F: include/drm/i915*
F: include/uapi/drm/i915*
+ DRM DRIVERS FOR ATMEL HLCDC
+ M: Boris Brezillon <boris.brezillon@free-electrons.com>
+ L: dri-devel@lists.freedesktop.org
+ S: Supported
+ F: drivers/gpu/drm/atmel-hlcdc/
+ F: Documentation/devicetree/bindings/drm/atmel/
+
DRM DRIVERS FOR EXYNOS
M: Inki Dae <inki.dae@samsung.com>
M: Joonyoung Shim <jy0922.shim@samsung.com>
F: drivers/gpu/drm/imx/
F: Documentation/devicetree/bindings/drm/imx/
+ DRM DRIVERS FOR GMA500 (Poulsbo, Moorestown and derivative chipsets)
+ M: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
+ L: dri-devel@lists.freedesktop.org
+ T: git git://github.com/patjak/drm-gma500
+ S: Maintained
+ F: drivers/gpu/drm/gma500
+ F: include/drm/gma500*
+
DRM DRIVERS FOR NVIDIA TEGRA
M: Thierry Reding <thierry.reding@gmail.com>
M: Terje Bergström <tbergstrom@nvidia.com>
F: sound/usb/misc/ua101.c
EXTENSIBLE FIRMWARE INTERFACE (EFI)
- M: Matt Fleming <matt.fleming@intel.com>
+ M: Matt Fleming <matt@codeblueprint.co.uk>
L: linux-efi@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
S: Maintained
EFI VARIABLE FILESYSTEM
M: Matthew Garrett <matthew.garrett@nebula.com>
M: Jeremy Kerr <jk@ozlabs.org>
- M: Matt Fleming <matt.fleming@intel.com>
+ M: Matt Fleming <matt@codeblueprint.co.uk>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git
L: linux-efi@vger.kernel.org
S: Maintained
INTEL WIRELESS WIFI LINK (iwlwifi)
M: Johannes Berg <johannes.berg@intel.com>
M: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
-M: Intel Linux Wireless <ilw@linux.intel.com>
+M: Intel Linux Wireless <linuxwifi@intel.com>
L: linux-wireless@vger.kernel.org
W: http://intellinuxwireless.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git
F: drivers/auxdisplay/ks0108.c
F: include/linux/ks0108.h
+L3MDEV
+M: David Ahern <dsa@cumulusnetworks.com>
+L: netdev@vger.kernel.org
+S: Maintained
+F: net/l3mdev
+F: include/net/l3mdev.h
+
LAPB module
L: linux-x25@vger.kernel.org
S: Orphan
MELLANOX ETHERNET DRIVER (mlx4_en)
M: Amir Vadai <amirv@mellanox.com>
- M: Ido Shamay <idos@mellanox.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
L: linux-wpan@vger.kernel.org
S: Maintained
F: drivers/net/ieee802154/mrf24j40.c
+F: Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt
MSI LAPTOP SUPPORT
M: "Lee, Chun-Yi" <jlee@suse.com>
F: drivers/net/
F: include/linux/if_*
F: include/linux/netdevice.h
-F: include/linux/arcdevice.h
F: include/linux/etherdevice.h
F: include/linux/fcdevice.h
F: include/linux/fddidevice.h
F: Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
F: drivers/net/ethernet/synopsys/dwc_eth_qos.c
+ SYNOPSYS DESIGNWARE I2C DRIVER
+ M: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ M: Jarkko Nikula <jarkko.nikula@linux.intel.com>
+ M: Mika Westerberg <mika.westerberg@linux.intel.com>
+ L: linux-i2c@vger.kernel.org
+ S: Maintained
+ F: drivers/i2c/busses/i2c-designware-*
+ F: include/linux/platform_data/i2c-designware.h
+
SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
M: Seungwon Jeon <tgih.jun@samsung.com>
M: Jaehoon Chung <jh80.chung@samsung.com>
F: drivers/staging/lustre
STAGING - NVIDIA COMPLIANT EMBEDDED CONTROLLER INTERFACE (nvec)
- M: Julian Andres Klode <jak@jak-linux.org>
M: Marc Dietrich <marvin24@gmx.de>
L: ac100@lists.launchpad.net (moderated for non-subscribers)
L: linux-tegra@vger.kernel.org
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/vrf.c
-F: include/net/vrf.h
F: Documentation/networking/vrf.txt
VT1211 HARDWARE MONITOR DRIVER
S: Maintained
F: drivers/net/wireless/wl3501*
- WM97XX TOUCHSCREEN DRIVERS
- M: Mark Brown <broonie@kernel.org>
- M: Liam Girdwood <lrg@slimlogic.co.uk>
- L: linux-input@vger.kernel.org
- W: https://github.com/CirrusLogic/linux-drivers/wiki
- S: Supported
- F: drivers/input/touchscreen/*wm97*
- F: include/linux/wm97xx.h
-
WOLFSON MICROELECTRONICS DRIVERS
L: patches@opensource.wolfsonmicro.com
T: git https://github.com/CirrusLogic/linux-drivers.git
}
/*
- * Wrapper that handles both OABI and EABI and assures Thumb2 interworking
+ * Wrappers which handle both OABI and EABI and assures Thumb2 interworking
* (where the assembly routines like __aeabi_uidiv could cause problems).
*/
static u32 jit_udiv(u32 dividend, u32 divisor)
return dividend / divisor;
}
+static u32 jit_mod(u32 dividend, u32 divisor)
+{
+ return dividend % divisor;
+}
+
static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
{
inst |= (cond << 28);
#endif
}
-static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx)
+static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx,
+ int bpf_op)
{
#if __LINUX_ARM_ARCH__ == 7
if (elf_hwcap & HWCAP_IDIVA) {
- emit(ARM_UDIV(rd, rm, rn), ctx);
+ if (bpf_op == BPF_DIV)
+ emit(ARM_UDIV(rd, rm, rn), ctx);
+ else {
+ emit(ARM_UDIV(ARM_R3, rm, rn), ctx);
+ emit(ARM_MLS(rd, rn, ARM_R3, rm), ctx);
+ }
return;
}
#endif
emit(ARM_MOV_R(ARM_R0, rm), ctx);
ctx->seen |= SEEN_CALL;
- emit_mov_i(ARM_R3, (u32)jit_udiv, ctx);
+ emit_mov_i(ARM_R3, bpf_op == BPF_DIV ? (u32)jit_udiv : (u32)jit_mod,
+ ctx);
emit_blx_r(ARM_R3, ctx);
if (rd != ARM_R0)
case BPF_LD | BPF_B | BPF_IND:
load_order = 0;
load_ind:
+ update_on_xread(ctx);
OP_IMM3(ARM_ADD, r_off, r_X, k, ctx);
goto load_common;
case BPF_LDX | BPF_IMM:
if (k == 1)
break;
emit_mov_i(r_scratch, k, ctx);
- emit_udiv(r_A, r_A, r_scratch, ctx);
+ emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_DIV);
break;
case BPF_ALU | BPF_DIV | BPF_X:
update_on_xread(ctx);
emit(ARM_CMP_I(r_X, 0), ctx);
emit_err_ret(ARM_COND_EQ, ctx);
- emit_udiv(r_A, r_A, r_X, ctx);
+ emit_udivmod(r_A, r_A, r_X, ctx, BPF_DIV);
+ break;
+ case BPF_ALU | BPF_MOD | BPF_K:
+ if (k == 1) {
+ emit_mov_i(r_A, 0, ctx);
+ break;
+ }
+ emit_mov_i(r_scratch, k, ctx);
+ emit_udivmod(r_A, r_A, r_scratch, ctx, BPF_MOD);
+ break;
+ case BPF_ALU | BPF_MOD | BPF_X:
+ update_on_xread(ctx);
+ emit(ARM_CMP_I(r_X, 0), ctx);
+ emit_err_ret(ARM_COND_EQ, ctx);
+ emit_udivmod(r_A, r_A, r_X, ctx, BPF_MOD);
break;
case BPF_ALU | BPF_OR | BPF_K:
/* A |= K */
set_memory_ro((unsigned long)header, header->pages);
fp->bpf_func = (void *)ctx.target;
- fp->jited = true;
+ fp->jited = 1;
out:
kfree(ctx.offsets);
return;
bnx2x_fill_fw_str(bp, info->fw_version, sizeof(info->fw_version));
strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
- info->n_stats = BNX2X_NUM_STATS;
- info->testinfo_len = BNX2X_NUM_TESTS(bp);
- info->eedump_len = bp->common.flash_size;
- info->regdump_len = bnx2x_get_regs_len(dev);
}
static void bnx2x_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
udp_rss_requested = 0;
else
return -EINVAL;
+
+ if (CHIP_IS_E1x(bp) && udp_rss_requested) {
+ DP(BNX2X_MSG_ETHTOOL,
+ "57710, 57711 boards don't support RSS according to UDP 4-tuple\n");
+ return -EINVAL;
+ }
+
if ((info->flow_type == UDP_V4_FLOW) &&
(bp->rss_conf_obj.udp_rss_v4 != udp_rss_requested)) {
bp->rss_conf_obj.udp_rss_v4 = udp_rss_requested;
DMA_INDEX2RING_5,
DMA_INDEX2RING_6,
DMA_INDEX2RING_7,
+ DMA_RING0_TIMEOUT,
+ DMA_RING1_TIMEOUT,
+ DMA_RING2_TIMEOUT,
+ DMA_RING3_TIMEOUT,
+ DMA_RING4_TIMEOUT,
+ DMA_RING5_TIMEOUT,
+ DMA_RING6_TIMEOUT,
+ DMA_RING7_TIMEOUT,
+ DMA_RING8_TIMEOUT,
+ DMA_RING9_TIMEOUT,
+ DMA_RING10_TIMEOUT,
+ DMA_RING11_TIMEOUT,
+ DMA_RING12_TIMEOUT,
+ DMA_RING13_TIMEOUT,
+ DMA_RING14_TIMEOUT,
+ DMA_RING15_TIMEOUT,
+ DMA_RING16_TIMEOUT,
};
static const u8 bcmgenet_dma_regs_v3plus[] = {
[DMA_PRIORITY_0] = 0x30,
[DMA_PRIORITY_1] = 0x34,
[DMA_PRIORITY_2] = 0x38,
+ [DMA_RING0_TIMEOUT] = 0x2C,
+ [DMA_RING1_TIMEOUT] = 0x30,
+ [DMA_RING2_TIMEOUT] = 0x34,
+ [DMA_RING3_TIMEOUT] = 0x38,
+ [DMA_RING4_TIMEOUT] = 0x3c,
+ [DMA_RING5_TIMEOUT] = 0x40,
+ [DMA_RING6_TIMEOUT] = 0x44,
+ [DMA_RING7_TIMEOUT] = 0x48,
+ [DMA_RING8_TIMEOUT] = 0x4c,
+ [DMA_RING9_TIMEOUT] = 0x50,
+ [DMA_RING10_TIMEOUT] = 0x54,
+ [DMA_RING11_TIMEOUT] = 0x58,
+ [DMA_RING12_TIMEOUT] = 0x5c,
+ [DMA_RING13_TIMEOUT] = 0x60,
+ [DMA_RING14_TIMEOUT] = 0x64,
+ [DMA_RING15_TIMEOUT] = 0x68,
+ [DMA_RING16_TIMEOUT] = 0x6C,
[DMA_INDEX2RING_0] = 0x70,
[DMA_INDEX2RING_1] = 0x74,
[DMA_INDEX2RING_2] = 0x78,
[DMA_PRIORITY_0] = 0x34,
[DMA_PRIORITY_1] = 0x38,
[DMA_PRIORITY_2] = 0x3C,
+ [DMA_RING0_TIMEOUT] = 0x2C,
+ [DMA_RING1_TIMEOUT] = 0x30,
+ [DMA_RING2_TIMEOUT] = 0x34,
+ [DMA_RING3_TIMEOUT] = 0x38,
+ [DMA_RING4_TIMEOUT] = 0x3c,
+ [DMA_RING5_TIMEOUT] = 0x40,
+ [DMA_RING6_TIMEOUT] = 0x44,
+ [DMA_RING7_TIMEOUT] = 0x48,
+ [DMA_RING8_TIMEOUT] = 0x4c,
+ [DMA_RING9_TIMEOUT] = 0x50,
+ [DMA_RING10_TIMEOUT] = 0x54,
+ [DMA_RING11_TIMEOUT] = 0x58,
+ [DMA_RING12_TIMEOUT] = 0x5c,
+ [DMA_RING13_TIMEOUT] = 0x60,
+ [DMA_RING14_TIMEOUT] = 0x64,
+ [DMA_RING15_TIMEOUT] = 0x68,
+ [DMA_RING16_TIMEOUT] = 0x6C,
};
static const u8 bcmgenet_dma_regs_v1[] = {
[DMA_PRIORITY_0] = 0x34,
[DMA_PRIORITY_1] = 0x38,
[DMA_PRIORITY_2] = 0x3C,
+ [DMA_RING0_TIMEOUT] = 0x2C,
+ [DMA_RING1_TIMEOUT] = 0x30,
+ [DMA_RING2_TIMEOUT] = 0x34,
+ [DMA_RING3_TIMEOUT] = 0x38,
+ [DMA_RING4_TIMEOUT] = 0x3c,
+ [DMA_RING5_TIMEOUT] = 0x40,
+ [DMA_RING6_TIMEOUT] = 0x44,
+ [DMA_RING7_TIMEOUT] = 0x48,
+ [DMA_RING8_TIMEOUT] = 0x4c,
+ [DMA_RING9_TIMEOUT] = 0x50,
+ [DMA_RING10_TIMEOUT] = 0x54,
+ [DMA_RING11_TIMEOUT] = 0x58,
+ [DMA_RING12_TIMEOUT] = 0x5c,
+ [DMA_RING13_TIMEOUT] = 0x60,
+ [DMA_RING14_TIMEOUT] = 0x64,
+ [DMA_RING15_TIMEOUT] = 0x68,
+ [DMA_RING16_TIMEOUT] = 0x6C,
};
/* Set at runtime once bcmgenet version is known */
priv->msg_enable = level;
}
+static int bcmgenet_get_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *ec)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+
+ ec->tx_max_coalesced_frames =
+ bcmgenet_tdma_ring_readl(priv, DESC_INDEX,
+ DMA_MBUF_DONE_THRESH);
+ ec->rx_max_coalesced_frames =
+ bcmgenet_rdma_ring_readl(priv, DESC_INDEX,
+ DMA_MBUF_DONE_THRESH);
+ ec->rx_coalesce_usecs =
+ bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT) * 8192 / 1000;
+
+ return 0;
+}
+
+static int bcmgenet_set_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *ec)
+{
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ unsigned int i;
+ u32 reg;
+
+ /* Base system clock is 125Mhz, DMA timeout is this reference clock
+ * divided by 1024, which yields roughly 8.192us, our maximum value
+ * has to fit in the DMA_TIMEOUT_MASK (16 bits)
+ */
+ if (ec->tx_max_coalesced_frames > DMA_INTR_THRESHOLD_MASK ||
+ ec->tx_max_coalesced_frames == 0 ||
+ ec->rx_max_coalesced_frames > DMA_INTR_THRESHOLD_MASK ||
+ ec->rx_coalesce_usecs > (DMA_TIMEOUT_MASK * 8) + 1)
+ return -EINVAL;
+
+ if (ec->rx_coalesce_usecs == 0 && ec->rx_max_coalesced_frames == 0)
+ return -EINVAL;
+
+ /* GENET TDMA hardware does not support a configurable timeout, but will
+ * always generate an interrupt either after MBDONE packets have been
+ * transmitted, or when the ring is emtpy.
+ */
+ if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high ||
+ ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low)
+ return -EOPNOTSUPP;
+
+ /* Program all TX queues with the same values, as there is no
+ * ethtool knob to do coalescing on a per-queue basis
+ */
+ for (i = 0; i < priv->hw_params->tx_queues; i++)
+ bcmgenet_tdma_ring_writel(priv, i,
+ ec->tx_max_coalesced_frames,
+ DMA_MBUF_DONE_THRESH);
+ bcmgenet_tdma_ring_writel(priv, DESC_INDEX,
+ ec->tx_max_coalesced_frames,
+ DMA_MBUF_DONE_THRESH);
+
+ for (i = 0; i < priv->hw_params->rx_queues; i++) {
+ bcmgenet_rdma_ring_writel(priv, i,
+ ec->rx_max_coalesced_frames,
+ DMA_MBUF_DONE_THRESH);
+
+ reg = bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT + i);
+ reg &= ~DMA_TIMEOUT_MASK;
+ reg |= DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000, 8192);
+ bcmgenet_rdma_writel(priv, reg, DMA_RING0_TIMEOUT + i);
+ }
+
+ bcmgenet_rdma_ring_writel(priv, DESC_INDEX,
+ ec->rx_max_coalesced_frames,
+ DMA_MBUF_DONE_THRESH);
+
+ reg = bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT);
+ reg &= ~DMA_TIMEOUT_MASK;
+ reg |= DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000, 8192);
+ bcmgenet_rdma_writel(priv, reg, DMA_RING16_TIMEOUT);
+
+ return 0;
+}
+
/* standard ethtool support functions. */
enum bcmgenet_stat_type {
BCMGENET_STAT_NETDEV = -1,
{
strlcpy(info->driver, "bcmgenet", sizeof(info->driver));
strlcpy(info->version, "v2.0", sizeof(info->version));
- info->n_stats = BCMGENET_STATS_LEN;
}
static int bcmgenet_get_sset_count(struct net_device *dev, int string_set)
.get_eee = bcmgenet_get_eee,
.set_eee = bcmgenet_set_eee,
.nway_reset = bcmgenet_nway_reset,
+ .get_coalesce = bcmgenet_get_coalesce,
+ .set_coalesce = bcmgenet_set_coalesce,
};
/* Power down the unimac, based on mode. */
bcmgenet_intrl2_1_writel(priv, 0, INTRL2_CPU_MASK_CLEAR);
}
+ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
+ {
+ u32 int0_enable = 0;
+
+ /* Monitor cable plug/unplugged event for internal PHY, external PHY
+ * and MoCA PHY
+ */
+ if (priv->internal_phy) {
+ int0_enable |= UMAC_IRQ_LINK_EVENT;
+ } else if (priv->ext_phy) {
+ int0_enable |= UMAC_IRQ_LINK_EVENT;
+ } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
+ if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+ int0_enable |= UMAC_IRQ_LINK_EVENT;
+ }
+ bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
+ }
+
static int init_umac(struct bcmgenet_priv *priv)
{
struct device *kdev = &priv->pdev->dev;
/* Enable Tx default queue 16 interrupts */
int0_enable |= UMAC_IRQ_TXDMA_DONE;
- /* Monitor cable plug/unplugged event for internal PHY */
- if (priv->internal_phy) {
- int0_enable |= UMAC_IRQ_LINK_EVENT;
- } else if (priv->ext_phy) {
- int0_enable |= UMAC_IRQ_LINK_EVENT;
- } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
- if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
- int0_enable |= UMAC_IRQ_LINK_EVENT;
-
+ /* Configure backpressure vectors for MoCA */
+ if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
reg = bcmgenet_bp_mc_get(priv);
reg |= BIT(priv->hw_params->bp_in_en_shift);
netif_tx_start_all_queues(dev);
+ /* Monitor link interrupts now */
+ bcmgenet_link_intr_enable(priv);
+
phy_start(priv->phydev);
}
hw->aq.asq.next_to_use = 0;
hw->aq.asq.next_to_clean = 0;
- hw->aq.asq.count = hw->aq.num_asq_entries;
/* allocate the ring memory */
ret_code = i40e_alloc_adminq_asq_ring(hw);
goto init_adminq_free_rings;
/* success! */
+ hw->aq.asq.count = hw->aq.num_asq_entries;
goto init_adminq_exit;
init_adminq_free_rings:
hw->aq.arq.next_to_use = 0;
hw->aq.arq.next_to_clean = 0;
- hw->aq.arq.count = hw->aq.num_arq_entries;
/* allocate the ring memory */
ret_code = i40e_alloc_adminq_arq_ring(hw);
goto init_adminq_free_rings;
/* success! */
+ hw->aq.arq.count = hw->aq.num_arq_entries;
goto init_adminq_exit;
init_adminq_free_rings:
{
i40e_status ret_code = 0;
- if (hw->aq.asq.count == 0)
- return I40E_ERR_NOT_READY;
+ mutex_lock(&hw->aq.asq_mutex);
+
+ if (hw->aq.asq.count == 0) {
+ ret_code = I40E_ERR_NOT_READY;
+ goto shutdown_asq_out;
+ }
/* Stop firmware AdminQ processing */
wr32(hw, hw->aq.asq.head, 0);
wr32(hw, hw->aq.asq.bal, 0);
wr32(hw, hw->aq.asq.bah, 0);
- /* make sure lock is available */
- mutex_lock(&hw->aq.asq_mutex);
-
hw->aq.asq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers */
i40e_free_asq_bufs(hw);
+shutdown_asq_out:
mutex_unlock(&hw->aq.asq_mutex);
-
return ret_code;
}
{
i40e_status ret_code = 0;
- if (hw->aq.arq.count == 0)
- return I40E_ERR_NOT_READY;
+ mutex_lock(&hw->aq.arq_mutex);
+
+ if (hw->aq.arq.count == 0) {
+ ret_code = I40E_ERR_NOT_READY;
+ goto shutdown_arq_out;
+ }
/* Stop firmware AdminQ processing */
wr32(hw, hw->aq.arq.head, 0);
wr32(hw, hw->aq.arq.bal, 0);
wr32(hw, hw->aq.arq.bah, 0);
- /* make sure lock is available */
- mutex_lock(&hw->aq.arq_mutex);
-
hw->aq.arq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers */
i40e_free_arq_bufs(hw);
+shutdown_arq_out:
mutex_unlock(&hw->aq.arq_mutex);
-
return ret_code;
}
**/
i40e_status i40e_init_adminq(struct i40e_hw *hw)
{
- i40e_status ret_code;
+ u16 cfg_ptr, oem_hi, oem_lo;
u16 eetrack_lo, eetrack_hi;
+ i40e_status ret_code;
int retry = 0;
/* verify input for valid configuration */
i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_LO, &eetrack_lo);
i40e_read_nvm_word(hw, I40E_SR_NVM_EETRACK_HI, &eetrack_hi);
hw->nvm.eetrack = (eetrack_hi << 16) | eetrack_lo;
+ i40e_read_nvm_word(hw, I40E_SR_BOOT_CONFIG_PTR, &cfg_ptr);
+ i40e_read_nvm_word(hw, (cfg_ptr + I40E_NVM_OEM_VER_OFF),
+ &oem_hi);
+ i40e_read_nvm_word(hw, (cfg_ptr + (I40E_NVM_OEM_VER_OFF + 1)),
+ &oem_lo);
+ hw->nvm.oem_ver = ((u32)oem_hi << 16) | oem_lo;
if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) {
ret_code = I40E_ERR_FIRMWARE_API_VERSION;
/* destroy the locks */
+ if (hw->nvm_buff.va)
+ i40e_free_virt_mem(hw, &hw->nvm_buff);
+
return ret_code;
}
details = I40E_ADMINQ_DETAILS(*asq, ntc);
while (rd32(hw, hw->aq.asq.head) != ntc) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
- "%s: ntc %d head %d.\n", __func__, ntc,
- rd32(hw, hw->aq.asq.head));
+ "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
if (details->callback) {
I40E_ADMINQ_CALLBACK cb_func =
u16 retval = 0;
u32 val = 0;
- val = rd32(hw, hw->aq.asq.head);
- if (val >= hw->aq.num_asq_entries) {
+ mutex_lock(&hw->aq.asq_mutex);
+
+ if (hw->aq.asq.count == 0) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
- "AQTX: head overrun at %d\n", val);
+ "AQTX: Admin queue not initialized.\n");
status = I40E_ERR_QUEUE_EMPTY;
- goto asq_send_command_exit;
+ goto asq_send_command_error;
}
- if (hw->aq.asq.count == 0) {
+ hw->aq.asq_last_status = I40E_AQ_RC_OK;
+
+ val = rd32(hw, hw->aq.asq.head);
+ if (val >= hw->aq.num_asq_entries) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
- "AQTX: Admin queue not initialized.\n");
+ "AQTX: head overrun at %d\n", val);
status = I40E_ERR_QUEUE_EMPTY;
- goto asq_send_command_exit;
+ goto asq_send_command_error;
}
details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
desc->flags &= ~cpu_to_le16(details->flags_dis);
desc->flags |= cpu_to_le16(details->flags_ena);
- mutex_lock(&hw->aq.asq_mutex);
-
if (buff_size > hw->aq.asq_buf_size) {
i40e_debug(hw,
I40E_DEBUG_AQ_MESSAGE,
"AQTX: desc and buffer writeback:\n");
i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size);
+ /* save writeback aq if requested */
+ if (details->wb_desc)
+ *details->wb_desc = *desc_on_ring;
+
/* update the error if time out occurred */
if ((!cmd_completed) &&
(!details->async && !details->postpone)) {
asq_send_command_error:
mutex_unlock(&hw->aq.asq_mutex);
-asq_send_command_exit:
return status;
}
i40e_release_nvm(hw);
hw->aq.nvm_release_on_done = false;
}
+
+ switch (hw->nvmupd_state) {
+ case I40E_NVMUPD_STATE_INIT_WAIT:
+ hw->nvmupd_state = I40E_NVMUPD_STATE_INIT;
+ break;
+
+ case I40E_NVMUPD_STATE_WRITE_WAIT:
+ hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING;
+ break;
+
+ default:
+ break;
+ }
}
return ret_code;
#define DRV_VERSION_MAJOR 1
#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 9
+#define DRV_VERSION_BUILD 34
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_B), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_X722), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0},
/* required last entry */
{0, }
};
ret = i;
pile->search_hint = i + j;
break;
- } else {
- /* not enough, so skip over it and continue looking */
- i += j;
}
+
+ /* not enough, so skip over it and continue looking */
+ i += j;
}
return ret;
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
+ struct i40e_ring *tx_ring = NULL;
+ unsigned int i, hung_queue = 0;
+ u32 head, val;
pf->tx_timeout_count++;
+ /* find the stopped queue the same way the stack does */
+ for (i = 0; i < netdev->num_tx_queues; i++) {
+ struct netdev_queue *q;
+ unsigned long trans_start;
+
+ q = netdev_get_tx_queue(netdev, i);
+ trans_start = q->trans_start ? : netdev->trans_start;
+ if (netif_xmit_stopped(q) &&
+ time_after(jiffies,
+ (trans_start + netdev->watchdog_timeo))) {
+ hung_queue = i;
+ break;
+ }
+ }
+
+ if (i == netdev->num_tx_queues) {
+ netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
+ } else {
+ /* now that we have an index, find the tx_ring struct */
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
+ if (hung_queue ==
+ vsi->tx_rings[i]->queue_index) {
+ tx_ring = vsi->tx_rings[i];
+ break;
+ }
+ }
+ }
+ }
+
if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ*20)))
- pf->tx_timeout_recovery_level = 1;
+ pf->tx_timeout_recovery_level = 1; /* reset after some time */
+ else if (time_before(jiffies,
+ (pf->tx_timeout_last_recovery + netdev->watchdog_timeo)))
+ return; /* don't do any new action before the next timeout */
+
+ if (tx_ring) {
+ head = i40e_get_head(tx_ring);
+ /* Read interrupt register */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ val = rd32(&pf->hw,
+ I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx +
+ tx_ring->vsi->base_vector - 1));
+ else
+ val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
+
+ netdev_info(netdev, "tx_timeout: VSI_seid: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n",
+ vsi->seid, hung_queue, tx_ring->next_to_clean,
+ head, tx_ring->next_to_use,
+ readl(tx_ring->tail), val);
+ }
+
pf->tx_timeout_last_recovery = jiffies;
- netdev_info(netdev, "tx_timeout recovery level %d\n",
- pf->tx_timeout_recovery_level);
+ netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n",
+ pf->tx_timeout_recovery_level, hung_queue);
switch (pf->tx_timeout_recovery_level) {
- case 0:
- /* disable and re-enable queues for the VSI */
- if (in_interrupt()) {
- set_bit(__I40E_REINIT_REQUESTED, &pf->state);
- set_bit(__I40E_REINIT_REQUESTED, &vsi->state);
- } else {
- i40e_vsi_reinit_locked(vsi);
- }
- break;
case 1:
set_bit(__I40E_PF_RESET_REQUESTED, &pf->state);
break;
break;
default:
netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
- set_bit(__I40E_DOWN_REQUESTED, &pf->state);
- set_bit(__I40E_DOWN_REQUESTED, &vsi->state);
break;
}
+
i40e_service_event_schedule(pf);
pf->tx_timeout_recovery_level++;
}
stats->tx_errors = vsi_stats->tx_errors;
stats->tx_dropped = vsi_stats->tx_dropped;
stats->rx_errors = vsi_stats->rx_errors;
+ stats->rx_dropped = vsi_stats->rx_dropped;
stats->rx_crc_errors = vsi_stats->rx_crc_errors;
stats->rx_length_errors = vsi_stats->rx_length_errors;
memset(&vsi->eth_stats_offsets, 0, sizeof(vsi->eth_stats_offsets));
if (vsi->rx_rings && vsi->rx_rings[0]) {
for (i = 0; i < vsi->num_queue_pairs; i++) {
- memset(&vsi->rx_rings[i]->stats, 0 ,
+ memset(&vsi->rx_rings[i]->stats, 0,
sizeof(vsi->rx_rings[i]->stats));
- memset(&vsi->rx_rings[i]->rx_stats, 0 ,
+ memset(&vsi->rx_rings[i]->rx_stats, 0,
sizeof(vsi->rx_rings[i]->rx_stats));
- memset(&vsi->tx_rings[i]->stats, 0 ,
+ memset(&vsi->tx_rings[i]->stats, 0,
sizeof(vsi->tx_rings[i]->stats));
memset(&vsi->tx_rings[i]->tx_stats, 0,
sizeof(vsi->tx_rings[i]->tx_stats));
struct i40e_hw_port_stats *nsd = &pf->stats;
struct i40e_hw *hw = &pf->hw;
u64 xoff = 0;
- u16 i, v;
if ((hw->fc.current_mode != I40E_FC_FULL) &&
(hw->fc.current_mode != I40E_FC_RX_PAUSE))
if (!(nsd->link_xoff_rx - xoff))
return;
- /* Clear the __I40E_HANG_CHECK_ARMED bit for all Tx rings */
- for (v = 0; v < pf->num_alloc_vsi; v++) {
- struct i40e_vsi *vsi = pf->vsi[v];
-
- if (!vsi || !vsi->tx_rings[0])
- continue;
-
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- struct i40e_ring *ring = vsi->tx_rings[i];
- clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state);
- }
- }
}
/**
bool xoff[I40E_MAX_TRAFFIC_CLASS] = {false};
struct i40e_dcbx_config *dcb_cfg;
struct i40e_hw *hw = &pf->hw;
- u16 i, v;
+ u16 i;
u8 tc;
dcb_cfg = &hw->local_dcbx_config;
for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
u64 prio_xoff = nsd->priority_xoff_rx[i];
+
i40e_stat_update32(hw, I40E_GLPRT_PXOFFRXC(hw->port, i),
pf->stat_offsets_loaded,
&osd->priority_xoff_rx[i],
tc = dcb_cfg->etscfg.prioritytable[i];
xoff[tc] = true;
}
-
- /* Clear the __I40E_HANG_CHECK_ARMED bit for Tx rings */
- for (v = 0; v < pf->num_alloc_vsi; v++) {
- struct i40e_vsi *vsi = pf->vsi[v];
-
- if (!vsi || !vsi->tx_rings[0])
- continue;
-
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- struct i40e_ring *ring = vsi->tx_rings[i];
-
- tc = ring->dcb_tc;
- if (xoff[tc])
- clear_bit(__I40E_HANG_CHECK_ARMED,
- &ring->state);
- }
- }
}
/**
u32 rx_page, rx_buf;
u64 bytes, packets;
unsigned int start;
+ u64 tx_linearize;
u64 rx_p, rx_b;
u64 tx_p, tx_b;
u16 q;
*/
rx_b = rx_p = 0;
tx_b = tx_p = 0;
- tx_restart = tx_busy = 0;
+ tx_restart = tx_busy = tx_linearize = 0;
rx_page = 0;
rx_buf = 0;
rcu_read_lock();
tx_p += packets;
tx_restart += p->tx_stats.restart_queue;
tx_busy += p->tx_stats.tx_busy;
+ tx_linearize += p->tx_stats.tx_linearize;
/* Rx queue is part of the same block as Tx queue */
p = &p[1];
rcu_read_unlock();
vsi->tx_restart = tx_restart;
vsi->tx_busy = tx_busy;
+ vsi->tx_linearize = tx_linearize;
vsi->rx_page_failed = rx_page;
vsi->rx_buf_failed = rx_buf;
* so we have to go through all the list in order to make sure
*/
list_for_each_entry(f, &vsi->mac_filter_list, list) {
- if (f->vlan >= 0)
+ if (f->vlan >= 0 || vsi->info.pvid)
return true;
}
} else {
/* make sure we don't remove a filter in use by VF or netdev */
int min_f = 0;
+
min_f += (f->is_vf ? 1 : 0);
min_f += (f->is_netdev ? 1 : 0);
if (vsi->type == I40E_VSI_MAIN) {
i40e_status ret;
+
ret = i40e_aq_mac_address_write(&vsi->back->hw,
I40E_AQC_WRITE_TYPE_LAA_WOL,
addr->sa_data, NULL);
f->is_laa = true;
}
- i40e_sync_vsi_filters(vsi);
+ i40e_sync_vsi_filters(vsi, false);
ether_addr_copy(netdev->dev_addr, addr->sa_data);
return 0;
/* remove filter if not in netdev list */
list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) {
- bool found = false;
if (!f->is_netdev)
continue;
- if (is_multicast_ether_addr(f->macaddr)) {
- netdev_for_each_mc_addr(mca, netdev) {
- if (ether_addr_equal(mca->addr, f->macaddr)) {
- found = true;
- break;
- }
- }
- } else {
- netdev_for_each_uc_addr(uca, netdev) {
- if (ether_addr_equal(uca->addr, f->macaddr)) {
- found = true;
- break;
- }
- }
+ netdev_for_each_mc_addr(mca, netdev)
+ if (ether_addr_equal(mca->addr, f->macaddr))
+ goto bottom_of_search_loop;
- for_each_dev_addr(netdev, ha) {
- if (ether_addr_equal(ha->addr, f->macaddr)) {
- found = true;
- break;
- }
- }
- }
- if (!found)
- i40e_del_filter(
- vsi, f->macaddr, I40E_VLAN_ANY, false, true);
+ netdev_for_each_uc_addr(uca, netdev)
+ if (ether_addr_equal(uca->addr, f->macaddr))
+ goto bottom_of_search_loop;
+
+ for_each_dev_addr(netdev, ha)
+ if (ether_addr_equal(ha->addr, f->macaddr))
+ goto bottom_of_search_loop;
+
+ /* f->macaddr wasn't found in uc, mc, or ha list so delete it */
+ i40e_del_filter(vsi, f->macaddr, I40E_VLAN_ANY, false, true);
+
+bottom_of_search_loop:
+ continue;
}
/* check for other flag changes */
/**
* i40e_sync_vsi_filters - Update the VSI filter list to the HW
* @vsi: ptr to the VSI
+ * @grab_rtnl: whether RTNL needs to be grabbed
*
* Push any outstanding VSI filter changes through the AdminQ.
*
* Returns 0 or error value
**/
-int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
+int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl)
{
struct i40e_mac_filter *f, *ftmp;
bool promisc_forced_on = false;
/* check for changes in promiscuous modes */
if (changed_flags & IFF_ALLMULTI) {
bool cur_multipromisc;
+
cur_multipromisc = !!(vsi->current_netdev_flags & IFF_ALLMULTI);
ret = i40e_aq_set_vsi_multicast_promiscuous(&vsi->back->hw,
vsi->seid,
}
if ((changed_flags & IFF_PROMISC) || promisc_forced_on) {
bool cur_promisc;
+
cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
test_bit(__I40E_FILTER_OVERFLOW_PROMISC,
&vsi->state));
*/
if (pf->cur_promisc != cur_promisc) {
pf->cur_promisc = cur_promisc;
- i40e_do_reset_safe(pf,
+ if (grab_rtnl)
+ i40e_do_reset_safe(pf,
+ BIT(__I40E_PF_RESET_REQUESTED));
+ else
+ i40e_do_reset(pf,
BIT(__I40E_PF_RESET_REQUESTED));
}
} else {
for (v = 0; v < pf->num_alloc_vsi; v++) {
if (pf->vsi[v] &&
(pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED))
- i40e_sync_vsi_filters(pf->vsi[v]);
+ i40e_sync_vsi_filters(pf->vsi[v], true);
}
}
test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
return 0;
- return i40e_sync_vsi_filters(vsi);
+ return i40e_sync_vsi_filters(vsi, false);
}
/**
test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
return 0;
- return i40e_sync_vsi_filters(vsi);
+ return i40e_sync_vsi_filters(vsi, false);
}
/**
wr32(hw, I40E_QTX_CTL(pf_q), qtx_ctl);
i40e_flush(hw);
- clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state);
-
/* cache tail off for easier writes later */
ring->tail = hw->hw_addr + I40E_QTX_TAIL(pf_q);
static void i40e_vsi_configure_msix(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
- struct i40e_q_vector *q_vector;
struct i40e_hw *hw = &pf->hw;
u16 vector;
int i, q;
- u32 val;
u32 qp;
/* The interrupt indexing is offset by 1 in the PFINT_ITRn
qp = vsi->base_queue;
vector = vsi->base_vector;
for (i = 0; i < vsi->num_q_vectors; i++, vector++) {
- q_vector = vsi->q_vectors[i];
+ struct i40e_q_vector *q_vector = vsi->q_vectors[i];
+
q_vector->rx.itr = ITR_TO_REG(vsi->rx_itr_setting);
q_vector->rx.latency_range = I40E_LOW_LATENCY;
wr32(hw, I40E_PFINT_ITRN(I40E_RX_ITR, vector - 1),
q_vector->tx.latency_range = I40E_LOW_LATENCY;
wr32(hw, I40E_PFINT_ITRN(I40E_TX_ITR, vector - 1),
q_vector->tx.itr);
+ wr32(hw, I40E_PFINT_RATEN(vector - 1),
+ INTRL_USEC_TO_REG(vsi->int_rate_limit));
/* Linked list for the queuepairs assigned to this vector */
wr32(hw, I40E_PFINT_LNKLSTN(vector - 1), qp);
for (q = 0; q < q_vector->num_ringpairs; q++) {
+ u32 val;
+
val = I40E_QINT_RQCTL_CAUSE_ENA_MASK |
(I40E_RX_ITR << I40E_QINT_RQCTL_ITR_INDX_SHIFT) |
(vector << I40E_QINT_RQCTL_MSIX_INDX_SHIFT) |
i40e_flush(hw);
}
-/**
- * i40e_irq_dynamic_enable - Enable default interrupt generation settings
- * @vsi: pointer to a vsi
- * @vector: enable a particular Hw Interrupt vector
- **/
-void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector)
-{
- struct i40e_pf *pf = vsi->back;
- struct i40e_hw *hw = &pf->hw;
- u32 val;
-
- val = I40E_PFINT_DYN_CTLN_INTENA_MASK |
- I40E_PFINT_DYN_CTLN_CLEARPBA_MASK |
- (I40E_ITR_NONE << I40E_PFINT_DYN_CTLN_ITR_INDX_SHIFT);
- wr32(hw, I40E_PFINT_DYN_CTLN(vector - 1), val);
- /* skip the flush */
-}
-
/**
* i40e_irq_dynamic_disable - Disable default interrupt generation settings
* @vsi: pointer to a vsi
q_vector);
if (err) {
dev_info(&pf->pdev->dev,
- "%s: request_irq failed, error: %d\n",
- __func__, err);
+ "MSIX request_irq failed, error: %d\n", err);
goto free_queue_irqs;
}
/* assign the mask for this irq */
int i;
if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
- for (i = vsi->base_vector;
- i < (vsi->num_q_vectors + vsi->base_vector); i++)
+ for (i = 0; i < vsi->num_q_vectors; i++)
i40e_irq_dynamic_enable(vsi, i);
} else {
i40e_irq_dynamic_enable_icr0(pf);
/* temporarily disable queue cause for NAPI processing */
u32 qval = rd32(hw, I40E_QINT_RQCTL(0));
+
qval &= ~I40E_QINT_RQCTL_CAUSE_ENA_MASK;
wr32(hw, I40E_QINT_RQCTL(0), qval);
i += tx_ring->count;
tx_ring->next_to_clean = i;
- if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED) {
- i40e_irq_dynamic_enable(vsi,
- tx_ring->q_vector->v_idx + vsi->base_vector);
- }
+ if (vsi->back->flags & I40E_FLAG_MSIX_ENABLED)
+ i40e_irq_dynamic_enable(vsi, tx_ring->q_vector->v_idx);
+
return budget > 0;
}
if (test_bit(__I40E_DOWN, &vsi->state))
return;
- pf->flags |= I40E_FLAG_IN_NETPOLL;
if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
for (i = 0; i < vsi->num_q_vectors; i++)
i40e_msix_clean_rings(0, vsi->q_vectors[i]);
} else {
i40e_intr(pf->pdev->irq, netdev);
}
- pf->flags &= ~I40E_FLAG_IN_NETPOLL;
}
#endif
ret = i40e_pf_txq_wait(pf, pf_q, enable);
if (ret) {
dev_info(&pf->pdev->dev,
- "%s: VSI seid %d Tx ring %d %sable timeout\n",
- __func__, vsi->seid, pf_q,
- (enable ? "en" : "dis"));
+ "VSI seid %d Tx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
break;
}
}
ret = i40e_pf_rxq_wait(pf, pf_q, enable);
if (ret) {
dev_info(&pf->pdev->dev,
- "%s: VSI seid %d Rx ring %d %sable timeout\n",
- __func__, vsi->seid, pf_q,
- (enable ? "en" : "dis"));
+ "VSI seid %d Rx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
break;
}
}
if ((test_bit(__I40E_PORT_TX_SUSPENDED, &vsi->back->state)) &&
vsi->type == I40E_VSI_FCOE) {
dev_dbg(&vsi->back->pdev->dev,
- "%s: VSI seid %d skipping FCoE VSI disable\n",
- __func__, vsi->seid);
+ "VSI seid %d skipping FCoE VSI disable\n", vsi->seid);
return;
}
set_bit(__I40E_NEEDS_RESTART, &vsi->state);
- if (vsi->netdev && netif_running(vsi->netdev)) {
+ if (vsi->netdev && netif_running(vsi->netdev))
vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
- } else {
+ else
i40e_vsi_close(vsi);
- }
}
/**
ret = i40e_pf_txq_wait(pf, pf_q, false);
if (ret) {
dev_info(&pf->pdev->dev,
- "%s: VSI seid %d Tx ring %d disable timeout\n",
- __func__, vsi->seid, pf_q);
+ "VSI seid %d Tx ring %d disable timeout\n",
+ vsi->seid, pf_q);
return ret;
}
}
}
#endif
+
+/**
+ * i40e_detect_recover_hung_queue - Function to detect and recover hung_queue
+ * @q_idx: TX queue number
+ * @vsi: Pointer to VSI struct
+ *
+ * This function checks specified queue for given VSI. Detects hung condition.
+ * Sets hung bit since it is two step process. Before next run of service task
+ * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not,
+ * hung condition remain unchanged and during subsequent run, this function
+ * issues SW interrupt to recover from hung condition.
+ **/
+static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi)
+{
+ struct i40e_ring *tx_ring = NULL;
+ struct i40e_pf *pf;
+ u32 head, val, tx_pending;
+ int i;
+
+ pf = vsi->back;
+
+ /* now that we have an index, find the tx_ring struct */
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
+ if (q_idx == vsi->tx_rings[i]->queue_index) {
+ tx_ring = vsi->tx_rings[i];
+ break;
+ }
+ }
+ }
+
+ if (!tx_ring)
+ return;
+
+ /* Read interrupt register */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ val = rd32(&pf->hw,
+ I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx +
+ tx_ring->vsi->base_vector - 1));
+ else
+ val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
+
+ head = i40e_get_head(tx_ring);
+
+ tx_pending = i40e_get_tx_pending(tx_ring);
+
+ /* Interrupts are disabled and TX pending is non-zero,
+ * trigger the SW interrupt (don't wait). Worst case
+ * there will be one extra interrupt which may result
+ * into not cleaning any queues because queues are cleaned.
+ */
+ if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK)))
+ i40e_force_wb(vsi, tx_ring->q_vector);
+}
+
+/**
+ * i40e_detect_recover_hung - Function to detect and recover hung_queues
+ * @pf: pointer to PF struct
+ *
+ * LAN VSI has netdev and netdev has TX queues. This function is to check
+ * each of those TX queues if they are hung, trigger recovery by issuing
+ * SW interrupt.
+ **/
+static void i40e_detect_recover_hung(struct i40e_pf *pf)
+{
+ struct net_device *netdev;
+ struct i40e_vsi *vsi;
+ int i;
+
+ /* Only for LAN VSI */
+ vsi = pf->vsi[pf->lan_vsi];
+
+ if (!vsi)
+ return;
+
+ /* Make sure, VSI state is not DOWN/RECOVERY_PENDING */
+ if (test_bit(__I40E_DOWN, &vsi->back->state) ||
+ test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state))
+ return;
+
+ /* Make sure type is MAIN VSI */
+ if (vsi->type != I40E_VSI_MAIN)
+ return;
+
+ netdev = vsi->netdev;
+ if (!netdev)
+ return;
+
+ /* Bail out if netif_carrier is not OK */
+ if (!netif_carrier_ok(netdev))
+ return;
+
+ /* Go thru' TX queues for netdev */
+ for (i = 0; i < netdev->num_tx_queues; i++) {
+ struct netdev_queue *q;
+
+ q = netdev_get_tx_queue(netdev, i);
+ if (q)
+ i40e_detect_recover_hung_queue(i, vsi);
+ }
+}
+
/**
* i40e_get_iscsi_tc_map - Return TC map for iSCSI APP
* @pf: pointer to PF
* i40e_print_link_message - print link up or down
* @vsi: the VSI for which link needs a message
*/
-static void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
+void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
{
- char speed[SPEED_SIZE] = "Unknown";
- char fc[FC_SIZE] = "RX/TX";
+ char *speed = "Unknown";
+ char *fc = "Unknown";
+ if (vsi->current_isup == isup)
+ return;
+ vsi->current_isup = isup;
if (!isup) {
netdev_info(vsi->netdev, "NIC Link is Down\n");
return;
switch (vsi->back->hw.phy.link_info.link_speed) {
case I40E_LINK_SPEED_40GB:
- strlcpy(speed, "40 Gbps", SPEED_SIZE);
+ speed = "40 G";
break;
case I40E_LINK_SPEED_20GB:
- strncpy(speed, "20 Gbps", SPEED_SIZE);
+ speed = "20 G";
break;
case I40E_LINK_SPEED_10GB:
- strlcpy(speed, "10 Gbps", SPEED_SIZE);
+ speed = "10 G";
break;
case I40E_LINK_SPEED_1GB:
- strlcpy(speed, "1000 Mbps", SPEED_SIZE);
+ speed = "1000 M";
break;
case I40E_LINK_SPEED_100MB:
- strncpy(speed, "100 Mbps", SPEED_SIZE);
+ speed = "100 M";
break;
default:
break;
switch (vsi->back->hw.fc.current_mode) {
case I40E_FC_FULL:
- strlcpy(fc, "RX/TX", FC_SIZE);
+ fc = "RX/TX";
break;
case I40E_FC_TX_PAUSE:
- strlcpy(fc, "TX", FC_SIZE);
+ fc = "TX";
break;
case I40E_FC_RX_PAUSE:
- strlcpy(fc, "RX", FC_SIZE);
+ fc = "RX";
break;
default:
- strlcpy(fc, "None", FC_SIZE);
+ fc = "None";
break;
}
- netdev_info(vsi->netdev, "NIC Link is Up %s Full Duplex, Flow Control: %s\n",
+ netdev_info(vsi->netdev, "NIC Link is Up %sbps Full Duplex, Flow Control: %s\n",
speed, fc);
}
"VSI reinit requested\n");
for (v = 0; v < pf->num_alloc_vsi; v++) {
struct i40e_vsi *vsi = pf->vsi[v];
+
if (vsi != NULL &&
test_bit(__I40E_REINIT_REQUESTED, &vsi->state)) {
i40e_vsi_reinit_locked(pf->vsi[v]);
clear_bit(__I40E_REINIT_REQUESTED, &vsi->state);
}
}
-
- /* no further action needed, so return now */
- return;
} else if (reset_flags & BIT_ULL(__I40E_DOWN_REQUESTED)) {
int v;
dev_info(&pf->pdev->dev, "VSI down requested\n");
for (v = 0; v < pf->num_alloc_vsi; v++) {
struct i40e_vsi *vsi = pf->vsi[v];
+
if (vsi != NULL &&
test_bit(__I40E_DOWN_REQUESTED, &vsi->state)) {
set_bit(__I40E_DOWN, &vsi->state);
clear_bit(__I40E_DOWN_REQUESTED, &vsi->state);
}
}
-
- /* no further action needed, so return now */
- return;
} else {
dev_info(&pf->pdev->dev,
"bad reset request 0x%08x\n", reset_flags);
- return;
}
}
dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");
}
- dev_dbg(&pf->pdev->dev, "%s: need_reconfig=%d\n", __func__,
- need_reconfig);
+ dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig);
return need_reconfig;
}
/* Ignore if event is not for Nearest Bridge */
type = ((mib->type >> I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT)
& I40E_AQ_LLDP_BRIDGE_TYPE_MASK);
- dev_dbg(&pf->pdev->dev,
- "%s: LLDP event mib bridge type 0x%x\n", __func__, type);
+ dev_dbg(&pf->pdev->dev, "LLDP event mib bridge type 0x%x\n", type);
if (type != I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE)
return ret;
/* Check MIB Type and return if event for Remote MIB update */
type = mib->type & I40E_AQ_LLDP_MIB_TYPE_MASK;
dev_dbg(&pf->pdev->dev,
- "%s: LLDP event mib type %s\n", __func__,
- type ? "remote" : "local");
+ "LLDP event mib type %s\n", type ? "remote" : "local");
if (type == I40E_AQ_LLDP_MIB_REMOTE) {
/* Update the remote cached instance and return */
ret = i40e_aq_get_dcb_config(hw, I40E_AQ_LLDP_MIB_REMOTE,
**/
void i40e_fdir_check_and_reenable(struct i40e_pf *pf)
{
+ struct i40e_fdir_filter *filter;
u32 fcnt_prog, fcnt_avail;
+ struct hlist_node *node;
if (test_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state))
return;
dev_info(&pf->pdev->dev, "ATR is being enabled since we have space in the table now\n");
}
}
+
+ /* if hw had a problem adding a filter, delete it */
+ if (pf->fd_inv > 0) {
+ hlist_for_each_entry_safe(filter, node,
+ &pf->fdir_filter_list, fdir_node) {
+ if (filter->fd_id == pf->fd_inv) {
+ hlist_del(&filter->fdir_node);
+ kfree(filter);
+ pf->fdir_pf_active_filters--;
+ }
+ }
+ }
}
#define I40E_MIN_FD_FLUSH_INTERVAL 10
if (!(pf->flags & (I40E_FLAG_FD_SB_ENABLED | I40E_FLAG_FD_ATR_ENABLED)))
return;
- if (time_after(jiffies, pf->fd_flush_timestamp +
- (I40E_MIN_FD_FLUSH_INTERVAL * HZ))) {
- /* If the flush is happening too quick and we have mostly
- * SB rules we should not re-enable ATR for some time.
- */
- min_flush_time = pf->fd_flush_timestamp
- + (I40E_MIN_FD_FLUSH_SB_ATR_UNSTABLE * HZ);
- fd_room = pf->fdir_pf_filter_count - pf->fdir_pf_active_filters;
+ if (!time_after(jiffies, pf->fd_flush_timestamp +
+ (I40E_MIN_FD_FLUSH_INTERVAL * HZ)))
+ return;
- if (!(time_after(jiffies, min_flush_time)) &&
- (fd_room < I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) {
- if (I40E_DEBUG_FD & pf->hw.debug_mask)
- dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
- disable_atr = true;
- }
+ /* If the flush is happening too quick and we have mostly SB rules we
+ * should not re-enable ATR for some time.
+ */
+ min_flush_time = pf->fd_flush_timestamp +
+ (I40E_MIN_FD_FLUSH_SB_ATR_UNSTABLE * HZ);
+ fd_room = pf->fdir_pf_filter_count - pf->fdir_pf_active_filters;
- pf->fd_flush_timestamp = jiffies;
- pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
- /* flush all filters */
- wr32(&pf->hw, I40E_PFQF_CTL_1,
- I40E_PFQF_CTL_1_CLEARFDTABLE_MASK);
- i40e_flush(&pf->hw);
- pf->fd_flush_cnt++;
- pf->fd_add_err = 0;
- do {
- /* Check FD flush status every 5-6msec */
- usleep_range(5000, 6000);
- reg = rd32(&pf->hw, I40E_PFQF_CTL_1);
- if (!(reg & I40E_PFQF_CTL_1_CLEARFDTABLE_MASK))
- break;
- } while (flush_wait_retry--);
- if (reg & I40E_PFQF_CTL_1_CLEARFDTABLE_MASK) {
- dev_warn(&pf->pdev->dev, "FD table did not flush, needs more time\n");
- } else {
- /* replay sideband filters */
- i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
- if (!disable_atr)
- pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
- clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
- if (I40E_DEBUG_FD & pf->hw.debug_mask)
- dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
- }
+ if (!(time_after(jiffies, min_flush_time)) &&
+ (fd_room < I40E_FDIR_BUFFER_HEAD_ROOM_FOR_ATR)) {
+ if (I40E_DEBUG_FD & pf->hw.debug_mask)
+ dev_info(&pf->pdev->dev, "ATR disabled, not enough FD filter space.\n");
+ disable_atr = true;
}
+
+ pf->fd_flush_timestamp = jiffies;
+ pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED;
+ /* flush all filters */
+ wr32(&pf->hw, I40E_PFQF_CTL_1,
+ I40E_PFQF_CTL_1_CLEARFDTABLE_MASK);
+ i40e_flush(&pf->hw);
+ pf->fd_flush_cnt++;
+ pf->fd_add_err = 0;
+ do {
+ /* Check FD flush status every 5-6msec */
+ usleep_range(5000, 6000);
+ reg = rd32(&pf->hw, I40E_PFQF_CTL_1);
+ if (!(reg & I40E_PFQF_CTL_1_CLEARFDTABLE_MASK))
+ break;
+ } while (flush_wait_retry--);
+ if (reg & I40E_PFQF_CTL_1_CLEARFDTABLE_MASK) {
+ dev_warn(&pf->pdev->dev, "FD table did not flush, needs more time\n");
+ } else {
+ /* replay sideband filters */
+ i40e_fdir_filter_restore(pf->vsi[pf->lan_vsi]);
+ if (!disable_atr)
+ pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
+ clear_bit(__I40E_FD_FLUSH_REQUESTED, &pf->state);
+ if (I40E_DEBUG_FD & pf->hw.debug_mask)
+ dev_info(&pf->pdev->dev, "FD Filter table flushed and FD-SB replayed.\n");
+ }
+
}
/**
**/
static void i40e_link_event(struct i40e_pf *pf)
{
- bool new_link, old_link;
struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
u8 new_link_speed, old_link_speed;
+ i40e_status status;
+ bool new_link, old_link;
/* set this to force the get_link_status call to refresh state */
pf->hw.phy.get_link_info = true;
old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP);
- new_link = i40e_get_link_status(&pf->hw);
+
+ status = i40e_get_link_status(&pf->hw, &new_link);
+ if (status) {
+ dev_dbg(&pf->pdev->dev, "couldn't get link state, status: %d\n",
+ status);
+ return;
+ }
+
old_link_speed = pf->hw.phy.link_info_old.link_speed;
new_link_speed = pf->hw.phy.link_info.link_speed;
i40e_ptp_set_increment(pf);
}
-/**
- * i40e_check_hang_subtask - Check for hung queues and dropped interrupts
- * @pf: board private structure
- *
- * Set the per-queue flags to request a check for stuck queues in the irq
- * clean functions, then force interrupts to be sure the irq clean is called.
- **/
-static void i40e_check_hang_subtask(struct i40e_pf *pf)
-{
- int i, v;
-
- /* If we're down or resetting, just bail */
- if (test_bit(__I40E_DOWN, &pf->state) ||
- test_bit(__I40E_CONFIG_BUSY, &pf->state))
- return;
-
- /* for each VSI/netdev
- * for each Tx queue
- * set the check flag
- * for each q_vector
- * force an interrupt
- */
- for (v = 0; v < pf->num_alloc_vsi; v++) {
- struct i40e_vsi *vsi = pf->vsi[v];
- int armed = 0;
-
- if (!pf->vsi[v] ||
- test_bit(__I40E_DOWN, &vsi->state) ||
- (vsi->netdev && !netif_carrier_ok(vsi->netdev)))
- continue;
-
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- set_check_for_tx_hang(vsi->tx_rings[i]);
- if (test_bit(__I40E_HANG_CHECK_ARMED,
- &vsi->tx_rings[i]->state))
- armed++;
- }
-
- if (armed) {
- if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) {
- wr32(&vsi->back->hw, I40E_PFINT_DYN_CTL0,
- (I40E_PFINT_DYN_CTL0_INTENA_MASK |
- I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK |
- I40E_PFINT_DYN_CTL0_ITR_INDX_MASK |
- I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK |
- I40E_PFINT_DYN_CTL0_SW_ITR_INDX_MASK));
- } else {
- u16 vec = vsi->base_vector - 1;
- u32 val = (I40E_PFINT_DYN_CTLN_INTENA_MASK |
- I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK |
- I40E_PFINT_DYN_CTLN_ITR_INDX_MASK |
- I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK |
- I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK);
- for (i = 0; i < vsi->num_q_vectors; i++, vec++)
- wr32(&vsi->back->hw,
- I40E_PFINT_DYN_CTLN(vec), val);
- }
- i40e_flush(&vsi->back->hw);
- }
- }
-}
-
/**
* i40e_watchdog_subtask - periodic checks not using event driven response
* @pf: board private structure
return;
pf->service_timer_previous = jiffies;
- i40e_check_hang_subtask(pf);
- i40e_link_event(pf);
+ if (pf->flags & I40E_FLAG_LINK_POLLING_ENABLED)
+ i40e_link_event(pf);
/* Update the stats for active netdevs so the network stack
* can look at updated numbers whenever it cares to
if (pf->vsi[i] && pf->vsi[i]->netdev)
i40e_update_stats(pf->vsi[i]);
- /* Update the stats for the active switching components */
- for (i = 0; i < I40E_MAX_VEB; i++)
- if (pf->veb[i])
- i40e_update_veb_stats(pf->veb[i]);
+ if (pf->flags & I40E_FLAG_VEB_STATS_ENABLED) {
+ /* Update the stats for the active switching components */
+ for (i = 0; i < I40E_MAX_VEB; i++)
+ if (pf->veb[i])
+ i40e_update_veb_stats(pf->veb[i]);
+ }
i40e_ptp_rx_hang(pf->vsi[pf->lan_vsi]);
}
{
struct i40e_pf *pf = veb->pf;
- dev_info(&pf->pdev->dev, "enabling bridge mode: %s\n",
- veb->bridge_mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
+ if (pf->hw.debug_mask & I40E_DEBUG_LAN)
+ dev_info(&pf->pdev->dev, "enabling bridge mode: %s\n",
+ veb->bridge_mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
if (veb->bridge_mode & BRIDGE_MODE_VEPA)
i40e_disable_pf_switch_lb(pf);
else
if (pf->vsi[v]->veb_idx == veb->idx) {
struct i40e_vsi *vsi = pf->vsi[v];
+
vsi->uplink_seid = veb->seid;
ret = i40e_add_vsi(vsi);
if (ret) {
}
} while (err);
- if (((pf->hw.aq.fw_maj_ver == 2) && (pf->hw.aq.fw_min_ver < 22)) ||
- (pf->hw.aq.fw_maj_ver < 2)) {
- pf->hw.func_caps.num_msix_vectors++;
- pf->hw.func_caps.num_msix_vectors_vf++;
- }
-
if (pf->hw.debug_mask & I40E_DEBUG_USER)
dev_info(&pf->pdev->dev,
"pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n",
}
#endif /* CONFIG_I40E_DCB */
#ifdef I40E_FCOE
- ret = i40e_init_pf_fcoe(pf);
- if (ret)
- dev_info(&pf->pdev->dev, "init_pf_fcoe failed: %d\n", ret);
+ i40e_init_pf_fcoe(pf);
#endif
/* do basic switch setup */
/* make sure our flow control settings are restored */
ret = i40e_set_fc(&pf->hw, &set_fc_aq_fail, true);
if (ret)
- dev_info(&pf->pdev->dev, "set fc fail, err %s aq_err %s\n",
- i40e_stat_str(&pf->hw, ret),
- i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+ dev_dbg(&pf->pdev->dev, "setting flow control: ret = %s last_status = %s\n",
+ i40e_stat_str(&pf->hw, ret),
+ i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
/* Rebuild the VSIs and VEBs that existed before reset.
* They are still in our local switch element arrays, so only
return;
}
+ i40e_detect_recover_hung(pf);
i40e_reset_subtask(pf);
i40e_handle_mdd_event(pf);
i40e_vc_process_vflr_event(pf);
vsi->idx = vsi_idx;
vsi->rx_itr_setting = pf->rx_itr_default;
vsi->tx_itr_setting = pf->tx_itr_default;
+ vsi->int_rate_limit = 0;
vsi->rss_table_size = (vsi->type == I40E_VSI_MAIN) ?
pf->rss_table_size : 64;
vsi->netdev_registered = false;
"Cannot set RSS key, err %s aq_err %s\n",
i40e_stat_str(&pf->hw, ret),
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
- return ret;
+ goto config_rss_aq_out;
}
if (vsi->type == I40E_VSI_MAIN)
i40e_stat_str(&pf->hw, ret),
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+config_rss_aq_out:
+ kfree(rss_lut);
return ret;
}
/* Set default capability flags */
pf->flags = I40E_FLAG_RX_CSUM_ENABLED |
I40E_FLAG_MSI_ENABLED |
+ I40E_FLAG_LINK_POLLING_ENABLED |
I40E_FLAG_MSIX_ENABLED;
if (iommu_present(&pci_bus_type))
(pf->hw.func_caps.fd_filters_best_effort > 0)) {
pf->flags |= I40E_FLAG_FD_ATR_ENABLED;
pf->atr_sample_rate = I40E_DEFAULT_ATR_SAMPLE_RATE;
- if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) {
- pf->flags |= I40E_FLAG_FD_SB_ENABLED;
- } else {
+ if (pf->flags & I40E_FLAG_MFP_ENABLED &&
+ pf->hw.num_partitions > 1)
dev_info(&pf->pdev->dev,
"Flow Director Sideband mode Disabled in MFP mode\n");
- }
+ else
+ pf->flags |= I40E_FLAG_FD_SB_ENABLED;
pf->fdir_pf_filter_count =
pf->hw.func_caps.fd_filters_guaranteed;
pf->hw.fdir_shared_filter_count =
}
#ifdef I40E_FCOE
- err = i40e_init_pf_fcoe(pf);
- if (err)
- dev_info(&pf->pdev->dev, "init_pf_fcoe failed: %d\n", err);
+ i40e_init_pf_fcoe(pf);
#endif /* I40E_FCOE */
#ifdef CONFIG_PCI_IOV
pf->lan_veb = I40E_NO_VEB;
pf->lan_vsi = I40E_NO_VSI;
+ /* By default FW has this off for performance reasons */
+ pf->flags &= ~I40E_FLAG_VEB_STATS_ENABLED;
+
/* set up queue assignment tracking */
size = sizeof(struct i40e_lump_tracking)
+ (sizeof(u16) * pf->hw.func_caps.num_tx_qp);
pf->vxlan_ports[idx] = 0;
pf->pending_vxlan_bitmap |= BIT_ULL(idx);
pf->flags |= I40E_FLAG_VXLAN_FILTER_SYNC;
-
- dev_info(&pf->pdev->dev, "deleting vxlan port %d\n",
- ntohs(port));
} else {
netdev_warn(netdev, "vxlan port %d was not found, not deleting\n",
ntohs(port));
* @seq: RTNL message seq #
* @dev: the netdev being configured
* @filter_mask: unused
+ * @nlflags: netlink flags passed in
*
* Return the mode in which the hardware bridge is operating in
* i.e VEB or VEPA.
**/
static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
struct net_device *dev,
- u32 filter_mask, int nlflags)
+ u32 __always_unused filter_mask,
+ int nlflags)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
netdev->hw_enc_features |= NETIF_F_IP_CSUM |
NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_GSO_GRE |
NETIF_F_TSO;
netdev->features = NETIF_F_SG |
NETIF_F_SCTP_CSUM |
NETIF_F_HIGHDMA |
NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_GSO_GRE |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_FILTER |
list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list)
i40e_del_filter(vsi, f->macaddr, f->vlan,
f->is_vf, f->is_netdev);
- i40e_sync_vsi_filters(vsi);
+ i40e_sync_vsi_filters(vsi, false);
i40e_vsi_delete(vsi);
i40e_vsi_free_q_vectors(vsi);
if (veb) {
if (vsi->seid != pf->vsi[pf->lan_vsi]->seid) {
dev_info(&vsi->back->pdev->dev,
- "%s: New VSI creation error, uplink seid of LAN VSI expected.\n",
- __func__);
+ "New VSI creation error, uplink seid of LAN VSI expected.\n");
return NULL;
}
/* We come up by default in VEPA mode if SRIOV is not
} else {
/* force a reset of TC and queue layout configurations */
u8 enabled_tc = pf->vsi[pf->lan_vsi]->tc_config.enabled_tc;
+
pf->vsi[pf->lan_vsi]->tc_config.enabled_tc = 0;
pf->vsi[pf->lan_vsi]->seid = pf->main_vsi_seid;
i40e_vsi_config_tc(pf->vsi[pf->lan_vsi], enabled_tc);
i40e_config_rss(pf);
/* fill in link information and enable LSE reporting */
- i40e_aq_get_link_info(&pf->hw, true, NULL, NULL);
+ i40e_update_link_info(&pf->hw);
i40e_link_event(pf);
/* Initialize user-specific link properties */
}
pf->queues_left = queues_left;
+ dev_dbg(&pf->pdev->dev,
+ "qs_avail=%d FD SB=%d lan_qs=%d lan_tc0=%d vf=%d*%d vmdq=%d*%d, remaining=%d\n",
+ pf->hw.func_caps.num_tx_qp,
+ !!(pf->flags & I40E_FLAG_FD_SB_ENABLED),
+ pf->num_lan_qps, pf->rss_size, pf->num_req_vfs, pf->num_vf_qps,
+ pf->num_vmdq_vsis, pf->num_vmdq_qps, queues_left);
#ifdef I40E_FCOE
- dev_info(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps);
+ dev_dbg(&pf->pdev->dev, "fcoe queues = %d\n", pf->num_fcoe_qps);
#endif
}
}
if (pf->flags & I40E_FLAG_DCB_CAPABLE)
buf += sprintf(buf, "DCB ");
+#if IS_ENABLED(CONFIG_VXLAN)
+ buf += sprintf(buf, "VxLAN ");
+#endif
if (pf->flags & I40E_FLAG_PTP)
buf += sprintf(buf, "PTP ");
#ifdef I40E_FCOE
if (pf->flags & I40E_FLAG_FCOE_ENABLED)
buf += sprintf(buf, "FCOE ");
#endif
+ if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
+ buf += sprintf(buf, "VEB ");
+ else
+ buf += sprintf(buf, "VEPA ");
BUG_ON(buf > (string + INFO_STRING_LEN));
dev_info(&pf->pdev->dev, "%s\n", string);
static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
struct i40e_aq_get_phy_abilities_resp abilities;
- unsigned long ioremap_len;
struct i40e_pf *pf;
struct i40e_hw *hw;
static u16 pfs_found;
+ u16 wol_nvm_bits;
u16 link_status;
int err = 0;
u32 len;
hw = &pf->hw;
hw->back = pf;
- ioremap_len = min_t(unsigned long, pci_resource_len(pdev, 0),
- I40E_MAX_CSR_SPACE);
+ pf->ioremap_len = min_t(int, pci_resource_len(pdev, 0),
+ I40E_MAX_CSR_SPACE);
- hw->hw_addr = ioremap(pci_resource_start(pdev, 0), ioremap_len);
+ hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pf->ioremap_len);
if (!hw->hw_addr) {
err = -EIO;
dev_info(&pdev->dev, "ioremap(0x%04x, 0x%04x) failed: 0x%x\n",
(unsigned int)pci_resource_start(pdev, 0),
- (unsigned int)pci_resource_len(pdev, 0), err);
+ pf->ioremap_len, err);
goto err_ioremap;
}
hw->vendor_id = pdev->vendor;
pf->hw.fc.requested_mode = I40E_FC_NONE;
err = i40e_init_adminq(hw);
- dev_info(&pdev->dev, "%s\n", i40e_fw_version_str(hw));
+
+ /* provide nvm, fw, api versions */
+ dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
+ hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build,
+ hw->aq.api_maj_ver, hw->aq.api_min_ver,
+ i40e_nvm_version_str(hw));
+
if (err) {
dev_info(&pdev->dev,
"The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
INIT_WORK(&pf->service_task, i40e_service_task);
clear_bit(__I40E_SERVICE_SCHED, &pf->state);
pf->flags |= I40E_FLAG_NEED_LINK_UPDATE;
- pf->link_check_timeout = jiffies;
- /* WoL defaults to disabled */
- pf->wol_en = false;
+ /* NVM bit on means WoL disabled for the port */
+ i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits);
+ if ((1 << hw->port) & wol_nvm_bits || hw->partition_id != 1)
+ pf->wol_en = false;
+ else
+ pf->wol_en = true;
device_set_wakeup_enable(&pf->pdev->dev, pf->wol_en);
/* set up the main switch operations */
i40e_fcoe_vsi_setup(pf);
#endif
- /* Get the negotiated link width and speed from PCI config space */
- pcie_capability_read_word(pf->pdev, PCI_EXP_LNKSTA, &link_status);
+#define PCI_SPEED_SIZE 8
+#define PCI_WIDTH_SIZE 8
+ /* Devices on the IOSF bus do not have this information
+ * and will report PCI Gen 1 x 1 by default so don't bother
+ * checking them.
+ */
+ if (!(pf->flags & I40E_FLAG_NO_PCI_LINK_CHECK)) {
+ char speed[PCI_SPEED_SIZE] = "Unknown";
+ char width[PCI_WIDTH_SIZE] = "Unknown";
- i40e_set_pci_config_data(hw, link_status);
+ /* Get the negotiated link width and speed from PCI config
+ * space
+ */
+ pcie_capability_read_word(pf->pdev, PCI_EXP_LNKSTA,
+ &link_status);
+
+ i40e_set_pci_config_data(hw, link_status);
+
+ switch (hw->bus.speed) {
+ case i40e_bus_speed_8000:
+ strncpy(speed, "8.0", PCI_SPEED_SIZE); break;
+ case i40e_bus_speed_5000:
+ strncpy(speed, "5.0", PCI_SPEED_SIZE); break;
+ case i40e_bus_speed_2500:
+ strncpy(speed, "2.5", PCI_SPEED_SIZE); break;
+ default:
+ break;
+ }
+ switch (hw->bus.width) {
+ case i40e_bus_width_pcie_x8:
+ strncpy(width, "8", PCI_WIDTH_SIZE); break;
+ case i40e_bus_width_pcie_x4:
+ strncpy(width, "4", PCI_WIDTH_SIZE); break;
+ case i40e_bus_width_pcie_x2:
+ strncpy(width, "2", PCI_WIDTH_SIZE); break;
+ case i40e_bus_width_pcie_x1:
+ strncpy(width, "1", PCI_WIDTH_SIZE); break;
+ default:
+ break;
+ }
- dev_info(&pdev->dev, "PCI-Express: %s %s\n",
- (hw->bus.speed == i40e_bus_speed_8000 ? "Speed 8.0GT/s" :
- hw->bus.speed == i40e_bus_speed_5000 ? "Speed 5.0GT/s" :
- hw->bus.speed == i40e_bus_speed_2500 ? "Speed 2.5GT/s" :
- "Unknown"),
- (hw->bus.width == i40e_bus_width_pcie_x8 ? "Width x8" :
- hw->bus.width == i40e_bus_width_pcie_x4 ? "Width x4" :
- hw->bus.width == i40e_bus_width_pcie_x2 ? "Width x2" :
- hw->bus.width == i40e_bus_width_pcie_x1 ? "Width x1" :
- "Unknown"));
+ dev_info(&pdev->dev, "PCI-Express: Speed %sGT/s Width x%s\n",
+ speed, width);
- if (hw->bus.width < i40e_bus_width_pcie_x8 ||
- hw->bus.speed < i40e_bus_speed_8000) {
- dev_warn(&pdev->dev, "PCI-Express bandwidth available for this device may be insufficient for optimal performance.\n");
- dev_warn(&pdev->dev, "Please move the device to a different PCI-e link with more lanes and/or higher transfer rate.\n");
+ if (hw->bus.width < i40e_bus_width_pcie_x8 ||
+ hw->bus.speed < i40e_bus_speed_8000) {
+ dev_warn(&pdev->dev, "PCI-Express bandwidth available for this device may be insufficient for optimal performance.\n");
+ dev_warn(&pdev->dev, "Please move the device to a different PCI-e link with more lanes and/or higher transfer rate.\n");
+ }
}
/* get the requested speeds from the fw */
err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL);
if (err)
- dev_info(&pf->pdev->dev,
- "get phy capabilities failed, err %s aq_err %s, advertised speed settings may not be correct\n",
- i40e_stat_str(&pf->hw, err),
- i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+ dev_dbg(&pf->pdev->dev, "get requested speeds ret = %s last_status = %s\n",
+ i40e_stat_str(&pf->hw, err),
+ i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
+ /* get the supported phy types from the fw */
+ err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
+ if (err)
+ dev_dbg(&pf->pdev->dev, "get supported phy types ret = %s last_status = %s\n",
+ i40e_stat_str(&pf->hw, err),
+ i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+ pf->hw.phy.phy_types = le32_to_cpu(abilities.phy_type);
+
/* print a string summarizing features */
i40e_print_features(pf);
int err;
u32 reg;
- dev_info(&pdev->dev, "%s\n", __func__);
+ dev_dbg(&pdev->dev, "%s\n", __func__);
if (pci_enable_device_mem(pdev)) {
dev_info(&pdev->dev,
"Cannot re-enable PCI device after reset.\n");
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
- dev_info(&pdev->dev, "%s\n", __func__);
+ dev_dbg(&pdev->dev, "%s\n", __func__);
if (test_bit(__I40E_SUSPENDED, &pf->state))
return;
rtnl_lock();
i40e_handle_reset_warning(pf);
- rtnl_lock();
+ rtnl_unlock();
}
/**
err = pci_enable_device_mem(pdev);
if (err) {
- dev_err(&pdev->dev,
- "%s: Cannot enable PCI device from suspend\n",
- __func__);
+ dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
return err;
}
pci_set_master(pdev);
hw->aq.asq.next_to_use = 0;
hw->aq.asq.next_to_clean = 0;
- hw->aq.asq.count = hw->aq.num_asq_entries;
/* allocate the ring memory */
ret_code = i40e_alloc_adminq_asq_ring(hw);
goto init_adminq_free_rings;
/* success! */
+ hw->aq.asq.count = hw->aq.num_asq_entries;
goto init_adminq_exit;
init_adminq_free_rings:
hw->aq.arq.next_to_use = 0;
hw->aq.arq.next_to_clean = 0;
- hw->aq.arq.count = hw->aq.num_arq_entries;
/* allocate the ring memory */
ret_code = i40e_alloc_adminq_arq_ring(hw);
goto init_adminq_free_rings;
/* success! */
+ hw->aq.arq.count = hw->aq.num_arq_entries;
goto init_adminq_exit;
init_adminq_free_rings:
{
i40e_status ret_code = 0;
- if (hw->aq.asq.count == 0)
- return I40E_ERR_NOT_READY;
+ mutex_lock(&hw->aq.asq_mutex);
+
+ if (hw->aq.asq.count == 0) {
+ ret_code = I40E_ERR_NOT_READY;
+ goto shutdown_asq_out;
+ }
/* Stop firmware AdminQ processing */
wr32(hw, hw->aq.asq.head, 0);
wr32(hw, hw->aq.asq.bal, 0);
wr32(hw, hw->aq.asq.bah, 0);
- /* make sure lock is available */
- mutex_lock(&hw->aq.asq_mutex);
-
hw->aq.asq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers */
i40e_free_asq_bufs(hw);
+shutdown_asq_out:
mutex_unlock(&hw->aq.asq_mutex);
-
return ret_code;
}
{
i40e_status ret_code = 0;
- if (hw->aq.arq.count == 0)
- return I40E_ERR_NOT_READY;
+ mutex_lock(&hw->aq.arq_mutex);
+
+ if (hw->aq.arq.count == 0) {
+ ret_code = I40E_ERR_NOT_READY;
+ goto shutdown_arq_out;
+ }
/* Stop firmware AdminQ processing */
wr32(hw, hw->aq.arq.head, 0);
wr32(hw, hw->aq.arq.bal, 0);
wr32(hw, hw->aq.arq.bah, 0);
- /* make sure lock is available */
- mutex_lock(&hw->aq.arq_mutex);
-
hw->aq.arq.count = 0; /* to indicate uninitialized queue */
/* free ring buffers */
i40e_free_arq_bufs(hw);
+shutdown_arq_out:
mutex_unlock(&hw->aq.arq_mutex);
-
return ret_code;
}
/* destroy the locks */
+ if (hw->nvm_buff.va)
+ i40e_free_virt_mem(hw, &hw->nvm_buff);
+
return ret_code;
}
details = I40E_ADMINQ_DETAILS(*asq, ntc);
while (rd32(hw, hw->aq.asq.head) != ntc) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
- "%s: ntc %d head %d.\n", __func__, ntc,
- rd32(hw, hw->aq.asq.head));
+ "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head));
if (details->callback) {
I40E_ADMINQ_CALLBACK cb_func =
u16 retval = 0;
u32 val = 0;
- val = rd32(hw, hw->aq.asq.head);
- if (val >= hw->aq.num_asq_entries) {
+ mutex_lock(&hw->aq.asq_mutex);
+
+ if (hw->aq.asq.count == 0) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
- "AQTX: head overrun at %d\n", val);
+ "AQTX: Admin queue not initialized.\n");
status = I40E_ERR_QUEUE_EMPTY;
- goto asq_send_command_exit;
+ goto asq_send_command_error;
}
- if (hw->aq.asq.count == 0) {
+ hw->aq.asq_last_status = I40E_AQ_RC_OK;
+
+ val = rd32(hw, hw->aq.asq.head);
+ if (val >= hw->aq.num_asq_entries) {
i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
- "AQTX: Admin queue not initialized.\n");
+ "AQTX: head overrun at %d\n", val);
status = I40E_ERR_QUEUE_EMPTY;
- goto asq_send_command_exit;
+ goto asq_send_command_error;
}
details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
desc->flags &= ~cpu_to_le16(details->flags_dis);
desc->flags |= cpu_to_le16(details->flags_ena);
- mutex_lock(&hw->aq.asq_mutex);
-
if (buff_size > hw->aq.asq_buf_size) {
i40e_debug(hw,
I40E_DEBUG_AQ_MESSAGE,
i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff,
buff_size);
+ /* save writeback aq if requested */
+ if (details->wb_desc)
+ *details->wb_desc = *desc_on_ring;
+
/* update the error if time out occurred */
if ((!cmd_completed) &&
(!details->async && !details->postpone)) {
asq_send_command_error:
mutex_unlock(&hw->aq.asq_mutex);
-asq_send_command_exit:
return status;
}
return -ENODEV;
}
+ mlx4_replace_zero_macs(dev);
+
dev->caps.qp0_qkey = kcalloc(dev->caps.num_ports, sizeof(u32), GFP_KERNEL);
dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
if (msi_x) {
int nreq = dev->caps.num_ports * num_online_cpus() + 1;
- bool shared_ports = false;
nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
nreq);
- if (nreq > MAX_MSIX) {
+ if (nreq > MAX_MSIX)
nreq = MAX_MSIX;
- shared_ports = true;
- }
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports,
dev->caps.num_ports);
- if (MLX4_IS_LEGACY_EQ_MODE(dev->caps))
- shared_ports = true;
-
for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) {
if (i == MLX4_EQ_ASYNC)
continue;
priv->eq_table.eq[i].irq =
entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector;
- if (shared_ports) {
+ if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) {
bitmap_fill(priv->eq_table.eq[i].actv_ports.ports,
dev->caps.num_ports);
/* We don't set affinity hint when there
{
struct mlx5_reg_pcap in;
struct mlx5_reg_pcap out;
- int err;
memset(&in, 0, sizeof(in));
in.caps_127_96 = cpu_to_be32(caps);
in.port_num = port_num;
- err = mlx5_core_access_reg(dev, &in, sizeof(in), &out,
- sizeof(out), MLX5_REG_PCAP, 0, 1);
-
- return err;
+ return mlx5_core_access_reg(dev, &in, sizeof(in), &out,
+ sizeof(out), MLX5_REG_PCAP, 0, 1);
}
EXPORT_SYMBOL_GPL(mlx5_set_port_caps);
int ptys_size, int proto_mask, u8 local_port)
{
u32 in[MLX5_ST_SZ_DW(ptys_reg)];
- int err;
memset(in, 0, sizeof(in));
MLX5_SET(ptys_reg, in, local_port, local_port);
MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
- err = mlx5_core_access_reg(dev, in, sizeof(in), ptys,
- ptys_size, MLX5_REG_PTYS, 0, 0);
-
- return err;
+ return mlx5_core_access_reg(dev, in, sizeof(in), ptys,
+ ptys_size, MLX5_REG_PTYS, 0, 0);
}
EXPORT_SYMBOL_GPL(mlx5_query_port_ptys);
{
u32 in[MLX5_ST_SZ_DW(ptys_reg)];
u32 out[MLX5_ST_SZ_DW(ptys_reg)];
- int err;
memset(in, 0, sizeof(in));
else
MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin);
- err = mlx5_core_access_reg(dev, in, sizeof(in), out,
- sizeof(out), MLX5_REG_PTYS, 0, 1);
- return err;
+ return mlx5_core_access_reg(dev, in, sizeof(in), out,
+ sizeof(out), MLX5_REG_PTYS, 0, 1);
}
EXPORT_SYMBOL_GPL(mlx5_set_port_proto);
return err;
*status = MLX5_GET(paos_reg, out, admin_status);
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
int pvlc_size, u8 local_port)
{
u32 in[MLX5_ST_SZ_DW(pvlc_reg)];
- int err;
memset(in, 0, sizeof(in));
- MLX5_SET(ptys_reg, in, local_port, local_port);
+ MLX5_SET(pvlc_reg, in, local_port, local_port);
- err = mlx5_core_access_reg(dev, in, sizeof(in), pvlc,
- pvlc_size, MLX5_REG_PVLC, 0, 0);
-
- return err;
+ return mlx5_core_access_reg(dev, in, sizeof(in), pvlc,
+ pvlc_size, MLX5_REG_PVLC, 0, 0);
}
int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
{
u32 in[MLX5_ST_SZ_DW(pfcc_reg)];
u32 out[MLX5_ST_SZ_DW(pfcc_reg)];
- int err;
memset(in, 0, sizeof(in));
MLX5_SET(pfcc_reg, in, local_port, 1);
MLX5_SET(pfcc_reg, in, pptx, tx_pause);
MLX5_SET(pfcc_reg, in, pprx, rx_pause);
- err = mlx5_core_access_reg(dev, in, sizeof(in), out,
- sizeof(out), MLX5_REG_PFCC, 0, 1);
- return err;
+ return mlx5_core_access_reg(dev, in, sizeof(in), out,
+ sizeof(out), MLX5_REG_PFCC, 0, 1);
}
EXPORT_SYMBOL_GPL(mlx5_set_port_pause);
int err;
int ret;
+ mlxsw_core->emad.trans_active = true;
+
err = mlxsw_core_skb_transmit(mlxsw_core->driver_priv, skb, tx_info);
if (err) {
dev_err(mlxsw_core->bus_info->dev, "Failed to transmit EMAD (tid=%llx)\n",
mlxsw_core->emad.tid);
dev_kfree_skb(skb);
- return err;
+ goto trans_inactive_out;
}
- mlxsw_core->emad.trans_active = true;
ret = wait_event_timeout(mlxsw_core->emad.wait,
!(mlxsw_core->emad.trans_active),
msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS));
if (!ret) {
dev_warn(mlxsw_core->bus_info->dev, "EMAD timed-out (tid=%llx)\n",
mlxsw_core->emad.tid);
- mlxsw_core->emad.trans_active = false;
- return -EIO;
+ err = -EIO;
+ goto trans_inactive_out;
}
return 0;
+
+ trans_inactive_out:
+ mlxsw_core->emad.trans_active = false;
+ return err;
}
static int mlxsw_emad_process_status(struct mlxsw_core *mlxsw_core,
return err;
mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU,
- MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
MLXSW_TRAP_ID_ETHEMAD);
return mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl);
}
{
char hpkt_pl[MLXSW_REG_HPKT_LEN];
+ mlxsw_core->emad.use_emad = false;
mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_DISCARD,
- MLXSW_REG_HTGT_TRAP_GROUP_EMAD,
MLXSW_TRAP_ID_ETHEMAD);
mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl);
}
static inline void __mlxsw_item_memcpy_from(char *buf, char *dst,
- struct mlxsw_item *item)
+ struct mlxsw_item *item,
+ unsigned short index)
{
- memcpy(dst, &buf[item->offset], item->size.bytes);
+ unsigned int offset = __mlxsw_item_offset(item, index, sizeof(char));
+
+ memcpy(dst, &buf[offset], item->size.bytes);
}
-static inline void __mlxsw_item_memcpy_to(char *buf, char *src,
- struct mlxsw_item *item)
+static inline void __mlxsw_item_memcpy_to(char *buf, const char *src,
+ struct mlxsw_item *item,
+ unsigned short index)
{
- memcpy(&buf[item->offset], src, item->size.bytes);
+ unsigned int offset = __mlxsw_item_offset(item, index, sizeof(char));
+
+ memcpy(&buf[offset], src, item->size.bytes);
}
static inline u16
{
u16 max_index, be_index;
u16 offset; /* byte offset inside the array */
+ u8 in_byte_index;
BUG_ON(index && !item->element_size);
if (item->offset % sizeof(u32) != 0 ||
max_index = (item->size.bytes << 3) / item->element_size - 1;
be_index = max_index - index;
offset = be_index * item->element_size >> 3;
- *shift = index % (BITS_PER_BYTE / item->element_size) << 1;
+ in_byte_index = index % (BITS_PER_BYTE / item->element_size);
+ *shift = in_byte_index * item->element_size;
return item->offset + offset;
}
static inline void \
mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(char *buf, char *dst) \
{ \
- __mlxsw_item_memcpy_from(buf, dst, &__ITEM_NAME(_type, _cname, _iname));\
+ __mlxsw_item_memcpy_from(buf, dst, \
+ &__ITEM_NAME(_type, _cname, _iname), 0); \
+} \
+static inline void \
+mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, const char *src) \
+{ \
+ __mlxsw_item_memcpy_to(buf, src, \
+ &__ITEM_NAME(_type, _cname, _iname), 0); \
+}
+
+#define MLXSW_ITEM_BUF_INDEXED(_type, _cname, _iname, _offset, _sizebytes, \
+ _step, _instepoffset) \
+static struct mlxsw_item __ITEM_NAME(_type, _cname, _iname) = { \
+ .offset = _offset, \
+ .step = _step, \
+ .in_step_offset = _instepoffset, \
+ .size = {.bytes = _sizebytes,}, \
+ .name = #_type "_" #_cname "_" #_iname, \
+}; \
+static inline void \
+mlxsw_##_type##_##_cname##_##_iname##_memcpy_from(char *buf, \
+ unsigned short index, \
+ char *dst) \
+{ \
+ __mlxsw_item_memcpy_from(buf, dst, \
+ &__ITEM_NAME(_type, _cname, _iname), index); \
} \
static inline void \
-mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, char *src) \
+mlxsw_##_type##_##_cname##_##_iname##_memcpy_to(char *buf, \
+ unsigned short index, \
+ const char *src) \
{ \
- __mlxsw_item_memcpy_to(buf, src, &__ITEM_NAME(_type, _cname, _iname)); \
+ __mlxsw_item_memcpy_to(buf, src, \
+ &__ITEM_NAME(_type, _cname, _iname), index); \
}
#define MLXSW_ITEM_BIT_ARRAY(_type, _cname, _iname, _offset, _sizebytes, \
static const struct pci_device_id mlxsw_pci_id_table[] = {
{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHX2), 0},
+ {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
{0, }
};
switch (id->device) {
case PCI_DEVICE_ID_MELLANOX_SWITCHX2:
return MLXSW_DEVICE_KIND_SWITCHX2;
+ case PCI_DEVICE_ID_MELLANOX_SPECTRUM:
+ return MLXSW_DEVICE_KIND_SPECTRUM;
default:
BUG();
}
struct msix_entry msix_entry;
struct mlxsw_core *core;
struct {
- u16 num_pages;
struct mlxsw_pci_mem_item *items;
+ unsigned int count;
} fw_area;
struct {
struct mlxsw_pci_mem_item out_mbox;
mapaddr = pci_map_single(pdev, frag_data, frag_len, direction);
if (unlikely(pci_dma_mapping_error(pdev, mapaddr))) {
- if (net_ratelimit())
- dev_err(&pdev->dev, "failed to dma map tx frag\n");
+ dev_err_ratelimited(&pdev->dev, "failed to dma map tx frag\n");
return -EIO;
}
mlxsw_pci_wqe_address_set(wqe, index, mapaddr);
struct mlxsw_pci_queue *q)
{
struct mlxsw_pci_queue_elem_info *elem_info;
+ u8 sdq_count = mlxsw_pci_sdq_count(mlxsw_pci);
int i;
int err;
q->consumer_counter = 0;
/* Set CQ of same number of this RDQ with base
- * above MLXSW_PCI_SDQS_MAX as the lower ones are assigned to SDQs.
+ * above SDQ count as the lower ones are assigned to SDQs.
*/
- mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, q->num + MLXSW_PCI_SDQS_COUNT);
+ mlxsw_cmd_mbox_sw2hw_dq_cq_set(mbox, sdq_count + q->num);
mlxsw_cmd_mbox_sw2hw_dq_log2_dq_sz_set(mbox, 3); /* 8 pages */
for (i = 0; i < MLXSW_PCI_AQ_PAGES; i++) {
dma_addr_t mapaddr = __mlxsw_pci_queue_page_get(q, i);
put_new_skb:
memset(wqe, 0, q->elem_size);
err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
- if (err && net_ratelimit())
- dev_dbg(&pdev->dev, "Failed to alloc skb for RDQ\n");
+ if (err)
+ dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
/* Everything is set up, ring doorbell to pass elem to HW */
q->producer_counter++;
mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
{
struct mlxsw_pci_queue *q = (struct mlxsw_pci_queue *) data;
struct mlxsw_pci *mlxsw_pci = q->pci;
- unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_COUNT)];
+ u8 cq_count = mlxsw_pci_cq_count(mlxsw_pci);
+ unsigned long active_cqns[BITS_TO_LONGS(MLXSW_PCI_CQS_MAX)];
char *eqe;
u8 cqn;
bool cq_handle = false;
if (!cq_handle)
return;
- for_each_set_bit(cqn, active_cqns, MLXSW_PCI_CQS_COUNT) {
+ for_each_set_bit(cqn, active_cqns, cq_count) {
q = mlxsw_pci_cq_get(mlxsw_pci, cqn);
mlxsw_pci_queue_tasklet_schedule(q);
}
num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox);
eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox);
- if ((num_sdqs != MLXSW_PCI_SDQS_COUNT) ||
- (num_rdqs != MLXSW_PCI_RDQS_COUNT) ||
- (num_cqs != MLXSW_PCI_CQS_COUNT) ||
- (num_eqs != MLXSW_PCI_EQS_COUNT)) {
+ if (num_sdqs + num_rdqs > num_cqs ||
+ num_cqs > MLXSW_PCI_CQS_MAX || num_eqs != MLXSW_PCI_EQS_COUNT) {
dev_err(&pdev->dev, "Unsupported number of queues\n");
return -EINVAL;
}
mbox, profile->max_flood_tables);
mlxsw_cmd_mbox_config_profile_max_vid_flood_tables_set(
mbox, profile->max_vid_flood_tables);
+ mlxsw_cmd_mbox_config_profile_max_fid_offset_flood_tables_set(
+ mbox, profile->max_fid_offset_flood_tables);
+ mlxsw_cmd_mbox_config_profile_fid_offset_flood_table_size_set(
+ mbox, profile->fid_offset_flood_table_size);
+ mlxsw_cmd_mbox_config_profile_max_fid_flood_tables_set(
+ mbox, profile->max_fid_flood_tables);
+ mlxsw_cmd_mbox_config_profile_fid_flood_table_size_set(
+ mbox, profile->fid_flood_table_size);
}
if (profile->used_flood_mode) {
mlxsw_cmd_mbox_config_profile_set_flood_mode_set(
u16 num_pages)
{
struct mlxsw_pci_mem_item *mem_item;
+ int nent = 0;
int i;
int err;
GFP_KERNEL);
if (!mlxsw_pci->fw_area.items)
return -ENOMEM;
- mlxsw_pci->fw_area.num_pages = num_pages;
+ mlxsw_pci->fw_area.count = num_pages;
mlxsw_cmd_mbox_zero(mbox);
for (i = 0; i < num_pages; i++) {
err = -ENOMEM;
goto err_alloc;
}
- mlxsw_cmd_mbox_map_fa_pa_set(mbox, i, mem_item->mapaddr);
- mlxsw_cmd_mbox_map_fa_log2size_set(mbox, i, 0); /* 1 page */
+ mlxsw_cmd_mbox_map_fa_pa_set(mbox, nent, mem_item->mapaddr);
+ mlxsw_cmd_mbox_map_fa_log2size_set(mbox, nent, 0); /* 1 page */
+ if (++nent == MLXSW_CMD_MAP_FA_VPM_ENTRIES_MAX) {
+ err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, nent);
+ if (err)
+ goto err_cmd_map_fa;
+ nent = 0;
+ mlxsw_cmd_mbox_zero(mbox);
+ }
}
- err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, num_pages);
- if (err)
- goto err_cmd_map_fa;
+ if (nent) {
+ err = mlxsw_cmd_map_fa(mlxsw_pci->core, mbox, nent);
+ if (err)
+ goto err_cmd_map_fa;
+ }
return 0;
mlxsw_cmd_unmap_fa(mlxsw_pci->core);
- for (i = 0; i < mlxsw_pci->fw_area.num_pages; i++) {
+ for (i = 0; i < mlxsw_pci->fw_area.count; i++) {
mem_item = &mlxsw_pci->fw_area.items[i];
pci_free_consistent(mlxsw_pci->pdev, mem_item->size,
if (in_mbox)
memcpy(mlxsw_pci->cmd.in_mbox.buf, in_mbox, in_mbox_size);
- mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_HI, in_mapaddr >> 32);
- mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_LO, in_mapaddr);
+ mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_HI, upper_32_bits(in_mapaddr));
+ mlxsw_pci_write32(mlxsw_pci, CIR_IN_PARAM_LO, lower_32_bits(in_mapaddr));
- mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_HI, out_mapaddr >> 32);
- mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_LO, out_mapaddr);
+ mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_HI, upper_32_bits(out_mapaddr));
+ mlxsw_pci_write32(mlxsw_pci, CIR_OUT_PARAM_LO, lower_32_bits(out_mapaddr));
mlxsw_pci_write32(mlxsw_pci, CIR_IN_MODIFIER, in_mod);
mlxsw_pci_write32(mlxsw_pci, CIR_TOKEN, 0);
struct mlxsw_sx_port;
-#define MLXSW_SW_HW_ID_LEN 6
-
struct mlxsw_sx {
struct mlxsw_sx_port **ports;
struct mlxsw_core *core;
const struct mlxsw_bus_info *bus_info;
- u8 hw_id[MLXSW_SW_HW_ID_LEN];
+ u8 hw_id[ETH_ALEN];
};
struct mlxsw_sx_port_pcpu_stats {
struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
switch (attr->id) {
- case SWITCHDEV_ATTR_PORT_PARENT_ID:
+ case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
attr->u.ppid.id_len = sizeof(mlxsw_sx->hw_id);
memcpy(&attr->u.ppid.id, &mlxsw_sx->hw_id, attr->u.ppid.id_len);
break;
spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL);
if (!spms_pl)
return -ENOMEM;
- mlxsw_reg_spms_pack(spms_pl, mlxsw_sx_port->local_port, vid, state);
+ mlxsw_reg_spms_pack(spms_pl, mlxsw_sx_port->local_port);
+ mlxsw_reg_spms_vid_pack(spms_pl, vid, state);
err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spms), spms_pl);
kfree(spms_pl);
return err;
return 0;
err_register_netdev:
- err_port_admin_status_set:
err_port_mac_learning_mode_set:
err_port_stp_state_set:
+ err_port_admin_status_set:
err_port_mtu_set:
err_port_speed_set:
err_port_swid_set:
if (err)
return err;
- mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD,
- MLXSW_REG_HTGT_TRAP_GROUP_EMAD, trap_id);
+ mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD, trap_id);
err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl);
if (err)
goto err_event_trap_set;
struct mlxsw_sx_port_pcpu_stats *pcpu_stats;
if (unlikely(!mlxsw_sx_port)) {
- if (net_ratelimit())
- dev_warn(mlxsw_sx->bus_info->dev, "Port %d: skb received for non-existent port\n",
- local_port);
+ dev_warn_ratelimited(mlxsw_sx->bus_info->dev, "Port %d: skb received for non-existent port\n",
+ local_port);
return;
}
if (err)
return err;
+ mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_CTRL);
+ err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(htgt), htgt_pl);
+ if (err)
+ return err;
+
for (i = 0; i < ARRAY_SIZE(mlxsw_sx_rx_listener); i++) {
err = mlxsw_core_rx_listener_register(mlxsw_sx->core,
&mlxsw_sx_rx_listener[i],
goto err_rx_listener_register;
mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU,
- MLXSW_REG_HTGT_TRAP_GROUP_RX,
mlxsw_sx_rx_listener[i].trap_id);
err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl);
if (err)
err_rx_listener_register:
for (i--; i >= 0; i--) {
mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD,
- MLXSW_REG_HTGT_TRAP_GROUP_RX,
mlxsw_sx_rx_listener[i].trap_id);
mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl);
for (i = 0; i < ARRAY_SIZE(mlxsw_sx_rx_listener); i++) {
mlxsw_reg_hpkt_pack(hpkt_pl, MLXSW_REG_HPKT_ACTION_FORWARD,
- MLXSW_REG_HTGT_TRAP_GROUP_RX,
mlxsw_sx_rx_listener[i].trap_id);
mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(hpkt), hpkt_pl);
{
char sfgc_pl[MLXSW_REG_SFGC_LEN];
char sgcr_pl[MLXSW_REG_SGCR_LEN];
- char *smid_pl;
char *sftr_pl;
int err;
- /* Due to FW bug, we must configure SMID. */
- smid_pl = kmalloc(MLXSW_REG_SMID_LEN, GFP_KERNEL);
- if (!smid_pl)
- return -ENOMEM;
- mlxsw_reg_smid_pack(smid_pl, MLXSW_PORT_MID);
- err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(smid), smid_pl);
- kfree(smid_pl);
- if (err)
- return err;
-
/* Configure a flooding table, which includes only CPU port. */
sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
if (!sftr_pl)
return -ENOMEM;
- mlxsw_reg_sftr_pack(sftr_pl, 0, 0, MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, 0);
+ mlxsw_reg_sftr_pack(sftr_pl, 0, 0, MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, 0,
+ MLXSW_PORT_CPU_PORT, true);
err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sftr), sftr_pl);
kfree(sftr_pl);
if (err)
---help---
Currently supports the LAN83C185, LAN8187 and LAN8700 PHYs
+config BCM_NET_PHYLIB
+ tristate
+
config BROADCOM_PHY
tristate "Drivers for Broadcom PHYs"
+ select BCM_NET_PHYLIB
---help---
Currently supports the BCM5411, BCM5421, BCM5461, BCM54616S, BCM5464,
BCM5481 and BCM5482 PHYs.
+config BCM_CYGNUS_PHY
+ tristate "Drivers for Broadcom Cygnus SoC internal PHY"
+ depends on ARCH_BCM_CYGNUS || COMPILE_TEST
+ depends on MDIO_BCM_IPROC
+ select BCM_NET_PHYLIB
+ ---help---
+ This PHY driver is for the 1G internal PHYs of the Broadcom
+ Cygnus Family SoC.
+
+ Currently supports internal PHY's used in the BCM11300,
+ BCM11320, BCM11350, BCM11360, BCM58300, BCM58302,
+ BCM58303 & BCM58305 Broadcom Cygnus SoCs.
+
config BCM63XX_PHY
tristate "Drivers for Broadcom 63xx SOCs internal PHY"
depends on BCM63XX
+ select BCM_NET_PHYLIB
---help---
Currently supports the 6348 and 6358 PHYs.
config BCM7XXX_PHY
tristate "Drivers for Broadcom 7xxx SOCs internal PHYs"
+ select BCM_NET_PHYLIB
---help---
Currently supports the BCM7366, BCM7439, BCM7445, and
40nm and 65nm generation of BCM7xxx Set Top Box SoCs.
busses. It is required by the Octeon and ThunderX ethernet device
drivers.
- If in doubt, say Y.
-
config MDIO_SUN4I
tristate "Allwinner sun4i MDIO interface support"
depends on ARCH_SUNXI
This hardware can be found in the Broadcom GENET Ethernet MAC
controllers as well as some Broadcom Ethernet switches such as the
Starfighter 2 switches.
+
+config MDIO_BCM_IPROC
+ tristate "Broadcom iProc MDIO bus controller"
+ depends on ARCH_BCM_IPROC || COMPILE_TEST
+ depends on HAS_IOMEM && OF_MDIO
+ help
+ This module provides a driver for the MDIO busses found in the
+ Broadcom iProc SoC's.
+
endif # PHYLIB
config MICREL_KS8995MA
config USB_LAN78XX
tristate "Microchip LAN78XX Based USB Ethernet Adapters"
select MII
+ select PHYLIB
+ select MICROCHIP_PHY
help
This option adds support for Microchip LAN78XX based USB 2
& USB 3 10/100/1000 Ethernet adapters.
* Aten UC210T
* ASIX AX88172
* Billionton Systems, USB2AR
+ * Billionton Systems, GUSB2AM-1G-B
* Buffalo LUA-U2-KTX
* Corega FEther USB2-TX
* D-Link DUB-E100
config USB_CDC_PHONET
tristate "CDC Phonet support"
- depends on PHONET
+ depends on PHONET && USB_USBNET
help
Choose this option to support the Phonet interface to a Nokia
cellular modem, as found on most Nokia handsets with the
static const u8 all_zeros_mac[ETH_ALEN];
-static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- bool no_share, u32 flags);
+static int vxlan_sock_add(struct vxlan_dev *vxlan);
/* per-network namespace private data for this module */
struct vxlan_net {
static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
{
struct vxlan_dev *vxlan;
+ unsigned short family = dev->default_dst.remote_ip.sa.sa_family;
/* The vxlan_sock is only used by dev, leaving group has
* no effect on other vxlan devices.
*/
- if (atomic_read(&dev->vn_sock->refcnt) == 1)
+ if (family == AF_INET && dev->vn4_sock &&
+ atomic_read(&dev->vn4_sock->refcnt) == 1)
return false;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (family == AF_INET6 && dev->vn6_sock &&
+ atomic_read(&dev->vn6_sock->refcnt) == 1)
+ return false;
+#endif
list_for_each_entry(vxlan, &vn->vxlan_list, next) {
if (!netif_running(vxlan->dev) || vxlan == dev)
continue;
- if (vxlan->vn_sock != dev->vn_sock)
+ if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock)
continue;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock)
+ continue;
+#endif
if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip,
&dev->default_dst.remote_ip))
return false;
}
-static void vxlan_sock_release(struct vxlan_sock *vs)
+static void __vxlan_sock_release(struct vxlan_sock *vs)
{
- struct sock *sk = vs->sock->sk;
- struct net *net = sock_net(sk);
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+ struct vxlan_net *vn;
+ if (!vs)
+ return;
if (!atomic_dec_and_test(&vs->refcnt))
return;
+ vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
spin_lock(&vn->sock_lock);
hlist_del_rcu(&vs->hlist);
vxlan_notify_del_rx_port(vs);
queue_work(vxlan_wq, &vs->del_work);
}
+static void vxlan_sock_release(struct vxlan_dev *vxlan)
+{
+ __vxlan_sock_release(vxlan->vn4_sock);
+#if IS_ENABLED(CONFIG_IPV6)
+ __vxlan_sock_release(vxlan->vn6_sock);
+#endif
+}
+
/* Update multicast group membership when first VNI on
* multicast address is brought up
*/
static int vxlan_igmp_join(struct vxlan_dev *vxlan)
{
- struct vxlan_sock *vs = vxlan->vn_sock;
- struct sock *sk = vs->sock->sk;
+ struct sock *sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
int ret = -EINVAL;
- lock_sock(sk);
if (ip->sa.sa_family == AF_INET) {
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = ifindex,
};
+ sk = vxlan->vn4_sock->sock->sk;
+ lock_sock(sk);
ret = ip_mc_join_group(sk, &mreq);
+ release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
} else {
+ sk = vxlan->vn6_sock->sock->sk;
+ lock_sock(sk);
ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
&ip->sin6.sin6_addr);
+ release_sock(sk);
#endif
}
- release_sock(sk);
return ret;
}
/* Inverse of vxlan_igmp_join when last VNI is brought down */
static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
{
- struct vxlan_sock *vs = vxlan->vn_sock;
- struct sock *sk = vs->sock->sk;
+ struct sock *sk;
union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
int ifindex = vxlan->default_dst.remote_ifindex;
int ret = -EINVAL;
- lock_sock(sk);
if (ip->sa.sa_family == AF_INET) {
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr,
.imr_ifindex = ifindex,
};
+ sk = vxlan->vn4_sock->sock->sk;
+ lock_sock(sk);
ret = ip_mc_leave_group(sk, &mreq);
+ release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
} else {
+ sk = vxlan->vn6_sock->sock->sk;
+ lock_sock(sk);
ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
&ip->sin6.sin6_addr);
+ release_sock(sk);
#endif
}
- release_sock(sk);
return ret;
}
{
struct ip_tunnel_info *info;
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct sock *sk = vxlan->vn_sock->sock->sk;
- unsigned short family = vxlan_get_sk_family(vxlan->vn_sock);
+ struct sock *sk;
struct rtable *rt = NULL;
const struct iphdr *old_iph;
struct flowi4 fl4;
dev->name);
goto drop;
}
- if (family != ip_tunnel_info_af(info))
- goto drop;
-
dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
vni = be64_to_cpu(info->key.tun_id);
- remote_ip.sa.sa_family = family;
- if (family == AF_INET)
+ remote_ip.sa.sa_family = ip_tunnel_info_af(info);
+ if (remote_ip.sa.sa_family == AF_INET)
remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
else
remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
}
if (dst->sa.sa_family == AF_INET) {
+ if (!vxlan->vn4_sock)
+ goto drop;
+ sk = vxlan->vn4_sock->sock->sk;
+
if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT))
df = htons(IP_DF);
struct flowi6 fl6;
u32 rt6i_flags;
+ if (!vxlan->vn6_sock)
+ goto drop;
+ sk = vxlan->vn6_sock->sock->sk;
+
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0;
fl6.daddr = dst->sin6.sin6_addr;
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
__u32 vni = vxlan->default_dst.remote_vni;
- vxlan->vn_sock = vs;
spin_lock(&vn->sock_lock);
hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni));
spin_unlock(&vn->sock_lock);
static int vxlan_open(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_sock *vs;
- int ret = 0;
+ int ret;
- vs = vxlan_sock_add(vxlan->net, vxlan->cfg.dst_port,
- vxlan->cfg.no_share, vxlan->flags);
- if (IS_ERR(vs))
- return PTR_ERR(vs);
-
- vxlan_vs_add_dev(vs, vxlan);
+ ret = vxlan_sock_add(vxlan);
+ if (ret < 0)
+ return ret;
if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) {
ret = vxlan_igmp_join(vxlan);
if (ret == -EADDRINUSE)
ret = 0;
if (ret) {
- vxlan_sock_release(vs);
+ vxlan_sock_release(vxlan);
return ret;
}
}
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
- struct vxlan_sock *vs = vxlan->vn_sock;
int ret = 0;
if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) &&
del_timer_sync(&vxlan->age_timer);
vxlan_flush(vxlan);
- vxlan_sock_release(vs);
+ vxlan_sock_release(vxlan);
return ret;
}
}
/* Create new listen socket if needed */
-static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
- u32 flags)
+static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
+ __be16 port, u32 flags)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
struct vxlan_sock *vs;
struct socket *sock;
unsigned int h;
- bool ipv6 = !!(flags & VXLAN_F_IPV6);
struct udp_tunnel_sock_cfg tunnel_cfg;
vs = kzalloc(sizeof(*vs), GFP_KERNEL);
return vs;
}
-static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
- bool no_share, u32 flags)
+static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6)
{
- struct vxlan_net *vn = net_generic(net, vxlan_net_id);
- struct vxlan_sock *vs;
- bool ipv6 = flags & VXLAN_F_IPV6;
+ struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
+ struct vxlan_sock *vs = NULL;
- if (!no_share) {
+ if (!vxlan->cfg.no_share) {
spin_lock(&vn->sock_lock);
- vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port,
- flags);
- if (vs) {
- if (!atomic_add_unless(&vs->refcnt, 1, 0))
- vs = ERR_PTR(-EBUSY);
+ vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET,
+ vxlan->cfg.dst_port, vxlan->flags);
+ if (vs && !atomic_add_unless(&vs->refcnt, 1, 0)) {
spin_unlock(&vn->sock_lock);
- return vs;
+ return -EBUSY;
}
spin_unlock(&vn->sock_lock);
}
+ if (!vs)
+ vs = vxlan_socket_create(vxlan->net, ipv6,
+ vxlan->cfg.dst_port, vxlan->flags);
+ if (IS_ERR(vs))
+ return PTR_ERR(vs);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (ipv6)
+ vxlan->vn6_sock = vs;
+ else
+#endif
+ vxlan->vn4_sock = vs;
+ vxlan_vs_add_dev(vs, vxlan);
+ return 0;
+}
- return vxlan_socket_create(net, port, flags);
+static int vxlan_sock_add(struct vxlan_dev *vxlan)
+{
+ bool ipv6 = vxlan->flags & VXLAN_F_IPV6;
+ bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA;
+ int ret = 0;
+
+ vxlan->vn4_sock = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
+ vxlan->vn6_sock = NULL;
+ if (ipv6 || metadata)
+ ret = __vxlan_sock_add(vxlan, true);
+#endif
+ if (!ret && (!ipv6 || metadata))
+ ret = __vxlan_sock_add(vxlan, false);
+ if (ret < 0)
+ vxlan_sock_release(vxlan);
+ return ret;
}
static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_rdst *dst = &vxlan->default_dst;
+ unsigned short needed_headroom = ETH_HLEN;
int err;
bool use_ipv6 = false;
__be16 default_port = vxlan->cfg.dst_port;
if (!IS_ENABLED(CONFIG_IPV6))
return -EPFNOSUPPORT;
use_ipv6 = true;
+ vxlan->flags |= VXLAN_F_IPV6;
}
if (conf->remote_ifindex) {
pr_info("IPv6 is disabled via sysctl\n");
return -EPERM;
}
- vxlan->flags |= VXLAN_F_IPV6;
}
#endif
if (!conf->mtu)
dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
- dev->needed_headroom = lowerdev->hard_header_len +
- (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
- } else if (use_ipv6) {
- vxlan->flags |= VXLAN_F_IPV6;
- dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM;
- } else {
- dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM;
+ needed_headroom = lowerdev->hard_header_len;
}
+ if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
+ needed_headroom += VXLAN6_HEADROOM;
+ else
+ needed_headroom += VXLAN_HEADROOM;
+ dev->needed_headroom = needed_headroom;
+
memcpy(&vxlan->cfg, conf, sizeof(*conf));
if (!vxlan->cfg.dst_port)
vxlan->cfg.dst_port = default_port;
struct vxlan_config conf;
int err;
- if (!data[IFLA_VXLAN_ID])
- return -EINVAL;
-
memset(&conf, 0, sizeof(conf));
- conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]);
+
+ if (data[IFLA_VXLAN_ID])
+ conf.vni = nla_get_u32(data[IFLA_VXLAN_ID]);
if (data[IFLA_VXLAN_GROUP]) {
conf.remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]);
#define TARGET_10X_MAX_FRAG_ENTRIES 0
/* 10.2 parameters */
- #define TARGET_10_2_DMA_BURST_SIZE 1
+ #define TARGET_10_2_DMA_BURST_SIZE 0
/* Target specific defines for WMI-TLV firmware */
#define TARGET_TLV_NUM_VDEVS 4
#define TARGET_10_4_TX_DBG_LOG_SIZE 1024
#define TARGET_10_4_NUM_WDS_ENTRIES 32
- #define TARGET_10_4_DMA_BURST_SIZE 1
+ #define TARGET_10_4_DMA_BURST_SIZE 0
#define TARGET_10_4_MAC_AGGR_DELIM 0
#define TARGET_10_4_RX_SKIP_DEFRAG_TIMEOUT_DUP_DETECTION_CHECK 1
#define TARGET_10_4_VOW_CONFIG 0
/* Number of Copy Engines supported */
#define CE_COUNT ar->hw_values->ce_count
-/*
- * Total number of PCIe MSI interrupts requested for all interrupt sources.
- * PCIe standard forces this to be a power of 2.
- * Some Host OS's limit MSI requests that can be granted to 8
- * so for now we abide by this limit and avoid requesting more
- * than that.
- */
-#define MSI_NUM_REQUEST_LOG2 3
-#define MSI_NUM_REQUEST (1<<MSI_NUM_REQUEST_LOG2)
-
/*
* Granted MSIs are assigned as follows:
* Firmware uses the first
BIT(NL80211_IFTYPE_STATION) |
BIT(NL80211_IFTYPE_ADHOC) |
BIT(NL80211_IFTYPE_MESH_POINT) |
- BIT(NL80211_IFTYPE_WDS);
+ BIT(NL80211_IFTYPE_WDS) |
+ BIT(NL80211_IFTYPE_OCB);
if (ath9k_is_chanctx_enabled())
hw->wiphy->interface_modes |=
hw->max_rate_tries = 10;
hw->sta_data_size = sizeof(struct ath_node);
hw->vif_data_size = sizeof(struct ath_vif);
+ hw->extra_tx_headroom = 4;
hw->wiphy->available_antennas_rx = BIT(ah->caps.max_rxchains) - 1;
hw->wiphy->available_antennas_tx = BIT(ah->caps.max_txchains) - 1;
#define IWL7260_UCODE_API_MAX 17
/* Oldest version we won't warn about */
-#define IWL7260_UCODE_API_OK 12
-#define IWL3165_UCODE_API_OK 13
+#define IWL7260_UCODE_API_OK 13
/* Lowest firmware API version supported */
-#define IWL7260_UCODE_API_MIN 12
-#define IWL3165_UCODE_API_MIN 13
+#define IWL7260_UCODE_API_MIN 13
/* NVM versions */
#define IWL7260_NVM_VERSION 0x0a1d
static const struct iwl_base_params iwl7000_base_params = {
.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_7000,
- .num_of_queues = IWLAGN_NUM_QUEUES,
+ .num_of_queues = 31,
.pll_cfg_val = 0,
.shadow_ram_support = true,
.led_compensation = 57,
.name = "Intel(R) Dual Band Wireless AC 3165",
.fw_name_pre = IWL7265D_FW_PRE,
IWL_DEVICE_7000,
- /* sparse doens't like the re-assignment but it is safe */
-#ifndef __CHECKER__
- .ucode_api_ok = IWL3165_UCODE_API_OK,
- .ucode_api_min = IWL3165_UCODE_API_MIN,
-#endif
.ht_params = &iwl7000_ht_params,
.nvm_ver = IWL3165_NVM_VERSION,
.nvm_calib_ver = IWL3165_TX_POWER_VERSION,
};
MODULE_FIRMWARE(IWL7260_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
- MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL3160_UCODE_API_OK));
+ MODULE_FIRMWARE(IWL3160_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
MODULE_FIRMWARE(IWL7265D_MODULE_FIRMWARE(IWL7260_UCODE_API_OK));
break;
case WLAN_CIPHER_SUITE_CCMP:
if (sta) {
- u8 *pn = seq.ccmp.pn;
+ u64 pn64;
aes_sc = data->rsc_tsc->all_tsc_rsc.aes.unicast_rsc;
aes_tx_sc = &data->rsc_tsc->all_tsc_rsc.aes.tsc;
- ieee80211_get_key_tx_seq(key, &seq);
- aes_tx_sc->pn = cpu_to_le64((u64)pn[5] |
- ((u64)pn[4] << 8) |
- ((u64)pn[3] << 16) |
- ((u64)pn[2] << 24) |
- ((u64)pn[1] << 32) |
- ((u64)pn[0] << 40));
+ pn64 = atomic64_read(&key->tx_pn);
+ aes_tx_sc->pn = cpu_to_le64(pn64);
} else {
aes_sc = data->rsc_tsc->all_tsc_rsc.aes.multicast_rsc;
}
u8 *pn = seq.ccmp.pn;
ieee80211_get_key_rx_seq(key, i, &seq);
- aes_sc->pn = cpu_to_le64((u64)pn[5] |
- ((u64)pn[4] << 8) |
- ((u64)pn[3] << 16) |
- ((u64)pn[2] << 24) |
- ((u64)pn[1] << 32) |
- ((u64)pn[0] << 40));
+ aes_sc[i].pn = cpu_to_le64((u64)pn[5] |
+ ((u64)pn[4] << 8) |
+ ((u64)pn[3] << 16) |
+ ((u64)pn[2] << 24) |
+ ((u64)pn[1] << 32) |
+ ((u64)pn[0] << 40));
}
data->use_rsc_tsc = true;
break;
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
int ret;
+ /* make sure the d0i3 exit work is not pending */
+ flush_work(&mvm->d0i3_exit_work);
+
ret = iwl_trans_suspend(mvm->trans);
if (ret)
return ret;
switch (key->cipher) {
case WLAN_CIPHER_SUITE_CCMP:
- iwl_mvm_aes_sc_to_seq(&sc->aes.tsc, &seq);
iwl_mvm_set_aes_rx_seq(sc->aes.unicast_rsc, key);
+ atomic64_set(&key->tx_pn, le64_to_cpu(sc->aes.tsc.pn));
break;
case WLAN_CIPHER_SUITE_TKIP:
iwl_mvm_tkip_sc_to_seq(&sc->tkip.tsc, &seq);
iwl_mvm_set_tkip_rx_seq(sc->tkip.unicast_rsc, key);
+ ieee80211_set_key_tx_seq(key, &seq);
break;
}
- ieee80211_set_key_tx_seq(key, &seq);
/* that's it for this key */
return;
* will be empty.
*/
- for (i = 0; i < IWL_MAX_HW_QUEUES; i++) {
- if (i < mvm->first_agg_queue && i != IWL_MVM_CMD_QUEUE)
- mvm->queue_to_mac80211[i] = i;
- else
- mvm->queue_to_mac80211[i] = IWL_INVALID_MAC80211_QUEUE;
- }
+ memset(&mvm->queue_info, 0, sizeof(mvm->queue_info));
+ mvm->queue_info[IWL_MVM_CMD_QUEUE].hw_queue_refcount = 1;
for (i = 0; i < IEEE80211_MAX_QUEUES; i++)
atomic_set(&mvm->mac80211_queue_stop_count[i], 0);
* abort after reading the nvm in case RF Kill is on, we will complete
* the init seq later when RF kill will switch to off
*/
- if (iwl_mvm_is_radio_killed(mvm)) {
+ if (iwl_mvm_is_radio_hw_killed(mvm)) {
IWL_DEBUG_RF_KILL(mvm,
"jump over all phy activities due to RF kill\n");
iwl_remove_notification(&mvm->notif_wait, &calib_wait);
ret = iwl_wait_notification(&mvm->notif_wait, &calib_wait,
MVM_UCODE_CALIB_TIMEOUT);
- if (ret && iwl_mvm_is_radio_killed(mvm)) {
+ if (ret && iwl_mvm_is_radio_hw_killed(mvm)) {
IWL_DEBUG_RF_KILL(mvm, "RFKILL while calibrating.\n");
ret = 1;
}
return ret;
}
-static int iwl_mvm_config_ltr_v1(struct iwl_mvm *mvm)
-{
- struct iwl_ltr_config_cmd_v1 cmd_v1 = {
- .flags = cpu_to_le32(LTR_CFG_FLAG_FEATURE_ENABLE),
- };
-
- if (!mvm->trans->ltr_enabled)
- return 0;
-
- return iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0,
- sizeof(cmd_v1), &cmd_v1);
-}
-
static int iwl_mvm_config_ltr(struct iwl_mvm *mvm)
{
struct iwl_ltr_config_cmd cmd = {
if (!mvm->trans->ltr_enabled)
return 0;
- if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_HDC_PHASE_0))
- return iwl_mvm_config_ltr_v1(mvm);
-
return iwl_mvm_send_cmd_pdu(mvm, LTR_CONFIG, 0,
sizeof(cmd), &cmd);
}
struct ieee80211_vif *vif,
enum ieee80211_ampdu_mlme_action action,
struct ieee80211_sta *sta, u16 tid,
- u16 *ssn, u8 buf_size)
+ u16 *ssn, u8 buf_size, bool amsdu)
{
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
int ret;
return NULL;
}
-static int iwl_mvm_set_tx_power_old(struct iwl_mvm *mvm,
- struct ieee80211_vif *vif, s8 tx_power)
-{
- /* FW is in charge of regulatory enforcement */
- struct iwl_reduce_tx_power_cmd reduce_txpwr_cmd = {
- .mac_context_id = iwl_mvm_vif_from_mac80211(vif)->id,
- .pwr_restriction = cpu_to_le16(tx_power),
- };
-
- return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0,
- sizeof(reduce_txpwr_cmd),
- &reduce_txpwr_cmd);
-}
-
static int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
s16 tx_power)
{
};
int len = sizeof(cmd);
- if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_TX_POWER_DEV))
- return iwl_mvm_set_tx_power_old(mvm, vif, tx_power);
-
if (tx_power == IWL_DEFAULT_MAX_TX_POWER)
cmd.v2.pwr_restriction = cpu_to_le16(IWL_DEV_MAX_TX_POWER);
if (vif->type == NL80211_IFTYPE_AP)
iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif);
+ mvmvif->ap_assoc_sta_count = 0;
+
/* Add the mac context */
ret = iwl_mvm_mac_ctxt_add(mvm, vif);
if (ret)
iwl_mvm_remove_time_event(mvm, mvmvif,
&mvmvif->time_event_data);
RCU_INIT_POINTER(mvm->csa_vif, NULL);
+ mvmvif->csa_countdown = false;
}
if (rcu_access_pointer(mvm->csa_tx_blocked_vif) == vif) {
struct ieee80211_sta *sta)
{
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+ struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
/*
if (sta == rcu_access_pointer(mvm->fw_id_to_mac_id[mvm_sta->sta_id]))
rcu_assign_pointer(mvm->fw_id_to_mac_id[mvm_sta->sta_id],
ERR_PTR(-ENOENT));
+
+ if (mvm_sta->vif->type == NL80211_IFTYPE_AP) {
+ mvmvif->ap_assoc_sta_count--;
+ iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
+ }
+
mutex_unlock(&mvm->mutex);
}
#include "constants.h"
#include "tof.h"
-#define IWL_INVALID_MAC80211_QUEUE 0xff
#define IWL_MVM_MAX_ADDRESSES 5
/* RSSI offset for WkP */
#define IWL_RSSI_OFFSET 50
struct iwl_mvm_vif_bf_data {
bool bf_enabled;
bool ba_enabled;
- s8 ave_beacon_signal;
- s8 last_cqm_event;
- s8 bt_coex_min_thold;
- s8 bt_coex_max_thold;
- s8 last_bt_coex_event;
+ int ave_beacon_signal;
+ int last_cqm_event;
+ int bt_coex_min_thold;
+ int bt_coex_max_thold;
+ int last_bt_coex_event;
};
/**
* @bssid: BSSID for this (client) interface
* @associated: indicates that we're currently associated, used only for
* managing the firmware state in iwl_mvm_bss_info_changed_station()
+ * @ap_assoc_sta_count: count of stations associated to us - valid only
+ * if VIF type is AP
* @uploaded: indicates the MAC context has been added to the device
* @ap_ibss_active: indicates that AP/IBSS is configured and that the interface
* should get quota etc.
u8 bssid[ETH_ALEN];
bool associated;
+ u8 ap_assoc_sta_count;
bool uploaded;
bool ap_ibss_active;
u64 on_time_scan;
} radio_stats, accu_radio_stats;
- u8 queue_to_mac80211[IWL_MAX_HW_QUEUES];
+ struct {
+ /* Map to HW queue */
+ u32 hw_queue_to_mac80211;
+ u8 hw_queue_refcount;
+ bool setup_reserved;
+ u16 tid_bitmap; /* Bitmap of the TIDs mapped to this queue */
+ } queue_info[IWL_MAX_HW_QUEUES];
+ spinlock_t queue_info_lock; /* For syncing queue mgmt operations */
atomic_t mac80211_queue_stop_count[IEEE80211_MAX_QUEUES];
const char *nvm_file_name;
struct debugfs_blob_wrapper nvm_sw_blob;
struct debugfs_blob_wrapper nvm_calib_blob;
struct debugfs_blob_wrapper nvm_prod_blob;
+ struct debugfs_blob_wrapper nvm_phy_sku_blob;
struct iwl_mvm_frame_stats drv_rx_stats;
spinlock_t drv_stats_lock;
test_bit(IWL_MVM_STATUS_HW_CTKILL, &mvm->status);
}
+ static inline bool iwl_mvm_is_radio_hw_killed(struct iwl_mvm *mvm)
+ {
+ return test_bit(IWL_MVM_STATUS_HW_RFKILL, &mvm->status);
+ }
+
/* Must be called with rcu_read_lock() held and it can only be
* released when mvmsta is not needed anymore.
*/
IWL_UCODE_TLV_CAPA_D0I3_SUPPORT);
}
+static inline bool iwl_mvm_is_dqa_supported(struct iwl_mvm *mvm)
+{
+ return fw_has_capa(&mvm->fw->ucode_capa,
+ IWL_UCODE_TLV_CAPA_DQA_SUPPORT);
+}
+
static inline bool iwl_mvm_is_lar_supported(struct iwl_mvm *mvm)
{
bool nvm_lar = mvm->nvm_data->lar_enabled;
IWL_UCODE_TLV_CAPA_LAR_MULTI_MCC);
}
-static inline bool iwl_mvm_is_scd_cfg_supported(struct iwl_mvm *mvm)
-{
- return fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_SCD_CFG);
-}
-
static inline bool iwl_mvm_bt_is_plcr_supported(struct iwl_mvm *mvm)
{
return fw_has_capa(&mvm->fw->ucode_capa,
IWL_UCODE_TLV_CAPA_CSUM_SUPPORT);
}
+static inline bool iwl_mvm_has_new_rx_api(struct iwl_mvm *mvm)
+{
+ /* firmware flag isn't defined yet */
+ return false;
+}
+
extern const u8 iwl_mvm_ac_to_tx_fifo[];
struct iwl_rate_info {
struct ieee80211_vif *vif);
unsigned long iwl_mvm_get_used_hw_queues(struct iwl_mvm *mvm,
struct ieee80211_vif *exclude_vif);
-
/* Bindings */
int iwl_mvm_binding_add_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
int iwl_mvm_binding_remove_vif(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
}
/* hw scheduler queue config */
-void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, u16 ssn,
- const struct iwl_trans_txq_scd_cfg *cfg,
+void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
+ u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg,
unsigned int wdg_timeout);
-void iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, u8 flags);
+/*
+ * Disable a TXQ.
+ * Note that in non-DQA mode the %mac80211_queue and %tid params are ignored.
+ */
+void iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
+ u8 tid, u8 flags);
+int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 minq, u8 maxq);
static inline
-void iwl_mvm_enable_ac_txq(struct iwl_mvm *mvm, int queue,
- u8 fifo, unsigned int wdg_timeout)
+void iwl_mvm_enable_ac_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
+ u8 fifo, u16 ssn, unsigned int wdg_timeout)
{
struct iwl_trans_txq_scd_cfg cfg = {
.fifo = fifo,
.frame_limit = IWL_FRAME_LIMIT,
};
- iwl_mvm_enable_txq(mvm, queue, 0, &cfg, wdg_timeout);
+ iwl_mvm_enable_txq(mvm, queue, mac80211_queue, ssn, &cfg, wdg_timeout);
}
static inline void iwl_mvm_enable_agg_txq(struct iwl_mvm *mvm, int queue,
- int fifo, int sta_id, int tid,
- int frame_limit, u16 ssn,
- unsigned int wdg_timeout)
+ int mac80211_queue, int fifo,
+ int sta_id, int tid, int frame_limit,
+ u16 ssn, unsigned int wdg_timeout)
{
struct iwl_trans_txq_scd_cfg cfg = {
.fifo = fifo,
.aggregate = true,
};
- iwl_mvm_enable_txq(mvm, queue, ssn, &cfg, wdg_timeout);
+ iwl_mvm_enable_txq(mvm, queue, mac80211_queue, ssn, &cfg, wdg_timeout);
}
/* Thermal management and CT-kill */
MODULE_LICENSE("GPL");
static const struct iwl_op_mode_ops iwl_mvm_ops;
+static const struct iwl_op_mode_ops iwl_mvm_ops_mq;
struct iwl_mvm_mod_params iwlmvm_mod_params = {
.power_scheme = IWL_POWER_SCHEME_BPS,
* called from a worker with mvm->mutex held.
*/
static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
- RX_HANDLER(REPLY_RX_PHY_CMD, iwl_mvm_rx_rx_phy_cmd, false),
RX_HANDLER(TX_CMD, iwl_mvm_rx_tx_cmd, false),
RX_HANDLER(BA_NOTIF, iwl_mvm_rx_ba_notif, false),
RX_HANDLER(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION,
iwl_mvm_power_uapsd_misbehaving_ap_notif, false),
RX_HANDLER(DTS_MEASUREMENT_NOTIFICATION, iwl_mvm_temp_notif, true),
+ RX_HANDLER_GRP(PHY_OPS_GROUP, DTS_MEASUREMENT_NOTIF_WIDE,
+ iwl_mvm_temp_notif, true),
RX_HANDLER(TDLS_CHANNEL_SWITCH_NOTIFICATION, iwl_mvm_rx_tdls_notif,
true),
static const char *const iwl_mvm_cmd_strings[REPLY_MAX + 1] = {
CMD(MVM_ALIVE),
CMD(REPLY_ERROR),
+ CMD(ECHO_CMD),
CMD(INIT_COMPLETE_NOTIF),
CMD(PHY_CONTEXT_CMD),
CMD(MGMT_MCAST_KEY),
hw->max_tx_aggregation_subframes = cfg->max_tx_agg_size;
op_mode = hw->priv;
- op_mode->ops = &iwl_mvm_ops;
mvm = IWL_OP_MODE_GET_MVM(op_mode);
mvm->dev = trans->dev;
mvm->fw = fw;
mvm->hw = hw;
+ if (iwl_mvm_has_new_rx_api(mvm)) {
+ op_mode->ops = &iwl_mvm_ops_mq;
+ } else {
+ op_mode->ops = &iwl_mvm_ops;
+
+ if (WARN_ON(trans->num_rx_queues > 1))
+ goto out_free;
+ }
+
mvm->restart_fw = iwlwifi_mod_params.restart_fw ? -1 : 0;
mvm->aux_queue = 15;
INIT_LIST_HEAD(&mvm->aux_roc_te_list);
INIT_LIST_HEAD(&mvm->async_handlers_list);
spin_lock_init(&mvm->time_event_lock);
+ spin_lock_init(&mvm->queue_info_lock);
INIT_WORK(&mvm->async_handlers_wk, iwl_mvm_async_handlers_wk);
INIT_WORK(&mvm->roc_done_wk, iwl_mvm_roc_done_wk);
ieee80211_unregister_hw(mvm->hw);
iwl_mvm_leds_exit(mvm);
out_free:
+ flush_delayed_work(&mvm->fw_dump_wk);
iwl_phy_db_free(mvm->phy_db);
kfree(mvm->scan_cmd);
if (!cfg->no_power_up_nic_in_init || !mvm->nvm_file_name)
}
}
-static void iwl_mvm_rx_dispatch(struct iwl_op_mode *op_mode,
- struct napi_struct *napi,
- struct iwl_rx_cmd_buffer *rxb)
+static void iwl_mvm_rx_common(struct iwl_mvm *mvm,
+ struct iwl_rx_cmd_buffer *rxb,
+ struct iwl_rx_packet *pkt)
{
- struct iwl_rx_packet *pkt = rxb_addr(rxb);
- struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
- u8 i;
-
- if (likely(pkt->hdr.cmd == REPLY_RX_MPDU_CMD)) {
- iwl_mvm_rx_rx_mpdu(mvm, napi, rxb);
- return;
- }
+ int i;
iwl_mvm_rx_check_trigger(mvm, pkt);
}
}
+static void iwl_mvm_rx(struct iwl_op_mode *op_mode,
+ struct napi_struct *napi,
+ struct iwl_rx_cmd_buffer *rxb)
+{
+ struct iwl_rx_packet *pkt = rxb_addr(rxb);
+ struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+ if (likely(pkt->hdr.cmd == REPLY_RX_MPDU_CMD))
+ iwl_mvm_rx_rx_mpdu(mvm, napi, rxb);
+ else if (pkt->hdr.cmd == REPLY_RX_PHY_CMD)
+ iwl_mvm_rx_rx_phy_cmd(mvm, rxb);
+ else
+ iwl_mvm_rx_common(mvm, rxb, pkt);
+}
+
+static void iwl_mvm_rx_mq(struct iwl_op_mode *op_mode,
+ struct napi_struct *napi,
+ struct iwl_rx_cmd_buffer *rxb)
+{
+ struct iwl_rx_packet *pkt = rxb_addr(rxb);
+ struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+ if (likely(pkt->hdr.cmd == REPLY_RX_MPDU_CMD))
+ iwl_mvm_rx_rx_mpdu(mvm, napi, rxb);
+ else if (pkt->hdr.cmd == REPLY_RX_PHY_CMD)
+ iwl_mvm_rx_rx_phy_cmd(mvm, rxb);
+ else
+ iwl_mvm_rx_common(mvm, rxb, pkt);
+}
+
static void iwl_mvm_stop_sw_queue(struct iwl_op_mode *op_mode, int queue)
{
struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
- int mq = mvm->queue_to_mac80211[queue];
+ unsigned long mq;
+ int q;
- if (WARN_ON_ONCE(mq == IWL_INVALID_MAC80211_QUEUE))
- return;
+ spin_lock_bh(&mvm->queue_info_lock);
+ mq = mvm->queue_info[queue].hw_queue_to_mac80211;
+ spin_unlock_bh(&mvm->queue_info_lock);
- if (atomic_inc_return(&mvm->mac80211_queue_stop_count[mq]) > 1) {
- IWL_DEBUG_TX_QUEUES(mvm,
- "queue %d (mac80211 %d) already stopped\n",
- queue, mq);
+ if (WARN_ON_ONCE(!mq))
return;
- }
- ieee80211_stop_queue(mvm->hw, mq);
+ for_each_set_bit(q, &mq, IEEE80211_MAX_QUEUES) {
+ if (atomic_inc_return(&mvm->mac80211_queue_stop_count[q]) > 1) {
+ IWL_DEBUG_TX_QUEUES(mvm,
+ "queue %d (mac80211 %d) already stopped\n",
+ queue, q);
+ continue;
+ }
+
+ ieee80211_stop_queue(mvm->hw, q);
+ }
}
static void iwl_mvm_wake_sw_queue(struct iwl_op_mode *op_mode, int queue)
{
struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
- int mq = mvm->queue_to_mac80211[queue];
+ unsigned long mq;
+ int q;
- if (WARN_ON_ONCE(mq == IWL_INVALID_MAC80211_QUEUE))
- return;
+ spin_lock_bh(&mvm->queue_info_lock);
+ mq = mvm->queue_info[queue].hw_queue_to_mac80211;
+ spin_unlock_bh(&mvm->queue_info_lock);
- if (atomic_dec_return(&mvm->mac80211_queue_stop_count[mq]) > 0) {
- IWL_DEBUG_TX_QUEUES(mvm,
- "queue %d (mac80211 %d) still stopped\n",
- queue, mq);
+ if (WARN_ON_ONCE(!mq))
return;
- }
- ieee80211_wake_queue(mvm->hw, mq);
+ for_each_set_bit(q, &mq, IEEE80211_MAX_QUEUES) {
+ if (atomic_dec_return(&mvm->mac80211_queue_stop_count[q]) > 0) {
+ IWL_DEBUG_TX_QUEUES(mvm,
+ "queue %d (mac80211 %d) still stopped\n",
+ queue, q);
+ continue;
+ }
+
+ ieee80211_wake_queue(mvm->hw, q);
+ }
}
void iwl_mvm_set_hw_ctkill_state(struct iwl_mvm *mvm, bool state)
/* make sure we have no running tx while configuring the seqno */
synchronize_net();
- iwl_mvm_set_wowlan_data(mvm, &wowlan_config_cmd, &d0i3_iter_data);
- ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_CONFIGURATION, flags,
- sizeof(wowlan_config_cmd),
- &wowlan_config_cmd);
- if (ret)
- return ret;
+ /* configure wowlan configuration only if needed */
+ if (mvm->d0i3_ap_sta_id != IWL_MVM_STATION_COUNT) {
+ iwl_mvm_set_wowlan_data(mvm, &wowlan_config_cmd,
+ &d0i3_iter_data);
+
+ ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_CONFIGURATION, flags,
+ sizeof(wowlan_config_cmd),
+ &wowlan_config_cmd);
+ if (ret)
+ return ret;
+ }
return iwl_mvm_send_cmd_pdu(mvm, D3_CONFIG_CMD,
flags | CMD_MAKE_TRANS_IDLE,
};
struct iwl_wowlan_status *status;
int ret;
- u32 handled_reasons, wakeup_reasons;
+ u32 handled_reasons, wakeup_reasons = 0;
__le16 *qos_seq = NULL;
mutex_lock(&mvm->mutex);
out:
iwl_mvm_d0i3_enable_tx(mvm, qos_seq);
+ IWL_DEBUG_INFO(mvm, "d0i3 exit completed (wakeup reasons: 0x%x)\n",
+ wakeup_reasons);
+
/* qos_seq might point inside resp_pkt, so free it only now */
if (get_status_cmd.resp_pkt)
iwl_free_resp(&get_status_cmd);
return _iwl_mvm_exit_d0i3(mvm);
}
+#define IWL_MVM_COMMON_OPS \
+ /* these could be differentiated */ \
+ .queue_full = iwl_mvm_stop_sw_queue, \
+ .queue_not_full = iwl_mvm_wake_sw_queue, \
+ .hw_rf_kill = iwl_mvm_set_hw_rfkill_state, \
+ .free_skb = iwl_mvm_free_skb, \
+ .nic_error = iwl_mvm_nic_error, \
+ .cmd_queue_full = iwl_mvm_cmd_queue_full, \
+ .nic_config = iwl_mvm_nic_config, \
+ .enter_d0i3 = iwl_mvm_enter_d0i3, \
+ .exit_d0i3 = iwl_mvm_exit_d0i3, \
+ /* as we only register one, these MUST be common! */ \
+ .start = iwl_op_mode_mvm_start, \
+ .stop = iwl_op_mode_mvm_stop
+
static const struct iwl_op_mode_ops iwl_mvm_ops = {
- .start = iwl_op_mode_mvm_start,
- .stop = iwl_op_mode_mvm_stop,
- .rx = iwl_mvm_rx_dispatch,
- .queue_full = iwl_mvm_stop_sw_queue,
- .queue_not_full = iwl_mvm_wake_sw_queue,
- .hw_rf_kill = iwl_mvm_set_hw_rfkill_state,
- .free_skb = iwl_mvm_free_skb,
- .nic_error = iwl_mvm_nic_error,
- .cmd_queue_full = iwl_mvm_cmd_queue_full,
- .nic_config = iwl_mvm_nic_config,
- .enter_d0i3 = iwl_mvm_enter_d0i3,
- .exit_d0i3 = iwl_mvm_exit_d0i3,
+ IWL_MVM_COMMON_OPS,
+ .rx = iwl_mvm_rx,
+};
+
+static void iwl_mvm_rx_mq_rss(struct iwl_op_mode *op_mode,
+ struct napi_struct *napi,
+ struct iwl_rx_cmd_buffer *rxb,
+ unsigned int queue)
+{
+ struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
+
+ iwl_mvm_rx_rx_mpdu(mvm, napi, rxb);
+}
+
+static const struct iwl_op_mode_ops iwl_mvm_ops_mq = {
+ IWL_MVM_COMMON_OPS,
+ .rx = iwl_mvm_rx_mq,
+ .rx_rss = iwl_mvm_rx_mq_rss,
};
#define tw_dport __tw_common.skc_dport
#define tw_num __tw_common.skc_num
#define tw_cookie __tw_common.skc_cookie
+#define tw_dr __tw_common.skc_tw_dr
int tw_timeout;
volatile unsigned char tw_substate;
kmemcheck_bitfield_end(flags);
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
- struct inet_timewait_death_row *tw_dr;
};
#define tw_tclass tw_tos
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
bool rearm);
- static void inline inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
+ static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
{
__inet_twsk_schedule(tw, timeo, false);
}
- static void inline inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
+ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
{
__inet_twsk_schedule(tw, timeo, true);
}
* @skc_node: main hash linkage for various protocol lookup tables
* @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
* @skc_tx_queue_mapping: tx queue number for this connection
+ * @skc_flags: place holder for sk_flags
+ * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
+ * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
+ * @skc_incoming_cpu: record/match cpu processing incoming packets
* @skc_refcnt: reference count
*
* This is the minimal network layer representation of sockets, the header
atomic64_t skc_cookie;
+ /* following fields are padding to force
+ * offset(struct sock, sk_refcnt) == 128 on 64bit arches
+ * assuming IPV6 is enabled. We use this padding differently
+ * for different kind of 'sockets'
+ */
+ union {
+ unsigned long skc_flags;
+ struct sock *skc_listener; /* request_sock */
+ struct inet_timewait_death_row *skc_tw_dr; /* inet_timewait_sock */
+ };
/*
* fields between dontcopy_begin/dontcopy_end
* are not copied in sock_copy()
struct hlist_nulls_node skc_nulls_node;
};
int skc_tx_queue_mapping;
+ union {
+ int skc_incoming_cpu;
+ u32 skc_rcv_wnd;
+ u32 skc_tw_rcv_nxt; /* struct tcp_timewait_sock */
+ };
+
atomic_t skc_refcnt;
/* private: */
int skc_dontcopy_end[0];
+ union {
+ u32 skc_rxhash;
+ u32 skc_window_clamp;
+ u32 skc_tw_snd_nxt; /* struct tcp_timewait_sock */
+ };
/* public: */
};
* @sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
* @sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
* @sk_sndbuf: size of send buffer in bytes
- * @sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
- * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
* @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets
* @sk_no_check_rx: allow zero checksum in RX packets
* @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
* @sk_rcvlowat: %SO_RCVLOWAT setting
* @sk_rcvtimeo: %SO_RCVTIMEO setting
* @sk_sndtimeo: %SO_SNDTIMEO setting
- * @sk_rxhash: flow hash received from netif layer
- * @sk_incoming_cpu: record cpu processing incoming packets
* @sk_txhash: computed flow hash for use on transmit
* @sk_filter: socket filtering instructions
* @sk_timer: sock cleanup timer
#define sk_v6_daddr __sk_common.skc_v6_daddr
#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr
#define sk_cookie __sk_common.skc_cookie
+#define sk_incoming_cpu __sk_common.skc_incoming_cpu
+#define sk_flags __sk_common.skc_flags
+#define sk_rxhash __sk_common.skc_rxhash
socket_lock_t sk_lock;
struct sk_buff_head sk_receive_queue;
} sk_backlog;
#define sk_rmem_alloc sk_backlog.rmem_alloc
int sk_forward_alloc;
-#ifdef CONFIG_RPS
- __u32 sk_rxhash;
-#endif
- u16 sk_incoming_cpu;
- /* 16bit hole
- * Warned : sk_incoming_cpu can be set from softirq,
- * Do not use this hole without fully understanding possible issues.
- */
__u32 sk_txhash;
#ifdef CONFIG_NET_RX_BUSY_POLL
#ifdef CONFIG_XFRM
struct xfrm_policy *sk_policy[2];
#endif
- unsigned long sk_flags;
struct dst_entry *sk_rx_dst;
struct dst_entry __rcu *sk_dst_cache;
spinlock_t sk_dst_lock;
#endif
-static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask)
+static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask)
{
return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC);
}
if (sk_rcvqueues_full(sk, limit))
return -ENOBUFS;
+ /*
+ * If the skb was allocated from pfmemalloc reserves, only
+ * allow SOCK_MEMALLOC sockets to use it as this socket is
+ * helping free memory
+ */
+ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC))
+ return -ENOMEM;
+
__sk_add_backlog(sk, skb);
sk->sk_backlog.len += skb->truesize;
return 0;
void sock_kzfree_s(struct sock *sk, void *mem, int size);
void sk_send_sigurg(struct sock *sk);
+struct sockcm_cookie {
+ u32 mark;
+};
+
+int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
+ struct sockcm_cookie *sockc);
+
/*
* Functions to fill in entries in struct proto_ops when a protocol
* does not implement a particular function.
kuid_t sock_i_uid(struct sock *sk);
unsigned long sock_i_ino(struct sock *sk);
-static inline void sk_set_txhash(struct sock *sk)
+static inline u32 net_tx_rndhash(void)
{
- sk->sk_txhash = prandom_u32();
+ u32 v = prandom_u32();
- if (unlikely(!sk->sk_txhash))
- sk->sk_txhash = 1;
+ return v ?: 1;
+}
+
+static inline void sk_set_txhash(struct sock *sk)
+{
+ sk->sk_txhash = net_tx_rndhash();
}
static inline void sk_rethink_txhash(struct sock *sk)
return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
}
+/* This helper checks if a socket is a LISTEN or NEW_SYN_RECV
+ * SYNACK messages can be attached to either ones (depending on SYNCOOKIE)
+ */
+static inline bool sk_listener(const struct sock *sk)
+{
+ return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
+}
+
void sock_enable_timestamp(struct sock *sk, int flag);
int sock_get_timestamp(struct sock *, struct timeval __user *);
int sock_get_timestampns(struct sock *, struct timespec __user *);
OVS_KEY_ATTR_MPLS, /* array of struct ovs_key_mpls.
* The implementation may restrict
* the accepted length of the array. */
- OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */
+ OVS_KEY_ATTR_CT_STATE, /* u32 bitmask of OVS_CS_F_* */
OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */
OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */
- OVS_KEY_ATTR_CT_LABEL, /* 16-octet connection tracking label */
+ OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */
#ifdef __KERNEL__
OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */
OVS_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */
OVS_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */
OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS, /* Nested OVS_VXLAN_EXT_* */
+ OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */
+ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */
__OVS_TUNNEL_KEY_ATTR_MAX
};
__u8 nd_tll[ETH_ALEN];
};
- #define OVS_CT_LABEL_LEN 16
- struct ovs_key_ct_label {
- __u8 ct_label[OVS_CT_LABEL_LEN];
+ #define OVS_CT_LABELS_LEN 16
+ struct ovs_key_ct_labels {
+ __u8 ct_labels[OVS_CT_LABELS_LEN];
};
/* OVS_KEY_ATTR_CT_STATE flags */
#define OVS_CS_F_ESTABLISHED 0x02 /* Part of an existing connection. */
#define OVS_CS_F_RELATED 0x04 /* Related to an established
* connection. */
- #define OVS_CS_F_INVALID 0x20 /* Could not track connection. */
- #define OVS_CS_F_REPLY_DIR 0x40 /* Flow is in the reply direction. */
- #define OVS_CS_F_TRACKED 0x80 /* Conntrack has occurred. */
+ #define OVS_CS_F_REPLY_DIR 0x08 /* Flow is in the reply direction. */
+ #define OVS_CS_F_INVALID 0x10 /* Could not track connection. */
+ #define OVS_CS_F_TRACKED 0x20 /* Conntrack has occurred. */
/**
* enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
/**
* enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action.
- * @OVS_CT_ATTR_FLAGS: u32 connection tracking flags.
+ * @OVS_CT_ATTR_COMMIT: If present, commits the connection to the conntrack
+ * table. This allows future packets for the same connection to be identified
+ * as 'established' or 'related'.
* @OVS_CT_ATTR_ZONE: u16 connection tracking zone.
* @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the
* mask, the corresponding bit in the value is copied to the connection
* tracking mark field in the connection.
- * @OVS_CT_ATTR_LABEL: %OVS_CT_LABEL_LEN value followed by %OVS_CT_LABEL_LEN
+ * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN
* mask. For each bit set in the mask, the corresponding bit in the value is
* copied to the connection tracking label field in the connection.
* @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG.
*/
enum ovs_ct_attr {
OVS_CT_ATTR_UNSPEC,
- OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */
+ OVS_CT_ATTR_COMMIT, /* No argument, commits connection. */
OVS_CT_ATTR_ZONE, /* u16 zone id. */
OVS_CT_ATTR_MARK, /* mark to associate with this connection. */
- OVS_CT_ATTR_LABEL, /* label to associate with this connection. */
+ OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */
OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of
related connections. */
__OVS_CT_ATTR_MAX
#define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1)
- /*
- * OVS_CT_ATTR_FLAGS flags - bitmask of %OVS_CT_F_*
- * @OVS_CT_F_COMMIT: Commits the flow to the conntrack table. This allows
- * future packets for the same connection to be identified as 'established'
- * or 'related'.
- */
- #define OVS_CT_F_COMMIT 0x01
-
/**
* enum ovs_action_attr - Action types.
*
* data immediately followed by a mask.
* The data must be zero for the unmasked
* bits. */
- OVS_ACTION_ATTR_CT, /* One nested OVS_CT_ATTR_* . */
+ OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
/* Macros to handle rtattributes */
- #define RTA_ALIGNTO 4
+ #define RTA_ALIGNTO 4U
#define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) )
#define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \
(rta)->rta_len >= sizeof(struct rtattr) && \
#define RTM_F_CLONED 0x200 /* This route is cloned */
#define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */
#define RTM_F_PREFIX 0x800 /* Prefix addresses */
+#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */
/* Reserved table identifiers */
#define RTEXT_FILTER_VF (1 << 0)
#define RTEXT_FILTER_BRVLAN (1 << 1)
#define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2)
+#define RTEXT_FILTER_SKIP_STATS (1 << 3)
/* End of information exported to user level */
.llseek = default_llseek,
};
+static ssize_t vendor_diag_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct hci_dev *hdev = file->private_data;
+ char buf[3];
+
+ buf[0] = hci_dev_test_flag(hdev, HCI_VENDOR_DIAG) ? 'Y': 'N';
+ buf[1] = '\n';
+ buf[2] = '\0';
+ return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t vendor_diag_write(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct hci_dev *hdev = file->private_data;
+ char buf[32];
+ size_t buf_size = min(count, (sizeof(buf)-1));
+ bool enable;
+ int err;
+
+ if (copy_from_user(buf, user_buf, buf_size))
+ return -EFAULT;
+
+ buf[buf_size] = '\0';
+ if (strtobool(buf, &enable))
+ return -EINVAL;
+
+ hci_req_lock(hdev);
+ err = hdev->set_diag(hdev, enable);
+ hci_req_unlock(hdev);
+
+ if (err < 0)
+ return err;
+
+ if (enable)
+ hci_dev_set_flag(hdev, HCI_VENDOR_DIAG);
+ else
+ hci_dev_clear_flag(hdev, HCI_VENDOR_DIAG);
+
+ return count;
+}
+
+static const struct file_operations vendor_diag_fops = {
+ .open = simple_open,
+ .read = vendor_diag_read,
+ .write = vendor_diag_write,
+ .llseek = default_llseek,
+};
+
+static void hci_debugfs_create_basic(struct hci_dev *hdev)
+{
+ debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev,
+ &dut_mode_fops);
+
+ if (hdev->set_diag)
+ debugfs_create_file("vendor_diag", 0644, hdev->debugfs, hdev,
+ &vendor_diag_fops);
+}
+
/* ---- HCI requests ---- */
static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
hci_setup_event_mask(req);
- if (hdev->commands[6] & 0x20) {
+ if (hdev->commands[6] & 0x20 &&
+ !test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) {
struct hci_cp_read_stored_link_key cp;
bacpy(&cp.bdaddr, BDADDR_ANY);
if (err < 0)
return err;
- /* The Device Under Test (DUT) mode is special and available for
- * all controller types. So just create it early on.
- */
- if (hci_dev_test_flag(hdev, HCI_SETUP)) {
- debugfs_create_file("dut_mode", 0644, hdev->debugfs, hdev,
- &dut_mode_fops);
- }
+ if (hci_dev_test_flag(hdev, HCI_SETUP))
+ hci_debugfs_create_basic(hdev);
err = __hci_req_sync(hdev, hci_init2_req, 0, HCI_INIT_TIMEOUT);
if (err < 0)
if (err < 0)
return err;
+ if (hci_dev_test_flag(hdev, HCI_SETUP))
+ hci_debugfs_create_basic(hdev);
+
return 0;
}
goto done;
}
+ set_bit(HCI_RUNNING, &hdev->flags);
+ hci_notify(hdev, HCI_DEV_OPEN);
+
atomic_set(&hdev->cmd_cnt, 1);
set_bit(HCI_INIT, &hdev->flags);
hdev->sent_cmd = NULL;
}
+ clear_bit(HCI_RUNNING, &hdev->flags);
+ hci_notify(hdev, HCI_DEV_CLOSE);
+
hdev->close(hdev);
hdev->flags &= BIT(HCI_RAW);
}
BT_DBG("All LE pending actions cleared");
}
-static int hci_dev_do_close(struct hci_dev *hdev)
+int hci_dev_do_close(struct hci_dev *hdev)
{
+ bool auto_off;
+
BT_DBG("%s %p", hdev->name, hdev);
if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) &&
hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
- if (!hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) {
- if (hdev->dev_type == HCI_BREDR)
- mgmt_powered(hdev, 0);
- }
+ auto_off = hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF);
+
+ if (!auto_off && hdev->dev_type == HCI_BREDR)
+ mgmt_powered(hdev, 0);
hci_inquiry_cache_flush(hdev);
hci_pend_le_actions_clear(hdev);
/* Reset device */
skb_queue_purge(&hdev->cmd_q);
atomic_set(&hdev->cmd_cnt, 1);
- if (!hci_dev_test_flag(hdev, HCI_AUTO_OFF) &&
- !hci_dev_test_flag(hdev, HCI_UNCONFIGURED) &&
- test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks)) {
+ if (test_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks) &&
+ !auto_off && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
set_bit(HCI_INIT, &hdev->flags);
__hci_req_sync(hdev, hci_reset_req, 0, HCI_CMD_TIMEOUT);
clear_bit(HCI_INIT, &hdev->flags);
hdev->sent_cmd = NULL;
}
+ clear_bit(HCI_RUNNING, &hdev->flags);
+ hci_notify(hdev, HCI_DEV_CLOSE);
+
/* After this point our queues are empty
* and no tasks are scheduled. */
hdev->close(hdev);
return param;
}
- list_for_each_entry(param, &hdev->pend_le_reports, action) {
- if (bacmp(¶m->addr, addr) == 0 &&
- param->addr_type == addr_type &&
- param->explicit_connect)
- return param;
- }
-
return NULL;
}
return -ENXIO;
}
+ if (bt_cb(skb)->pkt_type != HCI_EVENT_PKT &&
+ bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+ bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
/* Incoming skb */
bt_cb(skb)->incoming = 1;
}
EXPORT_SYMBOL(hci_recv_frame);
+/* Receive diagnostic message from HCI drivers */
+int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ /* Time stamp */
+ __net_timestamp(skb);
+
+ /* Mark as diagnostic packet and send to monitor */
+ bt_cb(skb)->pkt_type = HCI_DIAG_PKT;
+ hci_send_to_monitor(hdev, skb);
+
+ kfree_skb(skb);
+ return 0;
+}
+EXPORT_SYMBOL(hci_recv_diag);
+
/* ---- Interface to upper protocols ---- */
int hci_register_cb(struct hci_cb *cb)
/* Get rid of skb owner, prior to sending to the driver. */
skb_orphan(skb);
+ if (!test_bit(HCI_RUNNING, &hdev->flags)) {
+ kfree_skb(skb);
+ return;
+ }
+
err = hdev->send(hdev, skb);
if (err < 0) {
BT_ERR("%s sending frame failed (%d)", hdev->name, err);
return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE;
}
+/* Send HCI command and wait for command commplete event */
+struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen,
+ const void *param, u32 timeout)
+{
+ struct sk_buff *skb;
+
+ if (!test_bit(HCI_UP, &hdev->flags))
+ return ERR_PTR(-ENETDOWN);
+
+ bt_dev_dbg(hdev, "opcode 0x%4.4x plen %d", opcode, plen);
+
+ hci_req_lock(hdev);
+ skb = __hci_cmd_sync(hdev, opcode, plen, param, timeout);
+ hci_req_unlock(hdev);
+
+ return skb;
+}
+EXPORT_SYMBOL(hci_cmd_sync);
+
/* Send ACL data */
static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags)
{
wake_up_bit(&hdev->flags, HCI_INQUIRY);
hci_dev_lock(hdev);
- hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
+ /* Set discovery state to stopped if we're not doing LE active
+ * scanning.
+ */
+ if (!hci_dev_test_flag(hdev, HCI_LE_SCAN) ||
+ hdev->le_scan_type != LE_SCAN_ACTIVE)
+ hci_discovery_set_state(hdev, DISCOVERY_STOPPED);
hci_dev_unlock(hdev);
hci_conn_check_pending(hdev);
/* If we're not connectable only connect devices that we have in
* our pend_le_conns list.
*/
- params = hci_explicit_connect_lookup(hdev, addr, addr_type);
-
+ params = hci_pend_le_action_lookup(&hdev->pend_le_conns, addr,
+ addr_type);
if (!params)
return NULL;
struct hci_conn *conn;
bool match;
u32 flags;
+ u8 *ptr, real_len;
+
+ /* Find the end of the data in case the report contains padded zero
+ * bytes at the end causing an invalid length value.
+ *
+ * When data is NULL, len is 0 so there is no need for extra ptr
+ * check as 'ptr < data + 0' is already false in such case.
+ */
+ for (ptr = data; ptr < data + len && *ptr; ptr += *ptr + 1) {
+ if (ptr + 1 + *ptr > data + len)
+ break;
+ }
+
+ real_len = ptr - data;
+
+ /* Adjust for actual length */
+ if (len != real_len) {
+ BT_ERR_RATELIMITED("%s advertising data length corrected",
+ hdev->name);
+ len = real_len;
+ }
/* If the direct address is present, then this report is from
* a LE Direct Advertising Report event. In that case it is
#include <net/sch_generic.h>
#include <net/cls_cgroup.h>
#include <net/dst_metadata.h>
+#include <net/dst.h>
/**
* sk_filter - run a packet through a socket filter
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
*
- * Run the filter code and then cut skb->data to correct size returned by
- * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller
+ * Run the eBPF program and then cut skb->data to correct size returned by
+ * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
- * wrapper to SK_RUN_FILTER. It returns 0 if the packet should
+ * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
- unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
+ unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
return raw_smp_processor_id();
}
-/* note that this only generates 32-bit random numbers */
-static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
-{
- return prandom_u32();
-}
-
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
- *insn = BPF_EMIT_CALL(__get_random_u32);
+ *insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
+ bpf_user_rnd_init_once();
break;
}
break;
int err;
fp->bpf_func = NULL;
- fp->jited = false;
+ fp->jited = 0;
err = bpf_check_classic(fp->insns, fp->len);
if (err) {
* @pfp: the unattached filter that is created
* @fprog: the filter program
* @trans: post-classic verifier transformation handler
+ * @save_orig: save classic BPF program
*
* This function effectively does the same as bpf_prog_create(), only
* that it builds up its insns buffer from user space provided buffer.
* It also allows for passing a bpf_aux_classic_check_t handler.
*/
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
- bpf_aux_classic_check_t trans)
+ bpf_aux_classic_check_t trans, bool save_orig)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
+ int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
}
fp->len = fprog->len;
- /* Since unattached filters are not copied back to user
- * space through sk_get_filter(), we do not need to hold
- * a copy here, and can spare us the work.
- */
fp->orig_prog = NULL;
+ if (save_orig) {
+ err = bpf_prog_store_orig_filter(fp, fprog);
+ if (err) {
+ __bpf_prog_free(fp);
+ return -ENOMEM;
+ }
+ }
+
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
if (unlikely(!dev))
return -EINVAL;
- if (unlikely(!(dev->flags & IFF_UP)))
- return -EINVAL;
-
skb2 = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!skb2))
return -ENOMEM;
return dev_forward_skb(dev, skb2);
skb2->dev = dev;
+ skb_sender_cpu_clear(skb2);
return dev_queue_xmit(skb2);
}
.arg3_type = ARG_ANYTHING,
};
+struct redirect_info {
+ u32 ifindex;
+ u32 flags;
+};
+
+static DEFINE_PER_CPU(struct redirect_info, redirect_info);
+static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+
+ ri->ifindex = ifindex;
+ ri->flags = flags;
+ return TC_ACT_REDIRECT;
+}
+
+int skb_do_redirect(struct sk_buff *skb)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ struct net_device *dev;
+
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex);
+ ri->ifindex = 0;
+ if (unlikely(!dev)) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ if (BPF_IS_REDIRECT_INGRESS(ri->flags))
+ return dev_forward_skb(dev, skb);
+
+ skb->dev = dev;
+ skb_sender_cpu_clear(skb);
+ return dev_queue_xmit(skb);
+}
+
+const struct bpf_func_proto bpf_redirect_proto = {
+ .func = bpf_redirect,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+ .arg2_type = ARG_ANYTHING,
+};
+
static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
return task_get_classid((struct sk_buff *) (unsigned long) r1);
.arg1_type = ARG_PTR_TO_CTX,
};
+static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ const struct dst_entry *dst;
+
+ dst = skb_dst((struct sk_buff *) (unsigned long) r1);
+ if (dst)
+ return dst->tclassid;
+#endif
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_route_realm_proto = {
+ .func = bpf_get_route_realm,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_trace_printk:
- return bpf_get_trace_printk_proto();
+ if (capable(CAP_SYS_ADMIN))
+ return bpf_get_trace_printk_proto();
default:
return NULL;
}
return &bpf_skb_get_tunnel_key_proto;
case BPF_FUNC_skb_set_tunnel_key:
return bpf_get_skb_set_tunnel_key_proto();
+ case BPF_FUNC_redirect:
+ return &bpf_redirect_proto;
+ case BPF_FUNC_get_route_realm:
+ return &bpf_get_route_realm_proto;
default:
return sk_filter_func_proto(func_id);
}
static bool sk_filter_is_valid_access(int off, int size,
enum bpf_access_type type)
{
+ if (off == offsetof(struct __sk_buff, tc_classid))
+ return false;
+
if (type == BPF_WRITE) {
switch (off) {
case offsetof(struct __sk_buff, cb[0]) ...
static bool tc_cls_act_is_valid_access(int off, int size,
enum bpf_access_type type)
{
+ if (off == offsetof(struct __sk_buff, tc_classid))
+ return type == BPF_WRITE ? true : false;
+
if (type == BPF_WRITE) {
switch (off) {
case offsetof(struct __sk_buff, mark):
case offsetof(struct __sk_buff, tc_index):
+ case offsetof(struct __sk_buff, priority):
case offsetof(struct __sk_buff, cb[0]) ...
offsetof(struct __sk_buff, cb[4]):
break;
static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
- struct bpf_insn *insn_buf)
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog)
{
struct bpf_insn *insn = insn_buf;
case offsetof(struct __sk_buff, priority):
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4);
- *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
- offsetof(struct sk_buff, priority));
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
break;
case offsetof(struct __sk_buff, ingress_ifindex):
offsetof(struct __sk_buff, cb[4]):
BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20);
+ prog->cb_access = 1;
ctx_off -= offsetof(struct __sk_buff, cb[0]);
ctx_off += offsetof(struct sk_buff, cb);
ctx_off += offsetof(struct qdisc_skb_cb, data);
*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off);
break;
+ case offsetof(struct __sk_buff, tc_classid):
+ ctx_off -= offsetof(struct __sk_buff, tc_classid);
+ ctx_off += offsetof(struct sk_buff, cb);
+ ctx_off += offsetof(struct qdisc_skb_cb, tc_classid);
+ WARN_ON(type != BPF_WRITE);
+ *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off);
+ break;
+
case offsetof(struct __sk_buff, tc_index):
#ifdef CONFIG_NET_SCHED
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2);
goto out;
/* We're copying the filter that has been originally attached,
- * so no conversion/decode needed anymore.
+ * so no conversion/decode needed anymore. eBPF programs that
+ * have no original program cannot be dumped through this.
*/
+ ret = -EACCES;
fprog = filter->prog->orig_prog;
+ if (!fprog)
+ goto out;
ret = fprog->len;
if (!len)
#include <linux/of_platform.h>
#include <linux/of_net.h>
#include <linux/sysfs.h>
+ #include <linux/phy_fixed.h>
#include "dsa_priv.h"
char dsa_driver_version[] = "0.1";
if (ret < 0)
goto out;
- ds->slave_mii_bus = mdiobus_alloc();
+ ds->slave_mii_bus = devm_mdiobus_alloc(parent);
if (ds->slave_mii_bus == NULL) {
ret = -ENOMEM;
goto out;
ret = mdiobus_register(ds->slave_mii_bus);
if (ret < 0)
- goto out_free;
+ goto out;
/*
ret = dsa_slave_create(ds, parent, i, pd->port_names[i]);
if (ret < 0) {
- netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s)\n",
- index, i, pd->port_names[i]);
+ netdev_err(dst->master_netdev, "[%d]: can't create dsa slave device for port %d(%s): %d\n",
+ index, i, pd->port_names[i], ret);
ret = 0;
}
}
return ret;
- out_free:
- mdiobus_free(ds->slave_mii_bus);
out:
- kfree(ds);
return ret;
}
/*
* Allocate and initialise switch state.
*/
- ds = kzalloc(sizeof(*ds) + drv->priv_size, GFP_KERNEL);
+ ds = devm_kzalloc(parent, sizeof(*ds) + drv->priv_size, GFP_KERNEL);
if (ds == NULL)
return ERR_PTR(-ENOMEM);
static void dsa_switch_destroy(struct dsa_switch *ds)
{
+ struct device_node *port_dn;
+ struct phy_device *phydev;
+ struct dsa_chip_data *cd = ds->pd;
+ int port;
+
#ifdef CONFIG_NET_DSA_HWMON
if (ds->hwmon_dev)
hwmon_device_unregister(ds->hwmon_dev);
#endif
+
+ /* Disable configuration of the CPU and DSA ports */
+ for (port = 0; port < DSA_MAX_PORTS; port++) {
+ if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
+ continue;
+
+ port_dn = cd->port_dn[port];
+ if (of_phy_is_fixed_link(port_dn)) {
+ phydev = of_phy_find_device(port_dn);
+ if (phydev) {
+ int addr = phydev->addr;
+
+ phy_device_free(phydev);
+ of_node_put(port_dn);
+ fixed_phy_del(addr);
+ }
+ }
+ }
+
+ /* Destroy network devices for physical switch ports. */
+ for (port = 0; port < DSA_MAX_PORTS; port++) {
+ if (!(ds->phys_port_mask & (1 << port)))
+ continue;
+
+ if (!ds->ports[port])
+ continue;
+
+ unregister_netdev(ds->ports[port]);
+ free_netdev(ds->ports[port]);
+ }
+
+ mdiobus_unregister(ds->slave_mii_bus);
}
#ifdef CONFIG_PM_SLEEP
}
#endif
- static void dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
- struct device *parent, struct dsa_platform_data *pd)
+ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev,
+ struct device *parent, struct dsa_platform_data *pd)
{
int i;
+ unsigned configured = 0;
dst->pd = pd;
dst->master_netdev = dev;
dst->ds[i] = ds;
if (ds->drv->poll_link != NULL)
dst->link_poll_needed = 1;
+
+ ++configured;
}
+ /*
+ * If no switch was found, exit cleanly
+ */
+ if (!configured)
+ return -EPROBE_DEFER;
+
/*
* If we use a tagging format that doesn't have an ethertype
* field, make sure that all packets from this point on get
dst->link_poll_timer.expires = round_jiffies(jiffies + HZ);
add_timer(&dst->link_poll_timer);
}
+
+ return 0;
}
static int dsa_probe(struct platform_device *pdev)
goto out;
}
- dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ dst = devm_kzalloc(&pdev->dev, sizeof(*dst), GFP_KERNEL);
if (dst == NULL) {
dev_put(dev);
ret = -ENOMEM;
platform_set_drvdata(pdev, dst);
- dsa_setup_dst(dst, dev, &pdev->dev, pd);
+ ret = dsa_setup_dst(dst, dev, &pdev->dev, pd);
+ if (ret)
+ goto out;
return 0;
for (i = 0; i < dst->pd->nr_chips; i++) {
struct dsa_switch *ds = dst->ds[i];
- if (ds != NULL)
+ if (ds)
dsa_switch_destroy(ds);
}
}
if (!skb)
return;
- skb_dst_set(skb, dst);
+ skb_dst_set(skb, dst_clone(dst));
arp_xmit(skb);
}
}
if (skb && !(dev->priv_flags & IFF_XMIT_DST_RELEASE))
- dst = dst_clone(skb_dst(skb));
+ dst = skb_dst(skb);
arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
dst_hw, dev->dev_addr, NULL, dst);
}
}
EXPORT_SYMBOL(arp_create);
+static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+ return dev_queue_xmit(skb);
+}
+
/*
* Send an arp packet.
*/
void arp_xmit(struct sk_buff *skb)
{
/* Send it off, maybe filter it using firewalling first. */
- NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, NULL, skb,
- NULL, skb->dev, dev_queue_xmit_sk);
+ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT,
+ dev_net(skb->dev), NULL, skb, NULL, skb->dev,
+ arp_xmit_finish);
}
EXPORT_SYMBOL(arp_xmit);
* Process an arp request.
*/
-static int arp_process(struct sock *sk, struct sk_buff *skb)
+static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev = __in_dev_get_rcu(dev);
u16 dev_type = dev->type;
int addr_type;
struct neighbour *n;
- struct net *net = dev_net(dev);
struct dst_entry *reply_dst = NULL;
bool is_garp = false;
} else {
pneigh_enqueue(&arp_tbl,
in_dev->arp_parms, skb);
- return 0;
+ goto out_free_dst;
}
goto out;
}
out:
consume_skb(skb);
+ out_free_dst:
+ dst_release(reply_dst);
return 0;
}
static void parp_redo(struct sk_buff *skb)
{
- arp_process(NULL, skb);
+ arp_process(dev_net(skb->dev), NULL, skb);
}
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
- return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, NULL, skb,
- dev, NULL, arp_process);
+ return NF_HOOK(NFPROTO_ARP, NF_ARP_IN,
+ dev_net(dev), NULL, skb, dev, NULL,
+ arp_process);
consumeskb:
consume_skb(skb);
#include <net/ip.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
+#include <net/l3mdev.h>
#include <linux/if_tunnel.h>
#include <linux/rtnetlink.h>
#include <linux/netconf.h>
unsigned long expires, u32 flags)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_PREFIX,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_table *table;
+ u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
- table = fib6_get_table(dev_net(dev), RT6_TABLE_PREFIX);
+ table = fib6_get_table(dev_net(dev), tb_id);
if (!table)
return NULL;
static void addrconf_add_mroute(struct net_device *dev)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_LOCAL,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_LOCAL,
.fc_metric = IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_dst_len = 8,
{
struct in6_addr addr;
+ /* no link local addresses on L3 master devices */
+ if (netif_is_l3_master(idev->dev))
+ return;
+
ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0);
if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) {
}
addrconf_addr_gen(idev, true);
+ if (dev->flags & IFF_POINTOPOINT)
+ addrconf_add_mroute(dev);
}
#endif
/* send a neighbour solicitation for our addr */
addrconf_addr_solict_mult(&ifp->addr, &mcaddr);
- ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL);
+ ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, NULL);
out:
in6_ifa_put(ifp);
rtnl_unlock();
}
}
-static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev)
+static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
+ u32 ext_filter_mask)
{
struct nlattr *nla;
struct ifla_cacheinfo ci;
/* XXX - MC not implemented */
+ if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
+ return 0;
+
nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
if (!nla)
goto nla_put_failure;
return inet6_ifla6_size();
}
-static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev)
+static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev,
+ u32 ext_filter_mask)
{
struct inet6_dev *idev = __in6_dev_get(dev);
if (!idev)
return -ENODATA;
- if (inet6_fill_ifla6_attrs(skb, idev) < 0)
+ if (inet6_fill_ifla6_attrs(skb, idev, ext_filter_mask) < 0)
return -EMSGSIZE;
return 0;
if (!protoinfo)
goto nla_put_failure;
- if (inet6_fill_ifla6_attrs(skb, idev) < 0)
+ if (inet6_fill_ifla6_attrs(skb, idev, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, protoinfo);
#include <net/xfrm.h>
#include <net/checksum.h>
#include <linux/mroute6.h>
+#include <net/l3mdev.h>
-static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
- ((mroute6_socket(dev_net(dev), skb) &&
+ ((mroute6_socket(net, skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
*/
if (newskb)
NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING,
- sk, newskb, NULL, newskb->dev,
+ net, sk, newskb, NULL, newskb->dev,
dev_loopback_xmit);
if (ipv6_hdr(skb)->hop_limit == 0) {
- IP6_INC_STATS(dev_net(dev), idev,
+ IP6_INC_STATS(net, idev,
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
}
- IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
- skb->len);
+ IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len);
if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <=
IPV6_ADDR_SCOPE_NODELOCAL &&
}
rcu_read_unlock_bh();
- IP6_INC_STATS(dev_net(dst->dev),
- ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+ IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
kfree_skb(skb);
return -EINVAL;
}
-static int ip6_finish_output(struct sock *sk, struct sk_buff *skb)
+static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
dst_allfrag(skb_dst(skb)) ||
(IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
- return ip6_fragment(sk, skb, ip6_finish_output2);
+ return ip6_fragment(net, sk, skb, ip6_finish_output2);
else
- return ip6_finish_output2(sk, skb);
+ return ip6_finish_output2(net, sk, skb);
}
-int ip6_output(struct sock *sk, struct sk_buff *skb)
+int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb_dst(skb)->dev;
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
+
if (unlikely(idev->cnf.disable_ipv6)) {
- IP6_INC_STATS(dev_net(dev), idev,
- IPSTATS_MIB_OUTDISCARDS);
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return 0;
}
- return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb,
- NULL, dev,
+ return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
+ net, sk, skb, NULL, dev,
ip6_finish_output,
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}
/*
- * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * xmit an sk_buff (used by TCP, SCTP and DCCP)
+ * Note : socket lock is not held for SYNACK packets, but might be modified
+ * by calls to skb_set_owner_w() and ipv6_local_error(),
+ * which are using proper atomic operations or spinlocks.
*/
-
-int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
+int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt, int tclass)
{
struct net *net = sock_net(sk);
- struct ipv6_pinfo *np = inet6_sk(sk);
+ const struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
}
consume_skb(skb);
skb = skb2;
- skb_set_owner_w(skb, sk);
+ /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically,
+ * it is safe to call in our context (socket lock not held)
+ */
+ skb_set_owner_w(skb, (struct sock *)sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
- return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb,
- NULL, dst->dev, dst_output_sk);
+ /* hooks should never assume socket lock is held.
+ * we promote our socket to non const
+ */
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
+ net, (struct sock *)sk, skb, NULL, dst->dev,
+ dst_output);
}
skb->dev = dst->dev;
- ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
+ /* ipv6_local_error() does not require socket lock,
+ * we promote our socket to non const
+ */
+ ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu);
+
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
return 0;
}
-static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb)
+static inline int ip6_forward_finish(struct net *net, struct sock *sk,
+ struct sk_buff *skb)
{
skb_sender_cpu_clear(skb);
- return dst_output_sk(sk, skb);
+ return dst_output(net, sk, skb);
}
static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
if (skb->pkt_type != PACKET_HOST)
goto drop;
+ if (unlikely(skb->sk))
+ goto drop;
+
if (skb_warn_if_lro(skb))
goto drop;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
- return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb,
- skb->dev, dst->dev,
+ return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
+ net, NULL, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
skb_copy_secmark(to, from);
}
-int ip6_fragment(struct sock *sk, struct sk_buff *skb,
- int (*output)(struct sock *, struct sk_buff *))
+int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+ int (*output)(struct net *, struct sock *, struct sk_buff *))
{
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
__be32 frag_id;
int ptr, offset = 0, err = 0;
u8 *prevhdr, nexthdr = 0;
- struct net *net = dev_net(skb_dst(skb)->dev);
hlen = ip6_find_1stfragopt(skb, &prevhdr);
nexthdr = *prevhdr;
ip6_copy_metadata(frag, skb);
}
- err = output(sk, skb);
+ err = output(net, sk, skb);
if (!err)
IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
IPSTATS_MIB_FRAGCREATES);
/*
* Put this fragment into the sending queue.
*/
- err = output(sk, frag);
+ err = output(net, sk, frag);
if (err)
goto fail;
#ifdef CONFIG_IPV6_SUBTREES
ip6_rt_check(&rt->rt6i_src, &fl6->saddr, np->saddr_cache) ||
#endif
- (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex)) {
+ (!(fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) &&
+ (fl6->flowi6_oif && fl6->flowi6_oif != dst->dev->ifindex))) {
dst_release(dst);
dst = NULL;
}
return dst;
}
-static int ip6_dst_lookup_tail(struct net *net, struct sock *sk,
+static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
* It returns a valid dst pointer on success, or a pointer encoded
* error code.
*/
-struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
+struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst)
{
struct dst_entry *dst = NULL;
if (final_dst)
fl6->daddr = *final_dst;
if (!fl6->flowi6_oif)
- fl6->flowi6_oif = dst->dev->ifindex;
+ fl6->flowi6_oif = l3mdev_fib_oif(dst->dev);
return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
int err;
- err = ip6_local_out(skb);
+ err = ip6_local_out(net, skb->sk, skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
#include <net/nexthop.h>
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>
+#include <net/l3mdev.h>
#include <asm/uaccess.h>
static int ip6_dst_gc(struct dst_ops *ops);
static int ip6_pkt_discard(struct sk_buff *skb);
-static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb);
+static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static int ip6_pkt_prohibit(struct sk_buff *skb);
-static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb);
+static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static void ip6_link_failure(struct sk_buff *skb);
static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
struct net_device *loopback_dev = net->loopback_dev;
int cpu;
+ if (dev == loopback_dev)
+ return;
+
for_each_possible_cpu(cpu) {
struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
struct rt6_info *rt;
struct inet6_dev *rt_idev = rt->rt6i_idev;
struct net_device *rt_dev = rt->dst.dev;
- if (rt_idev && (rt_idev->dev == dev || !dev) &&
- rt_idev->dev != loopback_dev) {
+ if (rt_idev->dev == dev) {
rt->rt6i_idev = in6_dev_get(loopback_dev);
in6_dev_put(rt_idev);
}
- if (rt_dev && (rt_dev == dev || !dev) &&
- rt_dev != loopback_dev) {
+ if (rt_dev == dev) {
rt->dst.dev = loopback_dev;
dev_hold(rt->dst.dev);
dev_put(rt_dev);
{
}
- static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst,
- unsigned long old)
- {
- return NULL;
- }
-
static struct dst_ops ip6_dst_blackhole_ops = {
.family = AF_INET6,
.destroy = ip6_dst_destroy,
.default_advmss = ip6_default_advmss,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
.redirect = ip6_rt_blackhole_redirect,
- .cow_metrics = ip6_rt_blackhole_cow_metrics,
+ .cow_metrics = dst_cow_metrics_generic,
.neigh_lookup = ip6_neigh_lookup,
};
.obsolete = DST_OBSOLETE_FORCE_CHK,
.error = -EINVAL,
.input = dst_discard,
- .output = dst_discard_sk,
+ .output = dst_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
.rt6i_protocol = RTPROT_KERNEL,
#endif
+ static void rt6_info_init(struct rt6_info *rt)
+ {
+ struct dst_entry *dst = &rt->dst;
+
+ memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
+ INIT_LIST_HEAD(&rt->rt6i_siblings);
+ INIT_LIST_HEAD(&rt->rt6i_uncached);
+ }
+
/* allocate dst with ip6_dst_ops */
static struct rt6_info *__ip6_dst_alloc(struct net *net,
struct net_device *dev,
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
- if (rt) {
- struct dst_entry *dst = &rt->dst;
+ if (rt)
+ rt6_info_init(rt);
- memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
- INIT_LIST_HEAD(&rt->rt6i_siblings);
- INIT_LIST_HEAD(&rt->rt6i_uncached);
- }
return rt;
}
static int rt6_info_hash_nhsfn(unsigned int candidate_count,
const struct flowi6 *fl6)
{
- unsigned int val = fl6->flowi6_proto;
-
- val ^= ipv6_addr_hash(&fl6->daddr);
- val ^= ipv6_addr_hash(&fl6->saddr);
-
- /* Work only if this not encapsulated */
- switch (fl6->flowi6_proto) {
- case IPPROTO_UDP:
- case IPPROTO_TCP:
- case IPPROTO_SCTP:
- val ^= (__force u16)fl6->fl6_sport;
- val ^= (__force u16)fl6->fl6_dport;
- break;
-
- case IPPROTO_ICMPV6:
- val ^= (__force u16)fl6->fl6_icmp_type;
- val ^= (__force u16)fl6->fl6_icmp_code;
- break;
- }
- /* RFC6438 recommands to use flowlabel */
- val ^= (__force u32)fl6->flowlabel;
-
- /* Perhaps, we need to tune, this function? */
- val = val ^ (val >> 7) ^ (val >> 12);
- return val % candidate_count;
+ return get_hash_from_flowi6(fl6) % candidate_count;
}
static struct rt6_info *rt6_multipath_select(struct rt6_info *match,
if (dev->flags & IFF_LOOPBACK) {
if (!sprt->rt6i_idev ||
sprt->rt6i_idev->dev->ifindex != oif) {
- if (flags & RT6_LOOKUP_F_IFACE && oif)
+ if (flags & RT6_LOOKUP_F_IFACE)
continue;
- if (local && (!oif ||
- local->rt6i_idev->dev->ifindex == oif))
+ if (local &&
+ local->rt6i_idev->dev->ifindex == oif)
continue;
}
local = sprt;
container_of(w, struct __rt6_probe_work, work);
addrconf_addr_solict_mult(&work->target, &mcaddr);
- ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL);
+ ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL);
dev_put(work->dev);
kfree(work);
}
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
+ if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
+ oif = 0;
+
redo_rt6_select:
rt = rt6_select(fn, oif, strict);
if (rt->rt6i_nsiblings)
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct ip_tunnel_info *tun_info;
struct flowi6 fl6 = {
- .flowi6_iif = skb->dev->ifindex,
+ .flowi6_iif = l3mdev_fib_oif(skb->dev),
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
struct flowi6 *fl6)
{
+ struct dst_entry *dst;
int flags = 0;
+ dst = l3mdev_rt6_dst_by_oif(net, fl6);
+ if (dst)
+ return dst;
+
fl6->flowi6_iif = LOOPBACK_IFINDEX;
if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0);
if (rt) {
- new = &rt->dst;
-
- memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
+ rt6_info_init(rt);
+ new = &rt->dst;
new->__use = 1;
new->input = dst_discard;
- new->output = dst_discard_sk;
+ new->output = dst_discard_out;
- if (dst_metrics_read_only(&ort->dst))
- new->_metrics = ort->dst._metrics;
- else
- dst_copy_metrics(new, &ort->dst);
+ dst_copy_metrics(new, &ort->dst);
rt->rt6i_idev = ort->rt6i_idev;
if (rt->rt6i_idev)
in6_dev_hold(rt->rt6i_idev);
rt->rt6i_gateway = ort->rt6i_gateway;
- rt->rt6i_flags = ort->rt6i_flags;
+ rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU;
rt->rt6i_metric = 0;
memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
return -EINVAL;
}
-int ip6_route_info_create(struct fib6_config *cfg, struct rt6_info **rt_ret)
+static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg)
{
- int err;
struct net *net = cfg->fc_nlinfo.nl_net;
struct rt6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
struct fib6_table *table;
int addr_type;
+ int err = -EINVAL;
if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
- return -EINVAL;
+ goto out;
#ifndef CONFIG_IPV6_SUBTREES
if (cfg->fc_src_len)
- return -EINVAL;
+ goto out;
#endif
if (cfg->fc_ifindex) {
err = -ENODEV;
switch (cfg->fc_type) {
case RTN_BLACKHOLE:
rt->dst.error = -EINVAL;
- rt->dst.output = dst_discard_sk;
+ rt->dst.output = dst_discard_out;
rt->dst.input = dst_discard;
break;
case RTN_PROHIBIT:
cfg->fc_nlinfo.nl_net = dev_net(dev);
- *rt_ret = rt;
-
- return 0;
+ return rt;
out:
if (dev)
dev_put(dev);
if (rt)
dst_free(&rt->dst);
- *rt_ret = NULL;
-
- return err;
+ return ERR_PTR(err);
}
int ip6_route_add(struct fib6_config *cfg)
{
struct mx6_config mxc = { .mx = NULL, };
- struct rt6_info *rt = NULL;
+ struct rt6_info *rt;
int err;
- err = ip6_route_info_create(cfg, &rt);
- if (err)
+ rt = ip6_route_info_create(cfg);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ rt = NULL;
goto out;
+ }
err = ip6_convert_metrics(&mxc, cfg);
if (err)
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_INFO,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = ifindex,
.fc_dst_len = prefixlen,
.fc_nlinfo.nl_net = net,
};
+ cfg.fc_table = l3mdev_fib_table_by_index(net, ifindex) ? : RT6_TABLE_INFO;
cfg.fc_dst = *prefix;
cfg.fc_gateway = *gwaddr;
unsigned int pref)
{
struct fib6_config cfg = {
- .fc_table = RT6_TABLE_DFLT,
+ .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT,
.fc_metric = IP6_RT_PRIO_USER,
.fc_ifindex = dev->ifindex,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
{
memset(cfg, 0, sizeof(*cfg));
- cfg->fc_table = RT6_TABLE_MAIN;
+ cfg->fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ?
+ : RT6_TABLE_MAIN;
cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
cfg->fc_metric = rtmsg->rtmsg_metric;
cfg->fc_expires = rtmsg->rtmsg_info;
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
}
-static int ip6_pkt_discard_out(struct sock *sk, struct sk_buff *skb)
+static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
}
-static int ip6_pkt_prohibit_out(struct sock *sk, struct sk_buff *skb)
+static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
skb->dev = skb_dst(skb)->dev;
return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
const struct in6_addr *addr,
bool anycast)
{
+ u32 tb_id;
struct net *net = dev_net(idev->dev);
struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
DST_NOCOUNT);
rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
- rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
+ tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
+ rt->rt6i_table = fib6_get_table(net, tb_id);
rt->dst.flags |= DST_NOCACHE;
atomic_set(&rt->dst.__refcnt, 1);
fib6_clean_all(net, fib6_ifdown, &adn);
icmp6_clean_all(fib6_ifdown, &adn);
- rt6_uncached_list_flush_dev(net, dev);
+ if (dev)
+ rt6_uncached_list_flush_dev(net, dev);
}
struct rt6_mtu_change_arg {
r_cfg.fc_encap_type = nla_get_u16(nla);
}
- err = ip6_route_info_create(&r_cfg, &rt);
- if (err)
+ rt = ip6_route_info_create(&r_cfg);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ rt = NULL;
goto cleanup;
+ }
err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
if (err) {
} else {
fl6.flowi6_oif = oif;
+ if (netif_index_is_l3_master(net, oif)) {
+ fl6.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC |
+ FLOWI_FLAG_SKIP_NH_OIF;
+ }
+
rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
}
FLAG(SUPPORTS_CLONED_SKBS),
FLAG(SINGLE_SCAN_ON_ALL_BANDS),
FLAG(TDLS_WIDER_BW),
+ FLAG(SUPPORTS_AMSDU_IN_AMPDU),
+ FLAG(BEACON_TX_STATUS),
/* keep last for the build bug below */
(void *)0x1
for (i = 0; i < NUM_IEEE80211_HW_FLAGS; i++) {
if (test_bit(i, local->hw.flags))
- pos += scnprintf(pos, end - pos, "%s",
+ pos += scnprintf(pos, end - pos, "%s\n",
hw_flag_names[i]);
}
* when it wakes up for the next time.
*/
set_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT);
+ ieee80211_clear_fast_xmit(sta);
/*
* This code races in the following way:
}
EXPORT_SYMBOL(ieee80211_tx_status_noskb);
-void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
+ struct ieee80211_supported_band *sband,
+ int retry_count, int shift, bool send_to_cooked)
{
struct sk_buff *skb2;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ struct ieee80211_sub_if_data *sdata;
+ struct net_device *prev_dev = NULL;
+ int rtap_len;
+
+ /* send frame to monitor interfaces now */
+ rtap_len = ieee80211_tx_radiotap_len(info);
+ if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) {
+ pr_err("ieee80211_tx_status: headroom too small\n");
+ dev_kfree_skb(skb);
+ return;
+ }
+ ieee80211_add_tx_radiotap_header(local, sband, skb, retry_count,
+ rtap_len, shift);
+
+ /* XXX: is this sufficient for BPF? */
+ skb_set_mac_header(skb, 0);
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ skb->pkt_type = PACKET_OTHERHOST;
+ skb->protocol = htons(ETH_P_802_2);
+ memset(skb->cb, 0, sizeof(skb->cb));
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+ if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
+ if (!ieee80211_sdata_running(sdata))
+ continue;
+
+ if ((sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) &&
+ !send_to_cooked)
+ continue;
+
+ if (prev_dev) {
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (skb2) {
+ skb2->dev = prev_dev;
+ netif_rx(skb2);
+ }
+ }
+
+ prev_dev = sdata->dev;
+ }
+ }
+ if (prev_dev) {
+ skb->dev = prev_dev;
+ netif_rx(skb);
+ skb = NULL;
+ }
+ rcu_read_unlock();
+ dev_kfree_skb(skb);
+}
+
+void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
+{
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
struct ieee80211_local *local = hw_to_local(hw);
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
__le16 fc;
struct ieee80211_supported_band *sband;
- struct ieee80211_sub_if_data *sdata;
- struct net_device *prev_dev = NULL;
struct sta_info *sta;
struct rhash_head *tmp;
int retry_count;
bool send_to_cooked;
bool acked;
struct ieee80211_bar *bar;
- int rtap_len;
int shift = 0;
int tid = IEEE80211_NUM_TIDS;
const struct bucket_table *tbl;
return;
}
- /* send frame to monitor interfaces now */
- rtap_len = ieee80211_tx_radiotap_len(info);
- if (WARN_ON_ONCE(skb_headroom(skb) < rtap_len)) {
- pr_err("ieee80211_tx_status: headroom too small\n");
- dev_kfree_skb(skb);
- return;
- }
- ieee80211_add_tx_radiotap_header(local, sband, skb, retry_count,
- rtap_len, shift);
-
- /* XXX: is this sufficient for BPF? */
- skb_set_mac_header(skb, 0);
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- skb->pkt_type = PACKET_OTHERHOST;
- skb->protocol = htons(ETH_P_802_2);
- memset(skb->cb, 0, sizeof(skb->cb));
-
- rcu_read_lock();
- list_for_each_entry_rcu(sdata, &local->interfaces, list) {
- if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
- if (!ieee80211_sdata_running(sdata))
- continue;
-
- if ((sdata->u.mntr_flags & MONITOR_FLAG_COOK_FRAMES) &&
- !send_to_cooked)
- continue;
-
- if (prev_dev) {
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (skb2) {
- skb2->dev = prev_dev;
- netif_rx(skb2);
- }
- }
-
- prev_dev = sdata->dev;
- }
- }
- if (prev_dev) {
- skb->dev = prev_dev;
- netif_rx(skb);
- skb = NULL;
- }
- rcu_read_unlock();
- dev_kfree_skb(skb);
+ /* send to monitor interfaces */
+ ieee80211_tx_monitor(local, skb, sband, retry_count, shift, send_to_cooked);
}
EXPORT_SYMBOL(ieee80211_tx_status);
if (!tx->sta)
info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT;
- else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT))
+ else if (test_and_clear_sta_flag(tx->sta, WLAN_STA_CLEAR_PS_FILT)) {
info->flags |= IEEE80211_TX_CTL_CLEAR_PS_FILT;
+ ieee80211_check_fast_xmit(tx->sta);
+ }
info->flags |= IEEE80211_TX_CTL_FIRST_FRAGMENT;
if (test_sta_flag(sta, WLAN_STA_PS_STA) ||
test_sta_flag(sta, WLAN_STA_PS_DRIVER) ||
- test_sta_flag(sta, WLAN_STA_PS_DELIVER))
+ test_sta_flag(sta, WLAN_STA_PS_DELIVER) ||
+ test_sta_flag(sta, WLAN_STA_CLEAR_PS_FILT))
goto out;
if (sdata->noack_map)
if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
*ieee80211_get_qos_ctl(hdr) = tid;
- hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
+ if (!sta->sta.txq[0])
+ hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
} else {
info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
hdr->seq_ctrl = cpu_to_le16(sdata->sequence_number);
{
struct ieee80211_mutable_offsets offs = {};
struct sk_buff *bcn = __ieee80211_beacon_get(hw, vif, &offs, false);
+ struct sk_buff *copy;
+ struct ieee80211_supported_band *sband;
+ int shift;
+
+ if (!bcn)
+ return bcn;
if (tim_offset)
*tim_offset = offs.tim_offset;
if (tim_length)
*tim_length = offs.tim_length;
+ if (ieee80211_hw_check(hw, BEACON_TX_STATUS) ||
+ !hw_to_local(hw)->monitors)
+ return bcn;
+
+ /* send a copy to monitor interfaces */
+ copy = skb_copy(bcn, GFP_ATOMIC);
+ if (!copy)
+ return bcn;
+
+ shift = ieee80211_vif_get_shift(vif);
+ sband = hw->wiphy->bands[ieee80211_get_sdata_band(vif_to_sdata(vif))];
+ ieee80211_tx_monitor(hw_to_local(hw), copy, sband, 1, shift, false);
+
return bcn;
}
EXPORT_SYMBOL(ieee80211_beacon_get_tim);
return 0;
}
-static int ovs_vport_output(struct sock *sock, struct sk_buff *skb)
+static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
struct vport *vport = data->vport;
skb_pull(skb, hlen);
}
-static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
- __be16 ethertype)
+static void ovs_fragment(struct net *net, struct vport *vport,
+ struct sk_buff *skb, u16 mru, __be16 ethertype)
{
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
- return;
+ goto err;
}
if (ethertype == htons(ETH_P_IP)) {
skb_dst_set_noref(skb, &ovs_dst);
IPCB(skb)->frag_max_size = mru;
- ip_do_fragment(skb->sk, skb, ovs_vport_output);
+ ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
} else if (ethertype == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
struct rt6_info ovs_rt;
if (!v6ops) {
- kfree_skb(skb);
- return;
+ goto err;
}
prepare_frag(vport, skb);
skb_dst_set_noref(skb, &ovs_rt.dst);
IP6CB(skb)->frag_max_size = mru;
- v6ops->fragment(skb->sk, skb, ovs_vport_output);
+ v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
ovs_vport_name(vport), ntohs(ethertype), mru,
vport->dev->mtu);
- kfree_skb(skb);
+ goto err;
}
+
+ return;
+ err:
+ kfree_skb(skb);
}
static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
ovs_vport_send(vport, skb);
} else if (mru <= vport->dev->mtu) {
+ struct net *net = read_pnet(&dp->net);
__be16 ethertype = key->eth.type;
if (!is_flow_key_valid(key)) {
ethertype = vlan_get_protocol(skb);
}
- ovs_fragment(vport, skb, mru, ethertype);
+ ovs_fragment(net, vport, skb, mru, ethertype);
} else {
kfree_skb(skb);
}
case OVS_KEY_ATTR_CT_STATE:
case OVS_KEY_ATTR_CT_ZONE:
case OVS_KEY_ATTR_CT_MARK:
- case OVS_KEY_ATTR_CT_LABEL:
+ case OVS_KEY_ATTR_CT_LABELS:
err = -EINVAL;
break;
}
break;
case OVS_ACTION_ATTR_CT:
+ if (!is_flow_key_valid(key)) {
+ err = ovs_flow_key_update(skb, key);
+ if (err)
+ return err;
+ }
+
err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key,
nla_data(a));
};
/* Metadata label for masked write to conntrack label. */
- struct md_label {
- struct ovs_key_ct_label value;
- struct ovs_key_ct_label mask;
+ struct md_labels {
+ struct ovs_key_ct_labels value;
+ struct ovs_key_ct_labels mask;
};
/* Conntrack action context for execution. */
struct nf_conntrack_helper *helper;
struct nf_conntrack_zone zone;
struct nf_conn *ct;
- u32 flags;
+ u8 commit : 1;
u16 family;
struct md_mark mark;
- struct md_label label;
+ struct md_labels labels;
};
static u16 key_to_nfproto(const struct sw_flow_key *key)
#endif
}
- static void ovs_ct_get_label(const struct nf_conn *ct,
- struct ovs_key_ct_label *label)
+ static void ovs_ct_get_labels(const struct nf_conn *ct,
+ struct ovs_key_ct_labels *labels)
{
struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL;
if (cl) {
size_t len = cl->words * sizeof(long);
- if (len > OVS_CT_LABEL_LEN)
- len = OVS_CT_LABEL_LEN;
- else if (len < OVS_CT_LABEL_LEN)
- memset(label, 0, OVS_CT_LABEL_LEN);
- memcpy(label, cl->bits, len);
+ if (len > OVS_CT_LABELS_LEN)
+ len = OVS_CT_LABELS_LEN;
+ else if (len < OVS_CT_LABELS_LEN)
+ memset(labels, 0, OVS_CT_LABELS_LEN);
+ memcpy(labels, cl->bits, len);
} else {
- memset(label, 0, OVS_CT_LABEL_LEN);
+ memset(labels, 0, OVS_CT_LABELS_LEN);
}
}
key->ct.state = state;
key->ct.zone = zone->id;
key->ct.mark = ovs_ct_get_mark(ct);
- ovs_ct_get_label(ct, &key->ct.label);
+ ovs_ct_get_labels(ct, &key->ct.labels);
}
/* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has
int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb)
{
- if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state))
+ if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
- nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label),
- &key->ct.label))
+ nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels),
+ &key->ct.labels))
return -EMSGSIZE;
return 0;
#endif
}
- static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key,
- const struct ovs_key_ct_label *label,
- const struct ovs_key_ct_label *mask)
+ static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_key_ct_labels *labels,
+ const struct ovs_key_ct_labels *mask)
{
enum ip_conntrack_info ctinfo;
struct nf_conn_labels *cl;
nf_ct_labels_ext_add(ct);
cl = nf_ct_labels_find(ct);
}
- if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN)
+ if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN)
return -ENOSPC;
- err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask,
- OVS_CT_LABEL_LEN / sizeof(u32));
+ err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask,
+ OVS_CT_LABELS_LEN / sizeof(u32));
if (err)
return err;
- ovs_ct_get_label(ct, &key->ct.label);
+ ovs_ct_get_labels(ct, &key->ct.labels);
return 0;
}
int err;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
- err = ip_defrag(skb, user);
+ err = ip_defrag(net, skb, user);
if (err)
return err;
struct sk_buff *reasm;
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
- reasm = nf_ct_frag6_gather(skb, user);
+ reasm = nf_ct_frag6_gather(net, skb, user);
if (!reasm)
return -EINPROGRESS;
{
struct nf_conntrack_tuple tuple;
- if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple))
+ if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple))
return NULL;
return __nf_ct_expect_find(net, zone, &tuple);
}
return 0;
}
- static bool label_nonzero(const struct ovs_key_ct_label *label)
+ static bool labels_nonzero(const struct ovs_key_ct_labels *labels)
{
size_t i;
- for (i = 0; i < sizeof(*label); i++)
- if (label->ct_label[i])
+ for (i = 0; i < sizeof(*labels); i++)
+ if (labels->ct_labels[i])
return true;
return false;
return err;
}
- if (info->flags & OVS_CT_F_COMMIT)
+ if (info->commit)
err = ovs_ct_commit(net, key, info, skb);
else
err = ovs_ct_lookup(net, key, info, skb);
if (err)
goto err;
}
- if (label_nonzero(&info->label.mask))
- err = ovs_ct_set_label(skb, key, &info->label.value,
- &info->label.mask);
+ if (labels_nonzero(&info->labels.mask))
+ err = ovs_ct_set_labels(skb, key, &info->labels.value,
+ &info->labels.mask);
err:
skb_push(skb, nh_ofs);
return err;
}
static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = {
- [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32),
- .maxlen = sizeof(u32) },
+ [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 },
[OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16),
.maxlen = sizeof(u16) },
[OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark),
.maxlen = sizeof(struct md_mark) },
- [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label),
- .maxlen = sizeof(struct md_label) },
+ [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels),
+ .maxlen = sizeof(struct md_labels) },
[OVS_CT_ATTR_HELPER] = { .minlen = 1,
.maxlen = NF_CT_HELPER_NAME_LEN }
};
}
switch (type) {
- case OVS_CT_ATTR_FLAGS:
- info->flags = nla_get_u32(a);
+ case OVS_CT_ATTR_COMMIT:
+ info->commit = true;
break;
#ifdef CONFIG_NF_CONNTRACK_ZONES
case OVS_CT_ATTR_ZONE:
}
#endif
#ifdef CONFIG_NF_CONNTRACK_LABELS
- case OVS_CT_ATTR_LABEL: {
- struct md_label *label = nla_data(a);
+ case OVS_CT_ATTR_LABELS: {
+ struct md_labels *labels = nla_data(a);
- info->label = *label;
+ info->labels = *labels;
break;
}
#endif
attr == OVS_KEY_ATTR_CT_MARK)
return true;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
- attr == OVS_KEY_ATTR_CT_LABEL) {
+ attr == OVS_KEY_ATTR_CT_LABELS) {
struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
return ovs_net->xt_label;
if (!start)
return -EMSGSIZE;
- if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags))
+ if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id))
&ct_info->mark))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
- nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label),
- &ct_info->label))
+ nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels),
+ &ct_info->labels))
return -EMSGSIZE;
if (ct_info->helper) {
if (nla_put_string(skb, OVS_CT_ATTR_HELPER,
void ovs_ct_init(struct net *net)
{
- unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE;
+ unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
if (nf_connlabels_get(net, n_bits)) {
u32 skb_mark; /* SKB mark. */
u16 in_port; /* Input switch port (or DP_MAX_PORTS). */
} __packed phy; /* Safe when right after 'tun_key'. */
+ u8 tun_proto; /* Protocol of encapsulating tunnel. */
u32 ovs_flow_hash; /* Datapath computed hash value. */
u32 recirc_id; /* Recirculation ID. */
struct {
u16 zone;
u32 mark;
u8 state;
- struct ovs_key_ct_label label;
+ struct ovs_key_ct_labels labels;
} ct;
} __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */
* updating this function.
*/
return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */
+ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */
+ nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */
- + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */
+ + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */
+ nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */
+ nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */
- + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */
+ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE },
[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED,
.next = ovs_vxlan_ext_key_lens },
+ [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
+ [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) },
};
/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */
[OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED,
.next = ovs_tunnel_key_lens, },
[OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) },
- [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) },
+ [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) },
[OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) },
[OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) },
- [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) },
+ [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) },
};
static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
return 0;
}
-static int ipv4_tun_from_nlattr(const struct nlattr *attr,
- struct sw_flow_match *match, bool is_mask,
- bool log)
+static int ip_tun_from_nlattr(const struct nlattr *attr,
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
{
struct nlattr *a;
int rem;
bool ttl = false;
- __be16 tun_flags = 0;
+ __be16 tun_flags = 0, ipv4 = false, ipv6 = false;
int opts_type = 0;
nla_for_each_nested(a, attr, rem) {
case OVS_TUNNEL_KEY_ATTR_IPV4_SRC:
SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src,
nla_get_in_addr(a), is_mask);
+ ipv4 = true;
break;
case OVS_TUNNEL_KEY_ATTR_IPV4_DST:
SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst,
nla_get_in_addr(a), is_mask);
+ ipv4 = true;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ nla_get_in6_addr(a), is_mask);
+ ipv6 = true;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_IPV6_DST:
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ nla_get_in6_addr(a), is_mask);
+ ipv6 = true;
break;
case OVS_TUNNEL_KEY_ATTR_TOS:
SW_FLOW_KEY_PUT(match, tun_key.tos,
opts_type = type;
break;
default:
- OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
+ OVS_NLERR(log, "Unknown IP tunnel attribute %d",
type);
return -EINVAL;
}
}
SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
+ if (is_mask)
+ SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true);
+ else
+ SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET,
+ false);
if (rem > 0) {
- OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+ OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.",
rem);
return -EINVAL;
}
+ if (ipv4 && ipv6) {
+ OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes");
+ return -EINVAL;
+ }
+
if (!is_mask) {
- if (!match->key->tun_key.u.ipv4.dst) {
+ if (!ipv4 && !ipv6) {
+ OVS_NLERR(log, "IP tunnel dst address not specified");
+ return -EINVAL;
+ }
+ if (ipv4 && !match->key->tun_key.u.ipv4.dst) {
OVS_NLERR(log, "IPv4 tunnel dst address is zero");
return -EINVAL;
}
+ if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
+ OVS_NLERR(log, "IPv6 tunnel dst address is zero");
+ return -EINVAL;
+ }
if (!ttl) {
- OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
+ OVS_NLERR(log, "IP tunnel TTL not specified.");
return -EINVAL;
}
}
return 0;
}
-static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ip_tunnel_key *output,
- const void *tun_opts, int swkey_tun_opts_len)
+static int __ip_tun_to_nlattr(struct sk_buff *skb,
+ const struct ip_tunnel_key *output,
+ const void *tun_opts, int swkey_tun_opts_len,
+ unsigned short tun_proto)
{
if (output->tun_flags & TUNNEL_KEY &&
nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
return -EMSGSIZE;
- if (output->u.ipv4.src &&
- nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
- output->u.ipv4.src))
- return -EMSGSIZE;
- if (output->u.ipv4.dst &&
- nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
- output->u.ipv4.dst))
- return -EMSGSIZE;
+ switch (tun_proto) {
+ case AF_INET:
+ if (output->u.ipv4.src &&
+ nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
+ output->u.ipv4.src))
+ return -EMSGSIZE;
+ if (output->u.ipv4.dst &&
+ nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
+ output->u.ipv4.dst))
+ return -EMSGSIZE;
+ break;
+ case AF_INET6:
+ if (!ipv6_addr_any(&output->u.ipv6.src) &&
+ nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC,
+ &output->u.ipv6.src))
+ return -EMSGSIZE;
+ if (!ipv6_addr_any(&output->u.ipv6.dst) &&
+ nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST,
+ &output->u.ipv6.dst))
+ return -EMSGSIZE;
+ break;
+ }
if (output->tos &&
nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos))
return -EMSGSIZE;
return 0;
}
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ip_tunnel_key *output,
- const void *tun_opts, int swkey_tun_opts_len)
+static int ip_tun_to_nlattr(struct sk_buff *skb,
+ const struct ip_tunnel_key *output,
+ const void *tun_opts, int swkey_tun_opts_len,
+ unsigned short tun_proto)
{
struct nlattr *nla;
int err;
if (!nla)
return -EMSGSIZE;
- err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+ err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
+ tun_proto);
if (err)
return err;
const struct ip_tunnel_info *egress_tun_info,
const void *egress_tun_opts)
{
- return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key,
- egress_tun_opts,
- egress_tun_info->options_len);
+ return __ip_tun_to_nlattr(skb, &egress_tun_info->key,
+ egress_tun_opts,
+ egress_tun_info->options_len,
+ ip_tunnel_info_af(egress_tun_info));
}
static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
*attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK);
}
if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
- if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
- is_mask, log) < 0)
+ if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
+ is_mask, log) < 0)
return -EINVAL;
*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
}
if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) &&
ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) {
- u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]);
+ u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]);
+
+ if (!is_mask && !ovs_ct_state_supported(ct_state)) {
+ OVS_NLERR(log, "ct_state flags %08x unsupported",
+ ct_state);
+ return -EINVAL;
+ }
SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE);
SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK);
}
- if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) &&
- ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) {
- const struct ovs_key_ct_label *cl;
+ if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) &&
+ ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) {
+ const struct ovs_key_ct_labels *cl;
- cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]);
- SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label,
+ cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]);
+ SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels,
sizeof(*cl), is_mask);
- *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
}
return 0;
}
/* The userspace does not send tunnel attributes that
* are 0, but we should not wildcard them nonetheless.
*/
- if (match->key->tun_key.u.ipv4.dst)
+ if (match->key->tun_proto)
SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
0xff, true);
if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
- if ((swkey->tun_key.u.ipv4.dst || is_mask)) {
+ if ((swkey->tun_proto || is_mask)) {
const void *opts = NULL;
if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
- if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
- swkey->tun_opts_len))
+ if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
+ swkey->tun_opts_len, swkey->tun_proto))
goto nla_put_failure;
}
int err = 0, start, opts_type;
ovs_match_init(&match, &key, NULL);
- opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+ opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
if (opts_type < 0)
return opts_type;
tun_info = &tun_dst->u.tun_info;
tun_info->mode = IP_TUNNEL_INFO_TX;
+ if (key.tun_proto == AF_INET6)
+ tun_info->mode |= IP_TUNNEL_INFO_IPV6;
tun_info->key = key.tun_key;
/* We need to store the options in the action itself since
case OVS_KEY_ATTR_PRIORITY:
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_CT_MARK:
- case OVS_KEY_ATTR_CT_LABEL:
+ case OVS_KEY_ATTR_CT_LABELS:
case OVS_KEY_ATTR_ETHERNET:
break;
if (!start)
return -EMSGSIZE;
- err = ipv4_tun_to_nlattr(skb, &tun_info->key,
- tun_info->options_len ?
+ err = ip_tun_to_nlattr(skb, &tun_info->key,
+ tun_info->options_len ?
ip_tunnel_info_opts(tun_info) : NULL,
- tun_info->options_len);
+ tun_info->options_len,
+ ip_tunnel_info_af(tun_info));
if (err)
return err;
nla_nest_end(skb, start);
/* Initialize the default stat node. */
stats = kmem_cache_alloc_node(flow_stats_cache,
- GFP_KERNEL | __GFP_ZERO, 0);
+ GFP_KERNEL | __GFP_ZERO,
+ node_online(0) ? 0 : NUMA_NO_NODE);
if (!stats)
goto err;
static int flow_key_start(const struct sw_flow_key *key)
{
- if (key->tun_key.u.ipv4.dst)
+ if (key->tun_proto)
return 0;
else
return rounddown(offsetof(struct sw_flow_key, phy),
/*
* net/switchdev/switchdev.c - Switch device API
- * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us>
* Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com>
*
* This program is free software; you can redistribute it and/or modify
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
+#include <linux/list.h>
+#include <linux/workqueue.h>
+ #include <linux/if_vlan.h>
#include <net/ip_fib.h>
#include <net/switchdev.h>
+/**
+ * switchdev_trans_item_enqueue - Enqueue data item to transaction queue
+ *
+ * @trans: transaction
+ * @data: pointer to data being queued
+ * @destructor: data destructor
+ * @tritem: transaction item being queued
+ *
+ * Enqeueue data item to transaction queue. tritem is typically placed in
+ * cointainter pointed at by data pointer. Destructor is called on
+ * transaction abort and after successful commit phase in case
+ * the caller did not dequeue the item before.
+ */
+void switchdev_trans_item_enqueue(struct switchdev_trans *trans,
+ void *data, void (*destructor)(void const *),
+ struct switchdev_trans_item *tritem)
+{
+ tritem->data = data;
+ tritem->destructor = destructor;
+ list_add_tail(&tritem->list, &trans->item_list);
+}
+EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue);
+
+static struct switchdev_trans_item *
+__switchdev_trans_item_dequeue(struct switchdev_trans *trans)
+{
+ struct switchdev_trans_item *tritem;
+
+ if (list_empty(&trans->item_list))
+ return NULL;
+ tritem = list_first_entry(&trans->item_list,
+ struct switchdev_trans_item, list);
+ list_del(&tritem->list);
+ return tritem;
+}
+
+/**
+ * switchdev_trans_item_dequeue - Dequeue data item from transaction queue
+ *
+ * @trans: transaction
+ */
+void *switchdev_trans_item_dequeue(struct switchdev_trans *trans)
+{
+ struct switchdev_trans_item *tritem;
+
+ tritem = __switchdev_trans_item_dequeue(trans);
+ BUG_ON(!tritem);
+ return tritem->data;
+}
+EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue);
+
+static void switchdev_trans_init(struct switchdev_trans *trans)
+{
+ INIT_LIST_HEAD(&trans->item_list);
+}
+
+static void switchdev_trans_items_destroy(struct switchdev_trans *trans)
+{
+ struct switchdev_trans_item *tritem;
+
+ while ((tritem = __switchdev_trans_item_dequeue(trans)))
+ tritem->destructor(tritem->data);
+}
+
+static void switchdev_trans_items_warn_destroy(struct net_device *dev,
+ struct switchdev_trans *trans)
+{
+ WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n",
+ dev->name);
+ switchdev_trans_items_destroy(trans);
+}
+
+static LIST_HEAD(deferred);
+static DEFINE_SPINLOCK(deferred_lock);
+
+typedef void switchdev_deferred_func_t(struct net_device *dev,
+ const void *data);
+
+struct switchdev_deferred_item {
+ struct list_head list;
+ struct net_device *dev;
+ switchdev_deferred_func_t *func;
+ unsigned long data[0];
+};
+
+static struct switchdev_deferred_item *switchdev_deferred_dequeue(void)
+{
+ struct switchdev_deferred_item *dfitem;
+
+ spin_lock_bh(&deferred_lock);
+ if (list_empty(&deferred)) {
+ dfitem = NULL;
+ goto unlock;
+ }
+ dfitem = list_first_entry(&deferred,
+ struct switchdev_deferred_item, list);
+ list_del(&dfitem->list);
+unlock:
+ spin_unlock_bh(&deferred_lock);
+ return dfitem;
+}
+
+/**
+ * switchdev_deferred_process - Process ops in deferred queue
+ *
+ * Called to flush the ops currently queued in deferred ops queue.
+ * rtnl_lock must be held.
+ */
+void switchdev_deferred_process(void)
+{
+ struct switchdev_deferred_item *dfitem;
+
+ ASSERT_RTNL();
+
+ while ((dfitem = switchdev_deferred_dequeue())) {
+ dfitem->func(dfitem->dev, dfitem->data);
+ dev_put(dfitem->dev);
+ kfree(dfitem);
+ }
+}
+EXPORT_SYMBOL_GPL(switchdev_deferred_process);
+
+static void switchdev_deferred_process_work(struct work_struct *work)
+{
+ rtnl_lock();
+ switchdev_deferred_process();
+ rtnl_unlock();
+}
+
+static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work);
+
+static int switchdev_deferred_enqueue(struct net_device *dev,
+ const void *data, size_t data_len,
+ switchdev_deferred_func_t *func)
+{
+ struct switchdev_deferred_item *dfitem;
+
+ dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC);
+ if (!dfitem)
+ return -ENOMEM;
+ dfitem->dev = dev;
+ dfitem->func = func;
+ memcpy(dfitem->data, data, data_len);
+ dev_hold(dev);
+ spin_lock_bh(&deferred_lock);
+ list_add_tail(&dfitem->list, &deferred);
+ spin_unlock_bh(&deferred_lock);
+ schedule_work(&deferred_process_work);
+ return 0;
+}
+
/**
* switchdev_port_attr_get - Get port attribute
*
struct net_device *lower_dev;
struct list_head *iter;
struct switchdev_attr first = {
- .id = SWITCHDEV_ATTR_UNDEFINED
+ .id = SWITCHDEV_ATTR_ID_UNDEFINED
};
int err = -EOPNOTSUPP;
err = switchdev_port_attr_get(lower_dev, attr);
if (err)
break;
- if (first.id == SWITCHDEV_ATTR_UNDEFINED)
+ if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED)
first = *attr;
else if (memcmp(&first, attr, sizeof(*attr)))
return -ENODATA;
EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
static int __switchdev_port_attr_set(struct net_device *dev,
- struct switchdev_attr *attr)
+ const struct switchdev_attr *attr,
+ struct switchdev_trans *trans)
{
const struct switchdev_ops *ops = dev->switchdev_ops;
struct net_device *lower_dev;
int err = -EOPNOTSUPP;
if (ops && ops->switchdev_port_attr_set)
- return ops->switchdev_port_attr_set(dev, attr);
+ return ops->switchdev_port_attr_set(dev, attr, trans);
if (attr->flags & SWITCHDEV_F_NO_RECURSE)
- return err;
+ goto done;
/* Switch device port(s) may be stacked under
* bond/team/vlan dev, so recurse down to set attr on
*/
netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = __switchdev_port_attr_set(lower_dev, attr);
+ err = __switchdev_port_attr_set(lower_dev, attr, trans);
+ if (err == -EOPNOTSUPP &&
+ attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
+ continue;
if (err)
break;
}
- return err;
-}
-
-struct switchdev_attr_set_work {
- struct work_struct work;
- struct net_device *dev;
- struct switchdev_attr attr;
-};
-
-static void switchdev_port_attr_set_work(struct work_struct *work)
-{
- struct switchdev_attr_set_work *asw =
- container_of(work, struct switchdev_attr_set_work, work);
- int err;
-
- rtnl_lock();
- err = switchdev_port_attr_set(asw->dev, &asw->attr);
- if (err && err != -EOPNOTSUPP)
- netdev_err(asw->dev, "failed (err=%d) to set attribute (id=%d)\n",
- err, asw->attr.id);
- rtnl_unlock();
+done:
+ if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP)
+ err = 0;
- dev_put(asw->dev);
- kfree(work);
-}
-
-static int switchdev_port_attr_set_defer(struct net_device *dev,
- struct switchdev_attr *attr)
-{
- struct switchdev_attr_set_work *asw;
-
- asw = kmalloc(sizeof(*asw), GFP_ATOMIC);
- if (!asw)
- return -ENOMEM;
-
- INIT_WORK(&asw->work, switchdev_port_attr_set_work);
-
- dev_hold(dev);
- asw->dev = dev;
- memcpy(&asw->attr, attr, sizeof(asw->attr));
-
- schedule_work(&asw->work);
-
- return 0;
+ return err;
}
-/**
- * switchdev_port_attr_set - Set port attribute
- *
- * @dev: port device
- * @attr: attribute to set
- *
- * Use a 2-phase prepare-commit transaction model to ensure
- * system is not left in a partially updated state due to
- * failure from driver/device.
- */
-int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
+static int switchdev_port_attr_set_now(struct net_device *dev,
+ const struct switchdev_attr *attr)
{
+ struct switchdev_trans trans;
int err;
- if (!rtnl_is_locked()) {
- /* Running prepare-commit transaction across stacked
- * devices requires nothing moves, so if rtnl_lock is
- * not held, schedule a worker thread to hold rtnl_lock
- * while setting attr.
- */
-
- return switchdev_port_attr_set_defer(dev, attr);
- }
+ switchdev_trans_init(&trans);
/* Phase I: prepare for attr set. Driver/device should fail
* here if there are going to be issues in the commit phase,
* but should not commit the attr.
*/
- attr->trans = SWITCHDEV_TRANS_PREPARE;
- err = __switchdev_port_attr_set(dev, attr);
+ trans.ph_prepare = true;
+ err = __switchdev_port_attr_set(dev, attr, &trans);
if (err) {
/* Prepare phase failed: abort the transaction. Any
* resources reserved in the prepare phase are
* released.
*/
- if (err != -EOPNOTSUPP) {
- attr->trans = SWITCHDEV_TRANS_ABORT;
- __switchdev_port_attr_set(dev, attr);
- }
+ if (err != -EOPNOTSUPP)
+ switchdev_trans_items_destroy(&trans);
return err;
}
* because the driver said everythings was OK in phase I.
*/
- attr->trans = SWITCHDEV_TRANS_COMMIT;
- err = __switchdev_port_attr_set(dev, attr);
+ trans.ph_prepare = false;
+ err = __switchdev_port_attr_set(dev, attr, &trans);
WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
dev->name, attr->id);
+ switchdev_trans_items_warn_destroy(dev, &trans);
return err;
}
+
+static void switchdev_port_attr_set_deferred(struct net_device *dev,
+ const void *data)
+{
+ const struct switchdev_attr *attr = data;
+ int err;
+
+ err = switchdev_port_attr_set_now(dev, attr);
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n",
+ err, attr->id);
+}
+
+static int switchdev_port_attr_set_defer(struct net_device *dev,
+ const struct switchdev_attr *attr)
+{
+ return switchdev_deferred_enqueue(dev, attr, sizeof(*attr),
+ switchdev_port_attr_set_deferred);
+}
+
+/**
+ * switchdev_port_attr_set - Set port attribute
+ *
+ * @dev: port device
+ * @attr: attribute to set
+ *
+ * Use a 2-phase prepare-commit transaction model to ensure
+ * system is not left in a partially updated state due to
+ * failure from driver/device.
+ *
+ * rtnl_lock must be held and must not be in atomic section,
+ * in case SWITCHDEV_F_DEFER flag is not set.
+ */
+int switchdev_port_attr_set(struct net_device *dev,
+ const struct switchdev_attr *attr)
+{
+ if (attr->flags & SWITCHDEV_F_DEFER)
+ return switchdev_port_attr_set_defer(dev, attr);
+ ASSERT_RTNL();
+ return switchdev_port_attr_set_now(dev, attr);
+}
EXPORT_SYMBOL_GPL(switchdev_port_attr_set);
static int __switchdev_port_obj_add(struct net_device *dev,
- struct switchdev_obj *obj)
+ const struct switchdev_obj *obj,
+ struct switchdev_trans *trans)
{
const struct switchdev_ops *ops = dev->switchdev_ops;
struct net_device *lower_dev;
int err = -EOPNOTSUPP;
if (ops && ops->switchdev_port_obj_add)
- return ops->switchdev_port_obj_add(dev, obj);
+ return ops->switchdev_port_obj_add(dev, obj, trans);
/* Switch device port(s) may be stacked under
* bond/team/vlan dev, so recurse down to add object on
*/
netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = __switchdev_port_obj_add(lower_dev, obj);
+ err = __switchdev_port_obj_add(lower_dev, obj, trans);
if (err)
break;
}
return err;
}
-/**
- * switchdev_port_obj_add - Add port object
- *
- * @dev: port device
- * @obj: object to add
- *
- * Use a 2-phase prepare-commit transaction model to ensure
- * system is not left in a partially updated state due to
- * failure from driver/device.
- *
- * rtnl_lock must be held.
- */
-int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj)
+static int switchdev_port_obj_add_now(struct net_device *dev,
+ const struct switchdev_obj *obj)
{
+ struct switchdev_trans trans;
int err;
ASSERT_RTNL();
+ switchdev_trans_init(&trans);
+
/* Phase I: prepare for obj add. Driver/device should fail
* here if there are going to be issues in the commit phase,
* such as lack of resources or support. The driver/device
* but should not commit the obj.
*/
- obj->trans = SWITCHDEV_TRANS_PREPARE;
- err = __switchdev_port_obj_add(dev, obj);
+ trans.ph_prepare = true;
+ err = __switchdev_port_obj_add(dev, obj, &trans);
if (err) {
/* Prepare phase failed: abort the transaction. Any
* resources reserved in the prepare phase are
* released.
*/
- if (err != -EOPNOTSUPP) {
- obj->trans = SWITCHDEV_TRANS_ABORT;
- __switchdev_port_obj_add(dev, obj);
- }
+ if (err != -EOPNOTSUPP)
+ switchdev_trans_items_destroy(&trans);
return err;
}
* because the driver said everythings was OK in phase I.
*/
- obj->trans = SWITCHDEV_TRANS_COMMIT;
- err = __switchdev_port_obj_add(dev, obj);
+ trans.ph_prepare = false;
+ err = __switchdev_port_obj_add(dev, obj, &trans);
WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);
+ switchdev_trans_items_warn_destroy(dev, &trans);
return err;
}
-EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
+
+static void switchdev_port_obj_add_deferred(struct net_device *dev,
+ const void *data)
+{
+ const struct switchdev_obj *obj = data;
+ int err;
+
+ err = switchdev_port_obj_add_now(dev, obj);
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(dev, "failed (err=%d) to add object (id=%d)\n",
+ err, obj->id);
+}
+
+static int switchdev_port_obj_add_defer(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ return switchdev_deferred_enqueue(dev, obj, sizeof(*obj),
+ switchdev_port_obj_add_deferred);
+}
/**
- * switchdev_port_obj_del - Delete port object
+ * switchdev_port_obj_add - Add port object
*
* @dev: port device
- * @obj: object to delete
+ * @id: object ID
+ * @obj: object to add
+ *
+ * Use a 2-phase prepare-commit transaction model to ensure
+ * system is not left in a partially updated state due to
+ * failure from driver/device.
+ *
+ * rtnl_lock must be held and must not be in atomic section,
+ * in case SWITCHDEV_F_DEFER flag is not set.
*/
-int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj)
+int switchdev_port_obj_add(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ if (obj->flags & SWITCHDEV_F_DEFER)
+ return switchdev_port_obj_add_defer(dev, obj);
+ ASSERT_RTNL();
+ return switchdev_port_obj_add_now(dev, obj);
+}
+EXPORT_SYMBOL_GPL(switchdev_port_obj_add);
+
+static int switchdev_port_obj_del_now(struct net_device *dev,
+ const struct switchdev_obj *obj)
{
const struct switchdev_ops *ops = dev->switchdev_ops;
struct net_device *lower_dev;
*/
netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = switchdev_port_obj_del(lower_dev, obj);
+ err = switchdev_port_obj_del_now(lower_dev, obj);
if (err)
break;
}
return err;
}
+
+static void switchdev_port_obj_del_deferred(struct net_device *dev,
+ const void *data)
+{
+ const struct switchdev_obj *obj = data;
+ int err;
+
+ err = switchdev_port_obj_del_now(dev, obj);
+ if (err && err != -EOPNOTSUPP)
+ netdev_err(dev, "failed (err=%d) to del object (id=%d)\n",
+ err, obj->id);
+}
+
+static int switchdev_port_obj_del_defer(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ return switchdev_deferred_enqueue(dev, obj, sizeof(*obj),
+ switchdev_port_obj_del_deferred);
+}
+
+/**
+ * switchdev_port_obj_del - Delete port object
+ *
+ * @dev: port device
+ * @id: object ID
+ * @obj: object to delete
+ *
+ * rtnl_lock must be held and must not be in atomic section,
+ * in case SWITCHDEV_F_DEFER flag is not set.
+ */
+int switchdev_port_obj_del(struct net_device *dev,
+ const struct switchdev_obj *obj)
+{
+ if (obj->flags & SWITCHDEV_F_DEFER)
+ return switchdev_port_obj_del_defer(dev, obj);
+ ASSERT_RTNL();
+ return switchdev_port_obj_del_now(dev, obj);
+}
EXPORT_SYMBOL_GPL(switchdev_port_obj_del);
/**
* switchdev_port_obj_dump - Dump port objects
*
* @dev: port device
+ * @id: object ID
* @obj: object to dump
+ * @cb: function to call with a filled object
+ *
+ * rtnl_lock must be held.
*/
-int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj)
+int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj,
+ switchdev_obj_dump_cb_t *cb)
{
const struct switchdev_ops *ops = dev->switchdev_ops;
struct net_device *lower_dev;
struct list_head *iter;
int err = -EOPNOTSUPP;
+ ASSERT_RTNL();
+
if (ops && ops->switchdev_port_obj_dump)
- return ops->switchdev_port_obj_dump(dev, obj);
+ return ops->switchdev_port_obj_dump(dev, obj, cb);
/* Switch device port(s) may be stacked under
* bond/team/vlan dev, so recurse down to dump objects on
*/
netdev_for_each_lower_dev(dev, lower_dev, iter) {
- err = switchdev_port_obj_dump(lower_dev, obj);
+ err = switchdev_port_obj_dump(lower_dev, obj, cb);
break;
}
EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
struct switchdev_vlan_dump {
- struct switchdev_obj obj;
+ struct switchdev_obj_port_vlan vlan;
struct sk_buff *skb;
u32 filter_mask;
u16 flags;
u16 end;
};
-static int switchdev_port_vlan_dump_put(struct net_device *dev,
- struct switchdev_vlan_dump *dump)
+static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump)
{
struct bridge_vlan_info vinfo;
return 0;
}
-static int switchdev_port_vlan_dump_cb(struct net_device *dev,
- struct switchdev_obj *obj)
+static int switchdev_port_vlan_dump_cb(struct switchdev_obj *obj)
{
+ struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
struct switchdev_vlan_dump *dump =
- container_of(obj, struct switchdev_vlan_dump, obj);
- struct switchdev_obj_vlan *vlan = &dump->obj.u.vlan;
+ container_of(vlan, struct switchdev_vlan_dump, vlan);
int err = 0;
if (vlan->vid_begin > vlan->vid_end)
for (dump->begin = dump->end = vlan->vid_begin;
dump->begin <= vlan->vid_end;
dump->begin++, dump->end++) {
- err = switchdev_port_vlan_dump_put(dev, dump);
+ err = switchdev_port_vlan_dump_put(dump);
if (err)
return err;
}
/* prepend */
dump->begin = vlan->vid_begin;
} else {
- err = switchdev_port_vlan_dump_put(dev, dump);
+ err = switchdev_port_vlan_dump_put(dump);
dump->flags = vlan->flags;
dump->begin = vlan->vid_begin;
dump->end = vlan->vid_end;
/* append */
dump->end = vlan->vid_end;
} else {
- err = switchdev_port_vlan_dump_put(dev, dump);
+ err = switchdev_port_vlan_dump_put(dump);
dump->flags = vlan->flags;
dump->begin = vlan->vid_begin;
dump->end = vlan->vid_end;
u32 filter_mask)
{
struct switchdev_vlan_dump dump = {
- .obj = {
- .id = SWITCHDEV_OBJ_PORT_VLAN,
- .cb = switchdev_port_vlan_dump_cb,
- },
+ .vlan.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
.skb = skb,
.filter_mask = filter_mask,
};
if ((filter_mask & RTEXT_FILTER_BRVLAN) ||
(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) {
- err = switchdev_port_obj_dump(dev, &dump.obj);
+ err = switchdev_port_obj_dump(dev, &dump.vlan.obj,
+ switchdev_port_vlan_dump_cb);
if (err)
goto err_out;
if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)
/* last one */
- err = switchdev_port_vlan_dump_put(dev, &dump);
+ err = switchdev_port_vlan_dump_put(&dump);
}
err_out:
int nlflags)
{
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS,
+ .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
};
u16 mode = BRIDGE_MODE_UNDEF;
u32 mask = BR_LEARNING | BR_LEARNING_SYNC;
unsigned long brport_flag)
{
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS,
+ .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS,
};
u8 flag = nla_get_u8(nlattr);
int err;
static int switchdev_port_br_afspec(struct net_device *dev,
struct nlattr *afspec,
int (*f)(struct net_device *dev,
- struct switchdev_obj *obj))
+ const struct switchdev_obj *obj))
{
struct nlattr *attr;
struct bridge_vlan_info *vinfo;
- struct switchdev_obj obj = {
- .id = SWITCHDEV_OBJ_PORT_VLAN,
+ struct switchdev_obj_port_vlan vlan = {
+ .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
};
- struct switchdev_obj_vlan *vlan = &obj.u.vlan;
int rem;
int err;
if (nla_len(attr) != sizeof(struct bridge_vlan_info))
return -EINVAL;
vinfo = nla_data(attr);
- vlan->flags = vinfo->flags;
+ if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK)
+ return -EINVAL;
+ vlan.flags = vinfo->flags;
if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
- if (vlan->vid_begin)
+ if (vlan.vid_begin)
+ return -EINVAL;
+ vlan.vid_begin = vinfo->vid;
+ /* don't allow range of pvids */
+ if (vlan.flags & BRIDGE_VLAN_INFO_PVID)
return -EINVAL;
- vlan->vid_begin = vinfo->vid;
} else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) {
- if (!vlan->vid_begin)
+ if (!vlan.vid_begin)
return -EINVAL;
- vlan->vid_end = vinfo->vid;
- if (vlan->vid_end <= vlan->vid_begin)
+ vlan.vid_end = vinfo->vid;
+ if (vlan.vid_end <= vlan.vid_begin)
return -EINVAL;
- err = f(dev, &obj);
+ err = f(dev, &vlan.obj);
if (err)
return err;
- memset(vlan, 0, sizeof(*vlan));
+ memset(&vlan, 0, sizeof(vlan));
} else {
- if (vlan->vid_begin)
+ if (vlan.vid_begin)
return -EINVAL;
- vlan->vid_begin = vinfo->vid;
- vlan->vid_end = vinfo->vid;
- err = f(dev, &obj);
+ vlan.vid_begin = vinfo->vid;
+ vlan.vid_end = vinfo->vid;
+ err = f(dev, &vlan.obj);
if (err)
return err;
- memset(vlan, 0, sizeof(*vlan));
+ memset(&vlan, 0, sizeof(vlan));
}
}
struct net_device *dev, const unsigned char *addr,
u16 vid, u16 nlm_flags)
{
- struct switchdev_obj obj = {
- .id = SWITCHDEV_OBJ_PORT_FDB,
- .u.fdb = {
- .addr = addr,
- .vid = vid,
- },
+ struct switchdev_obj_port_fdb fdb = {
+ .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
+ .vid = vid,
};
- return switchdev_port_obj_add(dev, &obj);
+ ether_addr_copy(fdb.addr, addr);
+ return switchdev_port_obj_add(dev, &fdb.obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_add);
struct net_device *dev, const unsigned char *addr,
u16 vid)
{
- struct switchdev_obj obj = {
- .id = SWITCHDEV_OBJ_PORT_FDB,
- .u.fdb = {
- .addr = addr,
- .vid = vid,
- },
+ struct switchdev_obj_port_fdb fdb = {
+ .obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
+ .vid = vid,
};
- return switchdev_port_obj_del(dev, &obj);
+ ether_addr_copy(fdb.addr, addr);
+ return switchdev_port_obj_del(dev, &fdb.obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_del);
struct switchdev_fdb_dump {
- struct switchdev_obj obj;
+ struct switchdev_obj_port_fdb fdb;
+ struct net_device *dev;
struct sk_buff *skb;
struct netlink_callback *cb;
int idx;
};
-static int switchdev_port_fdb_dump_cb(struct net_device *dev,
- struct switchdev_obj *obj)
+static int switchdev_port_fdb_dump_cb(struct switchdev_obj *obj)
{
+ struct switchdev_obj_port_fdb *fdb = SWITCHDEV_OBJ_PORT_FDB(obj);
struct switchdev_fdb_dump *dump =
- container_of(obj, struct switchdev_fdb_dump, obj);
+ container_of(fdb, struct switchdev_fdb_dump, fdb);
u32 portid = NETLINK_CB(dump->cb->skb).portid;
u32 seq = dump->cb->nlh->nlmsg_seq;
struct nlmsghdr *nlh;
ndm->ndm_pad2 = 0;
ndm->ndm_flags = NTF_SELF;
ndm->ndm_type = 0;
- ndm->ndm_ifindex = dev->ifindex;
- ndm->ndm_state = obj->u.fdb.ndm_state;
+ ndm->ndm_ifindex = dump->dev->ifindex;
+ ndm->ndm_state = fdb->ndm_state;
- if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr))
+ if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, fdb->addr))
goto nla_put_failure;
- if (obj->u.fdb.vid && nla_put_u16(dump->skb, NDA_VLAN, obj->u.fdb.vid))
+ if (fdb->vid && nla_put_u16(dump->skb, NDA_VLAN, fdb->vid))
goto nla_put_failure;
nlmsg_end(dump->skb, nlh);
struct net_device *filter_dev, int idx)
{
struct switchdev_fdb_dump dump = {
- .obj = {
- .id = SWITCHDEV_OBJ_PORT_FDB,
- .cb = switchdev_port_fdb_dump_cb,
- },
+ .fdb.obj.id = SWITCHDEV_OBJ_ID_PORT_FDB,
+ .dev = dev,
.skb = skb,
.cb = cb,
.idx = idx,
};
- switchdev_port_obj_dump(dev, &dump.obj);
+ switchdev_port_obj_dump(dev, &dump.fdb.obj, switchdev_port_fdb_dump_cb);
return dump.idx;
}
EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump);
static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi)
{
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
};
struct switchdev_attr prev_attr;
struct net_device *dev = NULL;
int nhsel;
+ ASSERT_RTNL();
+
/* For this route, all nexthop devs must be on the same switch. */
for (nhsel = 0; nhsel < fi->fib_nhs; nhsel++) {
int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
u8 tos, u8 type, u32 nlflags, u32 tb_id)
{
- struct switchdev_obj fib_obj = {
- .id = SWITCHDEV_OBJ_IPV4_FIB,
- .u.ipv4_fib = {
- .dst = dst,
- .dst_len = dst_len,
- .fi = fi,
- .tos = tos,
- .type = type,
- .nlflags = nlflags,
- .tb_id = tb_id,
- },
+ struct switchdev_obj_ipv4_fib ipv4_fib = {
+ .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
+ .dst = dst,
+ .dst_len = dst_len,
+ .tos = tos,
+ .type = type,
+ .nlflags = nlflags,
+ .tb_id = tb_id,
};
struct net_device *dev;
int err = 0;
+ memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
+
/* Don't offload route if using custom ip rules or if
* IPv4 FIB offloading has been disabled completely.
*/
if (!dev)
return 0;
- err = switchdev_port_obj_add(dev, &fib_obj);
+ err = switchdev_port_obj_add(dev, &ipv4_fib.obj);
if (!err)
fi->fib_flags |= RTNH_F_OFFLOAD;
int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
u8 tos, u8 type, u32 tb_id)
{
- struct switchdev_obj fib_obj = {
- .id = SWITCHDEV_OBJ_IPV4_FIB,
- .u.ipv4_fib = {
- .dst = dst,
- .dst_len = dst_len,
- .fi = fi,
- .tos = tos,
- .type = type,
- .nlflags = 0,
- .tb_id = tb_id,
- },
+ struct switchdev_obj_ipv4_fib ipv4_fib = {
+ .obj.id = SWITCHDEV_OBJ_ID_IPV4_FIB,
+ .dst = dst,
+ .dst_len = dst_len,
+ .tos = tos,
+ .type = type,
+ .nlflags = 0,
+ .tb_id = tb_id,
};
struct net_device *dev;
int err = 0;
+ memcpy(&ipv4_fib.fi, fi, sizeof(ipv4_fib.fi));
+
if (!(fi->fib_flags & RTNH_F_OFFLOAD))
return 0;
if (!dev)
return 0;
- err = switchdev_port_obj_del(dev, &fib_obj);
+ err = switchdev_port_obj_del(dev, &ipv4_fib.obj);
if (!err)
fi->fib_flags &= ~RTNH_F_OFFLOAD;
struct net_device *b)
{
struct switchdev_attr a_attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
struct switchdev_attr b_attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
u32 mark = dev->ifindex;
u32 reset_mark = 0;
- if (group_dev && joining) {
- mark = switchdev_port_fwd_mark_get(dev, group_dev);
- } else if (group_dev && !joining) {
- if (dev->offload_fwd_mark == mark)
+ if (group_dev) {
+ ASSERT_RTNL();
+ if (joining)
+ mark = switchdev_port_fwd_mark_get(dev, group_dev);
+ else if (dev->offload_fwd_mark == mark)
/* Ohoh, this port was the mark reference port,
* but it's leaving the group, so reset the
* mark for the remaining ports in the group.
if (likely((usr <= TIPC_CRITICAL_IMPORTANCE) && !msg_errcode(m)))
return usr;
if ((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER))
- return msg_bits(m, 5, 13, 0x7);
+ return msg_bits(m, 9, 0, 0x7);
return TIPC_SYSTEM_IMPORTANCE;
}
int usr = msg_user(m);
if (likely((usr == MSG_FRAGMENTER) || (usr == MSG_BUNDLER)))
- msg_set_bits(m, 5, 13, 0x7, i);
+ msg_set_bits(m, 9, 0, 0x7, i);
else if (i < TIPC_SYSTEM_IMPORTANCE)
msg_set_user(m, i);
else
int offset, int dsz, int mtu, struct sk_buff_head *list);
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err);
struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list);
+void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
+ struct sk_buff *skb);
static inline u16 buf_seqno(struct sk_buff *skb)
{
return skb;
}
-/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number
- * @list: list to be appended to
- * @skb: buffer to add
- * Returns true if queue should treated further, otherwise false
- */
-static inline bool __tipc_skb_queue_sorted(struct sk_buff_head *list,
- struct sk_buff *skb)
-{
- struct sk_buff *_skb, *tmp;
- struct tipc_msg *hdr = buf_msg(skb);
- u16 seqno = msg_seqno(hdr);
-
- if (skb_queue_empty(list) || (msg_user(hdr) == LINK_PROTOCOL)) {
- __skb_queue_head(list, skb);
- return true;
- }
- if (likely(less(seqno, buf_seqno(skb_peek(list))))) {
- __skb_queue_head(list, skb);
- return true;
- }
- if (!more(seqno, buf_seqno(skb_peek_tail(list)))) {
- skb_queue_walk_safe(list, _skb, tmp) {
- if (likely(less(seqno, buf_seqno(_skb)))) {
- __skb_queue_before(list, _skb, skb);
- return true;
- }
- }
- }
- __skb_queue_tail(list, skb);
- return false;
-}
-
/* tipc_skb_queue_splice_tail - append an skb list to lock protected list
* @list: the new list to append. Not lock protected
* @head: target list. Lock protected.
struct tipc_link *ol = node_active_link(n, 0);
struct tipc_link *nl = n->links[bearer_id].link;
- if (!nl || !tipc_link_is_up(nl))
+ if (!nl)
+ return;
+
+ tipc_link_fsm_evt(nl, LINK_ESTABLISH_EVT);
+ if (!tipc_link_is_up(nl))
return;
n->working_links++;
}
if (!tipc_node_is_up(n)) {
+ if (tipc_link_peer_is_down(l))
+ tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
+ tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_reset(l);
+ tipc_link_build_reset_msg(l, xmitq);
+ *maddr = &n->links[*bearer_id].maddr;
node_lost_contact(n, &le->inputq);
return;
}
n->sync_point = tnl->rcv_nxt + (U16_MAX / 2 - 1);
tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq);
tipc_link_reset(l);
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT);
*maddr = &n->links[tnl->bearer_id].maddr;
static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
{
struct tipc_link_entry *le = &n->links[bearer_id];
+ struct tipc_link *l = le->link;
struct tipc_media_addr *maddr;
struct sk_buff_head xmitq;
+ if (!l)
+ return;
+
__skb_queue_head_init(&xmitq);
tipc_node_lock(n);
- __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
- if (delete && le->link) {
- kfree(le->link);
- le->link = NULL;
- n->link_cnt--;
+ if (!tipc_link_is_establishing(l)) {
+ __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr);
+ if (delete) {
+ kfree(l);
+ le->link = NULL;
+ n->link_cnt--;
+ }
+ } else {
+ /* Defuse pending tipc_node_link_up() */
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
}
tipc_node_unlock(n);
-
tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
tipc_sk_rcv(n->net, &le->inputq);
}
goto exit;
}
tipc_link_reset(l);
+ tipc_link_fsm_evt(l, LINK_RESET_EVT);
if (n->state == NODE_FAILINGOVER)
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
le->link = l;
memcpy(&le->maddr, maddr, sizeof(*maddr));
exit:
tipc_node_unlock(n);
- if (reset)
+ if (reset && !tipc_link_is_reset(l))
tipc_node_link_down(n, b->identity, false);
tipc_node_put(n);
}
break;
case SELF_ESTABL_CONTACT_EVT:
case PEER_LOST_CONTACT_EVT:
- break;
case NODE_SYNCH_END_EVT:
- case NODE_SYNCH_BEGIN_EVT:
case NODE_FAILOVER_BEGIN_EVT:
+ break;
+ case NODE_SYNCH_BEGIN_EVT:
case NODE_FAILOVER_END_EVT:
default:
goto illegal_evt;
tipc_link_fsm_evt(l, LINK_FAILOVER_END_EVT);
}
- /* Prevent re-contact with node until cleanup is done */
- tipc_node_fsm_evt(n_ptr, SELF_LOST_CONTACT_EVT);
-
/* Notify publications from this node */
n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN;
}
/* Ignore duplicate packets */
- if (less(oseqno, rcv_nxt))
+ if ((usr != LINK_PROTOCOL) && less(oseqno, rcv_nxt))
return true;
/* Initiate or update failover mode if applicable */
if (!pl || !tipc_link_is_up(pl))
return true;
- /* Initiate or update synch mode if applicable */
- if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG)) {
+ /* Initiate synch mode if applicable */
+ if ((usr == TUNNEL_PROTOCOL) && (mtyp == SYNCH_MSG) && (oseqno == 1)) {
syncpt = iseqno + exp_pkts - 1;
if (!tipc_link_is_up(l)) {
tipc_link_fsm_evt(l, LINK_ESTABLISH_EVT);