From ec4efc4a10c3b9a3ab4cf37dc3719fd3c4632cd0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 13 Dec 2016 09:39:18 +0100 Subject: [PATCH 01/63] mac80211: don't call drv_set_default_unicast_key() for VLANs Since drivers know nothing about AP_VLAN interfaces, trying to call drv_set_default_unicast_key() just results in a warning and no call to the driver. Avoid the warning by not calling the driver for this on AP_VLAN interfaces. This means that drivers that somehow need this call for AP mode will fail to work properly in the presence of VLAN interfaces, but the current drivers don't seem to use it, and mac80211 will select and indicate the key - so drivers should be OK now. Reported-by: Jouni Malinen Signed-off-by: Johannes Berg --- net/mac80211/key.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mac80211/key.c b/net/mac80211/key.c index edd6f2945f69..a98fc2b5e0dc 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -265,7 +265,8 @@ static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, if (uni) { rcu_assign_pointer(sdata->default_unicast_key, key); ieee80211_check_fast_xmit_iface(sdata); - drv_set_default_unicast_key(sdata->local, sdata, idx); + if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) + drv_set_default_unicast_key(sdata->local, sdata, idx); } if (multi) From d8da0b5d64d58f7775a94bcf12dda50f13a76f22 Mon Sep 17 00:00:00 2001 From: Cedric Izoard Date: Wed, 7 Dec 2016 09:59:00 +0000 Subject: [PATCH 02/63] mac80211: Ensure enough headroom when forwarding mesh pkt When a buffer is duplicated during MESH packet forwarding, this patch ensures that the new buffer has enough headroom. Signed-off-by: Cedric Izoard Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index eeab7250f4b9..3e289a64ed43 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2472,7 +2472,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; - fwd_skb = skb_copy(skb, GFP_ATOMIC); + fwd_skb = skb_copy_expand(skb, local->tx_headroom, 0, GFP_ATOMIC); if (!fwd_skb) { net_info_ratelimited("%s: failed to clone mesh frame\n", sdata->name); From a220871be66f99d8957c693cf22ec67ecbd9c23a Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 13 Dec 2016 14:23:05 +0800 Subject: [PATCH 03/63] virtio-net: correctly enable multiqueue Commit 4490001029012539937ff02778fe6180613fa949 ("virtio-net: enable multiqueue by default") blindly set the affinity instead of queues during probe which can cause a mismatch of #queues between guest and host. This patch fixes it by setting queues. Reported-by: Theodore Ts'o Tested-by: Theodore Ts'o Cc: Neil Horman Cc: Michael S. Tsirkin Fixes: 49000102901 ("virtio-net: enable multiqueue by default") Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b425fa1013af..fe9f7726e990 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1930,7 +1930,9 @@ static int virtnet_probe(struct virtio_device *vdev) goto free_unregister_netdev; } - virtnet_set_affinity(vi); + rtnl_lock(); + virtnet_set_queues(vi, vi->curr_queue_pairs); + rtnl_unlock(); /* Assume link up if device can't report link status, otherwise get link status from config. */ From 3e1ed981b7a903ba81199d4d25b80c6bba705160 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 13 Dec 2016 22:30:15 +0300 Subject: [PATCH 04/63] netlink: revert broken, broken "2-clause nla_ok()" Commit 4f7df337fe79bba1e4c2d525525d63b5ba186bbd "netlink: 2-clause nla_ok()" is BROKEN. First clause tests if "->nla_len" could even be accessed at all, it can not possibly be omitted. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/netlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/netlink.h b/include/net/netlink.h index dd657a33f8c3..d3938f11ae52 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -698,7 +698,8 @@ static inline int nla_len(const struct nlattr *nla) */ static inline int nla_ok(const struct nlattr *nla, int remaining) { - return nla->nla_len >= sizeof(*nla) && + return remaining >= (int) sizeof(*nla) && + nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } From a17d93ff3a950fefaea40e4a4bf3669b9137c533 Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Wed, 14 Dec 2016 11:30:38 -0800 Subject: [PATCH 05/63] mac80211: fix legacy and invalid rx-rate report This fixes obtaining the rate info via sta_set_sinfo when the rx rate is invalid (for instance, on IBSS interface that has received no frames from one of its peers). Also initialize rinfo->flags for legacy rates, to not rely on the whole sinfo being initialized to zero. Signed-off-by: Ben Greear Signed-off-by: Johannes Berg --- net/mac80211/sta_info.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 1711bae4abf2..b6cfcf038c11 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1972,6 +1972,7 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, u16 brate; unsigned int shift; + rinfo->flags = 0; sband = local->hw.wiphy->bands[(rate >> 4) & 0xf]; brate = sband->bitrates[rate & 0xf].bitrate; if (rinfo->bw == RATE_INFO_BW_5) @@ -1987,14 +1988,15 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate, rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; } -static void sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) +static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) { u16 rate = ACCESS_ONCE(sta_get_last_rx_stats(sta)->last_rate); if (rate == STA_STATS_RATE_INVALID) - rinfo->flags = 0; - else - sta_stats_decode_rate(sta->local, rate, rinfo); + return -EINVAL; + + sta_stats_decode_rate(sta->local, rate, rinfo); + return 0; } static void sta_set_tidstats(struct sta_info *sta, @@ -2199,8 +2201,8 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo) } if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) { - sta_set_rate_info_rx(sta, &sinfo->rxrate); - sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE); + if (sta_set_rate_info_rx(sta, &sinfo->rxrate) == 0) + sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE); } sinfo->filled |= BIT(NL80211_STA_INFO_TID_STATS); From e28ceeb10cd1883a4b6528c17a2b1f2024e35cad Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 11 Dec 2016 18:31:22 +0100 Subject: [PATCH 06/63] net/3com/3c515: Fix timer handling, prevent leaks and crashes The timer handling in this driver is broken in several ways: - corkscrew_open() initializes and arms a timer before requesting the device interrupt. If the request fails the timer stays armed. A second call to corkscrew_open will unconditionally reinitialize the quued timer and arm it again. Also a immediate device removal will leave the timer queued because close() is not called (open() failed) and therefore nothing issues del_timer(). The reinitialization corrupts the link chain in the timer wheel hash bucket and causes a NULL pointer dereference when the timer wheel tries to operate on that hash bucket. Immediate device removal lets the link chain poke into freed and possibly reused memory. Solution: Arm the timer after the successful irq request. - corkscrew_close() uses del_timer() On close the timer is disarmed with del_timer() which lets the following code race against a concurrent timer expiry function. Solution: Use del_timer_sync() instead - corkscrew_close() calls del_timer() unconditionally del_timer() is invoked even if the timer was never initialized. This works by chance because the struct containing the timer is zeroed at allocation time. Solution: Move the setup of the timer into corkscrew_setup(). Reported-by: Matthew Whitehead Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/ethernet/3com/3c515.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index b9f4c463e516..be5b80103bec 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -627,6 +627,8 @@ static int corkscrew_setup(struct net_device *dev, int ioaddr, spin_lock_init(&vp->lock); + setup_timer(&vp->timer, corkscrew_timer, (unsigned long) dev); + /* Read the station address from the EEPROM. */ EL3WINDOW(0); for (i = 0; i < 0x18; i++) { @@ -707,6 +709,7 @@ static int corkscrew_open(struct net_device *dev) { int ioaddr = dev->base_addr; struct corkscrew_private *vp = netdev_priv(dev); + bool armtimer = false; __u32 config; int i; @@ -731,12 +734,7 @@ static int corkscrew_open(struct net_device *dev) if (corkscrew_debug > 1) pr_debug("%s: Initial media type %s.\n", dev->name, media_tbl[dev->if_port].name); - - init_timer(&vp->timer); - vp->timer.expires = jiffies + media_tbl[dev->if_port].wait; - vp->timer.data = (unsigned long) dev; - vp->timer.function = corkscrew_timer; /* timer handler */ - add_timer(&vp->timer); + armtimer = true; } else dev->if_port = vp->default_media; @@ -776,6 +774,9 @@ static int corkscrew_open(struct net_device *dev) return -EAGAIN; } + if (armtimer) + mod_timer(&vp->timer, jiffies + media_tbl[dev->if_port].wait); + if (corkscrew_debug > 1) { EL3WINDOW(4); pr_debug("%s: corkscrew_open() irq %d media status %4.4x.\n", @@ -1426,7 +1427,7 @@ static int corkscrew_close(struct net_device *dev) dev->name, rx_nocopy, rx_copy, queued_packet); } - del_timer(&vp->timer); + del_timer_sync(&vp->timer); /* Turn off statistics ASAP. We update lp->stats below. */ outw(StatsDisable, ioaddr + EL3_CMD); From 66e2809dd324f0ab5e1f9d997b40d4d31a2e42b1 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Sun, 11 Dec 2016 21:07:19 +0100 Subject: [PATCH 07/63] net: dsa: mv88e6xxx: Fix opps when adding vlan bridge A port is not necessarily assigned to a netdev. And a port does not need to be a member of a bridge. So when iterating over all ports, check before using the netdev and bridge_dev for a port. Otherwise we dereference a NULL pointer. Fixes: da9c359e19f0 ("net: dsa: mv88e6xxx: check hardware VLAN in use") Signed-off-by: Andrew Lunn Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 4da379f28d5d..f7222dc6581d 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1775,6 +1775,9 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, if (dsa_is_dsa_port(ds, i) || dsa_is_cpu_port(ds, i)) continue; + if (!ds->ports[port].netdev) + continue; + if (vlan.data[i] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER) continue; @@ -1783,6 +1786,9 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, chip->ports[port].bridge_dev) break; /* same bridge, check next VLAN */ + if (!chip->ports[i].bridge_dev) + continue; + netdev_warn(ds->ports[port].netdev, "hardware VLAN %d already used by %s\n", vlan.vid, From 2087d421a5a1af4883e3cf0afb93823b7e12132a Mon Sep 17 00:00:00 2001 From: Dongpo Li Date: Mon, 12 Dec 2016 20:03:42 +0800 Subject: [PATCH 08/63] net: ethernet: hisi_femac: Call SET_NETDEV_DEV() The hisi_femac driver calls into PHYLIB which now checks for net_device->dev.parent, so make sure we do set it before calling into any MDIO/PHYLIB related function. Fixes: ec988ad78ed6 ("phy: Don't increment MDIO bus refcount unless it's a different owner") Signed-off-by: Dongpo Li Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hisi_femac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 49863068c59e..979852d56f31 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -805,6 +805,7 @@ static int hisi_femac_drv_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, ndev); + SET_NETDEV_DEV(ndev, &pdev->dev); priv = netdev_priv(ndev); priv->dev = dev; @@ -882,7 +883,6 @@ static int hisi_femac_drv_probe(struct platform_device *pdev) ndev->netdev_ops = &hisi_femac_netdev_ops; ndev->ethtool_ops = &hisi_femac_ethtools_ops; netif_napi_add(ndev, &priv->napi, hisi_femac_poll, FEMAC_POLL_WEIGHT); - SET_NETDEV_DEV(ndev, &pdev->dev); hisi_femac_port_init(priv); From 8cd1f70f205a1c684037f06906566ddb3066d659 Mon Sep 17 00:00:00 2001 From: Dongpo Li Date: Mon, 12 Dec 2016 20:03:43 +0800 Subject: [PATCH 09/63] net: ethernet: hip04: Call SET_NETDEV_DEV() The hip04 driver calls into PHYLIB which now checks for net_device->dev.parent, so make sure we do set it before calling into any MDIO/PHYLIB related function. Fixes: ec988ad78ed6 ("phy: Don't increment MDIO bus refcount unless it's a different owner") Signed-off-by: Dongpo Li Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/hisilicon/hip04_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 854befde0a08..97b184774784 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -828,6 +828,7 @@ static int hip04_mac_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->ndev = ndev; platform_set_drvdata(pdev, ndev); + SET_NETDEV_DEV(ndev, &pdev->dev); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->base = devm_ioremap_resource(d, res); @@ -903,7 +904,6 @@ static int hip04_mac_probe(struct platform_device *pdev) ndev->priv_flags |= IFF_UNICAST_FLT; ndev->irq = irq; netif_napi_add(ndev, &priv->napi, hip04_rx_poll, NAPI_POLL_WEIGHT); - SET_NETDEV_DEV(ndev, &pdev->dev); hip04_reset_ppe(priv); if (priv->phy_mode == PHY_INTERFACE_MODE_MII) From ebe5236d06abcdb1beb93ffbab73557d5b496824 Mon Sep 17 00:00:00 2001 From: Jeroen De Wachter Date: Mon, 12 Dec 2016 14:29:08 +0100 Subject: [PATCH 10/63] encx24j600: bugfix - always move ERXTAIL to next packet in encx24j600_rx_packets Before, encx24j600_rx_packets did not update encx24j600_priv's next_packet member when an error occurred during packet handling (either because the packet's RSV header indicates an error or because the encx24j600_receive_packet method can't allocate an sk_buff). If the next_packet member is not updated, the ERXTAIL register will be set to the same value it had before, which means the bad packet remains in the component's memory and its RSV header will be read again when a new packet arrives. If the RSV header indicates a bad packet or if sk_buff allocation continues to fail, new packets will be stored in the component's memory until that memory is full, after which packets will be dropped. The SETPKTDEC command is always executed though, so the encx24j600 hardware has an incorrect count of the packets in its memory. To prevent this, the next_packet member should always be updated, allowing the packet to be skipped (either because it's bad, as indicated in its RSV header, or because allocating an sk_buff failed). In the allocation failure case, this does mean dropping a valid packet, but dropping the oldest packet to keep as much memory as possible available for new packets seems preferable to keeping old (but valid) packets around while dropping new ones. Signed-off-by: Jeroen De Wachter Signed-off-by: David S. Miller --- drivers/net/ethernet/microchip/encx24j600.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index b14f0305aa31..5251aa3cf4d7 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -346,7 +346,6 @@ static int encx24j600_receive_packet(struct encx24j600_priv *priv, /* Maintain stats */ dev->stats.rx_packets++; dev->stats.rx_bytes += rsv->len; - priv->next_packet = rsv->next_packet; netif_rx(skb); @@ -383,6 +382,8 @@ static void encx24j600_rx_packets(struct encx24j600_priv *priv, u8 packet_count) encx24j600_receive_packet(priv, &rsv); } + priv->next_packet = rsv.next_packet; + newrxtail = priv->next_packet - 2; if (newrxtail == ENC_RX_BUF_START) newrxtail = SRAM_SIZE - 2; From b822ee6c5e5ba1f695fc514a65849cdd87618bd3 Mon Sep 17 00:00:00 2001 From: Jeroen De Wachter Date: Mon, 12 Dec 2016 14:29:09 +0100 Subject: [PATCH 11/63] encx24j600: Fix some checkstyle warnings Signed-off-by: Jeroen De Wachter Signed-off-by: David S. Miller --- .../net/ethernet/microchip/encx24j600-regmap.c | 17 +++++++++++------ drivers/net/ethernet/microchip/encx24j600.c | 16 ++++++++++++++-- 2 files changed, 25 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c index f3bb9055a292..44bb04d4d21b 100644 --- a/drivers/net/ethernet/microchip/encx24j600-regmap.c +++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c @@ -26,11 +26,11 @@ static inline bool is_bits_set(int value, int mask) } static int encx24j600_switch_bank(struct encx24j600_context *ctx, - int bank) + int bank) { int ret = 0; - int bank_opcode = BANK_SELECT(bank); + ret = spi_write(ctx->spi, &bank_opcode, 1); if (ret == 0) ctx->bank = bank; @@ -39,7 +39,7 @@ static int encx24j600_switch_bank(struct encx24j600_context *ctx, } static int encx24j600_cmdn(struct encx24j600_context *ctx, u8 opcode, - const void *buf, size_t len) + const void *buf, size_t len) { struct spi_message m; struct spi_transfer t[2] = { { .tx_buf = &opcode, .len = 1, }, @@ -54,12 +54,14 @@ static int encx24j600_cmdn(struct encx24j600_context *ctx, u8 opcode, static void regmap_lock_mutex(void *context) { struct encx24j600_context *ctx = context; + mutex_lock(&ctx->mutex); } static void regmap_unlock_mutex(void *context) { struct encx24j600_context *ctx = context; + mutex_unlock(&ctx->mutex); } @@ -128,6 +130,7 @@ static int regmap_encx24j600_sfr_update(struct encx24j600_context *ctx, if (reg < 0x80) { int ret = 0; + cmd = banked_code | banked_reg; if ((banked_reg < 0x16) && (ctx->bank != bank)) ret = encx24j600_switch_bank(ctx, bank); @@ -174,6 +177,7 @@ static int regmap_encx24j600_sfr_write(void *context, u8 reg, u8 *val, size_t len) { struct encx24j600_context *ctx = context; + return regmap_encx24j600_sfr_update(ctx, reg, val, len, WCRU, WCRCODE); } @@ -228,9 +232,9 @@ int regmap_encx24j600_spi_write(void *context, u8 reg, const u8 *data, if (reg < 0xc0) return encx24j600_cmdn(ctx, reg, data, count); - else - /* SPI 1-byte command. Ignore data */ - return spi_write(ctx->spi, ®, 1); + + /* SPI 1-byte command. Ignore data */ + return spi_write(ctx->spi, ®, 1); } EXPORT_SYMBOL_GPL(regmap_encx24j600_spi_write); @@ -495,6 +499,7 @@ static struct regmap_config phycfg = { .writeable_reg = encx24j600_phymap_writeable, .volatile_reg = encx24j600_phymap_volatile, }; + static struct regmap_bus phymap_encx24j600 = { .reg_write = regmap_encx24j600_phy_reg_write, .reg_read = regmap_encx24j600_phy_reg_read, diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 5251aa3cf4d7..fbce6166504e 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -30,7 +30,7 @@ #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) static int debug = -1; -module_param(debug, int, 0); +module_param(debug, int, 0000); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); /* SRAM memory layout: @@ -105,6 +105,7 @@ static u16 encx24j600_read_reg(struct encx24j600_priv *priv, u8 reg) struct net_device *dev = priv->ndev; unsigned int val = 0; int ret = regmap_read(priv->ctx.regmap, reg, &val); + if (unlikely(ret)) netif_err(priv, drv, dev, "%s: error %d reading reg %02x\n", __func__, ret, reg); @@ -115,6 +116,7 @@ static void encx24j600_write_reg(struct encx24j600_priv *priv, u8 reg, u16 val) { struct net_device *dev = priv->ndev; int ret = regmap_write(priv->ctx.regmap, reg, val); + if (unlikely(ret)) netif_err(priv, drv, dev, "%s: error %d writing reg %02x=%04x\n", __func__, ret, reg, val); @@ -125,6 +127,7 @@ static void encx24j600_update_reg(struct encx24j600_priv *priv, u8 reg, { struct net_device *dev = priv->ndev; int ret = regmap_update_bits(priv->ctx.regmap, reg, mask, val); + if (unlikely(ret)) netif_err(priv, drv, dev, "%s: error %d updating reg %02x=%04x~%04x\n", __func__, ret, reg, val, mask); @@ -135,6 +138,7 @@ static u16 encx24j600_read_phy(struct encx24j600_priv *priv, u8 reg) struct net_device *dev = priv->ndev; unsigned int val = 0; int ret = regmap_read(priv->ctx.phymap, reg, &val); + if (unlikely(ret)) netif_err(priv, drv, dev, "%s: error %d reading %02x\n", __func__, ret, reg); @@ -145,6 +149,7 @@ static void encx24j600_write_phy(struct encx24j600_priv *priv, u8 reg, u16 val) { struct net_device *dev = priv->ndev; int ret = regmap_write(priv->ctx.phymap, reg, val); + if (unlikely(ret)) netif_err(priv, drv, dev, "%s: error %d writing reg %02x=%04x\n", __func__, ret, reg, val); @@ -164,6 +169,7 @@ static void encx24j600_cmd(struct encx24j600_priv *priv, u8 cmd) { struct net_device *dev = priv->ndev; int ret = regmap_write(priv->ctx.regmap, cmd, 0); + if (unlikely(ret)) netif_err(priv, drv, dev, "%s: error %d with cmd %02x\n", __func__, ret, cmd); @@ -173,6 +179,7 @@ static int encx24j600_raw_read(struct encx24j600_priv *priv, u8 reg, u8 *data, size_t count) { int ret; + mutex_lock(&priv->ctx.mutex); ret = regmap_encx24j600_spi_read(&priv->ctx, reg, data, count); mutex_unlock(&priv->ctx.mutex); @@ -184,6 +191,7 @@ static int encx24j600_raw_write(struct encx24j600_priv *priv, u8 reg, const u8 *data, size_t count) { int ret; + mutex_lock(&priv->ctx.mutex); ret = regmap_encx24j600_spi_write(&priv->ctx, reg, data, count); mutex_unlock(&priv->ctx.mutex); @@ -194,6 +202,7 @@ static int encx24j600_raw_write(struct encx24j600_priv *priv, u8 reg, static void encx24j600_update_phcon1(struct encx24j600_priv *priv) { u16 phcon1 = encx24j600_read_phy(priv, PHCON1); + if (priv->autoneg == AUTONEG_ENABLE) { phcon1 |= ANEN | RENEG; } else { @@ -328,6 +337,7 @@ static int encx24j600_receive_packet(struct encx24j600_priv *priv, { struct net_device *dev = priv->ndev; struct sk_buff *skb = netdev_alloc_skb(dev, rsv->len + NET_IP_ALIGN); + if (!skb) { pr_err_ratelimited("RX: OOM: packet dropped\n"); dev->stats.rx_dropped++; @@ -828,6 +838,7 @@ static void encx24j600_set_multicast_list(struct net_device *dev) static void encx24j600_hw_tx(struct encx24j600_priv *priv) { struct net_device *dev = priv->ndev; + netif_info(priv, tx_queued, dev, "TX Packet Len:%d\n", priv->tx_skb->len); @@ -895,7 +906,6 @@ static void encx24j600_tx_timeout(struct net_device *dev) dev->stats.tx_errors++; netif_wake_queue(dev); - return; } static int encx24j600_get_regs_len(struct net_device *dev) @@ -958,12 +968,14 @@ static int encx24j600_set_settings(struct net_device *dev, static u32 encx24j600_get_msglevel(struct net_device *dev) { struct encx24j600_priv *priv = netdev_priv(dev); + return priv->msg_enable; } static void encx24j600_set_msglevel(struct net_device *dev, u32 val) { struct encx24j600_priv *priv = netdev_priv(dev); + priv->msg_enable = val; } From 026acd5f47340382844f0af73516cf7ae6cdc876 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Tue, 13 Dec 2016 17:49:02 -0600 Subject: [PATCH 12/63] net: qcom/emac: don't try to claim clocks on ACPI systems On ACPI systems, clocks are not available to drivers directly. They are handled exclusively by ACPI and/or firmware, so there is no clock driver. Calls to clk_get() always fail, so we should not even attempt to claim any clocks on ACPI systems. Signed-off-by: Timur Tabi Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index ae32f855e31b..422289c232bc 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -460,6 +460,12 @@ static int emac_clks_phase1_init(struct platform_device *pdev, { int ret; + /* On ACPI platforms, clocks are controlled by firmware and/or + * ACPI, not by drivers. + */ + if (has_acpi_companion(&pdev->dev)) + return 0; + ret = emac_clks_get(pdev, adpt); if (ret) return ret; @@ -485,6 +491,9 @@ static int emac_clks_phase2_init(struct platform_device *pdev, { int ret; + if (has_acpi_companion(&pdev->dev)) + return 0; + ret = clk_set_rate(adpt->clk[EMAC_CLK_TX], 125000000); if (ret) return ret; From 94acf164dc8f1184e8d0737be7125134c2701dbe Mon Sep 17 00:00:00 2001 From: Thomas Falcon Date: Tue, 13 Dec 2016 18:15:09 -0600 Subject: [PATCH 13/63] ibmveth: calculate gso_segs for large packets Include calculations to compute the number of segments that comprise an aggregated large packet. Signed-off-by: Thomas Falcon Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Jonathan Maxwell Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmveth.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index fbece63395a8..a831f947ca8c 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1181,7 +1181,9 @@ static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt) { + struct tcphdr *tcph; int offset = 0; + int hdr_len; /* only TCP packets will be aggregated */ if (skb->protocol == htons(ETH_P_IP)) { @@ -1208,14 +1210,20 @@ static void ibmveth_rx_mss_helper(struct sk_buff *skb, u16 mss, int lrg_pkt) /* if mss is not set through Large Packet bit/mss in rx buffer, * expect that the mss will be written to the tcp header checksum. */ + tcph = (struct tcphdr *)(skb->data + offset); if (lrg_pkt) { skb_shinfo(skb)->gso_size = mss; } else if (offset) { - struct tcphdr *tcph = (struct tcphdr *)(skb->data + offset); - skb_shinfo(skb)->gso_size = ntohs(tcph->check); tcph->check = 0; } + + if (skb_shinfo(skb)->gso_size) { + hdr_len = offset + tcph->doff * 4; + skb_shinfo(skb)->gso_segs = + DIV_ROUND_UP(skb->len - hdr_len, + skb_shinfo(skb)->gso_size); + } } static int ibmveth_poll(struct napi_struct *napi, int budget) From 83a77e9ec4150ee4acc635638f7dedd9da523a26 Mon Sep 17 00:00:00 2001 From: Bartosz Folta Date: Wed, 14 Dec 2016 06:39:15 +0000 Subject: [PATCH 14/63] net: macb: Added PCI wrapper for Platform Driver. There are hardware PCI implementations of Cadence GEM network controller. This patch will allow to use such hardware with reuse of existing Platform Driver. Signed-off-by: Bartosz Folta Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/Kconfig | 9 ++ drivers/net/ethernet/cadence/Makefile | 1 + drivers/net/ethernet/cadence/macb.c | 31 ++++- drivers/net/ethernet/cadence/macb_pci.c | 153 ++++++++++++++++++++++++ include/linux/platform_data/macb.h | 6 + 5 files changed, 195 insertions(+), 5 deletions(-) create mode 100644 drivers/net/ethernet/cadence/macb_pci.c diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index f0bcb15d3fec..608bea171956 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -31,4 +31,13 @@ config MACB To compile this driver as a module, choose M here: the module will be called macb. +config MACB_PCI + tristate "Cadence PCI MACB/GEM support" + depends on MACB && PCI && COMMON_CLK + ---help--- + This is PCI wrapper for MACB driver. + + To compile this driver as a module, choose M here: the module + will be called macb_pci. + endif # NET_CADENCE diff --git a/drivers/net/ethernet/cadence/Makefile b/drivers/net/ethernet/cadence/Makefile index 91f79b1f0505..4ba75594d5c5 100644 --- a/drivers/net/ethernet/cadence/Makefile +++ b/drivers/net/ethernet/cadence/Makefile @@ -3,3 +3,4 @@ # obj-$(CONFIG_MACB) += macb.o +obj-$(CONFIG_MACB_PCI) += macb_pci.o diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 538544a7c642..c0fb80acc2da 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -404,6 +404,8 @@ static int macb_mii_probe(struct net_device *dev) phy_irq = gpio_to_irq(pdata->phy_irq_pin); phydev->irq = (phy_irq < 0) ? PHY_POLL : phy_irq; } + } else { + phydev->irq = PHY_POLL; } /* attach the mac to the phy */ @@ -482,6 +484,9 @@ static int macb_mii_init(struct macb *bp) goto err_out_unregister_bus; } } else { + for (i = 0; i < PHY_MAX_ADDR; i++) + bp->mii_bus->irq[i] = PHY_POLL; + if (pdata) bp->mii_bus->phy_mask = pdata->phy_mask; @@ -2523,16 +2528,24 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk, struct clk **hclk, struct clk **tx_clk, struct clk **rx_clk) { + struct macb_platform_data *pdata; int err; - *pclk = devm_clk_get(&pdev->dev, "pclk"); + pdata = dev_get_platdata(&pdev->dev); + if (pdata) { + *pclk = pdata->pclk; + *hclk = pdata->hclk; + } else { + *pclk = devm_clk_get(&pdev->dev, "pclk"); + *hclk = devm_clk_get(&pdev->dev, "hclk"); + } + if (IS_ERR(*pclk)) { err = PTR_ERR(*pclk); dev_err(&pdev->dev, "failed to get macb_clk (%u)\n", err); return err; } - *hclk = devm_clk_get(&pdev->dev, "hclk"); if (IS_ERR(*hclk)) { err = PTR_ERR(*hclk); dev_err(&pdev->dev, "failed to get hclk (%u)\n", err); @@ -3107,15 +3120,23 @@ static const struct of_device_id macb_dt_ids[] = { MODULE_DEVICE_TABLE(of, macb_dt_ids); #endif /* CONFIG_OF */ +static const struct macb_config default_gem_config = { + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO, + .dma_burst_length = 16, + .clk_init = macb_clk_init, + .init = macb_init, + .jumbo_max_len = 10240, +}; + static int macb_probe(struct platform_device *pdev) { + const struct macb_config *macb_config = &default_gem_config; int (*clk_init)(struct platform_device *, struct clk **, struct clk **, struct clk **, struct clk **) - = macb_clk_init; - int (*init)(struct platform_device *) = macb_init; + = macb_config->clk_init; + int (*init)(struct platform_device *) = macb_config->init; struct device_node *np = pdev->dev.of_node; struct device_node *phy_node; - const struct macb_config *macb_config = NULL; struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL; unsigned int queue_mask, num_queues; struct macb_platform_data *pdata; diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c new file mode 100644 index 000000000000..92be2cd8f817 --- /dev/null +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -0,0 +1,153 @@ +/** + * macb_pci.c - Cadence GEM PCI wrapper. + * + * Copyright (C) 2016 Cadence Design Systems - http://www.cadence.com + * + * Authors: Rafal Ozieblo + * Bartosz Folta + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 of + * the License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include +#include "macb.h" + +#define PCI_DRIVER_NAME "macb_pci" +#define PLAT_DRIVER_NAME "macb" + +#define CDNS_VENDOR_ID 0x17cd +#define CDNS_DEVICE_ID 0xe007 + +#define GEM_PCLK_RATE 50000000 +#define GEM_HCLK_RATE 50000000 + +static int macb_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + int err; + struct platform_device *plat_dev; + struct platform_device_info plat_info; + struct macb_platform_data plat_data; + struct resource res[2]; + + /* sanity check */ + if (!id) + return -EINVAL; + + /* enable pci device */ + err = pci_enable_device(pdev); + if (err < 0) { + dev_err(&pdev->dev, "Enabling PCI device has failed: 0x%04X", + err); + return -EACCES; + } + + pci_set_master(pdev); + + /* set up resources */ + memset(res, 0x00, sizeof(struct resource) * ARRAY_SIZE(res)); + res[0].start = pdev->resource[0].start; + res[0].end = pdev->resource[0].end; + res[0].name = PCI_DRIVER_NAME; + res[0].flags = IORESOURCE_MEM; + res[1].start = pdev->irq; + res[1].name = PCI_DRIVER_NAME; + res[1].flags = IORESOURCE_IRQ; + + dev_info(&pdev->dev, "EMAC physical base addr = 0x%p\n", + (void *)(uintptr_t)pci_resource_start(pdev, 0)); + + /* set up macb platform data */ + memset(&plat_data, 0, sizeof(plat_data)); + + /* initialize clocks */ + plat_data.pclk = clk_register_fixed_rate(&pdev->dev, "pclk", NULL, 0, + GEM_PCLK_RATE); + if (IS_ERR(plat_data.pclk)) { + err = PTR_ERR(plat_data.pclk); + goto err_pclk_register; + } + + plat_data.hclk = clk_register_fixed_rate(&pdev->dev, "hclk", NULL, 0, + GEM_HCLK_RATE); + if (IS_ERR(plat_data.hclk)) { + err = PTR_ERR(plat_data.hclk); + goto err_hclk_register; + } + + /* set up platform device info */ + memset(&plat_info, 0, sizeof(plat_info)); + plat_info.parent = &pdev->dev; + plat_info.fwnode = pdev->dev.fwnode; + plat_info.name = PLAT_DRIVER_NAME; + plat_info.id = pdev->devfn; + plat_info.res = res; + plat_info.num_res = ARRAY_SIZE(res); + plat_info.data = &plat_data; + plat_info.size_data = sizeof(plat_data); + plat_info.dma_mask = DMA_BIT_MASK(32); + + /* register platform device */ + plat_dev = platform_device_register_full(&plat_info); + if (IS_ERR(plat_dev)) { + err = PTR_ERR(plat_dev); + goto err_plat_dev_register; + } + + pci_set_drvdata(pdev, plat_dev); + + return 0; + +err_plat_dev_register: + clk_unregister(plat_data.hclk); + +err_hclk_register: + clk_unregister(plat_data.pclk); + +err_pclk_register: + pci_disable_device(pdev); + return err; +} + +static void macb_remove(struct pci_dev *pdev) +{ + struct platform_device *plat_dev = pci_get_drvdata(pdev); + struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev); + + platform_device_unregister(plat_dev); + pci_disable_device(pdev); + clk_unregister(plat_data->pclk); + clk_unregister(plat_data->hclk); +} + +static struct pci_device_id dev_id_table[] = { + { PCI_DEVICE(CDNS_VENDOR_ID, CDNS_DEVICE_ID), }, + { 0, } +}; + +static struct pci_driver macb_pci_driver = { + .name = PCI_DRIVER_NAME, + .id_table = dev_id_table, + .probe = macb_probe, + .remove = macb_remove, +}; + +module_pci_driver(macb_pci_driver); +MODULE_DEVICE_TABLE(pci, dev_id_table); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence NIC PCI wrapper"); diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h index 21b15f6fee25..7815d50c26ff 100644 --- a/include/linux/platform_data/macb.h +++ b/include/linux/platform_data/macb.h @@ -8,6 +8,8 @@ #ifndef __MACB_PDATA_H__ #define __MACB_PDATA_H__ +#include + /** * struct macb_platform_data - platform data for MACB Ethernet * @phy_mask: phy mask passed when register the MDIO bus @@ -15,12 +17,16 @@ * @phy_irq_pin: PHY IRQ * @is_rmii: using RMII interface? * @rev_eth_addr: reverse Ethernet address byte order + * @pclk: platform clock + * @hclk: AHB clock */ struct macb_platform_data { u32 phy_mask; int phy_irq_pin; u8 is_rmii; u8 rev_eth_addr; + struct clk *pclk; + struct clk *hclk; }; #endif /* __MACB_PDATA_H__ */ From 970bfcd09791282de7de6589bfe440eb11e2efd2 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 14 Dec 2016 19:00:57 +0200 Subject: [PATCH 15/63] net/sched: cls_flower: Use mask for addr_type When addr_type is set, mask should also be set. Fixes: 66530bdf85eb ('sched,cls_flower: set key address type when present') Fixes: bc3103f1ed40 ('net/sched: cls_flower: Classify packet in ip tunnels') Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index e040c5140f61..9758f5adbc2a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -509,6 +509,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) { key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + mask->control.addr_type = ~0; fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC, &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK, sizeof(key->ipv4.src)); @@ -517,6 +518,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, sizeof(key->ipv4.dst)); } else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) { key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + mask->control.addr_type = ~0; fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC, &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK, sizeof(key->ipv6.src)); @@ -571,6 +573,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (tb[TCA_FLOWER_KEY_ENC_IPV4_SRC] || tb[TCA_FLOWER_KEY_ENC_IPV4_DST]) { key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + mask->enc_control.addr_type = ~0; fl_set_key_val(tb, &key->enc_ipv4.src, TCA_FLOWER_KEY_ENC_IPV4_SRC, &mask->enc_ipv4.src, @@ -586,6 +589,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (tb[TCA_FLOWER_KEY_ENC_IPV6_SRC] || tb[TCA_FLOWER_KEY_ENC_IPV6_DST]) { key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + mask->enc_control.addr_type = ~0; fl_set_key_val(tb, &key->enc_ipv6.src, TCA_FLOWER_KEY_ENC_IPV6_SRC, &mask->enc_ipv6.src, From f93bd17b916959fc20fbb7dc578e1f2657a8c343 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 14 Dec 2016 19:00:58 +0200 Subject: [PATCH 16/63] net/sched: cls_flower: Use masked key when calling HW offloads Zero bits on the mask signify a "don't care" on the corresponding bits in key. Some HWs require those bits on the key to be zero. Since these bits are masked anyway, it's okay to provide the masked key to all drivers. Fixes: 5b33f48842fa ('net/flower: Introduce hardware offload support') Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9758f5adbc2a..35ac28d0720c 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -252,7 +252,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, offload.cookie = (unsigned long)f; offload.dissector = dissector; offload.mask = mask; - offload.key = &f->key; + offload.key = &f->mkey; offload.exts = &f->exts; tc->type = TC_SETUP_CLSFLOWER; From a0f37efa82253994b99623dbf41eea8dd0ba169b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 14 Dec 2016 11:06:18 -0800 Subject: [PATCH 17/63] net: vrf: Fix NAT within a VRF Connection tracking with VRF is broken because the pass through the VRF device drops the connection tracking info. Removing the call to nf_reset allows DNAT and MASQUERADE to work across interfaces within a VRF. Fixes: 73e20b761acf ("net: vrf: Add support for PREROUTING rules on vrf device") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 3bca24651dc0..015a1321c7dd 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -849,8 +849,6 @@ static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook, { struct net *net = dev_net(dev); - nf_reset(skb); - if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0) skb = NULL; /* kfree_skb(skb) handled by nf code */ From eb63ecc1706b3e094d0f57438b6c2067cfc299f2 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 14 Dec 2016 14:31:11 -0800 Subject: [PATCH 18/63] net: vrf: Drop conntrack data after pass through VRF device on Tx Locally originated traffic in a VRF fails in the presence of a POSTROUTING rule. For example, $ iptables -t nat -A POSTROUTING -s 11.1.1.0/24 -j MASQUERADE $ ping -I red -c1 11.1.1.3 ping: Warning: source address might be selected on device other than red. PING 11.1.1.3 (11.1.1.3) from 11.1.1.2 red: 56(84) bytes of data. ping: sendmsg: Operation not permitted Worse, the above causes random corruption resulting in a panic in random places (I have not seen a consistent backtrace). Call nf_reset to drop the conntrack info following the pass through the VRF device. The nf_reset is needed on Tx but not Rx because of the order in which NF_HOOK's are hit: on Rx the VRF device is after the real ingress device and on Tx it is is before the real egress device. Connection tracking should be tied to the real egress device and not the VRF device. Fixes: 8f58336d3f78a ("net: Add ethernet header for pass through VRF device") Fixes: 35402e3136634 ("net: Add IPv6 support to VRF device") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- drivers/net/vrf.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 015a1321c7dd..7532646c3b7b 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -366,6 +366,8 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, struct in6_addr *nexthop; int ret; + nf_reset(skb); + skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -547,6 +549,8 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s u32 nexthop; int ret = -EINVAL; + nf_reset(skb); + /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { struct sk_buff *skb2; From a08dd0da5307ba01295c8383923e51e7997c3576 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 15 Dec 2016 01:30:06 +0100 Subject: [PATCH 19/63] bpf: fix regression on verifier pruning wrt map lookups Commit 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") introduced a regression where existing programs stopped loading due to reaching the verifier's maximum complexity limit, whereas prior to this commit they were loading just fine; the affected program has roughly 2k instructions. What was found is that state pruning couldn't be performed effectively anymore due to mismatches of the verifier's register state, in particular in the id tracking. It doesn't mean that 57a09bf0a416 is incorrect per se, but rather that verifier needs to perform a lot more work for the same program with regards to involved map lookups. Since commit 57a09bf0a416 is only about tracking registers with type PTR_TO_MAP_VALUE_OR_NULL, the id is only needed to follow registers until they are promoted through pattern matching with a NULL check to either PTR_TO_MAP_VALUE or UNKNOWN_VALUE type. After that point, the id becomes irrelevant for the transitioned types. For UNKNOWN_VALUE, id is already reset to 0 via mark_reg_unknown_value(), but not so for PTR_TO_MAP_VALUE where id is becoming stale. It's even transferred further into other types that don't make use of it. Among others, one example is where UNKNOWN_VALUE is set on function call return with RET_INTEGER return type. states_equal() will then fall through the memcmp() on register state; note that the second memcmp() uses offsetofend(), so the id is part of that since d2a4dd37f6b4 ("bpf: fix state equivalence"). But the bisect pointed already to 57a09bf0a416, where we really reach beyond complexity limit. What I found was that states_equal() often failed in this case due to id mismatches in spilled regs with registers in type PTR_TO_MAP_VALUE. Unlike non-spilled regs, spilled regs just perform a memcmp() on their reg state and don't have any other optimizations in place, therefore also id was relevant in this case for making a pruning decision. We can safely reset id to 0 as well when converting to PTR_TO_MAP_VALUE. For the affected program, it resulted in a ~17 fold reduction of complexity and let the program load fine again. Selftest suite also runs fine. The only other place where env->id_gen is used currently is through direct packet access, but for these cases id is long living, thus a different scenario. Also, the current logic in mark_map_regs() is not fully correct when marking NULL branch with UNKNOWN_VALUE. We need to cache the destination reg's id in any case. Otherwise, once we marked that reg as UNKNOWN_VALUE, it's id is reset and any subsequent registers that hold the original id and are of type PTR_TO_MAP_VALUE_OR_NULL won't be marked UNKNOWN_VALUE anymore, since mark_map_reg() reuses the uncached regs[regno].id that was just overridden. Note, we don't need to cache it outside of mark_map_regs(), since it's called once on this_branch and the other time on other_branch, which are both two independent verifier states. A test case for this is added here, too. Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") Signed-off-by: Daniel Borkmann Acked-by: Thomas Graf Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 11 +++++--- tools/testing/selftests/bpf/test_verifier.c | 28 +++++++++++++++++++++ 2 files changed, 36 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d28f9a3380a9..81e267bc4640 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1970,6 +1970,11 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) { reg->type = type; + /* We don't need id from this point onwards anymore, thus we + * should better reset it, so that state pruning has chances + * to take effect. + */ + reg->id = 0; if (type == UNKNOWN_VALUE) mark_reg_unknown_value(regs, regno); } @@ -1982,16 +1987,16 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno, enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs; + u32 id = regs[regno].id; int i; for (i = 0; i < MAX_BPF_REG; i++) - mark_map_reg(regs, i, regs[regno].id, type); + mark_map_reg(regs, i, id, type); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; - mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, - regs[regno].id, type); + mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, type); } } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 0103bf2e0c0d..072dc63dc957 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -2660,6 +2660,34 @@ static struct bpf_test tests[] = { .result = ACCEPT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, + { + "multiple registers share map_lookup_elem bad reg type", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_1, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 0), + BPF_MOV64_IMM(BPF_REG_1, 3), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .result = REJECT, + .errstr = "R3 invalid mem access 'inv'", + .prog_type = BPF_PROG_TYPE_SCHED_CLS + }, { "invalid map access from else condition", .insns = { From 0eb6984f70005e792917d9e51142a57f79b32c91 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 15 Dec 2016 01:39:10 +0100 Subject: [PATCH 20/63] bpf, test_verifier: fix a test case error result on unprivileged Running ./test_verifier as unprivileged lets 1 out of 98 tests fail: [...] #71 unpriv: check that printk is disallowed FAIL Unexpected error message! 0: (7a) *(u64 *)(r10 -8) = 0 1: (bf) r1 = r10 2: (07) r1 += -8 3: (b7) r2 = 8 4: (bf) r3 = r1 5: (85) call bpf_trace_printk#6 unknown func bpf_trace_printk#6 [...] The test case is correct, just that the error outcome changed with ebb676daa1a3 ("bpf: Print function name in addition to function id"). Same as with e00c7b216f34 ("bpf: fix multiple issues in selftest suite and samples") issue 2), so just fix up the function name. Fixes: ebb676daa1a3 ("bpf: Print function name in addition to function id") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- tools/testing/selftests/bpf/test_verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 072dc63dc957..853d7e43434a 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1059,7 +1059,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "unknown func 6", + .errstr_unpriv = "unknown func bpf_trace_printk#6", .result_unpriv = REJECT, .result = ACCEPT, }, From 9af7e923fdd82dc25ad5ea75e24e92708947f961 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 14 Dec 2016 16:54:15 -0800 Subject: [PATCH 21/63] inet: Don't go into port scan when looking for specific bind port inet_csk_get_port is called with port number (snum argument) that may be zero or nonzero. If it is zero, then the intent is to find an available ephemeral port number to bind to. If snum is non-zero then the caller is asking to allocate a specific port number. In the latter case we never want to perform the scan in ephemeral port range. It is conceivable that this can happen if the "goto again" in "tb_found:" is done. This patch adds a check that snum is zero before doing the "goto again". Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/inet_connection_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d5d3ead0a6c3..f59838a60ea5 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -212,7 +212,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) sk->sk_reuseport && !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(tb->fastuid, uid))) && - smallest_size != -1 && --attempts >= 0) { + !snum && smallest_size != -1 && --attempts >= 0) { spin_unlock_bh(&head->lock); goto again; } From 0643ee4fd1b79c1af3bd7bc8968dbf5fd047f490 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 14 Dec 2016 16:54:16 -0800 Subject: [PATCH 22/63] inet: Fix get port to handle zero port number with soreuseport set A user may call listen with binding an explicit port with the intent that the kernel will assign an available port to the socket. In this case inet_csk_get_port does a port scan. For such sockets, the user may also set soreuseport with the intent a creating more sockets for the port that is selected. The problem is that the initial socket being opened could inadvertently choose an existing and unreleated port number that was already created with soreuseport. This patch adds a boolean parameter to inet_bind_conflict that indicates rather soreuseport is allowed for the check (in addition to sk->sk_reuseport). In calls to inet_bind_conflict from inet_csk_get_port the argument is set to true if an explicit port is being looked up (snum argument is nonzero), and is false if port scan is done. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 3 ++- include/net/inet_connection_sock.h | 6 ++++-- net/ipv4/inet_connection_sock.c | 14 +++++++++----- net/ipv6/inet6_connection_sock.c | 7 ++++--- 4 files changed, 19 insertions(+), 11 deletions(-) diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 954ad6bfb56a..3212b39b5bfc 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -22,7 +22,8 @@ struct sock; struct sockaddr; int inet6_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax); + const struct inet_bind_bucket *tb, bool relax, + bool soreuseport_ok); struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, const struct request_sock *req, u8 proto); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 146054ceea8e..85ee3879499e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -63,7 +63,8 @@ struct inet_connection_sock_af_ops { #endif void (*addr2sockaddr)(struct sock *sk, struct sockaddr *); int (*bind_conflict)(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax); + const struct inet_bind_bucket *tb, + bool relax, bool soreuseport_ok); void (*mtu_reduced)(struct sock *sk); }; @@ -261,7 +262,8 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); int inet_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax); + const struct inet_bind_bucket *tb, bool relax, + bool soreuseport_ok); int inet_csk_get_port(struct sock *sk, unsigned short snum); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f59838a60ea5..19ea045c50ed 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -45,11 +45,12 @@ void inet_get_local_port_range(struct net *net, int *low, int *high) EXPORT_SYMBOL(inet_get_local_port_range); int inet_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax) + const struct inet_bind_bucket *tb, bool relax, + bool reuseport_ok) { struct sock *sk2; - int reuse = sk->sk_reuse; - int reuseport = sk->sk_reuseport; + bool reuse = sk->sk_reuse; + bool reuseport = !!sk->sk_reuseport && reuseport_ok; kuid_t uid = sock_i_uid((struct sock *)sk); /* @@ -105,6 +106,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct inet_bind_bucket *tb; kuid_t uid = sock_i_uid(sk); u32 remaining, offset; + bool reuseport_ok = !!snum; if (port) { have_port: @@ -165,7 +167,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) smallest_size = tb->num_owners; smallest_port = port; } - if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false)) + if (!inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, false, + reuseport_ok)) goto tb_found; goto next_port; } @@ -206,7 +209,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size == -1) goto success; - if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { + if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true, + reuseport_ok)) { if ((reuse || (tb->fastreuseport > 0 && sk->sk_reuseport && diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 1c86c478f578..7396e75e161b 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -29,11 +29,12 @@ #include int inet6_csk_bind_conflict(const struct sock *sk, - const struct inet_bind_bucket *tb, bool relax) + const struct inet_bind_bucket *tb, bool relax, + bool reuseport_ok) { const struct sock *sk2; - int reuse = sk->sk_reuse; - int reuseport = sk->sk_reuseport; + bool reuse = !!sk->sk_reuse; + bool reuseport = !!sk->sk_reuseport && reuseport_ok; kuid_t uid = sock_i_uid((struct sock *)sk); /* We must walk the whole port owner list in this case. -DaveM */ From dcdc43d6642c828fa10d25130a92b712003d2ca4 Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Thu, 15 Dec 2016 10:53:21 +0100 Subject: [PATCH 23/63] bpf: cgroup: annotate pointers in struct cgroup_bpf with __rcu The member 'effective' in 'struct cgroup_bpf' is protected by RCU. Annotate it accordingly to squelch a sparse warning. Signed-off-by: Daniel Mack Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 7b6e5d168c95..92bc89ae7e20 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -20,7 +20,7 @@ struct cgroup_bpf { * when this cgroup is accessed. */ struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog *effective[MAX_BPF_ATTACH_TYPE]; + struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; }; void cgroup_bpf_put(struct cgroup *cgrp); From 078497a4d9535026b137c08e3746e600d5669a05 Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 15 Dec 2016 11:42:46 +0100 Subject: [PATCH 24/63] irda: irproc.c: Remove unneeded linux/miscdevice.h include irproc.c does not use any miscdevice so this patch remove this unnecessary inclusion. Signed-off-by: Corentin Labbe Signed-off-by: David S. Miller --- net/irda/irproc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/irda/irproc.c b/net/irda/irproc.c index b9ac598e2116..77cfdde9d82f 100644 --- a/net/irda/irproc.c +++ b/net/irda/irproc.c @@ -23,7 +23,6 @@ * ********************************************************************/ -#include #include #include #include From e292823559709b09cd9bf7bd112bd13c93daa146 Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 15 Dec 2016 11:42:47 +0100 Subject: [PATCH 25/63] irda: irnet: Move linux/miscdevice.h include The only use of miscdevice is irda_ppp so no need to include linux/miscdevice.h for all irda files. This patch move the linux/miscdevice.h include to irnet_ppp.h Signed-off-by: Corentin Labbe Signed-off-by: David S. Miller --- net/irda/irnet/irnet.h | 1 - net/irda/irnet/irnet_ppp.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index 8d65bb9477fc..c69f0f38f566 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -245,7 +245,6 @@ #include #include #include -#include #include #include #include /* isspace() */ diff --git a/net/irda/irnet/irnet_ppp.h b/net/irda/irnet/irnet_ppp.h index 940225866da0..693ebc08fa2e 100644 --- a/net/irda/irnet/irnet_ppp.h +++ b/net/irda/irnet/irnet_ppp.h @@ -15,6 +15,7 @@ /***************************** INCLUDES *****************************/ #include "irnet.h" /* Module global include */ +#include /************************ CONSTANTS & MACROS ************************/ From 24c946cc5d35e32c5bb0c07ebdad32756e2bd20d Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 15 Dec 2016 11:42:48 +0100 Subject: [PATCH 26/63] irnet: ppp: move IRNET_MINOR to include/linux/miscdevice.h This patch move the define for IRNET_MINOR to include/linux/miscdevice.h It is better that all minor number definitions are in the same place. Signed-off-by: Corentin Labbe Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/linux/miscdevice.h | 1 + net/irda/irnet/irnet_ppp.h | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 722698a43d79..86d5704c9e23 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -32,6 +32,7 @@ #define STORE_QUEUE_MINOR 155 /* unused */ #define I2O_MINOR 166 #define MICROCODE_MINOR 184 +#define IRNET_MINOR 187 #define VFIO_MINOR 196 #define TUN_MINOR 200 #define CUSE_MINOR 203 diff --git a/net/irda/irnet/irnet_ppp.h b/net/irda/irnet/irnet_ppp.h index 693ebc08fa2e..18fceadbb4bf 100644 --- a/net/irda/irnet/irnet_ppp.h +++ b/net/irda/irnet/irnet_ppp.h @@ -21,7 +21,6 @@ /* /dev/irnet file constants */ #define IRNET_MAJOR 10 /* Misc range */ -#define IRNET_MINOR 187 /* Official allocation */ /* IrNET control channel stuff */ #define IRNET_MAX_COMMAND 256 /* Max length of a command line */ From 33de4d1bb9e3d90e2238e85d7865ec664cf48e60 Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 15 Dec 2016 11:42:49 +0100 Subject: [PATCH 27/63] irda: irnet: Remove unused IRNET_MAJOR define The IRNET_MAJOR define is not used, so this patch remove it. Signed-off-by: Corentin Labbe Signed-off-by: David S. Miller --- net/irda/irnet/irnet_ppp.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/irda/irnet/irnet_ppp.h b/net/irda/irnet/irnet_ppp.h index 18fceadbb4bf..ec092c9bdf3c 100644 --- a/net/irda/irnet/irnet_ppp.h +++ b/net/irda/irnet/irnet_ppp.h @@ -19,9 +19,6 @@ /************************ CONSTANTS & MACROS ************************/ -/* /dev/irnet file constants */ -#define IRNET_MAJOR 10 /* Misc range */ - /* IrNET control channel stuff */ #define IRNET_MAX_COMMAND 256 /* Max length of a command line */ From 616f6b40236fb9fdfc5267e2e945e16b7448b641 Mon Sep 17 00:00:00 2001 From: LABBE Corentin Date: Thu, 15 Dec 2016 11:42:50 +0100 Subject: [PATCH 28/63] irda: irnet: add member name to the miscdevice declaration Since the struct miscdevice have many members, it is dangerous to init it without members name relying only on member order. This patch add member name to the init declaration. Signed-off-by: Corentin Labbe Signed-off-by: David S. Miller --- net/irda/irnet/irnet_ppp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/irda/irnet/irnet_ppp.h b/net/irda/irnet/irnet_ppp.h index ec092c9bdf3c..32061442cc8e 100644 --- a/net/irda/irnet/irnet_ppp.h +++ b/net/irda/irnet/irnet_ppp.h @@ -108,9 +108,9 @@ static const struct file_operations irnet_device_fops = /* Structure so that the misc major (drivers/char/misc.c) take care of us... */ static struct miscdevice irnet_misc_device = { - IRNET_MINOR, - "irnet", - &irnet_device_fops + .minor = IRNET_MINOR, + .name = "irnet", + .fops = &irnet_device_fops }; #endif /* IRNET_PPP_H */ From 7d6f8dc0b2180ed60aea65660b35d7618ff6e4ee Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Thu, 15 Dec 2016 15:13:04 +0200 Subject: [PATCH 29/63] dpaa_eth: use big endian accessors Ensure correct access to the big endian QMan HW through proper accessors. Signed-off-by: Claudiu Manoil Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- .../net/ethernet/freescale/dpaa/dpaa_eth.c | 71 ++++++++++--------- 1 file changed, 37 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 3c48a84dec86..624ba9058dc4 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -733,7 +733,7 @@ static int dpaa_eth_cgr_init(struct dpaa_priv *priv) priv->cgr_data.cgr.cb = dpaa_eth_cgscn; /* Enable Congestion State Change Notifications and CS taildrop */ - initcgr.we_mask = QM_CGR_WE_CSCN_EN | QM_CGR_WE_CS_THRES; + initcgr.we_mask = cpu_to_be16(QM_CGR_WE_CSCN_EN | QM_CGR_WE_CS_THRES); initcgr.cgr.cscn_en = QM_CGR_EN; /* Set different thresholds based on the MAC speed. @@ -747,7 +747,7 @@ static int dpaa_eth_cgr_init(struct dpaa_priv *priv) cs_th = DPAA_CS_THRESHOLD_1G; qm_cgr_cs_thres_set64(&initcgr.cgr.cs_thres, cs_th, 1); - initcgr.we_mask |= QM_CGR_WE_CSTD_EN; + initcgr.we_mask |= cpu_to_be16(QM_CGR_WE_CSTD_EN); initcgr.cgr.cstd_en = QM_CGR_EN; err = qman_create_cgr(&priv->cgr_data.cgr, QMAN_CGR_FLAG_USE_INIT, @@ -896,18 +896,18 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) if (dpaa_fq->init) { memset(&initfq, 0, sizeof(initfq)); - initfq.we_mask = QM_INITFQ_WE_FQCTRL; + initfq.we_mask = cpu_to_be16(QM_INITFQ_WE_FQCTRL); /* Note: we may get to keep an empty FQ in cache */ - initfq.fqd.fq_ctrl = QM_FQCTRL_PREFERINCACHE; + initfq.fqd.fq_ctrl = cpu_to_be16(QM_FQCTRL_PREFERINCACHE); /* Try to reduce the number of portal interrupts for * Tx Confirmation FQs. */ if (dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM) - initfq.fqd.fq_ctrl |= QM_FQCTRL_HOLDACTIVE; + initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE); /* FQ placement */ - initfq.we_mask |= QM_INITFQ_WE_DESTWQ; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_DESTWQ); qm_fqd_set_destwq(&initfq.fqd, dpaa_fq->channel, dpaa_fq->wq); @@ -920,8 +920,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) if (dpaa_fq->fq_type == FQ_TYPE_TX || dpaa_fq->fq_type == FQ_TYPE_TX_CONFIRM || dpaa_fq->fq_type == FQ_TYPE_TX_CONF_MQ) { - initfq.we_mask |= QM_INITFQ_WE_CGID; - initfq.fqd.fq_ctrl |= QM_FQCTRL_CGE; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CGID); + initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_CGE); initfq.fqd.cgid = (u8)priv->cgr_data.cgr.cgrid; /* Set a fixed overhead accounting, in an attempt to * reduce the impact of fixed-size skb shells and the @@ -932,7 +932,7 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) * insufficient value, but even that is better than * no overhead accounting at all. */ - initfq.we_mask |= QM_INITFQ_WE_OAC; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_OAC); qm_fqd_set_oac(&initfq.fqd, QM_OAC_CG); qm_fqd_set_oal(&initfq.fqd, min(sizeof(struct sk_buff) + @@ -941,9 +941,9 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) } if (td_enable) { - initfq.we_mask |= QM_INITFQ_WE_TDTHRESH; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_TDTHRESH); qm_fqd_set_taildrop(&initfq.fqd, DPAA_FQ_TD, 1); - initfq.fqd.fq_ctrl = QM_FQCTRL_TDE; + initfq.fqd.fq_ctrl = cpu_to_be16(QM_FQCTRL_TDE); } if (dpaa_fq->fq_type == FQ_TYPE_TX) { @@ -951,7 +951,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) if (queue_id >= 0) confq = priv->conf_fqs[queue_id]; if (confq) { - initfq.we_mask |= QM_INITFQ_WE_CONTEXTA; + initfq.we_mask |= + cpu_to_be16(QM_INITFQ_WE_CONTEXTA); /* ContextA: OVOM=1(use contextA2 bits instead of ICAD) * A2V=1 (contextA A2 field is valid) * A0V=1 (contextA A0 field is valid) @@ -959,8 +960,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) * ContextA A2: EBD=1 (deallocate buffers inside FMan) * ContextB B0(ASPID): 0 (absolute Virtual Storage ID) */ - initfq.fqd.context_a.hi = 0x1e000000; - initfq.fqd.context_a.lo = 0x80000000; + qm_fqd_context_a_set64(&initfq.fqd, + 0x1e00000080000000ULL); } } @@ -968,13 +969,13 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) if (priv->use_ingress_cgr && (dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT || dpaa_fq->fq_type == FQ_TYPE_RX_ERROR)) { - initfq.we_mask |= QM_INITFQ_WE_CGID; - initfq.fqd.fq_ctrl |= QM_FQCTRL_CGE; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CGID); + initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_CGE); initfq.fqd.cgid = (u8)priv->ingress_cgr.cgrid; /* Set a fixed overhead accounting, just like for the * egress CGR. */ - initfq.we_mask |= QM_INITFQ_WE_OAC; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_OAC); qm_fqd_set_oac(&initfq.fqd, QM_OAC_CG); qm_fqd_set_oal(&initfq.fqd, min(sizeof(struct sk_buff) + @@ -984,9 +985,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) /* Initialization common to all ingress queues */ if (dpaa_fq->flags & QMAN_FQ_FLAG_NO_ENQUEUE) { - initfq.we_mask |= QM_INITFQ_WE_CONTEXTA; - initfq.fqd.fq_ctrl |= - QM_FQCTRL_HOLDACTIVE; + initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CONTEXTA); + initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_HOLDACTIVE); initfq.fqd.context_a.stashing.exclusive = QM_STASHING_EXCL_DATA | QM_STASHING_EXCL_CTX | QM_STASHING_EXCL_ANNOTATION; @@ -1350,7 +1350,7 @@ static int dpaa_enable_tx_csum(struct dpaa_priv *priv, parse_result->l4_off = (u8)skb_transport_offset(skb); /* Enable L3 (and L4, if TCP or UDP) HW checksum. */ - fd->cmd |= FM_FD_CMD_RPD | FM_FD_CMD_DTC; + fd->cmd |= cpu_to_be32(FM_FD_CMD_RPD | FM_FD_CMD_DTC); /* On P1023 and similar platforms fd->cmd interpretation could * be disabled by setting CONTEXT_A bit ICMD; currently this bit @@ -1732,7 +1732,7 @@ static int skb_to_contig_fd(struct dpaa_priv *priv, /* Fill in the rest of the FD fields */ qm_fd_set_contig(fd, priv->tx_headroom, skb->len); - fd->cmd |= FM_FD_CMD_FCO; + fd->cmd |= cpu_to_be32(FM_FD_CMD_FCO); /* Map the entire buffer size that may be seen by FMan, but no more */ addr = dma_map_single(dev, skbh, @@ -1840,7 +1840,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, } fd->bpid = FSL_DPAA_BPID_INV; - fd->cmd |= FM_FD_CMD_FCO; + fd->cmd |= cpu_to_be32(FM_FD_CMD_FCO); qm_fd_addr_set64(fd, addr); return 0; @@ -1867,7 +1867,7 @@ static inline int dpaa_xmit(struct dpaa_priv *priv, egress_fq = priv->egress_fqs[queue]; if (fd->bpid == FSL_DPAA_BPID_INV) - fd->cmd |= qman_fq_fqid(priv->conf_fqs[queue]); + fd->cmd |= cpu_to_be32(qman_fq_fqid(priv->conf_fqs[queue])); /* Trace this Tx fd */ trace_dpaa_tx_fd(priv->net_dev, egress_fq, fd); @@ -1960,17 +1960,17 @@ static void dpaa_rx_error(struct net_device *net_dev, { if (net_ratelimit()) netif_err(priv, hw, net_dev, "Err FD status = 0x%08x\n", - fd->status & FM_FD_STAT_RX_ERRORS); + be32_to_cpu(fd->status) & FM_FD_STAT_RX_ERRORS); percpu_priv->stats.rx_errors++; - if (fd->status & FM_FD_ERR_DMA) + if (be32_to_cpu(fd->status) & FM_FD_ERR_DMA) percpu_priv->rx_errors.dme++; - if (fd->status & FM_FD_ERR_PHYSICAL) + if (be32_to_cpu(fd->status) & FM_FD_ERR_PHYSICAL) percpu_priv->rx_errors.fpe++; - if (fd->status & FM_FD_ERR_SIZE) + if (be32_to_cpu(fd->status) & FM_FD_ERR_SIZE) percpu_priv->rx_errors.fse++; - if (fd->status & FM_FD_ERR_PRS_HDR_ERR) + if (be32_to_cpu(fd->status) & FM_FD_ERR_PRS_HDR_ERR) percpu_priv->rx_errors.phe++; dpaa_fd_release(net_dev, fd); @@ -1986,7 +1986,7 @@ static void dpaa_tx_error(struct net_device *net_dev, if (net_ratelimit()) netif_warn(priv, hw, net_dev, "FD status = 0x%08x\n", - fd->status & FM_FD_STAT_TX_ERRORS); + be32_to_cpu(fd->status) & FM_FD_STAT_TX_ERRORS); percpu_priv->stats.tx_errors++; @@ -2020,10 +2020,11 @@ static void dpaa_tx_conf(struct net_device *net_dev, { struct sk_buff *skb; - if (unlikely(fd->status & FM_FD_STAT_TX_ERRORS) != 0) { + if (unlikely(be32_to_cpu(fd->status) & FM_FD_STAT_TX_ERRORS)) { if (net_ratelimit()) netif_warn(priv, hw, net_dev, "FD status = 0x%08x\n", - fd->status & FM_FD_STAT_TX_ERRORS); + be32_to_cpu(fd->status) & + FM_FD_STAT_TX_ERRORS); percpu_priv->stats.tx_errors++; } @@ -2100,6 +2101,8 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, struct sk_buff *skb; int *count_ptr; + fd_status = be32_to_cpu(fd->status); + fd_format = qm_fd_get_format(fd); net_dev = ((struct dpaa_fq *)fq)->net_dev; priv = netdev_priv(net_dev); dpaa_bp = dpaa_bpid2pool(dq->fd.bpid); @@ -2417,12 +2420,12 @@ static int dpaa_ingress_cgr_init(struct dpaa_priv *priv) } /* Enable CS TD, but disable Congestion State Change Notifications. */ - initcgr.we_mask = QM_CGR_WE_CS_THRES; + initcgr.we_mask = cpu_to_be16(QM_CGR_WE_CS_THRES); initcgr.cgr.cscn_en = QM_CGR_EN; cs_th = DPAA_INGRESS_CS_THRESHOLD; qm_cgr_cs_thres_set64(&initcgr.cgr.cs_thres, cs_th, 1); - initcgr.we_mask |= QM_CGR_WE_CSTD_EN; + initcgr.we_mask |= cpu_to_be16(QM_CGR_WE_CSTD_EN); initcgr.cgr.cstd_en = QM_CGR_EN; /* This CGR will be associated with the SWP affined to the current CPU. From 708f0f4f9cec143403f8575493bea62a692b4ca2 Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Thu, 15 Dec 2016 15:13:05 +0200 Subject: [PATCH 30/63] dpaa_eth: remove redundant dependency on FSL_SOC Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/dpaa/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig index f3a3454805f9..a654736237a9 100644 --- a/drivers/net/ethernet/freescale/dpaa/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa/Kconfig @@ -1,6 +1,6 @@ menuconfig FSL_DPAA_ETH tristate "DPAA Ethernet" - depends on FSL_SOC && FSL_DPAA && FSL_FMAN + depends on FSL_DPAA && FSL_FMAN select PHYLIB select FSL_FMAN_MAC ---help--- From 63f4b4b0348b494c0fcfa1c41e7da865108dcaab Mon Sep 17 00:00:00 2001 From: Madalin Bucur Date: Thu, 15 Dec 2016 15:13:06 +0200 Subject: [PATCH 31/63] MAINTAINERS: net: add entry for Freescale QorIQ DPAA Ethernet driver Add record for Freescale QORIQ DPAA Ethernet driver adding myself as maintainer. Signed-off-by: Madalin Bucur Signed-off-by: David S. Miller --- MAINTAINERS | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index e2463baf33e5..0ff9757e524a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5058,6 +5058,12 @@ S: Maintained F: drivers/net/ethernet/freescale/fman F: Documentation/devicetree/bindings/powerpc/fsl/fman.txt +FREESCALE QORIQ DPAA ETHERNET DRIVER +M: Madalin Bucur +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/freescale/dpaa + FREESCALE QUICC ENGINE LIBRARY L: linuxppc-dev@lists.ozlabs.org S: Orphan From 5cb2cd68ddf9a13af36cec633006c0f2bdfb300a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 15 Dec 2016 23:00:55 +0800 Subject: [PATCH 32/63] sctp: sctp_epaddr_lookup_transport should be protected by rcu_read_lock Since commit 7fda702f9315 ("sctp: use new rhlist interface on sctp transport rhashtable"), sctp has changed to use rhlist_lookup to look up transport, but rhlist_lookup doesn't call rcu_read_lock inside, unlike rhashtable_lookup_fast. It is called in sctp_epaddr_lookup_transport and sctp_addrs_lookup_transport. sctp_addrs_lookup_transport is always in the protection of rcu_read_lock(), as __sctp_lookup_association is called in rx path or sctp_lookup_association which are in the protection of rcu_read_lock() already. But sctp_epaddr_lookup_transport is called by sctp_endpoint_lookup_assoc, it doesn't call rcu_read_lock, which may cause "suspicious rcu_dereference_check usage' in __rhashtable_lookup. This patch is to fix it by adding rcu_read_lock in sctp_endpoint_lookup_assoc before calling sctp_epaddr_lookup_transport. Fixes: 7fda702f9315 ("sctp: use new rhlist interface on sctp transport rhashtable") Reported-by: Dmitry Vyukov Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/endpointola.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 1f03065686fe..410ddc1e3443 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -331,7 +331,9 @@ struct sctp_association *sctp_endpoint_lookup_assoc( * on this endpoint. */ if (!ep->base.bind_addr.port) - goto out; + return NULL; + + rcu_read_lock(); t = sctp_epaddr_lookup_transport(ep, paddr); if (!t) goto out; @@ -339,6 +341,7 @@ struct sctp_association *sctp_endpoint_lookup_assoc( *transport = t; asoc = t->asoc; out: + rcu_read_unlock(); return asoc; } From 08abb79542c9e8c367d1d8e44fe1026868d3f0a7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 15 Dec 2016 23:05:52 +0800 Subject: [PATCH 33/63] sctp: sctp_transport_lookup_process should rcu_read_unlock when transport is null Prior to this patch, sctp_transport_lookup_process didn't rcu_read_unlock when it failed to find a transport by sctp_addrs_lookup_transport. This patch is to fix it by moving up rcu_read_unlock right before checking transport and also to remove the out path. Fixes: 1cceda784980 ("sctp: fix the issue sctp_diag uses lock_sock in rcu_read_lock") Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sctp/socket.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index d5f4b4a8369b..318c6786d653 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4472,18 +4472,17 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), const union sctp_addr *paddr, void *p) { struct sctp_transport *transport; - int err = -ENOENT; + int err; rcu_read_lock(); transport = sctp_addrs_lookup_transport(net, laddr, paddr); - if (!transport) - goto out; - rcu_read_unlock(); + if (!transport) + return -ENOENT; + err = cb(transport, p); sctp_transport_put(transport); -out: return err; } EXPORT_SYMBOL_GPL(sctp_transport_lookup_process); From f23bc46c30ca5ef58b8549434899fcbac41b2cfc Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 15 Dec 2016 12:12:54 -0800 Subject: [PATCH 34/63] net: xdp: add invalid buffer warning This adds a warning for drivers to use when encountering an invalid buffer for XDP. For normal cases this should not happen but to catch this in virtual/qemu setups that I may not have expected from the emulation layer having a standard warning is useful. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + net/core/filter.c | 6 ++++++ 2 files changed, 7 insertions(+) diff --git a/include/linux/filter.h b/include/linux/filter.h index 6a1658308612..af8a1804cac6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -602,6 +602,7 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_buffer(void); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/net/core/filter.c b/net/core/filter.c index b1461708a977..7190bd648154 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2972,6 +2972,12 @@ void bpf_warn_invalid_xdp_action(u32 act) } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); +void bpf_warn_invalid_xdp_buffer(void) +{ + WARN_ONCE(1, "Illegal XDP buffer encountered, expect throughput degradation\n"); +} +EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_buffer); + static u32 sk_filter_convert_ctx_access(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, struct bpf_insn *insn_buf, From f600b690501550b94e83e07295d9c8b9c4c39f4e Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 15 Dec 2016 12:13:24 -0800 Subject: [PATCH 35/63] virtio_net: Add XDP support This adds XDP support to virtio_net. Some requirements must be met for XDP to be enabled depending on the mode. First it will only be supported with LRO disabled so that data is not pushed across multiple buffers. Second the MTU must be less than a page size to avoid having to handle XDP across multiple pages. If mergeable receive is enabled this patch only supports the case where header and data are in the same buf which we can check when a packet is received by looking at num_buf. If the num_buf is greater than 1 and a XDP program is loaded the packet is dropped and a warning is thrown. When any_header_sg is set this does not happen and both header and data is put in a single buffer as expected so we check this when XDP programs are loaded. Subsequent patches will process the packet in a degraded mode to ensure connectivity and correctness is not lost even if backend pushes packets into multiple buffers. If big packets mode is enabled and MTU/LRO conditions above are met then XDP is allowed. This patch was tested with qemu with vhost=on and vhost=off where mergeable and big_packet modes were forced via hard coding feature negotiation. Multiple buffers per packet was forced via a small test patch to vhost.c in the vhost=on qemu mode. Suggested-by: Shrijeet Mukherjee Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 176 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 171 insertions(+), 5 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index fe9f7726e990..6fdb6065b940 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -81,6 +82,8 @@ struct receive_queue { struct napi_struct napi; + struct bpf_prog __rcu *xdp_prog; + /* Chain pages by the private ptr. */ struct page *pages; @@ -324,6 +327,38 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, return skb; } +static u32 do_xdp_prog(struct virtnet_info *vi, + struct bpf_prog *xdp_prog, + struct page *page, int offset, int len) +{ + int hdr_padded_len; + struct xdp_buff xdp; + u32 act; + u8 *buf; + + buf = page_address(page) + offset; + + if (vi->mergeable_rx_bufs) + hdr_padded_len = sizeof(struct virtio_net_hdr_mrg_rxbuf); + else + hdr_padded_len = sizeof(struct padded_vnet_hdr); + + xdp.data = buf + hdr_padded_len; + xdp.data_end = xdp.data + (len - vi->hdr_len); + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + return XDP_PASS; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_TX: + case XDP_ABORTED: + case XDP_DROP: + return XDP_DROP; + } +} + static struct sk_buff *receive_small(struct virtnet_info *vi, void *buf, unsigned int len) { struct sk_buff * skb = buf; @@ -340,14 +375,32 @@ static struct sk_buff *receive_big(struct net_device *dev, void *buf, unsigned int len) { + struct bpf_prog *xdp_prog; struct page *page = buf; - struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); + struct sk_buff *skb; + rcu_read_lock(); + xdp_prog = rcu_dereference(rq->xdp_prog); + if (xdp_prog) { + struct virtio_net_hdr_mrg_rxbuf *hdr = buf; + u32 act; + + if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags)) + goto err_xdp; + act = do_xdp_prog(vi, xdp_prog, page, 0, len); + if (act == XDP_DROP) + goto err_xdp; + } + rcu_read_unlock(); + + skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); if (unlikely(!skb)) goto err; return skb; +err_xdp: + rcu_read_unlock(); err: dev->stats.rx_dropped++; give_pages(rq, page); @@ -365,11 +418,42 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); struct page *page = virt_to_head_page(buf); int offset = buf - page_address(page); - unsigned int truesize = max(len, mergeable_ctx_to_buf_truesize(ctx)); + struct sk_buff *head_skb, *curr_skb; + struct bpf_prog *xdp_prog; + unsigned int truesize; - struct sk_buff *head_skb = page_to_skb(vi, rq, page, offset, len, - truesize); - struct sk_buff *curr_skb = head_skb; + rcu_read_lock(); + xdp_prog = rcu_dereference(rq->xdp_prog); + if (xdp_prog) { + u32 act; + + /* No known backend devices should send packets with + * more than a single buffer when XDP conditions are + * met. However it is not strictly illegal so the case + * is handled as an exception and a warning is thrown. + */ + if (unlikely(num_buf > 1)) { + bpf_warn_invalid_xdp_buffer(); + goto err_xdp; + } + + /* Transient failure which in theory could occur if + * in-flight packets from before XDP was enabled reach + * the receive path after XDP is loaded. In practice I + * was not able to create this condition. + */ + if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags)) + goto err_xdp; + + act = do_xdp_prog(vi, xdp_prog, page, offset, len); + if (act == XDP_DROP) + goto err_xdp; + } + rcu_read_unlock(); + + truesize = max(len, mergeable_ctx_to_buf_truesize(ctx)); + head_skb = page_to_skb(vi, rq, page, offset, len, truesize); + curr_skb = head_skb; if (unlikely(!curr_skb)) goto err_skb; @@ -423,6 +507,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, ewma_pkt_len_add(&rq->mrg_avg_pkt_len, head_skb->len); return head_skb; +err_xdp: + rcu_read_unlock(); err_skb: put_page(page); while (--num_buf) { @@ -1337,6 +1423,13 @@ static int virtnet_set_channels(struct net_device *dev, if (queue_pairs > vi->max_queue_pairs || queue_pairs == 0) return -EINVAL; + /* For now we don't support modifying channels while XDP is loaded + * also when XDP is loaded all RX queues have XDP programs so we only + * need to check a single RX queue. + */ + if (vi->rq[0].xdp_prog) + return -EINVAL; + get_online_cpus(); err = virtnet_set_queues(vi, queue_pairs); if (!err) { @@ -1428,6 +1521,70 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .set_settings = virtnet_set_settings, }; +static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog) +{ + unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr); + struct virtnet_info *vi = netdev_priv(dev); + struct bpf_prog *old_prog; + int i; + + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || + virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6)) { + netdev_warn(dev, "can't set XDP while host is implementing LRO, disable LRO first\n"); + return -EOPNOTSUPP; + } + + if (vi->mergeable_rx_bufs && !vi->any_header_sg) { + netdev_warn(dev, "XDP expects header/data in single page, any_header_sg required\n"); + return -EINVAL; + } + + if (dev->mtu > max_sz) { + netdev_warn(dev, "XDP requires MTU less than %lu\n", max_sz); + return -EINVAL; + } + + if (prog) { + prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + + for (i = 0; i < vi->max_queue_pairs; i++) { + old_prog = rtnl_dereference(vi->rq[i].xdp_prog); + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + } + + return 0; +} + +static bool virtnet_xdp_query(struct net_device *dev) +{ + struct virtnet_info *vi = netdev_priv(dev); + int i; + + for (i = 0; i < vi->max_queue_pairs; i++) { + if (vi->rq[i].xdp_prog) + return true; + } + return false; +} + +static int virtnet_xdp(struct net_device *dev, struct netdev_xdp *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return virtnet_xdp_set(dev, xdp->prog); + case XDP_QUERY_PROG: + xdp->prog_attached = virtnet_xdp_query(dev); + return 0; + default: + return -EINVAL; + } +} + static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, @@ -1444,6 +1601,7 @@ static const struct net_device_ops virtnet_netdev = { #ifdef CONFIG_NET_RX_BUSY_POLL .ndo_busy_poll = virtnet_busy_poll, #endif + .ndo_xdp = virtnet_xdp, }; static void virtnet_config_changed_work(struct work_struct *work) @@ -1505,12 +1663,20 @@ static void virtnet_free_queues(struct virtnet_info *vi) static void free_receive_bufs(struct virtnet_info *vi) { + struct bpf_prog *old_prog; int i; + rtnl_lock(); for (i = 0; i < vi->max_queue_pairs; i++) { while (vi->rq[i].pages) __free_pages(get_a_page(&vi->rq[i], GFP_KERNEL), 0); + + old_prog = rtnl_dereference(vi->rq[i].xdp_prog); + RCU_INIT_POINTER(vi->rq[i].xdp_prog, NULL); + if (old_prog) + bpf_prog_put(old_prog); } + rtnl_unlock(); } static void free_receive_page_frags(struct virtnet_info *vi) From 672aafd5d88a951f394334802b938b502010d9eb Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 15 Dec 2016 12:13:49 -0800 Subject: [PATCH 36/63] virtio_net: add dedicated XDP transmit queues XDP requires using isolated transmit queues to avoid interference with normal networking stack (BQL, NETDEV_TX_BUSY, etc). This patch adds a XDP queue per cpu when a XDP program is loaded and does not expose the queues to the OS via the normal API call to netif_set_real_num_tx_queues(). This way the stack will never push an skb to these queues. However virtio/vhost/qemu implementation only allows for creating TX/RX queue pairs at this time so creating only TX queues was not possible. And because the associated RX queues are being created I went ahead and exposed these to the stack and let the backend use them. This creates more RX queues visible to the network stack than TX queues which is worth mentioning but does not cause any issues as far as I can tell. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 6fdb6065b940..1d16862c5710 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -114,6 +114,9 @@ struct virtnet_info { /* # of queue pairs currently used by the driver */ u16 curr_queue_pairs; + /* # of XDP queue pairs currently used by the driver */ + u16 xdp_queue_pairs; + /* I like... big packets and I cannot lie! */ bool big_packets; @@ -1526,7 +1529,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog) unsigned long int max_sz = PAGE_SIZE - sizeof(struct padded_vnet_hdr); struct virtnet_info *vi = netdev_priv(dev); struct bpf_prog *old_prog; - int i; + u16 xdp_qp = 0, curr_qp; + int i, err; if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6)) { @@ -1544,12 +1548,34 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog) return -EINVAL; } + curr_qp = vi->curr_queue_pairs - vi->xdp_queue_pairs; + if (prog) + xdp_qp = nr_cpu_ids; + + /* XDP requires extra queues for XDP_TX */ + if (curr_qp + xdp_qp > vi->max_queue_pairs) { + netdev_warn(dev, "request %i queues but max is %i\n", + curr_qp + xdp_qp, vi->max_queue_pairs); + return -ENOMEM; + } + + err = virtnet_set_queues(vi, curr_qp + xdp_qp); + if (err) { + dev_warn(&dev->dev, "XDP Device queue allocation failure.\n"); + return err; + } + if (prog) { prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); - if (IS_ERR(prog)) + if (IS_ERR(prog)) { + virtnet_set_queues(vi, curr_qp); return PTR_ERR(prog); + } } + vi->xdp_queue_pairs = xdp_qp; + netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); + for (i = 0; i < vi->max_queue_pairs; i++) { old_prog = rtnl_dereference(vi->rq[i].xdp_prog); rcu_assign_pointer(vi->rq[i].xdp_prog, prog); From 56434a01b12e99eb60908f5f2b27b90726d0a183 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 15 Dec 2016 12:14:13 -0800 Subject: [PATCH 37/63] virtio_net: add XDP_TX support This adds support for the XDP_TX action to virtio_net. When an XDP program is run and returns the XDP_TX action the virtio_net XDP implementation will transmit the packet on a TX queue that aligns with the current CPU that the XDP packet was processed on. Before sending the packet the header is zeroed. Also XDP is expected to handle checksum correctly so no checksum offload support is provided. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 100 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 93 insertions(+), 7 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1d16862c5710..ca3d2e2350c6 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -330,12 +330,58 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, return skb; } +static void virtnet_xdp_xmit(struct virtnet_info *vi, + struct receive_queue *rq, + struct send_queue *sq, + struct xdp_buff *xdp) +{ + struct page *page = virt_to_head_page(xdp->data); + struct virtio_net_hdr_mrg_rxbuf *hdr; + unsigned int num_sg, len; + void *xdp_sent; + int err; + + /* Free up any pending old buffers before queueing new ones. */ + while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) { + struct page *sent_page = virt_to_head_page(xdp_sent); + + if (vi->mergeable_rx_bufs) + put_page(sent_page); + else + give_pages(rq, sent_page); + } + + /* Zero header and leave csum up to XDP layers */ + hdr = xdp->data; + memset(hdr, 0, vi->hdr_len); + + num_sg = 1; + sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data); + err = virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, + xdp->data, GFP_ATOMIC); + if (unlikely(err)) { + if (vi->mergeable_rx_bufs) + put_page(page); + else + give_pages(rq, page); + return; // On error abort to avoid unnecessary kick + } else if (!vi->mergeable_rx_bufs) { + /* If not mergeable bufs must be big packets so cleanup pages */ + give_pages(rq, (struct page *)page->private); + page->private = 0; + } + + virtqueue_kick(sq->vq); +} + static u32 do_xdp_prog(struct virtnet_info *vi, + struct receive_queue *rq, struct bpf_prog *xdp_prog, struct page *page, int offset, int len) { int hdr_padded_len; struct xdp_buff xdp; + unsigned int qp; u32 act; u8 *buf; @@ -353,9 +399,15 @@ static u32 do_xdp_prog(struct virtnet_info *vi, switch (act) { case XDP_PASS: return XDP_PASS; + case XDP_TX: + qp = vi->curr_queue_pairs - + vi->xdp_queue_pairs + + smp_processor_id(); + xdp.data = buf + (vi->mergeable_rx_bufs ? 0 : 4); + virtnet_xdp_xmit(vi, rq, &vi->sq[qp], &xdp); + return XDP_TX; default: bpf_warn_invalid_xdp_action(act); - case XDP_TX: case XDP_ABORTED: case XDP_DROP: return XDP_DROP; @@ -390,9 +442,17 @@ static struct sk_buff *receive_big(struct net_device *dev, if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags)) goto err_xdp; - act = do_xdp_prog(vi, xdp_prog, page, 0, len); - if (act == XDP_DROP) + act = do_xdp_prog(vi, rq, xdp_prog, page, 0, len); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + rcu_read_unlock(); + goto xdp_xmit; + case XDP_DROP: + default: goto err_xdp; + } } rcu_read_unlock(); @@ -407,6 +467,7 @@ static struct sk_buff *receive_big(struct net_device *dev, err: dev->stats.rx_dropped++; give_pages(rq, page); +xdp_xmit: return NULL; } @@ -425,6 +486,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct bpf_prog *xdp_prog; unsigned int truesize; + head_skb = NULL; + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -448,9 +511,17 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, if (unlikely(hdr->hdr.gso_type || hdr->hdr.flags)) goto err_xdp; - act = do_xdp_prog(vi, xdp_prog, page, offset, len); - if (act == XDP_DROP) + act = do_xdp_prog(vi, rq, xdp_prog, page, offset, len); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + rcu_read_unlock(); + goto xdp_xmit; + case XDP_DROP: + default: goto err_xdp; + } } rcu_read_unlock(); @@ -528,6 +599,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, err_buf: dev->stats.rx_dropped++; dev_kfree_skb(head_skb); +xdp_xmit: return NULL; } @@ -1713,6 +1785,16 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } +static bool is_xdp_queue(struct virtnet_info *vi, int q) +{ + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) + return false; + else if (q < vi->curr_queue_pairs) + return true; + else + return false; +} + static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -1720,8 +1802,12 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; - while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) - dev_kfree_skb(buf); + while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { + if (!is_xdp_queue(vi, i)) + dev_kfree_skb(buf); + else + put_page(virt_to_head_page(buf)); + } } for (i = 0; i < vi->max_queue_pairs; i++) { From 72979a6c35907b6a7ab85e7bc60e0d52dba68f9d Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 15 Dec 2016 12:14:36 -0800 Subject: [PATCH 38/63] virtio_net: xdp, add slowpath case for non contiguous buffers virtio_net XDP support expects receive buffers to be contiguous. If this is not the case we enable a slowpath to allow connectivity to continue but at a significan performance overhead associated with linearizing data. To make it painfully aware to users that XDP is running in a degraded mode we throw an xdp buffer error. To linearize packets we allocate a page and copy the segments of the data, including the header, into it. After this the page can be handled by XDP code flow as normal. Then depending on the return code the page is either freed or sent to the XDP xmit path. There is no attempt to optimize this path. This case is being handled simple as a precaution in case some unknown backend were to generate packets in this form. To test this I had to hack qemu and force it to generate these packets. I do not expect this case to be generated by "real" backends. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/virtio_net.c | 75 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 74 insertions(+), 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index ca3d2e2350c6..08327e005ccc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -471,6 +471,64 @@ static struct sk_buff *receive_big(struct net_device *dev, return NULL; } +/* The conditions to enable XDP should preclude the underlying device from + * sending packets across multiple buffers (num_buf > 1). However per spec + * it does not appear to be illegal to do so but rather just against convention. + * So in order to avoid making a system unresponsive the packets are pushed + * into a page and the XDP program is run. This will be extremely slow and we + * push a warning to the user to fix this as soon as possible. Fixing this may + * require resolving the underlying hardware to determine why multiple buffers + * are being received or simply loading the XDP program in the ingress stack + * after the skb is built because there is no advantage to running it here + * anymore. + */ +static struct page *xdp_linearize_page(struct receive_queue *rq, + u16 num_buf, + struct page *p, + int offset, + unsigned int *len) +{ + struct page *page = alloc_page(GFP_ATOMIC); + unsigned int page_off = 0; + + if (!page) + return NULL; + + memcpy(page_address(page) + page_off, page_address(p) + offset, *len); + page_off += *len; + + while (--num_buf) { + unsigned int buflen; + unsigned long ctx; + void *buf; + int off; + + ctx = (unsigned long)virtqueue_get_buf(rq->vq, &buflen); + if (unlikely(!ctx)) + goto err_buf; + + /* guard against a misconfigured or uncooperative backend that + * is sending packet larger than the MTU. + */ + if ((page_off + buflen) > PAGE_SIZE) + goto err_buf; + + buf = mergeable_ctx_to_buf_address(ctx); + p = virt_to_head_page(buf); + off = buf - page_address(p); + + memcpy(page_address(page) + page_off, + page_address(p) + off, buflen); + page_off += buflen; + } + + *len = page_off; + return page; +err_buf: + __free_pages(page, 0); + return NULL; +} + static struct sk_buff *receive_mergeable(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, @@ -491,6 +549,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { + struct page *xdp_page; u32 act; /* No known backend devices should send packets with @@ -500,7 +559,15 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, */ if (unlikely(num_buf > 1)) { bpf_warn_invalid_xdp_buffer(); - goto err_xdp; + + /* linearize data for XDP */ + xdp_page = xdp_linearize_page(rq, num_buf, + page, offset, &len); + if (!xdp_page) + goto err_xdp; + offset = 0; + } else { + xdp_page = page; } /* Transient failure which in theory could occur if @@ -514,12 +581,18 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, act = do_xdp_prog(vi, rq, xdp_prog, page, offset, len); switch (act) { case XDP_PASS: + if (unlikely(xdp_page != page)) + __free_pages(xdp_page, 0); break; case XDP_TX: + if (unlikely(xdp_page != page)) + goto err_xdp; rcu_read_unlock(); goto xdp_xmit; case XDP_DROP: default: + if (unlikely(xdp_page != page)) + __free_pages(xdp_page, 0); goto err_xdp; } } From 4794195058b916cabcfaf9f4dfc699e6f48784f7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 16:58:06 -0800 Subject: [PATCH 39/63] isdn/gigaset: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/gigaset/bas-gigaset.c | 32 +++++++++++++++--------------- drivers/isdn/gigaset/ser-gigaset.c | 32 +++++++++++++++--------------- drivers/isdn/gigaset/usb-gigaset.c | 32 +++++++++++++++--------------- 3 files changed, 48 insertions(+), 48 deletions(-) diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c index aecec6d32463..11e13c56126f 100644 --- a/drivers/isdn/gigaset/bas-gigaset.c +++ b/drivers/isdn/gigaset/bas-gigaset.c @@ -2565,22 +2565,22 @@ static int gigaset_post_reset(struct usb_interface *intf) static const struct gigaset_ops gigops = { - gigaset_write_cmd, - gigaset_write_room, - gigaset_chars_in_buffer, - gigaset_brkchars, - gigaset_init_bchannel, - gigaset_close_bchannel, - gigaset_initbcshw, - gigaset_freebcshw, - gigaset_reinitbcshw, - gigaset_initcshw, - gigaset_freecshw, - gigaset_set_modem_ctrl, - gigaset_baud_rate, - gigaset_set_line_ctrl, - gigaset_isoc_send_skb, - gigaset_isoc_input, + .write_cmd = gigaset_write_cmd, + .write_room = gigaset_write_room, + .chars_in_buffer = gigaset_chars_in_buffer, + .brkchars = gigaset_brkchars, + .init_bchannel = gigaset_init_bchannel, + .close_bchannel = gigaset_close_bchannel, + .initbcshw = gigaset_initbcshw, + .freebcshw = gigaset_freebcshw, + .reinitbcshw = gigaset_reinitbcshw, + .initcshw = gigaset_initcshw, + .freecshw = gigaset_freecshw, + .set_modem_ctrl = gigaset_set_modem_ctrl, + .baud_rate = gigaset_baud_rate, + .set_line_ctrl = gigaset_set_line_ctrl, + .send_skb = gigaset_isoc_send_skb, + .handle_input = gigaset_isoc_input, }; /* bas_gigaset_init diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index b90776ef56ec..ab0b63a4d045 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -445,22 +445,22 @@ static int gigaset_set_line_ctrl(struct cardstate *cs, unsigned cflag) } static const struct gigaset_ops ops = { - gigaset_write_cmd, - gigaset_write_room, - gigaset_chars_in_buffer, - gigaset_brkchars, - gigaset_init_bchannel, - gigaset_close_bchannel, - gigaset_initbcshw, - gigaset_freebcshw, - gigaset_reinitbcshw, - gigaset_initcshw, - gigaset_freecshw, - gigaset_set_modem_ctrl, - gigaset_baud_rate, - gigaset_set_line_ctrl, - gigaset_m10x_send_skb, /* asyncdata.c */ - gigaset_m10x_input, /* asyncdata.c */ + .write_cmd = gigaset_write_cmd, + .write_room = gigaset_write_room, + .chars_in_buffer = gigaset_chars_in_buffer, + .brkchars = gigaset_brkchars, + .init_bchannel = gigaset_init_bchannel, + .close_bchannel = gigaset_close_bchannel, + .initbcshw = gigaset_initbcshw, + .freebcshw = gigaset_freebcshw, + .reinitbcshw = gigaset_reinitbcshw, + .initcshw = gigaset_initcshw, + .freecshw = gigaset_freecshw, + .set_modem_ctrl = gigaset_set_modem_ctrl, + .baud_rate = gigaset_baud_rate, + .set_line_ctrl = gigaset_set_line_ctrl, + .send_skb = gigaset_m10x_send_skb, /* asyncdata.c */ + .handle_input = gigaset_m10x_input, /* asyncdata.c */ }; diff --git a/drivers/isdn/gigaset/usb-gigaset.c b/drivers/isdn/gigaset/usb-gigaset.c index 5f306e2eece5..eade36dafa34 100644 --- a/drivers/isdn/gigaset/usb-gigaset.c +++ b/drivers/isdn/gigaset/usb-gigaset.c @@ -862,22 +862,22 @@ static int gigaset_pre_reset(struct usb_interface *intf) } static const struct gigaset_ops ops = { - gigaset_write_cmd, - gigaset_write_room, - gigaset_chars_in_buffer, - gigaset_brkchars, - gigaset_init_bchannel, - gigaset_close_bchannel, - gigaset_initbcshw, - gigaset_freebcshw, - gigaset_reinitbcshw, - gigaset_initcshw, - gigaset_freecshw, - gigaset_set_modem_ctrl, - gigaset_baud_rate, - gigaset_set_line_ctrl, - gigaset_m10x_send_skb, - gigaset_m10x_input, + .write_cmd = gigaset_write_cmd, + .write_room = gigaset_write_room, + .chars_in_buffer = gigaset_chars_in_buffer, + .brkchars = gigaset_brkchars, + .init_bchannel = gigaset_init_bchannel, + .close_bchannel = gigaset_close_bchannel, + .initbcshw = gigaset_initbcshw, + .freebcshw = gigaset_freebcshw, + .reinitbcshw = gigaset_reinitbcshw, + .initcshw = gigaset_initcshw, + .freecshw = gigaset_freecshw, + .set_modem_ctrl = gigaset_set_modem_ctrl, + .baud_rate = gigaset_baud_rate, + .set_line_ctrl = gigaset_set_line_ctrl, + .send_skb = gigaset_m10x_send_skb, + .handle_input = gigaset_m10x_input, }; /* From 99a5e178bde4b0fa1f25ca8d9caee0cb5e329e7c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 16:58:43 -0800 Subject: [PATCH 40/63] ATM: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/atm/lec.c | 6 +-- net/atm/mpoa_caches.c | 43 ++++++++++---------- net/vmw_vsock/vmci_transport_notify.c | 30 +++++++------- net/vmw_vsock/vmci_transport_notify_qstate.c | 30 +++++++------- 4 files changed, 54 insertions(+), 55 deletions(-) diff --git a/net/atm/lec.c b/net/atm/lec.c index 779b3fa6052d..019557d0a11d 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -111,9 +111,9 @@ static inline void lec_arp_put(struct lec_arp_table *entry) } static struct lane2_ops lane2_ops = { - lane2_resolve, /* resolve, spec 3.1.3 */ - lane2_associate_req, /* associate_req, spec 3.1.4 */ - NULL /* associate indicator, spec 3.1.5 */ + .resolve = lane2_resolve, /* spec 3.1.3 */ + .associate_req = lane2_associate_req, /* spec 3.1.4 */ + .associate_indicator = NULL /* spec 3.1.5 */ }; static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; diff --git a/net/atm/mpoa_caches.c b/net/atm/mpoa_caches.c index 9e60e74c807d..a89fdebeffda 100644 --- a/net/atm/mpoa_caches.c +++ b/net/atm/mpoa_caches.c @@ -535,33 +535,32 @@ static void eg_destroy_cache(struct mpoa_client *mpc) static const struct in_cache_ops ingress_ops = { - in_cache_add_entry, /* add_entry */ - in_cache_get, /* get */ - in_cache_get_with_mask, /* get_with_mask */ - in_cache_get_by_vcc, /* get_by_vcc */ - in_cache_put, /* put */ - in_cache_remove_entry, /* remove_entry */ - cache_hit, /* cache_hit */ - clear_count_and_expired, /* clear_count */ - check_resolving_entries, /* check_resolving */ - refresh_entries, /* refresh */ - in_destroy_cache /* destroy_cache */ + .add_entry = in_cache_add_entry, + .get = in_cache_get, + .get_with_mask = in_cache_get_with_mask, + .get_by_vcc = in_cache_get_by_vcc, + .put = in_cache_put, + .remove_entry = in_cache_remove_entry, + .cache_hit = cache_hit, + .clear_count = clear_count_and_expired, + .check_resolving = check_resolving_entries, + .refresh = refresh_entries, + .destroy_cache = in_destroy_cache }; static const struct eg_cache_ops egress_ops = { - eg_cache_add_entry, /* add_entry */ - eg_cache_get_by_cache_id, /* get_by_cache_id */ - eg_cache_get_by_tag, /* get_by_tag */ - eg_cache_get_by_vcc, /* get_by_vcc */ - eg_cache_get_by_src_ip, /* get_by_src_ip */ - eg_cache_put, /* put */ - eg_cache_remove_entry, /* remove_entry */ - update_eg_cache_entry, /* update */ - clear_expired, /* clear_expired */ - eg_destroy_cache /* destroy_cache */ + .add_entry = eg_cache_add_entry, + .get_by_cache_id = eg_cache_get_by_cache_id, + .get_by_tag = eg_cache_get_by_tag, + .get_by_vcc = eg_cache_get_by_vcc, + .get_by_src_ip = eg_cache_get_by_src_ip, + .put = eg_cache_put, + .remove_entry = eg_cache_remove_entry, + .update = update_eg_cache_entry, + .clear_expired = clear_expired, + .destroy_cache = eg_destroy_cache }; - void atm_mpoa_init_cache(struct mpoa_client *mpc) { mpc->in_ops = &ingress_ops; diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c index fd8cf0214d51..1406db4d97d1 100644 --- a/net/vmw_vsock/vmci_transport_notify.c +++ b/net/vmw_vsock/vmci_transport_notify.c @@ -662,19 +662,19 @@ static void vmci_transport_notify_pkt_process_negotiate(struct sock *sk) /* Socket control packet based operations. */ const struct vmci_transport_notify_ops vmci_transport_notify_pkt_ops = { - vmci_transport_notify_pkt_socket_init, - vmci_transport_notify_pkt_socket_destruct, - vmci_transport_notify_pkt_poll_in, - vmci_transport_notify_pkt_poll_out, - vmci_transport_notify_pkt_handle_pkt, - vmci_transport_notify_pkt_recv_init, - vmci_transport_notify_pkt_recv_pre_block, - vmci_transport_notify_pkt_recv_pre_dequeue, - vmci_transport_notify_pkt_recv_post_dequeue, - vmci_transport_notify_pkt_send_init, - vmci_transport_notify_pkt_send_pre_block, - vmci_transport_notify_pkt_send_pre_enqueue, - vmci_transport_notify_pkt_send_post_enqueue, - vmci_transport_notify_pkt_process_request, - vmci_transport_notify_pkt_process_negotiate, + .socket_init = vmci_transport_notify_pkt_socket_init, + .socket_destruct = vmci_transport_notify_pkt_socket_destruct, + .poll_in = vmci_transport_notify_pkt_poll_in, + .poll_out = vmci_transport_notify_pkt_poll_out, + .handle_notify_pkt = vmci_transport_notify_pkt_handle_pkt, + .recv_init = vmci_transport_notify_pkt_recv_init, + .recv_pre_block = vmci_transport_notify_pkt_recv_pre_block, + .recv_pre_dequeue = vmci_transport_notify_pkt_recv_pre_dequeue, + .recv_post_dequeue = vmci_transport_notify_pkt_recv_post_dequeue, + .send_init = vmci_transport_notify_pkt_send_init, + .send_pre_block = vmci_transport_notify_pkt_send_pre_block, + .send_pre_enqueue = vmci_transport_notify_pkt_send_pre_enqueue, + .send_post_enqueue = vmci_transport_notify_pkt_send_post_enqueue, + .process_request = vmci_transport_notify_pkt_process_request, + .process_negotiate = vmci_transport_notify_pkt_process_negotiate, }; diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c index 21e591dafb03..f3a0afc46208 100644 --- a/net/vmw_vsock/vmci_transport_notify_qstate.c +++ b/net/vmw_vsock/vmci_transport_notify_qstate.c @@ -420,19 +420,19 @@ vmci_transport_notify_pkt_send_pre_enqueue( /* Socket always on control packet based operations. */ const struct vmci_transport_notify_ops vmci_transport_notify_pkt_q_state_ops = { - vmci_transport_notify_pkt_socket_init, - vmci_transport_notify_pkt_socket_destruct, - vmci_transport_notify_pkt_poll_in, - vmci_transport_notify_pkt_poll_out, - vmci_transport_notify_pkt_handle_pkt, - vmci_transport_notify_pkt_recv_init, - vmci_transport_notify_pkt_recv_pre_block, - vmci_transport_notify_pkt_recv_pre_dequeue, - vmci_transport_notify_pkt_recv_post_dequeue, - vmci_transport_notify_pkt_send_init, - vmci_transport_notify_pkt_send_pre_block, - vmci_transport_notify_pkt_send_pre_enqueue, - vmci_transport_notify_pkt_send_post_enqueue, - vmci_transport_notify_pkt_process_request, - vmci_transport_notify_pkt_process_negotiate, + .socket_init = vmci_transport_notify_pkt_socket_init, + .socket_destruct = vmci_transport_notify_pkt_socket_destruct, + .poll_in = vmci_transport_notify_pkt_poll_in, + .poll_out = vmci_transport_notify_pkt_poll_out, + .handle_notify_pkt = vmci_transport_notify_pkt_handle_pkt, + .recv_init = vmci_transport_notify_pkt_recv_init, + .recv_pre_block = vmci_transport_notify_pkt_recv_pre_block, + .recv_pre_dequeue = vmci_transport_notify_pkt_recv_pre_dequeue, + .recv_post_dequeue = vmci_transport_notify_pkt_recv_post_dequeue, + .send_init = vmci_transport_notify_pkt_send_init, + .send_pre_block = vmci_transport_notify_pkt_send_pre_block, + .send_pre_enqueue = vmci_transport_notify_pkt_send_pre_enqueue, + .send_post_enqueue = vmci_transport_notify_pkt_send_post_enqueue, + .process_request = vmci_transport_notify_pkt_process_request, + .process_negotiate = vmci_transport_notify_pkt_process_negotiate, }; From 9d1c0ca5e1d6697ce1e32bb708bfe24dff34f287 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 16:58:58 -0800 Subject: [PATCH 41/63] net: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/decnet/dn_dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index b2c26b081134..41f803e35da3 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -201,7 +201,7 @@ static struct dn_dev_sysctl_table { .extra1 = &min_t3, .extra2 = &max_t3 }, - {0} + { } }, }; From aabd7ad949247ef315fa5086d2caad7885567434 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 16:59:18 -0800 Subject: [PATCH 42/63] WAN: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/wan/lmc/lmc_media.c | 97 +++++++++++++++++---------------- 1 file changed, 49 insertions(+), 48 deletions(-) diff --git a/drivers/net/wan/lmc/lmc_media.c b/drivers/net/wan/lmc/lmc_media.c index 5920c996fcdf..ff2e4a5654c7 100644 --- a/drivers/net/wan/lmc/lmc_media.c +++ b/drivers/net/wan/lmc/lmc_media.c @@ -95,62 +95,63 @@ static inline void write_av9110_bit (lmc_softc_t *, int); static void write_av9110(lmc_softc_t *, u32, u32, u32, u32, u32); lmc_media_t lmc_ds3_media = { - lmc_ds3_init, /* special media init stuff */ - lmc_ds3_default, /* reset to default state */ - lmc_ds3_set_status, /* reset status to state provided */ - lmc_dummy_set_1, /* set clock source */ - lmc_dummy_set2_1, /* set line speed */ - lmc_ds3_set_100ft, /* set cable length */ - lmc_ds3_set_scram, /* set scrambler */ - lmc_ds3_get_link_status, /* get link status */ - lmc_dummy_set_1, /* set link status */ - lmc_ds3_set_crc_length, /* set CRC length */ - lmc_dummy_set_1, /* set T1 or E1 circuit type */ - lmc_ds3_watchdog + .init = lmc_ds3_init, /* special media init stuff */ + .defaults = lmc_ds3_default, /* reset to default state */ + .set_status = lmc_ds3_set_status, /* reset status to state provided */ + .set_clock_source = lmc_dummy_set_1, /* set clock source */ + .set_speed = lmc_dummy_set2_1, /* set line speed */ + .set_cable_length = lmc_ds3_set_100ft, /* set cable length */ + .set_scrambler = lmc_ds3_set_scram, /* set scrambler */ + .get_link_status = lmc_ds3_get_link_status, /* get link status */ + .set_link_status = lmc_dummy_set_1, /* set link status */ + .set_crc_length = lmc_ds3_set_crc_length, /* set CRC length */ + .set_circuit_type = lmc_dummy_set_1, /* set T1 or E1 circuit type */ + .watchdog = lmc_ds3_watchdog }; lmc_media_t lmc_hssi_media = { - lmc_hssi_init, /* special media init stuff */ - lmc_hssi_default, /* reset to default state */ - lmc_hssi_set_status, /* reset status to state provided */ - lmc_hssi_set_clock, /* set clock source */ - lmc_dummy_set2_1, /* set line speed */ - lmc_dummy_set_1, /* set cable length */ - lmc_dummy_set_1, /* set scrambler */ - lmc_hssi_get_link_status, /* get link status */ - lmc_hssi_set_link_status, /* set link status */ - lmc_hssi_set_crc_length, /* set CRC length */ - lmc_dummy_set_1, /* set T1 or E1 circuit type */ - lmc_hssi_watchdog + .init = lmc_hssi_init, /* special media init stuff */ + .defaults = lmc_hssi_default, /* reset to default state */ + .set_status = lmc_hssi_set_status, /* reset status to state provided */ + .set_clock_source = lmc_hssi_set_clock, /* set clock source */ + .set_speed = lmc_dummy_set2_1, /* set line speed */ + .set_cable_length = lmc_dummy_set_1, /* set cable length */ + .set_scrambler = lmc_dummy_set_1, /* set scrambler */ + .get_link_status = lmc_hssi_get_link_status, /* get link status */ + .set_link_status = lmc_hssi_set_link_status, /* set link status */ + .set_crc_length = lmc_hssi_set_crc_length, /* set CRC length */ + .set_circuit_type = lmc_dummy_set_1, /* set T1 or E1 circuit type */ + .watchdog = lmc_hssi_watchdog }; -lmc_media_t lmc_ssi_media = { lmc_ssi_init, /* special media init stuff */ - lmc_ssi_default, /* reset to default state */ - lmc_ssi_set_status, /* reset status to state provided */ - lmc_ssi_set_clock, /* set clock source */ - lmc_ssi_set_speed, /* set line speed */ - lmc_dummy_set_1, /* set cable length */ - lmc_dummy_set_1, /* set scrambler */ - lmc_ssi_get_link_status, /* get link status */ - lmc_ssi_set_link_status, /* set link status */ - lmc_ssi_set_crc_length, /* set CRC length */ - lmc_dummy_set_1, /* set T1 or E1 circuit type */ - lmc_ssi_watchdog +lmc_media_t lmc_ssi_media = { + .init = lmc_ssi_init, /* special media init stuff */ + .defaults = lmc_ssi_default, /* reset to default state */ + .set_status = lmc_ssi_set_status, /* reset status to state provided */ + .set_clock_source = lmc_ssi_set_clock, /* set clock source */ + .set_speed = lmc_ssi_set_speed, /* set line speed */ + .set_cable_length = lmc_dummy_set_1, /* set cable length */ + .set_scrambler = lmc_dummy_set_1, /* set scrambler */ + .get_link_status = lmc_ssi_get_link_status, /* get link status */ + .set_link_status = lmc_ssi_set_link_status, /* set link status */ + .set_crc_length = lmc_ssi_set_crc_length, /* set CRC length */ + .set_circuit_type = lmc_dummy_set_1, /* set T1 or E1 circuit type */ + .watchdog = lmc_ssi_watchdog }; lmc_media_t lmc_t1_media = { - lmc_t1_init, /* special media init stuff */ - lmc_t1_default, /* reset to default state */ - lmc_t1_set_status, /* reset status to state provided */ - lmc_t1_set_clock, /* set clock source */ - lmc_dummy_set2_1, /* set line speed */ - lmc_dummy_set_1, /* set cable length */ - lmc_dummy_set_1, /* set scrambler */ - lmc_t1_get_link_status, /* get link status */ - lmc_dummy_set_1, /* set link status */ - lmc_t1_set_crc_length, /* set CRC length */ - lmc_t1_set_circuit_type, /* set T1 or E1 circuit type */ - lmc_t1_watchdog + .init = lmc_t1_init, /* special media init stuff */ + .defaults = lmc_t1_default, /* reset to default state */ + .set_status = lmc_t1_set_status, /* reset status to state provided */ + .set_clock_source = lmc_t1_set_clock, /* set clock source */ + .set_speed = lmc_dummy_set2_1, /* set line speed */ + .set_cable_length = lmc_dummy_set_1, /* set cable length */ + .set_scrambler = lmc_dummy_set_1, /* set scrambler */ + .get_link_status = lmc_t1_get_link_status, /* get link status */ + .set_link_status = lmc_dummy_set_1, /* set link status */ + .set_crc_length = lmc_t1_set_crc_length, /* set CRC length */ + .set_circuit_type = lmc_t1_set_circuit_type, /* set T1 or E1 circuit type */ + .watchdog = lmc_t1_watchdog }; static void From 9751362a4fe7ad37115d20344ce6d914a088268d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 17:00:54 -0800 Subject: [PATCH 43/63] bna: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/net/ethernet/brocade/bna/bna_enet.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/brocade/bna/bna_enet.c b/drivers/net/ethernet/brocade/bna/bna_enet.c index 4e5c3874a50f..bba81735ce87 100644 --- a/drivers/net/ethernet/brocade/bna/bna_enet.c +++ b/drivers/net/ethernet/brocade/bna/bna_enet.c @@ -1676,10 +1676,10 @@ bna_cb_ioceth_reset(void *arg) } static struct bfa_ioc_cbfn bna_ioceth_cbfn = { - bna_cb_ioceth_enable, - bna_cb_ioceth_disable, - bna_cb_ioceth_hbfail, - bna_cb_ioceth_reset + .enable_cbfn = bna_cb_ioceth_enable, + .disable_cbfn = bna_cb_ioceth_disable, + .hbfail_cbfn = bna_cb_ioceth_hbfail, + .reset_cbfn = bna_cb_ioceth_reset }; static void bna_attr_init(struct bna_ioceth *ioceth) From ebf12f1320c70c3eaeb5b7d108444fafd54d352c Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 17:01:42 -0800 Subject: [PATCH 44/63] isdn: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/i4l/isdn_concap.c | 6 +++--- drivers/isdn/i4l/isdn_x25iface.c | 16 ++++++++-------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/drivers/isdn/i4l/isdn_concap.c b/drivers/isdn/i4l/isdn_concap.c index 91d57304d4d3..336523ec077c 100644 --- a/drivers/isdn/i4l/isdn_concap.c +++ b/drivers/isdn/i4l/isdn_concap.c @@ -80,9 +80,9 @@ static int isdn_concap_dl_disconn_req(struct concap_proto *concap) } struct concap_device_ops isdn_concap_reliable_dl_dops = { - &isdn_concap_dl_data_req, - &isdn_concap_dl_connect_req, - &isdn_concap_dl_disconn_req + .data_req = &isdn_concap_dl_data_req, + .connect_req = &isdn_concap_dl_connect_req, + .disconn_req = &isdn_concap_dl_disconn_req }; /* The following should better go into a dedicated source file such that diff --git a/drivers/isdn/i4l/isdn_x25iface.c b/drivers/isdn/i4l/isdn_x25iface.c index 0c5d8de41b23..ba60076e0b95 100644 --- a/drivers/isdn/i4l/isdn_x25iface.c +++ b/drivers/isdn/i4l/isdn_x25iface.c @@ -53,14 +53,14 @@ static int isdn_x25iface_disconn_ind(struct concap_proto *); static struct concap_proto_ops ix25_pops = { - &isdn_x25iface_proto_new, - &isdn_x25iface_proto_del, - &isdn_x25iface_proto_restart, - &isdn_x25iface_proto_close, - &isdn_x25iface_xmit, - &isdn_x25iface_receive, - &isdn_x25iface_connect_ind, - &isdn_x25iface_disconn_ind + .proto_new = &isdn_x25iface_proto_new, + .proto_del = &isdn_x25iface_proto_del, + .restart = &isdn_x25iface_proto_restart, + .close = &isdn_x25iface_proto_close, + .encap_and_xmit = &isdn_x25iface_xmit, + .data_ind = &isdn_x25iface_receive, + .connect_ind = &isdn_x25iface_connect_ind, + .disconn_ind = &isdn_x25iface_disconn_ind }; /* error message helper function */ From e999cb43d51f3635afd6253c5c066798ad998255 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 16 Dec 2016 17:03:39 -0800 Subject: [PATCH 45/63] net/x25: use designated initializers Prepare to mark sensitive kernel structures for randomization by making sure they're using designated initializers. These were identified during allyesconfig builds of x86, arm, and arm64, with most initializer fixes extracted from grsecurity. Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- net/x25/sysctl_net_x25.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/x25/sysctl_net_x25.c b/net/x25/sysctl_net_x25.c index 43239527a205..a06dfe143c67 100644 --- a/net/x25/sysctl_net_x25.c +++ b/net/x25/sysctl_net_x25.c @@ -70,7 +70,7 @@ static struct ctl_table x25_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { 0, }, + { }, }; void __init x25_register_sysctl(void) From 88edf10315c8d72db70d39f3851cf2c91abdb634 Mon Sep 17 00:00:00 2001 From: Lionel Gauthier Date: Thu, 15 Dec 2016 22:35:52 +0100 Subject: [PATCH 46/63] gtp: gtp_check_src_ms_ipv4() always return success gtp_check_src_ms_ipv4() did not find the PDP context matching with the UE IP address because the memory location is not right, but the result is inverted by the Boolean "not" operator. So whatever is the PDP context, any call to this function is successful. Signed-off-by: Lionel Gauthier Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- drivers/net/gtp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 98f10c216521..6031d499f2be 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -158,9 +158,9 @@ static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx, if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr))) return false; - iph = (struct iphdr *)(skb->data + hdrlen + sizeof(struct iphdr)); + iph = (struct iphdr *)(skb->data + hdrlen); - return iph->saddr != pctx->ms_addr_ip4.s_addr; + return iph->saddr == pctx->ms_addr_ip4.s_addr; } /* Check if the inner IP source address in this packet is assigned to any From d928be81b44dc3cad75d7a9f9fcbe99725dc7e56 Mon Sep 17 00:00:00 2001 From: Harald Welte Date: Thu, 15 Dec 2016 22:35:53 +0100 Subject: [PATCH 47/63] gtp: Fix initialization of Flags octet in GTPv1 header When generating a GTPv1 header in gtp1_push_header(), initialize the 'reserved' bit to zero. All 3GPP specifications for GTPv1 from Release 99 through Release 13 agree that a transmitter shall set this bit to zero, see e.g. Note 0 of Figure 2 in Section 6 of 3GPP TS 29.060 v13.5.0 Release 13, available from http://www.etsi.org/deliver/etsi_ts/129000_129099/129060/13.05.00_60/ts_129060v130500p.pdf Signed-off-by: Harald Welte Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- drivers/net/gtp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 6031d499f2be..8b6810bad54b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -423,11 +423,11 @@ static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) /* Bits 8 7 6 5 4 3 2 1 * +--+--+--+--+--+--+--+--+ - * |version |PT| 1| E| S|PN| + * |version |PT| 0| E| S|PN| * +--+--+--+--+--+--+--+--+ * 0 0 1 1 1 0 0 0 */ - gtp1->flags = 0x38; /* v1, GTP-non-prime. */ + gtp1->flags = 0x30; /* v1, GTP-non-prime. */ gtp1->type = GTP_TPDU; gtp1->length = htons(payload_len); gtp1->tid = htonl(pctx->u.v1.o_tei); From aafe6ae9cee32df85eb5e8bb6dd1d918e6807b09 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:57 +0100 Subject: [PATCH 48/63] bpf: dynamically allocate digest scratch buffer Geert rightfully complained that 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") added a too large allocation of variable 'raw' from bss section, and should instead be done dynamically: # ./scripts/bloat-o-meter kernel/bpf/core.o.1 kernel/bpf/core.o.2 add/remove: 3/0 grow/shrink: 0/0 up/down: 33291/0 (33291) function old new delta raw - 32832 +32832 [...] Since this is only relevant during program creation path, which can be considered slow-path anyway, lets allocate that dynamically and be not implicitly dependent on verifier mutex. Move bpf_prog_calc_digest() at the beginning of replace_map_fd_with_map_ptr() and also error handling stays straight forward. Reported-by: Geert Uytterhoeven Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 +- include/linux/filter.h | 14 +++++++++++--- kernel/bpf/core.c | 27 ++++++++++++++++----------- kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 6 ++++-- 5 files changed, 33 insertions(+), 18 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8796ff03f472..201eb483c46f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -216,7 +216,7 @@ u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); -void bpf_prog_calc_digest(struct bpf_prog *fp); +int bpf_prog_calc_digest(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/include/linux/filter.h b/include/linux/filter.h index af8a1804cac6..702314253797 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -57,9 +57,6 @@ struct bpf_prog_aux; /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 -/* Maximum BPF program size in bytes. */ -#define MAX_BPF_SIZE (BPF_MAXINSNS * sizeof(struct bpf_insn)) - /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ @@ -517,6 +514,17 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, return BPF_PROG_RUN(prog, xdp); } +static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) +{ + return prog->len * sizeof(struct bpf_insn); +} + +static inline u32 bpf_prog_digest_scratch_size(const struct bpf_prog *prog) +{ + return round_up(bpf_prog_insn_size(prog) + + sizeof(__be64) + 1, SHA_MESSAGE_BYTES); +} + static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 83e0d153b0b4..75c08b8068d6 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -136,28 +136,29 @@ void __bpf_prog_free(struct bpf_prog *fp) vfree(fp); } -#define SHA_BPF_RAW_SIZE \ - round_up(MAX_BPF_SIZE + sizeof(__be64) + 1, SHA_MESSAGE_BYTES) - -/* Called under verifier mutex. */ -void bpf_prog_calc_digest(struct bpf_prog *fp) +int bpf_prog_calc_digest(struct bpf_prog *fp) { const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64); - static u32 ws[SHA_WORKSPACE_WORDS]; - static u8 raw[SHA_BPF_RAW_SIZE]; - struct bpf_insn *dst = (void *)raw; + u32 raw_size = bpf_prog_digest_scratch_size(fp); + u32 ws[SHA_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; + struct bpf_insn *dst; bool was_ld_map; - u8 *todo = raw; + u8 *raw, *todo; __be32 *result; __be64 *bits; + raw = vmalloc(raw_size); + if (!raw) + return -ENOMEM; + sha_init(fp->digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation * since they are unstable from user space side. */ + dst = (void *)raw; for (i = 0, was_ld_map = false; i < fp->len; i++) { dst[i] = fp->insnsi[i]; if (!was_ld_map && @@ -177,12 +178,13 @@ void bpf_prog_calc_digest(struct bpf_prog *fp) } } - psize = fp->len * sizeof(struct bpf_insn); - memset(&raw[psize], 0, sizeof(raw) - psize); + psize = bpf_prog_insn_size(fp); + memset(&raw[psize], 0, raw_size - psize); raw[psize++] = 0x80; bsize = round_up(psize, SHA_MESSAGE_BYTES); blocks = bsize / SHA_MESSAGE_BYTES; + todo = raw; if (bsize - psize >= sizeof(__be64)) { bits = (__be64 *)(todo + bsize - sizeof(__be64)); } else { @@ -199,6 +201,9 @@ void bpf_prog_calc_digest(struct bpf_prog *fp) result = (__force __be32 *)fp->digest; for (i = 0; i < SHA_DIGEST_WORDS; i++) result[i] = cpu_to_be32(fp->digest[i]); + + vfree(raw); + return 0; } static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4819ec9d95f6..35d674c1f12e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -811,7 +811,7 @@ static int bpf_prog_load(union bpf_attr *attr) err = -EFAULT; if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), - prog->len * sizeof(struct bpf_insn)) != 0) + bpf_prog_insn_size(prog)) != 0) goto free_prog; prog->orig_prog = NULL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 81e267bc4640..64b7b1abe087 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2931,6 +2931,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) int insn_cnt = env->prog->len; int i, j, err; + err = bpf_prog_calc_digest(env->prog); + if (err) + return err; + for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { @@ -3178,8 +3182,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) log_level = 0; } - bpf_prog_calc_digest(env->prog); - ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; From 5ccb071e97fbd9ffe623a0d3977cc6d013bee93c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:58 +0100 Subject: [PATCH 49/63] bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 11 +++++++++++ kernel/bpf/core.c | 16 +++++++++++++--- kernel/bpf/syscall.c | 36 ++++++++++++++++++++++++++++-------- 3 files changed, 52 insertions(+), 11 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 201eb483c46f..f74ae68086dc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -238,6 +238,8 @@ struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); +int __bpf_prog_charge(struct user_struct *user, u32 pages); +void __bpf_prog_uncharge(struct user_struct *user, u32 pages); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); @@ -318,6 +320,15 @@ static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } + +static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) +{ + return 0; +} + +static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) +{ +} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 75c08b8068d6..1eb4f1303756 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -105,19 +105,29 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; + u32 pages, delta; + int ret; BUG_ON(fp_old == NULL); size = round_up(size, PAGE_SIZE); - if (size <= fp_old->pages * PAGE_SIZE) + pages = size / PAGE_SIZE; + if (pages <= fp_old->pages) return fp_old; + delta = pages - fp_old->pages; + ret = __bpf_prog_charge(fp_old->aux->user, delta); + if (ret) + return NULL; + fp = __vmalloc(size, gfp_flags, PAGE_KERNEL); - if (fp != NULL) { + if (fp == NULL) { + __bpf_prog_uncharge(fp_old->aux->user, delta); + } else { kmemcheck_annotate_bitfield(fp, meta); memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); - fp->pages = size / PAGE_SIZE; + fp->pages = pages; fp->aux->prog = fp; /* We keep fp->aux from fp_old around in the new diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 35d674c1f12e..e89acea22ecf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -615,19 +615,39 @@ static void free_used_maps(struct bpf_prog_aux *aux) kfree(aux->used_maps); } +int __bpf_prog_charge(struct user_struct *user, u32 pages) +{ + unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + unsigned long user_bufs; + + if (user) { + user_bufs = atomic_long_add_return(pages, &user->locked_vm); + if (user_bufs > memlock_limit) { + atomic_long_sub(pages, &user->locked_vm); + return -EPERM; + } + } + + return 0; +} + +void __bpf_prog_uncharge(struct user_struct *user, u32 pages) +{ + if (user) + atomic_long_sub(pages, &user->locked_vm); +} + static int bpf_prog_charge_memlock(struct bpf_prog *prog) { struct user_struct *user = get_current_user(); - unsigned long memlock_limit; + int ret; - memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - atomic_long_add(prog->pages, &user->locked_vm); - if (atomic_long_read(&user->locked_vm) > memlock_limit) { - atomic_long_sub(prog->pages, &user->locked_vm); + ret = __bpf_prog_charge(user, prog->pages); + if (ret) { free_uid(user); - return -EPERM; + return ret; } + prog->aux->user = user; return 0; } @@ -636,7 +656,7 @@ static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) { struct user_struct *user = prog->aux->user; - atomic_long_sub(prog->pages, &user->locked_vm); + __bpf_prog_uncharge(user, prog->pages); free_uid(user); } From 6760bf2ddde8ad64f8205a651223a93de3a35494 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 18 Dec 2016 01:52:59 +0100 Subject: [PATCH 50/63] bpf: fix mark_reg_unknown_value for spilled regs on map value marking Martin reported a verifier issue that hit the BUG_ON() for his test case in the mark_reg_unknown_value() function: [ 202.861380] kernel BUG at kernel/bpf/verifier.c:467! [...] [ 203.291109] Call Trace: [ 203.296501] [] mark_map_reg+0x45/0x50 [ 203.308225] [] mark_map_regs+0x78/0x90 [ 203.320140] [] do_check+0x226d/0x2c90 [ 203.331865] [] bpf_check+0x48b/0x780 [ 203.343403] [] bpf_prog_load+0x27e/0x440 [ 203.355705] [] ? handle_mm_fault+0x11af/0x1230 [ 203.369158] [] ? security_capable+0x48/0x60 [ 203.382035] [] SyS_bpf+0x124/0x960 [ 203.393185] [] ? __do_page_fault+0x276/0x490 [ 203.406258] [] entry_SYSCALL_64_fastpath+0x13/0x94 This issue got uncovered after the fix in a08dd0da5307 ("bpf: fix regression on verifier pruning wrt map lookups"). The reason why it wasn't noticed before was, because as mentioned in a08dd0da5307, mark_map_regs() was doing the id matching incorrectly based on the uncached regs[regno].id. So, in the first loop, we walked all regs and as soon as we found regno == i, then this reg's id was cleared when calling mark_reg_unknown_value() thus that every subsequent register was probed against id of 0 (which, in combination with the PTR_TO_MAP_VALUE_OR_NULL type is an invalid condition that no other register state can hold), and therefore wasn't type transitioned such as in the spilled register case for the second loop. Now since that got fixed, it turned out that 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") used mark_reg_unknown_value() incorrectly for the spilled regs, and thus hitting the BUG_ON() in some cases due to regno >= MAX_BPF_REG. Although spilled regs have the same type as the non-spilled regs for the verifier state, that is, struct bpf_reg_state, they are semantically different from the non-spilled regs. In other words, there can be up to 64 (MAX_BPF_STACK / BPF_REG_SIZE) spilled regs in the stack, for example, register R could have been spilled by the program to stack location X, Y, Z, and in mark_map_regs() we need to scan these stack slots of type STACK_SPILL for potential registers that we have to transition from PTR_TO_MAP_VALUE_OR_NULL. Therefore, depending on the location, the spilled_regs regno can be a lot higher than just MAX_BPF_REG's value since we operate on stack instead. The reset in mark_reg_unknown_value() itself is just fine, only that the BUG_ON() was inappropriate for this. Fix it by making a __mark_reg_unknown_value() version that can be called from mark_map_reg() generically; we know for the non-spilled case that the regno is always < MAX_BPF_REG anyway. Fixes: 57a09bf0a416 ("bpf: Detect identical PTR_TO_MAP_VALUE_OR_NULL registers") Reported-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 64b7b1abe087..83ed2f8f6f22 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -462,14 +462,19 @@ static void init_reg_state(struct bpf_reg_state *regs) regs[BPF_REG_1].type = PTR_TO_CTX; } -static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno) +static void __mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno) { - BUG_ON(regno >= MAX_BPF_REG); regs[regno].type = UNKNOWN_VALUE; regs[regno].id = 0; regs[regno].imm = 0; } +static void mark_reg_unknown_value(struct bpf_reg_state *regs, u32 regno) +{ + BUG_ON(regno >= MAX_BPF_REG); + __mark_reg_unknown_value(regs, regno); +} + static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno) { regs[regno].min_value = BPF_REGISTER_MIN_RANGE; @@ -1976,7 +1981,7 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, */ reg->id = 0; if (type == UNKNOWN_VALUE) - mark_reg_unknown_value(regs, regno); + __mark_reg_unknown_value(regs, regno); } } From 49cad93909b18acf942b70356e65eeeaa9ca9d23 Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Sun, 11 Dec 2016 22:47:50 +0100 Subject: [PATCH 51/63] net: chelsio: cxgb2: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 64 +++++++++++++---------- 1 file changed, 37 insertions(+), 27 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index 81d1d0bc7553..3a05f9098e75 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -568,28 +568,33 @@ static void get_regs(struct net_device *dev, struct ethtool_regs *regs, reg_block_dump(ap, buf, A_MC5_CONFIG, A_MC5_MASK_WRITE_CMD); } -static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct adapter *adapter = dev->ml_priv; struct port_info *p = &adapter->port[dev->if_port]; + u32 supported, advertising; - cmd->supported = p->link_config.supported; - cmd->advertising = p->link_config.advertising; + supported = p->link_config.supported; + advertising = p->link_config.advertising; if (netif_carrier_ok(dev)) { - ethtool_cmd_speed_set(cmd, p->link_config.speed); - cmd->duplex = p->link_config.duplex; + cmd->base.speed = p->link_config.speed; + cmd->base.duplex = p->link_config.duplex; } else { - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); - cmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } - cmd->port = (cmd->supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE; - cmd->phy_address = p->phy->mdio.prtad; - cmd->transceiver = XCVR_EXTERNAL; - cmd->autoneg = p->link_config.autoneg; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + cmd->base.port = (supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE; + cmd->base.phy_address = p->phy->mdio.prtad; + cmd->base.autoneg = p->link_config.autoneg; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + return 0; } @@ -628,36 +633,41 @@ static int speed_duplex_to_caps(int speed, int duplex) ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full | \ ADVERTISED_10000baseT_Full) -static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct adapter *adapter = dev->ml_priv; struct port_info *p = &adapter->port[dev->if_port]; struct link_config *lc = &p->link_config; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if (!(lc->supported & SUPPORTED_Autoneg)) return -EOPNOTSUPP; /* can't change speed/duplex */ - if (cmd->autoneg == AUTONEG_DISABLE) { - u32 speed = ethtool_cmd_speed(cmd); - int cap = speed_duplex_to_caps(speed, cmd->duplex); + if (cmd->base.autoneg == AUTONEG_DISABLE) { + u32 speed = cmd->base.speed; + int cap = speed_duplex_to_caps(speed, cmd->base.duplex); if (!(lc->supported & cap) || (speed == SPEED_1000)) return -EINVAL; lc->requested_speed = speed; - lc->requested_duplex = cmd->duplex; + lc->requested_duplex = cmd->base.duplex; lc->advertising = 0; } else { - cmd->advertising &= ADVERTISED_MASK; - if (cmd->advertising & (cmd->advertising - 1)) - cmd->advertising = lc->supported; - cmd->advertising &= lc->supported; - if (!cmd->advertising) + advertising &= ADVERTISED_MASK; + if (advertising & (advertising - 1)) + advertising = lc->supported; + advertising &= lc->supported; + if (!advertising) return -EINVAL; lc->requested_speed = SPEED_INVALID; lc->requested_duplex = DUPLEX_INVALID; - lc->advertising = cmd->advertising | ADVERTISED_Autoneg; + lc->advertising = advertising | ADVERTISED_Autoneg; } - lc->autoneg = cmd->autoneg; + lc->autoneg = cmd->base.autoneg; if (netif_running(dev)) t1_link_start(p->phy, p->mac, lc); return 0; @@ -788,8 +798,6 @@ static int get_eeprom(struct net_device *dev, struct ethtool_eeprom *e, } static const struct ethtool_ops t1_ethtool_ops = { - .get_settings = get_settings, - .set_settings = set_settings, .get_drvinfo = get_drvinfo, .get_msglevel = get_msglevel, .set_msglevel = set_msglevel, @@ -807,6 +815,8 @@ static const struct ethtool_ops t1_ethtool_ops = { .get_ethtool_stats = get_stats, .get_regs_len = get_regs_len, .get_regs = get_regs, + .get_link_ksettings = get_link_ksettings, + .set_link_ksettings = set_link_ksettings, }; static int t1_ioctl(struct net_device *dev, struct ifreq *req, int cmd) From b7b44fd23e6d2a896c6efbe85b39862f14aae11a Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 12 Dec 2016 00:27:49 +0100 Subject: [PATCH 52/63] net: chelsio: cxgb3: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- .../net/ethernet/chelsio/cxgb3/cxgb3_main.c | 65 +++++++++++-------- 1 file changed, 37 insertions(+), 28 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 092b3c16440b..7b2224ae72f2 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1801,27 +1801,31 @@ static int set_phys_id(struct net_device *dev, return 0; } -static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct port_info *p = netdev_priv(dev); + u32 supported; - cmd->supported = p->link_config.supported; - cmd->advertising = p->link_config.advertising; + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + p->link_config.supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + p->link_config.advertising); if (netif_carrier_ok(dev)) { - ethtool_cmd_speed_set(cmd, p->link_config.speed); - cmd->duplex = p->link_config.duplex; + cmd->base.speed = p->link_config.speed; + cmd->base.duplex = p->link_config.duplex; } else { - ethtool_cmd_speed_set(cmd, SPEED_UNKNOWN); - cmd->duplex = DUPLEX_UNKNOWN; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; } - cmd->port = (cmd->supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE; - cmd->phy_address = p->phy.mdio.prtad; - cmd->transceiver = XCVR_EXTERNAL; - cmd->autoneg = p->link_config.autoneg; - cmd->maxtxpkt = 0; - cmd->maxrxpkt = 0; + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + + cmd->base.port = (supported & SUPPORTED_TP) ? PORT_TP : PORT_FIBRE; + cmd->base.phy_address = p->phy.mdio.prtad; + cmd->base.autoneg = p->link_config.autoneg; return 0; } @@ -1860,44 +1864,49 @@ static int speed_duplex_to_caps(int speed, int duplex) ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full | \ ADVERTISED_10000baseT_Full) -static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct port_info *p = netdev_priv(dev); struct link_config *lc = &p->link_config; + u32 advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); if (!(lc->supported & SUPPORTED_Autoneg)) { /* * PHY offers a single speed/duplex. See if that's what's * being requested. */ - if (cmd->autoneg == AUTONEG_DISABLE) { - u32 speed = ethtool_cmd_speed(cmd); - int cap = speed_duplex_to_caps(speed, cmd->duplex); + if (cmd->base.autoneg == AUTONEG_DISABLE) { + u32 speed = cmd->base.speed; + int cap = speed_duplex_to_caps(speed, cmd->base.duplex); if (lc->supported & cap) return 0; } return -EINVAL; } - if (cmd->autoneg == AUTONEG_DISABLE) { - u32 speed = ethtool_cmd_speed(cmd); - int cap = speed_duplex_to_caps(speed, cmd->duplex); + if (cmd->base.autoneg == AUTONEG_DISABLE) { + u32 speed = cmd->base.speed; + int cap = speed_duplex_to_caps(speed, cmd->base.duplex); if (!(lc->supported & cap) || (speed == SPEED_1000)) return -EINVAL; lc->requested_speed = speed; - lc->requested_duplex = cmd->duplex; + lc->requested_duplex = cmd->base.duplex; lc->advertising = 0; } else { - cmd->advertising &= ADVERTISED_MASK; - cmd->advertising &= lc->supported; - if (!cmd->advertising) + advertising &= ADVERTISED_MASK; + advertising &= lc->supported; + if (!advertising) return -EINVAL; lc->requested_speed = SPEED_INVALID; lc->requested_duplex = DUPLEX_INVALID; - lc->advertising = cmd->advertising | ADVERTISED_Autoneg; + lc->advertising = advertising | ADVERTISED_Autoneg; } - lc->autoneg = cmd->autoneg; + lc->autoneg = cmd->base.autoneg; if (netif_running(dev)) t3_link_start(&p->phy, &p->mac, lc); return 0; @@ -2097,8 +2106,6 @@ static void get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) } static const struct ethtool_ops cxgb_ethtool_ops = { - .get_settings = get_settings, - .set_settings = set_settings, .get_drvinfo = get_drvinfo, .get_msglevel = get_msglevel, .set_msglevel = set_msglevel, @@ -2120,6 +2127,8 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_regs_len = get_regs_len, .get_regs = get_regs, .get_wol = get_wol, + .get_link_ksettings = get_link_ksettings, + .set_link_ksettings = set_link_ksettings, }; static int in_range(int val, int lo, int hi) From 93dfe6c290123f1059828001678e6f8b1a102d9a Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Mon, 12 Dec 2016 23:28:33 +0100 Subject: [PATCH 53/63] net: cirrus: ep93xx: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/cirrus/ep93xx_eth.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/cirrus/ep93xx_eth.c b/drivers/net/ethernet/cirrus/ep93xx_eth.c index a1de0d12927d..396c88678eab 100644 --- a/drivers/net/ethernet/cirrus/ep93xx_eth.c +++ b/drivers/net/ethernet/cirrus/ep93xx_eth.c @@ -715,16 +715,18 @@ static void ep93xx_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); } -static int ep93xx_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ep93xx_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct ep93xx_priv *ep = netdev_priv(dev); - return mii_ethtool_gset(&ep->mii, cmd); + return mii_ethtool_get_link_ksettings(&ep->mii, cmd); } -static int ep93xx_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int ep93xx_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct ep93xx_priv *ep = netdev_priv(dev); - return mii_ethtool_sset(&ep->mii, cmd); + return mii_ethtool_set_link_ksettings(&ep->mii, cmd); } static int ep93xx_nway_reset(struct net_device *dev) @@ -741,10 +743,10 @@ static u32 ep93xx_get_link(struct net_device *dev) static const struct ethtool_ops ep93xx_ethtool_ops = { .get_drvinfo = ep93xx_get_drvinfo, - .get_settings = ep93xx_get_settings, - .set_settings = ep93xx_set_settings, .nway_reset = ep93xx_nway_reset, .get_link = ep93xx_get_link, + .get_link_ksettings = ep93xx_get_link_ksettings, + .set_link_ksettings = ep93xx_set_link_ksettings, }; static const struct net_device_ops ep93xx_netdev_ops = { From 99bff5ee44f32c3ca5115922e487b067d9c3dd6b Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Wed, 14 Dec 2016 10:01:58 +0100 Subject: [PATCH 54/63] net: davicom: dm9000: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. Signed-off-by: Philippe Reynes Signed-off-by: David S. Miller --- drivers/net/ethernet/davicom/dm9000.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index f1a81c52afe3..008dc8161775 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -570,19 +570,21 @@ static void dm9000_set_msglevel(struct net_device *dev, u32 value) dm->msg_enable = value; } -static int dm9000_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int dm9000_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { struct board_info *dm = to_dm9000_board(dev); - mii_ethtool_gset(&dm->mii, cmd); + mii_ethtool_get_link_ksettings(&dm->mii, cmd); return 0; } -static int dm9000_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int dm9000_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { struct board_info *dm = to_dm9000_board(dev); - return mii_ethtool_sset(&dm->mii, cmd); + return mii_ethtool_set_link_ksettings(&dm->mii, cmd); } static int dm9000_nway_reset(struct net_device *dev) @@ -741,8 +743,6 @@ static int dm9000_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) static const struct ethtool_ops dm9000_ethtool_ops = { .get_drvinfo = dm9000_get_drvinfo, - .get_settings = dm9000_get_settings, - .set_settings = dm9000_set_settings, .get_msglevel = dm9000_get_msglevel, .set_msglevel = dm9000_set_msglevel, .nway_reset = dm9000_nway_reset, @@ -752,6 +752,8 @@ static const struct ethtool_ops dm9000_ethtool_ops = { .get_eeprom_len = dm9000_get_eeprom_len, .get_eeprom = dm9000_get_eeprom, .set_eeprom = dm9000_set_eeprom, + .get_link_ksettings = dm9000_get_link_ksettings, + .set_link_ksettings = dm9000_set_link_ksettings, }; static void dm9000_show_carrier(struct board_info *db, From 7cafe8f82438ced6de4c6f17b872a02c10f7a63a Mon Sep 17 00:00:00 2001 From: Philippe Reynes Date: Thu, 15 Dec 2016 00:12:53 +0100 Subject: [PATCH 55/63] net: sfc: use new api ethtool_{get|set}_link_ksettings The ethtool api {get|set}_settings is deprecated. We move this driver to new api {get|set}_link_ksettings. Signed-off-by: Philippe Reynes Tested-by: Bert Kenward Acked-by: Bert Kenward Signed-off-by: David S. Miller --- drivers/net/ethernet/sfc/ethtool.c | 35 ++++++++++------ drivers/net/ethernet/sfc/mcdi_port.c | 58 +++++++++++++++++---------- drivers/net/ethernet/sfc/net_driver.h | 12 +++--- 3 files changed, 64 insertions(+), 41 deletions(-) diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index f644216eda1b..87bdc56b4e3a 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -120,44 +120,53 @@ static int efx_ethtool_phys_id(struct net_device *net_dev, } /* This must be called with rtnl_lock held. */ -static int efx_ethtool_get_settings(struct net_device *net_dev, - struct ethtool_cmd *ecmd) +static int +efx_ethtool_get_link_ksettings(struct net_device *net_dev, + struct ethtool_link_ksettings *cmd) { struct efx_nic *efx = netdev_priv(net_dev); struct efx_link_state *link_state = &efx->link_state; + u32 supported; mutex_lock(&efx->mac_lock); - efx->phy_op->get_settings(efx, ecmd); + efx->phy_op->get_link_ksettings(efx, cmd); mutex_unlock(&efx->mac_lock); /* Both MACs support pause frames (bidirectional and respond-only) */ - ecmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + ethtool_convert_link_mode_to_legacy_u32(&supported, + cmd->link_modes.supported); + + supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); if (LOOPBACK_INTERNAL(efx)) { - ethtool_cmd_speed_set(ecmd, link_state->speed); - ecmd->duplex = link_state->fd ? DUPLEX_FULL : DUPLEX_HALF; + cmd->base.speed = link_state->speed; + cmd->base.duplex = link_state->fd ? DUPLEX_FULL : DUPLEX_HALF; } return 0; } /* This must be called with rtnl_lock held. */ -static int efx_ethtool_set_settings(struct net_device *net_dev, - struct ethtool_cmd *ecmd) +static int +efx_ethtool_set_link_ksettings(struct net_device *net_dev, + const struct ethtool_link_ksettings *cmd) { struct efx_nic *efx = netdev_priv(net_dev); int rc; /* GMAC does not support 1000Mbps HD */ - if ((ethtool_cmd_speed(ecmd) == SPEED_1000) && - (ecmd->duplex != DUPLEX_FULL)) { + if ((cmd->base.speed == SPEED_1000) && + (cmd->base.duplex != DUPLEX_FULL)) { netif_dbg(efx, drv, efx->net_dev, "rejecting unsupported 1000Mbps HD setting\n"); return -EINVAL; } mutex_lock(&efx->mac_lock); - rc = efx->phy_op->set_settings(efx, ecmd); + rc = efx->phy_op->set_link_ksettings(efx, cmd); mutex_unlock(&efx->mac_lock); return rc; } @@ -1342,8 +1351,6 @@ static int efx_ethtool_get_module_info(struct net_device *net_dev, } const struct ethtool_ops efx_ethtool_ops = { - .get_settings = efx_ethtool_get_settings, - .set_settings = efx_ethtool_set_settings, .get_drvinfo = efx_ethtool_get_drvinfo, .get_regs_len = efx_ethtool_get_regs_len, .get_regs = efx_ethtool_get_regs, @@ -1373,4 +1380,6 @@ const struct ethtool_ops efx_ethtool_ops = { .get_ts_info = efx_ethtool_get_ts_info, .get_module_info = efx_ethtool_get_module_info, .get_module_eeprom = efx_ethtool_get_module_eeprom, + .get_link_ksettings = efx_ethtool_get_link_ksettings, + .set_link_ksettings = efx_ethtool_set_link_ksettings, }; diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index 9dcd396784ae..c905971c5f3a 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -503,45 +503,59 @@ static void efx_mcdi_phy_remove(struct efx_nic *efx) kfree(phy_data); } -static void efx_mcdi_phy_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) +static void efx_mcdi_phy_get_link_ksettings(struct efx_nic *efx, + struct ethtool_link_ksettings *cmd) { struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN); int rc; + u32 supported, advertising, lp_advertising; - ecmd->supported = - mcdi_to_ethtool_cap(phy_cfg->media, phy_cfg->supported_cap); - ecmd->advertising = efx->link_advertising; - ethtool_cmd_speed_set(ecmd, efx->link_state.speed); - ecmd->duplex = efx->link_state.fd; - ecmd->port = mcdi_to_ethtool_media(phy_cfg->media); - ecmd->phy_address = phy_cfg->port; - ecmd->transceiver = XCVR_INTERNAL; - ecmd->autoneg = !!(efx->link_advertising & ADVERTISED_Autoneg); - ecmd->mdio_support = (efx->mdio.mode_support & + supported = mcdi_to_ethtool_cap(phy_cfg->media, phy_cfg->supported_cap); + advertising = efx->link_advertising; + cmd->base.speed = efx->link_state.speed; + cmd->base.duplex = efx->link_state.fd; + cmd->base.port = mcdi_to_ethtool_media(phy_cfg->media); + cmd->base.phy_address = phy_cfg->port; + cmd->base.autoneg = !!(efx->link_advertising & ADVERTISED_Autoneg); + cmd->base.mdio_support = (efx->mdio.mode_support & (MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22)); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, + advertising); + BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, outbuf, sizeof(outbuf), NULL); if (rc) return; - ecmd->lp_advertising = + lp_advertising = mcdi_to_ethtool_cap(phy_cfg->media, MCDI_DWORD(outbuf, GET_LINK_OUT_LP_CAP)); + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising, + lp_advertising); } -static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd) +static int +efx_mcdi_phy_set_link_ksettings(struct efx_nic *efx, + const struct ethtool_link_ksettings *cmd) { struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; u32 caps; int rc; + u32 advertising; - if (ecmd->autoneg) { - caps = (ethtool_to_mcdi_cap(ecmd->advertising) | + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); + + if (cmd->base.autoneg) { + caps = (ethtool_to_mcdi_cap(advertising) | 1 << MC_CMD_PHY_CAP_AN_LBN); - } else if (ecmd->duplex) { - switch (ethtool_cmd_speed(ecmd)) { + } else if (cmd->base.duplex) { + switch (cmd->base.speed) { case 10: caps = 1 << MC_CMD_PHY_CAP_10FDX_LBN; break; case 100: caps = 1 << MC_CMD_PHY_CAP_100FDX_LBN; break; case 1000: caps = 1 << MC_CMD_PHY_CAP_1000FDX_LBN; break; @@ -550,7 +564,7 @@ static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ec default: return -EINVAL; } } else { - switch (ethtool_cmd_speed(ecmd)) { + switch (cmd->base.speed) { case 10: caps = 1 << MC_CMD_PHY_CAP_10HDX_LBN; break; case 100: caps = 1 << MC_CMD_PHY_CAP_100HDX_LBN; break; case 1000: caps = 1 << MC_CMD_PHY_CAP_1000HDX_LBN; break; @@ -563,9 +577,9 @@ static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ec if (rc) return rc; - if (ecmd->autoneg) { + if (cmd->base.autoneg) { efx_link_set_advertising( - efx, ecmd->advertising | ADVERTISED_Autoneg); + efx, advertising | ADVERTISED_Autoneg); phy_cfg->forced_cap = 0; } else { efx_link_set_advertising(efx, 0); @@ -812,8 +826,8 @@ static const struct efx_phy_operations efx_mcdi_phy_ops = { .poll = efx_mcdi_phy_poll, .fini = efx_port_dummy_op_void, .remove = efx_mcdi_phy_remove, - .get_settings = efx_mcdi_phy_get_settings, - .set_settings = efx_mcdi_phy_set_settings, + .get_link_ksettings = efx_mcdi_phy_get_link_ksettings, + .set_link_ksettings = efx_mcdi_phy_set_link_ksettings, .test_alive = efx_mcdi_phy_test_alive, .run_tests = efx_mcdi_phy_run_tests, .test_name = efx_mcdi_phy_test_name, diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 8692e829b40f..1a635ced62d0 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -720,8 +720,8 @@ static inline bool efx_link_state_equal(const struct efx_link_state *left, * @reconfigure: Reconfigure PHY (e.g. for new link parameters) * @poll: Update @link_state and report whether it changed. * Serialised by the mac_lock. - * @get_settings: Get ethtool settings. Serialised by the mac_lock. - * @set_settings: Set ethtool settings. Serialised by the mac_lock. + * @get_link_ksettings: Get ethtool settings. Serialised by the mac_lock. + * @set_link_ksettings: Set ethtool settings. Serialised by the mac_lock. * @set_npage_adv: Set abilities advertised in (Extended) Next Page * (only needed where AN bit is set in mmds) * @test_alive: Test that PHY is 'alive' (online) @@ -736,10 +736,10 @@ struct efx_phy_operations { void (*remove) (struct efx_nic *efx); int (*reconfigure) (struct efx_nic *efx); bool (*poll) (struct efx_nic *efx); - void (*get_settings) (struct efx_nic *efx, - struct ethtool_cmd *ecmd); - int (*set_settings) (struct efx_nic *efx, - struct ethtool_cmd *ecmd); + void (*get_link_ksettings)(struct efx_nic *efx, + struct ethtool_link_ksettings *cmd); + int (*set_link_ksettings)(struct efx_nic *efx, + const struct ethtool_link_ksettings *cmd); void (*set_npage_adv) (struct efx_nic *efx, u32); int (*test_alive) (struct efx_nic *efx); const char *(*test_name) (struct efx_nic *efx, unsigned int index); From 3a7f0762a6b784ac9257287346e4f5f5f7f420b7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 12 Dec 2016 14:21:34 +0300 Subject: [PATCH 56/63] irda: w83977af_ir: cleanup an indent issue In commit 99d8d2159d7c ("irda: w83977af_ir: Neaten logging"), we accidentally added an extra tab to these lines. Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- drivers/net/irda/w83977af_ir.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c index f293d33fb28f..8d5b903d1d9d 100644 --- a/drivers/net/irda/w83977af_ir.c +++ b/drivers/net/irda/w83977af_ir.c @@ -517,9 +517,9 @@ static netdev_tx_t w83977af_hard_xmit(struct sk_buff *skb, mtt = irda_get_mtt(skb); pr_debug("%s: %ld, mtt=%d\n", __func__, jiffies, mtt); - if (mtt > 1000) - mdelay(mtt / 1000); - else if (mtt) + if (mtt > 1000) + mdelay(mtt / 1000); + else if (mtt) udelay(mtt); /* Enable DMA interrupt */ From c762eaa777b789540e3fe33581d6d0e593dbb22e Mon Sep 17 00:00:00 2001 From: Manuel Bessler Date: Thu, 15 Dec 2016 22:55:00 -0500 Subject: [PATCH 57/63] r6040: move spinlock in r6040_close as SOFTIRQ-unsafe lock order detected 'ifconfig eth0 down' makes r6040_close() trigger: INFO: HARDIRQ-safe -> HARDIRQ-unsafe lock order detected Fixed by moving calls to phy_stop(), napi_disable(), netif_stop_queue() to outside of the module's private spin_lock_irq block. Found on a Versalogic Tomcat SBC with a Vortex86 SoC s1660e_5150:~# sudo ifconfig eth0 down [ 61.306415] ====================================================== [ 61.306415] [ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ] [ 61.306415] 4.9.0-gb898d2d-manuel #1 Not tainted [ 61.306415] ------------------------------------------------------ [ 61.306415] ifconfig/449 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: [ 61.306415] (&dev->lock){+.+...}, at: [] phy_stop+0x16/0x80 [ 61.306415] and this task is already holding: [ 61.306415] (&(&lp->lock)->rlock){+.-...}, at: [] r6040_close+0x24/0x230 [r6040] which would create a new lock dependency: [ 61.306415] (&(&lp->lock)->rlock){+.-...} -> (&dev->lock){+.+...} [ 61.306415] but this new dependency connects a SOFTIRQ-irq-safe lock: [ 61.306415] (&(&lp->lock)->rlock){+.-...} [ 61.306415] ... which became SOFTIRQ-irq-safe at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x555/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] _raw_spin_lock_irqsave+0x24/0x40 [ 61.306415] [ 61.306415] [] r6040_start_xmit+0x30/0x1d0 [r6040] [ 61.306415] [ 61.306415] [] dev_hard_start_xmit+0x9d/0x2d0 [ 61.306415] [ 61.306415] [] sch_direct_xmit+0xa8/0x140 [ 61.306415] [ 61.306415] [] __dev_queue_xmit+0x416/0x780 [ 61.306415] [ 61.306415] [] dev_queue_xmit+0xa/0x10 [ 61.306415] [ 61.306415] [] neigh_resolve_output+0x147/0x220 [ 61.306415] [ 61.306415] [] ip6_finish_output2+0x2fb/0x910 [ 61.306415] [ 61.306415] [] ip6_finish_output+0xa6/0x1a0 [ 61.306415] [ 61.306415] [] ip6_output+0x55/0x320 [ 61.306415] [ 61.306415] [] mld_sendpack+0x352/0x560 [ 61.306415] [ 61.306415] [] mld_ifc_timer_expire+0x155/0x280 [ 61.306415] [ 61.306415] [] call_timer_fn+0x81/0x270 [ 61.306415] [ 61.306415] [] expire_timers+0xc1/0x180 [ 61.306415] [ 61.306415] [] run_timer_softirq+0x77/0x150 [ 61.306415] [ 61.306415] [] __do_softirq+0xb4/0x3d0 [ 61.306415] [ 61.306415] [] do_softirq_own_stack+0x1c/0x30 [ 61.306415] [ 61.306415] [] irq_exit+0x8e/0xa0 [ 61.306415] [ 61.306415] [] do_IRQ+0x51/0x100 [ 61.306415] [ 61.306415] [] common_interrupt+0x36/0x40 [ 61.306415] [ 61.306415] [] set_root+0x68/0xf0 [ 61.306415] [ 61.306415] [] path_init+0x400/0x640 [ 61.306415] [ 61.306415] [] path_lookupat+0xf/0xe0 [ 61.306415] [ 61.306415] [] filename_lookup+0x6c/0x100 [ 61.306415] [ 61.306415] [] user_path_at_empty+0x25/0x30 [ 61.306415] [ 61.306415] [] SyS_faccessat+0x86/0x1e0 [ 61.306415] [ 61.306415] [] SyS_access+0x10/0x20 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] [ 61.306415] to a SOFTIRQ-irq-unsafe lock: [ 61.306415] (&dev->lock){+.+...} [ 61.306415] ... which became SOFTIRQ-irq-unsafe at: [ 61.306415] ...[ 61.306415] [ 61.306415] [] __lock_acquire+0x59c/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] [ 61.306415] [] phy_probe+0x4d/0xc0 [ 61.306415] [ 61.306415] [] phy_attach_direct+0xbe/0x190 [ 61.306415] [ 61.306415] [] phy_connect_direct+0x17/0x60 [ 61.306415] [ 61.306415] [] phy_connect+0x33/0x70 [ 61.306415] [ 61.306415] [] r6040_init_one+0x3a0/0x500 [r6040] [ 61.306415] [ 61.306415] [] pci_device_probe+0x77/0xd0 [ 61.306415] [ 61.306415] [] driver_probe_device+0x145/0x280 [ 61.306415] [ 61.306415] [] __driver_attach+0x89/0x90 [ 61.306415] [ 61.306415] [] bus_for_each_dev+0x4f/0x80 [ 61.306415] [ 61.306415] [] driver_attach+0x14/0x20 [ 61.306415] [ 61.306415] [] bus_add_driver+0x197/0x210 [ 61.306415] [ 61.306415] [] driver_register+0x51/0xd0 [ 61.306415] [ 61.306415] [] __pci_register_driver+0x45/0x50 [ 61.306415] [ 61.306415] [] 0xd0938017 [ 61.306415] [ 61.306415] [] do_one_initcall+0x2f/0x140 [ 61.306415] [ 61.306415] [] do_init_module+0x4a/0x19b [ 61.306415] [ 61.306415] [] load_module+0x1b2e/0x2070 [ 61.306415] [ 61.306415] [] SyS_finit_module+0x69/0x80 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] [ 61.306415] other info that might help us debug this: [ 61.306415] [ 61.306415] Possible interrupt unsafe locking scenario: [ 61.306415] [ 61.306415] CPU0 CPU1 [ 61.306415] ---- ---- [ 61.306415] lock(&dev->lock); [ 61.306415] local_irq_disable(); [ 61.306415] lock(&(&lp->lock)->rlock); [ 61.306415] lock(&dev->lock); [ 61.306415] [ 61.306415] lock(&(&lp->lock)->rlock); [ 61.306415] [ 61.306415] *** DEADLOCK *** [ 61.306415] [ 61.306415] 2 locks held by ifconfig/449: [ 61.306415] #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0xf/0x20 [ 61.306415] #1: (&(&lp->lock)->rlock){+.-...}, at: [] r6040_close+0x24/0x230 [r6040] [ 61.306415] [ 61.306415] the dependencies between SOFTIRQ-irq-safe lock and the holding lock: [ 61.306415] -> (&(&lp->lock)->rlock){+.-...} ops: 3049 { [ 61.306415] HARDIRQ-ON-W at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x577/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] _raw_spin_lock+0x1b/0x30 [ 61.306415] [ 61.306415] [] r6040_poll+0x2c/0x330 [r6040] [ 61.306415] [ 61.306415] [] net_rx_action+0x197/0x340 [ 61.306415] [ 61.306415] [] __do_softirq+0xb4/0x3d0 [ 61.306415] [ 61.306415] [] run_ksoftirqd+0x17/0x40 [ 61.306415] [ 61.306415] [] smpboot_thread_fn+0x141/0x180 [ 61.306415] [ 61.306415] [] kthread+0xde/0x110 [ 61.306415] [ 61.306415] [] ret_from_fork+0x19/0x30 [ 61.306415] IN-SOFTIRQ-W at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x555/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] _raw_spin_lock_irqsave+0x24/0x40 [ 61.306415] [ 61.306415] [] r6040_start_xmit+0x30/0x1d0 [r6040] [ 61.306415] [ 61.306415] [] dev_hard_start_xmit+0x9d/0x2d0 [ 61.306415] [ 61.306415] [] sch_direct_xmit+0xa8/0x140 [ 61.306415] [ 61.306415] [] __dev_queue_xmit+0x416/0x780 [ 61.306415] [ 61.306415] [] dev_queue_xmit+0xa/0x10 [ 61.306415] [ 61.306415] [] neigh_resolve_output+0x147/0x220 [ 61.306415] [ 61.306415] [] ip6_finish_output2+0x2fb/0x910 [ 61.306415] [ 61.306415] [] ip6_finish_output+0xa6/0x1a0 [ 61.306415] [ 61.306415] [] ip6_output+0x55/0x320 [ 61.306415] [ 61.306415] [] mld_sendpack+0x352/0x560 [ 61.306415] [ 61.306415] [] mld_ifc_timer_expire+0x155/0x280 [ 61.306415] [ 61.306415] [] call_timer_fn+0x81/0x270 [ 61.306415] [ 61.306415] [] expire_timers+0xc1/0x180 [ 61.306415] [ 61.306415] [] run_timer_softirq+0x77/0x150 [ 61.306415] [ 61.306415] [] __do_softirq+0xb4/0x3d0 [ 61.306415] [ 61.306415] [] do_softirq_own_stack+0x1c/0x30 [ 61.306415] [ 61.306415] [] irq_exit+0x8e/0xa0 [ 61.306415] [ 61.306415] [] do_IRQ+0x51/0x100 [ 61.306415] [ 61.306415] [] common_interrupt+0x36/0x40 [ 61.306415] [ 61.306415] [] set_root+0x68/0xf0 [ 61.306415] [ 61.306415] [] path_init+0x400/0x640 [ 61.306415] [ 61.306415] [] path_lookupat+0xf/0xe0 [ 61.306415] [ 61.306415] [] filename_lookup+0x6c/0x100 [ 61.306415] [ 61.306415] [] user_path_at_empty+0x25/0x30 [ 61.306415] [ 61.306415] [] SyS_faccessat+0x86/0x1e0 [ 61.306415] [ 61.306415] [] SyS_access+0x10/0x20 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] INITIAL USE at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x1fe/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] _raw_spin_lock_irqsave+0x24/0x40 [ 61.306415] [ 61.306415] [] r6040_get_stats+0x1e/0x60 [r6040] [ 61.306415] [ 61.306415] [] dev_get_stats+0x96/0xc0 [ 61.306415] [ 61.306415] [] rtnl_fill_stats+0x36/0xfd [ 61.306415] [ 61.306415] [] rtnl_fill_ifinfo+0x47c/0xce0 [ 61.306415] [ 61.306415] [] rtmsg_ifinfo_build_skb+0x4e/0xd0 [ 61.306415] [ 61.306415] [] rtmsg_ifinfo.part.20+0x10/0x40 [ 61.306415] [ 61.306415] [] rtmsg_ifinfo+0x1b/0x20 [ 61.306415] [ 61.306415] [] register_netdevice+0x409/0x550 [ 61.306415] [ 61.306415] [] register_netdev+0x12/0x20 [ 61.306415] [ 61.306415] [] r6040_init_one+0x3e8/0x500 [r6040] [ 61.306415] [ 61.306415] [] pci_device_probe+0x77/0xd0 [ 61.306415] [ 61.306415] [] driver_probe_device+0x145/0x280 [ 61.306415] [ 61.306415] [] __driver_attach+0x89/0x90 [ 61.306415] [ 61.306415] [] bus_for_each_dev+0x4f/0x80 [ 61.306415] [ 61.306415] [] driver_attach+0x14/0x20 [ 61.306415] [ 61.306415] [] bus_add_driver+0x197/0x210 [ 61.306415] [ 61.306415] [] driver_register+0x51/0xd0 [ 61.306415] [ 61.306415] [] __pci_register_driver+0x45/0x50 [ 61.306415] [ 61.306415] [] 0xd0938017 [ 61.306415] [ 61.306415] [] do_one_initcall+0x2f/0x140 [ 61.306415] [ 61.306415] [] do_init_module+0x4a/0x19b [ 61.306415] [ 61.306415] [] load_module+0x1b2e/0x2070 [ 61.306415] [ 61.306415] [] SyS_finit_module+0x69/0x80 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] } [ 61.306415] ... key at: [] __key.45893+0x0/0xfffff739 [r6040] [ 61.306415] ... acquired at: [ 61.306415] [ 61.306415] [] check_irq_usage+0x42/0xb0 [ 61.306415] [ 61.306415] [] __lock_acquire+0x110c/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] [ 61.306415] [] phy_stop+0x16/0x80 [ 61.306415] [ 61.306415] [] r6040_close+0x89/0x230 [r6040] [ 61.306415] [ 61.306415] [] __dev_close_many+0x61/0xa0 [ 61.306415] [ 61.306415] [] __dev_close+0x1f/0x30 [ 61.306415] [ 61.306415] [] __dev_change_flags+0x87/0x150 [ 61.306415] [ 61.306415] [] dev_change_flags+0x23/0x60 [ 61.306415] [ 61.306415] [] devinet_ioctl+0x5f8/0x6f0 [ 61.306415] [ 61.306415] [] inet_ioctl+0x65/0x90 [ 61.306415] [ 61.306415] [] sock_ioctl+0x124/0x2b0 [ 61.306415] [ 61.306415] [] do_vfs_ioctl+0x7c/0x790 [ 61.306415] [ 61.306415] [] SyS_ioctl+0x28/0x50 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] [ 61.306415] the dependencies between the lock to be acquired[ 61.306415] and SOFTIRQ-irq-unsafe lock: [ 61.306415] -> (&dev->lock){+.+...} ops: 56 { [ 61.306415] HARDIRQ-ON-W at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x577/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] [ 61.306415] [] phy_probe+0x4d/0xc0 [ 61.306415] [ 61.306415] [] phy_attach_direct+0xbe/0x190 [ 61.306415] [ 61.306415] [] phy_connect_direct+0x17/0x60 [ 61.306415] [ 61.306415] [] phy_connect+0x33/0x70 [ 61.306415] [ 61.306415] [] r6040_init_one+0x3a0/0x500 [r6040] [ 61.306415] [ 61.306415] [] pci_device_probe+0x77/0xd0 [ 61.306415] [ 61.306415] [] driver_probe_device+0x145/0x280 [ 61.306415] [ 61.306415] [] __driver_attach+0x89/0x90 [ 61.306415] [ 61.306415] [] bus_for_each_dev+0x4f/0x80 [ 61.306415] [ 61.306415] [] driver_attach+0x14/0x20 [ 61.306415] [ 61.306415] [] bus_add_driver+0x197/0x210 [ 61.306415] [ 61.306415] [] driver_register+0x51/0xd0 [ 61.306415] [ 61.306415] [] __pci_register_driver+0x45/0x50 [ 61.306415] [ 61.306415] [] 0xd0938017 [ 61.306415] [ 61.306415] [] do_one_initcall+0x2f/0x140 [ 61.306415] [ 61.306415] [] do_init_module+0x4a/0x19b [ 61.306415] [ 61.306415] [] load_module+0x1b2e/0x2070 [ 61.306415] [ 61.306415] [] SyS_finit_module+0x69/0x80 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] SOFTIRQ-ON-W at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x59c/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] [ 61.306415] [] phy_probe+0x4d/0xc0 [ 61.306415] [ 61.306415] [] phy_attach_direct+0xbe/0x190 [ 61.306415] [ 61.306415] [] phy_connect_direct+0x17/0x60 [ 61.306415] [ 61.306415] [] phy_connect+0x33/0x70 [ 61.306415] [ 61.306415] [] r6040_init_one+0x3a0/0x500 [r6040] [ 61.306415] [ 61.306415] [] pci_device_probe+0x77/0xd0 [ 61.306415] [ 61.306415] [] driver_probe_device+0x145/0x280 [ 61.306415] [ 61.306415] [] __driver_attach+0x89/0x90 [ 61.306415] [ 61.306415] [] bus_for_each_dev+0x4f/0x80 [ 61.306415] [ 61.306415] [] driver_attach+0x14/0x20 [ 61.306415] [ 61.306415] [] bus_add_driver+0x197/0x210 [ 61.306415] [ 61.306415] [] driver_register+0x51/0xd0 [ 61.306415] [ 61.306415] [] __pci_register_driver+0x45/0x50 [ 61.306415] [ 61.306415] [] 0xd0938017 [ 61.306415] [ 61.306415] [] do_one_initcall+0x2f/0x140 [ 61.306415] [ 61.306415] [] do_init_module+0x4a/0x19b [ 61.306415] [ 61.306415] [] load_module+0x1b2e/0x2070 [ 61.306415] [ 61.306415] [] SyS_finit_module+0x69/0x80 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] INITIAL USE at: [ 61.306415] [ 61.306415] [] __lock_acquire+0x1fe/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] [ 61.306415] [] phy_probe+0x4d/0xc0 [ 61.306415] [ 61.306415] [] phy_attach_direct+0xbe/0x190 [ 61.306415] [ 61.306415] [] phy_connect_direct+0x17/0x60 [ 61.306415] [ 61.306415] [] phy_connect+0x33/0x70 [ 61.306415] [ 61.306415] [] r6040_init_one+0x3a0/0x500 [r6040] [ 61.306415] [ 61.306415] [] pci_device_probe+0x77/0xd0 [ 61.306415] [ 61.306415] [] driver_probe_device+0x145/0x280 [ 61.306415] [ 61.306415] [] __driver_attach+0x89/0x90 [ 61.306415] [ 61.306415] [] bus_for_each_dev+0x4f/0x80 [ 61.306415] [ 61.306415] [] driver_attach+0x14/0x20 [ 61.306415] [ 61.306415] [] bus_add_driver+0x197/0x210 [ 61.306415] [ 61.306415] [] driver_register+0x51/0xd0 [ 61.306415] [ 61.306415] [] __pci_register_driver+0x45/0x50 [ 61.306415] [ 61.306415] [] 0xd0938017 [ 61.306415] [ 61.306415] [] do_one_initcall+0x2f/0x140 [ 61.306415] [ 61.306415] [] do_init_module+0x4a/0x19b [ 61.306415] [ 61.306415] [] load_module+0x1b2e/0x2070 [ 61.306415] [ 61.306415] [] SyS_finit_module+0x69/0x80 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] } [ 61.306415] ... key at: [] __key.43998+0x0/0x8 [ 61.306415] ... acquired at: [ 61.306415] [ 61.306415] [] check_irq_usage+0x42/0xb0 [ 61.306415] [ 61.306415] [] __lock_acquire+0x110c/0x1770 [ 61.306415] [ 61.306415] [] lock_acquire+0x7c/0x150 [ 61.306415] [ 61.306415] [] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] [ 61.306415] [] phy_stop+0x16/0x80 [ 61.306415] [ 61.306415] [] r6040_close+0x89/0x230 [r6040] [ 61.306415] [ 61.306415] [] __dev_close_many+0x61/0xa0 [ 61.306415] [ 61.306415] [] __dev_close+0x1f/0x30 [ 61.306415] [ 61.306415] [] __dev_change_flags+0x87/0x150 [ 61.306415] [ 61.306415] [] dev_change_flags+0x23/0x60 [ 61.306415] [ 61.306415] [] devinet_ioctl+0x5f8/0x6f0 [ 61.306415] [ 61.306415] [] inet_ioctl+0x65/0x90 [ 61.306415] [ 61.306415] [] sock_ioctl+0x124/0x2b0 [ 61.306415] [ 61.306415] [] do_vfs_ioctl+0x7c/0x790 [ 61.306415] [ 61.306415] [] SyS_ioctl+0x28/0x50 [ 61.306415] [ 61.306415] [] do_int80_syscall_32+0x3f/0x110 [ 61.306415] [ 61.306415] [] restore_all+0x0/0x61 [ 61.306415] [ 61.306415] [ 61.306415] stack backtrace: [ 61.306415] CPU: 0 PID: 449 Comm: ifconfig Not tainted 4.9.0-gb898d2d-manuel #1 [ 61.306415] Call Trace: [ 61.306415] dump_stack+0x16/0x19 [ 61.306415] check_usage+0x3f6/0x550 [ 61.306415] ? check_usage+0x4d/0x550 [ 61.306415] check_irq_usage+0x42/0xb0 [ 61.306415] __lock_acquire+0x110c/0x1770 [ 61.306415] lock_acquire+0x7c/0x150 [ 61.306415] ? phy_stop+0x16/0x80 [ 61.306415] mutex_lock_nested+0x2d/0x4a0 [ 61.306415] ? phy_stop+0x16/0x80 [ 61.306415] ? r6040_close+0x24/0x230 [r6040] [ 61.306415] ? __delay+0x9/0x10 [ 61.306415] phy_stop+0x16/0x80 [ 61.306415] r6040_close+0x89/0x230 [r6040] [ 61.306415] __dev_close_many+0x61/0xa0 [ 61.306415] __dev_close+0x1f/0x30 [ 61.306415] __dev_change_flags+0x87/0x150 [ 61.306415] dev_change_flags+0x23/0x60 [ 61.306415] devinet_ioctl+0x5f8/0x6f0 [ 61.306415] inet_ioctl+0x65/0x90 [ 61.306415] sock_ioctl+0x124/0x2b0 [ 61.306415] ? dlci_ioctl_set+0x30/0x30 [ 61.306415] do_vfs_ioctl+0x7c/0x790 [ 61.306415] ? trace_hardirqs_on+0xb/0x10 [ 61.306415] ? call_rcu_sched+0xd/0x10 [ 61.306415] ? __put_cred+0x32/0x50 [ 61.306415] ? SyS_faccessat+0x178/0x1e0 [ 61.306415] SyS_ioctl+0x28/0x50 [ 61.306415] do_int80_syscall_32+0x3f/0x110 [ 61.306415] entry_INT80_32+0x2f/0x2f [ 61.306415] EIP: 0xb764d364 [ 61.306415] EFLAGS: 00000286 CPU: 0 [ 61.306415] EAX: ffffffda EBX: 00000004 ECX: 00008914 EDX: bfa99d7c [ 61.306415] ESI: bfa99e4c EDI: fffffffe EBP: 00000004 ESP: bfa99d58 [ 61.306415] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b [ 63.836607] r6040 0000:00:08.0 eth0: Link is Down Signed-off-by: Manuel Bessler Signed-off-by: David S. Miller --- drivers/net/ethernet/rdc/r6040.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 4ff4e0491406..aa11b70b9ca4 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -472,8 +472,6 @@ static void r6040_down(struct net_device *dev) iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); - - phy_stop(dev->phydev); } static int r6040_close(struct net_device *dev) @@ -481,12 +479,12 @@ static int r6040_close(struct net_device *dev) struct r6040_private *lp = netdev_priv(dev); struct pci_dev *pdev = lp->pdev; - spin_lock_irq(&lp->lock); + phy_stop(dev->phydev); napi_disable(&lp->napi); netif_stop_queue(dev); - r6040_down(dev); - free_irq(dev->irq, dev); + spin_lock_irq(&lp->lock); + r6040_down(dev); /* Free RX buffer */ r6040_free_rxbufs(dev); @@ -496,6 +494,8 @@ static int r6040_close(struct net_device *dev) spin_unlock_irq(&lp->lock); + free_irq(dev->irq, dev); + /* Free Descriptor memory */ if (lp->rx_ring) { pci_free_consistent(pdev, From c2ed1880fd61a998e3ce40254a99a2ad000f1a7d Mon Sep 17 00:00:00 2001 From: Mantas M Date: Fri, 16 Dec 2016 10:30:59 +0200 Subject: [PATCH 58/63] net: ipv6: check route protocol when deleting routes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The protocol field is checked when deleting IPv4 routes, but ignored for IPv6, which causes problems with routing daemons accidentally deleting externally set routes (observed by multiple bird6 users). This can be verified using `ip -6 route del proto something`. Signed-off-by: Mantas Mikulėnas Signed-off-by: David S. Miller --- net/ipv6/route.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2413a0637d99..890acace01d0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2174,6 +2174,8 @@ static int ip6_route_del(struct fib6_config *cfg) continue; if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; + if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) + continue; dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); From 7729bad4fd95e48bcafcb2222c63a8a5cdc42f61 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 16 Dec 2016 09:47:41 +0100 Subject: [PATCH 59/63] qed: fix old-style function definition The newly added file causes a harmless warning, with "make W=1": drivers/net/ethernet/qlogic/qed/qed_iscsi.c: In function 'qed_get_iscsi_ops': drivers/net/ethernet/qlogic/qed/qed_iscsi.c:1268:29: warning: old-style function definition [-Wold-style-definition] This makes it a proper prototype. Fixes: fc831825f99e ("qed: Add support for hardware offloaded iSCSI.") Signed-off-by: Arnd Bergmann Reviewed-by: Johannes Thumshirn Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iscsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 00efb1c4c57e..17a70122df05 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -1265,7 +1265,7 @@ static const struct qed_iscsi_ops qed_iscsi_ops_pass = { .get_stats = &qed_iscsi_stats, }; -const struct qed_iscsi_ops *qed_get_iscsi_ops() +const struct qed_iscsi_ops *qed_get_iscsi_ops(void) { return &qed_iscsi_ops_pass; } From 483c4933ea09b7aa625b9d64af286fc22ec7e419 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Fri, 16 Dec 2016 08:33:45 -0800 Subject: [PATCH 60/63] cgroup: Fix CGROUP_BPF config CGROUP_BPF depended on SOCK_CGROUP_DATA which can't be manually enabled, making it rather challenging to turn CGROUP_BPF on. Signed-off-by: Andy Lutomirski Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- init/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index 405120b5f13e..951102707007 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1156,7 +1156,8 @@ config CGROUP_PERF config CGROUP_BPF bool "Support for eBPF programs attached to cgroups" - depends on BPF_SYSCALL && SOCK_CGROUP_DATA + depends on BPF_SYSCALL + select SOCK_CGROUP_DATA help Allow attaching eBPF programs to a cgroup using the bpf(2) syscall command BPF_PROG_ATTACH. From 9a60c9072295b30459284beca9aff52be8dfd64b Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 16 Dec 2016 19:29:03 +0100 Subject: [PATCH 61/63] mlxsw: spectrum: Mark split ports as such When a port is split we should mark it as such, as otherwise the split ports aren't renamed correctly (e.g. sw1p3 -> sw1p3s1) and the unsplit operation fails: $ devlink port split sw1p3 count 4 $ devlink port unsplit eth0 devlink answers: Invalid argument [ 598.565307] mlxsw_spectrum 0000:03:00.0 eth0: Port wasn't split Fixes: 67963a33b4fd ("mlxsw: Make devlink port instances independent of spectrum/switchx2 port instances") Signed-off-by: Ido Schimmel Reported-by: Tamir Winetroub Reviewed-by: Elad Raz Tested-by: Tamir Winetroub Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index fece974b4edd..d768c7b6c6d6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2404,7 +2404,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, local_port); return err; } - err = __mlxsw_sp_port_create(mlxsw_sp, local_port, false, + err = __mlxsw_sp_port_create(mlxsw_sp, local_port, split, module, width, lane); if (err) goto err_port_create; From a6b3c48312f6a2c3905653c0633344f811c1dde5 Mon Sep 17 00:00:00 2001 From: Emese Revfy Date: Fri, 16 Dec 2016 13:40:47 -0800 Subject: [PATCH 62/63] isdn: Constify some function parameters The coming initify gcc plugin expects const pointer types, and caught some __printf arguments that weren't const yet. This fixes those. Signed-off-by: Emese Revfy [kees: expanded commit message] Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- drivers/isdn/hisax/config.c | 16 ++++++++-------- drivers/isdn/hisax/hisax.h | 4 ++-- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c index bf04d2a3cf4a..2d12c6ceeb89 100644 --- a/drivers/isdn/hisax/config.c +++ b/drivers/isdn/hisax/config.c @@ -659,7 +659,7 @@ int jiftime(char *s, long mark) static u_char tmpbuf[HISAX_STATUS_BUFSIZE]; -void VHiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, +void VHiSax_putstatus(struct IsdnCardState *cs, char *head, const char *fmt, va_list args) { /* if head == NULL the fmt contains the full info */ @@ -669,23 +669,24 @@ void VHiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, u_char *p; isdn_ctrl ic; int len; + const u_char *data; if (!cs) { printk(KERN_WARNING "HiSax: No CardStatus for message"); return; } spin_lock_irqsave(&cs->statlock, flags); - p = tmpbuf; if (head) { + p = tmpbuf; p += jiftime(p, jiffies); p += sprintf(p, " %s", head); p += vsprintf(p, fmt, args); *p++ = '\n'; *p = 0; len = p - tmpbuf; - p = tmpbuf; + data = tmpbuf; } else { - p = fmt; + data = fmt; len = strlen(fmt); } if (len > HISAX_STATUS_BUFSIZE) { @@ -699,13 +700,12 @@ void VHiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, if (i >= len) i = len; len -= i; - memcpy(cs->status_write, p, i); + memcpy(cs->status_write, data, i); cs->status_write += i; if (cs->status_write > cs->status_end) cs->status_write = cs->status_buf; - p += i; if (len) { - memcpy(cs->status_write, p, len); + memcpy(cs->status_write, data + i, len); cs->status_write += len; } #ifdef KERNELSTACK_DEBUG @@ -729,7 +729,7 @@ void VHiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, } } -void HiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, ...) +void HiSax_putstatus(struct IsdnCardState *cs, char *head, const char *fmt, ...) { va_list args; diff --git a/drivers/isdn/hisax/hisax.h b/drivers/isdn/hisax/hisax.h index 6ead6314e6d2..338d0408b377 100644 --- a/drivers/isdn/hisax/hisax.h +++ b/drivers/isdn/hisax/hisax.h @@ -1288,9 +1288,9 @@ int jiftime(char *s, long mark); int HiSax_command(isdn_ctrl *ic); int HiSax_writebuf_skb(int id, int chan, int ack, struct sk_buff *skb); __printf(3, 4) -void HiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, ...); +void HiSax_putstatus(struct IsdnCardState *cs, char *head, const char *fmt, ...); __printf(3, 0) -void VHiSax_putstatus(struct IsdnCardState *cs, char *head, char *fmt, va_list args); +void VHiSax_putstatus(struct IsdnCardState *cs, char *head, const char *fmt, va_list args); void HiSax_reportcard(int cardnr, int sel); int QuickHex(char *txt, u_char *p, int cnt); void LogFrame(struct IsdnCardState *cs, u_char *p, int size); From 3e3397e7b11ce1b9526975ddfbe8dd569fc1f316 Mon Sep 17 00:00:00 2001 From: Sudip Mukherjee Date: Sat, 17 Dec 2016 00:45:05 +0000 Subject: [PATCH 63/63] net: mv643xx_eth: fix build failure The build of sparc allmodconfig fails with the error: "of_irq_to_resource" [drivers/net/ethernet/marvell/mv643xx_eth.ko] undefined! of_irq_to_resource() is defined when CONFIG_OF_IRQ is defined. And also CONFIG_OF_IRQ can only be defined if CONFIG_IRQ is defined. So we can safely use #if defined(CONFIG_OF_IRQ) in the code. Signed-off-by: Sudip Mukherjee Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mv643xx_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 5f62c3d70df9..1fa7c03edec2 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2713,7 +2713,7 @@ static const struct of_device_id mv643xx_eth_shared_ids[] = { MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids); #endif -#if defined(CONFIG_OF) && !defined(CONFIG_MV64X60) +#if defined(CONFIG_OF_IRQ) && !defined(CONFIG_MV64X60) #define mv643xx_eth_property(_np, _name, _v) \ do { \ u32 tmp; \