_RESET_GEM2>;
+ reset-names = "gem2_rst";
};
gem3: ethernet@ff0e0000 {
#stream-id-cells = <1>;
iommus = <&smmu 0x877>;
power-domains = <&zynqmp_firmware PD_ETH_3>;
+ resets = <&zynqmp_reset ZYNQMP_RESET_GEM3>;
+ reset-names = "gem3_rst";
};
gpio: gpio@ff0a0000 {
#define SO_RESERVE_MEM 73
+#define SO_TXREHASH 74
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64
#define SO_RESERVE_MEM 0x4047
+#define SO_TXREHASH 0x4048
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64
#define SO_RESERVE_MEM 0x0052
+#define SO_TXREHASH 0x0053
+
#if !defined(__KERNEL__)
/* Apply the device specific HCI quirks
*
- * WBS for SdP - SdP and Stp have a same hw_varaint but
- * different fw_variant
+ * WBS for SdP - For the Legacy ROM products, only SdP
+ * supports the WBS. But the version information is not
+ * enough to use here because the StP2 and SdP have same
+ * hw_variant and fw_variant. So, this flag is set by
+ * the transport driver (btusb) based on the HW info
+ * (idProduct)
*/
- if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22)
+ if (!btintel_test_flag(hdev,
+ INTEL_ROM_LEGACY_NO_WBS_SUPPORT))
set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
&hdev->quirks);
INTEL_BROKEN_INITIAL_NCMD,
INTEL_BROKEN_SHUTDOWN_LED,
INTEL_ROM_LEGACY,
+ INTEL_ROM_LEGACY_NO_WBS_SUPPORT,
__INTEL_NUM_FLAGS,
};
-/**
+/*
* Marvell Bluetooth driver: debugfs related functions
*
* Copyright (C) 2009, Marvell International Ltd.
-/**
+/*
* Marvell BT-over-SDIO driver: SDIO interface related functions.
*
* Copyright (C) 2009, Marvell International Ltd.
#define HCI_WMT_MAX_EVENT_SIZE 64
+#define BTMTK_WMT_REG_WRITE 0x1
#define BTMTK_WMT_REG_READ 0x2
+#define MT7921_PINMUX_0 0x70005050
+#define MT7921_PINMUX_1 0x70005054
+
enum {
BTMTK_WMT_PATCH_DWNLD = 0x1,
BTMTK_WMT_TEST = 0x2,
u8 time_compensation;
} __packed;
+struct btmtk_wakeon {
+ u8 mode;
+ u8 gpo;
+ u8 active_high;
+ __le16 enable_delay;
+ __le16 wakeup_delay;
+} __packed;
+
+struct btmtk_sco {
+ u8 clock_config;
+ u8 transmit_format_config;
+ u8 channel_format_config;
+ u8 channel_select_config;
+} __packed;
+
+struct reg_read_cmd {
+ u8 type;
+ u8 rsv;
+ u8 num;
+ __le32 addr;
+} __packed;
+
+struct reg_write_cmd {
+ u8 type;
+ u8 rsv;
+ u8 num;
+ __le32 addr;
+ __le32 data;
+ __le32 mask;
+} __packed;
+
struct btmtk_hci_wmt_params {
u8 op;
u8 flag;
#define VERSION "0.1"
-#define MTKBTSDIO_AUTOSUSPEND_DELAY 8000
+#define MTKBTSDIO_AUTOSUSPEND_DELAY 1000
-static bool enable_autosuspend;
+static bool enable_autosuspend = true;
struct btmtksdio_data {
const char *fwname;
u16 chipid;
+ bool lp_mbox_supported;
};
static const struct btmtksdio_data mt7663_data = {
.fwname = FIRMWARE_MT7663,
.chipid = 0x7663,
+ .lp_mbox_supported = false,
};
static const struct btmtksdio_data mt7668_data = {
.fwname = FIRMWARE_MT7668,
.chipid = 0x7668,
+ .lp_mbox_supported = false,
};
static const struct btmtksdio_data mt7921_data = {
.fwname = FIRMWARE_MT7961,
.chipid = 0x7921,
+ .lp_mbox_supported = true,
};
static const struct sdio_device_id btmtksdio_table[] = {
#define RX_DONE_INT BIT(1)
#define TX_EMPTY BIT(2)
#define TX_FIFO_OVERFLOW BIT(8)
+#define FW_MAILBOX_INT BIT(15)
+#define INT_MASK GENMASK(15, 0)
#define RX_PKT_LEN GENMASK(31, 16)
+#define MTK_REG_CSICR 0xc0
+#define CSICR_CLR_MBOX_ACK BIT(0)
+#define MTK_REG_PH2DSM0R 0xc4
+#define PH2DSM0R_DRIVER_OWN BIT(0)
+#define MTK_REG_PD2HRM0R 0xdc
+#define PD2HRM0R_DRV_OWN BIT(0)
+
#define MTK_REG_CTDR 0x18
#define MTK_REG_CRDR 0x1c
#define BTMTKSDIO_TX_WAIT_VND_EVT 1
#define BTMTKSDIO_HW_TX_READY 2
#define BTMTKSDIO_FUNC_ENABLED 3
+#define BTMTKSDIO_PATCH_ENABLED 4
struct mtkbtsdio_hdr {
__le16 len;
return sdio_readl(bdev->func, MTK_REG_CHLPCR, NULL);
}
+static u32 btmtksdio_drv_own_query_79xx(struct btmtksdio_dev *bdev)
+{
+ return sdio_readl(bdev->func, MTK_REG_PD2HRM0R, NULL);
+}
+
+static int btmtksdio_fw_pmctrl(struct btmtksdio_dev *bdev)
+{
+ u32 status;
+ int err;
+
+ sdio_claim_host(bdev->func);
+
+ if (bdev->data->lp_mbox_supported &&
+ test_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state)) {
+ sdio_writel(bdev->func, CSICR_CLR_MBOX_ACK, MTK_REG_CSICR,
+ &err);
+ err = readx_poll_timeout(btmtksdio_drv_own_query_79xx, bdev,
+ status, !(status & PD2HRM0R_DRV_OWN),
+ 2000, 1000000);
+ if (err < 0) {
+ bt_dev_err(bdev->hdev, "mailbox ACK not cleared");
+ goto out;
+ }
+ }
+
+ /* Return ownership to the device */
+ sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, &err);
+ if (err < 0)
+ goto out;
+
+ err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status,
+ !(status & C_COM_DRV_OWN), 2000, 1000000);
+
+out:
+ sdio_release_host(bdev->func);
+
+ if (err < 0)
+ bt_dev_err(bdev->hdev, "Cannot return ownership to device");
+
+ return err;
+}
+
+static int btmtksdio_drv_pmctrl(struct btmtksdio_dev *bdev)
+{
+ u32 status;
+ int err;
+
+ sdio_claim_host(bdev->func);
+
+ /* Get ownership from the device */
+ sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err);
+ if (err < 0)
+ goto out;
+
+ err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status,
+ status & C_COM_DRV_OWN, 2000, 1000000);
+
+ if (!err && bdev->data->lp_mbox_supported &&
+ test_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state))
+ err = readx_poll_timeout(btmtksdio_drv_own_query_79xx, bdev,
+ status, status & PD2HRM0R_DRV_OWN,
+ 2000, 1000000);
+
+out:
+ sdio_release_host(bdev->func);
+
+ if (err < 0)
+ bt_dev_err(bdev->hdev, "Cannot get ownership from device");
+
+ return err;
+}
+
static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
{
struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
* FIFO.
*/
sdio_writel(bdev->func, int_status, MTK_REG_CHISR, NULL);
+ int_status &= INT_MASK;
+
+ if ((int_status & FW_MAILBOX_INT) &&
+ bdev->data->chipid == 0x7921) {
+ sdio_writel(bdev->func, PH2DSM0R_DRIVER_OWN,
+ MTK_REG_PH2DSM0R, 0);
+ }
if (int_status & FW_OWN_BACK_INT)
bt_dev_dbg(bdev->hdev, "Get fw own back");
static int btmtksdio_open(struct hci_dev *hdev)
{
struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
- u32 status, val;
+ u32 val;
int err;
sdio_claim_host(bdev->func);
set_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state);
- /* Get ownership from the device */
- sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err);
+ err = btmtksdio_drv_pmctrl(bdev);
if (err < 0)
goto err_disable_func;
- err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status,
- status & C_COM_DRV_OWN, 2000, 1000000);
- if (err < 0) {
- bt_dev_err(bdev->hdev, "Cannot get ownership from device");
- goto err_disable_func;
- }
-
/* Disable interrupt & mask out all interrupt sources */
sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, &err);
if (err < 0)
static int btmtksdio_close(struct hci_dev *hdev)
{
struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
- u32 status;
- int err;
sdio_claim_host(bdev->func);
cancel_work_sync(&bdev->txrx_work);
- /* Return ownership to the device */
- sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, NULL);
-
- err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status,
- !(status & C_COM_DRV_OWN), 2000, 1000000);
- if (err < 0)
- bt_dev_err(bdev->hdev, "Cannot return ownership to device");
+ btmtksdio_fw_pmctrl(bdev);
clear_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state);
sdio_disable_func(bdev->func);
static int mt76xx_setup(struct hci_dev *hdev, const char *fwname)
{
+ struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
struct btmtk_hci_wmt_params wmt_params;
struct btmtk_tci_sleep tci_sleep;
struct sk_buff *skb;
return err;
}
+ set_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state);
+
ignore_func_on:
/* Apply the low power environment setup */
tci_sleep.mode = 0x5;
static int mt79xx_setup(struct hci_dev *hdev, const char *fwname)
{
+ struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
struct btmtk_hci_wmt_params wmt_params;
u8 param = 0x1;
int err;
hci_set_msft_opcode(hdev, 0xFD30);
hci_set_aosp_capable(hdev);
+ set_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state);
return err;
}
-static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val)
+static int btmtksdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val)
{
struct btmtk_hci_wmt_params wmt_params;
- struct reg_read_cmd {
- u8 type;
- u8 rsv;
- u8 num;
- __le32 addr;
- } __packed reg_read = {
+ struct reg_read_cmd reg_read = {
.type = 1,
.num = 1,
};
err = mtk_hci_wmt_sync(hdev, &wmt_params);
if (err < 0) {
- bt_dev_err(hdev, "Failed to read reg(%d)", err);
+ bt_dev_err(hdev, "Failed to read reg (%d)", err);
return err;
}
return err;
}
+static int btmtksdio_mtk_reg_write(struct hci_dev *hdev, u32 reg, u32 val, u32 mask)
+{
+ struct btmtk_hci_wmt_params wmt_params;
+ const struct reg_write_cmd reg_write = {
+ .type = 1,
+ .num = 1,
+ .addr = cpu_to_le32(reg),
+ .data = cpu_to_le32(val),
+ .mask = cpu_to_le32(mask),
+ };
+ int err, status;
+
+ wmt_params.op = BTMTK_WMT_REGISTER;
+ wmt_params.flag = BTMTK_WMT_REG_WRITE;
+ wmt_params.dlen = sizeof(reg_write);
+ wmt_params.data = ®_write;
+ wmt_params.status = &status;
+
+ err = mtk_hci_wmt_sync(hdev, &wmt_params);
+ if (err < 0)
+ bt_dev_err(hdev, "Failed to write reg (%d)", err);
+
+ return err;
+}
+
+static int btmtksdio_sco_setting(struct hci_dev *hdev)
+{
+ const struct btmtk_sco sco_setting = {
+ .clock_config = 0x49,
+ .channel_format_config = 0x80,
+ };
+ struct sk_buff *skb;
+ u32 val;
+ int err;
+
+ /* Enable SCO over I2S/PCM for MediaTek chipset */
+ skb = __hci_cmd_sync(hdev, 0xfc72, sizeof(sco_setting),
+ &sco_setting, HCI_CMD_TIMEOUT);
+ if (IS_ERR(skb))
+ return PTR_ERR(skb);
+
+ kfree_skb(skb);
+
+ err = btmtksdio_mtk_reg_read(hdev, MT7921_PINMUX_0, &val);
+ if (err < 0)
+ return err;
+
+ val |= 0x11000000;
+ err = btmtksdio_mtk_reg_write(hdev, MT7921_PINMUX_0, val, ~0);
+ if (err < 0)
+ return err;
+
+ err = btmtksdio_mtk_reg_read(hdev, MT7921_PINMUX_1, &val);
+ if (err < 0)
+ return err;
+
+ val |= 0x00000101;
+ return btmtksdio_mtk_reg_write(hdev, MT7921_PINMUX_1, val, ~0);
+}
+
static int btmtksdio_setup(struct hci_dev *hdev)
{
struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
switch (bdev->data->chipid) {
case 0x7921:
- err = btsdio_mtk_reg_read(hdev, 0x70010200, &dev_id);
+ err = btmtksdio_mtk_reg_read(hdev, 0x70010200, &dev_id);
if (err < 0) {
bt_dev_err(hdev, "Failed to get device id (%d)", err);
return err;
}
- err = btsdio_mtk_reg_read(hdev, 0x80021004, &fw_version);
+ err = btmtksdio_mtk_reg_read(hdev, 0x80021004, &fw_version);
if (err < 0) {
bt_dev_err(hdev, "Failed to get fw version (%d)", err);
return err;
err = mt79xx_setup(hdev, fwname);
if (err < 0)
return err;
+
+ err = btmtksdio_fw_pmctrl(bdev);
+ if (err < 0)
+ return err;
+
+ err = btmtksdio_drv_pmctrl(bdev);
+ if (err < 0)
+ return err;
+
+ /* Enable SCO over I2S/PCM */
+ err = btmtksdio_sco_setting(hdev);
+ if (err < 0) {
+ bt_dev_err(hdev, "Failed to enable SCO setting (%d)", err);
+ return err;
+ }
+
break;
case 0x7663:
case 0x7668:
return 0;
}
+static bool btmtksdio_sdio_wakeup(struct hci_dev *hdev)
+{
+ struct btmtksdio_dev *bdev = hci_get_drvdata(hdev);
+ bool may_wakeup = device_may_wakeup(bdev->dev);
+ const struct btmtk_wakeon bt_awake = {
+ .mode = 0x1,
+ .gpo = 0,
+ .active_high = 0x1,
+ .enable_delay = cpu_to_le16(0xc80),
+ .wakeup_delay = cpu_to_le16(0x20),
+ };
+
+ if (may_wakeup && bdev->data->chipid == 0x7921) {
+ struct sk_buff *skb;
+
+ skb = __hci_cmd_sync(hdev, 0xfc27, sizeof(bt_awake),
+ &bt_awake, HCI_CMD_TIMEOUT);
+ if (IS_ERR(skb))
+ may_wakeup = false;
+
+ kfree_skb(skb);
+ }
+
+ return may_wakeup;
+}
+
static int btmtksdio_probe(struct sdio_func *func,
const struct sdio_device_id *id)
{
hdev->setup = btmtksdio_setup;
hdev->shutdown = btmtksdio_shutdown;
hdev->send = btmtksdio_send_frame;
+ hdev->wakeup = btmtksdio_sdio_wakeup;
hdev->set_bdaddr = btmtk_set_bdaddr;
SET_HCIDEV_DEV(hdev, &func->dev);
*/
pm_runtime_put_noidle(bdev->dev);
- return 0;
+ err = device_init_wakeup(bdev->dev, true);
+ if (err)
+ bt_dev_err(hdev, "failed to initialize device wakeup");
+
+ return err;
}
static void btmtksdio_remove(struct sdio_func *func)
{
struct sdio_func *func = dev_to_sdio_func(dev);
struct btmtksdio_dev *bdev;
- u32 status;
int err;
bdev = sdio_get_drvdata(func);
sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
- sdio_claim_host(bdev->func);
+ err = btmtksdio_fw_pmctrl(bdev);
- sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, &err);
- if (err < 0)
- goto out;
-
- err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status,
- !(status & C_COM_DRV_OWN), 2000, 1000000);
-out:
- bt_dev_info(bdev->hdev, "status (%d) return ownership to device", err);
-
- sdio_release_host(bdev->func);
+ bt_dev_dbg(bdev->hdev, "status (%d) return ownership to device", err);
return err;
}
{
struct sdio_func *func = dev_to_sdio_func(dev);
struct btmtksdio_dev *bdev;
- u32 status;
int err;
bdev = sdio_get_drvdata(func);
if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state))
return 0;
- sdio_claim_host(bdev->func);
+ err = btmtksdio_drv_pmctrl(bdev);
- sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err);
- if (err < 0)
- goto out;
-
- err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status,
- status & C_COM_DRV_OWN, 2000, 1000000);
-out:
- bt_dev_info(bdev->hdev, "status (%d) get ownership from device", err);
-
- sdio_release_host(bdev->func);
+ bt_dev_dbg(bdev->hdev, "status (%d) get ownership from device", err);
return err;
}
.cfg_name = "rtl_bt/rtl8761bu_config" },
/* 8822C with UART interface */
+ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0x8, HCI_UART),
+ .config_needed = true,
+ .has_rom_version = true,
+ .has_msft_ext = true,
+ .fw_name = "rtl_bt/rtl8822cs_fw.bin",
+ .cfg_name = "rtl_bt/rtl8822cs_config" },
+
+ /* 8822C with UART interface */
{ IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_UART),
.config_needed = true,
.has_rom_version = true,
#define BTUSB_QCA_WCN6855 0x1000000
#define BTUSB_INTEL_BROKEN_SHUTDOWN_LED 0x2000000
#define BTUSB_INTEL_BROKEN_INITIAL_NCMD 0x4000000
+#define BTUSB_INTEL_NO_WBS_SUPPORT 0x8000000
static const struct usb_device_id btusb_table[] = {
/* Generic Bluetooth USB device */
{ USB_DEVICE(0x8087, 0x0033), .driver_info = BTUSB_INTEL_COMBINED },
{ USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR },
{ USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL_COMBINED |
+ BTUSB_INTEL_NO_WBS_SUPPORT |
BTUSB_INTEL_BROKEN_INITIAL_NCMD |
BTUSB_INTEL_BROKEN_SHUTDOWN_LED },
{ USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL_COMBINED |
+ BTUSB_INTEL_NO_WBS_SUPPORT |
BTUSB_INTEL_BROKEN_SHUTDOWN_LED },
{ USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_COMBINED },
{ USB_DEVICE(0x8087, 0x0aa7), .driver_info = BTUSB_INTEL_COMBINED |
BTUSB_WIDEBAND_SPEECH },
/* Realtek 8852AE Bluetooth devices */
+ { USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK |
+ BTUSB_WIDEBAND_SPEECH },
{ USB_DEVICE(0x0bda, 0xc852), .driver_info = BTUSB_REALTEK |
BTUSB_WIDEBAND_SPEECH },
{ USB_DEVICE(0x0bda, 0x385a), .driver_info = BTUSB_REALTEK |
* These controllers are really messed-up.
*
* 1. Their bulk RX endpoint will never report any data unless
- * the device was suspended at least once (yes, really).
+ * the device was suspended at least once (yes, really).
* 2. They will not wakeup when autosuspended and receiving data
- * on their bulk RX endpoint from e.g. a keyboard or mouse
- * (IOW remote-wakeup support is broken for the bulk endpoint).
+ * on their bulk RX endpoint from e.g. a keyboard or mouse
+ * (IOW remote-wakeup support is broken for the bulk endpoint).
*
* To fix 1. enable runtime-suspend, force-suspend the
* HCI and then wake-it up by disabling runtime-suspend.
hdev->send = btusb_send_frame_intel;
hdev->cmd_timeout = btusb_intel_cmd_timeout;
+ if (id->driver_info & BTUSB_INTEL_NO_WBS_SUPPORT)
+ btintel_set_flag(hdev, INTEL_ROM_LEGACY_NO_WBS_SUPPORT);
+
if (id->driver_info & BTUSB_INTEL_BROKEN_INITIAL_NCMD)
btintel_set_flag(hdev, INTEL_BROKEN_INITIAL_NCMD);
pm_runtime_enable(&h5->hu->serdev->dev);
}
+ /* The controller needs reset to startup */
+ gpiod_set_value_cansleep(h5->enable_gpio, 0);
+ gpiod_set_value_cansleep(h5->device_wake_gpio, 0);
+ msleep(100);
+
/* The controller needs up to 500ms to wakeup */
gpiod_set_value_cansleep(h5->enable_gpio, 1);
gpiod_set_value_cansleep(h5->device_wake_gpio, 1);
return 0;
}
-/**
+/*
* download_firmware -
* internal function which parses through the .bts firmware
* script file intreprets SEND, DELAY actions only as of now
if (err)
return err;
+ percpu_init_rwsem(&hu->proto_lock);
+
err = p->open(hu);
if (err)
goto err_open;
INIT_WORK(&hu->init_ready, hci_uart_init_work);
INIT_WORK(&hu->write_work, hci_uart_write_work);
- percpu_init_rwsem(&hu->proto_lock);
/* Only when vendor specific setup callback is provided, consider
* the manufacturer information valid. This avoids filling in the
return res;
}
+/* determine if the packet is NA or NS */
+static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond)
+{
+ struct ipv6hdr *ip6hdr;
+ struct icmp6hdr *hdr;
+
+ if (!pskb_network_may_pull(skb, sizeof(*ip6hdr)))
+ return true;
+
+ ip6hdr = ipv6_hdr(skb);
+ if (ip6hdr->nexthdr != IPPROTO_ICMPV6)
+ return false;
+
+ if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr)))
+ return true;
+
+ hdr = icmp6_hdr(skb);
+ return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT ||
+ hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION;
+}
+
/************************ exported alb functions ************************/
int bond_alb_initialize(struct bonding *bond, int rlb_enabled)
/* Do not TX balance any multicast or broadcast */
if (!is_multicast_ether_addr(eth_data->h_dest)) {
switch (skb->protocol) {
- case htons(ETH_P_IP):
case htons(ETH_P_IPV6):
+ if (alb_determine_nd(skb, bond))
+ break;
+ fallthrough;
+ case htons(ETH_P_IP):
hash_index = bond_xmit_hash(bond, skb);
if (bond->params.tlb_dynamic_lb) {
tx_slave = tlb_choose_channel(bond,
break;
}
- if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) {
+ if (alb_determine_nd(skb, bond)) {
do_tx_balance = false;
break;
}
+
+ /* The IPv6 header is pulled by alb_determine_nd */
/* Additionally, DAD probes should not be tx-balanced as that
* will lead to false positives for duplicate addresses and
* prevent address configuration from working.
This enables support for the Qualcomm Atheros QCA8K Ethernet
switch chips.
-config NET_DSA_REALTEK_SMI
- tristate "Realtek SMI Ethernet switch family support"
- select NET_DSA_TAG_RTL4_A
- select NET_DSA_TAG_RTL8_4
- select FIXED_PHY
- select IRQ_DOMAIN
- select REALTEK_PHY
- select REGMAP
- help
- This enables support for the Realtek SMI-based switch
- chips, currently only RTL8366RB.
+source "drivers/net/dsa/realtek/Kconfig"
config NET_DSA_SMSC_LAN9303
tristate
obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o
obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o
-obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o
-realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o rtl8365mb.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
obj-y += mv88e6xxx/
obj-y += ocelot/
obj-y += qca/
+obj-y += realtek/
obj-y += sja1105/
obj-y += xrs700x/
{
int ret;
- ret = phy_init_eee(phy, 0);
+ ret = phy_init_eee(phy, false);
if (ret)
return 0;
PHY_BRCM_IDDQ_SUSPEND;
}
-static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port,
- unsigned long *supported,
- struct phylink_link_state *state)
+static void bcm_sf2_sw_get_caps(struct dsa_switch *ds, int port,
+ struct phylink_config *config)
{
+ unsigned long *interfaces = config->supported_interfaces;
struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
-
- if (!phy_interface_mode_is_rgmii(state->interface) &&
- state->interface != PHY_INTERFACE_MODE_MII &&
- state->interface != PHY_INTERFACE_MODE_REVMII &&
- state->interface != PHY_INTERFACE_MODE_GMII &&
- state->interface != PHY_INTERFACE_MODE_INTERNAL &&
- state->interface != PHY_INTERFACE_MODE_MOCA) {
- linkmode_zero(supported);
- if (port != core_readl(priv, CORE_IMP0_PRT_ID))
- dev_err(ds->dev,
- "Unsupported interface: %d for port %d\n",
- state->interface, port);
- return;
- }
-
- /* Allow all the expected bits */
- phylink_set(mask, Autoneg);
- phylink_set_port_modes(mask);
- phylink_set(mask, Pause);
- phylink_set(mask, Asym_Pause);
- /* With the exclusion of MII and Reverse MII, we support Gigabit,
- * including Half duplex
- */
- if (state->interface != PHY_INTERFACE_MODE_MII &&
- state->interface != PHY_INTERFACE_MODE_REVMII) {
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseT_Half);
+ if (priv->int_phy_mask & BIT(port)) {
+ __set_bit(PHY_INTERFACE_MODE_INTERNAL, interfaces);
+ } else if (priv->moca_port == port) {
+ __set_bit(PHY_INTERFACE_MODE_MOCA, interfaces);
+ } else {
+ __set_bit(PHY_INTERFACE_MODE_MII, interfaces);
+ __set_bit(PHY_INTERFACE_MODE_REVMII, interfaces);
+ __set_bit(PHY_INTERFACE_MODE_GMII, interfaces);
+ phy_interface_set_rgmii(interfaces);
}
- phylink_set(mask, 10baseT_Half);
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Half);
- phylink_set(mask, 100baseT_Full);
-
- linkmode_and(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mask);
+ config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100 | MAC_1000;
}
static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port,
.get_sset_count = bcm_sf2_sw_get_sset_count,
.get_ethtool_phy_stats = b53_get_ethtool_phy_stats,
.get_phy_flags = bcm_sf2_sw_get_phy_flags,
- .phylink_validate = bcm_sf2_sw_validate,
+ .phylink_get_caps = bcm_sf2_sw_get_caps,
.phylink_mac_config = bcm_sf2_sw_mac_config,
.phylink_mac_link_down = bcm_sf2_sw_mac_link_down,
.phylink_mac_link_up = bcm_sf2_sw_mac_link_up,
return 0;
}
-static void ksz8_validate(struct dsa_switch *ds, int port,
- unsigned long *supported,
- struct phylink_link_state *state)
+static void ksz8_get_caps(struct dsa_switch *ds, int port,
+ struct phylink_config *config)
{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
struct ksz_device *dev = ds->priv;
if (port == dev->cpu_port) {
- if (state->interface != PHY_INTERFACE_MODE_RMII &&
- state->interface != PHY_INTERFACE_MODE_MII &&
- state->interface != PHY_INTERFACE_MODE_NA)
- goto unsupported;
+ __set_bit(PHY_INTERFACE_MODE_RMII,
+ config->supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_MII,
+ config->supported_interfaces);
} else {
- if (state->interface != PHY_INTERFACE_MODE_INTERNAL &&
- state->interface != PHY_INTERFACE_MODE_NA)
- goto unsupported;
+ __set_bit(PHY_INTERFACE_MODE_INTERNAL,
+ config->supported_interfaces);
}
- /* Allow all the expected bits */
- phylink_set_port_modes(mask);
- phylink_set(mask, Autoneg);
+ config->mac_capabilities = MAC_10 | MAC_100;
/* Silicon Errata Sheet (DS80000830A):
* "Port 1 does not respond to received flow control PAUSE frames"
* switches.
*/
if (!ksz_is_ksz88x3(dev) || port)
- phylink_set(mask, Pause);
+ config->mac_capabilities |= MAC_SYM_PAUSE;
/* Asym pause is not supported on KSZ8863 and KSZ8873 */
if (!ksz_is_ksz88x3(dev))
- phylink_set(mask, Asym_Pause);
-
- /* 10M and 100M are only supported */
- phylink_set(mask, 10baseT_Half);
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Half);
- phylink_set(mask, 100baseT_Full);
-
- linkmode_and(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mask);
-
- return;
-
-unsupported:
- linkmode_zero(supported);
- dev_err(ds->dev, "Unsupported interface: %s, port: %d\n",
- phy_modes(state->interface), port);
+ config->mac_capabilities |= MAC_ASYM_PAUSE;
}
static const struct dsa_switch_ops ksz8_switch_ops = {
.setup = ksz8_setup,
.phy_read = ksz_phy_read16,
.phy_write = ksz_phy_write16,
- .phylink_validate = ksz8_validate,
+ .phylink_get_caps = ksz8_get_caps,
.phylink_mac_link_down = ksz_mac_link_down,
.port_enable = ksz_enable_port,
.get_strings = ksz8_get_strings,
(BROADCAST_STORM_VALUE *
BROADCAST_STORM_PROT_RATE) / 100);
- if (dev->synclko_125)
- ksz_write8(dev, REG_SW_GLOBAL_OUTPUT_CTRL__1,
- SW_ENABLE_REFCLKO | SW_REFCLKO_IS_125MHZ);
+ data8 = SW_ENABLE_REFCLKO;
+ if (dev->synclko_disable)
+ data8 = 0;
+ else if (dev->synclko_125)
+ data8 = SW_ENABLE_REFCLKO | SW_REFCLKO_IS_125MHZ;
+ ksz_write8(dev, REG_SW_GLOBAL_OUTPUT_CTRL__1, data8);
return 0;
}
}
dev->synclko_125 = of_property_read_bool(dev->dev->of_node,
"microchip,synclko-125");
+ dev->synclko_disable = of_property_read_bool(dev->dev->of_node,
+ "microchip,synclko-disable");
+ if (dev->synclko_125 && dev->synclko_disable) {
+ dev_err(dev->dev, "inconsistent synclko settings\n");
+ return -EINVAL;
+ }
}
ret = dsa_register_switch(dev->ds);
u32 regs_size;
bool phy_errata_9477;
bool synclko_125;
+ bool synclko_disable;
struct vlan_table *vlan_cache;
mcr |= PMCR_RX_FC_EN;
}
- if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, 0) >= 0) {
+ if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) {
switch (speed) {
case SPEED_1000:
mcr |= PMCR_FORCE_EEE1G;
int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg,
u16 mask, u16 val)
{
+ const unsigned long timeout = jiffies + msecs_to_jiffies(50);
u16 data;
int err;
int i;
- /* There's no bus specific operation to wait for a mask */
- for (i = 0; i < 16; i++) {
+ /* There's no bus specific operation to wait for a mask. Even
+ * if the initial poll takes longer than 50ms, always do at
+ * least one more attempt.
+ */
+ for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) {
err = mv88e6xxx_read(chip, addr, reg, &data);
if (err)
return err;
if ((data & mask) == val)
return 0;
- usleep_range(1000, 2000);
+ if (i < 2)
+ cpu_relax();
+ else
+ usleep_range(1000, 2000);
}
dev_err(chip->dev, "Timeout while waiting for switch\n");
return 0;
}
-static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
+static const u8 mv88e6185_phy_interface_modes[] = {
+ [MV88E6185_PORT_STS_CMODE_GMII_FD] = PHY_INTERFACE_MODE_GMII,
+ [MV88E6185_PORT_STS_CMODE_MII_100_FD_PS] = PHY_INTERFACE_MODE_MII,
+ [MV88E6185_PORT_STS_CMODE_MII_100] = PHY_INTERFACE_MODE_MII,
+ [MV88E6185_PORT_STS_CMODE_MII_10] = PHY_INTERFACE_MODE_MII,
+ [MV88E6185_PORT_STS_CMODE_SERDES] = PHY_INTERFACE_MODE_1000BASEX,
+ [MV88E6185_PORT_STS_CMODE_1000BASE_X] = PHY_INTERFACE_MODE_1000BASEX,
+ [MV88E6185_PORT_STS_CMODE_PHY] = PHY_INTERFACE_MODE_SGMII,
+};
+
+static void mv88e6185_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
{
- if (!phy_interface_mode_is_8023z(state->interface)) {
- /* 10M and 100M are only supported in non-802.3z mode */
- phylink_set(mask, 10baseT_Half);
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Half);
- phylink_set(mask, 100baseT_Full);
- }
+ u8 cmode = chip->ports[port].cmode;
+
+ if (cmode <= ARRAY_SIZE(mv88e6185_phy_interface_modes) &&
+ mv88e6185_phy_interface_modes[cmode])
+ __set_bit(mv88e6185_phy_interface_modes[cmode],
+ config->supported_interfaces);
+
+ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+ MAC_1000FD;
}
-static void mv88e6185_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
-{
- /* FIXME: if the port is in 1000Base-X mode, then it only supports
- * 1000M FD speeds. In this case, CMODE will indicate 5.
+static const u8 mv88e6xxx_phy_interface_modes[] = {
+ [MV88E6XXX_PORT_STS_CMODE_MII_PHY] = PHY_INTERFACE_MODE_MII,
+ [MV88E6XXX_PORT_STS_CMODE_MII] = PHY_INTERFACE_MODE_MII,
+ [MV88E6XXX_PORT_STS_CMODE_GMII] = PHY_INTERFACE_MODE_GMII,
+ [MV88E6XXX_PORT_STS_CMODE_RMII_PHY] = PHY_INTERFACE_MODE_RMII,
+ [MV88E6XXX_PORT_STS_CMODE_RMII] = PHY_INTERFACE_MODE_RMII,
+ [MV88E6XXX_PORT_STS_CMODE_100BASEX] = PHY_INTERFACE_MODE_100BASEX,
+ [MV88E6XXX_PORT_STS_CMODE_1000BASEX] = PHY_INTERFACE_MODE_1000BASEX,
+ [MV88E6XXX_PORT_STS_CMODE_SGMII] = PHY_INTERFACE_MODE_SGMII,
+ /* higher interface modes are not needed here, since ports supporting
+ * them are writable, and so the supported interfaces are filled in the
+ * corresponding .phylink_set_interfaces() implementation below
*/
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseX_Full);
+};
- mv88e6065_phylink_validate(chip, port, mask, state);
+static void mv88e6xxx_translate_cmode(u8 cmode, unsigned long *supported)
+{
+ if (cmode < ARRAY_SIZE(mv88e6xxx_phy_interface_modes) &&
+ mv88e6xxx_phy_interface_modes[cmode])
+ __set_bit(mv88e6xxx_phy_interface_modes[cmode], supported);
+ else if (cmode == MV88E6XXX_PORT_STS_CMODE_RGMII)
+ phy_interface_set_rgmii(supported);
}
-static void mv88e6341_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
+static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
{
- if (port >= 5)
- phylink_set(mask, 2500baseX_Full);
+ unsigned long *supported = config->supported_interfaces;
- /* No ethtool bits for 200Mbps */
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseX_Full);
+ /* Translate the default cmode */
+ mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
- mv88e6065_phylink_validate(chip, port, mask, state);
+ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100;
}
-static void mv88e6352_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
+static int mv88e6352_get_port4_serdes_cmode(struct mv88e6xxx_chip *chip)
{
- /* No ethtool bits for 200Mbps */
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseX_Full);
+ u16 reg, val;
+ int err;
+
+ err = mv88e6xxx_port_read(chip, 4, MV88E6XXX_PORT_STS, ®);
+ if (err)
+ return err;
+
+ /* If PHY_DETECT is zero, then we are not in auto-media mode */
+ if (!(reg & MV88E6XXX_PORT_STS_PHY_DETECT))
+ return 0xf;
+
+ val = reg & ~MV88E6XXX_PORT_STS_PHY_DETECT;
+ err = mv88e6xxx_port_write(chip, 4, MV88E6XXX_PORT_STS, val);
+ if (err)
+ return err;
+
+ err = mv88e6xxx_port_read(chip, 4, MV88E6XXX_PORT_STS, &val);
+ if (err)
+ return err;
+
+ /* Restore PHY_DETECT value */
+ err = mv88e6xxx_port_write(chip, 4, MV88E6XXX_PORT_STS, reg);
+ if (err)
+ return err;
- mv88e6065_phylink_validate(chip, port, mask, state);
+ return val & MV88E6XXX_PORT_STS_CMODE_MASK;
}
-static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
+static void mv88e6352_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
{
- if (port >= 9) {
- phylink_set(mask, 2500baseX_Full);
- phylink_set(mask, 2500baseT_Full);
+ unsigned long *supported = config->supported_interfaces;
+ int err, cmode;
+
+ /* Translate the default cmode */
+ mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
+
+ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+ MAC_1000FD;
+
+ /* Port 4 supports automedia if the serdes is associated with it. */
+ if (port == 4) {
+ mv88e6xxx_reg_lock(chip);
+ err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+ if (err < 0)
+ dev_err(chip->dev, "p%d: failed to read scratch\n",
+ port);
+ if (err <= 0)
+ goto unlock;
+
+ cmode = mv88e6352_get_port4_serdes_cmode(chip);
+ if (cmode < 0)
+ dev_err(chip->dev, "p%d: failed to read serdes cmode\n",
+ port);
+ else
+ mv88e6xxx_translate_cmode(cmode, supported);
+unlock:
+ mv88e6xxx_reg_unlock(chip);
}
+}
+
+static void mv88e6341_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
+{
+ unsigned long *supported = config->supported_interfaces;
+
+ /* Translate the default cmode */
+ mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
/* No ethtool bits for 200Mbps */
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseX_Full);
+ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+ MAC_1000FD;
+
+ /* The C_Mode field is programmable on port 5 */
+ if (port == 5) {
+ __set_bit(PHY_INTERFACE_MODE_SGMII, supported);
+ __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported);
+ __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported);
- mv88e6065_phylink_validate(chip, port, mask, state);
+ config->mac_capabilities |= MAC_2500FD;
+ }
}
-static void mv88e6390x_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
+static void mv88e6390_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
{
- if (port >= 9) {
- phylink_set(mask, 10000baseT_Full);
- phylink_set(mask, 10000baseKR_Full);
+ unsigned long *supported = config->supported_interfaces;
+
+ /* Translate the default cmode */
+ mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
+
+ /* No ethtool bits for 200Mbps */
+ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+ MAC_1000FD;
+
+ /* The C_Mode field is programmable on ports 9 and 10 */
+ if (port == 9 || port == 10) {
+ __set_bit(PHY_INTERFACE_MODE_SGMII, supported);
+ __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported);
+ __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported);
+
+ config->mac_capabilities |= MAC_2500FD;
}
+}
+
+static void mv88e6390x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
+{
+ unsigned long *supported = config->supported_interfaces;
- mv88e6390_phylink_validate(chip, port, mask, state);
+ mv88e6390_phylink_get_caps(chip, port, config);
+
+ /* For the 6x90X, ports 2-7 can be in automedia mode.
+ * (Note that 6x90 doesn't support RXAUI nor XAUI).
+ *
+ * Port 2 can also support 1000BASE-X in automedia mode if port 9 is
+ * configured for 1000BASE-X, SGMII or 2500BASE-X.
+ * Port 3-4 can also support 1000BASE-X in automedia mode if port 9 is
+ * configured for RXAUI, 1000BASE-X, SGMII or 2500BASE-X.
+ *
+ * Port 5 can also support 1000BASE-X in automedia mode if port 10 is
+ * configured for 1000BASE-X, SGMII or 2500BASE-X.
+ * Port 6-7 can also support 1000BASE-X in automedia mode if port 10 is
+ * configured for RXAUI, 1000BASE-X, SGMII or 2500BASE-X.
+ *
+ * For now, be permissive (as the old code was) and allow 1000BASE-X
+ * on ports 2..7.
+ */
+ if (port >= 2 && port <= 7)
+ __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported);
+
+ /* The C_Mode field can also be programmed for 10G speeds */
+ if (port == 9 || port == 10) {
+ __set_bit(PHY_INTERFACE_MODE_XAUI, supported);
+ __set_bit(PHY_INTERFACE_MODE_RXAUI, supported);
+
+ config->mac_capabilities |= MAC_10000FD;
+ }
}
-static void mv88e6393x_phylink_validate(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state)
+static void mv88e6393x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config)
{
+ unsigned long *supported = config->supported_interfaces;
bool is_6191x =
chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6191X;
- if (((port == 0 || port == 9) && !is_6191x) || port == 10) {
- phylink_set(mask, 10000baseT_Full);
- phylink_set(mask, 10000baseKR_Full);
- phylink_set(mask, 10000baseCR_Full);
- phylink_set(mask, 10000baseSR_Full);
- phylink_set(mask, 10000baseLR_Full);
- phylink_set(mask, 10000baseLRM_Full);
- phylink_set(mask, 10000baseER_Full);
- phylink_set(mask, 5000baseT_Full);
- phylink_set(mask, 2500baseX_Full);
- phylink_set(mask, 2500baseT_Full);
- }
+ mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported);
+
+ config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 |
+ MAC_1000FD;
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseX_Full);
+ /* The C_Mode field can be programmed for ports 0, 9 and 10 */
+ if (port == 0 || port == 9 || port == 10) {
+ __set_bit(PHY_INTERFACE_MODE_SGMII, supported);
+ __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported);
- mv88e6065_phylink_validate(chip, port, mask, state);
+ /* 6191X supports >1G modes only on port 10 */
+ if (!is_6191x || port == 10) {
+ __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported);
+ __set_bit(PHY_INTERFACE_MODE_5GBASER, supported);
+ __set_bit(PHY_INTERFACE_MODE_10GBASER, supported);
+ /* FIXME: USXGMII is not supported yet */
+ /* __set_bit(PHY_INTERFACE_MODE_USXGMII, supported); */
+
+ config->mac_capabilities |= MAC_2500FD | MAC_5000FD |
+ MAC_10000FD;
+ }
+ }
}
-static void mv88e6xxx_validate(struct dsa_switch *ds, int port,
- unsigned long *supported,
- struct phylink_link_state *state)
+static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port,
+ struct phylink_config *config)
{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
struct mv88e6xxx_chip *chip = ds->priv;
- /* Allow all the expected bits */
- phylink_set(mask, Autoneg);
- phylink_set(mask, Pause);
- phylink_set_port_modes(mask);
+ chip->info->ops->phylink_get_caps(chip, port, config);
- if (chip->info->ops->phylink_validate)
- chip->info->ops->phylink_validate(chip, port, mask, state);
-
- linkmode_and(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mask);
-
- /* We can only operate at 2500BaseX or 1000BaseX. If requested
- * to advertise both, only report advertising at 2500BaseX.
- */
- phylink_helper_basex_speed(state);
+ /* Internal ports need GMII for PHYLIB */
+ if (mv88e6xxx_phy_is_internal(ds, port))
+ __set_bit(PHY_INTERFACE_MODE_GMII,
+ config->supported_interfaces);
}
static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
pvlan = 0;
- /* Frames from user ports can egress any local DSA links and CPU ports,
- * as well as any local member of their bridge group.
+ /* Frames from standalone user ports can only egress on the
+ * upstream port.
+ */
+ if (!dsa_port_bridge_dev_get(dp))
+ return BIT(dsa_switch_upstream_port(ds));
+
+ /* Frames from bridged user ports can egress any local DSA
+ * links and CPU ports, as well as any local member of their
+ * bridge group.
*/
dsa_switch_for_each_port(other_dp, ds)
if (other_dp->type == DSA_PORT_TYPE_CPU ||
int mv88e6xxx_fid_map(struct mv88e6xxx_chip *chip, unsigned long *fid_bitmap)
{
- int i, err;
- u16 fid;
-
bitmap_zero(fid_bitmap, MV88E6XXX_N_FID);
- /* Set every FID bit used by the (un)bridged ports */
- for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) {
- err = mv88e6xxx_port_get_fid(chip, i, &fid);
- if (err)
- return err;
-
- set_bit(fid, fid_bitmap);
- }
-
- /* Set every FID bit used by the VLAN entries */
+ /* Every FID has an associated VID, so walking the VTU
+ * will discover the full set of FIDs in use.
+ */
return mv88e6xxx_vtu_walk(chip, mv88e6xxx_fid_map_vlan, fid_bitmap);
}
if (err)
return err;
- /* The reset value 0x000 is used to indicate that multiple address
- * databases are not needed. Return the next positive available.
- */
- *fid = find_next_zero_bit(fid_bitmap, MV88E6XXX_N_FID, 1);
+ *fid = find_first_zero_bit(fid_bitmap, MV88E6XXX_N_FID);
if (unlikely(*fid >= mv88e6xxx_num_databases(chip)))
return -ENOSPC;
if (!vlan.valid) {
memset(&vlan, 0, sizeof(vlan));
+ if (vid == MV88E6XXX_VID_STANDALONE)
+ vlan.policy = true;
+
err = mv88e6xxx_atu_new(chip, &vlan.fid);
if (err)
return err;
if (err)
goto unlock;
+ err = mv88e6xxx_port_set_map_da(chip, port, true);
+ if (err)
+ return err;
+
err = mv88e6xxx_port_commit_pvid(chip, port);
if (err)
goto unlock;
mv88e6xxx_port_vlan_map(chip, port))
dev_err(ds->dev, "failed to remap in-chip Port VLAN\n");
+ err = mv88e6xxx_port_set_map_da(chip, port, false);
+ if (err)
+ dev_err(ds->dev,
+ "port %d failed to restore map-DA: %pe\n",
+ port, ERR_PTR(err));
+
err = mv88e6xxx_port_commit_pvid(chip, port);
if (err)
dev_err(ds->dev,
return err;
/* Port Control 2: don't force a good FCS, set the MTU size to
- * 10222 bytes, disable 802.1q tags checking, don't discard tagged or
- * untagged frames on this port, do a destination address lookup on all
- * received packets as usual, disable ARP mirroring and don't send a
- * copy of all transmitted/received frames on this port to the CPU.
+ * 10222 bytes, disable 802.1q tags checking, don't discard
+ * tagged or untagged frames on this port, skip destination
+ * address lookup on user ports, disable ARP mirroring and don't
+ * send a copy of all transmitted/received frames on this port
+ * to the CPU.
*/
- err = mv88e6xxx_port_set_map_da(chip, port);
+ err = mv88e6xxx_port_set_map_da(chip, port, !dsa_is_user_port(ds, port));
if (err)
return err;
if (err)
return err;
+ /* On chips that support it, set all downstream DSA ports'
+ * VLAN policy to TRAP. In combination with loading
+ * MV88E6XXX_VID_STANDALONE as a policy entry in the VTU, this
+ * provides a better isolation barrier between standalone
+ * ports, as the ATU is bypassed on any intermediate switches
+ * between the incoming port and the CPU.
+ */
+ if (dsa_is_downstream_port(ds, port) &&
+ chip->info->ops->port_set_policy) {
+ err = chip->info->ops->port_set_policy(chip, port,
+ MV88E6XXX_POLICY_MAPPING_VTU,
+ MV88E6XXX_POLICY_ACTION_TRAP);
+ if (err)
+ return err;
+ }
+
+ /* User ports start out in standalone mode and 802.1Q is
+ * therefore disabled. On DSA ports, all valid VIDs are always
+ * loaded in the VTU - therefore, enable 802.1Q in order to take
+ * advantage of VLAN policy on chips that supports it.
+ */
err = mv88e6xxx_port_set_8021q_mode(chip, port,
- MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED);
+ dsa_is_user_port(ds, port) ?
+ MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED :
+ MV88E6XXX_PORT_CTL2_8021Q_MODE_SECURE);
+ if (err)
+ return err;
+
+ /* Bind MV88E6XXX_VID_STANDALONE to MV88E6XXX_FID_STANDALONE by
+ * virtue of the fact that mv88e6xxx_atu_new() will pick it as
+ * the first free FID. This will be used as the private PVID for
+ * unbridged ports. Shared (DSA and CPU) ports must also be
+ * members of this VID, in order to trap all frames assigned to
+ * it to the CPU.
+ */
+ err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_STANDALONE,
+ MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNMODIFIED,
+ false);
if (err)
return err;
* relying on their port default FID.
*/
err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_BRIDGED,
- MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNTAGGED,
+ MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNMODIFIED,
false);
if (err)
return err;
.rmu_disable = mv88e6085_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
.reset = mv88e6185_g1_reset,
.vtu_getnext = mv88e6185_g1_vtu_getnext,
.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
.port_sync_link = mv88e6185_port_sync_link,
.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
.port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_policy = mv88e6352_port_set_policy,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
.rmu_disable = mv88e6085_g1_rmu_disable,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
.atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
.reset = mv88e6185_g1_reset,
.vtu_getnext = mv88e6185_g1_vtu_getnext,
.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6141_ops = {
.serdes_get_stats = mv88e6390_serdes_get_stats,
.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
.serdes_get_regs = mv88e6390_serdes_get_regs,
- .phylink_validate = mv88e6341_phylink_validate,
+ .phylink_get_caps = mv88e6341_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6161_ops = {
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.avb_ops = &mv88e6165_avb_ops,
.ptp_ops = &mv88e6165_ptp_ops,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.avb_ops = &mv88e6165_avb_ops,
.ptp_ops = &mv88e6165_ptp_ops,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6171_ops = {
.atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6172_ops = {
.serdes_get_regs_len = mv88e6352_serdes_get_regs_len,
.serdes_get_regs = mv88e6352_serdes_get_regs,
.gpio_ops = &mv88e6352_gpio_ops,
- .phylink_validate = mv88e6352_phylink_validate,
+ .phylink_get_caps = mv88e6352_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6175_ops = {
.atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6176_ops = {
.serdes_get_regs_len = mv88e6352_serdes_get_regs_len,
.serdes_get_regs = mv88e6352_serdes_get_regs,
.gpio_ops = &mv88e6352_gpio_ops,
- .phylink_validate = mv88e6352_phylink_validate,
+ .phylink_get_caps = mv88e6352_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6185_ops = {
.reset = mv88e6185_g1_reset,
.vtu_getnext = mv88e6185_g1_vtu_getnext,
.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
.set_max_frame_size = mv88e6185_g1_set_max_frame_size,
};
.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
.serdes_get_regs = mv88e6390_serdes_get_regs,
.gpio_ops = &mv88e6352_gpio_ops,
- .phylink_validate = mv88e6390_phylink_validate,
+ .phylink_get_caps = mv88e6390_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6190x_ops = {
.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
.serdes_get_regs = mv88e6390_serdes_get_regs,
.gpio_ops = &mv88e6352_gpio_ops,
- .phylink_validate = mv88e6390x_phylink_validate,
+ .phylink_get_caps = mv88e6390x_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6191_ops = {
.serdes_get_regs = mv88e6390_serdes_get_regs,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6390_phylink_validate,
+ .phylink_get_caps = mv88e6390_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6240_ops = {
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6352_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6352_phylink_validate,
+ .phylink_get_caps = mv88e6352_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6250_ops = {
.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
.avb_ops = &mv88e6352_avb_ops,
.ptp_ops = &mv88e6250_ptp_ops,
- .phylink_validate = mv88e6065_phylink_validate,
+ .phylink_get_caps = mv88e6250_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6290_ops = {
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6390_phylink_validate,
+ .phylink_get_caps = mv88e6390_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6320_ops = {
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6352_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6321_ops = {
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6352_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6341_ops = {
.serdes_get_stats = mv88e6390_serdes_get_stats,
.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
.serdes_get_regs = mv88e6390_serdes_get_regs,
- .phylink_validate = mv88e6341_phylink_validate,
+ .phylink_get_caps = mv88e6341_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6350_ops = {
.atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6351_ops = {
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.avb_ops = &mv88e6352_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6185_phylink_validate,
+ .phylink_get_caps = mv88e6185_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6352_ops = {
.serdes_get_stats = mv88e6352_serdes_get_stats,
.serdes_get_regs_len = mv88e6352_serdes_get_regs_len,
.serdes_get_regs = mv88e6352_serdes_get_regs,
- .phylink_validate = mv88e6352_phylink_validate,
+ .phylink_get_caps = mv88e6352_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6390_ops = {
.serdes_get_stats = mv88e6390_serdes_get_stats,
.serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
.serdes_get_regs = mv88e6390_serdes_get_regs,
- .phylink_validate = mv88e6390_phylink_validate,
+ .phylink_get_caps = mv88e6390_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6390x_ops = {
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6390x_phylink_validate,
+ .phylink_get_caps = mv88e6390x_phylink_get_caps,
};
static const struct mv88e6xxx_ops mv88e6393x_ops = {
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
- .phylink_validate = mv88e6393x_phylink_validate,
+ .phylink_get_caps = mv88e6393x_phylink_get_caps,
};
static const struct mv88e6xxx_info mv88e6xxx_table[] = {
.teardown = mv88e6xxx_teardown,
.port_setup = mv88e6xxx_port_setup,
.port_teardown = mv88e6xxx_port_teardown,
- .phylink_validate = mv88e6xxx_validate,
+ .phylink_get_caps = mv88e6xxx_get_caps,
.phylink_mac_link_state = mv88e6xxx_serdes_pcs_get_state,
.phylink_mac_config = mv88e6xxx_mac_config,
.phylink_mac_an_restart = mv88e6xxx_serdes_pcs_an_restart,
u16 fid;
u8 sid;
bool valid;
+ bool policy;
u8 member[DSA_MAX_PORTS];
u8 state[DSA_MAX_PORTS];
};
struct mv88e6xxx_bus_ops {
int (*read)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val);
int (*write)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val);
+ int (*init)(struct mv88e6xxx_chip *chip);
};
struct mv88e6xxx_mdio_bus {
const struct mv88e6xxx_ptp_ops *ptp_ops;
/* Phylink */
- void (*phylink_validate)(struct mv88e6xxx_chip *chip, int port,
- unsigned long *mask,
- struct phylink_link_state *state);
+ void (*phylink_get_caps)(struct mv88e6xxx_chip *chip, int port,
+ struct phylink_config *config);
/* Max Frame Size */
int (*set_max_frame_size)(struct mv88e6xxx_chip *chip, int mtu);
/* Offset 0x02: VTU FID Register */
#define MV88E6352_G1_VTU_FID 0x02
+#define MV88E6352_G1_VTU_FID_VID_POLICY 0x1000
#define MV88E6352_G1_VTU_FID_MASK 0x0fff
/* Offset 0x03: VTU SID Register */
return err;
entry->fid = val & MV88E6352_G1_VTU_FID_MASK;
-
+ entry->policy = !!(val & MV88E6352_G1_VTU_FID_VID_POLICY);
return 0;
}
{
u16 val = entry->fid & MV88E6352_G1_VTU_FID_MASK;
+ if (entry->policy)
+ val |= MV88E6352_G1_VTU_FID_VID_POLICY;
+
return mv88e6xxx_g1_write(chip, MV88E6352_G1_VTU_FID, val);
}
#define MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU BIT(2)
#define MV88E6352_G2_SCRATCH_CONFIG_DATA2 0x72
#define MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK 0x3
+#define MV88E6352_G2_SCRATCH_CONFIG_DATA3 0x73
+#define MV88E6352_G2_SCRATCH_CONFIG_DATA3_S_SEL BIT(1)
#define MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO 0
#define MV88E6352_G2_SCRATCH_GPIO_PCTL_TRIG 1
int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip,
bool external);
+int mv88e6352_g2_scratch_port_has_serdes(struct mv88e6xxx_chip *chip, int port);
int mv88e6xxx_g2_atu_stats_set(struct mv88e6xxx_chip *chip, u16 kind, u16 bin);
int mv88e6xxx_g2_atu_stats_get(struct mv88e6xxx_chip *chip, u16 *stats);
return mv88e6xxx_g2_scratch_write(chip, misc_cfg, val);
}
+
+/**
+ * mv88e6352_g2_scratch_port_has_serdes - indicate if a port can have a serdes
+ * @chip: chip private data
+ * @port: port number to check for serdes
+ *
+ * Indicates whether the port may have a serdes attached according to the
+ * pin strapping. Returns negative error number, 0 if the port is not
+ * configured to have a serdes, and 1 if the port is configured to have a
+ * serdes attached.
+ */
+int mv88e6352_g2_scratch_port_has_serdes(struct mv88e6xxx_chip *chip, int port)
+{
+ u8 config3, p;
+ int err;
+
+ err = mv88e6xxx_g2_scratch_read(chip, MV88E6352_G2_SCRATCH_CONFIG_DATA3,
+ &config3);
+ if (err)
+ return err;
+
+ if (config3 & MV88E6352_G2_SCRATCH_CONFIG_DATA3_S_SEL)
+ p = 5;
+ else
+ p = 4;
+
+ return port == p;
+}
return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, new);
}
-int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port)
+int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port, bool map)
{
u16 reg;
int err;
if (err)
return err;
- reg |= MV88E6XXX_PORT_CTL2_MAP_DA;
+ if (map)
+ reg |= MV88E6XXX_PORT_CTL2_MAP_DA;
+ else
+ reg &= ~MV88E6XXX_PORT_CTL2_MAP_DA;
return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, reg);
}
#define MV88E6XXX_PORT_STS_TX_PAUSED 0x0020
#define MV88E6XXX_PORT_STS_FLOW_CTL 0x0010
#define MV88E6XXX_PORT_STS_CMODE_MASK 0x000f
+#define MV88E6XXX_PORT_STS_CMODE_MII_PHY 0x0001
+#define MV88E6XXX_PORT_STS_CMODE_MII 0x0002
+#define MV88E6XXX_PORT_STS_CMODE_GMII 0x0003
+#define MV88E6XXX_PORT_STS_CMODE_RMII_PHY 0x0004
+#define MV88E6XXX_PORT_STS_CMODE_RMII 0x0005
#define MV88E6XXX_PORT_STS_CMODE_RGMII 0x0007
#define MV88E6XXX_PORT_STS_CMODE_100BASEX 0x0008
#define MV88E6XXX_PORT_STS_CMODE_1000BASEX 0x0009
int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port,
bool drop_untagged);
-int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
+int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port, bool map);
int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
int upstream_port);
int mv88e6xxx_port_set_mirror(struct mv88e6xxx_chip *chip, int port,
return lane;
}
-static bool mv88e6352_port_has_serdes(struct mv88e6xxx_chip *chip, int port)
-{
- if (mv88e6xxx_serdes_get_lane(chip, port) >= 0)
- return true;
-
- return false;
-}
-
struct mv88e6352_serdes_hw_stat {
char string[ETH_GSTRING_LEN];
int sizeof_stat;
int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port)
{
- if (mv88e6352_port_has_serdes(chip, port))
- return ARRAY_SIZE(mv88e6352_serdes_hw_stats);
+ int err;
- return 0;
+ err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+ if (err <= 0)
+ return err;
+
+ return ARRAY_SIZE(mv88e6352_serdes_hw_stats);
}
int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
int port, uint8_t *data)
{
struct mv88e6352_serdes_hw_stat *stat;
- int i;
+ int err, i;
- if (!mv88e6352_port_has_serdes(chip, port))
- return 0;
+ err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+ if (err <= 0)
+ return err;
for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_hw_stats); i++) {
stat = &mv88e6352_serdes_hw_stats[i];
{
struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port];
struct mv88e6352_serdes_hw_stat *stat;
+ int i, err;
u64 value;
- int i;
- if (!mv88e6352_port_has_serdes(chip, port))
- return 0;
+ err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+ if (err <= 0)
+ return err;
BUILD_BUG_ON(ARRAY_SIZE(mv88e6352_serdes_hw_stats) >
ARRAY_SIZE(mv88e6xxx_port->serdes_stats));
int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port)
{
- if (!mv88e6352_port_has_serdes(chip, port))
- return 0;
+ int err;
+
+ mv88e6xxx_reg_lock(chip);
+ err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+ mv88e6xxx_reg_unlock(chip);
+ if (err <= 0)
+ return err;
return 32 * sizeof(u16);
}
int err;
int i;
- if (!mv88e6352_port_has_serdes(chip, port))
+ err = mv88e6352_g2_scratch_port_has_serdes(chip, port);
+ if (err <= 0)
return;
for (i = 0 ; i < 32; i++) {
static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip,
int dev, int reg, int bit, int val)
{
+ const unsigned long timeout = jiffies + msecs_to_jiffies(50);
u16 data;
int err;
int i;
- for (i = 0; i < 16; i++) {
+ /* Even if the initial poll takes longer than 50ms, always do
+ * at least one more attempt.
+ */
+ for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) {
err = mv88e6xxx_smi_direct_read(chip, dev, reg, &data);
if (err)
return err;
if (!!(data & BIT(bit)) == !!val)
return 0;
- usleep_range(1000, 2000);
+ if (i < 2)
+ cpu_relax();
+ else
+ usleep_range(1000, 2000);
}
return -ETIMEDOUT;
{
int err;
- err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr,
- MV88E6XXX_SMI_CMD, 15, 0);
- if (err)
- return err;
-
err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr,
MV88E6XXX_SMI_CMD,
MV88E6XXX_SMI_CMD_BUSY |
{
int err;
- err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr,
- MV88E6XXX_SMI_CMD, 15, 0);
- if (err)
- return err;
-
err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr,
MV88E6XXX_SMI_DATA, data);
if (err)
MV88E6XXX_SMI_CMD, 15, 0);
}
+static int mv88e6xxx_smi_indirect_init(struct mv88e6xxx_chip *chip)
+{
+ /* Ensure that the chip starts out in the ready state. As both
+ * reads and writes always ensure this on return, they can
+ * safely depend on the chip not being busy on entry.
+ */
+ return mv88e6xxx_smi_direct_wait(chip, chip->sw_addr,
+ MV88E6XXX_SMI_CMD, 15, 0);
+}
+
static const struct mv88e6xxx_bus_ops mv88e6xxx_smi_indirect_ops = {
.read = mv88e6xxx_smi_indirect_read,
.write = mv88e6xxx_smi_indirect_write,
+ .init = mv88e6xxx_smi_indirect_init,
};
int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip,
chip->bus = bus;
chip->sw_addr = sw_addr;
+ if (chip->smi_ops->init)
+ return chip->smi_ops->init(chip);
+
return 0;
}
return DSA_TAG_PROTO_AR9331;
}
-static void ar9331_sw_phylink_validate(struct dsa_switch *ds, int port,
- unsigned long *supported,
- struct phylink_link_state *state)
+static void ar9331_sw_phylink_get_caps(struct dsa_switch *ds, int port,
+ struct phylink_config *config)
{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+ config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100;
switch (port) {
case 0:
- if (state->interface != PHY_INTERFACE_MODE_GMII)
- goto unsupported;
-
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseT_Half);
+ __set_bit(PHY_INTERFACE_MODE_GMII,
+ config->supported_interfaces);
+ config->mac_capabilities |= MAC_1000;
break;
case 1:
case 2:
case 3:
case 4:
case 5:
- if (state->interface != PHY_INTERFACE_MODE_INTERNAL)
- goto unsupported;
+ __set_bit(PHY_INTERFACE_MODE_INTERNAL,
+ config->supported_interfaces);
break;
- default:
- linkmode_zero(supported);
- dev_err(ds->dev, "Unsupported port: %i\n", port);
- return;
}
-
- phylink_set_port_modes(mask);
- phylink_set(mask, Pause);
- phylink_set(mask, Asym_Pause);
-
- phylink_set(mask, 10baseT_Half);
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Half);
- phylink_set(mask, 100baseT_Full);
-
- linkmode_and(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mask);
-
- return;
-
-unsupported:
- linkmode_zero(supported);
- dev_err(ds->dev, "Unsupported interface: %d, port: %d\n",
- state->interface, port);
}
static void ar9331_sw_phylink_mac_config(struct dsa_switch *ds, int port,
.get_tag_protocol = ar9331_sw_get_tag_protocol,
.setup = ar9331_sw_setup,
.port_disable = ar9331_sw_port_disable,
- .phylink_validate = ar9331_sw_phylink_validate,
+ .phylink_get_caps = ar9331_sw_phylink_get_caps,
.phylink_mac_config = ar9331_sw_phylink_mac_config,
.phylink_mac_link_down = ar9331_sw_phylink_mac_link_down,
.phylink_mac_link_up = ar9331_sw_phylink_mac_link_up,
#include <linux/phylink.h>
#include <linux/gpio/consumer.h>
#include <linux/etherdevice.h>
+#include <linux/dsa/tag_qca.h>
#include "qca8k.h"
MIB_DESC(1, 0xac, "TXUnicast"),
};
-/* The 32bit switch registers are accessed indirectly. To achieve this we need
- * to set the page of the register. Track the last page that was set to reduce
- * mdio writes
- */
-static u16 qca8k_current_page = 0xffff;
-
static void
qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page)
{
}
static int
+qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo)
+{
+ u16 *cached_lo = &priv->mdio_cache.lo;
+ struct mii_bus *bus = priv->bus;
+ int ret;
+
+ if (lo == *cached_lo)
+ return 0;
+
+ ret = bus->write(bus, phy_id, regnum, lo);
+ if (ret < 0)
+ dev_err_ratelimited(&bus->dev,
+ "failed to write qca8k 32bit lo register\n");
+
+ *cached_lo = lo;
+ return 0;
+}
+
+static int
+qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi)
+{
+ u16 *cached_hi = &priv->mdio_cache.hi;
+ struct mii_bus *bus = priv->bus;
+ int ret;
+
+ if (hi == *cached_hi)
+ return 0;
+
+ ret = bus->write(bus, phy_id, regnum, hi);
+ if (ret < 0)
+ dev_err_ratelimited(&bus->dev,
+ "failed to write qca8k 32bit hi register\n");
+
+ *cached_hi = hi;
+ return 0;
+}
+
+static int
qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
{
int ret;
}
static void
-qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
+qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val)
{
u16 lo, hi;
int ret;
lo = val & 0xffff;
hi = (u16)(val >> 16);
- ret = bus->write(bus, phy_id, regnum, lo);
+ ret = qca8k_set_lo(priv, phy_id, regnum, lo);
if (ret >= 0)
- ret = bus->write(bus, phy_id, regnum + 1, hi);
- if (ret < 0)
- dev_err_ratelimited(&bus->dev,
- "failed to write qca8k 32bit register\n");
+ ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi);
}
static int
-qca8k_set_page(struct mii_bus *bus, u16 page)
+qca8k_set_page(struct qca8k_priv *priv, u16 page)
{
+ u16 *cached_page = &priv->mdio_cache.page;
+ struct mii_bus *bus = priv->bus;
int ret;
- if (page == qca8k_current_page)
+ if (page == *cached_page)
return 0;
ret = bus->write(bus, 0x18, 0, page);
return ret;
}
- qca8k_current_page = page;
+ *cached_page = page;
usleep_range(1000, 2000);
return 0;
}
return regmap_update_bits(priv->regmap, reg, mask, write_val);
}
+static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb)
+{
+ struct qca8k_mgmt_eth_data *mgmt_eth_data;
+ struct qca8k_priv *priv = ds->priv;
+ struct qca_mgmt_ethhdr *mgmt_ethhdr;
+ u8 len, cmd;
+
+ mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb_mac_header(skb);
+ mgmt_eth_data = &priv->mgmt_eth_data;
+
+ cmd = FIELD_GET(QCA_HDR_MGMT_CMD, mgmt_ethhdr->command);
+ len = FIELD_GET(QCA_HDR_MGMT_LENGTH, mgmt_ethhdr->command);
+
+ /* Make sure the seq match the requested packet */
+ if (mgmt_ethhdr->seq == mgmt_eth_data->seq)
+ mgmt_eth_data->ack = true;
+
+ if (cmd == MDIO_READ) {
+ mgmt_eth_data->data[0] = mgmt_ethhdr->mdio_data;
+
+ /* Get the rest of the 12 byte of data.
+ * The read/write function will extract the requested data.
+ */
+ if (len > QCA_HDR_MGMT_DATA1_LEN)
+ memcpy(mgmt_eth_data->data + 1, skb->data,
+ QCA_HDR_MGMT_DATA2_LEN);
+ }
+
+ complete(&mgmt_eth_data->rw_done);
+}
+
+static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 *val,
+ int priority, unsigned int len)
+{
+ struct qca_mgmt_ethhdr *mgmt_ethhdr;
+ unsigned int real_len;
+ struct sk_buff *skb;
+ u32 *data2;
+ u16 hdr;
+
+ skb = dev_alloc_skb(QCA_HDR_MGMT_PKT_LEN);
+ if (!skb)
+ return NULL;
+
+ /* Max value for len reg is 15 (0xf) but the switch actually return 16 byte
+ * Actually for some reason the steps are:
+ * 0: nothing
+ * 1-4: first 4 byte
+ * 5-6: first 12 byte
+ * 7-15: all 16 byte
+ */
+ if (len == 16)
+ real_len = 15;
+ else
+ real_len = len;
+
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, skb->len);
+
+ mgmt_ethhdr = skb_push(skb, QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN);
+
+ hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION);
+ hdr |= FIELD_PREP(QCA_HDR_XMIT_PRIORITY, priority);
+ hdr |= QCA_HDR_XMIT_FROM_CPU;
+ hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(0));
+ hdr |= FIELD_PREP(QCA_HDR_XMIT_CONTROL, QCA_HDR_XMIT_TYPE_RW_REG);
+
+ mgmt_ethhdr->command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg);
+ mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len);
+ mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd);
+ mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE,
+ QCA_HDR_MGMT_CHECK_CODE_VAL);
+
+ if (cmd == MDIO_WRITE)
+ mgmt_ethhdr->mdio_data = *val;
+
+ mgmt_ethhdr->hdr = htons(hdr);
+
+ data2 = skb_put_zero(skb, QCA_HDR_MGMT_DATA2_LEN + QCA_HDR_MGMT_PADDING_LEN);
+ if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN)
+ memcpy(data2, val + 1, len - QCA_HDR_MGMT_DATA1_LEN);
+
+ return skb;
+}
+
+static void qca8k_mdio_header_fill_seq_num(struct sk_buff *skb, u32 seq_num)
+{
+ struct qca_mgmt_ethhdr *mgmt_ethhdr;
+
+ mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb->data;
+ mgmt_ethhdr->seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num);
+}
+
+static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len)
+{
+ struct qca8k_mgmt_eth_data *mgmt_eth_data = &priv->mgmt_eth_data;
+ struct sk_buff *skb;
+ bool ack;
+ int ret;
+
+ skb = qca8k_alloc_mdio_header(MDIO_READ, reg, NULL,
+ QCA8K_ETHERNET_MDIO_PRIORITY, len);
+ if (!skb)
+ return -ENOMEM;
+
+ mutex_lock(&mgmt_eth_data->mutex);
+
+ /* Check mgmt_master if is operational */
+ if (!priv->mgmt_master) {
+ kfree_skb(skb);
+ mutex_unlock(&mgmt_eth_data->mutex);
+ return -EINVAL;
+ }
+
+ skb->dev = priv->mgmt_master;
+
+ reinit_completion(&mgmt_eth_data->rw_done);
+
+ /* Increment seq_num and set it in the mdio pkt */
+ mgmt_eth_data->seq++;
+ qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq);
+ mgmt_eth_data->ack = false;
+
+ dev_queue_xmit(skb);
+
+ ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done,
+ msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT));
+
+ *val = mgmt_eth_data->data[0];
+ if (len > QCA_HDR_MGMT_DATA1_LEN)
+ memcpy(val + 1, mgmt_eth_data->data + 1, len - QCA_HDR_MGMT_DATA1_LEN);
+
+ ack = mgmt_eth_data->ack;
+
+ mutex_unlock(&mgmt_eth_data->mutex);
+
+ if (ret <= 0)
+ return -ETIMEDOUT;
+
+ if (!ack)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int qca8k_write_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len)
+{
+ struct qca8k_mgmt_eth_data *mgmt_eth_data = &priv->mgmt_eth_data;
+ struct sk_buff *skb;
+ bool ack;
+ int ret;
+
+ skb = qca8k_alloc_mdio_header(MDIO_WRITE, reg, val,
+ QCA8K_ETHERNET_MDIO_PRIORITY, len);
+ if (!skb)
+ return -ENOMEM;
+
+ mutex_lock(&mgmt_eth_data->mutex);
+
+ /* Check mgmt_master if is operational */
+ if (!priv->mgmt_master) {
+ kfree_skb(skb);
+ mutex_unlock(&mgmt_eth_data->mutex);
+ return -EINVAL;
+ }
+
+ skb->dev = priv->mgmt_master;
+
+ reinit_completion(&mgmt_eth_data->rw_done);
+
+ /* Increment seq_num and set it in the mdio pkt */
+ mgmt_eth_data->seq++;
+ qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq);
+ mgmt_eth_data->ack = false;
+
+ dev_queue_xmit(skb);
+
+ ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done,
+ msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT));
+
+ ack = mgmt_eth_data->ack;
+
+ mutex_unlock(&mgmt_eth_data->mutex);
+
+ if (ret <= 0)
+ return -ETIMEDOUT;
+
+ if (!ack)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int
+qca8k_regmap_update_bits_eth(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val)
+{
+ u32 val = 0;
+ int ret;
+
+ ret = qca8k_read_eth(priv, reg, &val, sizeof(val));
+ if (ret)
+ return ret;
+
+ val &= ~mask;
+ val |= write_val;
+
+ return qca8k_write_eth(priv, reg, &val, sizeof(val));
+}
+
+static int
+qca8k_bulk_read(struct qca8k_priv *priv, u32 reg, u32 *val, int len)
+{
+ int i, count = len / sizeof(u32), ret;
+
+ if (priv->mgmt_master && !qca8k_read_eth(priv, reg, val, len))
+ return 0;
+
+ for (i = 0; i < count; i++) {
+ ret = regmap_read(priv->regmap, reg + (i * 4), val + i);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int
+qca8k_bulk_write(struct qca8k_priv *priv, u32 reg, u32 *val, int len)
+{
+ int i, count = len / sizeof(u32), ret;
+ u32 tmp;
+
+ if (priv->mgmt_master && !qca8k_write_eth(priv, reg, val, len))
+ return 0;
+
+ for (i = 0; i < count; i++) {
+ tmp = val[i];
+
+ ret = regmap_write(priv->regmap, reg + (i * 4), tmp);
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
+
static int
qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val)
{
u16 r1, r2, page;
int ret;
+ if (!qca8k_read_eth(priv, reg, val, sizeof(val)))
+ return 0;
+
qca8k_split_addr(reg, &r1, &r2, &page);
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
- ret = qca8k_set_page(bus, page);
+ ret = qca8k_set_page(priv, page);
if (ret < 0)
goto exit;
u16 r1, r2, page;
int ret;
+ if (!qca8k_write_eth(priv, reg, &val, sizeof(val)))
+ return 0;
+
qca8k_split_addr(reg, &r1, &r2, &page);
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
- ret = qca8k_set_page(bus, page);
+ ret = qca8k_set_page(priv, page);
if (ret < 0)
goto exit;
- qca8k_mii_write32(bus, 0x10 | r2, r1, val);
+ qca8k_mii_write32(priv, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
u32 val;
int ret;
+ if (!qca8k_regmap_update_bits_eth(priv, reg, mask, write_val))
+ return 0;
+
qca8k_split_addr(reg, &r1, &r2, &page);
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
- ret = qca8k_set_page(bus, page);
+ ret = qca8k_set_page(priv, page);
if (ret < 0)
goto exit;
val &= ~mask;
val |= write_val;
- qca8k_mii_write32(bus, 0x10 | r2, r1, val);
+ qca8k_mii_write32(priv, 0x10 | r2, r1, val);
exit:
mutex_unlock(&bus->mdio_lock);
static int
qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb)
{
- u32 reg[4], val;
- int i, ret;
+ u32 reg[3];
+ int ret;
/* load the ARL table into an array */
- for (i = 0; i < 4; i++) {
- ret = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4), &val);
- if (ret < 0)
- return ret;
-
- reg[i] = val;
- }
+ ret = qca8k_bulk_read(priv, QCA8K_REG_ATU_DATA0, reg, sizeof(reg));
+ if (ret)
+ return ret;
/* vid - 83:72 */
fdb->vid = FIELD_GET(QCA8K_ATU_VID_MASK, reg[2]);
u8 aging)
{
u32 reg[3] = { 0 };
- int i;
/* vid - 83:72 */
reg[2] = FIELD_PREP(QCA8K_ATU_VID_MASK, vid);
reg[0] |= FIELD_PREP(QCA8K_ATU_ADDR5_MASK, mac[5]);
/* load the array into the ARL table */
- for (i = 0; i < 3; i++)
- qca8k_write(priv, QCA8K_REG_ATU_DATA0 + (i * 4), reg[i]);
+ qca8k_bulk_write(priv, QCA8K_REG_ATU_DATA0, reg, sizeof(reg));
}
static int
int ret;
mutex_lock(&priv->reg_mutex);
- ret = regmap_set_bits(priv->regmap, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY);
+ ret = regmap_update_bits(priv->regmap, QCA8K_REG_MIB,
+ QCA8K_MIB_FUNC | QCA8K_MIB_BUSY,
+ FIELD_PREP(QCA8K_MIB_FUNC, QCA8K_MIB_FLUSH) |
+ QCA8K_MIB_BUSY);
if (ret)
goto exit;
regmap_clear_bits(priv->regmap, QCA8K_REG_PORT_STATUS(port), mask);
}
+static int
+qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data,
+ struct sk_buff *read_skb, u32 *val)
+{
+ struct sk_buff *skb = skb_copy(read_skb, GFP_KERNEL);
+ bool ack;
+ int ret;
+
+ reinit_completion(&mgmt_eth_data->rw_done);
+
+ /* Increment seq_num and set it in the copy pkt */
+ mgmt_eth_data->seq++;
+ qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq);
+ mgmt_eth_data->ack = false;
+
+ dev_queue_xmit(skb);
+
+ ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done,
+ QCA8K_ETHERNET_TIMEOUT);
+
+ ack = mgmt_eth_data->ack;
+
+ if (ret <= 0)
+ return -ETIMEDOUT;
+
+ if (!ack)
+ return -EINVAL;
+
+ *val = mgmt_eth_data->data[0];
+
+ return 0;
+}
+
+static int
+qca8k_phy_eth_command(struct qca8k_priv *priv, bool read, int phy,
+ int regnum, u16 data)
+{
+ struct sk_buff *write_skb, *clear_skb, *read_skb;
+ struct qca8k_mgmt_eth_data *mgmt_eth_data;
+ u32 write_val, clear_val = 0, val;
+ struct net_device *mgmt_master;
+ int ret, ret1;
+ bool ack;
+
+ if (regnum >= QCA8K_MDIO_MASTER_MAX_REG)
+ return -EINVAL;
+
+ mgmt_eth_data = &priv->mgmt_eth_data;
+
+ write_val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN |
+ QCA8K_MDIO_MASTER_PHY_ADDR(phy) |
+ QCA8K_MDIO_MASTER_REG_ADDR(regnum);
+
+ if (read) {
+ write_val |= QCA8K_MDIO_MASTER_READ;
+ } else {
+ write_val |= QCA8K_MDIO_MASTER_WRITE;
+ write_val |= QCA8K_MDIO_MASTER_DATA(data);
+ }
+
+ /* Prealloc all the needed skb before the lock */
+ write_skb = qca8k_alloc_mdio_header(MDIO_WRITE, QCA8K_MDIO_MASTER_CTRL, &write_val,
+ QCA8K_ETHERNET_PHY_PRIORITY, sizeof(write_val));
+ if (!write_skb)
+ return -ENOMEM;
+
+ clear_skb = qca8k_alloc_mdio_header(MDIO_WRITE, QCA8K_MDIO_MASTER_CTRL, &clear_val,
+ QCA8K_ETHERNET_PHY_PRIORITY, sizeof(clear_val));
+ if (!write_skb) {
+ ret = -ENOMEM;
+ goto err_clear_skb;
+ }
+
+ read_skb = qca8k_alloc_mdio_header(MDIO_READ, QCA8K_MDIO_MASTER_CTRL, &clear_val,
+ QCA8K_ETHERNET_PHY_PRIORITY, sizeof(clear_val));
+ if (!read_skb) {
+ ret = -ENOMEM;
+ goto err_read_skb;
+ }
+
+ /* Actually start the request:
+ * 1. Send mdio master packet
+ * 2. Busy Wait for mdio master command
+ * 3. Get the data if we are reading
+ * 4. Reset the mdio master (even with error)
+ */
+ mutex_lock(&mgmt_eth_data->mutex);
+
+ /* Check if mgmt_master is operational */
+ mgmt_master = priv->mgmt_master;
+ if (!mgmt_master) {
+ mutex_unlock(&mgmt_eth_data->mutex);
+ ret = -EINVAL;
+ goto err_mgmt_master;
+ }
+
+ read_skb->dev = mgmt_master;
+ clear_skb->dev = mgmt_master;
+ write_skb->dev = mgmt_master;
+
+ reinit_completion(&mgmt_eth_data->rw_done);
+
+ /* Increment seq_num and set it in the write pkt */
+ mgmt_eth_data->seq++;
+ qca8k_mdio_header_fill_seq_num(write_skb, mgmt_eth_data->seq);
+ mgmt_eth_data->ack = false;
+
+ dev_queue_xmit(write_skb);
+
+ ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done,
+ QCA8K_ETHERNET_TIMEOUT);
+
+ ack = mgmt_eth_data->ack;
+
+ if (ret <= 0) {
+ ret = -ETIMEDOUT;
+ kfree_skb(read_skb);
+ goto exit;
+ }
+
+ if (!ack) {
+ ret = -EINVAL;
+ kfree_skb(read_skb);
+ goto exit;
+ }
+
+ ret = read_poll_timeout(qca8k_phy_eth_busy_wait, ret1,
+ !(val & QCA8K_MDIO_MASTER_BUSY), 0,
+ QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
+ mgmt_eth_data, read_skb, &val);
+
+ if (ret < 0 && ret1 < 0) {
+ ret = ret1;
+ goto exit;
+ }
+
+ if (read) {
+ reinit_completion(&mgmt_eth_data->rw_done);
+
+ /* Increment seq_num and set it in the read pkt */
+ mgmt_eth_data->seq++;
+ qca8k_mdio_header_fill_seq_num(read_skb, mgmt_eth_data->seq);
+ mgmt_eth_data->ack = false;
+
+ dev_queue_xmit(read_skb);
+
+ ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done,
+ QCA8K_ETHERNET_TIMEOUT);
+
+ ack = mgmt_eth_data->ack;
+
+ if (ret <= 0) {
+ ret = -ETIMEDOUT;
+ goto exit;
+ }
+
+ if (!ack) {
+ ret = -EINVAL;
+ goto exit;
+ }
+
+ ret = mgmt_eth_data->data[0] & QCA8K_MDIO_MASTER_DATA_MASK;
+ } else {
+ kfree_skb(read_skb);
+ }
+exit:
+ reinit_completion(&mgmt_eth_data->rw_done);
+
+ /* Increment seq_num and set it in the clear pkt */
+ mgmt_eth_data->seq++;
+ qca8k_mdio_header_fill_seq_num(clear_skb, mgmt_eth_data->seq);
+ mgmt_eth_data->ack = false;
+
+ dev_queue_xmit(clear_skb);
+
+ wait_for_completion_timeout(&mgmt_eth_data->rw_done,
+ QCA8K_ETHERNET_TIMEOUT);
+
+ mutex_unlock(&mgmt_eth_data->mutex);
+
+ return ret;
+
+ /* Error handling before lock */
+err_mgmt_master:
+ kfree_skb(read_skb);
+err_read_skb:
+ kfree_skb(clear_skb);
+err_clear_skb:
+ kfree_skb(write_skb);
+
+ return ret;
+}
+
static u32
qca8k_port_to_phy(int port)
{
}
static int
-qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data)
+qca8k_mdio_write(struct qca8k_priv *priv, int phy, int regnum, u16 data)
{
+ struct mii_bus *bus = priv->bus;
u16 r1, r2, page;
u32 val;
int ret;
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
- ret = qca8k_set_page(bus, page);
+ ret = qca8k_set_page(priv, page);
if (ret)
goto exit;
- qca8k_mii_write32(bus, 0x10 | r2, r1, val);
+ qca8k_mii_write32(priv, 0x10 | r2, r1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
+ qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
mutex_unlock(&bus->mdio_lock);
}
static int
-qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum)
+qca8k_mdio_read(struct qca8k_priv *priv, int phy, int regnum)
{
+ struct mii_bus *bus = priv->bus;
u16 r1, r2, page;
u32 val;
int ret;
mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED);
- ret = qca8k_set_page(bus, page);
+ ret = qca8k_set_page(priv, page);
if (ret)
goto exit;
- qca8k_mii_write32(bus, 0x10 | r2, r1, val);
+ qca8k_mii_write32(priv, 0x10 | r2, r1, val);
ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
QCA8K_MDIO_MASTER_BUSY);
exit:
/* even if the busy_wait timeouts try to clear the MASTER_EN */
- qca8k_mii_write32(bus, 0x10 | r2, r1, 0);
+ qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
mutex_unlock(&bus->mdio_lock);
qca8k_internal_mdio_write(struct mii_bus *slave_bus, int phy, int regnum, u16 data)
{
struct qca8k_priv *priv = slave_bus->priv;
- struct mii_bus *bus = priv->bus;
+ int ret;
- return qca8k_mdio_write(bus, phy, regnum, data);
+ /* Use mdio Ethernet when available, fallback to legacy one on error */
+ ret = qca8k_phy_eth_command(priv, false, phy, regnum, data);
+ if (!ret)
+ return 0;
+
+ return qca8k_mdio_write(priv, phy, regnum, data);
}
static int
qca8k_internal_mdio_read(struct mii_bus *slave_bus, int phy, int regnum)
{
struct qca8k_priv *priv = slave_bus->priv;
- struct mii_bus *bus = priv->bus;
+ int ret;
- return qca8k_mdio_read(bus, phy, regnum);
+ /* Use mdio Ethernet when available, fallback to legacy one on error */
+ ret = qca8k_phy_eth_command(priv, true, phy, regnum, 0);
+ if (ret >= 0)
+ return ret;
+
+ return qca8k_mdio_read(priv, phy, regnum);
}
static int
qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data)
{
struct qca8k_priv *priv = ds->priv;
+ int ret;
/* Check if the legacy mapping should be used and the
* port is not correctly mapped to the right PHY in the
if (priv->legacy_phy_port_mapping)
port = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
- return qca8k_mdio_write(priv->bus, port, regnum, data);
+ /* Use mdio Ethernet when available, fallback to legacy one on error */
+ ret = qca8k_phy_eth_command(priv, false, port, regnum, 0);
+ if (!ret)
+ return ret;
+
+ return qca8k_mdio_write(priv, port, regnum, data);
}
static int
if (priv->legacy_phy_port_mapping)
port = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
- ret = qca8k_mdio_read(priv->bus, port, regnum);
+ /* Use mdio Ethernet when available, fallback to legacy one on error */
+ ret = qca8k_phy_eth_command(priv, true, port, regnum, 0);
+ if (ret >= 0)
+ return ret;
+
+ ret = qca8k_mdio_read(priv, port, regnum);
if (ret < 0)
return 0xffff;
}
}
-static void
-qca8k_phylink_validate(struct dsa_switch *ds, int port,
- unsigned long *supported,
- struct phylink_link_state *state)
+static void qca8k_phylink_get_caps(struct dsa_switch *ds, int port,
+ struct phylink_config *config)
{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
-
switch (port) {
case 0: /* 1st CPU port */
- if (state->interface != PHY_INTERFACE_MODE_NA &&
- state->interface != PHY_INTERFACE_MODE_RGMII &&
- state->interface != PHY_INTERFACE_MODE_RGMII_ID &&
- state->interface != PHY_INTERFACE_MODE_RGMII_TXID &&
- state->interface != PHY_INTERFACE_MODE_RGMII_RXID &&
- state->interface != PHY_INTERFACE_MODE_SGMII)
- goto unsupported;
+ phy_interface_set_rgmii(config->supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_SGMII,
+ config->supported_interfaces);
break;
+
case 1:
case 2:
case 3:
case 4:
case 5:
/* Internal PHY */
- if (state->interface != PHY_INTERFACE_MODE_NA &&
- state->interface != PHY_INTERFACE_MODE_GMII &&
- state->interface != PHY_INTERFACE_MODE_INTERNAL)
- goto unsupported;
+ __set_bit(PHY_INTERFACE_MODE_GMII,
+ config->supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_INTERNAL,
+ config->supported_interfaces);
break;
+
case 6: /* 2nd CPU port / external PHY */
- if (state->interface != PHY_INTERFACE_MODE_NA &&
- state->interface != PHY_INTERFACE_MODE_RGMII &&
- state->interface != PHY_INTERFACE_MODE_RGMII_ID &&
- state->interface != PHY_INTERFACE_MODE_RGMII_TXID &&
- state->interface != PHY_INTERFACE_MODE_RGMII_RXID &&
- state->interface != PHY_INTERFACE_MODE_SGMII &&
- state->interface != PHY_INTERFACE_MODE_1000BASEX)
- goto unsupported;
+ phy_interface_set_rgmii(config->supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_SGMII,
+ config->supported_interfaces);
+ __set_bit(PHY_INTERFACE_MODE_1000BASEX,
+ config->supported_interfaces);
break;
- default:
-unsupported:
- linkmode_zero(supported);
- return;
}
- phylink_set_port_modes(mask);
- phylink_set(mask, Autoneg);
-
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 10baseT_Half);
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Half);
- phylink_set(mask, 100baseT_Full);
-
- if (state->interface == PHY_INTERFACE_MODE_1000BASEX)
- phylink_set(mask, 1000baseX_Full);
-
- phylink_set(mask, Pause);
- phylink_set(mask, Asym_Pause);
-
- linkmode_and(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mask);
+ config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100 | MAC_1000FD;
}
static int
ETH_GSTRING_LEN);
}
+static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *skb)
+{
+ const struct qca8k_match_data *match_data;
+ struct qca8k_mib_eth_data *mib_eth_data;
+ struct qca8k_priv *priv = ds->priv;
+ const struct qca8k_mib_desc *mib;
+ struct mib_ethhdr *mib_ethhdr;
+ int i, mib_len, offset = 0;
+ u64 *data;
+ u8 port;
+
+ mib_ethhdr = (struct mib_ethhdr *)skb_mac_header(skb);
+ mib_eth_data = &priv->mib_eth_data;
+
+ /* The switch autocast every port. Ignore other packet and
+ * parse only the requested one.
+ */
+ port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, ntohs(mib_ethhdr->hdr));
+ if (port != mib_eth_data->req_port)
+ goto exit;
+
+ match_data = device_get_match_data(priv->dev);
+ data = mib_eth_data->data;
+
+ for (i = 0; i < match_data->mib_count; i++) {
+ mib = &ar8327_mib[i];
+
+ /* First 3 mib are present in the skb head */
+ if (i < 3) {
+ data[i] = mib_ethhdr->data[i];
+ continue;
+ }
+
+ mib_len = sizeof(uint32_t);
+
+ /* Some mib are 64 bit wide */
+ if (mib->size == 2)
+ mib_len = sizeof(uint64_t);
+
+ /* Copy the mib value from packet to the */
+ memcpy(data + i, skb->data + offset, mib_len);
+
+ /* Set the offset for the next mib */
+ offset += mib_len;
+ }
+
+exit:
+ /* Complete on receiving all the mib packet */
+ if (refcount_dec_and_test(&mib_eth_data->port_parsed))
+ complete(&mib_eth_data->rw_done);
+}
+
+static int
+qca8k_get_ethtool_stats_eth(struct dsa_switch *ds, int port, u64 *data)
+{
+ struct dsa_port *dp = dsa_to_port(ds, port);
+ struct qca8k_mib_eth_data *mib_eth_data;
+ struct qca8k_priv *priv = ds->priv;
+ int ret;
+
+ mib_eth_data = &priv->mib_eth_data;
+
+ mutex_lock(&mib_eth_data->mutex);
+
+ reinit_completion(&mib_eth_data->rw_done);
+
+ mib_eth_data->req_port = dp->index;
+ mib_eth_data->data = data;
+ refcount_set(&mib_eth_data->port_parsed, QCA8K_NUM_PORTS);
+
+ mutex_lock(&priv->reg_mutex);
+
+ /* Send mib autocast request */
+ ret = regmap_update_bits(priv->regmap, QCA8K_REG_MIB,
+ QCA8K_MIB_FUNC | QCA8K_MIB_BUSY,
+ FIELD_PREP(QCA8K_MIB_FUNC, QCA8K_MIB_CAST) |
+ QCA8K_MIB_BUSY);
+
+ mutex_unlock(&priv->reg_mutex);
+
+ if (ret)
+ goto exit;
+
+ ret = wait_for_completion_timeout(&mib_eth_data->rw_done, QCA8K_ETHERNET_TIMEOUT);
+
+exit:
+ mutex_unlock(&mib_eth_data->mutex);
+
+ return ret;
+}
+
static void
qca8k_get_ethtool_stats(struct dsa_switch *ds, int port,
uint64_t *data)
u32 hi = 0;
int ret;
+ if (priv->mgmt_master &&
+ qca8k_get_ethtool_stats_eth(ds, port, data) > 0)
+ return;
+
match_data = of_device_get_match_data(priv->dev);
for (i = 0; i < match_data->mib_count; i++) {
return qca8k_lag_refresh_portmap(ds, port, lag, true);
}
+static void
+qca8k_master_change(struct dsa_switch *ds, const struct net_device *master,
+ bool operational)
+{
+ struct dsa_port *dp = master->dsa_ptr;
+ struct qca8k_priv *priv = ds->priv;
+
+ /* Ethernet MIB/MDIO is only supported for CPU port 0 */
+ if (dp->index != 0)
+ return;
+
+ mutex_lock(&priv->mgmt_eth_data.mutex);
+ mutex_lock(&priv->mib_eth_data.mutex);
+
+ priv->mgmt_master = operational ? (struct net_device *)master : NULL;
+
+ mutex_unlock(&priv->mib_eth_data.mutex);
+ mutex_unlock(&priv->mgmt_eth_data.mutex);
+}
+
+static int qca8k_connect_tag_protocol(struct dsa_switch *ds,
+ enum dsa_tag_protocol proto)
+{
+ struct qca_tagger_data *tagger_data;
+
+ switch (proto) {
+ case DSA_TAG_PROTO_QCA:
+ tagger_data = ds->tagger_data;
+
+ tagger_data->rw_reg_ack_handler = qca8k_rw_reg_ack_handler;
+ tagger_data->mib_autocast_handler = qca8k_mib_autocast_handler;
+
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
static const struct dsa_switch_ops qca8k_switch_ops = {
.get_tag_protocol = qca8k_get_tag_protocol,
.setup = qca8k_setup,
.port_vlan_filtering = qca8k_port_vlan_filtering,
.port_vlan_add = qca8k_port_vlan_add,
.port_vlan_del = qca8k_port_vlan_del,
- .phylink_validate = qca8k_phylink_validate,
+ .phylink_get_caps = qca8k_phylink_get_caps,
.phylink_mac_link_state = qca8k_phylink_mac_link_state,
.phylink_mac_config = qca8k_phylink_mac_config,
.phylink_mac_link_down = qca8k_phylink_mac_link_down,
.get_phy_flags = qca8k_get_phy_flags,
.port_lag_join = qca8k_port_lag_join,
.port_lag_leave = qca8k_port_lag_leave,
+ .master_state_change = qca8k_master_change,
+ .connect_tag_protocol = qca8k_connect_tag_protocol,
};
static int qca8k_read_switch_id(struct qca8k_priv *priv)
return PTR_ERR(priv->regmap);
}
+ priv->mdio_cache.page = 0xffff;
+ priv->mdio_cache.lo = 0xffff;
+ priv->mdio_cache.hi = 0xffff;
+
/* Check the detected switch id */
ret = qca8k_read_switch_id(priv);
if (ret)
if (!priv->ds)
return -ENOMEM;
+ mutex_init(&priv->mgmt_eth_data.mutex);
+ init_completion(&priv->mgmt_eth_data.rw_done);
+
+ mutex_init(&priv->mib_eth_data.mutex);
+ init_completion(&priv->mib_eth_data.rw_done);
+
priv->ds->dev = &mdiodev->dev;
priv->ds->num_ports = QCA8K_NUM_PORTS;
priv->ds->priv = priv;
#include <linux/delay.h>
#include <linux/regmap.h>
#include <linux/gpio.h>
+#include <linux/dsa/tag_qca.h>
+
+#define QCA8K_ETHERNET_MDIO_PRIORITY 7
+#define QCA8K_ETHERNET_PHY_PRIORITY 6
+#define QCA8K_ETHERNET_TIMEOUT 100
#define QCA8K_NUM_PORTS 7
#define QCA8K_NUM_CPU_PORTS 2
#define QCA8K_REG_MODULE_EN 0x030
#define QCA8K_MODULE_EN_MIB BIT(0)
#define QCA8K_REG_MIB 0x034
-#define QCA8K_MIB_FLUSH BIT(24)
+#define QCA8K_MIB_FUNC GENMASK(26, 24)
#define QCA8K_MIB_CPU_KEEP BIT(20)
#define QCA8K_MIB_BUSY BIT(17)
#define QCA8K_MDIO_MASTER_CTRL 0x3c
QCA8K_VLAN_READ = 6,
};
+enum qca8k_mid_cmd {
+ QCA8K_MIB_FLUSH = 1,
+ QCA8K_MIB_FLUSH_PORT = 2,
+ QCA8K_MIB_CAST = 3,
+};
+
struct ar8xxx_port_status {
int enabled;
};
QCA8K_CPU_PORT6,
};
+struct qca8k_mgmt_eth_data {
+ struct completion rw_done;
+ struct mutex mutex; /* Enforce one mdio read/write at time */
+ bool ack;
+ u32 seq;
+ u32 data[4];
+};
+
+struct qca8k_mib_eth_data {
+ struct completion rw_done;
+ struct mutex mutex; /* Process one command at time */
+ refcount_t port_parsed; /* Counter to track parsed port */
+ u8 req_port;
+ u64 *data; /* pointer to ethtool data */
+};
+
struct qca8k_ports_config {
bool sgmii_rx_clk_falling_edge;
bool sgmii_tx_clk_falling_edge;
u8 rgmii_tx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */
};
+struct qca8k_mdio_cache {
+/* The 32bit switch registers are accessed indirectly. To achieve this we need
+ * to set the page of the register. Track the last page that was set to reduce
+ * mdio writes
+ */
+ u16 page;
+/* lo and hi can also be cached and from Documentation we can skip one
+ * extra mdio write if lo or hi is didn't change.
+ */
+ u16 lo;
+ u16 hi;
+};
+
struct qca8k_priv {
u8 switch_id;
u8 switch_revision;
struct dsa_switch_ops ops;
struct gpio_desc *reset_gpio;
unsigned int port_mtu[QCA8K_NUM_PORTS];
+ struct net_device *mgmt_master; /* Track if mdio/mib Ethernet is available */
+ struct qca8k_mgmt_eth_data mgmt_eth_data;
+ struct qca8k_mib_eth_data mib_eth_data;
+ struct qca8k_mdio_cache mdio_cache;
};
struct qca8k_mib_desc {
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0+
-/* Realtek Simple Management Interface (SMI) driver
- * It can be discussed how "simple" this interface is.
- *
- * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels
- * but the protocol is not MDIO at all. Instead it is a Realtek
- * pecularity that need to bit-bang the lines in a special way to
- * communicate with the switch.
- *
- * ASICs we intend to support with this driver:
- *
- * RTL8366 - The original version, apparently
- * RTL8369 - Similar enough to have the same datsheet as RTL8366
- * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite
- * different register layout from the other two
- * RTL8366S - Is this "RTL8366 super"?
- * RTL8367 - Has an OpenWRT driver as well
- * RTL8368S - Seems to be an alternative name for RTL8366RB
- * RTL8370 - Also uses SMI
- *
- * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
- * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
- * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
- * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
- * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/spinlock.h>
-#include <linux/skbuff.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_mdio.h>
-#include <linux/delay.h>
-#include <linux/gpio/consumer.h>
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include <linux/bitops.h>
-#include <linux/if_bridge.h>
-
-#include "realtek-smi-core.h"
-
-#define REALTEK_SMI_ACK_RETRY_COUNT 5
-#define REALTEK_SMI_HW_STOP_DELAY 25 /* msecs */
-#define REALTEK_SMI_HW_START_DELAY 100 /* msecs */
-
-static inline void realtek_smi_clk_delay(struct realtek_smi *smi)
-{
- ndelay(smi->clk_delay);
-}
-
-static void realtek_smi_start(struct realtek_smi *smi)
-{
- /* Set GPIO pins to output mode, with initial state:
- * SCK = 0, SDA = 1
- */
- gpiod_direction_output(smi->mdc, 0);
- gpiod_direction_output(smi->mdio, 1);
- realtek_smi_clk_delay(smi);
-
- /* CLK 1: 0 -> 1, 1 -> 0 */
- gpiod_set_value(smi->mdc, 1);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 0);
- realtek_smi_clk_delay(smi);
-
- /* CLK 2: */
- gpiod_set_value(smi->mdc, 1);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdio, 0);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 0);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdio, 1);
-}
-
-static void realtek_smi_stop(struct realtek_smi *smi)
-{
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdio, 0);
- gpiod_set_value(smi->mdc, 1);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdio, 1);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 1);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 0);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 1);
-
- /* Add a click */
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 0);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 1);
-
- /* Set GPIO pins to input mode */
- gpiod_direction_input(smi->mdio);
- gpiod_direction_input(smi->mdc);
-}
-
-static void realtek_smi_write_bits(struct realtek_smi *smi, u32 data, u32 len)
-{
- for (; len > 0; len--) {
- realtek_smi_clk_delay(smi);
-
- /* Prepare data */
- gpiod_set_value(smi->mdio, !!(data & (1 << (len - 1))));
- realtek_smi_clk_delay(smi);
-
- /* Clocking */
- gpiod_set_value(smi->mdc, 1);
- realtek_smi_clk_delay(smi);
- gpiod_set_value(smi->mdc, 0);
- }
-}
-
-static void realtek_smi_read_bits(struct realtek_smi *smi, u32 len, u32 *data)
-{
- gpiod_direction_input(smi->mdio);
-
- for (*data = 0; len > 0; len--) {
- u32 u;
-
- realtek_smi_clk_delay(smi);
-
- /* Clocking */
- gpiod_set_value(smi->mdc, 1);
- realtek_smi_clk_delay(smi);
- u = !!gpiod_get_value(smi->mdio);
- gpiod_set_value(smi->mdc, 0);
-
- *data |= (u << (len - 1));
- }
-
- gpiod_direction_output(smi->mdio, 0);
-}
-
-static int realtek_smi_wait_for_ack(struct realtek_smi *smi)
-{
- int retry_cnt;
-
- retry_cnt = 0;
- do {
- u32 ack;
-
- realtek_smi_read_bits(smi, 1, &ack);
- if (ack == 0)
- break;
-
- if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) {
- dev_err(smi->dev, "ACK timeout\n");
- return -ETIMEDOUT;
- }
- } while (1);
-
- return 0;
-}
-
-static int realtek_smi_write_byte(struct realtek_smi *smi, u8 data)
-{
- realtek_smi_write_bits(smi, data, 8);
- return realtek_smi_wait_for_ack(smi);
-}
-
-static int realtek_smi_write_byte_noack(struct realtek_smi *smi, u8 data)
-{
- realtek_smi_write_bits(smi, data, 8);
- return 0;
-}
-
-static int realtek_smi_read_byte0(struct realtek_smi *smi, u8 *data)
-{
- u32 t;
-
- /* Read data */
- realtek_smi_read_bits(smi, 8, &t);
- *data = (t & 0xff);
-
- /* Send an ACK */
- realtek_smi_write_bits(smi, 0x00, 1);
-
- return 0;
-}
-
-static int realtek_smi_read_byte1(struct realtek_smi *smi, u8 *data)
-{
- u32 t;
-
- /* Read data */
- realtek_smi_read_bits(smi, 8, &t);
- *data = (t & 0xff);
-
- /* Send an ACK */
- realtek_smi_write_bits(smi, 0x01, 1);
-
- return 0;
-}
-
-static int realtek_smi_read_reg(struct realtek_smi *smi, u32 addr, u32 *data)
-{
- unsigned long flags;
- u8 lo = 0;
- u8 hi = 0;
- int ret;
-
- spin_lock_irqsave(&smi->lock, flags);
-
- realtek_smi_start(smi);
-
- /* Send READ command */
- ret = realtek_smi_write_byte(smi, smi->cmd_read);
- if (ret)
- goto out;
-
- /* Set ADDR[7:0] */
- ret = realtek_smi_write_byte(smi, addr & 0xff);
- if (ret)
- goto out;
-
- /* Set ADDR[15:8] */
- ret = realtek_smi_write_byte(smi, addr >> 8);
- if (ret)
- goto out;
-
- /* Read DATA[7:0] */
- realtek_smi_read_byte0(smi, &lo);
- /* Read DATA[15:8] */
- realtek_smi_read_byte1(smi, &hi);
-
- *data = ((u32)lo) | (((u32)hi) << 8);
-
- ret = 0;
-
- out:
- realtek_smi_stop(smi);
- spin_unlock_irqrestore(&smi->lock, flags);
-
- return ret;
-}
-
-static int realtek_smi_write_reg(struct realtek_smi *smi,
- u32 addr, u32 data, bool ack)
-{
- unsigned long flags;
- int ret;
-
- spin_lock_irqsave(&smi->lock, flags);
-
- realtek_smi_start(smi);
-
- /* Send WRITE command */
- ret = realtek_smi_write_byte(smi, smi->cmd_write);
- if (ret)
- goto out;
-
- /* Set ADDR[7:0] */
- ret = realtek_smi_write_byte(smi, addr & 0xff);
- if (ret)
- goto out;
-
- /* Set ADDR[15:8] */
- ret = realtek_smi_write_byte(smi, addr >> 8);
- if (ret)
- goto out;
-
- /* Write DATA[7:0] */
- ret = realtek_smi_write_byte(smi, data & 0xff);
- if (ret)
- goto out;
-
- /* Write DATA[15:8] */
- if (ack)
- ret = realtek_smi_write_byte(smi, data >> 8);
- else
- ret = realtek_smi_write_byte_noack(smi, data >> 8);
- if (ret)
- goto out;
-
- ret = 0;
-
- out:
- realtek_smi_stop(smi);
- spin_unlock_irqrestore(&smi->lock, flags);
-
- return ret;
-}
-
-/* There is one single case when we need to use this accessor and that
- * is when issueing soft reset. Since the device reset as soon as we write
- * that bit, no ACK will come back for natural reasons.
- */
-int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
- u32 data)
-{
- return realtek_smi_write_reg(smi, addr, data, false);
-}
-EXPORT_SYMBOL_GPL(realtek_smi_write_reg_noack);
-
-/* Regmap accessors */
-
-static int realtek_smi_write(void *ctx, u32 reg, u32 val)
-{
- struct realtek_smi *smi = ctx;
-
- return realtek_smi_write_reg(smi, reg, val, true);
-}
-
-static int realtek_smi_read(void *ctx, u32 reg, u32 *val)
-{
- struct realtek_smi *smi = ctx;
-
- return realtek_smi_read_reg(smi, reg, val);
-}
-
-static const struct regmap_config realtek_smi_mdio_regmap_config = {
- .reg_bits = 10, /* A4..A0 R4..R0 */
- .val_bits = 16,
- .reg_stride = 1,
- /* PHY regs are at 0x8000 */
- .max_register = 0xffff,
- .reg_format_endian = REGMAP_ENDIAN_BIG,
- .reg_read = realtek_smi_read,
- .reg_write = realtek_smi_write,
- .cache_type = REGCACHE_NONE,
-};
-
-static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum)
-{
- struct realtek_smi *smi = bus->priv;
-
- return smi->ops->phy_read(smi, addr, regnum);
-}
-
-static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum,
- u16 val)
-{
- struct realtek_smi *smi = bus->priv;
-
- return smi->ops->phy_write(smi, addr, regnum, val);
-}
-
-int realtek_smi_setup_mdio(struct realtek_smi *smi)
-{
- struct device_node *mdio_np;
- int ret;
-
- mdio_np = of_get_compatible_child(smi->dev->of_node, "realtek,smi-mdio");
- if (!mdio_np) {
- dev_err(smi->dev, "no MDIO bus node\n");
- return -ENODEV;
- }
-
- smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev);
- if (!smi->slave_mii_bus) {
- ret = -ENOMEM;
- goto err_put_node;
- }
- smi->slave_mii_bus->priv = smi;
- smi->slave_mii_bus->name = "SMI slave MII";
- smi->slave_mii_bus->read = realtek_smi_mdio_read;
- smi->slave_mii_bus->write = realtek_smi_mdio_write;
- snprintf(smi->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d",
- smi->ds->index);
- smi->slave_mii_bus->dev.of_node = mdio_np;
- smi->slave_mii_bus->parent = smi->dev;
- smi->ds->slave_mii_bus = smi->slave_mii_bus;
-
- ret = devm_of_mdiobus_register(smi->dev, smi->slave_mii_bus, mdio_np);
- if (ret) {
- dev_err(smi->dev, "unable to register MDIO bus %s\n",
- smi->slave_mii_bus->id);
- goto err_put_node;
- }
-
- return 0;
-
-err_put_node:
- of_node_put(mdio_np);
-
- return ret;
-}
-
-static int realtek_smi_probe(struct platform_device *pdev)
-{
- const struct realtek_smi_variant *var;
- struct device *dev = &pdev->dev;
- struct realtek_smi *smi;
- struct device_node *np;
- int ret;
-
- var = of_device_get_match_data(dev);
- np = dev->of_node;
-
- smi = devm_kzalloc(dev, sizeof(*smi) + var->chip_data_sz, GFP_KERNEL);
- if (!smi)
- return -ENOMEM;
- smi->chip_data = (void *)smi + sizeof(*smi);
- smi->map = devm_regmap_init(dev, NULL, smi,
- &realtek_smi_mdio_regmap_config);
- if (IS_ERR(smi->map)) {
- ret = PTR_ERR(smi->map);
- dev_err(dev, "regmap init failed: %d\n", ret);
- return ret;
- }
-
- /* Link forward and backward */
- smi->dev = dev;
- smi->clk_delay = var->clk_delay;
- smi->cmd_read = var->cmd_read;
- smi->cmd_write = var->cmd_write;
- smi->ops = var->ops;
-
- dev_set_drvdata(dev, smi);
- spin_lock_init(&smi->lock);
-
- /* TODO: if power is software controlled, set up any regulators here */
-
- /* Assert then deassert RESET */
- smi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
- if (IS_ERR(smi->reset)) {
- dev_err(dev, "failed to get RESET GPIO\n");
- return PTR_ERR(smi->reset);
- }
- msleep(REALTEK_SMI_HW_STOP_DELAY);
- gpiod_set_value(smi->reset, 0);
- msleep(REALTEK_SMI_HW_START_DELAY);
- dev_info(dev, "deasserted RESET\n");
-
- /* Fetch MDIO pins */
- smi->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW);
- if (IS_ERR(smi->mdc))
- return PTR_ERR(smi->mdc);
- smi->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW);
- if (IS_ERR(smi->mdio))
- return PTR_ERR(smi->mdio);
-
- smi->leds_disabled = of_property_read_bool(np, "realtek,disable-leds");
-
- ret = smi->ops->detect(smi);
- if (ret) {
- dev_err(dev, "unable to detect switch\n");
- return ret;
- }
-
- smi->ds = devm_kzalloc(dev, sizeof(*smi->ds), GFP_KERNEL);
- if (!smi->ds)
- return -ENOMEM;
-
- smi->ds->dev = dev;
- smi->ds->num_ports = smi->num_ports;
- smi->ds->priv = smi;
-
- smi->ds->ops = var->ds_ops;
- ret = dsa_register_switch(smi->ds);
- if (ret) {
- dev_err_probe(dev, ret, "unable to register switch\n");
- return ret;
- }
- return 0;
-}
-
-static int realtek_smi_remove(struct platform_device *pdev)
-{
- struct realtek_smi *smi = platform_get_drvdata(pdev);
-
- if (!smi)
- return 0;
-
- dsa_unregister_switch(smi->ds);
- if (smi->slave_mii_bus)
- of_node_put(smi->slave_mii_bus->dev.of_node);
- gpiod_set_value(smi->reset, 1);
-
- platform_set_drvdata(pdev, NULL);
-
- return 0;
-}
-
-static void realtek_smi_shutdown(struct platform_device *pdev)
-{
- struct realtek_smi *smi = platform_get_drvdata(pdev);
-
- if (!smi)
- return;
-
- dsa_switch_shutdown(smi->ds);
-
- platform_set_drvdata(pdev, NULL);
-}
-
-static const struct of_device_id realtek_smi_of_match[] = {
- {
- .compatible = "realtek,rtl8366rb",
- .data = &rtl8366rb_variant,
- },
- {
- /* FIXME: add support for RTL8366S and more */
- .compatible = "realtek,rtl8366s",
- .data = NULL,
- },
- {
- .compatible = "realtek,rtl8365mb",
- .data = &rtl8365mb_variant,
- },
- { /* sentinel */ },
-};
-MODULE_DEVICE_TABLE(of, realtek_smi_of_match);
-
-static struct platform_driver realtek_smi_driver = {
- .driver = {
- .name = "realtek-smi",
- .of_match_table = of_match_ptr(realtek_smi_of_match),
- },
- .probe = realtek_smi_probe,
- .remove = realtek_smi_remove,
- .shutdown = realtek_smi_shutdown,
-};
-module_platform_driver(realtek_smi_driver);
-
-MODULE_LICENSE("GPL");
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig NET_DSA_REALTEK
+ tristate "Realtek Ethernet switch family support"
+ depends on NET_DSA
+ select FIXED_PHY
+ select IRQ_DOMAIN
+ select REALTEK_PHY
+ select REGMAP
+ help
+ Select to enable support for Realtek Ethernet switch chips.
+
+config NET_DSA_REALTEK_MDIO
+ tristate "Realtek MDIO connected switch driver"
+ depends on NET_DSA_REALTEK
+ default y
+ help
+ Select to enable support for registering switches configured
+ through MDIO.
+
+config NET_DSA_REALTEK_SMI
+ tristate "Realtek SMI connected switch driver"
+ depends on NET_DSA_REALTEK
+ default y
+ help
+ Select to enable support for registering switches connected
+ through SMI.
+
+config NET_DSA_REALTEK_RTL8365MB
+ tristate "Realtek RTL8365MB switch subdriver"
+ default y
+ depends on NET_DSA_REALTEK
+ depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO
+ select NET_DSA_TAG_RTL8_4
+ help
+ Select to enable support for Realtek RTL8365MB-VC and RTL8367S.
+
+config NET_DSA_REALTEK_RTL8366RB
+ tristate "Realtek RTL8366RB switch subdriver"
+ default y
+ depends on NET_DSA_REALTEK
+ depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO
+ select NET_DSA_TAG_RTL4_A
+ help
+ Select to enable support for Realtek RTL8366RB
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_NET_DSA_REALTEK_MDIO) += realtek-mdio.o
+obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o
+obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o
+rtl8366-objs := rtl8366-core.o rtl8366rb.o
+obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/* Realtek MDIO interface driver
+ *
+ * ASICs we intend to support with this driver:
+ *
+ * RTL8366 - The original version, apparently
+ * RTL8369 - Similar enough to have the same datsheet as RTL8366
+ * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite
+ * different register layout from the other two
+ * RTL8366S - Is this "RTL8366 super"?
+ * RTL8367 - Has an OpenWRT driver as well
+ * RTL8368S - Seems to be an alternative name for RTL8366RB
+ * RTL8370 - Also uses SMI
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+
+#include "realtek.h"
+
+/* Read/write via mdiobus */
+#define REALTEK_MDIO_CTRL0_REG 31
+#define REALTEK_MDIO_START_REG 29
+#define REALTEK_MDIO_CTRL1_REG 21
+#define REALTEK_MDIO_ADDRESS_REG 23
+#define REALTEK_MDIO_DATA_WRITE_REG 24
+#define REALTEK_MDIO_DATA_READ_REG 25
+
+#define REALTEK_MDIO_START_OP 0xFFFF
+#define REALTEK_MDIO_ADDR_OP 0x000E
+#define REALTEK_MDIO_READ_OP 0x0001
+#define REALTEK_MDIO_WRITE_OP 0x0003
+
+static int realtek_mdio_write(void *ctx, u32 reg, u32 val)
+{
+ struct realtek_priv *priv = ctx;
+ struct mii_bus *bus = priv->bus;
+ int ret;
+
+ mutex_lock(&bus->mdio_lock);
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL0_REG, REALTEK_MDIO_ADDR_OP);
+ if (ret)
+ goto out_unlock;
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_ADDRESS_REG, reg);
+ if (ret)
+ goto out_unlock;
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_DATA_WRITE_REG, val);
+ if (ret)
+ goto out_unlock;
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL1_REG, REALTEK_MDIO_WRITE_OP);
+
+out_unlock:
+ mutex_unlock(&bus->mdio_lock);
+
+ return ret;
+}
+
+static int realtek_mdio_read(void *ctx, u32 reg, u32 *val)
+{
+ struct realtek_priv *priv = ctx;
+ struct mii_bus *bus = priv->bus;
+ int ret;
+
+ mutex_lock(&bus->mdio_lock);
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL0_REG, REALTEK_MDIO_ADDR_OP);
+ if (ret)
+ goto out_unlock;
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_ADDRESS_REG, reg);
+ if (ret)
+ goto out_unlock;
+
+ ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL1_REG, REALTEK_MDIO_READ_OP);
+ if (ret)
+ goto out_unlock;
+
+ ret = bus->read(bus, priv->mdio_addr, REALTEK_MDIO_DATA_READ_REG);
+ if (ret >= 0) {
+ *val = ret;
+ ret = 0;
+ }
+
+out_unlock:
+ mutex_unlock(&bus->mdio_lock);
+
+ return ret;
+}
+
+static const struct regmap_config realtek_mdio_regmap_config = {
+ .reg_bits = 10, /* A4..A0 R4..R0 */
+ .val_bits = 16,
+ .reg_stride = 1,
+ /* PHY regs are at 0x8000 */
+ .max_register = 0xffff,
+ .reg_format_endian = REGMAP_ENDIAN_BIG,
+ .reg_read = realtek_mdio_read,
+ .reg_write = realtek_mdio_write,
+ .cache_type = REGCACHE_NONE,
+};
+
+static int realtek_mdio_probe(struct mdio_device *mdiodev)
+{
+ struct realtek_priv *priv;
+ struct device *dev = &mdiodev->dev;
+ const struct realtek_variant *var;
+ int ret;
+ struct device_node *np;
+
+ var = of_device_get_match_data(dev);
+ if (!var)
+ return -EINVAL;
+
+ priv = devm_kzalloc(&mdiodev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->map = devm_regmap_init(dev, NULL, priv, &realtek_mdio_regmap_config);
+ if (IS_ERR(priv->map)) {
+ ret = PTR_ERR(priv->map);
+ dev_err(dev, "regmap init failed: %d\n", ret);
+ return ret;
+ }
+
+ priv->mdio_addr = mdiodev->addr;
+ priv->bus = mdiodev->bus;
+ priv->dev = &mdiodev->dev;
+ priv->chip_data = (void *)priv + sizeof(*priv);
+
+ priv->clk_delay = var->clk_delay;
+ priv->cmd_read = var->cmd_read;
+ priv->cmd_write = var->cmd_write;
+ priv->ops = var->ops;
+
+ priv->write_reg_noack = realtek_mdio_write;
+
+ np = dev->of_node;
+
+ dev_set_drvdata(dev, priv);
+
+ /* TODO: if power is software controlled, set up any regulators here */
+ priv->leds_disabled = of_property_read_bool(np, "realtek,disable-leds");
+
+ ret = priv->ops->detect(priv);
+ if (ret) {
+ dev_err(dev, "unable to detect switch\n");
+ return ret;
+ }
+
+ priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL);
+ if (!priv->ds)
+ return -ENOMEM;
+
+ priv->ds->dev = dev;
+ priv->ds->num_ports = priv->num_ports;
+ priv->ds->priv = priv;
+ priv->ds->ops = var->ds_ops_mdio;
+
+ ret = dsa_register_switch(priv->ds);
+ if (ret) {
+ dev_err(priv->dev, "unable to register switch ret = %d\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void realtek_mdio_remove(struct mdio_device *mdiodev)
+{
+ struct realtek_priv *priv = dev_get_drvdata(&mdiodev->dev);
+
+ if (!priv)
+ return;
+
+ dsa_unregister_switch(priv->ds);
+
+ dev_set_drvdata(&mdiodev->dev, NULL);
+}
+
+static void realtek_mdio_shutdown(struct mdio_device *mdiodev)
+{
+ struct realtek_priv *priv = dev_get_drvdata(&mdiodev->dev);
+
+ if (!priv)
+ return;
+
+ dsa_switch_shutdown(priv->ds);
+
+ dev_set_drvdata(&mdiodev->dev, NULL);
+}
+
+static const struct of_device_id realtek_mdio_of_match[] = {
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB)
+ { .compatible = "realtek,rtl8366rb", .data = &rtl8366rb_variant, },
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB)
+ { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, },
+ { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, },
+#endif
+ { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, realtek_mdio_of_match);
+
+static struct mdio_driver realtek_mdio_driver = {
+ .mdiodrv.driver = {
+ .name = "realtek-mdio",
+ .of_match_table = of_match_ptr(realtek_mdio_of_match),
+ },
+ .probe = realtek_mdio_probe,
+ .remove = realtek_mdio_remove,
+ .shutdown = realtek_mdio_shutdown,
+};
+
+mdio_module_driver(realtek_mdio_driver);
+
+MODULE_AUTHOR("Luiz Angelo Daros de Luca <luizluca@gmail.com>");
+MODULE_DESCRIPTION("Driver for Realtek ethernet switch connected via MDIO interface");
+MODULE_LICENSE("GPL");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/* Realtek Simple Management Interface (SMI) driver
+ * It can be discussed how "simple" this interface is.
+ *
+ * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels
+ * but the protocol is not MDIO at all. Instead it is a Realtek
+ * pecularity that need to bit-bang the lines in a special way to
+ * communicate with the switch.
+ *
+ * ASICs we intend to support with this driver:
+ *
+ * RTL8366 - The original version, apparently
+ * RTL8369 - Similar enough to have the same datsheet as RTL8366
+ * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite
+ * different register layout from the other two
+ * RTL8366S - Is this "RTL8366 super"?
+ * RTL8367 - Has an OpenWRT driver as well
+ * RTL8368S - Seems to be an alternative name for RTL8366RB
+ * RTL8370 - Also uses SMI
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+
+#include "realtek.h"
+
+#define REALTEK_SMI_ACK_RETRY_COUNT 5
+#define REALTEK_SMI_HW_STOP_DELAY 25 /* msecs */
+#define REALTEK_SMI_HW_START_DELAY 100 /* msecs */
+
+static inline void realtek_smi_clk_delay(struct realtek_priv *priv)
+{
+ ndelay(priv->clk_delay);
+}
+
+static void realtek_smi_start(struct realtek_priv *priv)
+{
+ /* Set GPIO pins to output mode, with initial state:
+ * SCK = 0, SDA = 1
+ */
+ gpiod_direction_output(priv->mdc, 0);
+ gpiod_direction_output(priv->mdio, 1);
+ realtek_smi_clk_delay(priv);
+
+ /* CLK 1: 0 -> 1, 1 -> 0 */
+ gpiod_set_value(priv->mdc, 1);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 0);
+ realtek_smi_clk_delay(priv);
+
+ /* CLK 2: */
+ gpiod_set_value(priv->mdc, 1);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdio, 0);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 0);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdio, 1);
+}
+
+static void realtek_smi_stop(struct realtek_priv *priv)
+{
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdio, 0);
+ gpiod_set_value(priv->mdc, 1);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdio, 1);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 1);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 0);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 1);
+
+ /* Add a click */
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 0);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 1);
+
+ /* Set GPIO pins to input mode */
+ gpiod_direction_input(priv->mdio);
+ gpiod_direction_input(priv->mdc);
+}
+
+static void realtek_smi_write_bits(struct realtek_priv *priv, u32 data, u32 len)
+{
+ for (; len > 0; len--) {
+ realtek_smi_clk_delay(priv);
+
+ /* Prepare data */
+ gpiod_set_value(priv->mdio, !!(data & (1 << (len - 1))));
+ realtek_smi_clk_delay(priv);
+
+ /* Clocking */
+ gpiod_set_value(priv->mdc, 1);
+ realtek_smi_clk_delay(priv);
+ gpiod_set_value(priv->mdc, 0);
+ }
+}
+
+static void realtek_smi_read_bits(struct realtek_priv *priv, u32 len, u32 *data)
+{
+ gpiod_direction_input(priv->mdio);
+
+ for (*data = 0; len > 0; len--) {
+ u32 u;
+
+ realtek_smi_clk_delay(priv);
+
+ /* Clocking */
+ gpiod_set_value(priv->mdc, 1);
+ realtek_smi_clk_delay(priv);
+ u = !!gpiod_get_value(priv->mdio);
+ gpiod_set_value(priv->mdc, 0);
+
+ *data |= (u << (len - 1));
+ }
+
+ gpiod_direction_output(priv->mdio, 0);
+}
+
+static int realtek_smi_wait_for_ack(struct realtek_priv *priv)
+{
+ int retry_cnt;
+
+ retry_cnt = 0;
+ do {
+ u32 ack;
+
+ realtek_smi_read_bits(priv, 1, &ack);
+ if (ack == 0)
+ break;
+
+ if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) {
+ dev_err(priv->dev, "ACK timeout\n");
+ return -ETIMEDOUT;
+ }
+ } while (1);
+
+ return 0;
+}
+
+static int realtek_smi_write_byte(struct realtek_priv *priv, u8 data)
+{
+ realtek_smi_write_bits(priv, data, 8);
+ return realtek_smi_wait_for_ack(priv);
+}
+
+static int realtek_smi_write_byte_noack(struct realtek_priv *priv, u8 data)
+{
+ realtek_smi_write_bits(priv, data, 8);
+ return 0;
+}
+
+static int realtek_smi_read_byte0(struct realtek_priv *priv, u8 *data)
+{
+ u32 t;
+
+ /* Read data */
+ realtek_smi_read_bits(priv, 8, &t);
+ *data = (t & 0xff);
+
+ /* Send an ACK */
+ realtek_smi_write_bits(priv, 0x00, 1);
+
+ return 0;
+}
+
+static int realtek_smi_read_byte1(struct realtek_priv *priv, u8 *data)
+{
+ u32 t;
+
+ /* Read data */
+ realtek_smi_read_bits(priv, 8, &t);
+ *data = (t & 0xff);
+
+ /* Send an ACK */
+ realtek_smi_write_bits(priv, 0x01, 1);
+
+ return 0;
+}
+
+static int realtek_smi_read_reg(struct realtek_priv *priv, u32 addr, u32 *data)
+{
+ unsigned long flags;
+ u8 lo = 0;
+ u8 hi = 0;
+ int ret;
+
+ spin_lock_irqsave(&priv->lock, flags);
+
+ realtek_smi_start(priv);
+
+ /* Send READ command */
+ ret = realtek_smi_write_byte(priv, priv->cmd_read);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[7:0] */
+ ret = realtek_smi_write_byte(priv, addr & 0xff);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[15:8] */
+ ret = realtek_smi_write_byte(priv, addr >> 8);
+ if (ret)
+ goto out;
+
+ /* Read DATA[7:0] */
+ realtek_smi_read_byte0(priv, &lo);
+ /* Read DATA[15:8] */
+ realtek_smi_read_byte1(priv, &hi);
+
+ *data = ((u32)lo) | (((u32)hi) << 8);
+
+ ret = 0;
+
+ out:
+ realtek_smi_stop(priv);
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ return ret;
+}
+
+static int realtek_smi_write_reg(struct realtek_priv *priv,
+ u32 addr, u32 data, bool ack)
+{
+ unsigned long flags;
+ int ret;
+
+ spin_lock_irqsave(&priv->lock, flags);
+
+ realtek_smi_start(priv);
+
+ /* Send WRITE command */
+ ret = realtek_smi_write_byte(priv, priv->cmd_write);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[7:0] */
+ ret = realtek_smi_write_byte(priv, addr & 0xff);
+ if (ret)
+ goto out;
+
+ /* Set ADDR[15:8] */
+ ret = realtek_smi_write_byte(priv, addr >> 8);
+ if (ret)
+ goto out;
+
+ /* Write DATA[7:0] */
+ ret = realtek_smi_write_byte(priv, data & 0xff);
+ if (ret)
+ goto out;
+
+ /* Write DATA[15:8] */
+ if (ack)
+ ret = realtek_smi_write_byte(priv, data >> 8);
+ else
+ ret = realtek_smi_write_byte_noack(priv, data >> 8);
+ if (ret)
+ goto out;
+
+ ret = 0;
+
+ out:
+ realtek_smi_stop(priv);
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ return ret;
+}
+
+/* There is one single case when we need to use this accessor and that
+ * is when issueing soft reset. Since the device reset as soon as we write
+ * that bit, no ACK will come back for natural reasons.
+ */
+static int realtek_smi_write_reg_noack(void *ctx, u32 reg, u32 val)
+{
+ return realtek_smi_write_reg(ctx, reg, val, false);
+}
+
+/* Regmap accessors */
+
+static int realtek_smi_write(void *ctx, u32 reg, u32 val)
+{
+ struct realtek_priv *priv = ctx;
+
+ return realtek_smi_write_reg(priv, reg, val, true);
+}
+
+static int realtek_smi_read(void *ctx, u32 reg, u32 *val)
+{
+ struct realtek_priv *priv = ctx;
+
+ return realtek_smi_read_reg(priv, reg, val);
+}
+
+static const struct regmap_config realtek_smi_mdio_regmap_config = {
+ .reg_bits = 10, /* A4..A0 R4..R0 */
+ .val_bits = 16,
+ .reg_stride = 1,
+ /* PHY regs are at 0x8000 */
+ .max_register = 0xffff,
+ .reg_format_endian = REGMAP_ENDIAN_BIG,
+ .reg_read = realtek_smi_read,
+ .reg_write = realtek_smi_write,
+ .cache_type = REGCACHE_NONE,
+};
+
+static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum)
+{
+ struct realtek_priv *priv = bus->priv;
+
+ return priv->ops->phy_read(priv, addr, regnum);
+}
+
+static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum,
+ u16 val)
+{
+ struct realtek_priv *priv = bus->priv;
+
+ return priv->ops->phy_write(priv, addr, regnum, val);
+}
+
+static int realtek_smi_setup_mdio(struct dsa_switch *ds)
+{
+ struct realtek_priv *priv = ds->priv;
+ struct device_node *mdio_np;
+ int ret;
+
+ mdio_np = of_get_compatible_child(priv->dev->of_node, "realtek,smi-mdio");
+ if (!mdio_np) {
+ dev_err(priv->dev, "no MDIO bus node\n");
+ return -ENODEV;
+ }
+
+ priv->slave_mii_bus = devm_mdiobus_alloc(priv->dev);
+ if (!priv->slave_mii_bus) {
+ ret = -ENOMEM;
+ goto err_put_node;
+ }
+ priv->slave_mii_bus->priv = priv;
+ priv->slave_mii_bus->name = "SMI slave MII";
+ priv->slave_mii_bus->read = realtek_smi_mdio_read;
+ priv->slave_mii_bus->write = realtek_smi_mdio_write;
+ snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d",
+ ds->index);
+ priv->slave_mii_bus->dev.of_node = mdio_np;
+ priv->slave_mii_bus->parent = priv->dev;
+ ds->slave_mii_bus = priv->slave_mii_bus;
+
+ ret = devm_of_mdiobus_register(priv->dev, priv->slave_mii_bus, mdio_np);
+ if (ret) {
+ dev_err(priv->dev, "unable to register MDIO bus %s\n",
+ priv->slave_mii_bus->id);
+ goto err_put_node;
+ }
+
+ return 0;
+
+err_put_node:
+ of_node_put(mdio_np);
+
+ return ret;
+}
+
+static int realtek_smi_probe(struct platform_device *pdev)
+{
+ const struct realtek_variant *var;
+ struct device *dev = &pdev->dev;
+ struct realtek_priv *priv;
+ struct device_node *np;
+ int ret;
+
+ var = of_device_get_match_data(dev);
+ np = dev->of_node;
+
+ priv = devm_kzalloc(dev, sizeof(*priv) + var->chip_data_sz, GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+ priv->chip_data = (void *)priv + sizeof(*priv);
+ priv->map = devm_regmap_init(dev, NULL, priv,
+ &realtek_smi_mdio_regmap_config);
+ if (IS_ERR(priv->map)) {
+ ret = PTR_ERR(priv->map);
+ dev_err(dev, "regmap init failed: %d\n", ret);
+ return ret;
+ }
+
+ /* Link forward and backward */
+ priv->dev = dev;
+ priv->clk_delay = var->clk_delay;
+ priv->cmd_read = var->cmd_read;
+ priv->cmd_write = var->cmd_write;
+ priv->ops = var->ops;
+
+ priv->setup_interface = realtek_smi_setup_mdio;
+ priv->write_reg_noack = realtek_smi_write_reg_noack;
+
+ dev_set_drvdata(dev, priv);
+ spin_lock_init(&priv->lock);
+
+ /* TODO: if power is software controlled, set up any regulators here */
+
+ /* Assert then deassert RESET */
+ priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+ if (IS_ERR(priv->reset)) {
+ dev_err(dev, "failed to get RESET GPIO\n");
+ return PTR_ERR(priv->reset);
+ }
+ msleep(REALTEK_SMI_HW_STOP_DELAY);
+ gpiod_set_value(priv->reset, 0);
+ msleep(REALTEK_SMI_HW_START_DELAY);
+ dev_info(dev, "deasserted RESET\n");
+
+ /* Fetch MDIO pins */
+ priv->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW);
+ if (IS_ERR(priv->mdc))
+ return PTR_ERR(priv->mdc);
+ priv->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW);
+ if (IS_ERR(priv->mdio))
+ return PTR_ERR(priv->mdio);
+
+ priv->leds_disabled = of_property_read_bool(np, "realtek,disable-leds");
+
+ ret = priv->ops->detect(priv);
+ if (ret) {
+ dev_err(dev, "unable to detect switch\n");
+ return ret;
+ }
+
+ priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL);
+ if (!priv->ds)
+ return -ENOMEM;
+
+ priv->ds->dev = dev;
+ priv->ds->num_ports = priv->num_ports;
+ priv->ds->priv = priv;
+
+ priv->ds->ops = var->ds_ops_smi;
+ ret = dsa_register_switch(priv->ds);
+ if (ret) {
+ dev_err_probe(dev, ret, "unable to register switch\n");
+ return ret;
+ }
+ return 0;
+}
+
+static int realtek_smi_remove(struct platform_device *pdev)
+{
+ struct realtek_priv *priv = platform_get_drvdata(pdev);
+
+ if (!priv)
+ return 0;
+
+ dsa_unregister_switch(priv->ds);
+ if (priv->slave_mii_bus)
+ of_node_put(priv->slave_mii_bus->dev.of_node);
+ gpiod_set_value(priv->reset, 1);
+
+ platform_set_drvdata(pdev, NULL);
+
+ return 0;
+}
+
+static void realtek_smi_shutdown(struct platform_device *pdev)
+{
+ struct realtek_priv *priv = platform_get_drvdata(pdev);
+
+ if (!priv)
+ return;
+
+ dsa_switch_shutdown(priv->ds);
+
+ platform_set_drvdata(pdev, NULL);
+}
+
+static const struct of_device_id realtek_smi_of_match[] = {
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB)
+ {
+ .compatible = "realtek,rtl8366rb",
+ .data = &rtl8366rb_variant,
+ },
+#endif
+ {
+ /* FIXME: add support for RTL8366S and more */
+ .compatible = "realtek,rtl8366s",
+ .data = NULL,
+ },
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB)
+ {
+ .compatible = "realtek,rtl8365mb",
+ .data = &rtl8365mb_variant,
+ },
+ {
+ .compatible = "realtek,rtl8367s",
+ .data = &rtl8365mb_variant,
+ },
+#endif
+ { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, realtek_smi_of_match);
+
+static struct platform_driver realtek_smi_driver = {
+ .driver = {
+ .name = "realtek-smi",
+ .of_match_table = of_match_ptr(realtek_smi_of_match),
+ },
+ .probe = realtek_smi_probe,
+ .remove = realtek_smi_remove,
+ .shutdown = realtek_smi_shutdown,
+};
+module_platform_driver(realtek_smi_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Driver for Realtek ethernet switch connected via SMI interface");
+MODULE_LICENSE("GPL");
#include <linux/gpio/consumer.h>
#include <net/dsa.h>
-struct realtek_smi_ops;
+struct realtek_ops;
struct dentry;
struct inode;
struct file;
const char *name;
};
-/**
+/*
* struct rtl8366_vlan_mc - Virtual LAN member configuration
*/
struct rtl8366_vlan_mc {
u8 fid;
};
-struct realtek_smi {
+struct realtek_priv {
struct device *dev;
struct gpio_desc *reset;
struct gpio_desc *mdc;
struct gpio_desc *mdio;
struct regmap *map;
struct mii_bus *slave_mii_bus;
+ struct mii_bus *bus;
+ int mdio_addr;
unsigned int clk_delay;
u8 cmd_read;
unsigned int num_mib_counters;
struct rtl8366_mib_counter *mib_counters;
- const struct realtek_smi_ops *ops;
+ const struct realtek_ops *ops;
+ int (*setup_interface)(struct dsa_switch *ds);
+ int (*write_reg_noack)(void *ctx, u32 addr, u32 data);
int vlan_enabled;
int vlan4k_enabled;
void *chip_data; /* Per-chip extra variant data */
};
-/**
- * struct realtek_smi_ops - vtable for the per-SMI-chiptype operations
+/*
+ * struct realtek_ops - vtable for the per-SMI-chiptype operations
* @detect: detects the chiptype
*/
-struct realtek_smi_ops {
- int (*detect)(struct realtek_smi *smi);
- int (*reset_chip)(struct realtek_smi *smi);
- int (*setup)(struct realtek_smi *smi);
- void (*cleanup)(struct realtek_smi *smi);
- int (*get_mib_counter)(struct realtek_smi *smi,
+struct realtek_ops {
+ int (*detect)(struct realtek_priv *priv);
+ int (*reset_chip)(struct realtek_priv *priv);
+ int (*setup)(struct realtek_priv *priv);
+ void (*cleanup)(struct realtek_priv *priv);
+ int (*get_mib_counter)(struct realtek_priv *priv,
int port,
struct rtl8366_mib_counter *mib,
u64 *mibvalue);
- int (*get_vlan_mc)(struct realtek_smi *smi, u32 index,
+ int (*get_vlan_mc)(struct realtek_priv *priv, u32 index,
struct rtl8366_vlan_mc *vlanmc);
- int (*set_vlan_mc)(struct realtek_smi *smi, u32 index,
+ int (*set_vlan_mc)(struct realtek_priv *priv, u32 index,
const struct rtl8366_vlan_mc *vlanmc);
- int (*get_vlan_4k)(struct realtek_smi *smi, u32 vid,
+ int (*get_vlan_4k)(struct realtek_priv *priv, u32 vid,
struct rtl8366_vlan_4k *vlan4k);
- int (*set_vlan_4k)(struct realtek_smi *smi,
+ int (*set_vlan_4k)(struct realtek_priv *priv,
const struct rtl8366_vlan_4k *vlan4k);
- int (*get_mc_index)(struct realtek_smi *smi, int port, int *val);
- int (*set_mc_index)(struct realtek_smi *smi, int port, int index);
- bool (*is_vlan_valid)(struct realtek_smi *smi, unsigned int vlan);
- int (*enable_vlan)(struct realtek_smi *smi, bool enable);
- int (*enable_vlan4k)(struct realtek_smi *smi, bool enable);
- int (*enable_port)(struct realtek_smi *smi, int port, bool enable);
- int (*phy_read)(struct realtek_smi *smi, int phy, int regnum);
- int (*phy_write)(struct realtek_smi *smi, int phy, int regnum,
+ int (*get_mc_index)(struct realtek_priv *priv, int port, int *val);
+ int (*set_mc_index)(struct realtek_priv *priv, int port, int index);
+ bool (*is_vlan_valid)(struct realtek_priv *priv, unsigned int vlan);
+ int (*enable_vlan)(struct realtek_priv *priv, bool enable);
+ int (*enable_vlan4k)(struct realtek_priv *priv, bool enable);
+ int (*enable_port)(struct realtek_priv *priv, int port, bool enable);
+ int (*phy_read)(struct realtek_priv *priv, int phy, int regnum);
+ int (*phy_write)(struct realtek_priv *priv, int phy, int regnum,
u16 val);
};
-struct realtek_smi_variant {
- const struct dsa_switch_ops *ds_ops;
- const struct realtek_smi_ops *ops;
+struct realtek_variant {
+ const struct dsa_switch_ops *ds_ops_smi;
+ const struct dsa_switch_ops *ds_ops_mdio;
+ const struct realtek_ops *ops;
unsigned int clk_delay;
u8 cmd_read;
u8 cmd_write;
size_t chip_data_sz;
};
-/* SMI core calls */
-int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
- u32 data);
-int realtek_smi_setup_mdio(struct realtek_smi *smi);
-
/* RTL8366 library helpers */
-int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used);
-int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+int rtl8366_mc_is_used(struct realtek_priv *priv, int mc_index, int *used);
+int rtl8366_set_vlan(struct realtek_priv *priv, int vid, u32 member,
u32 untag, u32 fid);
-int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+int rtl8366_set_pvid(struct realtek_priv *priv, unsigned int port,
unsigned int vid);
-int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable);
-int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable);
-int rtl8366_reset_vlan(struct realtek_smi *smi);
+int rtl8366_enable_vlan4k(struct realtek_priv *priv, bool enable);
+int rtl8366_enable_vlan(struct realtek_priv *priv, bool enable);
+int rtl8366_reset_vlan(struct realtek_priv *priv);
int rtl8366_vlan_add(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan,
struct netlink_ext_ack *extack);
int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset);
void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
-extern const struct realtek_smi_variant rtl8366rb_variant;
-extern const struct realtek_smi_variant rtl8365mb_variant;
+extern const struct realtek_variant rtl8366rb_variant;
+extern const struct realtek_variant rtl8365mb_variant;
#endif /* _REALTEK_SMI_H */
#include <linux/regmap.h>
#include <linux/if_bridge.h>
-#include "realtek-smi-core.h"
+#include "realtek.h"
/* Chip-specific data and limits */
-#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367
-#define RTL8365MB_CPU_PORT_NUM_8365MB_VC 6
-#define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC 2112
+#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367
+#define RTL8365MB_CHIP_VER_8365MB_VC 0x0040
+
+#define RTL8365MB_CHIP_ID_8367S 0x6367
+#define RTL8365MB_CHIP_VER_8367S 0x00A0
+
+#define RTL8365MB_CHIP_ID_8367RB 0x6367
+#define RTL8365MB_CHIP_VER_8367RB 0x0020
/* Family-specific data and limits */
-#define RTL8365MB_PHYADDRMAX 7
-#define RTL8365MB_NUM_PHYREGS 32
-#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1)
-#define RTL8365MB_MAX_NUM_PORTS (RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1)
+#define RTL8365MB_PHYADDRMAX 7
+#define RTL8365MB_NUM_PHYREGS 32
+#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1)
+/* RTL8370MB and RTL8310SR, possibly suportable by this driver, have 10 ports */
+#define RTL8365MB_MAX_NUM_PORTS 10
+#define RTL8365MB_LEARN_LIMIT_MAX 2112
+
+/* valid for all 6-port or less variants */
+static const int rtl8365mb_extint_port_map[] = { -1, -1, -1, -1, -1, -1, 1, 2, -1, -1};
/* Chip identification registers */
#define RTL8365MB_CHIP_ID_REG 0x1300
/* The PHY OCP addresses of PHY registers 0~31 start here */
#define RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE 0xA400
-/* EXT port interface mode values - used in DIGITAL_INTERFACE_SELECT */
+/* EXT interface port mode values - used in DIGITAL_INTERFACE_SELECT */
#define RTL8365MB_EXT_PORT_MODE_DISABLE 0
#define RTL8365MB_EXT_PORT_MODE_RGMII 1
#define RTL8365MB_EXT_PORT_MODE_MII_MAC 2
#define RTL8365MB_EXT_PORT_MODE_1000X 12
#define RTL8365MB_EXT_PORT_MODE_100FX 13
-/* EXT port interface mode configuration registers 0~1 */
-#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305
-#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3
-#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extport) \
- (RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 + \
- ((_extport) >> 1) * (0x13C3 - 0x1305))
-#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extport) \
- (0xF << (((_extport) % 2)))
-#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extport) \
- (((_extport) % 2) * 4)
-
-/* EXT port RGMII TX/RX delay configuration registers 1~2 */
-#define RTL8365MB_EXT_RGMXF_REG1 0x1307
-#define RTL8365MB_EXT_RGMXF_REG2 0x13C5
-#define RTL8365MB_EXT_RGMXF_REG(_extport) \
- (RTL8365MB_EXT_RGMXF_REG1 + \
- (((_extport) >> 1) * (0x13C5 - 0x1307)))
+/* Realtek docs and driver uses logic number as EXT_PORT0=16, EXT_PORT1=17,
+ * EXT_PORT2=18, to interact with switch ports. That logic number is internally
+ * converted to either a physical port number (0..9) or an external interface id (0..2),
+ * depending on which function was called. The external interface id is calculated as
+ * (ext_id=logic_port-15), while the logical to physical map depends on the chip id/version.
+ *
+ * EXT_PORT0 mentioned in datasheets and rtl8367c driver is used in this driver
+ * as extid==1, EXT_PORT2, mentioned in Realtek rtl8367c driver for 10-port switches,
+ * would have an ext_id of 3 (out of range for most extint macros) and ext_id 0 does
+ * not seem to be used as well for this family.
+ */
+
+/* EXT interface mode configuration registers 0~1 */
+#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 /* EXT1 */
+#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 /* EXT2 */
+#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extint) \
+ ((_extint) == 1 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 : \
+ (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 : \
+ 0x0)
+#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extint) \
+ (0xF << (((_extint) % 2)))
+#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extint) \
+ (((_extint) % 2) * 4)
+
+/* EXT interface RGMII TX/RX delay configuration registers 0~2 */
+#define RTL8365MB_EXT_RGMXF_REG0 0x1306 /* EXT0 */
+#define RTL8365MB_EXT_RGMXF_REG1 0x1307 /* EXT1 */
+#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 /* EXT2 */
+#define RTL8365MB_EXT_RGMXF_REG(_extint) \
+ ((_extint) == 0 ? RTL8365MB_EXT_RGMXF_REG0 : \
+ (_extint) == 1 ? RTL8365MB_EXT_RGMXF_REG1 : \
+ (_extint) == 2 ? RTL8365MB_EXT_RGMXF_REG2 : \
+ 0x0)
#define RTL8365MB_EXT_RGMXF_RXDELAY_MASK 0x0007
#define RTL8365MB_EXT_RGMXF_TXDELAY_MASK 0x0008
-/* External port speed values - used in DIGITAL_INTERFACE_FORCE */
+/* External interface port speed values - used in DIGITAL_INTERFACE_FORCE */
#define RTL8365MB_PORT_SPEED_10M 0
#define RTL8365MB_PORT_SPEED_100M 1
#define RTL8365MB_PORT_SPEED_1000M 2
-/* EXT port force configuration registers 0~2 */
-#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310
-#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311
-#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4
-#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extport) \
- (RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 + \
- ((_extport) & 0x1) + \
- ((((_extport) >> 1) & 0x1) * (0x13C4 - 0x1310)))
+/* EXT interface force configuration registers 0~2 */
+#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 /* EXT0 */
+#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 /* EXT1 */
+#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 /* EXT2 */
+#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extint) \
+ ((_extint) == 0 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 : \
+ (_extint) == 1 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 : \
+ (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 : \
+ 0x0)
#define RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK 0x1000
#define RTL8365MB_DIGITAL_INTERFACE_FORCE_NWAY_MASK 0x0080
#define RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK 0x0040
/**
* struct rtl8365mb_port - private per-port data
- * @smi: pointer to parent realtek_smi data
+ * @priv: pointer to parent realtek_priv data
* @index: DSA port index, same as dsa_port::index
* @stats: link statistics populated by rtl8365mb_stats_poll, ready for atomic
* access via rtl8365mb_get_stats64
* @mib_work: delayed work for polling MIB counters
*/
struct rtl8365mb_port {
- struct realtek_smi *smi;
+ struct realtek_priv *priv;
unsigned int index;
struct rtnl_link_stats64 stats;
spinlock_t stats_lock;
/**
* struct rtl8365mb - private chip-specific driver data
- * @smi: pointer to parent realtek_smi data
+ * @priv: pointer to parent realtek_priv data
* @irq: registered IRQ or zero
* @chip_id: chip identifier
* @chip_ver: chip silicon revision
* @port_mask: mask of all ports
* @learn_limit_max: maximum number of L2 addresses the chip can learn
- * @cpu: CPU tagging and CPU port configuration for this chip
* @mib_lock: prevent concurrent reads of MIB counters
* @ports: per-port data
* @jam_table: chip-specific initialization jam table
* Private data for this driver.
*/
struct rtl8365mb {
- struct realtek_smi *smi;
+ struct realtek_priv *priv;
int irq;
u32 chip_id;
u32 chip_ver;
u32 port_mask;
u32 learn_limit_max;
- struct rtl8365mb_cpu cpu;
struct mutex mib_lock;
struct rtl8365mb_port ports[RTL8365MB_MAX_NUM_PORTS];
const struct rtl8365mb_jam_tbl_entry *jam_table;
size_t jam_size;
};
-static int rtl8365mb_phy_poll_busy(struct realtek_smi *smi)
+static int rtl8365mb_phy_poll_busy(struct realtek_priv *priv)
{
u32 val;
- return regmap_read_poll_timeout(smi->map,
+ return regmap_read_poll_timeout(priv->map,
RTL8365MB_INDIRECT_ACCESS_STATUS_REG,
val, !val, 10, 100);
}
-static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy,
+static int rtl8365mb_phy_ocp_prepare(struct realtek_priv *priv, int phy,
u32 ocp_addr)
{
u32 val;
/* Set OCP prefix */
val = FIELD_GET(RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK, ocp_addr);
ret = regmap_update_bits(
- smi->map, RTL8365MB_GPHY_OCP_MSB_0_REG,
+ priv->map, RTL8365MB_GPHY_OCP_MSB_0_REG,
RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK,
FIELD_PREP(RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, val));
if (ret)
ocp_addr >> 1);
val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK,
ocp_addr >> 6);
- ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG,
+ ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG,
val);
if (ret)
return ret;
return 0;
}
-static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy,
+static int rtl8365mb_phy_ocp_read(struct realtek_priv *priv, int phy,
u32 ocp_addr, u16 *data)
{
u32 val;
int ret;
- ret = rtl8365mb_phy_poll_busy(smi);
+ ret = rtl8365mb_phy_poll_busy(priv);
if (ret)
return ret;
- ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr);
+ ret = rtl8365mb_phy_ocp_prepare(priv, phy, ocp_addr);
if (ret)
return ret;
RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) |
FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK,
RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ);
- ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val);
+ ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val);
if (ret)
return ret;
- ret = rtl8365mb_phy_poll_busy(smi);
+ ret = rtl8365mb_phy_poll_busy(priv);
if (ret)
return ret;
/* Get PHY register data */
- ret = regmap_read(smi->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG,
+ ret = regmap_read(priv->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG,
&val);
if (ret)
return ret;
return 0;
}
-static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy,
+static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy,
u32 ocp_addr, u16 data)
{
u32 val;
int ret;
- ret = rtl8365mb_phy_poll_busy(smi);
+ ret = rtl8365mb_phy_poll_busy(priv);
if (ret)
return ret;
- ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr);
+ ret = rtl8365mb_phy_ocp_prepare(priv, phy, ocp_addr);
if (ret)
return ret;
/* Set PHY register data */
- ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG,
+ ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG,
data);
if (ret)
return ret;
RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) |
FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK,
RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE);
- ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val);
+ ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val);
if (ret)
return ret;
- ret = rtl8365mb_phy_poll_busy(smi);
+ ret = rtl8365mb_phy_poll_busy(priv);
if (ret)
return ret;
return 0;
}
-static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum)
+static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum)
{
u32 ocp_addr;
u16 val;
ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2;
- ret = rtl8365mb_phy_ocp_read(smi, phy, ocp_addr, &val);
+ ret = rtl8365mb_phy_ocp_read(priv, phy, ocp_addr, &val);
if (ret) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to read PHY%d reg %02x @ %04x, ret %d\n", phy,
regnum, ocp_addr, ret);
return ret;
}
- dev_dbg(smi->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n",
+ dev_dbg(priv->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n",
phy, regnum, ocp_addr, val);
return val;
}
-static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum,
+static int rtl8365mb_phy_write(struct realtek_priv *priv, int phy, int regnum,
u16 val)
{
u32 ocp_addr;
ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2;
- ret = rtl8365mb_phy_ocp_write(smi, phy, ocp_addr, val);
+ ret = rtl8365mb_phy_ocp_write(priv, phy, ocp_addr, val);
if (ret) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to write PHY%d reg %02x @ %04x, ret %d\n", phy,
regnum, ocp_addr, ret);
return ret;
}
- dev_dbg(smi->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n",
+ dev_dbg(priv->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n",
phy, regnum, ocp_addr, val);
return 0;
}
+static int rtl8365mb_dsa_phy_read(struct dsa_switch *ds, int phy, int regnum)
+{
+ return rtl8365mb_phy_read(ds->priv, phy, regnum);
+}
+
+static int rtl8365mb_dsa_phy_write(struct dsa_switch *ds, int phy, int regnum,
+ u16 val)
+{
+ return rtl8365mb_phy_write(ds->priv, phy, regnum, val);
+}
+
static enum dsa_tag_protocol
rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port,
enum dsa_tag_protocol mp)
return DSA_TAG_PROTO_RTL8_4;
}
-static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port,
+static int rtl8365mb_ext_config_rgmii(struct realtek_priv *priv, int port,
phy_interface_t interface)
{
struct device_node *dn;
struct dsa_port *dp;
int tx_delay = 0;
int rx_delay = 0;
- int ext_port;
+ int ext_int;
u32 val;
int ret;
- if (port == smi->cpu_port) {
- ext_port = 1;
- } else {
- dev_err(smi->dev, "only one EXT port is currently supported\n");
+ ext_int = rtl8365mb_extint_port_map[port];
+
+ if (ext_int <= 0) {
+ dev_err(priv->dev, "Port %d is not an external interface port\n", port);
return -EINVAL;
}
- dp = dsa_to_port(smi->ds, port);
+ dp = dsa_to_port(priv->ds, port);
dn = dp->dn;
/* Set the RGMII TX/RX delay
if (val == 0 || val == 2)
tx_delay = val / 2;
else
- dev_warn(smi->dev,
- "EXT port TX delay must be 0 or 2 ns\n");
+ dev_warn(priv->dev,
+ "EXT interface TX delay must be 0 or 2 ns\n");
}
if (!of_property_read_u32(dn, "rx-internal-delay-ps", &val)) {
if (val <= 7)
rx_delay = val;
else
- dev_warn(smi->dev,
- "EXT port RX delay must be 0 to 2.1 ns\n");
+ dev_warn(priv->dev,
+ "EXT interface RX delay must be 0 to 2.1 ns\n");
}
ret = regmap_update_bits(
- smi->map, RTL8365MB_EXT_RGMXF_REG(ext_port),
+ priv->map, RTL8365MB_EXT_RGMXF_REG(ext_int),
RTL8365MB_EXT_RGMXF_TXDELAY_MASK |
RTL8365MB_EXT_RGMXF_RXDELAY_MASK,
FIELD_PREP(RTL8365MB_EXT_RGMXF_TXDELAY_MASK, tx_delay) |
return ret;
ret = regmap_update_bits(
- smi->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_port),
- RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_port),
+ priv->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_int),
+ RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_int),
RTL8365MB_EXT_PORT_MODE_RGMII
<< RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(
- ext_port));
+ ext_int));
if (ret)
return ret;
return 0;
}
-static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port,
+static int rtl8365mb_ext_config_forcemode(struct realtek_priv *priv, int port,
bool link, int speed, int duplex,
bool tx_pause, bool rx_pause)
{
u32 r_duplex;
u32 r_speed;
u32 r_link;
- int ext_port;
+ int ext_int;
int val;
int ret;
- if (port == smi->cpu_port) {
- ext_port = 1;
- } else {
- dev_err(smi->dev, "only one EXT port is currently supported\n");
+ ext_int = rtl8365mb_extint_port_map[port];
+
+ if (ext_int <= 0) {
+ dev_err(priv->dev, "Port %d is not an external interface port\n", port);
return -EINVAL;
}
} else if (speed == SPEED_10) {
r_speed = RTL8365MB_PORT_SPEED_10M;
} else {
- dev_err(smi->dev, "unsupported port speed %s\n",
+ dev_err(priv->dev, "unsupported port speed %s\n",
phy_speed_to_str(speed));
return -EINVAL;
}
} else if (duplex == DUPLEX_HALF) {
r_duplex = 0;
} else {
- dev_err(smi->dev, "unsupported duplex %s\n",
+ dev_err(priv->dev, "unsupported duplex %s\n",
phy_duplex_to_str(duplex));
return -EINVAL;
}
FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK,
r_duplex) |
FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK, r_speed);
- ret = regmap_write(smi->map,
- RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_port),
+ ret = regmap_write(priv->map,
+ RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_int),
val);
if (ret)
return ret;
static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port,
phy_interface_t interface)
{
- if (dsa_is_user_port(ds, port) &&
+ int ext_int;
+
+ ext_int = rtl8365mb_extint_port_map[port];
+
+ if (ext_int < 0 &&
(interface == PHY_INTERFACE_MODE_NA ||
interface == PHY_INTERFACE_MODE_INTERNAL ||
interface == PHY_INTERFACE_MODE_GMII))
/* Internal PHY */
return true;
- else if (dsa_is_cpu_port(ds, port) &&
+ else if ((ext_int >= 1) &&
phy_interface_mode_is_rgmii(interface))
/* Extension MAC */
return true;
unsigned long *supported,
struct phylink_link_state *state)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0 };
/* include/linux/phylink.h says:
*/
if (state->interface != PHY_INTERFACE_MODE_NA &&
!rtl8365mb_phy_mode_supported(ds, port, state->interface)) {
- dev_err(smi->dev, "phy mode %s is unsupported on port %d\n",
+ dev_err(priv->dev, "phy mode %s is unsupported on port %d\n",
phy_modes(state->interface), port);
linkmode_zero(supported);
return;
unsigned int mode,
const struct phylink_link_state *state)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret;
if (!rtl8365mb_phy_mode_supported(ds, port, state->interface)) {
- dev_err(smi->dev, "phy mode %s is unsupported on port %d\n",
+ dev_err(priv->dev, "phy mode %s is unsupported on port %d\n",
phy_modes(state->interface), port);
return;
}
if (mode != MLO_AN_PHY && mode != MLO_AN_FIXED) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"port %d supports only conventional PHY or fixed-link\n",
port);
return;
}
if (phy_interface_mode_is_rgmii(state->interface)) {
- ret = rtl8365mb_ext_config_rgmii(smi, port, state->interface);
+ ret = rtl8365mb_ext_config_rgmii(priv, port, state->interface);
if (ret)
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to configure RGMII mode on port %d: %d\n",
port, ret);
return;
unsigned int mode,
phy_interface_t interface)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb_port *p;
struct rtl8365mb *mb;
int ret;
- mb = smi->chip_data;
+ mb = priv->chip_data;
p = &mb->ports[port];
cancel_delayed_work_sync(&p->mib_work);
if (phy_interface_mode_is_rgmii(interface)) {
- ret = rtl8365mb_ext_config_forcemode(smi, port, false, 0, 0,
+ ret = rtl8365mb_ext_config_forcemode(priv, port, false, 0, 0,
false, false);
if (ret)
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to reset forced mode on port %d: %d\n",
port, ret);
int duplex, bool tx_pause,
bool rx_pause)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb_port *p;
struct rtl8365mb *mb;
int ret;
- mb = smi->chip_data;
+ mb = priv->chip_data;
p = &mb->ports[port];
schedule_delayed_work(&p->mib_work, 0);
if (phy_interface_mode_is_rgmii(interface)) {
- ret = rtl8365mb_ext_config_forcemode(smi, port, true, speed,
+ ret = rtl8365mb_ext_config_forcemode(priv, port, true, speed,
duplex, tx_pause,
rx_pause);
if (ret)
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to force mode on port %d: %d\n", port,
ret);
static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port,
u8 state)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
enum rtl8365mb_stp_state val;
int msti = 0;
val = RTL8365MB_STP_STATE_FORWARDING;
break;
default:
- dev_err(smi->dev, "invalid STP state: %u\n", state);
+ dev_err(priv->dev, "invalid STP state: %u\n", state);
return;
}
- regmap_update_bits(smi->map, RTL8365MB_MSTI_CTRL_REG(msti, port),
+ regmap_update_bits(priv->map, RTL8365MB_MSTI_CTRL_REG(msti, port),
RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(port),
val << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(port));
}
-static int rtl8365mb_port_set_learning(struct realtek_smi *smi, int port,
+static int rtl8365mb_port_set_learning(struct realtek_priv *priv, int port,
bool enable)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
/* Enable/disable learning by limiting the number of L2 addresses the
* port can learn. Realtek documentation states that a limit of zero
* disables learning. When enabling learning, set it to the chip's
* maximum.
*/
- return regmap_write(smi->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port),
+ return regmap_write(priv->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port),
enable ? mb->learn_limit_max : 0);
}
-static int rtl8365mb_port_set_isolation(struct realtek_smi *smi, int port,
+static int rtl8365mb_port_set_isolation(struct realtek_priv *priv, int port,
u32 mask)
{
- return regmap_write(smi->map, RTL8365MB_PORT_ISOLATION_REG(port), mask);
+ return regmap_write(priv->map, RTL8365MB_PORT_ISOLATION_REG(port), mask);
}
-static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port,
+static int rtl8365mb_mib_counter_read(struct realtek_priv *priv, int port,
u32 offset, u32 length, u64 *mibvalue)
{
u64 tmpvalue = 0;
* and then poll the control register before reading the value from some
* counter registers.
*/
- ret = regmap_write(smi->map, RTL8365MB_MIB_ADDRESS_REG,
+ ret = regmap_write(priv->map, RTL8365MB_MIB_ADDRESS_REG,
RTL8365MB_MIB_ADDRESS(port, offset));
if (ret)
return ret;
/* Poll for completion */
- ret = regmap_read_poll_timeout(smi->map, RTL8365MB_MIB_CTRL0_REG, val,
+ ret = regmap_read_poll_timeout(priv->map, RTL8365MB_MIB_CTRL0_REG, val,
!(val & RTL8365MB_MIB_CTRL0_BUSY_MASK),
10, 100);
if (ret)
/* Read the MIB counter 16 bits at a time */
for (i = 0; i < length; i++) {
- ret = regmap_read(smi->map,
+ ret = regmap_read(priv->map,
RTL8365MB_MIB_COUNTER_REG(offset - i), &val);
if (ret)
return ret;
static void rtl8365mb_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb *mb;
int ret;
int i;
- mb = smi->chip_data;
+ mb = priv->chip_data;
mutex_lock(&mb->mib_lock);
for (i = 0; i < RTL8365MB_MIB_END; i++) {
struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i];
- ret = rtl8365mb_mib_counter_read(smi, port, mib->offset,
+ ret = rtl8365mb_mib_counter_read(priv, port, mib->offset,
mib->length, &data[i]);
if (ret) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to read port %d counters: %d\n", port,
ret);
break;
static void rtl8365mb_get_phy_stats(struct dsa_switch *ds, int port,
struct ethtool_eth_phy_stats *phy_stats)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb_mib_counter *mib;
struct rtl8365mb *mb;
- mb = smi->chip_data;
+ mb = priv->chip_data;
mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3StatsSymbolErrors];
mutex_lock(&mb->mib_lock);
- rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length,
+ rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length,
&phy_stats->SymbolErrorDuringCarrier);
mutex_unlock(&mb->mib_lock);
}
[RTL8365MB_MIB_dot3StatsExcessiveCollisions] = 1,
};
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb *mb;
int ret;
int i;
- mb = smi->chip_data;
+ mb = priv->chip_data;
mutex_lock(&mb->mib_lock);
for (i = 0; i < RTL8365MB_MIB_END; i++) {
if (!cnt[i])
continue;
- ret = rtl8365mb_mib_counter_read(smi, port, mib->offset,
+ ret = rtl8365mb_mib_counter_read(priv, port, mib->offset,
mib->length, &cnt[i]);
if (ret)
break;
static void rtl8365mb_get_ctrl_stats(struct dsa_switch *ds, int port,
struct ethtool_eth_ctrl_stats *ctrl_stats)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb_mib_counter *mib;
struct rtl8365mb *mb;
- mb = smi->chip_data;
+ mb = priv->chip_data;
mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3ControlInUnknownOpcodes];
mutex_lock(&mb->mib_lock);
- rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length,
+ rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length,
&ctrl_stats->UnsupportedOpcodesReceived);
mutex_unlock(&mb->mib_lock);
}
-static void rtl8365mb_stats_update(struct realtek_smi *smi, int port)
+static void rtl8365mb_stats_update(struct realtek_priv *priv, int port)
{
u64 cnt[RTL8365MB_MIB_END] = {
[RTL8365MB_MIB_ifOutOctets] = 1,
[RTL8365MB_MIB_dot3StatsFCSErrors] = 1,
[RTL8365MB_MIB_dot3StatsLateCollisions] = 1,
};
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
struct rtnl_link_stats64 *stats;
int ret;
int i;
if (!cnt[i])
continue;
- ret = rtl8365mb_mib_counter_read(smi, port, c->offset,
+ ret = rtl8365mb_mib_counter_read(priv, port, c->offset,
c->length, &cnt[i]);
if (ret)
break;
struct rtl8365mb_port *p = container_of(to_delayed_work(work),
struct rtl8365mb_port,
mib_work);
- struct realtek_smi *smi = p->smi;
+ struct realtek_priv *priv = p->priv;
- rtl8365mb_stats_update(smi, p->index);
+ rtl8365mb_stats_update(priv, p->index);
schedule_delayed_work(&p->mib_work, RTL8365MB_STATS_INTERVAL_JIFFIES);
}
static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port,
struct rtnl_link_stats64 *s)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8365mb_port *p;
struct rtl8365mb *mb;
- mb = smi->chip_data;
+ mb = priv->chip_data;
p = &mb->ports[port];
spin_lock(&p->stats_lock);
spin_unlock(&p->stats_lock);
}
-static void rtl8365mb_stats_setup(struct realtek_smi *smi)
+static void rtl8365mb_stats_setup(struct realtek_priv *priv)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
int i;
/* Per-chip global mutex to protect MIB counter access, since doing
*/
mutex_init(&mb->mib_lock);
- for (i = 0; i < smi->num_ports; i++) {
+ for (i = 0; i < priv->num_ports; i++) {
struct rtl8365mb_port *p = &mb->ports[i];
- if (dsa_is_unused_port(smi->ds, i))
+ if (dsa_is_unused_port(priv->ds, i))
continue;
/* Per-port spinlock to protect the stats64 data */
}
}
-static void rtl8365mb_stats_teardown(struct realtek_smi *smi)
+static void rtl8365mb_stats_teardown(struct realtek_priv *priv)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
int i;
- for (i = 0; i < smi->num_ports; i++) {
+ for (i = 0; i < priv->num_ports; i++) {
struct rtl8365mb_port *p = &mb->ports[i];
- if (dsa_is_unused_port(smi->ds, i))
+ if (dsa_is_unused_port(priv->ds, i))
continue;
cancel_delayed_work_sync(&p->mib_work);
}
}
-static int rtl8365mb_get_and_clear_status_reg(struct realtek_smi *smi, u32 reg,
+static int rtl8365mb_get_and_clear_status_reg(struct realtek_priv *priv, u32 reg,
u32 *val)
{
int ret;
- ret = regmap_read(smi->map, reg, val);
+ ret = regmap_read(priv->map, reg, val);
if (ret)
return ret;
- return regmap_write(smi->map, reg, *val);
+ return regmap_write(priv->map, reg, *val);
}
static irqreturn_t rtl8365mb_irq(int irq, void *data)
{
- struct realtek_smi *smi = data;
+ struct realtek_priv *priv = data;
unsigned long line_changes = 0;
struct rtl8365mb *mb;
u32 stat;
int line;
int ret;
- mb = smi->chip_data;
+ mb = priv->chip_data;
- ret = rtl8365mb_get_and_clear_status_reg(smi, RTL8365MB_INTR_STATUS_REG,
+ ret = rtl8365mb_get_and_clear_status_reg(priv, RTL8365MB_INTR_STATUS_REG,
&stat);
if (ret)
goto out_error;
u32 val;
ret = rtl8365mb_get_and_clear_status_reg(
- smi, RTL8365MB_PORT_LINKUP_IND_REG, &val);
+ priv, RTL8365MB_PORT_LINKUP_IND_REG, &val);
if (ret)
goto out_error;
linkup_ind = FIELD_GET(RTL8365MB_PORT_LINKUP_IND_MASK, val);
ret = rtl8365mb_get_and_clear_status_reg(
- smi, RTL8365MB_PORT_LINKDOWN_IND_REG, &val);
+ priv, RTL8365MB_PORT_LINKDOWN_IND_REG, &val);
if (ret)
goto out_error;
if (!line_changes)
goto out_none;
- for_each_set_bit(line, &line_changes, smi->num_ports) {
- int child_irq = irq_find_mapping(smi->irqdomain, line);
+ for_each_set_bit(line, &line_changes, priv->num_ports) {
+ int child_irq = irq_find_mapping(priv->irqdomain, line);
handle_nested_irq(child_irq);
}
return IRQ_HANDLED;
out_error:
- dev_err(smi->dev, "failed to read interrupt status: %d\n", ret);
+ dev_err(priv->dev, "failed to read interrupt status: %d\n", ret);
out_none:
return IRQ_NONE;
.xlate = irq_domain_xlate_onecell,
};
-static int rtl8365mb_set_irq_enable(struct realtek_smi *smi, bool enable)
+static int rtl8365mb_set_irq_enable(struct realtek_priv *priv, bool enable)
{
- return regmap_update_bits(smi->map, RTL8365MB_INTR_CTRL_REG,
+ return regmap_update_bits(priv->map, RTL8365MB_INTR_CTRL_REG,
RTL8365MB_INTR_LINK_CHANGE_MASK,
FIELD_PREP(RTL8365MB_INTR_LINK_CHANGE_MASK,
enable ? 1 : 0));
}
-static int rtl8365mb_irq_enable(struct realtek_smi *smi)
+static int rtl8365mb_irq_enable(struct realtek_priv *priv)
{
- return rtl8365mb_set_irq_enable(smi, true);
+ return rtl8365mb_set_irq_enable(priv, true);
}
-static int rtl8365mb_irq_disable(struct realtek_smi *smi)
+static int rtl8365mb_irq_disable(struct realtek_priv *priv)
{
- return rtl8365mb_set_irq_enable(smi, false);
+ return rtl8365mb_set_irq_enable(priv, false);
}
-static int rtl8365mb_irq_setup(struct realtek_smi *smi)
+static int rtl8365mb_irq_setup(struct realtek_priv *priv)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
struct device_node *intc;
u32 irq_trig;
int virq;
int ret;
int i;
- intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller");
+ intc = of_get_child_by_name(priv->dev->of_node, "interrupt-controller");
if (!intc) {
- dev_err(smi->dev, "missing child interrupt-controller node\n");
+ dev_err(priv->dev, "missing child interrupt-controller node\n");
return -EINVAL;
}
irq = of_irq_get(intc, 0);
if (irq <= 0) {
if (irq != -EPROBE_DEFER)
- dev_err(smi->dev, "failed to get parent irq: %d\n",
+ dev_err(priv->dev, "failed to get parent irq: %d\n",
irq);
ret = irq ? irq : -EINVAL;
goto out_put_node;
}
- smi->irqdomain = irq_domain_add_linear(intc, smi->num_ports,
- &rtl8365mb_irqdomain_ops, smi);
- if (!smi->irqdomain) {
- dev_err(smi->dev, "failed to add irq domain\n");
+ priv->irqdomain = irq_domain_add_linear(intc, priv->num_ports,
+ &rtl8365mb_irqdomain_ops, priv);
+ if (!priv->irqdomain) {
+ dev_err(priv->dev, "failed to add irq domain\n");
ret = -ENOMEM;
goto out_put_node;
}
- for (i = 0; i < smi->num_ports; i++) {
- virq = irq_create_mapping(smi->irqdomain, i);
+ for (i = 0; i < priv->num_ports; i++) {
+ virq = irq_create_mapping(priv->irqdomain, i);
if (!virq) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to create irq domain mapping\n");
ret = -EINVAL;
goto out_remove_irqdomain;
val = RTL8365MB_INTR_POLARITY_LOW;
break;
default:
- dev_err(smi->dev, "unsupported irq trigger type %u\n",
+ dev_err(priv->dev, "unsupported irq trigger type %u\n",
irq_trig);
ret = -EINVAL;
goto out_remove_irqdomain;
}
- ret = regmap_update_bits(smi->map, RTL8365MB_INTR_POLARITY_REG,
+ ret = regmap_update_bits(priv->map, RTL8365MB_INTR_POLARITY_REG,
RTL8365MB_INTR_POLARITY_MASK,
FIELD_PREP(RTL8365MB_INTR_POLARITY_MASK, val));
if (ret)
goto out_remove_irqdomain;
/* Disable the interrupt in case the chip has it enabled on reset */
- ret = rtl8365mb_irq_disable(smi);
+ ret = rtl8365mb_irq_disable(priv);
if (ret)
goto out_remove_irqdomain;
/* Clear the interrupt status register */
- ret = regmap_write(smi->map, RTL8365MB_INTR_STATUS_REG,
+ ret = regmap_write(priv->map, RTL8365MB_INTR_STATUS_REG,
RTL8365MB_INTR_ALL_MASK);
if (ret)
goto out_remove_irqdomain;
ret = request_threaded_irq(irq, NULL, rtl8365mb_irq, IRQF_ONESHOT,
- "rtl8365mb", smi);
+ "rtl8365mb", priv);
if (ret) {
- dev_err(smi->dev, "failed to request irq: %d\n", ret);
+ dev_err(priv->dev, "failed to request irq: %d\n", ret);
goto out_remove_irqdomain;
}
/* Store the irq so that we know to free it during teardown */
mb->irq = irq;
- ret = rtl8365mb_irq_enable(smi);
+ ret = rtl8365mb_irq_enable(priv);
if (ret)
goto out_free_irq;
return 0;
out_free_irq:
- free_irq(mb->irq, smi);
+ free_irq(mb->irq, priv);
mb->irq = 0;
out_remove_irqdomain:
- for (i = 0; i < smi->num_ports; i++) {
- virq = irq_find_mapping(smi->irqdomain, i);
+ for (i = 0; i < priv->num_ports; i++) {
+ virq = irq_find_mapping(priv->irqdomain, i);
irq_dispose_mapping(virq);
}
- irq_domain_remove(smi->irqdomain);
- smi->irqdomain = NULL;
+ irq_domain_remove(priv->irqdomain);
+ priv->irqdomain = NULL;
out_put_node:
of_node_put(intc);
return ret;
}
-static void rtl8365mb_irq_teardown(struct realtek_smi *smi)
+static void rtl8365mb_irq_teardown(struct realtek_priv *priv)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
int virq;
int i;
if (mb->irq) {
- free_irq(mb->irq, smi);
+ free_irq(mb->irq, priv);
mb->irq = 0;
}
- if (smi->irqdomain) {
- for (i = 0; i < smi->num_ports; i++) {
- virq = irq_find_mapping(smi->irqdomain, i);
+ if (priv->irqdomain) {
+ for (i = 0; i < priv->num_ports; i++) {
+ virq = irq_find_mapping(priv->irqdomain, i);
irq_dispose_mapping(virq);
}
- irq_domain_remove(smi->irqdomain);
- smi->irqdomain = NULL;
+ irq_domain_remove(priv->irqdomain);
+ priv->irqdomain = NULL;
}
}
-static int rtl8365mb_cpu_config(struct realtek_smi *smi)
+static int rtl8365mb_cpu_config(struct realtek_priv *priv, const struct rtl8365mb_cpu *cpu)
{
- struct rtl8365mb *mb = smi->chip_data;
- struct rtl8365mb_cpu *cpu = &mb->cpu;
u32 val;
int ret;
- ret = regmap_update_bits(smi->map, RTL8365MB_CPU_PORT_MASK_REG,
+ ret = regmap_update_bits(priv->map, RTL8365MB_CPU_PORT_MASK_REG,
RTL8365MB_CPU_PORT_MASK_MASK,
FIELD_PREP(RTL8365MB_CPU_PORT_MASK_MASK,
cpu->mask));
FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_POSITION_MASK, cpu->position) |
FIELD_PREP(RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK, cpu->rx_length) |
FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK, cpu->format) |
- FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port) |
+ FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port & 0x7) |
FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK,
- cpu->trap_port >> 3);
- ret = regmap_write(smi->map, RTL8365MB_CPU_CTRL_REG, val);
+ cpu->trap_port >> 3 & 0x1);
+ ret = regmap_write(priv->map, RTL8365MB_CPU_CTRL_REG, val);
if (ret)
return ret;
return 0;
}
-static int rtl8365mb_switch_init(struct realtek_smi *smi)
+static int rtl8365mb_switch_init(struct realtek_priv *priv)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
int ret;
int i;
/* Do any chip-specific init jam before getting to the common stuff */
if (mb->jam_table) {
for (i = 0; i < mb->jam_size; i++) {
- ret = regmap_write(smi->map, mb->jam_table[i].reg,
+ ret = regmap_write(priv->map, mb->jam_table[i].reg,
mb->jam_table[i].val);
if (ret)
return ret;
/* Common init jam */
for (i = 0; i < ARRAY_SIZE(rtl8365mb_init_jam_common); i++) {
- ret = regmap_write(smi->map, rtl8365mb_init_jam_common[i].reg,
+ ret = regmap_write(priv->map, rtl8365mb_init_jam_common[i].reg,
rtl8365mb_init_jam_common[i].val);
if (ret)
return ret;
return 0;
}
-static int rtl8365mb_reset_chip(struct realtek_smi *smi)
+static int rtl8365mb_reset_chip(struct realtek_priv *priv)
{
u32 val;
- realtek_smi_write_reg_noack(smi, RTL8365MB_CHIP_RESET_REG,
- FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK,
- 1));
+ priv->write_reg_noack(priv, RTL8365MB_CHIP_RESET_REG,
+ FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, 1));
/* Realtek documentation says the chip needs 1 second to reset. Sleep
* for 100 ms before accessing any registers to prevent ACK timeouts.
*/
msleep(100);
- return regmap_read_poll_timeout(smi->map, RTL8365MB_CHIP_RESET_REG, val,
+ return regmap_read_poll_timeout(priv->map, RTL8365MB_CHIP_RESET_REG, val,
!(val & RTL8365MB_CHIP_RESET_HW_MASK),
20000, 1e6);
}
static int rtl8365mb_setup(struct dsa_switch *ds)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
+ struct rtl8365mb_cpu cpu = {0};
+ struct dsa_port *cpu_dp;
struct rtl8365mb *mb;
int ret;
int i;
- mb = smi->chip_data;
+ mb = priv->chip_data;
- ret = rtl8365mb_reset_chip(smi);
+ ret = rtl8365mb_reset_chip(priv);
if (ret) {
- dev_err(smi->dev, "failed to reset chip: %d\n", ret);
+ dev_err(priv->dev, "failed to reset chip: %d\n", ret);
goto out_error;
}
/* Configure switch to vendor-defined initial state */
- ret = rtl8365mb_switch_init(smi);
+ ret = rtl8365mb_switch_init(priv);
if (ret) {
- dev_err(smi->dev, "failed to initialize switch: %d\n", ret);
+ dev_err(priv->dev, "failed to initialize switch: %d\n", ret);
goto out_error;
}
/* Set up cascading IRQs */
- ret = rtl8365mb_irq_setup(smi);
+ ret = rtl8365mb_irq_setup(priv);
if (ret == -EPROBE_DEFER)
return ret;
else if (ret)
- dev_info(smi->dev, "no interrupt support\n");
+ dev_info(priv->dev, "no interrupt support\n");
/* Configure CPU tagging */
- ret = rtl8365mb_cpu_config(smi);
+ cpu.trap_port = RTL8365MB_MAX_NUM_PORTS;
+ dsa_switch_for_each_cpu_port(cpu_dp, priv->ds) {
+ cpu.mask |= BIT(cpu_dp->index);
+
+ if (cpu.trap_port == RTL8365MB_MAX_NUM_PORTS)
+ cpu.trap_port = cpu_dp->index;
+ }
+
+ cpu.enable = cpu.mask > 0;
+ cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL;
+ cpu.position = RTL8365MB_CPU_POS_AFTER_SA;
+ cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES;
+ cpu.format = RTL8365MB_CPU_FORMAT_8BYTES;
+
+ ret = rtl8365mb_cpu_config(priv, &cpu);
if (ret)
goto out_teardown_irq;
/* Configure ports */
- for (i = 0; i < smi->num_ports; i++) {
+ for (i = 0; i < priv->num_ports; i++) {
struct rtl8365mb_port *p = &mb->ports[i];
- if (dsa_is_unused_port(smi->ds, i))
+ if (dsa_is_unused_port(priv->ds, i))
continue;
- /* Set up per-port private data */
- p->smi = smi;
- p->index = i;
-
/* Forward only to the CPU */
- ret = rtl8365mb_port_set_isolation(smi, i, BIT(smi->cpu_port));
+ ret = rtl8365mb_port_set_isolation(priv, i, cpu.mask);
if (ret)
goto out_teardown_irq;
/* Disable learning */
- ret = rtl8365mb_port_set_learning(smi, i, false);
+ ret = rtl8365mb_port_set_learning(priv, i, false);
if (ret)
goto out_teardown_irq;
* ports will still forward frames to the CPU despite being
* administratively down by default.
*/
- rtl8365mb_port_stp_state_set(smi->ds, i, BR_STATE_DISABLED);
+ rtl8365mb_port_stp_state_set(priv->ds, i, BR_STATE_DISABLED);
+
+ /* Set up per-port private data */
+ p->priv = priv;
+ p->index = i;
}
/* Set maximum packet length to 1536 bytes */
- ret = regmap_update_bits(smi->map, RTL8365MB_CFG0_MAX_LEN_REG,
+ ret = regmap_update_bits(priv->map, RTL8365MB_CFG0_MAX_LEN_REG,
RTL8365MB_CFG0_MAX_LEN_MASK,
FIELD_PREP(RTL8365MB_CFG0_MAX_LEN_MASK, 1536));
if (ret)
goto out_teardown_irq;
- ret = realtek_smi_setup_mdio(smi);
- if (ret) {
- dev_err(smi->dev, "could not set up MDIO bus\n");
- goto out_teardown_irq;
+ if (priv->setup_interface) {
+ ret = priv->setup_interface(ds);
+ if (ret) {
+ dev_err(priv->dev, "could not set up MDIO bus\n");
+ goto out_teardown_irq;
+ }
}
/* Start statistics counter polling */
- rtl8365mb_stats_setup(smi);
+ rtl8365mb_stats_setup(priv);
return 0;
out_teardown_irq:
- rtl8365mb_irq_teardown(smi);
+ rtl8365mb_irq_teardown(priv);
out_error:
return ret;
static void rtl8365mb_teardown(struct dsa_switch *ds)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
- rtl8365mb_stats_teardown(smi);
- rtl8365mb_irq_teardown(smi);
+ rtl8365mb_stats_teardown(priv);
+ rtl8365mb_irq_teardown(priv);
}
static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver)
return 0;
}
-static int rtl8365mb_detect(struct realtek_smi *smi)
+static int rtl8365mb_detect(struct realtek_priv *priv)
{
- struct rtl8365mb *mb = smi->chip_data;
+ struct rtl8365mb *mb = priv->chip_data;
u32 chip_id;
u32 chip_ver;
int ret;
- ret = rtl8365mb_get_chip_id_and_ver(smi->map, &chip_id, &chip_ver);
+ ret = rtl8365mb_get_chip_id_and_ver(priv->map, &chip_id, &chip_ver);
if (ret) {
- dev_err(smi->dev, "failed to read chip id and version: %d\n",
+ dev_err(priv->dev, "failed to read chip id and version: %d\n",
ret);
return ret;
}
switch (chip_id) {
case RTL8365MB_CHIP_ID_8365MB_VC:
- dev_info(smi->dev,
- "found an RTL8365MB-VC switch (ver=0x%04x)\n",
- chip_ver);
+ switch (chip_ver) {
+ case RTL8365MB_CHIP_VER_8365MB_VC:
+ dev_info(priv->dev,
+ "found an RTL8365MB-VC switch (ver=0x%04x)\n",
+ chip_ver);
+ break;
+ case RTL8365MB_CHIP_VER_8367RB:
+ dev_info(priv->dev,
+ "found an RTL8367RB-VB switch (ver=0x%04x)\n",
+ chip_ver);
+ break;
+ case RTL8365MB_CHIP_VER_8367S:
+ dev_info(priv->dev,
+ "found an RTL8367S switch (ver=0x%04x)\n",
+ chip_ver);
+ break;
+ default:
+ dev_err(priv->dev, "unrecognized switch version (ver=0x%04x)",
+ chip_ver);
+ return -ENODEV;
+ }
- smi->cpu_port = RTL8365MB_CPU_PORT_NUM_8365MB_VC;
- smi->num_ports = smi->cpu_port + 1;
+ priv->num_ports = RTL8365MB_MAX_NUM_PORTS;
- mb->smi = smi;
+ mb->priv = priv;
mb->chip_id = chip_id;
mb->chip_ver = chip_ver;
- mb->port_mask = BIT(smi->num_ports) - 1;
- mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC;
+ mb->port_mask = GENMASK(priv->num_ports - 1, 0);
+ mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX;
mb->jam_table = rtl8365mb_init_jam_8365mb_vc;
mb->jam_size = ARRAY_SIZE(rtl8365mb_init_jam_8365mb_vc);
- mb->cpu.enable = 1;
- mb->cpu.mask = BIT(smi->cpu_port);
- mb->cpu.trap_port = smi->cpu_port;
- mb->cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL;
- mb->cpu.position = RTL8365MB_CPU_POS_AFTER_SA;
- mb->cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES;
- mb->cpu.format = RTL8365MB_CPU_FORMAT_8BYTES;
-
break;
default:
- dev_err(smi->dev,
+ dev_err(priv->dev,
"found an unknown Realtek switch (id=0x%04x, ver=0x%04x)\n",
chip_id, chip_ver);
return -ENODEV;
return 0;
}
-static const struct dsa_switch_ops rtl8365mb_switch_ops = {
+static const struct dsa_switch_ops rtl8365mb_switch_ops_smi = {
+ .get_tag_protocol = rtl8365mb_get_tag_protocol,
+ .setup = rtl8365mb_setup,
+ .teardown = rtl8365mb_teardown,
+ .phylink_validate = rtl8365mb_phylink_validate,
+ .phylink_mac_config = rtl8365mb_phylink_mac_config,
+ .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down,
+ .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up,
+ .port_stp_state_set = rtl8365mb_port_stp_state_set,
+ .get_strings = rtl8365mb_get_strings,
+ .get_ethtool_stats = rtl8365mb_get_ethtool_stats,
+ .get_sset_count = rtl8365mb_get_sset_count,
+ .get_eth_phy_stats = rtl8365mb_get_phy_stats,
+ .get_eth_mac_stats = rtl8365mb_get_mac_stats,
+ .get_eth_ctrl_stats = rtl8365mb_get_ctrl_stats,
+ .get_stats64 = rtl8365mb_get_stats64,
+};
+
+static const struct dsa_switch_ops rtl8365mb_switch_ops_mdio = {
.get_tag_protocol = rtl8365mb_get_tag_protocol,
.setup = rtl8365mb_setup,
.teardown = rtl8365mb_teardown,
.phylink_mac_config = rtl8365mb_phylink_mac_config,
.phylink_mac_link_down = rtl8365mb_phylink_mac_link_down,
.phylink_mac_link_up = rtl8365mb_phylink_mac_link_up,
+ .phy_read = rtl8365mb_dsa_phy_read,
+ .phy_write = rtl8365mb_dsa_phy_write,
.port_stp_state_set = rtl8365mb_port_stp_state_set,
.get_strings = rtl8365mb_get_strings,
.get_ethtool_stats = rtl8365mb_get_ethtool_stats,
.get_stats64 = rtl8365mb_get_stats64,
};
-static const struct realtek_smi_ops rtl8365mb_smi_ops = {
+static const struct realtek_ops rtl8365mb_ops = {
.detect = rtl8365mb_detect,
.phy_read = rtl8365mb_phy_read,
.phy_write = rtl8365mb_phy_write,
};
-const struct realtek_smi_variant rtl8365mb_variant = {
- .ds_ops = &rtl8365mb_switch_ops,
- .ops = &rtl8365mb_smi_ops,
+const struct realtek_variant rtl8365mb_variant = {
+ .ds_ops_smi = &rtl8365mb_switch_ops_smi,
+ .ds_ops_mdio = &rtl8365mb_switch_ops_mdio,
+ .ops = &rtl8365mb_ops,
.clk_delay = 10,
.cmd_read = 0xb9,
.cmd_write = 0xb8,
.chip_data_sz = sizeof(struct rtl8365mb),
};
EXPORT_SYMBOL_GPL(rtl8365mb_variant);
+
+MODULE_AUTHOR("Alvin Šipraga <alsi@bang-olufsen.dk>");
+MODULE_DESCRIPTION("Driver for RTL8365MB-VC ethernet switch");
+MODULE_LICENSE("GPL");
#include <linux/if_bridge.h>
#include <net/dsa.h>
-#include "realtek-smi-core.h"
+#include "realtek.h"
-int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used)
+int rtl8366_mc_is_used(struct realtek_priv *priv, int mc_index, int *used)
{
int ret;
int i;
*used = 0;
- for (i = 0; i < smi->num_ports; i++) {
+ for (i = 0; i < priv->num_ports; i++) {
int index = 0;
- ret = smi->ops->get_mc_index(smi, i, &index);
+ ret = priv->ops->get_mc_index(priv, i, &index);
if (ret)
return ret;
/**
* rtl8366_obtain_mc() - retrieve or allocate a VLAN member configuration
- * @smi: the Realtek SMI device instance
+ * @priv: the Realtek SMI device instance
* @vid: the VLAN ID to look up or allocate
* @vlanmc: the pointer will be assigned to a pointer to a valid member config
* if successful
* @return: index of a new member config or negative error number
*/
-static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid,
+static int rtl8366_obtain_mc(struct realtek_priv *priv, int vid,
struct rtl8366_vlan_mc *vlanmc)
{
struct rtl8366_vlan_4k vlan4k;
int i;
/* Try to find an existing member config entry for this VID */
- for (i = 0; i < smi->num_vlan_mc; i++) {
- ret = smi->ops->get_vlan_mc(smi, i, vlanmc);
+ for (i = 0; i < priv->num_vlan_mc; i++) {
+ ret = priv->ops->get_vlan_mc(priv, i, vlanmc);
if (ret) {
- dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n",
+ dev_err(priv->dev, "error searching for VLAN MC %d for VID %d\n",
i, vid);
return ret;
}
}
/* We have no MC entry for this VID, try to find an empty one */
- for (i = 0; i < smi->num_vlan_mc; i++) {
- ret = smi->ops->get_vlan_mc(smi, i, vlanmc);
+ for (i = 0; i < priv->num_vlan_mc; i++) {
+ ret = priv->ops->get_vlan_mc(priv, i, vlanmc);
if (ret) {
- dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n",
+ dev_err(priv->dev, "error searching for VLAN MC %d for VID %d\n",
i, vid);
return ret;
}
if (vlanmc->vid == 0 && vlanmc->member == 0) {
/* Update the entry from the 4K table */
- ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+ ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k);
if (ret) {
- dev_err(smi->dev, "error looking for 4K VLAN MC %d for VID %d\n",
+ dev_err(priv->dev, "error looking for 4K VLAN MC %d for VID %d\n",
i, vid);
return ret;
}
vlanmc->member = vlan4k.member;
vlanmc->untag = vlan4k.untag;
vlanmc->fid = vlan4k.fid;
- ret = smi->ops->set_vlan_mc(smi, i, vlanmc);
+ ret = priv->ops->set_vlan_mc(priv, i, vlanmc);
if (ret) {
- dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n",
+ dev_err(priv->dev, "unable to set/update VLAN MC %d for VID %d\n",
i, vid);
return ret;
}
- dev_dbg(smi->dev, "created new MC at index %d for VID %d\n",
+ dev_dbg(priv->dev, "created new MC at index %d for VID %d\n",
i, vid);
return i;
}
}
/* MC table is full, try to find an unused entry and replace it */
- for (i = 0; i < smi->num_vlan_mc; i++) {
+ for (i = 0; i < priv->num_vlan_mc; i++) {
int used;
- ret = rtl8366_mc_is_used(smi, i, &used);
+ ret = rtl8366_mc_is_used(priv, i, &used);
if (ret)
return ret;
if (!used) {
/* Update the entry from the 4K table */
- ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+ ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k);
if (ret)
return ret;
vlanmc->member = vlan4k.member;
vlanmc->untag = vlan4k.untag;
vlanmc->fid = vlan4k.fid;
- ret = smi->ops->set_vlan_mc(smi, i, vlanmc);
+ ret = priv->ops->set_vlan_mc(priv, i, vlanmc);
if (ret) {
- dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n",
+ dev_err(priv->dev, "unable to set/update VLAN MC %d for VID %d\n",
i, vid);
return ret;
}
- dev_dbg(smi->dev, "recycled MC at index %i for VID %d\n",
+ dev_dbg(priv->dev, "recycled MC at index %i for VID %d\n",
i, vid);
return i;
}
}
- dev_err(smi->dev, "all VLAN member configurations are in use\n");
+ dev_err(priv->dev, "all VLAN member configurations are in use\n");
return -ENOSPC;
}
-int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+int rtl8366_set_vlan(struct realtek_priv *priv, int vid, u32 member,
u32 untag, u32 fid)
{
struct rtl8366_vlan_mc vlanmc;
int mc;
int ret;
- if (!smi->ops->is_vlan_valid(smi, vid))
+ if (!priv->ops->is_vlan_valid(priv, vid))
return -EINVAL;
- dev_dbg(smi->dev,
+ dev_dbg(priv->dev,
"setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n",
vid, member, untag);
/* Update the 4K table */
- ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+ ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k);
if (ret)
return ret;
vlan4k.member |= member;
vlan4k.untag |= untag;
vlan4k.fid = fid;
- ret = smi->ops->set_vlan_4k(smi, &vlan4k);
+ ret = priv->ops->set_vlan_4k(priv, &vlan4k);
if (ret)
return ret;
- dev_dbg(smi->dev,
+ dev_dbg(priv->dev,
"resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n",
vid, vlan4k.member, vlan4k.untag);
/* Find or allocate a member config for this VID */
- ret = rtl8366_obtain_mc(smi, vid, &vlanmc);
+ ret = rtl8366_obtain_mc(priv, vid, &vlanmc);
if (ret < 0)
return ret;
mc = ret;
vlanmc.fid = fid;
/* Commit updates to the MC entry */
- ret = smi->ops->set_vlan_mc(smi, mc, &vlanmc);
+ ret = priv->ops->set_vlan_mc(priv, mc, &vlanmc);
if (ret)
- dev_err(smi->dev, "failed to commit changes to VLAN MC index %d for VID %d\n",
+ dev_err(priv->dev, "failed to commit changes to VLAN MC index %d for VID %d\n",
mc, vid);
else
- dev_dbg(smi->dev,
+ dev_dbg(priv->dev,
"resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n",
vid, vlanmc.member, vlanmc.untag);
}
EXPORT_SYMBOL_GPL(rtl8366_set_vlan);
-int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+int rtl8366_set_pvid(struct realtek_priv *priv, unsigned int port,
unsigned int vid)
{
struct rtl8366_vlan_mc vlanmc;
int mc;
int ret;
- if (!smi->ops->is_vlan_valid(smi, vid))
+ if (!priv->ops->is_vlan_valid(priv, vid))
return -EINVAL;
/* Find or allocate a member config for this VID */
- ret = rtl8366_obtain_mc(smi, vid, &vlanmc);
+ ret = rtl8366_obtain_mc(priv, vid, &vlanmc);
if (ret < 0)
return ret;
mc = ret;
- ret = smi->ops->set_mc_index(smi, port, mc);
+ ret = priv->ops->set_mc_index(priv, port, mc);
if (ret) {
- dev_err(smi->dev, "set PVID: failed to set MC index %d for port %d\n",
+ dev_err(priv->dev, "set PVID: failed to set MC index %d for port %d\n",
mc, port);
return ret;
}
- dev_dbg(smi->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n",
+ dev_dbg(priv->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n",
port, vid, mc);
return 0;
}
EXPORT_SYMBOL_GPL(rtl8366_set_pvid);
-int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable)
+int rtl8366_enable_vlan4k(struct realtek_priv *priv, bool enable)
{
int ret;
*/
if (enable) {
/* Make sure VLAN is ON */
- ret = smi->ops->enable_vlan(smi, true);
+ ret = priv->ops->enable_vlan(priv, true);
if (ret)
return ret;
- smi->vlan_enabled = true;
+ priv->vlan_enabled = true;
}
- ret = smi->ops->enable_vlan4k(smi, enable);
+ ret = priv->ops->enable_vlan4k(priv, enable);
if (ret)
return ret;
- smi->vlan4k_enabled = enable;
+ priv->vlan4k_enabled = enable;
return 0;
}
EXPORT_SYMBOL_GPL(rtl8366_enable_vlan4k);
-int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable)
+int rtl8366_enable_vlan(struct realtek_priv *priv, bool enable)
{
int ret;
- ret = smi->ops->enable_vlan(smi, enable);
+ ret = priv->ops->enable_vlan(priv, enable);
if (ret)
return ret;
- smi->vlan_enabled = enable;
+ priv->vlan_enabled = enable;
/* If we turn VLAN off, make sure that we turn off
* 4k VLAN as well, if that happened to be on.
*/
if (!enable) {
- smi->vlan4k_enabled = false;
- ret = smi->ops->enable_vlan4k(smi, false);
+ priv->vlan4k_enabled = false;
+ ret = priv->ops->enable_vlan4k(priv, false);
}
return ret;
}
EXPORT_SYMBOL_GPL(rtl8366_enable_vlan);
-int rtl8366_reset_vlan(struct realtek_smi *smi)
+int rtl8366_reset_vlan(struct realtek_priv *priv)
{
struct rtl8366_vlan_mc vlanmc;
int ret;
int i;
- rtl8366_enable_vlan(smi, false);
- rtl8366_enable_vlan4k(smi, false);
+ rtl8366_enable_vlan(priv, false);
+ rtl8366_enable_vlan4k(priv, false);
/* Clear the 16 VLAN member configurations */
vlanmc.vid = 0;
vlanmc.member = 0;
vlanmc.untag = 0;
vlanmc.fid = 0;
- for (i = 0; i < smi->num_vlan_mc; i++) {
- ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ for (i = 0; i < priv->num_vlan_mc; i++) {
+ ret = priv->ops->set_vlan_mc(priv, i, &vlanmc);
if (ret)
return ret;
}
{
bool untagged = !!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
bool pvid = !!(vlan->flags & BRIDGE_VLAN_INFO_PVID);
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
u32 member = 0;
u32 untag = 0;
int ret;
- if (!smi->ops->is_vlan_valid(smi, vlan->vid)) {
+ if (!priv->ops->is_vlan_valid(priv, vlan->vid)) {
NL_SET_ERR_MSG_MOD(extack, "VLAN ID not valid");
return -EINVAL;
}
* FIXME: what's with this 4k business?
* Just rtl8366_enable_vlan() seems inconclusive.
*/
- ret = rtl8366_enable_vlan4k(smi, true);
+ ret = rtl8366_enable_vlan4k(priv, true);
if (ret) {
NL_SET_ERR_MSG_MOD(extack, "Failed to enable VLAN 4K");
return ret;
}
- dev_dbg(smi->dev, "add VLAN %d on port %d, %s, %s\n",
+ dev_dbg(priv->dev, "add VLAN %d on port %d, %s, %s\n",
vlan->vid, port, untagged ? "untagged" : "tagged",
pvid ? "PVID" : "no PVID");
if (untagged)
untag |= BIT(port);
- ret = rtl8366_set_vlan(smi, vlan->vid, member, untag, 0);
+ ret = rtl8366_set_vlan(priv, vlan->vid, member, untag, 0);
if (ret) {
- dev_err(smi->dev, "failed to set up VLAN %04x", vlan->vid);
+ dev_err(priv->dev, "failed to set up VLAN %04x", vlan->vid);
return ret;
}
if (!pvid)
return 0;
- ret = rtl8366_set_pvid(smi, port, vlan->vid);
+ ret = rtl8366_set_pvid(priv, port, vlan->vid);
if (ret) {
- dev_err(smi->dev, "failed to set PVID on port %d to VLAN %04x",
+ dev_err(priv->dev, "failed to set PVID on port %d to VLAN %04x",
port, vlan->vid);
return ret;
}
int rtl8366_vlan_del(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret, i;
- dev_dbg(smi->dev, "del VLAN %d on port %d\n", vlan->vid, port);
+ dev_dbg(priv->dev, "del VLAN %d on port %d\n", vlan->vid, port);
- for (i = 0; i < smi->num_vlan_mc; i++) {
+ for (i = 0; i < priv->num_vlan_mc; i++) {
struct rtl8366_vlan_mc vlanmc;
- ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+ ret = priv->ops->get_vlan_mc(priv, i, &vlanmc);
if (ret)
return ret;
vlanmc.priority = 0;
vlanmc.fid = 0;
}
- ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+ ret = priv->ops->set_vlan_mc(priv, i, &vlanmc);
if (ret) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to remove VLAN %04x\n",
vlan->vid);
return ret;
void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
uint8_t *data)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8366_mib_counter *mib;
int i;
- if (port >= smi->num_ports)
+ if (port >= priv->num_ports)
return;
- for (i = 0; i < smi->num_mib_counters; i++) {
- mib = &smi->mib_counters[i];
+ for (i = 0; i < priv->num_mib_counters; i++) {
+ mib = &priv->mib_counters[i];
strncpy(data + i * ETH_GSTRING_LEN,
mib->name, ETH_GSTRING_LEN);
}
int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
/* We only support SS_STATS */
if (sset != ETH_SS_STATS)
return 0;
- if (port >= smi->num_ports)
+ if (port >= priv->num_ports)
return -EINVAL;
- return smi->num_mib_counters;
+ return priv->num_mib_counters;
}
EXPORT_SYMBOL_GPL(rtl8366_get_sset_count);
void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int i;
int ret;
- if (port >= smi->num_ports)
+ if (port >= priv->num_ports)
return;
- for (i = 0; i < smi->num_mib_counters; i++) {
+ for (i = 0; i < priv->num_mib_counters; i++) {
struct rtl8366_mib_counter *mib;
u64 mibvalue = 0;
- mib = &smi->mib_counters[i];
- ret = smi->ops->get_mib_counter(smi, port, mib, &mibvalue);
+ mib = &priv->mib_counters[i];
+ ret = priv->ops->get_mib_counter(priv, port, mib, &mibvalue);
if (ret) {
- dev_err(smi->dev, "error reading MIB counter %s\n",
+ dev_err(priv->dev, "error reading MIB counter %s\n",
mib->name);
}
data[i] = mibvalue;
#include <linux/of_irq.h>
#include <linux/regmap.h>
-#include "realtek-smi-core.h"
+#include "realtek.h"
#define RTL8366RB_PORT_NUM_CPU 5
#define RTL8366RB_NUM_PORTS 6
{ 0, 70, 2, "IfOutBroadcastPkts" },
};
-static int rtl8366rb_get_mib_counter(struct realtek_smi *smi,
+static int rtl8366rb_get_mib_counter(struct realtek_priv *priv,
int port,
struct rtl8366_mib_counter *mib,
u64 *mibvalue)
/* Writing access counter address first
* then ASIC will prepare 64bits counter wait for being retrived
*/
- ret = regmap_write(smi->map, addr, 0); /* Write whatever */
+ ret = regmap_write(priv->map, addr, 0); /* Write whatever */
if (ret)
return ret;
/* Read MIB control register */
- ret = regmap_read(smi->map, RTL8366RB_MIB_CTRL_REG, &val);
+ ret = regmap_read(priv->map, RTL8366RB_MIB_CTRL_REG, &val);
if (ret)
return -EIO;
/* Read each individual MIB 16 bits at the time */
*mibvalue = 0;
for (i = mib->length; i > 0; i--) {
- ret = regmap_read(smi->map, addr + (i - 1), &val);
+ ret = regmap_read(priv->map, addr + (i - 1), &val);
if (ret)
return ret;
*mibvalue = (*mibvalue << 16) | (val & 0xFFFF);
static void rtl8366rb_mask_irq(struct irq_data *d)
{
- struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+ struct realtek_priv *priv = irq_data_get_irq_chip_data(d);
int ret;
- ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+ ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_MASK_REG,
rtl8366rb_get_irqmask(d), 0);
if (ret)
- dev_err(smi->dev, "could not mask IRQ\n");
+ dev_err(priv->dev, "could not mask IRQ\n");
}
static void rtl8366rb_unmask_irq(struct irq_data *d)
{
- struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+ struct realtek_priv *priv = irq_data_get_irq_chip_data(d);
int ret;
- ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+ ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_MASK_REG,
rtl8366rb_get_irqmask(d),
rtl8366rb_get_irqmask(d));
if (ret)
- dev_err(smi->dev, "could not unmask IRQ\n");
+ dev_err(priv->dev, "could not unmask IRQ\n");
}
static irqreturn_t rtl8366rb_irq(int irq, void *data)
{
- struct realtek_smi *smi = data;
+ struct realtek_priv *priv = data;
u32 stat;
int ret;
/* This clears the IRQ status register */
- ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+ ret = regmap_read(priv->map, RTL8366RB_INTERRUPT_STATUS_REG,
&stat);
if (ret) {
- dev_err(smi->dev, "can't read interrupt status\n");
+ dev_err(priv->dev, "can't read interrupt status\n");
return IRQ_NONE;
}
stat &= RTL8366RB_INTERRUPT_VALID;
*/
if (line < 12 && line > 5)
line -= 5;
- child_irq = irq_find_mapping(smi->irqdomain, line);
+ child_irq = irq_find_mapping(priv->irqdomain, line);
handle_nested_irq(child_irq);
}
return IRQ_HANDLED;
.xlate = irq_domain_xlate_onecell,
};
-static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
+static int rtl8366rb_setup_cascaded_irq(struct realtek_priv *priv)
{
struct device_node *intc;
unsigned long irq_trig;
u32 val;
int i;
- intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller");
+ intc = of_get_child_by_name(priv->dev->of_node, "interrupt-controller");
if (!intc) {
- dev_err(smi->dev, "missing child interrupt-controller node\n");
+ dev_err(priv->dev, "missing child interrupt-controller node\n");
return -EINVAL;
}
/* RB8366RB IRQs cascade off this one */
irq = of_irq_get(intc, 0);
if (irq <= 0) {
- dev_err(smi->dev, "failed to get parent IRQ\n");
+ dev_err(priv->dev, "failed to get parent IRQ\n");
ret = irq ? irq : -EINVAL;
goto out_put_node;
}
/* This clears the IRQ status register */
- ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+ ret = regmap_read(priv->map, RTL8366RB_INTERRUPT_STATUS_REG,
&val);
if (ret) {
- dev_err(smi->dev, "can't read interrupt status\n");
+ dev_err(priv->dev, "can't read interrupt status\n");
goto out_put_node;
}
switch (irq_trig) {
case IRQF_TRIGGER_RISING:
case IRQF_TRIGGER_HIGH:
- dev_info(smi->dev, "active high/rising IRQ\n");
+ dev_info(priv->dev, "active high/rising IRQ\n");
val = 0;
break;
case IRQF_TRIGGER_FALLING:
case IRQF_TRIGGER_LOW:
- dev_info(smi->dev, "active low/falling IRQ\n");
+ dev_info(priv->dev, "active low/falling IRQ\n");
val = RTL8366RB_INTERRUPT_POLARITY;
break;
}
- ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_CONTROL_REG,
+ ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG,
RTL8366RB_INTERRUPT_POLARITY,
val);
if (ret) {
- dev_err(smi->dev, "could not configure IRQ polarity\n");
+ dev_err(priv->dev, "could not configure IRQ polarity\n");
goto out_put_node;
}
- ret = devm_request_threaded_irq(smi->dev, irq, NULL,
+ ret = devm_request_threaded_irq(priv->dev, irq, NULL,
rtl8366rb_irq, IRQF_ONESHOT,
- "RTL8366RB", smi);
+ "RTL8366RB", priv);
if (ret) {
- dev_err(smi->dev, "unable to request irq: %d\n", ret);
+ dev_err(priv->dev, "unable to request irq: %d\n", ret);
goto out_put_node;
}
- smi->irqdomain = irq_domain_add_linear(intc,
- RTL8366RB_NUM_INTERRUPT,
- &rtl8366rb_irqdomain_ops,
- smi);
- if (!smi->irqdomain) {
- dev_err(smi->dev, "failed to create IRQ domain\n");
+ priv->irqdomain = irq_domain_add_linear(intc,
+ RTL8366RB_NUM_INTERRUPT,
+ &rtl8366rb_irqdomain_ops,
+ priv);
+ if (!priv->irqdomain) {
+ dev_err(priv->dev, "failed to create IRQ domain\n");
ret = -EINVAL;
goto out_put_node;
}
- for (i = 0; i < smi->num_ports; i++)
- irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq);
+ for (i = 0; i < priv->num_ports; i++)
+ irq_set_parent(irq_create_mapping(priv->irqdomain, i), irq);
out_put_node:
of_node_put(intc);
return ret;
}
-static int rtl8366rb_set_addr(struct realtek_smi *smi)
+static int rtl8366rb_set_addr(struct realtek_priv *priv)
{
u8 addr[ETH_ALEN];
u16 val;
eth_random_addr(addr);
- dev_info(smi->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n",
+ dev_info(priv->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n",
addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
val = addr[0] << 8 | addr[1];
- ret = regmap_write(smi->map, RTL8366RB_SMAR0, val);
+ ret = regmap_write(priv->map, RTL8366RB_SMAR0, val);
if (ret)
return ret;
val = addr[2] << 8 | addr[3];
- ret = regmap_write(smi->map, RTL8366RB_SMAR1, val);
+ ret = regmap_write(priv->map, RTL8366RB_SMAR1, val);
if (ret)
return ret;
val = addr[4] << 8 | addr[5];
- ret = regmap_write(smi->map, RTL8366RB_SMAR2, val);
+ ret = regmap_write(priv->map, RTL8366RB_SMAR2, val);
if (ret)
return ret;
/* Function that jams the tables in the proper registers */
static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table,
- int jam_size, struct realtek_smi *smi,
+ int jam_size, struct realtek_priv *priv,
bool write_dbg)
{
u32 val;
for (i = 0; i < jam_size; i++) {
if ((jam_table[i].reg & 0xBE00) == 0xBE00) {
- ret = regmap_read(smi->map,
+ ret = regmap_read(priv->map,
RTL8366RB_PHY_ACCESS_BUSY_REG,
&val);
if (ret)
return ret;
if (!(val & RTL8366RB_PHY_INT_BUSY)) {
- ret = regmap_write(smi->map,
- RTL8366RB_PHY_ACCESS_CTRL_REG,
- RTL8366RB_PHY_CTRL_WRITE);
+ ret = regmap_write(priv->map,
+ RTL8366RB_PHY_ACCESS_CTRL_REG,
+ RTL8366RB_PHY_CTRL_WRITE);
if (ret)
return ret;
}
}
if (write_dbg)
- dev_dbg(smi->dev, "jam %04x into register %04x\n",
+ dev_dbg(priv->dev, "jam %04x into register %04x\n",
jam_table[i].val,
jam_table[i].reg);
- ret = regmap_write(smi->map,
+ ret = regmap_write(priv->map,
jam_table[i].reg,
jam_table[i].val);
if (ret)
static int rtl8366rb_setup(struct dsa_switch *ds)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
const struct rtl8366rb_jam_tbl_entry *jam_table;
struct rtl8366rb *rb;
u32 chip_ver = 0;
int ret;
int i;
- rb = smi->chip_data;
+ rb = priv->chip_data;
- ret = regmap_read(smi->map, RTL8366RB_CHIP_ID_REG, &chip_id);
+ ret = regmap_read(priv->map, RTL8366RB_CHIP_ID_REG, &chip_id);
if (ret) {
- dev_err(smi->dev, "unable to read chip id\n");
+ dev_err(priv->dev, "unable to read chip id\n");
return ret;
}
case RTL8366RB_CHIP_ID_8366:
break;
default:
- dev_err(smi->dev, "unknown chip id (%04x)\n", chip_id);
+ dev_err(priv->dev, "unknown chip id (%04x)\n", chip_id);
return -ENODEV;
}
- ret = regmap_read(smi->map, RTL8366RB_CHIP_VERSION_CTRL_REG,
+ ret = regmap_read(priv->map, RTL8366RB_CHIP_VERSION_CTRL_REG,
&chip_ver);
if (ret) {
- dev_err(smi->dev, "unable to read chip version\n");
+ dev_err(priv->dev, "unable to read chip version\n");
return ret;
}
- dev_info(smi->dev, "RTL%04x ver %u chip found\n",
+ dev_info(priv->dev, "RTL%04x ver %u chip found\n",
chip_id, chip_ver & RTL8366RB_CHIP_VERSION_MASK);
/* Do the init dance using the right jam table */
jam_size = ARRAY_SIZE(rtl8366rb_init_jam_dgn3500);
}
- ret = rtl8366rb_jam_table(jam_table, jam_size, smi, true);
+ ret = rtl8366rb_jam_table(jam_table, jam_size, priv, true);
if (ret)
return ret;
/* Isolate all user ports so they can only send packets to itself and the CPU port */
for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) {
- ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(i),
+ ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(i),
RTL8366RB_PORT_ISO_PORTS(BIT(RTL8366RB_PORT_NUM_CPU)) |
RTL8366RB_PORT_ISO_EN);
if (ret)
return ret;
}
/* CPU port can send packets to all ports */
- ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU),
+ ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU),
RTL8366RB_PORT_ISO_PORTS(dsa_user_ports(ds)) |
RTL8366RB_PORT_ISO_EN);
if (ret)
/* Set up the "green ethernet" feature */
ret = rtl8366rb_jam_table(rtl8366rb_green_jam,
- ARRAY_SIZE(rtl8366rb_green_jam), smi, false);
+ ARRAY_SIZE(rtl8366rb_green_jam), priv, false);
if (ret)
return ret;
- ret = regmap_write(smi->map,
+ ret = regmap_write(priv->map,
RTL8366RB_GREEN_FEATURE_REG,
(chip_ver == 1) ? 0x0007 : 0x0003);
if (ret)
return ret;
/* Vendor driver sets 0x240 in registers 0xc and 0xd (undocumented) */
- ret = regmap_write(smi->map, 0x0c, 0x240);
+ ret = regmap_write(priv->map, 0x0c, 0x240);
if (ret)
return ret;
- ret = regmap_write(smi->map, 0x0d, 0x240);
+ ret = regmap_write(priv->map, 0x0d, 0x240);
if (ret)
return ret;
/* Set some random MAC address */
- ret = rtl8366rb_set_addr(smi);
+ ret = rtl8366rb_set_addr(priv);
if (ret)
return ret;
* If you set RTL8368RB_CPU_NO_TAG (bit 15) in this registers
* the custom tag is turned off.
*/
- ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG,
+ ret = regmap_update_bits(priv->map, RTL8368RB_CPU_CTRL_REG,
0xFFFF,
- BIT(smi->cpu_port));
+ BIT(priv->cpu_port));
if (ret)
return ret;
/* Make sure we default-enable the fixed CPU port */
- ret = regmap_update_bits(smi->map, RTL8366RB_PECR,
- BIT(smi->cpu_port),
+ ret = regmap_update_bits(priv->map, RTL8366RB_PECR,
+ BIT(priv->cpu_port),
0);
if (ret)
return ret;
/* Set maximum packet length to 1536 bytes */
- ret = regmap_update_bits(smi->map, RTL8366RB_SGCR,
+ ret = regmap_update_bits(priv->map, RTL8366RB_SGCR,
RTL8366RB_SGCR_MAX_LENGTH_MASK,
RTL8366RB_SGCR_MAX_LENGTH_1536);
if (ret)
rb->max_mtu[i] = 1532;
/* Disable learning for all ports */
- ret = regmap_write(smi->map, RTL8366RB_PORT_LEARNDIS_CTRL,
+ ret = regmap_write(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL,
RTL8366RB_PORT_ALL);
if (ret)
return ret;
/* Enable auto ageing for all ports */
- ret = regmap_write(smi->map, RTL8366RB_SECURITY_CTRL, 0);
+ ret = regmap_write(priv->map, RTL8366RB_SECURITY_CTRL, 0);
if (ret)
return ret;
* connected to something exotic such as fiber, then this might
* be worth experimenting with.
*/
- ret = regmap_update_bits(smi->map, RTL8366RB_PMC0,
+ ret = regmap_update_bits(priv->map, RTL8366RB_PMC0,
RTL8366RB_PMC0_P4_IOMODE_MASK,
0 << RTL8366RB_PMC0_P4_IOMODE_SHIFT);
if (ret)
return ret;
/* Accept all packets by default, we enable filtering on-demand */
- ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG,
+ ret = regmap_write(priv->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG,
0);
if (ret)
return ret;
- ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
+ ret = regmap_write(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
0);
if (ret)
return ret;
/* Don't drop packets whose DA has not been learned */
- ret = regmap_update_bits(smi->map, RTL8366RB_SSCR2,
+ ret = regmap_update_bits(priv->map, RTL8366RB_SSCR2,
RTL8366RB_SSCR2_DROP_UNKNOWN_DA, 0);
if (ret)
return ret;
/* Set blinking, TODO: make this configurable */
- ret = regmap_update_bits(smi->map, RTL8366RB_LED_BLINKRATE_REG,
+ ret = regmap_update_bits(priv->map, RTL8366RB_LED_BLINKRATE_REG,
RTL8366RB_LED_BLINKRATE_MASK,
RTL8366RB_LED_BLINKRATE_56MS);
if (ret)
* behaviour (no individual config) but we can set up each
* LED separately.
*/
- if (smi->leds_disabled) {
+ if (priv->leds_disabled) {
/* Turn everything off */
- regmap_update_bits(smi->map,
+ regmap_update_bits(priv->map,
RTL8366RB_LED_0_1_CTRL_REG,
0x0FFF, 0);
- regmap_update_bits(smi->map,
+ regmap_update_bits(priv->map,
RTL8366RB_LED_2_3_CTRL_REG,
0x0FFF, 0);
- regmap_update_bits(smi->map,
+ regmap_update_bits(priv->map,
RTL8366RB_INTERRUPT_CONTROL_REG,
RTL8366RB_P4_RGMII_LED,
0);
val = RTL8366RB_LED_FORCE;
}
for (i = 0; i < 4; i++) {
- ret = regmap_update_bits(smi->map,
+ ret = regmap_update_bits(priv->map,
RTL8366RB_LED_CTRL_REG,
0xf << (i * 4),
val << (i * 4));
return ret;
}
- ret = rtl8366_reset_vlan(smi);
+ ret = rtl8366_reset_vlan(priv);
if (ret)
return ret;
- ret = rtl8366rb_setup_cascaded_irq(smi);
+ ret = rtl8366rb_setup_cascaded_irq(priv);
if (ret)
- dev_info(smi->dev, "no interrupt support\n");
+ dev_info(priv->dev, "no interrupt support\n");
- ret = realtek_smi_setup_mdio(smi);
- if (ret) {
- dev_info(smi->dev, "could not set up MDIO bus\n");
- return -ENODEV;
+ if (priv->setup_interface) {
+ ret = priv->setup_interface(ds);
+ if (ret) {
+ dev_err(priv->dev, "could not set up MDIO bus\n");
+ return -ENODEV;
+ }
}
return 0;
phy_interface_t interface, struct phy_device *phydev,
int speed, int duplex, bool tx_pause, bool rx_pause)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret;
- if (port != smi->cpu_port)
+ if (port != priv->cpu_port)
return;
- dev_dbg(smi->dev, "MAC link up on CPU port (%d)\n", port);
+ dev_dbg(priv->dev, "MAC link up on CPU port (%d)\n", port);
/* Force the fixed CPU port into 1Gbit mode, no autonegotiation */
- ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG,
+ ret = regmap_update_bits(priv->map, RTL8366RB_MAC_FORCE_CTRL_REG,
BIT(port), BIT(port));
if (ret) {
- dev_err(smi->dev, "failed to force 1Gbit on CPU port\n");
+ dev_err(priv->dev, "failed to force 1Gbit on CPU port\n");
return;
}
- ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2,
+ ret = regmap_update_bits(priv->map, RTL8366RB_PAACR2,
0xFF00U,
RTL8366RB_PAACR_CPU_PORT << 8);
if (ret) {
- dev_err(smi->dev, "failed to set PAACR on CPU port\n");
+ dev_err(priv->dev, "failed to set PAACR on CPU port\n");
return;
}
/* Enable the CPU port */
- ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port),
0);
if (ret) {
- dev_err(smi->dev, "failed to enable the CPU port\n");
+ dev_err(priv->dev, "failed to enable the CPU port\n");
return;
}
}
rtl8366rb_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode,
phy_interface_t interface)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret;
- if (port != smi->cpu_port)
+ if (port != priv->cpu_port)
return;
- dev_dbg(smi->dev, "MAC link down on CPU port (%d)\n", port);
+ dev_dbg(priv->dev, "MAC link down on CPU port (%d)\n", port);
/* Disable the CPU port */
- ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port),
BIT(port));
if (ret) {
- dev_err(smi->dev, "failed to disable the CPU port\n");
+ dev_err(priv->dev, "failed to disable the CPU port\n");
return;
}
}
-static void rb8366rb_set_port_led(struct realtek_smi *smi,
+static void rb8366rb_set_port_led(struct realtek_priv *priv,
int port, bool enable)
{
u16 val = enable ? 0x3f : 0;
int ret;
- if (smi->leds_disabled)
+ if (priv->leds_disabled)
return;
switch (port) {
case 0:
- ret = regmap_update_bits(smi->map,
+ ret = regmap_update_bits(priv->map,
RTL8366RB_LED_0_1_CTRL_REG,
0x3F, val);
break;
case 1:
- ret = regmap_update_bits(smi->map,
+ ret = regmap_update_bits(priv->map,
RTL8366RB_LED_0_1_CTRL_REG,
0x3F << RTL8366RB_LED_1_OFFSET,
val << RTL8366RB_LED_1_OFFSET);
break;
case 2:
- ret = regmap_update_bits(smi->map,
+ ret = regmap_update_bits(priv->map,
RTL8366RB_LED_2_3_CTRL_REG,
0x3F, val);
break;
case 3:
- ret = regmap_update_bits(smi->map,
+ ret = regmap_update_bits(priv->map,
RTL8366RB_LED_2_3_CTRL_REG,
0x3F << RTL8366RB_LED_3_OFFSET,
val << RTL8366RB_LED_3_OFFSET);
break;
case 4:
- ret = regmap_update_bits(smi->map,
+ ret = regmap_update_bits(priv->map,
RTL8366RB_INTERRUPT_CONTROL_REG,
RTL8366RB_P4_RGMII_LED,
enable ? RTL8366RB_P4_RGMII_LED : 0);
break;
default:
- dev_err(smi->dev, "no LED for port %d\n", port);
+ dev_err(priv->dev, "no LED for port %d\n", port);
return;
}
if (ret)
- dev_err(smi->dev, "error updating LED on port %d\n", port);
+ dev_err(priv->dev, "error updating LED on port %d\n", port);
}
static int
rtl8366rb_port_enable(struct dsa_switch *ds, int port,
struct phy_device *phy)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret;
- dev_dbg(smi->dev, "enable port %d\n", port);
- ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ dev_dbg(priv->dev, "enable port %d\n", port);
+ ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port),
0);
if (ret)
return ret;
- rb8366rb_set_port_led(smi, port, true);
+ rb8366rb_set_port_led(priv, port, true);
return 0;
}
static void
rtl8366rb_port_disable(struct dsa_switch *ds, int port)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret;
- dev_dbg(smi->dev, "disable port %d\n", port);
- ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+ dev_dbg(priv->dev, "disable port %d\n", port);
+ ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port),
BIT(port));
if (ret)
return;
- rb8366rb_set_port_led(smi, port, false);
+ rb8366rb_set_port_led(priv, port, false);
}
static int
struct dsa_bridge bridge,
bool *tx_fwd_offload)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
unsigned int port_bitmap = 0;
int ret, i;
if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge))
continue;
/* Join this port to each other port on the bridge */
- ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i),
+ ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i),
RTL8366RB_PORT_ISO_PORTS(BIT(port)),
RTL8366RB_PORT_ISO_PORTS(BIT(port)));
if (ret)
- dev_err(smi->dev, "failed to join port %d\n", port);
+ dev_err(priv->dev, "failed to join port %d\n", port);
port_bitmap |= BIT(i);
}
/* Set the bits for the ports we can access */
- return regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port),
+ return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port),
RTL8366RB_PORT_ISO_PORTS(port_bitmap),
RTL8366RB_PORT_ISO_PORTS(port_bitmap));
}
rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port,
struct dsa_bridge bridge)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
unsigned int port_bitmap = 0;
int ret, i;
if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge))
continue;
/* Remove this port from any other port on the bridge */
- ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i),
+ ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i),
RTL8366RB_PORT_ISO_PORTS(BIT(port)), 0);
if (ret)
- dev_err(smi->dev, "failed to leave port %d\n", port);
+ dev_err(priv->dev, "failed to leave port %d\n", port);
port_bitmap |= BIT(i);
}
/* Clear the bits for the ports we can not access, leave ourselves */
- regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port),
+ regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port),
RTL8366RB_PORT_ISO_PORTS(port_bitmap), 0);
}
/**
* rtl8366rb_drop_untagged() - make the switch drop untagged and C-tagged frames
- * @smi: SMI state container
+ * @priv: SMI state container
* @port: the port to drop untagged and C-tagged frames on
* @drop: whether to drop or pass untagged and C-tagged frames
+ *
+ * Return: zero for success, a negative number on error.
*/
-static int rtl8366rb_drop_untagged(struct realtek_smi *smi, int port, bool drop)
+static int rtl8366rb_drop_untagged(struct realtek_priv *priv, int port, bool drop)
{
- return regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG,
+ return regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG,
RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port),
drop ? RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port) : 0);
}
bool vlan_filtering,
struct netlink_ext_ack *extack)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8366rb *rb;
int ret;
- rb = smi->chip_data;
+ rb = priv->chip_data;
- dev_dbg(smi->dev, "port %d: %s VLAN filtering\n", port,
+ dev_dbg(priv->dev, "port %d: %s VLAN filtering\n", port,
vlan_filtering ? "enable" : "disable");
/* If the port is not in the member set, the frame will be dropped */
- ret = regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
+ ret = regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
BIT(port), vlan_filtering ? BIT(port) : 0);
if (ret)
return ret;
* filtering on a port, we need to accept any frames.
*/
if (vlan_filtering)
- ret = rtl8366rb_drop_untagged(smi, port, !rb->pvid_enabled[port]);
+ ret = rtl8366rb_drop_untagged(priv, port, !rb->pvid_enabled[port]);
else
- ret = rtl8366rb_drop_untagged(smi, port, false);
+ ret = rtl8366rb_drop_untagged(priv, port, false);
return ret;
}
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
int ret;
if (flags.mask & BR_LEARNING) {
- ret = regmap_update_bits(smi->map, RTL8366RB_PORT_LEARNDIS_CTRL,
+ ret = regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL,
BIT(port),
(flags.val & BR_LEARNING) ? 0 : BIT(port));
if (ret)
static void
rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
u32 val;
int i;
val = RTL8366RB_STP_STATE_FORWARDING;
break;
default:
- dev_err(smi->dev, "unknown bridge state requested\n");
+ dev_err(priv->dev, "unknown bridge state requested\n");
return;
}
/* Set the same status for the port on all the FIDs */
for (i = 0; i < RTL8366RB_NUM_FIDS; i++) {
- regmap_update_bits(smi->map, RTL8366RB_STP_STATE_BASE + i,
+ regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i,
RTL8366RB_STP_STATE_MASK(port),
RTL8366RB_STP_STATE(port, val));
}
static void
rtl8366rb_port_fast_age(struct dsa_switch *ds, int port)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
/* This will age out any learned L2 entries */
- regmap_update_bits(smi->map, RTL8366RB_SECURITY_CTRL,
+ regmap_update_bits(priv->map, RTL8366RB_SECURITY_CTRL,
BIT(port), BIT(port));
/* Restore the normal state of things */
- regmap_update_bits(smi->map, RTL8366RB_SECURITY_CTRL,
+ regmap_update_bits(priv->map, RTL8366RB_SECURITY_CTRL,
BIT(port), 0);
}
static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
{
- struct realtek_smi *smi = ds->priv;
+ struct realtek_priv *priv = ds->priv;
struct rtl8366rb *rb;
unsigned int max_mtu;
u32 len;
int i;
/* Cache the per-port MTU setting */
- rb = smi->chip_data;
+ rb = priv->chip_data;
rb->max_mtu[port] = new_mtu;
/* Roof out the MTU for the entire switch to the greatest
else
len = RTL8366RB_SGCR_MAX_LENGTH_16000;
- return regmap_update_bits(smi->map, RTL8366RB_SGCR,
+ return regmap_update_bits(priv->map, RTL8366RB_SGCR,
RTL8366RB_SGCR_MAX_LENGTH_MASK,
len);
}
return 15996;
}
-static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid,
+static int rtl8366rb_get_vlan_4k(struct realtek_priv *priv, u32 vid,
struct rtl8366_vlan_4k *vlan4k)
{
u32 data[3];
return -EINVAL;
/* write VID */
- ret = regmap_write(smi->map, RTL8366RB_VLAN_TABLE_WRITE_BASE,
+ ret = regmap_write(priv->map, RTL8366RB_VLAN_TABLE_WRITE_BASE,
vid & RTL8366RB_VLAN_VID_MASK);
if (ret)
return ret;
/* write table access control word */
- ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+ ret = regmap_write(priv->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
RTL8366RB_TABLE_VLAN_READ_CTRL);
if (ret)
return ret;
for (i = 0; i < 3; i++) {
- ret = regmap_read(smi->map,
+ ret = regmap_read(priv->map,
RTL8366RB_VLAN_TABLE_READ_BASE + i,
&data[i]);
if (ret)
return 0;
}
-static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi,
+static int rtl8366rb_set_vlan_4k(struct realtek_priv *priv,
const struct rtl8366_vlan_4k *vlan4k)
{
u32 data[3];
data[2] = vlan4k->fid & RTL8366RB_VLAN_FID_MASK;
for (i = 0; i < 3; i++) {
- ret = regmap_write(smi->map,
+ ret = regmap_write(priv->map,
RTL8366RB_VLAN_TABLE_WRITE_BASE + i,
data[i]);
if (ret)
}
/* write table access control word */
- ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+ ret = regmap_write(priv->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
RTL8366RB_TABLE_VLAN_WRITE_CTRL);
return ret;
}
-static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index,
+static int rtl8366rb_get_vlan_mc(struct realtek_priv *priv, u32 index,
struct rtl8366_vlan_mc *vlanmc)
{
u32 data[3];
return -EINVAL;
for (i = 0; i < 3; i++) {
- ret = regmap_read(smi->map,
+ ret = regmap_read(priv->map,
RTL8366RB_VLAN_MC_BASE(index) + i,
&data[i]);
if (ret)
return 0;
}
-static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index,
+static int rtl8366rb_set_vlan_mc(struct realtek_priv *priv, u32 index,
const struct rtl8366_vlan_mc *vlanmc)
{
u32 data[3];
data[2] = vlanmc->fid & RTL8366RB_VLAN_FID_MASK;
for (i = 0; i < 3; i++) {
- ret = regmap_write(smi->map,
+ ret = regmap_write(priv->map,
RTL8366RB_VLAN_MC_BASE(index) + i,
data[i]);
if (ret)
return 0;
}
-static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val)
+static int rtl8366rb_get_mc_index(struct realtek_priv *priv, int port, int *val)
{
u32 data;
int ret;
- if (port >= smi->num_ports)
+ if (port >= priv->num_ports)
return -EINVAL;
- ret = regmap_read(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+ ret = regmap_read(priv->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
&data);
if (ret)
return ret;
return 0;
}
-static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index)
+static int rtl8366rb_set_mc_index(struct realtek_priv *priv, int port, int index)
{
struct rtl8366rb *rb;
bool pvid_enabled;
int ret;
- rb = smi->chip_data;
+ rb = priv->chip_data;
pvid_enabled = !!index;
- if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS)
+ if (port >= priv->num_ports || index >= RTL8366RB_NUM_VLANS)
return -EINVAL;
- ret = regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
- RTL8366RB_PORT_VLAN_CTRL_MASK <<
+ ret = regmap_update_bits(priv->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+ RTL8366RB_PORT_VLAN_CTRL_MASK <<
RTL8366RB_PORT_VLAN_CTRL_SHIFT(port),
- (index & RTL8366RB_PORT_VLAN_CTRL_MASK) <<
+ (index & RTL8366RB_PORT_VLAN_CTRL_MASK) <<
RTL8366RB_PORT_VLAN_CTRL_SHIFT(port));
if (ret)
return ret;
* not drop any untagged or C-tagged frames. Make sure to update the
* filtering setting.
*/
- if (dsa_port_is_vlan_filtering(dsa_to_port(smi->ds, port)))
- ret = rtl8366rb_drop_untagged(smi, port, !pvid_enabled);
+ if (dsa_port_is_vlan_filtering(dsa_to_port(priv->ds, port)))
+ ret = rtl8366rb_drop_untagged(priv, port, !pvid_enabled);
return ret;
}
-static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan)
+static bool rtl8366rb_is_vlan_valid(struct realtek_priv *priv, unsigned int vlan)
{
unsigned int max = RTL8366RB_NUM_VLANS - 1;
- if (smi->vlan4k_enabled)
+ if (priv->vlan4k_enabled)
max = RTL8366RB_NUM_VIDS - 1;
if (vlan > max)
return true;
}
-static int rtl8366rb_enable_vlan(struct realtek_smi *smi, bool enable)
+static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable)
{
- dev_dbg(smi->dev, "%s VLAN\n", enable ? "enable" : "disable");
- return regmap_update_bits(smi->map,
+ dev_dbg(priv->dev, "%s VLAN\n", enable ? "enable" : "disable");
+ return regmap_update_bits(priv->map,
RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN,
enable ? RTL8366RB_SGCR_EN_VLAN : 0);
}
-static int rtl8366rb_enable_vlan4k(struct realtek_smi *smi, bool enable)
+static int rtl8366rb_enable_vlan4k(struct realtek_priv *priv, bool enable)
{
- dev_dbg(smi->dev, "%s VLAN 4k\n", enable ? "enable" : "disable");
- return regmap_update_bits(smi->map, RTL8366RB_SGCR,
+ dev_dbg(priv->dev, "%s VLAN 4k\n", enable ? "enable" : "disable");
+ return regmap_update_bits(priv->map, RTL8366RB_SGCR,
RTL8366RB_SGCR_EN_VLAN_4KTB,
enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0);
}
-static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum)
+static int rtl8366rb_phy_read(struct realtek_priv *priv, int phy, int regnum)
{
u32 val;
u32 reg;
if (phy > RTL8366RB_PHY_NO_MAX)
return -EINVAL;
- ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+ ret = regmap_write(priv->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
RTL8366RB_PHY_CTRL_READ);
if (ret)
return ret;
reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
- ret = regmap_write(smi->map, reg, 0);
+ ret = regmap_write(priv->map, reg, 0);
if (ret) {
- dev_err(smi->dev,
+ dev_err(priv->dev,
"failed to write PHY%d reg %04x @ %04x, ret %d\n",
phy, regnum, reg, ret);
return ret;
}
- ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val);
+ ret = regmap_read(priv->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val);
if (ret)
return ret;
- dev_dbg(smi->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n",
+ dev_dbg(priv->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n",
phy, regnum, reg, val);
return val;
}
-static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum,
+static int rtl8366rb_phy_write(struct realtek_priv *priv, int phy, int regnum,
u16 val)
{
u32 reg;
if (phy > RTL8366RB_PHY_NO_MAX)
return -EINVAL;
- ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+ ret = regmap_write(priv->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
RTL8366RB_PHY_CTRL_WRITE);
if (ret)
return ret;
reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
- dev_dbg(smi->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n",
+ dev_dbg(priv->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n",
phy, regnum, reg, val);
- ret = regmap_write(smi->map, reg, val);
+ ret = regmap_write(priv->map, reg, val);
if (ret)
return ret;
return 0;
}
-static int rtl8366rb_reset_chip(struct realtek_smi *smi)
+static int rtl8366rb_dsa_phy_read(struct dsa_switch *ds, int phy, int regnum)
+{
+ return rtl8366rb_phy_read(ds->priv, phy, regnum);
+}
+
+static int rtl8366rb_dsa_phy_write(struct dsa_switch *ds, int phy, int regnum,
+ u16 val)
+{
+ return rtl8366rb_phy_write(ds->priv, phy, regnum, val);
+}
+
+static int rtl8366rb_reset_chip(struct realtek_priv *priv)
{
int timeout = 10;
u32 val;
int ret;
- realtek_smi_write_reg_noack(smi, RTL8366RB_RESET_CTRL_REG,
- RTL8366RB_CHIP_CTRL_RESET_HW);
+ priv->write_reg_noack(priv, RTL8366RB_RESET_CTRL_REG,
+ RTL8366RB_CHIP_CTRL_RESET_HW);
do {
usleep_range(20000, 25000);
- ret = regmap_read(smi->map, RTL8366RB_RESET_CTRL_REG, &val);
+ ret = regmap_read(priv->map, RTL8366RB_RESET_CTRL_REG, &val);
if (ret)
return ret;
} while (--timeout);
if (!timeout) {
- dev_err(smi->dev, "timeout waiting for the switch to reset\n");
+ dev_err(priv->dev, "timeout waiting for the switch to reset\n");
return -EIO;
}
return 0;
}
-static int rtl8366rb_detect(struct realtek_smi *smi)
+static int rtl8366rb_detect(struct realtek_priv *priv)
{
- struct device *dev = smi->dev;
+ struct device *dev = priv->dev;
int ret;
u32 val;
/* Detect device */
- ret = regmap_read(smi->map, 0x5c, &val);
+ ret = regmap_read(priv->map, 0x5c, &val);
if (ret) {
dev_err(dev, "can't get chip ID (%d)\n", ret);
return ret;
return -ENODEV;
case 0x5937:
dev_info(dev, "found an RTL8366RB switch\n");
- smi->cpu_port = RTL8366RB_PORT_NUM_CPU;
- smi->num_ports = RTL8366RB_NUM_PORTS;
- smi->num_vlan_mc = RTL8366RB_NUM_VLANS;
- smi->mib_counters = rtl8366rb_mib_counters;
- smi->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters);
+ priv->cpu_port = RTL8366RB_PORT_NUM_CPU;
+ priv->num_ports = RTL8366RB_NUM_PORTS;
+ priv->num_vlan_mc = RTL8366RB_NUM_VLANS;
+ priv->mib_counters = rtl8366rb_mib_counters;
+ priv->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters);
break;
default:
dev_info(dev, "found an Unknown Realtek switch (id=0x%04x)\n",
break;
}
- ret = rtl8366rb_reset_chip(smi);
+ ret = rtl8366rb_reset_chip(priv);
if (ret)
return ret;
return 0;
}
-static const struct dsa_switch_ops rtl8366rb_switch_ops = {
+static const struct dsa_switch_ops rtl8366rb_switch_ops_smi = {
.get_tag_protocol = rtl8366_get_tag_protocol,
.setup = rtl8366rb_setup,
.phylink_mac_link_up = rtl8366rb_mac_link_up,
.port_max_mtu = rtl8366rb_max_mtu,
};
-static const struct realtek_smi_ops rtl8366rb_smi_ops = {
+static const struct dsa_switch_ops rtl8366rb_switch_ops_mdio = {
+ .get_tag_protocol = rtl8366_get_tag_protocol,
+ .setup = rtl8366rb_setup,
+ .phy_read = rtl8366rb_dsa_phy_read,
+ .phy_write = rtl8366rb_dsa_phy_write,
+ .phylink_mac_link_up = rtl8366rb_mac_link_up,
+ .phylink_mac_link_down = rtl8366rb_mac_link_down,
+ .get_strings = rtl8366_get_strings,
+ .get_ethtool_stats = rtl8366_get_ethtool_stats,
+ .get_sset_count = rtl8366_get_sset_count,
+ .port_bridge_join = rtl8366rb_port_bridge_join,
+ .port_bridge_leave = rtl8366rb_port_bridge_leave,
+ .port_vlan_filtering = rtl8366rb_vlan_filtering,
+ .port_vlan_add = rtl8366_vlan_add,
+ .port_vlan_del = rtl8366_vlan_del,
+ .port_enable = rtl8366rb_port_enable,
+ .port_disable = rtl8366rb_port_disable,
+ .port_pre_bridge_flags = rtl8366rb_port_pre_bridge_flags,
+ .port_bridge_flags = rtl8366rb_port_bridge_flags,
+ .port_stp_state_set = rtl8366rb_port_stp_state_set,
+ .port_fast_age = rtl8366rb_port_fast_age,
+ .port_change_mtu = rtl8366rb_change_mtu,
+ .port_max_mtu = rtl8366rb_max_mtu,
+};
+
+static const struct realtek_ops rtl8366rb_ops = {
.detect = rtl8366rb_detect,
.get_vlan_mc = rtl8366rb_get_vlan_mc,
.set_vlan_mc = rtl8366rb_set_vlan_mc,
.phy_write = rtl8366rb_phy_write,
};
-const struct realtek_smi_variant rtl8366rb_variant = {
- .ds_ops = &rtl8366rb_switch_ops,
- .ops = &rtl8366rb_smi_ops,
+const struct realtek_variant rtl8366rb_variant = {
+ .ds_ops_smi = &rtl8366rb_switch_ops_smi,
+ .ds_ops_mdio = &rtl8366rb_switch_ops_mdio,
+ .ops = &rtl8366rb_ops,
.clk_delay = 10,
.cmd_read = 0xa9,
.cmd_write = 0xa8,
.chip_data_sz = sizeof(struct rtl8366rb),
};
EXPORT_SYMBOL_GPL(rtl8366rb_variant);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Driver for RTL8366RB ethernet switch");
+MODULE_LICENSE("GPL");
cancel_delayed_work_sync(&priv->mib_work);
}
-static void xrs700x_phylink_validate(struct dsa_switch *ds, int port,
- unsigned long *supported,
- struct phylink_link_state *state)
+static void xrs700x_phylink_get_caps(struct dsa_switch *ds, int port,
+ struct phylink_config *config)
{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
-
switch (port) {
case 0:
+ __set_bit(PHY_INTERFACE_MODE_RMII,
+ config->supported_interfaces);
+ config->mac_capabilities = MAC_10FD | MAC_100FD;
break;
+
case 1:
case 2:
case 3:
- phylink_set(mask, 1000baseT_Full);
+ phy_interface_set_rgmii(config->supported_interfaces);
+ config->mac_capabilities = MAC_10FD | MAC_100FD | MAC_1000FD;
break;
+
default:
- linkmode_zero(supported);
dev_err(ds->dev, "Unsupported port: %i\n", port);
- return;
+ break;
}
-
- phylink_set_port_modes(mask);
-
- /* The switch only supports full duplex. */
- phylink_set(mask, 10baseT_Full);
- phylink_set(mask, 100baseT_Full);
-
- linkmode_and(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mask);
}
static void xrs700x_mac_link_up(struct dsa_switch *ds, int port,
.setup = xrs700x_setup,
.teardown = xrs700x_teardown,
.port_stp_state_set = xrs700x_port_stp_state_set,
- .phylink_validate = xrs700x_phylink_validate,
+ .phylink_get_caps = xrs700x_phylink_get_caps,
.phylink_mac_link_up = xrs700x_mac_link_up,
.get_strings = xrs700x_get_strings,
.get_sset_count = xrs700x_get_sset_count,
struct sk_buff *skb;
if (!first_frag)
- skb = netdev_alloc_skb_ip_align(rx_ring->netdev,
- rx_ring->rx_copybreak);
+ skb = napi_alloc_skb(rx_ring->napi, rx_ring->rx_copybreak);
else
- skb = build_skb(first_frag, ENA_PAGE_SIZE);
+ skb = napi_build_skb(first_frag, ENA_PAGE_SIZE);
if (unlikely(!skb)) {
ena_increase_stat(&rx_ring->rx_stats.skb_alloc_fail, 1,
ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST,
ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP,
ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT,
+ ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE,
};
static struct workqueue_struct *bnxt_pf_wq;
(BNXT_EVENT_RING_TYPE(data2) == \
ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX)
+#define BNXT_EVENT_PHC_EVENT_TYPE(data1) \
+ (((data1) & ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK) >>\
+ ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT)
+
+#define BNXT_EVENT_PHC_RTC_UPDATE(data1) \
+ (((data1) & ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK) >>\
+ ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT)
+
+#define BNXT_PHC_BITS 48
+
static int bnxt_async_event_process(struct bnxt *bp,
struct hwrm_async_event_cmpl *cmpl)
{
bnxt_event_error_report(bp, data1, data2);
goto async_event_process_exit;
}
+ case ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE: {
+ switch (BNXT_EVENT_PHC_EVENT_TYPE(data1)) {
+ case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE:
+ if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) {
+ struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+ u64 ns;
+
+ spin_lock_bh(&ptp->ptp_lock);
+ bnxt_ptp_update_current_time(bp);
+ ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) <<
+ BNXT_PHC_BITS) | ptp->current_time);
+ bnxt_ptp_rtc_timecounter_init(ptp, ns);
+ spin_unlock_bh(&ptp->ptp_lock);
+ }
+ break;
+ }
+ goto async_event_process_exit;
+ }
case ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE: {
u16 seq_id = le32_to_cpu(cmpl->event_data2) & 0xffff;
struct hwrm_port_mac_ptp_qcfg_output *resp;
struct hwrm_port_mac_ptp_qcfg_input *req;
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+ bool phc_cfg;
u8 flags;
int rc;
rc = -ENODEV;
goto exit;
}
- rc = bnxt_ptp_init(bp);
+ phc_cfg = (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0;
+ rc = bnxt_ptp_init(bp, phc_cfg);
if (rc)
netdev_warn(bp->dev, "PTP initialization failed.\n");
exit:
bp->fw_cap |= BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED;
if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED))
bp->fw_cap |= BNXT_FW_CAP_PTP_PPS;
+ if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED)
+ bp->fw_cap |= BNXT_FW_CAP_PTP_RTC;
if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT))
bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
/* VF-reps may need to be re-opened after the PF is re-opened */
if (BNXT_PF(bp))
bnxt_vf_reps_open(bp);
+ bnxt_ptp_init_rtc(bp, true);
return 0;
open_err_irq:
#define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000
#define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000
#define BNXT_FW_CAP_HOT_RESET 0x00200000
+ #define BNXT_FW_CAP_PTP_RTC 0x00400000
#define BNXT_FW_CAP_VLAN_RX_STRIP 0x01000000
#define BNXT_FW_CAP_VLAN_TX_INSERT 0x02000000
#define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED 0x04000000
#include <linux/ctype.h>
#include <linux/stringify.h>
#include <linux/ethtool.h>
+#include <linux/ethtool_netlink.h>
#include <linux/linkmode.h>
#include <linux/interrupt.h>
#include <linux/pci.h>
if (bp->flags & BNXT_FLAG_AGG_RINGS) {
ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT_JUM_ENA;
ering->rx_jumbo_max_pending = BNXT_MAX_RX_JUM_DESC_CNT;
+ kernel_ering->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED;
} else {
ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT;
ering->rx_jumbo_max_pending = 0;
+ kernel_ering->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED;
}
ering->tx_max_pending = BNXT_MAX_TX_DESC_CNT;
#define HWRM_FUNC_PTP_EXT_CFG 0x1a0UL
#define HWRM_FUNC_PTP_EXT_QCFG 0x1a1UL
#define HWRM_FUNC_KEY_CTX_ALLOC 0x1a2UL
+ #define HWRM_FUNC_BACKING_STORE_CFG_V2 0x1a3UL
+ #define HWRM_FUNC_BACKING_STORE_QCFG_V2 0x1a4UL
+ #define HWRM_FUNC_DBR_PACING_CFG 0x1a5UL
+ #define HWRM_FUNC_DBR_PACING_QCFG 0x1a6UL
+ #define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT 0x1a7UL
+ #define HWRM_FUNC_BACKING_STORE_QCAPS_V2 0x1a8UL
#define HWRM_SELFTEST_QLIST 0x200UL
#define HWRM_SELFTEST_EXEC 0x201UL
#define HWRM_SELFTEST_IRQ 0x202UL
#define HWRM_MFG_PRVSN_IMPORT_CERT 0x212UL
#define HWRM_MFG_PRVSN_GET_STATE 0x213UL
#define HWRM_MFG_GET_NVM_MEASUREMENT 0x214UL
+ #define HWRM_MFG_PSOC_QSTATUS 0x215UL
+ #define HWRM_MFG_SELFTEST_QLIST 0x216UL
+ #define HWRM_MFG_SELFTEST_EXEC 0x217UL
#define HWRM_TF 0x2bcUL
#define HWRM_TF_VERSION_GET 0x2bdUL
#define HWRM_TF_SESSION_OPEN 0x2c6UL
#define HWRM_VERSION_MAJOR 1
#define HWRM_VERSION_MINOR 10
#define HWRM_VERSION_UPDATE 2
-#define HWRM_VERSION_RSVD 63
-#define HWRM_VERSION_STR "1.10.2.63"
+#define HWRM_VERSION_RSVD 73
+#define HWRM_VERSION_STR "1.10.2.73"
/* hwrm_ver_get_input (size:192b/24B) */
struct hwrm_ver_get_input {
#define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE 0x40UL
#define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE 0x41UL
#define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST 0x42UL
- #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_MASTER 0x43UL
+ #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE 0x43UL
#define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP 0x44UL
#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT 0x45UL
- #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x46UL
+ #define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD 0x46UL
+ #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x47UL
#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL
#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL
#define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
__le32 event_data1;
};
-/* hwrm_async_event_cmpl_phc_master (size:128b/16B) */
-struct hwrm_async_event_cmpl_phc_master {
+/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */
+struct hwrm_async_event_cmpl_phc_update {
__le16 type;
- #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_MASK 0x3fUL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_SFT 0
- #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT 0x2eUL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_LAST ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK 0x3fUL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT 0
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT 0x2eUL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT
__le16 event_id;
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER 0x43UL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE
__le32 event_data2;
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_SFT 0
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_SFT 16
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT 16
u8 opaque_v;
- #define ASYNC_EVENT_CMPL_PHC_MASTER_V 0x1UL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_MASK 0xfeUL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_SFT 1
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_V 0x1UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1
u8 timestamp_lo;
__le16 timestamp_hi;
__le32 event_data1;
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_MASK 0xfUL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_SFT 0
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL
- #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK 0xfUL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT 0
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE 0x4UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK 0xffff0UL
+ #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT 4
};
/* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */
#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE
};
+/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold {
+ __le16 type;
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK 0x3fUL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT 0
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT 0x2eUL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT
+ __le16 event_id;
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT
+ __le32 event_data2;
+ u8 opaque_v;
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V 0x1UL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1
+ u8 timestamp_lo;
+ __le16 timestamp_hi;
+ __le32 event_data1;
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT 0
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL
+ #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD
+};
+
/* hwrm_func_reset_input (size:192b/24B) */
struct hwrm_func_reset_input {
__le16 req_type;
#define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL 0x800000UL
#define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED 0x1000000UL
#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP 0x2000000UL
+ #define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED 0x4000000UL
+ #define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED 0x8000000UL
+ #define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED 0x10000000UL
+ #define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED 0x20000000UL
u8 max_schqs;
u8 mpc_chnls_cap;
#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE 0x1UL
__le16 rkc_entry_size;
__le32 tkc_max_entries;
__le32 rkc_max_entries;
- u8 rsvd[7];
+ u8 rsvd1[7];
u8 valid;
};
u8 valid;
};
-/* hwrm_func_ptp_cfg_input (size:320b/40B) */
+/* hwrm_func_ptp_cfg_input (size:384b/48B) */
struct hwrm_func_ptp_cfg_input {
__le16 req_type;
__le16 cmpl_ring;
#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD 0x8UL
#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP 0x10UL
#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE 0x20UL
+ #define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME 0x40UL
u8 ptp_pps_event;
#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL 0x1UL
#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL 0x2UL
__le32 ptp_freq_adj_ext_up;
__le32 ptp_freq_adj_ext_phase_lower;
__le32 ptp_freq_adj_ext_phase_upper;
+ __le64 ptp_set_time;
};
/* hwrm_func_ptp_cfg_output (size:128b/16B) */
u8 valid;
};
+/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */
+struct hwrm_func_ptp_ext_cfg_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 enables;
+ #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID 0x1UL
+ #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID 0x2UL
+ #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE 0x4UL
+ #define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER 0x8UL
+ __le16 phc_master_fid;
+ __le16 phc_sec_fid;
+ u8 phc_sec_mode;
+ #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH 0x0UL
+ #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL 0x1UL
+ #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL
+ #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY
+ u8 unused_0;
+ __le32 failover_timer;
+ u8 unused_1[4];
+};
+
+/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_ext_cfg_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 unused_0[7];
+ u8 valid;
+};
+
+/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */
+struct hwrm_func_ptp_ext_qcfg_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ u8 unused_0[8];
+};
+
+/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */
+struct hwrm_func_ptp_ext_qcfg_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le16 phc_master_fid;
+ __le16 phc_sec_fid;
+ __le16 phc_active_fid0;
+ __le16 phc_active_fid1;
+ __le32 last_failover_event;
+ __le16 from_fid;
+ __le16 to_fid;
+ u8 unused_0[7];
+ u8 valid;
+};
+
+/* hwrm_func_backing_store_cfg_v2_input (size:448b/56B) */
+struct hwrm_func_backing_store_cfg_v2_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 type;
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TKC 0x13UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RKC 0x14UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
+ __le16 instance;
+ __le32 flags;
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL
+ __le64 page_dir;
+ __le32 num_entries;
+ __le16 entry_size;
+ u8 page_size_pbl_level;
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK 0xfUL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT 0
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0 0x0UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1 0x1UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2 0x2UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK 0xf0UL
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT 4
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K (0x0UL << 4)
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K (0x1UL << 4)
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K (0x2UL << 4)
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M (0x3UL << 4)
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M (0x4UL << 4)
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G (0x5UL << 4)
+ #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G
+ u8 subtype_valid_cnt;
+ __le32 split_entry_0;
+ __le32 split_entry_1;
+ __le32 split_entry_2;
+ __le32 split_entry_3;
+};
+
+/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_v2_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 rsvd0[7];
+ u8 valid;
+};
+
+/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */
+struct hwrm_func_backing_store_qcfg_v2_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 type;
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP 0x0UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ 0x1UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ 0x2UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC 0x3UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT 0x4UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV 0xeUL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM 0xfUL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC 0x13UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC 0x14UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID 0xffffUL
+ #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
+ __le16 instance;
+ u8 rsvd[4];
+};
+
+/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */
+struct hwrm_func_backing_store_qcfg_v2_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le16 type;
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TKC 0x13UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RKC 0x14UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
+ __le16 instance;
+ __le32 flags;
+ __le64 page_dir;
+ __le32 num_entries;
+ u8 page_size_pbl_level;
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK 0xfUL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT 0
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0 0x0UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1 0x1UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2 0x2UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK 0xf0UL
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT 4
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K (0x0UL << 4)
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K (0x1UL << 4)
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K (0x2UL << 4)
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M (0x3UL << 4)
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M (0x4UL << 4)
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G (0x5UL << 4)
+ #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G
+ u8 subtype_valid_cnt;
+ u8 rsvd[2];
+ __le32 split_entry_0;
+ __le32 split_entry_1;
+ __le32 split_entry_2;
+ __le32 split_entry_3;
+ u8 rsvd2[7];
+ u8 valid;
+};
+
+/* qpc_split_entries (size:128b/16B) */
+struct qpc_split_entries {
+ __le32 qp_num_l2_entries;
+ __le32 qp_num_qp1_entries;
+ __le32 rsvd[2];
+};
+
+/* srq_split_entries (size:128b/16B) */
+struct srq_split_entries {
+ __le32 srq_num_l2_entries;
+ __le32 rsvd;
+ __le32 rsvd2[2];
+};
+
+/* cq_split_entries (size:128b/16B) */
+struct cq_split_entries {
+ __le32 cq_num_l2_entries;
+ __le32 rsvd;
+ __le32 rsvd2[2];
+};
+
+/* vnic_split_entries (size:128b/16B) */
+struct vnic_split_entries {
+ __le32 vnic_num_vnic_entries;
+ __le32 rsvd;
+ __le32 rsvd2[2];
+};
+
+/* mrav_split_entries (size:128b/16B) */
+struct mrav_split_entries {
+ __le32 mrav_num_av_entries;
+ __le32 rsvd;
+ __le32 rsvd2[2];
+};
+
+/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
+struct hwrm_func_backing_store_qcaps_v2_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 type;
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC 0x13UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC 0x14UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL
+ #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
+ u8 rsvd[6];
+};
+
+/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */
+struct hwrm_func_backing_store_qcaps_v2_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ __le16 type;
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TKC 0x13UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RKC 0x14UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
+ __le16 entry_size;
+ __le32 flags;
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT 0x1UL
+ #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID 0x2UL
+ __le32 instance_bit_map;
+ u8 ctx_init_value;
+ u8 ctx_init_offset;
+ u8 entry_multiple;
+ u8 rsvd;
+ __le32 max_num_entries;
+ __le32 min_num_entries;
+ __le16 next_valid_type;
+ u8 subtype_valid_cnt;
+ u8 rsvd2;
+ __le32 split_entry_0;
+ __le32 split_entry_1;
+ __le32 split_entry_2;
+ __le32 split_entry_3;
+ u8 rsvd3[3];
+ u8 valid;
+};
+
/* hwrm_func_drv_if_change_input (size:192b/24B) */
struct hwrm_func_drv_if_change_input {
__le16 req_type;
u8 valid;
};
-/* hwrm_port_mac_cfg_input (size:384b/48B) */
+/* hwrm_port_mac_cfg_input (size:448b/56B) */
struct hwrm_port_mac_cfg_input {
__le16 req_type;
__le16 cmpl_ring;
#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT 5
u8 unused_0[3];
__le32 ptp_freq_adj_ppb;
- __le32 ptp_adj_phase;
+ u8 unused_1[4];
+ __le64 ptp_adj_phase;
};
/* hwrm_port_mac_cfg_output (size:128b/16B) */
#define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS 0x4UL
#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS 0x8UL
#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK 0x10UL
+ #define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED 0x20UL
u8 unused_0[3];
__le32 rx_ts_reg_off_lower;
__le32 rx_ts_reg_off_upper;
#define PORT_PHY_QCAPS_RESP_PORT_CNT_2 0x2UL
#define PORT_PHY_QCAPS_RESP_PORT_CNT_3 0x3UL
#define PORT_PHY_QCAPS_RESP_PORT_CNT_4 0x4UL
- #define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST PORT_PHY_QCAPS_RESP_PORT_CNT_4
+ #define PORT_PHY_QCAPS_RESP_PORT_CNT_12 0xcUL
+ #define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST PORT_PHY_QCAPS_RESP_PORT_CNT_12
__le16 supported_speeds_force_mode;
#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD 0x1UL
#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB 0x2UL
__le16 flags2;
#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL
#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL
- u8 unused_0[1];
+ u8 internal_port_cnt;
u8 valid;
};
__le16 target_id;
__le64 resp_addr;
__le32 hash_type;
- #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 0x1UL
- #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 0x2UL
- #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 0x4UL
- #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL
- #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL
- #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 0x1UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 0x2UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 0x4UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL
+ #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL 0x40UL
__le16 vnic_id;
u8 ring_table_pair_index;
u8 hash_mode_flags;
u8 valid;
};
+/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
struct hwrm_tunnel_dst_port_query_input {
__le16 req_type;
__le16 cmpl_ring;
u8 valid;
};
+/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */
+struct hwrm_dbg_crashdump_medium_cfg_input {
+ __le16 req_type;
+ __le16 cmpl_ring;
+ __le16 seq_id;
+ __le16 target_id;
+ __le64 resp_addr;
+ __le16 output_dest_flags;
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR 0x1UL
+ __le16 pg_size_lvl;
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK 0x3UL
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT 0
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0 0x0UL
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1 0x1UL
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2 0x2UL
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK 0x1cUL
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT 2
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K (0x0UL << 2)
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K (0x1UL << 2)
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K (0x2UL << 2)
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M (0x3UL << 2)
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M (0x4UL << 2)
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G (0x5UL << 2)
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT 5
+ __le32 size;
+ __le32 coredump_component_disable_flags;
+ #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM 0x1UL
+ __le32 unused_0;
+ __le64 pbl;
+};
+
+/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */
+struct hwrm_dbg_crashdump_medium_cfg_output {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 unused_1[7];
+ u8 valid;
+};
+
/* coredump_segment_record (size:128b/16B) */
struct coredump_segment_record {
__le16 component_id;
__le16 resp_len;
__le64 installed_items;
u8 result;
- #define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS 0x0UL
- #define NVM_INSTALL_UPDATE_RESP_RESULT_LAST NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS 0x0UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE 0xffUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE 0xfdUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER 0xfbUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER 0xf3UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE 0xf2UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER 0xecUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE 0xebUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM 0xeaUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH 0xe9UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST 0xe8UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER 0xe7UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM 0xe6UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM 0xe5UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH 0xe4UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE 0xe1UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV 0xceUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID 0xcdUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR 0xccUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID 0xcbUL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM 0xc5UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM 0xc4UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM 0xc3UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR 0xb9UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR 0xb8UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND 0xb0UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED 0xa7UL
+ #define NVM_INSTALL_UPDATE_RESP_RESULT_LAST NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED
u8 problem_item;
#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE 0x0UL
#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL
#include "bnxt_hwrm.h"
#include "bnxt_ptp.h"
+static int bnxt_ptp_cfg_settime(struct bnxt *bp, u64 time)
+{
+ struct hwrm_func_ptp_cfg_input *req;
+ int rc;
+
+ rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_CFG);
+ if (rc)
+ return rc;
+
+ req->enables = cpu_to_le16(FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME);
+ req->ptp_set_time = cpu_to_le64(time);
+ return hwrm_req_send(bp, req);
+}
+
int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off)
{
unsigned int ptp_class;
ptp_info);
u64 ns = timespec64_to_ns(ts);
+ if (ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC)
+ return bnxt_ptp_cfg_settime(ptp->bp, ns);
+
spin_lock_bh(&ptp->ptp_lock);
timecounter_init(&ptp->tc, &ptp->cc, ns);
spin_unlock_bh(&ptp->ptp_lock);
return 0;
}
+/* Caller holds ptp_lock */
+void bnxt_ptp_update_current_time(struct bnxt *bp)
+{
+ struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+
+ bnxt_refclk_read(ptp->bp, NULL, &ptp->current_time);
+ WRITE_ONCE(ptp->old_time, ptp->current_time);
+}
+
+static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta)
+{
+ struct hwrm_port_mac_cfg_input *req;
+ int rc;
+
+ rc = hwrm_req_init(ptp->bp, req, HWRM_PORT_MAC_CFG);
+ if (rc)
+ return rc;
+
+ req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE);
+ req->ptp_adj_phase = cpu_to_le64(delta);
+
+ rc = hwrm_req_send(ptp->bp, req);
+ if (rc) {
+ netdev_err(ptp->bp->dev, "ptp adjphc failed. rc = %x\n", rc);
+ } else {
+ spin_lock_bh(&ptp->ptp_lock);
+ bnxt_ptp_update_current_time(ptp->bp);
+ spin_unlock_bh(&ptp->ptp_lock);
+ }
+
+ return rc;
+}
+
static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta)
{
struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg,
ptp_info);
+ if (ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC)
+ return bnxt_ptp_adjphc(ptp, delta);
+
spin_lock_bh(&ptp->ptp_lock);
timecounter_adjtime(&ptp->tc, delta);
spin_unlock_bh(&ptp->ptp_lock);
return !(bp->fw_cap & BNXT_FW_CAP_PTP_PPS) == !ptp->ptp_info.pin_config;
}
-int bnxt_ptp_init(struct bnxt *bp)
+static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc)
+{
+ struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+
+ if (!ptp->ptp_clock) {
+ memset(&ptp->cc, 0, sizeof(ptp->cc));
+ ptp->cc.read = bnxt_cc_read;
+ ptp->cc.mask = CYCLECOUNTER_MASK(48);
+ ptp->cc.shift = 0;
+ ptp->cc.mult = 1;
+ ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD;
+ }
+ if (init_tc)
+ timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
+}
+
+/* Caller holds ptp_lock */
+void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns)
+{
+ timecounter_init(&ptp->tc, &ptp->cc, ns);
+ /* For RTC, cycle_last must be in sync with the timecounter value. */
+ ptp->tc.cycle_last = ns & ptp->cc.mask;
+}
+
+int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
+{
+ struct timespec64 tsp;
+ u64 ns;
+ int rc;
+
+ if (!bp->ptp_cfg || !(bp->fw_cap & BNXT_FW_CAP_PTP_RTC))
+ return -ENODEV;
+
+ if (!phc_cfg) {
+ ktime_get_real_ts64(&tsp);
+ ns = timespec64_to_ns(&tsp);
+ rc = bnxt_ptp_cfg_settime(bp, ns);
+ if (rc)
+ return rc;
+ } else {
+ rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME, &ns);
+ if (rc)
+ return rc;
+ }
+ spin_lock_bh(&bp->ptp_cfg->ptp_lock);
+ bnxt_ptp_rtc_timecounter_init(bp->ptp_cfg, ns);
+ spin_unlock_bh(&bp->ptp_cfg->ptp_lock);
+
+ return 0;
+}
+
+static void bnxt_ptp_free(struct bnxt *bp)
+{
+ struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
+
+ if (ptp->ptp_clock) {
+ ptp_clock_unregister(ptp->ptp_clock);
+ ptp->ptp_clock = NULL;
+ kfree(ptp->ptp_info.pin_config);
+ ptp->ptp_info.pin_config = NULL;
+ }
+}
+
+int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
{
struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
int rc;
if (rc)
return rc;
+ if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) {
+ bnxt_ptp_timecounter_init(bp, false);
+ rc = bnxt_ptp_init_rtc(bp, phc_cfg);
+ if (rc)
+ goto out;
+ }
+
if (ptp->ptp_clock && bnxt_pps_config_ok(bp))
return 0;
- if (ptp->ptp_clock) {
- ptp_clock_unregister(ptp->ptp_clock);
- ptp->ptp_clock = NULL;
- kfree(ptp->ptp_info.pin_config);
- ptp->ptp_info.pin_config = NULL;
- }
+ bnxt_ptp_free(bp);
+
atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS);
spin_lock_init(&ptp->ptp_lock);
- memset(&ptp->cc, 0, sizeof(ptp->cc));
- ptp->cc.read = bnxt_cc_read;
- ptp->cc.mask = CYCLECOUNTER_MASK(48);
- ptp->cc.shift = 0;
- ptp->cc.mult = 1;
-
- ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD;
- timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
+ if (!(bp->fw_cap & BNXT_FW_CAP_PTP_RTC))
+ bnxt_ptp_timecounter_init(bp, true);
ptp->ptp_info = bnxt_ptp_caps;
if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) {
int err = PTR_ERR(ptp->ptp_clock);
ptp->ptp_clock = NULL;
- bnxt_unmap_ptp_regs(bp);
- return err;
+ rc = err;
+ goto out;
}
if (bp->flags & BNXT_FLAG_CHIP_P5) {
spin_lock_bh(&ptp->ptp_lock);
ptp_schedule_worker(ptp->ptp_clock, 0);
}
return 0;
+
+out:
+ bnxt_ptp_free(bp);
+ bnxt_unmap_ptp_regs(bp);
+ return rc;
}
void bnxt_ptp_clear(struct bnxt *bp)
#endif
int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off);
+void bnxt_ptp_update_current_time(struct bnxt *bp);
void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2);
void bnxt_ptp_reapply_pps(struct bnxt *bp);
int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb);
int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
-int bnxt_ptp_init(struct bnxt *bp);
+void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns);
+int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg);
+int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg);
void bnxt_ptp_clear(struct bnxt *bp);
#endif
if (!p->eee_enabled) {
bcmgenet_eee_enable_set(dev, false);
} else {
- ret = phy_init_eee(dev->phydev, 0);
+ ret = phy_init_eee(dev->phydev, false);
if (ret) {
netif_err(priv, hw, dev, "EEE initialization failed\n");
return ret;
#include <linux/ptp_clock_kernel.h>
#include <linux/net_tstamp.h>
#include <linux/interrupt.h>
+#include <linux/phy/phy.h>
#if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP)
#define MACB_EXT_DESC
u32 wol;
struct macb_ptp_info *ptp_info; /* macb-ptp interface */
+
+ struct phy *sgmii_phy; /* for ZynqMP SGMII mode */
+
#ifdef MACB_EXT_DESC
uint8_t hw_dma_cap;
#endif
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/iopoll.h>
+#include <linux/phy/phy.h>
#include <linux/pm_runtime.h>
+#include <linux/reset.h>
#include "macb.h"
/* This structure is only used for MACB on SiFive FU540 devices */
macb_init_hw(bp);
- err = macb_phylink_connect(bp);
+ err = phy_power_on(bp->sgmii_phy);
if (err)
goto reset_hw;
+ err = macb_phylink_connect(bp);
+ if (err)
+ goto phy_off;
+
netif_tx_start_all_queues(dev);
if (bp->ptp_info)
return 0;
+phy_off:
+ phy_power_off(bp->sgmii_phy);
+
reset_hw:
macb_reset_hw(bp);
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
phylink_stop(bp->phylink);
phylink_disconnect_phy(bp->phylink);
+ phy_power_off(bp->sgmii_phy);
+
spin_lock_irqsave(&bp->lock, flags);
macb_reset_hw(bp);
netif_carrier_off(dev);
.usrio = &macb_default_usrio,
};
+static int zynqmp_init(struct platform_device *pdev)
+{
+ struct net_device *dev = platform_get_drvdata(pdev);
+ struct macb *bp = netdev_priv(dev);
+ int ret;
+
+ if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) {
+ /* Ensure PS-GTR PHY device used in SGMII mode is ready */
+ bp->sgmii_phy = devm_phy_get(&pdev->dev, "sgmii-phy");
+
+ if (IS_ERR(bp->sgmii_phy)) {
+ ret = PTR_ERR(bp->sgmii_phy);
+ dev_err_probe(&pdev->dev, ret,
+ "failed to get PS-GTR PHY\n");
+ return ret;
+ }
+
+ ret = phy_init(bp->sgmii_phy);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to init PS-GTR PHY: %d\n",
+ ret);
+ return ret;
+ }
+ }
+
+ /* Fully reset GEM controller at hardware level using zynqmp-reset driver,
+ * if mapped in device tree.
+ */
+ ret = device_reset_optional(&pdev->dev);
+ if (ret) {
+ dev_err_probe(&pdev->dev, ret, "failed to reset controller");
+ phy_exit(bp->sgmii_phy);
+ return ret;
+ }
+
+ ret = macb_init(pdev);
+ if (ret)
+ phy_exit(bp->sgmii_phy);
+
+ return ret;
+}
+
static const struct macb_config zynqmp_config = {
.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
MACB_CAPS_JUMBO |
MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH,
.dma_burst_length = 16,
.clk_init = macb_clk_init,
- .init = macb_init,
+ .init = zynqmp_init,
.jumbo_max_len = 10240,
.usrio = &macb_default_usrio,
};
err = macb_mii_init(bp);
if (err)
- goto err_out_free_netdev;
+ goto err_out_phy_exit;
netif_carrier_off(dev);
mdiobus_unregister(bp->mii_bus);
mdiobus_free(bp->mii_bus);
+err_out_phy_exit:
+ phy_exit(bp->sgmii_phy);
+
err_out_free_netdev:
free_netdev(dev);
if (dev) {
bp = netdev_priv(dev);
+ phy_exit(bp->sgmii_phy);
mdiobus_unregister(bp->mii_bus);
mdiobus_free(bp->mii_bus);
struct device *dev = &bgx->pdev->dev;
struct acpi_device *adev;
- if (acpi_bus_get_device(handle, &adev))
+ adev = acpi_fetch_acpi_dev(handle);
+ if (!adev)
goto out;
acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac);
static int gemini_ethernet_port_probe(struct platform_device *pdev)
{
char *port_names[2] = { "ethernet0", "ethernet1" };
+ struct device_node *np = pdev->dev.of_node;
struct gemini_ethernet_port *port;
struct device *dev = &pdev->dev;
struct gemini_ethernet *geth;
struct net_device *netdev;
struct device *parent;
+ u8 mac[ETH_ALEN];
unsigned int id;
int irq;
int ret;
netif_napi_add(netdev, &port->napi, gmac_napi_poll,
DEFAULT_NAPI_WEIGHT);
+ ret = of_get_mac_address(np, mac);
+ if (!ret) {
+ dev_info(dev, "Setting macaddr from DT %pM\n", mac);
+ memcpy(port->mac_addr, mac, ETH_ALEN);
+ }
+
if (is_valid_ether_addr((void *)port->mac_addr)) {
eth_hw_addr_set(netdev, (u8 *)port->mac_addr);
} else {
struct tulip_private *tp = netdev_priv(dev);
void __iomem *ioaddr = tp->base_addr;
u32 phy_reg = ioread32(ioaddr + 0xB8);
- u32 new_csr6 = tp->csr6 & ~0x40C40200;
+ u32 new_csr6;
if (phy_reg & 0x78000000) { /* Ignore baseT4 */
if (phy_reg & 0x20000000) dev->if_port = 5;
return err;
}
+static struct phylink_pcs *dpaa2_mac_select_pcs(struct phylink_config *config,
+ phy_interface_t interface)
+{
+ struct dpaa2_mac *mac = phylink_to_dpaa2_mac(config);
+
+ return mac->pcs;
+}
+
static void dpaa2_mac_config(struct phylink_config *config, unsigned int mode,
const struct phylink_link_state *state)
{
static const struct phylink_mac_ops dpaa2_mac_phylink_ops = {
.validate = phylink_generic_validate,
+ .mac_select_pcs = dpaa2_mac_select_pcs,
.mac_config = dpaa2_mac_config,
.mac_link_up = dpaa2_mac_link_up,
.mac_link_down = dpaa2_mac_link_down,
}
mac->phylink = phylink;
- if (mac->pcs)
- phylink_set_pcs(mac->phylink, mac->pcs);
-
err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0);
if (err) {
netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err);
enetc_imdio_remove(pf);
}
+static struct phylink_pcs *
+enetc_pl_mac_select_pcs(struct phylink_config *config, phy_interface_t iface)
+{
+ struct enetc_pf *pf = phylink_to_enetc_pf(config);
+
+ return pf->pcs;
+}
+
static void enetc_pl_mac_config(struct phylink_config *config,
unsigned int mode,
const struct phylink_link_state *state)
{
struct enetc_pf *pf = phylink_to_enetc_pf(config);
- struct enetc_ndev_priv *priv;
enetc_mac_config(&pf->si->hw, state->interface);
-
- priv = netdev_priv(pf->si->ndev);
- if (pf->pcs)
- phylink_set_pcs(priv->phylink, pf->pcs);
}
static void enetc_force_rgmii_mac(struct enetc_hw *hw, int speed, int duplex)
static const struct phylink_mac_ops enetc_mac_phylink_ops = {
.validate = phylink_generic_validate,
+ .mac_select_pcs = enetc_pl_mac_select_pcs,
.mac_config = enetc_pl_mac_config,
.mac_link_up = enetc_pl_mac_link_up,
.mac_link_down = enetc_pl_mac_link_down,
int ret = 0;
if (enable) {
- ret = phy_init_eee(ndev->phydev, 0);
+ ret = phy_init_eee(ndev->phydev, false);
if (ret)
return ret;
u32 val, tempval;
struct timespec64 ts;
u64 ns;
- val = 0;
if (fep->pps_enable == enable)
return 0;
#include <linux/acpi.h>
#include <linux/acpi_mdio.h>
+#include <linux/clk.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/mdio.h>
} __packed;
#define MDIO_STAT_ENC BIT(6)
-#define MDIO_STAT_CLKDIV(x) (((x>>1) & 0xff) << 8)
+#define MDIO_STAT_CLKDIV(x) (((x) & 0x1ff) << 7)
#define MDIO_STAT_BSY BIT(0)
#define MDIO_STAT_RD_ER BIT(1)
+#define MDIO_STAT_PRE_DIS BIT(5)
#define MDIO_CTL_DEV_ADDR(x) (x & 0x1f)
#define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5)
#define MDIO_CTL_PRE_DIS BIT(10)
struct mdio_fsl_priv {
struct tgec_mdio_controller __iomem *mdio_base;
+ struct clk *enet_clk;
+ u32 mdc_freq;
bool is_little_endian;
bool has_a009885;
bool has_a011043;
return ret;
}
+static int xgmac_mdio_set_mdc_freq(struct mii_bus *bus)
+{
+ struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv;
+ struct tgec_mdio_controller __iomem *regs = priv->mdio_base;
+ struct device *dev = bus->parent;
+ u32 mdio_stat, div;
+
+ if (device_property_read_u32(dev, "clock-frequency", &priv->mdc_freq))
+ return 0;
+
+ priv->enet_clk = devm_clk_get(dev, NULL);
+ if (IS_ERR(priv->enet_clk)) {
+ dev_err(dev, "Input clock unknown, not changing MDC frequency");
+ return PTR_ERR(priv->enet_clk);
+ }
+
+ div = ((clk_get_rate(priv->enet_clk) / priv->mdc_freq) - 1) / 2;
+ if (div < 5 || div > 0x1ff) {
+ dev_err(dev, "Requested MDC frequency is out of range, ignoring");
+ return -EINVAL;
+ }
+
+ mdio_stat = xgmac_read32(®s->mdio_stat, priv->is_little_endian);
+ mdio_stat &= ~MDIO_STAT_CLKDIV(0x1ff);
+ mdio_stat |= MDIO_STAT_CLKDIV(div);
+ xgmac_write32(mdio_stat, ®s->mdio_stat, priv->is_little_endian);
+ return 0;
+}
+
+static void xgmac_mdio_set_suppress_preamble(struct mii_bus *bus)
+{
+ struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv;
+ struct tgec_mdio_controller __iomem *regs = priv->mdio_base;
+ struct device *dev = bus->parent;
+ u32 mdio_stat;
+
+ if (!device_property_read_bool(dev, "suppress-preamble"))
+ return;
+
+ mdio_stat = xgmac_read32(®s->mdio_stat, priv->is_little_endian);
+ mdio_stat |= MDIO_STAT_PRE_DIS;
+ xgmac_write32(mdio_stat, ®s->mdio_stat, priv->is_little_endian);
+}
+
static int xgmac_mdio_probe(struct platform_device *pdev)
{
struct fwnode_handle *fwnode;
return -EINVAL;
}
- bus = mdiobus_alloc_size(sizeof(struct mdio_fsl_priv));
+ bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(struct mdio_fsl_priv));
if (!bus)
return -ENOMEM;
bus->probe_capabilities = MDIOBUS_C22_C45;
snprintf(bus->id, MII_BUS_ID_SIZE, "%pa", &res->start);
- /* Set the PHY base address */
priv = bus->priv;
- priv->mdio_base = ioremap(res->start, resource_size(res));
- if (!priv->mdio_base) {
- ret = -ENOMEM;
- goto err_ioremap;
- }
+ priv->mdio_base = devm_ioremap(&pdev->dev, res->start,
+ resource_size(res));
+ if (!priv->mdio_base)
+ return -ENOMEM;
/* For both ACPI and DT cases, endianness of MDIO controller
* needs to be specified using "little-endian" property.
priv->has_a011043 = device_property_read_bool(&pdev->dev,
"fsl,erratum-a011043");
+ xgmac_mdio_set_suppress_preamble(bus);
+
+ ret = xgmac_mdio_set_mdc_freq(bus);
+ if (ret)
+ return ret;
+
fwnode = pdev->dev.fwnode;
if (is_of_node(fwnode))
ret = of_mdiobus_register(bus, to_of_node(fwnode));
ret = -EINVAL;
if (ret) {
dev_err(&pdev->dev, "cannot register MDIO bus\n");
- goto err_registration;
+ return ret;
}
platform_set_drvdata(pdev, bus);
return 0;
-
-err_registration:
- iounmap(priv->mdio_base);
-
-err_ioremap:
- mdiobus_free(bus);
-
- return ret;
-}
-
-static int xgmac_mdio_remove(struct platform_device *pdev)
-{
- struct mii_bus *bus = platform_get_drvdata(pdev);
- struct mdio_fsl_priv *priv = bus->priv;
-
- mdiobus_unregister(bus);
- iounmap(priv->mdio_base);
- mdiobus_free(bus);
-
- return 0;
}
static const struct of_device_id xgmac_mdio_match[] = {
.acpi_match_table = xgmac_acpi_match,
},
.probe = xgmac_mdio_probe,
- .remove = xgmac_mdio_remove,
};
module_platform_driver(xgmac_mdio_driver);
resource_size_t flash_start, flash_len;
static int cards_found;
u16 aspm_disable_flag = 0;
- int bars, i, err, pci_using_dac;
u16 eeprom_data = 0;
u16 eeprom_apme_mask = E1000_EEPROM_APME;
+ int bars, i, err;
s32 ret_val = 0;
if (ei->flags2 & FLAG2_DISABLE_ASPM_L0S)
if (err)
return err;
- pci_using_dac = 0;
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (!err) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "No usable DMA configuration, aborting\n");
- goto err_dma;
- }
+ if (err) {
+ dev_err(&pdev->dev,
+ "No usable DMA configuration, aborting\n");
+ goto err_dma;
}
bars = pci_select_bars(pdev, IORESOURCE_MEM);
netdev->priv_flags |= IFF_UNICAST_FLT;
- if (pci_using_dac) {
- netdev->features |= NETIF_F_HIGHDMA;
- netdev->vlan_features |= NETIF_F_HIGHDMA;
- }
+ netdev->features |= NETIF_F_HIGHDMA;
+ netdev->vlan_features |= NETIF_F_HIGHDMA;
/* MTU range: 68 - max_hw_frame_size */
netdev->min_mtu = ETH_MIN_MTU;
/* set up for high or low dma */
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
if (err) {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "DMA configuration failed: 0x%x\n", err);
- goto err_dma;
- }
+ dev_err(&pdev->dev,
+ "DMA configuration failed: 0x%x\n", err);
+ goto err_dma;
}
/* set up pci connections */
static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring,
struct xdp_buff *xdp)
{
+ unsigned int totalsize = xdp->data_end - xdp->data_meta;
unsigned int metasize = xdp->data - xdp->data_meta;
- unsigned int datasize = xdp->data_end - xdp->data;
struct sk_buff *skb;
+ net_prefetch(xdp->data_meta);
+
/* allocate a skb to store the frags */
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- xdp->data_end - xdp->data_hard_start,
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
goto out;
- skb_reserve(skb, xdp->data - xdp->data_hard_start);
- memcpy(__skb_put(skb, datasize), xdp->data, datasize);
- if (metasize)
+ memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+ ALIGN(totalsize, sizeof(long)));
+
+ if (metasize) {
skb_metadata_set(skb, metasize);
+ __skb_pull(skb, metasize);
+ }
out:
xsk_buff_free(xdp);
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
if (err) {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "DMA configuration failed: 0x%x\n", err);
- goto err_dma;
- }
+ dev_err(&pdev->dev,
+ "DMA configuration failed: 0x%x\n", err);
+ goto err_dma;
}
err = pci_request_regions(pdev, iavf_driver_name);
/* set up for high or low DMA */
err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
- if (err)
- err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
if (err) {
dev_err(dev, "DMA configuration failed: 0x%x\n", err);
return err;
ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf,
struct xdp_buff *xdp)
{
+ unsigned int metasize = xdp->data - xdp->data_meta;
unsigned int size = xdp->data_end - xdp->data;
unsigned int headlen;
struct sk_buff *skb;
/* prefetch first cache line of first page */
- net_prefetch(xdp->data);
+ net_prefetch(xdp->data_meta);
/* allocate a skb to store the frags */
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE,
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
+ ICE_RX_HDR_SIZE + metasize,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE);
/* align pull length to size of long to optimize memcpy performance */
- memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen,
- sizeof(long)));
+ memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta,
+ ALIGN(headlen + metasize, sizeof(long)));
+
+ if (metasize) {
+ skb_metadata_set(skb, metasize);
+ __skb_pull(skb, metasize);
+ }
/* if we exhaust the linear part then add what is left as a frag */
size -= headlen;
static struct sk_buff *
ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
{
- unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
+ unsigned int totalsize = xdp->data_end - xdp->data_meta;
unsigned int metasize = xdp->data - xdp->data_meta;
- unsigned int datasize = xdp->data_end - xdp->data;
struct sk_buff *skb;
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
+ net_prefetch(xdp->data_meta);
+
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
- skb_reserve(skb, xdp->data - xdp->data_hard_start);
- memcpy(__skb_put(skb, datasize), xdp->data, datasize);
- if (metasize)
+ memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+ ALIGN(totalsize, sizeof(long)));
+
+ if (metasize) {
skb_metadata_set(skb, metasize);
+ __skb_pull(skb, metasize);
+ }
xsk_buff_free(xdp);
return skb;
s32 ret_val;
static int global_quad_port_a; /* global quad port a indication */
const struct e1000_info *ei = igb_info_tbl[ent->driver_data];
- int err, pci_using_dac;
u8 part_str[E1000_PBANUM_LENGTH];
+ int err;
/* Catch broken hardware that put the wrong VF device ID in
* the PCIe SR-IOV capability.
if (err)
return err;
- pci_using_dac = 0;
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (!err) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "No usable DMA configuration, aborting\n");
- goto err_dma;
- }
+ if (err) {
+ dev_err(&pdev->dev,
+ "No usable DMA configuration, aborting\n");
+ goto err_dma;
}
err = pci_request_mem_regions(pdev, igb_driver_name);
if (hw->mac.type >= e1000_i350)
netdev->hw_features |= NETIF_F_NTUPLE;
- if (pci_using_dac)
- netdev->features |= NETIF_F_HIGHDMA;
+ netdev->features |= NETIF_F_HIGHDMA;
netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
netdev->mpls_features |= NETIF_F_HW_CSUM;
struct igbvf_adapter *adapter;
struct e1000_hw *hw;
const struct igbvf_info *ei = igbvf_info_tbl[ent->driver_data];
-
static int cards_found;
- int err, pci_using_dac;
+ int err;
err = pci_enable_device_mem(pdev);
if (err)
return err;
- pci_using_dac = 0;
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (!err) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "No usable DMA configuration, aborting\n");
- goto err_dma;
- }
+ if (err) {
+ dev_err(&pdev->dev,
+ "No usable DMA configuration, aborting\n");
+ goto err_dma;
}
err = pci_request_regions(pdev, igbvf_driver_name);
netdev->hw_features |= NETIF_F_GSO_PARTIAL |
IGBVF_GSO_PARTIAL_FEATURES;
- netdev->features = netdev->hw_features;
-
- if (pci_using_dac)
- netdev->features |= NETIF_F_HIGHDMA;
+ netdev->features = netdev->hw_features | NETIF_F_HIGHDMA;
netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
netdev->mpls_features |= NETIF_F_HW_CSUM;
static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring,
struct xdp_buff *xdp)
{
+ unsigned int totalsize = xdp->data_end - xdp->data_meta;
unsigned int metasize = xdp->data - xdp->data_meta;
- unsigned int datasize = xdp->data_end - xdp->data;
- unsigned int totalsize = metasize + datasize;
struct sk_buff *skb;
- skb = __napi_alloc_skb(&ring->q_vector->napi,
- xdp->data_end - xdp->data_hard_start,
+ net_prefetch(xdp->data_meta);
+
+ skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
- skb_reserve(skb, xdp->data_meta - xdp->data_hard_start);
- memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize);
+ memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+ ALIGN(totalsize, sizeof(long)));
+
if (metasize) {
skb_metadata_set(skb, metasize);
__skb_pull(skb, metasize);
struct net_device *netdev;
struct igc_hw *hw;
const struct igc_info *ei = igc_info_tbl[ent->driver_data];
- int err, pci_using_dac;
+ int err;
err = pci_enable_device_mem(pdev);
if (err)
return err;
- pci_using_dac = 0;
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (!err) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "No usable DMA configuration, aborting\n");
- goto err_dma;
- }
+ if (err) {
+ dev_err(&pdev->dev,
+ "No usable DMA configuration, aborting\n");
+ goto err_dma;
}
err = pci_request_mem_regions(pdev, igc_driver_name);
netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
netdev->hw_features |= netdev->features;
- if (pci_using_dac)
- netdev->features |= NETIF_F_HIGHDMA;
+ netdev->features |= NETIF_F_HIGHDMA;
netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
netdev->mpls_features |= NETIF_F_HW_CSUM;
struct net_device *netdev = NULL;
struct ixgb_adapter *adapter;
static int cards_found = 0;
- int pci_using_dac;
u8 addr[ETH_ALEN];
int i;
int err;
if (err)
return err;
- pci_using_dac = 0;
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (!err) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- pr_err("No usable DMA configuration, aborting\n");
- goto err_dma_mask;
- }
+ if (err) {
+ pr_err("No usable DMA configuration, aborting\n");
+ goto err_dma_mask;
}
err = pci_request_regions(pdev, ixgb_driver_name);
NETIF_F_HW_VLAN_CTAG_FILTER;
netdev->hw_features |= NETIF_F_RXCSUM;
- if (pci_using_dac) {
- netdev->features |= NETIF_F_HIGHDMA;
- netdev->vlan_features |= NETIF_F_HIGHDMA;
- }
+ netdev->features |= NETIF_F_HIGHDMA;
+ netdev->vlan_features |= NETIF_F_HIGHDMA;
/* MTU range: 68 - 16114 */
netdev->min_mtu = ETH_MIN_MTU;
struct ixgbe_adapter *adapter = NULL;
struct ixgbe_hw *hw;
const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data];
- int i, err, pci_using_dac, expected_gts;
unsigned int indices = MAX_TX_QUEUES;
u8 part_str[IXGBE_PBANUM_LENGTH];
+ int i, err, expected_gts;
bool disable_dev = false;
#ifdef IXGBE_FCOE
u16 device_caps;
if (err)
return err;
- if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev,
- "No usable DMA configuration, aborting\n");
- goto err_dma;
- }
- pci_using_dac = 0;
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ if (err) {
+ dev_err(&pdev->dev,
+ "No usable DMA configuration, aborting\n");
+ goto err_dma;
}
err = pci_request_mem_regions(pdev, ixgbe_driver_name);
netdev->hw_features |= NETIF_F_NTUPLE |
NETIF_F_HW_TC;
- if (pci_using_dac)
- netdev->features |= NETIF_F_HIGHDMA;
+ netdev->features |= NETIF_F_HIGHDMA;
netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
netdev->hw_enc_features |= netdev->vlan_features;
}
static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring,
- struct ixgbe_rx_buffer *bi)
+ const struct xdp_buff *xdp)
{
- unsigned int metasize = bi->xdp->data - bi->xdp->data_meta;
- unsigned int datasize = bi->xdp->data_end - bi->xdp->data;
+ unsigned int totalsize = xdp->data_end - xdp->data_meta;
+ unsigned int metasize = xdp->data - xdp->data_meta;
struct sk_buff *skb;
+ net_prefetch(xdp->data_meta);
+
/* allocate a skb to store the frags */
- skb = __napi_alloc_skb(&rx_ring->q_vector->napi,
- bi->xdp->data_end - bi->xdp->data_hard_start,
+ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
return NULL;
- skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start);
- memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize);
- if (metasize)
+ memcpy(__skb_put(skb, totalsize), xdp->data_meta,
+ ALIGN(totalsize, sizeof(long)));
+
+ if (metasize) {
skb_metadata_set(skb, metasize);
+ __skb_pull(skb, metasize);
+ }
- xsk_buff_free(bi->xdp);
- bi->xdp = NULL;
return skb;
}
}
/* XDP_PASS path */
- skb = ixgbe_construct_skb_zc(rx_ring, bi);
+ skb = ixgbe_construct_skb_zc(rx_ring, bi->xdp);
if (!skb) {
rx_ring->rx_stats.alloc_rx_buff_failed++;
break;
}
+ xsk_buff_free(bi->xdp);
+ bi->xdp = NULL;
+
cleaned_count++;
ixgbe_inc_ntc(rx_ring);
struct ixgbevf_adapter *adapter = NULL;
struct ixgbe_hw *hw = NULL;
const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data];
- int err, pci_using_dac;
bool disable_dev = false;
+ int err;
err = pci_enable_device(pdev);
if (err)
return err;
- if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
- pci_using_dac = 1;
- } else {
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- dev_err(&pdev->dev, "No usable DMA configuration, aborting\n");
- goto err_dma;
- }
- pci_using_dac = 0;
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+ if (err) {
+ dev_err(&pdev->dev, "No usable DMA configuration, aborting\n");
+ goto err_dma;
}
err = pci_request_regions(pdev, ixgbevf_driver_name);
netdev->hw_features |= NETIF_F_GSO_PARTIAL |
IXGBEVF_GSO_PARTIAL_FEATURES;
- netdev->features = netdev->hw_features;
-
- if (pci_using_dac)
- netdev->features |= NETIF_F_HIGHDMA;
+ netdev->features = netdev->hw_features | NETIF_F_HIGHDMA;
netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID;
netdev->mpls_features |= NETIF_F_SG |
bytes_compl += buf->skb->len;
pkts_compl++;
dev_kfree_skb_any(buf->skb);
- } else if (buf->type == MVNETA_TYPE_XDP_TX ||
- buf->type == MVNETA_TYPE_XDP_NDO) {
+ } else if ((buf->type == MVNETA_TYPE_XDP_TX ||
+ buf->type == MVNETA_TYPE_XDP_NDO) && buf->xdpf) {
if (napi && buf->type == MVNETA_TYPE_XDP_TX)
xdp_return_frame_rx_napi(buf->xdpf);
else
static void
mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
- struct xdp_buff *xdp, struct skb_shared_info *sinfo,
- int sync_len)
+ struct xdp_buff *xdp, int sync_len)
{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
int i;
+ if (likely(!xdp_buff_has_frags(xdp)))
+ goto out;
+
for (i = 0; i < sinfo->nr_frags; i++)
page_pool_put_full_page(rxq->page_pool,
skb_frag_page(&sinfo->frags[i]), true);
+
+out:
page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
sync_len, true);
}
static int
mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq,
- struct xdp_frame *xdpf, bool dma_map)
+ struct xdp_frame *xdpf, int *nxmit_byte, bool dma_map)
{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
+ struct device *dev = pp->dev->dev.parent;
struct mvneta_tx_desc *tx_desc;
- struct mvneta_tx_buf *buf;
- dma_addr_t dma_addr;
+ int i, num_frames = 1;
+ struct page *page;
- if (txq->count >= txq->tx_stop_threshold)
+ if (unlikely(xdp_frame_has_frags(xdpf)))
+ num_frames += sinfo->nr_frags;
+
+ if (txq->count + num_frames >= txq->size)
return MVNETA_XDP_DROPPED;
- tx_desc = mvneta_txq_next_desc_get(txq);
+ for (i = 0; i < num_frames; i++) {
+ struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index];
+ skb_frag_t *frag = NULL;
+ int len = xdpf->len;
+ dma_addr_t dma_addr;
- buf = &txq->buf[txq->txq_put_index];
- if (dma_map) {
- /* ndo_xdp_xmit */
- dma_addr = dma_map_single(pp->dev->dev.parent, xdpf->data,
- xdpf->len, DMA_TO_DEVICE);
- if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) {
- mvneta_txq_desc_put(txq);
- return MVNETA_XDP_DROPPED;
+ if (unlikely(i)) { /* paged area */
+ frag = &sinfo->frags[i - 1];
+ len = skb_frag_size(frag);
}
- buf->type = MVNETA_TYPE_XDP_NDO;
- } else {
- struct page *page = virt_to_page(xdpf->data);
- dma_addr = page_pool_get_dma_addr(page) +
- sizeof(*xdpf) + xdpf->headroom;
- dma_sync_single_for_device(pp->dev->dev.parent, dma_addr,
- xdpf->len, DMA_BIDIRECTIONAL);
- buf->type = MVNETA_TYPE_XDP_TX;
- }
- buf->xdpf = xdpf;
+ tx_desc = mvneta_txq_next_desc_get(txq);
+ if (dma_map) {
+ /* ndo_xdp_xmit */
+ void *data;
+
+ data = unlikely(frag) ? skb_frag_address(frag)
+ : xdpf->data;
+ dma_addr = dma_map_single(dev, data, len,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(dev, dma_addr)) {
+ mvneta_txq_desc_put(txq);
+ goto unmap;
+ }
+
+ buf->type = MVNETA_TYPE_XDP_NDO;
+ } else {
+ page = unlikely(frag) ? skb_frag_page(frag)
+ : virt_to_page(xdpf->data);
+ dma_addr = page_pool_get_dma_addr(page);
+ if (unlikely(frag))
+ dma_addr += skb_frag_off(frag);
+ else
+ dma_addr += sizeof(*xdpf) + xdpf->headroom;
+ dma_sync_single_for_device(dev, dma_addr, len,
+ DMA_BIDIRECTIONAL);
+ buf->type = MVNETA_TYPE_XDP_TX;
+ }
+ buf->xdpf = unlikely(i) ? NULL : xdpf;
- tx_desc->command = MVNETA_TXD_FLZ_DESC;
- tx_desc->buf_phys_addr = dma_addr;
- tx_desc->data_size = xdpf->len;
+ tx_desc->command = unlikely(i) ? 0 : MVNETA_TXD_F_DESC;
+ tx_desc->buf_phys_addr = dma_addr;
+ tx_desc->data_size = len;
+ *nxmit_byte += len;
- mvneta_txq_inc_put(txq);
- txq->pending++;
- txq->count++;
+ mvneta_txq_inc_put(txq);
+ }
+ /*last descriptor */
+ tx_desc->command |= MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD;
+
+ txq->pending += num_frames;
+ txq->count += num_frames;
return MVNETA_XDP_TX;
+
+unmap:
+ for (i--; i >= 0; i--) {
+ mvneta_txq_desc_put(txq);
+ tx_desc = txq->descs + txq->next_desc_to_proc;
+ dma_unmap_single(dev, tx_desc->buf_phys_addr,
+ tx_desc->data_size,
+ DMA_TO_DEVICE);
+ }
+
+ return MVNETA_XDP_DROPPED;
}
static int
struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
struct mvneta_tx_queue *txq;
struct netdev_queue *nq;
+ int cpu, nxmit_byte = 0;
struct xdp_frame *xdpf;
- int cpu;
u32 ret;
xdpf = xdp_convert_buff_to_frame(xdp);
nq = netdev_get_tx_queue(pp->dev, txq->id);
__netif_tx_lock(nq, cpu);
- ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false);
+ ret = mvneta_xdp_submit_frame(pp, txq, xdpf, &nxmit_byte, false);
if (ret == MVNETA_XDP_TX) {
u64_stats_update_begin(&stats->syncp);
- stats->es.ps.tx_bytes += xdpf->len;
+ stats->es.ps.tx_bytes += nxmit_byte;
stats->es.ps.tx_packets++;
stats->es.ps.xdp_tx++;
u64_stats_update_end(&stats->syncp);
__netif_tx_lock(nq, cpu);
for (i = 0; i < num_frame; i++) {
- ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true);
+ ret = mvneta_xdp_submit_frame(pp, txq, frames[i], &nxmit_byte,
+ true);
if (ret != MVNETA_XDP_TX)
break;
- nxmit_byte += frames[i]->len;
nxmit++;
}
struct bpf_prog *prog, struct xdp_buff *xdp,
u32 frame_sz, struct mvneta_stats *stats)
{
- struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
unsigned int len, data_len, sync;
u32 ret, act;
err = xdp_do_redirect(pp->dev, xdp, prog);
if (unlikely(err)) {
- mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
+ mvneta_xdp_put_buff(pp, rxq, xdp, sync);
ret = MVNETA_XDP_DROPPED;
} else {
ret = MVNETA_XDP_REDIR;
case XDP_TX:
ret = mvneta_xdp_xmit_back(pp, xdp);
if (ret != MVNETA_XDP_TX)
- mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
+ mvneta_xdp_put_buff(pp, rxq, xdp, sync);
break;
default:
bpf_warn_invalid_xdp_action(pp->dev, prog, act);
trace_xdp_exception(pp->dev, prog, act);
fallthrough;
case XDP_DROP:
- mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync);
+ mvneta_xdp_put_buff(pp, rxq, xdp, sync);
ret = MVNETA_XDP_DROPPED;
stats->xdp_drop++;
break;
int data_len = -MVNETA_MH_SIZE, len;
struct net_device *dev = pp->dev;
enum dma_data_direction dma_dir;
- struct skb_shared_info *sinfo;
if (*size > MVNETA_MAX_RX_BUF_SIZE) {
len = MVNETA_MAX_RX_BUF_SIZE;
/* Prefetch header */
prefetch(data);
+ xdp_buff_clear_frags_flag(xdp);
xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE,
data_len, false);
-
- sinfo = xdp_get_shared_info_from_buff(xdp);
- sinfo->nr_frags = 0;
}
static void
struct mvneta_rx_desc *rx_desc,
struct mvneta_rx_queue *rxq,
struct xdp_buff *xdp, int *size,
- struct skb_shared_info *xdp_sinfo,
struct page *page)
{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
struct net_device *dev = pp->dev;
enum dma_data_direction dma_dir;
int data_len, len;
len, dma_dir);
rx_desc->buf_phys_addr = 0;
- if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) {
- skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++];
+ if (!xdp_buff_has_frags(xdp))
+ sinfo->nr_frags = 0;
+
+ if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) {
+ skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags++];
skb_frag_off_set(frag, pp->rx_offset_correction);
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
+
+ if (!xdp_buff_has_frags(xdp)) {
+ sinfo->xdp_frags_size = *size;
+ xdp_buff_set_frags_flag(xdp);
+ }
+ if (page_is_pfmemalloc(page))
+ xdp_buff_set_frag_pfmemalloc(xdp);
} else {
page_pool_put_full_page(rxq->page_pool, page, true);
}
-
- /* last fragment */
- if (len == *size) {
- struct skb_shared_info *sinfo;
-
- sinfo = xdp_get_shared_info_from_buff(xdp);
- sinfo->nr_frags = xdp_sinfo->nr_frags;
- memcpy(sinfo->frags, xdp_sinfo->frags,
- sinfo->nr_frags * sizeof(skb_frag_t));
- }
*size -= len;
}
struct xdp_buff *xdp, u32 desc_status)
{
struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
- int i, num_frags = sinfo->nr_frags;
struct sk_buff *skb;
+ u8 num_frags;
+
+ if (unlikely(xdp_buff_has_frags(xdp)))
+ num_frags = sinfo->nr_frags;
skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
if (!skb)
skb_put(skb, xdp->data_end - xdp->data);
skb->ip_summed = mvneta_rx_csum(pp, desc_status);
- for (i = 0; i < num_frags; i++) {
- skb_frag_t *frag = &sinfo->frags[i];
-
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
- skb_frag_page(frag), skb_frag_off(frag),
- skb_frag_size(frag), PAGE_SIZE);
- }
+ if (unlikely(xdp_buff_has_frags(xdp)))
+ xdp_update_skb_shared_info(skb, num_frags,
+ sinfo->xdp_frags_size,
+ num_frags * xdp->frame_sz,
+ xdp_buff_is_frag_pfmemalloc(xdp));
return skb;
}
{
int rx_proc = 0, rx_todo, refill, size = 0;
struct net_device *dev = pp->dev;
- struct skb_shared_info sinfo;
struct mvneta_stats ps = {};
struct bpf_prog *xdp_prog;
u32 desc_status, frame_sz;
xdp_init_buff(&xdp_buf, PAGE_SIZE, &rxq->xdp_rxq);
xdp_buf.data_hard_start = NULL;
- sinfo.nr_frags = 0;
-
/* Get number of received packets */
rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
}
mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf,
- &size, &sinfo, page);
+ &size, page);
} /* Middle or Last descriptor */
if (!(rx_status & MVNETA_RXD_LAST_DESC))
continue;
if (size) {
- mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
+ mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1);
goto next;
}
if (IS_ERR(skb)) {
struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
- mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
+ mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1);
u64_stats_update_begin(&stats->syncp);
stats->es.skb_alloc_error++;
napi_gro_receive(napi, skb);
next:
xdp_buf.data_hard_start = NULL;
- sinfo.nr_frags = 0;
}
if (xdp_buf.data_hard_start)
- mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1);
+ mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1);
if (ps.xdp_redirect)
xdp_do_flush_map();
return err;
}
- err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0);
+ err = __xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0,
+ PAGE_SIZE);
if (err < 0)
goto err_free_pp;
static int mvneta_change_mtu(struct net_device *dev, int mtu)
{
struct mvneta_port *pp = netdev_priv(dev);
+ struct bpf_prog *prog = pp->xdp_prog;
int ret;
if (!IS_ALIGNED(MVNETA_RX_PKT_SIZE(mtu), 8)) {
mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8);
}
- if (pp->xdp_prog && mtu > MVNETA_MAX_RX_BUF_SIZE) {
- netdev_info(dev, "Illegal MTU value %d for XDP mode\n", mtu);
+ if (prog && !prog->aux->xdp_has_frags &&
+ mtu > MVNETA_MAX_RX_BUF_SIZE) {
+ netdev_info(dev, "Illegal MTU %d for XDP prog without frags\n",
+ mtu);
+
return -EINVAL;
}
.pcs_an_restart = mvneta_pcs_an_restart,
};
+static struct phylink_pcs *mvneta_mac_select_pcs(struct phylink_config *config,
+ phy_interface_t interface)
+{
+ struct net_device *ndev = to_net_dev(config->dev);
+ struct mvneta_port *pp = netdev_priv(ndev);
+
+ return &pp->phylink_pcs;
+}
+
static int mvneta_mac_prepare(struct phylink_config *config, unsigned int mode,
phy_interface_t interface)
{
mvneta_port_up(pp);
if (phy && pp->eee_enabled) {
- pp->eee_active = phy_init_eee(phy, 0) >= 0;
+ pp->eee_active = phy_init_eee(phy, false) >= 0;
mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled);
}
}
static const struct phylink_mac_ops mvneta_phylink_ops = {
.validate = phylink_generic_validate,
+ .mac_select_pcs = mvneta_mac_select_pcs,
.mac_prepare = mvneta_mac_prepare,
.mac_config = mvneta_mac_config,
.mac_finish = mvneta_mac_finish,
struct mvneta_port *pp = netdev_priv(dev);
struct bpf_prog *old_prog;
- if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
- NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP");
+ if (prog && !prog->aux->xdp_has_frags &&
+ dev->mtu > MVNETA_MAX_RX_BUF_SIZE) {
+ NL_SET_ERR_MSG_MOD(extack, "prog does not support XDP frags");
return -EOPNOTSUPP;
}
if (!dev)
return -ENOMEM;
- dev->irq = irq_of_parse_and_map(dn, 0);
- if (dev->irq == 0)
- return -EINVAL;
+ dev->tx_queue_len = MVNETA_MAX_TXD;
+ dev->watchdog_timeo = 5 * HZ;
+ dev->netdev_ops = &mvneta_netdev_ops;
+ dev->ethtool_ops = &mvneta_eth_tool_ops;
+
+ pp = netdev_priv(dev);
+ spin_lock_init(&pp->lock);
+ pp->dn = dn;
+
+ pp->rxq_def = rxq_def;
+ pp->indir[0] = rxq_def;
err = of_get_phy_mode(dn, &phy_mode);
if (err) {
dev_err(&pdev->dev, "incorrect phy-mode\n");
- goto err_free_irq;
+ return err;
}
+ pp->phy_interface = phy_mode;
+
comphy = devm_of_phy_get(&pdev->dev, dn, NULL);
- if (comphy == ERR_PTR(-EPROBE_DEFER)) {
- err = -EPROBE_DEFER;
- goto err_free_irq;
- } else if (IS_ERR(comphy)) {
+ if (comphy == ERR_PTR(-EPROBE_DEFER))
+ return -EPROBE_DEFER;
+
+ if (IS_ERR(comphy))
comphy = NULL;
+
+ pp->comphy = comphy;
+
+ pp->base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(pp->base))
+ return PTR_ERR(pp->base);
+
+ /* Get special SoC configurations */
+ if (of_device_is_compatible(dn, "marvell,armada-3700-neta"))
+ pp->neta_armada3700 = true;
+
+ dev->irq = irq_of_parse_and_map(dn, 0);
+ if (dev->irq == 0)
+ return -EINVAL;
+
+ pp->clk = devm_clk_get(&pdev->dev, "core");
+ if (IS_ERR(pp->clk))
+ pp->clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(pp->clk)) {
+ err = PTR_ERR(pp->clk);
+ goto err_free_irq;
}
- pp = netdev_priv(dev);
- spin_lock_init(&pp->lock);
+ clk_prepare_enable(pp->clk);
+
+ pp->clk_bus = devm_clk_get(&pdev->dev, "bus");
+ if (!IS_ERR(pp->clk_bus))
+ clk_prepare_enable(pp->clk_bus);
+
+ pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops;
pp->phylink_config.dev = &dev->dev;
pp->phylink_config.type = PHYLINK_NETDEV;
phy_mode, &mvneta_phylink_ops);
if (IS_ERR(phylink)) {
err = PTR_ERR(phylink);
- goto err_free_irq;
- }
-
- dev->tx_queue_len = MVNETA_MAX_TXD;
- dev->watchdog_timeo = 5 * HZ;
- dev->netdev_ops = &mvneta_netdev_ops;
-
- dev->ethtool_ops = &mvneta_eth_tool_ops;
-
- pp->phylink = phylink;
- pp->comphy = comphy;
- pp->phy_interface = phy_mode;
- pp->dn = dn;
-
- pp->rxq_def = rxq_def;
- pp->indir[0] = rxq_def;
-
- /* Get special SoC configurations */
- if (of_device_is_compatible(dn, "marvell,armada-3700-neta"))
- pp->neta_armada3700 = true;
-
- pp->clk = devm_clk_get(&pdev->dev, "core");
- if (IS_ERR(pp->clk))
- pp->clk = devm_clk_get(&pdev->dev, NULL);
- if (IS_ERR(pp->clk)) {
- err = PTR_ERR(pp->clk);
- goto err_free_phylink;
- }
-
- clk_prepare_enable(pp->clk);
-
- pp->clk_bus = devm_clk_get(&pdev->dev, "bus");
- if (!IS_ERR(pp->clk_bus))
- clk_prepare_enable(pp->clk_bus);
-
- pp->base = devm_platform_ioremap_resource(pdev, 0);
- if (IS_ERR(pp->base)) {
- err = PTR_ERR(pp->base);
goto err_clk;
}
- pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops;
- phylink_set_pcs(phylink, &pp->phylink_pcs);
+ pp->phylink = phylink;
/* Alloc per-cpu port structure */
pp->ports = alloc_percpu(struct mvneta_pcpu_port);
if (!pp->ports) {
err = -ENOMEM;
- goto err_clk;
+ goto err_free_phylink;
}
/* Alloc per-cpu stats */
free_percpu(pp->stats);
err_free_ports:
free_percpu(pp->ports);
-err_clk:
- clk_disable_unprepare(pp->clk_bus);
- clk_disable_unprepare(pp->clk);
err_free_phylink:
if (pp->phylink)
phylink_destroy(pp->phylink);
+err_clk:
+ clk_disable_unprepare(pp->clk_bus);
+ clk_disable_unprepare(pp->clk);
err_free_irq:
irq_dispose_mapping(dev->irq);
return err;
int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu)
{
struct nix_frs_cfg *req;
+ u16 maxlen;
int err;
+ maxlen = otx2_get_max_mtu(pfvf) + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN;
+
mutex_lock(&pfvf->mbox.lock);
req = otx2_mbox_alloc_msg_nix_set_hw_frs(&pfvf->mbox);
if (!req) {
req->maxlen = pfvf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN;
+ /* Use max receive length supported by hardware for loopback devices */
+ if (is_otx2_lbkvf(pfvf->pdev))
+ req->maxlen = maxlen;
+
err = otx2_sync_mbox_msg(&pfvf->mbox);
mutex_unlock(&pfvf->mbox.lock);
return err;
u16 rqpool_cnt;
u16 sqpool_cnt;
+#define OTX2_DEFAULT_RBUF_LEN 2048
+ u16 rbuf_len;
+
/* NPA */
u32 stack_pg_ptrs; /* No of ptrs per stack page */
u32 stack_pg_bytes; /* Size of stack page */
ring->rx_pending = qs->rqe_cnt ? qs->rqe_cnt : Q_COUNT(Q_SIZE_256);
ring->tx_max_pending = Q_COUNT(Q_SIZE_MAX);
ring->tx_pending = qs->sqe_cnt ? qs->sqe_cnt : Q_COUNT(Q_SIZE_4K);
+ kernel_ring->rx_buf_len = pfvf->hw.rbuf_len;
}
static int otx2_set_ringparam(struct net_device *netdev,
struct netlink_ext_ack *extack)
{
struct otx2_nic *pfvf = netdev_priv(netdev);
+ u32 rx_buf_len = kernel_ring->rx_buf_len;
+ u32 old_rx_buf_len = pfvf->hw.rbuf_len;
bool if_up = netif_running(netdev);
struct otx2_qset *qs = &pfvf->qset;
u32 rx_count, tx_count;
if (ring->rx_mini_pending || ring->rx_jumbo_pending)
return -EINVAL;
+ /* Hardware supports max size of 32k for a receive buffer
+ * and 1536 is typical ethernet frame size.
+ */
+ if (rx_buf_len && (rx_buf_len < 1536 || rx_buf_len > 32768)) {
+ netdev_err(netdev,
+ "Receive buffer range is 1536 - 32768");
+ return -EINVAL;
+ }
+
/* Permitted lengths are 16 64 256 1K 4K 16K 64K 256K 1M */
rx_count = ring->rx_pending;
/* On some silicon variants a skid or reserved CQEs are
Q_COUNT(Q_SIZE_4K), Q_COUNT(Q_SIZE_MAX));
tx_count = Q_COUNT(Q_SIZE(tx_count, 3));
- if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt)
+ if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt &&
+ rx_buf_len == old_rx_buf_len)
return 0;
if (if_up)
qs->sqe_cnt = tx_count;
qs->rqe_cnt = rx_count;
+ pfvf->hw.rbuf_len = rx_buf_len;
+
if (if_up)
return netdev->netdev_ops->ndo_open(netdev);
static const struct ethtool_ops otx2_ethtool_ops = {
.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
ETHTOOL_COALESCE_MAX_FRAMES,
+ .supported_ring_params = ETHTOOL_RING_USE_RX_BUF_LEN,
.get_link = otx2_get_link,
.get_drvinfo = otx2_get_drvinfo,
.get_strings = otx2_get_strings,
static const struct ethtool_ops otx2vf_ethtool_ops = {
.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
ETHTOOL_COALESCE_MAX_FRAMES,
+ .supported_ring_params = ETHTOOL_RING_USE_RX_BUF_LEN,
.get_link = otx2_get_link,
.get_drvinfo = otx2vf_get_drvinfo,
.get_strings = otx2vf_get_strings,
int total_size;
int rbuf_size;
+ if (pf->hw.rbuf_len)
+ return ALIGN(pf->hw.rbuf_len, OTX2_ALIGN) + OTX2_HEAD_ROOM;
+
/* The data transferred by NIX to memory consists of actual packet
* plus additional data which has timestamp and/or EDSA/HIGIG2
* headers if interface is configured in corresponding modes.
hw->tx_queues = qcount;
hw->tot_tx_queues = qcount;
hw->max_queues = qcount;
+ hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN;
num_vec = pci_msix_vec_count(pdev);
hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,
hw->tx_queues = qcount;
hw->max_queues = qcount;
hw->tot_tx_queues = qcount;
+ hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN;
hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE,
GFP_KERNEL);
return devm_register_netdev(dev, ndev);
}
+#ifdef CONFIG_OF
static const struct of_device_id mtk_star_of_match[] = {
{ .compatible = "mediatek,mt8516-eth", },
{ .compatible = "mediatek,mt8518-eth", },
{ }
};
MODULE_DEVICE_TABLE(of, mtk_star_of_match);
+#endif
static SIMPLE_DEV_PM_OPS(mtk_star_pm_ops,
mtk_star_suspend, mtk_star_resume);
static bool
tc_act_can_offload_accept(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
{
attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
MLX5_FLOW_CONTEXT_ACTION_COUNT;
- attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT;
+ attr->flags |= MLX5_ATTR_FLAG_ACCEPT;
return 0;
}
unsigned int num_actions;
struct mlx5e_tc_flow *flow;
struct netlink_ext_ack *extack;
+ bool ct;
bool encap;
bool decap;
bool mpls_push;
bool ptype_host;
const struct ip_tunnel_info *tun_info;
- struct pedit_headers_action hdrs[__PEDIT_CMD_MAX];
int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS];
int if_count;
struct mlx5_tc_ct_priv *ct_priv;
struct mlx5e_tc_act {
bool (*can_offload)(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index);
+ int act_index,
+ struct mlx5_flow_attr *attr);
int (*parse_action)(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
static bool
tc_act_can_offload_csum(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct mlx5e_tc_flow *flow = parse_state->flow;
- return csum_offload_supported(flow->priv, flow->attr->action,
+ return csum_offload_supported(flow->priv, attr->action,
act->csum_flags, parse_state->extack);
}
static bool
tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
+ bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR;
struct netlink_ext_ack *extack = parse_state->extack;
if (flow_flag_test(parse_state->flow, SAMPLE)) {
return false;
}
+ if (parse_state->ct && !clear_action) {
+ NL_SET_ERR_MSG_MOD(extack, "Multiple CT actions are not supoported");
+ return false;
+ }
+
return true;
}
struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr)
{
+ bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR;
int err;
err = mlx5_tc_ct_parse_action(parse_state->ct_priv, attr,
if (err)
return err;
- flow_flag_set(parse_state->flow, CT);
if (mlx5e_is_eswitch_flow(parse_state->flow))
attr->esw_attr->split_count = attr->esw_attr->out_count;
+ if (!clear_action) {
+ attr->flags |= MLX5_ATTR_FLAG_CT;
+ flow_flag_set(parse_state->flow, CT);
+ parse_state->ct = true;
+ }
+
return 0;
}
static bool
tc_act_can_offload_drop(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
static int
validate_goto_chain(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
const struct flow_action_entry *act,
struct netlink_ext_ack *extack)
{
}
if (!mlx5_chains_backwards_supported(chains) &&
- dest_chain <= flow->attr->chain) {
+ dest_chain <= attr->chain) {
NL_SET_ERR_MSG_MOD(extack, "Goto lower numbered chain isn't supported");
return -EOPNOTSUPP;
}
return -EOPNOTSUPP;
}
- if (flow->attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
- MLX5_FLOW_CONTEXT_ACTION_DECAP) &&
+ if (attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
+ MLX5_FLOW_CONTEXT_ACTION_DECAP) &&
!reformat_and_fwd) {
NL_SET_ERR_MSG_MOD(extack,
"Goto chain is not allowed if action has reformat or decap");
static bool
tc_act_can_offload_goto(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_tc_flow *flow = parse_state->flow;
- if (validate_goto_chain(flow->priv, flow, act, extack))
+ if (validate_goto_chain(flow->priv, flow, attr, act, extack))
return false;
return true;
static bool
tc_act_can_offload_mark(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
if (act->mark & ~MLX5E_TC_FLOW_ID_MASK) {
NL_SET_ERR_MSG_MOD(parse_state->extack, "Bad flow mark, only 16 bit supported");
static bool
tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_tc_flow *flow = parse_state->flow;
struct mlx5e_priv *priv = flow->priv;
struct mlx5_esw_flow_attr *esw_attr;
- parse_attr = flow->attr->parse_attr;
- esw_attr = flow->attr->esw_attr;
+ parse_attr = attr->parse_attr;
+ esw_attr = attr->esw_attr;
if (!out_dev) {
/* out_dev is NULL when filters with
static bool
tc_act_can_offload_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_tc_flow *flow = parse_state->flow;
static bool
tc_act_can_offload_mpls_push(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_priv *priv = parse_state->flow->priv;
static bool
tc_act_can_offload_mpls_pop(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
- struct mlx5e_tc_flow *flow = parse_state->flow;
struct net_device *filter_dev;
- filter_dev = flow->attr->parse_attr->filter_dev;
+ filter_dev = attr->parse_attr->filter_dev;
/* we only support mpls pop if it is the first action
* and the filter net device is bareudp. Subsequent
parse_pedit_to_modify_hdr(struct mlx5e_priv *priv,
const struct flow_action_entry *act, int namespace,
struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
struct netlink_ext_ack *extack)
{
+ struct pedit_headers_action *hdrs = parse_attr->hdrs;
u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1;
u8 htype = act->mangle.htype;
int err = -EOPNOTSUPP;
mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv,
const struct flow_action_entry *act, int namespace,
struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack)
{
if (flow && flow_flag_test(flow, L3_TO_L2_DECAP))
return parse_pedit_to_reformat(act, parse_attr, extack);
- return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, hdrs, extack);
+ return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, extack);
}
static bool
tc_act_can_offload_pedit(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
ns_type = mlx5e_get_flow_namespace(flow);
- err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type,
- attr->parse_attr, parse_state->hdrs,
+ err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type, attr->parse_attr,
flow, parse_state->extack);
if (err)
return err;
mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv,
const struct flow_action_entry *act, int namespace,
struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack);
static bool
tc_act_can_offload_ptype(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
static bool
tc_act_can_offload_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
- struct mlx5e_tc_flow *flow = parse_state->flow;
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct net_device *out_dev = act->dev;
struct mlx5_esw_flow_attr *esw_attr;
- parse_attr = flow->attr->parse_attr;
- esw_attr = flow->attr->esw_attr;
+ parse_attr = attr->parse_attr;
+ esw_attr = attr->esw_attr;
if (!out_dev)
return false;
static bool
tc_act_can_offload_sample(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5e_priv *priv,
struct mlx5_flow_attr *attr)
{
- struct mlx5e_sample_attr *sample_attr;
-
- sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL);
- if (!sample_attr)
- return -ENOMEM;
+ struct mlx5e_sample_attr *sample_attr = &attr->sample_attr;
sample_attr->rate = act->sample.rate;
sample_attr->group_num = act->sample.psample_group->group_num;
if (act->sample.truncate)
sample_attr->trunc_size = act->sample.trunc_size;
- attr->sample_attr = sample_attr;
+ attr->flags |= MLX5_ATTR_FLAG_SAMPLE;
flow_flag_set(parse_state->flow, SAMPLE);
return 0;
static bool
tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
struct netlink_ext_ack *extack = parse_state->extack;
{
attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
MLX5_FLOW_CONTEXT_ACTION_COUNT;
- attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
+ attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
return 0;
}
static bool
tc_act_can_offload_tun_encap(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
if (!act->tunnel) {
NL_SET_ERR_MSG_MOD(parse_state->extack,
static bool
tc_act_can_offload_tun_decap(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
static int
add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv,
struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
u32 *action, struct netlink_ext_ack *extack)
{
const struct flow_action_entry prio_tag_act = {
};
return mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB,
- &prio_tag_act, parse_attr, hdrs, action,
+ &prio_tag_act, parse_attr, action,
extack);
}
static bool
tc_act_can_offload_vlan(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
/* Replace vlan pop+push with vlan modify */
attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
err = mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, act,
- attr->parse_attr, parse_state->hdrs,
- &attr->action, parse_state->extack);
+ attr->parse_attr, &attr->action,
+ parse_state->extack);
} else {
err = parse_tc_vlan_action(priv, act, esw_attr, &attr->action,
parse_state->extack);
struct mlx5_flow_attr *attr)
{
struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
- struct pedit_headers_action *hdrs = parse_state->hdrs;
struct netlink_ext_ack *extack = parse_state->extack;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
int err;
* tag rewrite.
*/
attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
- err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, hdrs,
+ err = add_vlan_prio_tag_rewrite_action(priv, parse_attr,
&attr->action, extack);
if (err)
return err;
mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace,
const struct flow_action_entry *act,
struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
u32 *action, struct netlink_ext_ack *extack);
#endif /* __MLX5_EN_TC_ACT_VLAN_H__ */
mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace,
const struct flow_action_entry *act,
struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
u32 *action, struct netlink_ext_ack *extack)
{
u16 mask16 = VLAN_VID_MASK;
return -EOPNOTSUPP;
}
- err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr, hdrs,
+ err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr,
NULL, extack);
*action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
static bool
tc_act_can_offload_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state,
const struct flow_action_entry *act,
- int act_index)
+ int act_index,
+ struct mlx5_flow_attr *attr)
{
return true;
}
int err;
ns_type = mlx5e_get_flow_namespace(parse_state->flow);
- err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act,
- attr->parse_attr, parse_state->hdrs,
+ err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act, attr->parse_attr,
&attr->action, parse_state->extack);
if (err)
return err;
post_attr->inner_match_level = MLX5_MATCH_NONE;
post_attr->outer_match_level = MLX5_MATCH_NONE;
post_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP);
+ post_attr->flags &= ~MLX5_ATTR_FLAG_SAMPLE;
handle->ns_type = post_act->ns_type;
/* Splits were handled before post action */
post_attr->chain = 0;
post_attr->prio = 0;
post_attr->ft = default_tbl;
- post_attr->flags = MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
+ post_attr->flags = MLX5_ATTR_FLAG_NO_IN_PORT;
/* When offloading sample and encap action, if there is no valid
* neigh data struct, a slow path rule is offloaded first. Source
struct mlx5_flow_handle *
mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
struct mlx5_flow_spec *spec,
- struct mlx5_flow_attr *attr,
- u32 tunnel_id)
+ struct mlx5_flow_attr *attr)
{
struct mlx5e_post_act_handle *post_act_handle = NULL;
struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
struct mlx5e_sample_flow *sample_flow;
struct mlx5e_sample_attr *sample_attr;
struct mlx5_flow_attr *pre_attr;
+ u32 tunnel_id = attr->tunnel_id;
struct mlx5_eswitch *esw;
u32 default_tbl_id;
u32 obj_id;
sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL);
if (!sample_flow)
return ERR_PTR(-ENOMEM);
- sample_attr = attr->sample_attr;
+ sample_attr = &attr->sample_attr;
sample_attr->sample_flow = sample_flow;
/* For NICs with reg_c_preserve support or decap action, use
err = PTR_ERR(sample_flow->sampler);
goto err_sampler;
}
+ sample_attr->sampler_id = sample_flow->sampler->sampler_id;
/* Create an id mapping reg_c0 value to sample object. */
restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE;
if (tunnel_id)
pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
pre_attr->modify_hdr = sample_flow->restore->modify_hdr;
- pre_attr->flags = MLX5_ESW_ATTR_FLAG_SAMPLE;
+ pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE;
pre_attr->inner_match_level = attr->inner_match_level;
pre_attr->outer_match_level = attr->outer_match_level;
pre_attr->chain = attr->chain;
pre_attr->prio = attr->prio;
- pre_attr->sample_attr = attr->sample_attr;
- sample_attr->sampler_id = sample_flow->sampler->sampler_id;
+ pre_attr->sample_attr = *sample_attr;
pre_esw_attr = pre_attr->esw_attr;
pre_esw_attr->in_mdev = esw_attr->in_mdev;
pre_esw_attr->in_rep = esw_attr->in_rep;
* will hit fw syndromes.
*/
esw = tc_psample->esw;
- sample_flow = attr->sample_attr->sample_flow;
+ sample_flow = attr->sample_attr.sample_flow;
mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr);
sample_restore_put(tc_psample, sample_flow->restore);
- mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id);
+ mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr.restore_obj_id);
sampler_put(tc_psample, sample_flow->sampler);
if (sample_flow->post_act_handle)
mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle);
struct mlx5_flow_handle *
mlx5e_tc_sample_offload(struct mlx5e_tc_psample *sample_priv,
struct mlx5_flow_spec *spec,
- struct mlx5_flow_attr *attr,
- u32 tunnel_id);
+ struct mlx5_flow_attr *attr);
void
mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *sample_priv,
static inline struct mlx5_flow_handle *
mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
struct mlx5_flow_spec *spec,
- struct mlx5_flow_attr *attr,
- u32 tunnel_id)
+ struct mlx5_flow_attr *attr)
{ return ERR_PTR(-EOPNOTSUPP); }
static inline void
attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct;
attr->outer_match_level = MLX5_MATCH_L4;
attr->counter = entry->counter->counter;
- attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT;
+ attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT;
if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB)
attr->esw_attr->in_mdev = priv->mdev;
*/
static struct mlx5_flow_handle *
__mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *orig_spec,
struct mlx5_flow_attr *attr)
{
*/
if ((pre_ct_attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) &&
attr->chain == 0) {
- u32 tun_id = mlx5e_tc_get_flow_tun_id(flow);
-
err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts,
ct_priv->ns_type,
TUNNEL_TO_REG,
- tun_id);
+ attr->tunnel_id);
if (err) {
ct_dbg("Failed to set tunnel register mapping");
goto err_mapping;
return ERR_PTR(err);
}
-static struct mlx5_flow_handle *
-__mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv,
- struct mlx5_flow_spec *orig_spec,
- struct mlx5_flow_attr *attr,
- struct mlx5e_tc_mod_hdr_acts *mod_acts)
-{
- struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
- u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type);
- struct mlx5_flow_attr *pre_ct_attr;
- struct mlx5_modify_hdr *mod_hdr;
- struct mlx5_flow_handle *rule;
- struct mlx5_ct_flow *ct_flow;
- int err;
-
- ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL);
- if (!ct_flow)
- return ERR_PTR(-ENOMEM);
-
- /* Base esw attributes on original rule attribute */
- pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type);
- if (!pre_ct_attr) {
- err = -ENOMEM;
- goto err_attr;
- }
-
- memcpy(pre_ct_attr, attr, attr_sz);
-
- mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type,
- mod_acts->num_actions,
- mod_acts->actions);
- if (IS_ERR(mod_hdr)) {
- err = PTR_ERR(mod_hdr);
- ct_dbg("Failed to add create ct clear mod hdr");
- goto err_mod_hdr;
- }
-
- pre_ct_attr->modify_hdr = mod_hdr;
-
- rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr);
- if (IS_ERR(rule)) {
- err = PTR_ERR(rule);
- ct_dbg("Failed to add ct clear rule");
- goto err_insert;
- }
-
- attr->ct_attr.ct_flow = ct_flow;
- ct_flow->pre_ct_attr = pre_ct_attr;
- ct_flow->pre_ct_rule = rule;
- return rule;
-
-err_insert:
- mlx5_modify_header_dealloc(priv->mdev, mod_hdr);
-err_mod_hdr:
- netdev_warn(priv->netdev,
- "Failed to offload ct clear flow, err %d\n", err);
- kfree(pre_ct_attr);
-err_attr:
- kfree(ct_flow);
-
- return ERR_PTR(err);
-}
-
struct mlx5_flow_handle *
mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *spec,
struct mlx5_flow_attr *attr,
struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts)
{
- bool clear_action = attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR;
struct mlx5_flow_handle *rule;
if (!priv)
return ERR_PTR(-EOPNOTSUPP);
mutex_lock(&priv->control_lock);
-
- if (clear_action)
- rule = __mlx5_tc_ct_flow_offload_clear(priv, spec, attr, mod_hdr_acts);
- else
- rule = __mlx5_tc_ct_flow_offload(priv, flow, spec, attr);
+ rule = __mlx5_tc_ct_flow_offload(priv, spec, attr);
mutex_unlock(&priv->control_lock);
return rule;
static void
__mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv,
- struct mlx5e_tc_flow *flow,
- struct mlx5_ct_flow *ct_flow)
+ struct mlx5_ct_flow *ct_flow,
+ struct mlx5_flow_attr *attr)
{
struct mlx5_flow_attr *pre_ct_attr = ct_flow->pre_ct_attr;
struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev);
- mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule,
- pre_ct_attr);
+ mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule, pre_ct_attr);
mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
if (ct_flow->post_act_handle) {
void
mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_attr *attr)
{
struct mlx5_ct_flow *ct_flow = attr->ct_attr.ct_flow;
return;
mutex_lock(&priv->control_lock);
- __mlx5_tc_ct_delete_flow(priv, flow, ct_flow);
+ __mlx5_tc_ct_delete_flow(priv, ct_flow, attr);
mutex_unlock(&priv->control_lock);
}
struct mlx5_flow_handle *
mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *spec,
struct mlx5_flow_attr *attr,
struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
void
mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_attr *attr);
bool
static inline struct mlx5_flow_handle *
mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *spec,
struct mlx5_flow_attr *attr,
struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts)
static inline void
mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
- struct mlx5e_tc_flow *flow,
struct mlx5_flow_attr *attr)
{
}
const struct ip_tunnel_info *tun_info[MLX5_MAX_FLOW_FWD_VPORTS];
struct net_device *filter_dev;
struct mlx5_flow_spec spec;
+ struct pedit_headers_action hdrs[__PEDIT_CMD_MAX];
struct mlx5e_tc_mod_hdr_acts mod_hdr_acts;
int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS];
struct ethhdr eth;
struct rcu_head rcu_head;
struct completion init_done;
struct completion del_hw_done;
- int tunnel_id; /* the mapped tunnel id of this flow */
struct mlx5_flow_attr *attr;
};
+struct mlx5_flow_handle *
+mlx5e_tc_rule_offload(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_flow_attr *attr);
+
+void
+mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv,
+ struct mlx5_flow_handle *rule,
+ struct mlx5_flow_attr *attr);
+
u8 mlx5e_tc_get_ip_version(struct mlx5_flow_spec *spec, bool outer);
struct mlx5_flow_handle *
mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *spec);
+
void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
struct mlx5e_tc_flow *flow,
struct mlx5_flow_attr *attr);
int out_index);
void mlx5e_detach_encap(struct mlx5e_priv *priv,
- struct mlx5e_tc_flow *flow, int out_index)
+ struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
+ int out_index)
{
struct mlx5e_encap_entry *e = flow->encaps[out_index].e;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- if (flow->attr->esw_attr->dests[out_index].flags &
+ if (attr->esw_attr->dests[out_index].flags &
MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE)
mlx5e_detach_encap_route(priv, flow, out_index);
static int mlx5e_attach_encap_route(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
struct mlx5e_encap_entry *e,
bool new_encap_entry,
unsigned long tbl_time_before,
int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
struct net_device *mirred_dev,
int out_index,
struct netlink_ext_ack *extack,
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5e_tc_flow_parse_attr *parse_attr;
- struct mlx5_flow_attr *attr = flow->attr;
const struct ip_tunnel_info *tun_info;
unsigned long tbl_time_before = 0;
struct mlx5e_encap_entry *e;
e->compl_result = 1;
attach_flow:
- err = mlx5e_attach_encap_route(priv, flow, e, entry_created, tbl_time_before,
- out_index);
+ err = mlx5e_attach_encap_route(priv, flow, attr, e, entry_created,
+ tbl_time_before, out_index);
if (err)
goto out_err;
static int mlx5e_attach_encap_route(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
struct mlx5e_encap_entry *e,
bool new_encap_entry,
unsigned long tbl_time_before,
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
unsigned long tbl_time_after = tbl_time_before;
struct mlx5e_tc_flow_parse_attr *parse_attr;
- struct mlx5_flow_attr *attr = flow->attr;
const struct ip_tunnel_info *tun_info;
struct mlx5_esw_flow_attr *esw_attr;
struct mlx5e_route_entry *r;
continue;
}
- err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow);
+ err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr);
if (err) {
mlx5_core_warn(priv->mdev, "Failed to update flow mod_hdr err=%d",
err);
#include "tc_priv.h"
void mlx5e_detach_encap(struct mlx5e_priv *priv,
- struct mlx5e_tc_flow *flow, int out_index);
+ struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
+ int out_index);
int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
struct net_device *mirred_dev,
int out_index,
struct netlink_ext_ack *extack,
struct net_device **encap_dev,
bool *encap_valid);
+
int mlx5e_attach_decap(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack);
if (is_mdev_switchdev_mode(priv->mdev)) {
mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
-
return;
}
mlx5e_del_offloaded_nic_rule(priv, rule, attr);
}
+struct mlx5_flow_handle *
+mlx5e_tc_rule_offload(struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec,
+ struct mlx5_flow_attr *attr)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+ if (attr->flags & MLX5_ATTR_FLAG_CT) {
+ struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts =
+ &attr->parse_attr->mod_hdr_acts;
+
+ return mlx5_tc_ct_flow_offload(get_ct_priv(priv),
+ spec, attr,
+ mod_hdr_acts);
+ }
+
+ if (!is_mdev_switchdev_mode(priv->mdev))
+ return mlx5e_add_offloaded_nic_rule(priv, spec, attr);
+
+ if (attr->flags & MLX5_ATTR_FLAG_SAMPLE)
+ return mlx5e_tc_sample_offload(get_sample_priv(priv), spec, attr);
+
+ return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
+}
+
+void
+mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv,
+ struct mlx5_flow_handle *rule,
+ struct mlx5_flow_attr *attr)
+{
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+ if (attr->flags & MLX5_ATTR_FLAG_CT) {
+ mlx5_tc_ct_delete_flow(get_ct_priv(priv), attr);
+ return;
+ }
+
+ if (!is_mdev_switchdev_mode(priv->mdev)) {
+ mlx5e_del_offloaded_nic_rule(priv, rule, attr);
+ return;
+ }
+
+ if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) {
+ mlx5e_tc_sample_unoffload(get_sample_priv(priv), rule, attr);
+ return;
+ }
+
+ mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
+}
+
int
mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts,
}
static int
+alloc_flow_attr_counter(struct mlx5_core_dev *counter_dev,
+ struct mlx5_flow_attr *attr)
+
+{
+ struct mlx5_fc *counter;
+
+ counter = mlx5_fc_create(counter_dev, true);
+ if (IS_ERR(counter))
+ return PTR_ERR(counter);
+
+ attr->counter = counter;
+ return 0;
+}
+
+static int
mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack)
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct mlx5_flow_attr *attr = flow->attr;
struct mlx5_core_dev *dev = priv->mdev;
- struct mlx5_fc *counter;
int err;
parse_attr = attr->parse_attr;
}
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
- counter = mlx5_fc_create(dev, true);
- if (IS_ERR(counter))
- return PTR_ERR(counter);
-
- attr->counter = counter;
+ err = alloc_flow_attr_counter(dev, attr);
+ if (err)
+ return err;
}
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
return err;
}
- if (flow_flag_test(flow, CT))
- flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), flow, &parse_attr->spec,
+ if (attr->flags & MLX5_ATTR_FLAG_CT)
+ flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), &parse_attr->spec,
attr, &parse_attr->mod_hdr_acts);
else
flow->rule[0] = mlx5e_add_offloaded_nic_rule(priv, &parse_attr->spec,
flow_flag_clear(flow, OFFLOADED);
- if (flow_flag_test(flow, CT))
- mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
+ if (attr->flags & MLX5_ATTR_FLAG_CT)
+ mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr);
else if (!IS_ERR_OR_NULL(flow->rule[0]))
mlx5e_del_offloaded_nic_rule(priv, flow->rule[0], attr);
struct mlx5_flow_spec *spec,
struct mlx5_flow_attr *attr)
{
- struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts;
struct mlx5_flow_handle *rule;
- if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
+ if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)
return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
- if (flow_flag_test(flow, CT)) {
- mod_hdr_acts = &attr->parse_attr->mod_hdr_acts;
-
- rule = mlx5_tc_ct_flow_offload(get_ct_priv(flow->priv),
- flow, spec, attr,
- mod_hdr_acts);
- } else if (flow_flag_test(flow, SAMPLE)) {
- rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr,
- mlx5e_tc_get_flow_tun_id(flow));
- } else {
- rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
- }
+ rule = mlx5e_tc_rule_offload(flow->priv, spec, attr);
if (IS_ERR(rule))
return rule;
if (attr->esw_attr->split_count) {
flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, spec, attr);
- if (IS_ERR(flow->rule[1])) {
- if (flow_flag_test(flow, CT))
- mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
- else
- mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
- return flow->rule[1];
- }
+ if (IS_ERR(flow->rule[1]))
+ goto err_rule1;
}
return rule;
+
+err_rule1:
+ mlx5e_tc_rule_unoffload(flow->priv, rule, attr);
+ return flow->rule[1];
}
void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
{
flow_flag_clear(flow, OFFLOADED);
- if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
- goto offload_rule_0;
+ if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)
+ return mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
if (attr->esw_attr->split_count)
mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
- if (flow_flag_test(flow, CT))
- mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr);
- else if (flow_flag_test(flow, SAMPLE))
- mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr);
- else
-offload_rule_0:
- mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
+ mlx5e_tc_rule_unoffload(flow->priv, flow->rule[0], attr);
}
struct mlx5_flow_handle *
memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ);
slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
slow_attr->esw_attr->split_count = 0;
- slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
+ slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
if (!IS_ERR(rule))
memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ);
slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
slow_attr->esw_attr->split_count = 0;
- slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH;
+ slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
flow_flag_clear(flow, SLOW);
kfree(slow_attr);
}
int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv,
- struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct mlx5e_tc_flow *flow)
+ struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr)
{
- struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &parse_attr->mod_hdr_acts;
+ struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &attr->parse_attr->mod_hdr_acts;
struct mlx5_modify_hdr *mod_hdr;
mod_hdr = mlx5_modify_header_alloc(priv->mdev,
if (IS_ERR(mod_hdr))
return PTR_ERR(mod_hdr);
- WARN_ON(flow->attr->modify_hdr);
- flow->attr->modify_hdr = mod_hdr;
+ WARN_ON(attr->modify_hdr);
+ attr->modify_hdr = mod_hdr;
return 0;
}
static int
+set_encap_dests(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
+ struct netlink_ext_ack *extack,
+ bool *encap_valid,
+ bool *vf_tun)
+{
+ struct mlx5e_tc_flow_parse_attr *parse_attr;
+ struct mlx5_esw_flow_attr *esw_attr;
+ struct net_device *encap_dev = NULL;
+ struct mlx5e_rep_priv *rpriv;
+ struct mlx5e_priv *out_priv;
+ int out_index;
+ int err = 0;
+
+ parse_attr = attr->parse_attr;
+ esw_attr = attr->esw_attr;
+ *vf_tun = false;
+ *encap_valid = true;
+
+ for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+ struct net_device *out_dev;
+ int mirred_ifindex;
+
+ if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+ continue;
+
+ mirred_ifindex = parse_attr->mirred_ifindex[out_index];
+ out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
+ if (!out_dev) {
+ NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
+ err = -ENODEV;
+ goto out;
+ }
+ err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index,
+ extack, &encap_dev, encap_valid);
+ dev_put(out_dev);
+ if (err)
+ goto out;
+
+ if (esw_attr->dests[out_index].flags &
+ MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
+ !esw_attr->dest_int_port)
+ *vf_tun = true;
+
+ out_priv = netdev_priv(encap_dev);
+ rpriv = out_priv->ppriv;
+ esw_attr->dests[out_index].rep = rpriv->rep;
+ esw_attr->dests[out_index].mdev = out_priv->mdev;
+ }
+
+ if (*vf_tun && esw_attr->out_count > 1) {
+ NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+out:
+ return err;
+}
+
+static void
+clean_encap_dests(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr,
+ bool *vf_tun)
+{
+ struct mlx5_esw_flow_attr *esw_attr;
+ int out_index;
+
+ esw_attr = attr->esw_attr;
+ *vf_tun = false;
+
+ for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+ if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+ continue;
+
+ if (esw_attr->dests[out_index].flags &
+ MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
+ !esw_attr->dest_int_port)
+ *vf_tun = true;
+
+ mlx5e_detach_encap(priv, flow, attr, out_index);
+ kfree(attr->parse_attr->tun_info[out_index]);
+ }
+}
+
+static int
mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct netlink_ext_ack *extack)
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct mlx5_flow_attr *attr = flow->attr;
- bool vf_tun = false, encap_valid = true;
- struct net_device *encap_dev = NULL;
struct mlx5_esw_flow_attr *esw_attr;
- struct mlx5e_rep_priv *rpriv;
- struct mlx5e_priv *out_priv;
- struct mlx5_fc *counter;
+ bool vf_tun, encap_valid;
u32 max_prio, max_chain;
int err = 0;
- int out_index;
parse_attr = attr->parse_attr;
esw_attr = attr->esw_attr;
esw_attr->int_port = int_port;
}
- for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
- struct net_device *out_dev;
- int mirred_ifindex;
-
- if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
- continue;
-
- mirred_ifindex = parse_attr->mirred_ifindex[out_index];
- out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
- if (!out_dev) {
- NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
- err = -ENODEV;
- goto err_out;
- }
- err = mlx5e_attach_encap(priv, flow, out_dev, out_index,
- extack, &encap_dev, &encap_valid);
- dev_put(out_dev);
- if (err)
- goto err_out;
-
- if (esw_attr->dests[out_index].flags &
- MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
- !esw_attr->dest_int_port)
- vf_tun = true;
- out_priv = netdev_priv(encap_dev);
- rpriv = out_priv->ppriv;
- esw_attr->dests[out_index].rep = rpriv->rep;
- esw_attr->dests[out_index].mdev = out_priv->mdev;
- }
-
- if (vf_tun && esw_attr->out_count > 1) {
- NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
- err = -EOPNOTSUPP;
+ err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun);
+ if (err)
goto err_out;
- }
err = mlx5_eswitch_add_vlan_action(esw, attr);
if (err)
goto err_out;
- if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
- !(attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR)) {
+ if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
if (vf_tun) {
- err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow);
+ err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr);
if (err)
goto err_out;
} else {
}
if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
- counter = mlx5_fc_create(esw_attr->counter_dev, true);
- if (IS_ERR(counter)) {
- err = PTR_ERR(counter);
+ err = alloc_flow_attr_counter(esw_attr->counter_dev, attr);
+ if (err)
goto err_out;
- }
-
- attr->counter = counter;
}
/* we get here if one of the following takes place:
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5_flow_attr *attr = flow->attr;
struct mlx5_esw_flow_attr *esw_attr;
- bool vf_tun = false;
- int out_index;
+ bool vf_tun;
esw_attr = attr->esw_attr;
mlx5e_put_flow_tunnel_id(flow);
if (flow->decap_route)
mlx5e_detach_decap_route(priv, flow);
- for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
- if (esw_attr->dests[out_index].flags &
- MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
- !esw_attr->dest_int_port)
- vf_tun = true;
- if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
- mlx5e_detach_encap(priv, flow, out_index);
- kfree(attr->parse_attr->tun_info[out_index]);
- }
- }
+ clean_encap_dests(priv, flow, attr, &vf_tun);
mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr);
if (flow_flag_test(flow, L3_TO_L2_DECAP))
mlx5e_detach_decap(priv, flow);
- kfree(attr->sample_attr);
kvfree(attr->esw_attr->rx_tun_attr);
kvfree(attr->parse_attr);
kfree(flow->attr);
attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
}
- flow->tunnel_id = value;
+ flow->attr->tunnel_id = value;
return 0;
err_set:
static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow)
{
- u32 enc_opts_id = flow->tunnel_id & ENC_OPTS_BITS_MASK;
- u32 tun_id = flow->tunnel_id >> ENC_OPTS_BITS;
+ u32 enc_opts_id = flow->attr->tunnel_id & ENC_OPTS_BITS_MASK;
+ u32 tun_id = flow->attr->tunnel_id >> ENC_OPTS_BITS;
struct mlx5_rep_uplink_priv *uplink_priv;
struct mlx5e_rep_priv *uplink_rpriv;
struct mlx5_eswitch *esw;
enc_opts_id);
}
-u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow)
-{
- return flow->tunnel_id;
-}
-
void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev,
struct flow_match_basic *match, bool outer,
void *headers_c, void *headers_v)
return mask;
}
+
static int offload_pedit_fields(struct mlx5e_priv *priv,
int namespace,
- struct pedit_headers_action *hdrs,
struct mlx5e_tc_flow_parse_attr *parse_attr,
u32 *action_flags,
struct netlink_ext_ack *extack)
{
struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
+ struct pedit_headers_action *hdrs = parse_attr->hdrs;
void *headers_c, *headers_v, *action, *vals_p;
u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
struct mlx5e_tc_mod_hdr_acts *mod_acts;
static const struct pedit_headers zero_masks = {};
-static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
- struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct pedit_headers_action *hdrs,
- u32 *action_flags,
- struct netlink_ext_ack *extack)
+static int verify_offload_pedit_fields(struct mlx5e_priv *priv,
+ struct mlx5e_tc_flow_parse_attr *parse_attr,
+ struct netlink_ext_ack *extack)
{
struct pedit_headers *cmd_masks;
- int err;
u8 cmd;
- err = offload_pedit_fields(priv, namespace, hdrs, parse_attr,
- action_flags, extack);
- if (err < 0)
- goto out_dealloc_parsed_actions;
-
for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
- cmd_masks = &hdrs[cmd].masks;
+ cmd_masks = &parse_attr->hdrs[cmd].masks;
if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
- NL_SET_ERR_MSG_MOD(extack,
- "attempt to offload an unsupported field");
+ NL_SET_ERR_MSG_MOD(extack, "attempt to offload an unsupported field");
netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd);
print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS,
16, 1, cmd_masks, sizeof(zero_masks), true);
- err = -EOPNOTSUPP;
- goto out_dealloc_parsed_actions;
+ return -EOPNOTSUPP;
}
}
return 0;
+}
+
+static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
+ struct mlx5e_tc_flow_parse_attr *parse_attr,
+ u32 *action_flags,
+ struct netlink_ext_ack *extack)
+{
+ int err;
+
+ err = offload_pedit_fields(priv, namespace, parse_attr, action_flags, extack);
+ if (err)
+ goto out_dealloc_parsed_actions;
+
+ err = verify_offload_pedit_fields(priv, parse_attr, extack);
+ if (err)
+ goto out_dealloc_parsed_actions;
+
+ return 0;
out_dealloc_parsed_actions:
mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts);
return -EOPNOTSUPP;
}
- if (!tc_act->can_offload(parse_state, act, i))
+ if (!tc_act->can_offload(parse_state, act, i, attr))
return -EOPNOTSUPP;
err = tc_act->parse_action(parse_state, act, priv, attr);
flow_action_for_each(i, act, flow_action) {
tc_act = mlx5e_tc_act_get(act->id, ns_type);
if (!tc_act || !tc_act->post_parse ||
- !tc_act->can_offload(parse_state, act, i))
+ !tc_act->can_offload(parse_state, act, i, attr))
continue;
err = tc_act->post_parse(parse_state, priv, attr);
actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv,
struct mlx5e_tc_flow *flow,
struct mlx5_flow_attr *attr,
- struct pedit_headers_action *hdrs,
struct netlink_ext_ack *extack)
{
struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
+ struct pedit_headers_action *hdrs = parse_attr->hdrs;
enum mlx5_flow_namespace_type ns_type;
int err;
ns_type = mlx5e_get_flow_namespace(flow);
- err = alloc_tc_pedit_action(priv, ns_type, parse_attr, hdrs,
- &attr->action, extack);
+ err = alloc_tc_pedit_action(priv, ns_type, parse_attr, &attr->action, extack);
if (err)
return err;
struct mlx5e_tc_act_parse_state *parse_state;
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct mlx5_flow_attr *attr = flow->attr;
- struct pedit_headers_action *hdrs;
int err;
err = flow_action_supported(flow_action, extack);
parse_state = &parse_attr->parse_state;
mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack);
parse_state->ct_priv = get_ct_priv(priv);
- hdrs = parse_state->hdrs;
err = parse_tc_actions(parse_state, flow_action);
if (err)
return err;
- err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack);
+ err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack);
if (err)
return err;
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct mlx5_flow_attr *attr = flow->attr;
struct mlx5_esw_flow_attr *esw_attr;
- struct pedit_headers_action *hdrs;
int err;
err = flow_action_supported(flow_action, extack);
parse_state = &parse_attr->parse_state;
mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack);
parse_state->ct_priv = get_ct_priv(priv);
- hdrs = parse_state->hdrs;
err = parse_tc_actions(parse_state, flow_action);
if (err)
return -EOPNOTSUPP;
}
- err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack);
+ err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack);
if (err)
return err;
struct mlx5_fc *counter;
struct mlx5_modify_hdr *modify_hdr;
struct mlx5_ct_attr ct_attr;
- struct mlx5e_sample_attr *sample_attr;
+ struct mlx5e_sample_attr sample_attr;
struct mlx5e_tc_flow_parse_attr *parse_attr;
u32 chain;
u16 prio;
u8 outer_match_level;
u8 ip_version;
u8 tun_ip_version;
+ int tunnel_id; /* mapped tunnel id */
u32 flags;
union {
struct mlx5_esw_flow_attr esw_attr[0];
};
};
+enum {
+ MLX5_ATTR_FLAG_VLAN_HANDLED = BIT(0),
+ MLX5_ATTR_FLAG_SLOW_PATH = BIT(1),
+ MLX5_ATTR_FLAG_NO_IN_PORT = BIT(2),
+ MLX5_ATTR_FLAG_SRC_REWRITE = BIT(3),
+ MLX5_ATTR_FLAG_SAMPLE = BIT(4),
+ MLX5_ATTR_FLAG_ACCEPT = BIT(5),
+ MLX5_ATTR_FLAG_CT = BIT(6),
+};
+
+/* Returns true if any of the flags that require skipping further TC/NF processing are set. */
+static inline bool
+mlx5e_tc_attr_flags_skip(u32 attr_flags)
+{
+ return attr_flags & (MLX5_ATTR_FLAG_SLOW_PATH | MLX5_ATTR_FLAG_ACCEPT);
+}
+
struct mlx5_rx_tun_attr {
u16 decap_vport;
union {
u32 data);
int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv,
- struct mlx5e_tc_flow_parse_attr *parse_attr,
- struct mlx5e_tc_flow *flow);
-
-struct mlx5e_tc_flow;
-u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow);
+ struct mlx5e_tc_flow *flow,
+ struct mlx5_flow_attr *attr);
void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev,
struct flow_match_basic *match, bool outer,
mlx5_eswitch_is_vf_vport(esw, vport_num) &&
esw->dev == dest_mdev &&
attr->ip_version &&
- attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
+ attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE;
}
u16
MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE = BIT(2),
};
-enum {
- MLX5_ESW_ATTR_FLAG_VLAN_HANDLED = BIT(0),
- MLX5_ESW_ATTR_FLAG_SLOW_PATH = BIT(1),
- MLX5_ESW_ATTR_FLAG_NO_IN_PORT = BIT(2),
- MLX5_ESW_ATTR_FLAG_SRC_REWRITE = BIT(3),
- MLX5_ESW_ATTR_FLAG_SAMPLE = BIT(4),
- MLX5_ESW_ATTR_FLAG_ACCEPT = BIT(5),
-};
-
-/* Returns true if any of the flags that require skipping further TC/NF processing are set. */
-static inline bool
-mlx5_esw_attr_flags_skip(u32 attr_flags)
-{
- return attr_flags & (MLX5_ESW_ATTR_FLAG_SLOW_PATH | MLX5_ESW_ATTR_FLAG_ACCEPT);
-}
-
struct mlx5_esw_flow_attr {
struct mlx5_eswitch_rep *in_rep;
struct mlx5_core_dev *in_mdev;
{
struct mlx5_flow_table *ft;
- if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE))
+ if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE))
return -EOPNOTSUPP;
ft = mlx5_esw_indir_table_get(esw, attr, spec,
static int
esw_setup_sampler_dest(struct mlx5_flow_destination *dest,
struct mlx5_flow_act *flow_act,
- struct mlx5_flow_attr *attr,
+ u32 sampler_id,
int i)
{
flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
- dest[i].sampler_id = attr->sample_attr->sampler_id;
+ dest[i].sampler_id = sampler_id;
return 0;
}
struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
int err;
- if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE))
+ if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE))
return -EOPNOTSUPP;
/* flow steering cannot handle more than one dest with the same ft
struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
int j, err;
- if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE))
+ if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE))
return -EOPNOTSUPP;
for (j = esw_attr->split_count; j < esw_attr->out_count; j++, (*i)++) {
if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) &&
esw_src_port_rewrite_supported(esw))
- attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
+ attr->flags |= MLX5_ATTR_FLAG_SRC_REWRITE;
- if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) {
- esw_setup_sampler_dest(dest, flow_act, attr, *i);
+ if (attr->flags & MLX5_ATTR_FLAG_SAMPLE &&
+ !(attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)) {
+ esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i);
(*i)++;
} else if (attr->dest_ft) {
esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i);
(*i)++;
- } else if (mlx5_esw_attr_flags_skip(attr->flags)) {
+ } else if (mlx5e_tc_attr_flags_skip(attr->flags)) {
esw_setup_slow_path_dest(dest, flow_act, chains, *i);
(*i)++;
} else if (attr->dest_chain) {
if (attr->dest_ft) {
esw_cleanup_decap_indir(esw, attr);
- } else if (!mlx5_esw_attr_flags_skip(attr->flags)) {
+ } else if (!mlx5e_tc_attr_flags_skip(attr->flags)) {
if (attr->dest_chain)
esw_cleanup_chain_dest(chains, attr->dest_chain, 1, 0);
else if (esw_is_indir_table(esw, attr))
else
fdb = attr->ft;
- if (!(attr->flags & MLX5_ESW_ATTR_FLAG_NO_IN_PORT))
+ if (!(attr->flags & MLX5_ATTR_FLAG_NO_IN_PORT))
mlx5_eswitch_set_rule_source_port(esw, spec, attr,
esw_attr->in_mdev->priv.eswitch,
esw_attr->in_rep->vport);
mlx5_del_flow_rules(rule);
- if (!mlx5_esw_attr_flags_skip(attr->flags)) {
+ if (!mlx5e_tc_attr_flags_skip(attr->flags)) {
/* unref the term table */
for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
if (esw_attr->dests[i].termtbl)
if (err)
goto unlock;
- attr->flags &= ~MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
+ attr->flags &= ~MLX5_ATTR_FLAG_VLAN_HANDLED;
vport = esw_vlan_action_get_vport(esw_attr, push, pop);
/* tracks VF --> wire rules without vlan push action */
if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
vport->vlan_refcount++;
- attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
+ attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED;
}
goto unlock;
}
out:
if (!err)
- attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED;
+ attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED;
unlock:
mutex_unlock(&esw->state_lock);
return err;
if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
return 0;
- if (!(attr->flags & MLX5_ESW_ATTR_FLAG_VLAN_HANDLED))
+ if (!(attr->flags & MLX5_ATTR_FLAG_VLAN_HANDLED))
return 0;
push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) ||
!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) ||
- mlx5_esw_attr_flags_skip(attr->flags) ||
+ mlx5e_tc_attr_flags_skip(attr->flags) ||
(!mlx5_eswitch_offload_is_uplink_port(esw, spec) && !esw_attr->int_port))
return false;
/* push vlan on RX */
- if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH)
+ if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH &&
+ !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) &
+ MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX))
return true;
/* hairpin */
return 0;
}
+static u32 mlx5_cmd_stub_get_capabilities(struct mlx5_flow_root_namespace *ns,
+ enum fs_flow_table_type ft_type)
+{
+ return 0;
+}
+
static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master,
struct mlx5_core_dev *slave,
bool ft_id_valid,
return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
}
+static u32 mlx5_cmd_get_capabilities(struct mlx5_flow_root_namespace *ns,
+ enum fs_flow_table_type ft_type)
+{
+ return 0;
+}
+
static const struct mlx5_flow_cmds mlx5_flow_cmds = {
.create_flow_table = mlx5_cmd_create_flow_table,
.destroy_flow_table = mlx5_cmd_destroy_flow_table,
.set_peer = mlx5_cmd_stub_set_peer,
.create_ns = mlx5_cmd_stub_create_ns,
.destroy_ns = mlx5_cmd_stub_destroy_ns,
+ .get_capabilities = mlx5_cmd_get_capabilities,
};
static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
.set_peer = mlx5_cmd_stub_set_peer,
.create_ns = mlx5_cmd_stub_create_ns,
.destroy_ns = mlx5_cmd_stub_destroy_ns,
+ .get_capabilities = mlx5_cmd_stub_get_capabilities,
};
const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void)
u16 format_id, u32 *match_mask);
int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns,
int definer_id);
+
+ u32 (*get_capabilities)(struct mlx5_flow_root_namespace *ns,
+ enum fs_flow_table_type ft_type);
};
int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
steering->esw_ingress_root_ns = NULL;
}
+u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type)
+{
+ struct mlx5_flow_root_namespace *root;
+ struct mlx5_flow_namespace *ns;
+
+ ns = mlx5_get_flow_namespace(dev, type);
+ if (!ns)
+ return 0;
+
+ root = find_root(&ns->node);
+ if (!root)
+ return 0;
+
+ return root->cmds->get_capabilities(root, root->table_type);
+}
+
static int init_egress_root_ns(struct mlx5_flow_steering *steering)
{
int err;
MLX5_FLOW_STEERING_MODE_SMFS
};
+enum mlx5_flow_steering_capabilty {
+ MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX = 1UL << 0,
+ MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX = 1UL << 1,
+};
+
struct mlx5_flow_steering {
struct mlx5_core_dev *dev;
enum mlx5_flow_steering_mode mode;
int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports);
void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev);
+u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type);
+
struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
#define fs_get_obj(v, _node) {v = container_of((_node), typeof(*v), node); }
return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain);
}
+static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns,
+ enum fs_flow_table_type ft_type)
+{
+ if (ft_type != FS_FT_FDB ||
+ MLX5_CAP_GEN(ns->dev, steering_format_version) != MLX5_STEERING_FORMAT_CONNECTX_6DX)
+ return 0;
+
+ return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX;
+}
+
bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
{
return mlx5dr_is_supported(dev);
.set_peer = mlx5_cmd_dr_set_peer,
.create_ns = mlx5_cmd_dr_create_ns,
.destroy_ns = mlx5_cmd_dr_destroy_ns,
+ .get_capabilities = mlx5_cmd_dr_get_capabilities,
};
const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
void *priv;
};
+static const u8 mlxsw_core_trap_groups[] = {
+ MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
+ MLXSW_REG_HTGT_TRAP_GROUP_CORE_EVENT,
+};
+
+static int mlxsw_core_trap_groups_set(struct mlxsw_core *mlxsw_core)
+{
+ char htgt_pl[MLXSW_REG_HTGT_LEN];
+ int err;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(mlxsw_core_trap_groups); i++) {
+ mlxsw_reg_htgt_pack(htgt_pl, mlxsw_core_trap_groups[i],
+ MLXSW_REG_HTGT_INVALID_POLICER,
+ MLXSW_REG_HTGT_DEFAULT_PRIORITY,
+ MLXSW_REG_HTGT_DEFAULT_TC);
+ err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
/******************
* EMAD processing
******************/
if (err)
goto err_trap_register;
- err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core);
- if (err)
- goto err_emad_trap_set;
mlxsw_core->emad.use_emad = true;
return 0;
-err_emad_trap_set:
- mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener,
- mlxsw_core);
err_trap_register:
destroy_workqueue(mlxsw_core->emad_wq);
return err;
}
static const struct mlxsw_listener mlxsw_core_health_listener =
- MLXSW_EVENTL(mlxsw_core_health_listener_func, MFDE, MFDE);
+ MLXSW_CORE_EVENTL(mlxsw_core_health_listener_func, MFDE);
static int
mlxsw_core_health_fw_fatal_dump_fatal_cause(const char *mfde_pl,
}
}
+ err = mlxsw_core_trap_groups_set(mlxsw_core);
+ if (err)
+ goto err_trap_groups_set;
+
err = mlxsw_emad_init(mlxsw_core);
if (err)
goto err_emad_init;
err_register_params:
mlxsw_emad_fini(mlxsw_core);
err_emad_init:
+err_trap_groups_set:
kfree(mlxsw_core->lag.mapping);
err_alloc_lag_mapping:
mlxsw_ports_fini(mlxsw_core, reload);
}
EXPORT_SYMBOL(mlxsw_core_trap_unregister);
+int mlxsw_core_traps_register(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_listener *listeners,
+ size_t listeners_count, void *priv)
+{
+ int i, err;
+
+ for (i = 0; i < listeners_count; i++) {
+ err = mlxsw_core_trap_register(mlxsw_core,
+ &listeners[i],
+ priv);
+ if (err)
+ goto err_listener_register;
+ }
+ return 0;
+
+err_listener_register:
+ for (i--; i >= 0; i--) {
+ mlxsw_core_trap_unregister(mlxsw_core,
+ &listeners[i],
+ priv);
+ }
+ return err;
+}
+EXPORT_SYMBOL(mlxsw_core_traps_register);
+
+void mlxsw_core_traps_unregister(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_listener *listeners,
+ size_t listeners_count, void *priv)
+{
+ int i;
+
+ for (i = 0; i < listeners_count; i++) {
+ mlxsw_core_trap_unregister(mlxsw_core,
+ &listeners[i],
+ priv);
+ }
+}
+EXPORT_SYMBOL(mlxsw_core_traps_unregister);
+
int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core,
const struct mlxsw_listener *listener,
bool enabled)
.enabled_on_register = true, \
}
+#define MLXSW_CORE_EVENTL(_func, _trap_id) \
+ MLXSW_EVENTL(_func, _trap_id, CORE_EVENT)
+
int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core,
const struct mlxsw_rx_listener *rxl,
void *priv, bool enabled);
void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core,
const struct mlxsw_listener *listener,
void *priv);
+int mlxsw_core_traps_register(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_listener *listeners,
+ size_t listeners_count, void *priv);
+void mlxsw_core_traps_unregister(struct mlxsw_core *mlxsw_core,
+ const struct mlxsw_listener *listeners,
+ size_t listeners_count, void *priv);
int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core,
const struct mlxsw_listener *listener,
bool enabled);
const struct mlxsw_bus_info *mlxsw_bus_info,
struct netlink_ext_ack *extack);
void (*fini)(struct mlxsw_core *mlxsw_core);
- int (*basic_trap_groups_set)(struct mlxsw_core *mlxsw_core);
int (*port_type_set)(struct mlxsw_core *mlxsw_core, u16 local_port,
enum devlink_port_type new_type);
int (*port_split)(struct mlxsw_core *mlxsw_core, u16 local_port,
int num_ports_mapped;
int num_ports_up;
enum ethtool_module_power_mode_policy power_mode_policy;
+ enum mlxsw_reg_pmtm_module_type type;
};
struct mlxsw_env {
struct mlxsw_env_module_info module_info[];
};
-static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
- bool *qsfp, bool *cmis)
+static int __mlxsw_env_validate_module_type(struct mlxsw_core *core, u8 module)
+{
+ struct mlxsw_env *mlxsw_env = mlxsw_core_env(core);
+ int err;
+
+ switch (mlxsw_env->module_info[module].type) {
+ case MLXSW_REG_PMTM_MODULE_TYPE_TWISTED_PAIR:
+ err = -EINVAL;
+ break;
+ default:
+ err = 0;
+ }
+
+ return err;
+}
+
+static int mlxsw_env_validate_module_type(struct mlxsw_core *core, u8 module)
+{
+ struct mlxsw_env *mlxsw_env = mlxsw_core_env(core);
+ int err;
+
+ mutex_lock(&mlxsw_env->module_info_lock);
+ err = __mlxsw_env_validate_module_type(core, module);
+ mutex_unlock(&mlxsw_env->module_info_lock);
+
+ return err;
+}
+
+static int
+mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, bool *qsfp,
+ bool *cmis)
{
char mcia_pl[MLXSW_REG_MCIA_LEN];
char *eeprom_tmp;
u8 ident;
int err;
+ err = mlxsw_env_validate_module_type(core, id);
+ if (err)
+ return err;
+
mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1,
MLXSW_REG_MCIA_I2C_ADDR_LOW);
err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
return 0;
}
-int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
+int mlxsw_env_get_module_info(struct net_device *netdev,
+ struct mlxsw_core *mlxsw_core, int module,
struct ethtool_modinfo *modinfo)
{
u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE];
unsigned int read_size;
int err;
+ err = mlxsw_env_validate_module_type(mlxsw_core, module);
+ if (err) {
+ netdev_err(netdev,
+ "EEPROM is not equipped on port module type");
+ return err;
+ }
+
err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset,
module_info, false, &read_size);
if (err)
{
u32 bytes_read = 0;
u16 device_addr;
+ int err;
+
+ err = mlxsw_env_validate_module_type(mlxsw_core, module);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "EEPROM is not equipped on port module type");
+ return err;
+ }
/* Offset cannot be larger than 2 * ETH_MODULE_EEPROM_PAGE_LEN */
device_addr = page->offset;
char mcia_pl[MLXSW_REG_MCIA_LEN];
char *eeprom_tmp;
u8 size;
- int err;
size = min_t(u8, page->length - bytes_read,
MLXSW_REG_MCIA_EEPROM_SIZE);
mutex_lock(&mlxsw_env->module_info_lock);
+ err = __mlxsw_env_validate_module_type(mlxsw_core, module);
+ if (err) {
+ netdev_err(netdev, "Reset module is not supported on port module type\n");
+ goto out;
+ }
+
if (mlxsw_env->module_info[module].num_ports_up) {
netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n");
err = -EINVAL;
mutex_lock(&mlxsw_env->module_info_lock);
+ err = __mlxsw_env_validate_module_type(mlxsw_core, module);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack, "Power mode is not supported on port module type");
+ goto out;
+ }
+
params->policy = mlxsw_env->module_info[module].power_mode_policy;
mlxsw_reg_mcion_pack(mcion_pl, module);
mutex_lock(&mlxsw_env->module_info_lock);
+ err = __mlxsw_env_validate_module_type(mlxsw_core, module);
+ if (err) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Power mode set is not supported on port module type");
+ goto out;
+ }
+
if (mlxsw_env->module_info[module].power_mode_policy == policy)
goto out;
return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl);
}
-static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core,
- u8 module_count)
+static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core)
{
int i, err, sensor_index;
bool has_temp_sensor;
- for (i = 0; i < module_count; i++) {
+ for (i = 0; i < mlxsw_core_env(mlxsw_core)->module_count; i++) {
err = mlxsw_env_module_has_temp_sensor(mlxsw_core, i,
&has_temp_sensor);
if (err)
}
static const struct mlxsw_listener mlxsw_env_temp_warn_listener =
- MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE);
+ MLXSW_CORE_EVENTL(mlxsw_env_mtwe_listener_func, MTWE);
static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core)
{
}
static const struct mlxsw_listener mlxsw_env_module_plug_listener =
- MLXSW_EVENTL(mlxsw_env_pmpe_listener_func, PMPE, PMPE);
+ MLXSW_CORE_EVENTL(mlxsw_env_pmpe_listener_func, PMPE);
static int
mlxsw_env_module_plug_event_register(struct mlxsw_core *mlxsw_core)
}
static int
-mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core,
- u8 module_count)
+mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core)
{
int i, err;
- for (i = 0; i < module_count; i++) {
+ for (i = 0; i < mlxsw_core_env(mlxsw_core)->module_count; i++) {
char pmaos_pl[MLXSW_REG_PMAOS_LEN];
mlxsw_reg_pmaos_pack(pmaos_pl, i);
}
EXPORT_SYMBOL(mlxsw_env_module_port_down);
+static int
+mlxsw_env_module_type_set(struct mlxsw_core *mlxsw_core)
+{
+ struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core);
+ int i;
+
+ for (i = 0; i < mlxsw_env->module_count; i++) {
+ char pmtm_pl[MLXSW_REG_PMTM_LEN];
+ int err;
+
+ mlxsw_reg_pmtm_pack(pmtm_pl, 0, i);
+ err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtm), pmtm_pl);
+ if (err)
+ return err;
+
+ mlxsw_env->module_info[i].type =
+ mlxsw_reg_pmtm_module_type_get(pmtm_pl);
+ }
+
+ return 0;
+}
+
int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env)
{
char mgpir_pl[MLXSW_REG_MGPIR_LEN];
if (err)
goto err_module_plug_event_register;
- err = mlxsw_env_module_oper_state_event_enable(mlxsw_core,
- env->module_count);
+ err = mlxsw_env_module_oper_state_event_enable(mlxsw_core);
if (err)
goto err_oper_state_event_enable;
- err = mlxsw_env_module_temp_event_enable(mlxsw_core, env->module_count);
+ err = mlxsw_env_module_temp_event_enable(mlxsw_core);
if (err)
goto err_temp_event_enable;
+ err = mlxsw_env_module_type_set(mlxsw_core);
+ if (err)
+ goto err_type_set;
+
return 0;
+err_type_set:
err_temp_event_enable:
err_oper_state_event_enable:
mlxsw_env_module_plug_event_unregister(env);
int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
int off, int *temp);
-int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
+int mlxsw_env_get_module_info(struct net_device *netdev,
+ struct mlxsw_core *mlxsw_core, int module,
struct ethtool_modinfo *modinfo);
int mlxsw_env_get_module_eeprom(struct net_device *netdev,
struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
- return mlxsw_env_get_module_info(core, mlxsw_m_port->module, modinfo);
+ return mlxsw_env_get_module_info(netdev, core, mlxsw_m_port->module,
+ modinfo);
}
static int
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21)
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 BIT(22)
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4 BIT(23)
+#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_T BIT(24)
+#define MLXSW_REG_PTYS_ETH_SPEED_1000BASE_T BIT(25)
#define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR BIT(27)
#define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR BIT(28)
#define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR BIT(29)
*slot_index = mlxsw_reg_pllp_slot_index_get(payload);
}
+/* PMTM - Port Module Type Mapping Register
+ * ----------------------------------------
+ * The PMTM register allows query or configuration of module types.
+ * The register can only be set when the module is disabled by PMAOS register
+ */
+#define MLXSW_REG_PMTM_ID 0x5067
+#define MLXSW_REG_PMTM_LEN 0x10
+
+MLXSW_REG_DEFINE(pmtm, MLXSW_REG_PMTM_ID, MLXSW_REG_PMTM_LEN);
+
+/* reg_pmtm_slot_index
+ * Slot index.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmtm, slot_index, 0x00, 24, 4);
+
+/* reg_pmtm_module
+ * Module number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pmtm, module, 0x00, 16, 8);
+
+enum mlxsw_reg_pmtm_module_type {
+ MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_4_LANES = 0,
+ MLXSW_REG_PMTM_MODULE_TYPE_QSFP = 1,
+ MLXSW_REG_PMTM_MODULE_TYPE_SFP = 2,
+ MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_SINGLE_LANE = 4,
+ MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_2_LANES = 8,
+ MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP4X = 10,
+ MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP2X = 11,
+ MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP1X = 12,
+ MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14,
+ MLXSW_REG_PMTM_MODULE_TYPE_OSFP = 15,
+ MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD = 16,
+ MLXSW_REG_PMTM_MODULE_TYPE_DSFP = 17,
+ MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP8X = 18,
+ MLXSW_REG_PMTM_MODULE_TYPE_TWISTED_PAIR = 19,
+};
+
+/* reg_pmtm_module_type
+ * Module type.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pmtm, module_type, 0x04, 0, 5);
+
+static inline void mlxsw_reg_pmtm_pack(char *payload, u8 slot_index, u8 module)
+{
+ MLXSW_REG_ZERO(pmtm, payload);
+ mlxsw_reg_pmtm_slot_index_set(payload, slot_index);
+ mlxsw_reg_pmtm_module_set(payload, module);
+}
+
/* HTGT - Host Trap Group Table
* ----------------------------
* Configures the properties for forwarding to CPU.
enum mlxsw_reg_htgt_trap_group {
MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
- MLXSW_REG_HTGT_TRAP_GROUP_MFDE,
- MLXSW_REG_HTGT_TRAP_GROUP_MTWE,
- MLXSW_REG_HTGT_TRAP_GROUP_PMPE,
+ MLXSW_REG_HTGT_TRAP_GROUP_CORE_EVENT,
MLXSW_REG_HTGT_TRAP_GROUP_SP_STP,
MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP,
MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP,
MLXSW_REG(pddr),
MLXSW_REG(pmmp),
MLXSW_REG(pllp),
+ MLXSW_REG(pmtm),
MLXSW_REG(htgt),
MLXSW_REG(hpkt),
MLXSW_REG(rgcr),
MLXSW_RES_ID_ACL_MAX_REGIONS,
MLXSW_RES_ID_ACL_MAX_GROUPS,
MLXSW_RES_ID_ACL_MAX_GROUP_SIZE,
+ MLXSW_RES_ID_ACL_MAX_DEFAULT_ACTIONS,
MLXSW_RES_ID_ACL_FLEX_KEYS,
MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE,
MLXSW_RES_ID_ACL_ACTIONS_PER_SET,
[MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903,
[MLXSW_RES_ID_ACL_MAX_GROUPS] = 0x2904,
[MLXSW_RES_ID_ACL_MAX_GROUP_SIZE] = 0x2905,
+ [MLXSW_RES_ID_ACL_MAX_DEFAULT_ACTIONS] = 0x2908,
[MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910,
[MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911,
[MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912,
struct mlxsw_sp *mlxsw_sp = priv;
struct mlxsw_sp_port *mlxsw_sp_port;
enum mlxsw_reg_pude_oper_status status;
- unsigned int max_ports;
u16 local_port;
- max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
local_port = mlxsw_reg_pude_local_port_get(pude_pl);
- if (WARN_ON_ONCE(!local_port || local_port >= max_ports))
+ if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port)))
return;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port)
return 0;
}
-static int mlxsw_sp_traps_register(struct mlxsw_sp *mlxsw_sp,
- const struct mlxsw_listener listeners[],
- size_t listeners_count)
-{
- int i;
- int err;
-
- for (i = 0; i < listeners_count; i++) {
- err = mlxsw_core_trap_register(mlxsw_sp->core,
- &listeners[i],
- mlxsw_sp);
- if (err)
- goto err_listener_register;
-
- }
- return 0;
-
-err_listener_register:
- for (i--; i >= 0; i--) {
- mlxsw_core_trap_unregister(mlxsw_sp->core,
- &listeners[i],
- mlxsw_sp);
- }
- return err;
-}
-
-static void mlxsw_sp_traps_unregister(struct mlxsw_sp *mlxsw_sp,
- const struct mlxsw_listener listeners[],
- size_t listeners_count)
-{
- int i;
-
- for (i = 0; i < listeners_count; i++) {
- mlxsw_core_trap_unregister(mlxsw_sp->core,
- &listeners[i],
- mlxsw_sp);
- }
-}
-
static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp)
{
struct mlxsw_sp_trap *trap;
if (err)
goto err_trap_groups_set;
- err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp_listener,
- ARRAY_SIZE(mlxsw_sp_listener));
+ err = mlxsw_core_traps_register(mlxsw_sp->core, mlxsw_sp_listener,
+ ARRAY_SIZE(mlxsw_sp_listener),
+ mlxsw_sp);
if (err)
goto err_traps_register;
- err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp->listeners,
- mlxsw_sp->listeners_count);
+ err = mlxsw_core_traps_register(mlxsw_sp->core, mlxsw_sp->listeners,
+ mlxsw_sp->listeners_count, mlxsw_sp);
if (err)
goto err_extra_traps_init;
return 0;
err_extra_traps_init:
- mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener,
- ARRAY_SIZE(mlxsw_sp_listener));
+ mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp_listener,
+ ARRAY_SIZE(mlxsw_sp_listener),
+ mlxsw_sp);
err_traps_register:
err_trap_groups_set:
err_cpu_policers_set:
static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp)
{
- mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp->listeners,
- mlxsw_sp->listeners_count);
- mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener,
- ARRAY_SIZE(mlxsw_sp_listener));
+ mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp->listeners,
+ mlxsw_sp->listeners_count,
+ mlxsw_sp);
+ mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp_listener,
+ ARRAY_SIZE(mlxsw_sp_listener), mlxsw_sp);
kfree(mlxsw_sp->trap);
}
kfree(mlxsw_sp->lags);
}
-static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core)
-{
- char htgt_pl[MLXSW_REG_HTGT_LEN];
- int err;
-
- mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
- MLXSW_REG_HTGT_INVALID_POLICER,
- MLXSW_REG_HTGT_DEFAULT_PRIORITY,
- MLXSW_REG_HTGT_DEFAULT_TC);
- err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
- if (err)
- return err;
-
- mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MFDE,
- MLXSW_REG_HTGT_INVALID_POLICER,
- MLXSW_REG_HTGT_DEFAULT_PRIORITY,
- MLXSW_REG_HTGT_DEFAULT_TC);
- err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
- if (err)
- return err;
-
- mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MTWE,
- MLXSW_REG_HTGT_INVALID_POLICER,
- MLXSW_REG_HTGT_DEFAULT_PRIORITY,
- MLXSW_REG_HTGT_DEFAULT_TC);
- err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
- if (err)
- return err;
-
- mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_PMPE,
- MLXSW_REG_HTGT_INVALID_POLICER,
- MLXSW_REG_HTGT_DEFAULT_PRIORITY,
- MLXSW_REG_HTGT_DEFAULT_TC);
- return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl);
-}
-
static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = {
.clock_init = mlxsw_sp1_ptp_clock_init,
.clock_fini = mlxsw_sp1_ptp_clock_fini,
.fw_filename = MLXSW_SP1_FW_FILENAME,
.init = mlxsw_sp1_init,
.fini = mlxsw_sp_fini,
- .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set,
.port_split = mlxsw_sp_port_split,
.port_unsplit = mlxsw_sp_port_unsplit,
.sb_pool_get = mlxsw_sp_sb_pool_get,
.fw_filename = MLXSW_SP2_FW_FILENAME,
.init = mlxsw_sp2_init,
.fini = mlxsw_sp_fini,
- .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set,
.port_split = mlxsw_sp_port_split,
.port_unsplit = mlxsw_sp_port_unsplit,
.sb_pool_get = mlxsw_sp_sb_pool_get,
.fw_filename = MLXSW_SP3_FW_FILENAME,
.init = mlxsw_sp3_init,
.fini = mlxsw_sp_fini,
- .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set,
.port_split = mlxsw_sp_port_split,
.port_unsplit = mlxsw_sp_port_unsplit,
.sb_pool_get = mlxsw_sp_sb_pool_get,
.priv_size = sizeof(struct mlxsw_sp),
.init = mlxsw_sp4_init,
.fini = mlxsw_sp_fini,
- .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set,
.port_split = mlxsw_sp_port_split,
.port_unsplit = mlxsw_sp_port_unsplit,
.sb_pool_get = mlxsw_sp_sb_pool_get,
mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port,
bool is_8021ad_tagged,
bool is_8021q_tagged);
+static inline bool
+mlxsw_sp_local_port_is_valid(struct mlxsw_sp *mlxsw_sp, u16 local_port)
+{
+ unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+
+ return local_port < max_ports && local_port;
+}
/* spectrum_buffers.c */
struct mlxsw_sp_hdroom_prio {
struct mlxsw_sp1_kvdl_part *part;
bool need_update = true;
unsigned int nr_entries;
- size_t usage_size;
u64 resource_size;
int err;
}
nr_entries = div_u64(resource_size, info->alloc_size);
- usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
- part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+ part = kzalloc(struct_size(part, usage, BITS_TO_LONGS(nr_entries)),
+ GFP_KERNEL);
if (!part)
return ERR_PTR(-ENOMEM);
int i;
int err;
+ /* Some TCAM regions are not exposed to the host and used internally
+ * by the device. Allocate KVDL entries for the default actions of
+ * these regions to avoid the host from overwriting them.
+ */
tcam->kvdl_count = _tcam->max_regions;
+ if (MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_DEFAULT_ACTIONS))
+ tcam->kvdl_count = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+ ACL_MAX_DEFAULT_ACTIONS);
err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
tcam->kvdl_count, &tcam->kvdl_index);
if (err)
goto err_afa_block_continue;
enc_actions = mlxsw_afa_block_cur_set(afa_block);
- for (i = 0; i < tcam->kvdl_count; i++) {
+ /* Only write to KVDL entries used by TCAM regions exposed to the
+ * host.
+ */
+ for (i = 0; i < _tcam->max_regions; i++) {
mlxsw_reg_pefa_pack(pefa_pl, tcam->kvdl_index + i,
true, enc_actions);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- int err;
-
- err = mlxsw_env_get_module_info(mlxsw_sp->core,
- mlxsw_sp_port->mapping.module,
- modinfo);
- return err;
+ return mlxsw_env_get_module_info(netdev, mlxsw_sp->core,
+ mlxsw_sp_port->mapping.module,
+ modinfo);
}
static int mlxsw_sp_get_module_eeprom(struct net_device *netdev,
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- int err;
-
- err = mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core,
- mlxsw_sp_port->mapping.module, ee,
- data);
- return err;
+ return mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core,
+ mlxsw_sp_port->mapping.module, ee,
+ data);
}
static int
static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = {
{
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+ .speed = SPEED_100,
+ },
+ {
.mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII |
MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX,
.mask_ethtool = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
.speed = SPEED_1000,
},
{
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_1000BASE_T,
+ .mask_ethtool = ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+ .speed = SPEED_1000,
+ },
+ {
.mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 |
MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4,
.mask_ethtool = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
u8 domain_number, u16 sequence_id,
u64 timestamp)
{
- unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
struct mlxsw_sp_port *mlxsw_sp_port;
struct mlxsw_sp1_ptp_key key;
u8 types;
- if (WARN_ON_ONCE(local_port >= max_ports))
+ if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port)))
return;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port)
char *sfn_pl, int rec_index,
bool adding)
{
- unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
struct mlxsw_sp_bridge_device *bridge_device;
struct mlxsw_sp_bridge_port *bridge_port;
mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port);
- if (WARN_ON_ONCE(local_port >= max_ports))
+ if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port)))
return;
mlxsw_sp_port = mlxsw_sp->ports[local_port];
if (!mlxsw_sp_port) {
}
if (eee->eee_enabled) {
- ret = phy_init_eee(phydev, 0);
+ ret = phy_init_eee(phydev, false);
if (ret) {
netif_err(adapter, drv, adapter->netdev,
"EEE initialization failed\n");
lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \
lan966x_mac.o lan966x_ethtool.o lan966x_switchdev.o \
- lan966x_vlan.o lan966x_fdb.o lan966x_mdb.o
+ lan966x_vlan.o lan966x_fdb.o lan966x_mdb.o \
+ lan966x_ptp.o
return phylink_ethtool_set_pauseparam(port->phylink, pause);
}
+static int lan966x_get_ts_info(struct net_device *dev,
+ struct ethtool_ts_info *info)
+{
+ struct lan966x_port *port = netdev_priv(dev);
+ struct lan966x *lan966x = port->lan966x;
+ struct lan966x_phc *phc;
+
+ if (!lan966x->ptp)
+ return ethtool_op_get_ts_info(dev, info);
+
+ phc = &lan966x->phc[LAN966X_PHC_PORT];
+
+ info->phc_index = phc->clock ? ptp_clock_index(phc->clock) : -1;
+ if (info->phc_index == -1) {
+ info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ return 0;
+ }
+ 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;
+ info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) |
+ BIT(HWTSTAMP_TX_ONESTEP_SYNC);
+ info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+ BIT(HWTSTAMP_FILTER_ALL);
+
+ return 0;
+}
+
const struct ethtool_ops lan966x_ethtool_ops = {
.get_link_ksettings = lan966x_get_link_ksettings,
.set_link_ksettings = lan966x_set_link_ksettings,
.get_eth_mac_stats = lan966x_get_eth_mac_stats,
.get_rmon_stats = lan966x_get_eth_rmon_stats,
.get_link = ethtool_op_get_link,
+ .get_ts_info = lan966x_get_ts_info,
};
static void lan966x_check_stats_work(struct work_struct *work)
{ TARGET_ORG, 0, 1 }, /* 0xe2000000 */
{ TARGET_GCB, 0x4000, 1 }, /* 0xe2004000 */
{ TARGET_QS, 0x8000, 1 }, /* 0xe2008000 */
+ { TARGET_PTP, 0xc000, 1 }, /* 0xe200c000 */
{ TARGET_CHIP_TOP, 0x10000, 1 }, /* 0xe2010000 */
{ TARGET_REW, 0x14000, 1 }, /* 0xe2014000 */
{ TARGET_SYS, 0x28000, 1 }, /* 0xe2028000 */
val = lan_rd(lan966x, QS_INJ_STATUS);
if (!(QS_INJ_STATUS_FIFO_RDY_GET(val) & BIT(grp)) ||
(QS_INJ_STATUS_WMARK_REACHED_GET(val) & BIT(grp)))
- return NETDEV_TX_BUSY;
+ goto err;
/* Write start of frame */
lan_wr(QS_INJ_CTRL_GAP_SIZE_SET(1) |
/* Wait until the fifo is ready */
err = lan966x_port_inj_ready(lan966x, grp);
if (err)
- return NETDEV_TX_BUSY;
+ goto err;
lan_wr((__force u32)ifh[i], lan966x, QS_INJ_WR(grp));
}
/* Wait until the fifo is ready */
err = lan966x_port_inj_ready(lan966x, grp);
if (err)
- return NETDEV_TX_BUSY;
+ goto err;
lan_wr(((u32 *)skb->data)[i], lan966x, QS_INJ_WR(grp));
}
/* Wait until the fifo is ready */
err = lan966x_port_inj_ready(lan966x, grp);
if (err)
- return NETDEV_TX_BUSY;
+ goto err;
lan_wr(0, lan966x, QS_INJ_WR(grp));
++i;
dev->stats.tx_packets++;
dev->stats.tx_bytes += skb->len;
+ if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+ LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP)
+ return NETDEV_TX_OK;
+
dev_consume_skb_any(skb);
return NETDEV_TX_OK;
+
+err:
+ if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+ LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP)
+ lan966x_ptp_txtstamp_release(port, skb);
+
+ return NETDEV_TX_BUSY;
}
static void lan966x_ifh_set_bypass(void *ifh, u64 bypass)
IFH_POS_TCI, IFH_LEN * 4, PACK, 0);
}
+static void lan966x_ifh_set_rew_op(void *ifh, u64 rew_op)
+{
+ packing(ifh, &rew_op, IFH_POS_REW_CMD + IFH_WID_REW_CMD - 1,
+ IFH_POS_REW_CMD, IFH_LEN * 4, PACK, 0);
+}
+
+static void lan966x_ifh_set_timestamp(void *ifh, u64 timestamp)
+{
+ packing(ifh, ×tamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1,
+ IFH_POS_TIMESTAMP, IFH_LEN * 4, PACK, 0);
+}
+
static int lan966x_port_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct lan966x_port *port = netdev_priv(dev);
__be32 ifh[IFH_LEN];
+ int err;
memset(ifh, 0x0, sizeof(__be32) * IFH_LEN);
lan966x_ifh_set_ipv(ifh, skb->priority >= 7 ? 0x7 : skb->priority);
lan966x_ifh_set_vid(ifh, skb_vlan_tag_get(skb));
+ if (port->lan966x->ptp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+ err = lan966x_ptp_txtstamp_request(port, skb);
+ if (err)
+ return err;
+
+ lan966x_ifh_set_rew_op(ifh, LAN966X_SKB_CB(skb)->rew_op);
+ lan966x_ifh_set_timestamp(ifh, LAN966X_SKB_CB(skb)->ts_id);
+ }
+
return lan966x_port_ifh_xmit(skb, ifh, dev);
}
return 0;
}
+static int lan966x_port_ioctl(struct net_device *dev, struct ifreq *ifr,
+ int cmd)
+{
+ struct lan966x_port *port = netdev_priv(dev);
+
+ if (!phy_has_hwtstamp(dev->phydev) && port->lan966x->ptp) {
+ switch (cmd) {
+ case SIOCSHWTSTAMP:
+ return lan966x_ptp_hwtstamp_set(port, ifr);
+ case SIOCGHWTSTAMP:
+ return lan966x_ptp_hwtstamp_get(port, ifr);
+ }
+ }
+
+ return phy_mii_ioctl(dev->phydev, ifr, cmd);
+}
+
static const struct net_device_ops lan966x_port_netdev_ops = {
.ndo_open = lan966x_port_open,
.ndo_stop = lan966x_port_stop,
.ndo_get_stats64 = lan966x_stats_get,
.ndo_set_mac_address = lan966x_port_set_mac_address,
.ndo_get_port_parent_id = lan966x_port_get_parent_id,
+ .ndo_eth_ioctl = lan966x_port_ioctl,
};
bool lan966x_netdevice_check(const struct net_device *dev)
IFH_POS_LEN, IFH_LEN * 4, UNPACK, 0);
}
+static void lan966x_ifh_get_timestamp(void *ifh, u64 *timestamp)
+{
+ packing(ifh, timestamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1,
+ IFH_POS_TIMESTAMP, IFH_LEN * 4, UNPACK, 0);
+}
+
static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args)
{
struct lan966x *lan966x = args;
return IRQ_NONE;
do {
+ u64 src_port, len, timestamp;
struct net_device *dev;
struct sk_buff *skb;
int sz = 0, buf_len;
- u64 src_port, len;
u32 ifh[IFH_LEN];
u32 *buf;
u32 val;
lan966x_ifh_get_src_port(ifh, &src_port);
lan966x_ifh_get_len(ifh, &len);
+ lan966x_ifh_get_timestamp(ifh, ×tamp);
WARN_ON(src_port >= lan966x->num_phys_ports);
*buf = val;
}
+ lan966x_ptp_rxtstamp(lan966x, skb, timestamp);
skb->protocol = eth_type_trans(skb, dev);
if (lan966x->bridge_mask & BIT(src_port))
return dev_err_probe(&pdev->dev, err, "Unable to use ana irq");
}
+ lan966x->ptp_irq = platform_get_irq_byname(pdev, "ptp");
+ if (lan966x->ptp_irq > 0) {
+ err = devm_request_threaded_irq(&pdev->dev, lan966x->ptp_irq, NULL,
+ lan966x_ptp_irq_handler, IRQF_ONESHOT,
+ "ptp irq", lan966x);
+ if (err)
+ return dev_err_probe(&pdev->dev, err, "Unable to use ptp irq");
+
+ lan966x->ptp = 1;
+ }
+
/* init switch */
lan966x_init(lan966x);
lan966x_stats_init(lan966x);
if (err)
goto cleanup_ports;
+ err = lan966x_ptp_init(lan966x);
+ if (err)
+ goto cleanup_fdb;
+
return 0;
+cleanup_fdb:
+ lan966x_fdb_deinit(lan966x);
+
cleanup_ports:
fwnode_handle_put(portnp);
lan966x_mac_purge_entries(lan966x);
lan966x_mdb_deinit(lan966x);
lan966x_fdb_deinit(lan966x);
+ lan966x_ptp_deinit(lan966x);
return 0;
}
#include <linux/jiffies.h>
#include <linux/phy.h>
#include <linux/phylink.h>
+#include <linux/ptp_clock_kernel.h>
#include <net/switchdev.h>
#include "lan966x_regs.h"
#define LAN966X_SPEED_100 2
#define LAN966X_SPEED_10 3
+#define LAN966X_PHC_COUNT 3
+#define LAN966X_PHC_PORT 0
+
+#define IFH_REW_OP_NOOP 0x0
+#define IFH_REW_OP_ONE_STEP_PTP 0x3
+#define IFH_REW_OP_TWO_STEP_PTP 0x4
+
/* MAC table entry types.
* ENTRYTYPE_NORMAL is subject to aging.
* ENTRYTYPE_LOCKED is not subject to aging.
char name[ETH_GSTRING_LEN];
};
+struct lan966x_phc {
+ struct ptp_clock *clock;
+ struct ptp_clock_info info;
+ struct hwtstamp_config hwtstamp_config;
+ struct lan966x *lan966x;
+ u8 index;
+};
+
+struct lan966x_skb_cb {
+ u8 rew_op;
+ u16 ts_id;
+ unsigned long jiffies;
+};
+
+#define LAN966X_PTP_TIMEOUT msecs_to_jiffies(10)
+#define LAN966X_SKB_CB(skb) \
+ ((struct lan966x_skb_cb *)((skb)->cb))
+
struct lan966x {
struct device *dev;
/* interrupts */
int xtr_irq;
int ana_irq;
+ int ptp_irq;
/* worqueue for fdb */
struct workqueue_struct *fdb_work;
/* mdb */
struct list_head mdb_entries;
struct list_head pgid_entries;
+
+ /* ptp */
+ bool ptp;
+ struct lan966x_phc phc[LAN966X_PHC_COUNT];
+ spinlock_t ptp_clock_lock; /* lock for phc */
+ spinlock_t ptp_ts_id_lock; /* lock for ts_id */
+ struct mutex ptp_lock; /* lock for ptp interface state */
+ u16 ptp_skbs;
};
struct lan966x_port_config {
struct phylink *phylink;
struct phy *serdes;
struct fwnode_handle *fwnode;
+
+ u8 ptp_cmd;
+ u16 ts_id;
+ struct sk_buff_head tx_skbs;
};
extern const struct phylink_mac_ops lan966x_phylink_mac_ops;
void lan966x_mdb_erase_entries(struct lan966x *lan966x, u16 vid);
void lan966x_mdb_write_entries(struct lan966x *lan966x, u16 vid);
+int lan966x_ptp_init(struct lan966x *lan966x);
+void lan966x_ptp_deinit(struct lan966x *lan966x);
+int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr);
+int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr);
+void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb,
+ u64 timestamp);
+int lan966x_ptp_txtstamp_request(struct lan966x_port *port,
+ struct sk_buff *skb);
+void lan966x_ptp_txtstamp_release(struct lan966x_port *port,
+ struct sk_buff *skb);
+irqreturn_t lan966x_ptp_irq_handler(int irq, void *args);
+
static inline void __iomem *lan_addr(void __iomem *base[],
int id, int tinst, int tcnt,
int gbase, int ginst,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/ptp_classify.h>
+
+#include "lan966x_main.h"
+
+#define LAN966X_MAX_PTP_ID 512
+
+/* Represents 1ppm adjustment in 2^59 format with 6.037735849ns as reference
+ * The value is calculated as following: (1/1000000)/((2^-59)/6.037735849)
+ */
+#define LAN966X_1PPM_FORMAT 3480517749723LL
+
+/* Represents 1ppb adjustment in 2^29 format with 6.037735849ns as reference
+ * The value is calculated as following: (1/1000000000)/((2^59)/6.037735849)
+ */
+#define LAN966X_1PPB_FORMAT 3480517749LL
+
+#define TOD_ACC_PIN 0x5
+
+enum {
+ PTP_PIN_ACTION_IDLE = 0,
+ PTP_PIN_ACTION_LOAD,
+ PTP_PIN_ACTION_SAVE,
+ PTP_PIN_ACTION_CLOCK,
+ PTP_PIN_ACTION_DELTA,
+ PTP_PIN_ACTION_TOD
+};
+
+static u64 lan966x_ptp_get_nominal_value(void)
+{
+ u64 res = 0x304d2df1;
+
+ res <<= 32;
+ return res;
+}
+
+int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr)
+{
+ struct lan966x *lan966x = port->lan966x;
+ struct hwtstamp_config cfg;
+ struct lan966x_phc *phc;
+
+ /* For now don't allow to run ptp on ports that are part of a bridge,
+ * because in case of transparent clock the HW will still forward the
+ * frames, so there would be duplicate frames
+ */
+ if (lan966x->bridge_mask & BIT(port->chip_port))
+ return -EINVAL;
+
+ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+ return -EFAULT;
+
+ switch (cfg.tx_type) {
+ case HWTSTAMP_TX_ON:
+ port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP;
+ break;
+ case HWTSTAMP_TX_ONESTEP_SYNC:
+ port->ptp_cmd = IFH_REW_OP_ONE_STEP_PTP;
+ break;
+ case HWTSTAMP_TX_OFF:
+ port->ptp_cmd = IFH_REW_OP_NOOP;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ switch (cfg.rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ break;
+ case HWTSTAMP_FILTER_ALL:
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ case HWTSTAMP_FILTER_NTP_ALL:
+ cfg.rx_filter = HWTSTAMP_FILTER_ALL;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ /* Commit back the result & save it */
+ mutex_lock(&lan966x->ptp_lock);
+ phc = &lan966x->phc[LAN966X_PHC_PORT];
+ memcpy(&phc->hwtstamp_config, &cfg, sizeof(cfg));
+ mutex_unlock(&lan966x->ptp_lock);
+
+ return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
+int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr)
+{
+ struct lan966x *lan966x = port->lan966x;
+ struct lan966x_phc *phc;
+
+ phc = &lan966x->phc[LAN966X_PHC_PORT];
+ return copy_to_user(ifr->ifr_data, &phc->hwtstamp_config,
+ sizeof(phc->hwtstamp_config)) ? -EFAULT : 0;
+}
+
+static int lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb)
+{
+ struct ptp_header *header;
+ u8 msgtype;
+ int type;
+
+ if (port->ptp_cmd == IFH_REW_OP_NOOP)
+ return IFH_REW_OP_NOOP;
+
+ type = ptp_classify_raw(skb);
+ if (type == PTP_CLASS_NONE)
+ return IFH_REW_OP_NOOP;
+
+ header = ptp_parse_header(skb, type);
+ if (!header)
+ return IFH_REW_OP_NOOP;
+
+ if (port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP)
+ return IFH_REW_OP_TWO_STEP_PTP;
+
+ /* If it is sync and run 1 step then set the correct operation,
+ * otherwise run as 2 step
+ */
+ msgtype = ptp_get_msgtype(header, type);
+ if ((msgtype & 0xf) == 0)
+ return IFH_REW_OP_ONE_STEP_PTP;
+
+ return IFH_REW_OP_TWO_STEP_PTP;
+}
+
+static void lan966x_ptp_txtstamp_old_release(struct lan966x_port *port)
+{
+ struct sk_buff *skb, *skb_tmp;
+ unsigned long flags;
+
+ spin_lock_irqsave(&port->tx_skbs.lock, flags);
+ skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) {
+ if time_after(LAN966X_SKB_CB(skb)->jiffies + LAN966X_PTP_TIMEOUT,
+ jiffies)
+ break;
+
+ __skb_unlink(skb, &port->tx_skbs);
+ dev_kfree_skb_any(skb);
+ }
+ spin_unlock_irqrestore(&port->tx_skbs.lock, flags);
+}
+
+int lan966x_ptp_txtstamp_request(struct lan966x_port *port,
+ struct sk_buff *skb)
+{
+ struct lan966x *lan966x = port->lan966x;
+ unsigned long flags;
+ u8 rew_op;
+
+ rew_op = lan966x_ptp_classify(port, skb);
+ LAN966X_SKB_CB(skb)->rew_op = rew_op;
+
+ if (rew_op != IFH_REW_OP_TWO_STEP_PTP)
+ return 0;
+
+ lan966x_ptp_txtstamp_old_release(port);
+
+ spin_lock_irqsave(&lan966x->ptp_ts_id_lock, flags);
+ if (lan966x->ptp_skbs == LAN966X_MAX_PTP_ID) {
+ spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags);
+ return -EBUSY;
+ }
+
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+ skb_queue_tail(&port->tx_skbs, skb);
+ LAN966X_SKB_CB(skb)->ts_id = port->ts_id;
+ LAN966X_SKB_CB(skb)->jiffies = jiffies;
+
+ lan966x->ptp_skbs++;
+ port->ts_id++;
+ if (port->ts_id == LAN966X_MAX_PTP_ID)
+ port->ts_id = 0;
+
+ spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags);
+
+ return 0;
+}
+
+void lan966x_ptp_txtstamp_release(struct lan966x_port *port,
+ struct sk_buff *skb)
+{
+ struct lan966x *lan966x = port->lan966x;
+ unsigned long flags;
+
+ spin_lock_irqsave(&lan966x->ptp_ts_id_lock, flags);
+ port->ts_id--;
+ lan966x->ptp_skbs--;
+ skb_unlink(skb, &port->tx_skbs);
+ spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags);
+}
+
+static void lan966x_get_hwtimestamp(struct lan966x *lan966x,
+ struct timespec64 *ts,
+ u32 nsec)
+{
+ /* Read current PTP time to get seconds */
+ unsigned long flags;
+ u32 curr_nsec;
+
+ spin_lock_irqsave(&lan966x->ptp_clock_lock, flags);
+
+ lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_SAVE) |
+ PTP_PIN_CFG_PIN_DOM_SET(LAN966X_PHC_PORT) |
+ PTP_PIN_CFG_PIN_SYNC_SET(0),
+ PTP_PIN_CFG_PIN_ACTION |
+ PTP_PIN_CFG_PIN_DOM |
+ PTP_PIN_CFG_PIN_SYNC,
+ lan966x, PTP_PIN_CFG(TOD_ACC_PIN));
+
+ ts->tv_sec = lan_rd(lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN));
+ curr_nsec = lan_rd(lan966x, PTP_TOD_NSEC(TOD_ACC_PIN));
+
+ ts->tv_nsec = nsec;
+
+ /* Sec has incremented since the ts was registered */
+ if (curr_nsec < nsec)
+ ts->tv_sec--;
+
+ spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags);
+}
+
+irqreturn_t lan966x_ptp_irq_handler(int irq, void *args)
+{
+ int budget = LAN966X_MAX_PTP_ID;
+ struct lan966x *lan966x = args;
+
+ while (budget--) {
+ struct sk_buff *skb, *skb_tmp, *skb_match = NULL;
+ struct skb_shared_hwtstamps shhwtstamps;
+ struct lan966x_port *port;
+ struct timespec64 ts;
+ unsigned long flags;
+ u32 val, id, txport;
+ u32 delay;
+
+ val = lan_rd(lan966x, PTP_TWOSTEP_CTRL);
+
+ /* Check if a timestamp can be retrieved */
+ if (!(val & PTP_TWOSTEP_CTRL_VLD))
+ break;
+
+ WARN_ON(val & PTP_TWOSTEP_CTRL_OVFL);
+
+ if (!(val & PTP_TWOSTEP_CTRL_STAMP_TX))
+ continue;
+
+ /* Retrieve the ts Tx port */
+ txport = PTP_TWOSTEP_CTRL_STAMP_PORT_GET(val);
+
+ /* Retrieve its associated skb */
+ port = lan966x->ports[txport];
+
+ /* Retrieve the delay */
+ delay = lan_rd(lan966x, PTP_TWOSTEP_STAMP);
+ delay = PTP_TWOSTEP_STAMP_STAMP_NSEC_GET(delay);
+
+ /* Get next timestamp from fifo, which needs to be the
+ * rx timestamp which represents the id of the frame
+ */
+ lan_rmw(PTP_TWOSTEP_CTRL_NXT_SET(1),
+ PTP_TWOSTEP_CTRL_NXT,
+ lan966x, PTP_TWOSTEP_CTRL);
+
+ val = lan_rd(lan966x, PTP_TWOSTEP_CTRL);
+
+ /* Check if a timestamp can be retried */
+ if (!(val & PTP_TWOSTEP_CTRL_VLD))
+ break;
+
+ /* Read RX timestamping to get the ID */
+ id = lan_rd(lan966x, PTP_TWOSTEP_STAMP);
+
+ spin_lock_irqsave(&port->tx_skbs.lock, flags);
+ skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) {
+ if (LAN966X_SKB_CB(skb)->ts_id != id)
+ continue;
+
+ __skb_unlink(skb, &port->tx_skbs);
+ skb_match = skb;
+ break;
+ }
+ spin_unlock_irqrestore(&port->tx_skbs.lock, flags);
+
+ /* Next ts */
+ lan_rmw(PTP_TWOSTEP_CTRL_NXT_SET(1),
+ PTP_TWOSTEP_CTRL_NXT,
+ lan966x, PTP_TWOSTEP_CTRL);
+
+ if (WARN_ON(!skb_match))
+ continue;
+
+ spin_lock(&lan966x->ptp_ts_id_lock);
+ lan966x->ptp_skbs--;
+ spin_unlock(&lan966x->ptp_ts_id_lock);
+
+ /* Get the h/w timestamp */
+ lan966x_get_hwtimestamp(lan966x, &ts, delay);
+
+ /* Set the timestamp into the skb */
+ shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec);
+ skb_tstamp_tx(skb_match, &shhwtstamps);
+
+ dev_kfree_skb_any(skb_match);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static int lan966x_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+ struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info);
+ struct lan966x *lan966x = phc->lan966x;
+ unsigned long flags;
+ bool neg_adj = 0;
+ u64 tod_inc;
+ u64 ref;
+
+ if (!scaled_ppm)
+ return 0;
+
+ if (scaled_ppm < 0) {
+ neg_adj = 1;
+ scaled_ppm = -scaled_ppm;
+ }
+
+ tod_inc = lan966x_ptp_get_nominal_value();
+
+ /* The multiplication is split in 2 separate additions because of
+ * overflow issues. If scaled_ppm with 16bit fractional part was bigger
+ * than 20ppm then we got overflow.
+ */
+ ref = LAN966X_1PPM_FORMAT * (scaled_ppm >> 16);
+ ref += (LAN966X_1PPM_FORMAT * (0xffff & scaled_ppm)) >> 16;
+ tod_inc = neg_adj ? tod_inc - ref : tod_inc + ref;
+
+ spin_lock_irqsave(&lan966x->ptp_clock_lock, flags);
+
+ lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(1 << BIT(phc->index)),
+ PTP_DOM_CFG_CLKCFG_DIS,
+ lan966x, PTP_DOM_CFG);
+
+ lan_wr((u32)tod_inc & 0xFFFFFFFF, lan966x,
+ PTP_CLK_PER_CFG(phc->index, 0));
+ lan_wr((u32)(tod_inc >> 32), lan966x,
+ PTP_CLK_PER_CFG(phc->index, 1));
+
+ lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0),
+ PTP_DOM_CFG_CLKCFG_DIS,
+ lan966x, PTP_DOM_CFG);
+
+ spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags);
+
+ return 0;
+}
+
+static int lan966x_ptp_settime64(struct ptp_clock_info *ptp,
+ const struct timespec64 *ts)
+{
+ struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info);
+ struct lan966x *lan966x = phc->lan966x;
+ unsigned long flags;
+
+ spin_lock_irqsave(&lan966x->ptp_clock_lock, flags);
+
+ /* Must be in IDLE mode before the time can be loaded */
+ lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_IDLE) |
+ PTP_PIN_CFG_PIN_DOM_SET(phc->index) |
+ PTP_PIN_CFG_PIN_SYNC_SET(0),
+ PTP_PIN_CFG_PIN_ACTION |
+ PTP_PIN_CFG_PIN_DOM |
+ PTP_PIN_CFG_PIN_SYNC,
+ lan966x, PTP_PIN_CFG(TOD_ACC_PIN));
+
+ /* Set new value */
+ lan_wr(PTP_TOD_SEC_MSB_TOD_SEC_MSB_SET(upper_32_bits(ts->tv_sec)),
+ lan966x, PTP_TOD_SEC_MSB(TOD_ACC_PIN));
+ lan_wr(lower_32_bits(ts->tv_sec),
+ lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN));
+ lan_wr(ts->tv_nsec, lan966x, PTP_TOD_NSEC(TOD_ACC_PIN));
+
+ /* Apply new values */
+ lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_LOAD) |
+ PTP_PIN_CFG_PIN_DOM_SET(phc->index) |
+ PTP_PIN_CFG_PIN_SYNC_SET(0),
+ PTP_PIN_CFG_PIN_ACTION |
+ PTP_PIN_CFG_PIN_DOM |
+ PTP_PIN_CFG_PIN_SYNC,
+ lan966x, PTP_PIN_CFG(TOD_ACC_PIN));
+
+ spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags);
+
+ return 0;
+}
+
+static int lan966x_ptp_gettime64(struct ptp_clock_info *ptp,
+ struct timespec64 *ts)
+{
+ struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info);
+ struct lan966x *lan966x = phc->lan966x;
+ unsigned long flags;
+ time64_t s;
+ s64 ns;
+
+ spin_lock_irqsave(&lan966x->ptp_clock_lock, flags);
+
+ lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_SAVE) |
+ PTP_PIN_CFG_PIN_DOM_SET(phc->index) |
+ PTP_PIN_CFG_PIN_SYNC_SET(0),
+ PTP_PIN_CFG_PIN_ACTION |
+ PTP_PIN_CFG_PIN_DOM |
+ PTP_PIN_CFG_PIN_SYNC,
+ lan966x, PTP_PIN_CFG(TOD_ACC_PIN));
+
+ s = lan_rd(lan966x, PTP_TOD_SEC_MSB(TOD_ACC_PIN));
+ s <<= 32;
+ s |= lan_rd(lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN));
+ ns = lan_rd(lan966x, PTP_TOD_NSEC(TOD_ACC_PIN));
+ ns &= PTP_TOD_NSEC_TOD_NSEC;
+
+ spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags);
+
+ /* Deal with negative values */
+ if ((ns & 0xFFFFFFF0) == 0x3FFFFFF0) {
+ s--;
+ ns &= 0xf;
+ ns += 999999984;
+ }
+
+ set_normalized_timespec64(ts, s, ns);
+ return 0;
+}
+
+static int lan966x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info);
+ struct lan966x *lan966x = phc->lan966x;
+
+ if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&lan966x->ptp_clock_lock, flags);
+
+ /* Must be in IDLE mode before the time can be loaded */
+ lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_IDLE) |
+ PTP_PIN_CFG_PIN_DOM_SET(phc->index) |
+ PTP_PIN_CFG_PIN_SYNC_SET(0),
+ PTP_PIN_CFG_PIN_ACTION |
+ PTP_PIN_CFG_PIN_DOM |
+ PTP_PIN_CFG_PIN_SYNC,
+ lan966x, PTP_PIN_CFG(TOD_ACC_PIN));
+
+ lan_wr(PTP_TOD_NSEC_TOD_NSEC_SET(delta),
+ lan966x, PTP_TOD_NSEC(TOD_ACC_PIN));
+
+ /* Adjust time with the value of PTP_TOD_NSEC */
+ lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_DELTA) |
+ PTP_PIN_CFG_PIN_DOM_SET(phc->index) |
+ PTP_PIN_CFG_PIN_SYNC_SET(0),
+ PTP_PIN_CFG_PIN_ACTION |
+ PTP_PIN_CFG_PIN_DOM |
+ PTP_PIN_CFG_PIN_SYNC,
+ lan966x, PTP_PIN_CFG(TOD_ACC_PIN));
+
+ spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags);
+ } else {
+ /* Fall back using lan966x_ptp_settime64 which is not exact */
+ struct timespec64 ts;
+ u64 now;
+
+ lan966x_ptp_gettime64(ptp, &ts);
+
+ now = ktime_to_ns(timespec64_to_ktime(ts));
+ ts = ns_to_timespec64(now + delta);
+
+ lan966x_ptp_settime64(ptp, &ts);
+ }
+
+ return 0;
+}
+
+static struct ptp_clock_info lan966x_ptp_clock_info = {
+ .owner = THIS_MODULE,
+ .name = "lan966x ptp",
+ .max_adj = 200000,
+ .gettime64 = lan966x_ptp_gettime64,
+ .settime64 = lan966x_ptp_settime64,
+ .adjtime = lan966x_ptp_adjtime,
+ .adjfine = lan966x_ptp_adjfine,
+};
+
+static int lan966x_ptp_phc_init(struct lan966x *lan966x,
+ int index,
+ struct ptp_clock_info *clock_info)
+{
+ struct lan966x_phc *phc = &lan966x->phc[index];
+
+ phc->info = *clock_info;
+ phc->clock = ptp_clock_register(&phc->info, lan966x->dev);
+ if (IS_ERR(phc->clock))
+ return PTR_ERR(phc->clock);
+
+ phc->index = index;
+ phc->lan966x = lan966x;
+
+ /* PTP Rx stamping is always enabled. */
+ phc->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+
+ return 0;
+}
+
+int lan966x_ptp_init(struct lan966x *lan966x)
+{
+ u64 tod_adj = lan966x_ptp_get_nominal_value();
+ struct lan966x_port *port;
+ int err, i;
+
+ if (!lan966x->ptp)
+ return 0;
+
+ for (i = 0; i < LAN966X_PHC_COUNT; ++i) {
+ err = lan966x_ptp_phc_init(lan966x, i, &lan966x_ptp_clock_info);
+ if (err)
+ return err;
+ }
+
+ spin_lock_init(&lan966x->ptp_clock_lock);
+ spin_lock_init(&lan966x->ptp_ts_id_lock);
+ mutex_init(&lan966x->ptp_lock);
+
+ /* Disable master counters */
+ lan_wr(PTP_DOM_CFG_ENA_SET(0), lan966x, PTP_DOM_CFG);
+
+ /* Configure the nominal TOD increment per clock cycle */
+ lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0x7),
+ PTP_DOM_CFG_CLKCFG_DIS,
+ lan966x, PTP_DOM_CFG);
+
+ for (i = 0; i < LAN966X_PHC_COUNT; ++i) {
+ lan_wr((u32)tod_adj & 0xFFFFFFFF, lan966x,
+ PTP_CLK_PER_CFG(i, 0));
+ lan_wr((u32)(tod_adj >> 32), lan966x,
+ PTP_CLK_PER_CFG(i, 1));
+ }
+
+ lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0),
+ PTP_DOM_CFG_CLKCFG_DIS,
+ lan966x, PTP_DOM_CFG);
+
+ /* Enable master counters */
+ lan_wr(PTP_DOM_CFG_ENA_SET(0x7), lan966x, PTP_DOM_CFG);
+
+ for (i = 0; i < lan966x->num_phys_ports; i++) {
+ port = lan966x->ports[i];
+ if (!port)
+ continue;
+
+ skb_queue_head_init(&port->tx_skbs);
+ }
+
+ return 0;
+}
+
+void lan966x_ptp_deinit(struct lan966x *lan966x)
+{
+ struct lan966x_port *port;
+ int i;
+
+ for (i = 0; i < lan966x->num_phys_ports; i++) {
+ port = lan966x->ports[i];
+ if (!port)
+ continue;
+
+ skb_queue_purge(&port->tx_skbs);
+ }
+
+ for (i = 0; i < LAN966X_PHC_COUNT; ++i)
+ ptp_clock_unregister(lan966x->phc[i].clock);
+}
+
+void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb,
+ u64 timestamp)
+{
+ struct skb_shared_hwtstamps *shhwtstamps;
+ struct lan966x_phc *phc;
+ struct timespec64 ts;
+ u64 full_ts_in_ns;
+
+ if (!lan966x->ptp)
+ return;
+
+ phc = &lan966x->phc[LAN966X_PHC_PORT];
+ lan966x_ptp_gettime64(&phc->info, &ts);
+
+ /* Drop the sub-ns precision */
+ timestamp = timestamp >> 2;
+ if (ts.tv_nsec < timestamp)
+ ts.tv_sec--;
+ ts.tv_nsec = timestamp;
+ full_ts_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec);
+
+ shhwtstamps = skb_hwtstamps(skb);
+ shhwtstamps->hwtstamp = full_ts_in_ns;
+}
TARGET_DEV = 13,
TARGET_GCB = 27,
TARGET_ORG = 36,
+ TARGET_PTP = 41,
TARGET_QS = 42,
TARGET_QSYS = 46,
TARGET_REW = 47,
#define DEV_PCS1G_STICKY_LINK_DOWN_STICKY_GET(x)\
FIELD_GET(DEV_PCS1G_STICKY_LINK_DOWN_STICKY, x)
+/* PTP:PTP_CFG:PTP_DOM_CFG */
+#define PTP_DOM_CFG __REG(TARGET_PTP, 0, 1, 512, 0, 1, 16, 12, 0, 1, 4)
+
+#define PTP_DOM_CFG_ENA GENMASK(11, 9)
+#define PTP_DOM_CFG_ENA_SET(x)\
+ FIELD_PREP(PTP_DOM_CFG_ENA, x)
+#define PTP_DOM_CFG_ENA_GET(x)\
+ FIELD_GET(PTP_DOM_CFG_ENA, x)
+
+#define PTP_DOM_CFG_CLKCFG_DIS GENMASK(2, 0)
+#define PTP_DOM_CFG_CLKCFG_DIS_SET(x)\
+ FIELD_PREP(PTP_DOM_CFG_CLKCFG_DIS, x)
+#define PTP_DOM_CFG_CLKCFG_DIS_GET(x)\
+ FIELD_GET(PTP_DOM_CFG_CLKCFG_DIS, x)
+
+/* PTP:PTP_TOD_DOMAINS:CLK_PER_CFG */
+#define PTP_CLK_PER_CFG(g, r) __REG(TARGET_PTP, 0, 1, 528, g, 3, 28, 0, r, 2, 4)
+
+/* PTP:PTP_PINS:PTP_PIN_CFG */
+#define PTP_PIN_CFG(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 0, 0, 1, 4)
+
+#define PTP_PIN_CFG_PIN_ACTION GENMASK(29, 27)
+#define PTP_PIN_CFG_PIN_ACTION_SET(x)\
+ FIELD_PREP(PTP_PIN_CFG_PIN_ACTION, x)
+#define PTP_PIN_CFG_PIN_ACTION_GET(x)\
+ FIELD_GET(PTP_PIN_CFG_PIN_ACTION, x)
+
+#define PTP_PIN_CFG_PIN_SYNC GENMASK(26, 25)
+#define PTP_PIN_CFG_PIN_SYNC_SET(x)\
+ FIELD_PREP(PTP_PIN_CFG_PIN_SYNC, x)
+#define PTP_PIN_CFG_PIN_SYNC_GET(x)\
+ FIELD_GET(PTP_PIN_CFG_PIN_SYNC, x)
+
+#define PTP_PIN_CFG_PIN_DOM GENMASK(17, 16)
+#define PTP_PIN_CFG_PIN_DOM_SET(x)\
+ FIELD_PREP(PTP_PIN_CFG_PIN_DOM, x)
+#define PTP_PIN_CFG_PIN_DOM_GET(x)\
+ FIELD_GET(PTP_PIN_CFG_PIN_DOM, x)
+
+/* PTP:PTP_PINS:PTP_TOD_SEC_MSB */
+#define PTP_TOD_SEC_MSB(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 4, 0, 1, 4)
+
+#define PTP_TOD_SEC_MSB_TOD_SEC_MSB GENMASK(15, 0)
+#define PTP_TOD_SEC_MSB_TOD_SEC_MSB_SET(x)\
+ FIELD_PREP(PTP_TOD_SEC_MSB_TOD_SEC_MSB, x)
+#define PTP_TOD_SEC_MSB_TOD_SEC_MSB_GET(x)\
+ FIELD_GET(PTP_TOD_SEC_MSB_TOD_SEC_MSB, x)
+
+/* PTP:PTP_PINS:PTP_TOD_SEC_LSB */
+#define PTP_TOD_SEC_LSB(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 8, 0, 1, 4)
+
+/* PTP:PTP_PINS:PTP_TOD_NSEC */
+#define PTP_TOD_NSEC(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 12, 0, 1, 4)
+
+#define PTP_TOD_NSEC_TOD_NSEC GENMASK(29, 0)
+#define PTP_TOD_NSEC_TOD_NSEC_SET(x)\
+ FIELD_PREP(PTP_TOD_NSEC_TOD_NSEC, x)
+#define PTP_TOD_NSEC_TOD_NSEC_GET(x)\
+ FIELD_GET(PTP_TOD_NSEC_TOD_NSEC, x)
+
+/* PTP:PTP_TS_FIFO:PTP_TWOSTEP_CTRL */
+#define PTP_TWOSTEP_CTRL __REG(TARGET_PTP, 0, 1, 612, 0, 1, 12, 0, 0, 1, 4)
+
+#define PTP_TWOSTEP_CTRL_NXT BIT(11)
+#define PTP_TWOSTEP_CTRL_NXT_SET(x)\
+ FIELD_PREP(PTP_TWOSTEP_CTRL_NXT, x)
+#define PTP_TWOSTEP_CTRL_NXT_GET(x)\
+ FIELD_GET(PTP_TWOSTEP_CTRL_NXT, x)
+
+#define PTP_TWOSTEP_CTRL_VLD BIT(10)
+#define PTP_TWOSTEP_CTRL_VLD_SET(x)\
+ FIELD_PREP(PTP_TWOSTEP_CTRL_VLD, x)
+#define PTP_TWOSTEP_CTRL_VLD_GET(x)\
+ FIELD_GET(PTP_TWOSTEP_CTRL_VLD, x)
+
+#define PTP_TWOSTEP_CTRL_STAMP_TX BIT(9)
+#define PTP_TWOSTEP_CTRL_STAMP_TX_SET(x)\
+ FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_TX, x)
+#define PTP_TWOSTEP_CTRL_STAMP_TX_GET(x)\
+ FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_TX, x)
+
+#define PTP_TWOSTEP_CTRL_STAMP_PORT GENMASK(8, 1)
+#define PTP_TWOSTEP_CTRL_STAMP_PORT_SET(x)\
+ FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_PORT, x)
+#define PTP_TWOSTEP_CTRL_STAMP_PORT_GET(x)\
+ FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_PORT, x)
+
+#define PTP_TWOSTEP_CTRL_OVFL BIT(0)
+#define PTP_TWOSTEP_CTRL_OVFL_SET(x)\
+ FIELD_PREP(PTP_TWOSTEP_CTRL_OVFL, x)
+#define PTP_TWOSTEP_CTRL_OVFL_GET(x)\
+ FIELD_GET(PTP_TWOSTEP_CTRL_OVFL, x)
+
+/* PTP:PTP_TS_FIFO:PTP_TWOSTEP_STAMP */
+#define PTP_TWOSTEP_STAMP __REG(TARGET_PTP, 0, 1, 612, 0, 1, 12, 4, 0, 1, 4)
+
+#define PTP_TWOSTEP_STAMP_STAMP_NSEC GENMASK(31, 2)
+#define PTP_TWOSTEP_STAMP_STAMP_NSEC_SET(x)\
+ FIELD_PREP(PTP_TWOSTEP_STAMP_STAMP_NSEC, x)
+#define PTP_TWOSTEP_STAMP_STAMP_NSEC_GET(x)\
+ FIELD_GET(PTP_TWOSTEP_STAMP_STAMP_NSEC, x)
+
/* DEVCPU_QS:XTR:XTR_GRP_CFG */
#define QS_XTR_GRP_CFG(r) __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 0, r, 2, 4)
return PTR_ERR(phylink);
spx5_port->phylink = phylink;
- phylink_set_pcs(phylink, &spx5_port->phylink_pcs);
return 0;
}
return false;
}
+static struct phylink_pcs *
+sparx5_phylink_mac_select_pcs(struct phylink_config *config,
+ phy_interface_t interface)
+{
+ struct sparx5_port *port = netdev_priv(to_net_dev(config->dev));
+
+ return &port->phylink_pcs;
+}
+
static void sparx5_phylink_mac_config(struct phylink_config *config,
unsigned int mode,
const struct phylink_link_state *state)
const struct phylink_mac_ops sparx5_phylink_mac_ops = {
.validate = phylink_generic_validate,
+ .mac_select_pcs = sparx5_phylink_mac_select_pcs,
.mac_config = sparx5_phylink_mac_config,
.mac_link_down = sparx5_phylink_mac_link_down,
.mac_link_up = sparx5_phylink_mac_link_up,
struct gdma_context *gc = gd->gdma_context;
struct hw_channel_context *hwc;
u32 length = gmi->length;
- u32 req_msg_size;
+ size_t req_msg_size;
int err;
int i;
return -EINVAL;
hwc = gc->hwc.driver_data;
- req_msg_size = sizeof(*req) + num_page * sizeof(u64);
+ req_msg_size = struct_size(req, page_addr_list, num_page);
if (req_msg_size > hwc->max_req_msg_size)
return -EINVAL;
#define MAX_PORTS_IN_MANA_DEV 256
-struct mana_stats {
+struct mana_stats_rx {
+ u64 packets;
+ u64 bytes;
+ u64 xdp_drop;
+ u64 xdp_tx;
+ struct u64_stats_sync syncp;
+};
+
+struct mana_stats_tx {
u64 packets;
u64 bytes;
struct u64_stats_sync syncp;
atomic_t pending_sends;
- struct mana_stats stats;
+ struct mana_stats_tx stats;
};
/* skb data and frags dma mappings */
u32 buf_index;
- struct mana_stats stats;
+ struct mana_stats_rx stats;
struct bpf_prog __rcu *bpf_prog;
struct xdp_rxq_info xdp_rxq;
+ struct page *xdp_save_page;
/* MUST BE THE LAST MEMBER:
* Each receive buffer has an associated mana_recv_buf_oob.
bool ipv4 = false, ipv6 = false;
struct mana_tx_package pkg = {};
struct netdev_queue *net_txq;
- struct mana_stats *tx_stats;
+ struct mana_stats_tx *tx_stats;
struct gdma_queue *gdma_sq;
unsigned int csum_type;
struct mana_txq *txq;
{
struct mana_port_context *apc = netdev_priv(ndev);
unsigned int num_queues = apc->num_queues;
- struct mana_stats *stats;
+ struct mana_stats_rx *rx_stats;
+ struct mana_stats_tx *tx_stats;
unsigned int start;
u64 packets, bytes;
int q;
netdev_stats_to_stats64(st, &ndev->stats);
for (q = 0; q < num_queues; q++) {
- stats = &apc->rxqs[q]->stats;
+ rx_stats = &apc->rxqs[q]->stats;
do {
- start = u64_stats_fetch_begin_irq(&stats->syncp);
- packets = stats->packets;
- bytes = stats->bytes;
- } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+ start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+ packets = rx_stats->packets;
+ bytes = rx_stats->bytes;
+ } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
st->rx_packets += packets;
st->rx_bytes += bytes;
}
for (q = 0; q < num_queues; q++) {
- stats = &apc->tx_qp[q].txq.stats;
+ tx_stats = &apc->tx_qp[q].txq.stats;
do {
- start = u64_stats_fetch_begin_irq(&stats->syncp);
- packets = stats->packets;
- bytes = stats->bytes;
- } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+ start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+ packets = tx_stats->packets;
+ bytes = tx_stats->bytes;
+ } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
st->tx_packets += packets;
st->tx_bytes += bytes;
static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
struct mana_rxq *rxq)
{
- struct mana_stats *rx_stats = &rxq->stats;
+ struct mana_stats_rx *rx_stats = &rxq->stats;
struct net_device *ndev = rxq->ndev;
uint pkt_len = cqe->ppi[0].pkt_len;
u16 rxq_idx = rxq->rxq_idx;
act = mana_run_xdp(ndev, rxq, &xdp, buf_va, pkt_len);
if (act != XDP_PASS && act != XDP_TX)
- goto drop;
+ goto drop_xdp;
skb = mana_build_skb(buf_va, pkt_len, &xdp);
skb_set_hash(skb, hash_value, PKT_HASH_TYPE_L3);
}
+ u64_stats_update_begin(&rx_stats->syncp);
+ rx_stats->packets++;
+ rx_stats->bytes += pkt_len;
+
+ if (act == XDP_TX)
+ rx_stats->xdp_tx++;
+ u64_stats_update_end(&rx_stats->syncp);
+
if (act == XDP_TX) {
skb_set_queue_mapping(skb, rxq_idx);
mana_xdp_tx(skb, ndev);
napi_gro_receive(napi, skb);
+ return;
+
+drop_xdp:
u64_stats_update_begin(&rx_stats->syncp);
- rx_stats->packets++;
- rx_stats->bytes += pkt_len;
+ rx_stats->xdp_drop++;
u64_stats_update_end(&rx_stats->syncp);
- return;
drop:
- free_page((unsigned long)buf_va);
+ WARN_ON_ONCE(rxq->xdp_save_page);
+ rxq->xdp_save_page = virt_to_page(buf_va);
+
++ndev->stats.rx_dropped;
+
return;
}
rxbuf_oob = &rxq->rx_oobs[curr];
WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
- new_page = alloc_page(GFP_ATOMIC);
+ /* Reuse XDP dropped page if available */
+ if (rxq->xdp_save_page) {
+ new_page = rxq->xdp_save_page;
+ rxq->xdp_save_page = NULL;
+ } else {
+ new_page = alloc_page(GFP_ATOMIC);
+ }
if (new_page) {
da = dma_map_page(dev, new_page, XDP_PACKET_HEADROOM, rxq->datasize,
mana_deinit_cq(apc, &rxq->rx_cq);
+ if (rxq->xdp_save_page)
+ __free_page(rxq->xdp_save_page);
+
for (i = 0; i < rxq->num_rx_buf; i++) {
rx_oob = &rxq->rx_oobs[i];
if (stringset != ETH_SS_STATS)
return -EINVAL;
- return ARRAY_SIZE(mana_eth_stats) + num_queues * 4;
+ return ARRAY_SIZE(mana_eth_stats) + num_queues * 6;
}
static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
p += ETH_GSTRING_LEN;
sprintf(p, "rx_%d_bytes", i);
p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_%d_xdp_drop", i);
+ p += ETH_GSTRING_LEN;
+ sprintf(p, "rx_%d_xdp_tx", i);
+ p += ETH_GSTRING_LEN;
}
for (i = 0; i < num_queues; i++) {
struct mana_port_context *apc = netdev_priv(ndev);
unsigned int num_queues = apc->num_queues;
void *eth_stats = &apc->eth_stats;
- struct mana_stats *stats;
+ struct mana_stats_rx *rx_stats;
+ struct mana_stats_tx *tx_stats;
unsigned int start;
u64 packets, bytes;
+ u64 xdp_drop;
+ u64 xdp_tx;
int q, i = 0;
if (!apc->port_is_up)
data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset);
for (q = 0; q < num_queues; q++) {
- stats = &apc->rxqs[q]->stats;
+ rx_stats = &apc->rxqs[q]->stats;
do {
- start = u64_stats_fetch_begin_irq(&stats->syncp);
- packets = stats->packets;
- bytes = stats->bytes;
- } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+ start = u64_stats_fetch_begin_irq(&rx_stats->syncp);
+ packets = rx_stats->packets;
+ bytes = rx_stats->bytes;
+ xdp_drop = rx_stats->xdp_drop;
+ xdp_tx = rx_stats->xdp_tx;
+ } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start));
data[i++] = packets;
data[i++] = bytes;
+ data[i++] = xdp_drop;
+ data[i++] = xdp_tx;
}
for (q = 0; q < num_queues; q++) {
- stats = &apc->tx_qp[q].txq.stats;
+ tx_stats = &apc->tx_qp[q].txq.stats;
do {
- start = u64_stats_fetch_begin_irq(&stats->syncp);
- packets = stats->packets;
- bytes = stats->bytes;
- } while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+ start = u64_stats_fetch_begin_irq(&tx_stats->syncp);
+ packets = tx_stats->packets;
+ bytes = tx_stats->bytes;
+ } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start));
data[i++] = packets;
data[i++] = bytes;
return 0;
}
- entry = kmalloc(sizeof(*entry) + add_len, GFP_ATOMIC);
+ entry = kmalloc(struct_size(entry, ip_add, add_len), GFP_ATOMIC);
if (!entry) {
spin_unlock_bh(list_lock);
return -ENOMEM;
/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
/* Copyright (C) 2015-2018 Netronome Systems, Inc. */
-/*
- * nfp_net_ctrl.h
+/* nfp_net_ctrl.h
* Netronome network device driver: Control BAR layout
* Authors: Jakub Kicinski <jakub.kicinski@netronome.com>
* Jason McMullan <jason.mcmullan@netronome.com>
#include <linux/types.h>
-/**
- * Configuration BAR size.
+/* Configuration BAR size.
*
* The configuration BAR is 8K in size, but due to
* THB-350, 32k needs to be reserved.
*/
#define NFP_NET_CFG_BAR_SZ (32 * 1024)
-/**
- * Offset in Freelist buffer where packet starts on RX
- */
+/* Offset in Freelist buffer where packet starts on RX */
#define NFP_NET_RX_OFFSET 32
-/**
- * LSO parameters
+/* LSO parameters
* %NFP_NET_LSO_MAX_HDR_SZ: Maximum header size supported for LSO frames
* %NFP_NET_LSO_MAX_SEGS: Maximum number of segments LSO frame can produce
*/
#define NFP_NET_LSO_MAX_HDR_SZ 255
#define NFP_NET_LSO_MAX_SEGS 64
-/**
- * Prepend field types
- */
+/* Prepend field types */
#define NFP_NET_META_FIELD_SIZE 4
#define NFP_NET_META_HASH 1 /* next field carries hash type */
#define NFP_NET_META_MARK 2
#define NFP_META_PORT_ID_CTRL ~0U
-/**
- * Hash type pre-pended when a RSS hash was computed
- */
+/* Hash type pre-pended when a RSS hash was computed */
#define NFP_NET_RSS_NONE 0
#define NFP_NET_RSS_IPV4 1
#define NFP_NET_RSS_IPV6 2
#define NFP_NET_RSS_IPV6_UDP 8
#define NFP_NET_RSS_IPV6_EX_UDP 9
-/**
- * Ring counts
+/* Ring counts
* %NFP_NET_TXR_MAX: Maximum number of TX rings
* %NFP_NET_RXR_MAX: Maximum number of RX rings
*/
#define NFP_NET_TXR_MAX 64
#define NFP_NET_RXR_MAX 64
-/**
- * Read/Write config words (0x0000 - 0x002c)
+/* Read/Write config words (0x0000 - 0x002c)
* %NFP_NET_CFG_CTRL: Global control
* %NFP_NET_CFG_UPDATE: Indicate which fields are updated
* %NFP_NET_CFG_TXRS_ENABLE: Bitmask of enabled TX rings
#define NFP_NET_CFG_LSC 0x0020
#define NFP_NET_CFG_MACADDR 0x0024
-/**
- * Read-only words (0x0030 - 0x0050):
+/* Read-only words (0x0030 - 0x0050):
* %NFP_NET_CFG_VERSION: Firmware version number
* %NFP_NET_CFG_STS: Status
* %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL)
#define NFP_NET_CFG_START_TXQ 0x0048
#define NFP_NET_CFG_START_RXQ 0x004c
-/**
- * Prepend configuration
+/* Prepend configuration
*/
#define NFP_NET_CFG_RX_OFFSET 0x0050
#define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */
-/**
- * RSS capabilities
+/* RSS capabilities
* %NFP_NET_CFG_RSS_CAP_HFUNC: supported hash functions (same bits as
* %NFP_NET_CFG_RSS_HFUNC)
*/
#define NFP_NET_CFG_RSS_CAP 0x0054
#define NFP_NET_CFG_RSS_CAP_HFUNC 0xff000000
-/**
- * TLV area start
+/* TLV area start
* %NFP_NET_CFG_TLV_BASE: start anchor of the TLV area
*/
#define NFP_NET_CFG_TLV_BASE 0x0058
-/**
- * VXLAN/UDP encap configuration
+/* VXLAN/UDP encap configuration
* %NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports
* %NFP_NET_CFG_VXLAN_SZ: Size of the UDP port table in bytes
*/
#define NFP_NET_CFG_VXLAN_PORT 0x0060
#define NFP_NET_CFG_VXLAN_SZ 0x0008
-/**
- * BPF section
+/* BPF section
* %NFP_NET_CFG_BPF_ABI: BPF ABI version
* %NFP_NET_CFG_BPF_CAP: BPF capabilities
* %NFP_NET_CFG_BPF_MAX_LEN: Maximum size of JITed BPF code in bytes
#define NFP_NET_CFG_BPF_CFG_MASK 7ULL
#define NFP_NET_CFG_BPF_ADDR_MASK (~NFP_NET_CFG_BPF_CFG_MASK)
-/**
- * 40B reserved for future use (0x0098 - 0x00c0)
+/* 40B reserved for future use (0x0098 - 0x00c0)
*/
#define NFP_NET_CFG_RESERVED 0x0098
#define NFP_NET_CFG_RESERVED_SZ 0x0028
-/**
- * RSS configuration (0x0100 - 0x01ac):
+/* RSS configuration (0x0100 - 0x01ac):
* Used only when NFP_NET_CFG_CTRL_RSS is enabled
* %NFP_NET_CFG_RSS_CFG: RSS configuration word
* %NFP_NET_CFG_RSS_KEY: RSS "secret" key
NFP_NET_CFG_RSS_KEY_SZ)
#define NFP_NET_CFG_RSS_ITBL_SZ 0x80
-/**
- * TX ring configuration (0x200 - 0x800)
+/* TX ring configuration (0x200 - 0x800)
* %NFP_NET_CFG_TXR_BASE: Base offset for TX ring configuration
* %NFP_NET_CFG_TXR_ADDR: Per TX ring DMA address (8B entries)
* %NFP_NET_CFG_TXR_WB_ADDR: Per TX ring write back DMA address (8B entries)
#define NFP_NET_CFG_TXR_IRQ_MOD(_x) (NFP_NET_CFG_TXR_BASE + 0x500 + \
((_x) * 0x4))
-/**
- * RX ring configuration (0x0800 - 0x0c00)
+/* RX ring configuration (0x0800 - 0x0c00)
* %NFP_NET_CFG_RXR_BASE: Base offset for RX ring configuration
* %NFP_NET_CFG_RXR_ADDR: Per RX ring DMA address (8B entries)
* %NFP_NET_CFG_RXR_SZ: Per RX ring ring size (1B entries)
#define NFP_NET_CFG_RXR_IRQ_MOD(_x) (NFP_NET_CFG_RXR_BASE + 0x300 + \
((_x) * 0x4))
-/**
- * Interrupt Control/Cause registers (0x0c00 - 0x0d00)
+/* Interrupt Control/Cause registers (0x0c00 - 0x0d00)
* These registers are only used when MSI-X auto-masking is not
* enabled (%NFP_NET_CFG_CTRL_MSIXAUTO not set). The array is index
* by MSI-X entry and are 1B in size. If an entry is zero, the
#define NFP_NET_CFG_ICR_RXTX 0x1
#define NFP_NET_CFG_ICR_LSC 0x2
-/**
- * General device stats (0x0d00 - 0x0d90)
+/* General device stats (0x0d00 - 0x0d90)
* all counters are 64bit.
*/
#define NFP_NET_CFG_STATS_BASE 0x0d00
#define NFP_NET_CFG_STATS_APP3_FRAMES (NFP_NET_CFG_STATS_BASE + 0xc0)
#define NFP_NET_CFG_STATS_APP3_BYTES (NFP_NET_CFG_STATS_BASE + 0xc8)
-/**
- * Per ring stats (0x1000 - 0x1800)
+/* Per ring stats (0x1000 - 0x1800)
* options, 64bit per entry
* %NFP_NET_CFG_TXR_STATS: TX ring statistics (Packet and Byte count)
* %NFP_NET_CFG_RXR_STATS: RX ring statistics (Packet and Byte count)
#define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \
((_x) * 0x10))
-/**
- * General use mailbox area (0x1800 - 0x19ff)
+/* General use mailbox area (0x1800 - 0x19ff)
* 4B used for update command and 4B return code
* followed by a max of 504B of variable length value
*/
#define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET 5
#define NFP_NET_CFG_MBOX_CMD_TLV_CMSG 6
-/**
- * VLAN filtering using general use mailbox
+/* VLAN filtering using general use mailbox
* %NFP_NET_CFG_VLAN_FILTER: Base address of VLAN filter mailbox
* %NFP_NET_CFG_VLAN_FILTER_VID: VLAN ID to filter
* %NFP_NET_CFG_VLAN_FILTER_PROTO: VLAN proto to filter
#define NFP_NET_CFG_VLAN_FILTER_PROTO (NFP_NET_CFG_VLAN_FILTER + 2)
#define NFP_NET_CFG_VLAN_FILTER_SZ 0x0004
-/**
- * TLV capabilities
+/* TLV capabilities
* %NFP_NET_CFG_TLV_TYPE: Offset of type within the TLV
* %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV
* %NFP_NET_CFG_TLV_LENGTH: Offset of length within the TLV
#define NFP_NET_CFG_TLV_HEADER_TYPE 0x7fff0000
#define NFP_NET_CFG_TLV_HEADER_LENGTH 0x0000ffff
-/**
- * Capability TLV types
+/* Capability TLV types
*
* %NFP_NET_CFG_TLV_TYPE_UNKNOWN:
* Special TLV type to catch bugs, should never be encountered. Drivers should
struct device;
-/**
- * struct nfp_net_tlv_caps - parsed control BAR TLV capabilities
+/* struct nfp_net_tlv_caps - parsed control BAR TLV capabilities
* @me_freq_mhz: ME clock_freq (MHz)
* @mbox_off: vNIC mailbox area offset
* @mbox_len: vNIC mailbox area length
#ifndef _NFP_NET_SRIOV_H_
#define _NFP_NET_SRIOV_H_
-/**
- * SRIOV VF configuration.
+/* SRIOV VF configuration.
* The configuration memory begins with a mailbox region for communication with
* the firmware followed by individual VF entries.
*/
void nfp_devlink_port_type_eth_set(struct nfp_port *port);
void nfp_devlink_port_type_clear(struct nfp_port *port);
-/**
- * Mac stats (0x0000 - 0x0200)
+/* Mac stats (0x0000 - 0x0200)
* all counters are 64bit.
*/
#define NFP_MAC_STATS_BASE 0x0000
dma_size = BIT_ULL(dma_order);
nseg = DIV_ROUND_UP(max_size, chunk_size);
- chunks = kzalloc(array_size(sizeof(*chunks), nseg), GFP_KERNEL);
+ chunks = kcalloc(nseg, sizeof(*chunks), GFP_KERNEL);
if (!chunks)
return -ENOMEM;
#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002
#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003
-#define DEVCMD_TIMEOUT 10
+#define DEVCMD_TIMEOUT 5
#define IONIC_ADMINQ_TIME_SLICE msecs_to_jiffies(100)
#define IONIC_PHC_UPDATE_NS 10000000000 /* 10s in nanoseconds */
u8 status, int err);
int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait);
+int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_wait);
+void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status,
+ int err);
int ionic_set_dma_mask(struct ionic *ionic);
int ionic_setup(struct ionic *ionic);
int ionic_port_init(struct ionic *ionic);
int ionic_port_reset(struct ionic *ionic);
+const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr);
+
#endif /* _IONIC_H_ */
static void ionic_vf_dealloc_locked(struct ionic *ionic)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_STATSADDR };
struct ionic_vf *v;
- dma_addr_t dma = 0;
int i;
if (!ionic->vfs)
v = &ionic->vfs[i];
if (v->stats_pa) {
- (void)ionic_set_vf_config(ionic, i,
- IONIC_VF_ATTR_STATSADDR,
- (u8 *)&dma);
+ vfc.stats_pa = 0;
+ (void)ionic_set_vf_config(ionic, i, &vfc);
dma_unmap_single(ionic->dev, v->stats_pa,
sizeof(v->stats), DMA_FROM_DEVICE);
v->stats_pa = 0;
static int ionic_vf_alloc(struct ionic *ionic, int num_vfs)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_STATSADDR };
struct ionic_vf *v;
int err = 0;
int i;
}
ionic->num_vfs++;
+
/* ignore failures from older FW, we just won't get stats */
- (void)ionic_set_vf_config(ionic, i, IONIC_VF_ATTR_STATSADDR,
- (u8 *)&v->stats_pa);
+ vfc.stats_pa = cpu_to_le64(v->stats_pa);
+ (void)ionic_set_vf_config(ionic, i, &vfc);
}
out:
goto err_out_deregister_lifs;
}
+ mod_timer(&ionic->watchdog_timer,
+ round_jiffies(jiffies + ionic->watchdog_period));
+
return 0;
err_out_deregister_lifs:
err_out_reset:
ionic_reset(ionic);
err_out_teardown:
- del_timer_sync(&ionic->watchdog_timer);
pci_clear_master(pdev);
/* Don't fail the probe for these errors, keep
* the hw interface around for inspection
!test_bit(IONIC_LIF_F_FW_RESET, lif->state))
ionic_link_status_check_request(lif, CAN_NOT_SLEEP);
- if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state)) {
+ if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state) &&
+ !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) {
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (!work) {
netdev_err(lif->netdev, "rxmode change dropped\n");
}
}
+static void ionic_watchdog_init(struct ionic *ionic)
+{
+ struct ionic_dev *idev = &ionic->idev;
+
+ timer_setup(&ionic->watchdog_timer, ionic_watchdog_cb, 0);
+ ionic->watchdog_period = IONIC_WATCHDOG_SECS * HZ;
+
+ /* set times to ensure the first check will proceed */
+ atomic_long_set(&idev->last_check_time, jiffies - 2 * HZ);
+ idev->last_hb_time = jiffies - 2 * ionic->watchdog_period;
+ /* init as ready, so no transition if the first check succeeds */
+ idev->last_fw_hb = 0;
+ idev->fw_hb_ready = true;
+ idev->fw_status_ready = true;
+ idev->fw_generation = IONIC_FW_STS_F_GENERATION &
+ ioread8(&idev->dev_info_regs->fw_status);
+}
+
void ionic_init_devinfo(struct ionic *ionic)
{
struct ionic_dev *idev = &ionic->idev;
return -EFAULT;
}
- timer_setup(&ionic->watchdog_timer, ionic_watchdog_cb, 0);
- ionic->watchdog_period = IONIC_WATCHDOG_SECS * HZ;
-
- /* set times to ensure the first check will proceed */
- atomic_long_set(&idev->last_check_time, jiffies - 2 * HZ);
- idev->last_hb_time = jiffies - 2 * ionic->watchdog_period;
- /* init as ready, so no transition if the first check succeeds */
- idev->last_fw_hb = 0;
- idev->fw_hb_ready = true;
- idev->fw_status_ready = true;
- idev->fw_generation = IONIC_FW_STS_F_GENERATION &
- ioread8(&idev->dev_info_regs->fw_status);
-
- mod_timer(&ionic->watchdog_timer,
- round_jiffies(jiffies + ionic->watchdog_period));
+ ionic_watchdog_init(ionic);
idev->db_pages = bar->vaddr;
idev->phy_db_pages = bar->bus_addr;
}
/* Devcmd Interface */
+bool ionic_is_fw_running(struct ionic_dev *idev)
+{
+ u8 fw_status = ioread8(&idev->dev_info_regs->fw_status);
+
+ /* firmware is useful only if the running bit is set and
+ * fw_status != 0xff (bad PCI read)
+ */
+ return (fw_status != 0xff) && (fw_status & IONIC_FW_STS_F_RUNNING);
+}
+
int ionic_heartbeat_check(struct ionic *ionic)
{
- struct ionic_dev *idev = &ionic->idev;
unsigned long check_time, last_check_time;
+ struct ionic_dev *idev = &ionic->idev;
+ struct ionic_lif *lif = ionic->lif;
bool fw_status_ready = true;
bool fw_hb_ready;
u8 fw_generation;
goto do_check_time;
}
- /* firmware is useful only if the running bit is set and
- * fw_status != 0xff (bad PCI read)
- * If fw_status is not ready don't bother with the generation.
- */
fw_status = ioread8(&idev->dev_info_regs->fw_status);
- if (fw_status == 0xff || !(fw_status & IONIC_FW_STS_F_RUNNING)) {
+ /* If fw_status is not ready don't bother with the generation */
+ if (!ionic_is_fw_running(idev)) {
fw_status_ready = false;
} else {
fw_generation = fw_status & IONIC_FW_STS_F_GENERATION;
* the down, the next watchdog will see the fw is up
* and the generation value stable, so will trigger
* the fw-up activity.
+ *
+ * If we had already moved to FW_RESET from a RESET event,
+ * it is possible that we never saw the fw_status go to 0,
+ * so we fake the current idev->fw_status_ready here to
+ * force the transition and get FW up again.
*/
- fw_status_ready = false;
+ if (test_bit(IONIC_LIF_F_FW_RESET, lif->state))
+ idev->fw_status_ready = false; /* go to running */
+ else
+ fw_status_ready = false; /* go to down */
}
}
/* is this a transition? */
if (fw_status_ready != idev->fw_status_ready) {
- struct ionic_lif *lif = ionic->lif;
bool trigger = false;
- idev->fw_status_ready = fw_status_ready;
-
- if (!fw_status_ready) {
- dev_info(ionic->dev, "FW stopped %u\n", fw_status);
- if (lif && !test_bit(IONIC_LIF_F_FW_RESET, lif->state))
- trigger = true;
- } else {
- dev_info(ionic->dev, "FW running %u\n", fw_status);
- if (lif && test_bit(IONIC_LIF_F_FW_RESET, lif->state))
- trigger = true;
+ if (!fw_status_ready && lif &&
+ !test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+ !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
+ dev_info(ionic->dev, "FW stopped 0x%02x\n", fw_status);
+ trigger = true;
+
+ } else if (fw_status_ready && lif &&
+ test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+ !test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
+ dev_info(ionic->dev, "FW running 0x%02x\n", fw_status);
+ trigger = true;
}
if (trigger) {
struct ionic_deferred_work *work;
+ idev->fw_status_ready = fw_status_ready;
+
work = kzalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
work->type = IONIC_DW_TYPE_LIF_RESET;
}
}
- if (!fw_status_ready)
+ if (!idev->fw_status_ready)
return -ENXIO;
- /* wait at least one watchdog period since the last heartbeat */
+ /* Because of some variability in the actual FW heartbeat, we
+ * wait longer than the DEVCMD_TIMEOUT before checking again.
+ */
last_check_time = idev->last_hb_time;
- if (time_before(check_time, last_check_time + ionic->watchdog_period))
+ if (time_before(check_time, last_check_time + DEVCMD_TIMEOUT * 2 * HZ))
return 0;
fw_hb = ioread32(&idev->dev_info_regs->fw_heartbeat);
}
/* VF commands */
-int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data)
+int ionic_set_vf_config(struct ionic *ionic, int vf,
+ struct ionic_vf_setattr_cmd *vfc)
{
union ionic_dev_cmd cmd = {
.vf_setattr.opcode = IONIC_CMD_VF_SETATTR,
- .vf_setattr.attr = attr,
+ .vf_setattr.attr = vfc->attr,
.vf_setattr.vf_index = cpu_to_le16(vf),
};
int err;
+ memcpy(cmd.vf_setattr.pad, vfc->pad, sizeof(vfc->pad));
+
+ mutex_lock(&ionic->dev_cmd_lock);
+ ionic_dev_cmd_go(&ionic->idev, &cmd);
+ err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
+ mutex_unlock(&ionic->dev_cmd_lock);
+
+ return err;
+}
+
+int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr,
+ struct ionic_vf_getattr_comp *comp)
+{
+ union ionic_dev_cmd cmd = {
+ .vf_getattr.opcode = IONIC_CMD_VF_GETATTR,
+ .vf_getattr.attr = attr,
+ .vf_getattr.vf_index = cpu_to_le16(vf),
+ };
+ int err;
+
+ if (vf >= ionic->num_vfs)
+ return -EINVAL;
+
switch (attr) {
case IONIC_VF_ATTR_SPOOFCHK:
- cmd.vf_setattr.spoofchk = *data;
- dev_dbg(ionic->dev, "%s: vf %d spoof %d\n",
- __func__, vf, *data);
- break;
case IONIC_VF_ATTR_TRUST:
- cmd.vf_setattr.trust = *data;
- dev_dbg(ionic->dev, "%s: vf %d trust %d\n",
- __func__, vf, *data);
- break;
case IONIC_VF_ATTR_LINKSTATE:
- cmd.vf_setattr.linkstate = *data;
- dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n",
- __func__, vf, *data);
- break;
case IONIC_VF_ATTR_MAC:
- ether_addr_copy(cmd.vf_setattr.macaddr, data);
- dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n",
- __func__, vf, data);
- break;
case IONIC_VF_ATTR_VLAN:
- cmd.vf_setattr.vlanid = cpu_to_le16(*(u16 *)data);
- dev_dbg(ionic->dev, "%s: vf %d vlan %d\n",
- __func__, vf, *(u16 *)data);
- break;
case IONIC_VF_ATTR_RATE:
- cmd.vf_setattr.maxrate = cpu_to_le32(*(u32 *)data);
- dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n",
- __func__, vf, *(u32 *)data);
break;
case IONIC_VF_ATTR_STATSADDR:
- cmd.vf_setattr.stats_pa = cpu_to_le64(*(u64 *)data);
- dev_dbg(ionic->dev, "%s: vf %d stats_pa 0x%08llx\n",
- __func__, vf, *(u64 *)data);
- break;
default:
return -EINVAL;
}
mutex_lock(&ionic->dev_cmd_lock);
ionic_dev_cmd_go(&ionic->idev, &cmd);
- err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
+ err = ionic_dev_cmd_wait_nomsg(ionic, DEVCMD_TIMEOUT);
+ memcpy_fromio(comp, &ionic->idev.dev_cmd_regs->comp.vf_getattr,
+ sizeof(*comp));
mutex_unlock(&ionic->dev_cmd_lock);
+ if (err && comp->status != IONIC_RC_ENOSUPP)
+ ionic_dev_cmd_dev_err_print(ionic, cmd.vf_getattr.opcode,
+ comp->status, err);
+
return err;
}
void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type);
void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type);
-int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data);
+int ionic_set_vf_config(struct ionic *ionic, int vf,
+ struct ionic_vf_setattr_cmd *vfc);
+int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr,
+ struct ionic_vf_getattr_comp *comp);
void ionic_dev_cmd_queue_identify(struct ionic_dev *idev,
u16 lif_type, u8 qtype, u8 qver);
void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver);
void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info,
unsigned int stop_index);
int ionic_heartbeat_check(struct ionic *ionic);
+bool ionic_is_fw_running(struct ionic_dev *idev);
#endif /* _IONIC_DEV_H_ */
ionic_link_status_check_request(lif, CAN_NOT_SLEEP);
break;
case IONIC_EVENT_RESET:
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work) {
- netdev_err(lif->netdev, "Reset event dropped\n");
- } else {
- work->type = IONIC_DW_TYPE_LIF_RESET;
- ionic_lif_deferred_enqueue(&lif->deferred, work);
+ if (lif->ionic->idev.fw_status_ready &&
+ !test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+ !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work) {
+ netdev_err(lif->netdev, "Reset event dropped\n");
+ clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state);
+ } else {
+ work->type = IONIC_DW_TYPE_LIF_RESET;
+ ionic_lif_deferred_enqueue(&lif->deferred, work);
+ }
}
break;
default:
err = ionic_adminq_post_wait(lif, &ctx);
if (err)
- netdev_err(lif->netdev, "lif quiesce failed %d\n", err);
+ netdev_dbg(lif->netdev, "lif quiesce failed %d\n", err);
}
static void ionic_txrx_disable(struct ionic_lif *lif)
}
}
+static int ionic_update_cached_vf_config(struct ionic *ionic, int vf)
+{
+ struct ionic_vf_getattr_comp comp = { 0 };
+ int err;
+ u8 attr;
+
+ attr = IONIC_VF_ATTR_VLAN;
+ err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
+ if (err && comp.status != IONIC_RC_ENOSUPP)
+ goto err_out;
+ if (!err)
+ ionic->vfs[vf].vlanid = comp.vlanid;
+
+ attr = IONIC_VF_ATTR_SPOOFCHK;
+ err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
+ if (err && comp.status != IONIC_RC_ENOSUPP)
+ goto err_out;
+ if (!err)
+ ionic->vfs[vf].spoofchk = comp.spoofchk;
+
+ attr = IONIC_VF_ATTR_LINKSTATE;
+ err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
+ if (err && comp.status != IONIC_RC_ENOSUPP)
+ goto err_out;
+ if (!err) {
+ switch (comp.linkstate) {
+ case IONIC_VF_LINK_STATUS_UP:
+ ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_ENABLE;
+ break;
+ case IONIC_VF_LINK_STATUS_DOWN:
+ ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_DISABLE;
+ break;
+ case IONIC_VF_LINK_STATUS_AUTO:
+ ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_AUTO;
+ break;
+ default:
+ dev_warn(ionic->dev, "Unexpected link state %u\n", comp.linkstate);
+ break;
+ }
+ }
+
+ attr = IONIC_VF_ATTR_RATE;
+ err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
+ if (err && comp.status != IONIC_RC_ENOSUPP)
+ goto err_out;
+ if (!err)
+ ionic->vfs[vf].maxrate = comp.maxrate;
+
+ attr = IONIC_VF_ATTR_TRUST;
+ err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
+ if (err && comp.status != IONIC_RC_ENOSUPP)
+ goto err_out;
+ if (!err)
+ ionic->vfs[vf].trusted = comp.trust;
+
+ attr = IONIC_VF_ATTR_MAC;
+ err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp);
+ if (err && comp.status != IONIC_RC_ENOSUPP)
+ goto err_out;
+ if (!err)
+ ether_addr_copy(ionic->vfs[vf].macaddr, comp.macaddr);
+
+err_out:
+ if (err)
+ dev_err(ionic->dev, "Failed to get %s for VF %d\n",
+ ionic_vf_attr_to_str(attr), vf);
+
+ return err;
+}
+
static int ionic_get_vf_config(struct net_device *netdev,
int vf, struct ifla_vf_info *ivf)
{
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ivf->vf = vf;
- ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid);
- ivf->qos = 0;
- ivf->spoofchk = ionic->vfs[vf].spoofchk;
- ivf->linkstate = ionic->vfs[vf].linkstate;
- ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate);
- ivf->trusted = ionic->vfs[vf].trusted;
- ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr);
+ ivf->vf = vf;
+ ivf->qos = 0;
+
+ ret = ionic_update_cached_vf_config(ionic, vf);
+ if (!ret) {
+ ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid);
+ ivf->spoofchk = ionic->vfs[vf].spoofchk;
+ ivf->linkstate = ionic->vfs[vf].linkstate;
+ ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate);
+ ivf->trusted = ionic->vfs[vf].trusted;
+ ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr);
+ }
}
up_read(&ionic->vf_op_lock);
static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_MAC };
struct ionic_lif *lif = netdev_priv(netdev);
struct ionic *ionic = lif->ionic;
int ret;
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ret = ionic_set_vf_config(ionic, vf, IONIC_VF_ATTR_MAC, mac);
+ ether_addr_copy(vfc.macaddr, mac);
+ dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n",
+ __func__, vf, vfc.macaddr);
+
+ ret = ionic_set_vf_config(ionic, vf, &vfc);
if (!ret)
ether_addr_copy(ionic->vfs[vf].macaddr, mac);
}
static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
u8 qos, __be16 proto)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_VLAN };
struct ionic_lif *lif = netdev_priv(netdev);
struct ionic *ionic = lif->ionic;
int ret;
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ret = ionic_set_vf_config(ionic, vf,
- IONIC_VF_ATTR_VLAN, (u8 *)&vlan);
+ vfc.vlanid = cpu_to_le16(vlan);
+ dev_dbg(ionic->dev, "%s: vf %d vlan %d\n",
+ __func__, vf, le16_to_cpu(vfc.vlanid));
+
+ ret = ionic_set_vf_config(ionic, vf, &vfc);
if (!ret)
ionic->vfs[vf].vlanid = cpu_to_le16(vlan);
}
static int ionic_set_vf_rate(struct net_device *netdev, int vf,
int tx_min, int tx_max)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_RATE };
struct ionic_lif *lif = netdev_priv(netdev);
struct ionic *ionic = lif->ionic;
int ret;
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ret = ionic_set_vf_config(ionic, vf,
- IONIC_VF_ATTR_RATE, (u8 *)&tx_max);
+ vfc.maxrate = cpu_to_le32(tx_max);
+ dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n",
+ __func__, vf, le32_to_cpu(vfc.maxrate));
+
+ ret = ionic_set_vf_config(ionic, vf, &vfc);
if (!ret)
lif->ionic->vfs[vf].maxrate = cpu_to_le32(tx_max);
}
static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_SPOOFCHK };
struct ionic_lif *lif = netdev_priv(netdev);
struct ionic *ionic = lif->ionic;
- u8 data = set; /* convert to u8 for config */
int ret;
if (!netif_device_present(netdev))
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ret = ionic_set_vf_config(ionic, vf,
- IONIC_VF_ATTR_SPOOFCHK, &data);
+ vfc.spoofchk = set;
+ dev_dbg(ionic->dev, "%s: vf %d spoof %d\n",
+ __func__, vf, vfc.spoofchk);
+
+ ret = ionic_set_vf_config(ionic, vf, &vfc);
if (!ret)
- ionic->vfs[vf].spoofchk = data;
+ ionic->vfs[vf].spoofchk = set;
}
up_write(&ionic->vf_op_lock);
static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_TRUST };
struct ionic_lif *lif = netdev_priv(netdev);
struct ionic *ionic = lif->ionic;
- u8 data = set; /* convert to u8 for config */
int ret;
if (!netif_device_present(netdev))
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ret = ionic_set_vf_config(ionic, vf,
- IONIC_VF_ATTR_TRUST, &data);
+ vfc.trust = set;
+ dev_dbg(ionic->dev, "%s: vf %d trust %d\n",
+ __func__, vf, vfc.trust);
+
+ ret = ionic_set_vf_config(ionic, vf, &vfc);
if (!ret)
- ionic->vfs[vf].trusted = data;
+ ionic->vfs[vf].trusted = set;
}
up_write(&ionic->vf_op_lock);
static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set)
{
+ struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_LINKSTATE };
struct ionic_lif *lif = netdev_priv(netdev);
struct ionic *ionic = lif->ionic;
- u8 data;
+ u8 vfls;
int ret;
switch (set) {
case IFLA_VF_LINK_STATE_ENABLE:
- data = IONIC_VF_LINK_STATUS_UP;
+ vfls = IONIC_VF_LINK_STATUS_UP;
break;
case IFLA_VF_LINK_STATE_DISABLE:
- data = IONIC_VF_LINK_STATUS_DOWN;
+ vfls = IONIC_VF_LINK_STATUS_DOWN;
break;
case IFLA_VF_LINK_STATE_AUTO:
- data = IONIC_VF_LINK_STATUS_AUTO;
+ vfls = IONIC_VF_LINK_STATUS_AUTO;
break;
default:
return -EINVAL;
if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) {
ret = -EINVAL;
} else {
- ret = ionic_set_vf_config(ionic, vf,
- IONIC_VF_ATTR_LINKSTATE, &data);
+ vfc.linkstate = vfls;
+ dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n",
+ __func__, vf, vfc.linkstate);
+
+ ret = ionic_set_vf_config(ionic, vf, &vfc);
if (!ret)
ionic->vfs[vf].linkstate = set;
}
mutex_unlock(&lif->queue_lock);
+ clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state);
dev_info(ionic->dev, "FW Down: LIFs stopped\n");
}
/* unmap doorbell page */
ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage);
lif->kern_dbpage = NULL;
- kfree(lif->dbid_inuse);
- lif->dbid_inuse = NULL;
mutex_destroy(&lif->config_lock);
mutex_destroy(&lif->queue_lock);
return -EINVAL;
}
- lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL);
- if (!lif->dbid_inuse) {
- dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n");
- return -ENOMEM;
- }
-
- /* first doorbell id reserved for kernel (dbid aka pid == zero) */
- set_bit(0, lif->dbid_inuse);
lif->kern_pid = 0;
-
dbpage_num = ionic_db_page_num(lif, lif->kern_pid);
lif->kern_dbpage = ionic_bus_map_dbpage(lif->ionic, dbpage_num);
if (!lif->kern_dbpage) {
dev_err(dev, "Cannot map dbpage, aborting\n");
- err = -ENOMEM;
- goto err_out_free_dbid;
+ return -ENOMEM;
}
err = ionic_lif_adminq_init(lif);
return 0;
err_out_notifyq_deinit:
+ napi_disable(&lif->adminqcq->napi);
ionic_lif_qcq_deinit(lif, lif->notifyqcq);
err_out_adminq_deinit:
ionic_lif_qcq_deinit(lif, lif->adminqcq);
ionic_lif_reset(lif);
ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage);
lif->kern_dbpage = NULL;
-err_out_free_dbid:
- kfree(lif->dbid_inuse);
- lif->dbid_inuse = NULL;
return err;
}
IONIC_LIF_F_LINK_CHECK_REQUESTED,
IONIC_LIF_F_FILTER_SYNC_NEEDED,
IONIC_LIF_F_FW_RESET,
+ IONIC_LIF_F_FW_STOPPING,
IONIC_LIF_F_SPLIT_INTR,
IONIC_LIF_F_BROKEN,
IONIC_LIF_F_TX_DIM_INTR,
u32 rx_coalesce_hw; /* what the hw is using */
u32 tx_coalesce_usecs; /* what the user asked for */
u32 tx_coalesce_hw; /* what the hw is using */
- unsigned long *dbid_inuse;
unsigned int dbid_count;
struct ionic_phc *phc;
}
}
+const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr)
+{
+ switch (attr) {
+ case IONIC_VF_ATTR_SPOOFCHK:
+ return "IONIC_VF_ATTR_SPOOFCHK";
+ case IONIC_VF_ATTR_TRUST:
+ return "IONIC_VF_ATTR_TRUST";
+ case IONIC_VF_ATTR_LINKSTATE:
+ return "IONIC_VF_ATTR_LINKSTATE";
+ case IONIC_VF_ATTR_MAC:
+ return "IONIC_VF_ATTR_MAC";
+ case IONIC_VF_ATTR_VLAN:
+ return "IONIC_VF_ATTR_VLAN";
+ case IONIC_VF_ATTR_RATE:
+ return "IONIC_VF_ATTR_RATE";
+ case IONIC_VF_ATTR_STATSADDR:
+ return "IONIC_VF_ATTR_STATSADDR";
+ default:
+ return "IONIC_VF_ATTR_UNKNOWN";
+ }
+}
+
static void ionic_adminq_flush(struct ionic_lif *lif)
{
struct ionic_desc_info *desc_info;
void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode,
u8 status, int err)
{
+ const char *stat_str;
+
+ stat_str = (err == -ETIMEDOUT) ? "TIMEOUT" :
+ ionic_error_to_str(status);
+
netdev_err(lif->netdev, "%s (%d) failed: %s (%d)\n",
- ionic_opcode_to_str(opcode), opcode,
- ionic_error_to_str(status), err);
+ ionic_opcode_to_str(opcode), opcode, stat_str, err);
}
static int ionic_adminq_check_err(struct ionic_lif *lif,
if (do_msg && !test_bit(IONIC_LIF_F_FW_RESET, lif->state))
netdev_err(netdev, "Posting of %s (%d) failed: %d\n",
name, ctx->cmd.cmd.opcode, err);
+ ctx->comp.comp.status = IONIC_RC_ERROR;
return err;
}
if (remaining)
break;
- /* interrupt the wait if FW stopped */
- if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) {
+ /* force a check of FW status and break out if FW reset */
+ (void)ionic_heartbeat_check(lif->ionic);
+ if ((test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+ !lif->ionic->idev.fw_status_ready) ||
+ test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
if (do_msg)
- netdev_err(netdev, "%s (%d) interrupted, FW in reset\n",
- name, ctx->cmd.cmd.opcode);
+ netdev_warn(netdev, "%s (%d) interrupted, FW in reset\n",
+ name, ctx->cmd.cmd.opcode);
+ ctx->comp.comp.status = IONIC_RC_ERROR;
return -ENXIO;
}
static void ionic_dev_cmd_clean(struct ionic *ionic)
{
- union __iomem ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs;
+ struct ionic_dev *idev = &ionic->idev;
- iowrite32(0, ®s->doorbell);
- memset_io(®s->cmd, 0, sizeof(regs->cmd));
+ iowrite32(0, &idev->dev_cmd_regs->doorbell);
+ memset_io(&idev->dev_cmd_regs->cmd, 0, sizeof(idev->dev_cmd_regs->cmd));
}
-int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds)
+void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status,
+ int err)
+{
+ const char *stat_str;
+
+ stat_str = (err == -ETIMEDOUT) ? "TIMEOUT" :
+ ionic_error_to_str(status);
+
+ dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n",
+ ionic_opcode_to_str(opcode), opcode, stat_str, err);
+}
+
+static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
+ const bool do_msg)
{
struct ionic_dev *idev = &ionic->idev;
unsigned long start_time;
unsigned long max_wait;
unsigned long duration;
+ int done = 0;
+ bool fw_up;
int opcode;
- int hb = 0;
- int done;
int err;
/* Wait for dev cmd to complete, retrying if we get EAGAIN,
try_again:
opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode);
start_time = jiffies;
- do {
+ for (fw_up = ionic_is_fw_running(idev);
+ !done && fw_up && time_before(jiffies, max_wait);
+ fw_up = ionic_is_fw_running(idev)) {
done = ionic_dev_cmd_done(idev);
if (done)
break;
usleep_range(100, 200);
-
- /* Don't check the heartbeat on FW_CONTROL commands as they are
- * notorious for interrupting the firmware's heartbeat update.
- */
- if (opcode != IONIC_CMD_FW_CONTROL)
- hb = ionic_heartbeat_check(ionic);
- } while (!done && !hb && time_before(jiffies, max_wait));
+ }
duration = jiffies - start_time;
dev_dbg(ionic->dev, "DEVCMD %s (%d) done=%d took %ld secs (%ld jiffies)\n",
ionic_opcode_to_str(opcode), opcode,
done, duration / HZ, duration);
- if (!done && hb) {
- /* It is possible (but unlikely) that FW was busy and missed a
- * heartbeat check but is still alive and will process this
- * request, so don't clean the dev_cmd in this case.
- */
- dev_dbg(ionic->dev, "DEVCMD %s (%d) failed - FW halted\n",
- ionic_opcode_to_str(opcode), opcode);
+ if (!done && !fw_up) {
+ ionic_dev_cmd_clean(ionic);
+ dev_warn(ionic->dev, "DEVCMD %s (%d) interrupted - FW is down\n",
+ ionic_opcode_to_str(opcode), opcode);
return -ENXIO;
}
}
if (!(opcode == IONIC_CMD_FW_CONTROL && err == IONIC_RC_EAGAIN))
- dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n",
- ionic_opcode_to_str(opcode), opcode,
- ionic_error_to_str(err), err);
+ if (do_msg)
+ ionic_dev_cmd_dev_err_print(ionic, opcode, err,
+ ionic_error_to_errno(err));
return ionic_error_to_errno(err);
}
return 0;
}
+int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds)
+{
+ return __ionic_dev_cmd_wait(ionic, max_seconds, true);
+}
+
+int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_seconds)
+{
+ return __ionic_dev_cmd_wait(ionic, max_seconds, false);
+}
+
int ionic_setup(struct ionic *ionic)
{
int err;
struct ionic_dev *idev = &ionic->idev;
int err;
+ if (!ionic_is_fw_running(idev))
+ return 0;
+
mutex_lock(&ionic->dev_cmd_lock);
ionic_dev_cmd_reset(idev);
err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
int ionic_port_reset(struct ionic *ionic)
{
struct ionic_dev *idev = &ionic->idev;
- int err;
+ int err = 0;
if (!idev->port_info)
return 0;
- mutex_lock(&ionic->dev_cmd_lock);
- ionic_dev_cmd_port_reset(idev);
- err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
- mutex_unlock(&ionic->dev_cmd_lock);
+ if (ionic_is_fw_running(idev)) {
+ mutex_lock(&ionic->dev_cmd_lock);
+ ionic_dev_cmd_port_reset(idev);
+ err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
+ mutex_unlock(&ionic->dev_cmd_lock);
+ }
dma_free_coherent(ionic->dev, idev->port_info_sz,
idev->port_info, idev->port_info_pa);
idev->port_info = NULL;
idev->port_info_pa = 0;
- if (err)
- dev_err(ionic->dev, "Failed to reset port\n");
-
return err;
}
spin_unlock_bh(&lif->rx_filters.lock);
- if (err == -ENOSPC) {
- if (le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN)
- lif->max_vlans = lif->nvlans;
+ /* store the max_vlans limit that we found */
+ if (err == -ENOSPC &&
+ le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN)
+ lif->max_vlans = lif->nvlans;
+
+ /* Prevent unnecessary error messages on recoverable
+ * errors as the filter will get retried on the next
+ * sync attempt.
+ */
+ switch (err) {
+ case -ENOSPC:
+ case -ENXIO:
+ case -ETIMEDOUT:
+ case -EAGAIN:
+ case -EBUSY:
return 0;
+ default:
+ break;
}
ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode,
spin_unlock_bh(&lif->rx_filters.lock);
if (state != IONIC_FILTER_STATE_NEW) {
- err = ionic_adminq_post_wait(lif, &ctx);
- if (err && err != -EEXIST)
+ err = ionic_adminq_post_wait_nomsg(lif, &ctx);
+
+ switch (err) {
+ /* ignore these errors */
+ case -EEXIST:
+ case -ENXIO:
+ case -ETIMEDOUT:
+ case -EAGAIN:
+ case -EBUSY:
+ case 0:
+ break;
+ default:
+ ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode,
+ ctx.comp.comp.status, err);
return err;
+ }
}
return 0;
return -EIO;
}
+static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q,
+ struct ionic_desc_info *desc_info)
+{
+ struct ionic_buf_info *buf_info = desc_info->bufs;
+ struct device *dev = q->dev;
+ unsigned int i;
+
+ if (!desc_info->nbufs)
+ return;
+
+ dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr,
+ buf_info->len, DMA_TO_DEVICE);
+ buf_info++;
+ for (i = 1; i < desc_info->nbufs; i++, buf_info++)
+ dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr,
+ buf_info->len, DMA_TO_DEVICE);
+
+ desc_info->nbufs = 0;
+}
+
static void ionic_tx_clean(struct ionic_queue *q,
struct ionic_desc_info *desc_info,
struct ionic_cq_info *cq_info,
void *cb_arg)
{
- struct ionic_buf_info *buf_info = desc_info->bufs;
struct ionic_tx_stats *stats = q_to_tx_stats(q);
struct ionic_qcq *qcq = q_to_qcq(q);
struct sk_buff *skb = cb_arg;
- struct device *dev = q->dev;
- unsigned int i;
u16 qi;
- if (desc_info->nbufs) {
- dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr,
- buf_info->len, DMA_TO_DEVICE);
- buf_info++;
- for (i = 1; i < desc_info->nbufs; i++, buf_info++)
- dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr,
- buf_info->len, DMA_TO_DEVICE);
- }
+ ionic_tx_desc_unmap_bufs(q, desc_info);
if (!skb)
return;
err = ionic_tx_tcp_inner_pseudo_csum(skb);
else
err = ionic_tx_tcp_pseudo_csum(skb);
- if (err)
+ if (err) {
+ /* clean up mapping from ionic_tx_map_skb */
+ ionic_tx_desc_unmap_bufs(q, desc_info);
return err;
+ }
if (encap)
hdrlen = skb_inner_transport_header(skb) - skb->data +
return 0;
}
-static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb,
- struct ionic_desc_info *desc_info)
+static void ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb,
+ struct ionic_desc_info *desc_info)
{
struct ionic_txq_desc *desc = desc_info->txq_desc;
struct ionic_buf_info *buf_info = desc_info->bufs;
stats->crc32_csum++;
else
stats->csum++;
-
- return 0;
}
-static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb,
- struct ionic_desc_info *desc_info)
+static void ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb,
+ struct ionic_desc_info *desc_info)
{
struct ionic_txq_desc *desc = desc_info->txq_desc;
struct ionic_buf_info *buf_info = desc_info->bufs;
desc->csum_offset = 0;
stats->csum_none++;
-
- return 0;
}
-static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb,
- struct ionic_desc_info *desc_info)
+static void ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb,
+ struct ionic_desc_info *desc_info)
{
struct ionic_txq_sg_desc *sg_desc = desc_info->txq_sg_desc;
struct ionic_buf_info *buf_info = &desc_info->bufs[1];
}
stats->frags += skb_shinfo(skb)->nr_frags;
-
- return 0;
}
static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb)
{
struct ionic_desc_info *desc_info = &q->info[q->head_idx];
struct ionic_tx_stats *stats = q_to_tx_stats(q);
- int err;
if (unlikely(ionic_tx_map_skb(q, skb, desc_info)))
return -EIO;
/* set up the initial descriptor */
if (skb->ip_summed == CHECKSUM_PARTIAL)
- err = ionic_tx_calc_csum(q, skb, desc_info);
+ ionic_tx_calc_csum(q, skb, desc_info);
else
- err = ionic_tx_calc_no_csum(q, skb, desc_info);
- if (err)
- return err;
+ ionic_tx_calc_no_csum(q, skb, desc_info);
/* add frags */
- err = ionic_tx_skb_frags(q, skb, desc_info);
- if (err)
- return err;
+ ionic_tx_skb_frags(q, skb, desc_info);
skb_tx_timestamp(skb);
stats->pkts++;
usecs);
}
-int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
- struct qed_ptt *p_ptt,
- u32 cmd,
- u32 param,
- u32 *o_mcp_resp,
- u32 *o_mcp_param)
+static int _qed_mcp_cmd(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 cmd,
+ u32 param,
+ u32 *o_mcp_resp,
+ u32 *o_mcp_param,
+ bool can_sleep)
{
struct qed_mcp_mb_params mb_params;
int rc;
memset(&mb_params, 0, sizeof(mb_params));
mb_params.cmd = cmd;
mb_params.param = param;
+ mb_params.flags = can_sleep ? QED_MB_FLAG_CAN_SLEEP : 0;
rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params);
if (rc)
return 0;
}
+int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 cmd,
+ u32 param,
+ u32 *o_mcp_resp,
+ u32 *o_mcp_param)
+{
+ return (_qed_mcp_cmd(p_hwfn, p_ptt, cmd, param,
+ o_mcp_resp, o_mcp_param, true));
+}
+
+int qed_mcp_cmd_nosleep(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 cmd,
+ u32 param,
+ u32 *o_mcp_resp,
+ u32 *o_mcp_param)
+{
+ return (_qed_mcp_cmd(p_hwfn, p_ptt, cmd, param,
+ o_mcp_resp, o_mcp_param, false));
+}
+
static int
qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt,
qed_configure_pf_max_bandwidth(p_hwfn->cdev, p_info->bandwidth_max);
/* Acknowledge the MFW */
- qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_BW_UPDATE_ACK, 0, &resp,
- ¶m);
+ qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_BW_UPDATE_ACK, 0, &resp,
+ ¶m);
}
static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode);
/* Acknowledge the MFW */
- qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0,
- &resp, ¶m);
+ qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0,
+ &resp, ¶m);
}
static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn,
{
int rc;
- rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, param,
- p_mcp_resp, p_mcp_param);
+ rc = qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD,
+ param, p_mcp_resp, p_mcp_param);
if (rc)
return rc;
struct qed_ptt *p_ptt, u32 *p_board_config);
/**
- * qed_mcp_cmd(): General function for sending commands to the MCP
+ * qed_mcp_cmd(): Sleepable function for sending commands to the MCP
* mailbox. It acquire mutex lock for the entire
* operation, from sending the request until the MCP
* response. Waiting for MCP response will be checked up
- * to 5 seconds every 5ms.
+ * to 5 seconds every 10ms. Should not be called from atomic
+ * context.
*
* @p_hwfn: HW device data.
* @p_ptt: PTT required for register access.
u32 *o_mcp_param);
/**
+ * qed_mcp_cmd_nosleep(): Function for sending commands to the MCP
+ * mailbox. It acquire mutex lock for the entire
+ * operation, from sending the request until the MCP
+ * response. Waiting for MCP response will be checked up
+ * to 5 seconds every 10us. Should be called when sleep
+ * is not allowed.
+ *
+ * @p_hwfn: HW device data.
+ * @p_ptt: PTT required for register access.
+ * @cmd: command to be sent to the MCP.
+ * @param: Optional param
+ * @o_mcp_resp: The MCP response code (exclude sequence).
+ * @o_mcp_param: Optional parameter provided by the MCP
+ * response
+ *
+ * Return: Int - 0 - Operation was successul.
+ */
+int qed_mcp_cmd_nosleep(struct qed_hwfn *p_hwfn,
+ struct qed_ptt *p_ptt,
+ u32 cmd,
+ u32 param,
+ u32 *o_mcp_resp,
+ u32 *o_mcp_param);
+
+/**
* qed_mcp_drain(): drains the nig, allowing completion to pass in
* case of pauses.
* (Should be called only from sleepable context)
case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38:
rtl_eri_set_bits(tp, 0xd4, 0x0c00);
break;
- case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53:
- rtl_eri_set_bits(tp, 0xd4, 0x1f80);
- break;
- case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63:
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_63:
r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80);
break;
default:
}
}
+static void rtl_disable_exit_l1(struct rtl8169_private *tp)
+{
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
+ rtl_eri_clear_bits(tp, 0xd4, 0x1f00);
+ break;
+ case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_63:
+ r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0);
+ break;
+ default:
+ break;
+ }
+}
+
static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
{
/* Don't enable ASPM in the chip if OS can't control ASPM */
if (enable && tp->aspm_manageable) {
RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
+
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_45 ... RTL_GIGA_MAC_VER_48:
+ case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63:
+ /* reset ephy tx/rx disable timer */
+ r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0);
+ /* chip can trigger L1.2 */
+ r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, BIT(2));
+ break;
+ default:
+ break;
+ }
} else {
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_45 ... RTL_GIGA_MAC_VER_48:
+ case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63:
+ r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0);
+ break;
+ default:
+ break;
+ }
+
RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
}
rtl_pci_commit(tp);
rtl8169_cleanup(tp, true);
-
+ rtl_disable_exit_l1(tp);
rtl_prepare_power_down(tp);
}
rtl8169_down(tp);
}
-#ifdef CONFIG_PM
-
static int rtl8169_runtime_resume(struct device *dev)
{
struct rtl8169_private *tp = dev_get_drvdata(dev);
return 0;
}
-static int __maybe_unused rtl8169_suspend(struct device *device)
+static int rtl8169_suspend(struct device *device)
{
struct rtl8169_private *tp = dev_get_drvdata(device);
return 0;
}
-static int __maybe_unused rtl8169_resume(struct device *device)
+static int rtl8169_resume(struct device *device)
{
struct rtl8169_private *tp = dev_get_drvdata(device);
}
static const struct dev_pm_ops rtl8169_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume)
- SET_RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume,
- rtl8169_runtime_idle)
+ SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume)
+ RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume,
+ rtl8169_runtime_idle)
};
-#endif /* CONFIG_PM */
-
static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp)
{
/* WoL fails with 8168b when the receiver is disabled. */
rtl_rar_set(tp, mac_addr);
}
+/* register is set if system vendor successfully tested ASPM 1.2 */
+static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
+{
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_60 &&
+ r8168_mac_ocp_read(tp, 0xc0b2) & 0xf)
+ return true;
+
+ return false;
+}
+
static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct rtl8169_private *tp;
* Chips from RTL8168h partially have issues with L1.2, but seem
* to work fine with L1 and L1.1.
*/
- if (tp->mac_version >= RTL_GIGA_MAC_VER_45)
+ if (rtl_aspm_is_safe(tp))
+ rc = 0;
+ else if (tp->mac_version >= RTL_GIGA_MAC_VER_45)
rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
else
rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
.probe = rtl_init_one,
.remove = rtl_remove_one,
.shutdown = rtl_shutdown,
-#ifdef CONFIG_PM
- .driver.pm = &rtl8169_pm_ops,
-#endif
+ .driver.pm = pm_ptr(&rtl8169_pm_ops),
};
module_pci_driver(rtl8169_pci_driver);
* at this time.
*/
if (soc_device_match(r8a7795es10)) {
- err = phy_set_max_speed(phydev, SPEED_100);
- if (err) {
- netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n");
- goto err_phy_disconnect;
- }
+ phy_set_max_speed(phydev, SPEED_100);
netdev_info(ndev, "limited PHY to 100Mbit/s\n");
}
return 0;
-err_phy_disconnect:
- phy_disconnect(phydev);
err_deregister_fixed_link:
if (of_phy_is_fixed_link(np))
of_phy_deregister_fixed_link(np);
{
struct ravb_private *priv = netdev_priv(ndev);
const struct ravb_hw_info *info = priv->info;
- int ret;
if (info->nc_queues)
napi_enable(&priv->napi[RAVB_NC]);
/* Disable MagicPacket */
ravb_modify(ndev, ECMR, ECMR_MPDE, 0);
- ret = ravb_close(ndev);
- if (ret < 0)
- return ret;
+ ravb_close(ndev);
return disable_irq_wake(priv->emac_irq);
}
}
/* mask with MAC supported features */
- if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) {
- int err = phy_set_max_speed(phydev, SPEED_100);
- if (err) {
- netdev_err(ndev, "failed to limit PHY to 100 Mbit/s\n");
- phy_disconnect(phydev);
- return err;
- }
- }
+ if (mdp->cd->register_type != SH_ETH_REG_GIGABIT)
+ phy_set_max_speed(phydev, SPEED_100);
phy_attached_info(phydev);
* both be reset and all registers restored. This is what
* happens during suspend and resume without WoL enabled.
*/
- ret = sh_eth_close(ndev);
- if (ret < 0)
- return ret;
+ sh_eth_close(ndev);
ret = sh_eth_open(ndev);
if (ret < 0)
return ret;
{
struct net_device *ndev = dev_get_drvdata(dev);
struct sh_eth_private *mdp = netdev_priv(ndev);
- int ret = 0;
+ int ret;
if (!netif_running(ndev))
return 0;
{
struct net_device *ndev = dev_get_drvdata(dev);
struct sh_eth_private *mdp = netdev_priv(ndev);
- int ret = 0;
+ int ret;
if (!netif_running(ndev))
return 0;
/* MAC core supports the EEE feature. */
if (priv->hw_cap.eee) {
/* Check if the PHY supports EEE */
- if (phy_init_eee(ndev->phydev, 1))
+ if (phy_init_eee(ndev->phydev, true))
return false;
priv->eee_active = 1;
}
}
+static unsigned int efx_ef10_recycle_ring_size(const struct efx_nic *efx)
+{
+ unsigned int ret = EFX_RECYCLE_RING_SIZE_10G;
+
+ /* There is no difference between PFs and VFs. The side is based on
+ * the maximum link speed of a given NIC.
+ */
+ switch (efx->pci_dev->device & 0xfff) {
+ case 0x0903: /* Farmingdale can do up to 10G */
+ break;
+ case 0x0923: /* Greenport can do up to 40G */
+ case 0x0a03: /* Medford can do up to 40G */
+ ret *= 4;
+ break;
+ default: /* Medford2 can do up to 100G */
+ ret *= 10;
+ }
+
+ if (IS_ENABLED(CONFIG_PPC64))
+ ret *= 4;
+
+ return ret;
+}
+
#define EF10_OFFLOAD_FEATURES \
(NETIF_F_IP_CSUM | \
NETIF_F_HW_VLAN_CTAG_FILTER | \
.check_caps = ef10_check_caps,
.print_additional_fwver = efx_ef10_print_additional_fwver,
.sensor_event = efx_mcdi_sensor_event,
+ .rx_recycle_ring_size = efx_ef10_recycle_ring_size,
};
const struct efx_nic_type efx_hunt_a0_nic_type = {
.check_caps = ef10_check_caps,
.print_additional_fwver = efx_ef10_print_additional_fwver,
.sensor_event = efx_mcdi_sensor_event,
+ .rx_recycle_ring_size = efx_ef10_recycle_ring_size,
};
#include "ef100_rx.h"
#include "ef100_tx.h"
#include "ef100_netdev.h"
+#include "rx_common.h"
#define EF100_MAX_VIS 4096
#define EF100_NUM_MCDI_BUFFERS 1
}
}
+static unsigned int efx_ef100_recycle_ring_size(const struct efx_nic *efx)
+{
+ /* Maximum link speed for Riverhead is 100G */
+ return 10 * EFX_RECYCLE_RING_SIZE_10G;
+}
+
/* NIC level access functions
*/
#define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \
.rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config,
.rx_pull_rss_context_config = efx_mcdi_rx_pull_rss_context_config,
.rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts,
+ .rx_recycle_ring_size = efx_ef100_recycle_ring_size,
.reconfigure_mac = ef100_reconfigure_mac,
.reconfigure_port = efx_mcdi_port_reconfigure,
.rx_pull_rss_config = efx_mcdi_rx_pull_rss_config,
.rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config,
.rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts,
+ .rx_recycle_ring_size = efx_ef100_recycle_ring_size,
.reconfigure_mac = ef100_reconfigure_mac,
.test_nvram = efx_new_mcdi_nvram_test_all,
* @udp_tnl_has_port: Check if a port has been added as UDP tunnel
* @print_additional_fwver: Dump NIC-specific additional FW version info
* @sensor_event: Handle a sensor event from MCDI
+ * @rx_recycle_ring_size: Size of the RX recycle ring
* @revision: Hardware architecture revision
* @txd_ptr_tbl_base: TX descriptor ring base address
* @rxd_ptr_tbl_base: RX descriptor ring base address
size_t (*print_additional_fwver)(struct efx_nic *efx, char *buf,
size_t len);
void (*sensor_event)(struct efx_nic *efx, efx_qword_t *ev);
+ unsigned int (*rx_recycle_ring_size)(const struct efx_nic *efx);
int revision;
unsigned int txd_ptr_tbl_base;
efx->type->sensor_event(efx, ev);
}
+static inline unsigned int efx_rx_recycle_ring_size(const struct efx_nic *efx)
+{
+ return efx->type->rx_recycle_ring_size(efx);
+}
+
/* Some statistics are computed as A - B where A and B each increase
* linearly with some hardware counter(s) and the counters are read
* asynchronously. If the counters contributing to B are always read
MODULE_PARM_DESC(rx_refill_threshold,
"RX descriptor ring refill threshold (%)");
-/* Number of RX buffers to recycle pages for. When creating the RX page recycle
- * ring, this number is divided by the number of buffers per page to calculate
- * the number of pages to store in the RX page recycle ring.
- */
-#define EFX_RECYCLE_RING_SIZE_IOMMU 4096
-#define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
-
/* RX maximum head room required.
*
* This must be at least 1 to prevent overflow, plus one packet-worth
unsigned int bufs_in_recycle_ring, page_ring_size;
struct efx_nic *efx = rx_queue->efx;
- /* Set the RX recycle ring size */
-#ifdef CONFIG_PPC64
- bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
-#else
- if (iommu_present(&pci_bus_type))
- bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
- else
- bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU;
-#endif /* CONFIG_PPC64 */
-
+ bufs_in_recycle_ring = efx_rx_recycle_ring_size(efx);
page_ring_size = roundup_pow_of_two(bufs_in_recycle_ring /
efx->rx_bufs_per_page);
rx_queue->page_ring = kcalloc(page_ring_size,
#define EFX_RX_MAX_FRAGS DIV_ROUND_UP(EFX_MAX_FRAME_LEN(EFX_MAX_MTU), \
EFX_RX_USR_BUF_SIZE)
+/* Number of RX buffers to recycle pages for. When creating the RX page recycle
+ * ring, this number is divided by the number of buffers per page to calculate
+ * the number of pages to store in the RX page recycle ring.
+ */
+#define EFX_RECYCLE_RING_SIZE_10G 256
+
static inline u8 *efx_rx_buf_va(struct efx_rx_buffer *buf)
{
return page_address(buf->page) + buf->page_offset;
#include "mcdi_port_common.h"
#include "selftest.h"
#include "siena_sriov.h"
+#include "rx_common.h"
/* Hardware control for SFC9000 family including SFL9021 (aka Siena). */
return 0;
}
+static unsigned int efx_siena_recycle_ring_size(const struct efx_nic *efx)
+{
+ /* Maximum link speed is 10G */
+ return EFX_RECYCLE_RING_SIZE_10G;
+}
+
/**************************************************************************
*
* Revision-dependent attributes used by efx.c and nic.c
.rx_hash_key_size = 16,
.check_caps = siena_check_caps,
.sensor_event = efx_mcdi_sensor_event,
+ .rx_recycle_ring_size = efx_siena_recycle_ring_size,
};
#include <linux/of_net.h>
#include <linux/phy.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/regulator/consumer.h>
#include <linux/regmap.h>
#include <linux/stmmac.h>
};
/* struct sunxi_priv_data - hold all sunxi private data
- * @tx_clk: reference to MAC TX clock
* @ephy_clk: reference to the optional EPHY clock for the internal PHY
* @regulator: reference to the optional regulator
* @rst_ephy: reference to the optional EPHY reset for the internal PHY
* @mux_handle: Internal pointer used by mdio-mux lib
*/
struct sunxi_priv_data {
- struct clk *tx_clk;
struct clk *ephy_clk;
struct regulator *regulator;
struct reset_control *rst_ephy;
}
}
- ret = clk_prepare_enable(gmac->tx_clk);
- if (ret) {
- dev_err(&pdev->dev, "Could not enable AHB clock\n");
- goto err_disable_regulator;
- }
-
if (gmac->use_internal_phy) {
ret = sun8i_dwmac_power_internal_phy(netdev_priv(ndev));
if (ret)
- goto err_disable_clk;
+ goto err_disable_regulator;
}
return 0;
-err_disable_clk:
- clk_disable_unprepare(gmac->tx_clk);
err_disable_regulator:
if (gmac->regulator)
regulator_disable(gmac->regulator);
if (gmac->variant->soc_has_internal_phy)
sun8i_dwmac_unpower_internal_phy(gmac);
- clk_disable_unprepare(gmac->tx_clk);
-
if (gmac->regulator)
regulator_disable(gmac->regulator);
}
return -EINVAL;
}
- gmac->tx_clk = devm_clk_get(dev, "stmmaceth");
- if (IS_ERR(gmac->tx_clk)) {
- dev_err(dev, "Could not get TX clock\n");
- return PTR_ERR(gmac->tx_clk);
- }
-
/* Optional regulator for PHY */
gmac->regulator = devm_regulator_get_optional(dev, "phy");
if (IS_ERR(gmac->regulator)) {
ndev = dev_get_drvdata(&pdev->dev);
priv = netdev_priv(ndev);
+ /* the MAC is runtime suspended after stmmac_dvr_probe(), so we
+ * need to ensure the MAC resume back before other operations such
+ * as reset.
+ */
+ pm_runtime_get_sync(&pdev->dev);
+
/* The mux must be registered after parent MDIO
* so after stmmac_dvr_probe()
*/
goto dwmac_remove;
}
+ pm_runtime_put(&pdev->dev);
+
return 0;
dwmac_mux:
reset_control_put(gmac->rst_ephy);
clk_put(gmac->ephy_clk);
dwmac_remove:
+ pm_runtime_put_noidle(&pdev->dev);
stmmac_dvr_remove(&pdev->dev);
dwmac_exit:
sun8i_dwmac_exit(pdev, gmac);
priv->pause, tx_cnt);
}
-static void stmmac_validate(struct phylink_config *config,
- unsigned long *supported,
- struct phylink_link_state *state)
+static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config,
+ phy_interface_t interface)
{
struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mac_supported) = { 0, };
- __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
- int tx_cnt = priv->plat->tx_queues_to_use;
- int max_speed = priv->plat->max_speed;
-
- phylink_set(mac_supported, 10baseT_Half);
- phylink_set(mac_supported, 10baseT_Full);
- phylink_set(mac_supported, 100baseT_Half);
- phylink_set(mac_supported, 100baseT_Full);
- phylink_set(mac_supported, 1000baseT_Half);
- phylink_set(mac_supported, 1000baseT_Full);
- phylink_set(mac_supported, 1000baseKX_Full);
-
- phylink_set(mac_supported, Autoneg);
- phylink_set(mac_supported, Pause);
- phylink_set(mac_supported, Asym_Pause);
- phylink_set_port_modes(mac_supported);
-
- /* Cut down 1G if asked to */
- if ((max_speed > 0) && (max_speed < 1000)) {
- phylink_set(mask, 1000baseT_Full);
- phylink_set(mask, 1000baseX_Full);
- } else if (priv->plat->has_gmac4) {
- if (!max_speed || max_speed >= 2500) {
- phylink_set(mac_supported, 2500baseT_Full);
- phylink_set(mac_supported, 2500baseX_Full);
- }
- } else if (priv->plat->has_xgmac) {
- if (!max_speed || (max_speed >= 2500)) {
- phylink_set(mac_supported, 2500baseT_Full);
- phylink_set(mac_supported, 2500baseX_Full);
- }
- if (!max_speed || (max_speed >= 5000)) {
- phylink_set(mac_supported, 5000baseT_Full);
- }
- if (!max_speed || (max_speed >= 10000)) {
- phylink_set(mac_supported, 10000baseSR_Full);
- phylink_set(mac_supported, 10000baseLR_Full);
- phylink_set(mac_supported, 10000baseER_Full);
- phylink_set(mac_supported, 10000baseLRM_Full);
- phylink_set(mac_supported, 10000baseT_Full);
- phylink_set(mac_supported, 10000baseKX4_Full);
- phylink_set(mac_supported, 10000baseKR_Full);
- }
- if (!max_speed || (max_speed >= 25000)) {
- phylink_set(mac_supported, 25000baseCR_Full);
- phylink_set(mac_supported, 25000baseKR_Full);
- phylink_set(mac_supported, 25000baseSR_Full);
- }
- if (!max_speed || (max_speed >= 40000)) {
- phylink_set(mac_supported, 40000baseKR4_Full);
- phylink_set(mac_supported, 40000baseCR4_Full);
- phylink_set(mac_supported, 40000baseSR4_Full);
- phylink_set(mac_supported, 40000baseLR4_Full);
- }
- if (!max_speed || (max_speed >= 50000)) {
- phylink_set(mac_supported, 50000baseCR2_Full);
- phylink_set(mac_supported, 50000baseKR2_Full);
- phylink_set(mac_supported, 50000baseSR2_Full);
- phylink_set(mac_supported, 50000baseKR_Full);
- phylink_set(mac_supported, 50000baseSR_Full);
- phylink_set(mac_supported, 50000baseCR_Full);
- phylink_set(mac_supported, 50000baseLR_ER_FR_Full);
- phylink_set(mac_supported, 50000baseDR_Full);
- }
- if (!max_speed || (max_speed >= 100000)) {
- phylink_set(mac_supported, 100000baseKR4_Full);
- phylink_set(mac_supported, 100000baseSR4_Full);
- phylink_set(mac_supported, 100000baseCR4_Full);
- phylink_set(mac_supported, 100000baseLR4_ER4_Full);
- phylink_set(mac_supported, 100000baseKR2_Full);
- phylink_set(mac_supported, 100000baseSR2_Full);
- phylink_set(mac_supported, 100000baseCR2_Full);
- phylink_set(mac_supported, 100000baseLR2_ER2_FR2_Full);
- phylink_set(mac_supported, 100000baseDR2_Full);
- }
- }
-
- /* Half-Duplex can only work with single queue */
- if (tx_cnt > 1) {
- phylink_set(mask, 10baseT_Half);
- phylink_set(mask, 100baseT_Half);
- phylink_set(mask, 1000baseT_Half);
- }
-
- linkmode_and(supported, supported, mac_supported);
- linkmode_andnot(supported, supported, mask);
- linkmode_and(state->advertising, state->advertising, mac_supported);
- linkmode_andnot(state->advertising, state->advertising, mask);
+ if (!priv->hw->xpcs)
+ return NULL;
- /* If PCS is supported, check which modes it supports. */
- if (priv->hw->xpcs)
- xpcs_validate(priv->hw->xpcs, supported, state);
+ return &priv->hw->xpcs->pcs;
}
static void stmmac_mac_config(struct phylink_config *config, unsigned int mode,
}
static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
- .validate = stmmac_validate,
+ .validate = phylink_generic_validate,
+ .mac_select_pcs = stmmac_mac_select_pcs,
.mac_config = stmmac_mac_config,
.mac_link_down = stmmac_mac_link_down,
.mac_link_up = stmmac_mac_link_up,
{
struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node);
+ int max_speed = priv->plat->max_speed;
int mode = priv->plat->phy_interface;
struct phylink *phylink;
priv->phylink_config.dev = &priv->dev->dev;
priv->phylink_config.type = PHYLINK_NETDEV;
- priv->phylink_config.pcs_poll = true;
if (priv->plat->mdio_bus_data)
priv->phylink_config.ovr_an_inband =
mdio_bus_data->xpcs_an_inband;
if (!fwnode)
fwnode = dev_fwnode(priv->device);
+ /* Set the platform/firmware specified interface mode */
+ __set_bit(mode, priv->phylink_config.supported_interfaces);
+
+ /* If we have an xpcs, it defines which PHY interfaces are supported. */
+ if (priv->hw->xpcs)
+ xpcs_get_interfaces(priv->hw->xpcs,
+ priv->phylink_config.supported_interfaces);
+
+ priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+ MAC_10 | MAC_100;
+
+ if (!max_speed || max_speed >= 1000)
+ priv->phylink_config.mac_capabilities |= MAC_1000;
+
+ if (priv->plat->has_gmac4) {
+ if (!max_speed || max_speed >= 2500)
+ priv->phylink_config.mac_capabilities |= MAC_2500FD;
+ } else if (priv->plat->has_xgmac) {
+ if (!max_speed || max_speed >= 2500)
+ priv->phylink_config.mac_capabilities |= MAC_2500FD;
+ if (!max_speed || max_speed >= 5000)
+ priv->phylink_config.mac_capabilities |= MAC_5000FD;
+ if (!max_speed || max_speed >= 10000)
+ priv->phylink_config.mac_capabilities |= MAC_10000FD;
+ if (!max_speed || max_speed >= 25000)
+ priv->phylink_config.mac_capabilities |= MAC_25000FD;
+ if (!max_speed || max_speed >= 40000)
+ priv->phylink_config.mac_capabilities |= MAC_40000FD;
+ if (!max_speed || max_speed >= 50000)
+ priv->phylink_config.mac_capabilities |= MAC_50000FD;
+ if (!max_speed || max_speed >= 100000)
+ priv->phylink_config.mac_capabilities |= MAC_100000FD;
+ }
+
+ /* Half-Duplex can only work with single queue */
+ if (priv->plat->tx_queues_to_use > 1)
+ priv->phylink_config.mac_capabilities &=
+ ~(MAC_10HD | MAC_100HD | MAC_1000HD);
+
phylink = phylink_create(&priv->phylink_config, fwnode,
mode, &stmmac_phylink_mac_ops);
if (IS_ERR(phylink))
return PTR_ERR(phylink);
- if (priv->hw->xpcs)
- phylink_set_pcs(phylink, &priv->hw->xpcs->pcs);
-
priv->phylink = phylink;
return 0;
}
* @phylink: Pointer to phylink instance
* @phylink_config: phylink configuration settings
* @pcs_phy: Reference to PCS/PMA PHY if used
+ * @pcs: phylink pcs structure for PCS PHY
* @switch_x_sgmii: Whether switchable 1000BaseX/SGMII mode is enabled in the core
* @axi_clk: AXI4-Lite bus clock
* @misc_clks: Misc ethernet clocks (AXI4-Stream, Ref, MGT clocks)
struct phylink_config phylink_config;
struct mdio_device *pcs_phy;
+ struct phylink_pcs pcs;
bool switch_x_sgmii;
.nway_reset = axienet_ethtools_nway_reset,
};
-static void axienet_mac_pcs_get_state(struct phylink_config *config,
- struct phylink_link_state *state)
+static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs)
{
- struct net_device *ndev = to_net_dev(config->dev);
- struct axienet_local *lp = netdev_priv(ndev);
+ return container_of(pcs, struct axienet_local, pcs);
+}
- switch (state->interface) {
- case PHY_INTERFACE_MODE_SGMII:
- case PHY_INTERFACE_MODE_1000BASEX:
- phylink_mii_c22_pcs_get_state(lp->pcs_phy, state);
- break;
- default:
- break;
- }
+static void axienet_pcs_get_state(struct phylink_pcs *pcs,
+ struct phylink_link_state *state)
+{
+ struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy;
+
+ phylink_mii_c22_pcs_get_state(pcs_phy, state);
}
-static void axienet_mac_an_restart(struct phylink_config *config)
+static void axienet_pcs_an_restart(struct phylink_pcs *pcs)
{
- struct net_device *ndev = to_net_dev(config->dev);
- struct axienet_local *lp = netdev_priv(ndev);
+ struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy;
- phylink_mii_c22_pcs_an_restart(lp->pcs_phy);
+ phylink_mii_c22_pcs_an_restart(pcs_phy);
}
-static int axienet_mac_prepare(struct phylink_config *config, unsigned int mode,
- phy_interface_t iface)
+static int axienet_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
+ phy_interface_t interface,
+ const unsigned long *advertising,
+ bool permit_pause_to_mac)
{
- struct net_device *ndev = to_net_dev(config->dev);
+ struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy;
+ struct net_device *ndev = pcs_to_axienet_local(pcs)->ndev;
struct axienet_local *lp = netdev_priv(ndev);
int ret;
- switch (iface) {
- case PHY_INTERFACE_MODE_SGMII:
- case PHY_INTERFACE_MODE_1000BASEX:
- if (!lp->switch_x_sgmii)
- return 0;
-
- ret = mdiobus_write(lp->pcs_phy->bus,
- lp->pcs_phy->addr,
- XLNX_MII_STD_SELECT_REG,
- iface == PHY_INTERFACE_MODE_SGMII ?
+ if (lp->switch_x_sgmii) {
+ ret = mdiodev_write(pcs_phy, XLNX_MII_STD_SELECT_REG,
+ interface == PHY_INTERFACE_MODE_SGMII ?
XLNX_MII_STD_SELECT_SGMII : 0);
- if (ret < 0)
- netdev_warn(ndev, "Failed to switch PHY interface: %d\n",
+ if (ret < 0) {
+ netdev_warn(ndev,
+ "Failed to switch PHY interface: %d\n",
ret);
- return ret;
- default:
- return 0;
+ return ret;
+ }
}
+
+ ret = phylink_mii_c22_pcs_config(pcs_phy, mode, interface, advertising);
+ if (ret < 0)
+ netdev_warn(ndev, "Failed to configure PCS: %d\n", ret);
+
+ return ret;
}
-static void axienet_mac_config(struct phylink_config *config, unsigned int mode,
- const struct phylink_link_state *state)
+static const struct phylink_pcs_ops axienet_pcs_ops = {
+ .pcs_get_state = axienet_pcs_get_state,
+ .pcs_config = axienet_pcs_config,
+ .pcs_an_restart = axienet_pcs_an_restart,
+};
+
+static struct phylink_pcs *axienet_mac_select_pcs(struct phylink_config *config,
+ phy_interface_t interface)
{
struct net_device *ndev = to_net_dev(config->dev);
struct axienet_local *lp = netdev_priv(ndev);
- int ret;
- switch (state->interface) {
- case PHY_INTERFACE_MODE_SGMII:
- case PHY_INTERFACE_MODE_1000BASEX:
- ret = phylink_mii_c22_pcs_config(lp->pcs_phy, mode,
- state->interface,
- state->advertising);
- if (ret < 0)
- netdev_warn(ndev, "Failed to configure PCS: %d\n",
- ret);
- break;
+ if (interface == PHY_INTERFACE_MODE_1000BASEX ||
+ interface == PHY_INTERFACE_MODE_SGMII)
+ return &lp->pcs;
- default:
- break;
- }
+ return NULL;
+}
+
+static void axienet_mac_config(struct phylink_config *config, unsigned int mode,
+ const struct phylink_link_state *state)
+{
+ /* nothing meaningful to do */
}
static void axienet_mac_link_down(struct phylink_config *config,
static const struct phylink_mac_ops axienet_phylink_ops = {
.validate = phylink_generic_validate,
- .mac_pcs_get_state = axienet_mac_pcs_get_state,
- .mac_an_restart = axienet_mac_an_restart,
- .mac_prepare = axienet_mac_prepare,
+ .mac_select_pcs = axienet_mac_select_pcs,
.mac_config = axienet_mac_config,
.mac_link_down = axienet_mac_link_down,
.mac_link_up = axienet_mac_link_up,
ret = -EPROBE_DEFER;
goto cleanup_mdio;
}
- lp->phylink_config.pcs_poll = true;
+ lp->pcs.ops = &axienet_pcs_ops;
+ lp->pcs.poll = true;
}
lp->phylink_config.dev = &ndev->dev;
lp->phylink_config.type = PHYLINK_NETDEV;
- lp->phylink_config.legacy_pre_march2020 = true;
lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE |
MAC_10FD | MAC_100FD | MAC_1000FD;
{
struct acpi_device *device;
bool *found = context;
- int result;
- result = acpi_bus_get_device(obj_handle, &device);
- if (result)
+ device = acpi_fetch_acpi_dev(obj_handle);
+ if (!device)
return AE_OK;
if (strcmp(acpi_device_hid(device), ACPI_MOTHERBOARD_RESOURCE_HID))
.aggregation = true,
.status_enable = true,
.rx = {
+ .buffer_size = 8192,
.pad_align = ilog2(sizeof(u32)),
},
},
.qmap = true,
.aggregation = true,
.rx = {
+ .buffer_size = 8192,
.aggr_close_eof = true,
},
},
.aggregation = true,
.status_enable = true,
.rx = {
+ .buffer_size = 8192,
.pad_align = ilog2(sizeof(u32)),
},
},
.qmap = true,
.aggregation = true,
.rx = {
+ .buffer_size = 8192,
.aggr_close_eof = true,
},
},
.aggregation = true,
.status_enable = true,
.rx = {
+ .buffer_size = 8192,
.pad_align = ilog2(sizeof(u32)),
},
},
.qmap = true,
.aggregation = true,
.rx = {
+ .buffer_size = 32768,
.aggr_close_eof = true,
},
},
.aggregation = true,
.status_enable = true,
.rx = {
+ .buffer_size = 8192,
.pad_align = ilog2(sizeof(u32)),
},
},
.qmap = true,
.aggregation = true,
.rx = {
+ .buffer_size = 8192,
.aggr_close_eof = true,
},
},
.aggregation = true,
.status_enable = true,
.rx = {
+ .buffer_size = 8192,
.pad_align = ilog2(sizeof(u32)),
},
},
.qmap = true,
.aggregation = true,
.rx = {
+ .buffer_size = 8192,
.aggr_close_eof = true,
},
},
.aggregation = true,
.status_enable = true,
.rx = {
+ .buffer_size = 8192,
.pad_align = ilog2(sizeof(u32)),
},
},
.qmap = true,
.aggregation = true,
.rx = {
+ .buffer_size = 8192,
.aggr_close_eof = true,
},
},
/**
* struct ipa_endpoint_rx_data - configuration data for RX endpoints
+ * @buffer_size: requested receive buffer size (bytes)
* @pad_align: power-of-2 boundary to which packet payload is aligned
* @aggr_close_eof: whether aggregation closes on end-of-frame
*
* a "frame" consisting of several transfers has ended.
*/
struct ipa_endpoint_rx_data {
+ u32 buffer_size;
u32 pad_align;
bool aggr_close_eof;
};
#define IPA_REPLENISH_BATCH 16
-/* RX buffer is 1 page (or a power-of-2 contiguous pages) */
-#define IPA_RX_BUFFER_SIZE 8192 /* PAGE_SIZE > 4096 wastes a LOT */
-
/* The amount of RX buffer space consumed by standard skb overhead */
#define IPA_RX_BUFFER_OVERHEAD (PAGE_SIZE - SKB_MAX_ORDER(NET_SKB_PAD, 0))
#define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK GENMASK(31, 22)
#define IPA_STATUS_FLAGS2_TAG_FMASK GENMASK_ULL(63, 16)
+static u32 aggr_byte_limit_max(enum ipa_version version)
+{
+ if (version < IPA_VERSION_4_5)
+ return field_max(aggr_byte_limit_fmask(true));
+
+ return field_max(aggr_byte_limit_fmask(false));
+}
+
static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count,
const struct ipa_gsi_endpoint_data *all_data,
const struct ipa_gsi_endpoint_data *data)
return true;
if (!data->toward_ipa) {
+ u32 buffer_size;
+ u32 limit;
+
if (data->endpoint.filter_support) {
dev_err(dev, "filtering not supported for "
"RX endpoint %u\n",
return false;
}
+ /* Nothing more to check for non-AP RX */
+ if (data->ee_id != GSI_EE_AP)
+ return true;
+
+ buffer_size = data->endpoint.config.rx.buffer_size;
+ /* The buffer size must hold an MTU plus overhead */
+ limit = IPA_MTU + IPA_RX_BUFFER_OVERHEAD;
+ if (buffer_size < limit) {
+ dev_err(dev, "RX buffer size too small for RX endpoint %u (%u < %u)\n",
+ data->endpoint_id, buffer_size, limit);
+ return false;
+ }
+
+ /* For an endpoint supporting receive aggregation, the
+ * aggregation byte limit defines the point at which an
+ * aggregation window will close. It is programmed into the
+ * IPA hardware as a number of KB. We don't use "hard byte
+ * limit" aggregation, so we need to supply enough space in
+ * a receive buffer to hold a complete MTU plus normal skb
+ * overhead *after* that aggregation byte limit has been
+ * crossed.
+ *
+ * This check just ensures the receive buffer size doesn't
+ * exceed what's representable in the aggregation limit field.
+ */
+ if (data->endpoint.config.aggregation) {
+ limit += SZ_1K * aggr_byte_limit_max(ipa->version);
+ if (buffer_size > limit) {
+ dev_err(dev, "RX buffer size too large for aggregated RX endpoint %u (%u > %u)\n",
+ data->endpoint_id, buffer_size, limit);
+
+ return false;
+ }
+ }
+
return true; /* Nothing more to check for RX */
}
return true;
}
-static u32 aggr_byte_limit_max(enum ipa_version version)
-{
- if (version < IPA_VERSION_4_5)
- return field_max(aggr_byte_limit_fmask(true));
-
- return field_max(aggr_byte_limit_fmask(false));
-}
-
static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count,
const struct ipa_gsi_endpoint_data *data)
{
const struct ipa_gsi_endpoint_data *dp = data;
struct device *dev = &ipa->pdev->dev;
enum ipa_endpoint_name name;
- u32 limit;
if (count > IPA_ENDPOINT_COUNT) {
dev_err(dev, "too many endpoints specified (%u > %u)\n",
return false;
}
- /* The aggregation byte limit defines the point at which an
- * aggregation window will close. It is programmed into the
- * IPA hardware as a number of KB. We don't use "hard byte
- * limit" aggregation, which means that we need to supply
- * enough space in a receive buffer to hold a complete MTU
- * plus normal skb overhead *after* that aggregation byte
- * limit has been crossed.
- *
- * This check ensures we don't define a receive buffer size
- * that would exceed what we can represent in the field that
- * is used to program its size.
- */
- limit = aggr_byte_limit_max(ipa->version) * SZ_1K;
- limit += IPA_MTU + IPA_RX_BUFFER_OVERHEAD;
- if (limit < IPA_RX_BUFFER_SIZE) {
- dev_err(dev, "buffer size too big for aggregation (%u > %u)\n",
- IPA_RX_BUFFER_SIZE, limit);
- return false;
- }
-
/* Make sure needed endpoints have defined data */
if (ipa_gsi_endpoint_data_empty(&data[IPA_ENDPOINT_AP_COMMAND_TX])) {
dev_err(dev, "command TX endpoint not defined\n");
if (endpoint->data->aggregation) {
if (!endpoint->toward_ipa) {
+ const struct ipa_endpoint_rx_data *rx_data;
bool close_eof;
u32 limit;
+ rx_data = &endpoint->data->rx;
val |= u32_encode_bits(IPA_ENABLE_AGGR, AGGR_EN_FMASK);
val |= u32_encode_bits(IPA_GENERIC, AGGR_TYPE_FMASK);
- limit = ipa_aggr_size_kb(IPA_RX_BUFFER_SIZE);
+ limit = ipa_aggr_size_kb(rx_data->buffer_size);
val |= aggr_byte_limit_encoded(version, limit);
limit = IPA_AGGR_TIME_LIMIT;
/* AGGR_PKT_LIMIT is 0 (unlimited) */
- close_eof = endpoint->data->rx.aggr_close_eof;
+ close_eof = rx_data->aggr_close_eof;
val |= aggr_sw_eof_active_encoded(version, close_eof);
/* AGGR_HARD_BYTE_LIMIT_ENABLE is 0 */
struct gsi_trans *trans;
bool doorbell = false;
struct page *page;
+ u32 buffer_size;
u32 offset;
u32 len;
int ret;
- page = dev_alloc_pages(get_order(IPA_RX_BUFFER_SIZE));
+ buffer_size = endpoint->data->rx.buffer_size;
+ page = dev_alloc_pages(get_order(buffer_size));
if (!page)
return -ENOMEM;
/* Offset the buffer to make space for skb headroom */
offset = NET_SKB_PAD;
- len = IPA_RX_BUFFER_SIZE - offset;
+ len = buffer_size - offset;
ret = gsi_trans_page_add(trans, page, len, offset);
if (ret)
err_trans_free:
gsi_trans_free(trans);
err_free_pages:
- __free_pages(page, get_order(IPA_RX_BUFFER_SIZE));
+ __free_pages(page, get_order(buffer_size));
return -ENOMEM;
}
static bool ipa_endpoint_skb_build(struct ipa_endpoint *endpoint,
struct page *page, u32 len)
{
+ u32 buffer_size = endpoint->data->rx.buffer_size;
struct sk_buff *skb;
/* Nothing to do if there's no netdev */
if (!endpoint->netdev)
return false;
- WARN_ON(len > SKB_WITH_OVERHEAD(IPA_RX_BUFFER_SIZE - NET_SKB_PAD));
+ WARN_ON(len > SKB_WITH_OVERHEAD(buffer_size - NET_SKB_PAD));
- skb = build_skb(page_address(page), IPA_RX_BUFFER_SIZE);
+ skb = build_skb(page_address(page), buffer_size);
if (skb) {
/* Reserve the headroom and account for the data */
skb_reserve(skb, NET_SKB_PAD);
static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint,
struct page *page, u32 total_len)
{
+ u32 buffer_size = endpoint->data->rx.buffer_size;
void *data = page_address(page) + NET_SKB_PAD;
- u32 unused = IPA_RX_BUFFER_SIZE - total_len;
+ u32 unused = buffer_size - total_len;
u32 resid = total_len;
while (resid) {
} else {
struct page *page = trans->data;
- if (page)
- __free_pages(page, get_order(IPA_RX_BUFFER_SIZE));
+ if (page) {
+ u32 buffer_size = endpoint->data->rx.buffer_size;
+
+ __free_pages(page, get_order(buffer_size));
+ }
}
}
const union acpi_object *obj;
u32 phy_addr;
- if (acpi_bus_get_device(handle, &adev))
+ adev = acpi_fetch_acpi_dev(handle);
+ if (!adev)
return AE_OK;
if (acpi_dev_get_property(adev, "phy-channel", ACPI_TYPE_INTEGER, &obj))
}
}
-void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported,
- struct phylink_link_state *state)
+static int xpcs_validate(struct phylink_pcs *pcs, unsigned long *supported,
+ const struct phylink_link_state *state)
{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported);
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported) = { 0, };
const struct xpcs_compat *compat;
+ struct dw_xpcs *xpcs;
int i;
- /* phylink expects us to report all supported modes with
- * PHY_INTERFACE_MODE_NA, just don't limit the supported and
- * advertising masks and exit.
- */
- if (state->interface == PHY_INTERFACE_MODE_NA)
- return;
-
- linkmode_zero(xpcs_supported);
-
+ xpcs = phylink_pcs_to_xpcs(pcs);
compat = xpcs_find_compat(xpcs->id, state->interface);
- /* Populate the supported link modes for this
- * PHY interface type
+ /* Populate the supported link modes for this PHY interface type.
+ * FIXME: what about the port modes and autoneg bit? This masks
+ * all those away.
*/
if (compat)
for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++)
set_bit(compat->supported[i], xpcs_supported);
linkmode_and(supported, supported, xpcs_supported);
- linkmode_and(state->advertising, state->advertising, xpcs_supported);
+
+ return 0;
+}
+
+void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces)
+{
+ int i, j;
+
+ for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) {
+ const struct xpcs_compat *compat = &xpcs->id->compat[i];
+
+ for (j = 0; j < compat->num_interfaces; j++)
+ if (compat->interface[j] < PHY_INTERFACE_MODE_MAX)
+ __set_bit(compat->interface[j], interfaces);
+ }
}
-EXPORT_SYMBOL_GPL(xpcs_validate);
+EXPORT_SYMBOL_GPL(xpcs_get_interfaces);
int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable)
{
};
static const struct phylink_pcs_ops xpcs_phylink_ops = {
+ .pcs_validate = xpcs_validate,
.pcs_config = xpcs_config,
.pcs_get_state = xpcs_get_state,
.pcs_link_up = xpcs_link_up,
* PMA speed ability bits are the same for all members of the family,
* AQCS109 however supports speeds up to 2.5G only.
*/
- ret = phy_set_max_speed(phydev, SPEED_2500);
- if (ret)
- return ret;
+ phy_set_max_speed(phydev, SPEED_2500);
return aqr107_set_downshift(phydev, MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT);
}
#include <linux/regulator/of_regulator.h>
#include <linux/regulator/driver.h>
#include <linux/regulator/consumer.h>
+#include <linux/phylink.h>
+#include <linux/sfp.h>
#include <dt-bindings/net/qca-ar803x.h>
#define AT803X_SPECIFIC_FUNCTION_CONTROL 0x10
#define AT803X_INTR_ENABLE_PAGE_RECEIVED BIT(12)
#define AT803X_INTR_ENABLE_LINK_FAIL BIT(11)
#define AT803X_INTR_ENABLE_LINK_SUCCESS BIT(10)
+#define AT803X_INTR_ENABLE_LINK_FAIL_BX BIT(8)
+#define AT803X_INTR_ENABLE_LINK_SUCCESS_BX BIT(7)
#define AT803X_INTR_ENABLE_WIRESPEED_DOWNGRADE BIT(5)
#define AT803X_INTR_ENABLE_POLARITY_CHANGED BIT(1)
#define AT803X_INTR_ENABLE_WOL BIT(0)
#define AT803X_DEBUG_DATA 0x1E
#define AT803X_MODE_CFG_MASK 0x0F
-#define AT803X_MODE_CFG_SGMII 0x01
+#define AT803X_MODE_CFG_BASET_RGMII 0x00
+#define AT803X_MODE_CFG_BASET_SGMII 0x01
+#define AT803X_MODE_CFG_BX1000_RGMII_50OHM 0x02
+#define AT803X_MODE_CFG_BX1000_RGMII_75OHM 0x03
+#define AT803X_MODE_CFG_BX1000_CONV_50OHM 0x04
+#define AT803X_MODE_CFG_BX1000_CONV_75OHM 0x05
+#define AT803X_MODE_CFG_FX100_RGMII_50OHM 0x06
+#define AT803X_MODE_CFG_FX100_CONV_50OHM 0x07
+#define AT803X_MODE_CFG_RGMII_AUTO_MDET 0x0B
+#define AT803X_MODE_CFG_FX100_RGMII_75OHM 0x0E
+#define AT803X_MODE_CFG_FX100_CONV_75OHM 0x0F
#define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/
#define AT803X_PSSR_MR_AN_COMPLETE 0x0200
u16 clk_25m_mask;
u8 smarteee_lpi_tw_1g;
u8 smarteee_lpi_tw_100m;
+ bool is_fiber;
+ bool is_1000basex;
struct regulator_dev *vddio_rdev;
struct regulator_dev *vddh_rdev;
struct regulator *vddio;
return 0;
}
+static int at803x_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
+{
+ struct phy_device *phydev = upstream;
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_support);
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support);
+ phy_interface_t iface;
+
+ linkmode_zero(phy_support);
+ phylink_set(phy_support, 1000baseX_Full);
+ phylink_set(phy_support, 1000baseT_Full);
+ phylink_set(phy_support, Autoneg);
+ phylink_set(phy_support, Pause);
+ phylink_set(phy_support, Asym_Pause);
+
+ linkmode_zero(sfp_support);
+ sfp_parse_support(phydev->sfp_bus, id, sfp_support);
+ /* Some modules support 10G modes as well as others we support.
+ * Mask out non-supported modes so the correct interface is picked.
+ */
+ linkmode_and(sfp_support, phy_support, sfp_support);
+
+ if (linkmode_empty(sfp_support)) {
+ dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n");
+ return -EINVAL;
+ }
+
+ iface = sfp_select_interface(phydev->sfp_bus, sfp_support);
+
+ /* Only 1000Base-X is supported by AR8031/8033 as the downstream SerDes
+ * interface for use with SFP modules.
+ * However, some copper modules detected as having a preferred SGMII
+ * interface do default to and function in 1000Base-X mode, so just
+ * print a warning and allow such modules, as they may have some chance
+ * of working.
+ */
+ if (iface == PHY_INTERFACE_MODE_SGMII)
+ dev_warn(&phydev->mdio.dev, "module may not function if 1000Base-X not supported\n");
+ else if (iface != PHY_INTERFACE_MODE_1000BASEX)
+ return -EINVAL;
+
+ return 0;
+}
+
+static const struct sfp_upstream_ops at803x_sfp_ops = {
+ .attach = phy_sfp_attach,
+ .detach = phy_sfp_detach,
+ .module_insert = at803x_sfp_insert,
+};
+
static int at803x_parse_dt(struct phy_device *phydev)
{
struct device_node *node = phydev->mdio.dev.of_node;
phydev_err(phydev, "failed to get VDDIO regulator\n");
return PTR_ERR(priv->vddio);
}
+
+ /* Only AR8031/8033 support 1000Base-X for SFP modules */
+ ret = phy_sfp_probe(phydev, &at803x_sfp_ops);
+ if (ret < 0)
+ return ret;
}
return 0;
return ret;
}
- /* Some bootloaders leave the fiber page selected.
- * Switch to the copper page, as otherwise we read
- * the PHY capabilities from the fiber side.
- */
if (phydev->drv->phy_id == ATH8031_PHY_ID) {
- phy_lock_mdio_bus(phydev);
- ret = at803x_write_page(phydev, AT803X_PAGE_COPPER);
- phy_unlock_mdio_bus(phydev);
- if (ret)
+ int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG);
+ int mode_cfg;
+
+ if (ccr < 0)
goto err;
+ mode_cfg = ccr & AT803X_MODE_CFG_MASK;
+
+ switch (mode_cfg) {
+ case AT803X_MODE_CFG_BX1000_RGMII_50OHM:
+ case AT803X_MODE_CFG_BX1000_RGMII_75OHM:
+ priv->is_1000basex = true;
+ fallthrough;
+ case AT803X_MODE_CFG_FX100_RGMII_50OHM:
+ case AT803X_MODE_CFG_FX100_RGMII_75OHM:
+ priv->is_fiber = true;
+ break;
+ }
}
return 0;
static int at803x_get_features(struct phy_device *phydev)
{
+ struct at803x_priv *priv = phydev->priv;
int err;
err = genphy_read_abilities(phydev);
* As a result of that, ESTATUS_1000_XFULL is set
* to 1 even when operating in copper TP mode.
*
- * Remove this mode from the supported link modes,
- * as this driver currently only supports copper
- * operation.
+ * Remove this mode from the supported link modes
+ * when not operating in 1000BaseX mode.
*/
- linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
- phydev->supported);
+ if (!priv->is_1000basex)
+ linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
+ phydev->supported);
+
return 0;
}
static int at803x_config_init(struct phy_device *phydev)
{
+ struct at803x_priv *priv = phydev->priv;
int ret;
+ if (phydev->drv->phy_id == ATH8031_PHY_ID) {
+ /* Some bootloaders leave the fiber page selected.
+ * Switch to the appropriate page (fiber or copper), as otherwise we
+ * read the PHY capabilities from the wrong page.
+ */
+ phy_lock_mdio_bus(phydev);
+ ret = at803x_write_page(phydev,
+ priv->is_fiber ? AT803X_PAGE_FIBER :
+ AT803X_PAGE_COPPER);
+ phy_unlock_mdio_bus(phydev);
+ if (ret)
+ return ret;
+
+ ret = at8031_pll_config(phydev);
+ if (ret < 0)
+ return ret;
+ }
+
/* The RX and TX delay default is:
* after HW reset: RX delay enabled and TX delay disabled
* after SW reset: RX delay enabled, while TX delay retains the
if (ret < 0)
return ret;
- if (phydev->drv->phy_id == ATH8031_PHY_ID) {
- ret = at8031_pll_config(phydev);
- if (ret < 0)
- return ret;
- }
-
/* Ar803x extended next page bit is enabled by default. Cisco
* multigig switches read this bit and attempt to negotiate 10Gbps
* rates even if the next page bit is disabled. This is incorrect
static int at803x_config_intr(struct phy_device *phydev)
{
+ struct at803x_priv *priv = phydev->priv;
int err;
int value;
value |= AT803X_INTR_ENABLE_DUPLEX_CHANGED;
value |= AT803X_INTR_ENABLE_LINK_FAIL;
value |= AT803X_INTR_ENABLE_LINK_SUCCESS;
+ if (priv->is_fiber) {
+ value |= AT803X_INTR_ENABLE_LINK_FAIL_BX;
+ value |= AT803X_INTR_ENABLE_LINK_SUCCESS_BX;
+ }
err = phy_write(phydev, AT803X_INTR_ENABLE, value);
} else {
static int at803x_read_status(struct phy_device *phydev)
{
+ struct at803x_priv *priv = phydev->priv;
int err, old_link = phydev->link;
+ if (priv->is_1000basex)
+ return genphy_c37_read_status(phydev);
+
/* Update the link, but return if there was an error */
err = genphy_update_link(phydev);
if (err)
static int at803x_config_aneg(struct phy_device *phydev)
{
+ struct at803x_priv *priv = phydev->priv;
int ret;
ret = at803x_config_mdix(phydev, phydev->mdix_ctrl);
return ret;
}
+ if (priv->is_1000basex)
+ return genphy_c37_config_aneg(phydev);
+
/* Do not restart auto-negotiation by setting ret to 0 defautly,
* when calling __genphy_config_aneg later.
*/
return count;
}
-static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr)
+static void __set_linkmode_max_speed(u32 max_speed, unsigned long *addr)
{
const struct phy_setting *p;
int i;
else
break;
}
-
- return 0;
}
-static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
+static void __set_phy_supported(struct phy_device *phydev, u32 max_speed)
{
- return __set_linkmode_max_speed(max_speed, phydev->supported);
+ __set_linkmode_max_speed(max_speed, phydev->supported);
}
/**
* is connected to a 1G PHY. This function allows the MAC to indicate its
* maximum speed, and so limit what the PHY will advertise.
*/
-int phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
+void phy_set_max_speed(struct phy_device *phydev, u32 max_speed)
{
- int err;
-
- err = __set_phy_supported(phydev, max_speed);
- if (err)
- return err;
+ __set_phy_supported(phydev, max_speed);
phy_advertise_supported(phydev);
-
- return 0;
}
EXPORT_SYMBOL(phy_set_max_speed);
if (min_common_speed == SPEED_UNKNOWN)
return -EINVAL;
- return __set_linkmode_max_speed(min_common_speed, phydev->advertising);
+ __set_linkmode_max_speed(min_common_speed, phydev->advertising);
+
+ return 0;
}
static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad,
reg = asix_mdio_read(dev->net, dev->mii.phy_id,
MII_MARVELL_LED_CTRL);
netdev_dbg(dev->net, "MII_MARVELL_LED_CTRL (2) = 0x%04x\n", reg);
- reg &= 0xfc0f;
}
return 0;
int st_nci_vendor_cmds_init(struct nci_dev *ndev)
{
- return nfc_set_vendor_cmds(ndev->nfc_dev, st_nci_vendor_cmds,
+ return nci_set_vendor_cmds(ndev, st_nci_vendor_cmds,
sizeof(st_nci_vendor_cmds));
}
EXPORT_SYMBOL(st_nci_vendor_cmds_init);
struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev);
init_completion(&info->vendor_info.req_completion);
- return nfc_set_vendor_cmds(hdev->ndev, st21nfca_vendor_cmds,
- sizeof(st21nfca_vendor_cmds));
+ return nfc_hci_set_vendor_cmds(hdev, st21nfca_vendor_cmds,
+ sizeof(st21nfca_vendor_cmds));
}
EXPORT_SYMBOL(st21nfca_vendor_cmds_init);
}
EXPORT_SYMBOL(ptp_clock_register);
+static int unregister_vclock(struct device *dev, void *data)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+
+ ptp_vclock_unregister(info_to_vclock(ptp->info));
+ return 0;
+}
+
int ptp_clock_unregister(struct ptp_clock *ptp)
{
if (ptp_vclock_in_use(ptp)) {
- pr_err("ptp: virtual clock in use\n");
- return -EBUSY;
+ device_for_each_child(&ptp->dev, NULL, unregister_vclock);
}
ptp->defunct = 1;
struct device_attribute *attr, char *page)
{
struct ptp_clock *ptp = dev_get_drvdata(dev);
- return snprintf(page, PAGE_SIZE-1, "%s\n", ptp->info->name);
+ return sysfs_emit(page, "%s\n", ptp->info->name);
}
static DEVICE_ATTR_RO(clock_name);
mutex_unlock(&ptp->pincfg_mux);
- return snprintf(page, PAGE_SIZE, "%u %u\n", func, chan);
+ return sysfs_emit(page, "%u %u\n", func, chan);
}
static ssize_t ptp_pin_store(struct device *dev, struct device_attribute *attr,
return 0;
}
+static int ptp_vclock_gettimex(struct ptp_clock_info *ptp,
+ struct timespec64 *ts,
+ struct ptp_system_timestamp *sts)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ struct ptp_clock *pptp = vclock->pclock;
+ struct timespec64 pts;
+ unsigned long flags;
+ int err;
+ u64 ns;
+
+ err = pptp->info->gettimex64(pptp->info, &pts, sts);
+ if (err)
+ return err;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ ns = timecounter_cyc2time(&vclock->tc, timespec64_to_ns(&pts));
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ *ts = ns_to_timespec64(ns);
+
+ return 0;
+}
+
static int ptp_vclock_settime(struct ptp_clock_info *ptp,
const struct timespec64 *ts)
{
return 0;
}
+static int ptp_vclock_getcrosststamp(struct ptp_clock_info *ptp,
+ struct system_device_crosststamp *xtstamp)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ struct ptp_clock *pptp = vclock->pclock;
+ unsigned long flags;
+ int err;
+ u64 ns;
+
+ err = pptp->info->getcrosststamp(pptp->info, xtstamp);
+ if (err)
+ return err;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ ns = timecounter_cyc2time(&vclock->tc, ktime_to_ns(xtstamp->device));
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ xtstamp->device = ns_to_ktime(ns);
+
+ return 0;
+}
+
static long ptp_vclock_refresh(struct ptp_clock_info *ptp)
{
struct ptp_vclock *vclock = info_to_vclock(ptp);
static const struct ptp_clock_info ptp_vclock_info = {
.owner = THIS_MODULE,
.name = "ptp virtual clock",
- /* The maximum ppb value that long scaled_ppm can support */
- .max_adj = 32767999,
+ .max_adj = 500000000,
.adjfine = ptp_vclock_adjfine,
.adjtime = ptp_vclock_adjtime,
- .gettime64 = ptp_vclock_gettime,
.settime64 = ptp_vclock_settime,
.do_aux_work = ptp_vclock_refresh,
};
vclock->pclock = pclock;
vclock->info = ptp_vclock_info;
+ if (pclock->info->gettimex64)
+ vclock->info.gettimex64 = ptp_vclock_gettimex;
+ else
+ vclock->info.gettime64 = ptp_vclock_gettime;
+ if (pclock->info->getcrosststamp)
+ vclock->info.getcrosststamp = ptp_vclock_getcrosststamp;
vclock->cc = ptp_vclock_cc;
snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt",
struct work_struct work;
struct mutex freeze_mutex;
atomic64_t writecnt;
+ /* 'Ownership' of program-containing map is claimed by the first program
+ * that is going to use this map or by the first program which FD is
+ * stored in the map to make sure that all callers and callees have the
+ * same prog type, JITed flag and xdp_has_frags flag.
+ */
+ struct {
+ spinlock_t lock;
+ enum bpf_prog_type type;
+ bool jited;
+ bool xdp_has_frags;
+ } owner;
};
static inline bool map_value_has_spin_lock(const struct bpf_map *map)
const struct btf_type *t, int off, int size,
enum bpf_access_type atype,
u32 *next_btf_id);
- bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner);
};
struct bpf_prog_offload_ops {
bool func_proto_unreliable;
bool sleepable;
bool tail_call_reachable;
+ bool xdp_has_frags;
struct hlist_node tramp_hlist;
/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
const struct btf_type *attach_func_proto;
};
struct bpf_array_aux {
- /* 'Ownership' of prog array is claimed by the first program that
- * is going to use this map or by the first program which FD is
- * stored in the map to make sure that all callers and callees have
- * the same prog type and JITed flag.
- */
- struct {
- spinlock_t lock;
- enum bpf_prog_type type;
- bool jited;
- } owner;
/* Programs with direct jumps into programs part of this array. */
struct list_head poke_progs;
struct bpf_map *map;
struct rcu_head rcu;
};
-bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
+static inline bool map_type_contains_progs(struct bpf_map *map)
+{
+ return map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+ map->map_type == BPF_MAP_TYPE_DEVMAP ||
+ map->map_type == BPF_MAP_TYPE_CPUMAP;
+}
+
+bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp);
int bpf_prog_calc_tag(struct bpf_prog *fp);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
struct bpf_cg_run_ctx {
struct bpf_run_ctx run_ctx;
const struct bpf_prog_array_item *prog_item;
+ int retval;
};
struct bpf_trace_run_ctx {
typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx);
-static __always_inline u32
+static __always_inline int
BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu,
const void *ctx, bpf_prog_run_fn run_prog,
- u32 *ret_flags)
+ int retval, u32 *ret_flags)
{
const struct bpf_prog_array_item *item;
const struct bpf_prog *prog;
const struct bpf_prog_array *array;
struct bpf_run_ctx *old_run_ctx;
struct bpf_cg_run_ctx run_ctx;
- u32 ret = 1;
u32 func_ret;
+ run_ctx.retval = retval;
migrate_disable();
rcu_read_lock();
array = rcu_dereference(array_rcu);
while ((prog = READ_ONCE(item->prog))) {
run_ctx.prog_item = item;
func_ret = run_prog(prog, ctx);
- ret &= (func_ret & 1);
+ if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
+ run_ctx.retval = -EPERM;
*(ret_flags) |= (func_ret >> 1);
item++;
}
bpf_reset_run_ctx(old_run_ctx);
rcu_read_unlock();
migrate_enable();
- return ret;
+ return run_ctx.retval;
}
-static __always_inline u32
+static __always_inline int
BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu,
- const void *ctx, bpf_prog_run_fn run_prog)
+ const void *ctx, bpf_prog_run_fn run_prog,
+ int retval)
{
const struct bpf_prog_array_item *item;
const struct bpf_prog *prog;
const struct bpf_prog_array *array;
struct bpf_run_ctx *old_run_ctx;
struct bpf_cg_run_ctx run_ctx;
- u32 ret = 1;
+ run_ctx.retval = retval;
migrate_disable();
rcu_read_lock();
array = rcu_dereference(array_rcu);
old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
while ((prog = READ_ONCE(item->prog))) {
run_ctx.prog_item = item;
- ret &= run_prog(prog, ctx);
+ if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
+ run_ctx.retval = -EPERM;
item++;
}
bpf_reset_run_ctx(old_run_ctx);
rcu_read_unlock();
migrate_enable();
- return ret;
+ return run_ctx.retval;
}
static __always_inline u32
* 0: NET_XMIT_SUCCESS skb should be transmitted
* 1: NET_XMIT_DROP skb should be dropped and cn
* 2: NET_XMIT_CN skb should be transmitted and cn
- * 3: -EPERM skb should be dropped
+ * 3: -err skb should be dropped
*/
#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \
({ \
u32 _flags = 0; \
bool _cn; \
u32 _ret; \
- _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \
+ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \
_cn = _flags & BPF_RET_SET_CN; \
- if (_ret) \
+ if (_ret && !IS_ERR_VALUE((long)_ret)) \
+ _ret = -EFAULT; \
+ if (!_ret) \
_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \
else \
- _ret = (_cn ? NET_XMIT_DROP : -EPERM); \
+ _ret = (_cn ? NET_XMIT_DROP : _ret); \
_ret; \
})
int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
-bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner);
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
return -ENOTSUPP;
}
-static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id,
- struct module *owner)
-{
- return false;
-}
-
static inline void bpf_map_put(struct bpf_map *map)
{
}
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
+int sock_map_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr);
+
void sock_map_unhash(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
#else
{
return -EOPNOTSUPP;
}
+
+static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return -EINVAL;
+}
#endif /* CONFIG_BPF_SYSCALL */
#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
int check_ptr_off_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno);
+int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+ u32 regno);
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno, u32 mem_size);
return type & ~BPF_BASE_TYPE_MASK;
}
+static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
+{
+ return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
+}
+
#endif /* _LINUX_BPF_VERIFIER_H */
#define BTF_TYPE_EMIT(type) ((void)(type *)0)
#define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val)
+enum btf_kfunc_type {
+ BTF_KFUNC_TYPE_CHECK,
+ BTF_KFUNC_TYPE_ACQUIRE,
+ BTF_KFUNC_TYPE_RELEASE,
+ BTF_KFUNC_TYPE_RET_NULL,
+ BTF_KFUNC_TYPE_MAX,
+};
+
struct btf;
struct btf_member;
struct btf_type;
union bpf_attr;
struct btf_show;
+struct btf_id_set;
+
+struct btf_kfunc_id_set {
+ struct module *owner;
+ union {
+ struct {
+ struct btf_id_set *check_set;
+ struct btf_id_set *acquire_set;
+ struct btf_id_set *release_set;
+ struct btf_id_set *ret_null_set;
+ };
+ struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX];
+ };
+};
extern const struct file_operations btf_fops;
const char *btf_name_by_offset(const struct btf *btf, u32 offset);
struct btf *btf_parse_vmlinux(void);
struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
+bool btf_kfunc_id_set_contains(const struct btf *btf,
+ enum bpf_prog_type prog_type,
+ enum btf_kfunc_type type, u32 kfunc_btf_id);
+int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+ const struct btf_kfunc_id_set *s);
#else
static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
u32 type_id)
{
return NULL;
}
-#endif
-
-struct kfunc_btf_id_set {
- struct list_head list;
- struct btf_id_set *set;
- struct module *owner;
-};
-
-struct kfunc_btf_id_list {
- struct list_head list;
- struct mutex mutex;
-};
-
-#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
-void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
- struct kfunc_btf_id_set *s);
-void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
- struct kfunc_btf_id_set *s);
-bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
- struct module *owner);
-
-extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
-extern struct kfunc_btf_id_list prog_test_kfunc_list;
-#else
-static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
- struct kfunc_btf_id_set *s)
-{
-}
-static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
- struct kfunc_btf_id_set *s)
+static inline bool btf_kfunc_id_set_contains(const struct btf *btf,
+ enum bpf_prog_type prog_type,
+ enum btf_kfunc_type type,
+ u32 kfunc_btf_id)
{
+ return false;
}
-static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist,
- u32 kfunc_id, struct module *owner)
+static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+ const struct btf_kfunc_id_set *s)
{
- return false;
+ return 0;
}
-
-static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused;
-static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused;
#endif
-#define DEFINE_KFUNC_BTF_ID_SET(set, name) \
- struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \
- THIS_MODULE }
-
#endif
#ifdef CONFIG_DEBUG_INFO_BTF
#include <linux/compiler.h> /* for __PASTE */
+#include <linux/compiler_attributes.h> /* for __maybe_unused */
/*
* Following macros help to define lists of BTF IDs placed
#else
-#define BTF_ID_LIST(name) static u32 name[5];
+#define BTF_ID_LIST(name) static u32 __maybe_unused name[5];
#define BTF_ID(prefix, name)
#define BTF_ID_UNUSED
-#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n];
-#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1];
-#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1];
-#define BTF_SET_START(name) static struct btf_id_set name = { 0 };
-#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 };
+#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n];
+#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1];
+#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1];
+#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 };
+#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 };
#define BTF_SET_END(name)
#endif /* CONFIG_DEBUG_INFO_BTF */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __TAG_QCA_H
+#define __TAG_QCA_H
+
+#define QCA_HDR_LEN 2
+#define QCA_HDR_VERSION 0x2
+
+#define QCA_HDR_RECV_VERSION GENMASK(15, 14)
+#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11)
+#define QCA_HDR_RECV_TYPE GENMASK(10, 6)
+#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3)
+#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0)
+
+/* Packet type for recv */
+#define QCA_HDR_RECV_TYPE_NORMAL 0x0
+#define QCA_HDR_RECV_TYPE_MIB 0x1
+#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2
+
+#define QCA_HDR_XMIT_VERSION GENMASK(15, 14)
+#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11)
+#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8)
+#define QCA_HDR_XMIT_FROM_CPU BIT(7)
+#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0)
+
+/* Packet type for xmit */
+#define QCA_HDR_XMIT_TYPE_NORMAL 0x0
+#define QCA_HDR_XMIT_TYPE_RW_REG 0x1
+
+/* Check code for a valid mgmt packet. Switch will ignore the packet
+ * with this wrong.
+ */
+#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5
+
+/* Specific define for in-band MDIO read/write with Ethernet packet */
+#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */
+#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */
+#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */
+#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \
+ QCA_HDR_MGMT_COMMAND_LEN + \
+ QCA_HDR_MGMT_DATA1_LEN)
+
+#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */
+#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */
+
+#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \
+ QCA_HDR_LEN + \
+ QCA_HDR_MGMT_DATA2_LEN + \
+ QCA_HDR_MGMT_PADDING_LEN)
+
+#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */
+#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */
+#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */
+#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */
+#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */
+
+/* Special struct emulating a Ethernet header */
+struct qca_mgmt_ethhdr {
+ u32 command; /* command bit 31:0 */
+ u32 seq; /* seq 63:32 */
+ u32 mdio_data; /* first 4byte mdio */
+ __be16 hdr; /* qca hdr */
+} __packed;
+
+enum mdio_cmd {
+ MDIO_WRITE = 0x0,
+ MDIO_READ
+};
+
+struct mib_ethhdr {
+ u32 data[3]; /* first 3 mib counter */
+ __be16 hdr; /* qca hdr */
+} __packed;
+
+struct qca_tagger_data {
+ void (*rw_reg_ack_handler)(struct dsa_switch *ds,
+ struct sk_buff *skb);
+ void (*mib_autocast_handler)(struct dsa_switch *ds,
+ struct sk_buff *skb);
+};
+
+#endif /* __TAG_QCA_H */
/**
* struct kernel_ethtool_ringparam - RX/TX ring configuration
* @rx_buf_len: Current length of buffers on the rx ring.
+ * @tcp_data_split: Scatter packet headers and data to separate buffers
*/
struct kernel_ethtool_ringparam {
u32 rx_buf_len;
+ u8 tcp_data_split;
};
/**
s32 level;
s32 optname;
s32 optlen;
- s32 retval;
+ /* for retval in struct bpf_cg_run_ctx */
+ struct task_struct *current_task;
+ /* Temporary "register" for indirect stores to ppos. */
+ u64 tmp_reg;
};
int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
return NULL;
}
-static inline struct inet6_request_sock *
- inet6_rsk(const struct request_sock *rsk)
-{
- return NULL;
-}
-
static inline struct raw6_sock *raw6_sk(const struct sock *sk)
{
return NULL;
}
#define inet6_rcv_saddr(__sk) NULL
-#define tcp_twsk_ipv6only(__sk) 0
#define inet_v6_ipv6only(__sk) 0
#endif /* IS_ENABLED(CONFIG_IPV6) */
#endif /* _IPV6_H */
linkmode_clear_bit(nr, addr);
}
-static inline void linkmode_change_bit(int nr, volatile unsigned long *addr)
-{
- __change_bit(nr, addr);
-}
-
static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr)
{
return test_bit(nr, addr);
}
/**
- * mii_lpa_mod_linkmode_adv_sgmii
- * @lp_advertising: pointer to destination link mode.
- * @lpa: value of the MII_LPA register
- *
- * A small helper function that translates MII_LPA bits to
- * linkmode advertisement settings for SGMII.
- * Leaves other bits unchanged.
- */
-static inline void
-mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa)
-{
- u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK;
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising,
- speed_duplex == LPA_SGMII_1000HALF);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising,
- speed_duplex == LPA_SGMII_1000FULL);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising,
- speed_duplex == LPA_SGMII_100HALF);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising,
- speed_duplex == LPA_SGMII_100FULL);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising,
- speed_duplex == LPA_SGMII_10HALF);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising,
- speed_duplex == LPA_SGMII_10FULL);
-}
-
-/**
- * mii_lpa_to_linkmode_adv_sgmii
- * @advertising: pointer to destination link mode.
- * @lpa: value of the MII_LPA register
- *
- * A small helper function that translates MII_ADVERTISE bits
- * to linkmode advertisement settings when in SGMII mode.
- * Clears the old value of advertising.
- */
-static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising,
- u32 lpa)
-{
- linkmode_zero(lp_advertising);
-
- mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa);
-}
-
-/**
* mii_adv_mod_linkmode_adv_t
* @advertising:pointer to destination link mode.
* @adv: value of the MII_ADVERTISE register
};
enum {
- MLX5_MODIFY_TIR_BITMASK_LRO = 0x0,
- MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1,
- MLX5_MODIFY_TIR_BITMASK_HASH = 0x2,
- MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3
-};
-
-enum {
MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0,
MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2,
MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3,
extack->cookie_len = sizeof(cookie);
}
-static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack,
- u32 cookie)
-{
- if (!extack)
- return;
- memcpy(extack->cookie, &cookie, sizeof(cookie));
- extack->cookie_len = sizeof(cookie);
-}
-
void netlink_kernel_release(struct sock *sk);
int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
int netlink_change_ngroups(struct sock *sk, unsigned int groups);
phy_interface_t interface, int speed, int duplex);
int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
unsigned int mode);
-void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported,
- struct phylink_link_state *state);
+void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces);
int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
int enable);
struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev,
void phy_request_interrupt(struct phy_device *phydev);
void phy_free_interrupt(struct phy_device *phydev);
void phy_print_status(struct phy_device *phydev);
-int phy_set_max_speed(struct phy_device *phydev, u32 max_speed);
+void phy_set_max_speed(struct phy_device *phydev, u32 max_speed);
void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode);
void phy_advertise_supported(struct phy_device *phydev);
void phy_support_sym_pause(struct phy_device *phydev);
* Warning : all fields before dataref are cleared in __alloc_skb()
*/
atomic_t dataref;
+ unsigned int xdp_frags_size;
/* Intermediate layers must ensure that destructor_arg
* remains valid until skb destructor */
return ktime_sub(ktime_get_real(), t);
}
-static inline ktime_t net_invalid_timestamp(void)
-{
- return 0;
-}
-
static inline u8 skb_metadata_len(const struct sk_buff *skb)
{
return skb_shinfo(skb)->meta_len;
struct list_head xpt_users; /* callbacks on free */
struct net *xpt_net;
+ netns_tracker ns_tracker;
const struct cred *xpt_cred;
struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */
struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */
} stat;
struct net *xprt_net;
+ netns_tracker ns_tracker;
const char *servername;
const char *address_strings[RPC_DISPLAY_MAX];
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
return (struct udphdr *)skb_transport_header(skb);
}
-static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb)
-{
- return (struct udphdr *)skb_inner_transport_header(skb);
-}
-
#define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256)
static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask)
typedef struct ax25_route {
struct ax25_route *next;
- refcount_t refcount;
ax25_address callsign;
struct net_device *dev;
ax25_digi *digipeat;
char ip_mode;
} ax25_route;
-static inline void ax25_hold_route(ax25_route *ax25_rt)
-{
- refcount_inc(&ax25_rt->refcount);
-}
-
void __ax25_put_route(ax25_route *ax25_rt);
extern rwlock_t ax25_route_lock;
read_unlock(&ax25_route_lock);
}
-static inline void ax25_put_route(ax25_route *ax25_rt)
-{
- if (refcount_dec_and_test(&ax25_rt->refcount))
- __ax25_put_route(ax25_rt);
-}
-
typedef struct {
char slave; /* slave_mode? */
struct timer_list slave_timer; /* timeout timer */
#define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F
+struct monitored_device {
+ struct list_head list;
+
+ bdaddr_t bdaddr;
+ __u8 addr_type;
+ __u16 handle;
+ bool notified;
+};
+
struct adv_pattern {
struct list_head list;
__u8 ad_type;
#define HCI_MAX_SHORT_NAME_LENGTH 10
+#define HCI_CONN_HANDLE_UNSET 0xffff
+#define HCI_CONN_HANDLE_MAX 0x0eff
+
/* Min encryption key size to match with SMP */
#define HCI_MIN_ENC_KEY_SIZE 7
struct delayed_work interleave_scan;
+ struct list_head monitored_devices;
+ bool advmon_pend_notify;
+
#if IS_ENABLED(CONFIG_BT_LEDS)
struct led_trigger *power_led;
#endif
int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip);
int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status);
int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status);
+void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle,
+ bdaddr_t *bdaddr, u8 addr_type);
u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency,
u16 to_multiplier);
#define MGMT_WAKE_REASON_NON_BT_WAKE 0x0
#define MGMT_WAKE_REASON_UNEXPECTED 0x1
#define MGMT_WAKE_REASON_REMOTE_WAKE 0x2
+
+#define MGMT_EV_ADV_MONITOR_DEVICE_FOUND 0x002f
+struct mgmt_ev_adv_monitor_device_found {
+ __le16 monitor_handle;
+ struct mgmt_addr_info addr;
+ __s8 rssi;
+ __le32 flags;
+ __le16 eir_len;
+ __u8 eir[0];
+} __packed;
+
+#define MGMT_EV_ADV_MONITOR_DEVICE_LOST 0x0030
+struct mgmt_ev_adv_monitor_device_lost {
+ __le16 monitor_handle;
+ struct mgmt_addr_info addr;
+} __packed;
}
/* Caller must hold rcu_read_lock() for read */
-static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond,
- const u8 *mac)
-{
- struct list_head *iter;
- struct slave *tmp;
-
- bond_for_each_slave_rcu(bond, tmp, iter)
- if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr))
- return tmp;
-
- return NULL;
-}
-
-/* Caller must hold rcu_read_lock() for read */
static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac)
{
struct list_head *iter;
u8 devlink_port_setup:1;
+ /* Master state bits, valid only on CPU ports */
+ u8 master_admin_up:1;
+ u8 master_oper_up:1;
+
u8 setup:1;
struct device_node *dn;
return dp->type == DSA_PORT_TYPE_UNUSED;
}
+static inline bool dsa_port_master_is_operational(struct dsa_port *dp)
+{
+ return dsa_port_is_cpu(dp) && dp->master_admin_up &&
+ dp->master_oper_up;
+}
+
static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p)
{
return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED;
return port == dsa_upstream_port(ds, port);
}
+/* Return true if this is a DSA port leading away from the CPU */
+static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port)
+{
+ return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port);
+}
+
+/* Return the local port used to reach the CPU port */
+static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds)
+{
+ struct dsa_port *dp;
+
+ dsa_switch_for_each_available_port(dp, ds) {
+ return dsa_upstream_port(ds, dp->index);
+ }
+
+ return ds->num_ports;
+}
+
/* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning
* that the routing port from @downstream_ds to @upstream_ds is also the port
* which @downstream_ds uses to reach its dedicated CPU.
int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid,
u16 flags);
int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid);
+
+ /*
+ * DSA master tracking operations
+ */
+ void (*master_state_change)(struct dsa_switch *ds,
+ const struct net_device *master,
+ bool operational);
};
#define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \
bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
+static inline unsigned long
+reqsk_timeout(struct request_sock *req, unsigned long max_timeout)
+{
+ u64 timeout = (u64)req->timeout << req->num_timeout;
+
+ return (unsigned long)min_t(u64, timeout, max_timeout);
+}
+
static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
{
/* The below has to be done to allow calling inet_csk_destroy_sock */
/* these three are in inet_sock */
__be16 tw_sport;
/* And these are ours. */
- unsigned int tw_kill : 1,
- tw_transparent : 1,
+ unsigned int tw_transparent : 1,
tw_flowlabel : 20,
- tw_pad : 2, /* 2 bits hole */
+ tw_pad : 3, /* 3 bits hole */
tw_tos : 8;
u32 tw_txhash;
u32 tw_priority;
+ u32 tw_bslot; /* bind bucket slot */
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
};
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
-void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family);
-
static inline
struct net *twsk_net(const struct inet_timewait_sock *twsk)
{
kfree(p);
}
-u32 ip_idents_reserve(u32 hash, int segs);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs);
static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb,
*/
void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
- __be32 daddr, struct rtable *rt, int is_frag);
+ __be32 daddr, struct rtable *rt);
int __ip_options_echo(struct net *net, struct ip_options *dopt,
struct sk_buff *skb, const struct ip_options *sopt);
struct ipv6_txoptions *opt,
int newtype,
struct ipv6_opt_hdr *newopt);
-struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
- struct ipv6_txoptions *opt);
+struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space,
+ struct ipv6_txoptions *opt);
+
+static inline struct ipv6_txoptions *
+ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt)
+{
+ if (!opt)
+ return NULL;
+ return __ipv6_fixup_options(opt_space, opt);
+}
bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,
const struct inet6_skb_parm *opt);
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
- struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
+ struct ipcm6_cookie *ipc6,
struct rt6_info *rt, unsigned int flags,
struct inet_cork_full *cork);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _NF_CONNTRACK_BPF_H
+#define _NF_CONNTRACK_BPF_H
+
+#include <linux/btf.h>
+#include <linux/kconfig.h>
+
+#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \
+ (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES))
+
+extern int register_nf_conntrack_bpf(void);
+
+#else
+
+static inline int register_nf_conntrack_bpf(void)
+{
+ return 0;
+}
+
+#endif
+
+#endif /* _NF_CONNTRACK_BPF_H */
struct ctl_table_header *sysctl_hdr;
int sysctl_somaxconn;
+ u8 sysctl_txrehash;
#ifdef CONFIG_PROC_FS
struct prot_inuse __percpu *prot_inuse;
struct inet_hashinfo;
struct inet_timewait_death_row {
- atomic_t tw_count;
- char tw_pad[L1_CACHE_BYTES - sizeof(atomic_t)];
+ refcount_t tw_refcount;
- struct inet_hashinfo *hashinfo;
+ struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp;
int sysctl_max_tw_buckets;
};
struct tcp_fastopen_context;
struct netns_ipv4 {
- /* Please keep tcp_death_row at first field in netns_ipv4 */
- struct inet_timewait_death_row tcp_death_row ____cacheline_aligned_in_smp;
+ struct inet_timewait_death_row *tcp_death_row;
#ifdef CONFIG_SYSCTL
struct ctl_table_header *forw_hdr;
struct hlist_head *fib_table_hash;
struct sock *fibnl;
- struct sock * __percpu *icmp_sk;
struct sock *mc_autojoin_sk;
struct inet_peer_base *peers;
- struct sock * __percpu *tcp_sk;
struct fqdir *fqdir;
u8 sysctl_icmp_echo_ignore_all;
u32 ip_rt_min_pmtu;
int ip_rt_mtu_expires;
+ int ip_rt_min_advmss;
struct local_ports ip_local_ports;
struct fib6_table *fib6_local_tbl;
struct fib_rules_ops *fib6_rules_ops;
#endif
- struct sock * __percpu *icmp_sk;
struct sock *ndisc_sk;
struct sock *tcp_sk;
struct sock *igmp_sk;
}
#endif
-void page_pool_put_page(struct page_pool *pool, struct page *page,
- unsigned int dma_sync_size, bool allow_direct);
+void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size,
+ bool allow_direct);
-/* Same as above but will try to sync the entire area pool->max_len */
-static inline void page_pool_put_full_page(struct page_pool *pool,
- struct page *page, bool allow_direct)
+static inline void page_pool_fragment_page(struct page *page, long nr)
+{
+ atomic_long_set(&page->pp_frag_count, nr);
+}
+
+static inline long page_pool_defrag_page(struct page *page, long nr)
+{
+ long ret;
+
+ /* If nr == pp_frag_count then we have cleared all remaining
+ * references to the page. No need to actually overwrite it, instead
+ * we can leave this to be overwritten by the calling function.
+ *
+ * The main advantage to doing this is that an atomic_read is
+ * generally a much cheaper operation than an atomic update,
+ * especially when dealing with a page that may be partitioned
+ * into only 2 or 3 pieces.
+ */
+ if (atomic_long_read(&page->pp_frag_count) == nr)
+ return 0;
+
+ ret = atomic_long_sub_return(nr, &page->pp_frag_count);
+ WARN_ON(ret < 0);
+ return ret;
+}
+
+static inline bool page_pool_is_last_frag(struct page_pool *pool,
+ struct page *page)
+{
+ /* If fragments aren't enabled or count is 0 we were the last user */
+ return !(pool->p.flags & PP_FLAG_PAGE_FRAG) ||
+ (page_pool_defrag_page(page, 1) == 0);
+}
+
+static inline void page_pool_put_page(struct page_pool *pool,
+ struct page *page,
+ unsigned int dma_sync_size,
+ bool allow_direct)
{
/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
* allow registering MEM_TYPE_PAGE_POOL, but shield linker.
*/
#ifdef CONFIG_PAGE_POOL
- page_pool_put_page(pool, page, -1, allow_direct);
+ if (!page_pool_is_last_frag(pool, page))
+ return;
+
+ page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct);
#endif
}
+/* Same as above but will try to sync the entire area pool->max_len */
+static inline void page_pool_put_full_page(struct page_pool *pool,
+ struct page *page, bool allow_direct)
+{
+ page_pool_put_page(pool, page, -1, allow_direct);
+}
+
/* Same as above but the caller must guarantee safe context. e.g NAPI */
static inline void page_pool_recycle_direct(struct page_pool *pool,
struct page *page)
page->dma_addr_upper = upper_32_bits(addr);
}
-static inline void page_pool_set_frag_count(struct page *page, long nr)
-{
- atomic_long_set(&page->pp_frag_count, nr);
-}
-
-static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
- long nr)
-{
- long ret;
-
- /* As suggested by Alexander, atomic_long_read() may cover up the
- * reference count errors, so avoid calling atomic_long_read() in
- * the cases of freeing or draining the page_frags, where we would
- * not expect it to match or that are slowpath anyway.
- */
- if (__builtin_constant_p(nr) &&
- atomic_long_read(&page->pp_frag_count) == nr)
- return 0;
-
- ret = atomic_long_sub_return(nr, &page->pp_frag_count);
- WARN_ON(ret < 0);
- return ret;
-}
-
static inline bool is_page_pool_compiled_in(void)
{
#ifdef CONFIG_PAGE_POOL
return PSCHED_NS2TICKS(ktime_get_ns());
}
-static inline psched_tdiff_t
-psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound)
-{
- return min(tv1 - tv2, bound);
-}
-
struct qdisc_watchdog {
u64 last_expires;
struct hrtimer timer;
struct saved_syn *saved_syn;
u32 secid;
u32 peer_secid;
+ u32 timeout;
};
static inline struct request_sock *inet_reqsk(const struct sock *sk)
sk_node_init(&req_to_sk(req)->sk_node);
sk_tx_queue_clear(req_to_sk(req));
req->saved_syn = NULL;
+ req->timeout = 0;
req->num_timeout = 0;
req->num_retrans = 0;
req->sk = NULL;
BUILD_BUG_ON(sizeof(qcb->data) < sz);
}
-static inline int qdisc_qlen_cpu(const struct Qdisc *q)
-{
- return this_cpu_ptr(q->cpu_qstats)->qlen;
-}
-
static inline int qdisc_qlen(const struct Qdisc *q)
{
return q->q.qlen;
* @sk_rcvtimeo: %SO_RCVTIMEO setting
* @sk_sndtimeo: %SO_SNDTIMEO setting
* @sk_txhash: computed flow hash for use on transmit
+ * @sk_txrehash: enable TX hash rethink
* @sk_filter: socket filtering instructions
* @sk_timer: sock cleanup timer
* @sk_stamp: time stamp of last packet received
u32 sk_ack_backlog;
u32 sk_max_ack_backlog;
kuid_t sk_uid;
+ u8 sk_txrehash;
#ifdef CONFIG_NET_RX_BUSY_POLL
u8 sk_prefer_busy_poll;
u16 sk_busy_poll_budget;
__tmp | SK_USER_DATA_NOCOPY); \
})
+static inline
+struct net *sock_net(const struct sock *sk)
+{
+ return read_pnet(&sk->sk_net);
+}
+
+static inline
+void sock_net_set(struct sock *sk, struct net *net)
+{
+ write_pnet(&sk->sk_net, net);
+}
+
/*
* SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
* or not whether his port will be reused by someone else. SK_FORCE_REUSE
static inline bool sk_rethink_txhash(struct sock *sk)
{
- if (sk->sk_txhash) {
+ if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) {
sk_set_txhash(sk);
return true;
}
__kfree_skb(skb);
}
-static inline
-struct net *sock_net(const struct sock *sk)
-{
- return read_pnet(&sk->sk_net);
-}
-
-static inline
-void sock_net_set(struct sock *sk, struct net *net)
-{
- write_pnet(&sk->sk_net, net);
-}
-
static inline bool
skb_sk_is_prefetched(struct sk_buff *skb)
{
if (timeout <= 0)
timeout = TCP_TIMEOUT_INIT;
- return timeout;
+ return min_t(int, timeout, TCP_RTO_MAX);
}
static inline u32 tcp_rwnd_init_bpf(struct sock *sk)
return 0;
}
-/* Slow-path computation of checksum. Socket is locked. */
-static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb)
-{
- const struct udp_sock *up = udp_sk(skb->sk);
- int cscov = up->len;
- __wsum csum = 0;
-
- if (up->pcflag & UDPLITE_SEND_CC) {
- /*
- * Sender has set `partial coverage' option on UDP-Lite socket.
- * The special case "up->pcslen == 0" signifies full coverage.
- */
- if (up->pcslen < up->len) {
- if (0 < up->pcslen)
- cscov = up->pcslen;
- udp_hdr(skb)->len = htons(up->pcslen);
- }
- /*
- * NOTE: Causes for the error case `up->pcslen > up->len':
- * (i) Application error (will not be penalized).
- * (ii) Payload too big for send buffer: data is split
- * into several packets, each with its own header.
- * In this case (e.g. last segment), coverage may
- * exceed packet length.
- * Since packets with coverage length > packet length are
- * illegal, we fall back to the defaults here.
- */
- }
-
- skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */
-
- skb_queue_walk(&sk->sk_write_queue, skb) {
- const int off = skb_transport_offset(skb);
- const int len = skb->len - off;
-
- csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum);
-
- if ((cscov -= len) <= 0)
- break;
- }
- return csum;
-}
-
/* Fast-path computation of checksum. Socket may not be locked. */
static inline __wsum udplite_csum(struct sk_buff *skb)
{
u32 reg_state;
struct xdp_mem_info mem;
unsigned int napi_id;
+ u32 frag_size;
} ____cacheline_aligned; /* perf critical, avoid false-sharing */
struct xdp_txq_info {
struct net_device *dev;
};
+enum xdp_buff_flags {
+ XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */
+ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under
+ * pressure
+ */
+};
+
struct xdp_buff {
void *data;
void *data_end;
struct xdp_rxq_info *rxq;
struct xdp_txq_info *txq;
u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/
+ u32 flags; /* supported values defined in xdp_buff_flags */
};
+static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp)
+{
+ return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS);
+}
+
+static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp)
+{
+ xdp->flags |= XDP_FLAGS_HAS_FRAGS;
+}
+
+static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp)
+{
+ xdp->flags &= ~XDP_FLAGS_HAS_FRAGS;
+}
+
+static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+ return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
+static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+ xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC;
+}
+
static __always_inline void
xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
{
xdp->frame_sz = frame_sz;
xdp->rxq = rxq;
+ xdp->flags = 0;
}
static __always_inline void
return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}
+static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp)
+{
+ unsigned int len = xdp->data_end - xdp->data;
+ struct skb_shared_info *sinfo;
+
+ if (likely(!xdp_buff_has_frags(xdp)))
+ goto out;
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ len += sinfo->xdp_frags_size;
+out:
+ return len;
+}
+
struct xdp_frame {
void *data;
u16 len;
*/
struct xdp_mem_info mem;
struct net_device *dev_rx; /* used by cpumap */
+ u32 flags; /* supported values defined in xdp_buff_flags */
};
+static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame)
+{
+ return !!(frame->flags & XDP_FLAGS_HAS_FRAGS);
+}
+
+static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame)
+{
+ return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
#define XDP_BULK_QUEUE_SIZE 16
struct xdp_frame_bulk {
int count;
frame->dev_rx = NULL;
}
+static inline void
+xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
+ unsigned int size, unsigned int truesize,
+ bool pfmemalloc)
+{
+ skb_shinfo(skb)->nr_frags = nr_frags;
+
+ skb->len += size;
+ skb->data_len += size;
+ skb->truesize += truesize;
+ skb->pfmemalloc |= pfmemalloc;
+}
+
/* Avoids inlining WARN macro in fast-path */
void xdp_warn(const char *msg, const char *func, const int line);
#define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
xdp->data_end = frame->data + frame->len;
xdp->data_meta = frame->data - frame->metasize;
xdp->frame_sz = frame->frame_sz;
+ xdp->flags = frame->flags;
}
static inline
xdp_frame->headroom = headroom - sizeof(*xdp_frame);
xdp_frame->metasize = metasize;
xdp_frame->frame_sz = xdp->frame_sz;
+ xdp_frame->flags = xdp->flags;
return 0;
}
return xdp_frame;
}
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+ struct xdp_buff *xdp);
void xdp_return_frame(struct xdp_frame *xdpf);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
static inline void xdp_release_frame(struct xdp_frame *xdpf)
{
struct xdp_mem_info *mem = &xdpf->mem;
+ struct skb_shared_info *sinfo;
+ int i;
/* Curr only page_pool needs this */
- if (mem->type == MEM_TYPE_PAGE_POOL)
- __xdp_release_frame(xdpf->data, mem);
+ if (mem->type != MEM_TYPE_PAGE_POOL)
+ return;
+
+ if (likely(!xdp_frame_has_frags(xdpf)))
+ goto out;
+
+ sinfo = xdp_get_shared_info_from_frame(xdpf);
+ for (i = 0; i < sinfo->nr_frags; i++) {
+ struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+ __xdp_release_frame(page_address(page), mem);
+ }
+out:
+ __xdp_release_frame(xdpf->data, mem);
+}
+
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+ struct net_device *dev, u32 queue_index,
+ unsigned int napi_id, u32 frag_size);
+static inline int
+xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+ struct net_device *dev, u32 queue_index,
+ unsigned int napi_id)
+{
+ return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0);
}
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
- struct net_device *dev, u32 queue_index, unsigned int napi_id);
void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
#define SO_RESERVE_MEM 73
+#define SO_TXREHASH 74
+
#if !defined(__KERNEL__)
#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
* *ctx_out*, *data_in* and *data_out* must be NULL.
* *repeat* must be zero.
*
+ * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*/
#define BPF_F_SLEEPABLE (1U << 4)
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS (1U << 5)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* the following extensions:
*
* 0 on success, or a negative error in case of failure.
*
* u64 bpf_get_current_pid_tgid(void)
+ * Description
+ * Get the current pid and tgid.
* Return
* A 64-bit integer containing the current tgid and pid, and
* created as such:
* *current_task*\ **->pid**.
*
* u64 bpf_get_current_uid_gid(void)
+ * Description
+ * Get the current uid and gid.
* Return
* A 64-bit integer containing the current GID and UID, and
* created as such: *current_gid* **<< 32 \|** *current_uid*.
* The 32-bit hash.
*
* u64 bpf_get_current_task(void)
+ * Description
+ * Get the current task.
* Return
* A pointer to the current task struct.
*
* indicate that the hash is outdated and to trigger a
* recalculation the next time the kernel tries to access this
* hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * Return
+ * void.
*
* long bpf_get_numa_node_id(void)
* Description
* A 8-byte long unique number or 0 if *sk* is NULL.
*
* u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Description
+ * Get the owner UID of the socked associated to *skb*.
* Return
* The owner UID of the socket associated to *skb*. If the socket
* is **NULL**, or if it is not a full socket (i.e. if it is a
* The id is returned or 0 in case the id could not be retrieved.
*
* u64 bpf_get_current_cgroup_id(void)
+ * Description
+ * Get the current cgroup id based on the cgroup within which
+ * the current task is running.
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
*
* Return
* The number of arguments of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * The syscall's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ * Description
+ * Get the total size of a given xdp buff (linear and paged area)
+ * Return
+ * The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * This helper is provided as an easy way to load data from a
+ * xdp buffer. It can be used to load *len* bytes from *offset* from
+ * the frame associated to *xdp_md*, into the buffer pointed by
+ * *buf*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * Store *len* bytes from buffer *buf* into the frame
+ * associated to *xdp_md*, at *offset*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
FN(get_func_arg), \
FN(get_func_ret), \
FN(get_func_arg_cnt), \
+ FN(get_retval), \
+ FN(set_retval), \
+ FN(xdp_get_buff_len), \
+ FN(xdp_load_bytes), \
+ FN(xdp_store_bytes), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
/* RINGS */
enum {
+ ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0,
+ ETHTOOL_TCP_DATA_SPLIT_DISABLED,
+ ETHTOOL_TCP_DATA_SPLIT_ENABLED,
+};
+
+enum {
ETHTOOL_A_RINGS_UNSPEC,
ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */
ETHTOOL_A_RINGS_RX_MAX, /* u32 */
ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */
ETHTOOL_A_RINGS_TX, /* u32 */
ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */
+ ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */
/* add new constants above here */
__ETHTOOL_A_RINGS_CNT,
#define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK)
+#define SOCK_TXREHASH_DEFAULT ((u8)-1)
+#define SOCK_TXREHASH_DISABLED 0
+#define SOCK_TXREHASH_ENABLED 1
+
#endif /* _UAPI_LINUX_SOCKET_H */
static void *prog_fd_array_get_ptr(struct bpf_map *map,
struct file *map_file, int fd)
{
- struct bpf_array *array = container_of(map, struct bpf_array, map);
struct bpf_prog *prog = bpf_prog_get(fd);
if (IS_ERR(prog))
return prog;
- if (!bpf_prog_array_compatible(array, prog)) {
+ if (!bpf_prog_map_compatible(map, prog)) {
bpf_prog_put(prog);
return ERR_PTR(-EINVAL);
}
INIT_WORK(&aux->work, prog_array_map_clear_deferred);
INIT_LIST_HEAD(&aux->poke_progs);
mutex_init(&aux->poke_mutex);
- spin_lock_init(&aux->owner.lock);
map = array_map_alloc(attr);
if (IS_ERR(map)) {
DEFINE_IDR(btf_idr);
DEFINE_SPINLOCK(btf_idr_lock);
+enum btf_kfunc_hook {
+ BTF_KFUNC_HOOK_XDP,
+ BTF_KFUNC_HOOK_TC,
+ BTF_KFUNC_HOOK_STRUCT_OPS,
+ BTF_KFUNC_HOOK_MAX,
+};
+
+enum {
+ BTF_KFUNC_SET_MAX_CNT = 32,
+};
+
+struct btf_kfunc_set_tab {
+ struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX];
+};
+
struct btf {
void *data;
struct btf_type **types;
refcount_t refcnt;
u32 id;
struct rcu_head rcu;
+ struct btf_kfunc_set_tab *kfunc_set_tab;
/* split BTF support */
struct btf *base_btf;
spin_unlock_irqrestore(&btf_idr_lock, flags);
}
+static void btf_free_kfunc_set_tab(struct btf *btf)
+{
+ struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab;
+ int hook, type;
+
+ if (!tab)
+ return;
+ /* For module BTF, we directly assign the sets being registered, so
+ * there is nothing to free except kfunc_set_tab.
+ */
+ if (btf_is_module(btf))
+ goto free_tab;
+ for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) {
+ for (type = 0; type < ARRAY_SIZE(tab->sets[0]); type++)
+ kfree(tab->sets[hook][type]);
+ }
+free_tab:
+ kfree(tab);
+ btf->kfunc_set_tab = NULL;
+}
+
static void btf_free(struct btf *btf)
{
+ btf_free_kfunc_set_tab(btf);
kvfree(btf->types);
kvfree(btf->resolved_sizes);
kvfree(btf->resolved_ids);
return true;
}
+static bool is_kfunc_arg_mem_size(const struct btf *btf,
+ const struct btf_param *arg,
+ const struct bpf_reg_state *reg)
+{
+ int len, sfx_len = sizeof("__sz") - 1;
+ const struct btf_type *t;
+ const char *param_name;
+
+ t = btf_type_skip_modifiers(btf, arg->type, NULL);
+ if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE)
+ return false;
+
+ /* In the future, this can be ported to use BTF tagging */
+ param_name = btf_name_by_offset(btf, arg->name_off);
+ if (str_is_empty(param_name))
+ return false;
+ len = strlen(param_name);
+ if (len < sfx_len)
+ return false;
+ param_name += len - sfx_len;
+ if (strncmp(param_name, "__sz", sfx_len))
+ return false;
+
+ return true;
+}
+
static int btf_check_func_arg_match(struct bpf_verifier_env *env,
const struct btf *btf, u32 func_id,
struct bpf_reg_state *regs,
bool ptr_to_mem_ok)
{
struct bpf_verifier_log *log = &env->log;
+ u32 i, nargs, ref_id, ref_obj_id = 0;
bool is_kfunc = btf_is_kernel(btf);
const char *func_name, *ref_tname;
const struct btf_type *t, *ref_t;
const struct btf_param *args;
- u32 i, nargs, ref_id;
+ int ref_regno = 0;
+ bool rel = false;
t = btf_type_by_id(btf, func_id);
if (!t || !btf_type_is_func(t)) {
if (reg->type == PTR_TO_BTF_ID) {
reg_btf = reg->btf;
reg_ref_id = reg->btf_id;
+ /* Ensure only one argument is referenced PTR_TO_BTF_ID */
+ if (reg->ref_obj_id) {
+ if (ref_obj_id) {
+ bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
+ regno, reg->ref_obj_id, ref_obj_id);
+ return -EFAULT;
+ }
+ ref_regno = regno;
+ ref_obj_id = reg->ref_obj_id;
+ }
} else {
reg_btf = btf_vmlinux;
reg_ref_id = *reg2btf_ids[reg->type];
u32 type_size;
if (is_kfunc) {
+ bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]);
+
/* Permit pointer to mem, but only when argument
* type is pointer to scalar, or struct composed
* (recursively) of scalars.
+ * When arg_mem_size is true, the pointer can be
+ * void *.
*/
if (!btf_type_is_scalar(ref_t) &&
- !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) {
+ !__btf_type_is_scalar_struct(log, btf, ref_t, 0) &&
+ (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) {
bpf_log(log,
- "arg#%d pointer type %s %s must point to scalar or struct with scalar\n",
- i, btf_type_str(ref_t), ref_tname);
+ "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n",
+ i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : "");
return -EINVAL;
}
+
+ /* Check for mem, len pair */
+ if (arg_mem_size) {
+ if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) {
+ bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n",
+ i, i + 1);
+ return -EINVAL;
+ }
+ i++;
+ continue;
+ }
}
resolve_ret = btf_resolve_size(btf, ref_t, &type_size);
}
}
- return 0;
+ /* Either both are set, or neither */
+ WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno));
+ if (is_kfunc) {
+ rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog),
+ BTF_KFUNC_TYPE_RELEASE, func_id);
+ /* We already made sure ref_obj_id is set only for one argument */
+ if (rel && !ref_obj_id) {
+ bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n",
+ func_name);
+ return -EINVAL;
+ }
+ /* Allow (!rel && ref_obj_id), so that passing such referenced PTR_TO_BTF_ID to
+ * other kfuncs works
+ */
+ }
+ /* returns argument register number > 0 in case of reference release kfunc */
+ return rel ? ref_regno : 0;
}
/* Compare BTF of a function with given bpf_reg_state.
return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;
}
+enum {
+ BTF_MODULE_F_LIVE = (1 << 0),
+};
+
#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
struct btf_module {
struct list_head list;
struct module *module;
struct btf *btf;
struct bin_attribute *sysfs_attr;
+ int flags;
};
static LIST_HEAD(btf_modules);
int err = 0;
if (mod->btf_data_size == 0 ||
- (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING))
+ (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE &&
+ op != MODULE_STATE_GOING))
goto out;
switch (op) {
}
break;
+ case MODULE_STATE_LIVE:
+ mutex_lock(&btf_module_mutex);
+ list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+ if (btf_mod->module != module)
+ continue;
+
+ btf_mod->flags |= BTF_MODULE_F_LIVE;
+ break;
+ }
+ mutex_unlock(&btf_module_mutex);
+ break;
case MODULE_STATE_GOING:
mutex_lock(&btf_module_mutex);
list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
if (btf_mod->btf != btf)
continue;
- if (try_module_get(btf_mod->module))
+ /* We must only consider module whose __init routine has
+ * finished, hence we must check for BTF_MODULE_F_LIVE flag,
+ * which is set from the notifier callback for
+ * MODULE_STATE_LIVE.
+ */
+ if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module))
res = btf_mod->module;
break;
return res;
}
+/* Returns struct btf corresponding to the struct module
+ *
+ * This function can return NULL or ERR_PTR. Note that caller must
+ * release reference for struct btf iff btf_is_module is true.
+ */
+static struct btf *btf_get_module_btf(const struct module *module)
+{
+ struct btf *btf = NULL;
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ struct btf_module *btf_mod, *tmp;
+#endif
+
+ if (!module)
+ return bpf_get_btf_vmlinux();
+#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+ mutex_lock(&btf_module_mutex);
+ list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) {
+ if (btf_mod->module != module)
+ continue;
+
+ btf_get(btf_mod->btf);
+ btf = btf_mod->btf;
+ break;
+ }
+ mutex_unlock(&btf_module_mutex);
+#endif
+
+ return btf;
+}
+
BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags)
{
struct btf *btf;
BTF_TRACING_TYPE_xxx
#undef BTF_TRACING_TYPE
-/* BTF ID set registration API for modules */
-
-#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
+/* Kernel Function (kfunc) BTF ID set registration API */
-void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
- struct kfunc_btf_id_set *s)
+static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
+ enum btf_kfunc_type type,
+ struct btf_id_set *add_set, bool vmlinux_set)
{
- mutex_lock(&l->mutex);
- list_add(&s->list, &l->list);
- mutex_unlock(&l->mutex);
+ struct btf_kfunc_set_tab *tab;
+ struct btf_id_set *set;
+ u32 set_cnt;
+ int ret;
+
+ if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) {
+ ret = -EINVAL;
+ goto end;
+ }
+
+ if (!add_set->cnt)
+ return 0;
+
+ tab = btf->kfunc_set_tab;
+ if (!tab) {
+ tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN);
+ if (!tab)
+ return -ENOMEM;
+ btf->kfunc_set_tab = tab;
+ }
+
+ set = tab->sets[hook][type];
+ /* Warn when register_btf_kfunc_id_set is called twice for the same hook
+ * for module sets.
+ */
+ if (WARN_ON_ONCE(set && !vmlinux_set)) {
+ ret = -EINVAL;
+ goto end;
+ }
+
+ /* We don't need to allocate, concatenate, and sort module sets, because
+ * only one is allowed per hook. Hence, we can directly assign the
+ * pointer and return.
+ */
+ if (!vmlinux_set) {
+ tab->sets[hook][type] = add_set;
+ return 0;
+ }
+
+ /* In case of vmlinux sets, there may be more than one set being
+ * registered per hook. To create a unified set, we allocate a new set
+ * and concatenate all individual sets being registered. While each set
+ * is individually sorted, they may become unsorted when concatenated,
+ * hence re-sorting the final set again is required to make binary
+ * searching the set using btf_id_set_contains function work.
+ */
+ set_cnt = set ? set->cnt : 0;
+
+ if (set_cnt > U32_MAX - add_set->cnt) {
+ ret = -EOVERFLOW;
+ goto end;
+ }
+
+ if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) {
+ ret = -E2BIG;
+ goto end;
+ }
+
+ /* Grow set */
+ set = krealloc(tab->sets[hook][type],
+ offsetof(struct btf_id_set, ids[set_cnt + add_set->cnt]),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!set) {
+ ret = -ENOMEM;
+ goto end;
+ }
+
+ /* For newly allocated set, initialize set->cnt to 0 */
+ if (!tab->sets[hook][type])
+ set->cnt = 0;
+ tab->sets[hook][type] = set;
+
+ /* Concatenate the two sets */
+ memcpy(set->ids + set->cnt, add_set->ids, add_set->cnt * sizeof(set->ids[0]));
+ set->cnt += add_set->cnt;
+
+ sort(set->ids, set->cnt, sizeof(set->ids[0]), btf_id_cmp_func, NULL);
+
+ return 0;
+end:
+ btf_free_kfunc_set_tab(btf);
+ return ret;
}
-EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set);
-void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
- struct kfunc_btf_id_set *s)
+static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook,
+ const struct btf_kfunc_id_set *kset)
{
- mutex_lock(&l->mutex);
- list_del_init(&s->list);
- mutex_unlock(&l->mutex);
+ bool vmlinux_set = !btf_is_module(btf);
+ int type, ret;
+
+ for (type = 0; type < ARRAY_SIZE(kset->sets); type++) {
+ if (!kset->sets[type])
+ continue;
+
+ ret = __btf_populate_kfunc_set(btf, hook, type, kset->sets[type], vmlinux_set);
+ if (ret)
+ break;
+ }
+ return ret;
}
-EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set);
-bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
- struct module *owner)
+static bool __btf_kfunc_id_set_contains(const struct btf *btf,
+ enum btf_kfunc_hook hook,
+ enum btf_kfunc_type type,
+ u32 kfunc_btf_id)
{
- struct kfunc_btf_id_set *s;
+ struct btf_id_set *set;
- mutex_lock(&klist->mutex);
- list_for_each_entry(s, &klist->list, list) {
- if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
- mutex_unlock(&klist->mutex);
- return true;
- }
+ if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX)
+ return false;
+ if (!btf->kfunc_set_tab)
+ return false;
+ set = btf->kfunc_set_tab->sets[hook][type];
+ if (!set)
+ return false;
+ return btf_id_set_contains(set, kfunc_btf_id);
+}
+
+static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
+{
+ switch (prog_type) {
+ case BPF_PROG_TYPE_XDP:
+ return BTF_KFUNC_HOOK_XDP;
+ case BPF_PROG_TYPE_SCHED_CLS:
+ return BTF_KFUNC_HOOK_TC;
+ case BPF_PROG_TYPE_STRUCT_OPS:
+ return BTF_KFUNC_HOOK_STRUCT_OPS;
+ default:
+ return BTF_KFUNC_HOOK_MAX;
}
- mutex_unlock(&klist->mutex);
- return false;
}
-#define DEFINE_KFUNC_BTF_ID_LIST(name) \
- struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \
- __MUTEX_INITIALIZER(name.mutex) }; \
- EXPORT_SYMBOL_GPL(name)
+/* Caution:
+ * Reference to the module (obtained using btf_try_get_module) corresponding to
+ * the struct btf *MUST* be held when calling this function from verifier
+ * context. This is usually true as we stash references in prog's kfunc_btf_tab;
+ * keeping the reference for the duration of the call provides the necessary
+ * protection for looking up a well-formed btf->kfunc_set_tab.
+ */
+bool btf_kfunc_id_set_contains(const struct btf *btf,
+ enum bpf_prog_type prog_type,
+ enum btf_kfunc_type type, u32 kfunc_btf_id)
+{
+ enum btf_kfunc_hook hook;
-DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
-DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+ hook = bpf_prog_type_to_kfunc_hook(prog_type);
+ return __btf_kfunc_id_set_contains(btf, hook, type, kfunc_btf_id);
+}
-#endif
+/* This function must be invoked only from initcalls/module init functions */
+int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
+ const struct btf_kfunc_id_set *kset)
+{
+ enum btf_kfunc_hook hook;
+ struct btf *btf;
+ int ret;
+
+ btf = btf_get_module_btf(kset->owner);
+ if (IS_ERR_OR_NULL(btf))
+ return btf ? PTR_ERR(btf) : -ENOENT;
+
+ hook = bpf_prog_type_to_kfunc_hook(prog_type);
+ ret = btf_populate_kfunc_set(btf, hook, kset);
+ /* reference is only taken for module BTF */
+ if (btf_is_module(btf))
+ btf_put(btf);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set);
int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id,
const struct btf *targ_btf, __u32 targ_id)
* NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr
* NET_XMIT_CN (2) - continue with packet output and notify TCP
* to call cwr
- * -EPERM - drop packet
+ * -err - drop packet
*
* For ingress packets, this function will return -EPERM if any
* attached program was found and if it returned != 1 during execution.
cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb);
} else {
ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb,
- __bpf_prog_run_save_cb);
- ret = (ret == 1 ? 0 : -EPERM);
+ __bpf_prog_run_save_cb, 0);
+ if (ret && !IS_ERR_VALUE((long)ret))
+ ret = -EFAULT;
}
bpf_restore_data_end(skb, saved_data_end);
__skb_pull(skb, offset);
enum cgroup_bpf_attach_type atype)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- int ret;
- ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, bpf_prog_run);
- return ret == 1 ? 0 : -EPERM;
+ return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk,
+ bpf_prog_run, 0);
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
};
struct sockaddr_storage unspec;
struct cgroup *cgrp;
- int ret;
/* Check socket family since not all sockets represent network
* endpoint (e.g. AF_UNIX).
}
cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx,
- bpf_prog_run, flags);
-
- return ret == 1 ? 0 : -EPERM;
+ return BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx,
+ bpf_prog_run, 0, flags);
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
enum cgroup_bpf_attach_type atype)
{
struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
- int ret;
- ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops,
- bpf_prog_run);
- return ret == 1 ? 0 : -EPERM;
+ return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops,
+ bpf_prog_run, 0);
}
EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
.major = major,
.minor = minor,
};
- int allow;
+ int ret;
rcu_read_lock();
cgrp = task_dfl_cgroup(current);
- allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
- bpf_prog_run);
+ ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
+ bpf_prog_run, 0);
rcu_read_unlock();
- return !allow;
+ return ret;
}
+BPF_CALL_0(bpf_get_retval)
+{
+ struct bpf_cg_run_ctx *ctx =
+ container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+
+ return ctx->retval;
+}
+
+static const struct bpf_func_proto bpf_get_retval_proto = {
+ .func = bpf_get_retval,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+};
+
+BPF_CALL_1(bpf_set_retval, int, retval)
+{
+ struct bpf_cg_run_ctx *ctx =
+ container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+
+ ctx->retval = retval;
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_set_retval_proto = {
+ .func = bpf_set_retval,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+};
+
static const struct bpf_func_proto *
cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
{
return &bpf_get_current_cgroup_id_proto;
case BPF_FUNC_perf_event_output:
return &bpf_event_output_data_proto;
+ case BPF_FUNC_get_retval:
+ return &bpf_get_retval_proto;
+ case BPF_FUNC_set_retval:
+ return &bpf_set_retval_proto;
default:
return bpf_base_func_proto(func_id);
}
rcu_read_lock();
cgrp = task_dfl_cgroup(current);
- ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, bpf_prog_run);
+ ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx,
+ bpf_prog_run, 0);
rcu_read_unlock();
kfree(ctx.cur_val);
kfree(ctx.new_val);
}
- return ret == 1 ? 0 : -EPERM;
+ return ret;
}
#ifdef CONFIG_NET
lock_sock(sk);
ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT],
- &ctx, bpf_prog_run);
+ &ctx, bpf_prog_run, 0);
release_sock(sk);
- if (!ret) {
- ret = -EPERM;
+ if (ret)
goto out;
- }
if (ctx.optlen == -1) {
/* optlen set to -1, bypass kernel */
.sk = sk,
.level = level,
.optname = optname,
- .retval = retval,
+ .current_task = current,
};
int ret;
lock_sock(sk);
ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT],
- &ctx, bpf_prog_run);
+ &ctx, bpf_prog_run, retval);
release_sock(sk);
- if (!ret) {
- ret = -EPERM;
+ if (ret < 0)
goto out;
- }
if (ctx.optlen > max_optlen || ctx.optlen < 0) {
ret = -EFAULT;
goto out;
}
- /* BPF programs only allowed to set retval to 0, not some
- * arbitrary value.
- */
- if (ctx.retval != 0 && ctx.retval != retval) {
- ret = -EFAULT;
- goto out;
- }
-
if (ctx.optlen != 0) {
if (copy_to_user(optval, ctx.optval, ctx.optlen) ||
put_user(ctx.optlen, optlen)) {
}
}
- ret = ctx.retval;
-
out:
sockopt_free_buf(&ctx, &buf);
return ret;
.sk = sk,
.level = level,
.optname = optname,
- .retval = retval,
.optlen = *optlen,
.optval = optval,
.optval_end = optval + *optlen,
+ .current_task = current,
};
int ret;
*/
ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT],
- &ctx, bpf_prog_run);
- if (!ret)
- return -EPERM;
+ &ctx, bpf_prog_run, retval);
+ if (ret < 0)
+ return ret;
if (ctx.optlen > *optlen)
return -EFAULT;
- /* BPF programs only allowed to set retval to 0, not some
- * arbitrary value.
- */
- if (ctx.retval != 0 && ctx.retval != retval)
- return -EFAULT;
-
/* BPF programs can shrink the buffer, export the modifications.
*/
if (ctx.optlen != 0)
*optlen = ctx.optlen;
- return ctx.retval;
+ return ret;
}
#endif
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen);
break;
case offsetof(struct bpf_sockopt, retval):
- if (type == BPF_WRITE)
- *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval);
- else
- *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval);
+ BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0);
+
+ if (type == BPF_WRITE) {
+ int treg = BPF_REG_9;
+
+ if (si->src_reg == treg || si->dst_reg == treg)
+ --treg;
+ if (si->src_reg == treg || si->dst_reg == treg)
+ --treg;
+ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg,
+ offsetof(struct bpf_sockopt_kern, tmp_reg));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task),
+ treg, si->dst_reg,
+ offsetof(struct bpf_sockopt_kern, current_task));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx),
+ treg, treg,
+ offsetof(struct task_struct, bpf_ctx));
+ *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval),
+ treg, si->src_reg,
+ offsetof(struct bpf_cg_run_ctx, retval));
+ *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg,
+ offsetof(struct bpf_sockopt_kern, tmp_reg));
+ } else {
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task),
+ si->dst_reg, si->src_reg,
+ offsetof(struct bpf_sockopt_kern, current_task));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx),
+ si->dst_reg, si->dst_reg,
+ offsetof(struct task_struct, bpf_ctx));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval),
+ si->dst_reg, si->dst_reg,
+ offsetof(struct bpf_cg_run_ctx, retval));
+ }
break;
case offsetof(struct bpf_sockopt, optval):
*insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval);
}
#endif
-bool bpf_prog_array_compatible(struct bpf_array *array,
- const struct bpf_prog *fp)
+bool bpf_prog_map_compatible(struct bpf_map *map,
+ const struct bpf_prog *fp)
{
bool ret;
if (fp->kprobe_override)
return false;
- spin_lock(&array->aux->owner.lock);
-
- if (!array->aux->owner.type) {
+ spin_lock(&map->owner.lock);
+ if (!map->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
- array->aux->owner.type = fp->type;
- array->aux->owner.jited = fp->jited;
+ map->owner.type = fp->type;
+ map->owner.jited = fp->jited;
+ map->owner.xdp_has_frags = fp->aux->xdp_has_frags;
ret = true;
} else {
- ret = array->aux->owner.type == fp->type &&
- array->aux->owner.jited == fp->jited;
+ ret = map->owner.type == fp->type &&
+ map->owner.jited == fp->jited &&
+ map->owner.xdp_has_frags == fp->aux->xdp_has_frags;
}
- spin_unlock(&array->aux->owner.lock);
+ spin_unlock(&map->owner.lock);
+
return ret;
}
mutex_lock(&aux->used_maps_mutex);
for (i = 0; i < aux->used_map_cnt; i++) {
struct bpf_map *map = aux->used_maps[i];
- struct bpf_array *array;
- if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
+ if (!map_type_contains_progs(map))
continue;
- array = container_of(map, struct bpf_array, map);
- if (!bpf_prog_array_compatible(array, fp)) {
+ if (!bpf_prog_map_compatible(map, fp)) {
ret = -EINVAL;
goto out;
}
return 0;
}
-static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
+static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu,
+ struct bpf_map *map, int fd)
{
struct bpf_prog *prog;
if (IS_ERR(prog))
return PTR_ERR(prog);
- if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
+ if (prog->expected_attach_type != BPF_XDP_CPUMAP ||
+ !bpf_prog_map_compatible(map, prog)) {
bpf_prog_put(prog);
return -EINVAL;
}
rcpu->map_id = map->id;
rcpu->value.qsize = value->qsize;
- if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
+ if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd))
goto free_ptr_ring;
/* Setup kthread */
BPF_PROG_TYPE_XDP, false);
if (IS_ERR(prog))
goto err_put_dev;
- if (prog->expected_attach_type != BPF_XDP_DEVMAP)
+ if (prog->expected_attach_type != BPF_XDP_DEVMAP ||
+ !bpf_prog_map_compatible(&dtab->map, prog))
goto err_put_prog;
}
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
- const struct bpf_map *map = filp->private_data;
- const struct bpf_array *array;
+ struct bpf_map *map = filp->private_data;
u32 type = 0, jited = 0;
- if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
- array = container_of(map, struct bpf_array, map);
- spin_lock(&array->aux->owner.lock);
- type = array->aux->owner.type;
- jited = array->aux->owner.jited;
- spin_unlock(&array->aux->owner.lock);
+ if (map_type_contains_progs(map)) {
+ spin_lock(&map->owner.lock);
+ type = map->owner.type;
+ jited = map->owner.jited;
+ spin_unlock(&map->owner.lock);
}
seq_printf(m,
atomic64_set(&map->refcnt, 1);
atomic64_set(&map->usercnt, 1);
mutex_init(&map->freeze_mutex);
+ spin_lock_init(&map->owner.lock);
map->spin_lock_off = -EINVAL;
map->timer_off = -EINVAL;
BPF_F_ANY_ALIGNMENT |
BPF_F_TEST_STATE_FREQ |
BPF_F_SLEEPABLE |
- BPF_F_TEST_RND_HI32))
+ BPF_F_TEST_RND_HI32 |
+ BPF_F_XDP_HAS_FRAGS))
return -EINVAL;
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
prog->aux->dst_prog = dst_prog;
prog->aux->offload_requested = !!attr->prog_ifindex;
prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE;
+ prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS;
err = security_bpf_prog_alloc(prog->aux);
if (err)
case BPF_FLOW_DISSECTOR:
case BPF_SK_LOOKUP:
return netns_bpf_prog_query(attr, uattr);
+ case BPF_SK_SKB_STREAM_PARSER:
+ case BPF_SK_SKB_STREAM_VERDICT:
+ case BPF_SK_MSG_VERDICT:
+ case BPF_SK_SKB_VERDICT:
+ return sock_map_bpf_prog_query(attr, uattr);
default:
return -EINVAL;
}
{
return base_type(type) == PTR_TO_SOCKET ||
base_type(type) == PTR_TO_TCP_SOCK ||
- base_type(type) == PTR_TO_MEM;
+ base_type(type) == PTR_TO_MEM ||
+ base_type(type) == PTR_TO_BTF_ID;
}
static bool type_is_rdonly_mem(u32 type)
}
static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
- s16 offset, struct module **btf_modp)
+ s16 offset)
{
struct bpf_kfunc_btf kf_btf = { .offset = offset };
struct bpf_kfunc_btf_tab *tab;
sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
kfunc_btf_cmp_by_off, NULL);
}
- if (btf_modp)
- *btf_modp = b->module;
return b->btf;
}
}
static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env,
- u32 func_id, s16 offset,
- struct module **btf_modp)
+ u32 func_id, s16 offset)
{
if (offset) {
if (offset < 0) {
return ERR_PTR(-EINVAL);
}
- return __find_kfunc_desc_btf(env, offset, btf_modp);
+ return __find_kfunc_desc_btf(env, offset);
}
return btf_vmlinux ?: ERR_PTR(-ENOENT);
}
prog_aux->kfunc_btf_tab = btf_tab;
}
- desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL);
+ desc_btf = find_kfunc_desc_btf(env, func_id, offset);
if (IS_ERR(desc_btf)) {
verbose(env, "failed to find BTF for kernel function\n");
return PTR_ERR(desc_btf);
if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL)
return NULL;
- desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL);
+ desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off);
if (IS_ERR(desc_btf))
return "<error>";
#define MAX_PACKET_OFF 0xffff
-static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
-{
- return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
-}
-
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
const struct bpf_call_arg_meta *meta,
enum bpf_access_type t)
}
}
+static int check_mem_size_reg(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg, u32 regno,
+ bool zero_size_allowed,
+ struct bpf_call_arg_meta *meta)
+{
+ int err;
+
+ /* This is used to refine r0 return value bounds for helpers
+ * that enforce this value as an upper bound on return values.
+ * See do_refine_retval_range() for helpers that can refine
+ * the return value. C type of helper is u32 so we pull register
+ * bound from umax_value however, if negative verifier errors
+ * out. Only upper bounds can be learned because retval is an
+ * int type and negative retvals are allowed.
+ */
+ if (meta)
+ meta->msize_max_value = reg->umax_value;
+
+ /* The register is SCALAR_VALUE; the access check
+ * happens using its boundaries.
+ */
+ if (!tnum_is_const(reg->var_off))
+ /* For unprivileged variable accesses, disable raw
+ * mode so that the program is required to
+ * initialize all the memory that the helper could
+ * just partially fill up.
+ */
+ meta = NULL;
+
+ if (reg->smin_value < 0) {
+ verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
+ regno);
+ return -EACCES;
+ }
+
+ if (reg->umin_value == 0) {
+ err = check_helper_mem_access(env, regno - 1, 0,
+ zero_size_allowed,
+ meta);
+ if (err)
+ return err;
+ }
+
+ if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
+ verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
+ regno);
+ return -EACCES;
+ }
+ err = check_helper_mem_access(env, regno - 1,
+ reg->umax_value,
+ zero_size_allowed, meta);
+ if (!err)
+ err = mark_chain_precision(env, regno);
+ return err;
+}
+
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno, u32 mem_size)
{
return check_helper_mem_access(env, regno, mem_size, true, NULL);
}
+int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+ u32 regno)
+{
+ struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1];
+ bool may_be_null = type_may_be_null(mem_reg->type);
+ struct bpf_reg_state saved_reg;
+ int err;
+
+ WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5);
+
+ if (may_be_null) {
+ saved_reg = *mem_reg;
+ mark_ptr_not_null_reg(mem_reg);
+ }
+
+ err = check_mem_size_reg(env, reg, regno, true, NULL);
+
+ if (may_be_null)
+ *mem_reg = saved_reg;
+ return err;
+}
+
/* Implementation details:
* bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL
* Two bpf_map_lookups (even with the same key) will have different reg->id.
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
- /* This is used to refine r0 return value bounds for helpers
- * that enforce this value as an upper bound on return values.
- * See do_refine_retval_range() for helpers that can refine
- * the return value. C type of helper is u32 so we pull register
- * bound from umax_value however, if negative verifier errors
- * out. Only upper bounds can be learned because retval is an
- * int type and negative retvals are allowed.
- */
- meta->msize_max_value = reg->umax_value;
-
- /* The register is SCALAR_VALUE; the access check
- * happens using its boundaries.
- */
- if (!tnum_is_const(reg->var_off))
- /* For unprivileged variable accesses, disable raw
- * mode so that the program is required to
- * initialize all the memory that the helper could
- * just partially fill up.
- */
- meta = NULL;
-
- if (reg->smin_value < 0) {
- verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
- regno);
- return -EACCES;
- }
-
- if (reg->umin_value == 0) {
- err = check_helper_mem_access(env, regno - 1, 0,
- zero_size_allowed,
- meta);
- if (err)
- return err;
- }
-
- if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
- verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
- regno);
- return -EACCES;
- }
- err = check_helper_mem_access(env, regno - 1,
- reg->umax_value,
- zero_size_allowed, meta);
- if (!err)
- err = mark_chain_precision(env, regno);
+ err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta);
} else if (arg_type_is_alloc_size(arg_type)) {
if (!tnum_is_const(reg->var_off)) {
verbose(env, "R%d is not a known constant'\n",
}
}
-static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
+static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ int *insn_idx_p)
{
const struct btf_type *t, *func, *func_proto, *ptr_type;
struct bpf_reg_state *regs = cur_regs(env);
const char *func_name, *ptr_type_name;
u32 i, nargs, func_id, ptr_type_id;
- struct module *btf_mod = NULL;
+ int err, insn_idx = *insn_idx_p;
const struct btf_param *args;
struct btf *desc_btf;
- int err;
+ bool acq;
/* skip for now, but return error when we find this in fixup_kfunc_call */
if (!insn->imm)
return 0;
- desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod);
+ desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off);
if (IS_ERR(desc_btf))
return PTR_ERR(desc_btf);
func_name = btf_name_by_offset(desc_btf, func->name_off);
func_proto = btf_type_by_id(desc_btf, func->type);
- if (!env->ops->check_kfunc_call ||
- !env->ops->check_kfunc_call(func_id, btf_mod)) {
+ if (!btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
+ BTF_KFUNC_TYPE_CHECK, func_id)) {
verbose(env, "calling kernel function %s is not allowed\n",
func_name);
return -EACCES;
}
+ acq = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
+ BTF_KFUNC_TYPE_ACQUIRE, func_id);
+
/* Check the arguments */
err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs);
- if (err)
+ if (err < 0)
return err;
+ /* In case of release function, we get register number of refcounted
+ * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now
+ */
+ if (err) {
+ err = release_reference(env, regs[err].ref_obj_id);
+ if (err) {
+ verbose(env, "kfunc %s#%d reference has not been acquired before\n",
+ func_name, func_id);
+ return err;
+ }
+ }
for (i = 0; i < CALLER_SAVED_REGS; i++)
mark_reg_not_init(env, regs, caller_saved[i]);
/* Check return type */
t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
+
+ if (acq && !btf_type_is_ptr(t)) {
+ verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
+ return -EINVAL;
+ }
+
if (btf_type_is_scalar(t)) {
mark_reg_unknown(env, regs, BPF_REG_0);
mark_btf_func_reg_size(env, BPF_REG_0, t->size);
regs[BPF_REG_0].btf = desc_btf;
regs[BPF_REG_0].type = PTR_TO_BTF_ID;
regs[BPF_REG_0].btf_id = ptr_type_id;
+ if (btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog),
+ BTF_KFUNC_TYPE_RET_NULL, func_id)) {
+ regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
+ /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */
+ regs[BPF_REG_0].id = ++env->id_gen;
+ }
mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *));
+ if (acq) {
+ int id = acquire_reference_state(env, insn_idx);
+
+ if (id < 0)
+ return id;
+ regs[BPF_REG_0].id = id;
+ regs[BPF_REG_0].ref_obj_id = id;
+ }
} /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */
nargs = btf_type_vlen(func_proto);
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &env->insn_idx);
else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
- err = check_kfunc_call(env, insn);
+ err = check_kfunc_call(env, insn, &env->insn_idx);
else
err = check_helper_call(env, insn, &env->insn_idx);
if (err)
extern const struct bpf_func_proto bpf_skb_output_proto;
extern const struct bpf_func_proto bpf_xdp_output_proto;
+extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto;
BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
struct bpf_map *, map, u64, flags)
return &bpf_sock_from_file_proto;
case BPF_FUNC_get_socket_cookie:
return &bpf_get_socket_ptr_cookie_proto;
+ case BPF_FUNC_xdp_get_buff_len:
+ return &bpf_xdp_get_buff_len_trace_proto;
#endif
case BPF_FUNC_seq_printf:
return prog->expected_attach_type == BPF_TRACE_ITER ?
return -ENOMEM;
}
- refcount_set(&ax25_rt->refcount, 1);
ax25_rt->callsign = route->dest_addr;
ax25_rt->dev = ax25_dev->dev;
ax25_rt->digipeat = NULL;
ax25cmp(&route->dest_addr, &s->callsign) == 0) {
if (ax25_route_list == s) {
ax25_route_list = s->next;
- ax25_put_route(s);
+ __ax25_put_route(s);
} else {
for (t = ax25_route_list; t != NULL; t = t->next) {
if (t->next == s) {
t->next = s->next;
- ax25_put_route(s);
+ __ax25_put_route(s);
break;
}
}
bacpy(&conn->dst, dst);
bacpy(&conn->src, &hdev->bdaddr);
+ conn->handle = HCI_CONN_HANDLE_UNSET;
conn->hdev = hdev;
conn->type = type;
conn->role = role;
INIT_LIST_HEAD(&hdev->conn_hash.list);
INIT_LIST_HEAD(&hdev->adv_instances);
INIT_LIST_HEAD(&hdev->blocked_keys);
+ INIT_LIST_HEAD(&hdev->monitored_devices);
INIT_LIST_HEAD(&hdev->local_codecs);
INIT_WORK(&hdev->rx_work, hci_rx_work);
sco_recv_scodata(conn, skb);
return;
} else {
- bt_dev_err(hdev, "SCO packet for unknown connection handle %d",
- handle);
+ bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d",
+ handle);
}
kfree_skb(skb);
struct hci_ev_conn_complete *ev = data;
struct hci_conn *conn;
+ if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) {
+ bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle");
+ return;
+ }
+
bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
hci_dev_lock(hdev);
}
}
+ /* The HCI_Connection_Complete event is only sent once per connection.
+ * Processing it more than once per connection can corrupt kernel memory.
+ *
+ * As the connection handle is set here for the first time, it indicates
+ * whether the connection is already set up.
+ */
+ if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+ bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection");
+ goto unlock;
+ }
+
if (!ev->status) {
conn->handle = __le16_to_cpu(ev->handle);
if (!info) {
bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x",
HCI_EV_INQUIRY_RESULT_WITH_RSSI);
- return;
+ goto unlock;
}
bacpy(&data.bdaddr, &info->bdaddr);
if (!info) {
bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x",
HCI_EV_INQUIRY_RESULT_WITH_RSSI);
- return;
+ goto unlock;
}
bacpy(&data.bdaddr, &info->bdaddr);
bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x",
HCI_EV_INQUIRY_RESULT_WITH_RSSI);
}
-
+unlock:
hci_dev_unlock(hdev);
}
struct hci_ev_sync_conn_complete *ev = data;
struct hci_conn *conn;
+ switch (ev->link_type) {
+ case SCO_LINK:
+ case ESCO_LINK:
+ break;
+ default:
+ /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type
+ * for HCI_Synchronous_Connection_Complete is limited to
+ * either SCO or eSCO
+ */
+ bt_dev_err(hdev, "Ignoring connect complete event for invalid link type");
+ return;
+ }
+
+ if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) {
+ bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle");
+ return;
+ }
+
bt_dev_dbg(hdev, "status 0x%2.2x", ev->status);
hci_dev_lock(hdev);
goto unlock;
}
+ /* The HCI_Synchronous_Connection_Complete event is only sent once per connection.
+ * Processing it more than once per connection can corrupt kernel memory.
+ *
+ * As the connection handle is set here for the first time, it indicates
+ * whether the connection is already set up.
+ */
+ if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+ bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection");
+ goto unlock;
+ }
+
switch (ev->status) {
case 0x00:
- /* The synchronous connection complete event should only be
- * sent once per new connection. Receiving a successful
- * complete event when the connection status is already
- * BT_CONNECTED means that the device is misbehaving and sent
- * multiple complete event packets for the same new connection.
- *
- * Registering the device more than once can corrupt kernel
- * memory, hence upon detecting this invalid event, we report
- * an error and ignore the packet.
- */
- if (conn->state == BT_CONNECTED) {
- bt_dev_err(hdev, "Ignoring connect complete event for existing connection");
- goto unlock;
- }
-
conn->handle = __le16_to_cpu(ev->handle);
conn->state = BT_CONNECTED;
conn->type = ev->link_type;
struct smp_irk *irk;
u8 addr_type;
+ if (handle > HCI_CONN_HANDLE_MAX) {
+ bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle");
+ return;
+ }
+
hci_dev_lock(hdev);
/* All controllers implicitly stop advertising in the event of a
cancel_delayed_work(&conn->le_conn_timeout);
}
+ /* The HCI_LE_Connection_Complete event is only sent once per connection.
+ * Processing it more than once per connection can corrupt kernel memory.
+ *
+ * As the connection handle is set here for the first time, it indicates
+ * whether the connection is already set up.
+ */
+ if (conn->handle != HCI_CONN_HANDLE_UNSET) {
+ bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection");
+ goto unlock;
+ }
+
le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa);
/* Lookup the identity address from the stored connection
HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt,
sizeof(struct hci_ev_num_comp_blocks)),
/* [0xff = HCI_EV_VENDOR] */
- HCI_EV(HCI_EV_VENDOR, msft_vendor_evt, 0),
+ HCI_EV_VL(HCI_EV_VENDOR, msft_vendor_evt, 0, HCI_MAX_EVENT_SIZE),
};
static void hci_event_func(struct hci_dev *hdev, u8 event, struct sk_buff *skb,
* decide if that is acceptable.
*/
if (skb->len > ev->max_len)
- bt_dev_warn(hdev, "unexpected event 0x%2.2x length: %u > %u",
- event, skb->len, ev->max_len);
+ bt_dev_warn_ratelimited(hdev,
+ "unexpected event 0x%2.2x length: %u > %u",
+ event, skb->len, ev->max_len);
data = hci_ev_skb_pull(hdev, skb, event, ev->min_len);
if (!data)
{
struct hci_cmd_sync_work_entry *entry;
+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+ return -ENODEV;
+
entry = kmalloc(sizeof(*entry), GFP_KERNEL);
if (!entry)
return -ENOMEM;
p->max_ce_len = cpu_to_le16(0x0000);
}
-int hci_le_ext_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn,
- u8 own_addr_type)
+static int hci_le_ext_create_conn_sync(struct hci_dev *hdev,
+ struct hci_conn *conn, u8 own_addr_type)
{
struct hci_cp_le_ext_create_conn *cp;
struct hci_cp_le_ext_conn_param *p;
#include "aosp.h"
#define MGMT_VERSION 1
-#define MGMT_REVISION 21
+#define MGMT_REVISION 22
static const u16 mgmt_commands[] = {
MGMT_OP_READ_INDEX_LIST,
MGMT_EV_ADV_MONITOR_REMOVED,
MGMT_EV_CONTROLLER_SUSPEND,
MGMT_EV_CONTROLLER_RESUME,
+ MGMT_EV_ADV_MONITOR_DEVICE_FOUND,
+ MGMT_EV_ADV_MONITOR_DEVICE_LOST,
};
static const u16 mgmt_untrusted_commands[] = {
return true;
}
+void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle,
+ bdaddr_t *bdaddr, u8 addr_type)
+{
+ struct mgmt_ev_adv_monitor_device_lost ev;
+
+ ev.monitor_handle = cpu_to_le16(handle);
+ bacpy(&ev.addr.bdaddr, bdaddr);
+ ev.addr.type = addr_type;
+
+ mgmt_event(MGMT_EV_ADV_MONITOR_DEVICE_LOST, hdev, &ev, sizeof(ev),
+ NULL);
+}
+
+static void mgmt_adv_monitor_device_found(struct hci_dev *hdev,
+ bdaddr_t *bdaddr, bool report_device,
+ struct sk_buff *skb,
+ struct sock *skip_sk)
+{
+ struct sk_buff *advmon_skb;
+ size_t advmon_skb_len;
+ __le16 *monitor_handle;
+ struct monitored_device *dev, *tmp;
+ bool matched = false;
+ bool notify = false;
+
+ /* We have received the Advertisement Report because:
+ * 1. the kernel has initiated active discovery
+ * 2. if not, we have pend_le_reports > 0 in which case we are doing
+ * passive scanning
+ * 3. if none of the above is true, we have one or more active
+ * Advertisement Monitor
+ *
+ * For case 1 and 2, report all advertisements via MGMT_EV_DEVICE_FOUND
+ * and report ONLY one advertisement per device for the matched Monitor
+ * via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event.
+ *
+ * For case 3, since we are not active scanning and all advertisements
+ * received are due to a matched Advertisement Monitor, report all
+ * advertisements ONLY via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event.
+ */
+ if (report_device && !hdev->advmon_pend_notify) {
+ mgmt_event_skb(skb, skip_sk);
+ return;
+ }
+
+ advmon_skb_len = (sizeof(struct mgmt_ev_adv_monitor_device_found) -
+ sizeof(struct mgmt_ev_device_found)) + skb->len;
+ advmon_skb = mgmt_alloc_skb(hdev, MGMT_EV_ADV_MONITOR_DEVICE_FOUND,
+ advmon_skb_len);
+ if (!advmon_skb) {
+ if (report_device)
+ mgmt_event_skb(skb, skip_sk);
+ else
+ kfree_skb(skb);
+ return;
+ }
+
+ /* ADV_MONITOR_DEVICE_FOUND is similar to DEVICE_FOUND event except
+ * that it also has 'monitor_handle'. Make a copy of DEVICE_FOUND and
+ * store monitor_handle of the matched monitor.
+ */
+ monitor_handle = skb_put(advmon_skb, sizeof(*monitor_handle));
+ skb_put_data(advmon_skb, skb->data, skb->len);
+
+ hdev->advmon_pend_notify = false;
+
+ list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) {
+ if (!bacmp(&dev->bdaddr, bdaddr)) {
+ matched = true;
+
+ if (!dev->notified) {
+ *monitor_handle = cpu_to_le16(dev->handle);
+ notify = true;
+ dev->notified = true;
+ }
+ }
+
+ if (!dev->notified)
+ hdev->advmon_pend_notify = true;
+ }
+
+ if (!report_device &&
+ ((matched && !notify) || !msft_monitor_supported(hdev))) {
+ /* Handle 0 indicates that we are not active scanning and this
+ * is a subsequent advertisement report for an already matched
+ * Advertisement Monitor or the controller offloading support
+ * is not available.
+ */
+ *monitor_handle = 0;
+ notify = true;
+ }
+
+ if (report_device)
+ mgmt_event_skb(skb, skip_sk);
+ else
+ kfree_skb(skb);
+
+ if (notify)
+ mgmt_event_skb(advmon_skb, skip_sk);
+ else
+ kfree_skb(advmon_skb);
+}
+
void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
u8 addr_type, u8 *dev_class, s8 rssi, u32 flags,
u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len)
{
struct sk_buff *skb;
struct mgmt_ev_device_found *ev;
+ bool report_device = hci_discovery_active(hdev);
/* Don't send events for a non-kernel initiated discovery. With
* LE one exception is if we have pend_le_reports > 0 in which
if (!hci_discovery_active(hdev)) {
if (link_type == ACL_LINK)
return;
- if (link_type == LE_LINK &&
- list_empty(&hdev->pend_le_reports) &&
- !hci_is_adv_monitoring(hdev)) {
+ if (link_type == LE_LINK && !list_empty(&hdev->pend_le_reports))
+ report_device = true;
+ else if (!hci_is_adv_monitoring(hdev))
return;
- }
}
if (hdev->discovery.result_filtering) {
ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len);
- mgmt_event_skb(skb, NULL);
+ mgmt_adv_monitor_device_found(hdev, bdaddr, report_device, skb, NULL);
}
void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
__u8 sub_opcode;
} __packed;
+#define MSFT_EV_LE_MONITOR_DEVICE 0x02
+struct msft_ev_le_monitor_device {
+ __u8 addr_type;
+ bdaddr_t bdaddr;
+ __u8 monitor_handle;
+ __u8 monitor_state;
+} __packed;
+
struct msft_monitor_advertisement_handle_data {
__u8 msft_handle;
__u16 mgmt_handle;
return NULL;
}
+/* This function requires the caller holds hdev->lock */
+static int msft_monitor_device_del(struct hci_dev *hdev, __u16 mgmt_handle,
+ bdaddr_t *bdaddr, __u8 addr_type,
+ bool notify)
+{
+ struct monitored_device *dev, *tmp;
+ int count = 0;
+
+ list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) {
+ /* mgmt_handle == 0 indicates remove all devices, whereas,
+ * bdaddr == NULL indicates remove all devices matching the
+ * mgmt_handle.
+ */
+ if ((!mgmt_handle || dev->handle == mgmt_handle) &&
+ (!bdaddr || (!bacmp(bdaddr, &dev->bdaddr) &&
+ addr_type == dev->addr_type))) {
+ if (notify && dev->notified) {
+ mgmt_adv_monitor_device_lost(hdev, dev->handle,
+ &dev->bdaddr,
+ dev->addr_type);
+ }
+
+ list_del(&dev->list);
+ kfree(dev);
+ count++;
+ }
+ }
+
+ return count;
+}
+
static void msft_le_monitor_advertisement_cb(struct hci_dev *hdev,
u8 status, u16 opcode,
struct sk_buff *skb)
if (monitor && !msft->suspending)
hci_free_adv_monitor(hdev, monitor);
+ /* Clear any monitored devices by this Adv Monitor */
+ msft_monitor_device_del(hdev, handle_data->mgmt_handle, NULL,
+ 0, false);
+
list_del(&handle_data->list);
kfree(handle_data);
}
list_del(&handle_data->list);
kfree(handle_data);
}
+
+ hci_dev_lock(hdev);
+
+ /* Clear any devices that are being monitored and notify device lost */
+ hdev->advmon_pend_notify = false;
+ msft_monitor_device_del(hdev, 0, NULL, 0, true);
+
+ hci_dev_unlock(hdev);
}
void msft_register(struct hci_dev *hdev)
kfree(msft);
}
+/* This function requires the caller holds hdev->lock */
+static void msft_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ __u8 addr_type, __u16 mgmt_handle)
+{
+ struct monitored_device *dev;
+
+ dev = kmalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev) {
+ bt_dev_err(hdev, "MSFT vendor event %u: no memory",
+ MSFT_EV_LE_MONITOR_DEVICE);
+ return;
+ }
+
+ bacpy(&dev->bdaddr, bdaddr);
+ dev->addr_type = addr_type;
+ dev->handle = mgmt_handle;
+ dev->notified = false;
+
+ INIT_LIST_HEAD(&dev->list);
+ list_add(&dev->list, &hdev->monitored_devices);
+ hdev->advmon_pend_notify = true;
+}
+
+/* This function requires the caller holds hdev->lock */
+static void msft_device_lost(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ __u8 addr_type, __u16 mgmt_handle)
+{
+ if (!msft_monitor_device_del(hdev, mgmt_handle, bdaddr, addr_type,
+ true)) {
+ bt_dev_err(hdev, "MSFT vendor event %u: dev %pMR not in list",
+ MSFT_EV_LE_MONITOR_DEVICE, bdaddr);
+ }
+}
+
+static void *msft_skb_pull(struct hci_dev *hdev, struct sk_buff *skb,
+ u8 ev, size_t len)
+{
+ void *data;
+
+ data = skb_pull_data(skb, len);
+ if (!data)
+ bt_dev_err(hdev, "Malformed MSFT vendor event: 0x%02x", ev);
+
+ return data;
+}
+
+/* This function requires the caller holds hdev->lock */
+static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ struct msft_ev_le_monitor_device *ev;
+ struct msft_monitor_advertisement_handle_data *handle_data;
+ u8 addr_type;
+
+ ev = msft_skb_pull(hdev, skb, MSFT_EV_LE_MONITOR_DEVICE, sizeof(*ev));
+ if (!ev)
+ return;
+
+ bt_dev_dbg(hdev,
+ "MSFT vendor event 0x%02x: handle 0x%04x state %d addr %pMR",
+ MSFT_EV_LE_MONITOR_DEVICE, ev->monitor_handle,
+ ev->monitor_state, &ev->bdaddr);
+
+ handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false);
+ if (!handle_data)
+ return;
+
+ switch (ev->addr_type) {
+ case ADDR_LE_DEV_PUBLIC:
+ addr_type = BDADDR_LE_PUBLIC;
+ break;
+
+ case ADDR_LE_DEV_RANDOM:
+ addr_type = BDADDR_LE_RANDOM;
+ break;
+
+ default:
+ bt_dev_err(hdev,
+ "MSFT vendor event 0x%02x: unknown addr type 0x%02x",
+ MSFT_EV_LE_MONITOR_DEVICE, ev->addr_type);
+ return;
+ }
+
+ if (ev->monitor_state)
+ msft_device_found(hdev, &ev->bdaddr, addr_type,
+ handle_data->mgmt_handle);
+ else
+ msft_device_lost(hdev, &ev->bdaddr, addr_type,
+ handle_data->mgmt_handle);
+}
+
void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb)
{
struct msft_data *msft = hdev->msft_data;
- u8 event;
+ u8 *evt_prefix;
+ u8 *evt;
if (!msft)
return;
* matches, and otherwise just return.
*/
if (msft->evt_prefix_len > 0) {
- if (skb->len < msft->evt_prefix_len)
+ evt_prefix = msft_skb_pull(hdev, skb, 0, msft->evt_prefix_len);
+ if (!evt_prefix)
return;
- if (memcmp(skb->data, msft->evt_prefix, msft->evt_prefix_len))
+ if (memcmp(evt_prefix, msft->evt_prefix, msft->evt_prefix_len))
return;
-
- skb_pull(skb, msft->evt_prefix_len);
}
/* Every event starts at least with an event code and the rest of
if (skb->len < 1)
return;
- event = *skb->data;
- skb_pull(skb, 1);
+ evt = msft_skb_pull(hdev, skb, 0, sizeof(*evt));
+ if (!evt)
+ return;
+
+ hci_dev_lock(hdev);
+
+ switch (*evt) {
+ case MSFT_EV_LE_MONITOR_DEVICE:
+ msft_monitor_device_evt(hdev, skb);
+ break;
- bt_dev_dbg(hdev, "MSFT vendor event %u", event);
+ default:
+ bt_dev_dbg(hdev, "MSFT vendor event 0x%02x", *evt);
+ break;
+ }
+
+ hci_dev_unlock(hdev);
}
__u64 msft_get_features(struct hci_dev *hdev)
#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/slab.h>
+#include <linux/init.h>
#include <linux/vmalloc.h>
#include <linux/etherdevice.h>
#include <linux/filter.h>
static int bpf_test_finish(const union bpf_attr *kattr,
union bpf_attr __user *uattr, const void *data,
- u32 size, u32 retval, u32 duration)
+ struct skb_shared_info *sinfo, u32 size,
+ u32 retval, u32 duration)
{
void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
int err = -EFAULT;
err = -ENOSPC;
}
- if (data_out && copy_to_user(data_out, data, copy_size))
- goto out;
+ if (data_out) {
+ int len = sinfo ? copy_size - sinfo->xdp_frags_size : copy_size;
+
+ if (copy_to_user(data_out, data, len))
+ goto out;
+
+ if (sinfo) {
+ int i, offset = len, data_len;
+
+ for (i = 0; i < sinfo->nr_frags; i++) {
+ skb_frag_t *frag = &sinfo->frags[i];
+
+ if (offset >= copy_size) {
+ err = -ENOSPC;
+ break;
+ }
+
+ data_len = min_t(int, copy_size - offset,
+ skb_frag_size(frag));
+
+ if (copy_to_user(data_out + offset,
+ skb_frag_address(frag),
+ data_len))
+ goto out;
+
+ offset += data_len;
+ }
+ }
+ }
+
if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
goto out;
if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
{
return a + 1;
}
+EXPORT_SYMBOL_GPL(bpf_fentry_test1);
+ALLOW_ERROR_INJECTION(bpf_fentry_test1, ERRNO);
int noinline bpf_fentry_test2(int a, u64 b)
{
return sk;
}
+struct prog_test_ref_kfunc {
+ int a;
+ int b;
+ struct prog_test_ref_kfunc *next;
+};
+
+static struct prog_test_ref_kfunc prog_test_struct = {
+ .a = 42,
+ .b = 108,
+ .next = &prog_test_struct,
+};
+
+noinline struct prog_test_ref_kfunc *
+bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr)
+{
+ /* randomly return NULL */
+ if (get_jiffies_64() % 2)
+ return NULL;
+ return &prog_test_struct;
+}
+
+noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p)
+{
+}
+
+struct prog_test_pass1 {
+ int x0;
+ struct {
+ int x1;
+ struct {
+ int x2;
+ struct {
+ int x3;
+ };
+ };
+ };
+};
+
+struct prog_test_pass2 {
+ int len;
+ short arr1[4];
+ struct {
+ char arr2[4];
+ unsigned long arr3[8];
+ } x;
+};
+
+struct prog_test_fail1 {
+ void *p;
+ int x;
+};
+
+struct prog_test_fail2 {
+ int x8;
+ struct prog_test_pass1 x;
+};
+
+struct prog_test_fail3 {
+ int len;
+ char arr1[2];
+ char arr2[];
+};
+
+noinline void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb)
+{
+}
+
+noinline void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p)
+{
+}
+
+noinline void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p)
+{
+}
+
+noinline void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p)
+{
+}
+
+noinline void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p)
+{
+}
+
+noinline void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p)
+{
+}
+
+noinline void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz)
+{
+}
+
+noinline void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len)
+{
+}
+
+noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len)
+{
+}
+
__diag_pop();
ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO);
-BTF_SET_START(test_sk_kfunc_ids)
+BTF_SET_START(test_sk_check_kfunc_ids)
BTF_ID(func, bpf_kfunc_call_test1)
BTF_ID(func, bpf_kfunc_call_test2)
BTF_ID(func, bpf_kfunc_call_test3)
-BTF_SET_END(test_sk_kfunc_ids)
-
-bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner)
-{
- if (btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id))
- return true;
- return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner);
-}
-
-static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
- u32 headroom, u32 tailroom)
+BTF_ID(func, bpf_kfunc_call_test_acquire)
+BTF_ID(func, bpf_kfunc_call_test_release)
+BTF_ID(func, bpf_kfunc_call_test_pass_ctx)
+BTF_ID(func, bpf_kfunc_call_test_pass1)
+BTF_ID(func, bpf_kfunc_call_test_pass2)
+BTF_ID(func, bpf_kfunc_call_test_fail1)
+BTF_ID(func, bpf_kfunc_call_test_fail2)
+BTF_ID(func, bpf_kfunc_call_test_fail3)
+BTF_ID(func, bpf_kfunc_call_test_mem_len_pass1)
+BTF_ID(func, bpf_kfunc_call_test_mem_len_fail1)
+BTF_ID(func, bpf_kfunc_call_test_mem_len_fail2)
+BTF_SET_END(test_sk_check_kfunc_ids)
+
+BTF_SET_START(test_sk_acquire_kfunc_ids)
+BTF_ID(func, bpf_kfunc_call_test_acquire)
+BTF_SET_END(test_sk_acquire_kfunc_ids)
+
+BTF_SET_START(test_sk_release_kfunc_ids)
+BTF_ID(func, bpf_kfunc_call_test_release)
+BTF_SET_END(test_sk_release_kfunc_ids)
+
+BTF_SET_START(test_sk_ret_null_kfunc_ids)
+BTF_ID(func, bpf_kfunc_call_test_acquire)
+BTF_SET_END(test_sk_ret_null_kfunc_ids)
+
+static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size,
+ u32 size, u32 headroom, u32 tailroom)
{
void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
- u32 user_size = kattr->test.data_size_in;
void *data;
if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
if (kattr->test.flags || kattr->test.cpu)
return -EINVAL;
- data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
+ data = bpf_test_init(kattr, kattr->test.data_size_in,
+ size, NET_SKB_PAD + NET_IP_ALIGN,
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
if (IS_ERR(data))
return PTR_ERR(data);
/* bpf program can never convert linear skb to non-linear */
if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
size = skb_headlen(skb);
- ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+ ret = bpf_test_finish(kattr, uattr, skb->data, NULL, size, retval,
+ duration);
if (!ret)
ret = bpf_ctx_finish(kattr, uattr, ctx,
sizeof(struct __sk_buff));
union bpf_attr __user *uattr)
{
u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
- u32 headroom = XDP_PACKET_HEADROOM;
u32 size = kattr->test.data_size_in;
+ u32 headroom = XDP_PACKET_HEADROOM;
+ u32 retval, duration, max_data_sz;
u32 repeat = kattr->test.repeat;
struct netdev_rx_queue *rxqueue;
+ struct skb_shared_info *sinfo;
struct xdp_buff xdp = {};
- u32 retval, duration;
+ int i, ret = -EINVAL;
struct xdp_md *ctx;
- u32 max_data_sz;
void *data;
- int ret = -EINVAL;
if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
prog->expected_attach_type == BPF_XDP_CPUMAP)
headroom -= ctx->data;
}
- /* XDP have extra tailroom as (most) drivers use full page */
max_data_sz = 4096 - headroom - tailroom;
+ size = min_t(u32, size, max_data_sz);
- data = bpf_test_init(kattr, max_data_sz, headroom, tailroom);
+ data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom);
if (IS_ERR(data)) {
ret = PTR_ERR(data);
goto free_ctx;
}
rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
- xdp_init_buff(&xdp, headroom + max_data_sz + tailroom,
- &rxqueue->xdp_rxq);
+ rxqueue->xdp_rxq.frag_size = headroom + max_data_sz + tailroom;
+ xdp_init_buff(&xdp, rxqueue->xdp_rxq.frag_size, &rxqueue->xdp_rxq);
xdp_prepare_buff(&xdp, data, headroom, size, true);
+ sinfo = xdp_get_shared_info_from_buff(&xdp);
ret = xdp_convert_md_to_buff(ctx, &xdp);
if (ret)
goto free_data;
+ if (unlikely(kattr->test.data_size_in > size)) {
+ void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
+
+ while (size < kattr->test.data_size_in) {
+ struct page *page;
+ skb_frag_t *frag;
+ int data_len;
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ frag = &sinfo->frags[sinfo->nr_frags++];
+ __skb_frag_set_page(frag, page);
+
+ data_len = min_t(int, kattr->test.data_size_in - size,
+ PAGE_SIZE);
+ skb_frag_size_set(frag, data_len);
+
+ if (copy_from_user(page_address(page), data_in + size,
+ data_len)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ sinfo->xdp_frags_size += data_len;
+ size += data_len;
+ }
+ xdp_buff_set_frags_flag(&xdp);
+ }
+
if (repeat > 1)
bpf_prog_change_xdp(NULL, prog);
+
ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true);
/* We convert the xdp_buff back to an xdp_md before checking the return
* code so the reference count of any held netdevice will be decremented
if (ret)
goto out;
- if (xdp.data_meta != data + headroom ||
- xdp.data_end != xdp.data_meta + size)
- size = xdp.data_end - xdp.data_meta;
-
- ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval,
- duration);
+ size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size;
+ ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size,
+ retval, duration);
if (!ret)
ret = bpf_ctx_finish(kattr, uattr, ctx,
sizeof(struct xdp_md));
if (repeat > 1)
bpf_prog_change_xdp(prog, NULL);
free_data:
+ for (i = 0; i < sinfo->nr_frags; i++)
+ __free_page(skb_frag_page(&sinfo->frags[i]));
kfree(data);
free_ctx:
kfree(ctx);
if (size < ETH_HLEN)
return -EINVAL;
- data = bpf_test_init(kattr, size, 0, 0);
+ data = bpf_test_init(kattr, kattr->test.data_size_in, size, 0, 0);
if (IS_ERR(data))
return PTR_ERR(data);
if (ret < 0)
goto out;
- ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys),
- retval, duration);
+ ret = bpf_test_finish(kattr, uattr, &flow_keys, NULL,
+ sizeof(flow_keys), retval, duration);
if (!ret)
ret = bpf_ctx_finish(kattr, uattr, user_ctx,
sizeof(struct bpf_flow_keys));
user_ctx->cookie = sock_gen_cookie(ctx.selected_sk);
}
- ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration);
+ ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, retval, duration);
if (!ret)
ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx));
kfree(ctx);
return err;
}
+
+static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &test_sk_check_kfunc_ids,
+ .acquire_set = &test_sk_acquire_kfunc_ids,
+ .release_set = &test_sk_release_kfunc_ids,
+ .ret_null_set = &test_sk_ret_null_kfunc_ids,
+};
+
+static int __init bpf_prog_test_run_init(void)
+{
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set);
+}
+late_initcall(bpf_prog_test_run_init);
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_ANYTHING,
};
+
+BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp)
+{
+ return xdp_get_buff_len(xdp);
+}
+
+static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = {
+ .func = bpf_xdp_get_buff_len,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff)
+
+const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = {
+ .func = bpf_xdp_get_buff_len,
+ .gpl_only = false,
+ .arg1_type = ARG_PTR_TO_BTF_ID,
+ .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0],
+};
+
static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
{
return xdp_data_meta_unsupported(xdp) ? 0 :
.arg2_type = ARG_ANYTHING,
};
+static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
+ void *buf, unsigned long len, bool flush)
+{
+ unsigned long ptr_len, ptr_off = 0;
+ skb_frag_t *next_frag, *end_frag;
+ struct skb_shared_info *sinfo;
+ void *src, *dst;
+ u8 *ptr_buf;
+
+ if (likely(xdp->data_end - xdp->data >= off + len)) {
+ src = flush ? buf : xdp->data + off;
+ dst = flush ? xdp->data + off : buf;
+ memcpy(dst, src, len);
+ return;
+ }
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ end_frag = &sinfo->frags[sinfo->nr_frags];
+ next_frag = &sinfo->frags[0];
+
+ ptr_len = xdp->data_end - xdp->data;
+ ptr_buf = xdp->data;
+
+ while (true) {
+ if (off < ptr_off + ptr_len) {
+ unsigned long copy_off = off - ptr_off;
+ unsigned long copy_len = min(len, ptr_len - copy_off);
+
+ src = flush ? buf : ptr_buf + copy_off;
+ dst = flush ? ptr_buf + copy_off : buf;
+ memcpy(dst, src, copy_len);
+
+ off += copy_len;
+ len -= copy_len;
+ buf += copy_len;
+ }
+
+ if (!len || next_frag == end_frag)
+ break;
+
+ ptr_off += ptr_len;
+ ptr_buf = skb_frag_address(next_frag);
+ ptr_len = skb_frag_size(next_frag);
+ next_frag++;
+ }
+}
+
+static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
+{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+ u32 size = xdp->data_end - xdp->data;
+ void *addr = xdp->data;
+ int i;
+
+ if (unlikely(offset > 0xffff || len > 0xffff))
+ return ERR_PTR(-EFAULT);
+
+ if (offset + len > xdp_get_buff_len(xdp))
+ return ERR_PTR(-EINVAL);
+
+ if (offset < size) /* linear area */
+ goto out;
+
+ offset -= size;
+ for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */
+ u32 frag_size = skb_frag_size(&sinfo->frags[i]);
+
+ if (offset < frag_size) {
+ addr = skb_frag_address(&sinfo->frags[i]);
+ size = frag_size;
+ break;
+ }
+ offset -= frag_size;
+ }
+out:
+ return offset + len < size ? addr + offset : NULL;
+}
+
+BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset,
+ void *, buf, u32, len)
+{
+ void *ptr;
+
+ ptr = bpf_xdp_pointer(xdp, offset, len);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ if (!ptr)
+ bpf_xdp_copy_buf(xdp, offset, buf, len, false);
+ else
+ memcpy(buf, ptr, len);
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_load_bytes_proto = {
+ .func = bpf_xdp_load_bytes,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg4_type = ARG_CONST_SIZE,
+};
+
+BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset,
+ void *, buf, u32, len)
+{
+ void *ptr;
+
+ ptr = bpf_xdp_pointer(xdp, offset, len);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ if (!ptr)
+ bpf_xdp_copy_buf(xdp, offset, buf, len, true);
+ else
+ memcpy(ptr, buf, len);
+
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_store_bytes_proto = {
+ .func = bpf_xdp_store_bytes,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_PTR_TO_UNINIT_MEM,
+ .arg4_type = ARG_CONST_SIZE,
+};
+
+static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
+{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+ skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1];
+ struct xdp_rxq_info *rxq = xdp->rxq;
+ unsigned int tailroom;
+
+ if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)
+ return -EOPNOTSUPP;
+
+ tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag);
+ if (unlikely(offset > tailroom))
+ return -EINVAL;
+
+ memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
+ skb_frag_size_add(frag, offset);
+ sinfo->xdp_frags_size += offset;
+
+ return 0;
+}
+
+static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
+{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+ int i, n_frags_free = 0, len_free = 0;
+
+ if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN))
+ return -EINVAL;
+
+ for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) {
+ skb_frag_t *frag = &sinfo->frags[i];
+ int shrink = min_t(int, offset, skb_frag_size(frag));
+
+ len_free += shrink;
+ offset -= shrink;
+
+ if (skb_frag_size(frag) == shrink) {
+ struct page *page = skb_frag_page(frag);
+
+ __xdp_return(page_address(page), &xdp->rxq->mem,
+ false, NULL);
+ n_frags_free++;
+ } else {
+ skb_frag_size_sub(frag, shrink);
+ break;
+ }
+ }
+ sinfo->nr_frags -= n_frags_free;
+ sinfo->xdp_frags_size -= len_free;
+
+ if (unlikely(!sinfo->nr_frags)) {
+ xdp_buff_clear_frags_flag(xdp);
+ xdp->data_end -= offset;
+ }
+
+ return 0;
+}
+
BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
{
void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
void *data_end = xdp->data_end + offset;
+ if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */
+ if (offset < 0)
+ return bpf_xdp_frags_shrink_tail(xdp, -offset);
+
+ return bpf_xdp_frags_increase_tail(xdp, offset);
+ }
+
/* Notice that xdp_data_hard_end have reserved some tailroom */
if (unlikely(data_end > data_hard_end))
return -EINVAL;
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
enum bpf_map_type map_type = ri->map_type;
+ /* XDP_REDIRECT is not fully supported yet for xdp frags since
+ * not all XDP capable drivers can map non-linear xdp_frame in
+ * ndo_xdp_xmit.
+ */
+ if (unlikely(xdp_buff_has_frags(xdp) &&
+ map_type != BPF_MAP_TYPE_CPUMAP))
+ return -EOPNOTSUPP;
+
if (map_type == BPF_MAP_TYPE_XSKMAP)
return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
};
#endif
-static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
+static unsigned long bpf_xdp_copy(void *dst, const void *ctx,
unsigned long off, unsigned long len)
{
- memcpy(dst_buff, src_buff + off, len);
+ struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+
+ bpf_xdp_copy_buf(xdp, off, dst, len, false);
return 0;
}
if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK)))
return -EINVAL;
- if (unlikely(!xdp ||
- xdp_size > (unsigned long)(xdp->data_end - xdp->data)))
+
+ if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp)))
return -EFAULT;
- return bpf_event_output(map, flags, meta, meta_size, xdp->data,
+ return bpf_event_output(map, flags, meta, meta_size, xdp,
xdp_size, bpf_xdp_copy);
}
case SO_REUSEPORT:
sk->sk_reuseport = valbool;
break;
+ case SO_TXREHASH:
+ if (val < -1 || val > 1) {
+ ret = -EINVAL;
+ break;
+ }
+ sk->sk_txrehash = (u8)val;
+ break;
default:
ret = -EINVAL;
}
case SO_REUSEPORT:
*((int *)optval) = sk->sk_reuseport;
break;
+ case SO_TXREHASH:
+ *((int *)optval) = sk->sk_txrehash;
+ break;
default:
goto err_clear;
}
return &bpf_xdp_redirect_map_proto;
case BPF_FUNC_xdp_adjust_tail:
return &bpf_xdp_adjust_tail_proto;
+ case BPF_FUNC_xdp_get_buff_len:
+ return &bpf_xdp_get_buff_len_proto;
+ case BPF_FUNC_xdp_load_bytes:
+ return &bpf_xdp_load_bytes_proto;
+ case BPF_FUNC_xdp_store_bytes:
+ return &bpf_xdp_store_bytes_proto;
case BPF_FUNC_fib_lookup:
return &bpf_xdp_fib_lookup_proto;
case BPF_FUNC_check_mtu:
.convert_ctx_access = tc_cls_act_convert_ctx_access,
.gen_prologue = tc_cls_act_prologue,
.gen_ld_abs = bpf_gen_ld_abs,
- .check_kfunc_call = bpf_prog_test_check_kfunc_call,
};
const struct bpf_prog_ops tc_cls_act_prog_ops = {
return peer;
}
+EXPORT_SYMBOL_GPL(get_net_ns_by_id);
/*
* setup_net runs the initializers for the network namespace object.
static int __net_init net_defaults_init_net(struct net *net)
{
net->core.sysctl_somaxconn = SOMAXCONN;
+ net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
+
return 0;
}
__page_pool_put_page(struct page_pool *pool, struct page *page,
unsigned int dma_sync_size, bool allow_direct)
{
- /* It is not the last user for the page frag case */
- if (pool->p.flags & PP_FLAG_PAGE_FRAG &&
- page_pool_atomic_sub_frag_count_return(page, 1))
- return NULL;
-
/* This allocator is optimized for the XDP mode that uses
* one-frame-per-page, but have fallbacks that act like the
* regular page allocator APIs.
return NULL;
}
-void page_pool_put_page(struct page_pool *pool, struct page *page,
- unsigned int dma_sync_size, bool allow_direct)
+void page_pool_put_defragged_page(struct page_pool *pool, struct page *page,
+ unsigned int dma_sync_size, bool allow_direct)
{
page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
if (page && !page_pool_recycle_in_ring(pool, page)) {
page_pool_return_page(pool, page);
}
}
-EXPORT_SYMBOL(page_pool_put_page);
+EXPORT_SYMBOL(page_pool_put_defragged_page);
/* Caller must not use data area after call, as this function overwrites it */
void page_pool_put_page_bulk(struct page_pool *pool, void **data,
for (i = 0; i < count; i++) {
struct page *page = virt_to_head_page(data[i]);
+ /* It is not the last user for the page frag case */
+ if (!page_pool_is_last_frag(pool, page))
+ continue;
+
page = __page_pool_put_page(pool, page, -1, false);
/* Approved for bulk recycling in ptr_ring cache */
if (page)
long drain_count = BIAS_MAX - pool->frag_users;
/* Some user is still using the page frag */
- if (likely(page_pool_atomic_sub_frag_count_return(page,
- drain_count)))
+ if (likely(page_pool_defrag_page(page, drain_count)))
return NULL;
if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) {
pool->frag_page = NULL;
- if (!page ||
- page_pool_atomic_sub_frag_count_return(page, drain_count))
+ if (!page || page_pool_defrag_page(page, drain_count))
return;
page_pool_return_page(pool, page);
pool->frag_users = 1;
*offset = 0;
pool->frag_offset = size;
- page_pool_set_frag_count(page, BIAS_MAX);
+ page_pool_fragment_page(page, BIAS_MAX);
return page;
}
break;
}
+ case SO_TXREHASH:
+ if (val < -1 || val > 1) {
+ ret = -EINVAL;
+ break;
+ }
+ /* Paired with READ_ONCE() in tcp_rtx_synack() */
+ WRITE_ONCE(sk->sk_txrehash, (u8)val);
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
v.val = sk->sk_reserved_mem;
break;
+ case SO_TXREHASH:
+ v.val = sk->sk_txrehash;
+ break;
+
default:
/* We implement the SO_SNDLOWAT etc to not be settable
* (1003.1g 7).
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
+ sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
}
switch (cmsg->cmsg_type) {
case SO_MARK:
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
+ !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
return -EINVAL;
sk->sk_pacing_rate = ~0UL;
WRITE_ONCE(sk->sk_pacing_shift, 10);
sk->sk_incoming_cpu = -1;
+ sk->sk_txrehash = SOCK_TXREHASH_DEFAULT;
sk_rx_queue_clear(sk);
/*
return NULL;
}
-static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
- struct bpf_prog *old, u32 which)
+static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog,
+ u32 which)
{
struct sk_psock_progs *progs = sock_map_progs(map);
- struct bpf_prog **pprog;
if (!progs)
return -EOPNOTSUPP;
switch (which) {
case BPF_SK_MSG_VERDICT:
- pprog = &progs->msg_parser;
+ *pprog = &progs->msg_parser;
break;
#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
case BPF_SK_SKB_STREAM_PARSER:
- pprog = &progs->stream_parser;
+ *pprog = &progs->stream_parser;
break;
#endif
case BPF_SK_SKB_STREAM_VERDICT:
if (progs->skb_verdict)
return -EBUSY;
- pprog = &progs->stream_verdict;
+ *pprog = &progs->stream_verdict;
break;
case BPF_SK_SKB_VERDICT:
if (progs->stream_verdict)
return -EBUSY;
- pprog = &progs->skb_verdict;
+ *pprog = &progs->skb_verdict;
break;
default:
return -EOPNOTSUPP;
}
+ return 0;
+}
+
+static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+ struct bpf_prog *old, u32 which)
+{
+ struct bpf_prog **pprog;
+ int ret;
+
+ ret = sock_map_prog_lookup(map, &pprog, which);
+ if (ret)
+ return ret;
+
if (old)
return psock_replace_prog(pprog, prog, old);
return 0;
}
+int sock_map_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+ u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd;
+ struct bpf_prog **pprog;
+ struct bpf_prog *prog;
+ struct bpf_map *map;
+ struct fd f;
+ u32 id = 0;
+ int ret;
+
+ if (attr->query.query_flags)
+ return -EINVAL;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ rcu_read_lock();
+
+ ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type);
+ if (ret)
+ goto end;
+
+ prog = *pprog;
+ prog_cnt = !prog ? 0 : 1;
+
+ if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+ goto end;
+
+ /* we do not hold the refcnt, the bpf prog may be released
+ * asynchronously and the id would be set to 0.
+ */
+ id = data_race(prog->aux->id);
+ if (id == 0)
+ prog_cnt = 0;
+
+end:
+ rcu_read_unlock();
+
+ if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) ||
+ (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) ||
+ copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+ ret = -EFAULT;
+
+ fdput(f);
+ return ret;
+}
+
static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link)
{
switch (link->map->map_type) {
.extra1 = SYSCTL_ZERO,
.proc_handler = proc_dointvec_minmax
},
+ {
+ .procname = "txrehash",
+ .data = &init_net.core.sysctl_txrehash,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ .proc_handler = proc_dou8vec_minmax,
+ },
{ }
};
static __net_init int sysctl_core_net_init(struct net *net)
{
- struct ctl_table *tbl;
+ struct ctl_table *tbl, *tmp;
tbl = netns_core_table;
if (!net_eq(net, &init_net)) {
if (tbl == NULL)
goto err_dup;
- tbl[0].data = &net->core.sysctl_somaxconn;
+ for (tmp = tbl; tmp->procname; tmp++)
+ tmp->data += (char *)net - (char *)&init_net;
/* Don't export any sysctls to unprivileged users */
if (net->user_ns != &init_user_ns) {
}
/* Returns 0 on success, negative on failure */
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
- struct net_device *dev, u32 queue_index, unsigned int napi_id)
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+ struct net_device *dev, u32 queue_index,
+ unsigned int napi_id, u32 frag_size)
{
if (!dev) {
WARN(1, "Missing net_device from driver");
xdp_rxq->dev = dev;
xdp_rxq->queue_index = queue_index;
xdp_rxq->napi_id = napi_id;
+ xdp_rxq->frag_size = frag_size;
xdp_rxq->reg_state = REG_STATE_REGISTERED;
return 0;
}
-EXPORT_SYMBOL_GPL(xdp_rxq_info_reg);
+EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg);
void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq)
{
* is used for those calls sites. Thus, allowing for faster recycling
* of xdp_frames/pages in those cases.
*/
-static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
- struct xdp_buff *xdp)
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+ struct xdp_buff *xdp)
{
struct xdp_mem_allocator *xa;
struct page *page;
void xdp_return_frame(struct xdp_frame *xdpf)
{
+ struct skb_shared_info *sinfo;
+ int i;
+
+ if (likely(!xdp_frame_has_frags(xdpf)))
+ goto out;
+
+ sinfo = xdp_get_shared_info_from_frame(xdpf);
+ for (i = 0; i < sinfo->nr_frags; i++) {
+ struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+ __xdp_return(page_address(page), &xdpf->mem, false, NULL);
+ }
+out:
__xdp_return(xdpf->data, &xdpf->mem, false, NULL);
}
EXPORT_SYMBOL_GPL(xdp_return_frame);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
{
+ struct skb_shared_info *sinfo;
+ int i;
+
+ if (likely(!xdp_frame_has_frags(xdpf)))
+ goto out;
+
+ sinfo = xdp_get_shared_info_from_frame(xdpf);
+ for (i = 0; i < sinfo->nr_frags; i++) {
+ struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+ __xdp_return(page_address(page), &xdpf->mem, true, NULL);
+ }
+out:
__xdp_return(xdpf->data, &xdpf->mem, true, NULL);
}
EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
struct xdp_mem_allocator *xa;
if (mem->type != MEM_TYPE_PAGE_POOL) {
- __xdp_return(xdpf->data, &xdpf->mem, false, NULL);
+ xdp_return_frame(xdpf);
return;
}
bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
}
+ if (unlikely(xdp_frame_has_frags(xdpf))) {
+ struct skb_shared_info *sinfo;
+ int i;
+
+ sinfo = xdp_get_shared_info_from_frame(xdpf);
+ for (i = 0; i < sinfo->nr_frags; i++) {
+ skb_frag_t *frag = &sinfo->frags[i];
+
+ bq->q[bq->count++] = skb_frag_address(frag);
+ if (bq->count == XDP_BULK_QUEUE_SIZE)
+ xdp_flush_frame_bulk(bq);
+ }
+ }
bq->q[bq->count++] = xdpf->data;
}
EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
void xdp_return_buff(struct xdp_buff *xdp)
{
+ struct skb_shared_info *sinfo;
+ int i;
+
+ if (likely(!xdp_buff_has_frags(xdp)))
+ goto out;
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ for (i = 0; i < sinfo->nr_frags; i++) {
+ struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+ __xdp_return(page_address(page), &xdp->rxq->mem, true, xdp);
+ }
+out:
__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp);
}
struct sk_buff *skb,
struct net_device *dev)
{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
unsigned int headroom, frame_size;
void *hard_start;
+ u8 nr_frags;
+
+ /* xdp frags frame */
+ if (unlikely(xdp_frame_has_frags(xdpf)))
+ nr_frags = sinfo->nr_frags;
/* Part of headroom was reserved to xdpf */
headroom = sizeof(*xdpf) + xdpf->headroom;
if (xdpf->metasize)
skb_metadata_set(skb, xdpf->metasize);
+ if (unlikely(xdp_frame_has_frags(xdpf)))
+ xdp_update_skb_shared_info(skb, nr_frags,
+ sinfo->xdp_frags_size,
+ nr_frags * xdpf->frame_sz,
+ xdp_frame_is_frag_pfmemalloc(xdpf));
+
/* Essential SKB info: protocol and skb->dev */
skb->protocol = eth_type_trans(skb, dev);
return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16);
}
-static inline u64 max48(const u64 seq1, const u64 seq2)
-{
- return after48(seq1, seq2) ? seq1 : seq2;
-}
-
/**
* dccp_loss_count - Approximate the number of lost data packets in a burst loss
* @s1: last known sequence number before the loss ('hole')
inet_ctl_sock_destroy(pn->v4_ctl_sk);
}
-static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list)
-{
- inet_twsk_purge(&dccp_hashinfo, AF_INET);
-}
-
static struct pernet_operations dccp_v4_ops = {
.init = dccp_v4_init_net,
.exit = dccp_v4_exit_net,
- .exit_batch = dccp_v4_exit_batch,
.id = &dccp_v4_pernet_id,
.size = sizeof(struct dccp_v4_pernet),
};
inet_ctl_sock_destroy(pn->v6_ctl_sk);
}
-static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list)
-{
- inet_twsk_purge(&dccp_hashinfo, AF_INET6);
-}
-
static struct pernet_operations dccp_v6_ops = {
.init = dccp_v6_init_net,
.exit = dccp_v6_exit_net,
- .exit_batch = dccp_v6_exit_batch,
.id = &dccp_v6_pernet_id,
.size = sizeof(struct dccp_v6_pernet),
};
#include "feat.h"
struct inet_timewait_death_row dccp_death_row = {
+ .tw_refcount = REFCOUNT_INIT(1),
.sysctl_max_tw_buckets = NR_FILE * 2,
.hashinfo = &dccp_hashinfo,
};
#include <linux/of.h>
#include <linux/of_net.h>
#include <net/devlink.h>
+#include <net/sch_generic.h>
#include "dsa_priv.h"
list_for_each_entry(dp, &dst->ports, list) {
if (dsa_port_is_cpu(dp)) {
- err = dsa_master_setup(dp->master, dp);
+ struct net_device *master = dp->master;
+ bool admin_up = (master->flags & IFF_UP) &&
+ !qdisc_tx_is_noop(master);
+
+ err = dsa_master_setup(master, dp);
if (err)
return err;
+
+ /* Replay master state event */
+ dsa_tree_master_admin_state_change(dst, master, admin_up);
+ dsa_tree_master_oper_state_change(dst, master,
+ netif_oper_up(master));
}
}
rtnl_lock();
- list_for_each_entry(dp, &dst->ports, list)
- if (dsa_port_is_cpu(dp))
- dsa_master_teardown(dp->master);
+ list_for_each_entry(dp, &dst->ports, list) {
+ if (dsa_port_is_cpu(dp)) {
+ struct net_device *master = dp->master;
+
+ /* Synthesizing an "admin down" state is sufficient for
+ * the switches to get a notification if the master is
+ * currently up and running.
+ */
+ dsa_tree_master_admin_state_change(dst, master, false);
+
+ dsa_master_teardown(master);
+ }
+ }
rtnl_unlock();
}
return err;
}
+static void dsa_tree_master_state_change(struct dsa_switch_tree *dst,
+ struct net_device *master)
+{
+ struct dsa_notifier_master_state_info info;
+ struct dsa_port *cpu_dp = master->dsa_ptr;
+
+ info.master = master;
+ info.operational = dsa_port_master_is_operational(cpu_dp);
+
+ dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info);
+}
+
+void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst,
+ struct net_device *master,
+ bool up)
+{
+ struct dsa_port *cpu_dp = master->dsa_ptr;
+ bool notify = false;
+
+ if ((dsa_port_master_is_operational(cpu_dp)) !=
+ (up && cpu_dp->master_oper_up))
+ notify = true;
+
+ cpu_dp->master_admin_up = up;
+
+ if (notify)
+ dsa_tree_master_state_change(dst, master);
+}
+
+void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst,
+ struct net_device *master,
+ bool up)
+{
+ struct dsa_port *cpu_dp = master->dsa_ptr;
+ bool notify = false;
+
+ if ((dsa_port_master_is_operational(cpu_dp)) !=
+ (cpu_dp->master_admin_up && up))
+ notify = true;
+
+ cpu_dp->master_oper_up = up;
+
+ if (notify)
+ dsa_tree_master_state_change(dst, master);
+}
+
static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index)
{
struct dsa_switch_tree *dst = ds->dst;
DSA_NOTIFIER_TAG_PROTO_DISCONNECT,
DSA_NOTIFIER_TAG_8021Q_VLAN_ADD,
DSA_NOTIFIER_TAG_8021Q_VLAN_DEL,
+ DSA_NOTIFIER_MASTER_STATE_CHANGE,
};
/* DSA_NOTIFIER_AGEING_TIME */
u16 vid;
};
+/* DSA_NOTIFIER_MASTER_STATE_CHANGE */
+struct dsa_notifier_master_state_info {
+ const struct net_device *master;
+ bool operational;
+};
+
struct dsa_switchdev_event_work {
struct dsa_switch *ds;
int port;
struct net_device *master,
const struct dsa_device_ops *tag_ops,
const struct dsa_device_ops *old_tag_ops);
+void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst,
+ struct net_device *master,
+ bool up);
+void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst,
+ struct net_device *master,
+ bool up);
unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max);
void dsa_bridge_num_put(const struct net_device *bridge_dev,
unsigned int bridge_num);
err = dsa_port_lag_change(dp, info->lower_state_info);
return notifier_from_errno(err);
}
+ case NETDEV_CHANGE:
+ case NETDEV_UP: {
+ /* Track state of master port.
+ * DSA driver may require the master port (and indirectly
+ * the tagger) to be available for some special operation.
+ */
+ if (netdev_uses_dsa(dev)) {
+ struct dsa_port *cpu_dp = dev->dsa_ptr;
+ struct dsa_switch_tree *dst = cpu_dp->ds->dst;
+
+ /* Track when the master port is UP */
+ dsa_tree_master_oper_state_change(dst, dev,
+ netif_oper_up(dev));
+
+ /* Track when the master port is ready and can accept
+ * packet.
+ * NETDEV_UP event is not enough to flag a port as ready.
+ * We also have to wait for linkwatch_do_dev to dev_activate
+ * and emit a NETDEV_CHANGE event.
+ * We check if a master port is ready by checking if the dev
+ * have a qdisc assigned and is not noop.
+ */
+ dsa_tree_master_admin_state_change(dst, dev,
+ !qdisc_tx_is_noop(dev));
+
+ return NOTIFY_OK;
+ }
+
+ return NOTIFY_DONE;
+ }
case NETDEV_GOING_DOWN: {
struct dsa_port *dp, *cpu_dp;
struct dsa_switch_tree *dst;
cpu_dp = dev->dsa_ptr;
dst = cpu_dp->ds->dst;
+ dsa_tree_master_admin_state_change(dst, dev, false);
+
list_for_each_entry(dp, &dst->ports, list) {
if (!dsa_port_is_user(dp))
continue;
return dsa_tag_8021q_bridge_join(ds, info);
}
-static int dsa_switch_bridge_leave(struct dsa_switch *ds,
- struct dsa_notifier_bridge_info *info)
+static int dsa_switch_sync_vlan_filtering(struct dsa_switch *ds,
+ struct dsa_notifier_bridge_info *info)
{
- struct dsa_switch_tree *dst = ds->dst;
struct netlink_ext_ack extack = {0};
bool change_vlan_filtering = false;
bool vlan_filtering;
struct dsa_port *dp;
int err;
- if (dst->index == info->tree_index && ds->index == info->sw_index &&
- ds->ops->port_bridge_leave)
- ds->ops->port_bridge_leave(ds, info->port, info->bridge);
-
- if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
- ds->ops->crosschip_bridge_leave)
- ds->ops->crosschip_bridge_leave(ds, info->tree_index,
- info->sw_index, info->port,
- info->bridge);
-
if (ds->needs_standalone_vlan_filtering &&
!br_vlan_enabled(info->bridge.dev)) {
change_vlan_filtering = true;
return err;
}
+ return 0;
+}
+
+static int dsa_switch_bridge_leave(struct dsa_switch *ds,
+ struct dsa_notifier_bridge_info *info)
+{
+ struct dsa_switch_tree *dst = ds->dst;
+ int err;
+
+ if (dst->index == info->tree_index && ds->index == info->sw_index &&
+ ds->ops->port_bridge_leave)
+ ds->ops->port_bridge_leave(ds, info->port, info->bridge);
+
+ if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
+ ds->ops->crosschip_bridge_leave)
+ ds->ops->crosschip_bridge_leave(ds, info->tree_index,
+ info->sw_index, info->port,
+ info->bridge);
+
+ if (ds->dst->index == info->tree_index && ds->index == info->sw_index) {
+ err = dsa_switch_sync_vlan_filtering(ds, info);
+ if (err)
+ return err;
+ }
+
return dsa_tag_8021q_bridge_leave(ds, info);
}
return 0;
}
+static int
+dsa_switch_master_state_change(struct dsa_switch *ds,
+ struct dsa_notifier_master_state_info *info)
+{
+ if (!ds->ops->master_state_change)
+ return 0;
+
+ ds->ops->master_state_change(ds, info->master, info->operational);
+
+ return 0;
+}
+
static int dsa_switch_event(struct notifier_block *nb,
unsigned long event, void *info)
{
case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL:
err = dsa_switch_tag_8021q_vlan_del(ds, info);
break;
+ case DSA_NOTIFIER_MASTER_STATE_CHANGE:
+ err = dsa_switch_master_state_change(ds, info);
+ break;
default:
err = -EOPNOTSUPP;
break;
*/
#include <linux/etherdevice.h>
+#include <linux/bitfield.h>
+#include <net/dsa.h>
+#include <linux/dsa/tag_qca.h>
#include "dsa_priv.h"
-#define QCA_HDR_LEN 2
-#define QCA_HDR_VERSION 0x2
-
-#define QCA_HDR_RECV_VERSION_MASK GENMASK(15, 14)
-#define QCA_HDR_RECV_VERSION_S 14
-#define QCA_HDR_RECV_PRIORITY_MASK GENMASK(13, 11)
-#define QCA_HDR_RECV_PRIORITY_S 11
-#define QCA_HDR_RECV_TYPE_MASK GENMASK(10, 6)
-#define QCA_HDR_RECV_TYPE_S 6
-#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3)
-#define QCA_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0)
-
-#define QCA_HDR_XMIT_VERSION_MASK GENMASK(15, 14)
-#define QCA_HDR_XMIT_VERSION_S 14
-#define QCA_HDR_XMIT_PRIORITY_MASK GENMASK(13, 11)
-#define QCA_HDR_XMIT_PRIORITY_S 11
-#define QCA_HDR_XMIT_CONTROL_MASK GENMASK(10, 8)
-#define QCA_HDR_XMIT_CONTROL_S 8
-#define QCA_HDR_XMIT_FROM_CPU BIT(7)
-#define QCA_HDR_XMIT_DP_BIT_MASK GENMASK(6, 0)
-
static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
phdr = dsa_etype_header_pos_tx(skb);
/* Set the version field, and set destination port information */
- hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S |
- QCA_HDR_XMIT_FROM_CPU | BIT(dp->index);
+ hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION);
+ hdr |= QCA_HDR_XMIT_FROM_CPU;
+ hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(dp->index));
*phdr = htons(hdr);
static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev)
{
- u8 ver;
- u16 hdr;
- int port;
+ struct qca_tagger_data *tagger_data;
+ struct dsa_port *dp = dev->dsa_ptr;
+ struct dsa_switch *ds = dp->ds;
+ u8 ver, pk_type;
__be16 *phdr;
+ int port;
+ u16 hdr;
+
+ BUILD_BUG_ON(sizeof(struct qca_mgmt_ethhdr) != QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN);
+
+ tagger_data = ds->tagger_data;
if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN)))
return NULL;
hdr = ntohs(*phdr);
/* Make sure the version is correct */
- ver = (hdr & QCA_HDR_RECV_VERSION_MASK) >> QCA_HDR_RECV_VERSION_S;
+ ver = FIELD_GET(QCA_HDR_RECV_VERSION, hdr);
if (unlikely(ver != QCA_HDR_VERSION))
return NULL;
+ /* Get pk type */
+ pk_type = FIELD_GET(QCA_HDR_RECV_TYPE, hdr);
+
+ /* Ethernet mgmt read/write packet */
+ if (pk_type == QCA_HDR_RECV_TYPE_RW_REG_ACK) {
+ if (likely(tagger_data->rw_reg_ack_handler))
+ tagger_data->rw_reg_ack_handler(ds, skb);
+ return NULL;
+ }
+
+ /* Ethernet MIB counter packet */
+ if (pk_type == QCA_HDR_RECV_TYPE_MIB) {
+ if (likely(tagger_data->mib_autocast_handler))
+ tagger_data->mib_autocast_handler(ds, skb);
+ return NULL;
+ }
+
/* Remove QCA tag and recalculate checksum */
skb_pull_rcsum(skb, QCA_HDR_LEN);
dsa_strip_etype_header(skb, QCA_HDR_LEN);
/* Get source port information */
- port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK);
+ port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr);
skb->dev = dsa_master_find_slave(dev, 0, port);
if (!skb->dev)
return skb;
}
+static int qca_tag_connect(struct dsa_switch *ds)
+{
+ struct qca_tagger_data *tagger_data;
+
+ tagger_data = kzalloc(sizeof(*tagger_data), GFP_KERNEL);
+ if (!tagger_data)
+ return -ENOMEM;
+
+ ds->tagger_data = tagger_data;
+
+ return 0;
+}
+
+static void qca_tag_disconnect(struct dsa_switch *ds)
+{
+ kfree(ds->tagger_data);
+ ds->tagger_data = NULL;
+}
+
static const struct dsa_device_ops qca_netdev_ops = {
.name = "qca",
.proto = DSA_TAG_PROTO_QCA,
+ .connect = qca_tag_connect,
+ .disconnect = qca_tag_disconnect,
.xmit = qca_tag_xmit,
.rcv = qca_tag_rcv,
.needed_headroom = QCA_HDR_LEN,
+ .promisc_on_master = true,
};
MODULE_LICENSE("GPL");
nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */
nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */
nla_total_size(sizeof(u32)) + /* _RINGS_TX */
- nla_total_size(sizeof(u32)); /* _RINGS_RX_BUF_LEN */
+ nla_total_size(sizeof(u32)) + /* _RINGS_RX_BUF_LEN */
+ nla_total_size(sizeof(u8)); /* _RINGS_TCP_DATA_SPLIT */
}
static int rings_fill_reply(struct sk_buff *skb,
const struct ethnl_reply_data *reply_base)
{
const struct rings_reply_data *data = RINGS_REPDATA(reply_base);
- const struct kernel_ethtool_ringparam *kernel_ringparam = &data->kernel_ringparam;
+ const struct kernel_ethtool_ringparam *kr = &data->kernel_ringparam;
const struct ethtool_ringparam *ringparam = &data->ringparam;
+ WARN_ON(kr->tcp_data_split > ETHTOOL_TCP_DATA_SPLIT_ENABLED);
+
if ((ringparam->rx_max_pending &&
(nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MAX,
ringparam->rx_max_pending) ||
ringparam->tx_max_pending) ||
nla_put_u32(skb, ETHTOOL_A_RINGS_TX,
ringparam->tx_pending))) ||
- (kernel_ringparam->rx_buf_len &&
- (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN,
- kernel_ringparam->rx_buf_len))))
+ (kr->rx_buf_len &&
+ (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) ||
+ (kr->tcp_data_split &&
+ (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT,
+ kr->tcp_data_split))))
return -EMSGSIZE;
return 0;
return ntohs(rct->sequence_nr);
}
-static inline u16 get_prp_lan_id(struct prp_rct *rct)
-{
- return ntohs(rct->lan_id_and_LSDU_size) >> 12;
-}
-
/* assume there is a valid rct */
static inline bool prp_check_lsdu_size(struct sk_buff *skb,
struct prp_rct *rct,
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 Facebook */
+#include <linux/init.h>
#include <linux/types.h>
#include <linux/bpf_verifier.h>
#include <linux/bpf.h>
}
}
-BTF_SET_START(bpf_tcp_ca_kfunc_ids)
+BTF_SET_START(bpf_tcp_ca_check_kfunc_ids)
BTF_ID(func, tcp_reno_ssthresh)
BTF_ID(func, tcp_reno_cong_avoid)
BTF_ID(func, tcp_reno_undo_cwnd)
BTF_ID(func, tcp_slow_start)
BTF_ID(func, tcp_cong_avoid_ai)
-BTF_SET_END(bpf_tcp_ca_kfunc_ids)
+BTF_SET_END(bpf_tcp_ca_check_kfunc_ids)
-static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id, struct module *owner)
-{
- if (btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id))
- return true;
- return bpf_check_mod_kfunc_call(&bpf_tcp_ca_kfunc_list, kfunc_btf_id, owner);
-}
+static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &bpf_tcp_ca_check_kfunc_ids,
+};
static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = {
.get_func_proto = bpf_tcp_ca_get_func_proto,
.is_valid_access = bpf_tcp_ca_is_valid_access,
.btf_struct_access = bpf_tcp_ca_btf_struct_access,
- .check_kfunc_call = bpf_tcp_ca_check_kfunc_call,
};
static int bpf_tcp_ca_init_member(const struct btf_type *t,
.init = bpf_tcp_ca_init,
.name = "tcp_congestion_ops",
};
+
+static int __init bpf_tcp_ca_kfunc_init(void)
+{
+ return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set);
+}
+late_initcall(bpf_tcp_ca_kfunc_init);
return &fib_info_laddrhash[slot];
}
-static struct hlist_head *fib_info_hash_alloc(int bytes)
-{
- if (bytes <= PAGE_SIZE)
- return kzalloc(bytes, GFP_KERNEL);
- else
- return (struct hlist_head *)
- __get_free_pages(GFP_KERNEL | __GFP_ZERO,
- get_order(bytes));
-}
-
-static void fib_info_hash_free(struct hlist_head *hash, int bytes)
-{
- if (!hash)
- return;
-
- if (bytes <= PAGE_SIZE)
- kfree(hash);
- else
- free_pages((unsigned long) hash, get_order(bytes));
-}
-
static void fib_info_hash_move(struct hlist_head *new_info_hash,
struct hlist_head *new_laddrhash,
unsigned int new_size)
{
struct hlist_head *old_info_hash, *old_laddrhash;
unsigned int old_size = fib_info_hash_size;
- unsigned int i, bytes;
+ unsigned int i;
spin_lock_bh(&fib_info_lock);
old_info_hash = fib_info_hash;
spin_unlock_bh(&fib_info_lock);
- bytes = old_size * sizeof(struct hlist_head *);
- fib_info_hash_free(old_info_hash, bytes);
- fib_info_hash_free(old_laddrhash, bytes);
+ kvfree(old_info_hash);
+ kvfree(old_laddrhash);
}
__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
unsigned int new_size = fib_info_hash_size << 1;
struct hlist_head *new_info_hash;
struct hlist_head *new_laddrhash;
- unsigned int bytes;
+ size_t bytes;
if (!new_size)
new_size = 16;
- bytes = new_size * sizeof(struct hlist_head *);
- new_info_hash = fib_info_hash_alloc(bytes);
- new_laddrhash = fib_info_hash_alloc(bytes);
+ bytes = (size_t)new_size * sizeof(struct hlist_head *);
+ new_info_hash = kvzalloc(bytes, GFP_KERNEL);
+ new_laddrhash = kvzalloc(bytes, GFP_KERNEL);
if (!new_info_hash || !new_laddrhash) {
- fib_info_hash_free(new_info_hash, bytes);
- fib_info_hash_free(new_laddrhash, bytes);
- } else
+ kvfree(new_info_hash);
+ kvfree(new_laddrhash);
+ } else {
fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
-
+ }
if (!fib_info_hash_size)
goto failure;
}
static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
-/*
- * The ICMP socket(s). This is the most convenient way to flow control
- * our ICMP output as well as maintain a clean interface throughout
- * all layers. All Socketless IP sends will soon be gone.
- *
- * On SMP we have one ICMP socket per-cpu.
- */
-static struct sock *icmp_sk(struct net *net)
-{
- return this_cpu_read(*net->ipv4.icmp_sk);
-}
+static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk);
/* Called with BH disabled */
static inline struct sock *icmp_xmit_lock(struct net *net)
{
struct sock *sk;
- sk = icmp_sk(net);
+ sk = this_cpu_read(ipv4_icmp_sk);
if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path signals a
*/
return NULL;
}
+ sock_net_set(sk, net);
return sk;
}
static inline void icmp_xmit_unlock(struct sock *sk)
{
+ sock_net_set(sk, &init_net);
spin_unlock(&sk->sk_lock.slock);
}
return 0;
}
-static void icmp_push_reply(struct icmp_bxm *icmp_param,
+static void icmp_push_reply(struct sock *sk,
+ struct icmp_bxm *icmp_param,
struct flowi4 *fl4,
struct ipcm_cookie *ipc, struct rtable **rt)
{
- struct sock *sk;
struct sk_buff *skb;
- sk = icmp_sk(dev_net((*rt)->dst.dev));
if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param,
icmp_param->data_len+icmp_param->head_len,
icmp_param->head_len,
if (IS_ERR(rt))
goto out_unlock;
if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
- icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
+ icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt);
ip_rt_put(rt);
out_unlock:
icmp_xmit_unlock(sk);
if (!fl4.saddr)
fl4.saddr = htonl(INADDR_DUMMY);
- icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
+ icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
out_unlock:
},
};
-static void __net_exit icmp_sk_exit(struct net *net)
-{
- int i;
-
- for_each_possible_cpu(i)
- inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i));
- free_percpu(net->ipv4.icmp_sk);
- net->ipv4.icmp_sk = NULL;
-}
-
static int __net_init icmp_sk_init(struct net *net)
{
- int i, err;
-
- net->ipv4.icmp_sk = alloc_percpu(struct sock *);
- if (!net->ipv4.icmp_sk)
- return -ENOMEM;
-
- for_each_possible_cpu(i) {
- struct sock *sk;
-
- err = inet_ctl_sock_create(&sk, PF_INET,
- SOCK_RAW, IPPROTO_ICMP, net);
- if (err < 0)
- goto fail;
-
- *per_cpu_ptr(net->ipv4.icmp_sk, i) = sk;
-
- /* Enough space for 2 64K ICMP packets, including
- * sk_buff/skb_shared_info struct overhead.
- */
- sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
-
- /*
- * Speedup sock_wfree()
- */
- sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
- inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
- }
-
/* Control parameters for ECHO replies. */
net->ipv4.sysctl_icmp_echo_ignore_all = 0;
net->ipv4.sysctl_icmp_echo_enable_probe = 0;
net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;
return 0;
-
-fail:
- icmp_sk_exit(net);
- return err;
}
static struct pernet_operations __net_initdata icmp_sk_ops = {
.init = icmp_sk_init,
- .exit = icmp_sk_exit,
};
int __init icmp_init(void)
{
+ int err, i;
+
+ for_each_possible_cpu(i) {
+ struct sock *sk;
+
+ err = inet_ctl_sock_create(&sk, PF_INET,
+ SOCK_RAW, IPPROTO_ICMP, &init_net);
+ if (err < 0)
+ return err;
+
+ per_cpu(ipv4_icmp_sk, i) = sk;
+
+ /* Enough space for 2 64K ICMP packets, including
+ * sk_buff/skb_shared_info struct overhead.
+ */
+ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
+
+ /*
+ * Speedup sock_wfree()
+ */
+ sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
+ }
return register_pernet_subsys(&icmp_sk_ops);
}
(!resend ||
!inet_rtx_syn_ack(sk_listener, req) ||
inet_rsk(req)->acked)) {
- unsigned long timeo;
-
if (req->num_timeout++ == 0)
atomic_dec(&queue->young);
- timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
- mod_timer(&req->rsk_timer, jiffies + timeo);
+ mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX));
if (!nreq)
return;
sk->sk_ack_backlog = 0;
inet_csk_delack_init(sk);
+ if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT)
+ sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
+
/* There is race window here: we announce ourselves listening,
* but this transition is still not validated by get_port().
* It is OK, because this socket enters to hash table only
spin_unlock(lock);
/* Disassociate with bind bucket. */
- bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
- hashinfo->bhash_size)];
+ bhead = &hashinfo->bhash[tw->tw_bslot];
spin_lock(&bhead->lock);
inet_twsk_bind_unhash(tw, hashinfo);
spin_unlock(&bhead->lock);
- atomic_dec(&tw->tw_dr->tw_count);
+ if (refcount_dec_and_test(&tw->tw_dr->tw_refcount))
+ kfree(tw->tw_dr);
+
inet_twsk_put(tw);
}
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
- bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
- hashinfo->bhash_size)];
+ /* Cache inet_bhashfn(), because 'struct net' might be no longer
+ * available later in inet_twsk_kill().
+ */
+ tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num,
+ hashinfo->bhash_size);
+ bhead = &hashinfo->bhash[tw->tw_bslot];
spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
WARN_ON(!icsk->icsk_bind_hash);
{
struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer);
- if (tw->tw_kill)
- __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED);
- else
- __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITED);
inet_twsk_kill(tw);
}
{
struct inet_timewait_sock *tw;
- if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets)
+ if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets)
return NULL;
tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
* of PAWS.
*/
- tw->tw_kill = timeo <= 4*HZ;
if (!rearm) {
+ bool kill = timeo <= 4*HZ;
+
+ __NET_INC_STATS(twsk_net(tw), kill ? LINUX_MIB_TIMEWAITKILLED :
+ LINUX_MIB_TIMEWAITED);
BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo));
- atomic_inc(&tw->tw_dr->tw_count);
+ refcount_inc(&tw->tw_dr->tw_refcount);
} else {
mod_timer_pending(&tw->tw_timer, jiffies + timeo);
}
}
EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
-
-void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
-{
- struct inet_timewait_sock *tw;
- struct sock *sk;
- struct hlist_nulls_node *node;
- unsigned int slot;
-
- for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
- struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
-restart_rcu:
- cond_resched();
- rcu_read_lock();
-restart:
- sk_nulls_for_each_rcu(sk, node, &head->chain) {
- if (sk->sk_state != TCP_TIME_WAIT)
- continue;
- tw = inet_twsk(sk);
- if ((tw->tw_family != family) ||
- refcount_read(&twsk_net(tw)->ns.count))
- continue;
-
- if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
- continue;
-
- if (unlikely((tw->tw_family != family) ||
- refcount_read(&twsk_net(tw)->ns.count))) {
- inet_twsk_put(tw);
- goto restart;
- }
-
- rcu_read_unlock();
- local_bh_disable();
- inet_twsk_deschedule_put(tw);
- local_bh_enable();
- goto restart_rcu;
- }
- /* If the nulls value we got at the end of this lookup is
- * not the expected one, we must restart lookup.
- * We probably met an item that was moved to another chain.
- */
- if (get_nulls_value(node) != slot)
- goto restart;
- rcu_read_unlock();
- }
-}
-EXPORT_SYMBOL_GPL(inet_twsk_purge);
*/
void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
- __be32 daddr, struct rtable *rt, int is_frag)
+ __be32 daddr, struct rtable *rt)
{
unsigned char *iph = skb_network_header(skb);
if (opt->srr)
memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4);
- if (!is_frag) {
- if (opt->rr_needaddr)
- ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt);
- if (opt->ts_needaddr)
- ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt);
- if (opt->ts_needtime) {
- __be32 midtime;
+ if (opt->rr_needaddr)
+ ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt);
+ if (opt->ts_needaddr)
+ ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt);
+ if (opt->ts_needtime) {
+ __be32 midtime;
- midtime = inet_current_timestamp();
- memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4);
- }
- return;
- }
- if (opt->rr) {
- memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]);
- opt->rr = 0;
- opt->rr_needaddr = 0;
- }
- if (opt->ts) {
- memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]);
- opt->ts = 0;
- opt->ts_needaddr = opt->ts_needtime = 0;
+ midtime = inet_current_timestamp();
+ memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4);
}
}
if (opt && opt->opt.optlen) {
iph->ihl += opt->opt.optlen>>2;
- ip_options_build(skb, &opt->opt, daddr, rt, 0);
+ ip_options_build(skb, &opt->opt, daddr, rt);
}
skb->priority = sk->sk_priority;
if (inet_opt && inet_opt->opt.optlen) {
iph->ihl += inet_opt->opt.optlen >> 2;
- ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0);
+ ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt);
}
ip_select_ident_segs(net, skb, sk,
if (opt) {
iph->ihl += opt->optlen >> 2;
- ip_options_build(skb, opt, cork->addr, rt, 0);
+ ip_options_build(skb, opt, cork->addr, rt);
}
skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
socket_seq_show(seq);
seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
sock_prot_inuse_get(net, &tcp_prot), orphans,
- atomic_read(&net->ipv4.tcp_death_row.tw_count), sockets,
- proto_memory_allocated(&tcp_prot));
+ refcount_read(&net->ipv4.tcp_death_row->tw_refcount) - 1,
+ sockets, proto_memory_allocated(&tcp_prot));
seq_printf(seq, "UDP: inuse %d mem %ld\n",
sock_prot_inuse_get(net, &udp_prot),
proto_memory_allocated(&udp_prot));
#define DEFAULT_MIN_PMTU (512 + 20 + 20)
#define DEFAULT_MTU_EXPIRES (10 * 60 * HZ)
-
+#define DEFAULT_MIN_ADVMSS 256
static int ip_rt_max_size;
static int ip_rt_redirect_number __read_mostly = 9;
static int ip_rt_redirect_load __read_mostly = HZ / 50;
static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
-static int ip_rt_min_advmss __read_mostly = 256;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
* if one generator is seldom used. This makes hard for an attacker
* to infer how many packets were sent between two points in time.
*/
-u32 ip_idents_reserve(u32 hash, int segs)
+static u32 ip_idents_reserve(u32 hash, int segs)
{
u32 bucket, old, now = (u32)jiffies;
atomic_t *p_id;
*/
return atomic_add_return(segs + delta, p_id) - segs;
}
-EXPORT_SYMBOL(ip_idents_reserve);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
{
static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
{
+ struct net *net = dev_net(dst->dev);
unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
- ip_rt_min_advmss);
+ net->ipv4.ip_rt_min_advmss);
return min(advmss, IPV4_MAX_PMTU - header_size);
}
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "min_adv_mss",
- .data = &ip_rt_min_advmss,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
{ }
};
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "min_adv_mss",
+ .data = &init_net.ipv4.ip_rt_min_advmss,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{ },
};
/* Set default value for namespaceified sysctls */
net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU;
net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES;
+ net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS;
return 0;
}
};
static struct ctl_table ipv4_net_table[] = {
+ /* tcp_max_tw_buckets must be first in this table. */
+ {
+ .procname = "tcp_max_tw_buckets",
+/* .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, */
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{
.procname = "icmp_echo_ignore_all",
.data = &init_net.ipv4.sysctl_icmp_echo_ignore_all,
.extra2 = &two,
},
{
- .procname = "tcp_max_tw_buckets",
- .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_max_syn_backlog",
.data = &init_net.ipv4.sysctl_max_syn_backlog,
.maxlen = sizeof(int),
if (!table)
goto err_alloc;
- for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) {
+ /* skip first entry (sysctl_max_tw_buckets) */
+ for (i = 1; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) {
if (table[i].data) {
/* Update the variables to point into
* the current struct net
}
}
+ table[0].data = &net->ipv4.tcp_death_row->sysctl_max_tw_buckets;
+
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
if (!net->ipv4.ipv4_hdr)
goto err_reg;
return mss_now;
/* Note : tcp_tso_autosize() will eventually split this later */
- new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER;
- new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
+ new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size);
/* We try hard to avoid divides here */
size_goal = tp->gso_segs * mss_now;
.set_state = bbr_set_state,
};
-BTF_SET_START(tcp_bbr_kfunc_ids)
+BTF_SET_START(tcp_bbr_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
BTF_ID(func, bbr_init)
BTF_ID(func, bbr_set_state)
#endif
#endif
-BTF_SET_END(tcp_bbr_kfunc_ids)
+BTF_SET_END(tcp_bbr_check_kfunc_ids)
-static DEFINE_KFUNC_BTF_ID_SET(&tcp_bbr_kfunc_ids, tcp_bbr_kfunc_btf_set);
+static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &tcp_bbr_check_kfunc_ids,
+};
static int __init bbr_register(void)
{
int ret;
BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE);
- ret = tcp_register_congestion_control(&tcp_bbr_cong_ops);
- if (ret)
+
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_bbr_kfunc_set);
+ if (ret < 0)
return ret;
- register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set);
- return 0;
+ return tcp_register_congestion_control(&tcp_bbr_cong_ops);
}
static void __exit bbr_unregister(void)
{
- unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set);
tcp_unregister_congestion_control(&tcp_bbr_cong_ops);
}
.name = "cubic",
};
-BTF_SET_START(tcp_cubic_kfunc_ids)
+BTF_SET_START(tcp_cubic_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
BTF_ID(func, cubictcp_init)
BTF_ID(func, cubictcp_acked)
#endif
#endif
-BTF_SET_END(tcp_cubic_kfunc_ids)
+BTF_SET_END(tcp_cubic_check_kfunc_ids)
-static DEFINE_KFUNC_BTF_ID_SET(&tcp_cubic_kfunc_ids, tcp_cubic_kfunc_btf_set);
+static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &tcp_cubic_check_kfunc_ids,
+};
static int __init cubictcp_register(void)
{
/* divide by bic_scale and by constant Srtt (100ms) */
do_div(cube_factor, bic_scale * 10);
- ret = tcp_register_congestion_control(&cubictcp);
- if (ret)
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_cubic_kfunc_set);
+ if (ret < 0)
return ret;
- register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set);
- return 0;
+ return tcp_register_congestion_control(&cubictcp);
}
static void __exit cubictcp_unregister(void)
{
- unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set);
tcp_unregister_congestion_control(&cubictcp);
}
.name = "dctcp-reno",
};
-BTF_SET_START(tcp_dctcp_kfunc_ids)
+BTF_SET_START(tcp_dctcp_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
BTF_ID(func, dctcp_init)
BTF_ID(func, dctcp_state)
#endif
#endif
-BTF_SET_END(tcp_dctcp_kfunc_ids)
+BTF_SET_END(tcp_dctcp_check_kfunc_ids)
-static DEFINE_KFUNC_BTF_ID_SET(&tcp_dctcp_kfunc_ids, tcp_dctcp_kfunc_btf_set);
+static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &tcp_dctcp_check_kfunc_ids,
+};
static int __init dctcp_register(void)
{
int ret;
BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE);
- ret = tcp_register_congestion_control(&dctcp);
- if (ret)
+
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_dctcp_kfunc_set);
+ if (ret < 0)
return ret;
- register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set);
- return 0;
+ return tcp_register_congestion_control(&dctcp);
}
static void __exit dctcp_unregister(void)
{
- unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set);
tcp_unregister_congestion_control(&dctcp);
}
ireq->ireq_state = TCP_NEW_SYN_RECV;
write_pnet(&ireq->ireq_net, sock_net(sk_listener));
ireq->ireq_family = sk_listener->sk_family;
+ req->timeout = TCP_TIMEOUT_INIT;
}
return req;
sock_put(fastopen_sk);
} else {
tcp_rsk(req)->tfo_listener = false;
- if (!want_cookie)
- inet_csk_reqsk_queue_hash_add(sk, req,
- tcp_timeout_init((struct sock *)req));
+ if (!want_cookie) {
+ req->timeout = tcp_timeout_init((struct sock *)req);
+ inet_csk_reqsk_queue_hash_add(sk, req, req->timeout);
+ }
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :
TCP_SYNACK_COOKIE,
struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);
+static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+
static u32 tcp_v4_init_seq(const struct sk_buff *skb)
{
return secure_tcp_seq(ip_hdr(skb)->daddr,
struct rtable *rt;
int err;
struct ip_options_rcu *inet_opt;
- struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
+ struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
arg.tos = ip_hdr(skb)->tos;
arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+ ctl_sk = this_cpu_read(ipv4_tcp_sk);
+ sock_net_set(ctl_sk, net);
if (sk) {
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
inet_twsk(sk)->tw_mark : sk->sk_mark;
transmit_time);
ctl_sk->sk_mark = 0;
+ sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
local_bh_enable();
arg.tos = tos;
arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
local_bh_disable();
- ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+ ctl_sk = this_cpu_read(ipv4_tcp_sk);
+ sock_net_set(ctl_sk, net);
ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
inet_twsk(sk)->tw_mark : sk->sk_mark;
ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
transmit_time);
ctl_sk->sk_mark = 0;
+ sock_net_set(ctl_sk, &init_net);
__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
local_bh_enable();
}
static void __net_exit tcp_sk_exit(struct net *net)
{
- int cpu;
+ struct inet_timewait_death_row *tcp_death_row = net->ipv4.tcp_death_row;
if (net->ipv4.tcp_congestion_control)
bpf_module_put(net->ipv4.tcp_congestion_control,
net->ipv4.tcp_congestion_control->owner);
-
- for_each_possible_cpu(cpu)
- inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
- free_percpu(net->ipv4.tcp_sk);
+ if (refcount_dec_and_test(&tcp_death_row->tw_refcount))
+ kfree(tcp_death_row);
}
static int __net_init tcp_sk_init(struct net *net)
{
- int res, cpu, cnt;
-
- net->ipv4.tcp_sk = alloc_percpu(struct sock *);
- if (!net->ipv4.tcp_sk)
- return -ENOMEM;
-
- for_each_possible_cpu(cpu) {
- struct sock *sk;
-
- res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
- IPPROTO_TCP, net);
- if (res)
- goto fail;
- sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
-
- /* Please enforce IP_DF and IPID==0 for RST and
- * ACK sent in SYN-RECV and TIME-WAIT state.
- */
- inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
-
- *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
- }
+ int cnt;
net->ipv4.sysctl_tcp_ecn = 2;
net->ipv4.sysctl_tcp_ecn_fallback = 1;
net->ipv4.sysctl_tcp_tw_reuse = 2;
net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1;
+ net->ipv4.tcp_death_row = kzalloc(sizeof(struct inet_timewait_death_row), GFP_KERNEL);
+ if (!net->ipv4.tcp_death_row)
+ return -ENOMEM;
+ refcount_set(&net->ipv4.tcp_death_row->tw_refcount, 1);
cnt = tcp_hashinfo.ehash_mask + 1;
- net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
- net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
+ net->ipv4.tcp_death_row->sysctl_max_tw_buckets = cnt / 2;
+ net->ipv4.tcp_death_row->hashinfo = &tcp_hashinfo;
net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
net->ipv4.sysctl_tcp_sack = 1;
net->ipv4.tcp_congestion_control = &tcp_reno;
return 0;
-fail:
- tcp_sk_exit(net);
-
- return res;
}
static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
struct net *net;
- inet_twsk_purge(&tcp_hashinfo, AF_INET);
-
list_for_each_entry(net, net_exit_list, exit_list)
tcp_fastopen_ctx_destroy(net);
}
void __init tcp_v4_init(void)
{
+ int cpu, res;
+
+ for_each_possible_cpu(cpu) {
+ struct sock *sk;
+
+ res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+ IPPROTO_TCP, &init_net);
+ if (res)
+ panic("Failed to create the TCP control socket.\n");
+ sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+ /* Please enforce IP_DF and IPID==0 for RST and
+ * ACK sent in SYN-RECV and TIME-WAIT state.
+ */
+ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
+
+ per_cpu(ipv4_tcp_sk, cpu) = sk;
+ }
if (register_pernet_subsys(&tcp_sk_ops))
panic("Failed to create the TCP control socket.\n");
const struct inet_connection_sock *icsk = inet_csk(sk);
const struct tcp_sock *tp = tcp_sk(sk);
struct inet_timewait_sock *tw;
- struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
+ struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row;
tw = inet_twsk_alloc(sk, tcp_death_row, state);
* it can be estimated (approximately)
* from another data.
*/
- tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
+ tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ;
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
}
}
!inet_rtx_syn_ack(sk, req)) {
unsigned long expires = jiffies;
- expires += min(TCP_TIMEOUT_INIT << req->num_timeout,
- TCP_RTO_MAX);
+ expires += reqsk_timeout(req, TCP_RTO_MAX);
if (!fastopen)
mod_timer_pending(&req->rsk_timer, expires);
else
bytes = min_t(unsigned long,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
- sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);
+ sk->sk_gso_max_size);
/* Goal is to send at least one packet per ms,
* not one big TSO packet every 100 ms.
struct flowi fl;
int res;
- tcp_rsk(req)->txhash = net_tx_rndhash();
+ /* Paired with WRITE_ONCE() in sock_setsockopt() */
+ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED)
+ tcp_rsk(req)->txhash = net_tx_rndhash();
res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
NULL);
if (!res) {
return opt2;
}
-struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
- struct ipv6_txoptions *opt)
+struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space,
+ struct ipv6_txoptions *opt)
{
/*
* ignore the dest before srcrt unless srcrt is being included.
* --yoshfuji
*/
- if (opt && opt->dst0opt && !opt->srcrt) {
+ if (opt->dst0opt && !opt->srcrt) {
if (opt_space != opt) {
memcpy(opt_space, opt, sizeof(*opt_space));
opt = opt_space;
return opt;
}
-EXPORT_SYMBOL_GPL(ipv6_fixup_options);
+EXPORT_SYMBOL_GPL(__ipv6_fixup_options);
/**
* fl6_update_dst - update flowi destination address with info given
#include <linux/uaccess.h>
-/*
- * The ICMP socket(s). This is the most convenient way to flow control
- * our ICMP output as well as maintain a clean interface throughout
- * all layers. All Socketless IP sends will soon be gone.
- *
- * On SMP we have one ICMP socket per-cpu.
- */
-static struct sock *icmpv6_sk(struct net *net)
-{
- return this_cpu_read(*net->ipv6.icmp_sk);
-}
+static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk);
static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
};
/* Called with BH disabled */
-static __inline__ struct sock *icmpv6_xmit_lock(struct net *net)
+static struct sock *icmpv6_xmit_lock(struct net *net)
{
struct sock *sk;
- sk = icmpv6_sk(net);
+ sk = this_cpu_read(ipv6_icmp_sk);
if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path (f.e. SIT or
* ip6ip6 tunnel) signals dst_link_failure() for an
*/
return NULL;
}
+ sock_net_set(sk, net);
return sk;
}
-static __inline__ void icmpv6_xmit_unlock(struct sock *sk)
+static void icmpv6_xmit_unlock(struct sock *sk)
{
+ sock_net_set(sk, &init_net);
spin_unlock(&sk->sk_lock.slock);
}
security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
}
-static void __net_exit icmpv6_sk_exit(struct net *net)
-{
- int i;
-
- for_each_possible_cpu(i)
- inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv6.icmp_sk, i));
- free_percpu(net->ipv6.icmp_sk);
-}
-
-static int __net_init icmpv6_sk_init(struct net *net)
+int __init icmpv6_init(void)
{
struct sock *sk;
int err, i;
- net->ipv6.icmp_sk = alloc_percpu(struct sock *);
- if (!net->ipv6.icmp_sk)
- return -ENOMEM;
-
for_each_possible_cpu(i) {
err = inet_ctl_sock_create(&sk, PF_INET6,
- SOCK_RAW, IPPROTO_ICMPV6, net);
+ SOCK_RAW, IPPROTO_ICMPV6, &init_net);
if (err < 0) {
pr_err("Failed to initialize the ICMP6 control socket (err %d)\n",
err);
- goto fail;
+ return err;
}
- *per_cpu_ptr(net->ipv6.icmp_sk, i) = sk;
+ per_cpu(ipv6_icmp_sk, i) = sk;
/* Enough space for 2 64K ICMP packets, including
* sk_buff struct overhead.
*/
sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
}
- return 0;
-
- fail:
- icmpv6_sk_exit(net);
- return err;
-}
-
-static struct pernet_operations icmpv6_sk_ops = {
- .init = icmpv6_sk_init,
- .exit = icmpv6_sk_exit,
-};
-
-int __init icmpv6_init(void)
-{
- int err;
-
- err = register_pernet_subsys(&icmpv6_sk_ops);
- if (err < 0)
- return err;
err = -EAGAIN;
if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
fail:
pr_err("Failed to register ICMP6 protocol\n");
- unregister_pernet_subsys(&icmpv6_sk_ops);
return err;
}
void icmpv6_cleanup(void)
{
inet6_unregister_icmp_sender(icmp6_send);
- unregister_pernet_subsys(&icmpv6_sk_ops);
inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
}
if ((first_word & htonl(0xF00FFFFF)) ||
!ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
!ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
- *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
+ iph->nexthdr != iph2->nexthdr) {
not_same_flow:
NAPI_GRO_CB(p)->same_flow = 0;
continue;
goto not_same_flow;
}
/* flush if Traffic Class fields are different */
- NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
+ NAPI_GRO_CB(p)->flush |= !!((first_word & htonl(0x0FF00000)) |
+ (__force __be32)(iph->hop_limit ^ iph2->hop_limit));
NAPI_GRO_CB(p)->flush |= flush;
/* If the previous IP ID value was based on an atomic
static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
- struct rt6_info *rt, struct flowi6 *fl6)
+ struct rt6_info *rt)
{
struct ipv6_pinfo *np = inet6_sk(sk);
unsigned int mtu;
- struct ipv6_txoptions *opt = ipc6->opt;
+ struct ipv6_txoptions *nopt, *opt = ipc6->opt;
+
+ /* callers pass dst together with a reference, set it first so
+ * ip6_cork_release() can put it down even in case of an error.
+ */
+ cork->base.dst = &rt->dst;
/*
* setup for corking
if (WARN_ON(v6_cork->opt))
return -EINVAL;
- v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
- if (unlikely(!v6_cork->opt))
+ nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation);
+ if (unlikely(!nopt))
return -ENOBUFS;
- v6_cork->opt->tot_len = sizeof(*opt);
- v6_cork->opt->opt_flen = opt->opt_flen;
- v6_cork->opt->opt_nflen = opt->opt_nflen;
+ nopt->tot_len = sizeof(*opt);
+ nopt->opt_flen = opt->opt_flen;
+ nopt->opt_nflen = opt->opt_nflen;
- v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt,
- sk->sk_allocation);
- if (opt->dst0opt && !v6_cork->opt->dst0opt)
+ nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation);
+ if (opt->dst0opt && !nopt->dst0opt)
return -ENOBUFS;
- v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt,
- sk->sk_allocation);
- if (opt->dst1opt && !v6_cork->opt->dst1opt)
+ nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation);
+ if (opt->dst1opt && !nopt->dst1opt)
return -ENOBUFS;
- v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt,
- sk->sk_allocation);
- if (opt->hopopt && !v6_cork->opt->hopopt)
+ nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation);
+ if (opt->hopopt && !nopt->hopopt)
return -ENOBUFS;
- v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt,
- sk->sk_allocation);
- if (opt->srcrt && !v6_cork->opt->srcrt)
+ nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation);
+ if (opt->srcrt && !nopt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
- dst_hold(&rt->dst);
- cork->base.dst = &rt->dst;
- cork->fl.u.ip6 = *fl6;
v6_cork->hop_limit = ipc6->hlimit;
v6_cork->tclass = ipc6->tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
}
static int __ip6_append_data(struct sock *sk,
- struct flowi6 *fl6,
struct sk_buff_head *queue,
- struct inet_cork *cork,
+ struct inet_cork_full *cork_full,
struct inet6_cork *v6_cork,
struct page_frag *pfrag,
int getfrag(void *from, char *to, int offset,
unsigned int flags, struct ipcm6_cookie *ipc6)
{
struct sk_buff *skb, *skb_prev = NULL;
+ struct inet_cork *cork = &cork_full->base;
+ struct flowi6 *fl6 = &cork_full->fl.u.ip6;
unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
struct ubuf_info *uarg = NULL;
int exthdrlen = 0;
/*
* setup for corking
*/
+ dst_hold(&rt->dst);
err = ip6_setup_cork(sk, &inet->cork, &np->cork,
- ipc6, rt, fl6);
+ ipc6, rt);
if (err)
return err;
+ inet->cork.fl.u.ip6 = *fl6;
exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
- fl6 = &inet->cork.fl.u.ip6;
transhdrlen = 0;
}
- return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
+ return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
&np->cork, sk_page_frag(sk), getfrag,
from, length, transhdrlen, flags, ipc6);
}
EXPORT_SYMBOL_GPL(ip6_append_data);
+static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork)
+{
+ struct dst_entry *dst = cork->base.dst;
+
+ cork->base.dst = NULL;
+ cork->base.flags &= ~IPCORK_ALLFRAG;
+ skb_dst_set(skb, dst);
+}
+
static void ip6_cork_release(struct inet_cork_full *cork,
struct inet6_cork *v6_cork)
{
if (v6_cork->opt) {
- kfree(v6_cork->opt->dst0opt);
- kfree(v6_cork->opt->dst1opt);
- kfree(v6_cork->opt->hopopt);
- kfree(v6_cork->opt->srcrt);
- kfree(v6_cork->opt);
+ struct ipv6_txoptions *opt = v6_cork->opt;
+
+ kfree(opt->dst0opt);
+ kfree(opt->dst1opt);
+ kfree(opt->hopopt);
+ kfree(opt->srcrt);
+ kfree(opt);
v6_cork->opt = NULL;
}
cork->base.dst = NULL;
cork->base.flags &= ~IPCORK_ALLFRAG;
}
- memset(&cork->fl, 0, sizeof(cork->fl));
}
struct sk_buff *__ip6_make_skb(struct sock *sk,
{
struct sk_buff *skb, *tmp_skb;
struct sk_buff **tail_skb;
- struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
+ struct in6_addr *final_dst;
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
struct ipv6hdr *hdr;
/* Allow local fragmentation. */
skb->ignore_df = ip6_sk_ignore_df(sk);
-
- *final_dst = fl6->daddr;
__skb_pull(skb, skb_network_header_len(skb));
+
+ final_dst = &fl6->daddr;
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
skb->priority = sk->sk_priority;
skb->mark = cork->base.mark;
-
skb->tstamp = cork->base.transmit_time;
- skb_dst_set(skb, dst_clone(&rt->dst));
+ ip6_cork_steal_dst(skb, cork);
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
int getfrag(void *from, char *to, int offset,
int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
- struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
- struct rt6_info *rt, unsigned int flags,
- struct inet_cork_full *cork)
+ struct ipcm6_cookie *ipc6, struct rt6_info *rt,
+ unsigned int flags, struct inet_cork_full *cork)
{
struct inet6_cork v6_cork;
struct sk_buff_head queue;
int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0);
int err;
- if (flags & MSG_PROBE)
+ if (flags & MSG_PROBE) {
+ dst_release(&rt->dst);
return NULL;
+ }
__skb_queue_head_init(&queue);
cork->base.flags = 0;
cork->base.addr = 0;
cork->base.opt = NULL;
- cork->base.dst = NULL;
v6_cork.opt = NULL;
- err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
+ err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt);
if (err) {
ip6_cork_release(cork, &v6_cork);
return ERR_PTR(err);
if (ipc6->dontfrag < 0)
ipc6->dontfrag = inet6_sk(sk)->dontfrag;
- err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork,
+ err = __ip6_append_data(sk, &queue, cork, &v6_cork,
¤t->task_frag, getfrag, from,
length + exthdrlen, transhdrlen + exthdrlen,
flags, ipc6);
memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
neigh_release(neigh);
+ } else if (skb->protocol == htons(ETH_P_IP)) {
+ struct rtable *rt = skb_rtable(skb);
+
+ if (rt->rt_gw_family == AF_INET6)
+ memcpy(&fl6->daddr, &rt->rt_gw6, sizeof(fl6->daddr));
}
} else if (t->parms.proto != 0 && !(t->parms.flags &
(IP6_TNL_F_USE_ORIG_TCLASS |
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct inet_timewait_death_row *tcp_death_row;
struct ipv6_pinfo *np = tcp_inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct in6_addr *saddr = NULL, *final_p, final;
struct dst_entry *dst;
int addr_type;
int err;
- struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
inet->inet_dport = usin->sin6_port;
tcp_set_state(sk, TCP_SYN_SENT);
+ tcp_death_row = sock_net(sk)->ipv4.tcp_death_row;
err = inet6_hash_connect(tcp_death_row, sk);
if (err)
goto late_failure;
inet_ctl_sock_destroy(net->ipv6.tcp_sk);
}
-static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
-{
- inet_twsk_purge(&tcp_hashinfo, AF_INET6);
-}
-
static struct pernet_operations tcpv6_net_ops = {
.init = tcpv6_net_init,
.exit = tcpv6_net_exit,
- .exit_batch = tcpv6_net_exit_batch,
};
int __init tcpv6_init(void)
{
struct sk_buff *skb;
struct udp_sock *up = udp_sk(sk);
- struct flowi6 fl6;
int err = 0;
if (up->pending == AF_INET)
return udp_push_pending_frames(sk);
- /* ip6_finish_skb will release the cork, so make a copy of
- * fl6 here.
- */
- fl6 = inet_sk(sk)->cork.fl.u.ip6;
-
skb = ip6_finish_skb(sk);
if (!skb)
goto out;
- err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base);
-
+ err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6,
+ &inet_sk(sk)->cork.base);
out:
up->len = 0;
up->pending = 0;
struct ipv6_txoptions *opt = NULL;
struct ipv6_txoptions *opt_to_free = NULL;
struct ip6_flowlabel *flowlabel = NULL;
- struct flowi6 fl6;
+ struct inet_cork_full cork;
+ struct flowi6 *fl6 = &cork.fl.u.ip6;
struct dst_entry *dst;
struct ipcm6_cookie ipc6;
int addr_len = msg->msg_namelen;
}
}
- if (up->pending == AF_INET)
- return udp_sendmsg(sk, msg, len);
-
/* Rough check on arithmetic overflow,
better check is made in ip6_append_data().
*/
getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
if (up->pending) {
+ if (up->pending == AF_INET)
+ return udp_sendmsg(sk, msg, len);
/*
* There are pending frames.
* The socket lock must be held while it's corked.
}
ulen += sizeof(struct udphdr);
- memset(&fl6, 0, sizeof(fl6));
+ memset(fl6, 0, sizeof(*fl6));
if (sin6) {
if (sin6->sin6_port == 0)
return -EINVAL;
- fl6.fl6_dport = sin6->sin6_port;
+ fl6->fl6_dport = sin6->sin6_port;
daddr = &sin6->sin6_addr;
if (np->sndflow) {
- fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
- if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
- flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
+ fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+ if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) {
+ flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
if (IS_ERR(flowlabel))
return -EINVAL;
}
if (addr_len >= sizeof(struct sockaddr_in6) &&
sin6->sin6_scope_id &&
__ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
- fl6.flowi6_oif = sin6->sin6_scope_id;
+ fl6->flowi6_oif = sin6->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
- fl6.fl6_dport = inet->inet_dport;
+ fl6->fl6_dport = inet->inet_dport;
daddr = &sk->sk_v6_daddr;
- fl6.flowlabel = np->flow_label;
+ fl6->flowlabel = np->flow_label;
connected = true;
}
- if (!fl6.flowi6_oif)
- fl6.flowi6_oif = sk->sk_bound_dev_if;
+ if (!fl6->flowi6_oif)
+ fl6->flowi6_oif = sk->sk_bound_dev_if;
- if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+ if (!fl6->flowi6_oif)
+ fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
- fl6.flowi6_uid = sk->sk_uid;
+ fl6->flowi6_uid = sk->sk_uid;
if (msg->msg_controllen) {
opt = &opt_space;
err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
if (err > 0)
- err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6,
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6,
&ipc6);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
}
- if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
- flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
+ if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
+ flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
if (IS_ERR(flowlabel))
return -EINVAL;
}
opt = ipv6_fixup_options(&opt_space, opt);
ipc6.opt = opt;
- fl6.flowi6_proto = sk->sk_protocol;
- fl6.flowi6_mark = ipc6.sockc.mark;
- fl6.daddr = *daddr;
- if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
- fl6.saddr = np->saddr;
- fl6.fl6_sport = inet->inet_sport;
+ fl6->flowi6_proto = sk->sk_protocol;
+ fl6->flowi6_mark = ipc6.sockc.mark;
+ fl6->daddr = *daddr;
+ if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr))
+ fl6->saddr = np->saddr;
+ fl6->fl6_sport = inet->inet_sport;
if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) {
err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
- (struct sockaddr *)sin6, &fl6.saddr);
+ (struct sockaddr *)sin6,
+ &fl6->saddr);
if (err)
goto out_no_dst;
if (sin6) {
err = -EINVAL;
goto out_no_dst;
}
- fl6.fl6_dport = sin6->sin6_port;
- fl6.daddr = sin6->sin6_addr;
+ fl6->fl6_dport = sin6->sin6_port;
+ fl6->daddr = sin6->sin6_addr;
}
}
- if (ipv6_addr_any(&fl6.daddr))
- fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
+ if (ipv6_addr_any(&fl6->daddr))
+ fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
- final_p = fl6_update_dst(&fl6, opt, &final);
+ final_p = fl6_update_dst(fl6, opt, &final);
if (final_p)
connected = false;
- if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) {
- fl6.flowi6_oif = np->mcast_oif;
+ if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) {
+ fl6->flowi6_oif = np->mcast_oif;
connected = false;
- } else if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->ucast_oif;
+ } else if (!fl6->flowi6_oif)
+ fl6->flowi6_oif = np->ucast_oif;
- security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
+ security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
if (ipc6.tclass < 0)
ipc6.tclass = np->tclass;
- fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+ fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);
- dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected);
+ dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
}
if (ipc6.hlimit < 0)
- ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
+ ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst);
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
/* Lockless fast path for the non-corking case */
if (!corkreq) {
- struct inet_cork_full cork;
struct sk_buff *skb;
skb = ip6_make_skb(sk, getfrag, msg, ulen,
sizeof(struct udphdr), &ipc6,
- &fl6, (struct rt6_info *)dst,
+ (struct rt6_info *)dst,
msg->msg_flags, &cork);
err = PTR_ERR(skb);
if (!IS_ERR_OR_NULL(skb))
- err = udp_v6_send_skb(skb, &fl6, &cork.base);
- goto out;
+ err = udp_v6_send_skb(skb, fl6, &cork.base);
+ /* ip6_make_skb steals dst reference */
+ goto out_no_dst;
}
lock_sock(sk);
ipc6.dontfrag = np->dontfrag;
up->len += ulen;
err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
- &ipc6, &fl6, (struct rt6_info *)dst,
+ &ipc6, fl6, (struct rt6_info *)dst,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
if (err)
udp_v6_flush_pending_frames(sk);
do_confirm:
if (msg->msg_flags & MSG_PROBE)
- dst_confirm_neigh(dst, &fl6.daddr);
+ dst_confirm_neigh(dst, &fl6->daddr);
if (!(msg->msg_flags&MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
flags = *ptr++;
mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
mp_opt->reset_reason = *ptr;
+ pr_debug("MP_RST: transient=%u reason=%u",
+ mp_opt->reset_transient, mp_opt->reset_reason);
break;
case MPTCPOPT_MP_FAIL:
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
- if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) {
- const struct sock *ssk = (const struct sock *)tp;
- struct mptcp_subflow_context *subflow;
-
- subflow = mptcp_subflow_ctx(ssk);
- subflow->send_mp_fail = 0;
-
- *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL,
- TCPOLEN_MPTCP_FAIL,
- 0, 0);
- put_unaligned_be64(opts->fail_seq, ptr);
- ptr += 2;
- }
-
- /* DSS, MPC, MPJ, ADD_ADDR, FASTCLOSE and RST are mutually exclusive,
- * see mptcp_established_options*()
+ const struct sock *ssk = (const struct sock *)tp;
+ struct mptcp_subflow_context *subflow;
+
+ /* Which options can be used together?
+ *
+ * X: mutually exclusive
+ * O: often used together
+ * C: can be used together in some cases
+ * P: could be used together but we prefer not to (optimisations)
+ *
+ * Opt: | MPC | MPJ | DSS | ADD | RM | PRIO | FAIL | FC |
+ * ------|------|------|------|------|------|------|------|------|
+ * MPC |------|------|------|------|------|------|------|------|
+ * MPJ | X |------|------|------|------|------|------|------|
+ * DSS | X | X |------|------|------|------|------|------|
+ * ADD | X | X | P |------|------|------|------|------|
+ * RM | C | C | C | P |------|------|------|------|
+ * PRIO | X | C | C | C | C |------|------|------|
+ * FAIL | X | X | C | X | X | X |------|------|
+ * FC | X | X | X | X | X | X | X |------|
+ * RST | X | X | X | X | X | X | O | O |
+ * ------|------|------|------|------|------|------|------|------|
+ *
+ * The same applies in mptcp_established_options() function.
*/
if (likely(OPTION_MPTCP_DSS & opts->suboptions)) {
struct mptcp_ext *mpext = &opts->ext_copy;
}
ptr += 1;
}
+
+ /* We might need to add MP_FAIL options in rare cases */
+ if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions))
+ goto mp_fail;
} else if (OPTIONS_MPTCP_MPC & opts->suboptions) {
u8 len, flag = MPTCP_CAP_HMAC_SHA256;
if (OPTION_MPTCP_RST & opts->suboptions)
goto mp_rst;
return;
+ } else if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) {
+mp_fail:
+ /* MP_FAIL is mutually exclusive with others except RST */
+ subflow = mptcp_subflow_ctx(ssk);
+ subflow->send_mp_fail = 0;
+
+ *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL,
+ TCPOLEN_MPTCP_FAIL,
+ 0, 0);
+ put_unaligned_be64(opts->fail_seq, ptr);
+ ptr += 2;
+
+ if (OPTION_MPTCP_RST & opts->suboptions)
+ goto mp_rst;
+ return;
} else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) {
mp_rst:
*ptr++ = mptcp_option(MPTCPOPT_RST,
}
if (OPTION_MPTCP_PRIO & opts->suboptions) {
- const struct sock *ssk = (const struct sock *)tp;
- struct mptcp_subflow_context *subflow;
-
subflow = mptcp_subflow_ctx(ssk);
subflow->send_mp_prio = 0;
return -EMSGSIZE;
}
-static int mptcp_nl_addr_backup(struct net *net,
- struct mptcp_addr_info *addr,
- u8 bkup)
+static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
+ struct mptcp_addr_info *addr)
+{
+ struct mptcp_rm_list list = { .nr = 0 };
+
+ list.ids[list.nr++] = addr->id;
+
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
+ mptcp_pm_create_subflow_or_signal_addr(msk);
+}
+
+static int mptcp_nl_set_flags(struct net *net,
+ struct mptcp_addr_info *addr,
+ u8 bkup, u8 changed)
{
long s_slot = 0, s_num = 0;
struct mptcp_sock *msk;
lock_sock(sk);
spin_lock_bh(&msk->pm.lock);
- ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup);
+ if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
+ ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup);
+ if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
+ mptcp_pm_nl_fullmesh(msk, addr);
spin_unlock_bh(&msk->pm.lock);
release_sock(sk);
struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+ u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
+ MPTCP_PM_ADDR_FLAG_FULLMESH;
struct net *net = sock_net(skb->sk);
u8 bkup = 0, lookup_by_id = 0;
int ret;
spin_unlock_bh(&pernet->lock);
return -EINVAL;
}
+ if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+ (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+ spin_unlock_bh(&pernet->lock);
+ return -EINVAL;
+ }
- if (bkup)
- entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
- else
- entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP;
+ changed = (addr.flags ^ entry->flags) & mask;
+ entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
addr = *entry;
spin_unlock_bh(&pernet->lock);
- mptcp_nl_addr_backup(net, &addr.addr, bkup);
+ mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
return 0;
}
nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o
nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o
nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o
+ifeq ($(CONFIG_NF_CONNTRACK),m)
+nf_conntrack-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_conntrack_bpf.o
+else ifeq ($(CONFIG_NF_CONNTRACK),y)
+nf_conntrack-$(CONFIG_DEBUG_INFO_BTF) += nf_conntrack_bpf.o
+endif
obj-$(CONFIG_NETFILTER) = netfilter.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/* Unstable Conntrack Helpers for XDP and TC-BPF hook
+ *
+ * These are called from the XDP and SCHED_CLS BPF programs. Note that it is
+ * allowed to break compatibility for these functions since the interface they
+ * are exposed through to BPF programs is explicitly unstable.
+ */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/types.h>
+#include <linux/btf_ids.h>
+#include <linux/net_namespace.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+
+/* bpf_ct_opts - Options for CT lookup helpers
+ *
+ * Members:
+ * @netns_id - Specify the network namespace for lookup
+ * Values:
+ * BPF_F_CURRENT_NETNS (-1)
+ * Use namespace associated with ctx (xdp_md, __sk_buff)
+ * [0, S32_MAX]
+ * Network Namespace ID
+ * @error - Out parameter, set for any errors encountered
+ * Values:
+ * -EINVAL - Passed NULL for bpf_tuple pointer
+ * -EINVAL - opts->reserved is not 0
+ * -EINVAL - netns_id is less than -1
+ * -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (12)
+ * -EPROTO - l4proto isn't one of IPPROTO_TCP or IPPROTO_UDP
+ * -ENONET - No network namespace found for netns_id
+ * -ENOENT - Conntrack lookup could not find entry for tuple
+ * -EAFNOSUPPORT - tuple__sz isn't one of sizeof(tuple->ipv4)
+ * or sizeof(tuple->ipv6)
+ * @l4proto - Layer 4 protocol
+ * Values:
+ * IPPROTO_TCP, IPPROTO_UDP
+ * @reserved - Reserved member, will be reused for more options in future
+ * Values:
+ * 0
+ */
+struct bpf_ct_opts {
+ s32 netns_id;
+ s32 error;
+ u8 l4proto;
+ u8 reserved[3];
+};
+
+enum {
+ NF_BPF_CT_OPTS_SZ = 12,
+};
+
+static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
+ struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple_len, u8 protonum,
+ s32 netns_id)
+{
+ struct nf_conntrack_tuple_hash *hash;
+ struct nf_conntrack_tuple tuple;
+
+ if (unlikely(protonum != IPPROTO_TCP && protonum != IPPROTO_UDP))
+ return ERR_PTR(-EPROTO);
+ if (unlikely(netns_id < BPF_F_CURRENT_NETNS))
+ return ERR_PTR(-EINVAL);
+
+ memset(&tuple, 0, sizeof(tuple));
+ switch (tuple_len) {
+ case sizeof(bpf_tuple->ipv4):
+ tuple.src.l3num = AF_INET;
+ tuple.src.u3.ip = bpf_tuple->ipv4.saddr;
+ tuple.src.u.tcp.port = bpf_tuple->ipv4.sport;
+ tuple.dst.u3.ip = bpf_tuple->ipv4.daddr;
+ tuple.dst.u.tcp.port = bpf_tuple->ipv4.dport;
+ break;
+ case sizeof(bpf_tuple->ipv6):
+ tuple.src.l3num = AF_INET6;
+ memcpy(tuple.src.u3.ip6, bpf_tuple->ipv6.saddr, sizeof(bpf_tuple->ipv6.saddr));
+ tuple.src.u.tcp.port = bpf_tuple->ipv6.sport;
+ memcpy(tuple.dst.u3.ip6, bpf_tuple->ipv6.daddr, sizeof(bpf_tuple->ipv6.daddr));
+ tuple.dst.u.tcp.port = bpf_tuple->ipv6.dport;
+ break;
+ default:
+ return ERR_PTR(-EAFNOSUPPORT);
+ }
+
+ tuple.dst.protonum = protonum;
+
+ if (netns_id >= 0) {
+ net = get_net_ns_by_id(net, netns_id);
+ if (unlikely(!net))
+ return ERR_PTR(-ENONET);
+ }
+
+ hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple);
+ if (netns_id >= 0)
+ put_net(net);
+ if (!hash)
+ return ERR_PTR(-ENOENT);
+ return nf_ct_tuplehash_to_ctrack(hash);
+}
+
+__diag_push();
+__diag_ignore(GCC, 8, "-Wmissing-prototypes",
+ "Global functions as their definitions will be in nf_conntrack BTF");
+
+/* bpf_xdp_ct_lookup - Lookup CT entry for the given tuple, and acquire a
+ * reference to it
+ *
+ * Parameters:
+ * @xdp_ctx - Pointer to ctx (xdp_md) in XDP program
+ * Cannot be NULL
+ * @bpf_tuple - Pointer to memory representing the tuple to look up
+ * Cannot be NULL
+ * @tuple__sz - Length of the tuple structure
+ * Must be one of sizeof(bpf_tuple->ipv4) or
+ * sizeof(bpf_tuple->ipv6)
+ * @opts - Additional options for lookup (documented above)
+ * Cannot be NULL
+ * @opts__sz - Length of the bpf_ct_opts structure
+ * Must be NF_BPF_CT_OPTS_SZ (12)
+ */
+struct nf_conn *
+bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
+{
+ struct xdp_buff *ctx = (struct xdp_buff *)xdp_ctx;
+ struct net *caller_net;
+ struct nf_conn *nfct;
+
+ BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ);
+
+ if (!opts)
+ return NULL;
+ if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
+ opts->reserved[2] || opts__sz != NF_BPF_CT_OPTS_SZ) {
+ opts->error = -EINVAL;
+ return NULL;
+ }
+ caller_net = dev_net(ctx->rxq->dev);
+ nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto,
+ opts->netns_id);
+ if (IS_ERR(nfct)) {
+ opts->error = PTR_ERR(nfct);
+ return NULL;
+ }
+ return nfct;
+}
+
+/* bpf_skb_ct_lookup - Lookup CT entry for the given tuple, and acquire a
+ * reference to it
+ *
+ * Parameters:
+ * @skb_ctx - Pointer to ctx (__sk_buff) in TC program
+ * Cannot be NULL
+ * @bpf_tuple - Pointer to memory representing the tuple to look up
+ * Cannot be NULL
+ * @tuple__sz - Length of the tuple structure
+ * Must be one of sizeof(bpf_tuple->ipv4) or
+ * sizeof(bpf_tuple->ipv6)
+ * @opts - Additional options for lookup (documented above)
+ * Cannot be NULL
+ * @opts__sz - Length of the bpf_ct_opts structure
+ * Must be NF_BPF_CT_OPTS_SZ (12)
+ */
+struct nf_conn *
+bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple,
+ u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz)
+{
+ struct sk_buff *skb = (struct sk_buff *)skb_ctx;
+ struct net *caller_net;
+ struct nf_conn *nfct;
+
+ BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ);
+
+ if (!opts)
+ return NULL;
+ if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] ||
+ opts->reserved[2] || opts__sz != NF_BPF_CT_OPTS_SZ) {
+ opts->error = -EINVAL;
+ return NULL;
+ }
+ caller_net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk);
+ nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto,
+ opts->netns_id);
+ if (IS_ERR(nfct)) {
+ opts->error = PTR_ERR(nfct);
+ return NULL;
+ }
+ return nfct;
+}
+
+/* bpf_ct_release - Release acquired nf_conn object
+ *
+ * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects
+ * the program if any references remain in the program in all of the explored
+ * states.
+ *
+ * Parameters:
+ * @nf_conn - Pointer to referenced nf_conn object, obtained using
+ * bpf_xdp_ct_lookup or bpf_skb_ct_lookup.
+ */
+void bpf_ct_release(struct nf_conn *nfct)
+{
+ if (!nfct)
+ return;
+ nf_ct_put(nfct);
+}
+
+__diag_pop()
+
+BTF_SET_START(nf_ct_xdp_check_kfunc_ids)
+BTF_ID(func, bpf_xdp_ct_lookup)
+BTF_ID(func, bpf_ct_release)
+BTF_SET_END(nf_ct_xdp_check_kfunc_ids)
+
+BTF_SET_START(nf_ct_tc_check_kfunc_ids)
+BTF_ID(func, bpf_skb_ct_lookup)
+BTF_ID(func, bpf_ct_release)
+BTF_SET_END(nf_ct_tc_check_kfunc_ids)
+
+BTF_SET_START(nf_ct_acquire_kfunc_ids)
+BTF_ID(func, bpf_xdp_ct_lookup)
+BTF_ID(func, bpf_skb_ct_lookup)
+BTF_SET_END(nf_ct_acquire_kfunc_ids)
+
+BTF_SET_START(nf_ct_release_kfunc_ids)
+BTF_ID(func, bpf_ct_release)
+BTF_SET_END(nf_ct_release_kfunc_ids)
+
+/* Both sets are identical */
+#define nf_ct_ret_null_kfunc_ids nf_ct_acquire_kfunc_ids
+
+static const struct btf_kfunc_id_set nf_conntrack_xdp_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &nf_ct_xdp_check_kfunc_ids,
+ .acquire_set = &nf_ct_acquire_kfunc_ids,
+ .release_set = &nf_ct_release_kfunc_ids,
+ .ret_null_set = &nf_ct_ret_null_kfunc_ids,
+};
+
+static const struct btf_kfunc_id_set nf_conntrack_tc_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &nf_ct_tc_check_kfunc_ids,
+ .acquire_set = &nf_ct_acquire_kfunc_ids,
+ .release_set = &nf_ct_release_kfunc_ids,
+ .ret_null_set = &nf_ct_ret_null_kfunc_ids,
+};
+
+int register_nf_conntrack_bpf(void)
+{
+ int ret;
+
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_xdp_kfunc_set);
+ return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_tc_kfunc_set);
+}
#include <linux/rculist_nulls.h>
#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_bpf.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
conntrack_gc_work_init(&conntrack_gc_work);
queue_delayed_work(system_power_efficient_wq, &conntrack_gc_work.dwork, HZ);
+ ret = register_nf_conntrack_bpf();
+ if (ret < 0)
+ goto err_kfunc;
+
return 0;
+err_kfunc:
+ cancel_delayed_work_sync(&conntrack_gc_work.dwork);
+ nf_conntrack_proto_fini();
err_proto:
nf_conntrack_seqadj_fini();
err_seqadj:
sk->sk_state != SMC_CLOSED) {
if (!val) {
SMC_STAT_INC(smc, cork_cnt);
- mod_delayed_work(smc->conn.lgr->tx_wq,
- &smc->conn.tx_work, 0);
+ smc_tx_pending(&smc->conn);
+ cancel_delayed_work(&smc->conn.tx_work);
}
}
break;
rc = kernel_sendpage(smc->clcsock, page, offset,
size, flags);
} else {
+ lock_sock(sk);
+ rc = smc_tx_sendpage(smc, page, offset, size, flags);
+ release_sock(sk);
SMC_STAT_INC(smc, sendpage_cnt);
- rc = sock_no_sendpage(sock, page, offset, size, flags);
}
out:
#include "smc_tracepoint.h"
#define SMC_TX_WORK_DELAY 0
-#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */
/***************************** sndbuf producer *******************************/
*/
if ((msg->msg_flags & MSG_OOB) && !send_remaining)
conn->urg_tx_pend = true;
- if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) &&
- (atomic_read(&conn->sndbuf_space) >
- (conn->sndbuf_desc->len >> 1)))
- /* for a corked socket defer the RDMA writes if there
- * is still sufficient sndbuf_space available
+ if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc) ||
+ msg->msg_flags & MSG_SENDPAGE_NOTLAST) &&
+ (atomic_read(&conn->sndbuf_space)))
+ /* for a corked socket defer the RDMA writes if
+ * sndbuf_space is still available. The applications
+ * should known how/when to uncork it.
*/
- queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work,
- SMC_TX_CORK_DELAY);
- else
- smc_tx_sndbuf_nonempty(conn);
+ continue;
+ smc_tx_sndbuf_nonempty(conn);
trace_smc_tx_sendmsg(smc, copylen);
} /* while (msg_data_left(msg)) */
return rc;
}
+int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
+ size_t size, int flags)
+{
+ struct msghdr msg = {.msg_flags = flags};
+ char *kaddr = kmap(page);
+ struct kvec iov;
+ int rc;
+
+ iov.iov_base = kaddr + offset;
+ iov.iov_len = size;
+ iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size);
+ rc = smc_tx_sendmsg(smc, &msg, size);
+ kunmap(page);
+ return rc;
+}
+
/***************************** sndbuf consumer *******************************/
/* sndbuf consumer: actual data transfer of one target chunk with ISM write */
return rc;
}
-/* Wakeup sndbuf consumers from process context
- * since there is more data to transmit
- */
-void smc_tx_work(struct work_struct *work)
+void smc_tx_pending(struct smc_connection *conn)
{
- struct smc_connection *conn = container_of(to_delayed_work(work),
- struct smc_connection,
- tx_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
int rc;
- lock_sock(&smc->sk);
if (smc->sk.sk_err)
- goto out;
+ return;
rc = smc_tx_sndbuf_nonempty(conn);
if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked &&
!atomic_read(&conn->bytes_to_rcv))
conn->local_rx_ctrl.prod_flags.write_blocked = 0;
+}
+
+/* Wakeup sndbuf consumers from process context
+ * since there is more data to transmit
+ */
+void smc_tx_work(struct work_struct *work)
+{
+ struct smc_connection *conn = container_of(to_delayed_work(work),
+ struct smc_connection,
+ tx_work);
+ struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
-out:
+ lock_sock(&smc->sk);
+ smc_tx_pending(conn);
release_sock(&smc->sk);
}
return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
}
+void smc_tx_pending(struct smc_connection *conn);
void smc_tx_work(struct work_struct *work);
void smc_tx_init(struct smc_sock *smc);
int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
+int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
+ size_t size, int flags);
int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
void smc_tx_consumer_update(struct smc_connection *conn, bool force);
struct gss_api_mech *mech;
enum rpc_gss_svc service;
struct rpc_clnt *client;
- struct net *net;
+ struct net *net;
+ netns_tracker ns_tracker;
/*
* There are two upcall pipes; dentry[1], named "gssd", is used
* for the new text-based upcall; dentry[0] is named after the
goto err_free;
}
gss_auth->client = clnt;
- gss_auth->net = get_net(rpc_net_ns(clnt));
+ gss_auth->net = get_net_track(rpc_net_ns(clnt), &gss_auth->ns_tracker,
+ GFP_KERNEL);
err = -EINVAL;
gss_auth->mech = gss_mech_get_by_pseudoflavor(flavor);
if (!gss_auth->mech)
err_put_mech:
gss_mech_put(gss_auth->mech);
err_put_net:
- put_net(gss_auth->net);
+ put_net_track(gss_auth->net, &gss_auth->ns_tracker);
err_free:
kfree(gss_auth->target_name);
kfree(gss_auth);
gss_pipe_free(gss_auth->gss_pipe[0]);
gss_pipe_free(gss_auth->gss_pipe[1]);
gss_mech_put(gss_auth->mech);
- put_net(gss_auth->net);
+ put_net_track(gss_auth->net, &gss_auth->ns_tracker);
kfree(gss_auth->target_name);
kfree(gss_auth);
if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags))
svcauth_unix_info_release(xprt);
put_cred(xprt->xpt_cred);
- put_net(xprt->xpt_net);
+ put_net_track(xprt->xpt_net, &xprt->ns_tracker);
/* See comment on corresponding get in xs_setup_bc_tcp(): */
if (xprt->xpt_bc_xprt)
xprt_put(xprt->xpt_bc_xprt);
mutex_init(&xprt->xpt_mutex);
spin_lock_init(&xprt->xpt_lock);
set_bit(XPT_BUSY, &xprt->xpt_flags);
- xprt->xpt_net = get_net(net);
+ xprt->xpt_net = get_net_track(net, &xprt->ns_tracker, GFP_ATOMIC);
strcpy(xprt->xpt_remotebuf, "uninitialized");
}
EXPORT_SYMBOL_GPL(svc_xprt_init);
void xprt_free(struct rpc_xprt *xprt)
{
- put_net(xprt->xprt_net);
+ put_net_track(xprt->xprt_net, &xprt->ns_tracker);
xprt_free_all_slots(xprt);
xprt_free_id(xprt);
rpc_sysfs_xprt_destroy(xprt);
xprt_init_xid(xprt);
- xprt->xprt_net = get_net(net);
+ xprt->xprt_net = get_net_track(net, &xprt->ns_tracker, GFP_KERNEL);
}
/**
m->hdr[w] |= htonl(val);
}
-static inline void msg_swap_words(struct tipc_msg *msg, u32 a, u32 b)
-{
- u32 temp = msg->hdr[a];
-
- msg->hdr[a] = msg->hdr[b];
- msg->hdr[b] = temp;
-}
-
/*
* Word 0
*/
msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1);
}
-static inline void msg_reset_reroute_cnt(struct tipc_msg *m)
-{
- msg_set_bits(m, 1, 21, 0xf, 0);
-}
-
static inline u32 msg_lookup_scope(struct tipc_msg *m)
{
return msg_bits(m, 1, 19, 0x3);
msg_set_word(m, 2, n);
}
-static inline u32 msg_bcgap_after(struct tipc_msg *m)
-{
- return msg_bits(m, 2, 16, 0xffff);
-}
-
static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n)
{
msg_set_bits(m, 2, 16, 0xffff, n);
msg_set_bits(m, 4, 0, 0xffff, n);
}
-static inline void msg_set_long_msgno(struct tipc_msg *m, u32 n)
-{
- msg_set_bits(m, 4, 0, 0xffff, n);
-}
-
static inline u32 msg_bc_netid(struct tipc_msg *m)
{
return msg_word(m, 4);
return sk;
}
-static struct sock *unix_next_socket(struct seq_file *seq,
- struct sock *sk,
- loff_t *pos)
+static struct sock *unix_get_first(struct seq_file *seq, loff_t *pos)
{
unsigned long bucket = get_bucket(*pos);
+ struct sock *sk;
- while (sk > (struct sock *)SEQ_START_TOKEN) {
- sk = sk_next(sk);
- if (!sk)
- goto next_bucket;
- if (sock_net(sk) == seq_file_net(seq))
- return sk;
- }
-
- do {
+ while (bucket < ARRAY_SIZE(unix_socket_table)) {
spin_lock(&unix_table_locks[bucket]);
+
sk = unix_from_bucket(seq, pos);
if (sk)
return sk;
-next_bucket:
- spin_unlock(&unix_table_locks[bucket++]);
- *pos = set_bucket_offset(bucket, 1);
- } while (bucket < ARRAY_SIZE(unix_socket_table));
+ spin_unlock(&unix_table_locks[bucket]);
+
+ *pos = set_bucket_offset(++bucket, 1);
+ }
return NULL;
}
+static struct sock *unix_get_next(struct seq_file *seq, struct sock *sk,
+ loff_t *pos)
+{
+ unsigned long bucket = get_bucket(*pos);
+
+ for (sk = sk_next(sk); sk; sk = sk_next(sk))
+ if (sock_net(sk) == seq_file_net(seq))
+ return sk;
+
+ spin_unlock(&unix_table_locks[bucket]);
+
+ *pos = set_bucket_offset(++bucket, 1);
+
+ return unix_get_first(seq, pos);
+}
+
static void *unix_seq_start(struct seq_file *seq, loff_t *pos)
{
if (!*pos)
return SEQ_START_TOKEN;
- if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table))
- return NULL;
-
- return unix_next_socket(seq, NULL, pos);
+ return unix_get_first(seq, pos);
}
static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
- return unix_next_socket(seq, v, pos);
+
+ if (v == SEQ_START_TOKEN)
+ return unix_get_first(seq, pos);
+
+ return unix_get_next(seq, v, pos);
}
static void unix_seq_stop(struct seq_file *seq, void *v)
};
#if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_unix_iter_state {
+ struct seq_net_private p;
+ unsigned int cur_sk;
+ unsigned int end_sk;
+ unsigned int max_sk;
+ struct sock **batch;
+ bool st_bucket_done;
+};
+
struct bpf_iter__unix {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct unix_sock *, unix_sk);
return bpf_iter_run_prog(prog, &ctx);
}
+static int bpf_iter_unix_hold_batch(struct seq_file *seq, struct sock *start_sk)
+
+{
+ struct bpf_unix_iter_state *iter = seq->private;
+ unsigned int expected = 1;
+ struct sock *sk;
+
+ sock_hold(start_sk);
+ iter->batch[iter->end_sk++] = start_sk;
+
+ for (sk = sk_next(start_sk); sk; sk = sk_next(sk)) {
+ if (sock_net(sk) != seq_file_net(seq))
+ continue;
+
+ if (iter->end_sk < iter->max_sk) {
+ sock_hold(sk);
+ iter->batch[iter->end_sk++] = sk;
+ }
+
+ expected++;
+ }
+
+ spin_unlock(&unix_table_locks[start_sk->sk_hash]);
+
+ return expected;
+}
+
+static void bpf_iter_unix_put_batch(struct bpf_unix_iter_state *iter)
+{
+ while (iter->cur_sk < iter->end_sk)
+ sock_put(iter->batch[iter->cur_sk++]);
+}
+
+static int bpf_iter_unix_realloc_batch(struct bpf_unix_iter_state *iter,
+ unsigned int new_batch_sz)
+{
+ struct sock **new_batch;
+
+ new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz,
+ GFP_USER | __GFP_NOWARN);
+ if (!new_batch)
+ return -ENOMEM;
+
+ bpf_iter_unix_put_batch(iter);
+ kvfree(iter->batch);
+ iter->batch = new_batch;
+ iter->max_sk = new_batch_sz;
+
+ return 0;
+}
+
+static struct sock *bpf_iter_unix_batch(struct seq_file *seq,
+ loff_t *pos)
+{
+ struct bpf_unix_iter_state *iter = seq->private;
+ unsigned int expected;
+ bool resized = false;
+ struct sock *sk;
+
+ if (iter->st_bucket_done)
+ *pos = set_bucket_offset(get_bucket(*pos) + 1, 1);
+
+again:
+ /* Get a new batch */
+ iter->cur_sk = 0;
+ iter->end_sk = 0;
+
+ sk = unix_get_first(seq, pos);
+ if (!sk)
+ return NULL; /* Done */
+
+ expected = bpf_iter_unix_hold_batch(seq, sk);
+
+ if (iter->end_sk == expected) {
+ iter->st_bucket_done = true;
+ return sk;
+ }
+
+ if (!resized && !bpf_iter_unix_realloc_batch(iter, expected * 3 / 2)) {
+ resized = true;
+ goto again;
+ }
+
+ return sk;
+}
+
+static void *bpf_iter_unix_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ if (!*pos)
+ return SEQ_START_TOKEN;
+
+ /* bpf iter does not support lseek, so it always
+ * continue from where it was stop()-ped.
+ */
+ return bpf_iter_unix_batch(seq, pos);
+}
+
+static void *bpf_iter_unix_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ struct bpf_unix_iter_state *iter = seq->private;
+ struct sock *sk;
+
+ /* Whenever seq_next() is called, the iter->cur_sk is
+ * done with seq_show(), so advance to the next sk in
+ * the batch.
+ */
+ if (iter->cur_sk < iter->end_sk)
+ sock_put(iter->batch[iter->cur_sk++]);
+
+ ++*pos;
+
+ if (iter->cur_sk < iter->end_sk)
+ sk = iter->batch[iter->cur_sk];
+ else
+ sk = bpf_iter_unix_batch(seq, pos);
+
+ return sk;
+}
+
static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v)
{
struct bpf_iter_meta meta;
struct bpf_prog *prog;
struct sock *sk = v;
uid_t uid;
+ bool slow;
+ int ret;
if (v == SEQ_START_TOKEN)
return 0;
+ slow = lock_sock_fast(sk);
+
+ if (unlikely(sk_unhashed(sk))) {
+ ret = SEQ_SKIP;
+ goto unlock;
+ }
+
uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
meta.seq = seq;
prog = bpf_iter_get_info(&meta, false);
- return unix_prog_seq_show(prog, &meta, v, uid);
+ ret = unix_prog_seq_show(prog, &meta, v, uid);
+unlock:
+ unlock_sock_fast(sk, slow);
+ return ret;
}
static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v)
{
+ struct bpf_unix_iter_state *iter = seq->private;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
(void)unix_prog_seq_show(prog, &meta, v, 0);
}
- unix_seq_stop(seq, v);
+ if (iter->cur_sk < iter->end_sk)
+ bpf_iter_unix_put_batch(iter);
}
static const struct seq_operations bpf_iter_unix_seq_ops = {
- .start = unix_seq_start,
- .next = unix_seq_next,
+ .start = bpf_iter_unix_seq_start,
+ .next = bpf_iter_unix_seq_next,
.stop = bpf_iter_unix_seq_stop,
.show = bpf_iter_unix_seq_show,
};
DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta,
struct unix_sock *unix_sk, uid_t uid)
+#define INIT_BATCH_SZ 16
+
+static int bpf_iter_init_unix(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+ struct bpf_unix_iter_state *iter = priv_data;
+ int err;
+
+ err = bpf_iter_init_seq_net(priv_data, aux);
+ if (err)
+ return err;
+
+ err = bpf_iter_unix_realloc_batch(iter, INIT_BATCH_SZ);
+ if (err) {
+ bpf_iter_fini_seq_net(priv_data);
+ return err;
+ }
+
+ return 0;
+}
+
+static void bpf_iter_fini_unix(void *priv_data)
+{
+ struct bpf_unix_iter_state *iter = priv_data;
+
+ bpf_iter_fini_seq_net(priv_data);
+ kvfree(iter->batch);
+}
+
static const struct bpf_iter_seq_info unix_seq_info = {
.seq_ops = &bpf_iter_unix_seq_ops,
- .init_seq_private = bpf_iter_init_seq_net,
- .fini_seq_private = bpf_iter_fini_seq_net,
- .seq_priv_size = sizeof(struct seq_net_private),
+ .init_seq_private = bpf_iter_init_unix,
+ .fini_seq_private = bpf_iter_fini_unix,
+ .seq_priv_size = sizeof(struct bpf_unix_iter_state),
};
+static const struct bpf_func_proto *
+bpf_iter_unix_get_func_proto(enum bpf_func_id func_id,
+ const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_setsockopt:
+ return &bpf_sk_setsockopt_proto;
+ case BPF_FUNC_getsockopt:
+ return &bpf_sk_getsockopt_proto;
+ default:
+ return NULL;
+ }
+}
+
static struct bpf_iter_reg unix_reg_info = {
.target = "unix",
.ctx_arg_info_size = 1,
{ offsetof(struct bpf_iter__unix, unix_sk),
PTR_TO_BTF_ID_OR_NULL },
},
+ .get_func_proto = bpf_iter_unix_get_func_proto,
.seq_info = &unix_seq_info,
};
{
__u32 curr_prog_id = 0;
- if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
- printf("bpf_get_link_xdp_id failed\n");
+ if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
+ printf("bpf_xdp_query_id failed\n");
exit(1);
}
if (prog_id == curr_prog_id)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ bpf_xdp_detach(ifindex, xdp_flags, NULL);
else if (!curr_prog_id)
printf("couldn't find a prog id on a given interface\n");
else
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
+ if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
__u32 curr_prog_id = 0;
if (ifindex > -1) {
- if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
- printf("bpf_get_link_xdp_id failed\n");
+ if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
+ printf("bpf_xdp_query_id failed\n");
exit(1);
}
if (prog_id == curr_prog_id)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ bpf_xdp_detach(ifindex, xdp_flags, NULL);
else if (!curr_prog_id)
printf("couldn't find a prog id on a given iface\n");
else
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
+ if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
{
int err;
- err = bpf_set_link_xdp_fd(idx, prog_fd, xdp_flags);
+ err = bpf_xdp_attach(idx, prog_fd, xdp_flags, NULL);
if (err < 0) {
printf("ERROR: failed to attach program to %s\n", name);
return err;
{
int err;
- err = bpf_set_link_xdp_fd(idx, -1, xdp_flags);
+ err = bpf_xdp_detach(idx, xdp_flags, NULL);
if (err < 0)
printf("ERROR: failed to detach program from %s\n", name);
int i = 0;
for (i = 0; i < total_ifindex; i++) {
- if (bpf_get_link_xdp_id(ifindex_list[i], &prog_id, flags)) {
- printf("bpf_get_link_xdp_id on iface %d failed\n",
+ if (bpf_xdp_query_id(ifindex_list[i], flags, &prog_id)) {
+ printf("bpf_xdp_query_id on iface %d failed\n",
ifindex_list[i]);
exit(1);
}
if (prog_id_list[i] == prog_id)
- bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
+ bpf_xdp_detach(ifindex_list[i], flags, NULL);
else if (!prog_id)
printf("couldn't find a prog id on iface %d\n",
ifindex_list[i]);
}
prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *));
for (i = 0; i < total_ifindex; i++) {
- if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd, flags) < 0) {
+ if (bpf_xdp_attach(ifindex_list[i], prog_fd, flags, NULL) < 0) {
printf("link set xdp fd failed\n");
int recovery_index = i;
for (i = 0; i < recovery_index; i++)
- bpf_set_link_xdp_fd(ifindex_list[i], -1, flags);
+ bpf_xdp_detach(ifindex_list[i], flags, NULL);
return 1;
}
__u32 curr_prog_id = 0;
if (ifindex > -1) {
- if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
- printf("bpf_get_link_xdp_id failed\n");
+ if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
+ printf("bpf_xdp_query_id failed\n");
exit(EXIT_FAIL);
}
if (prog_id == curr_prog_id) {
fprintf(stderr,
"Interrupted: Removing XDP program on ifindex:%d device:%s\n",
ifindex, ifname);
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ bpf_xdp_detach(ifindex, xdp_flags, NULL);
} else if (!curr_prog_id) {
printf("couldn't find a prog id on a given iface\n");
} else {
static struct record *alloc_record_per_rxq(void)
{
- unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
+ unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
struct record *array;
array = calloc(nr_rxqs, sizeof(struct record));
static struct stats_record *alloc_stats_record(void)
{
- unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
+ unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
struct stats_record *rec;
int i;
static void free_stats_record(struct stats_record *r)
{
- unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
+ unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
int i;
for (i = 0; i < nr_rxqs; i++)
map_collect_percpu(fd, 0, &rec->stats);
fd = bpf_map__fd(rx_queue_index_map);
- max_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
+ max_rxqs = bpf_map__max_entries(rx_queue_index_map);
for (i = 0; i < max_rxqs; i++)
map_collect_percpu(fd, i, &rec->rxq[i]);
}
struct stats_record *stats_prev,
int action, __u32 cfg_opt)
{
- unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
+ unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map);
unsigned int nr_cpus = bpf_num_possible_cpus();
double pps = 0, err = 0;
struct record *rec, *prev;
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
- if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
+ if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
fprintf(stderr, "link set xdp fd failed\n");
return EXIT_FAIL_XDP;
}
__u32 info_len = sizeof(info);
int err;
- err = bpf_set_link_xdp_fd(idx, fd, xdp_flags);
+ err = bpf_xdp_attach(idx, fd, xdp_flags, NULL);
if (err < 0) {
printf("ERROR: failed to attach program to %s\n", name);
return err;
__u32 curr_prog_id = 0;
int err = 0;
- err = bpf_get_link_xdp_id(idx, &curr_prog_id, xdp_flags);
+ err = bpf_xdp_query_id(idx, xdp_flags, &curr_prog_id);
if (err) {
- printf("bpf_get_link_xdp_id failed\n");
+ printf("bpf_xdp_query_id failed\n");
return err;
}
if (prog_id == curr_prog_id) {
- err = bpf_set_link_xdp_fd(idx, -1, xdp_flags);
+ err = bpf_xdp_detach(idx, xdp_flags, NULL);
if (err < 0)
printf("ERROR: failed to detach prog from %s\n", name);
} else if (!curr_prog_id) {
int ret;
if (prog_id) {
- ret = bpf_get_link_xdp_id(ifindex, &cur_prog_id, xdp_flags);
+ ret = bpf_xdp_query_id(ifindex, xdp_flags, &cur_prog_id);
if (ret < 0)
return -errno;
}
}
- return bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ return bpf_xdp_detach(ifindex, xdp_flags, NULL);
}
int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic,
xdp_flags |= !force ? XDP_FLAGS_UPDATE_IF_NOEXIST : 0;
xdp_flags |= generic ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE;
- ret = bpf_set_link_xdp_fd(ifindex, bpf_program__fd(xdp_prog),
- xdp_flags);
+ ret = bpf_xdp_attach(ifindex, bpf_program__fd(xdp_prog), xdp_flags, NULL);
if (ret < 0) {
ret = -errno;
fprintf(stderr,
return ret;
}
- ret = bpf_get_link_xdp_id(ifindex, &prog_id, xdp_flags);
+ ret = bpf_xdp_query_id(ifindex, xdp_flags, &prog_id);
if (ret < 0) {
ret = -errno;
fprintf(stderr,
__u32 curr_prog_id = 0;
if (ifindex > -1) {
- if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) {
- printf("bpf_get_link_xdp_id failed\n");
+ if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
+ printf("bpf_xdp_query_id failed\n");
exit(1);
}
if (prog_id == curr_prog_id)
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ bpf_xdp_detach(ifindex, xdp_flags, NULL);
else if (!curr_prog_id)
printf("couldn't find a prog id on a given iface\n");
else
}
}
- if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) {
+ if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
poll_stats(kill_after_s);
- bpf_set_link_xdp_fd(ifindex, -1, xdp_flags);
+ bpf_xdp_detach(ifindex, xdp_flags, NULL);
return 0;
}
unlink(SOCKET_NAME);
/* Unset fd for given ifindex */
- err = bpf_set_link_xdp_fd(ifindex, -1, 0);
+ err = bpf_xdp_detach(ifindex, 0, NULL);
if (err) {
fprintf(stderr, "Error when unsetting bpf prog_fd for ifindex(%d)\n", ifindex);
return err;
{
u32 curr_prog_id = 0;
- if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
- printf("bpf_get_link_xdp_id failed\n");
+ if (bpf_xdp_query_id(opt_ifindex, opt_xdp_flags, &curr_prog_id)) {
+ printf("bpf_xdp_query_id failed\n");
exit(EXIT_FAILURE);
}
if (prog_id == curr_prog_id)
- bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
+ bpf_xdp_detach(opt_ifindex, opt_xdp_flags, NULL);
else if (!curr_prog_id)
printf("couldn't find a prog id on a given interface\n");
else
if (ret)
exit_with_error(-ret);
- ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags);
+ ret = bpf_xdp_query_id(opt_ifindex, opt_xdp_flags, &prog_id);
if (ret)
exit_with_error(-ret);
exit(EXIT_FAILURE);
}
- if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) {
+ if (bpf_xdp_attach(opt_ifindex, prog_fd, opt_xdp_flags, NULL) < 0) {
fprintf(stderr, "ERROR: link set xdp fd failed\n");
exit(EXIT_FAILURE);
}
int i;
for (i = 0 ; i < n_ports; i++)
- bpf_set_link_xdp_fd(if_nametoindex(port_params[i].iface), -1,
- port_params[i].xsk_cfg.xdp_flags);
+ bpf_xdp_detach(if_nametoindex(port_params[i].iface),
+ port_params[i].xsk_cfg.xdp_flags, NULL);
}
int main(int argc, char **argv)
self.line = ''
self.helpers = []
self.commands = []
+ self.desc_unique_helpers = set()
+ self.define_unique_helpers = []
+ self.desc_syscalls = []
+ self.enum_syscalls = []
def parse_element(self):
proto = self.parse_symbol()
- desc = self.parse_desc()
- ret = self.parse_ret()
+ desc = self.parse_desc(proto)
+ ret = self.parse_ret(proto)
return APIElement(proto=proto, desc=desc, ret=ret)
def parse_helper(self):
proto = self.parse_proto()
- desc = self.parse_desc()
- ret = self.parse_ret()
+ desc = self.parse_desc(proto)
+ ret = self.parse_ret(proto)
return Helper(proto=proto, desc=desc, ret=ret)
def parse_symbol(self):
- p = re.compile(' \* ?(.+)$')
+ p = re.compile(' \* ?(BPF\w+)$')
capture = p.match(self.line)
if not capture:
raise NoSyscallCommandFound
self.line = self.reader.readline()
return capture.group(1)
- def parse_desc(self):
+ def parse_desc(self, proto):
p = re.compile(' \* ?(?:\t| {5,8})Description$')
capture = p.match(self.line)
if not capture:
- # Helper can have empty description and we might be parsing another
- # attribute: return but do not consume.
- return ''
+ raise Exception("No description section found for " + proto)
# Description can be several lines, some of them possibly empty, and it
# stops when another subsection title is met.
desc = ''
+ desc_present = False
while True:
self.line = self.reader.readline()
if self.line == ' *\n':
p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')
capture = p.match(self.line)
if capture:
+ desc_present = True
desc += capture.group(1) + '\n'
else:
break
+
+ if not desc_present:
+ raise Exception("No description found for " + proto)
return desc
- def parse_ret(self):
+ def parse_ret(self, proto):
p = re.compile(' \* ?(?:\t| {5,8})Return$')
capture = p.match(self.line)
if not capture:
- # Helper can have empty retval and we might be parsing another
- # attribute: return but do not consume.
- return ''
+ raise Exception("No return section found for " + proto)
# Return value description can be several lines, some of them possibly
# empty, and it stops when another subsection title is met.
ret = ''
+ ret_present = False
while True:
self.line = self.reader.readline()
if self.line == ' *\n':
p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)')
capture = p.match(self.line)
if capture:
+ ret_present = True
ret += capture.group(1) + '\n'
else:
break
+
+ if not ret_present:
+ raise Exception("No return found for " + proto)
return ret
- def seek_to(self, target, help_message):
+ def seek_to(self, target, help_message, discard_lines = 1):
self.reader.seek(0)
offset = self.reader.read().find(target)
if offset == -1:
raise Exception(help_message)
self.reader.seek(offset)
self.reader.readline()
- self.reader.readline()
+ for _ in range(discard_lines):
+ self.reader.readline()
self.line = self.reader.readline()
- def parse_syscall(self):
+ def parse_desc_syscall(self):
self.seek_to('* DOC: eBPF Syscall Commands',
'Could not find start of eBPF syscall descriptions list')
while True:
try:
command = self.parse_element()
self.commands.append(command)
+ self.desc_syscalls.append(command.proto)
+
except NoSyscallCommandFound:
break
- def parse_helpers(self):
+ def parse_enum_syscall(self):
+ self.seek_to('enum bpf_cmd {',
+ 'Could not find start of bpf_cmd enum', 0)
+ # Searches for either one or more BPF\w+ enums
+ bpf_p = re.compile('\s*(BPF\w+)+')
+ # Searches for an enum entry assigned to another entry,
+ # for e.g. BPF_PROG_RUN = BPF_PROG_TEST_RUN, which is
+ # not documented hence should be skipped in check to
+ # determine if the right number of syscalls are documented
+ assign_p = re.compile('\s*(BPF\w+)\s*=\s*(BPF\w+)')
+ bpf_cmd_str = ''
+ while True:
+ capture = assign_p.match(self.line)
+ if capture:
+ # Skip line if an enum entry is assigned to another entry
+ self.line = self.reader.readline()
+ continue
+ capture = bpf_p.match(self.line)
+ if capture:
+ bpf_cmd_str += self.line
+ else:
+ break
+ self.line = self.reader.readline()
+ # Find the number of occurences of BPF\w+
+ self.enum_syscalls = re.findall('(BPF\w+)+', bpf_cmd_str)
+
+ def parse_desc_helpers(self):
self.seek_to('* Start of BPF helper function descriptions:',
'Could not find start of eBPF helper descriptions list')
while True:
try:
helper = self.parse_helper()
self.helpers.append(helper)
+ proto = helper.proto_break_down()
+ self.desc_unique_helpers.add(proto['name'])
except NoHelperFound:
break
+ def parse_define_helpers(self):
+ # Parse the number of FN(...) in #define __BPF_FUNC_MAPPER to compare
+ # later with the number of unique function names present in description.
+ # Note: seek_to(..) discards the first line below the target search text,
+ # resulting in FN(unspec) being skipped and not added to self.define_unique_helpers.
+ self.seek_to('#define __BPF_FUNC_MAPPER(FN)',
+ 'Could not find start of eBPF helper definition list')
+ # Searches for either one or more FN(\w+) defines or a backslash for newline
+ p = re.compile('\s*(FN\(\w+\))+|\\\\')
+ fn_defines_str = ''
+ while True:
+ capture = p.match(self.line)
+ if capture:
+ fn_defines_str += self.line
+ else:
+ break
+ self.line = self.reader.readline()
+ # Find the number of occurences of FN(\w+)
+ self.define_unique_helpers = re.findall('FN\(\w+\)', fn_defines_str)
+
def run(self):
- self.parse_syscall()
- self.parse_helpers()
+ self.parse_desc_syscall()
+ self.parse_enum_syscall()
+ self.parse_desc_helpers()
+ self.parse_define_helpers()
self.reader.close()
###############################################################################
self.print_one(elem)
self.print_footer()
+ def elem_number_check(self, desc_unique_elem, define_unique_elem, type, instance):
+ """
+ Checks the number of helpers/syscalls documented within the header file
+ description with those defined as part of enum/macro and raise an
+ Exception if they don't match.
+ """
+ nr_desc_unique_elem = len(desc_unique_elem)
+ nr_define_unique_elem = len(define_unique_elem)
+ if nr_desc_unique_elem != nr_define_unique_elem:
+ exception_msg = '''
+The number of unique %s in description (%d) doesn\'t match the number of unique %s defined in %s (%d)
+''' % (type, nr_desc_unique_elem, type, instance, nr_define_unique_elem)
+ if nr_desc_unique_elem < nr_define_unique_elem:
+ # Function description is parsed until no helper is found (which can be due to
+ # misformatting). Hence, only print the first missing/misformatted helper/enum.
+ exception_msg += '''
+The description for %s is not present or formatted correctly.
+''' % (define_unique_elem[nr_desc_unique_elem])
+ raise Exception(exception_msg)
class PrinterRST(Printer):
"""
print('')
-
class PrinterHelpersRST(PrinterRST):
"""
A printer for dumping collected information about helpers as a ReStructured
"""
def __init__(self, parser):
self.elements = parser.helpers
+ self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER')
def print_header(self):
header = '''\
"""
def __init__(self, parser):
self.elements = parser.commands
+ self.elem_number_check(parser.desc_syscalls, parser.enum_syscalls, 'syscall', 'bpf_cmd')
def print_header(self):
header = '''\
"""
def __init__(self, parser):
self.elements = parser.helpers
+ self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER')
type_fwds = [
'struct bpf_fib_lookup',
int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
if (rc)
- return -EPERM;
+ return rc;
#ifdef CONFIG_CGROUP_DEVICE
return devcgroup_legacy_check_permission(type, major, minor, access);
equal_fn_for_key_as_id, NULL);
btf_map_table = hashmap__new(hash_fn_for_key_as_id,
equal_fn_for_key_as_id, NULL);
- if (!btf_prog_table || !btf_map_table) {
+ if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) {
hashmap__free(btf_prog_table);
hashmap__free(btf_map_table);
if (fd >= 0)
const char *attach_flags_str,
int level)
{
+ char prog_name[MAX_PROG_FULL_NAME];
struct bpf_prog_info info = {};
__u32 info_len = sizeof(info);
int prog_fd;
return -1;
}
+ get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name));
if (json_output) {
jsonw_start_object(json_wtr);
jsonw_uint_field(json_wtr, "id", info.id);
jsonw_uint_field(json_wtr, "attach_type", attach_type);
jsonw_string_field(json_wtr, "attach_flags",
attach_flags_str);
- jsonw_string_field(json_wtr, "name", info.name);
+ jsonw_string_field(json_wtr, "name", prog_name);
jsonw_end_object(json_wtr);
} else {
printf("%s%-8u ", level ? " " : "", info.id);
printf("%-15s", attach_type_name[attach_type]);
else
printf("type %-10u", attach_type);
- printf(" %-15s %-15s\n", attach_flags_str, info.name);
+ printf(" %-15s %-15s\n", attach_flags_str, prog_name);
}
close(prog_fd);
#include <bpf/bpf.h>
#include <bpf/hashmap.h>
#include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
+#include <bpf/btf.h>
#include "main.h"
return names[type];
}
+void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
+ char *name_buff, size_t buff_len)
+{
+ const char *prog_name = prog_info->name;
+ const struct btf_type *func_type;
+ const struct bpf_func_info finfo;
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ struct btf *prog_btf = NULL;
+
+ if (buff_len <= BPF_OBJ_NAME_LEN ||
+ strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1)
+ goto copy_name;
+
+ if (!prog_info->btf_id || prog_info->nr_func_info == 0)
+ goto copy_name;
+
+ info.nr_func_info = 1;
+ info.func_info_rec_size = prog_info->func_info_rec_size;
+ if (info.func_info_rec_size > sizeof(finfo))
+ info.func_info_rec_size = sizeof(finfo);
+ info.func_info = ptr_to_u64(&finfo);
+
+ if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len))
+ goto copy_name;
+
+ prog_btf = btf__load_from_kernel_by_id(info.btf_id);
+ if (!prog_btf)
+ goto copy_name;
+
+ func_type = btf__type_by_id(prog_btf, finfo.type_id);
+ if (!func_type || !btf_is_func(func_type))
+ goto copy_name;
+
+ prog_name = btf__name_by_offset(prog_btf, func_type->name_off);
+
+copy_name:
+ snprintf(name_buff, buff_len, "%s", prog_name);
+
+ if (prog_btf)
+ btf__free(prog_btf);
+}
+
int get_fd_type(int fd)
{
char path[PATH_MAX];
/* only generate definitions for memory-mapped internal maps */
if (!bpf_map__is_internal(map))
continue;
- if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+ if (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE))
continue;
if (!get_map_ident(map, map_ident, sizeof(map_ident)))
if (!get_map_ident(map, ident, sizeof(ident)))
continue;
if (bpf_map__is_internal(map) &&
- (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+ (bpf_map__map_flags(map) & BPF_F_MMAPABLE))
printf("\tmunmap(skel->%1$s, %2$zd);\n",
ident, bpf_map_mmap_sz(map));
codegen("\
continue;
if (!bpf_map__is_internal(map) ||
- !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+ !(bpf_map__map_flags(map) & BPF_F_MMAPABLE))
continue;
codegen("\
continue;
if (!bpf_map__is_internal(map) ||
- !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+ !(bpf_map__map_flags(map) & BPF_F_MMAPABLE))
continue;
- if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG)
+ if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG)
mmap_flags = "PROT_READ";
else
mmap_flags = "PROT_READ | PROT_WRITE";
s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
if (!s) \n\
goto err; \n\
- obj->skeleton = s; \n\
\n\
s->sz = sizeof(*s); \n\
s->name = \"%1$s\"; \n\
i, bpf_map__name(map), i, ident);
/* memory-mapped internal maps */
if (bpf_map__is_internal(map) &&
- (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) {
+ (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) {
printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n",
i, ident);
}
\n\
s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\
\n\
+ obj->skeleton = s; \n\
return 0; \n\
err: \n\
bpf_object__destroy_skeleton(s); \n\
/* Copyright (C) 2020 Facebook */
#include <errno.h>
+#include <linux/err.h>
#include <net/if.h>
#include <stdio.h>
#include <unistd.h>
if (show_pinned) {
link_table = hashmap__new(hash_fn_for_key_as_id,
equal_fn_for_key_as_id, NULL);
- if (!link_table) {
+ if (IS_ERR(link_table)) {
p_err("failed to create hashmap for pinned paths");
return -1;
}
}
if (!legacy_libbpf) {
- ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+ enum libbpf_strict_mode mode;
+
+ /* Allow legacy map definitions for skeleton generation.
+ * It will still be rejected if users use LIBBPF_STRICT_ALL
+ * mode for loading generated skeleton.
+ */
+ mode = (__LIBBPF_STRICT_LAST - 1) & ~LIBBPF_STRICT_MAP_DEFINITIONS;
+ ret = libbpf_set_strict_mode(mode);
if (ret)
p_err("failed to enable libbpf strict mode: %d", ret);
}
int cmd_select(const struct cmd *cmds, int argc, char **argv,
int (*help)(int argc, char **argv));
+#define MAX_PROG_FULL_NAME 128
+void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
+ char *name_buff, size_t buff_len);
+
int get_fd_type(int fd);
const char *get_fd_type_name(enum bpf_obj_type type);
char *get_fdinfo(int fd, const char *key);
if (show_pinned) {
map_table = hashmap__new(hash_fn_for_key_as_id,
equal_fn_for_key_as_id, NULL);
- if (!map_table) {
+ if (IS_ERR(map_table)) {
p_err("failed to create hashmap for pinned paths");
return -1;
}
if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD)
flags |= XDP_FLAGS_HW_MODE;
- return bpf_set_link_xdp_fd(ifindex, progfd, flags);
+ return bpf_xdp_attach(ifindex, progfd, flags, NULL);
}
static int do_attach(int argc, char **argv)
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
/* Copyright (C) 2020 Facebook */
#include <errno.h>
+#include <linux/err.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
libbpf_print_fn_t default_print;
*map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL);
- if (!*map) {
+ if (IS_ERR(*map)) {
p_err("failed to create hashmap for PID references");
return -1;
}
free(value);
}
-static void print_prog_header_json(struct bpf_prog_info *info)
+static void print_prog_header_json(struct bpf_prog_info *info, int fd)
{
+ char prog_name[MAX_PROG_FULL_NAME];
+
jsonw_uint_field(json_wtr, "id", info->id);
if (info->type < ARRAY_SIZE(prog_type_name))
jsonw_string_field(json_wtr, "type",
else
jsonw_uint_field(json_wtr, "type", info->type);
- if (*info->name)
- jsonw_string_field(json_wtr, "name", info->name);
+ if (*info->name) {
+ get_prog_full_name(info, fd, prog_name, sizeof(prog_name));
+ jsonw_string_field(json_wtr, "name", prog_name);
+ }
jsonw_name(json_wtr, "tag");
jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"",
char *memlock;
jsonw_start_object(json_wtr);
- print_prog_header_json(info);
+ print_prog_header_json(info, fd);
print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
if (info->load_time) {
jsonw_end_object(json_wtr);
}
-static void print_prog_header_plain(struct bpf_prog_info *info)
+static void print_prog_header_plain(struct bpf_prog_info *info, int fd)
{
+ char prog_name[MAX_PROG_FULL_NAME];
+
printf("%u: ", info->id);
if (info->type < ARRAY_SIZE(prog_type_name))
printf("%s ", prog_type_name[info->type]);
else
printf("type %u ", info->type);
- if (*info->name)
- printf("name %s ", info->name);
+ if (*info->name) {
+ get_prog_full_name(info, fd, prog_name, sizeof(prog_name));
+ printf("name %s ", prog_name);
+ }
printf("tag ");
fprint_hex(stdout, info->tag, BPF_TAG_SIZE, "");
{
char *memlock;
- print_prog_header_plain(info);
+ print_prog_header_plain(info, fd);
if (info->load_time) {
char buf[32];
if (show_pinned) {
prog_table = hashmap__new(hash_fn_for_key_as_id,
equal_fn_for_key_as_id, NULL);
- if (!prog_table) {
+ if (IS_ERR(prog_table)) {
p_err("failed to create hashmap for pinned paths");
return -1;
}
if (json_output && nb_fds > 1) {
jsonw_start_object(json_wtr); /* prog object */
- print_prog_header_json(&info);
+ print_prog_header_json(&info, fds[i]);
jsonw_name(json_wtr, "insns");
} else if (nb_fds > 1) {
- print_prog_header_plain(&info);
+ print_prog_header_plain(&info, fds[i]);
}
err = prog_dump(&info, mode, filepath, opcodes, visual, linum);
static int do_register(int argc, char **argv)
{
LIBBPF_OPTS(bpf_object_open_opts, open_opts);
- const struct bpf_map_def *def;
struct bpf_map_info info = {};
__u32 info_len = sizeof(info);
int nr_errs = 0, nr_maps = 0;
}
bpf_object__for_each_map(map, obj) {
- def = bpf_map__def(map);
- if (def->type != BPF_MAP_TYPE_STRUCT_OPS)
+ if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS)
continue;
link = bpf_map__attach_struct_ops(map);
ARCH = $(HOSTARCH)
RM ?= rm
CROSS_COMPILE =
+CFLAGS := $(KBUILD_HOSTCFLAGS)
+LDFLAGS := $(KBUILD_HOSTLDFLAGS)
OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/
$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT)
$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \
- DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+ DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \
$(abspath $@) install_headers
-CFLAGS := -g \
+CFLAGS += -g \
-I$(srctree)/tools/include \
-I$(srctree)/tools/include/uapi \
-I$(LIBBPF_INCLUDE) \
* *ctx_out*, *data_in* and *data_out* must be NULL.
* *repeat* must be zero.
*
+ * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN.
+ *
* Return
* Returns zero on success. On error, -1 is returned and *errno*
* is set appropriately.
*/
#define BPF_F_SLEEPABLE (1U << 4)
+/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program
+ * fully support xdp frags.
+ */
+#define BPF_F_XDP_HAS_FRAGS (1U << 5)
+
/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
* the following extensions:
*
* 0 on success, or a negative error in case of failure.
*
* u64 bpf_get_current_pid_tgid(void)
+ * Description
+ * Get the current pid and tgid.
* Return
* A 64-bit integer containing the current tgid and pid, and
* created as such:
* *current_task*\ **->pid**.
*
* u64 bpf_get_current_uid_gid(void)
+ * Description
+ * Get the current uid and gid.
* Return
* A 64-bit integer containing the current GID and UID, and
* created as such: *current_gid* **<< 32 \|** *current_uid*.
* The 32-bit hash.
*
* u64 bpf_get_current_task(void)
+ * Description
+ * Get the current task.
* Return
* A pointer to the current task struct.
*
* indicate that the hash is outdated and to trigger a
* recalculation the next time the kernel tries to access this
* hash or when the **bpf_get_hash_recalc**\ () helper is called.
+ * Return
+ * void.
*
* long bpf_get_numa_node_id(void)
* Description
* A 8-byte long unique number or 0 if *sk* is NULL.
*
* u32 bpf_get_socket_uid(struct sk_buff *skb)
+ * Description
+ * Get the owner UID of the socked associated to *skb*.
* Return
* The owner UID of the socket associated to *skb*. If the socket
* is **NULL**, or if it is not a full socket (i.e. if it is a
* The id is returned or 0 in case the id could not be retrieved.
*
* u64 bpf_get_current_cgroup_id(void)
+ * Description
+ * Get the current cgroup id based on the cgroup within which
+ * the current task is running.
* Return
* A 64-bit integer containing the current cgroup id based
* on the cgroup within which the current task is running.
*
* Return
* The number of arguments of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * The syscall's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md)
+ * Description
+ * Get the total size of a given xdp buff (linear and paged area)
+ * Return
+ * The total size of a given xdp buffer.
+ *
+ * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * This helper is provided as an easy way to load data from a
+ * xdp buffer. It can be used to load *len* bytes from *offset* from
+ * the frame associated to *xdp_md*, into the buffer pointed by
+ * *buf*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
+ *
+ * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len)
+ * Description
+ * Store *len* bytes from buffer *buf* into the frame
+ * associated to *xdp_md*, at *offset*.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
FN(get_func_arg), \
FN(get_func_ret), \
FN(get_func_arg_cnt), \
+ FN(get_retval), \
+ FN(set_retval), \
+ FN(xdp_get_buff_len), \
+ FN(xdp_load_bytes), \
+ FN(xdp_store_bytes), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
.flags = flags,
);
- return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts);
+ return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts);
}
-int bpf_prog_attach_xattr(int prog_fd, int target_fd,
+int bpf_prog_attach_opts(int prog_fd, int target_fd,
enum bpf_attach_type type,
const struct bpf_prog_attach_opts *opts)
{
return libbpf_err_errno(ret);
}
+__attribute__((alias("bpf_prog_attach_opts")))
+int bpf_prog_attach_xattr(int prog_fd, int target_fd,
+ enum bpf_attach_type type,
+ const struct bpf_prog_attach_opts *opts);
+
int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
{
union bpf_attr attr;
LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
enum bpf_attach_type type, unsigned int flags);
+LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd,
+ enum bpf_attach_type type,
+ const struct bpf_prog_attach_opts *opts);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead")
LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd,
enum bpf_attach_type type,
const struct bpf_prog_attach_opts *opts);
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
-};
+} __attribute__((deprecated("use BTF-defined maps in .maps section")));
enum libbpf_pin_type {
LIBBPF_PIN_NONE,
struct btf_pipe {
const struct btf *src;
struct btf *dst;
+ struct hashmap *str_off_map; /* map string offsets from src to dst */
};
static int btf_rewrite_str(__u32 *str_off, void *ctx)
{
struct btf_pipe *p = ctx;
- int off;
+ void *mapped_off;
+ int off, err;
if (!*str_off) /* nothing to do for empty strings */
return 0;
+ if (p->str_off_map &&
+ hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) {
+ *str_off = (__u32)(long)mapped_off;
+ return 0;
+ }
+
off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off));
if (off < 0)
return off;
+ /* Remember string mapping from src to dst. It avoids
+ * performing expensive string comparisons.
+ */
+ if (p->str_off_map) {
+ err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off);
+ if (err)
+ return err;
+ }
+
*str_off = off;
return 0;
}
return 0;
}
+static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx);
+static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx);
+
int btf__add_btf(struct btf *btf, const struct btf *src_btf)
{
struct btf_pipe p = { .src = src_btf, .dst = btf };
if (!off)
return libbpf_err(-ENOMEM);
+ /* Map the string offsets from src_btf to the offsets from btf to improve performance */
+ p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL);
+ if (IS_ERR(p.str_off_map))
+ return libbpf_err(-ENOMEM);
+
/* bulk copy types data for all types from src_btf */
memcpy(t, src_btf->types_data, data_sz);
btf->hdr->str_off += data_sz;
btf->nr_types += cnt;
+ hashmap__free(p.str_off_map);
+
/* return type ID of the first added BTF type */
return btf->start_id + btf->nr_types - cnt;
err_out:
* wasn't modified, so doesn't need restoring, see big comment above */
btf->hdr->str_len = old_strs_len;
+ hashmap__free(p.str_off_map);
+
return libbpf_err(err);
}
const struct btf_dump_type_data_opts *opts);
/*
- * A set of helpers for easier BTF types handling
+ * A set of helpers for easier BTF types handling.
+ *
+ * The inline functions below rely on constants from the kernel headers which
+ * may not be available for applications including this header file. To avoid
+ * compilation errors, we define all the constants here that were added after
+ * the initial introduction of the BTF_KIND* constants.
*/
+#ifndef BTF_KIND_FUNC
+#define BTF_KIND_FUNC 12 /* Function */
+#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */
+#endif
+#ifndef BTF_KIND_VAR
+#define BTF_KIND_VAR 14 /* Variable */
+#define BTF_KIND_DATASEC 15 /* Section */
+#endif
+#ifndef BTF_KIND_FLOAT
+#define BTF_KIND_FLOAT 16 /* Floating point */
+#endif
+/* The kernel header switched to enums, so these two were never #defined */
+#define BTF_KIND_DECL_TAG 17 /* Decl Tag */
+#define BTF_KIND_TYPE_TAG 18 /* Type Tag */
+
static inline __u16 btf_kind(const struct btf_type *t)
{
return BTF_INFO_KIND(t->info);
void hashmap__free(struct hashmap *map)
{
- if (!map)
+ if (IS_ERR_OR_NULL(map))
return;
hashmap__clear(map);
return true;
}
-
SEC_SLEEPABLE = 8,
/* allow non-strict prefix matching */
SEC_SLOPPY_PFX = 16,
+ /* BPF program support non-linear XDP buffer */
+ SEC_XDP_FRAGS = 32,
};
struct bpf_sec_def {
if (obj->efile.maps_shndx < 0)
return 0;
+ if (libbpf_mode & LIBBPF_STRICT_MAP_DEFINITIONS) {
+ pr_warn("legacy map definitions in SEC(\"maps\") are not supported\n");
+ return -EOPNOTSUPP;
+ }
+
if (!symbols)
return -EINVAL;
return -LIBBPF_ERRNO__FORMAT;
}
+ pr_warn("map '%s' (legacy): legacy map definitions are deprecated, use BTF-defined maps instead\n", map_name);
+
if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) {
pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
return -ENOTSUP;
return 0;
if (!bpf_map__is_internal(map)) {
+ pr_warn("Use of BPF_ANNOTATE_KV_PAIR is deprecated, use BTF-defined maps in .maps section instead\n");
ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size,
def->value_size, &key_type_id,
&value_type_id);
if (def & SEC_SLEEPABLE)
opts->prog_flags |= BPF_F_SLEEPABLE;
+ if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS))
+ opts->prog_flags |= BPF_F_XDP_HAS_FRAGS;
+
if ((prog->type == BPF_PROG_TYPE_TRACING ||
prog->type == BPF_PROG_TYPE_LSM ||
prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm),
SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter),
SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE),
+ SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS),
SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE),
+ SEC_DEF("xdp.frags/cpumap", XDP, BPF_XDP_CPUMAP, SEC_XDP_FRAGS),
SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE),
+ SEC_DEF("xdp.frags", XDP, BPF_XDP, SEC_XDP_FRAGS),
SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX),
SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX),
void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s)
{
+ if (!s)
+ return;
+
if (s->progs)
bpf_object__detach_skeleton(s);
if (s->obj)
LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
/* get map definition */
-LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead")
+const struct bpf_map_def *bpf_map__def(const struct bpf_map *map);
/* get map name */
LIBBPF_API const char *bpf_map__name(const struct bpf_map *map);
/* get/set map type */
};
#define bpf_xdp_set_link_opts__last_field old_fd
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead")
LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead")
LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
const struct bpf_xdp_set_link_opts *opts);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead")
LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags);
+LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead")
LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
size_t info_size, __u32 flags);
+struct bpf_xdp_attach_opts {
+ size_t sz;
+ int old_prog_fd;
+ size_t :0;
+};
+#define bpf_xdp_attach_opts__last_field old_prog_fd
+
+struct bpf_xdp_query_opts {
+ size_t sz;
+ __u32 prog_id; /* output */
+ __u32 drv_prog_id; /* output */
+ __u32 hw_prog_id; /* output */
+ __u32 skb_prog_id; /* output */
+ __u8 attach_mode; /* output */
+ size_t :0;
+};
+#define bpf_xdp_query_opts__last_field attach_mode
+
+LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
+ const struct bpf_xdp_attach_opts *opts);
+LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags,
+ const struct bpf_xdp_attach_opts *opts);
+LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts);
+LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id);
+
/* TC related API */
enum bpf_tc_attach_point {
BPF_TC_INGRESS = 1 << 0,
bpf_link_create;
bpf_link_update;
bpf_map__set_initial_value;
+ bpf_prog_attach_opts;
bpf_program__attach_cgroup;
bpf_program__attach_lsm;
bpf_program__is_lsm;
bpf_program__log_level;
bpf_program__set_log_buf;
bpf_program__set_log_level;
+ bpf_xdp_attach;
+ bpf_xdp_detach;
+ bpf_xdp_query;
+ bpf_xdp_query_id;
libbpf_probe_bpf_helper;
libbpf_probe_bpf_map_type;
libbpf_probe_bpf_prog_type;
* operation.
*/
LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10,
+ /*
+ * Error out on any SEC("maps") map definition, which are deprecated
+ * in favor of BTF-defined map definitions in SEC(".maps").
+ */
+ LIBBPF_STRICT_MAP_DEFINITIONS = 0x20,
__LIBBPF_STRICT_LAST,
};
return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
}
+int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
+{
+ int old_prog_fd, err;
+
+ if (!OPTS_VALID(opts, bpf_xdp_attach_opts))
+ return libbpf_err(-EINVAL);
+
+ old_prog_fd = OPTS_GET(opts, old_prog_fd, 0);
+ if (old_prog_fd)
+ flags |= XDP_FLAGS_REPLACE;
+ else
+ old_prog_fd = -1;
+
+ err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags);
+ return libbpf_err(err);
+}
+
+int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts)
+{
+ return bpf_xdp_attach(ifindex, -1, flags, opts);
+}
+
int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags,
const struct bpf_xdp_set_link_opts *opts)
{
return 0;
}
-int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
- size_t info_size, __u32 flags)
+int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
{
- struct xdp_id_md xdp_id = {};
- __u32 mask;
- int ret;
struct libbpf_nla_req req = {
.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
.nh.nlmsg_type = RTM_GETLINK,
.nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
.ifinfo.ifi_family = AF_PACKET,
};
+ struct xdp_id_md xdp_id = {};
+ int err;
- if (flags & ~XDP_FLAGS_MASK || !info_size)
+ if (!OPTS_VALID(opts, bpf_xdp_query_opts))
+ return libbpf_err(-EINVAL);
+
+ if (xdp_flags & ~XDP_FLAGS_MASK)
return libbpf_err(-EINVAL);
/* Check whether the single {HW,DRV,SKB} mode is set */
- flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE);
- mask = flags - 1;
- if (flags && flags & mask)
+ xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE;
+ if (xdp_flags & (xdp_flags - 1))
return libbpf_err(-EINVAL);
xdp_id.ifindex = ifindex;
- xdp_id.flags = flags;
+ xdp_id.flags = xdp_flags;
- ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+ err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
get_xdp_info, &xdp_id);
- if (!ret) {
- size_t sz = min(info_size, sizeof(xdp_id.info));
+ if (err)
+ return libbpf_err(err);
- memcpy(info, &xdp_id.info, sz);
- memset((void *) info + sz, 0, info_size - sz);
- }
+ OPTS_SET(opts, prog_id, xdp_id.info.prog_id);
+ OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id);
+ OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id);
+ OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
+ OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
- return libbpf_err(ret);
+ return 0;
}
-static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags)
+int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info,
+ size_t info_size, __u32 flags)
{
- flags &= XDP_FLAGS_MODES;
+ LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+ size_t sz;
+ int err;
+
+ if (!info_size)
+ return libbpf_err(-EINVAL);
- if (info->attach_mode != XDP_ATTACHED_MULTI && !flags)
- return info->prog_id;
- if (flags & XDP_FLAGS_DRV_MODE)
- return info->drv_prog_id;
- if (flags & XDP_FLAGS_HW_MODE)
- return info->hw_prog_id;
- if (flags & XDP_FLAGS_SKB_MODE)
- return info->skb_prog_id;
+ err = bpf_xdp_query(ifindex, flags, &opts);
+ if (err)
+ return libbpf_err(err);
+
+ /* struct xdp_link_info field layout matches struct bpf_xdp_query_opts
+ * layout after sz field
+ */
+ sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode));
+ memcpy(info, &opts.prog_id, sz);
+ memset((void *)info + sz, 0, info_size - sz);
return 0;
}
-int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id)
{
- struct xdp_link_info info;
+ LIBBPF_OPTS(bpf_xdp_query_opts, opts);
int ret;
- ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags);
- if (!ret)
- *prog_id = get_xdp_id(&info, flags);
+ ret = bpf_xdp_query(ifindex, flags, &opts);
+ if (ret)
+ return libbpf_err(ret);
+
+ flags &= XDP_FLAGS_MODES;
- return libbpf_err(ret);
+ if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags)
+ *prog_id = opts.prog_id;
+ else if (flags & XDP_FLAGS_DRV_MODE)
+ *prog_id = opts.drv_prog_id;
+ else if (flags & XDP_FLAGS_HW_MODE)
+ *prog_id = opts.hw_prog_id;
+ else if (flags & XDP_FLAGS_SKB_MODE)
+ *prog_id = opts.skb_prog_id;
+ else
+ *prog_id = 0;
+
+ return 0;
+}
+
+
+int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags)
+{
+ return bpf_xdp_query_id(ifindex, flags, prog_id);
}
typedef int (*qdisc_config_t)(struct libbpf_nla_req *req);
{
struct bpf_map_op *op;
const char *map_name = bpf_map__name(map);
- const struct bpf_map_def *def = bpf_map__def(map);
- if (IS_ERR(def)) {
- pr_debug("Unable to get map definition from '%s'\n",
- map_name);
+ if (!map) {
+ pr_debug("Map '%s' is invalid\n", map_name);
return -BPF_LOADER_ERRNO__INTERNAL;
}
- if (def->type != BPF_MAP_TYPE_ARRAY) {
+ if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) {
pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
map_name);
return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
}
- if (def->key_size < sizeof(unsigned int)) {
+ if (bpf_map__key_size(map) < sizeof(unsigned int)) {
pr_debug("Map %s has incorrect key size\n", map_name);
return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
}
- switch (def->value_size) {
+ switch (bpf_map__value_size(map)) {
case 1:
case 2:
case 4:
struct parse_events_term *term,
struct evlist *evlist)
{
- const struct bpf_map_def *def;
struct bpf_map_op *op;
const char *map_name = bpf_map__name(map);
struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str);
return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
}
- def = bpf_map__def(map);
- if (IS_ERR(def)) {
- pr_debug("Unable to get map definition from '%s'\n",
- map_name);
- return PTR_ERR(def);
+ if (!map) {
+ pr_debug("Map '%s' is invalid\n", map_name);
+ return PTR_ERR(map);
}
/*
* No need to check key_size and value_size:
* kernel has already checked them.
*/
- if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+ if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
map_name);
return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
const char *map_name)
{
struct parse_events_array *array = &term->array;
- const struct bpf_map_def *def;
unsigned int i;
if (!array->nr_ranges)
return -BPF_LOADER_ERRNO__INTERNAL;
}
- def = bpf_map__def(map);
- if (IS_ERR(def)) {
- pr_debug("ERROR: Unable to get map definition from '%s'\n",
- map_name);
+ if (!map) {
+ pr_debug("Map '%s' is invalid\n", map_name);
return -BPF_LOADER_ERRNO__INTERNAL;
}
size_t length = array->ranges[i].length;
unsigned int idx = start + length - 1;
- if (idx >= def->max_entries) {
+ if (idx >= bpf_map__max_entries(map)) {
pr_debug("ERROR: index %d too large\n", idx);
return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
}
}
typedef int (*map_config_func_t)(const char *name, int map_fd,
- const struct bpf_map_def *pdef,
+ const struct bpf_map *map,
struct bpf_map_op *op,
void *pkey, void *arg);
static int
foreach_key_array_all(map_config_func_t func,
void *arg, const char *name,
- int map_fd, const struct bpf_map_def *pdef,
+ int map_fd, const struct bpf_map *map,
struct bpf_map_op *op)
{
unsigned int i;
int err;
- for (i = 0; i < pdef->max_entries; i++) {
- err = func(name, map_fd, pdef, op, &i, arg);
+ for (i = 0; i < bpf_map__max_entries(map); i++) {
+ err = func(name, map_fd, map, op, &i, arg);
if (err) {
pr_debug("ERROR: failed to insert value to %s[%u]\n",
name, i);
static int
foreach_key_array_ranges(map_config_func_t func, void *arg,
const char *name, int map_fd,
- const struct bpf_map_def *pdef,
+ const struct bpf_map *map,
struct bpf_map_op *op)
{
unsigned int i, j;
for (j = 0; j < length; j++) {
unsigned int idx = start + j;
- err = func(name, map_fd, pdef, op, &idx, arg);
+ err = func(name, map_fd, map, op, &idx, arg);
if (err) {
pr_debug("ERROR: failed to insert value to %s[%u]\n",
name, idx);
map_config_func_t func,
void *arg)
{
- int err, map_fd;
+ int err, map_fd, type;
struct bpf_map_op *op;
- const struct bpf_map_def *def;
const char *name = bpf_map__name(map);
struct bpf_map_priv *priv = bpf_map__priv(map);
return 0;
}
- def = bpf_map__def(map);
- if (IS_ERR(def)) {
- pr_debug("ERROR: failed to get definition from map %s\n", name);
+ if (!map) {
+ pr_debug("Map '%s' is invalid\n", name);
return -BPF_LOADER_ERRNO__INTERNAL;
}
map_fd = bpf_map__fd(map);
return map_fd;
}
+ type = bpf_map__type(map);
list_for_each_entry(op, &priv->ops_list, list) {
- switch (def->type) {
+ switch (type) {
case BPF_MAP_TYPE_ARRAY:
case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
switch (op->key_type) {
case BPF_MAP_KEY_ALL:
err = foreach_key_array_all(func, arg, name,
- map_fd, def, op);
+ map_fd, map, op);
break;
case BPF_MAP_KEY_RANGES:
err = foreach_key_array_ranges(func, arg, name,
- map_fd, def,
- op);
+ map_fd, map, op);
break;
default:
pr_debug("ERROR: keytype for map '%s' invalid\n",
static int
apply_obj_config_map_for_key(const char *name, int map_fd,
- const struct bpf_map_def *pdef,
+ const struct bpf_map *map,
struct bpf_map_op *op,
void *pkey, void *arg __maybe_unused)
{
switch (op->op_type) {
case BPF_MAP_OP_SET_VALUE:
err = apply_config_value_for_key(map_fd, pkey,
- pdef->value_size,
+ bpf_map__value_size(map),
op->v.value);
break;
case BPF_MAP_OP_SET_EVSEL:
#include <stdlib.h>
#include <unistd.h>
-static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def)
+static bool bpf_map__is_per_cpu(enum bpf_map_type type)
{
- return def->type == BPF_MAP_TYPE_PERCPU_HASH ||
- def->type == BPF_MAP_TYPE_PERCPU_ARRAY ||
- def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
- def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
+ return type == BPF_MAP_TYPE_PERCPU_HASH ||
+ type == BPF_MAP_TYPE_PERCPU_ARRAY ||
+ type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
+ type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE;
}
-static void *bpf_map_def__alloc_value(const struct bpf_map_def *def)
+static void *bpf_map__alloc_value(const struct bpf_map *map)
{
- if (bpf_map_def__is_per_cpu(def))
- return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF));
+ if (bpf_map__is_per_cpu(bpf_map__type(map)))
+ return malloc(round_up(bpf_map__value_size(map), 8) *
+ sysconf(_SC_NPROCESSORS_CONF));
- return malloc(def->value_size);
+ return malloc(bpf_map__value_size(map));
}
int bpf_map__fprintf(struct bpf_map *map, FILE *fp)
{
- const struct bpf_map_def *def = bpf_map__def(map);
void *prev_key = NULL, *key, *value;
int fd = bpf_map__fd(map), err;
int printed = 0;
if (fd < 0)
return fd;
- if (IS_ERR(def))
- return PTR_ERR(def);
+ if (!map)
+ return PTR_ERR(map);
err = -ENOMEM;
- key = malloc(def->key_size);
+ key = malloc(bpf_map__key_size(map));
if (key == NULL)
goto out;
- value = bpf_map_def__alloc_value(def);
+ value = bpf_map__alloc_value(map);
if (value == NULL)
goto out_free_key;
BPF_GCC ?= $(shell command -v bpf-gcc;)
SAN_CFLAGS ?=
-CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \
+CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \
-I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \
-I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
LDFLAGS += $(SAN_CFLAGS)
MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
-BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
+BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \
-I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \
-I$(abspath $(OUTPUT)/../usr/include)
.write = bpf_testmod_test_write,
};
-BTF_SET_START(bpf_testmod_kfunc_ids)
+BTF_SET_START(bpf_testmod_check_kfunc_ids)
BTF_ID(func, bpf_testmod_test_mod_kfunc)
-BTF_SET_END(bpf_testmod_kfunc_ids)
+BTF_SET_END(bpf_testmod_check_kfunc_ids)
-static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set);
+static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = {
+ .owner = THIS_MODULE,
+ .check_set = &bpf_testmod_check_kfunc_ids,
+};
+
+extern int bpf_fentry_test1(int a);
static int bpf_testmod_init(void)
{
int ret;
- ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
- if (ret)
+ ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set);
+ if (ret < 0)
return ret;
- register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set);
- return 0;
+ if (bpf_fentry_test1(0) < 0)
+ return -EINVAL;
+ return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
}
static void bpf_testmod_exit(void)
{
- unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set);
return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
}
CONFIG_BLK_DEV_LOOP=y
CONFIG_FUNCTION_TRACER=y
CONFIG_DYNAMIC_FTRACE=y
+CONFIG_NETFILTER=y
+CONFIG_NF_DEFRAG_IPV4=y
+CONFIG_NF_DEFRAG_IPV6=y
+CONFIG_NF_CONNTRACK=y
+CONFIG_USERFAULTFD=y
// SPDX-License-Identifier: GPL-2.0
-#include <test_progs.h>
-#include "bind_perm.skel.h"
-
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdlib.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/capability.h>
+#include "test_progs.h"
+#include "bind_perm.skel.h"
+
static int duration;
+static int create_netns(void)
+{
+ if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+ return -1;
+
+ return 0;
+}
+
void try_bind(int family, int port, int expected_errno)
{
struct sockaddr_storage addr = {};
struct bind_perm *skel;
int cgroup_fd;
+ if (create_netns())
+ return;
+
cgroup_fd = test__join_cgroup("/bind_perm");
if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno))
return;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <test_progs.h>
+#include "bpf_iter_setsockopt_unix.skel.h"
+
+#define NR_CASES 5
+
+static int create_unix_socket(struct bpf_iter_setsockopt_unix *skel)
+{
+ struct sockaddr_un addr = {
+ .sun_family = AF_UNIX,
+ .sun_path = "",
+ };
+ socklen_t len;
+ int fd, err;
+
+ fd = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (!ASSERT_NEQ(fd, -1, "socket"))
+ return -1;
+
+ len = offsetof(struct sockaddr_un, sun_path);
+ err = bind(fd, (struct sockaddr *)&addr, len);
+ if (!ASSERT_OK(err, "bind"))
+ return -1;
+
+ len = sizeof(addr);
+ err = getsockname(fd, (struct sockaddr *)&addr, &len);
+ if (!ASSERT_OK(err, "getsockname"))
+ return -1;
+
+ memcpy(&skel->bss->sun_path, &addr.sun_path,
+ len - offsetof(struct sockaddr_un, sun_path));
+
+ return fd;
+}
+
+static void test_sndbuf(struct bpf_iter_setsockopt_unix *skel, int fd)
+{
+ socklen_t optlen;
+ int i, err;
+
+ for (i = 0; i < NR_CASES; i++) {
+ if (!ASSERT_NEQ(skel->data->sndbuf_getsockopt[i], -1,
+ "bpf_(get|set)sockopt"))
+ return;
+
+ err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF,
+ &(skel->data->sndbuf_setsockopt[i]),
+ sizeof(skel->data->sndbuf_setsockopt[i]));
+ if (!ASSERT_OK(err, "setsockopt"))
+ return;
+
+ optlen = sizeof(skel->bss->sndbuf_getsockopt_expected[i]);
+ err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF,
+ &(skel->bss->sndbuf_getsockopt_expected[i]),
+ &optlen);
+ if (!ASSERT_OK(err, "getsockopt"))
+ return;
+
+ if (!ASSERT_EQ(skel->data->sndbuf_getsockopt[i],
+ skel->bss->sndbuf_getsockopt_expected[i],
+ "bpf_(get|set)sockopt"))
+ return;
+ }
+}
+
+void test_bpf_iter_setsockopt_unix(void)
+{
+ struct bpf_iter_setsockopt_unix *skel;
+ int err, unix_fd, iter_fd;
+ char buf;
+
+ skel = bpf_iter_setsockopt_unix__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "open_and_load"))
+ return;
+
+ unix_fd = create_unix_socket(skel);
+ if (!ASSERT_NEQ(unix_fd, -1, "create_unix_server"))
+ goto destroy;
+
+ skel->links.change_sndbuf = bpf_program__attach_iter(skel->progs.change_sndbuf, NULL);
+ if (!ASSERT_OK_PTR(skel->links.change_sndbuf, "bpf_program__attach_iter"))
+ goto destroy;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(skel->links.change_sndbuf));
+ if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create"))
+ goto destroy;
+
+ while ((err = read(iter_fd, &buf, sizeof(buf))) == -1 &&
+ errno == EAGAIN)
+ ;
+ if (!ASSERT_OK(err, "read iter error"))
+ goto destroy;
+
+ test_sndbuf(skel, unix_fd);
+destroy:
+ bpf_iter_setsockopt_unix__destroy(skel);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <stdatomic.h>
+#include <test_progs.h>
+#include <sys/syscall.h>
+#include <linux/module.h>
+#include <linux/userfaultfd.h>
+
+#include "ksym_race.skel.h"
+#include "bpf_mod_race.skel.h"
+#include "kfunc_call_race.skel.h"
+
+/* This test crafts a race between btf_try_get_module and do_init_module, and
+ * checks whether btf_try_get_module handles the invocation for a well-formed
+ * but uninitialized module correctly. Unless the module has completed its
+ * initcalls, the verifier should fail the program load and return ENXIO.
+ *
+ * userfaultfd is used to trigger a fault in an fmod_ret program, and make it
+ * sleep, then the BPF program is loaded and the return value from verifier is
+ * inspected. After this, the userfaultfd is closed so that the module loading
+ * thread makes forward progress, and fmod_ret injects an error so that the
+ * module load fails and it is freed.
+ *
+ * If the verifier succeeded in loading the supplied program, it will end up
+ * taking reference to freed module, and trigger a crash when the program fd
+ * is closed later. This is true for both kfuncs and ksyms. In both cases,
+ * the crash is triggered inside bpf_prog_free_deferred, when module reference
+ * is finally released.
+ */
+
+struct test_config {
+ const char *str_open;
+ void *(*bpf_open_and_load)();
+ void (*bpf_destroy)(void *);
+};
+
+enum test_state {
+ _TS_INVALID,
+ TS_MODULE_LOAD,
+ TS_MODULE_LOAD_FAIL,
+};
+
+static _Atomic enum test_state state = _TS_INVALID;
+
+static int sys_finit_module(int fd, const char *param_values, int flags)
+{
+ return syscall(__NR_finit_module, fd, param_values, flags);
+}
+
+static int sys_delete_module(const char *name, unsigned int flags)
+{
+ return syscall(__NR_delete_module, name, flags);
+}
+
+static int load_module(const char *mod)
+{
+ int ret, fd;
+
+ fd = open("bpf_testmod.ko", O_RDONLY);
+ if (fd < 0)
+ return fd;
+
+ ret = sys_finit_module(fd, "", 0);
+ close(fd);
+ if (ret < 0)
+ return ret;
+ return 0;
+}
+
+static void *load_module_thread(void *p)
+{
+
+ if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail"))
+ atomic_store(&state, TS_MODULE_LOAD);
+ else
+ atomic_store(&state, TS_MODULE_LOAD_FAIL);
+ return p;
+}
+
+static int sys_userfaultfd(int flags)
+{
+ return syscall(__NR_userfaultfd, flags);
+}
+
+static int test_setup_uffd(void *fault_addr)
+{
+ struct uffdio_register uffd_register = {};
+ struct uffdio_api uffd_api = {};
+ int uffd;
+
+ uffd = sys_userfaultfd(O_CLOEXEC);
+ if (uffd < 0)
+ return -errno;
+
+ uffd_api.api = UFFD_API;
+ uffd_api.features = 0;
+ if (ioctl(uffd, UFFDIO_API, &uffd_api)) {
+ close(uffd);
+ return -1;
+ }
+
+ uffd_register.range.start = (unsigned long)fault_addr;
+ uffd_register.range.len = 4096;
+ uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) {
+ close(uffd);
+ return -1;
+ }
+ return uffd;
+}
+
+static void test_bpf_mod_race_config(const struct test_config *config)
+{
+ void *fault_addr, *skel_fail;
+ struct bpf_mod_race *skel;
+ struct uffd_msg uffd_msg;
+ pthread_t load_mod_thrd;
+ _Atomic int *blockingp;
+ int uffd, ret;
+
+ fault_addr = mmap(0, 4096, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration"))
+ return;
+
+ if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod"))
+ goto end_mmap;
+
+ skel = bpf_mod_race__open();
+ if (!ASSERT_OK_PTR(skel, "bpf_mod_kfunc_race__open"))
+ goto end_module;
+
+ skel->rodata->bpf_mod_race_config.tgid = getpid();
+ skel->rodata->bpf_mod_race_config.inject_error = -4242;
+ skel->rodata->bpf_mod_race_config.fault_addr = fault_addr;
+ if (!ASSERT_OK(bpf_mod_race__load(skel), "bpf_mod___load"))
+ goto end_destroy;
+ blockingp = (_Atomic int *)&skel->bss->bpf_blocking;
+
+ if (!ASSERT_OK(bpf_mod_race__attach(skel), "bpf_mod_kfunc_race__attach"))
+ goto end_destroy;
+
+ uffd = test_setup_uffd(fault_addr);
+ if (!ASSERT_GE(uffd, 0, "userfaultfd open + register address"))
+ goto end_destroy;
+
+ if (!ASSERT_OK(pthread_create(&load_mod_thrd, NULL, load_module_thread, NULL),
+ "load module thread"))
+ goto end_uffd;
+
+ /* Now, we either fail loading module, or block in bpf prog, spin to find out */
+ while (!atomic_load(&state) && !atomic_load(blockingp))
+ ;
+ if (!ASSERT_EQ(state, _TS_INVALID, "module load should block"))
+ goto end_join;
+ if (!ASSERT_EQ(*blockingp, 1, "module load blocked")) {
+ pthread_kill(load_mod_thrd, SIGKILL);
+ goto end_uffd;
+ }
+
+ /* We might have set bpf_blocking to 1, but may have not blocked in
+ * bpf_copy_from_user. Read userfaultfd descriptor to verify that.
+ */
+ if (!ASSERT_EQ(read(uffd, &uffd_msg, sizeof(uffd_msg)), sizeof(uffd_msg),
+ "read uffd block event"))
+ goto end_join;
+ if (!ASSERT_EQ(uffd_msg.event, UFFD_EVENT_PAGEFAULT, "read uffd event is pagefault"))
+ goto end_join;
+
+ /* We know that load_mod_thrd is blocked in the fmod_ret program, the
+ * module state is still MODULE_STATE_COMING because mod->init hasn't
+ * returned. This is the time we try to load a program calling kfunc and
+ * check if we get ENXIO from verifier.
+ */
+ skel_fail = config->bpf_open_and_load();
+ ret = errno;
+ if (!ASSERT_EQ(skel_fail, NULL, config->str_open)) {
+ /* Close uffd to unblock load_mod_thrd */
+ close(uffd);
+ uffd = -1;
+ while (atomic_load(blockingp) != 2)
+ ;
+ ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu");
+ config->bpf_destroy(skel_fail);
+ goto end_join;
+
+ }
+ ASSERT_EQ(ret, ENXIO, "verifier returns ENXIO");
+ ASSERT_EQ(skel->data->res_try_get_module, false, "btf_try_get_module == false");
+
+ close(uffd);
+ uffd = -1;
+end_join:
+ pthread_join(load_mod_thrd, NULL);
+ if (uffd < 0)
+ ASSERT_EQ(atomic_load(&state), TS_MODULE_LOAD_FAIL, "load_mod_thrd success");
+end_uffd:
+ if (uffd >= 0)
+ close(uffd);
+end_destroy:
+ bpf_mod_race__destroy(skel);
+ ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu");
+end_module:
+ sys_delete_module("bpf_testmod", 0);
+ ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod");
+end_mmap:
+ munmap(fault_addr, 4096);
+ atomic_store(&state, _TS_INVALID);
+}
+
+static const struct test_config ksym_config = {
+ .str_open = "ksym_race__open_and_load",
+ .bpf_open_and_load = (void *)ksym_race__open_and_load,
+ .bpf_destroy = (void *)ksym_race__destroy,
+};
+
+static const struct test_config kfunc_config = {
+ .str_open = "kfunc_call_race__open_and_load",
+ .bpf_open_and_load = (void *)kfunc_call_race__open_and_load,
+ .bpf_destroy = (void *)kfunc_call_race__destroy,
+};
+
+void serial_test_bpf_mod_race(void)
+{
+ if (test__start_subtest("ksym (used_btfs UAF)"))
+ test_bpf_mod_race_config(&ksym_config);
+ if (test__start_subtest("kfunc (kfunc_btf_tab UAF)"))
+ test_bpf_mod_race_config(&kfunc_config);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_bpf_nf.skel.h"
+
+enum {
+ TEST_XDP,
+ TEST_TC_BPF,
+};
+
+void test_bpf_nf_ct(int mode)
+{
+ struct test_bpf_nf *skel;
+ int prog_fd, err, retval;
+
+ skel = test_bpf_nf__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load"))
+ return;
+
+ if (mode == TEST_XDP)
+ prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test);
+ else
+ prog_fd = bpf_program__fd(skel->progs.nf_skb_ct_test);
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL,
+ (__u32 *)&retval, NULL);
+ if (!ASSERT_OK(err, "bpf_prog_test_run"))
+ goto end;
+
+ ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple");
+ ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0");
+ ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1");
+ ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ");
+ ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP");
+ ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id");
+ ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup");
+ ASSERT_EQ(skel->bss->test_eafnosupport, -EAFNOSUPPORT, "Test EAFNOSUPPORT for invalid len__tuple");
+end:
+ test_bpf_nf__destroy(skel);
+}
+
+void test_bpf_nf(void)
+{
+ if (test__start_subtest("xdp-ct"))
+ test_bpf_nf_ct(TEST_XDP);
+ if (test__start_subtest("tc-bpf-ct"))
+ test_bpf_nf_ct(TEST_TC_BPF);
+}
has_btf_ext = btf_ext != NULL;
btf_ext__free(btf_ext);
+ /* temporary disable LIBBPF_STRICT_MAP_DEFINITIONS to test legacy maps */
+ libbpf_set_strict_mode((__LIBBPF_STRICT_LAST - 1) & ~LIBBPF_STRICT_MAP_DEFINITIONS);
obj = bpf_object__open(test->file);
err = libbpf_get_error(obj);
if (CHECK(err, "obj: %d", err))
fprintf(stderr, "OK");
done:
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
btf__free(btf);
free(func_info);
bpf_object__close(obj);
attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE;
attach_opts.replace_prog_fd = allow_prog[0];
- if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+ if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1,
BPF_CGROUP_INET_EGRESS, &attach_opts),
"fail_prog_replace_override", "unexpected success\n"))
goto err;
CHECK_FAIL(errno != EINVAL);
attach_opts.flags = BPF_F_REPLACE;
- if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+ if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1,
BPF_CGROUP_INET_EGRESS, &attach_opts),
"fail_prog_replace_no_multi", "unexpected success\n"))
goto err;
attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE;
attach_opts.replace_prog_fd = -1;
- if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+ if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1,
BPF_CGROUP_INET_EGRESS, &attach_opts),
"fail_prog_replace_bad_fd", "unexpected success\n"))
goto err;
/* replacing a program that is not attached to cgroup should fail */
attach_opts.replace_prog_fd = allow_prog[3];
- if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+ if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1,
BPF_CGROUP_INET_EGRESS, &attach_opts),
"fail_prog_replace_no_ent", "unexpected success\n"))
goto err;
/* replace 1st from the top program */
attach_opts.replace_prog_fd = allow_prog[0];
- if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1,
+ if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1,
BPF_CGROUP_INET_EGRESS, &attach_opts),
"prog_replace", "errno=%d\n", errno))
goto err;
/* replace program with itself */
attach_opts.replace_prog_fd = allow_prog[6];
- if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1,
+ if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1,
BPF_CGROUP_INET_EGRESS, &attach_opts),
"prog_replace", "errno=%d\n", errno))
goto err;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2021 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <cgroup_helpers.h>
+#include <network_helpers.h>
+
+#include "cgroup_getset_retval_setsockopt.skel.h"
+#include "cgroup_getset_retval_getsockopt.skel.h"
+
+#define SOL_CUSTOM 0xdeadbeef
+
+static int zero;
+
+static void test_setsockopt_set(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_set_eunatch = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that sets EUNATCH, assert that
+ * we actually get that error when we run setsockopt()
+ */
+ link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_set_eunatch);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_set_eunatch = NULL, *link_get_retval = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that sets EUNATCH, and one that gets the
+ * previously set errno. Assert that we get the same errno back.
+ */
+ link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch"))
+ goto close_bpf_object;
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_set_eunatch);
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_get_retval = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that gets the previously set errno.
+ * Assert that, without anything setting one, we get 0.
+ */
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_OK(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_get_retval = NULL, *link_set_eunatch = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that gets the previously set errno, and then
+ * one that sets the errno to EUNATCH. Assert that the get does not
+ * see EUNATCH set later, and does not prevent EUNATCH from being set.
+ */
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+ link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_get_retval);
+ bpf_link__destroy(link_set_eunatch);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_setsockopt_override(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_set_eunatch = NULL, *link_set_eisconn = NULL;
+ struct bpf_link *link_get_retval = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN,
+ * and then one that gets the exported errno. Assert both the syscall
+ * and the helper sees the last set errno.
+ */
+ link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch"))
+ goto close_bpf_object;
+ link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn"))
+ goto close_bpf_object;
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EISCONN, "setsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, -EISCONN, "retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_set_eunatch);
+ bpf_link__destroy(link_set_eisconn);
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_legacy_eperm = NULL, *link_get_retval = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that return a reject without setting errno
+ * (legacy reject), and one that gets the errno. Assert that for
+ * backward compatibility the syscall result in EPERM, and this
+ * is also visible to the helper.
+ */
+ link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm"))
+ goto close_bpf_object;
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EPERM, "setsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, -EPERM, "retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_legacy_eperm);
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_setsockopt *obj;
+ struct bpf_link *link_set_eunatch = NULL, *link_legacy_eperm = NULL;
+ struct bpf_link *link_get_retval = NULL;
+
+ obj = cgroup_getset_retval_setsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach setsockopt that sets EUNATCH, then one that return a reject
+ * without setting errno, and then one that gets the exported errno.
+ * Assert both the syscall and the helper's errno are unaffected by
+ * the second prog (i.e. legacy rejects does not override the errno
+ * to EPERM).
+ */
+ link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch"))
+ goto close_bpf_object;
+ link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm"))
+ goto close_bpf_object;
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR,
+ &zero, sizeof(int)), "setsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_set_eunatch);
+ bpf_link__destroy(link_legacy_eperm);
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_setsockopt__destroy(obj);
+}
+
+static void test_getsockopt_get(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_getsockopt *obj;
+ struct bpf_link *link_get_retval = NULL;
+ int buf;
+ socklen_t optlen = sizeof(buf);
+
+ obj = cgroup_getset_retval_getsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach getsockopt that gets previously set errno. Assert that the
+ * error from kernel is in both ctx_retval_value and retval_value.
+ */
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0,
+ &buf, &optlen), "getsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EOPNOTSUPP, "getsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, -EOPNOTSUPP, "retval_value"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->ctx_retval_value, -EOPNOTSUPP, "ctx_retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_getsockopt__destroy(obj);
+}
+
+static void test_getsockopt_override(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_getsockopt *obj;
+ struct bpf_link *link_set_eisconn = NULL;
+ int buf;
+ socklen_t optlen = sizeof(buf);
+
+ obj = cgroup_getset_retval_getsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach getsockopt that sets retval to -EISCONN. Assert that this
+ * overrides the value from kernel.
+ */
+ link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn"))
+ goto close_bpf_object;
+
+ if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0,
+ &buf, &optlen), "getsockopt"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(errno, EISCONN, "getsockopt-errno"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_set_eisconn);
+
+ cgroup_getset_retval_getsockopt__destroy(obj);
+}
+
+static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd)
+{
+ struct cgroup_getset_retval_getsockopt *obj;
+ struct bpf_link *link_set_eisconn = NULL, *link_clear_retval = NULL;
+ struct bpf_link *link_get_retval = NULL;
+ int buf;
+ socklen_t optlen = sizeof(buf);
+
+ obj = cgroup_getset_retval_getsockopt__open_and_load();
+ if (!ASSERT_OK_PTR(obj, "skel-load"))
+ return;
+
+ /* Attach getsockopt that sets retval to -EISCONN, and one that clears
+ * ctx retval. Assert that the clearing ctx retval is synced to helper
+ * and clears any errors both from kernel and BPF..
+ */
+ link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn"))
+ goto close_bpf_object;
+ link_clear_retval = bpf_program__attach_cgroup(obj->progs.clear_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_clear_retval, "cg-attach-clear_retval"))
+ goto close_bpf_object;
+ link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval,
+ cgroup_fd);
+ if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval"))
+ goto close_bpf_object;
+
+ if (!ASSERT_OK(getsockopt(sock_fd, SOL_CUSTOM, 0,
+ &buf, &optlen), "getsockopt"))
+ goto close_bpf_object;
+
+ if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations"))
+ goto close_bpf_object;
+ if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value"))
+ goto close_bpf_object;
+ if (!ASSERT_EQ(obj->bss->ctx_retval_value, 0, "ctx_retval_value"))
+ goto close_bpf_object;
+
+close_bpf_object:
+ bpf_link__destroy(link_set_eisconn);
+ bpf_link__destroy(link_clear_retval);
+ bpf_link__destroy(link_get_retval);
+
+ cgroup_getset_retval_getsockopt__destroy(obj);
+}
+
+void test_cgroup_getset_retval(void)
+{
+ int cgroup_fd = -1;
+ int sock_fd = -1;
+
+ cgroup_fd = test__join_cgroup("/cgroup_getset_retval");
+ if (!ASSERT_GE(cgroup_fd, 0, "cg-create"))
+ goto close_fd;
+
+ sock_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0);
+ if (!ASSERT_GE(sock_fd, 0, "start-server"))
+ goto close_fd;
+
+ if (test__start_subtest("setsockopt-set"))
+ test_setsockopt_set(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("setsockopt-set_and_get"))
+ test_setsockopt_set_and_get(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("setsockopt-default_zero"))
+ test_setsockopt_default_zero(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("setsockopt-default_zero_and_set"))
+ test_setsockopt_default_zero_and_set(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("setsockopt-override"))
+ test_setsockopt_override(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("setsockopt-legacy_eperm"))
+ test_setsockopt_legacy_eperm(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("setsockopt-legacy_no_override"))
+ test_setsockopt_legacy_no_override(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("getsockopt-get"))
+ test_getsockopt_get(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("getsockopt-override"))
+ test_getsockopt_override(cgroup_fd, sock_fd);
+
+ if (test__start_subtest("getsockopt-retval_sync"))
+ test_getsockopt_retval_sync(cgroup_fd, sock_fd);
+
+close_fd:
+ close(cgroup_fd);
+}
if (map_fd < 0)
return -1;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK_FAIL(map_fd < 0))
return;
- buff = malloc(bpf_map__def(map)->value_size);
+ buff = malloc(bpf_map__value_size(map));
if (buff)
err = bpf_map_update_elem(map_fd, &zero, buff, 0);
free(buff);
if (CHECK_FAIL(!map || !bpf_map__is_internal(map)))
goto out;
- sz = bpf_map__def(map)->value_size;
+ sz = bpf_map__value_size(map);
newval = malloc(sz);
if (CHECK_FAIL(!newval))
goto out;
ASSERT_OK(err, "bpf_prog_test_run(test2)");
ASSERT_EQ(retval, 3, "test2-retval");
+ prog_fd = skel->progs.kfunc_call_test_ref_btf_id.prog_fd;
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, (__u32 *)&retval, NULL);
+ ASSERT_OK(err, "bpf_prog_test_run(test_ref_btf_id)");
+ ASSERT_EQ(retval, 0, "test_ref_btf_id-retval");
+
kfunc_call_test_lskel__destroy(skel);
}
#include "test_sockmap_update.skel.h"
#include "test_sockmap_invalid_update.skel.h"
#include "test_sockmap_skb_verdict_attach.skel.h"
+#include "test_sockmap_progs_query.skel.h"
#include "bpf_iter_sockmap.skel.h"
#define TCP_REPAIR 19 /* TCP sock is under repair right now */
test_sockmap_skb_verdict_attach__destroy(skel);
}
+static __u32 query_prog_id(int prog_fd)
+{
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ int err;
+
+ err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+ if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") ||
+ !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd"))
+ return 0;
+
+ return info.id;
+}
+
+static void test_sockmap_progs_query(enum bpf_attach_type attach_type)
+{
+ struct test_sockmap_progs_query *skel;
+ int err, map_fd, verdict_fd;
+ __u32 attach_flags = 0;
+ __u32 prog_ids[3] = {};
+ __u32 prog_cnt = 3;
+
+ skel = test_sockmap_progs_query__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_sockmap_progs_query__open_and_load"))
+ return;
+
+ map_fd = bpf_map__fd(skel->maps.sock_map);
+
+ if (attach_type == BPF_SK_MSG_VERDICT)
+ verdict_fd = bpf_program__fd(skel->progs.prog_skmsg_verdict);
+ else
+ verdict_fd = bpf_program__fd(skel->progs.prog_skb_verdict);
+
+ err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */,
+ &attach_flags, prog_ids, &prog_cnt);
+ ASSERT_OK(err, "bpf_prog_query failed");
+ ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query");
+ ASSERT_EQ(prog_cnt, 0, "wrong program count on query");
+
+ err = bpf_prog_attach(verdict_fd, map_fd, attach_type, 0);
+ if (!ASSERT_OK(err, "bpf_prog_attach failed"))
+ goto out;
+
+ prog_cnt = 1;
+ err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */,
+ &attach_flags, prog_ids, &prog_cnt);
+ ASSERT_OK(err, "bpf_prog_query failed");
+ ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query");
+ ASSERT_EQ(prog_cnt, 1, "wrong program count on query");
+ ASSERT_EQ(prog_ids[0], query_prog_id(verdict_fd),
+ "wrong prog_ids on query");
+
+ bpf_prog_detach2(verdict_fd, map_fd, attach_type);
+out:
+ test_sockmap_progs_query__destroy(skel);
+}
+
void test_sockmap_basic(void)
{
if (test__start_subtest("sockmap create_update_free"))
test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT,
BPF_SK_SKB_VERDICT);
}
+ if (test__start_subtest("sockmap msg_verdict progs query"))
+ test_sockmap_progs_query(BPF_SK_MSG_VERDICT);
+ if (test__start_subtest("sockmap stream_parser progs query"))
+ test_sockmap_progs_query(BPF_SK_SKB_STREAM_PARSER);
+ if (test__start_subtest("sockmap stream_verdict progs query"))
+ test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT);
+ if (test__start_subtest("sockmap skb_verdict progs query"))
+ test_sockmap_progs_query(BPF_SK_SKB_VERDICT);
}
static void test_ops_cleanup(const struct bpf_map *map)
{
- const struct bpf_map_def *def;
int err, mapfd;
u32 key;
- def = bpf_map__def(map);
mapfd = bpf_map__fd(map);
- for (key = 0; key < def->max_entries; key++) {
+ for (key = 0; key < bpf_map__max_entries(map); key++) {
err = bpf_map_delete_elem(mapfd, &key);
if (err && errno != EINVAL && errno != ENOENT)
FAIL_ERRNO("map_delete: expected EINVAL/ENOENT");
static const char *map_type_str(const struct bpf_map *map)
{
- const struct bpf_map_def *def;
+ int type;
- def = bpf_map__def(map);
- if (IS_ERR(def))
+ if (!map)
return "invalid";
+ type = bpf_map__type(map);
- switch (def->type) {
+ switch (type) {
case BPF_MAP_TYPE_SOCKMAP:
return "sockmap";
case BPF_MAP_TYPE_SOCKHASH:
}
memset(&buf, 0, sizeof(buf));
- buf.zc.address = 12345; /* rejected by BPF */
+ buf.zc.address = 12345; /* Not page aligned. Rejected by tcp_zerocopy_receive() */
optlen = sizeof(buf.zc);
errno = 0;
err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen);
- if (errno != EPERM) {
+ if (errno != EINVAL) {
log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d",
err, errno);
goto err;
if (CHECK_FAIL(map_fd < 0))
goto out;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
goto out;
}
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
&duration, &retval, NULL);
CHECK(err || retval != i, "tailcall",
CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n",
err, errno, retval);
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n",
err, errno, retval);
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
- j = bpf_map__def(prog_array)->max_entries - 1 - i;
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+ j = bpf_map__max_entries(prog_array) - 1 - i;
snprintf(prog_name, sizeof(prog_name), "classifier_%d", j);
prog = bpf_object__find_program_by_name(obj, prog_name);
goto out;
}
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
- j = bpf_map__def(prog_array)->max_entries - 1 - i;
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+ j = bpf_map__max_entries(prog_array) - 1 - i;
err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0,
&duration, &retval, NULL);
CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n",
err, errno, retval);
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
err = bpf_map_delete_elem(map_fd, &i);
if (CHECK_FAIL(err >= 0 || errno != ENOENT))
goto out;
if (CHECK_FAIL(map_fd < 0))
goto out;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK_FAIL(map_fd < 0))
return;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
goto out;
}
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY);
if (CHECK_FAIL(err))
goto out;
"err %d errno %d retval %d\n", err, errno, retval);
}
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY);
if (CHECK_FAIL(err))
goto out;
if (CHECK_FAIL(map_fd < 0))
return;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
goto out;
}
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY);
if (CHECK_FAIL(err))
goto out;
"err %d errno %d retval %d\n", err, errno, retval);
}
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY);
if (CHECK_FAIL(err))
goto out;
goto out;
/* nop -> jmp */
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK_FAIL(map_fd < 0))
goto out;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
if (CHECK_FAIL(map_fd < 0))
goto out;
- for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
+ for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
prog = bpf_object__find_program_by_name(obj, prog_name);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+void test_xdp_update_frags(void)
+{
+ const char *file = "./test_xdp_update_frags.o";
+ __u32 duration, retval, size;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int err, prog_fd;
+ __u32 *offset;
+ __u8 *buf;
+
+ obj = bpf_object__open(file);
+ if (libbpf_get_error(obj))
+ return;
+
+ prog = bpf_object__next_program(obj, NULL);
+ if (bpf_object__load(obj))
+ return;
+
+ prog_fd = bpf_program__fd(prog);
+
+ buf = malloc(128);
+ if (!ASSERT_OK_PTR(buf, "alloc buf 128b"))
+ goto out;
+
+ memset(buf, 0, 128);
+ offset = (__u32 *)buf;
+ *offset = 16;
+ buf[*offset] = 0xaa; /* marker at offset 16 (head) */
+ buf[*offset + 15] = 0xaa; /* marker at offset 31 (head) */
+
+ err = bpf_prog_test_run(prog_fd, 1, buf, 128,
+ buf, &size, &retval, &duration);
+
+ /* test_xdp_update_frags: buf[16,31]: 0xaa -> 0xbb */
+ ASSERT_OK(err, "xdp_update_frag");
+ ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval");
+ ASSERT_EQ(buf[16], 0xbb, "xdp_update_frag buf[16]");
+ ASSERT_EQ(buf[31], 0xbb, "xdp_update_frag buf[31]");
+
+ free(buf);
+
+ buf = malloc(9000);
+ if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb"))
+ goto out;
+
+ memset(buf, 0, 9000);
+ offset = (__u32 *)buf;
+ *offset = 5000;
+ buf[*offset] = 0xaa; /* marker at offset 5000 (frag0) */
+ buf[*offset + 15] = 0xaa; /* marker at offset 5015 (frag0) */
+
+ err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+ buf, &size, &retval, &duration);
+
+ /* test_xdp_update_frags: buf[5000,5015]: 0xaa -> 0xbb */
+ ASSERT_OK(err, "xdp_update_frag");
+ ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval");
+ ASSERT_EQ(buf[5000], 0xbb, "xdp_update_frag buf[5000]");
+ ASSERT_EQ(buf[5015], 0xbb, "xdp_update_frag buf[5015]");
+
+ memset(buf, 0, 9000);
+ offset = (__u32 *)buf;
+ *offset = 3510;
+ buf[*offset] = 0xaa; /* marker at offset 3510 (head) */
+ buf[*offset + 15] = 0xaa; /* marker at offset 3525 (frag0) */
+
+ err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+ buf, &size, &retval, &duration);
+
+ /* test_xdp_update_frags: buf[3510,3525]: 0xaa -> 0xbb */
+ ASSERT_OK(err, "xdp_update_frag");
+ ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval");
+ ASSERT_EQ(buf[3510], 0xbb, "xdp_update_frag buf[3510]");
+ ASSERT_EQ(buf[3525], 0xbb, "xdp_update_frag buf[3525]");
+
+ memset(buf, 0, 9000);
+ offset = (__u32 *)buf;
+ *offset = 7606;
+ buf[*offset] = 0xaa; /* marker at offset 7606 (frag0) */
+ buf[*offset + 15] = 0xaa; /* marker at offset 7621 (frag1) */
+
+ err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+ buf, &size, &retval, &duration);
+
+ /* test_xdp_update_frags: buf[7606,7621]: 0xaa -> 0xbb */
+ ASSERT_OK(err, "xdp_update_frag");
+ ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval");
+ ASSERT_EQ(buf[7606], 0xbb, "xdp_update_frag buf[7606]");
+ ASSERT_EQ(buf[7621], 0xbb, "xdp_update_frag buf[7621]");
+
+ free(buf);
+out:
+ bpf_object__close(obj);
+}
+
+void test_xdp_adjust_frags(void)
+{
+ if (test__start_subtest("xdp_adjust_frags"))
+ test_xdp_update_frags();
+}
char buf[128];
err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
- if (CHECK_FAIL(err))
+ if (ASSERT_OK(err, "test_xdp_adjust_tail_shrink"))
return;
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
-
- CHECK(err || retval != XDP_DROP,
- "ipv4", "err %d errno %d retval %d size %d\n",
- err, errno, retval, size);
+ ASSERT_OK(err, "ipv4");
+ ASSERT_EQ(retval, XDP_DROP, "ipv4 retval");
expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
buf, &size, &retval, &duration);
- CHECK(err || retval != XDP_TX || size != expect_sz,
- "ipv6", "err %d errno %d retval %d size %d expect-size %d\n",
- err, errno, retval, size, expect_sz);
+ ASSERT_OK(err, "ipv6");
+ ASSERT_EQ(retval, XDP_TX, "ipv6 retval");
+ ASSERT_EQ(size, expect_sz, "ipv6 size");
+
bpf_object__close(obj);
}
int err, prog_fd;
err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
- if (CHECK_FAIL(err))
+ if (ASSERT_OK(err, "test_xdp_adjust_tail_grow"))
return;
err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
buf, &size, &retval, &duration);
- CHECK(err || retval != XDP_DROP,
- "ipv4", "err %d errno %d retval %d size %d\n",
- err, errno, retval, size);
+ ASSERT_OK(err, "ipv4");
+ ASSERT_EQ(retval, XDP_DROP, "ipv4 retval");
expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */
err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */,
buf, &size, &retval, &duration);
- CHECK(err || retval != XDP_TX || size != expect_sz,
- "ipv6", "err %d errno %d retval %d size %d expect-size %d\n",
- err, errno, retval, size, expect_sz);
+ ASSERT_OK(err, "ipv6");
+ ASSERT_EQ(retval, XDP_TX, "ipv6 retval");
+ ASSERT_EQ(size, expect_sz, "ipv6 size");
bpf_object__close(obj);
}
};
err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd);
- if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+ if (ASSERT_OK(err, "test_xdp_adjust_tail_grow"))
return;
/* Test case-64 */
/* Kernel side alloc packet memory area that is zero init */
err = bpf_prog_test_run_xattr(&tattr);
- CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */
- || tattr.retval != XDP_TX
- || tattr.data_size_out != 192, /* Expected grow size */
- "case-64",
- "err %d errno %d retval %d size %d\n",
- err, errno, tattr.retval, tattr.data_size_out);
+ ASSERT_EQ(errno, ENOSPC, "case-64 errno"); /* Due limit copy_size in bpf_test_finish */
+ ASSERT_EQ(tattr.retval, XDP_TX, "case-64 retval");
+ ASSERT_EQ(tattr.data_size_out, 192, "case-64 data_size_out"); /* Expected grow size */
/* Extra checks for data contents */
- CHECK_ATTR(tattr.data_size_out != 192
- || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */
- || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */
- || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */
- "case-64-data",
- "err %d errno %d retval %d size %d\n",
- err, errno, tattr.retval, tattr.data_size_out);
+ ASSERT_EQ(buf[0], 1, "case-64-data buf[0]"); /* 0-63 memset to 1 */
+ ASSERT_EQ(buf[63], 1, "case-64-data buf[63]");
+ ASSERT_EQ(buf[64], 0, "case-64-data buf[64]"); /* 64-127 memset to 0 */
+ ASSERT_EQ(buf[127], 0, "case-64-data buf[127]");
+ ASSERT_EQ(buf[128], 1, "case-64-data buf[128]"); /* 128-191 memset to 1 */
+ ASSERT_EQ(buf[191], 1, "case-64-data buf[191]");
/* Test case-128 */
memset(buf, 2, sizeof(buf));
err = bpf_prog_test_run_xattr(&tattr);
max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */
- CHECK_ATTR(err
- || tattr.retval != XDP_TX
- || tattr.data_size_out != max_grow,/* Expect max grow size */
- "case-128",
- "err %d errno %d retval %d size %d expect-size %d\n",
- err, errno, tattr.retval, tattr.data_size_out, max_grow);
+ ASSERT_OK(err, "case-128");
+ ASSERT_EQ(tattr.retval, XDP_TX, "case-128 retval");
+ ASSERT_EQ(tattr.data_size_out, max_grow, "case-128 data_size_out"); /* Expect max grow */
/* Extra checks for data content: Count grow size, will contain zeros */
for (i = 0, cnt = 0; i < sizeof(buf); i++) {
if (buf[i] == 0)
cnt++;
}
- CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */
- || tattr.data_size_out != max_grow, /* Total grow size */
- "case-128-data",
- "err %d errno %d retval %d size %d grow-size %d\n",
- err, errno, tattr.retval, tattr.data_size_out, cnt);
+ ASSERT_EQ(cnt, max_grow - tattr.data_size_in, "case-128-data cnt"); /* Grow increase */
+ ASSERT_EQ(tattr.data_size_out, max_grow, "case-128-data data_size_out"); /* Total grow */
+
+ bpf_object__close(obj);
+}
+
+void test_xdp_adjust_frags_tail_shrink(void)
+{
+ const char *file = "./test_xdp_adjust_tail_shrink.o";
+ __u32 duration, retval, size, exp_size;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int err, prog_fd;
+ __u8 *buf;
+
+ /* For the individual test cases, the first byte in the packet
+ * indicates which test will be run.
+ */
+ obj = bpf_object__open(file);
+ if (libbpf_get_error(obj))
+ return;
+
+ prog = bpf_object__next_program(obj, NULL);
+ if (bpf_object__load(obj))
+ return;
+
+ prog_fd = bpf_program__fd(prog);
+
+ buf = malloc(9000);
+ if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb"))
+ goto out;
+
+ memset(buf, 0, 9000);
+
+ /* Test case removing 10 bytes from last frag, NOT freeing it */
+ exp_size = 8990; /* 9000 - 10 */
+ err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+ buf, &size, &retval, &duration);
+
+ ASSERT_OK(err, "9Kb-10b");
+ ASSERT_EQ(retval, XDP_TX, "9Kb-10b retval");
+ ASSERT_EQ(size, exp_size, "9Kb-10b size");
+
+ /* Test case removing one of two pages, assuming 4K pages */
+ buf[0] = 1;
+ exp_size = 4900; /* 9000 - 4100 */
+ err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+ buf, &size, &retval, &duration);
+
+ ASSERT_OK(err, "9Kb-4Kb");
+ ASSERT_EQ(retval, XDP_TX, "9Kb-4Kb retval");
+ ASSERT_EQ(size, exp_size, "9Kb-4Kb size");
+
+ /* Test case removing two pages resulting in a linear xdp_buff */
+ buf[0] = 2;
+ exp_size = 800; /* 9000 - 8200 */
+ err = bpf_prog_test_run(prog_fd, 1, buf, 9000,
+ buf, &size, &retval, &duration);
+
+ ASSERT_OK(err, "9Kb-9Kb");
+ ASSERT_EQ(retval, XDP_TX, "9Kb-9Kb retval");
+ ASSERT_EQ(size, exp_size, "9Kb-9Kb size");
+
+ free(buf);
+out:
+ bpf_object__close(obj);
+}
+
+void test_xdp_adjust_frags_tail_grow(void)
+{
+ const char *file = "./test_xdp_adjust_tail_grow.o";
+ __u32 duration, retval, size, exp_size;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int err, i, prog_fd;
+ __u8 *buf;
+
+ obj = bpf_object__open(file);
+ if (libbpf_get_error(obj))
+ return;
+
+ prog = bpf_object__next_program(obj, NULL);
+ if (bpf_object__load(obj))
+ return;
+
+ prog_fd = bpf_program__fd(prog);
+
+ buf = malloc(16384);
+ if (!ASSERT_OK_PTR(buf, "alloc buf 16Kb"))
+ goto out;
+
+ /* Test case add 10 bytes to last frag */
+ memset(buf, 1, 16384);
+ size = 9000;
+ exp_size = size + 10;
+ err = bpf_prog_test_run(prog_fd, 1, buf, size,
+ buf, &size, &retval, &duration);
+
+ ASSERT_OK(err, "9Kb+10b");
+ ASSERT_EQ(retval, XDP_TX, "9Kb+10b retval");
+ ASSERT_EQ(size, exp_size, "9Kb+10b size");
+
+ for (i = 0; i < 9000; i++)
+ ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+
+ for (i = 9000; i < 9010; i++)
+ ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+
+ for (i = 9010; i < 16384; i++)
+ ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+
+ /* Test a too large grow */
+ memset(buf, 1, 16384);
+ size = 9001;
+ exp_size = size;
+ err = bpf_prog_test_run(prog_fd, 1, buf, size,
+ buf, &size, &retval, &duration);
+
+ ASSERT_OK(err, "9Kb+10b");
+ ASSERT_EQ(retval, XDP_DROP, "9Kb+10b retval");
+ ASSERT_EQ(size, exp_size, "9Kb+10b size");
+ free(buf);
+out:
bpf_object__close(obj);
}
test_xdp_adjust_tail_grow();
if (test__start_subtest("xdp_adjust_tail_grow2"))
test_xdp_adjust_tail_grow2();
+ if (test__start_subtest("xdp_adjust_frags_tail_shrink"))
+ test_xdp_adjust_frags_tail_shrink();
+ if (test__start_subtest("xdp_adjust_frags_tail_grow"))
+ test_xdp_adjust_frags_tail_grow();
}
int pkt_len;
};
+struct test_ctx_s {
+ bool passed;
+ int pkt_size;
+};
+
+struct test_ctx_s test_ctx;
+
static void on_sample(void *ctx, int cpu, void *data, __u32 size)
{
- int duration = 0;
struct meta *meta = (struct meta *)data;
struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta);
+ unsigned char *raw_pkt = data + sizeof(*meta);
+ struct test_ctx_s *tst_ctx = ctx;
+
+ ASSERT_GE(size, sizeof(pkt_v4) + sizeof(*meta), "check_size");
+ ASSERT_EQ(meta->ifindex, if_nametoindex("lo"), "check_meta_ifindex");
+ ASSERT_EQ(meta->pkt_len, tst_ctx->pkt_size, "check_meta_pkt_len");
+ ASSERT_EQ(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), 0,
+ "check_packet_content");
+
+ if (meta->pkt_len > sizeof(pkt_v4)) {
+ for (int i = 0; i < meta->pkt_len - sizeof(pkt_v4); i++)
+ ASSERT_EQ(raw_pkt[i + sizeof(pkt_v4)], (unsigned char)i,
+ "check_packet_content");
+ }
+
+ tst_ctx->passed = true;
+}
- if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta),
- "check_size", "size %u < %zu\n",
- size, sizeof(pkt_v4) + sizeof(*meta)))
- return;
+#define BUF_SZ 9000
- if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex",
- "meta->ifindex = %d\n", meta->ifindex))
+static void run_xdp_bpf2bpf_pkt_size(int pkt_fd, struct perf_buffer *pb,
+ struct test_xdp_bpf2bpf *ftrace_skel,
+ int pkt_size)
+{
+ __u32 duration = 0, retval, size;
+ __u8 *buf, *buf_in;
+ int err;
+
+ if (!ASSERT_LE(pkt_size, BUF_SZ, "pkt_size") ||
+ !ASSERT_GE(pkt_size, sizeof(pkt_v4), "pkt_size"))
return;
- if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len",
- "meta->pkt_len = %zd\n", sizeof(pkt_v4)))
+ buf_in = malloc(BUF_SZ);
+ if (!ASSERT_OK_PTR(buf_in, "buf_in malloc()"))
return;
- if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)),
- "check_packet_content", "content not the same\n"))
+ buf = malloc(BUF_SZ);
+ if (!ASSERT_OK_PTR(buf, "buf malloc()")) {
+ free(buf_in);
return;
+ }
+
+ test_ctx.passed = false;
+ test_ctx.pkt_size = pkt_size;
+
+ memcpy(buf_in, &pkt_v4, sizeof(pkt_v4));
+ if (pkt_size > sizeof(pkt_v4)) {
+ for (int i = 0; i < (pkt_size - sizeof(pkt_v4)); i++)
+ buf_in[i + sizeof(pkt_v4)] = i;
+ }
+
+ /* Run test program */
+ err = bpf_prog_test_run(pkt_fd, 1, buf_in, pkt_size,
+ buf, &size, &retval, &duration);
+
+ ASSERT_OK(err, "ipv4");
+ ASSERT_EQ(retval, XDP_PASS, "ipv4 retval");
+ ASSERT_EQ(size, pkt_size, "ipv4 size");
+
+ /* Make sure bpf_xdp_output() was triggered and it sent the expected
+ * data to the perf ring buffer.
+ */
+ err = perf_buffer__poll(pb, 100);
- *(bool *)ctx = true;
+ ASSERT_GE(err, 0, "perf_buffer__poll");
+ ASSERT_TRUE(test_ctx.passed, "test passed");
+ /* Verify test results */
+ ASSERT_EQ(ftrace_skel->bss->test_result_fentry, if_nametoindex("lo"),
+ "fentry result");
+ ASSERT_EQ(ftrace_skel->bss->test_result_fexit, XDP_PASS, "fexit result");
+
+ free(buf);
+ free(buf_in);
}
void test_xdp_bpf2bpf(void)
{
- __u32 duration = 0, retval, size;
- char buf[128];
int err, pkt_fd, map_fd;
- bool passed = false;
- struct iphdr iph;
- struct iptnl_info value4 = {.family = AF_INET};
+ int pkt_sizes[] = {sizeof(pkt_v4), 1024, 4100, 8200};
+ struct iptnl_info value4 = {.family = AF_INET6};
struct test_xdp *pkt_skel = NULL;
struct test_xdp_bpf2bpf *ftrace_skel = NULL;
struct vip key4 = {.protocol = 6, .family = AF_INET};
/* Load XDP program to introspect */
pkt_skel = test_xdp__open_and_load();
- if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n"))
+ if (!ASSERT_OK_PTR(pkt_skel, "test_xdp__open_and_load"))
return;
pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel);
/* Load trace program */
ftrace_skel = test_xdp_bpf2bpf__open();
- if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n"))
+ if (!ASSERT_OK_PTR(ftrace_skel, "test_xdp_bpf2bpf__open"))
goto out;
/* Demonstrate the bpf_program__set_attach_target() API rather than
bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel");
err = test_xdp_bpf2bpf__load(ftrace_skel);
- if (CHECK(err, "__load", "ftrace skeleton failed\n"))
+ if (!ASSERT_OK(err, "test_xdp_bpf2bpf__load"))
goto out;
err = test_xdp_bpf2bpf__attach(ftrace_skel);
- if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
+ if (!ASSERT_OK(err, "test_xdp_bpf2bpf__attach"))
goto out;
/* Set up perf buffer */
- pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1,
- on_sample, NULL, &passed, NULL);
+ pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 8,
+ on_sample, NULL, &test_ctx, NULL);
if (!ASSERT_OK_PTR(pb, "perf_buf__new"))
goto out;
- /* Run test program */
- err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
- buf, &size, &retval, &duration);
- memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph));
- if (CHECK(err || retval != XDP_TX || size != 74 ||
- iph.protocol != IPPROTO_IPIP, "ipv4",
- "err %d errno %d retval %d size %d\n",
- err, errno, retval, size))
- goto out;
-
- /* Make sure bpf_xdp_output() was triggered and it sent the expected
- * data to the perf ring buffer.
- */
- err = perf_buffer__poll(pb, 100);
- if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
- goto out;
-
- CHECK_FAIL(!passed);
-
- /* Verify test results */
- if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
- "result", "fentry failed err %llu\n",
- ftrace_skel->bss->test_result_fentry))
- goto out;
-
- CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result",
- "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
-
+ for (int i = 0; i < ARRAY_SIZE(pkt_sizes); i++)
+ run_xdp_bpf2bpf_pkt_size(pkt_fd, pb, ftrace_skel,
+ pkt_sizes[i]);
out:
- if (pb)
- perf_buffer__free(pb);
+ perf_buffer__free(pb);
test_xdp__destroy(pkt_skel);
test_xdp_bpf2bpf__destroy(ftrace_skel);
}
#include <linux/if_link.h>
#include <test_progs.h>
+#include "test_xdp_with_cpumap_frags_helpers.skel.h"
#include "test_xdp_with_cpumap_helpers.skel.h"
#define IFINDEX_LO 1
-void serial_test_xdp_cpumap_attach(void)
+void test_xdp_with_cpumap_helpers(void)
{
struct test_xdp_with_cpumap_helpers *skel;
struct bpf_prog_info info = {};
err = bpf_map_update_elem(map_fd, &idx, &val, 0);
ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry");
+ /* Try to attach BPF_XDP program with frags to cpumap when we have
+ * already loaded a BPF_XDP program on the map
+ */
+ idx = 1;
+ val.qsize = 192;
+ val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags);
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry");
+
out_close:
test_xdp_with_cpumap_helpers__destroy(skel);
}
+
+void test_xdp_with_cpumap_frags_helpers(void)
+{
+ struct test_xdp_with_cpumap_frags_helpers *skel;
+ struct bpf_prog_info info = {};
+ __u32 len = sizeof(info);
+ struct bpf_cpumap_val val = {
+ .qsize = 192,
+ };
+ int err, frags_prog_fd, map_fd;
+ __u32 idx = 0;
+
+ skel = test_xdp_with_cpumap_frags_helpers__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load"))
+ return;
+
+ frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags);
+ map_fd = bpf_map__fd(skel->maps.cpu_map);
+ err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len);
+ if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+ goto out_close;
+
+ val.bpf_prog.fd = frags_prog_fd;
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ ASSERT_OK(err, "Add program to cpumap entry");
+
+ err = bpf_map_lookup_elem(map_fd, &idx, &val);
+ ASSERT_OK(err, "Read cpumap entry");
+ ASSERT_EQ(info.id, val.bpf_prog.id,
+ "Match program id to cpumap entry prog_id");
+
+ /* Try to attach BPF_XDP program to cpumap when we have
+ * already loaded a BPF_XDP program with frags on the map
+ */
+ idx = 1;
+ val.qsize = 192;
+ val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ ASSERT_NEQ(err, 0, "Add BPF_XDP program to cpumap entry");
+
+out_close:
+ test_xdp_with_cpumap_frags_helpers__destroy(skel);
+}
+
+void serial_test_xdp_cpumap_attach(void)
+{
+ if (test__start_subtest("CPUMAP with programs in entries"))
+ test_xdp_with_cpumap_helpers();
+
+ if (test__start_subtest("CPUMAP with frags programs in entries"))
+ test_xdp_with_cpumap_frags_helpers();
+}
#include <test_progs.h>
#include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_with_devmap_frags_helpers.skel.h"
#include "test_xdp_with_devmap_helpers.skel.h"
#define IFINDEX_LO 1
err = bpf_map_update_elem(map_fd, &idx, &val, 0);
ASSERT_NEQ(err, 0, "Add non-BPF_XDP_DEVMAP program to devmap entry");
+ /* Try to attach BPF_XDP program with frags to devmap when we have
+ * already loaded a BPF_XDP program on the map
+ */
+ idx = 1;
+ val.ifindex = 1;
+ val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm_frags);
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry");
+
out_close:
test_xdp_with_devmap_helpers__destroy(skel);
}
}
}
+void test_xdp_with_devmap_frags_helpers(void)
+{
+ struct test_xdp_with_devmap_frags_helpers *skel;
+ struct bpf_prog_info info = {};
+ struct bpf_devmap_val val = {
+ .ifindex = IFINDEX_LO,
+ };
+ __u32 len = sizeof(info);
+ int err, dm_fd_frags, map_fd;
+ __u32 idx = 0;
+
+ skel = test_xdp_with_devmap_frags_helpers__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load"))
+ return;
+
+ dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags);
+ map_fd = bpf_map__fd(skel->maps.dm_ports);
+ err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len);
+ if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+ goto out_close;
+
+ val.bpf_prog.fd = dm_fd_frags;
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ ASSERT_OK(err, "Add frags program to devmap entry");
+
+ err = bpf_map_lookup_elem(map_fd, &idx, &val);
+ ASSERT_OK(err, "Read devmap entry");
+ ASSERT_EQ(info.id, val.bpf_prog.id,
+ "Match program id to devmap entry prog_id");
+
+ /* Try to attach BPF_XDP program to devmap when we have
+ * already loaded a BPF_XDP program with frags on the map
+ */
+ idx = 1;
+ val.ifindex = 1;
+ val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
+ err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+ ASSERT_NEQ(err, 0, "Add BPF_XDP program to devmap entry");
+
+out_close:
+ test_xdp_with_devmap_frags_helpers__destroy(skel);
+}
void serial_test_xdp_devmap_attach(void)
{
if (test__start_subtest("DEVMAP with programs in entries"))
test_xdp_with_devmap_helpers();
+ if (test__start_subtest("DEVMAP with frags programs in entries"))
+ test_xdp_with_devmap_frags_helpers();
+
if (test__start_subtest("Verifier check of DEVMAP programs"))
test_neg_xdp_devmap_helpers();
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+#include "bpf_iter.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <limits.h>
+
+#define AUTOBIND_LEN 6
+char sun_path[AUTOBIND_LEN];
+
+#define NR_CASES 5
+int sndbuf_setsockopt[NR_CASES] = {-1, 0, 8192, INT_MAX / 2, INT_MAX};
+int sndbuf_getsockopt[NR_CASES] = {-1, -1, -1, -1, -1};
+int sndbuf_getsockopt_expected[NR_CASES];
+
+static inline int cmpname(struct unix_sock *unix_sk)
+{
+ int i;
+
+ for (i = 0; i < AUTOBIND_LEN; i++) {
+ if (unix_sk->addr->name->sun_path[i] != sun_path[i])
+ return -1;
+ }
+
+ return 0;
+}
+
+SEC("iter/unix")
+int change_sndbuf(struct bpf_iter__unix *ctx)
+{
+ struct unix_sock *unix_sk = ctx->unix_sk;
+ int i, err;
+
+ if (!unix_sk || !unix_sk->addr)
+ return 0;
+
+ if (unix_sk->addr->name->sun_path[0])
+ return 0;
+
+ if (cmpname(unix_sk))
+ return 0;
+
+ for (i = 0; i < NR_CASES; i++) {
+ err = bpf_setsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF,
+ &sndbuf_setsockopt[i],
+ sizeof(sndbuf_setsockopt[i]));
+ if (err)
+ break;
+
+ err = bpf_getsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF,
+ &sndbuf_getsockopt[i],
+ sizeof(sndbuf_getsockopt[i]));
+ if (err)
+ break;
+ }
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
BPF_SEQ_PRINTF(seq, " @");
for (i = 1; i < len; i++) {
- /* unix_mkname() tests this upper bound. */
+ /* unix_validate_addr() tests this upper bound. */
if (i >= sizeof(struct sockaddr_un))
break;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+const volatile struct {
+ /* thread to activate trace programs for */
+ pid_t tgid;
+ /* return error from __init function */
+ int inject_error;
+ /* uffd monitored range start address */
+ void *fault_addr;
+} bpf_mod_race_config = { -1 };
+
+int bpf_blocking = 0;
+int res_try_get_module = -1;
+
+static __always_inline bool check_thread_id(void)
+{
+ struct task_struct *task = bpf_get_current_task_btf();
+
+ return task->tgid == bpf_mod_race_config.tgid;
+}
+
+/* The trace of execution is something like this:
+ *
+ * finit_module()
+ * load_module()
+ * prepare_coming_module()
+ * notifier_call(MODULE_STATE_COMING)
+ * btf_parse_module()
+ * btf_alloc_id() // Visible to userspace at this point
+ * list_add(btf_mod->list, &btf_modules)
+ * do_init_module()
+ * freeinit = kmalloc()
+ * ret = mod->init()
+ * bpf_prog_widen_race()
+ * bpf_copy_from_user()
+ * ...<sleep>...
+ * if (ret < 0)
+ * ...
+ * free_module()
+ * return ret
+ *
+ * At this point, module loading thread is blocked, we now load the program:
+ *
+ * bpf_check
+ * add_kfunc_call/check_pseudo_btf_id
+ * btf_try_get_module
+ * try_get_module_live == false
+ * return -ENXIO
+ *
+ * Without the fix (try_get_module_live in btf_try_get_module):
+ *
+ * bpf_check
+ * add_kfunc_call/check_pseudo_btf_id
+ * btf_try_get_module
+ * try_get_module == true
+ * <store module reference in btf_kfunc_tab or used_btf array>
+ * ...
+ * return fd
+ *
+ * Now, if we inject an error in the blocked program, our module will be freed
+ * (going straight from MODULE_STATE_COMING to MODULE_STATE_GOING).
+ * Later, when bpf program is freed, it will try to module_put already freed
+ * module. This is why try_get_module_live returns false if mod->state is not
+ * MODULE_STATE_LIVE.
+ */
+
+SEC("fmod_ret.s/bpf_fentry_test1")
+int BPF_PROG(widen_race, int a, int ret)
+{
+ char dst;
+
+ if (!check_thread_id())
+ return 0;
+ /* Indicate that we will attempt to block */
+ bpf_blocking = 1;
+ bpf_copy_from_user(&dst, 1, bpf_mod_race_config.fault_addr);
+ return bpf_mod_race_config.inject_error;
+}
+
+SEC("fexit/do_init_module")
+int BPF_PROG(fexit_init_module, struct module *mod, int ret)
+{
+ if (!check_thread_id())
+ return 0;
+ /* Indicate that we finished blocking */
+ bpf_blocking = 2;
+ return 0;
+}
+
+SEC("fexit/btf_try_get_module")
+int BPF_PROG(fexit_module_get, const struct btf *btf, struct module *mod)
+{
+ res_try_get_module = !!mod;
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
#define AF_INET 2
#define AF_INET6 10
+#define SOL_SOCKET 1
+#define SO_SNDBUF 7
#define __SO_ACCEPTCON (1 << 16)
#define SOL_TCP 6
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2021 Google LLC.
+ */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__u32 invocations = 0;
+__u32 assertion_error = 0;
+__u32 retval_value = 0;
+__u32 ctx_retval_value = 0;
+
+SEC("cgroup/getsockopt")
+int get_retval(struct bpf_sockopt *ctx)
+{
+ retval_value = bpf_get_retval();
+ ctx_retval_value = ctx->retval;
+ __sync_fetch_and_add(&invocations, 1);
+
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int set_eisconn(struct bpf_sockopt *ctx)
+{
+ __sync_fetch_and_add(&invocations, 1);
+
+ if (bpf_set_retval(-EISCONN))
+ assertion_error = 1;
+
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int clear_retval(struct bpf_sockopt *ctx)
+{
+ __sync_fetch_and_add(&invocations, 1);
+
+ ctx->retval = 0;
+
+ return 1;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2021 Google LLC.
+ */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__u32 invocations = 0;
+__u32 assertion_error = 0;
+__u32 retval_value = 0;
+
+SEC("cgroup/setsockopt")
+int get_retval(struct bpf_sockopt *ctx)
+{
+ retval_value = bpf_get_retval();
+ __sync_fetch_and_add(&invocations, 1);
+
+ return 1;
+}
+
+SEC("cgroup/setsockopt")
+int set_eunatch(struct bpf_sockopt *ctx)
+{
+ __sync_fetch_and_add(&invocations, 1);
+
+ if (bpf_set_retval(-EUNATCH))
+ assertion_error = 1;
+
+ return 0;
+}
+
+SEC("cgroup/setsockopt")
+int set_eisconn(struct bpf_sockopt *ctx)
+{
+ __sync_fetch_and_add(&invocations, 1);
+
+ if (bpf_set_retval(-EISCONN))
+ assertion_error = 1;
+
+ return 0;
+}
+
+SEC("cgroup/setsockopt")
+int legacy_eperm(struct bpf_sockopt *ctx)
+{
+ __sync_fetch_and_add(&invocations, 1);
+
+ return 0;
+}
#include <bpf/bpf_endian.h>
#include <bpf/bpf_helpers.h>
-struct bpf_map_def SEC("maps") sock_map = {
- .type = BPF_MAP_TYPE_SOCKMAP,
- .key_size = sizeof(int),
- .value_size = sizeof(int),
- .max_entries = 2,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __type(key, int);
+ __type(value, int);
+ __uint(max_entries, 2);
+} sock_map SEC(".maps");
SEC("freplace/cls_redirect")
int freplace_cls_redirect_test(struct __sk_buff *skb)
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+extern void bpf_testmod_test_mod_kfunc(int i) __ksym;
+
+SEC("tc")
+int kfunc_call_fail(struct __sk_buff *ctx)
+{
+ bpf_testmod_test_mod_kfunc(0);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2021 Facebook */
-#include <linux/bpf.h>
+#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
__u32 c, __u64 d) __ksym;
+extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
+extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
+extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym;
+extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym;
+extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym;
+extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym;
+extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym;
+
SEC("tc")
int kfunc_call_test2(struct __sk_buff *skb)
{
return ret;
}
+SEC("tc")
+int kfunc_call_test_ref_btf_id(struct __sk_buff *skb)
+{
+ struct prog_test_ref_kfunc *pt;
+ unsigned long s = 0;
+ int ret = 0;
+
+ pt = bpf_kfunc_call_test_acquire(&s);
+ if (pt) {
+ if (pt->a != 42 || pt->b != 108)
+ ret = -1;
+ bpf_kfunc_call_test_release(pt);
+ }
+ return ret;
+}
+
+SEC("tc")
+int kfunc_call_test_pass(struct __sk_buff *skb)
+{
+ struct prog_test_pass1 p1 = {};
+ struct prog_test_pass2 p2 = {};
+ short a = 0;
+ __u64 b = 0;
+ long c = 0;
+ char d = 0;
+ int e = 0;
+
+ bpf_kfunc_call_test_pass_ctx(skb);
+ bpf_kfunc_call_test_pass1(&p1);
+ bpf_kfunc_call_test_pass2(&p2);
+
+ bpf_kfunc_call_test_mem_len_pass1(&a, sizeof(a));
+ bpf_kfunc_call_test_mem_len_pass1(&b, sizeof(b));
+ bpf_kfunc_call_test_mem_len_pass1(&c, sizeof(c));
+ bpf_kfunc_call_test_mem_len_pass1(&d, sizeof(d));
+ bpf_kfunc_call_test_mem_len_pass1(&e, sizeof(e));
+ bpf_kfunc_call_test_mem_len_fail2(&b, -1);
+
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+extern int bpf_testmod_ksym_percpu __ksym;
+
+SEC("tc")
+int ksym_fail(struct __sk_buff *ctx)
+{
+ return *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu);
+}
+
+char _license[] SEC("license") = "GPL";
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
-struct bpf_map_def SEC("maps") htab = {
- .type = BPF_MAP_TYPE_HASH,
- .key_size = sizeof(__u32),
- .value_size = sizeof(long),
- .max_entries = 2,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __u32);
+ __type(value, long);
+ __uint(max_entries, 2);
+} htab SEC(".maps");
-struct bpf_map_def SEC("maps") array = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(long),
- .max_entries = 2,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, long);
+ __uint(max_entries, 2);
+} array SEC(".maps");
/* Sample program which should always load for testing control paths. */
SEC(".text") int func()
{
void *data_end = (void *)(long) skb->data_end;
void *data = (void *)(long) skb->data;
- __u32 lport = skb->local_port;
- __u32 rport = skb->remote_port;
__u8 *d = data;
int err;
*/
if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
if (((struct tcp_zerocopy_receive *)optval)->address != 0)
- return 0; /* EPERM, unexpected data */
+ return 0; /* unexpected data */
return 1;
}
if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
if (optval + 1 > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
ctx->retval = 0; /* Reset system call return value to zero */
* bytes of data.
*/
if (optval_end - optval != page_size)
- return 0; /* EPERM, unexpected data size */
+ return 0; /* unexpected data size */
return 1;
}
if (ctx->level != SOL_CUSTOM)
- return 0; /* EPERM, deny everything except custom level */
+ return 0; /* deny everything except custom level */
if (optval + 1 > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0,
BPF_SK_STORAGE_GET_F_CREATE);
if (!storage)
- return 0; /* EPERM, couldn't get sk storage */
+ return 0; /* couldn't get sk storage */
if (!ctx->retval)
- return 0; /* EPERM, kernel should not have handled
+ return 0; /* kernel should not have handled
* SOL_CUSTOM, something is wrong!
*/
ctx->retval = 0; /* Reset system call return value to zero */
/* Overwrite SO_SNDBUF value */
if (optval + sizeof(__u32) > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
*(__u32 *)optval = 0x55AA;
ctx->optlen = 4;
/* Always use cubic */
if (optval + 5 > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
memcpy(optval, "cubic", 5);
ctx->optlen = 5;
if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
/* Original optlen is larger than PAGE_SIZE. */
if (ctx->optlen != page_size * 2)
- return 0; /* EPERM, unexpected data size */
+ return 0; /* unexpected data size */
if (optval + 1 > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
/* Make sure we can trim the buffer. */
optval[0] = 0;
* bytes of data.
*/
if (optval_end - optval != page_size)
- return 0; /* EPERM, unexpected data size */
+ return 0; /* unexpected data size */
return 1;
}
if (ctx->level != SOL_CUSTOM)
- return 0; /* EPERM, deny everything except custom level */
+ return 0; /* deny everything except custom level */
if (optval + 1 > optval_end)
- return 0; /* EPERM, bounds check */
+ return 0; /* bounds check */
storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0,
BPF_SK_STORAGE_GET_F_CREATE);
if (!storage)
- return 0; /* EPERM, couldn't get sk storage */
+ return 0; /* couldn't get sk storage */
storage->val = optval[0];
ctx->optlen = -1; /* BPF has consumed this option, don't call kernel
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+#define EAFNOSUPPORT 97
+#define EPROTO 71
+#define ENONET 64
+#define EINVAL 22
+#define ENOENT 2
+
+int test_einval_bpf_tuple = 0;
+int test_einval_reserved = 0;
+int test_einval_netns_id = 0;
+int test_einval_len_opts = 0;
+int test_eproto_l4proto = 0;
+int test_enonet_netns_id = 0;
+int test_enoent_lookup = 0;
+int test_eafnosupport = 0;
+
+struct nf_conn;
+
+struct bpf_ct_opts___local {
+ s32 netns_id;
+ s32 error;
+ u8 l4proto;
+ u8 reserved[3];
+} __attribute__((preserve_access_index));
+
+struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32) __ksym;
+struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32) __ksym;
+void bpf_ct_release(struct nf_conn *) __ksym;
+
+static __always_inline void
+nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32,
+ struct bpf_ct_opts___local *, u32),
+ void *ctx)
+{
+ struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 };
+ struct bpf_sock_tuple bpf_tuple;
+ struct nf_conn *ct;
+
+ __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4));
+
+ ct = func(ctx, NULL, 0, &opts_def, sizeof(opts_def));
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_einval_bpf_tuple = opts_def.error;
+
+ opts_def.reserved[0] = 1;
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ opts_def.reserved[0] = 0;
+ opts_def.l4proto = IPPROTO_TCP;
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_einval_reserved = opts_def.error;
+
+ opts_def.netns_id = -2;
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ opts_def.netns_id = -1;
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_einval_netns_id = opts_def.error;
+
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def) - 1);
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_einval_len_opts = opts_def.error;
+
+ opts_def.l4proto = IPPROTO_ICMP;
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ opts_def.l4proto = IPPROTO_TCP;
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_eproto_l4proto = opts_def.error;
+
+ opts_def.netns_id = 0xf00f;
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ opts_def.netns_id = -1;
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_enonet_netns_id = opts_def.error;
+
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def));
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_enoent_lookup = opts_def.error;
+
+ ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, sizeof(opts_def));
+ if (ct)
+ bpf_ct_release(ct);
+ else
+ test_eafnosupport = opts_def.error;
+}
+
+SEC("xdp")
+int nf_xdp_ct_test(struct xdp_md *ctx)
+{
+ nf_ct_test((void *)bpf_xdp_ct_lookup, ctx);
+ return 0;
+}
+
+SEC("tc")
+int nf_skb_ct_test(struct __sk_buff *ctx)
+{
+ nf_ct_test((void *)bpf_skb_ct_lookup, ctx);
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
unsigned int v6;
};
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
struct bpf_map_def SEC("maps") btf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(struct ipv_counts),
.max_entries = 4,
};
+#pragma GCC diagnostic pop
BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
unsigned int v6;
};
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
/* just to validate we can handle maps in multiple sections */
struct bpf_map_def SEC("maps") btf_map_legacy = {
.type = BPF_MAP_TYPE_ARRAY,
.value_size = sizeof(long long),
.max_entries = 4,
};
+#pragma GCC diagnostic pop
BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts);
unsigned int v6;
};
-struct bpf_map_def SEC("maps") btf_map = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(int),
- .value_size = sizeof(struct ipv_counts),
- .max_entries = 4,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(key_size, sizeof(int));
+ __uint(value_size, sizeof(struct ipv_counts));
+ __uint(max_entries, 4);
+} btf_map SEC(".maps");
__attribute__((noinline))
int test_long_fname_2(void)
#define NUM_CGROUP_LEVELS 4
-struct bpf_map_def SEC("maps") cgroup_ids = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u64),
- .max_entries = NUM_CGROUP_LEVELS,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u64);
+ __uint(max_entries, NUM_CGROUP_LEVELS);
+} cgroup_ids SEC(".maps");
static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
{
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SOCKMAP);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, __u64);
+} sock_map SEC(".maps");
+
+SEC("sk_skb")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ return SK_PASS;
+}
+
+SEC("sk_msg")
+int prog_skmsg_verdict(struct sk_msg_md *msg)
+{
+ return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
#define THROTTLE_RATE_BPS (5 * 1000 * 1000)
/* flow_key => last_tstamp timestamp used */
-struct bpf_map_def SEC("maps") flow_map = {
- .type = BPF_MAP_TYPE_HASH,
- .key_size = sizeof(uint32_t),
- .value_size = sizeof(uint64_t),
- .max_entries = 1,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, uint32_t);
+ __type(value, uint64_t);
+ __uint(max_entries, 1);
+} flow_map SEC(".maps");
static inline int throttle_flow(struct __sk_buff *skb)
{
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
-struct bpf_map_def SEC("maps") results = {
- .type = BPF_MAP_TYPE_ARRAY,
- .key_size = sizeof(__u32),
- .value_size = sizeof(__u32),
- .max_entries = 3,
-};
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 3);
+} results SEC(".maps");
static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk,
void *iph, __u32 ip_size,
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
- unsigned int data_len;
+ int data_len = bpf_xdp_get_buff_len(xdp);
int offset = 0;
/* Data length determine test case */
- data_len = data_end - data;
if (data_len == 54) { /* sizeof(pkt_v4) */
offset = 4096; /* test too large offset */
} else if (data_len == 64) {
offset = 128;
} else if (data_len == 128) {
- offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */
+ /* Max tail grow 3520 */
+ offset = 4096 - 256 - 320 - data_len;
+ } else if (data_len == 9000) {
+ offset = 10;
+ } else if (data_len == 9001) {
+ offset = 4096;
} else {
return XDP_ABORTED; /* No matching test */
}
SEC("xdp")
int _xdp_adjust_tail_shrink(struct xdp_md *xdp)
{
- void *data_end = (void *)(long)xdp->data_end;
- void *data = (void *)(long)xdp->data;
+ __u8 *data_end = (void *)(long)xdp->data_end;
+ __u8 *data = (void *)(long)xdp->data;
int offset = 0;
- if (data_end - data == 54) /* sizeof(pkt_v4) */
+ switch (bpf_xdp_get_buff_len(xdp)) {
+ case 54:
+ /* sizeof(pkt_v4) */
offset = 256; /* shrink too much */
- else
+ break;
+ case 9000:
+ /* non-linear buff test cases */
+ if (data + 1 > data_end)
+ return XDP_DROP;
+
+ switch (data[0]) {
+ case 0:
+ offset = 10;
+ break;
+ case 1:
+ offset = 4100;
+ break;
+ case 2:
+ offset = 8200;
+ break;
+ default:
+ return XDP_DROP;
+ }
+ break;
+ default:
offset = 20;
+ break;
+ }
if (bpf_xdp_adjust_tail(xdp, 0 - offset))
return XDP_DROP;
return XDP_TX;
void *data = (void *)(long)xdp->data;
meta.ifindex = xdp->rxq->dev->ifindex;
- meta.pkt_len = data_end - data;
+ meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp);
bpf_xdp_output(xdp, &perf_buf_map,
((__u64) meta.pkt_len << 32) |
BPF_F_CURRENT_CPU,
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <bpf/bpf_helpers.h>
+
+int _version SEC("version") = 1;
+
+SEC("xdp.frags")
+int xdp_adjust_frags(struct xdp_md *xdp)
+{
+ __u8 *data_end = (void *)(long)xdp->data_end;
+ __u8 *data = (void *)(long)xdp->data;
+ __u8 val[16] = {};
+ __u32 offset;
+ int err;
+
+ if (data + sizeof(__u32) > data_end)
+ return XDP_DROP;
+
+ offset = *(__u32 *)data;
+ err = bpf_xdp_load_bytes(xdp, offset, val, sizeof(val));
+ if (err < 0)
+ return XDP_DROP;
+
+ if (val[0] != 0xaa || val[15] != 0xaa) /* marker */
+ return XDP_DROP;
+
+ val[0] = 0xbb; /* update the marker */
+ val[15] = 0xbb;
+ err = bpf_xdp_store_bytes(xdp, offset, val, sizeof(val));
+ if (err < 0)
+ return XDP_DROP;
+
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define IFINDEX_LO 1
+
+struct {
+ __uint(type, BPF_MAP_TYPE_CPUMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_cpumap_val));
+ __uint(max_entries, 4);
+} cpu_map SEC(".maps");
+
+SEC("xdp_cpumap/dummy_cm")
+int xdp_dummy_cm(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+SEC("xdp.frags/cpumap")
+int xdp_dummy_cm_frags(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
return XDP_PASS;
}
+SEC("xdp.frags/cpumap")
+int xdp_dummy_cm_frags(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
char _license[] SEC("license") = "GPL";
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 4);
+} dm_ports SEC(".maps");
+
+/* valid program on DEVMAP entry via SEC name;
+ * has access to egress and ingress ifindex
+ */
+SEC("xdp_devmap/map_prog")
+int xdp_dummy_dm(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+SEC("xdp.frags/devmap")
+int xdp_dummy_dm_frags(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
return XDP_PASS;
}
+
+SEC("xdp.frags/devmap")
+int xdp_dummy_dm_frags(struct xdp_md *ctx)
+{
+ return XDP_PASS;
+}
+
char _license[] SEC("license") = "GPL";
#include <linux/if_ether.h>
#include <linux/btf.h>
+#include <bpf/btf.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
static int skips;
static bool verbose = false;
+struct kfunc_btf_id_pair {
+ const char *kfunc;
+ int insn_idx;
+};
+
struct bpf_test {
const char *descr;
struct bpf_insn insns[MAX_INSNS];
int fixup_map_reuseport_array[MAX_FIXUPS];
int fixup_map_ringbuf[MAX_FIXUPS];
int fixup_map_timer[MAX_FIXUPS];
+ struct kfunc_btf_id_pair fixup_kfunc_btf_id[MAX_FIXUPS];
/* Expected verifier log output for result REJECT or VERBOSE_ACCEPT.
* Can be a tab-separated sequence of expected strings. An empty string
* means no log verification.
int *fixup_map_reuseport_array = test->fixup_map_reuseport_array;
int *fixup_map_ringbuf = test->fixup_map_ringbuf;
int *fixup_map_timer = test->fixup_map_timer;
+ struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id;
if (test->fill_helper) {
test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
fixup_map_timer++;
} while (*fixup_map_timer);
}
+
+ /* Patch in kfunc BTF IDs */
+ if (fixup_kfunc_btf_id->kfunc) {
+ struct btf *btf;
+ int btf_id;
+
+ do {
+ btf_id = 0;
+ btf = btf__load_vmlinux_btf();
+ if (btf) {
+ btf_id = btf__find_by_name_kind(btf,
+ fixup_kfunc_btf_id->kfunc,
+ BTF_KIND_FUNC);
+ btf_id = btf_id < 0 ? 0 : btf_id;
+ }
+ btf__free(btf);
+ prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id;
+ fixup_kfunc_btf_id++;
+ } while (fixup_kfunc_btf_id->kfunc);
+ }
}
struct libcap {
.result = ACCEPT,
},
{
+ "calls: invalid kfunc call: ptr_to_mem to struct with non-scalar",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "arg#0 pointer type STRUCT prog_test_fail1 must point to scalar",
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_fail1", 2 },
+ },
+},
+{
+ "calls: invalid kfunc call: ptr_to_mem to struct with nesting depth > 4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "max struct nesting depth exceeded\narg#0 pointer type STRUCT prog_test_fail2",
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_fail2", 2 },
+ },
+},
+{
+ "calls: invalid kfunc call: ptr_to_mem to struct with FAM",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "arg#0 pointer type STRUCT prog_test_fail3 must point to scalar",
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_fail3", 2 },
+ },
+},
+{
+ "calls: invalid kfunc call: reg->type != PTR_TO_CTX",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "arg#0 expected pointer to ctx, but got PTR",
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_pass_ctx", 2 },
+ },
+},
+{
+ "calls: invalid kfunc call: void * not allowed in func proto without mem size arg",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "arg#0 pointer type UNKNOWN must point to scalar",
+ .fixup_kfunc_btf_id = {
+ { "bpf_kfunc_call_test_mem_len_fail1", 2 },
+ },
+},
+{
"calls: basic sanity",
.insns = {
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
return true;
case STAT_TEST_RX_FULL:
xsk_stat = stats.rx_ring_full;
- expected_stat -= RX_FULL_RXQSIZE;
+ if (ifobject->umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS)
+ expected_stat = ifobject->umem->num_frames - RX_FULL_RXQSIZE;
+ else
+ expected_stat = XSK_RING_PROD__DEFAULT_NUM_DESCS - RX_FULL_RXQSIZE;
break;
case STAT_TEST_RX_FILL_EMPTY:
xsk_stat = stats.rx_fill_ring_empty_descs;
fib_rule6_del_by_pref()
{
- pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1)
+ pref=$($IP -6 rule show $1 table $RTABLE | cut -d ":" -f 1)
$IP -6 rule del pref $pref
}
{
local match="$1"
local getmatch="$2"
+ local description="$3"
$IP -6 rule add $match table $RTABLE
$IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE"
- log_test $? 0 "rule6 check: $1"
+ log_test $? 0 "rule6 check: $description"
fib_rule6_del_by_pref "$match"
- log_test $? 0 "rule6 del by pref: $match"
+ log_test $? 0 "rule6 del by pref: $description"
}
fib_rule6_test()
{
+ local getmatch
+ local match
+
# setup the fib rule redirect route
$IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink
fib_rule4_del_by_pref()
{
- pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1)
+ pref=$($IP rule show $1 table $RTABLE | cut -d ":" -f 1)
$IP rule del pref $pref
}
{
local match="$1"
local getmatch="$2"
+ local description="$3"
$IP rule add $match table $RTABLE
$IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE"
- log_test $? 0 "rule4 check: $1"
+ log_test $? 0 "rule4 check: $description"
fib_rule4_del_by_pref "$match"
- log_test $? 0 "rule4 del by pref: $match"
+ log_test $? 0 "rule4 del by pref: $description"
}
fib_rule4_test()
{
+ local getmatch
+ local match
+
# setup the fib rule redirect route
$IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink
# need enable forwarding and disable rp_filter temporarily as all the
# addresses are in the same subnet and egress device == ingress device.
- ip netns exec testns sysctl -w net.ipv4.ip_forward=1
- ip netns exec testns sysctl -w net.ipv4.conf.$DEV.rp_filter=0
+ ip netns exec testns sysctl -qw net.ipv4.ip_forward=1
+ ip netns exec testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
match="from $SRC_IP iif $DEV"
fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table"
- ip netns exec testns sysctl -w net.ipv4.ip_forward=0
+ ip netns exec testns sysctl -qw net.ipv4.ip_forward=0
match="tos 0x10"
fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table"
switch_create()
{
- # 10 Seconds ageing time.
- ip link add dev br0 type bridge vlan_filtering 1 ageing_time 1000 \
+ ip link add dev br0 type bridge \
+ vlan_filtering 1 \
+ ageing_time $LOW_AGEING_TIME \
mcast_snooping 0
ip link set dev $swp1 master br0
switch_create()
{
- # 10 Seconds ageing time.
- ip link add dev br0 type bridge ageing_time 1000 mcast_snooping 0
+ ip link add dev br0 type bridge \
+ ageing_time $LOW_AGEING_TIME \
+ mcast_snooping 0
ip link set dev $swp1 master br0
ip link set dev $swp2 master br0
# Timeout (in seconds) before ping exits regardless of how many packets have
# been sent or received
PING_TIMEOUT=5
+# Minimum ageing_time (in centiseconds) supported by hardware
+LOW_AGEING_TIME=1000
# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process
# filter by software/hardware
TC_FLAG=skip_hw
PING_TIMEOUT=${PING_TIMEOUT:=5}
WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
+LOW_AGEING_TIME=${LOW_AGEING_TIME:=1000}
REQUIRE_JQ=${REQUIRE_JQ:=yes}
REQUIRE_MZ=${REQUIRE_MZ:=yes}
addr_nr_ns1="$7"
addr_nr_ns2="$8"
speed="$9"
- bkup="${10}"
+ sflags="${10}"
port=$((10000+$TEST_COUNT))
TEST_COUNT=$((TEST_COUNT+1))
fi
fi
- if [ ! -z $bkup ]; then
+ if [ ! -z $sflags ]; then
sleep 1
for netns in "$ns1" "$ns2"; do
dump=(`ip netns exec $netns ./pm_nl_ctl dump`)
if [ ${#dump[@]} -gt 0 ]; then
addr=${dump[${#dump[@]} - 1]}
- backup="ip netns exec $netns ./pm_nl_ctl set $addr flags $bkup"
- $backup
+ ip netns exec $netns ./pm_nl_ctl set $addr flags $sflags
fi
done
fi
addr_nr_ns1="${5:-0}"
addr_nr_ns2="${6:-0}"
speed="${7:-fast}"
- bkup="${8:-""}"
+ sflags="${8:-""}"
lret=0
oldin=""
fi
do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \
- ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup}
+ ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags}
lret=$?
}
run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow
chk_join_nr "fullmesh test 1x2, limited" 4 4 4
chk_add_nr 1 1
+
+ # set fullmesh flag
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 4 4
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags subflow
+ ip netns exec $ns2 ./pm_nl_ctl limits 4 4
+ run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh
+ chk_join_nr "set fullmesh flag test" 2 2 2
+ chk_rm_nr 0 1
+
+ # set nofullmesh flag
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 4 4
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags subflow,fullmesh
+ ip netns exec $ns2 ./pm_nl_ctl limits 4 4
+ run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh
+ chk_join_nr "set nofullmesh flag test" 2 2 2
+ chk_rm_nr 0 1
+
+ # set backup,fullmesh flags
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 4 4
+ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags subflow
+ ip netns exec $ns2 ./pm_nl_ctl limits 4 4
+ run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh
+ chk_join_nr "set backup,fullmesh flags test" 2 2 2
+ chk_prio_nr 0 1
+ chk_rm_nr 0 1
+
+ # set nobackup,nofullmesh flags
+ reset
+ ip netns exec $ns1 ./pm_nl_ctl limits 4 4
+ ip netns exec $ns2 ./pm_nl_ctl limits 4 4
+ ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow,backup,fullmesh
+ run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh
+ chk_join_nr "set nobackup,nofullmesh flags test" 2 2 2
+ chk_prio_nr 0 1
+ chk_rm_nr 0 1
}
all_tests()
fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n");
fprintf(stderr, "\tdel <id> [<ip>]\n");
fprintf(stderr, "\tget <id>\n");
- fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n");
+ fprintf(stderr, "\tset <ip> [flags backup|nobackup|fullmesh|nofullmesh]\n");
fprintf(stderr, "\tflush\n");
fprintf(stderr, "\tdump\n");
fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n");
if (++arg >= argc)
error(1, 0, " missing flags value");
- /* do not support flag list yet */
for (str = argv[arg]; (tok = strtok(str, ","));
str = NULL) {
if (!strcmp(tok, "backup"))
flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
- else if (strcmp(tok, "nobackup"))
+ else if (!strcmp(tok, "fullmesh"))
+ flags |= MPTCP_PM_ADDR_FLAG_FULLMESH;
+ else if (strcmp(tok, "nobackup") &&
+ strcmp(tok, "nofullmesh"))
error(1, errno,
"unknown flag %s", argv[arg]);
}
struct ifreq device;
struct ifreq hwtstamp;
struct hwtstamp_config hwconfig, hwconfig_requested;
- struct so_timestamping so_timestamping_get = { 0, -1 };
- struct so_timestamping so_timestamping = { 0, -1 };
+ struct so_timestamping so_timestamping_get = { 0, 0 };
+ struct so_timestamping so_timestamping = { 0, 0 };
struct sockaddr_in addr;
struct ip_mreq imr;
struct in_addr iaddr;
OSDN Git Service
