From 7f92083eb58f85ea114d97f65fcbe22be5b0468d Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 30 Sep 2016 11:11:07 +0200 Subject: [PATCH 001/174] vti6: flush x-netns xfrm cache when vti interface is removed This is the same fix than commit a5d0dc810abf ("vti: flush x-netns xfrm cache when vti interface is removed") This patch fixes a refcnt problem when a x-netns vti6 interface is removed: unregister_netdevice: waiting for vti6_test to become free. Usage count = 1 Here is a script to reproduce the problem: ip link set dev ntfp2 up ip addr add dev ntfp2 2001::1/64 ip link add vti6_test type vti6 local 2001::1 remote 2001::2 key 1 ip netns add secure ip link set vti6_test netns secure ip netns exec secure ip link set vti6_test up ip netns exec secure ip link s lo up ip netns exec secure ip addr add dev vti6_test 2003::1/64 ip -6 xfrm policy add dir out tmpl src 2001::1 dst 2001::2 proto esp \ mode tunnel mark 1 ip -6 xfrm policy add dir in tmpl src 2001::2 dst 2001::1 proto esp \ mode tunnel mark 1 ip xfrm state add src 2001::1 dst 2001::2 proto esp spi 1 mode tunnel \ enc des3_ede 0x112233445566778811223344556677881122334455667788 mark 1 ip xfrm state add src 2001::2 dst 2001::1 proto esp spi 1 mode tunnel \ enc des3_ede 0x112233445566778811223344556677881122334455667788 mark 1 ip netns exec secure ping6 -c 4 2003::2 ip netns del secure CC: Lance Richardson Signed-off-by: Nicolas Dichtel Acked-by: Lance Richardson Signed-off-by: Steffen Klassert --- net/ipv6/ip6_vti.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 8a02ca8a11af..c299c1e2bbf0 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1138,6 +1138,33 @@ static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .priority = 100, }; +static bool is_vti6_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti6_netdev_ops; +} + +static int vti6_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip6_tnl *t = netdev_priv(dev); + + if (!is_vti6_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(t->net, dev_net(dev))) + xfrm_garbage_collect(t->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti6_notifier_block __read_mostly = { + .notifier_call = vti6_device_event, +}; + /** * vti6_tunnel_init - register protocol and reserve needed resources * @@ -1148,6 +1175,8 @@ static int __init vti6_tunnel_init(void) const char *msg; int err; + register_netdevice_notifier(&vti6_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) @@ -1180,6 +1209,7 @@ static int __init vti6_tunnel_init(void) xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti6_notifier_block); pr_err("vti6 init: failed to register %s\n", msg); return err; } @@ -1194,6 +1224,7 @@ static void __exit vti6_tunnel_cleanup(void) xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); + unregister_netdevice_notifier(&vti6_notifier_block); } module_init(vti6_tunnel_init); From c699995663b40d61afcc14ca27f0106f13151772 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sat, 10 Sep 2016 09:55:49 +0800 Subject: [PATCH 002/174] pwm: meson: Add missing spin_lock_init() The driver uses the spin_lock but does not initialize it. Fix it. Signed-off-by: Axel Lin Acked-by: Neil Armstrong Signed-off-by: Thierry Reding --- drivers/pwm/pwm-meson.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c index 381871b2bb46..9d5bd7d5c610 100644 --- a/drivers/pwm/pwm-meson.c +++ b/drivers/pwm/pwm-meson.c @@ -474,6 +474,7 @@ static int meson_pwm_probe(struct platform_device *pdev) if (IS_ERR(meson->base)) return PTR_ERR(meson->base); + spin_lock_init(&meson->lock); meson->chip.dev = &pdev->dev; meson->chip.ops = &meson_pwm_ops; meson->chip.base = -1; From 18eddaedc940a49425364df98abda218ce1e771c Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 31 Oct 2016 15:04:10 +0000 Subject: [PATCH 003/174] mvsas: fix error return code in mvs_task_prep() Fix to return error code -ENOMEM from the error handling case instead of 0, as done elsewhere in this function. Signed-off-by: Wei Yongjun Signed-off-by: Tejun Heo --- drivers/scsi/mvsas/mv_sas.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index 86eb19902bac..c7cc8035eacb 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -791,8 +791,10 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf slot->slot_tag = tag; slot->buf = pci_pool_alloc(mvi->dma_pool, GFP_ATOMIC, &slot->buf_dma); - if (!slot->buf) + if (!slot->buf) { + rc = -ENOMEM; goto err_out_tag; + } memset(slot->buf, 0, MVS_SLOT_BUF_SZ); tei.task = task; From e0029dcb5b6e1c23e68f578ce7a3d6c5caba0501 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 31 Oct 2016 21:06:58 +0100 Subject: [PATCH 004/174] libata-scsi: Fixup ata_gen_passthru_sense() There's a typo in ata_gen_passthru_sense(), where the first byte would be overwritten incorrectly later on. Reported-by: Charles Machalow Signed-off-by: Hannes Reinecke Fixes: 11093cb1ef56 ("libata-scsi: generate correct ATA pass-through sense") Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: Tejun Heo --- drivers/ata/libata-scsi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 9cceb4a875a5..c4eb4ae9c3aa 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1088,7 +1088,7 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) desc[1] = tf->command; /* status */ desc[2] = tf->device; desc[3] = tf->nsect; - desc[0] = 0; + desc[7] = 0; if (tf->flags & ATA_TFLAG_LBA48) { desc[8] |= 0x80; if (tf->hob_nsect) From 286fbaef149f2054b1d13be2536e75ae4a52e2fe Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Fri, 11 Nov 2016 16:52:38 -0600 Subject: [PATCH 005/174] MAINTAINERS: Update Richard Zhu's email address FSL emails may become invalid soon, so switch to the NXP one. Signed-off-by: Fabio Estevam Signed-off-by: Bjorn Helgaas Acked-by: Richard Zhu --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index aefa6bf1782e..f78003d90f08 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9230,7 +9230,7 @@ S: Maintained F: drivers/pci/host/*layerscape* PCI DRIVER FOR IMX6 -M: Richard Zhu +M: Richard Zhu M: Lucas Stach L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) From 12e460649a01f34753c3b1a2ff6fd5f655e03097 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Fri, 11 Nov 2016 16:52:46 -0600 Subject: [PATCH 006/174] MAINTAINERS: Add devicetree binding to PCI i.MX6 entry Add an entry for the devicetree binding file, so that when people run ./scripts/get_maintainer.pl the PCI imx6 maintainers could also be listed. Signed-off-by: Fabio Estevam Signed-off-by: Bjorn Helgaas Acked-by: Lucas Stach --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index f78003d90f08..b6c0b9b89f9f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9235,6 +9235,7 @@ M: Lucas Stach L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained +F: Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.txt F: drivers/pci/host/*imx6* PCI DRIVER FOR TI KEYSTONE From fc2480f9b255c820f7111e0e59cbb343c9f95254 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Tue, 15 Nov 2016 16:10:46 +0000 Subject: [PATCH 007/174] PCI: designware: Change maintainer to Joao Pinto I accepted the invitation from Pratyush to replace him in the pcie-designware maintenance. This patch makes the maintainer replacement and simplifies the pcie-designware* maintenance structure. Signed-off-by: Joao Pinto Signed-off-by: Bjorn Helgaas CC: Pratyush Anand CC: Jose Abreu --- MAINTAINERS | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index b6c0b9b89f9f..a268ddb28956 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9294,17 +9294,11 @@ F: drivers/pci/host/pci-exynos.c PCI DRIVER FOR SYNOPSIS DESIGNWARE M: Jingoo Han -M: Pratyush Anand -L: linux-pci@vger.kernel.org -S: Maintained -F: drivers/pci/host/*designware* - -PCI DRIVER FOR SYNOPSYS PROTOTYPING DEVICE -M: Jose Abreu +M: Joao Pinto L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/designware-pcie.txt -F: drivers/pci/host/pcie-designware-plat.c +F: drivers/pci/host/*designware* PCI DRIVER FOR GENERIC OF HOSTS M: Will Deacon From 9f46107b8ce4f9a4bd6be50e2967df506d1c1631 Mon Sep 17 00:00:00 2001 From: Joao Pinto Date: Tue, 15 Nov 2016 16:10:47 +0000 Subject: [PATCH 008/174] PCI: designware-plat: Update author email I returned to Synopsys and so I am sending this patch to update the email address of the pcie-designware-plat author. Signed-off-by: Joao Pinto Signed-off-by: Bjorn Helgaas --- drivers/pci/host/pcie-designware-plat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pci/host/pcie-designware-plat.c b/drivers/pci/host/pcie-designware-plat.c index 8df6312ed300..1a02038c4640 100644 --- a/drivers/pci/host/pcie-designware-plat.c +++ b/drivers/pci/host/pcie-designware-plat.c @@ -3,7 +3,7 @@ * * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com) * - * Authors: Joao Pinto + * Authors: Joao Pinto * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as From e9fb7cc63801d3dc71b60ca11c4d08f68f879a53 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Sat, 12 Nov 2016 10:45:48 -0800 Subject: [PATCH 009/174] Input: psmouse - disable automatic probing of BYD touchpads MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit BYD automatic protocol detection is extremely unreliable and is often triggers false positives on regular mice, Sentelic touchpads, and other devices. BYD has several documents that have recommended detection sequence, but they conflict with each other and, as far as I can see, still would not produce unique enough output to reliably differentiate BYD from other PS/2 devices. OEMs sourcing BYD devices also do not do us any favors by not supplying any reasonable DMI data and instead leaving turds like "To Be Filled By O.E.M." in place of vendor data, or "System Serial Number" as serial number. On top of that BYD is not truly modern multitouch controller, but rather a single-touch transitional device that only reports absolute coordinates at the beginning of finger contact and then reverts to reporting displacements, and thus not very precise; the only benefit from using BYD mode vs the legacy PS/2 mode is possibility of edge scrolling. Given the above, and the fact that BYD devices are somewhat uncommon, let's disable automatic detection of BYD devices. Users who know they have BYD trackpads or want to experiment can attempt to activate BYD protocol via sysfs: echo -n "byd" > /sys/bus/serio/devices/serio1/drvctl Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=151691 Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=175421 Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=120781 Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=121281 Fixes: 98ee37714493 ("Input: byd - add BYD PS/2 touchpad driver") Cc: stable@vger.kernel.org # 4.6+ Reviewed-by: Pali Rohár Signed-off-by: Dmitry Torokhov --- drivers/input/mouse/psmouse-base.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index fb4b185dea96..bee267424972 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -1115,10 +1115,6 @@ static int psmouse_extensions(struct psmouse *psmouse, if (psmouse_try_protocol(psmouse, PSMOUSE_TOUCHKIT_PS2, &max_proto, set_properties, true)) return PSMOUSE_TOUCHKIT_PS2; - - if (psmouse_try_protocol(psmouse, PSMOUSE_BYD, - &max_proto, set_properties, true)) - return PSMOUSE_BYD; } /* From fcd2042e8d36cf644bd2d69c26378d17158b17df Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 8 Nov 2016 18:28:24 -0800 Subject: [PATCH 010/174] mwifiex: printk() overflow with 32-byte SSIDs SSIDs aren't guaranteed to be 0-terminated. Let's cap the max length when we print them out. This can be easily noticed by connecting to a network with a 32-octet SSID: [ 3903.502925] mwifiex_pcie 0000:01:00.0: info: trying to associate to '0123456789abcdef0123456789abcdef ' bssid xx:xx:xx:xx:xx:xx Fixes: 5e6e3a92b9a4 ("wireless: mwifiex: initial commit for Marvell mwifiex driver") Signed-off-by: Brian Norris Cc: Acked-by: Amitkumar Karwar Signed-off-by: Kalle Valo --- drivers/net/wireless/marvell/mwifiex/cfg80211.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 39ce76ad00bc..16241d21727b 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -2222,8 +2222,9 @@ mwifiex_cfg80211_assoc(struct mwifiex_private *priv, size_t ssid_len, is_scanning_required = 1; } else { mwifiex_dbg(priv->adapter, MSG, - "info: trying to associate to '%s' bssid %pM\n", - (char *)req_ssid.ssid, bss->bssid); + "info: trying to associate to '%.*s' bssid %pM\n", + req_ssid.ssid_len, (char *)req_ssid.ssid, + bss->bssid); memcpy(&priv->cfg_bssid, bss->bssid, ETH_ALEN); break; } @@ -2283,8 +2284,8 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev, } mwifiex_dbg(adapter, INFO, - "info: Trying to associate to %s and bssid %pM\n", - (char *)sme->ssid, sme->bssid); + "info: Trying to associate to %.*s and bssid %pM\n", + (int)sme->ssid_len, (char *)sme->ssid, sme->bssid); if (!mwifiex_stop_bg_scan(priv)) cfg80211_sched_scan_stopped_rtnl(priv->wdev.wiphy); @@ -2417,8 +2418,8 @@ mwifiex_cfg80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, } mwifiex_dbg(priv->adapter, MSG, - "info: trying to join to %s and bssid %pM\n", - (char *)params->ssid, params->bssid); + "info: trying to join to %.*s and bssid %pM\n", + params->ssid_len, (char *)params->ssid, params->bssid); mwifiex_set_ibss_params(priv, params); From 208da78e8ec8b6d6ce3747ab0e5c120458e08ae6 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Thu, 17 Nov 2016 12:50:23 +0100 Subject: [PATCH 011/174] scsi: libfc: fix seconds_since_last_reset miscalculation Commit 540eb1eef0ab ("scsi: libfc: fix seconds_since_last_reset calculation") removed the use of 'struct timespec' from fc_get_host_stats(). This broke the output of 'fcoeadm -s' after kernel 4.8-rc1. Signed-off-by: Johannes Thumshirn Cc: # v4.8+ Fixes: 540eb1eef0ab ("scsi: libfc: fix seconds_since_last_reset calculation") Acked-by: Arnd Bergmann Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/scsi/libfc/fc_lport.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index 04ce7cfb6d1b..50c71678a156 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -308,7 +308,7 @@ struct fc_host_statistics *fc_get_host_stats(struct Scsi_Host *shost) fc_stats = &lport->host_stats; memset(fc_stats, 0, sizeof(struct fc_host_statistics)); - fc_stats->seconds_since_last_reset = (lport->boot_time - jiffies) / HZ; + fc_stats->seconds_since_last_reset = (jiffies - lport->boot_time) / HZ; for_each_possible_cpu(cpu) { struct fc_stats *stats; From 330e832abda923df06a4ca6d3faac6e9c1b42548 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 17 Nov 2016 13:21:46 +0100 Subject: [PATCH 012/174] xfrm: unbreak xfrm_sk_policy_lookup if we succeed grabbing the refcount, then if (err && !xfrm_pol_hold_rcu) will evaluate to false so this hits last else branch which then sets policy to ERR_PTR(0). Fixes: ae33786f73a7ce ("xfrm: policy: only use rcu in xfrm_sk_policy_lookup") Reported-by: Nicolas Dichtel Tested-by: Nicolas Dichtel Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index fd6986634e6f..5bf7e1bfeac7 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1268,12 +1268,14 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, policy_to_flow_dir(dir)); - if (!err && !xfrm_pol_hold_rcu(pol)) - goto again; - else if (err == -ESRCH) + if (!err) { + if (!xfrm_pol_hold_rcu(pol)) + goto again; + } else if (err == -ESRCH) { pol = NULL; - else + } else { pol = ERR_PTR(err); + } } else pol = NULL; } From 6929ef385e09c0065b87fda3e7b872a5070ac783 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 18 Nov 2016 14:09:06 +0100 Subject: [PATCH 013/174] ahci: always fall back to single-MSI mode Don't try to guess what the errors from pci_irq_alloc_vectors mean, as that's too fragile. Instead always try allocating a single vector when multi-MSI mode fails. This makes various intel Desktop and Laptop CPUs use MSI again. Signed-off-by: Christoph Hellwig Reported-by: Michael Marley Tested-by: Michael Marley Fixes: 0b9e2988ab22 ("ahci: use pci_alloc_irq_vectors") Signed-off-by: Tejun Heo --- drivers/ata/ahci.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 9669fc7c19df..74f4c662f776 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1436,13 +1436,6 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, "ahci: MRSM is on, fallback to single MSI\n"); pci_free_irq_vectors(pdev); } - - /* - * -ENOSPC indicated we don't have enough vectors. Don't bother - * trying a single vectors for any other error: - */ - if (nvec < 0 && nvec != -ENOSPC) - return nvec; } /* From 95881a54b8b175be56adbcd86a473d8e8d5be2aa Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Fri, 18 Nov 2016 15:15:57 +0800 Subject: [PATCH 014/174] clk: sunxi-ng: sun6i-a31: Enable PLL-MIPI LDOs when ungating it The PLL-MIPI clock is somewhat special as it has its own LDOs which need to be turned on for this PLL to actually work and output a clock signal. Add the 2 LDO enable bits to the gate bits. This fixes issues with the TCON not sending vblank interrupts when the tcon and dot clock are indirectly clocked from the PLL-MIPI clock. Fixes: c6e6c96d8fa6 ("clk: sunxi-ng: Add A31/A31s clocks") Signed-off-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard --- drivers/clk/sunxi-ng/ccu-sun6i-a31.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c index 4a82a49cff5e..fc75a335a7ce 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c @@ -143,7 +143,7 @@ static SUNXI_CCU_NKM_WITH_MUX_GATE_LOCK(pll_mipi_clk, "pll-mipi", 4, 2, /* K */ 0, 4, /* M */ 21, 0, /* mux */ - BIT(31), /* gate */ + BIT(31) | BIT(23) | BIT(22), /* gate */ BIT(28), /* lock */ CLK_SET_RATE_UNGATE); From e5cd7ff7058dc6f2133455636809a09b691ee419 Mon Sep 17 00:00:00 2001 From: Maxime Ripard Date: Tue, 22 Nov 2016 15:06:04 +0100 Subject: [PATCH 015/174] ARM: gr8: Rename the DTSI and relevant DTS Reviews have found that sun5i was a better prefix after all for the GR8. Rename the relevant device trees before it's too late. Signed-off-by: Maxime Ripard --- arch/arm/boot/dts/Makefile | 2 +- arch/arm/boot/dts/{ntc-gr8-evb.dts => sun5i-gr8-evb.dts} | 2 +- arch/arm/boot/dts/{ntc-gr8.dtsi => sun5i-gr8.dtsi} | 0 3 files changed, 2 insertions(+), 2 deletions(-) rename arch/arm/boot/dts/{ntc-gr8-evb.dts => sun5i-gr8-evb.dts} (99%) rename arch/arm/boot/dts/{ntc-gr8.dtsi => sun5i-gr8.dtsi} (100%) diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index befcd2619902..c558ba75cbcc 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -745,7 +745,6 @@ dtb-$(CONFIG_MACH_SUN4I) += \ sun4i-a10-pcduino2.dtb \ sun4i-a10-pov-protab2-ips9.dtb dtb-$(CONFIG_MACH_SUN5I) += \ - ntc-gr8-evb.dtb \ sun5i-a10s-auxtek-t003.dtb \ sun5i-a10s-auxtek-t004.dtb \ sun5i-a10s-mk802.dtb \ @@ -761,6 +760,7 @@ dtb-$(CONFIG_MACH_SUN5I) += \ sun5i-a13-olinuxino-micro.dtb \ sun5i-a13-q8-tablet.dtb \ sun5i-a13-utoo-p66.dtb \ + sun5i-gr8-evb.dtb \ sun5i-r8-chip.dtb dtb-$(CONFIG_MACH_SUN6I) += \ sun6i-a31-app4-evb1.dtb \ diff --git a/arch/arm/boot/dts/ntc-gr8-evb.dts b/arch/arm/boot/dts/sun5i-gr8-evb.dts similarity index 99% rename from arch/arm/boot/dts/ntc-gr8-evb.dts rename to arch/arm/boot/dts/sun5i-gr8-evb.dts index 4b622f3b5220..714381fd64d7 100644 --- a/arch/arm/boot/dts/ntc-gr8-evb.dts +++ b/arch/arm/boot/dts/sun5i-gr8-evb.dts @@ -44,7 +44,7 @@ */ /dts-v1/; -#include "ntc-gr8.dtsi" +#include "sun5i-gr8.dtsi" #include "sunxi-common-regulators.dtsi" #include diff --git a/arch/arm/boot/dts/ntc-gr8.dtsi b/arch/arm/boot/dts/sun5i-gr8.dtsi similarity index 100% rename from arch/arm/boot/dts/ntc-gr8.dtsi rename to arch/arm/boot/dts/sun5i-gr8.dtsi From 7630b3a599e2c6d1c042945d32ff2debc855ad29 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Thu, 17 Nov 2016 12:15:56 +0100 Subject: [PATCH 016/174] scsi: hpsa: use bus '3' for legacy HBA devices Older controllers use SCSI target id '0' for the first internal disk. As the controllers are now placed on the same bus as the internal disks this leads to a clash with the SCSI target id of controller. This patch checks the SCSI revision, and moves older controller to bus '3' to be compatible with older releases and avoid this problem. [mkp: fixed uninitialized variable] Fixes: 09371d623c9 ("hpsa: Change SAS transport devices to bus 0.") Cc: # v4.5+ Signed-off-by: Hannes Reinecke Acked-by: Don Brace Signed-off-by: Martin K. Petersen --- drivers/scsi/hpsa.c | 16 +++++++++++----- drivers/scsi/hpsa.h | 2 ++ 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index d007ec18179a..a1d6ab76a514 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -2009,7 +2009,7 @@ static struct hpsa_scsi_dev_t *lookup_hpsa_scsi_dev(struct ctlr_info *h, static int hpsa_slave_alloc(struct scsi_device *sdev) { - struct hpsa_scsi_dev_t *sd; + struct hpsa_scsi_dev_t *sd = NULL; unsigned long flags; struct ctlr_info *h; @@ -2026,7 +2026,8 @@ static int hpsa_slave_alloc(struct scsi_device *sdev) sd->target = sdev_id(sdev); sd->lun = sdev->lun; } - } else + } + if (!sd) sd = lookup_hpsa_scsi_dev(h, sdev_channel(sdev), sdev_id(sdev), sdev->lun); @@ -3840,6 +3841,7 @@ static int hpsa_update_device_info(struct ctlr_info *h, sizeof(this_device->vendor)); memcpy(this_device->model, &inq_buff[16], sizeof(this_device->model)); + this_device->rev = inq_buff[2]; memset(this_device->device_id, 0, sizeof(this_device->device_id)); if (hpsa_get_device_id(h, scsi3addr, this_device->device_id, 8, @@ -3929,10 +3931,14 @@ static void figure_bus_target_lun(struct ctlr_info *h, if (!is_logical_dev_addr_mode(lunaddrbytes)) { /* physical device, target and lun filled in later */ - if (is_hba_lunid(lunaddrbytes)) + if (is_hba_lunid(lunaddrbytes)) { + int bus = HPSA_HBA_BUS; + + if (!device->rev) + bus = HPSA_LEGACY_HBA_BUS; hpsa_set_bus_target_lun(device, - HPSA_HBA_BUS, 0, lunid & 0x3fff); - else + bus, 0, lunid & 0x3fff); + } else /* defer target, lun assignment for physical devices */ hpsa_set_bus_target_lun(device, HPSA_PHYSICAL_DEVICE_BUS, -1, -1); diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h index 82cdfad874f3..9ea162de80dc 100644 --- a/drivers/scsi/hpsa.h +++ b/drivers/scsi/hpsa.h @@ -69,6 +69,7 @@ struct hpsa_scsi_dev_t { u64 sas_address; unsigned char vendor[8]; /* bytes 8-15 of inquiry data */ unsigned char model[16]; /* bytes 16-31 of inquiry data */ + unsigned char rev; /* byte 2 of inquiry data */ unsigned char raid_level; /* from inquiry page 0xC1 */ unsigned char volume_offline; /* discovered via TUR or VPD */ u16 queue_depth; /* max queue_depth for this device */ @@ -402,6 +403,7 @@ struct offline_device_entry { #define HPSA_RAID_VOLUME_BUS 1 #define HPSA_EXTERNAL_RAID_VOLUME_BUS 2 #define HPSA_HBA_BUS 0 +#define HPSA_LEGACY_HBA_BUS 3 /* Send the command to the hardware From 7ff723ad0f87feba43dda45fdae71206063dd7d4 Mon Sep 17 00:00:00 2001 From: Suganath Prabu S Date: Thu, 17 Nov 2016 16:15:58 +0530 Subject: [PATCH 017/174] scsi: mpt3sas: Unblock device after controller reset While issuing any ATA passthrough command to firmware the driver will block the device. But it will unblock the device only if the I/O completes through the ISR path. If a controller reset occurs before command completion the device will remain in blocked state. Make sure we unblock the device following a controller reset if an ATA passthrough command was queued. [mkp: clarified patch description] Cc: # v4.4+ Fixes: ac6c2a93bd07 ("mpt3sas: Fix for SATA drive in blocked state, after diag reset") Signed-off-by: Suganath Prabu S Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 91b70bc46e7f..1c4744e78173 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -3885,6 +3885,11 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc, } } +static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd) +{ + return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16); +} + /** * _scsih_flush_running_cmds - completing outstanding commands. * @ioc: per adapter object @@ -3906,6 +3911,9 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc) if (!scmd) continue; count++; + if (ata_12_16_cmd(scmd)) + scsi_internal_device_unblock(scmd->device, + SDEV_RUNNING); mpt3sas_base_free_smid(ioc, smid); scsi_dma_unmap(scmd); if (ioc->pci_error_recovery) @@ -4010,11 +4018,6 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status) SAM_STAT_CHECK_CONDITION; } -static inline bool ata_12_16_cmd(struct scsi_cmnd *scmd) -{ - return (scmd->cmnd[0] == ATA_12 || scmd->cmnd[0] == ATA_16); -} - /** * scsih_qcmd - main scsi request entry point * @scmd: pointer to scsi command object From 23b98e4b5fc5efd1d5d5f018bc7f954cd119f538 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 18 Nov 2016 14:53:39 +0300 Subject: [PATCH 018/174] scsi: be2iscsi: allocate enough memory in beiscsi_boot_get_sinfo() We accidentally allocate sizeof(u32) instead of sizeof(struct be_cmd_get_session_resp). Fixes: 50a4b824be9e ("scsi: be2iscsi: Fix to make boot discovery non-blocking") Signed-off-by: Dan Carpenter Reviewed by: Jitendra Bhivare Signed-off-by: Martin K. Petersen --- drivers/scsi/be2iscsi/be_mgmt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c index aebc4ddb3060..ac05317bba7f 100644 --- a/drivers/scsi/be2iscsi/be_mgmt.c +++ b/drivers/scsi/be2iscsi/be_mgmt.c @@ -1083,7 +1083,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba) nonemb_cmd = &phba->boot_struct.nonemb_cmd; nonemb_cmd->size = sizeof(*resp); nonemb_cmd->va = pci_alloc_consistent(phba->ctrl.pdev, - sizeof(nonemb_cmd->size), + nonemb_cmd->size, &nonemb_cmd->dma); if (!nonemb_cmd->va) { mutex_unlock(&ctrl->mbox_lock); From 6b226487815574193c1da864f2eac274781a2b0c Mon Sep 17 00:00:00 2001 From: Miroslav Urbanek Date: Mon, 21 Nov 2016 15:48:21 +0100 Subject: [PATCH 019/174] flowcache: Increase threshold for refusing new allocations MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The threshold for OOM protection is too small for systems with large number of CPUs. Applications report ENOBUFs on connect() every 10 minutes. The problem is that the variable net->xfrm.flow_cache_gc_count is a global counter while the variable fc->high_watermark is a per-CPU constant. Take the number of CPUs into account as well. Fixes: 6ad3122a08e3 ("flowcache: Avoid OOM condition under preasure") Reported-by: Lukáš Koldrt Tested-by: Jan Hejl Signed-off-by: Miroslav Urbanek Signed-off-by: Steffen Klassert --- net/core/flow.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/core/flow.c b/net/core/flow.c index 3937b1b68d5b..18e8893d4be5 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -95,7 +95,6 @@ static void flow_cache_gc_task(struct work_struct *work) list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) { flow_entry_kill(fce, xfrm); atomic_dec(&xfrm->flow_cache_gc_count); - WARN_ON(atomic_read(&xfrm->flow_cache_gc_count) < 0); } } @@ -236,9 +235,8 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); - if (fcp->hash_count > 2 * fc->high_watermark || - atomic_read(&net->xfrm.flow_cache_gc_count) > fc->high_watermark) { - atomic_inc(&net->xfrm.flow_cache_genid); + if (atomic_read(&net->xfrm.flow_cache_gc_count) > + 2 * num_online_cpus() * fc->high_watermark) { flo = ERR_PTR(-ENOBUFS); goto ret_object; } From 86b4522d19329b3bf9c05722f217568b803439f7 Mon Sep 17 00:00:00 2001 From: Loic Pallardy Date: Wed, 16 Nov 2016 13:57:00 +0100 Subject: [PATCH 020/174] ARM: dts: STiH407-family: fix i2c nodes The I2C nodes are missing #address-cells and #size-cells. This is causing warning at device tree compilation when some I2C device sub-nodes are defined. Signed-off-by: Loic Pallardy --- arch/arm/boot/dts/stih407-family.dtsi | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index 91096a49efa9..8f79b4147bba 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -283,6 +283,8 @@ i2c@9840000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c0_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -296,6 +298,8 @@ i2c@9841000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -309,6 +313,8 @@ i2c@9842000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -322,6 +328,8 @@ i2c@9843000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -335,6 +343,8 @@ i2c@9844000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c4_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -348,6 +358,8 @@ i2c@9845000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c5_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -363,6 +375,8 @@ i2c@9540000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c10_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; @@ -376,6 +390,8 @@ i2c@9541000 { clock-frequency = <400000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c11_default>; + #address-cells = <1>; + #size-cells = <0>; status = "disabled"; }; From 98fb2b95d293c4e29c35f188f7745a5e5db3db2d Mon Sep 17 00:00:00 2001 From: Icenowy Zheng Date: Fri, 18 Nov 2016 00:49:54 +0800 Subject: [PATCH 021/174] clk: sunxi-ng: enable so-said LDOs for A33 SoC's pll-mipi clock In the user manual of A33 SoC, the bit 22 and 23 of pll-mipi control register is called "LDO{1,2}_EN", and according to the BSP source code from Allwinner [1], the LDOs are enabled during the clock's enabling process. The clock failed to generate output if the two LDOs are not enabled. Add the two bits to the clock's gate bits, so that the LDOs are enabled when the PLL is enabled. [1] https://github.com/allwinner-zh/linux-3.4-sunxi/blob/master/drivers/clk/sunxi/clk-sun8iw5.c#L429 Fixes: d05c748bd730 ("clk: sunxi-ng: Add A33 CCU support") Signed-off-by: Icenowy Zheng Acked-by: Chen-Yu Tsai Signed-off-by: Maxime Ripard --- drivers/clk/sunxi-ng/ccu-sun8i-a33.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c index 96b40ca57697..9bd1f78a0547 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-a33.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-a33.c @@ -131,7 +131,7 @@ static SUNXI_CCU_NKM_WITH_GATE_LOCK(pll_mipi_clk, "pll-mipi", 8, 4, /* N */ 4, 2, /* K */ 0, 4, /* M */ - BIT(31), /* gate */ + BIT(31) | BIT(23) | BIT(22), /* gate */ BIT(28), /* lock */ CLK_SET_RATE_UNGATE); From e784930bd645e7df78c66e7872fec282b0620075 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 2 Nov 2016 16:35:51 -0600 Subject: [PATCH 022/174] PCI: Export pcie_find_root_port Export pcie_find_root_port() so we can use it outside of PCIe-AER error injection. Signed-off-by: Johannes Thumshirn Signed-off-by: Bjorn Helgaas --- drivers/pci/pcie/aer/aer_inject.c | 14 -------------- include/linux/pci.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c index db553dc22c8e..2b6a59266689 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -307,20 +307,6 @@ static int pci_bus_set_aer_ops(struct pci_bus *bus) return 0; } -static struct pci_dev *pcie_find_root_port(struct pci_dev *dev) -{ - while (1) { - if (!pci_is_pcie(dev)) - break; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) - return dev; - if (!dev->bus->self) - break; - dev = dev->bus->self; - } - return NULL; -} - static int find_aer_device_iter(struct device *device, void *data) { struct pcie_device **result = data; diff --git a/include/linux/pci.h b/include/linux/pci.h index 0e49f70dbd9b..a38772a85588 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1928,6 +1928,20 @@ static inline int pci_pcie_type(const struct pci_dev *dev) return (pcie_caps_reg(dev) & PCI_EXP_FLAGS_TYPE) >> 4; } +static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) +{ + while (1) { + if (!pci_is_pcie(dev)) + break; + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + return dev; + if (!dev->bus->self) + break; + dev = dev->bus->self; + } + return NULL; +} + void pci_request_acs(void); bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); bool pci_acs_path_enabled(struct pci_dev *start, From e42010d8207f9d15a605ceb8e321bcd9648071b0 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 23 Nov 2016 10:56:28 -0600 Subject: [PATCH 023/174] PCI: Set Read Completion Boundary to 128 iff Root Port supports it (_HPX) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Per PCIe spec r3.0, sec 2.3.1.1, the Read Completion Boundary (RCB) determines the naturally aligned address boundaries on which a Read Request may be serviced with multiple Completions: - For a Root Complex, RCB is 64 bytes or 128 bytes This value is reported in the Link Control Register Note: Bridges and Endpoints may implement a corresponding command bit which may be set by system software to indicate the RCB value for the Root Complex, allowing the Bridge/Endpoint to optimize its behavior when the Root Complex’s RCB is 128 bytes. - For all other system elements, RCB is 128 bytes Per sec 7.8.7, if a Root Port only supports a 64-byte RCB, the RCB of all downstream devices must be clear, indicating an RCB of 64 bytes. If the Root Port supports a 128-byte RCB, we may optionally set the RCB of downstream devices so they know they can generate larger Completions. Some BIOSes supply an _HPX that tells us to set RCB, even though the Root Port doesn't have RCB set, which may lead to Malformed TLP errors if the Endpoint generates completions larger than the Root Port can handle. The IBM x3850 X6 with BIOS version -[A8E120CUS-1.30]- 08/22/2016 supplies such an _HPX and a Mellanox MT27500 ConnectX-3 device fails to initialize: mlx4_core 0000:41:00.0: command 0xfff timed out (go bit not cleared) mlx4_core 0000:41:00.0: device is going to be reset mlx4_core 0000:41:00.0: Failed to obtain HW semaphore, aborting mlx4_core 0000:41:00.0: Fail to reset HCA ------------[ cut here ]------------ kernel BUG at drivers/net/ethernet/mellanox/mlx4/catas.c:193! After 6cd33649fa83 ("PCI: Add pci_configure_device() during enumeration") and 7a1562d4f2d0 ("PCI: Apply _HPX Link Control settings to all devices with a link"), we apply _HPX settings to *all* devices, not just those hot-added after boot. Before 7a1562d4f2d0, we didn't touch the Mellanox RCB, and the device worked. After 7a1562d4f2d0, we set its RCB to 128, and it failed. Set the RCB to 128 iff the Root Port supports a 128-byte RCB. Otherwise, set RCB to 64 bytes. This effectively ignores what _HPX tells us about RCB. Note that this change only affects _HPX handling. If we have no _HPX, this does nothing with RCB. [bhelgaas: changelog, clear RCB if not set for Root Port] Fixes: 6cd33649fa83 ("PCI: Add pci_configure_device() during enumeration") Fixes: 7a1562d4f2d0 ("PCI: Apply _HPX Link Control settings to all devices with a link") Link: https://bugzilla.kernel.org/show_bug.cgi?id=187781 Tested-by: Frank Danapfel Signed-off-by: Johannes Thumshirn Signed-off-by: Bjorn Helgaas Acked-by: Myron Stowe CC: stable@vger.kernel.org # v3.18+ --- drivers/pci/probe.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ab002671fa60..104c46d53121 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1439,6 +1439,21 @@ static void program_hpp_type1(struct pci_dev *dev, struct hpp_type1 *hpp) dev_warn(&dev->dev, "PCI-X settings not supported\n"); } +static bool pcie_root_rcb_set(struct pci_dev *dev) +{ + struct pci_dev *rp = pcie_find_root_port(dev); + u16 lnkctl; + + if (!rp) + return false; + + pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &lnkctl); + if (lnkctl & PCI_EXP_LNKCTL_RCB) + return true; + + return false; +} + static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) { int pos; @@ -1468,9 +1483,20 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) ~hpp->pci_exp_devctl_and, hpp->pci_exp_devctl_or); /* Initialize Link Control Register */ - if (pcie_cap_has_lnkctl(dev)) + if (pcie_cap_has_lnkctl(dev)) { + + /* + * If the Root Port supports Read Completion Boundary of + * 128, set RCB to 128. Otherwise, clear it. + */ + hpp->pci_exp_lnkctl_and |= PCI_EXP_LNKCTL_RCB; + hpp->pci_exp_lnkctl_or &= ~PCI_EXP_LNKCTL_RCB; + if (pcie_root_rcb_set(dev)) + hpp->pci_exp_lnkctl_or |= PCI_EXP_LNKCTL_RCB; + pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, ~hpp->pci_exp_lnkctl_and, hpp->pci_exp_lnkctl_or); + } /* Find Advanced Error Reporting Enhanced Capability */ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR); From b7d79eb4615e3eb5947355f7b4354818cba037f7 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 22 Nov 2016 09:43:27 -0800 Subject: [PATCH 024/174] clk: bcm: Fix unmet Kconfig dependencies for CLK_BCM_63XX With commit f4e871509959 ("clk: iproc: Make clocks visible options"), COMMON_CLK_IPROC gained a dependency on ARCH_BCM_IPROC, yet CLK_BCM_63XX also selects that option, this causes the following Kconfig warning: warning: (CLK_BCM_63XX) selects COMMON_CLK_IPROC which has unmet direct dependencies ((ARCH_BCM_IPROC || COMPILE_TEST) && COMMON_CLK) Fix this by adding proper depends for COMMON_CLK_IPROC Fixes: f4e871509959 ("clk: iproc: Make clocks visible options") Signed-off-by: Florian Fainelli Reviewed-by: Ray Jui [sboyd@codeaurora.org: Drop default part as it's redundant] Signed-off-by: Stephen Boyd --- drivers/clk/bcm/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/bcm/Kconfig b/drivers/clk/bcm/Kconfig index f21e9b7afd1a..e3eed5a78404 100644 --- a/drivers/clk/bcm/Kconfig +++ b/drivers/clk/bcm/Kconfig @@ -20,7 +20,7 @@ config CLK_BCM_KONA config COMMON_CLK_IPROC bool "Broadcom iProc clock support" - depends on ARCH_BCM_IPROC || COMPILE_TEST + depends on ARCH_BCM_IPROC || ARCH_BCM_63XX || COMPILE_TEST depends on COMMON_CLK default ARCH_BCM_IPROC help From 6d8b49c3a3a3e1f11b52edd3b9beb6693bb8061d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 9 Nov 2016 10:24:40 -0800 Subject: [PATCH 025/174] netfilter: Update ip_route_me_harder to consider L3 domain ip_route_me_harder is not considering the L3 domain and sending lookups to the wrong table. For example consider the following output rule: iptables -I OUTPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset using perf to analyze lookups via the fib_table_lookup tracepoint shows: vrf-test 1187 [001] 46887.295927: fib:fib_table_lookup: table 255 oif 0 iif 0 src 0.0.0.0 dst 10.100.1.254 tos 0 scope 0 flags 0 ffffffff8143922c perf_trace_fib_table_lookup ([kernel.kallsyms]) ffffffff81493aac fib_table_lookup ([kernel.kallsyms]) ffffffff8148dda3 __inet_dev_addr_type ([kernel.kallsyms]) ffffffff8148ddf6 inet_addr_type ([kernel.kallsyms]) ffffffff8149e344 ip_route_me_harder ([kernel.kallsyms]) and vrf-test 1187 [001] 46887.295933: fib:fib_table_lookup: table 255 oif 0 iif 1 src 10.100.1.254 dst 10.100.1.2 tos 0 scope 0 flags ffffffff8143922c perf_trace_fib_table_lookup ([kernel.kallsyms]) ffffffff81493aac fib_table_lookup ([kernel.kallsyms]) ffffffff814998ff fib4_rule_action ([kernel.kallsyms]) ffffffff81437f35 fib_rules_lookup ([kernel.kallsyms]) ffffffff81499758 __fib_lookup ([kernel.kallsyms]) ffffffff8144f010 fib_lookup.constprop.34 ([kernel.kallsyms]) ffffffff8144f759 __ip_route_output_key_hash ([kernel.kallsyms]) ffffffff8144fc6a ip_route_output_flow ([kernel.kallsyms]) ffffffff8149e39b ip_route_me_harder ([kernel.kallsyms]) In both cases the lookups are directed to table 255 rather than the table associated with the device via the L3 domain. Update both lookups to pull the L3 domain from the dst currently attached to the skb. Signed-off-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3776ff6749f..b3cc1335adbc 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -24,10 +24,11 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; + struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); + addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) flags |= FLOWI_FLAG_ANYSRC; else @@ -40,6 +41,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t fl4.saddr = saddr; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + if (!fl4.flowi4_oif) + fl4.flowi4_oif = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); From 00b4422fe363cc7cadc51c50c5a0c3c510f0fa14 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 9 Nov 2016 10:25:05 -0800 Subject: [PATCH 026/174] netfilter: Update nf_send_reset6 to consider L3 domain nf_send_reset6 is not considering the L3 domain and lookups are sent to the wrong table. For example consider the following output rule: ip6tables -A OUTPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset using perf to analyze lookups via the fib6_table_lookup tracepoint shows: swapper 0 [001] 248.787816: fib6:fib6_table_lookup: table 255 oif 0 iif 1 src 2100:1::3 dst 2100:1: ffffffff81439cdc perf_trace_fib6_table_lookup ([kernel.kallsyms]) ffffffff814c1ce3 trace_fib6_table_lookup ([kernel.kallsyms]) ffffffff814c3e89 ip6_pol_route ([kernel.kallsyms]) ffffffff814c40d5 ip6_pol_route_output ([kernel.kallsyms]) ffffffff814e7b6f fib6_rule_action ([kernel.kallsyms]) ffffffff81437f60 fib_rules_lookup ([kernel.kallsyms]) ffffffff814e7c79 fib6_rule_lookup ([kernel.kallsyms]) ffffffff814c2541 ip6_route_output_flags ([kernel.kallsyms]) 528 nf_send_reset6 ([nf_reject_ipv6]) The lookup is directed to table 255 rather than the table associated with the device via the L3 domain. Update nf_send_reset6 to pull the L3 domain from the dst currently attached to the skb. Signed-off-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_reject_ipv6.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index a5400223fd74..10090400c72f 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -156,6 +156,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { From 486dcf43da7815baa615822f3e46883ccca5400f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 10 Nov 2016 14:24:40 +0100 Subject: [PATCH 027/174] netfilter: fix nf_conntrack_helper documentation Since kernel 4.7 this defaults to off. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/nf_conntrack-sysctl.txt | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt index 399e4e866a9c..433b6724797a 100644 --- a/Documentation/networking/nf_conntrack-sysctl.txt +++ b/Documentation/networking/nf_conntrack-sysctl.txt @@ -62,10 +62,13 @@ nf_conntrack_generic_timeout - INTEGER (seconds) protocols. nf_conntrack_helper - BOOLEAN - 0 - disabled - not 0 - enabled (default) + 0 - disabled (default) + not 0 - enabled Enable automatic conntrack helper assignment. + If disabled it is required to set up iptables rules to assign + helpers to connections. See the CT target description in the + iptables-extensions(8) man page for further information. nf_conntrack_icmp_timeout - INTEGER (seconds) default 30 From 8ca18eec2b2276b449c1dc86b98bf083c5fe4e09 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 23 Nov 2016 10:11:21 +0000 Subject: [PATCH 028/174] KVM: arm/arm64: vgic: Don't notify EOI for non-SPIs When we inject a level triggerered interrupt (and unless it is backed by the physical distributor - timer style), we request a maintenance interrupt. Part of the processing for that interrupt is to feed to the rest of KVM (and to the eventfd subsystem) the information that the interrupt has been EOIed. But that notification only makes sense for SPIs, and not PPIs (such as the PMU interrupt). Skip over the notification if the interrupt is not an SPI. Cc: stable@vger.kernel.org # 4.7+ Fixes: 140b086dd197 ("KVM: arm/arm64: vgic-new: Add GICv2 world switch backend") Fixes: 59529f69f504 ("KVM: arm/arm64: vgic-new: Add GICv3 world switch backend") Reported-by: Catalin Marinas Tested-by: Catalin Marinas Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic/vgic-v2.c | 6 ++++-- virt/kvm/arm/vgic/vgic-v3.c | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 0a063af40565..9bab86757fa4 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -50,8 +50,10 @@ void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu) WARN_ON(cpuif->vgic_lr[lr] & GICH_LR_STATE); - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); + /* Only SPIs require notification */ + if (vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); } } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 9f0dae397d9c..5c9f9745e6ca 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -41,8 +41,10 @@ void vgic_v3_process_maintenance(struct kvm_vcpu *vcpu) WARN_ON(cpuif->vgic_lr[lr] & ICH_LR_STATE); - kvm_notify_acked_irq(vcpu->kvm, 0, - intid - VGIC_NR_PRIVATE_IRQS); + /* Only SPIs require notification */ + if (vgic_valid_spi(vcpu->kvm, intid)) + kvm_notify_acked_irq(vcpu->kvm, 0, + intid - VGIC_NR_PRIVATE_IRQS); } /* From abd66e9f3cc50c9c3ba4cf609749374090a2f215 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Mon, 14 Nov 2016 22:33:34 +0100 Subject: [PATCH 029/174] netfilter: nft_hash: validate maximum value of u32 netlink hash attribute Use the function nft_parse_u32_check() to fetch the value and validate the u32 attribute into the hash len u8 field. This patch revisits 4da449ae1df9 ("netfilter: nft_exthdr: Add size check on u8 nft_exthdr attributes"). Fixes: cb1b69b0b15b ("netfilter: nf_tables: add hash expression") Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_hash.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index baf694de3935..d5447a22275c 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -53,6 +53,7 @@ static int nft_hash_init(const struct nft_ctx *ctx, { struct nft_hash *priv = nft_expr_priv(expr); u32 len; + int err; if (!tb[NFTA_HASH_SREG] || !tb[NFTA_HASH_DREG] || @@ -67,8 +68,10 @@ static int nft_hash_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - len = ntohl(nla_get_be32(tb[NFTA_HASH_LEN])); - if (len == 0 || len > U8_MAX) + err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); + if (err < 0) + return err; + if (len == 0) return -ERANGE; priv->len = len; From 728e87b49605f7ee02c0415c8255d3d185a36154 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 16 Nov 2016 15:13:35 +0100 Subject: [PATCH 030/174] netfilter: nat: fix cmp return value The comparator works like memcmp, i.e. 0 means objects are equal. In other words, when objects are distinct they are treated as identical, when they are distinct they are allegedly the same. The first case is rare (distinct objects are unlikely to get hashed to same bucket). The second case results in unneeded port conflict resolutions attempts. Fixes: 870190a9ec907 ("netfilter: nat: convert nat bysrc hash to rhashtable") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index bbb8f3df79f7..c632429706eb 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -193,9 +193,12 @@ static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, const struct nf_nat_conn_key *key = arg->key; const struct nf_conn *ct = obj; - return same_src(ct, key->tuple) && - net_eq(nf_ct_net(ct), key->net) && - nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL); + if (!same_src(ct, key->tuple) || + !net_eq(nf_ct_net(ct), key->net) || + !nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL)) + return 1; + + return 0; } static struct rhashtable_params nf_nat_bysource_params = { From 7223ecd4669921cb2a709193521967aaa2b06862 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 16 Nov 2016 15:13:36 +0100 Subject: [PATCH 031/174] netfilter: nat: switch to new rhlist interface I got offlist bug report about failing connections and high cpu usage. This happens because we hit 'elasticity' checks in rhashtable that refuses bucket list exceeding 16 entries. The nat bysrc hash unfortunately needs to insert distinct objects that share same key and are identical (have same source tuple), this cannot be avoided. Switch to the rhlist interface which is designed for this. The nulls_base is removed here, I don't think its needed: A (unlikely) false positive results in unneeded port clash resolution, a false negative results in packet drop during conntrack confirmation, when we try to insert the duplicate into main conntrack hash table. Tested by adding multiple ip addresses to host, then adding iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE ... and then creating multiple connections, from same source port but different addresses: for i in $(seq 2000 2032);do nc -p 1234 192.168.7.1 $i > /dev/null & done (all of these then get hashed to same bysource slot) Then, to test that nat conflict resultion is working: nc -s 10.0.0.1 -p 1234 192.168.7.1 2000 nc -s 10.0.0.2 -p 1234 192.168.7.1 2000 tcp .. src=10.0.0.1 dst=192.168.7.1 sport=1234 dport=2000 src=192.168.7.1 dst=192.168.7.10 sport=2000 dport=1024 [ASSURED] tcp .. src=10.0.0.2 dst=192.168.7.1 sport=1234 dport=2000 src=192.168.7.1 dst=192.168.7.10 sport=2000 dport=1025 [ASSURED] tcp .. src=192.168.7.10 dst=192.168.7.1 sport=1234 dport=2000 src=192.168.7.1 dst=192.168.7.10 sport=2000 dport=1234 [ASSURED] tcp .. src=192.168.7.10 dst=192.168.7.1 sport=1234 dport=2001 src=192.168.7.1 dst=192.168.7.10 sport=2001 dport=1234 [ASSURED] [..] -> nat altered source ports to 1024 and 1025, respectively. This can also be confirmed on destination host which shows ESTAB 0 0 192.168.7.1:2000 192.168.7.10:1024 ESTAB 0 0 192.168.7.1:2000 192.168.7.10:1025 ESTAB 0 0 192.168.7.1:2000 192.168.7.10:1234 Cc: Herbert Xu Fixes: 870190a9ec907 ("netfilter: nat: convert nat bysrc hash to rhashtable") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 +- net/netfilter/nf_nat_core.c | 40 +++++++++++++++++----------- 2 files changed, 25 insertions(+), 17 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 50418052a520..dc143ada9762 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -118,7 +118,7 @@ struct nf_conn { struct nf_ct_ext *ext; #if IS_ENABLED(CONFIG_NF_NAT) - struct rhash_head nat_bysource; + struct rhlist_head nat_bysource; #endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index c632429706eb..5b9c884a452e 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -42,7 +42,7 @@ struct nf_nat_conn_key { const struct nf_conntrack_zone *zone; }; -static struct rhashtable nf_nat_bysource_table; +static struct rhltable nf_nat_bysource_table; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -207,7 +207,6 @@ static struct rhashtable_params nf_nat_bysource_params = { .obj_cmpfn = nf_nat_bysource_cmp, .nelem_hint = 256, .min_size = 1024, - .nulls_base = (1U << RHT_BASE_SHIFT), }; /* Only called for SRC manip */ @@ -226,12 +225,15 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; + struct rhlist_head *hl; - ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key, - nf_nat_bysource_params); - if (!ct) + hl = rhltable_lookup(&nf_nat_bysource_table, &key, + nf_nat_bysource_params); + if (!hl) return 0; + ct = container_of(hl, typeof(*ct), nat_bysource); + nf_ct_invert_tuplepr(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; @@ -449,11 +451,17 @@ nf_nat_setup_info(struct nf_conn *ct, } if (maniptype == NF_NAT_MANIP_SRC) { + struct nf_nat_conn_key key = { + .net = nf_ct_net(ct), + .tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + .zone = nf_ct_zone(ct), + }; int err; - err = rhashtable_insert_fast(&nf_nat_bysource_table, - &ct->nat_bysource, - nf_nat_bysource_params); + err = rhltable_insert_key(&nf_nat_bysource_table, + &key, + &ct->nat_bysource, + nf_nat_bysource_params); if (err) return NF_DROP; } @@ -570,8 +578,8 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * will delete entry from already-freed table. */ ct->status &= ~IPS_NAT_DONE_MASK; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. @@ -701,8 +709,8 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (!nat) return; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); } static struct nf_ct_ext_type nat_extend __read_mostly = { @@ -837,13 +845,13 @@ static int __init nf_nat_init(void) { int ret; - ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); + ret = rhltable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); if (ret) return ret; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -867,7 +875,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -886,7 +894,7 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); } MODULE_LICENSE("GPL"); From d3e2a1110cae6ee5eeb1f9a97addf03e974f12e6 Mon Sep 17 00:00:00 2001 From: "Anders K. Pedersen" Date: Sun, 20 Nov 2016 16:38:47 +0000 Subject: [PATCH 032/174] netfilter: nf_tables: fix inconsistent element expiration calculation As Liping Zhang reports, after commit a8b1e36d0d1d ("netfilter: nft_dynset: fix element timeout for HZ != 1000"), priv->timeout was stored in jiffies, while set->timeout was stored in milliseconds. This is inconsistent and incorrect. Firstly, we already call msecs_to_jiffies in nft_set_elem_init, so priv->timeout will be converted to jiffies twice. Secondly, if the user did not specify the NFTA_DYNSET_TIMEOUT attr, set->timeout will be used, but we forget to call msecs_to_jiffies when do update elements. Fix this by using jiffies internally for traditional sets and doing the conversions to/from msec when interacting with userspace - as dynset already does. This is preferable to doing the conversions, when elements are inserted or updated, because this can happen very frequently on busy dynsets. Fixes: a8b1e36d0d1d ("netfilter: nft_dynset: fix element timeout for HZ != 1000") Reported-by: Liping Zhang Signed-off-by: Anders K. Pedersen Acked-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 14 +++++++++----- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d79d1e9b9546..b02af0bf5777 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -313,7 +313,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @size: maximum set size * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal - * @timeout: default timeout value in msecs + * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 026581b04ea8..e5194f6f906c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2570,7 +2570,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, } if (set->timeout && - nla_put_be64(skb, NFTA_SET_TIMEOUT, cpu_to_be64(set->timeout), + nla_put_be64(skb, NFTA_SET_TIMEOUT, + cpu_to_be64(jiffies_to_msecs(set->timeout)), NFTA_SET_PAD)) goto nla_put_failure; if (set->gc_int && @@ -2859,7 +2860,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_TIMEOUT]))); } gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { @@ -3178,7 +3180,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - cpu_to_be64(*nft_set_ext_timeout(ext)), + cpu_to_be64(jiffies_to_msecs( + *nft_set_ext_timeout(ext))), NFTA_SET_ELEM_PAD)) goto nla_put_failure; @@ -3447,7 +3450,7 @@ void *nft_set_elem_init(const struct nft_set *set, memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) *nft_set_ext_expiration(ext) = - jiffies + msecs_to_jiffies(timeout); + jiffies + timeout; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; @@ -3535,7 +3538,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_ELEM_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_ELEM_TIMEOUT]))); } else if (set->flags & NFT_SET_TIMEOUT) { timeout = set->timeout; } From 49cdc4c74918a5576cb93b679629714d8a9ef399 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Mon, 21 Nov 2016 21:18:23 +0800 Subject: [PATCH 033/174] netfilter: nft_range: add the missing NULL pointer check Otherwise, kernel panic will happen if the user does not specify the related attributes. Fixes: 0f3cd9b36977 ("netfilter: nf_tables: add range expression") Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_range.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index fbc88009ca2e..8f0aaaea1376 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -59,6 +59,12 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr int err; u32 op; + if (!tb[NFTA_RANGE_SREG] || + !tb[NFTA_RANGE_OP] || + !tb[NFTA_RANGE_FROM_DATA] || + !tb[NFTA_RANGE_TO_DATA]) + return -EINVAL; + err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from), &desc_from, tb[NFTA_RANGE_FROM_DATA]); if (err < 0) From 5173bc679dec881120df109a6a2b39143235382c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 23 Nov 2016 01:11:03 +0100 Subject: [PATCH 034/174] netfilter: nat: fix crash when conntrack entry is re-used Stas Nichiporovich reports oops in nf_nat_bysource_cmp(), trying to access nf_conn struct at address 0xffffffffffffff50. This is the result of fetching a null rhash list (struct embedded at offset 176; 0 - 176 gets us ...fff50). The problem is that conntrack entries are allocated from a SLAB_DESTROY_BY_RCU cache, i.e. entries can be free'd and reused on another cpu while nf nat bysource hash access the same conntrack entry. Freeing is fine (we hold rcu read lock); zeroing rhlist_head isn't. -> Move the rhlist struct outside of the memset()-inited area. Fixes: 7c9664351980aaa6a ("netfilter: move nat hlist_head to nf_conn") Reported-by: Stas Nichiporovich Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index dc143ada9762..d9d52c020a70 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -100,6 +100,9 @@ struct nf_conn { possible_net_t ct_net; +#if IS_ENABLED(CONFIG_NF_NAT) + struct rhlist_head nat_bysource; +#endif /* all members below initialized via memset */ u8 __nfct_init_offset[0]; @@ -117,9 +120,6 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; -#if IS_ENABLED(CONFIG_NF_NAT) - struct rhlist_head nat_bysource; -#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; From 747e5a5ff2a2ae84715c33d6679ac3c5220a3aec Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 24 Nov 2016 14:40:50 +0000 Subject: [PATCH 035/174] drm: hdlcd: Fix cleanup order If hdlcd_drm_bind() fails at drm_fbdev_cma_init(), its cleanup will call drm_mode_config_cleanup() as if to balance drm_mode_config_reset(). The net result is that drm_connector_cleanup() will clean up the active connectors long before component_unbind_all() gets called, so when the connector later tries to clean up itself after being unbound, Bad Things can happen: [ 4.121888] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 4.129951] pgd = ffffff80091e0000 [ 4.133345] [00000000] *pgd=00000009ffffe003, *pud=00000009ffffe003, *pmd=0000000000000000 [ 4.141613] Internal error: Oops: 96000005 [#1] PREEMPT SMP [ 4.147144] Modules linked in: [ 4.150188] CPU: 0 PID: 122 Comm: kworker/u12:2 Not tainted 4.8.0-rc2+ #989 [ 4.157097] Hardware name: ARM Juno development board (r1) (DT) [ 4.162981] Workqueue: deferwq deferred_probe_work_func [ 4.168173] task: ffffffc975d93200 task.stack: ffffffc975dac000 [ 4.174055] PC is at drm_connector_cleanup+0x58/0x1c0 [ 4.179074] LR is at tda998x_unbind+0x24/0x40 [ 4.183401] pc : [] lr : [] pstate: 00000045 [ 4.190750] sp : ffffffc975dafa10 [ 4.194041] x29: ffffffc975dafa10 x28: ffffffc9768152a8 [ 4.199325] x27: ffffffc97ff46450 x26: ffffff8008d99000 [ 4.204608] x25: dead000000000100 x24: dead000000000200 [ 4.209891] x23: ffffffc976bf91e8 x22: 0000000000000000 [ 4.215172] x21: ffffffc976bf9170 x20: ffffffc976bf9170 [ 4.220454] x19: ffffffc976bf9018 x18: 0000000000000000 [ 4.225737] x17: 0000000074ce71ee x16: 000000008ff5d35f [ 4.231019] x15: ffffffc97681e91c x14: ffffffffffffffff [ 4.236301] x13: ffffffc97681e185 x12: 0000000000000038 [ 4.241583] x11: 0101010101010101 x10: 0000000000000000 [ 4.246866] x9 : 0000000040000000 x8 : 0000000000210d00 [ 4.252148] x7 : ffffffc97fea8c00 x6 : 000000000000001b [ 4.257430] x5 : ffffff80084b7b8c x4 : 0000000000000080 [ 4.262712] x3 : ffffff8008504128 x2 : ffffffc975df3800 [ 4.267993] x1 : 0000000000000000 x0 : 0000000000000000 ... [ 4.750937] [] drm_connector_cleanup+0x58/0x1c0 [ 4.756990] [] tda998x_unbind+0x24/0x40 [ 4.762354] [] component_unbind.isra.4+0x28/0x50 [ 4.768492] [] component_unbind_all+0xcc/0xd8 [ 4.774373] [] hdlcd_drm_bind+0x234/0x418 [ 4.779909] [] try_to_bring_up_master+0x140/0x1a0 [ 4.786133] [] component_add+0x98/0x170 [ 4.791496] [] tda998x_probe+0x18/0x20 [ 4.796774] [] i2c_device_probe+0x164/0x258 [ 4.802481] [] driver_probe_device+0x204/0x2b0 [ 4.808447] [] __device_attach_driver+0x9c/0xf8 [ 4.814498] [] bus_for_each_drv+0x58/0x98 [ 4.820033] [] __device_attach+0xc4/0x138 [ 4.825567] [] device_initial_probe+0x10/0x18 [ 4.831446] [] bus_probe_device+0x94/0xa0 [ 4.836981] [] deferred_probe_work_func+0x78/0xb0 [ 4.843207] [] process_one_work+0x118/0x378 [ 4.848914] [] worker_thread+0x48/0x498 [ 4.854276] [] kthread+0xd0/0xe8 [ 4.859036] [] ret_from_fork+0x10/0x40 [ 4.864314] Code: f2fbd5b9 f2fbd5b8 f8478ee0 eb17001f (f9400013) [ 4.870472] ---[ end trace a643cfe4ce1d838b ]--- Fix this by moving the drm_mode_config_cleanup() much later such that it correctly balances drm_mode_config_init(). Suggested-by: Russell King Signed-off-by: Robin Murphy Signed-off-by: Liviu Dudau --- drivers/gpu/drm/arm/hdlcd_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index fb6a418ce6be..e138fb51e8ce 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -375,7 +375,6 @@ static int hdlcd_drm_bind(struct device *dev) err_fbdev: drm_kms_helper_poll_fini(drm); - drm_mode_config_cleanup(drm); drm_vblank_cleanup(drm); err_vblank: pm_runtime_disable(drm->dev); @@ -387,6 +386,7 @@ static int hdlcd_drm_bind(struct device *dev) drm_irq_uninstall(drm); of_reserved_mem_device_release(drm->dev); err_free: + drm_mode_config_cleanup(drm); dev_set_drvdata(dev, NULL); drm_dev_unref(drm); From 147fd2874d8a8ba69970f0069d67ac341bf0bb09 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Thu, 24 Nov 2016 23:39:59 +0800 Subject: [PATCH 036/174] driver: ipvlan: Fix one possible memleak in ipvlan_link_new When ipvlan_link_new fails and creates one ipvlan port, it does not destroy the ipvlan port created. It causes mem leak and the physical device contains invalid ipvlan data. Signed-off-by: Gao Feng Signed-off-by: David S. Miller --- drivers/net/ipvlan/ipvlan_main.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index f442eb366863..0fef17874d50 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -497,6 +497,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; + bool create = false; if (!tb[IFLA_LINK]) return -EINVAL; @@ -513,6 +514,7 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, err = ipvlan_port_create(phy_dev); if (err < 0) return err; + create = true; } if (data && data[IFLA_IPVLAN_MODE]) @@ -536,22 +538,27 @@ static int ipvlan_link_new(struct net *src_net, struct net_device *dev, err = register_netdevice(dev); if (err < 0) - return err; + goto destroy_ipvlan_port; err = netdev_upper_dev_link(phy_dev, dev); if (err) { - unregister_netdevice(dev); - return err; + goto unregister_netdev; } err = ipvlan_set_port_mode(port, mode); if (err) { - unregister_netdevice(dev); - return err; + goto unregister_netdev; } list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; + +unregister_netdev: + unregister_netdevice(dev); +destroy_ipvlan_port: + if (create) + ipvlan_port_destroy(phy_dev); + return err; } static void ipvlan_link_delete(struct net_device *dev, struct list_head *head) From c9bd28233b6d0d82ac3ba0215723be0a8262c39c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 24 Nov 2016 17:26:22 +0100 Subject: [PATCH 037/174] irda: fix overly long udelay() irda_get_mtt() returns a hardcoded '10000' in some cases, and with gcc-7, we get a build error because this triggers a compile-time check in udelay(): drivers/net/irda/w83977af_ir.o: In function `w83977af_hard_xmit': w83977af_ir.c:(.text.w83977af_hard_xmit+0x14c): undefined reference to `__bad_udelay' Older compilers did not run into this because they either did not completely inline the irda_get_mtt() or did not consider the 10000 value a constant expression. The code has been wrong since the start of git history. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/irda/w83977af_ir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/irda/w83977af_ir.c b/drivers/net/irda/w83977af_ir.c index 4e3d2e7c697c..e8c3a8c32534 100644 --- a/drivers/net/irda/w83977af_ir.c +++ b/drivers/net/irda/w83977af_ir.c @@ -518,7 +518,9 @@ 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) + if (mtt > 1000) + mdelay(mtt/1000); + else if (mtt) udelay(mtt); /* Enable DMA interrupt */ From fd05d7b18cec1af043990c4b3aabc6780575375c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 24 Nov 2016 19:21:27 +0100 Subject: [PATCH 038/174] net: dsa: fix fixed-link-phy device leaks Make sure to drop the reference taken by of_phy_find_device() when registering and deregistering the fixed-link PHY-device. Fixes: 39b0c705195e ("net: dsa: Allow configuration of CPU & DSA port speeds/duplex") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- net/dsa/dsa.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index a6902c1e2f28..cb0091b99592 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -233,6 +233,8 @@ int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, genphy_read_status(phydev); if (ds->ops->adjust_link) ds->ops->adjust_link(ds, port, phydev); + + put_device(&phydev->mdio.dev); } return 0; @@ -509,8 +511,9 @@ void dsa_cpu_dsa_destroy(struct device_node *port_dn) if (of_phy_is_fixed_link(port_dn)) { phydev = of_phy_find_device(port_dn); if (phydev) { - phy_device_free(phydev); fixed_phy_unregister(phydev); + put_device(&phydev->mdio.dev); + phy_device_free(phydev); } } } From 0da60541f8a771270d310a574cb0adeefcdebcb1 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 24 Nov 2016 19:21:28 +0100 Subject: [PATCH 039/174] net: bcmgenet: fix phydev reference leak Make sure to drop the reference taken by of_phy_find_device() when initialising MOCA PHYs. Fixes: 6ac9de5f6563 ("net: bcmgenet: Register link_update callback for all MoCA PHYs") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 457c3bc8cfff..2e745bd51df4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -542,8 +542,10 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) /* Make sure we initialize MoCA PHYs with a link down */ if (phy_mode == PHY_INTERFACE_MODE_MOCA) { phydev = of_phy_find_device(dn); - if (phydev) + if (phydev) { phydev->link = 0; + put_device(&phydev->mdio.dev); + } } return 0; From 966830340302fd79c51e2a3b9bccca9427256dee Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 24 Nov 2016 19:21:29 +0100 Subject: [PATCH 040/174] net: fsl/fman: fix phydev reference leak Make sure to drop the reference taken by of_phy_find_device() during initialisation when later freeing the struct fman_mac. Fixes: 57ba4c9b56d8 ("fsl/fman: Add FMan MAC support") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/fman_memac.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 53ef51e3bd9e..71a5ded9d1de 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1107,6 +1107,9 @@ int memac_free(struct fman_mac *memac) { free_init_resources(memac); + if (memac->pcsphy) + put_device(&memac->pcsphy->mdio.dev); + kfree(memac->memac_drv_param); kfree(memac); From cb1f3410ff12520b22fa03ccd23892c360de0c26 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 24 Nov 2016 19:21:30 +0100 Subject: [PATCH 041/174] net: fsl/fman: fix fixed-link-phydev reference leak Make sure to drop the reference taken by of_phy_find_device() when looking up a fixed-link phydev during probe. Fixes: 57ba4c9b56d8 ("fsl/fman: Add FMan MAC support") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fman/mac.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 8fe6b3e253fa..736db9d9b0ad 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -892,6 +892,8 @@ static int mac_probe(struct platform_device *_of_dev) priv->fixed_link->duplex = phy->duplex; priv->fixed_link->pause = phy->pause; priv->fixed_link->asym_pause = phy->asym_pause; + + put_device(&phy->mdio.dev); } err = mac_dev->init(mac_dev); From 6ffe1c4cd0a77f51d8d2985aa721d636b03ddf58 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Thu, 24 Nov 2016 19:21:31 +0100 Subject: [PATCH 042/174] net: qcom/emac: fix of_node and phydev leaks Make sure to drop the reference taken by of_phy_find_device() during probe on probe errors and on driver unbind. Also drop the of_node reference taken by of_parse_phandle() in the same path. Fixes: b9b17debc69d ("net: emac: emac gigabit ethernet controller driver") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/qualcomm/emac/emac-phy.c | 1 + drivers/net/ethernet/qualcomm/emac/emac.c | 4 ++++ 2 files changed, 5 insertions(+) diff --git a/drivers/net/ethernet/qualcomm/emac/emac-phy.c b/drivers/net/ethernet/qualcomm/emac/emac-phy.c index da4e90db4d98..99a14df28b96 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-phy.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-phy.c @@ -212,6 +212,7 @@ int emac_phy_config(struct platform_device *pdev, struct emac_adapter *adpt) phy_np = of_parse_phandle(np, "phy-handle", 0); adpt->phydev = of_phy_find_device(phy_np); + of_node_put(phy_np); } if (!adpt->phydev) { diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 4fede4b86538..57b35aeac51a 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -711,6 +711,8 @@ static int emac_probe(struct platform_device *pdev) err_undo_napi: netif_napi_del(&adpt->rx_q.napi); err_undo_mdiobus: + if (!has_acpi_companion(&pdev->dev)) + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); err_undo_clocks: emac_clks_teardown(adpt); @@ -730,6 +732,8 @@ static int emac_remove(struct platform_device *pdev) emac_clks_teardown(adpt); + if (!has_acpi_companion(&pdev->dev)) + put_device(&adpt->phydev->mdio.dev); mdiobus_unregister(adpt->mii_bus); free_netdev(netdev); From e824265d632629c3d2583d86b8a816e886a5136c Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Fri, 25 Nov 2016 10:05:06 +0800 Subject: [PATCH 043/174] driver: macvtap: Unregister netdev rx_handler if macvtap_newlink fails The macvtap_newlink registers the netdev rx_handler firstly, but it does not unregister the handler if macvlan_common_newlink failed. Signed-off-by: Gao Feng Acked-by: Jason Wang Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 070e3290aa6e..bceca2875771 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -491,7 +491,13 @@ static int macvtap_newlink(struct net *src_net, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - return macvlan_common_newlink(src_net, dev, tb, data); + err = macvlan_common_newlink(src_net, dev, tb, data); + if (err) { + netdev_rx_handler_unregister(dev); + return err; + } + + return 0; } static void macvtap_dellink(struct net_device *dev, From 9590112241baff6f9d0e751f9c8ecacbe591417a Mon Sep 17 00:00:00 2001 From: Jon Paul Maloy Date: Fri, 25 Nov 2016 10:35:02 -0500 Subject: [PATCH 044/174] tipc: fix link statistics counter errors In commit e4bf4f76962b ("tipc: simplify packet sequence number handling") we changed the internal representation of the packet sequence number counters from u32 to u16, reflecting what is really sent over the wire. Since then some link statistics counters have been displaying incorrect values, partially because the counters meant to be used as sequence number snapshots are now used as direct counters, stored as u32, and partially because some counter updates are just missing in the code. In this commit we correct this in two ways. First, we base the displayed packet sent/received values on direct counters instead of as previously a calculated difference between current sequence number and a snapshot. Second, we add the missing updates of the counters. This change is compatible with the current netlink API, and requires no changes to the user space tools. Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/link.c | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index ecc12411155e..bda89bf9f4ff 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -47,8 +47,8 @@ #include struct tipc_stats { - u32 sent_info; /* used in counting # sent packets */ - u32 recv_info; /* used in counting # recv'd packets */ + u32 sent_pkts; + u32 recv_pkts; u32 sent_states; u32 recv_states; u32 sent_probes; @@ -857,7 +857,6 @@ void tipc_link_reset(struct tipc_link *l) l->acked = 0; l->silent_intv_cnt = 0; l->rst_cnt = 0; - l->stats.recv_info = 0; l->stale_count = 0; l->bc_peer_is_up = false; memset(&l->mon_state, 0, sizeof(l->mon_state)); @@ -888,6 +887,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *transmq = &l->transmq; struct sk_buff_head *backlogq = &l->backlogq; struct sk_buff *skb, *_skb, *bskb; + int pkt_cnt = skb_queue_len(list); /* Match msg importance against this and all higher backlog limits: */ if (!skb_queue_empty(backlogq)) { @@ -901,6 +901,11 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, return -EMSGSIZE; } + if (pkt_cnt > 1) { + l->stats.sent_fragmented++; + l->stats.sent_fragments += pkt_cnt; + } + /* Prepare each packet for sending, and add to relevant queue: */ while (skb_queue_len(list)) { skb = skb_peek(list); @@ -920,6 +925,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, __skb_queue_tail(xmitq, _skb); TIPC_SKB_CB(skb)->ackers = l->ackers; l->rcv_unacked = 0; + l->stats.sent_pkts++; seqno++; continue; } @@ -968,6 +974,7 @@ void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq) msg_set_ack(hdr, ack); msg_set_bcast_ack(hdr, bc_ack); l->rcv_unacked = 0; + l->stats.sent_pkts++; seqno++; } l->snd_nxt = seqno; @@ -1260,7 +1267,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, /* Deliver packet */ l->rcv_nxt++; - l->stats.recv_info++; + l->stats.recv_pkts++; if (!tipc_data_input(l, skb, l->inputq)) rc |= tipc_link_input(l, skb, l->inputq); if (unlikely(++l->rcv_unacked >= TIPC_MIN_LINK_WIN)) @@ -1800,10 +1807,6 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 win) void tipc_link_reset_stats(struct tipc_link *l) { memset(&l->stats, 0, sizeof(l->stats)); - if (!link_is_bc_sndlink(l)) { - l->stats.sent_info = l->snd_nxt; - l->stats.recv_info = l->rcv_nxt; - } } static void link_print(struct tipc_link *l, const char *str) @@ -1867,12 +1870,12 @@ static int __tipc_nl_add_stats(struct sk_buff *skb, struct tipc_stats *s) }; struct nla_map map[] = { - {TIPC_NLA_STATS_RX_INFO, s->recv_info}, + {TIPC_NLA_STATS_RX_INFO, 0}, {TIPC_NLA_STATS_RX_FRAGMENTS, s->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, s->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, s->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, s->recv_bundled}, - {TIPC_NLA_STATS_TX_INFO, s->sent_info}, + {TIPC_NLA_STATS_TX_INFO, 0}, {TIPC_NLA_STATS_TX_FRAGMENTS, s->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, s->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, s->sent_bundles}, @@ -1947,9 +1950,9 @@ int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg, goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_LINK_MTU, link->mtu)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->rcv_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, link->stats.recv_pkts)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->snd_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, link->stats.sent_pkts)) goto attr_msg_full; if (tipc_link_is_up(link)) @@ -2004,12 +2007,12 @@ static int __tipc_nl_add_bc_link_stat(struct sk_buff *skb, }; struct nla_map map[] = { - {TIPC_NLA_STATS_RX_INFO, stats->recv_info}, + {TIPC_NLA_STATS_RX_INFO, stats->recv_pkts}, {TIPC_NLA_STATS_RX_FRAGMENTS, stats->recv_fragments}, {TIPC_NLA_STATS_RX_FRAGMENTED, stats->recv_fragmented}, {TIPC_NLA_STATS_RX_BUNDLES, stats->recv_bundles}, {TIPC_NLA_STATS_RX_BUNDLED, stats->recv_bundled}, - {TIPC_NLA_STATS_TX_INFO, stats->sent_info}, + {TIPC_NLA_STATS_TX_INFO, stats->sent_pkts}, {TIPC_NLA_STATS_TX_FRAGMENTS, stats->sent_fragments}, {TIPC_NLA_STATS_TX_FRAGMENTED, stats->sent_fragmented}, {TIPC_NLA_STATS_TX_BUNDLES, stats->sent_bundles}, @@ -2076,9 +2079,9 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_LINK_NAME, bcl->name)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, bcl->rcv_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_RX, 0)) goto attr_msg_full; - if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, bcl->snd_nxt)) + if (nla_put_u32(msg->skb, TIPC_NLA_LINK_TX, 0)) goto attr_msg_full; prop = nla_nest_start(msg->skb, TIPC_NLA_LINK_PROP); From d936377414fadbafb4d17148d222fe45ca5442d4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 27 Nov 2016 01:18:01 +0100 Subject: [PATCH 045/174] net, sched: respect rcu grace period on cls destruction Roi reported a crash in flower where tp->root was NULL in ->classify() callbacks. Reason is that in ->destroy() tp->root is set to NULL via RCU_INIT_POINTER(). It's problematic for some of the classifiers, because this doesn't respect RCU grace period for them, and as a result, still outstanding readers from tc_classify() will try to blindly dereference a NULL tp->root. The tp->root object is strictly private to the classifier implementation and holds internal data the core such as tc_ctl_tfilter() doesn't know about. Within some classifiers, such as cls_bpf, cls_basic, etc, tp->root is only checked for NULL in ->get() callback, but nowhere else. This is misleading and seemed to be copied from old classifier code that was not cleaned up properly. For example, d3fa76ee6b4a ("[NET_SCHED]: cls_basic: fix NULL pointer dereference") moved tp->root initialization into ->init() routine, where before it was part of ->change(), so ->get() had to deal with tp->root being NULL back then, so that was indeed a valid case, after d3fa76ee6b4a, not really anymore. We used to set tp->root to NULL long ago in ->destroy(), see 47a1a1d4be29 ("pkt_sched: remove unnecessary xchg() in packet classifiers"); but the NULLifying was reintroduced with the RCUification, but it's not correct for every classifier implementation. In the cases that are fixed here with one exception of cls_cgroup, tp->root object is allocated and initialized inside ->init() callback, which is always performed at a point in time after we allocate a new tp, which means tp and thus tp->root was not globally visible in the tp chain yet (see tc_ctl_tfilter()). Also, on destruction tp->root is strictly kfree_rcu()'ed in ->destroy() handler, same for the tp which is kfree_rcu()'ed right when we return from ->destroy() in tcf_destroy(). This means, the head object's lifetime for such classifiers is always tied to the tp lifetime. The RCU callback invocation for the two kfree_rcu() could be out of order, but that's fine since both are independent. Dropping the RCU_INIT_POINTER(tp->root, NULL) for these classifiers here means that 1) we don't need a useless NULL check in fast-path and, 2) that outstanding readers of that tp in tc_classify() can still execute under respect with RCU grace period as it is actually expected. Things that haven't been touched here: cls_fw and cls_route. They each handle tp->root being NULL in ->classify() path for historic reasons, so their ->destroy() implementation can stay as is. If someone actually cares, they could get cleaned up at some point to avoid the test in fast path. cls_u32 doesn't set tp->root to NULL. For cls_rsvp, I just added a !head should anyone actually be using/testing it, so it at least aligns with cls_fw and cls_route. For cls_flower we additionally need to defer rhashtable destruction (to a sleepable context) after RCU grace period as concurrent readers might still access it. (Note that in this case we need to hold module reference to keep work callback address intact, since we only wait on module unload for all call_rcu()s to finish.) This fixes one race to bring RCU grace period guarantees back. Next step as worked on by Cong however is to fix 1e052be69d04 ("net_sched: destroy proto tp when all filters are gone") to get the order of unlinking the tp in tc_ctl_tfilter() for the RTM_DELTFILTER case right by moving RCU_INIT_POINTER() before tcf_destroy() and let the notification for removal be done through the prior ->delete() callback. Both are independant issues. Once we have that right, we can then clean tp->root up for a number of classifiers by not making them RCU pointers, which requires a new callback (->uninit) that is triggered from tp's RCU callback, where we just kfree() tp->root from there. Fixes: 1f947bf151e9 ("net: sched: rcu'ify cls_bpf") Fixes: 9888faefe132 ("net: sched: cls_basic use RCU") Fixes: 70da9f0bf999 ("net: sched: cls_flow use RCU") Fixes: 77b9900ef53a ("tc: introduce Flower classifier") Fixes: bf3994d2ed31 ("net/sched: introduce Match-all classifier") Fixes: 952313bd6258 ("net: sched: cls_cgroup use RCU") Reported-by: Roi Dayan Signed-off-by: Daniel Borkmann Cc: Cong Wang Cc: John Fastabend Cc: Roi Dayan Cc: Jiri Pirko Acked-by: John Fastabend Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/sched/cls_basic.c | 4 ---- net/sched/cls_bpf.c | 4 ---- net/sched/cls_cgroup.c | 7 +++---- net/sched/cls_flow.c | 1 - net/sched/cls_flower.c | 31 ++++++++++++++++++++++++++----- net/sched/cls_matchall.c | 1 - net/sched/cls_rsvp.h | 3 ++- net/sched/cls_tcindex.c | 1 - 8 files changed, 31 insertions(+), 21 deletions(-) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index eb219b78cd49..5877f6061b57 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -62,9 +62,6 @@ static unsigned long basic_get(struct tcf_proto *tp, u32 handle) struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; - if (head == NULL) - return 0UL; - list_for_each_entry(f, &head->flist, link) { if (f->handle == handle) { l = (unsigned long) f; @@ -109,7 +106,6 @@ static bool basic_destroy(struct tcf_proto *tp, bool force) tcf_unbind_filter(tp, &f->res); call_rcu(&f->rcu, basic_delete_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bb1d5a487081..0a47ba5e6109 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -292,7 +292,6 @@ static bool cls_bpf_destroy(struct tcf_proto *tp, bool force) call_rcu(&prog->rcu, __cls_bpf_delete_prog); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } @@ -303,9 +302,6 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) struct cls_bpf_prog *prog; unsigned long ret = 0UL; - if (head == NULL) - return 0UL; - list_for_each_entry(prog, &head->plist, link) { if (prog->handle == handle) { ret = (unsigned long) prog; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 85233c470035..c1f20077837f 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -137,11 +137,10 @@ static bool cls_cgroup_destroy(struct tcf_proto *tp, bool force) if (!force) return false; - - if (head) { - RCU_INIT_POINTER(tp->root, NULL); + /* Head can still be NULL due to cls_cgroup_init(). */ + if (head) call_rcu(&head->rcu, cls_cgroup_destroy_rcu); - } + return true; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index e39672394c7b..6575aba87630 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -596,7 +596,6 @@ static bool flow_destroy(struct tcf_proto *tp, bool force) list_del_rcu(&f->list); call_rcu(&f->rcu, flow_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6f40fba599b..b296f3991ab2 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -64,7 +65,10 @@ struct cls_fl_head { bool mask_assigned; struct list_head filters; struct rhashtable_params ht_params; - struct rcu_head rcu; + union { + struct work_struct work; + struct rcu_head rcu; + }; }; struct cls_fl_filter { @@ -269,6 +273,24 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc); } +static void fl_destroy_sleepable(struct work_struct *work) +{ + struct cls_fl_head *head = container_of(work, struct cls_fl_head, + work); + if (head->mask_assigned) + rhashtable_destroy(&head->ht); + kfree(head); + module_put(THIS_MODULE); +} + +static void fl_destroy_rcu(struct rcu_head *rcu) +{ + struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu); + + INIT_WORK(&head->work, fl_destroy_sleepable); + schedule_work(&head->work); +} + static bool fl_destroy(struct tcf_proto *tp, bool force) { struct cls_fl_head *head = rtnl_dereference(tp->root); @@ -282,10 +304,9 @@ static bool fl_destroy(struct tcf_proto *tp, bool force) list_del_rcu(&f->list); call_rcu(&f->rcu, fl_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); - if (head->mask_assigned) - rhashtable_destroy(&head->ht); - kfree_rcu(head, rcu); + + __module_get(THIS_MODULE); + call_rcu(&head->rcu, fl_destroy_rcu); return true; } diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 25927b6c4436..f935429bd5ef 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -114,7 +114,6 @@ static bool mall_destroy(struct tcf_proto *tp, bool force) call_rcu(&f->rcu, mall_destroy_filter); } - RCU_INIT_POINTER(tp->root, NULL); kfree_rcu(head, rcu); return true; } diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 4f05a19fb073..322438fb3ffc 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -152,7 +152,8 @@ static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; nhptr = ip_hdr(skb); #endif - + if (unlikely(!head)) + return -1; restart: #if RSVP_DST_LEN == 4 diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 96144bdf30db..0751245a6ace 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -543,7 +543,6 @@ static bool tcindex_destroy(struct tcf_proto *tp, bool force) walker.fn = tcindex_destroy_element; tcindex_walk(tp, &walker); - RCU_INIT_POINTER(tp->root, NULL); call_rcu(&p->rcu, __tcindex_destroy); return true; } From e5f3a4a56ce2a707b2fb8ce37e4414dcac89c672 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Fri, 25 Nov 2016 14:12:00 +0100 Subject: [PATCH 046/174] Documentation: devicetree: clarify usage of the RGMII phy-modes RGMII requires special RX and/or TX delays depending on the actual hardware circuit/wiring. These delays can be added by the MAC, the PHY or the designer of the circuit (the latter means that no delay has to be added by PHY or MAC). There are 4 RGMII phy-modes used describe where a delay should be applied: - rgmii: the RX and TX delays are either added by the MAC (where the exact delay is typically configurable, and can be turned off when no extra delay is needed) or not needed at all (because the hardware wiring adds the delay already). The PHY should neither add the RX nor TX delay in this case. - rgmii-rxid: configures the PHY to enable the RX delay. The MAC should not add the RX delay in this case. - rgmii-txid: configures the PHY to enable the TX delay. The MAC should not add the TX delay in this case. - rgmii-id: combines rgmii-rxid and rgmii-txid and thus configures the PHY to enable the RX and TX delays. The MAC should neither add the RX nor TX delay in this case. Document these cases in the ethernet.txt documentation to make it clear when to use each mode. If applied incorrectly one might end up with MAC and PHY both enabling for example the TX delay, which breaks ethernet TX traffic on 1000Mbit/s links. Signed-off-by: Martin Blumenstingl Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- .../devicetree/bindings/net/ethernet.txt | 24 +++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt index e1d76812419c..05150957ecfd 100644 --- a/Documentation/devicetree/bindings/net/ethernet.txt +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -9,10 +9,26 @@ The following properties are common to the Ethernet controllers: - max-speed: number, specifies maximum speed in Mbit/s supported by the device; - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than the maximum frame size (there's contradiction in ePAPR). -- phy-mode: string, operation mode of the PHY interface; supported values are - "mii", "gmii", "sgmii", "qsgmii", "tbi", "rev-mii", "rmii", "rgmii", "rgmii-id", - "rgmii-rxid", "rgmii-txid", "rtbi", "smii", "xgmii", "trgmii"; this is now a - de-facto standard property; +- phy-mode: string, operation mode of the PHY interface. This is now a de-facto + standard property; supported values are: + * "mii" + * "gmii" + * "sgmii" + * "qsgmii" + * "tbi" + * "rev-mii" + * "rmii" + * "rgmii" (RX and TX delays are added by the MAC when required) + * "rgmii-id" (RGMII with internal RX and TX delays provided by the PHY, the + MAC should not add the RX or TX delays in this case) + * "rgmii-rxid" (RGMII with internal RX delay provided by the PHY, the MAC + should not add an RX delay in this case) + * "rgmii-txid" (RGMII with internal TX delay provided by the PHY, the MAC + should not add an TX delay in this case) + * "rtbi" + * "smii" + * "xgmii" + * "trgmii" - phy-connection-type: the same as "phy-mode" property but described in ePAPR; - phy-handle: phandle, specifies a reference to a node representing a PHY device; this property is described in ePAPR and so preferred; From e3230494b57ece68750e3e32d3e53d6b00917058 Mon Sep 17 00:00:00 2001 From: Martin Blumenstingl Date: Fri, 25 Nov 2016 14:12:01 +0100 Subject: [PATCH 047/174] net: phy: realtek: fix enabling of the TX-delay for RTL8211F The old logic always enabled the TX-delay when the phy-mode was set to PHY_INTERFACE_MODE_RGMII. There are dedicated phy-modes which tell the PHY driver to enable the RX and/or TX delays: - PHY_INTERFACE_MODE_RGMII should disable the RX and TX delay in the PHY (if required, the MAC should add the delays in this case) - PHY_INTERFACE_MODE_RGMII_ID should enable RX and TX delay in the PHY - PHY_INTERFACE_MODE_RGMII_TXID should enable the TX delay in the PHY - PHY_INTERFACE_MODE_RGMII_RXID should enable the RX delay in the PHY (currently not supported by RTL8211F) With this patch we enable the TX delay for PHY_INTERFACE_MODE_RGMII_ID and PHY_INTERFACE_MODE_RGMII_TXID. Additionally we now explicity disable the TX-delay, which seems to be enabled automatically after a hard-reset of the PHY (by triggering it's reset pin) to get a consistent state (as defined by the phy-mode). This fixes a compatibility problem with some SoCs where the TX-delay was also added by the MAC. With the TX-delay being applied twice the TX clock was off and TX traffic was broken or very slow (<10Mbit/s) on 1000Mbit/s links. Signed-off-by: Martin Blumenstingl Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/realtek.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index aadd6e9f54ad..9cbe645e3d89 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -102,15 +102,19 @@ static int rtl8211f_config_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->interface == PHY_INTERFACE_MODE_RGMII) { - /* enable TXDLY */ - phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08); - reg = phy_read(phydev, 0x11); + phy_write(phydev, RTL8211F_PAGE_SELECT, 0xd08); + reg = phy_read(phydev, 0x11); + + /* enable TX-delay for rgmii-id and rgmii-txid, otherwise disable it */ + if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || + phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) reg |= RTL8211F_TX_DELAY; - phy_write(phydev, 0x11, reg); - /* restore to default page 0 */ - phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0); - } + else + reg &= ~RTL8211F_TX_DELAY; + + phy_write(phydev, 0x11, reg); + /* restore to default page 0 */ + phy_write(phydev, RTL8211F_PAGE_SELECT, 0x0); return 0; } From 4df21dfcf2291865cf673ac786a81c7a3f7afcf5 Mon Sep 17 00:00:00 2001 From: Julian Wollrath Date: Fri, 25 Nov 2016 15:05:26 +0100 Subject: [PATCH 048/174] tcp: Set DEFAULT_TCP_CONG to bbr if DEFAULT_BBR is set Signed-off-by: Julian Wollrath Signed-off-by: David S. Miller --- net/ipv4/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 300b06888fdf..b54b3ca939db 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -715,6 +715,7 @@ config DEFAULT_TCP_CONG default "reno" if DEFAULT_RENO default "dctcp" if DEFAULT_DCTCP default "cdg" if DEFAULT_CDG + default "bbr" if DEFAULT_BBR default "cubic" config TCP_MD5SIG From 3c7c7a2fc8811bc7097479f69acf2527693d7562 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 23 Nov 2016 17:43:17 -0800 Subject: [PATCH 049/174] ARC: Don't use "+l" inline asm constraint Apparenty this is coming in the way of gcc fix which inhibits the usage of LP_COUNT as a gpr. Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta --- arch/arc/include/asm/delay.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index 08e7e2a16ac1..a36e8601114d 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -22,10 +22,11 @@ static inline void __delay(unsigned long loops) { __asm__ __volatile__( - " lp 1f \n" - " nop \n" - "1: \n" - : "+l"(loops)); + " mov lp_count, %0 \n" + " lp 1f \n" + " nop \n" + "1: \n" + : : "r"(loops)); } extern void __bad_udelay(void); From 23cb1f644019bac49d87b4dd7c1eac0569cc4f53 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 28 Nov 2016 09:18:21 -0800 Subject: [PATCH 050/174] ARC: mm: IOC: Don't enable IOC by default Signed-off-by: Vineet Gupta --- arch/arc/mm/cache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 2b96cfc3be75..50d71695cd4e 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -23,7 +23,7 @@ static int l2_line_sz; static int ioc_exists; -int slc_enable = 1, ioc_enable = 1; +int slc_enable = 1, ioc_enable = 0; unsigned long perip_base = ARC_UNCACHED_ADDR_SPACE; /* legacy value for boot */ unsigned long perip_end = 0xFFFFFFFF; /* legacy value */ From 91eefaabf102c539e6f5531e9a1e5ed46d2b41ca Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Sat, 26 Nov 2016 21:53:52 +0100 Subject: [PATCH 051/174] amd-xgbe: Fix unused suspend handlers build warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix: drivers/net/ethernet/amd/xgbe/xgbe-main.c:835:12: warning: ‘xgbe_suspend’ defined but not used [-Wunused-function] drivers/net/ethernet/amd/xgbe/xgbe-main.c:855:12: warning: ‘xgbe_resume’ defined but not used [-Wunused-function] I see it during randconfig builds here. Signed-off-by: Borislav Petkov Cc: Tom Lendacky Cc: netdev@vger.kernel.org Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/xgbe/xgbe-main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 9de078819aa6..4f7635178200 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -829,7 +829,7 @@ static int xgbe_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int xgbe_suspend(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); @@ -874,7 +874,7 @@ static int xgbe_resume(struct device *dev) return ret; } -#endif /* CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_ACPI static const struct acpi_device_id xgbe_acpi_match[] = { From faa1fa54fd25a59a6c4b731ac652a2b7cd21ace8 Mon Sep 17 00:00:00 2001 From: Roi Dayan Date: Sun, 27 Nov 2016 12:14:49 +0200 Subject: [PATCH 052/174] net/sched: Export tc_tunnel_key so its UAPI accessible Export tc_tunnel_key so it can be used from user space. Signed-off-by: Roi Dayan Reviewed-by: Amir Vadai Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/Kbuild | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/tc_act/Kbuild b/include/uapi/linux/tc_act/Kbuild index e3969bd939e4..9611c7b6c18f 100644 --- a/include/uapi/linux/tc_act/Kbuild +++ b/include/uapi/linux/tc_act/Kbuild @@ -11,3 +11,4 @@ header-y += tc_vlan.h header-y += tc_bpf.h header-y += tc_connmark.h header-y += tc_ife.h +header-y += tc_tunnel_key.h From b4353708f5a1c084fd73f1b6fd243b142157b173 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Sun, 27 Nov 2016 19:20:51 +0200 Subject: [PATCH 053/174] Revert "net/mlx4_en: Avoid unregister_netdev at shutdown flow" This reverts commit 9d76931180557270796f9631e2c79b9c7bb3c9fb. Using unregister_netdev at shutdown flow prevents calling the netdev's ndos or trying to access its freed resources. This fixes crashes like the following: Call Trace: [] dev_get_phys_port_id+0x1e/0x30 [] rtnl_fill_ifinfo+0x4be/0xff0 [] rtmsg_ifinfo_build_skb+0x73/0xe0 [] rtmsg_ifinfo.part.27+0x16/0x50 [] rtmsg_ifinfo+0x18/0x20 [] netdev_state_change+0x46/0x50 [] linkwatch_do_dev+0x38/0x50 [] __linkwatch_run_queue+0xf5/0x170 [] linkwatch_event+0x25/0x30 [] process_one_work+0x152/0x400 [] worker_thread+0x125/0x4b0 [] ? rescuer_thread+0x350/0x350 [] kthread+0xca/0xe0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x25/0x30 Fixes: 9d7693118055 ("net/mlx4_en: Avoid unregister_netdev at shutdown flow") Signed-off-by: Tariq Toukan Reported-by: Sebastian Ott Reported-by: Steve Wise Cc: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 17 ++--------------- drivers/net/ethernet/mellanox/mlx4/main.c | 5 +---- include/linux/mlx4/device.h | 1 - 3 files changed, 3 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a60f635da78b..fb8bb027b69c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2079,13 +2079,6 @@ static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) return -ENOMEM; } -static void mlx4_en_shutdown(struct net_device *dev) -{ - rtnl_lock(); - netif_device_detach(dev); - mlx4_en_close(dev); - rtnl_unlock(); -} static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, struct mlx4_en_priv *src, @@ -2162,8 +2155,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - bool shutdown = mdev->dev->persist->interface_state & - MLX4_INTERFACE_STATE_SHUTDOWN; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2171,10 +2162,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (priv->registered) { devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, priv->port)); - if (shutdown) - mlx4_en_shutdown(dev); - else - unregister_netdev(dev); + unregister_netdev(dev); } if (priv->allocated) @@ -2203,8 +2191,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) kfree(priv->tx_ring); kfree(priv->tx_cq); - if (!shutdown) - free_netdev(dev); + free_netdev(dev); } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 6f4e67bc3538..75d07fa9d0b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4147,11 +4147,8 @@ static void mlx4_shutdown(struct pci_dev *pdev) mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); - if (persist->interface_state & MLX4_INTERFACE_STATE_UP) { - /* Notify mlx4 clients that the kernel is being shut down */ - persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN; + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); - } mutex_unlock(&persist->interface_state_mutex); } diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 3be7abd6e722..c9f379689dd0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -476,7 +476,6 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, - MLX4_INTERFACE_STATE_SHUTDOWN = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ From 44b911e77793d686b481608770d0c55c18055ba0 Mon Sep 17 00:00:00 2001 From: Jack Morgenstein Date: Sun, 27 Nov 2016 19:20:52 +0200 Subject: [PATCH 054/174] net/mlx4: Fix uninitialized fields in rule when adding promiscuous mode to device managed flow steering In procedure mlx4_flow_steer_promisc_add(), several fields were left uninitialized in the rule structure. Correctly initialize these fields. Fixes: 592e49dda812 ("net/mlx4: Implement promiscuous mode with device managed flow-steering") Signed-off-by: Jack Morgenstein Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/mcg.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 94b891c118c1..1a670b681555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1457,7 +1457,12 @@ EXPORT_SYMBOL_GPL(mlx4_multicast_detach); int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode) { - struct mlx4_net_trans_rule rule; + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + }; + u64 *regid_p; switch (mode) { From e58566b1b17fef5c4590e652a337afe66277131a Mon Sep 17 00:00:00 2001 From: Tushar Dave Date: Wed, 23 Nov 2016 18:28:04 -0800 Subject: [PATCH 055/174] qlogicpti: Fix compiler warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit qlogicpti uses '__u32' for dma handle while invoking kernel DMA APIs, instead of using dma_addr_t. This hasn't caused any 'incompatible pointer type' warning on SPARC because until now dma_addr_t is of type u32. However, recent changes in SPARC ATU (iommu) enabled 64bit DMA and therefore dma_addr_t became of type u64. This makes 'incompatible pointer type' warnings inevitable. e.g. drivers/scsi/qlogicpti.c: In function ‘qpti_map_queues’: drivers/scsi/qlogicpti.c:813: warning: passing argument 3 of ‘dma_alloc_coherent’ from incompatible pointer type ./include/linux/dma-mapping.h:445: note: expected ‘dma_addr_t *’ but argument is of type ‘__u32 *’ drivers/scsi/qlogicpti.c:822: warning: passing argument 3 of ‘dma_alloc_coherent’ from incompatible pointer type ./include/linux/dma-mapping.h:445: note: expected ‘dma_addr_t *’ but argument is of type ‘__u32 *’ For the record, qlogicpti never executes on sun4v. Therefore even though 64bit DMA is enabled on SPARC, qlogicpti continues to use legacy iommu that guarantees DMA address is always in 32bit range. This patch resolves aforementioned compiler warnings. Signed-off-by: Tushar Dave Reviewed-by: thomas tai Signed-off-by: David S. Miller --- drivers/scsi/qlogicpti.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/qlogicpti.h b/drivers/scsi/qlogicpti.h index 4377e87ee79c..892a0b058b99 100644 --- a/drivers/scsi/qlogicpti.h +++ b/drivers/scsi/qlogicpti.h @@ -356,8 +356,8 @@ struct qlogicpti { /* The rest of the elements are unimportant for performance. */ struct qlogicpti *next; - __u32 res_dvma; /* Ptr to RESPONSE bufs (DVMA)*/ - __u32 req_dvma; /* Ptr to REQUEST bufs (DVMA) */ + dma_addr_t res_dvma; /* Ptr to RESPONSE bufs (DVMA)*/ + dma_addr_t req_dvma; /* Ptr to REQUEST bufs (DVMA) */ u_char fware_majrev, fware_minrev, fware_micrev; struct Scsi_Host *qhost; int qpti_id; From 16f46050e7094a95554555a505a984535d253cf6 Mon Sep 17 00:00:00 2001 From: Tushar Dave Date: Thu, 24 Nov 2016 12:35:16 -0800 Subject: [PATCH 056/174] dbri: Fix compiler warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dbri uses 'u32' for dma handle while invoking kernel DMA APIs, instead of using dma_addr_t. This hasn't caused any 'incompatible pointer type' warning on SPARC because until now dma_addr_t is of type u32. However, recent changes in SPARC ATU (iommu) enabled 64bit DMA and therefore dma_addr_t became of type u64. This makes 'incompatible pointer type' warnings inevitable. e.g. sound/sparc/dbri.c: In function ‘snd_dbri_create’: sound/sparc/dbri.c:2538: warning: passing argument 3 of ‘dma_zalloc_coherent’ from incompatible pointer type ./include/linux/dma-mapping.h:608: note: expected ‘dma_addr_t *’ but argument is of type ‘u32 *’ For the record, dbri(sbus) driver never executes on sun4v. Therefore even though 64bit DMA is enabled on SPARC, dbri continues to use legacy iommu that guarantees DMA address is always in 32bit range. This patch resolves above compiler warning. Signed-off-by: Tushar Dave Reviewed-by: thomas tai Signed-off-by: David S. Miller --- sound/sparc/dbri.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/sound/sparc/dbri.c b/sound/sparc/dbri.c index 0190cb6332f2..3fe4468ea2c5 100644 --- a/sound/sparc/dbri.c +++ b/sound/sparc/dbri.c @@ -304,7 +304,7 @@ struct snd_dbri { spinlock_t lock; struct dbri_dma *dma; /* Pointer to our DMA block */ - u32 dma_dvma; /* DBRI visible DMA address */ + dma_addr_t dma_dvma; /* DBRI visible DMA address */ void __iomem *regs; /* dbri HW regs */ int dbri_irqp; /* intr queue pointer */ @@ -657,12 +657,14 @@ static void dbri_cmdwait(struct snd_dbri *dbri) */ static s32 *dbri_cmdlock(struct snd_dbri *dbri, int len) { + u32 dvma_addr = (u32)dbri->dma_dvma; + /* Space for 2 WAIT cmds (replaced later by 1 JUMP cmd) */ len += 2; spin_lock(&dbri->cmdlock); if (dbri->cmdptr - dbri->dma->cmd + len < DBRI_NO_CMDS - 2) return dbri->cmdptr + 2; - else if (len < sbus_readl(dbri->regs + REG8) - dbri->dma_dvma) + else if (len < sbus_readl(dbri->regs + REG8) - dvma_addr) return dbri->dma->cmd; else printk(KERN_ERR "DBRI: no space for commands."); @@ -680,6 +682,7 @@ static s32 *dbri_cmdlock(struct snd_dbri *dbri, int len) */ static void dbri_cmdsend(struct snd_dbri *dbri, s32 *cmd, int len) { + u32 dvma_addr = (u32)dbri->dma_dvma; s32 tmp, addr; static int wait_id = 0; @@ -689,7 +692,7 @@ static void dbri_cmdsend(struct snd_dbri *dbri, s32 *cmd, int len) *(cmd+1) = DBRI_CMD(D_WAIT, 1, wait_id); /* Replace the last command with JUMP */ - addr = dbri->dma_dvma + (cmd - len - dbri->dma->cmd) * sizeof(s32); + addr = dvma_addr + (cmd - len - dbri->dma->cmd) * sizeof(s32); *(dbri->cmdptr+1) = addr; *(dbri->cmdptr) = DBRI_CMD(D_JUMP, 0, 0); @@ -747,6 +750,7 @@ static void dbri_reset(struct snd_dbri *dbri) /* Lock must not be held before calling this */ static void dbri_initialize(struct snd_dbri *dbri) { + u32 dvma_addr = (u32)dbri->dma_dvma; s32 *cmd; u32 dma_addr; unsigned long flags; @@ -764,7 +768,7 @@ static void dbri_initialize(struct snd_dbri *dbri) /* * Initialize the interrupt ring buffer. */ - dma_addr = dbri->dma_dvma + dbri_dma_off(intr, 0); + dma_addr = dvma_addr + dbri_dma_off(intr, 0); dbri->dma->intr[0] = dma_addr; dbri->dbri_irqp = 1; /* @@ -778,7 +782,7 @@ static void dbri_initialize(struct snd_dbri *dbri) dbri->cmdptr = cmd; *(cmd++) = DBRI_CMD(D_WAIT, 1, 0); *(cmd++) = DBRI_CMD(D_WAIT, 1, 0); - dma_addr = dbri->dma_dvma + dbri_dma_off(cmd, 0); + dma_addr = dvma_addr + dbri_dma_off(cmd, 0); sbus_writel(dma_addr, dbri->regs + REG8); spin_unlock(&dbri->cmdlock); @@ -1077,6 +1081,7 @@ static void recv_fixed(struct snd_dbri *dbri, int pipe, volatile __u32 *ptr) static int setup_descs(struct snd_dbri *dbri, int streamno, unsigned int period) { struct dbri_streaminfo *info = &dbri->stream_info[streamno]; + u32 dvma_addr = (u32)dbri->dma_dvma; __u32 dvma_buffer; int desc; int len; @@ -1177,7 +1182,7 @@ static int setup_descs(struct snd_dbri *dbri, int streamno, unsigned int period) else { dbri->next_desc[last_desc] = desc; dbri->dma->desc[last_desc].nda = - dbri->dma_dvma + dbri_dma_off(desc, desc); + dvma_addr + dbri_dma_off(desc, desc); } last_desc = desc; @@ -1192,7 +1197,7 @@ static int setup_descs(struct snd_dbri *dbri, int streamno, unsigned int period) } dbri->dma->desc[last_desc].nda = - dbri->dma_dvma + dbri_dma_off(desc, first_desc); + dvma_addr + dbri_dma_off(desc, first_desc); dbri->next_desc[last_desc] = first_desc; dbri->pipes[info->pipe].first_desc = first_desc; dbri->pipes[info->pipe].desc = first_desc; @@ -1697,6 +1702,7 @@ interrupts are disabled. static void xmit_descs(struct snd_dbri *dbri) { struct dbri_streaminfo *info; + u32 dvma_addr = (u32)dbri->dma_dvma; s32 *cmd; unsigned long flags; int first_td; @@ -1718,7 +1724,7 @@ static void xmit_descs(struct snd_dbri *dbri) *(cmd++) = DBRI_CMD(D_SDP, 0, dbri->pipes[info->pipe].sdp | D_SDP_P | D_SDP_EVERY | D_SDP_C); - *(cmd++) = dbri->dma_dvma + + *(cmd++) = dvma_addr + dbri_dma_off(desc, first_td); dbri_cmdsend(dbri, cmd, 2); @@ -1740,7 +1746,7 @@ static void xmit_descs(struct snd_dbri *dbri) *(cmd++) = DBRI_CMD(D_SDP, 0, dbri->pipes[info->pipe].sdp | D_SDP_P | D_SDP_EVERY | D_SDP_C); - *(cmd++) = dbri->dma_dvma + + *(cmd++) = dvma_addr + dbri_dma_off(desc, first_td); dbri_cmdsend(dbri, cmd, 2); @@ -2539,7 +2545,7 @@ static int snd_dbri_create(struct snd_card *card, if (!dbri->dma) return -ENOMEM; - dprintk(D_GEN, "DMA Cmd Block 0x%p (0x%08x)\n", + dprintk(D_GEN, "DMA Cmd Block 0x%p (%pad)\n", dbri->dma, dbri->dma_dvma); /* Map the registers into memory. */ From 79dc7e3f1cd323be4c81aa1a94faa1b3ed987fb2 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 27 Nov 2016 18:52:53 -0800 Subject: [PATCH 057/174] net: handle no dst on skb in icmp6_send Andrey reported the following while fuzzing the kernel with syzkaller: kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN Modules linked in: CPU: 0 PID: 3859 Comm: a.out Not tainted 4.9.0-rc6+ #429 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff8800666d4200 task.stack: ffff880067348000 RIP: 0010:[] [] icmp6_send+0x5fc/0x1e30 net/ipv6/icmp.c:451 RSP: 0018:ffff88006734f2c0 EFLAGS: 00010206 RAX: ffff8800666d4200 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: dffffc0000000000 RDI: 0000000000000018 RBP: ffff88006734f630 R08: ffff880064138418 R09: 0000000000000003 R10: dffffc0000000000 R11: 0000000000000005 R12: 0000000000000000 R13: ffffffff84e7e200 R14: ffff880064138484 R15: ffff8800641383c0 FS: 00007fb3887a07c0(0000) GS:ffff88006cc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000006b040000 CR4: 00000000000006f0 Stack: ffff8800666d4200 ffff8800666d49f8 ffff8800666d4200 ffffffff84c02460 ffff8800666d4a1a 1ffff1000ccdaa2f ffff88006734f498 0000000000000046 ffff88006734f440 ffffffff832f4269 ffff880064ba7456 0000000000000000 Call Trace: [] icmpv6_param_prob+0x2c/0x40 net/ipv6/icmp.c:557 [< inline >] ip6_tlvopt_unknown net/ipv6/exthdrs.c:88 [] ip6_parse_tlv+0x555/0x670 net/ipv6/exthdrs.c:157 [] ipv6_parse_hopopts+0x199/0x460 net/ipv6/exthdrs.c:663 [] ipv6_rcv+0xfa3/0x1dc0 net/ipv6/ip6_input.c:191 ... icmp6_send / icmpv6_send is invoked for both rx and tx paths. In both cases the dst->dev should be preferred for determining the L3 domain if the dst has been set on the skb. Fallback to the skb->dev if it has not. This covers the case reported here where icmp6_send is invoked on Rx before the route lookup. Fixes: 5d41ce29e ("net: icmp6_send should use dst dev to determine L3 domain") Reported-by: Andrey Konovalov Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/icmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 7370ad2e693a..2772004ba5a1 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -447,8 +447,10 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (__ipv6_addr_needs_scope_id(addr_type)) iif = skb->dev->ifindex; - else - iif = l3mdev_master_ifindex(skb_dst(skb)->dev); + else { + dst = skb_dst(skb); + iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev); + } /* * Must not send error if the source does not uniquely From 7a99cd6e213685b78118382e6a8fed506c82ccb2 Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Mon, 28 Nov 2016 09:48:48 +0300 Subject: [PATCH 058/174] net: dsa: fix unbalanced dsa_switch_tree reference counting _dsa_register_switch() gets a dsa_switch_tree object either via dsa_get_dst() or via dsa_add_dst(). Former path does not increase kref in returned object (resulting into caller not owning a reference), while later path does create a new object (resulting into caller owning a reference). The rest of _dsa_register_switch() assumes that it owns a reference, and calls dsa_put_dst(). This causes a memory breakage if first switch in the tree initialized successfully, but second failed to initialize. In particular, freed dsa_swith_tree object is left referenced by switch that was initialized, and later access to sysfs attributes of that switch cause OOPS. To fix, need to add kref_get() call to dsa_get_dst(). Fixes: 83c0afaec7b7 ("net: dsa: Add new binding implementation") Signed-off-by: Nikita Yushchenko Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- net/dsa/dsa2.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index f8a7d9aab437..5fff951a0a49 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -28,8 +28,10 @@ static struct dsa_switch_tree *dsa_get_dst(u32 tree) struct dsa_switch_tree *dst; list_for_each_entry(dst, &dsa_switch_trees, list) - if (dst->tree == tree) + if (dst->tree == tree) { + kref_get(&dst->refcount); return dst; + } return NULL; } From 2dbb4c05d048995455857a7c2927a4297fc66c3b Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Mon, 28 Nov 2016 13:48:30 +0100 Subject: [PATCH 059/174] bpf/samples: Fix PT_REGS_IP on s390x and use it The files "sampleip_kern.c" and "trace_event_kern.c" directly access "ctx->regs.ip" which is not available on s390x. Fix this and use the PT_REGS_IP() macro instead. Also fix the macro for s390x and use "psw.addr" from "pt_regs". Reported-by: Zvonko Kosic Signed-off-by: Michael Holzheu Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- samples/bpf/bpf_helpers.h | 2 +- samples/bpf/sampleip_kern.c | 2 +- samples/bpf/trace_event_kern.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 90f44bd2045e..dadd5161bd91 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -113,7 +113,7 @@ static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = #define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ #define PT_REGS_RC(x) ((x)->gprs[2]) #define PT_REGS_SP(x) ((x)->gprs[15]) -#define PT_REGS_IP(x) ((x)->ip) +#define PT_REGS_IP(x) ((x)->psw.addr) #elif defined(__aarch64__) diff --git a/samples/bpf/sampleip_kern.c b/samples/bpf/sampleip_kern.c index 774a681f374a..ceabf31079cf 100644 --- a/samples/bpf/sampleip_kern.c +++ b/samples/bpf/sampleip_kern.c @@ -25,7 +25,7 @@ int do_sample(struct bpf_perf_event_data *ctx) u64 ip; u32 *value, init_val = 1; - ip = ctx->regs.ip; + ip = PT_REGS_IP(&ctx->regs); value = bpf_map_lookup_elem(&ip_map, &ip); if (value) *value += 1; diff --git a/samples/bpf/trace_event_kern.c b/samples/bpf/trace_event_kern.c index 71a8ed32823e..41b6115a32eb 100644 --- a/samples/bpf/trace_event_kern.c +++ b/samples/bpf/trace_event_kern.c @@ -50,7 +50,7 @@ int bpf_prog1(struct bpf_perf_event_data *ctx) key.userstack = bpf_get_stackid(ctx, &stackmap, USER_STACKID_FLAGS); if ((int)key.kernstack < 0 && (int)key.userstack < 0) { bpf_trace_printk(fmt, sizeof(fmt), cpu, ctx->sample_period, - ctx->regs.ip); + PT_REGS_IP(&ctx->regs)); return 0; } From b64268d8a3f623c9b88676ad3dfacc95cfcfc62f Mon Sep 17 00:00:00 2001 From: Rex Zhu Date: Thu, 24 Nov 2016 13:33:47 +0800 Subject: [PATCH 060/174] drm/amd/powerplay: initialize the soft_regs offset in struct smu7_hwmgr This could lead to mclk dpm problems on some boards. Signed-off-by: Rex Zhu Ack-by: Tom St Denis Reviewed-by: Huang Rui Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c index 4ccc0b72324d..71bb2f8dc157 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c @@ -2214,6 +2214,7 @@ uint32_t polaris10_get_mac_definition(uint32_t value) int polaris10_process_firmware_header(struct pp_hwmgr *hwmgr) { struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smumgr->backend); + struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); uint32_t tmp; int result; bool error = false; @@ -2233,8 +2234,10 @@ int polaris10_process_firmware_header(struct pp_hwmgr *hwmgr) offsetof(SMU74_Firmware_Header, SoftRegisters), &tmp, SMC_RAM_END); - if (!result) + if (!result) { + data->soft_regs_start = tmp; smu_data->smu7_data.soft_regs_start = tmp; + } error |= (0 != result); From 5f4b55699aaff1028468e3f53853d781cdafedd6 Mon Sep 17 00:00:00 2001 From: Sachin Prabhu Date: Mon, 17 Oct 2016 16:40:22 -0400 Subject: [PATCH 061/174] CIFS: Fix BUG() in calc_seckey() Andy Lutromirski's new virtually mapped kernel stack allocations moves kernel stacks the vmalloc area. This triggers the bug kernel BUG at ./include/linux/scatterlist.h:140! at calc_seckey()->sg_init() Signed-off-by: Sachin Prabhu Signed-off-by: Steve French Reviewed-by: Jeff Layton --- fs/cifs/cifsencrypt.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 8347c90cf483..5eb04129f938 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -808,7 +808,11 @@ calc_seckey(struct cifs_ses *ses) struct crypto_skcipher *tfm_arc4; struct scatterlist sgin, sgout; struct skcipher_request *req; - unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */ + unsigned char *sec_key; + + sec_key = kmalloc(CIFS_SESS_KEY_SIZE, GFP_KERNEL); + if (sec_key == NULL) + return -ENOMEM; get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE); @@ -816,7 +820,7 @@ calc_seckey(struct cifs_ses *ses) if (IS_ERR(tfm_arc4)) { rc = PTR_ERR(tfm_arc4); cifs_dbg(VFS, "could not allocate crypto API arc4\n"); - return rc; + goto out; } rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response, @@ -854,7 +858,8 @@ calc_seckey(struct cifs_ses *ses) out_free_cipher: crypto_free_skcipher(tfm_arc4); - +out: + kfree(sec_key); return rc; } From b8c600120fc87d53642476f48c8055b38d6e14c7 Mon Sep 17 00:00:00 2001 From: Sachin Prabhu Date: Thu, 20 Oct 2016 19:52:24 -0400 Subject: [PATCH 062/174] Call echo service immediately after socket reconnect Commit 4fcd1813e640 ("Fix reconnect to not defer smb3 session reconnect long after socket reconnect") changes the behaviour of the SMB2 echo service and causes it to renegotiate after a socket reconnect. However under default settings, the echo service could take up to 120 seconds to be scheduled. The patch forces the echo service to be called immediately resulting a negotiate call being made immediately on reconnect. Signed-off-by: Sachin Prabhu Reviewed-by: Pavel Shilovsky Signed-off-by: Steve French --- fs/cifs/connect.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index aab5227979e2..4547aeddd12b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -412,6 +412,9 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); + if (server->tcpStatus == CifsNeedNegotiate) + mod_delayed_work(cifsiod_wq, &server->echo, 0); + return rc; } @@ -421,17 +424,25 @@ cifs_echo_request(struct work_struct *work) int rc; struct TCP_Server_Info *server = container_of(work, struct TCP_Server_Info, echo.work); - unsigned long echo_interval = server->echo_interval; + unsigned long echo_interval; /* - * We cannot send an echo if it is disabled or until the - * NEGOTIATE_PROTOCOL request is done, which is indicated by - * server->ops->need_neg() == true. Also, no need to ping if - * we got a response recently. + * If we need to renegotiate, set echo interval to zero to + * immediately call echo service where we can renegotiate. + */ + if (server->tcpStatus == CifsNeedNegotiate) + echo_interval = 0; + else + echo_interval = server->echo_interval; + + /* + * We cannot send an echo if it is disabled. + * Also, no need to ping if we got a response recently. */ if (server->tcpStatus == CifsNeedReconnect || - server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew || + server->tcpStatus == CifsExiting || + server->tcpStatus == CifsNew || (server->ops->can_echo && !server->ops->can_echo(server)) || time_before(jiffies, server->lstrp + echo_interval - HZ)) goto requeue_echo; @@ -442,7 +453,7 @@ cifs_echo_request(struct work_struct *work) server->hostname); requeue_echo: - queue_delayed_work(cifsiod_wq, &server->echo, echo_interval); + queue_delayed_work(cifsiod_wq, &server->echo, server->echo_interval); } static bool From ae9ebe7c4ee0c16c3d55d1ae3096c82e0a7c136f Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Mon, 24 Oct 2016 20:46:40 +0800 Subject: [PATCH 063/174] CIFS: iterate over posix acl xattr entry correctly in ACL_to_cifs_posix() Commit 2211d5ba5c6c ("posix_acl: xattr representation cleanups") removes the typedefs and the zero-length a_entries array in struct posix_acl_xattr_header, and uses bare struct posix_acl_xattr_header and struct posix_acl_xattr_entry directly. But it failed to iterate over posix acl slots when converting posix acls to CIFS format, which results in several test failures in xfstests (generic/053 generic/105) when testing against a samba v1 server, starting from v4.9-rc1 kernel. e.g. [root@localhost xfstests]# diff -u tests/generic/105.out /root/xfstests/results//generic/105.out.bad --- tests/generic/105.out 2016-09-19 16:33:28.577962575 +0800 +++ /root/xfstests/results//generic/105.out.bad 2016-10-22 15:41:15.201931110 +0800 @@ -1,3 +1,4 @@ QA output created by 105 -rw-r--r-- root +setfacl: subdir: Invalid argument -rw-r--r-- root Fix it by introducing a new "ace" var, like what cifs_copy_posix_acl() does, and iterating posix acl xattr entries over it in the for loop. Signed-off-by: Eryu Guan Signed-off-by: Steve French --- fs/cifs/cifssmb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 3f3185febc58..e3fed9249a04 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -3427,6 +3427,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL, __u16 rc = 0; struct cifs_posix_acl *cifs_acl = (struct cifs_posix_acl *)parm_data; struct posix_acl_xattr_header *local_acl = (void *)pACL; + struct posix_acl_xattr_entry *ace = (void *)(local_acl + 1); int count; int i; @@ -3453,8 +3454,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL, return 0; } for (i = 0; i < count; i++) { - rc = convert_ace_to_cifs_ace(&cifs_acl->ace_array[i], - (struct posix_acl_xattr_entry *)(local_acl + 1)); + rc = convert_ace_to_cifs_ace(&cifs_acl->ace_array[i], &ace[i]); if (rc != 0) { /* ACE not converted */ break; From c4fcfc1619ea43a8a89ad2f83ff23905eee088bd Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 29 Nov 2016 10:20:24 +0100 Subject: [PATCH 064/174] ovl: fix d_real() for stacked fs Handling of recursion in d_real() is completely broken. Recursion is only done in the 'inode != NULL' case. But when opening the file we have 'inode == NULL' hence d_real() will return an overlay dentry. This won't work since overlayfs doesn't define its own file operations, so all file ops will fail. Fix by doing the recursion first and the check against the inode second. Bash script to reproduce the issue written by Quentin: - 8< - - - - - 8< - - - - - 8< - - - - - 8< - - - - tmpdir=$(mktemp -d) pushd ${tmpdir} mkdir -p {upper,lower,work} echo -n 'rocks' > lower/ksplice mount -t overlay level_zero upper -o lowerdir=lower,upperdir=upper,workdir=work cat upper/ksplice tmpdir2=$(mktemp -d) pushd ${tmpdir2} mkdir -p {upper,work} mount -t overlay level_one upper -o lowerdir=${tmpdir}/upper,upperdir=upper,workdir=work ls -l upper/ksplice cat upper/ksplice - 8< - - - - - 8< - - - - - 8< - - - - - 8< - - - - Reported-by: Quentin Casasnovas Signed-off-by: Miklos Szeredi Fixes: 2d902671ce1c ("vfs: merge .d_select_inode() into .d_real()") Cc: # v4.8+ --- fs/overlayfs/super.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index edd46a0e951d..0e100856c7b8 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -328,11 +328,11 @@ static struct dentry *ovl_d_real(struct dentry *dentry, if (!real) goto bug; + /* Handle recursion */ + real = d_real(real, inode, open_flags); + if (!inode || inode == d_inode(real)) return real; - - /* Handle recursion */ - return d_real(real, inode, open_flags); bug: WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry, inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0); From 7ac33e47d5769632010e537964c7e45498f8dc26 Mon Sep 17 00:00:00 2001 From: Peter Wu Date: Sat, 26 Nov 2016 15:05:01 +0100 Subject: [PATCH 065/174] drm/amdgpu: fix check for port PM availability The ATPX method does not always exist on the dGPU, it may be located at the iGPU. The parent device of the iGPU is the root port for which bridge_d3 is false. This accidentally enables the legacy PM method which conflicts with port PM and prevented the dGPU from powering on. Fixes: 1db4496f167b ("drm/amdgpu: fix power state when port pm is unavailable") Reported-and-tested-by: Mike Lothian Signed-off-by: Peter Wu Signed-off-by: Alex Deucher Cc: # 4.8+ --- drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 02ca5dd978f6..6c343a933182 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -485,7 +485,6 @@ static int amdgpu_atpx_power_state(enum vga_switcheroo_client_id id, */ static bool amdgpu_atpx_pci_probe_handle(struct pci_dev *pdev) { - struct pci_dev *parent_pdev = pci_upstream_bridge(pdev); acpi_handle dhandle, atpx_handle; acpi_status status; @@ -500,7 +499,6 @@ static bool amdgpu_atpx_pci_probe_handle(struct pci_dev *pdev) } amdgpu_atpx_priv.dhandle = dhandle; amdgpu_atpx_priv.atpx.handle = atpx_handle; - amdgpu_atpx_priv.bridge_pm_usable = parent_pdev && parent_pdev->bridge_d3; return true; } @@ -562,17 +560,25 @@ static bool amdgpu_atpx_detect(void) struct pci_dev *pdev = NULL; bool has_atpx = false; int vga_count = 0; + bool d3_supported = false; + struct pci_dev *parent_pdev; while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { vga_count++; has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } if (has_atpx && vga_count == 2) { @@ -580,6 +586,7 @@ static bool amdgpu_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); amdgpu_atpx_priv.atpx_detected = true; + amdgpu_atpx_priv.bridge_pm_usable = d3_supported; amdgpu_atpx_init(); return true; } From bcfdd5d5105087e6f33dfeb08a1ca6b2c0287b61 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 28 Nov 2016 17:23:40 -0500 Subject: [PATCH 066/174] drm/radeon: fix check for port PM availability The ATPX method does not always exist on the dGPU, it may be located at the iGPU. The parent device of the iGPU is the root port for which bridge_d3 is false. This accidentally enables the legacy PM method which conflicts with port PM and prevented the dGPU from powering on. Ported from amdgpu commit: drm/amdgpu: fix check for port PM availability from Peter Wu. Fixes: d3ac31f3b4bf9fad (drm/radeon: fix power state when port pm is unavailable (v2)) Signed-off-by: Alex Deucher Cc: Peter Wu Cc: # 4.8+ --- drivers/gpu/drm/radeon/radeon_atpx_handler.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 4129b12521a6..0ae13cd2adda 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -479,7 +479,6 @@ static int radeon_atpx_power_state(enum vga_switcheroo_client_id id, */ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev) { - struct pci_dev *parent_pdev = pci_upstream_bridge(pdev); acpi_handle dhandle, atpx_handle; acpi_status status; @@ -493,7 +492,6 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev) radeon_atpx_priv.dhandle = dhandle; radeon_atpx_priv.atpx.handle = atpx_handle; - radeon_atpx_priv.bridge_pm_usable = parent_pdev && parent_pdev->bridge_d3; return true; } @@ -555,11 +553,16 @@ static bool radeon_atpx_detect(void) struct pci_dev *pdev = NULL; bool has_atpx = false; int vga_count = 0; + bool d3_supported = false; + struct pci_dev *parent_pdev; while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { vga_count++; has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } /* some newer PX laptops mark the dGPU as a non-VGA display device */ @@ -567,6 +570,9 @@ static bool radeon_atpx_detect(void) vga_count++; has_atpx |= (radeon_atpx_pci_probe_handle(pdev) == true); + + parent_pdev = pci_upstream_bridge(pdev); + d3_supported |= parent_pdev && parent_pdev->bridge_d3; } if (has_atpx && vga_count == 2) { @@ -574,6 +580,7 @@ static bool radeon_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); radeon_atpx_priv.atpx_detected = true; + radeon_atpx_priv.bridge_pm_usable = d3_supported; radeon_atpx_init(); return true; } From 0e1614ac84f1719d87bed577963bb8140d0c9ce8 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 1 Nov 2016 11:46:39 +0100 Subject: [PATCH 067/174] pwm: Fix device reference leak Make sure to drop the reference to the parent device taken by class_find_device() after "unexporting" any children when deregistering a PWM chip. Fixes: 0733424c9ba9 ("pwm: Unexport children before chip removal") Signed-off-by: Johan Hovold Signed-off-by: Thierry Reding --- drivers/pwm/sysfs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index 0296d8178ae2..a813239300c3 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -425,6 +425,8 @@ void pwmchip_sysfs_unexport_children(struct pwm_chip *chip) if (test_bit(PWMF_EXPORTED, &pwm->flags)) pwm_unexport_child(parent, pwm); } + + put_device(parent); } static int __init pwm_sysfs_init(void) From a2ce2666aa3509ac31fac0f540a3502372b7b630 Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Tue, 29 Nov 2016 13:27:31 +0800 Subject: [PATCH 068/174] mremap: move_ptes: check pte dirty after its removal Linus found there still is a race in mremap after commit 5d1904204c99 ("mremap: fix race between mremap() and page cleanning"). As described by Linus: "the issue is that another thread might make the pte be dirty (in the hardware walker, so no locking of ours will make any difference) *after* we checked whether it was dirty, but *before* we removed it from the page tables" Fix it by moving the check after we removed it from the page table. Suggested-by: Linus Torvalds Signed-off-by: Aaron Lu Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 4 ++-- mm/mremap.c | 18 +++++++++++------- 2 files changed, 13 insertions(+), 9 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index eff3de359d50..d4a6e4001512 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1456,9 +1456,9 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); - if (pmd_present(*old_pmd) && pmd_dirty(*old_pmd)) - force_flush = true; pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); + if (pmd_present(pmd) && pmd_dirty(pmd)) + force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); if (pmd_move_must_withdraw(new_ptl, old_ptl) && diff --git a/mm/mremap.c b/mm/mremap.c index 6ccecc03f56a..30d7d2482eea 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -149,14 +149,18 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, if (pte_none(*old_pte)) continue; - /* - * We are remapping a dirty PTE, make sure to - * flush TLB before we drop the PTL for the - * old PTE or we may race with page_mkclean(). - */ - if (pte_present(*old_pte) && pte_dirty(*old_pte)) - force_flush = true; pte = ptep_get_and_clear(mm, old_addr, old_pte); + /* + * If we are remapping a dirty PTE, make sure + * to flush TLB before we drop the PTL for the + * old PTE or we may race with page_mkclean(). + * + * This check has to be done after we removed the + * old PTE from page tables or another thread may + * dirty it after the check and before the removal. + */ + if (pte_present(pte) && pte_dirty(pte)) + force_flush = true; pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); pte = move_soft_dirty_pte(pte); set_pte_at(mm, new_addr, new_pte, pte); From 6a8b2ca702b279bea0e8f0363056439352e2081c Mon Sep 17 00:00:00 2001 From: Yuriy Kolerov Date: Mon, 28 Nov 2016 07:07:17 +0300 Subject: [PATCH 069/174] ARC: mm: PAE40: Fix crash at munmap commit 1c3c90930392 broke PAE40. Macro pfn_pte(pfn, prot) creates paddr from pfn, but the page shift was getting truncated to 32 bits since we lost the proper cast to 64 bits (for PAE400 Instead of reverting that commit, use a better helper which is 32/64 bits safe just like ARM implementation. Fixes: 1c3c90930392 ("ARC: mm: fix build breakage with STRICT_MM_TYPECHECKS") Cc: #4.4+ Signed-off-by: Yuriy Kolerov [vgupta: massaged changelog] Signed-off-by: Vineet Gupta --- arch/arc/include/asm/pgtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 89eeb3720051..e94ca72b974e 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) +#define pfn_pte(pfn, prot) __pte(__pfn_to_phys(pfn) | pgprot_val(prot)) /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) From dfa2ccc30e6556bd526f54f0e16fc9e5af4293cb Mon Sep 17 00:00:00 2001 From: Jan Glauber Date: Mon, 14 Nov 2016 19:50:43 +0100 Subject: [PATCH 070/174] Revert "i2c: octeon: thunderx: Limit register access retries" This reverts commit 70121f7f3725 ("i2c: octeon: thunderx: Limit register access retries"). Using readq_poll_timeout instead of __raw_readq triggers the following debug warning: [ 78.871568] ipmi_ssif: Trying hotmod-specified SSIF interface at i2c address 0x12, adapter Cavium ThunderX i2c adapter at 0000:01:09.4, slave address 0x0 [ 78.886107] do not call blocking ops when !TASK_RUNNING; state=2 set at [] prepare_to_wait_event+0x58/0x10c [ 78.897436] ------------[ cut here ]------------ [ 78.902050] WARNING: CPU: 6 PID: 2235 at kernel/sched/core.c:7718 __might_sleep+0x80/0x88 [...] [ 79.133553] [] __might_sleep+0x80/0x88 [ 79.138862] [] octeon_i2c_test_iflg+0x4c/0xbc [i2c_thunderx] [ 79.146077] [] octeon_i2c_test_ready+0x18/0x70 [i2c_thunderx] [ 79.153379] [] octeon_i2c_wait+0x154/0x1a4 [i2c_thunderx] [ 79.160334] [] octeon_i2c_xfer+0xf4/0xf60 [i2c_thunderx] Signed-off-by: Jan Glauber Acked-by: Steven J. Hill Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-octeon-core.c | 4 +--- drivers/i2c/busses/i2c-octeon-core.h | 27 +++++++++++---------------- 2 files changed, 12 insertions(+), 19 deletions(-) diff --git a/drivers/i2c/busses/i2c-octeon-core.c b/drivers/i2c/busses/i2c-octeon-core.c index 419b54bfc7c7..5e63b17f935d 100644 --- a/drivers/i2c/busses/i2c-octeon-core.c +++ b/drivers/i2c/busses/i2c-octeon-core.c @@ -381,9 +381,7 @@ static int octeon_i2c_read(struct octeon_i2c *i2c, int target, if (result) return result; - data[i] = octeon_i2c_data_read(i2c, &result); - if (result) - return result; + data[i] = octeon_i2c_data_read(i2c); if (recv_len && i == 0) { if (data[i] > I2C_SMBUS_BLOCK_MAX + 1) return -EPROTO; diff --git a/drivers/i2c/busses/i2c-octeon-core.h b/drivers/i2c/busses/i2c-octeon-core.h index 1db7c835a454..87151ea74acd 100644 --- a/drivers/i2c/busses/i2c-octeon-core.h +++ b/drivers/i2c/busses/i2c-octeon-core.h @@ -5,7 +5,6 @@ #include #include #include -#include #include #include @@ -145,9 +144,9 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 u64 tmp; __raw_writeq(SW_TWSI_V | eop_reg | data, i2c->twsi_base + SW_TWSI(i2c)); - - readq_poll_timeout(i2c->twsi_base + SW_TWSI(i2c), tmp, tmp & SW_TWSI_V, - I2C_OCTEON_EVENT_WAIT, i2c->adap.timeout); + do { + tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c)); + } while ((tmp & SW_TWSI_V) != 0); } #define octeon_i2c_ctl_write(i2c, val) \ @@ -164,28 +163,24 @@ static inline void octeon_i2c_reg_write(struct octeon_i2c *i2c, u64 eop_reg, u8 * * The I2C core registers are accessed indirectly via the SW_TWSI CSR. */ -static inline int octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg, - int *error) +static inline u8 octeon_i2c_reg_read(struct octeon_i2c *i2c, u64 eop_reg) { u64 tmp; - int ret; __raw_writeq(SW_TWSI_V | eop_reg | SW_TWSI_R, i2c->twsi_base + SW_TWSI(i2c)); + do { + tmp = __raw_readq(i2c->twsi_base + SW_TWSI(i2c)); + } while ((tmp & SW_TWSI_V) != 0); - ret = readq_poll_timeout(i2c->twsi_base + SW_TWSI(i2c), tmp, - tmp & SW_TWSI_V, I2C_OCTEON_EVENT_WAIT, - i2c->adap.timeout); - if (error) - *error = ret; return tmp & 0xFF; } #define octeon_i2c_ctl_read(i2c) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL, NULL) -#define octeon_i2c_data_read(i2c, error) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA, error) + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_CTL) +#define octeon_i2c_data_read(i2c) \ + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_DATA) #define octeon_i2c_stat_read(i2c) \ - octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT, NULL) + octeon_i2c_reg_read(i2c, SW_TWSI_EOP_TWSI_STAT) /** * octeon_i2c_read_int - read the TWSI_INT register From 9b57da0630c9fd36ed7a20fc0f98dc82cc0777fa Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 29 Nov 2016 02:17:34 +0100 Subject: [PATCH 071/174] netfilter: ipv6: nf_defrag: drop mangled skb on ream error Dmitry Vyukov reported GPF in network stack that Andrey traced down to negative nh offset in nf_ct_frag6_queue(). Problem is that all network headers before fragment header are pulled. Normal ipv6 reassembly will drop the skb when errors occur further down the line. netfilter doesn't do this, and instead passed the original fragment along. That was also fine back when netfilter ipv6 defrag worked with cloned fragments, as the original, pristine fragment was passed on. So we either have to undo the pull op, or discard such fragments. Since they're malformed after all (e.g. overlapping fragment) it seems preferrable to just drop them. Same for temporary errors -- it doesn't make sense to accept (and perhaps forward!) only some fragments of same datagram. Fixes: 029f7f3b8701cc7ac ("netfilter: ipv6: nf_defrag: avoid/free clone operations") Reported-by: Dmitry Vyukov Debugged-by: Andrey Konovalov Diagnosed-by: Eric Dumazet Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++-- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index e4347aeb2e65..9948b5ce52da 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -576,11 +576,11 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); - return -EINVAL; + return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) - return -EINVAL; + return 0; if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index f7aab5ab93a5..f06b0471f39f 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -69,7 +69,7 @@ static unsigned int ipv6_defrag(void *priv, if (err == -EINPROGRESS) return NF_STOLEN; - return NF_ACCEPT; + return err == 0 ? NF_ACCEPT : NF_DROP; } static struct nf_hook_ops ipv6_defrag_ops[] = { From faaae2a581435f32781a105dda3501df388fddcb Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 29 Nov 2016 15:20:14 -0800 Subject: [PATCH 072/174] Re-enable CONFIG_MODVERSIONS in a slightly weaker form This enables CONFIG_MODVERSIONS again, but allows for missing symbol CRC information in order to work around the issue that newer binutils versions seem to occasionally drop the CRC on the floor. binutils 2.26 seems to work fine, while binutils 2.27 seems to break MODVERSIONS of symbols that have been defined in assembler files. [ We've had random missing CRC's before - it may be an old problem that just is now reliably triggered with the weak asm symbols and a new version of binutils ] Some day I really do want to remove MODVERSIONS entirely. Sadly, today does not appear to be that day: Debian people apparently do want the option to enable MODVERSIONS to make it easier to have external modules across kernel versions, and this seems to be a fairly minimal fix for the annoying problem. Cc: Ben Hutchings Acked-by: Michal Marek Signed-off-by: Linus Torvalds --- init/Kconfig | 1 - kernel/module.c | 5 +++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/init/Kconfig b/init/Kconfig index c4fbc1e55c25..34407f15e6d3 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1945,7 +1945,6 @@ config MODULE_FORCE_UNLOAD config MODVERSIONS bool "Module versioning support" - depends on BROKEN help Usually, you have to use modules compiled with your kernel. Saying Y here makes it sometimes possible to use modules diff --git a/kernel/module.c b/kernel/module.c index f57dd63186e6..0e54d5bf0097 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1301,8 +1301,9 @@ static int check_version(Elf_Shdr *sechdrs, goto bad_version; } - pr_warn("%s: no symbol version for %s\n", mod->name, symname); - return 0; + /* Broken toolchain. Warn once, then let it go.. */ + pr_warn_once("%s: no symbol version for %s\n", mod->name, symname); + return 1; bad_version: pr_warn("%s: disagrees about version of symbol %s\n", From 95c2027bfeda21a28eb245121e6a249f38d0788e Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Mon, 28 Nov 2016 12:56:40 +0200 Subject: [PATCH 073/174] net/sched: pedit: make sure that offset is valid Add a validation function to make sure offset is valid: 1. Not below skb head (could happen when offset is negative). 2. Validate both 'offset' and 'at'. Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- net/sched/act_pedit.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b54d56d4959b..cf9b2fe8eac6 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -108,6 +108,17 @@ static void tcf_pedit_cleanup(struct tc_action *a, int bind) kfree(keys); } +static bool offset_valid(struct sk_buff *skb, int offset) +{ + if (offset > 0 && offset > skb->len) + return false; + + if (offset < 0 && -offset > skb_headroom(skb)) + return false; + + return true; +} + static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -134,6 +145,11 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, if (tkey->offmask) { char *d, _d; + if (!offset_valid(skb, off + tkey->at)) { + pr_info("tc filter pedit 'at' offset %d out of bounds\n", + off + tkey->at); + goto bad; + } d = skb_header_pointer(skb, off + tkey->at, 1, &_d); if (!d) @@ -146,10 +162,10 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, " offset must be on 32 bit boundaries\n"); goto bad; } - if (offset > 0 && offset > skb->len) { - pr_info("tc filter pedit" - " offset %d can't exceed pkt length %d\n", - offset, skb->len); + + if (!offset_valid(skb, off + offset)) { + pr_info("tc filter pedit offset %d out of bounds\n", + offset); goto bad; } From 707693c8a498697aa8db240b93eb76ec62e30892 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 28 Nov 2016 19:22:12 +0800 Subject: [PATCH 074/174] netlink: Call cb->done from a worker thread The cb->done interface expects to be called in process context. This was broken by the netlink RCU conversion. This patch fixes it by adding a worker struct to make the cb->done call where necessary. Fixes: 21e4902aea80 ("netlink: Lockless lookup with RCU grace...") Reported-by: Subash Abhinov Kasiviswanathan Signed-off-by: Herbert Xu Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/netlink/af_netlink.c | 27 +++++++++++++++++++++++---- net/netlink/af_netlink.h | 2 ++ 2 files changed, 25 insertions(+), 4 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 62bea4591054..602e5ebe9db3 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -322,14 +322,11 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) sk_mem_charge(sk, skb->truesize); } -static void netlink_sock_destruct(struct sock *sk) +static void __netlink_sock_destruct(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); if (nlk->cb_running) { - if (nlk->cb.done) - nlk->cb.done(&nlk->cb); - module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); } @@ -346,6 +343,28 @@ static void netlink_sock_destruct(struct sock *sk) WARN_ON(nlk_sk(sk)->groups); } +static void netlink_sock_destruct_work(struct work_struct *work) +{ + struct netlink_sock *nlk = container_of(work, struct netlink_sock, + work); + + nlk->cb.done(&nlk->cb); + __netlink_sock_destruct(&nlk->sk); +} + +static void netlink_sock_destruct(struct sock *sk) +{ + struct netlink_sock *nlk = nlk_sk(sk); + + if (nlk->cb_running && nlk->cb.done) { + INIT_WORK(&nlk->work, netlink_sock_destruct_work); + schedule_work(&nlk->work); + return; + } + + __netlink_sock_destruct(sk); +} + /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on * SMP. Look, when several writers sleep and reader wakes them up, all but one * immediately hit write lock and grab all the cpus. Exclusive sleep solves diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 3cfd6cc60504..4fdb38318977 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -3,6 +3,7 @@ #include #include +#include #include #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) @@ -33,6 +34,7 @@ struct netlink_sock { struct rhash_head node; struct rcu_head rcu; + struct work_struct work; }; static inline struct netlink_sock *nlk_sk(struct sock *sk) From a0b44eea372b449ef9744fb1d90491cc063289b8 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Mon, 28 Nov 2016 14:40:55 +0100 Subject: [PATCH 075/174] net: macb: fix the RX queue reset in macb_rx() On macb only (not gem), when a RX queue corruption was detected from macb_rx(), the RX queue was reset: during this process the RX ring buffer descriptor was initialized by macb_init_rx_ring() but we forgot to also set bp->rx_tail to 0. Indeed, when processing the received frames, bp->rx_tail provides the macb driver with the index in the RX ring buffer of the next buffer to process. So when the whole ring buffer is reset we must also reset bp->rx_tail so the driver is synchronized again with the hardware. Since macb_init_rx_ring() is called from many locations, currently from macb_rx() and macb_init_rings(), we'd rather add the "bp->rx_tail = 0;" line inside macb_init_rx_ring() than add the very same line after each call of this function. Without this fix, the rx queue is not reset properly to recover from queue corruption and connection drop may occur. Signed-off-by: Cyrille Pitchen Fixes: 9ba723b081a2 ("net: macb: remove BUG_ON() and reset the queue to handle RX errors") Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 533653bd7aec..3ede59c9cae0 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -975,6 +975,7 @@ static inline void macb_init_rx_ring(struct macb *bp) addr += bp->rx_buffer_size; } bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP); + bp->rx_tail = 0; } static int macb_rx(struct macb *bp, int budget) @@ -1616,8 +1617,6 @@ static void macb_init_rings(struct macb *bp) bp->queues[0].tx_head = 0; bp->queues[0].tx_tail = 0; bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP); - - bp->rx_tail = 0; } static void macb_reset_hw(struct macb *bp) From ffac0e967f20b7637936dbaa21df08c55f672604 Mon Sep 17 00:00:00 2001 From: Zumeng Chen Date: Mon, 28 Nov 2016 21:55:00 +0800 Subject: [PATCH 076/174] net: macb: ensure ordering write to re-enable RX smoothly When a hardware issue happened as described by inline comments, the register write pattern looks like the following: + wmb(); There might be a memory barrier between these two write operations, so add wmb to ensure an flip from 0 to 1 for NCR. Signed-off-by: Zumeng Chen Acked-by: Nicolas Ferre Signed-off-by: David S. Miller --- drivers/net/ethernet/cadence/macb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 3ede59c9cae0..ec09fcece711 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -1157,6 +1157,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE)); + wmb(); macb_writel(bp, NCR, ctrl | MACB_BIT(RE)); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) @@ -2769,6 +2770,7 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) if (intstatus & MACB_BIT(RXUBR)) { ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl & ~MACB_BIT(RE)); + wmb(); macb_writel(lp, NCR, ctl | MACB_BIT(RE)); } From 648f0c28df282636c0c8a7a19ca3ce5fc80a39c3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 28 Nov 2016 06:26:49 -0800 Subject: [PATCH 077/174] net/dccp: fix use-after-free in dccp_invalid_packet pskb_may_pull() can reallocate skb->head, we need to reload dh pointer in dccp_invalid_packet() or risk use after free. Bug found by Andrey Konovalov using syzkaller. Signed-off-by: Eric Dumazet Reported-by: Andrey Konovalov Signed-off-by: David S. Miller --- net/dccp/ipv4.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b567c8725aea..edbe59d203ef 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -700,6 +700,7 @@ int dccp_invalid_packet(struct sk_buff *skb) { const struct dccp_hdr *dh; unsigned int cscov; + u8 dccph_doff; if (skb->pkt_type != PACKET_HOST) return 1; @@ -721,18 +722,19 @@ int dccp_invalid_packet(struct sk_buff *skb) /* * If P.Data Offset is too small for packet type, drop packet and return */ - if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { - DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff); + dccph_doff = dh->dccph_doff; + if (dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) { + DCCP_WARN("P.Data Offset(%u) too small\n", dccph_doff); return 1; } /* * If P.Data Offset is too too large for packet, drop packet and return */ - if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) { - DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff); + if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) { + DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff); return 1; } - + dh = dccp_hdr(skb); /* * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return From 725cbb62e7ade1bb29aa21a902d74e72b42a0f3d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 28 Nov 2016 15:40:13 +0100 Subject: [PATCH 078/174] sched: cls_flower: remove from hashtable only in case skip sw flag is not set Be symmetric to hashtable insert and remove filter from hashtable only in case skip sw flag is not set. Fixes: e69985c67c33 ("net/sched: cls_flower: Introduce support in SKIP SW flag") Signed-off-by: Jiri Pirko Reviewed-by: Amir Vadai Signed-off-by: David S. Miller --- net/sched/cls_flower.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b296f3991ab2..904442421db3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -732,8 +732,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, goto errout; if (fold) { - rhashtable_remove_fast(&head->ht, &fold->ht_node, - head->ht_params); + if (!tc_skip_sw(fold->flags)) + rhashtable_remove_fast(&head->ht, &fold->ht_node, + head->ht_params); fl_hw_destroy_filter(tp, (unsigned long)fold); } @@ -760,8 +761,9 @@ static int fl_delete(struct tcf_proto *tp, unsigned long arg) struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = (struct cls_fl_filter *) arg; - rhashtable_remove_fast(&head->ht, &f->ht_node, - head->ht_params); + if (!tc_skip_sw(f->flags)) + rhashtable_remove_fast(&head->ht, &f->ht_node, + head->ht_params); list_del_rcu(&f->list); fl_hw_destroy_filter(tp, (unsigned long)f); tcf_unbind_filter(tp, &f->res); From a510887824171ad260cc4a2603396c6247fdd091 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 28 Nov 2016 12:36:58 -0300 Subject: [PATCH 079/174] GSO: Reload iph after pskb_may_pull As it may get stale and lead to use after free. Acked-by: Eric Dumazet Cc: Alexander Duyck Cc: Andrey Konovalov Fixes: cbc53e08a793 ("GSO: Add GSO type for fixed IPv4 ID") Signed-off-by: Arnaldo Carvalho de Melo Acked-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ddf5cda07f4..215143246e4b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1233,7 +1233,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, fixedid = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID); /* fixed ID is invalid if DF bit is not set */ - if (fixedid && !(iph->frag_off & htons(IP_DF))) + if (fixedid && !(ip_hdr(skb)->frag_off & htons(IP_DF))) goto out; } From 0d8f3c67151faaa80e332c254372dca58fb2a9d4 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:24:54 +0100 Subject: [PATCH 080/174] net: dsa: slave: fix of-node leak and phy priority Make sure to drop the reference taken by of_parse_phandle() before returning from dsa_slave_phy_setup(). Note that this also modifies the PHY priority so that any fixed-link node is only parsed when no phy-handle is given, which is in accordance with the common scheme for this. Fixes: 0d8bcdd383b8 ("net: dsa: allow for more complex PHY setups") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- net/dsa/slave.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6b1282c006b1..2a5c20a13fe4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1125,7 +1125,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, p->phy_interface = mode; phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); - if (of_phy_is_fixed_link(port_dn)) { + if (!phy_dn && of_phy_is_fixed_link(port_dn)) { /* In the case of a fixed PHY, the DT node associated * to the fixed PHY is the Port DT node */ @@ -1135,7 +1135,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, return ret; } phy_is_fixed = true; - phy_dn = port_dn; + phy_dn = of_node_get(port_dn); } if (ds->ops->get_phy_flags) @@ -1154,6 +1154,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, ret = dsa_slave_phy_connect(p, slave_dev, phy_id); if (ret) { netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret); + of_node_put(phy_dn); return ret; } } else { @@ -1162,6 +1163,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, phy_flags, p->phy_interface); } + + of_node_put(phy_dn); } if (p->phy && phy_is_fixed) From 3f65047c853a2a5abcd8ac1984af3452b5df4ada Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:24:55 +0100 Subject: [PATCH 081/174] of_mdio: add helper to deregister fixed-link PHYs Add helper to deregister fixed-link PHYs registered using of_phy_register_fixed_link(). Convert the two drivers that care to deregister their fixed-link PHYs to use the new helper, but note that most drivers currently fail to do so. Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpsw.c | 16 ++-------------- drivers/of/of_mdio.c | 15 +++++++++++++++ include/linux/of_mdio.h | 4 ++++ net/dsa/dsa.c | 12 ++---------- 4 files changed, 23 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 58947aae31c7..9f0646512624 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2459,20 +2459,8 @@ static void cpsw_remove_dt(struct platform_device *pdev) if (strcmp(slave_node->name, "slave")) continue; - if (of_phy_is_fixed_link(slave_node)) { - struct phy_device *phydev; - - phydev = of_phy_find_device(slave_node); - if (phydev) { - fixed_phy_unregister(phydev); - /* Put references taken by - * of_phy_find_device() and - * of_phy_register_fixed_link(). - */ - phy_device_free(phydev); - phy_device_free(phydev); - } - } + if (of_phy_is_fixed_link(slave_node)) + of_phy_deregister_fixed_link(slave_node); of_node_put(slave_data->phy_node); diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 5a3145a02547..262281bd68fa 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -490,3 +490,18 @@ int of_phy_register_fixed_link(struct device_node *np) return -ENODEV; } EXPORT_SYMBOL(of_phy_register_fixed_link); + +void of_phy_deregister_fixed_link(struct device_node *np) +{ + struct phy_device *phydev; + + phydev = of_phy_find_device(np); + if (!phydev) + return; + + fixed_phy_unregister(phydev); + + put_device(&phydev->mdio.dev); /* of_phy_find_device() */ + phy_device_free(phydev); /* fixed_phy_register() */ +} +EXPORT_SYMBOL(of_phy_deregister_fixed_link); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2ab233661ae5..a58cca8bcb29 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -29,6 +29,7 @@ struct phy_device *of_phy_attach(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); extern int of_mdio_parse_addr(struct device *dev, const struct device_node *np); extern int of_phy_register_fixed_link(struct device_node *np); +extern void of_phy_deregister_fixed_link(struct device_node *np); extern bool of_phy_is_fixed_link(struct device_node *np); #else /* CONFIG_OF */ @@ -83,6 +84,9 @@ static inline int of_phy_register_fixed_link(struct device_node *np) { return -ENOSYS; } +static inline void of_phy_deregister_fixed_link(struct device_node *np) +{ +} static inline bool of_phy_is_fixed_link(struct device_node *np) { return false; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index cb0091b99592..7899919cd9f0 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -506,16 +506,8 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, void dsa_cpu_dsa_destroy(struct device_node *port_dn) { - struct phy_device *phydev; - - if (of_phy_is_fixed_link(port_dn)) { - phydev = of_phy_find_device(port_dn); - if (phydev) { - fixed_phy_unregister(phydev); - put_device(&phydev->mdio.dev); - phy_device_free(phydev); - } - } + if (of_phy_is_fixed_link(port_dn)) + of_phy_deregister_fixed_link(port_dn); } static void dsa_switch_destroy(struct dsa_switch *ds) From 5a89394ad2a5b94885bdbbb611518b0cc70bf354 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:24:56 +0100 Subject: [PATCH 082/174] net: ethernet: altera: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: 7cdbc6f74f8e ("altera tse: add support for fixed-links.") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/altera/altera_tse_main.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index bda31f308cc2..6532829b70d2 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -819,6 +819,8 @@ static int init_phy(struct net_device *dev) if (!phydev) { netdev_err(dev, "Could not find the PHY\n"); + if (fixed_link) + of_phy_deregister_fixed_link(priv->device->of_node); return -ENODEV; } @@ -1545,10 +1547,15 @@ static int altera_tse_probe(struct platform_device *pdev) static int altera_tse_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); + struct altera_tse_private *priv = netdev_priv(ndev); - if (ndev->phydev) + if (ndev->phydev) { phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(priv->device->of_node)) + of_phy_deregister_fixed_link(priv->device->of_node); + } + platform_set_drvdata(pdev, NULL); altera_tse_mdio_destroy(ndev); unregister_netdev(ndev); From 9e081031303834bf86d8cfeccd44df09b2c21377 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:24:57 +0100 Subject: [PATCH 083/174] net: ethernet: aurora: nb8800: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: c7dfe3abf40e ("net: ethernet: nb8800: support fixed-link DT node") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/aurora/nb8800.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 00c38bf151e6..e078d8da978c 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1466,12 +1466,12 @@ static int nb8800_probe(struct platform_device *pdev) ret = nb8800_hw_init(dev); if (ret) - goto err_free_bus; + goto err_deregister_fixed_link; if (ops && ops->init) { ret = ops->init(dev); if (ret) - goto err_free_bus; + goto err_deregister_fixed_link; } dev->netdev_ops = &nb8800_netdev_ops; @@ -1504,6 +1504,9 @@ static int nb8800_probe(struct platform_device *pdev) err_free_dma: nb8800_dma_free(dev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); err_free_bus: of_node_put(priv->phy_node); mdiobus_unregister(bus); @@ -1521,6 +1524,8 @@ static int nb8800_remove(struct platform_device *pdev) struct nb8800_priv *priv = netdev_priv(ndev); unregister_netdev(ndev); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); of_node_put(priv->phy_node); mdiobus_unregister(priv->mii_bus); From 39f8b0d426e0b3e04ddf4c6ef0ae28873c0f8c0f Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:24:58 +0100 Subject: [PATCH 084/174] net: ethernet: bcmsysport: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: 186534a3f832 ("net: systemport: use the new fixed PHY helpers") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bcmsysport.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c3354b9941d1..25d1eb4933d0 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1755,13 +1755,13 @@ static int bcm_sysport_probe(struct platform_device *pdev) if (priv->irq0 <= 0 || priv->irq1 <= 0) { dev_err(&pdev->dev, "invalid interrupts\n"); ret = -EINVAL; - goto err; + goto err_free_netdev; } priv->base = devm_ioremap_resource(&pdev->dev, r); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); - goto err; + goto err_free_netdev; } priv->netdev = dev; @@ -1779,7 +1779,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) ret = of_phy_register_fixed_link(dn); if (ret) { dev_err(&pdev->dev, "failed to register fixed PHY\n"); - goto err; + goto err_free_netdev; } priv->phy_dn = dn; @@ -1821,7 +1821,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) ret = register_netdev(dev); if (ret) { dev_err(&pdev->dev, "failed to register net_device\n"); - goto err; + goto err_deregister_fixed_link; } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; @@ -1832,7 +1832,11 @@ static int bcm_sysport_probe(struct platform_device *pdev) priv->base, priv->irq0, priv->irq1, txq, rxq); return 0; -err: + +err_deregister_fixed_link: + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); +err_free_netdev: free_netdev(dev); return ret; } @@ -1840,11 +1844,14 @@ static int bcm_sysport_probe(struct platform_device *pdev) static int bcm_sysport_remove(struct platform_device *pdev) { struct net_device *dev = dev_get_drvdata(&pdev->dev); + struct device_node *dn = pdev->dev.of_node; /* Not much to do, ndo_close has been called * and we use managed allocations */ unregister_netdev(dev); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); free_netdev(dev); dev_set_drvdata(&pdev->dev, NULL); From 140ca9d3471c424ab4c4036ab8d8d995f24a9c5b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:24:59 +0100 Subject: [PATCH 085/174] net: ethernet: bcmgenet: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Note that we're still leaking any fixed-link PHY registered in the non-OF probe path. Fixes: 9abf0c2b717a ("net: bcmgenet: use the new fixed PHY helpers") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmmii.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 2e745bd51df4..e87607621e62 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -627,6 +627,7 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) int bcmgenet_mii_init(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; int ret; ret = bcmgenet_mii_alloc(priv); @@ -640,6 +641,8 @@ int bcmgenet_mii_init(struct net_device *dev) return 0; out: + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); @@ -649,7 +652,10 @@ int bcmgenet_mii_init(struct net_device *dev) void bcmgenet_mii_exit(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device_node *dn = priv->pdev->dev.of_node; + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); From 82005b1c19b11998ea98532d742c021a19f948d7 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:00 +0100 Subject: [PATCH 086/174] net: ethernet: fec: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: 407066f8f371 ("net: fec: Support phys probed from devicetree and fixed-link") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec_main.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5aa9d4ded214..74dcdf097348 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3475,6 +3475,8 @@ fec_probe(struct platform_device *pdev) failed_clk_ipg: fec_enet_clk_enable(ndev, false); failed_clk: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); failed_phy: of_node_put(phy_node); failed_ioremap: @@ -3488,6 +3490,7 @@ fec_drv_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); + struct device_node *np = pdev->dev.of_node; cancel_work_sync(&fep->tx_timeout_work); fec_ptp_stop(pdev); @@ -3495,6 +3498,8 @@ fec_drv_remove(struct platform_device *pdev) fec_enet_mii_remove(fep); if (fep->reg_phy) regulator_disable(fep->reg_phy); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); of_node_put(fep->phy_node); free_netdev(ndev); From b9755f03728b21c36375a47a6c6366e00b4f2062 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:01 +0100 Subject: [PATCH 087/174] net: ethernet: fs_enet: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: bb74d9a4a87b ("fs_enet: use the new fixed PHY helpers") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index dc120c148d97..4b86260584a0 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -980,7 +980,7 @@ static int fs_enet_probe(struct platform_device *ofdev) err = clk_prepare_enable(clk); if (err) { ret = err; - goto out_free_fpi; + goto out_deregister_fixed_link; } fpi->clk_per = clk; } @@ -1061,6 +1061,9 @@ static int fs_enet_probe(struct platform_device *ofdev) of_node_put(fpi->phy_node); if (fpi->clk_per) clk_disable_unprepare(fpi->clk_per); +out_deregister_fixed_link: + if (of_phy_is_fixed_link(ofdev->dev.of_node)) + of_phy_deregister_fixed_link(ofdev->dev.of_node); out_free_fpi: kfree(fpi); return ret; @@ -1079,6 +1082,8 @@ static int fs_enet_remove(struct platform_device *ofdev) of_node_put(fep->fpi->phy_node); if (fep->fpi->clk_per) clk_disable_unprepare(fep->fpi->clk_per); + if (of_phy_is_fixed_link(ofdev->dev.of_node)) + of_phy_deregister_fixed_link(ofdev->dev.of_node); free_netdev(ndev); return 0; } From 42c70042458d74ce049ce4a2ea7702f344a0dc0b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:02 +0100 Subject: [PATCH 088/174] net: ethernet: gianfar: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: be40364544bd ("gianfar: use the new fixed PHY helpers") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/gianfar.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 4b4f5bc0e279..9061c2f82b9c 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -1312,6 +1312,7 @@ static void gfar_init_addr_hash_table(struct gfar_private *priv) */ static int gfar_probe(struct platform_device *ofdev) { + struct device_node *np = ofdev->dev.of_node; struct net_device *dev = NULL; struct gfar_private *priv = NULL; int err = 0, i; @@ -1462,6 +1463,8 @@ static int gfar_probe(struct platform_device *ofdev) return 0; register_fail: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); unmap_group_regs(priv); gfar_free_rx_queues(priv); gfar_free_tx_queues(priv); @@ -1474,11 +1477,16 @@ static int gfar_probe(struct platform_device *ofdev) static int gfar_remove(struct platform_device *ofdev) { struct gfar_private *priv = platform_get_drvdata(ofdev); + struct device_node *np = ofdev->dev.of_node; of_node_put(priv->phy_node); of_node_put(priv->tbi_node); unregister_netdev(priv->ndev); + + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + unmap_group_regs(priv); gfar_free_rx_queues(priv); gfar_free_tx_queues(priv); From 0807c4ceb8d171a116edc33e34166416876cae5d Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:03 +0100 Subject: [PATCH 089/174] net: ethernet: ucc_geth: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: 87009814cdbb ("ucc_geth: use the new fixed PHY helpers") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/ucc_geth.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 186ef8f16c80..f76d33279454 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3868,9 +3868,8 @@ static int ucc_geth_probe(struct platform_device* ofdev) dev = alloc_etherdev(sizeof(*ugeth)); if (dev == NULL) { - of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); - return -ENOMEM; + err = -ENOMEM; + goto err_deregister_fixed_link; } ugeth = netdev_priv(dev); @@ -3907,10 +3906,7 @@ static int ucc_geth_probe(struct platform_device* ofdev) if (netif_msg_probe(ugeth)) pr_err("%s: Cannot register net device, aborting\n", dev->name); - free_netdev(dev); - of_node_put(ug_info->tbi_node); - of_node_put(ug_info->phy_node); - return err; + goto err_free_netdev; } mac_addr = of_get_mac_address(np); @@ -3923,16 +3919,29 @@ static int ucc_geth_probe(struct platform_device* ofdev) ugeth->node = np; return 0; + +err_free_netdev: + free_netdev(dev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(ug_info->tbi_node); + of_node_put(ug_info->phy_node); + + return err; } static int ucc_geth_remove(struct platform_device* ofdev) { struct net_device *dev = platform_get_drvdata(ofdev); struct ucc_geth_private *ugeth = netdev_priv(dev); + struct device_node *np = ofdev->dev.of_node; unregister_netdev(dev); free_netdev(dev); ucc_geth_memclean(ugeth); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); of_node_put(ugeth->ug_info->tbi_node); of_node_put(ugeth->ug_info->phy_node); From 5a57a304315c09f9f93b7b7230a5038555e7fcf9 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:04 +0100 Subject: [PATCH 090/174] net: ethernet: marvell: mvneta: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: 83895bedeee6 ("net: mvneta: add support for fixed links") Signed-off-by: Johan Hovold Reviewed-by: Thomas Petazzoni Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 0c0a45af950f..707bc4680b9b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4191,6 +4191,8 @@ static int mvneta_probe(struct platform_device *pdev) clk_disable_unprepare(pp->clk); err_put_phy_node: of_node_put(phy_node); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); err_free_irq: irq_dispose_mapping(dev->irq); err_free_netdev: @@ -4202,6 +4204,7 @@ static int mvneta_probe(struct platform_device *pdev) static int mvneta_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct device_node *dn = pdev->dev.of_node; struct mvneta_port *pp = netdev_priv(dev); unregister_netdev(dev); @@ -4209,6 +4212,8 @@ static int mvneta_remove(struct platform_device *pdev) clk_disable_unprepare(pp->clk); free_percpu(pp->ports); free_percpu(pp->stats); + if (of_phy_is_fixed_link(dn)) + of_phy_deregister_fixed_link(dn); irq_dispose_mapping(dev->irq); of_node_put(pp->phy_node); free_netdev(dev); From 16a67eb3ec21ddb557d064a6901ec4629e96b94c Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:05 +0100 Subject: [PATCH 091/174] net: ethernet: mediatek: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on initialisation errors and on uninit. Fixes: 0c72c50f6f93 ("net-next: mediatek: add fixed-phy support") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4a62ffd7729d..86a89cbd3ec9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -318,6 +318,8 @@ static int mtk_phy_connect(struct net_device *dev) return 0; err_phy: + if (of_phy_is_fixed_link(mac->of_node)) + of_phy_deregister_fixed_link(mac->of_node); of_node_put(np); dev_err(eth->dev, "%s: invalid phy\n", __func__); return -EINVAL; @@ -1923,6 +1925,8 @@ static void mtk_uninit(struct net_device *dev) struct mtk_eth *eth = mac->hw; phy_disconnect(dev->phydev); + if (of_phy_is_fixed_link(mac->of_node)) + of_phy_deregister_fixed_link(mac->of_node); mtk_irq_disable(eth, MTK_QDMA_INT_MASK, ~0); mtk_irq_disable(eth, MTK_PDMA_INT_MASK, ~0); } From 9f70eb339f5246ce7be6bb41a4602ce87ebbfc4b Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:06 +0100 Subject: [PATCH 092/174] net: ethernet: renesas: ravb: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on initialisation errors and on device close after having disconnected the PHY. Fixes: b4bc88a868ed ("ravb: Add fixed-link support") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 630536bc72f9..f1f3be2cfe21 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1008,7 +1008,8 @@ static int ravb_phy_init(struct net_device *ndev) of_node_put(pn); if (!phydev) { netdev_err(ndev, "failed to connect PHY\n"); - return -ENOENT; + err = -ENOENT; + goto err_deregister_fixed_link; } /* This driver only support 10/100Mbit speeds on Gen3 @@ -1020,8 +1021,7 @@ static int ravb_phy_init(struct net_device *ndev) err = phy_set_max_speed(phydev, SPEED_100); if (err) { netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n"); - phy_disconnect(phydev); - return err; + goto err_phy_disconnect; } netdev_info(ndev, "limited PHY to 100Mbit/s\n"); @@ -1033,6 +1033,14 @@ static int ravb_phy_init(struct net_device *ndev) phy_attached_info(phydev); return 0; + +err_phy_disconnect: + phy_disconnect(phydev); +err_deregister_fixed_link: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + + return err; } /* PHY control start function */ @@ -1634,6 +1642,7 @@ static void ravb_set_rx_mode(struct net_device *ndev) /* Device close function for Ethernet AVB */ static int ravb_close(struct net_device *ndev) { + struct device_node *np = ndev->dev.parent->of_node; struct ravb_private *priv = netdev_priv(ndev); struct ravb_tstamp_skb *ts_skb, *ts_skb2; @@ -1663,6 +1672,8 @@ static int ravb_close(struct net_device *ndev) if (ndev->phydev) { phy_stop(ndev->phydev); phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); } if (priv->chip_id != RCAR_GEN2) { From c41a47678d067efe8c87e8f1cfdcb0147e58ee62 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:07 +0100 Subject: [PATCH 093/174] net: ethernet: dwc_eth_qos: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Fixes: 077742dac2c7 ("dwc_eth_qos: Add support for Synopsys DWC Ethernet QoS") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/synopsys/dwc_eth_qos.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/synopsys/dwc_eth_qos.c b/drivers/net/ethernet/synopsys/dwc_eth_qos.c index 4ba2421e625d..97d64bfed465 100644 --- a/drivers/net/ethernet/synopsys/dwc_eth_qos.c +++ b/drivers/net/ethernet/synopsys/dwc_eth_qos.c @@ -2881,7 +2881,7 @@ static int dwceqos_probe(struct platform_device *pdev) ret = of_get_phy_mode(lp->pdev->dev.of_node); if (ret < 0) { dev_err(&lp->pdev->dev, "error in getting phy i/f\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } lp->phy_interface = ret; @@ -2889,14 +2889,14 @@ static int dwceqos_probe(struct platform_device *pdev) ret = dwceqos_mii_init(lp); if (ret) { dev_err(&lp->pdev->dev, "error in dwceqos_mii_init\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } ret = dwceqos_mii_probe(ndev); if (ret != 0) { netdev_err(ndev, "mii_probe fail.\n"); ret = -ENXIO; - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } dwceqos_set_umac_addr(lp, lp->ndev->dev_addr, 0); @@ -2914,7 +2914,7 @@ static int dwceqos_probe(struct platform_device *pdev) if (ret) { dev_err(&lp->pdev->dev, "Unable to retrieve DT, error %d\n", ret); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } dev_info(&lp->pdev->dev, "pdev->id %d, baseaddr 0x%08lx, irq %d\n", pdev->id, ndev->base_addr, ndev->irq); @@ -2924,7 +2924,7 @@ static int dwceqos_probe(struct platform_device *pdev) if (ret) { dev_err(&lp->pdev->dev, "Unable to request IRQ %d, error %d\n", ndev->irq, ret); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } if (netif_msg_probe(lp)) @@ -2935,11 +2935,14 @@ static int dwceqos_probe(struct platform_device *pdev) ret = register_netdev(ndev); if (ret) { dev_err(&pdev->dev, "Cannot register net device, aborting.\n"); - goto err_out_clk_dis_phy; + goto err_out_deregister_fixed_link; } return 0; +err_out_deregister_fixed_link: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); err_out_clk_dis_phy: clk_disable_unprepare(lp->phy_ref_clk); err_out_clk_dis_aper: @@ -2959,8 +2962,11 @@ static int dwceqos_remove(struct platform_device *pdev) if (ndev) { lp = netdev_priv(ndev); - if (ndev->phydev) + if (ndev->phydev) { phy_disconnect(ndev->phydev); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); + } mdiobus_unregister(lp->mii_bus); mdiobus_free(lp->mii_bus); From 14cab6f6510c498c2fd55d4fd6063a91b477d2ff Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:08 +0100 Subject: [PATCH 094/174] net: ethernet: ti: davinci_emac: fix fixed-link phydev and of-node leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on probe errors and on driver unbind. Also remember to put the of-node reference on probe errors. Fixes: 1bb6aa56bb38 ("net: davinci_emac: Add support for fixed-link PHY") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/davinci_emac.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 84fbe5714f8b..481c7bf0395b 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1767,6 +1767,7 @@ static int davinci_emac_try_get_mac(struct platform_device *pdev, */ static int davinci_emac_probe(struct platform_device *pdev) { + struct device_node *np = pdev->dev.of_node; int rc = 0; struct resource *res, *res_ctrl; struct net_device *ndev; @@ -1805,7 +1806,7 @@ static int davinci_emac_probe(struct platform_device *pdev) if (!pdata) { dev_err(&pdev->dev, "no platform data\n"); rc = -ENODEV; - goto no_pdata; + goto err_free_netdev; } /* MAC addr and PHY mask , RMII enable info from platform_data */ @@ -1941,6 +1942,10 @@ static int davinci_emac_probe(struct platform_device *pdev) cpdma_chan_destroy(priv->rxchan); cpdma_ctlr_destroy(priv->dma); no_pdata: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(priv->phy_node); +err_free_netdev: free_netdev(ndev); return rc; } @@ -1956,6 +1961,7 @@ static int davinci_emac_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct emac_priv *priv = netdev_priv(ndev); + struct device_node *np = pdev->dev.of_node; dev_notice(&ndev->dev, "DaVinci EMAC: davinci_emac_remove()\n"); @@ -1968,6 +1974,8 @@ static int davinci_emac_remove(struct platform_device *pdev) unregister_netdev(ndev); of_node_put(priv->phy_node); pm_runtime_disable(&pdev->dev); + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); free_netdev(ndev); return 0; From 881eadabe71fa78c081eda3cd5701768f3778a21 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 28 Nov 2016 19:25:09 +0100 Subject: [PATCH 095/174] net: dsa: slave: fix fixed-link phydev leaks Make sure to deregister and free any fixed-link PHY registered using of_phy_register_fixed_link() on slave-setup errors and on slave destroy. Fixes: 0d8bcdd383b8 ("net: dsa: allow for more complex PHY setups") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- net/dsa/slave.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 2a5c20a13fe4..30e2e21d7619 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1177,6 +1177,8 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, ret = dsa_slave_phy_connect(p, slave_dev, p->port); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", p->port, ret); + if (phy_is_fixed) + of_phy_deregister_fixed_link(port_dn); return ret; } } @@ -1292,10 +1294,18 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_switch *ds = p->parent; + struct device_node *port_dn; + + port_dn = ds->ports[p->port].dn; netif_carrier_off(slave_dev); - if (p->phy) + if (p->phy) { phy_disconnect(p->phy); + + if (of_phy_is_fixed_link(port_dn)) + of_phy_deregister_fixed_link(port_dn); + } unregister_netdev(slave_dev); free_netdev(slave_dev); } From e94bd1736f1f60e916a85a80c0b0ebeaae36cce5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michel=20D=C3=A4nzer?= Date: Wed, 30 Nov 2016 17:30:01 +0900 Subject: [PATCH 096/174] drm: Don't call drm_for_each_crtc with a non-KMS driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes oops if userspace calls DRM_IOCTL_GET_CAP for DRM_CAP_PAGE_FLIP_TARGET on a non-KMS device node. (Normal userspace doesn't do that, discovered by syzkaller) Reported-by: Dmitry Vyukov Fixes: f837297ad824 ("drm: Add DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags v2") Cc: stable@vger.kernel.org Signed-off-by: Michel Dänzer Signed-off-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/20161130083002.1520-1-michel@daenzer.net --- drivers/gpu/drm/drm_ioctl.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 0ad2c47f808f..71c3473476c7 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -254,10 +254,12 @@ static int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_ req->value = dev->mode_config.async_page_flip; break; case DRM_CAP_PAGE_FLIP_TARGET: - req->value = 1; - drm_for_each_crtc(crtc, dev) { - if (!crtc->funcs->page_flip_target) - req->value = 0; + if (drm_core_check_feature(dev, DRIVER_MODESET)) { + req->value = 1; + drm_for_each_crtc(crtc, dev) { + if (!crtc->funcs->page_flip_target) + req->value = 0; + } } break; case DRM_CAP_CURSOR_WIDTH: From 83e2d0587ae859aae75fd9d246c409b10a6bd137 Mon Sep 17 00:00:00 2001 From: Yi Zhao Date: Tue, 29 Nov 2016 18:09:01 +0800 Subject: [PATCH 097/174] xfrm_user: fix return value from xfrm_user_rcv_msg It doesn't support to run 32bit 'ip' to set xfrm objdect on 64bit host. But the return value is unknown for user program: ip xfrm policy list RTNETLINK answers: Unknown error 524 Replace ENOTSUPP with EOPNOTSUPP: ip xfrm policy list RTNETLINK answers: Operation not supported Signed-off-by: Yi Zhao Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 08892091cfe3..671a1d0333f0 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2450,7 +2450,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) #ifdef CONFIG_COMPAT if (in_compat_syscall()) - return -ENOTSUPP; + return -EOPNOTSUPP; #endif type = nlh->nlmsg_type; From 2420489bcb8910188578acc0c11c75445c2e4b92 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 14 Nov 2016 11:29:30 +0000 Subject: [PATCH 098/174] drm/i915: Don't touch NULL sg on i915_gem_object_get_pages_gtt() error On the DMA mapping error path, sg may be NULL (it has already been marked as the last scatterlist entry), and we should avoid dereferencing it again. Reported-by: Dan Carpenter Fixes: e227330223a7 ("drm/i915: avoid leaking DMA mappings") Signed-off-by: Chris Wilson Cc: Imre Deak Cc: stable@vger.kernel.org Link: http://patchwork.freedesktop.org/patch/msgid/20161114112930.2033-1-chris@chris-wilson.co.uk Reviewed-by: Matthew Auld (cherry picked from commit b17993b7b29612369270567643bcff814f4b3d7f) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_gem.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 91ab7e9d6d2e..00eb4814b913 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2268,7 +2268,7 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) { ret = PTR_ERR(page); - goto err_pages; + goto err_sg; } } #ifdef CONFIG_SWIOTLB @@ -2311,8 +2311,9 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj) return 0; -err_pages: +err_sg: sg_mark_end(sg); +err_pages: for_each_sgt_page(page, sgt_iter, st) put_page(page); sg_free_table(st); From e411072d5740a49cdc9d0713798c30440757e451 Mon Sep 17 00:00:00 2001 From: Matthew Auld Date: Mon, 28 Nov 2016 10:36:48 +0000 Subject: [PATCH 099/174] drm/i915: drop the struct_mutex when wedged or trying to reset We grab the struct_mutex in intel_crtc_page_flip, but if we are wedged or a reset is in progress we bail early but never seem to actually release the lock. Fixes: 7f1847ebf48b ("drm/i915: Simplify checking of GPU reset_counter in display pageflips") Cc: Chris Wilson Signed-off-by: Matthew Auld Link: http://patchwork.freedesktop.org/patch/msgid/20161128103648.9235-1-matthew.auld@intel.com Reviewed-by: Joonas Lahtinen Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Cc: # v4.7+ (cherry picked from commit ddbb271aea87fc6004d3c8bcdb0710e980c7ec85) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 81c11499bcf0..3cb70d73239b 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12260,7 +12260,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, intel_crtc->reset_count = i915_reset_count(&dev_priv->gpu_error); if (i915_reset_in_progress_or_wedged(&dev_priv->gpu_error)) { ret = -EIO; - goto cleanup; + goto unlock; } atomic_inc(&intel_crtc->unpin_work_count); @@ -12352,6 +12352,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, intel_unpin_fb_obj(fb, crtc->primary->state->rotation); cleanup_pending: atomic_dec(&intel_crtc->unpin_work_count); +unlock: mutex_unlock(&dev->struct_mutex); cleanup: crtc->primary->fb = old_fb; From 7c7fedd51c02f4418e8b2eed64bdab601f882aa4 Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 29 Nov 2016 17:05:20 +0100 Subject: [PATCH 100/174] esp4: Fix integrity verification when ESN are used When handling inbound packets, the two halves of the sequence number stored on the skb are already in network order. Fixes: 7021b2e1cddd ("esp4: Switch to new AEAD interface") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/ipv4/esp4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index d95631d09248..20fb25e3027b 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -476,7 +476,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } From a55e23864d381c5a4ef110df94b00b2fe121a70d Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 29 Nov 2016 17:05:25 +0100 Subject: [PATCH 101/174] esp6: Fix integrity verification when ESN are used When handling inbound packets, the two halves of the sequence number stored on the skb are already in network order. Fixes: 000ae7b2690e ("esp6: Switch to new AEAD interface") Signed-off-by: Tobias Brunner Acked-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/ipv6/esp6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 060a60b2f8a6..111ba55fd512 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -418,7 +418,7 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb) esph = (void *)skb_push(skb, 4); *seqhi = esph->spi; esph->spi = esph->seq_no; - esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.input.hi); + esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi; aead_request_set_callback(req, 0, esp_input_done_esn, skb); } From f92a80a9972175a6a1d36c6c44be47fb0efd020d Mon Sep 17 00:00:00 2001 From: Daniele Di Proietto Date: Mon, 28 Nov 2016 15:43:53 -0800 Subject: [PATCH 102/174] openvswitch: Fix skb leak in IPv6 reassembly. If nf_ct_frag6_gather() returns an error other than -EINPROGRESS, it means that we still have a reference to the skb. We should free it before returning from handle_fragments, as stated in the comment above. Fixes: daaa7d647f81 ("netfilter: ipv6: avoid nf_iterate recursion") CC: Florian Westphal CC: Pravin B Shelar CC: Joe Stringer Signed-off-by: Daniele Di Proietto Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/conntrack.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 31045ef44a82..fecefa2dc94e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -370,8 +370,11 @@ static int handle_fragments(struct net *net, struct sw_flow_key *key, skb_orphan(skb); memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); err = nf_ct_frag6_gather(net, skb, user); - if (err) + if (err) { + if (err != -EINPROGRESS) + kfree_skb(skb); return err; + } key->ip.proto = ipv6_hdr(skb)->nexthdr; ovs_cb.mru = IP6CB(skb)->frag_max_size; From 2425f1808123bf69a8f66d4ec90e0d0e302c2613 Mon Sep 17 00:00:00 2001 From: Ping Cheng Date: Mon, 28 Nov 2016 13:20:51 -0800 Subject: [PATCH 103/174] Input: change KEY_DATA from 0x275 to 0x277 0x275 is used by KEY_FASTREVERSE. Fixes: 488326947cd1 ("Input: add HDMI CEC specific keycodes") Signed-off-by: Ping Cheng Acked-by: Hans Verkuil Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input-event-codes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index d6d071fc3c56..3af60ee69053 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -640,7 +640,7 @@ * Control a data application associated with the currently viewed channel, * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.) */ -#define KEY_DATA 0x275 +#define KEY_DATA 0x277 #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 From 17b463654f41f0aa334efd5a6efeab8a6e9496f7 Mon Sep 17 00:00:00 2001 From: Haishuang Yan Date: Tue, 29 Nov 2016 09:59:36 +0800 Subject: [PATCH 104/174] vxlan: fix a potential issue when create a new vxlan fdb entry. vxlan_fdb_append may return error, so add the proper check, otherwise it will cause memory leak. Signed-off-by: Haishuang Yan Changes in v2: - Unnecessary to initialize rc to zero. Acked-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 24532cdebb00..2ba01ca02c9c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -611,6 +611,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int notify = 0; + int rc; f = __vxlan_find_mac(vxlan, mac); if (f) { @@ -641,8 +642,7 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { - int rc = vxlan_fdb_append(f, ip, port, vni, ifindex, - &rd); + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; @@ -673,7 +673,11 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); - vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) { + kfree(f); + return rc; + } ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, From 80cca775cdc4f8555612d2943a2872076b33e0ff Mon Sep 17 00:00:00 2001 From: Nikita Yushchenko Date: Tue, 29 Nov 2016 09:44:51 +0300 Subject: [PATCH 105/174] net: fec: cache statistics while device is down Execution 'ethtool -S' on fec device that is down causes OOPS on Vybrid board: Unhandled fault: external abort on non-linefetch (0x1008) at 0xe0898200 pgd = ddecc000 [e0898200] *pgd=9e406811, *pte=400d1653, *ppte=400d1453 Internal error: : 1008 [#1] SMP ARM ... Reason of OOPS is that fec_enet_get_ethtool_stats() accesses fec registers while IPG clock is stopped by PM. Fix that by caching statistics in fec_enet_private. Cache is initialized at device probe time, and updated at statistics request time if device is up, and also just before turning device off on down path. Additional locking is not needed, since cached statistics is accessed either before device is registered, or under rtnl_lock(). Signed-off-by: Nikita Yushchenko Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/fec.h | 2 ++ drivers/net/ethernet/freescale/fec_main.c | 23 +++++++++++++++++++---- 2 files changed, 21 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index c865135f3cb9..5ea740b4cf14 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -574,6 +574,8 @@ struct fec_enet_private { unsigned int reload_period; int pps_enable; unsigned int next_counter; + + u64 ethtool_stats[0]; }; void fec_ptp_init(struct platform_device *pdev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 74dcdf097348..5f77caa59534 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2313,14 +2313,24 @@ static const struct fec_stat { { "IEEE_rx_octets_ok", IEEE_R_OCTETS_OK }, }; -static void fec_enet_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) +static void fec_enet_update_ethtool_stats(struct net_device *dev) { struct fec_enet_private *fep = netdev_priv(dev); int i; for (i = 0; i < ARRAY_SIZE(fec_stats); i++) - data[i] = readl(fep->hwp + fec_stats[i].offset); + fep->ethtool_stats[i] = readl(fep->hwp + fec_stats[i].offset); +} + +static void fec_enet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct fec_enet_private *fep = netdev_priv(dev); + + if (netif_running(dev)) + fec_enet_update_ethtool_stats(dev); + + memcpy(data, fep->ethtool_stats, ARRAY_SIZE(fec_stats) * sizeof(u64)); } static void fec_enet_get_strings(struct net_device *netdev, @@ -2874,6 +2884,8 @@ fec_enet_close(struct net_device *ndev) if (fep->quirks & FEC_QUIRK_ERR006687) imx6q_cpuidle_fec_irqs_unused(); + fec_enet_update_ethtool_stats(ndev); + fec_enet_clk_enable(ndev, false); pinctrl_pm_select_sleep_state(&fep->pdev->dev); pm_runtime_mark_last_busy(&fep->pdev->dev); @@ -3180,6 +3192,8 @@ static int fec_enet_init(struct net_device *ndev) fec_restart(ndev); + fec_enet_update_ethtool_stats(ndev); + return 0; } @@ -3278,7 +3292,8 @@ fec_probe(struct platform_device *pdev) fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs); /* Init network device */ - ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private), + ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private) + + ARRAY_SIZE(fec_stats) * sizeof(u64), num_tx_qs, num_rx_qs); if (!ndev) return -ENOMEM; From a107bf8b3905b61bf8b5c181268bca8c05af7f69 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 30 Nov 2016 09:52:01 +0200 Subject: [PATCH 106/174] isofs: add KERN_CONT to printing of ER records The ER records are printed without explicit log level presuming line continuation until "\n". After the commit 4bcc595ccd8 (printk: reinstate KERN_CONT for printing continuation lines), the ER records are printed a character per line. Adding KERN_CONT to appropriate printk statements restores the printout behavior. Signed-off-by: Mike Rapoport Signed-off-by: Linus Torvalds --- fs/isofs/rock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 98b3eb7d8eaf..0ec137310320 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -377,9 +377,9 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de, { int p; for (p = 0; p < rr->u.ER.len_id; p++) - printk("%c", rr->u.ER.data[p]); + printk(KERN_CONT "%c", rr->u.ER.data[p]); } - printk("\n"); + printk(KERN_CONT "\n"); break; case SIG('P', 'X'): inode->i_mode = isonum_733(rr->u.PX.mode); From bb83d62fa83405d7c325873a317c9374f98eedef Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Tue, 29 Nov 2016 17:14:52 +0530 Subject: [PATCH 107/174] cxgb4: Add PCI device ID for new adapter Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index df1573c4a659..ecf3ccc257bc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -168,6 +168,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x509a), /* Custom T520-CR */ CH_PCI_ID_TABLE_FENTRY(0x509b), /* Custom T540-CR LOM */ CH_PCI_ID_TABLE_FENTRY(0x509c), /* Custom T520-CR*/ + CH_PCI_ID_TABLE_FENTRY(0x509d), /* Custom T540-CR*/ /* T6 adapters: */ From 0382a25af3c771a8e4d5e417d1834cbe28c2aaac Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 29 Nov 2016 13:09:44 +0100 Subject: [PATCH 108/174] l2tp: lock socket before checking flags in connect() Socket flags aren't updated atomically, so the socket must be locked while reading the SOCK_ZAPPED flag. This issue exists for both l2tp_ip and l2tp_ip6. For IPv6, this patch also brings error handling for __ip6_datagram_connect() failures. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 ++ net/ipv6/datagram.c | 4 +++- net/l2tp/l2tp_ip.c | 19 ++++++++++++------- net/l2tp/l2tp_ip6.c | 16 +++++++++++----- 4 files changed, 28 insertions(+), 13 deletions(-) diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 8fed1cd78658..f11ca837361b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -970,6 +970,8 @@ int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, + int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 37874e2f30ed..ccf40550c475 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -139,7 +139,8 @@ void ip6_datagram_release_cb(struct sock *sk) } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); -static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); @@ -252,6 +253,7 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a out: return err; } +EXPORT_SYMBOL_GPL(__ip6_datagram_connect); int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 982f6c44ea01..1f57094d3111 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -308,21 +308,24 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr; int rc; - if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ - return -EINVAL; - if (addr_len < sizeof(*lsa)) return -EINVAL; if (ipv4_is_multicast(lsa->l2tp_addr.s_addr)) return -EINVAL; - rc = ip4_datagram_connect(sk, uaddr, addr_len); - if (rc < 0) - return rc; - lock_sock(sk); + /* Must bind first - autobinding does not work */ + if (sock_flag(sk, SOCK_ZAPPED)) { + rc = -EINVAL; + goto out_sk; + } + + rc = __ip4_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + goto out_sk; + l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); @@ -330,7 +333,9 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len sk_add_bind_node(sk, &l2tp_ip_bind_table); write_unlock_bh(&l2tp_ip_lock); +out_sk: release_sock(sk); + return rc; } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9978d01ba0ba..af9abfff637c 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -371,9 +371,6 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_type; int rc; - if (sock_flag(sk, SOCK_ZAPPED)) /* Must bind first - autobinding does not work */ - return -EINVAL; - if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -390,10 +387,18 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - rc = ip6_datagram_connect(sk, uaddr, addr_len); - lock_sock(sk); + /* Must bind first - autobinding does not work */ + if (sock_flag(sk, SOCK_ZAPPED)) { + rc = -EINVAL; + goto out_sk; + } + + rc = __ip6_datagram_connect(sk, uaddr, addr_len); + if (rc < 0) + goto out_sk; + l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; write_lock_bh(&l2tp_ip6_lock); @@ -401,6 +406,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, sk_add_bind_node(sk, &l2tp_ip6_bind_table); write_unlock_bh(&l2tp_ip6_lock); +out_sk: release_sock(sk); return rc; From a3c18422a4b4e108bcf6a2328f48867e1003fd95 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 29 Nov 2016 13:09:45 +0100 Subject: [PATCH 109/174] l2tp: hold socket before dropping lock in l2tp_ip{, 6}_recv() Socket must be held while under the protection of the l2tp lock; there is no guarantee that sk remains valid after the read_unlock_bh() call. Same issue for l2tp_ip and l2tp_ip6. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_ip.c | 11 ++++++----- net/l2tp/l2tp_ip6.c | 11 ++++++----- 2 files changed, 12 insertions(+), 10 deletions(-) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 1f57094d3111..4d1c942cc91b 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -183,14 +183,15 @@ static int l2tp_ip_recv(struct sk_buff *skb) read_lock_bh(&l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id); + if (!sk) { + read_unlock_bh(&l2tp_ip_lock); + goto discard; + } + + sock_hold(sk); read_unlock_bh(&l2tp_ip_lock); } - if (sk == NULL) - goto discard; - - sock_hold(sk); - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index af9abfff637c..e3fc7786f188 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -198,14 +198,15 @@ static int l2tp_ip6_recv(struct sk_buff *skb) read_lock_bh(&l2tp_ip6_lock); sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, 0, tunnel_id); + if (!sk) { + read_unlock_bh(&l2tp_ip6_lock); + goto discard; + } + + sock_hold(sk); read_unlock_bh(&l2tp_ip6_lock); } - if (sk == NULL) - goto discard; - - sock_hold(sk); - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; From d5e3a190937a1e386671266202c62565741f0f1a Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 29 Nov 2016 13:09:46 +0100 Subject: [PATCH 110/174] l2tp: fix racy socket lookup in l2tp_ip and l2tp_ip6 bind() It's not enough to check for sockets bound to same address at the beginning of l2tp_ip{,6}_bind(): even if no socket is found at that time, a socket with the same address could be bound before we take the l2tp lock again. This patch moves the lookup right before inserting the new socket, so that no change can ever happen to the list between address lookup and socket insertion. Care is taken to avoid side effects on the socket in case of failure. That is, modifications of the socket are done after the lookup, when binding is guaranteed to succeed, and before releasing the l2tp lock, so that concurrent lookups will always see fully initialised sockets. For l2tp_ip, 'ret' is set to -EINVAL before checking the SOCK_ZAPPED bit. Error code was mistakenly set to -EADDRINUSE on error by commit 32c231164b76 ("l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()"). Using -EINVAL restores original behaviour. For l2tp_ip6, the lookup is now always done with the correct bound device. Before this patch, when binding to a link-local address, the lookup was done with the original sk->sk_bound_dev_if, which was later overwritten with addr->l2tp_scope_id. Lookup is now performed with the final sk->sk_bound_dev_if value. Finally, the (addr_len >= sizeof(struct sockaddr_in6)) check has been dropped: addr is a sockaddr_l2tpip6 not sockaddr_in6 and addr_len has already been checked at this point (this part of the code seems to have been copy-pasted from net/ipv6/raw.c). Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_ip.c | 29 +++++++++++++---------------- net/l2tp/l2tp_ip6.c | 43 ++++++++++++++++++++----------------------- 2 files changed, 33 insertions(+), 39 deletions(-) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 4d1c942cc91b..b517c3366922 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -257,15 +257,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr->l2tp_family != AF_INET) return -EINVAL; - ret = -EADDRINUSE; - read_lock_bh(&l2tp_ip_lock); - if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, - sk->sk_bound_dev_if, addr->l2tp_conn_id)) - goto out_in_use; - - read_unlock_bh(&l2tp_ip_lock); - lock_sock(sk); + + ret = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out; @@ -282,25 +276,28 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ - sk_dst_reset(sk); - - l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; write_lock_bh(&l2tp_ip_lock); + if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, + sk->sk_bound_dev_if, addr->l2tp_conn_id)) { + write_unlock_bh(&l2tp_ip_lock); + ret = -EADDRINUSE; + goto out; + } + + sk_dst_reset(sk); + l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; + sk_add_bind_node(sk, &l2tp_ip_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); + ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); out: release_sock(sk); - return ret; - -out_in_use: - read_unlock_bh(&l2tp_ip_lock); - return ret; } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index e3fc7786f188..5f2ae615c5f9 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -267,6 +267,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr; struct net *net = sock_net(sk); __be32 v4addr = 0; + int bound_dev_if; int addr_type; int err; @@ -285,13 +286,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_type & IPV6_ADDR_MULTICAST) return -EADDRNOTAVAIL; - err = -EADDRINUSE; - read_lock_bh(&l2tp_ip6_lock); - if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, - sk->sk_bound_dev_if, addr->l2tp_conn_id)) - goto out_in_use; - read_unlock_bh(&l2tp_ip6_lock); - lock_sock(sk); err = -EINVAL; @@ -301,28 +295,25 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE) goto out_unlock; + bound_dev_if = sk->sk_bound_dev_if; + /* Check if the address belongs to the host. */ rcu_read_lock(); if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (addr_type & IPV6_ADDR_LINKLOCAL) { - if (addr_len >= sizeof(struct sockaddr_in6) && - addr->l2tp_scope_id) { - /* Override any existing binding, if another - * one is supplied by user. - */ - sk->sk_bound_dev_if = addr->l2tp_scope_id; - } + if (addr->l2tp_scope_id) + bound_dev_if = addr->l2tp_scope_id; /* Binding to link-local address requires an - interface */ - if (!sk->sk_bound_dev_if) + * interface. + */ + if (!bound_dev_if) goto out_unlock_rcu; err = -ENODEV; - dev = dev_get_by_index_rcu(sock_net(sk), - sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if); if (!dev) goto out_unlock_rcu; } @@ -337,13 +328,22 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } rcu_read_unlock(); - inet->inet_rcv_saddr = inet->inet_saddr = v4addr; + write_lock_bh(&l2tp_ip6_lock); + if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, bound_dev_if, + addr->l2tp_conn_id)) { + write_unlock_bh(&l2tp_ip6_lock); + err = -EADDRINUSE; + goto out_unlock; + } + + inet->inet_saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + sk->sk_bound_dev_if = bound_dev_if; sk->sk_v6_rcv_saddr = addr->l2tp_addr; np->saddr = addr->l2tp_addr; l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; - write_lock_bh(&l2tp_ip6_lock); sk_add_bind_node(sk, &l2tp_ip6_bind_table); sk_del_node_init(sk); write_unlock_bh(&l2tp_ip6_lock); @@ -356,10 +356,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) rcu_read_unlock(); out_unlock: release_sock(sk); - return err; -out_in_use: - read_unlock_bh(&l2tp_ip6_lock); return err; } From df90e6886146dd744eb3929782e6df9749cd4a69 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 29 Nov 2016 13:09:47 +0100 Subject: [PATCH 111/174] l2tp: fix lookup for sockets not bound to a device in l2tp_ip When looking up an l2tp socket, we must consider a null netdevice id as wild card. There are currently two problems caused by __l2tp_ip_bind_lookup() not considering 'dif' as wild card when set to 0: * A socket bound to a device (i.e. with sk->sk_bound_dev_if != 0) never receives any packet. Since __l2tp_ip_bind_lookup() is called with dif == 0 in l2tp_ip_recv(), sk->sk_bound_dev_if is always different from 'dif' so the socket doesn't match. * Two sockets, one bound to a device but not the other, can be bound to the same address. If the first socket binding to the address is the one that is also bound to a device, the second socket can bind to the same address without __l2tp_ip_bind_lookup() noticing the overlap. To fix this issue, we need to consider that any null device index, be it 'sk->sk_bound_dev_if' or 'dif', matches with any other value. We also need to pass the input device index to __l2tp_ip_bind_lookup() on reception so that sockets bound to a device never receive packets from other devices. This patch fixes l2tp_ip6 in the same way. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_ip.c | 6 ++++-- net/l2tp/l2tp_ip6.c | 7 ++++--- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index b517c3366922..8938b6ba57a0 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -61,7 +61,8 @@ static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (!sk->sk_bound_dev_if || !dif || + sk->sk_bound_dev_if == dif)) goto found; } @@ -182,7 +183,8 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct iphdr *iph = (struct iphdr *) skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); - sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id); + sk = __l2tp_ip_bind_lookup(net, iph->daddr, inet_iif(skb), + tunnel_id); if (!sk) { read_unlock_bh(&l2tp_ip_lock); goto discard; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 5f2ae615c5f9..4a8644001d09 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -73,7 +73,8 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && !(addr && ipv6_addr_equal(addr, laddr)) && - !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (!sk->sk_bound_dev_if || !dif || + sk->sk_bound_dev_if == dif)) goto found; } @@ -196,8 +197,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct ipv6hdr *iph = ipv6_hdr(skb); read_lock_bh(&l2tp_ip6_lock); - sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, - 0, tunnel_id); + sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, inet6_iif(skb), + tunnel_id); if (!sk) { read_unlock_bh(&l2tp_ip6_lock); goto discard; From 31e2f21fb35bfaa5bdbe1a4860dc99e6b10d8dcd Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Tue, 29 Nov 2016 13:09:48 +0100 Subject: [PATCH 112/174] l2tp: fix address test in __l2tp_ip6_bind_lookup() The '!(addr && ipv6_addr_equal(addr, laddr))' part of the conditional matches if addr is NULL or if addr != laddr. But the intend of __l2tp_ip6_bind_lookup() is to find a sockets with the same address, so the ipv6_addr_equal() condition needs to be inverted. For better clarity and consistency with the rest of the expression, the (!X || X == Y) notation is used instead of !(X && X != Y). Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- net/l2tp/l2tp_ip6.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 4a8644001d09..aa821cb639e5 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -72,7 +72,7 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, if ((l2tp->conn_id == tunnel_id) && net_eq(sock_net(sk), net) && - !(addr && ipv6_addr_equal(addr, laddr)) && + (!addr || ipv6_addr_equal(addr, laddr)) && (!sk->sk_bound_dev_if || !dif || sk->sk_bound_dev_if == dif)) goto found; From 17a49cd549d9dc8707dc9262210166455c612dde Mon Sep 17 00:00:00 2001 From: Hongxu Jia Date: Tue, 29 Nov 2016 21:56:26 -0500 Subject: [PATCH 113/174] netfilter: arp_tables: fix invoking 32bit "iptable -P INPUT ACCEPT" failed in 64bit kernel Since 09d9686047db ("netfilter: x_tables: do compat validation via translate_table"), it used compatr structure to assign newinfo structure. In translate_compat_table of ip_tables.c and ip6_tables.c, it used compatr->hook_entry to replace info->hook_entry and compatr->underflow to replace info->underflow, but not do the same replacement in arp_tables.c. It caused invoking 32-bit "arptbale -P INPUT ACCEPT" failed in 64bit kernel. -------------------------------------- root@qemux86-64:~# arptables -P INPUT ACCEPT root@qemux86-64:~# arptables -P INPUT ACCEPT ERROR: Policy for `INPUT' offset 448 != underflow 0 arptables: Incompatible with this kernel -------------------------------------- Fixes: 09d9686047db ("netfilter: x_tables: do compat validation via translate_table") Signed-off-by: Hongxu Jia Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b31df597fd37..697538464e6e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1201,8 +1201,8 @@ static int translate_compat_table(struct xt_table_info **pinfo, newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; From e2d2afe15ed452f91797a80dbc0a17838ba03ed4 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 29 Nov 2016 12:27:09 -0500 Subject: [PATCH 114/174] bpf: fix states equal logic for varlen access If we have a branch that looks something like this int foo = map->value; if (condition) { foo += blah; } else { foo = bar; } map->array[foo] = baz; We will incorrectly assume that the !condition branch is equal to the condition branch as the register for foo will be UNKNOWN_VALUE in both cases. We need to adjust this logic to only do this if we didn't do a varlen access after we processed the !condition branch, otherwise we have different ranges and need to check the other branch as well. Fixes: 484611357c19 ("bpf: allow access into map value arrays") Reported-by: Jann Horn Signed-off-by: Josef Bacik Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6a936159c6e0..8199821f54cf 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2454,6 +2454,7 @@ static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { + bool varlen_map_access = env->varlen_map_value_access; struct bpf_reg_state *rold, *rcur; int i; @@ -2467,12 +2468,17 @@ static bool states_equal(struct bpf_verifier_env *env, /* If the ranges were not the same, but everything else was and * we didn't do a variable access into a map then we are a-ok. */ - if (!env->varlen_map_value_access && + if (!varlen_map_access && rold->type == rcur->type && rold->imm == rcur->imm) continue; + /* If we didn't map access then again we don't care about the + * mismatched range values and it's ok if our old type was + * UNKNOWN and we didn't go to a NOT_INIT'ed reg. + */ if (rold->type == NOT_INIT || - (rold->type == UNKNOWN_VALUE && rcur->type != NOT_INIT)) + (!varlen_map_access && rold->type == UNKNOWN_VALUE && + rcur->type != NOT_INIT)) continue; if (rold->type == PTR_TO_PACKET && rcur->type == PTR_TO_PACKET && From 4ccfd6383a1a4838ed034120f00d02dbdc681d6f Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Tue, 29 Nov 2016 16:27:03 -0600 Subject: [PATCH 115/174] net: ethernet: ti: cpsw: fix ASSERT_RTNL() warning during resume netif_set_real_num_tx/rx_queues() are required to be called with rtnl_lock taken, otherwise ASSERT_RTNL() warning will be triggered - which happens now during System resume from suspend: cpsw_resume() |- cpsw_ndo_open() |- netif_set_real_num_tx/rx_queues() |- ASSERT_RTNL(); Hence, fix it by surrounding cpsw_ndo_open() by rtnl_lock/unlock() calls. Cc: Dave Gerlach Cc: Ivan Khoronzhuk Fixes: commit e05107e6b747 ("net: ethernet: ti: cpsw: add multi queue support") Signed-off-by: Grygorii Strashko Reviewed-by: Ivan Khoronzhuk Tested-by: Dave Gerlach Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpsw.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9f0646512624..b9087b828eff 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2930,6 +2930,8 @@ static int cpsw_resume(struct device *dev) /* Select default pin state */ pinctrl_pm_select_default_state(dev); + /* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ + rtnl_lock(); if (cpsw->data.dual_emac) { int i; @@ -2941,6 +2943,8 @@ static int cpsw_resume(struct device *dev) if (netif_running(ndev)) cpsw_ndo_open(ndev); } + rtnl_unlock(); + return 0; } #endif From af1cc7a2b86ddb8668ac38097866bedd7b849a76 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 30 Nov 2016 13:17:51 +0800 Subject: [PATCH 116/174] tun: handle ubuf refcount correctly when meet errors We trigger uarg->callback() immediately after we decide do datacopy even if caller want to do zerocopy. This will cause the callback (vhost_net_zerocopy_callback) decrease the refcount. But when we meet an error afterwards, the error handling in vhost handle_tx() will try to decrease it again. This is wrong and fix this by delay the uarg->callback() until we're sure there's no errors. Reported-by: wangyunjian Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/tun.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8093e39ae263..db6acecabeaa 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1246,13 +1246,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) err = zerocopy_sg_from_iter(skb, from); - else { + else err = skb_copy_datagram_from_iter(skb, 0, from, len); - if (!err && msg_control) { - struct ubuf_info *uarg = msg_control; - uarg->callback(uarg, false); - } - } if (err) { this_cpu_inc(tun->pcpu_stats->rx_dropped); @@ -1298,6 +1293,9 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } else if (msg_control) { + struct ubuf_info *uarg = msg_control; + uarg->callback(uarg, false); } skb_reset_network_header(skb); From aa196eed3d80d4b003b04a270712b978a012a939 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 30 Nov 2016 13:17:52 +0800 Subject: [PATCH 117/174] macvtap: handle ubuf refcount correctly when meet errors We trigger uarg->callback() immediately after we decide do datacopy even if caller want to do zerocopy. This will cause the callback (vhost_net_zerocopy_callback) decrease the refcount. But when we meet an error afterwards, the error handling in vhost handle_tx() will try to decrease it again. This is wrong and fix this by delay the uarg->callback() until we're sure there's no errors. Signed-off-by: Jason Wang Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index bceca2875771..7869b0651576 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -742,13 +742,8 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, if (zerocopy) err = zerocopy_sg_from_iter(skb, from); - else { + else err = skb_copy_datagram_from_iter(skb, 0, from, len); - if (!err && m && m->msg_control) { - struct ubuf_info *uarg = m->msg_control; - uarg->callback(uarg, false); - } - } if (err) goto err_kfree; @@ -779,7 +774,11 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m, skb_shinfo(skb)->destructor_arg = m->msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } else if (m && m->msg_control) { + struct ubuf_info *uarg = m->msg_control; + uarg->callback(uarg, false); } + if (vlan) { skb->dev = vlan->dev; dev_queue_xmit(skb); From 4c9456df8849204435c4de1849120b916975d75d Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Tue, 29 Nov 2016 14:45:10 -0600 Subject: [PATCH 118/174] arm64: dts: juno: Correct PCI IO window The PCIe root complex on Juno translates the MMIO mapped at 0x5f800000 to the PIO address range starting at 0 (which is common because PIO addresses are generally < 64k). Correct the DT to reflect this. Signed-off-by: Jeremy Linton Signed-off-by: Arnd Bergmann --- arch/arm64/boot/dts/arm/juno-base.dtsi | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 334271a25f70..7d3a2acc6a55 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -393,7 +393,7 @@ pcie_ctlr: pcie-controller@40000000 { #address-cells = <3>; #size-cells = <2>; dma-coherent; - ranges = <0x01000000 0x00 0x5f800000 0x00 0x5f800000 0x0 0x00800000>, + ranges = <0x01000000 0x00 0x00000000 0x00 0x5f800000 0x0 0x00800000>, <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>, <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>; #interrupt-cells = <1>; From e1465d125d2189e667029b9fa8a6f455180fbcf2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=A9my=20Lefaure?= Date: Wed, 30 Nov 2016 15:54:02 -0800 Subject: [PATCH 119/174] mm, thp: propagation of conditional compilation in khugepaged.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit b46e756f5e47 ("thp: extract khugepaged from mm/huge_memory.c") moved code from huge_memory.c to khugepaged.c. Some of this code should be compiled only when CONFIG_SYSFS is enabled but the condition around this code was not moved into khugepaged.c. The result is a compilation error when CONFIG_SYSFS is disabled: mm/built-in.o: In function `khugepaged_defrag_store': khugepaged.c:(.text+0x2d095): undefined reference to `single_hugepage_flag_store' mm/built-in.o: In function `khugepaged_defrag_show': khugepaged.c:(.text+0x2d0ab): undefined reference to `single_hugepage_flag_show' This commit adds the #ifdef CONFIG_SYSFS around the code related to sysfs. Link: http://lkml.kernel.org/r/20161114203448.24197-1-jeremy.lefaure@lse.epita.fr Signed-off-by: Jérémy Lefaure Acked-by: Kirill A. Shutemov Acked-by: Hillf Danton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/khugepaged.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 728d7790dc2d..87e1a7ca3846 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -103,6 +103,7 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; +#ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -295,6 +296,7 @@ struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; +#endif /* CONFIG_SYSFS */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) From 655548bf6271b212cd1e4c259da9dbe616348d38 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 30 Nov 2016 15:54:05 -0800 Subject: [PATCH 120/174] thp: fix corner case of munlock() of PTE-mapped THPs The following program triggers BUG() in munlock_vma_pages_range(): // autogenerated by syzkaller (http://github.com/google/syzkaller) #include int main() { mmap((void*)0x20105000ul, 0xc00000ul, 0x2ul, 0x2172ul, -1, 0); mremap((void*)0x201fd000ul, 0x4000ul, 0xc00000ul, 0x3ul, 0x203f0000ul); return 0; } The test-case constructs the situation when munlock_vma_pages_range() finds PTE-mapped THP-head in the middle of page table and, by mistake, skips HPAGE_PMD_NR pages after that. As result, on the next iteration it hits the middle of PMD-mapped THP and gets upset seeing mlocked tail page. The solution is only skip HPAGE_PMD_NR pages if the THP was mlocked during munlock_vma_page(). It would guarantee that the page is PMD-mapped as we never mlock PTE-mapeed THPs. Fixes: e90309c9f772 ("thp: allow mlocked THP again") Link: http://lkml.kernel.org/r/20161115132703.7s7rrgmwttegcdh4@black.fi.intel.com Signed-off-by: Kirill A. Shutemov Reported-by: Dmitry Vyukov Cc: Konstantin Khlebnikov Cc: Andrey Ryabinin Cc: syzkaller Cc: Andrea Arcangeli Cc: [4.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mlock.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/mlock.c b/mm/mlock.c index 145a4258ddbc..cdbed8aaa426 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -190,10 +190,13 @@ unsigned int munlock_vma_page(struct page *page) */ spin_lock_irq(zone_lru_lock(zone)); - nr_pages = hpage_nr_pages(page); - if (!TestClearPageMlocked(page)) + if (!TestClearPageMlocked(page)) { + /* Potentially, PTE-mapped THP: do not skip the rest PTEs */ + nr_pages = 1; goto unlock_out; + } + nr_pages = hpage_nr_pages(page); __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); if (__munlock_isolate_lru_page(page, true)) { From 529e71e16403830ae0d737a66c55c5f360f3576b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 30 Nov 2016 15:54:08 -0800 Subject: [PATCH 121/174] zram: fix unbalanced idr management at hot removal The zram hot removal code calls idr_remove() even when zram_remove() returns an error (typically -EBUSY). This results in a leftover at the device release, eventually leading to a crash when the module is reloaded. As described in the bug report below, the following procedure would cause an Oops with zram: - provision three zram devices via modprobe zram num_devices=3 - configure a size for each device + echo "1G" > /sys/block/$zram_name/disksize - mkfs and mount zram0 only - attempt to hot remove all three devices + echo 2 > /sys/class/zram-control/hot_remove + echo 1 > /sys/class/zram-control/hot_remove + echo 0 > /sys/class/zram-control/hot_remove - zram0 removal fails with EBUSY, as expected - unmount zram0 - try zram0 hot remove again + echo 0 > /sys/class/zram-control/hot_remove - fails with ENODEV (unexpected) - unload zram kernel module + completes successfully - zram0 device node still exists - attempt to mount /dev/zram0 + mount command is killed + following BUG is encountered BUG: unable to handle kernel paging request at ffffffffa0002ba0 IP: get_disk+0x16/0x50 Oops: 0000 [#1] SMP CPU: 0 PID: 252 Comm: mount Not tainted 4.9.0-rc6 #176 Call Trace: exact_lock+0xc/0x20 kobj_lookup+0xdc/0x160 get_gendisk+0x2f/0x110 __blkdev_get+0x10c/0x3c0 blkdev_get+0x19d/0x2e0 blkdev_open+0x56/0x70 do_dentry_open.isra.19+0x1ff/0x310 vfs_open+0x43/0x60 path_openat+0x2c9/0xf30 do_filp_open+0x79/0xd0 do_sys_open+0x114/0x1e0 SyS_open+0x19/0x20 entry_SYSCALL_64_fastpath+0x13/0x94 This patch adds the proper error check in hot_remove_store() not to call idr_remove() unconditionally. Fixes: 17ec4cd98578 ("zram: don't call idr_remove() from zram_remove()") Bugzilla: https://bugzilla.opensuse.org/show_bug.cgi?id=1010970 Link: http://lkml.kernel.org/r/20161121132140.12683-1-tiwai@suse.de Signed-off-by: Takashi Iwai Reviewed-by: David Disseldorp Reported-by: David Disseldorp Tested-by: David Disseldorp Acked-by: Minchan Kim Acked-by: Sergey Senozhatsky Cc: [4.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 04365b17ee67..5163c8f918cb 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1403,7 +1403,8 @@ static ssize_t hot_remove_store(struct class *class, zram = idr_find(&zram_index_idr, dev_id); if (zram) { ret = zram_remove(zram); - idr_remove(&zram_index_idr, dev_id); + if (!ret) + idr_remove(&zram_index_idr, dev_id); } else { ret = -ENODEV; } From f8ff04e2be0815b34d11a72d08473a383a3c9eb5 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 30 Nov 2016 15:54:10 -0800 Subject: [PATCH 122/174] lib/debugobjects: export for use in modules Drivers, or other modules, that use a mixture of objects (especially objects embedded within other objects) would like to take advantage of the debugobjects facilities to help catch misuse. Currently, the debugobjects interface is only available to builtin drivers and requires a set of EXPORT_SYMBOL_GPL for use by modules. I am using the debugobjects in i915.ko to try and catch some invalid operations on embedded objects. The problem currently only presents itself across module unload so forcing i915 to be builtin is not an option. Link: http://lkml.kernel.org/r/20161122143039.6433-1-chris@chris-wilson.co.uk Signed-off-by: Chris Wilson Cc: "Du, Changbin" Cc: Thomas Gleixner Cc: Christian Borntraeger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/debugobjects.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a8e12601eb37..056052dc8e91 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -362,6 +362,7 @@ void debug_object_init(void *addr, struct debug_obj_descr *descr) __debug_object_init(addr, descr, 0); } +EXPORT_SYMBOL_GPL(debug_object_init); /** * debug_object_init_on_stack - debug checks when an object on stack is @@ -376,6 +377,7 @@ void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) __debug_object_init(addr, descr, 1); } +EXPORT_SYMBOL_GPL(debug_object_init_on_stack); /** * debug_object_activate - debug checks when an object is activated @@ -449,6 +451,7 @@ int debug_object_activate(void *addr, struct debug_obj_descr *descr) } return 0; } +EXPORT_SYMBOL_GPL(debug_object_activate); /** * debug_object_deactivate - debug checks when an object is deactivated @@ -496,6 +499,7 @@ void debug_object_deactivate(void *addr, struct debug_obj_descr *descr) raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_deactivate); /** * debug_object_destroy - debug checks when an object is destroyed @@ -542,6 +546,7 @@ void debug_object_destroy(void *addr, struct debug_obj_descr *descr) out_unlock: raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_destroy); /** * debug_object_free - debug checks when an object is freed @@ -582,6 +587,7 @@ void debug_object_free(void *addr, struct debug_obj_descr *descr) out_unlock: raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_free); /** * debug_object_assert_init - debug checks when object should be init-ed @@ -626,6 +632,7 @@ void debug_object_assert_init(void *addr, struct debug_obj_descr *descr) raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_assert_init); /** * debug_object_active_state - debug checks object usage state machine @@ -673,6 +680,7 @@ debug_object_active_state(void *addr, struct debug_obj_descr *descr, raw_spin_unlock_irqrestore(&db->lock, flags); } +EXPORT_SYMBOL_GPL(debug_object_active_state); #ifdef CONFIG_DEBUG_OBJECTS_FREE static void __debug_check_no_obj_freed(const void *address, unsigned long size) From 045d599a286bc01daa3510d59272440a17b23c2e Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Wed, 30 Nov 2016 15:54:13 -0800 Subject: [PATCH 123/174] kasan: update kasan_global for gcc 7 kasan_global struct is part of compiler/runtime ABI. gcc revision 241983 has added a new field to kasan_global struct. Update kernel definition of kasan_global struct to include the new field. Without this patch KASAN is broken with gcc 7. Link: http://lkml.kernel.org/r/1479219743-28682-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 4 +++- mm/kasan/kasan.h | 3 +++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 432f5c97e18f..928e5ca0caee 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -263,7 +263,9 @@ #endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ -#if GCC_VERSION >= 50000 +#if GCC_VERSION >= 70000 +#define KASAN_ABI_VERSION 5 +#elif GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 #elif GCC_VERSION >= 40902 #define KASAN_ABI_VERSION 3 diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index e5c2181fee6f..03f4545b103d 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -53,6 +53,9 @@ struct kasan_global { #if KASAN_ABI_VERSION >= 4 struct kasan_source_location *location; #endif +#if KASAN_ABI_VERSION >= 5 + char *odr_indicator; +#endif }; /** From 828347f8f9a558cf1af2faa46387a26564f2ac3e Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Wed, 30 Nov 2016 15:54:16 -0800 Subject: [PATCH 124/174] kasan: support use-after-scope detection Gcc revision 241896 implements use-after-scope detection. Will be available in gcc 7. Support it in KASAN. Gcc emits 2 new callbacks to poison/unpoison large stack objects when they go in/out of scope. Implement the callbacks and add a test. [dvyukov@google.com: v3] Link: http://lkml.kernel.org/r/1479998292-144502-1-git-send-email-dvyukov@google.com Link: http://lkml.kernel.org/r/1479226045-145148-1-git-send-email-dvyukov@google.com Signed-off-by: Dmitry Vyukov Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kasan.c | 29 +++++++++++++++++++++++++++++ mm/kasan/kasan.c | 19 +++++++++++++++++++ mm/kasan/kasan.h | 1 + mm/kasan/report.c | 3 +++ 4 files changed, 52 insertions(+) diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 5e51872b3fc1..fbdf87920093 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -20,6 +20,11 @@ #include #include +/* + * Note: test functions are marked noinline so that their names appear in + * reports. + */ + static noinline void __init kmalloc_oob_right(void) { char *ptr; @@ -411,6 +416,29 @@ static noinline void __init copy_user_test(void) kfree(kmem); } +static noinline void __init use_after_scope_test(void) +{ + volatile char *volatile p; + + pr_info("use-after-scope on int\n"); + { + int local = 0; + + p = (char *)&local; + } + p[0] = 1; + p[3] = 1; + + pr_info("use-after-scope on array\n"); + { + char local[1024] = {0}; + + p = local; + } + p[0] = 1; + p[1023] = 1; +} + static int __init kmalloc_tests_init(void) { kmalloc_oob_right(); @@ -436,6 +464,7 @@ static int __init kmalloc_tests_init(void) kasan_global_oob(); ksize_unpoisons_memory(); copy_user_test(); + use_after_scope_test(); return -EAGAIN; } diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 70c009741aab..0e9505f66ec1 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -764,6 +764,25 @@ EXPORT_SYMBOL(__asan_storeN_noabort); void __asan_handle_no_return(void) {} EXPORT_SYMBOL(__asan_handle_no_return); +/* Emitted by compiler to poison large objects when they go out of scope. */ +void __asan_poison_stack_memory(const void *addr, size_t size) +{ + /* + * Addr is KASAN_SHADOW_SCALE_SIZE-aligned and the object is surrounded + * by redzones, so we simply round up size to simplify logic. + */ + kasan_poison_shadow(addr, round_up(size, KASAN_SHADOW_SCALE_SIZE), + KASAN_USE_AFTER_SCOPE); +} +EXPORT_SYMBOL(__asan_poison_stack_memory); + +/* Emitted by compiler to unpoison large objects when they go into scope. */ +void __asan_unpoison_stack_memory(const void *addr, size_t size) +{ + kasan_unpoison_shadow(addr, size); +} +EXPORT_SYMBOL(__asan_unpoison_stack_memory); + #ifdef CONFIG_MEMORY_HOTPLUG static int kasan_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 03f4545b103d..1c260e6b3b3c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -21,6 +21,7 @@ #define KASAN_STACK_MID 0xF2 #define KASAN_STACK_RIGHT 0xF3 #define KASAN_STACK_PARTIAL 0xF4 +#define KASAN_USE_AFTER_SCOPE 0xF8 /* Don't break randconfig/all*config builds */ #ifndef KASAN_ABI_VERSION diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 24c1211fe9d5..073325aedc68 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -90,6 +90,9 @@ static void print_error_description(struct kasan_access_info *info) case KASAN_KMALLOC_FREE: bug_type = "use-after-free"; break; + case KASAN_USE_AFTER_SCOPE: + bug_type = "use-after-scope"; + break; } pr_err("BUG: KASAN: %s in %pS at addr %p\n", From 5cbc198ae08d84bd416b672ad8bd1222acd0855c Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 30 Nov 2016 15:54:19 -0800 Subject: [PATCH 125/174] mm: fix false-positive WARN_ON() in truncate/invalidate for hugetlb Hugetlb pages have ->index in size of the huge pages (PMD_SIZE or PUD_SIZE), not in PAGE_SIZE as other types of pages. This means we cannot user page_to_pgoff() to check whether we've got the right page for the radix-tree index. Let's introduce page_to_index() which would return radix-tree index for given page. We will be able to get rid of this once hugetlb will be switched to multi-order entries. Fixes: fc127da085c2 ("truncate: handle file thp") Link: http://lkml.kernel.org/r/20161123093053.mjbnvn5zwxw5e6lk@black.fi.intel.com Signed-off-by: Kirill A. Shutemov Reported-by: Doug Nelson Tested-by: Doug Nelson Reviewed-by: Naoya Horiguchi Cc: [4.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 21 +++++++++++++++------ mm/truncate.c | 8 ++++---- 2 files changed, 19 insertions(+), 10 deletions(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index dd15d39e1985..7dbe9148b2f8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -374,16 +374,13 @@ static inline struct page *read_mapping_page(struct address_space *mapping, } /* - * Get the offset in PAGE_SIZE. - * (TODO: hugepage should have ->index in PAGE_SIZE) + * Get index of the page with in radix-tree + * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ -static inline pgoff_t page_to_pgoff(struct page *page) +static inline pgoff_t page_to_index(struct page *page) { pgoff_t pgoff; - if (unlikely(PageHeadHuge(page))) - return page->index << compound_order(page); - if (likely(!PageTransTail(page))) return page->index; @@ -396,6 +393,18 @@ static inline pgoff_t page_to_pgoff(struct page *page) return pgoff; } +/* + * Get the offset in PAGE_SIZE. + * (TODO: hugepage should have ->index in PAGE_SIZE) + */ +static inline pgoff_t page_to_pgoff(struct page *page) +{ + if (unlikely(PageHeadHuge(page))) + return page->index << compound_order(page); + + return page_to_index(page); +} + /* * Return byte-offset into filesystem object for page. */ diff --git a/mm/truncate.c b/mm/truncate.c index a01cce450a26..8d8c62d89e6d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -283,7 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (!trylock_page(page)) continue; - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); if (PageWriteback(page)) { unlock_page(page); continue; @@ -371,7 +371,7 @@ void truncate_inode_pages_range(struct address_space *mapping, } lock_page(page); - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); @@ -492,7 +492,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (!trylock_page(page)) continue; - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); /* Middle of THP: skip */ if (PageTransTail(page)) { @@ -612,7 +612,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } lock_page(page); - WARN_ON(page_to_pgoff(page) != index); + WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { unlock_page(page); continue; From fe5b40642f1a2dddfeb84be007b2c975c28d4c6c Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Thu, 1 Dec 2016 11:41:11 +0100 Subject: [PATCH 126/174] can: peak: Fix bittiming fields size in bits This fixes the bitimings fields ranges supported by all the CAN-FD USB interfaces of the PEAK-System CAN-FD adapters. Very first development versions of the IP core API defined smaller TSGEx and SJW fields for both nominal and data bittimings records than the production versions. This patch fixes them by enlarging their sizes to the actual values: field: old size: fixed size: nominal TSGEG1 6 8 nominal TSGEG2 4 7 nominal SJW 4 7 data TSGEG1 4 5 data TSGEG2 3 4 data SJW 2 4 Note that this has no other consequences than offering larger choice to bitrate encoding. Signed-off-by: Stephane Grosjean Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_ucan.h | 37 +++++++++++++++++----- drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 32 +++++++++---------- 2 files changed, 45 insertions(+), 24 deletions(-) diff --git a/drivers/net/can/usb/peak_usb/pcan_ucan.h b/drivers/net/can/usb/peak_usb/pcan_ucan.h index e8fc4952c6b0..2147678f0225 100644 --- a/drivers/net/can/usb/peak_usb/pcan_ucan.h +++ b/drivers/net/can/usb/peak_usb/pcan_ucan.h @@ -43,11 +43,22 @@ struct __packed pucan_command { u16 args[3]; }; +#define PUCAN_TSLOW_BRP_BITS 10 +#define PUCAN_TSLOW_TSGEG1_BITS 8 +#define PUCAN_TSLOW_TSGEG2_BITS 7 +#define PUCAN_TSLOW_SJW_BITS 7 + +#define PUCAN_TSLOW_BRP_MASK ((1 << PUCAN_TSLOW_BRP_BITS) - 1) +#define PUCAN_TSLOW_TSEG1_MASK ((1 << PUCAN_TSLOW_TSGEG1_BITS) - 1) +#define PUCAN_TSLOW_TSEG2_MASK ((1 << PUCAN_TSLOW_TSGEG2_BITS) - 1) +#define PUCAN_TSLOW_SJW_MASK ((1 << PUCAN_TSLOW_SJW_BITS) - 1) + /* uCAN TIMING_SLOW command fields */ -#define PUCAN_TSLOW_SJW_T(s, t) (((s) & 0xf) | ((!!(t)) << 7)) -#define PUCAN_TSLOW_TSEG2(t) ((t) & 0xf) -#define PUCAN_TSLOW_TSEG1(t) ((t) & 0x3f) -#define PUCAN_TSLOW_BRP(b) ((b) & 0x3ff) +#define PUCAN_TSLOW_SJW_T(s, t) (((s) & PUCAN_TSLOW_SJW_MASK) | \ + ((!!(t)) << 7)) +#define PUCAN_TSLOW_TSEG2(t) ((t) & PUCAN_TSLOW_TSEG2_MASK) +#define PUCAN_TSLOW_TSEG1(t) ((t) & PUCAN_TSLOW_TSEG1_MASK) +#define PUCAN_TSLOW_BRP(b) ((b) & PUCAN_TSLOW_BRP_MASK) struct __packed pucan_timing_slow { __le16 opcode_channel; @@ -60,11 +71,21 @@ struct __packed pucan_timing_slow { __le16 brp; /* BaudRate Prescaler */ }; +#define PUCAN_TFAST_BRP_BITS 10 +#define PUCAN_TFAST_TSGEG1_BITS 5 +#define PUCAN_TFAST_TSGEG2_BITS 4 +#define PUCAN_TFAST_SJW_BITS 4 + +#define PUCAN_TFAST_BRP_MASK ((1 << PUCAN_TFAST_BRP_BITS) - 1) +#define PUCAN_TFAST_TSEG1_MASK ((1 << PUCAN_TFAST_TSGEG1_BITS) - 1) +#define PUCAN_TFAST_TSEG2_MASK ((1 << PUCAN_TFAST_TSGEG2_BITS) - 1) +#define PUCAN_TFAST_SJW_MASK ((1 << PUCAN_TFAST_SJW_BITS) - 1) + /* uCAN TIMING_FAST command fields */ -#define PUCAN_TFAST_SJW(s) ((s) & 0x3) -#define PUCAN_TFAST_TSEG2(t) ((t) & 0x7) -#define PUCAN_TFAST_TSEG1(t) ((t) & 0xf) -#define PUCAN_TFAST_BRP(b) ((b) & 0x3ff) +#define PUCAN_TFAST_SJW(s) ((s) & PUCAN_TFAST_SJW_MASK) +#define PUCAN_TFAST_TSEG2(t) ((t) & PUCAN_TFAST_TSEG2_MASK) +#define PUCAN_TFAST_TSEG1(t) ((t) & PUCAN_TFAST_TSEG1_MASK) +#define PUCAN_TFAST_BRP(b) ((b) & PUCAN_TFAST_BRP_MASK) struct __packed pucan_timing_fast { __le16 opcode_channel; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index ce44a033f63b..8a316a194cf7 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -993,24 +993,24 @@ static void pcan_usb_fd_free(struct peak_usb_device *dev) static const struct can_bittiming_const pcan_usb_fd_const = { .name = "pcan_usb_fd", .tseg1_min = 1, - .tseg1_max = 64, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 16, - .sjw_max = 16, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), .brp_inc = 1, }; static const struct can_bittiming_const pcan_usb_fd_data_const = { .name = "pcan_usb_fd", .tseg1_min = 1, - .tseg1_max = 16, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 8, - .sjw_max = 4, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), .brp_inc = 1, }; @@ -1065,24 +1065,24 @@ const struct peak_usb_adapter pcan_usb_fd = { static const struct can_bittiming_const pcan_usb_pro_fd_const = { .name = "pcan_usb_pro_fd", .tseg1_min = 1, - .tseg1_max = 64, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 16, - .sjw_max = 16, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), .brp_inc = 1, }; static const struct can_bittiming_const pcan_usb_pro_fd_data_const = { .name = "pcan_usb_pro_fd", .tseg1_min = 1, - .tseg1_max = 16, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), .tseg2_min = 1, - .tseg2_max = 8, - .sjw_max = 4, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), .brp_min = 1, - .brp_max = 1024, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), .brp_inc = 1, }; From f00b534ded60bd0a23c2fa8dec4ece52aa7d235f Mon Sep 17 00:00:00 2001 From: Stephane Grosjean Date: Thu, 1 Dec 2016 11:41:12 +0100 Subject: [PATCH 127/174] can: peak: Add support for PCAN-USB X6 USB interface This adds support for PEAK-System PCAN-USB X6 USB to CAN interface. The CAN FD adapter PCAN-USB X6 allows the connection of up to 6 CAN FD or CAN networks to a computer via USB. The interface is installed in an aluminum profile casing and is shipped in versions with D-Sub connectors or M12 circular connectors. The PCAN-USB X6 registers in the USB sub-system as if 3x PCAN-USB-Pro FD adapters were plugged. So, this patch: - updates the PEAK_USB entry of the corresponding Kconfig file - defines and adds the device id. of the PCAN-USB X6 (0x0014) into the table of supported device ids - defines and adds the new software structure implementing the PCAN-USB X6, which is obviously a clone of the software structure implementing the PCAN-USB Pro FD. Signed-off-by: Stephane Grosjean Tested-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 2 + drivers/net/can/usb/peak_usb/pcan_usb_core.h | 2 + drivers/net/can/usb/peak_usb/pcan_usb_fd.c | 72 ++++++++++++++++++++ 3 files changed, 76 insertions(+) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c06382cdfdfe..f3141ca56bc3 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -39,6 +39,7 @@ static struct usb_device_id peak_usb_table[] = { {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPRO_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBFD_PRODUCT_ID)}, {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBPROFD_PRODUCT_ID)}, + {USB_DEVICE(PCAN_USB_VENDOR_ID, PCAN_USBX6_PRODUCT_ID)}, {} /* Terminating entry */ }; @@ -50,6 +51,7 @@ static const struct peak_usb_adapter *const peak_usb_adapters_list[] = { &pcan_usb_pro, &pcan_usb_fd, &pcan_usb_pro_fd, + &pcan_usb_x6, }; /* diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index 506fe506c9d3..3cbfb069893d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -27,6 +27,7 @@ #define PCAN_USBPRO_PRODUCT_ID 0x000d #define PCAN_USBPROFD_PRODUCT_ID 0x0011 #define PCAN_USBFD_PRODUCT_ID 0x0012 +#define PCAN_USBX6_PRODUCT_ID 0x0014 #define PCAN_USB_DRIVER_NAME "peak_usb" @@ -90,6 +91,7 @@ extern const struct peak_usb_adapter pcan_usb; extern const struct peak_usb_adapter pcan_usb_pro; extern const struct peak_usb_adapter pcan_usb_fd; extern const struct peak_usb_adapter pcan_usb_pro_fd; +extern const struct peak_usb_adapter pcan_usb_x6; struct peak_time_ref { struct timeval tv_host_0, tv_host; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 8a316a194cf7..304732550f0a 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -1132,3 +1132,75 @@ const struct peak_usb_adapter pcan_usb_pro_fd = { .do_get_berr_counter = pcan_usb_fd_get_berr_counter, }; + +/* describes the PCAN-USB X6 adapter */ +static const struct can_bittiming_const pcan_usb_x6_const = { + .name = "pcan_usb_x6", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TSLOW_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TSLOW_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TSLOW_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TSLOW_BRP_BITS), + .brp_inc = 1, +}; + +static const struct can_bittiming_const pcan_usb_x6_data_const = { + .name = "pcan_usb_x6", + .tseg1_min = 1, + .tseg1_max = (1 << PUCAN_TFAST_TSGEG1_BITS), + .tseg2_min = 1, + .tseg2_max = (1 << PUCAN_TFAST_TSGEG2_BITS), + .sjw_max = (1 << PUCAN_TFAST_SJW_BITS), + .brp_min = 1, + .brp_max = (1 << PUCAN_TFAST_BRP_BITS), + .brp_inc = 1, +}; + +const struct peak_usb_adapter pcan_usb_x6 = { + .name = "PCAN-USB X6", + .device_id = PCAN_USBX6_PRODUCT_ID, + .ctrl_count = PCAN_USBPROFD_CHANNEL_COUNT, + .ctrlmode_supported = CAN_CTRLMODE_FD | + CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LISTENONLY, + .clock = { + .freq = PCAN_UFD_CRYSTAL_HZ, + }, + .bittiming_const = &pcan_usb_x6_const, + .data_bittiming_const = &pcan_usb_x6_data_const, + + /* size of device private data */ + .sizeof_dev_private = sizeof(struct pcan_usb_fd_device), + + /* timestamps usage */ + .ts_used_bits = 32, + .ts_period = 1000000, /* calibration period in ts. */ + .us_per_ts_scale = 1, /* us = (ts * scale) >> shift */ + .us_per_ts_shift = 0, + + /* give here messages in/out endpoints */ + .ep_msg_in = PCAN_USBPRO_EP_MSGIN, + .ep_msg_out = {PCAN_USBPRO_EP_MSGOUT_0, PCAN_USBPRO_EP_MSGOUT_1}, + + /* size of rx/tx usb buffers */ + .rx_buffer_size = PCAN_UFD_RX_BUFFER_SIZE, + .tx_buffer_size = PCAN_UFD_TX_BUFFER_SIZE, + + /* device callbacks */ + .intf_probe = pcan_usb_pro_probe, /* same as PCAN-USB Pro */ + .dev_init = pcan_usb_fd_init, + + .dev_exit = pcan_usb_fd_exit, + .dev_free = pcan_usb_fd_free, + .dev_set_bus = pcan_usb_fd_set_bus, + .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, + .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_decode_buf = pcan_usb_fd_decode_buf, + .dev_start = pcan_usb_fd_start, + .dev_stop = pcan_usb_fd_stop, + .dev_restart_async = pcan_usb_fd_restart_async, + .dev_encode_msg = pcan_usb_fd_encode_msg, + + .do_get_berr_counter = pcan_usb_fd_get_berr_counter, +}; From a0f1d21c1ccb1da66629627a74059dd7f5ac9c61 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 30 Nov 2016 22:21:05 +0300 Subject: [PATCH 128/174] KVM: use after free in kvm_ioctl_create_device() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We should move the ops->destroy(dev) after the list_del(&dev->vm_node) so that we don't use "dev" after freeing it. Fixes: a28ebea2adc4 ("KVM: Protect device ops->create and list_add with kvm->lock") Signed-off-by: Dan Carpenter Reviewed-by: David Hildenbrand Signed-off-by: Radim Krčmář --- virt/kvm/kvm_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5c360347a1e9..7f9ee2929cfe 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2889,10 +2889,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm, ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { - ops->destroy(dev); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); + ops->destroy(dev); return ret; } From d3fc425e819be7c251a9c208cd4c0a6373c19bfe Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Wed, 30 Nov 2016 17:41:58 -0500 Subject: [PATCH 129/174] kbuild: make sure autoksyms.h exists early Some people are able to trigger a race where autoksyms.h is used before its empty version is even created. Let's create it at the same time as the directory holding it is created. Signed-off-by: Nicolas Pitre Tested-by: Prarit Bhargava Tested-by: Jarod Wilson Signed-off-by: Linus Torvalds --- Makefile | 2 -- scripts/kconfig/Makefile | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 694111b43cf8..9f9c3b577c75 100644 --- a/Makefile +++ b/Makefile @@ -1019,8 +1019,6 @@ prepare2: prepare3 prepare-compiler-check outputmakefile asm-generic prepare1: prepare2 $(version_h) include/generated/utsrelease.h \ include/config/auto.conf $(cmd_crmodverdir) - $(Q)test -e include/generated/autoksyms.h || \ - touch include/generated/autoksyms.h archprepare: archheaders archscripts prepare1 scripts_basic diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index ebced77deb9c..90a091b6ae4d 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -35,6 +35,8 @@ nconfig: $(obj)/nconf silentoldconfig: $(obj)/conf $(Q)mkdir -p include/config include/generated + $(Q)test -e include/generated/autoksyms.h || \ + touch include/generated/autoksyms.h $< $(silent) --$@ $(Kconfig) localyesconfig localmodconfig: $(obj)/streamline_config.pl $(obj)/conf From fadf3a28054404f075c05d9ca8ebd4b4ce9ebc0f Mon Sep 17 00:00:00 2001 From: allan Date: Wed, 30 Nov 2016 16:29:08 +0800 Subject: [PATCH 130/174] net: asix: Fix AX88772_suspend() USB vendor commands failure issues The change fixes AX88772_suspend() USB vendor commands failure issues. Signed-off-by: Allan Chou Tested-by: Allan Chou Tested-by: Jon Hunter Signed-off-by: David S. Miller --- drivers/net/usb/asix_devices.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index cce24950a0ab..dc7b6392e75a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -603,12 +603,12 @@ static void ax88772_suspend(struct usbnet *dev) u16 medium; /* Stop MAC operation */ - medium = asix_read_medium_status(dev, 0); + medium = asix_read_medium_status(dev, 1); medium &= ~AX_MEDIUM_RE; - asix_write_medium_mode(dev, medium, 0); + asix_write_medium_mode(dev, medium, 1); netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n", - asix_read_medium_status(dev, 0)); + asix_read_medium_status(dev, 1)); /* Preserve BMCR for restoring */ priv->presvd_phy_bmcr = From 516165a1e2f22e512a976f8dafd76a22310ccfd9 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 28 Nov 2016 10:42:23 -0500 Subject: [PATCH 131/174] igb/igbvf: Don't use lco_csum to compute IPv4 checksum In the case of IPIP and SIT tunnel frames the outer transport header offset is actually set to the same offset as the inner transport header. This results in the lco_csum call not doing any checksum computation over the inner IPv4/v6 header data. In order to account for that I am updating the code so that we determine the location to start the checksum ourselves based on the location of the IPv4 header and the length. Fixes: e10715d3e961 ("igb/igbvf: Add support for GSO partial") Reported-by: Stephen Rothwell Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/igb/igb_main.c | 8 ++++++-- drivers/net/ethernet/intel/igbvf/netdev.c | 8 ++++++-- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index edc9a6ac5169..9affd7c198bd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4931,11 +4931,15 @@ static int igb_tso(struct igb_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 12bb877df860..7dff7f6239cd 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1965,11 +1965,15 @@ static int igbvf_tso(struct igbvf_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= E1000_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; From c54cdc316dbd35695cd54dd425327463c72809e4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 28 Nov 2016 10:42:29 -0500 Subject: [PATCH 132/174] ixgbe/ixgbevf: Don't use lco_csum to compute IPv4 checksum In the case of IPIP and SIT tunnel frames the outer transport header offset is actually set to the same offset as the inner transport header. This results in the lco_csum call not doing any checksum computation over the inner IPv4/v6 header data. In order to account for that I am updating the code so that we determine the location to start the checksum ourselves based on the location of the IPv4 header and the length. Fixes: b83e30104bd9 ("ixgbe/ixgbevf: Add support for GSO partial") Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++++++-- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 8 ++++++-- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bd93d823cc25..fee1f2918ead 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7277,11 +7277,15 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 7eaac3234049..cbf70fe4028a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3329,11 +3329,15 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, /* initialize outer IP header fields */ if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + /* IP header will have to cancel out any data that * is not a part of the outer IP header */ - ip.v4->check = csum_fold(csum_add(lco_csum(skb), - csum_unfold(l4.tcp->check))); + ip.v4->check = csum_fold(csum_partial(trans_start, + csum_start - trans_start, + 0)); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; From 6919756caaeaa76dc56287252fb656e3c2d9b4e1 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Wed, 30 Nov 2016 14:30:37 +0100 Subject: [PATCH 133/174] net/rtnetlink: fix attribute name in nlmsg_size() comments Use the correct attribute constant names IFLA_GSO_MAX_{SEGS,SIZE} instead of IFLA_MAX_GSO_{SEGS,SIZE} for the comments int nlmsg_size(). Cc: Eric Dumazet Signed-off-by: Tobias Klauser Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index deb35acbefd0..a6196cf844f6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -931,8 +931,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ - + nla_total_size(4) /* IFLA_MAX_GSO_SEGS */ - + nla_total_size(4) /* IFLA_MAX_GSO_SIZE */ + + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */ + + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ From 50ac64cfc39dad2ba0d8ad553d2d87dfc738cbba Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:49 +0100 Subject: [PATCH 134/174] net: ethernet: stmmac: dwmac-socfpga: fix use-after-free on probe errors Make sure to call stmmac_dvr_remove() before returning on late probe errors so that memory is freed, clocks are disabled, and the netdev is deregistered before its resources go away. Fixes: 3c201b5a84ed ("net: stmmac: socfpga: Remove re-registration of reset controller") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- .../ethernet/stmicro/stmmac/dwmac-socfpga.c | 29 ++++++++++++------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index bec6963ac71e..47db157da3e8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -304,6 +304,8 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; struct socfpga_dwmac *dwmac; + struct net_device *ndev; + struct stmmac_priv *stpriv; ret = stmmac_get_platform_resources(pdev, &stmmac_res); if (ret) @@ -327,19 +329,26 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + return ret; - if (!ret) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *stpriv = netdev_priv(ndev); + ndev = platform_get_drvdata(pdev); + stpriv = netdev_priv(ndev); - /* The socfpga driver needs to control the stmmac reset to - * set the phy mode. Create a copy of the core reset handel - * so it can be used by the driver later. - */ - dwmac->stmmac_rst = stpriv->stmmac_rst; + /* The socfpga driver needs to control the stmmac reset to set the phy + * mode. Create a copy of the core reset handle so it can be used by + * the driver later. + */ + dwmac->stmmac_rst = stpriv->stmmac_rst; - ret = socfpga_dwmac_set_phy_mode(dwmac); - } + ret = socfpga_dwmac_set_phy_mode(dwmac); + if (ret) + goto err_dvr_remove; + + return 0; + +err_dvr_remove: + stmmac_dvr_remove(&pdev->dev); return ret; } From 0a9e22715ee384cf2a714c28f24ce8881b9fd815 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:50 +0100 Subject: [PATCH 135/174] net: ethernet: stmmac: dwmac-sti: fix probe error path Make sure to disable clocks before returning on late probe errors. Fixes: 8387ee21f972 ("stmmac: dwmac-sti: turn setup callback into a probe function") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index 58c05acc2aab..a1ce018bf844 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -365,7 +365,16 @@ static int sti_dwmac_probe(struct platform_device *pdev) if (ret) return ret; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_dwmac_exit; + + return 0; + +err_dwmac_exit: + sti_dwmac_exit(pdev, plat_dat->bsp_priv); + + return ret; } static const struct sti_dwmac_of_data stih4xx_dwmac_data = { From 2d222656db08b8eef3b53b56cf1ce4a90fe8cd78 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:51 +0100 Subject: [PATCH 136/174] net: ethernet: stmmac: dwmac-rk: fix probe error path Make sure to disable runtime PM, power down the PHY, and disable clocks before returning on late probe errors. Fixes: 27ffefd2d109 ("stmmac: dwmac-rk: create a new probe function") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 3740a4417fa0..e7aabe56c15a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -988,7 +988,16 @@ static int rk_gmac_probe(struct platform_device *pdev) if (ret) return ret; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_gmac_exit; + + return 0; + +err_gmac_exit: + rk_gmac_exit(pdev, plat_dat->bsp_priv); + + return ret; } static const struct of_device_id rk_gmac_dwmac_match[] = { From 939b20022765bc338b0f72cbf1eed60a907398d7 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:52 +0100 Subject: [PATCH 137/174] net: ethernet: stmmac: dwmac-generic: fix probe error path Make sure to call any exit() callback to undo the effect of init() before returning on late probe errors. Fixes: cf3f047b9af4 ("stmmac: move hw init in the probe (v2)") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c index b1e5f24708c9..05e46a82cdb1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c @@ -53,7 +53,17 @@ static int dwmac_generic_probe(struct platform_device *pdev) return ret; } - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_exit; + + return 0; + +err_exit: + if (plat_dat->exit) + plat_dat->exit(pdev, plat_dat->bsp_priv); + + return ret; } static const struct of_device_id dwmac_generic_match[] = { From 5cc70bbcacf6728b598b529a061930d8271adbb5 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:53 +0100 Subject: [PATCH 138/174] net: ethernet: stmmac: dwmac-meson8b: fix probe error path Make sure to disable clocks before returning on late probe errors. Fixes: 566e82516253 ("net: stmmac: add a glue driver for the Amlogic Meson 8b / GXBB DWMAC") Signed-off-by: Johan Hovold Acked-by: Kevin Hilman Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 250e4ceafc8d..45e7aaf0170d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -289,7 +289,16 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = dwmac; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_clk_disable; + + return 0; + +err_clk_disable: + clk_disable_unprepare(dwmac->m25_div_clk); + + return ret; } static int meson8b_dwmac_remove(struct platform_device *pdev) From 661f049be17a3894cb438d46ba5af8e3643aac28 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:54 +0100 Subject: [PATCH 139/174] net: ethernet: stmmac: platform: fix outdated function header Fix the OF-helper function header to reflect that the function no longer has a platform-data parameter. Fixes: b0003ead75f3 ("stmmac: make stmmac_probe_config_dt return the platform data struct") Signed-off-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 0a0d6a86f397..bcbf123d5ba2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -200,7 +200,6 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, /** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure - * @plat: driver data platform structure * @mac: MAC address to use * Description: * this function is to read the driver parameters from device-tree and From d2ed0a7755fe14c790f398ae55088d00492ef168 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Wed, 30 Nov 2016 15:29:55 +0100 Subject: [PATCH 140/174] net: ethernet: stmmac: fix of-node and fixed-link-phydev leaks Make sure to deregister and free any fixed-link phy registered during probe on probe errors and on driver unbind by adding a new glue helper function. Drop the of-node reference taken in the same path also on late probe errors (and not just on driver unbind) by moving the put from stmmac_dvr_remove() to the new helper. Fixes: 277323814e49 ("stmmac: add fixed-link device-tree support") Fixes: 4613b279bee7 ("ethernet: stmicro: stmmac: add missing of_node_put after calling of_parse_phandle") Signed-off-by: Johan Hovold Acked-by: Maxime Ripard Signed-off-by: David S. Miller --- .../ethernet/stmicro/stmmac/dwmac-generic.c | 5 ++- .../ethernet/stmicro/stmmac/dwmac-ipq806x.c | 25 +++++++++++---- .../ethernet/stmicro/stmmac/dwmac-lpc18xx.c | 17 ++++++++-- .../net/ethernet/stmicro/stmmac/dwmac-meson.c | 23 ++++++++++--- .../ethernet/stmicro/stmmac/dwmac-meson8b.c | 21 ++++++++---- .../net/ethernet/stmicro/stmmac/dwmac-rk.c | 10 ++++-- .../ethernet/stmicro/stmmac/dwmac-socfpga.c | 12 ++++--- .../net/ethernet/stmicro/stmmac/dwmac-sti.c | 12 ++++--- .../net/ethernet/stmicro/stmmac/dwmac-stm32.c | 19 ++++++++--- .../net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 26 +++++++++++---- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 1 - .../ethernet/stmicro/stmmac/stmmac_platform.c | 32 +++++++++++++++++-- .../ethernet/stmicro/stmmac/stmmac_platform.h | 2 ++ 13 files changed, 156 insertions(+), 49 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c index 05e46a82cdb1..e6e6c2fcc4b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c @@ -50,7 +50,7 @@ static int dwmac_generic_probe(struct platform_device *pdev) if (plat_dat->init) { ret = plat_dat->init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; } ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); @@ -62,6 +62,9 @@ static int dwmac_generic_probe(struct platform_device *pdev) err_exit: if (plat_dat->exit) plat_dat->exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + if (pdev->dev.of_node) + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 36d3355f2fb0..866444b6c82f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -271,15 +271,17 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); - if (!gmac) - return -ENOMEM; + if (!gmac) { + err = -ENOMEM; + goto err_remove_config_dt; + } gmac->pdev = pdev; err = ipq806x_gmac_of_parse(gmac); if (err) { dev_err(dev, "device tree parsing error\n"); - return err; + goto err_remove_config_dt; } regmap_write(gmac->qsgmii_csr, QSGMII_PCS_CAL_LCKDT_CTL, @@ -300,7 +302,8 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", phy_modes(gmac->phy_mode)); - return -EINVAL; + err = -EINVAL; + goto err_remove_config_dt; } regmap_write(gmac->nss_common, NSS_COMMON_GMAC_CTL(gmac->id), val); @@ -319,7 +322,8 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported PHY mode: \"%s\"\n", phy_modes(gmac->phy_mode)); - return -EINVAL; + err = -EINVAL; + goto err_remove_config_dt; } regmap_write(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, val); @@ -346,7 +350,16 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = gmac; plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + err = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (err) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return err; } static const struct of_device_id ipq806x_gmac_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index 78e9d1861896..3d3f43d91b98 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -46,7 +46,8 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); if (IS_ERR(reg)) { dev_err(&pdev->dev, "syscon lookup failed\n"); - return PTR_ERR(reg); + ret = PTR_ERR(reg); + goto err_remove_config_dt; } if (plat_dat->interface == PHY_INTERFACE_MODE_MII) { @@ -55,13 +56,23 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII; } else { dev_err(&pdev->dev, "Only MII and RMII mode supported\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } regmap_update_bits(reg, LPC18XX_CREG_CREG6, LPC18XX_CREG_CREG6_ETHMODE_MASK, ethmode); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id lpc18xx_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 309d99536a2c..7fdd1760a74c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -64,18 +64,31 @@ static int meson6_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->reg = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(dwmac->reg)) - return PTR_ERR(dwmac->reg); + if (IS_ERR(dwmac->reg)) { + ret = PTR_ERR(dwmac->reg); + goto err_remove_config_dt; + } plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = meson6_dwmac_fix_mac_speed; - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; } static const struct of_device_id meson6_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 45e7aaf0170d..ffaed1f35efe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -264,28 +264,33 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(dwmac->regs)) - return PTR_ERR(dwmac->regs); + if (IS_ERR(dwmac->regs)) { + ret = PTR_ERR(dwmac->regs); + goto err_remove_config_dt; + } dwmac->pdev = pdev; dwmac->phy_mode = of_get_phy_mode(pdev->dev.of_node); if (dwmac->phy_mode < 0) { dev_err(&pdev->dev, "missing phy-mode property\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_config_dt; } ret = meson8b_init_clk(dwmac); if (ret) - return ret; + goto err_remove_config_dt; ret = meson8b_init_prg_eth(dwmac); if (ret) - return ret; + goto err_remove_config_dt; plat_dat->bsp_priv = dwmac; @@ -297,6 +302,8 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) err_clk_disable: clk_disable_unprepare(dwmac->m25_div_clk); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index e7aabe56c15a..d80c88bd2bba 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -981,12 +981,14 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->resume = rk_gmac_resume; plat_dat->bsp_priv = rk_gmac_setup(pdev, data); - if (IS_ERR(plat_dat->bsp_priv)) - return PTR_ERR(plat_dat->bsp_priv); + if (IS_ERR(plat_dat->bsp_priv)) { + ret = PTR_ERR(plat_dat->bsp_priv); + goto err_remove_config_dt; + } ret = rk_gmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) @@ -996,6 +998,8 @@ static int rk_gmac_probe(struct platform_device *pdev) err_gmac_exit: rk_gmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 47db157da3e8..0c420e97de1e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -316,13 +316,15 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = socfpga_dwmac_parse_data(dwmac, dev); if (ret) { dev_err(dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } plat_dat->bsp_priv = dwmac; @@ -330,7 +332,7 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - return ret; + goto err_remove_config_dt; ndev = platform_get_drvdata(pdev); stpriv = netdev_priv(ndev); @@ -349,6 +351,8 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) err_dvr_remove: stmmac_dvr_remove(&pdev->dev); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index a1ce018bf844..060b98c37a85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -345,13 +345,15 @@ static int sti_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = sti_dwmac_parse_data(dwmac, pdev); if (ret) { dev_err(&pdev->dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } dwmac->fix_retime_src = data->fix_retime_src; @@ -363,7 +365,7 @@ static int sti_dwmac_probe(struct platform_device *pdev) ret = sti_dwmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) @@ -373,6 +375,8 @@ static int sti_dwmac_probe(struct platform_device *pdev) err_dwmac_exit: sti_dwmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index e5a926b8bee7..61cb24810d10 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -107,24 +107,33 @@ static int stm32_dwmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); - if (!dwmac) - return -ENOMEM; + if (!dwmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } ret = stm32_dwmac_parse_data(dwmac, &pdev->dev); if (ret) { dev_err(&pdev->dev, "Unable to parse OF data\n"); - return ret; + goto err_remove_config_dt; } plat_dat->bsp_priv = dwmac; ret = stm32_dwmac_init(plat_dat); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - stm32_dwmac_clk_disable(dwmac); + goto err_clk_disable; + + return 0; + +err_clk_disable: + stm32_dwmac_clk_disable(dwmac); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index adff46375a32..d07520fb969e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -120,22 +120,27 @@ static int sun7i_gmac_probe(struct platform_device *pdev) return PTR_ERR(plat_dat); gmac = devm_kzalloc(dev, sizeof(*gmac), GFP_KERNEL); - if (!gmac) - return -ENOMEM; + if (!gmac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } gmac->interface = of_get_phy_mode(dev->of_node); gmac->tx_clk = devm_clk_get(dev, "allwinner_gmac_tx"); if (IS_ERR(gmac->tx_clk)) { dev_err(dev, "could not get tx clock\n"); - return PTR_ERR(gmac->tx_clk); + ret = PTR_ERR(gmac->tx_clk); + goto err_remove_config_dt; } /* Optional regulator for PHY */ gmac->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(gmac->regulator)) { - if (PTR_ERR(gmac->regulator) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(gmac->regulator) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto err_remove_config_dt; + } dev_info(dev, "no regulator found\n"); gmac->regulator = NULL; } @@ -151,11 +156,18 @@ static int sun7i_gmac_probe(struct platform_device *pdev) ret = sun7i_gmac_init(pdev, plat_dat->bsp_priv); if (ret) - return ret; + goto err_remove_config_dt; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) - sun7i_gmac_exit(pdev, plat_dat->bsp_priv); + goto err_gmac_exit; + + return 0; + +err_gmac_exit: + sun7i_gmac_exit(pdev, plat_dat->bsp_priv); +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1f9ec02fa7f8..caf069a465f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3416,7 +3416,6 @@ int stmmac_dvr_remove(struct device *dev) stmmac_set_mac(priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); - of_node_put(priv->plat->phy_node); if (priv->stmmac_rst) reset_control_assert(priv->stmmac_rst); clk_disable_unprepare(priv->pclk); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index bcbf123d5ba2..a840818bf4df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -305,7 +305,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) { - of_node_put(plat->phy_node); + stmmac_remove_config_dt(pdev, plat); return ERR_PTR(-ENOMEM); } plat->dma_cfg = dma_cfg; @@ -328,14 +328,37 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) return plat; } + +/** + * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt() + * @pdev: platform_device structure + * @plat: driver data platform structure + * + * Release resources claimed by stmmac_probe_config_dt(). + */ +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ + struct device_node *np = pdev->dev.of_node; + + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + of_node_put(plat->phy_node); +} #else struct plat_stmmacenet_data * stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) { return ERR_PTR(-ENOSYS); } + +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) +{ +} #endif /* CONFIG_OF */ EXPORT_SYMBOL_GPL(stmmac_probe_config_dt); +EXPORT_SYMBOL_GPL(stmmac_remove_config_dt); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res) @@ -391,10 +414,13 @@ int stmmac_pltfr_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *priv = netdev_priv(ndev); + struct plat_stmmacenet_data *plat = priv->plat; int ret = stmmac_dvr_remove(&pdev->dev); - if (priv->plat->exit) - priv->plat->exit(pdev, priv->plat->bsp_priv); + if (plat->exit) + plat->exit(pdev, plat->bsp_priv); + + stmmac_remove_config_dt(pdev, plat); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index 64e147f53a9c..b72eb0de57b7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -23,6 +23,8 @@ struct plat_stmmacenet_data * stmmac_probe_config_dt(struct platform_device *pdev, const char **mac); +void stmmac_remove_config_dt(struct platform_device *pdev, + struct plat_stmmacenet_data *plat); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res); From 909e481e2467f202b97d42beef246e8829416a85 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Wed, 16 Nov 2016 17:31:31 +0000 Subject: [PATCH 141/174] arm64: dts: juno: fix cluster sleep state entry latency on all SoC versions The core and the cluster sleep state entry latencies can't be same as cluster sleep involves more work compared to core level e.g. shared cache maintenance. Experiments have shown on an average about 100us more latency for the cluster sleep state compared to the core level sleep. This patch fixes the entry latency for the cluster sleep state. Fixes: 28e10a8f3a03 ("arm64: dts: juno: Add idle-states to device tree") Cc: Lorenzo Pieralisi Cc: "Jon Medhurst (Tixy)" Reviewed-by: Liviu Dudau Signed-off-by: Sudeep Holla Signed-off-by: Arnd Bergmann --- arch/arm64/boot/dts/arm/juno-r1.dts | 2 +- arch/arm64/boot/dts/arm/juno-r2.dts | 2 +- arch/arm64/boot/dts/arm/juno.dts | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/boot/dts/arm/juno-r1.dts b/arch/arm64/boot/dts/arm/juno-r1.dts index 123a58b29cbd..f0b857d6d73c 100644 --- a/arch/arm64/boot/dts/arm/juno-r1.dts +++ b/arch/arm64/boot/dts/arm/juno-r1.dts @@ -76,7 +76,7 @@ CLUSTER_SLEEP_0: cluster-sleep-0 { compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/arm64/boot/dts/arm/juno-r2.dts b/arch/arm64/boot/dts/arm/juno-r2.dts index 007be826efce..26aaa6a7670f 100644 --- a/arch/arm64/boot/dts/arm/juno-r2.dts +++ b/arch/arm64/boot/dts/arm/juno-r2.dts @@ -76,7 +76,7 @@ CLUSTER_SLEEP_0: cluster-sleep-0 { compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts index a7270eff6939..6e154d948a80 100644 --- a/arch/arm64/boot/dts/arm/juno.dts +++ b/arch/arm64/boot/dts/arm/juno.dts @@ -76,7 +76,7 @@ CLUSTER_SLEEP_0: cluster-sleep-0 { compatible = "arm,idle-state"; arm,psci-suspend-param = <0x1010000>; local-timer-stop; - entry-latency-us = <300>; + entry-latency-us = <400>; exit-latency-us = <1200>; min-residency-us = <2500>; }; From 8ab2ae655bfe384335c5b6b0d6041e0ddce26b00 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 2 Dec 2016 13:40:27 +0100 Subject: [PATCH 142/174] default exported asm symbols to zero With binutils-2.26 and before, a weak missing symbol was kept during the final link, and a missing CRC for an export would lead to that CRC being treated as zero implicitly. With binutils-2.27, the crc symbol gets dropped, and any module trying to use it will fail to load. This sets the weak CRC symbol to zero explicitly, making it defined in vmlinux, which in turn lets us load the modules referring to that CRC. The comment above the __CRC_SYMBOL macro suggests that this was always the intention, although it also seems that all symbols defined in C have a correct CRC these days, and only the exports that are now done in assembly need this. Signed-off-by: Arnd Bergmann Tested-by: Adam Borowski Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/asm-generic/export.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index 63554e9f6e0c..59a3b2f58c22 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -54,6 +54,7 @@ KSYM(__kstrtab_\name): KSYM(__kcrctab_\name): __put KSYM(__crc_\name) .weak KSYM(__crc_\name) + .set KSYM(__crc_\name), 0 .previous #endif #endif From 151a14db228181fb49abaf83e13f3be58ec102c4 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 30 Nov 2016 23:48:31 +0100 Subject: [PATCH 143/174] net: ethernet: altera: TSE: Remove unneeded dma sync for tx buffers An explicit dma sync for device directly after mapping as well as an explicit dma sync for cpu directly before unmapping is unnecessary and costly on the hotpath. So remove these calls. Signed-off-by: Lino Sanfilippo Signed-off-by: David S. Miller --- drivers/net/ethernet/altera/altera_tse_main.c | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 6532829b70d2..28689092ff19 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -400,12 +400,6 @@ static int tse_rx(struct altera_tse_private *priv, int limit) skb_put(skb, pktlength); - /* make cache consistent with receive packet buffer */ - dma_sync_single_for_cpu(priv->device, - priv->rx_ring[entry].dma_addr, - priv->rx_ring[entry].len, - DMA_FROM_DEVICE); - dma_unmap_single(priv->device, priv->rx_ring[entry].dma_addr, priv->rx_ring[entry].len, DMA_FROM_DEVICE); @@ -592,10 +586,6 @@ static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev) buffer->dma_addr = dma_addr; buffer->len = nopaged_len; - /* Push data out of the cache hierarchy into main memory */ - dma_sync_single_for_device(priv->device, buffer->dma_addr, - buffer->len, DMA_TO_DEVICE); - priv->dmaops->tx_buffer(priv, buffer); skb_tx_timestamp(skb); From 2219d5ed77e8bdc2ef1f0b79f34d2cc0be802b25 Mon Sep 17 00:00:00 2001 From: Lino Sanfilippo Date: Wed, 30 Nov 2016 23:48:32 +0100 Subject: [PATCH 144/174] net: ethernet: altera: TSE: do not use tx queue lock in tx completion handler The driver already uses its private lock for synchronization between xmit and xmit completion handler making the additional use of the xmit_lock unnecessary. Furthermore the driver does not set NETIF_F_LLTX resulting in xmit to be called with the xmit_lock held and then taking the private lock while xmit completion handler does the reverse, first take the private lock, then the xmit_lock. Fix these issues by not taking the xmit_lock in the tx completion handler. Signed-off-by: Lino Sanfilippo Signed-off-by: David S. Miller --- drivers/net/ethernet/altera/altera_tse_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 28689092ff19..a0eee7218695 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -463,7 +463,6 @@ static int tse_tx_complete(struct altera_tse_private *priv) if (unlikely(netif_queue_stopped(priv->dev) && tse_tx_avail(priv) > TSE_TX_THRESH(priv))) { - netif_tx_lock(priv->dev); if (netif_queue_stopped(priv->dev) && tse_tx_avail(priv) > TSE_TX_THRESH(priv)) { if (netif_msg_tx_done(priv)) @@ -471,7 +470,6 @@ static int tse_tx_complete(struct altera_tse_private *priv) __func__); netif_wake_queue(priv->dev); } - netif_tx_unlock(priv->dev); } spin_unlock(&priv->tx_lock); From 84ac7260236a49c79eede91617700174c2c19b0c Mon Sep 17 00:00:00 2001 From: Philip Pettersson Date: Wed, 30 Nov 2016 14:55:36 -0800 Subject: [PATCH 145/174] packet: fix race condition in packet_set_ring When packet_set_ring creates a ring buffer it will initialize a struct timer_list if the packet version is TPACKET_V3. This value can then be raced by a different thread calling setsockopt to set the version to TPACKET_V1 before packet_set_ring has finished. This leads to a use-after-free on a function pointer in the struct timer_list when the socket is closed as the previously initialized timer will not be deleted. The bug is fixed by taking lock_sock(sk) in packet_setsockopt when changing the packet version while also taking the lock at the start of packet_set_ring. Fixes: f6fb8f100b80 ("af-packet: TPACKET_V3 flexible buffer implementation.") Signed-off-by: Philip Pettersson Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/packet/af_packet.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d2238b204691..dd2332390c45 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3648,19 +3648,25 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: - po->tp_version = val; - return 0; + break; default: return -EINVAL; } + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_version = val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_RESERVE: { @@ -4164,6 +4170,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; + lock_sock(sk); /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { net_warn_ratelimited("Tx-ring is not supported.\n"); @@ -4245,7 +4252,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; } - lock_sock(sk); /* Detach socket from network */ spin_lock(&po->bind_lock); @@ -4294,11 +4300,11 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } - release_sock(sk); if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: + release_sock(sk); return err; } From f4180439109aa720774baafdd798b3234ab1a0d2 Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Thu, 1 Dec 2016 10:05:10 +0800 Subject: [PATCH 146/174] ipv4: Set skb->protocol properly for local output When xfrm is applied to TSO/GSO packets, it follows this path: xfrm_output() -> xfrm_output_gso() -> skb_gso_segment() where skb_gso_segment() relies on skb->protocol to function properly. This patch sets skb->protocol to ETH_P_IP before dst_output() is called, fixing a bug where GSO packets sent through a sit tunnel are dropped when xfrm is involved. Cc: stable@vger.kernel.org Signed-off-by: Eli Cooper Signed-off-by: David S. Miller --- net/ipv4/ip_output.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 105908d841a3..877bdb02e887 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -107,6 +107,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(!skb)) return 0; + skb->protocol = htons(ETH_P_IP); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); From b4e479a96fc398ccf83bb1cffb4ffef8631beaf1 Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Thu, 1 Dec 2016 10:05:11 +0800 Subject: [PATCH 147/174] ipv6: Set skb->protocol properly for local output When xfrm is applied to TSO/GSO packets, it follows this path: xfrm_output() -> xfrm_output_gso() -> skb_gso_segment() where skb_gso_segment() relies on skb->protocol to function properly. This patch sets skb->protocol to ETH_P_IPV6 before dst_output() is called, fixing a bug where GSO packets sent through an ipip6 tunnel are dropped when xfrm is involved. Cc: stable@vger.kernel.org Signed-off-by: Eli Cooper Signed-off-by: David S. Miller --- net/ipv6/output_core.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 7cca8ac66fe9..cd4252346a32 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -155,6 +155,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) if (unlikely(!skb)) return 0; + skb->protocol = htons(ETH_P_IPV6); + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); From 80d1106aeaf689ab5fdf33020c5fecd269b31c88 Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Thu, 1 Dec 2016 10:05:12 +0800 Subject: [PATCH 148/174] Revert: "ip6_tunnel: Update skb->protocol to ETH_P_IPV6 in ip6_tnl_xmit()" This reverts commit ae148b085876fa771d9ef2c05f85d4b4bf09ce0d ("ip6_tunnel: Update skb->protocol to ETH_P_IPV6 in ip6_tnl_xmit()"). skb->protocol is now set in __ip_local_out() and __ip6_local_out() before dst_output() is called. It is no longer necessary to do it for each tunnel. Cc: stable@vger.kernel.org Signed-off-by: Eli Cooper Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 0a4759b89da2..d76674efe523 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1181,7 +1181,6 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, if (err) return err; - skb->protocol = htons(ETH_P_IPV6); skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); From 721c7443dcb26bf8c0b4ad317a36c7dfa140f1e4 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Thu, 1 Dec 2016 04:44:43 -0800 Subject: [PATCH 149/174] RDS: TCP: unregister_netdevice_notifier() in error path of rds_tcp_init_net If some error is encountered in rds_tcp_init_net, make sure to unregister_netdevice_notifier(), else we could trigger a panic later on, when the modprobe from a netns fails. Signed-off-by: Sowmini Varadhan Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/tcp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/rds/tcp.c b/net/rds/tcp.c index fcddacc92e01..20e2923dc827 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -659,6 +659,8 @@ static int rds_tcp_init(void) out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); out_slab: + if (unregister_netdevice_notifier(&rds_tcp_dev_notifier)) + pr_warn("could not unregister rds_tcp_dev_notifier\n"); kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; From 6b6ebb6b01c873d0cfe3449e8a1219ee6e5fc022 Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Thu, 1 Dec 2016 14:06:04 +0100 Subject: [PATCH 150/174] ip6_offload: check segs for NULL in ipv6_gso_segment. segs needs to be checked for being NULL in ipv6_gso_segment() before calling skb_shinfo(segs), otherwise kernel can run into a NULL-pointer dereference: [ 97.811262] BUG: unable to handle kernel NULL pointer dereference at 00000000000000cc [ 97.819112] IP: [] ipv6_gso_segment+0x119/0x2f0 [ 97.825214] PGD 0 [ 97.827047] [ 97.828540] Oops: 0000 [#1] SMP [ 97.831678] Modules linked in: vhost_net vhost macvtap macvlan nfsv3 rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_conntrack ipt_REJECT nf_reject_ipv4 tun ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter bridge stp llc snd_hda_codec_realtek snd_hda_codec_hdmi snd_hda_codec_generic snd_hda_intel snd_hda_codec edac_mce_amd snd_hda_core edac_core snd_hwdep kvm_amd snd_seq kvm snd_seq_device snd_pcm irqbypass snd_timer ppdev parport_serial snd parport_pc k10temp pcspkr soundcore parport sp5100_tco shpchp sg wmi i2c_piix4 acpi_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sr_mod cdrom sd_mod ata_generic pata_acpi amdkfd amd_iommu_v2 radeon broadcom bcm_phy_lib i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm ahci serio_raw tg3 firewire_ohci libahci pata_atiixp drm ptp libata firewire_core pps_core i2c_core crc_itu_t fjes dm_mirror dm_region_hash dm_log dm_mod [ 97.927721] CPU: 1 PID: 3504 Comm: vhost-3495 Not tainted 4.9.0-7.el7.test.x86_64 #1 [ 97.935457] Hardware name: AMD Snook/Snook, BIOS ESK0726A 07/26/2010 [ 97.941806] task: ffff880129a1c080 task.stack: ffffc90001bcc000 [ 97.947720] RIP: 0010:[] [] ipv6_gso_segment+0x119/0x2f0 [ 97.956251] RSP: 0018:ffff88012fc43a10 EFLAGS: 00010207 [ 97.961557] RAX: 0000000000000000 RBX: ffff8801292c8700 RCX: 0000000000000594 [ 97.968687] RDX: 0000000000000593 RSI: ffff880129a846c0 RDI: 0000000000240000 [ 97.975814] RBP: ffff88012fc43a68 R08: ffff880129a8404e R09: 0000000000000000 [ 97.982942] R10: 0000000000000000 R11: ffff880129a84076 R12: 00000020002949b3 [ 97.990070] R13: ffff88012a580000 R14: 0000000000000000 R15: ffff88012a580000 [ 97.997198] FS: 0000000000000000(0000) GS:ffff88012fc40000(0000) knlGS:0000000000000000 [ 98.005280] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 98.011021] CR2: 00000000000000cc CR3: 0000000126c5d000 CR4: 00000000000006e0 [ 98.018149] Stack: [ 98.020157] 00000000ffffffff ffff88012fc43ac8 ffffffffa017ad0a 000000000000000e [ 98.027584] 0000001300000000 0000000077d59998 ffff8801292c8700 00000020002949b3 [ 98.035010] ffff88012a580000 0000000000000000 ffff88012a580000 ffff88012fc43a98 [ 98.042437] Call Trace: [ 98.044879] [ 98.046803] [] ? tg3_start_xmit+0x84a/0xd60 [tg3] [ 98.053156] [] skb_mac_gso_segment+0xb0/0x130 [ 98.059158] [] __skb_gso_segment+0x73/0x110 [ 98.064985] [] validate_xmit_skb+0x12d/0x2b0 [ 98.070899] [] validate_xmit_skb_list+0x42/0x70 [ 98.077073] [] sch_direct_xmit+0xd0/0x1b0 [ 98.082726] [] __dev_queue_xmit+0x486/0x690 [ 98.088554] [] ? cpumask_next_and+0x35/0x50 [ 98.094380] [] dev_queue_xmit+0x10/0x20 [ 98.099863] [] br_dev_queue_push_xmit+0xa7/0x170 [bridge] [ 98.106907] [] br_forward_finish+0x41/0xc0 [bridge] [ 98.113430] [] ? nf_iterate+0x52/0x60 [ 98.118735] [] ? nf_hook_slow+0x6b/0xc0 [ 98.124216] [] __br_forward+0x14c/0x1e0 [bridge] [ 98.130480] [] ? br_dev_queue_push_xmit+0x170/0x170 [bridge] [ 98.137785] [] br_forward+0x9d/0xb0 [bridge] [ 98.143701] [] br_handle_frame_finish+0x267/0x560 [bridge] [ 98.150834] [] br_handle_frame+0x174/0x2f0 [bridge] [ 98.157355] [] ? sched_clock+0x9/0x10 [ 98.162662] [] ? sched_clock_cpu+0x72/0xa0 [ 98.168403] [] __netif_receive_skb_core+0x1e5/0xa20 [ 98.174926] [] ? timerqueue_add+0x59/0xb0 [ 98.180580] [] __netif_receive_skb+0x18/0x60 [ 98.186494] [] process_backlog+0x95/0x140 [ 98.192145] [] net_rx_action+0x16d/0x380 [ 98.197713] [] __do_softirq+0xd1/0x283 [ 98.203106] [] do_softirq_own_stack+0x1c/0x30 [ 98.209107] [ 98.211029] [] do_softirq+0x50/0x60 [ 98.216166] [] netif_rx_ni+0x33/0x80 [ 98.221386] [] tun_get_user+0x487/0x7f0 [tun] [ 98.227388] [] tun_sendmsg+0x4b/0x60 [tun] [ 98.233129] [] handle_tx+0x282/0x540 [vhost_net] [ 98.239392] [] handle_tx_kick+0x15/0x20 [vhost_net] [ 98.245916] [] vhost_worker+0x9e/0xf0 [vhost] [ 98.251919] [] ? vhost_umem_alloc+0x40/0x40 [vhost] [ 98.258440] [] ? do_syscall_64+0x67/0x180 [ 98.264094] [] kthread+0xd9/0xf0 [ 98.268965] [] ? kthread_park+0x60/0x60 [ 98.274444] [] ret_from_fork+0x25/0x30 [ 98.279836] Code: 8b 93 d8 00 00 00 48 2b 93 d0 00 00 00 4c 89 e6 48 89 df 66 89 93 c2 00 00 00 ff 10 48 3d 00 f0 ff ff 49 89 c2 0f 87 52 01 00 00 <41> 8b 92 cc 00 00 00 48 8b 80 d0 00 00 00 44 0f b7 74 10 06 66 [ 98.299425] RIP [] ipv6_gso_segment+0x119/0x2f0 [ 98.305612] RSP [ 98.309094] CR2: 00000000000000cc [ 98.312406] ---[ end trace 726a2c7a2d2d78d0 ]--- Signed-off-by: Artem Savkov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv6/ip6_offload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1fcf61f1cbc3..89c59e656f44 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -99,7 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, segs = ops->callbacks.gso_segment(skb, features); } - if (IS_ERR(segs)) + if (IS_ERR_OR_NULL(segs)) goto out; gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); From d5c83d0d1d83b3798c71e0c8b7c3624d39c91d88 Mon Sep 17 00:00:00 2001 From: Kristian Evensen Date: Thu, 1 Dec 2016 14:23:17 +0100 Subject: [PATCH 151/174] cdc_ether: Fix handling connection notification MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling") introduced a work-around in usbnet_cdc_status() for devices that exported cdc carrier on twice on connect. Before the commit, this behavior caused the link state to be incorrect. It was assumed that all CDC Ethernet devices would either export this behavior, or send one off and then one on notification (which seems to be the default behavior). Unfortunately, it turns out multiple devices sends a connection notification multiple times per second (via an interrupt), even when connection state does not change. This has been observed with several different USB LAN dongles (at least), for example 13b1:0041 (Linksys). After bfe9b9d2df66, the link state has been set as down and then up for each notification. This has caused a flood of Netlink NEWLINK messages and syslog to be flooded with messages similar to: cdc_ether 2-1:2.0 eth1: kevent 12 may have been dropped This commit fixes the behavior by reverting usbnet_cdc_status() to how it was before bfe9b9d2df66. The work-around has been moved to a separate status-function which is only called when a known, affect device is detected. v1->v2: * Do not open-code netif_carrier_ok() (thanks Henning Schild). * Call netif_carrier_off() instead of usb_link_change(). This prevents calling schedule_work() twice without giving the work queue a chance to be processed (thanks Bjørn Mork). Fixes: bfe9b9d2df66 ("cdc_ether: Improve ZTE MF823/831/910 handling") Reported-by: Henning Schild Signed-off-by: Kristian Evensen Signed-off-by: David S. Miller --- drivers/net/usb/cdc_ether.c | 38 ++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index c47ec0a04c8e..dd623f674487 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -388,12 +388,6 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb) case USB_CDC_NOTIFY_NETWORK_CONNECTION: netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", event->wValue ? "on" : "off"); - - /* Work-around for devices with broken off-notifications */ - if (event->wValue && - !test_bit(__LINK_STATE_NOCARRIER, &dev->net->state)) - usbnet_link_change(dev, 0, 0); - usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: /* tx/rx rates */ @@ -466,6 +460,36 @@ static int usbnet_cdc_zte_rx_fixup(struct usbnet *dev, struct sk_buff *skb) return 1; } +/* Ensure correct link state + * + * Some devices (ZTE MF823/831/910) export two carrier on notifications when + * connected. This causes the link state to be incorrect. Work around this by + * always setting the state to off, then on. + */ +void usbnet_cdc_zte_status(struct usbnet *dev, struct urb *urb) +{ + struct usb_cdc_notification *event; + + if (urb->actual_length < sizeof(*event)) + return; + + event = urb->transfer_buffer; + + if (event->bNotificationType != USB_CDC_NOTIFY_NETWORK_CONNECTION) { + usbnet_cdc_status(dev, urb); + return; + } + + netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", + event->wValue ? "on" : "off"); + + if (event->wValue && + netif_carrier_ok(dev->net)) + netif_carrier_off(dev->net); + + usbnet_link_change(dev, !!event->wValue, 0); +} + static const struct driver_info cdc_info = { .description = "CDC Ethernet Device", .flags = FLAG_ETHER | FLAG_POINTTOPOINT, @@ -481,7 +505,7 @@ static const struct driver_info zte_cdc_info = { .flags = FLAG_ETHER | FLAG_POINTTOPOINT, .bind = usbnet_cdc_zte_bind, .unbind = usbnet_cdc_unbind, - .status = usbnet_cdc_status, + .status = usbnet_cdc_zte_status, .set_rx_mode = usbnet_cdc_update_filter, .manage_power = usbnet_manage_power, .rx_fixup = usbnet_cdc_zte_rx_fixup, From 9bd813da24cd49d749911d7fdc0e9ae9a673d746 Mon Sep 17 00:00:00 2001 From: Daniele Palmas Date: Thu, 1 Dec 2016 16:52:05 +0100 Subject: [PATCH 152/174] NET: usb: qmi_wwan: add support for Telit LE922A PID 0x1040 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds support for PID 0x1040 of Telit LE922A. The qmi adapter requires to have DTR set for proper working, so QMI_WWAN_QUIRK_DTR has been enabled. Signed-off-by: Daniele Palmas Acked-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3ff76c6db4f6..6fe1cdb0174f 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -894,6 +894,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ From ed8d747fd2b9d9204762ca6ab8c843c72c42cc41 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 2 Dec 2016 10:48:50 -0800 Subject: [PATCH 153/174] Fix up a couple of field names in the CREDITS file Ozgur Karatas reported that the very first entry in the CREDITS file had the wrong tag for name (M: instead of N: - it happened when moving the entry from the MAINTAINERS file, where 'M:' stands for "Maintainer"). And when I went looking, I found a couple of other cases of wrong tagging too. Reported-by: Ozgur Karatas Signed-off-by: Linus Torvalds --- CREDITS | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/CREDITS b/CREDITS index 837367624e45..d7ebdfbc4d4f 100644 --- a/CREDITS +++ b/CREDITS @@ -9,7 +9,7 @@ Linus ---------- -M: Matt Mackal +N: Matt Mackal E: mpm@selenic.com D: SLOB slab allocator @@ -1910,7 +1910,7 @@ S: Ra'annana, Israel N: Andi Kleen E: andi@firstfloor.org -U: http://www.halobates.de +W: http://www.halobates.de D: network, x86, NUMA, various hacks S: Schwalbenstr. 96 S: 85551 Ottobrunn @@ -2089,8 +2089,8 @@ D: ST Microelectronics SPEAr13xx PCI host bridge driver D: Synopsys Designware PCI host bridge driver N: Gabor Kuti -M: seasons@falcon.sch.bme.hu -M: seasons@makosteszta.sote.hu +E: seasons@falcon.sch.bme.hu +E: seasons@makosteszta.sote.hu D: Original author of software suspend N: Jaroslav Kysela From 8c4799ac799665065f9bf1364fd71bf4f7dc6a4a Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 1 Dec 2016 09:45:45 -0800 Subject: [PATCH 154/174] net: bcmgenet: Utilize correct struct device for all DMA operations __bcmgenet_tx_reclaim() and bcmgenet_free_rx_buffers() are not using the same struct device during unmap that was used for the map operation, which makes DMA-API debugging warn about it. Fix this by always using &priv->pdev->dev throughout the driver, using an identical device reference for all map/unmap calls. Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 4464bc5db934..a4e60e56c14f 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1172,6 +1172,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, struct bcmgenet_tx_ring *ring) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; struct enet_cb *tx_cb_ptr; struct netdev_queue *txq; unsigned int pkts_compl = 0; @@ -1199,13 +1200,13 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, if (tx_cb_ptr->skb) { pkts_compl++; bytes_compl += GENET_CB(tx_cb_ptr->skb)->bytes_sent; - dma_unmap_single(&dev->dev, + dma_unmap_single(kdev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); bcmgenet_free_cb(tx_cb_ptr); } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { - dma_unmap_page(&dev->dev, + dma_unmap_page(kdev, dma_unmap_addr(tx_cb_ptr, dma_addr), dma_unmap_len(tx_cb_ptr, dma_len), DMA_TO_DEVICE); @@ -1775,6 +1776,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) { + struct device *kdev = &priv->pdev->dev; struct enet_cb *cb; int i; @@ -1782,7 +1784,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) cb = &priv->rx_cbs[i]; if (dma_unmap_addr(cb, dma_addr)) { - dma_unmap_single(&priv->dev->dev, + dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), priv->rx_buf_len, DMA_FROM_DEVICE); dma_unmap_addr_set(cb, dma_addr, 0); From 33d446dbba4d4d6a77e1e900d434fa99e0f02c86 Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Thu, 1 Dec 2016 13:32:14 -0500 Subject: [PATCH 155/174] sh_eth: remove unchecked interrupts for RZ/A1 When streaming a lot of data and the RZ/A1 can't keep up, some status bits will get set that are not being checked or cleared which cause the following messages and the Ethernet driver to stop working. This patch fixes that issue. irq 21: nobody cared (try booting with the "irqpoll" option) handlers: [] sh_eth_interrupt Disabling IRQ #21 Fixes: db893473d313a4ad ("sh_eth: Add support for r7s72100") Signed-off-by: Chris Brandt Acked-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/sh_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 05b0dc55de77..1a92de705199 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -518,7 +518,7 @@ static struct sh_eth_cpu_data r7s72100_data = { .ecsr_value = ECSR_ICD, .ecsipr_value = ECSIPR_ICDIP, - .eesipr_value = 0xff7f009f, + .eesipr_value = 0xe77f009f, .tx_check = EESR_TC1 | EESR_FTC, .eesr_err_check = EESR_TWB1 | EESR_TWB | EESR_TABT | EESR_RABT | From 50d5aa4cf822887f88841e4d8f8502434af679a9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 1 Dec 2016 23:57:44 +0300 Subject: [PATCH 156/174] net: renesas: ravb: unintialized return value We want to set the other "err" variable here so that we can return it later. My version of GCC misses this issue but I caught it with a static checker. Fixes: 9f70eb339f52 ("net: ethernet: renesas: ravb: fix fixed-link phydev leaks") Signed-off-by: Dan Carpenter Acked-by: Sergei Shtylyov Reviewed-by: Johan Hovold Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index f1f3be2cfe21..d6a217874a8b 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1016,8 +1016,6 @@ static int ravb_phy_init(struct net_device *ndev) * at this time. */ if (priv->chip_id == RCAR_GEN3) { - int err; - err = phy_set_max_speed(phydev, SPEED_100); if (err) { netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n"); From 3de81b758853f0b29c61e246679d20b513c4cfec Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Michal=20Kube=C4=8Dek?= Date: Fri, 2 Dec 2016 09:33:41 +0100 Subject: [PATCH 157/174] tipc: check minimum bearer MTU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Qian Zhang (张谦) reported a potential socket buffer overflow in tipc_msg_build() which is also known as CVE-2016-8632: due to insufficient checks, a buffer overflow can occur if MTU is too short for even tipc headers. As anyone can set device MTU in a user/net namespace, this issue can be abused by a regular user. As agreed in the discussion on Ben Hutchings' original patch, we should check the MTU at the moment a bearer is attached rather than for each processed packet. We also need to repeat the check when bearer MTU is adjusted to new device MTU. UDP case also needs a check to avoid overflow when calculating bearer MTU. Fixes: b97bf3fd8f6a ("[TIPC] Initial merge") Signed-off-by: Michal Kubecek Reported-by: Qian Zhang (张谦) Acked-by: Ying Xue Signed-off-by: David S. Miller --- net/tipc/bearer.c | 11 +++++++++-- net/tipc/bearer.h | 13 +++++++++++++ net/tipc/udp_media.c | 5 +++++ 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 975dbeb60ab0..52d74760fb68 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -421,6 +421,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, dev = dev_get_by_name(net, driver_name); if (!dev) return -ENODEV; + if (tipc_mtu_bad(dev, 0)) { + dev_put(dev); + return -EINVAL; + } /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); @@ -610,8 +614,6 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, if (!b) return NOTIFY_DONE; - b->mtu = dev->mtu; - switch (evt) { case NETDEV_CHANGE: if (netif_carrier_ok(dev)) @@ -624,6 +626,11 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, tipc_reset_bearer(net, b); break; case NETDEV_CHANGEMTU: + if (tipc_mtu_bad(dev, 0)) { + bearer_disable(net, b); + break; + } + b->mtu = dev->mtu; tipc_reset_bearer(net, b); break; case NETDEV_CHANGEADDR: diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 78892e2f53e3..278ff7f616f9 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -39,6 +39,7 @@ #include "netlink.h" #include "core.h" +#include "msg.h" #include #define MAX_MEDIA 3 @@ -59,6 +60,9 @@ #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 +/* minimum bearer MTU */ +#define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) + /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) @@ -215,4 +219,13 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id, void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); +/* check if device MTU is too low for tipc headers */ +static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) +{ + if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) + return false; + netdev_warn(dev, "MTU too low for tipc bearer\n"); + return true; +} + #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 78cab9c5a445..b58dc95f3d35 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -697,6 +697,11 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, udp_conf.local_ip.s_addr = htonl(INADDR_ANY); udp_conf.use_udp_checksums = false; ub->ifindex = dev->ifindex; + if (tipc_mtu_bad(dev, sizeof(struct iphdr) + + sizeof(struct udphdr))) { + err = -EINVAL; + goto err; + } b->mtu = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); #if IS_ENABLED(CONFIG_IPV6) From 5b01014759991887b1e450c9def01e58c02ab81b Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 2 Dec 2016 16:49:29 +0100 Subject: [PATCH 158/174] geneve: avoid use-after-free of skb->data geneve{,6}_build_skb can end up doing a pskb_expand_head(), which makes the ip_hdr(skb) reference we stashed earlier stale. Since it's only needed as an argument to ip_tunnel_ecn_encap(), move this directly in the function call. Fixes: 08399efc6319 ("geneve: ensure ECN info is handled properly in all tx/rx paths") Signed-off-by: Sabrina Dubroca Reviewed-by: John W. Linville Signed-off-by: David S. Miller --- drivers/net/geneve.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 42edd7b7902f..8b4822ad27cb 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -859,7 +859,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4; struct rtable *rt = NULL; - const struct iphdr *iip; /* interior IP header */ int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; @@ -890,8 +889,6 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); - iip = ip_hdr(skb); - if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -911,7 +908,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - tos = ip_tunnel_ecn_encap(key->tos, iip, skb); + tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; } else { @@ -920,7 +917,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb); + tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && IN_MULTICAST(ntohl(fl4.daddr))) ttl = 1; @@ -952,7 +949,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, { struct geneve_dev *geneve = netdev_priv(dev); struct dst_entry *dst = NULL; - const struct iphdr *iip; /* interior IP header */ struct geneve_sock *gs6; int err = -EINVAL; struct flowi6 fl6; @@ -982,8 +978,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); skb_reset_mac_header(skb); - iip = ip_hdr(skb); - if (info) { const struct ip_tunnel_key *key = &info->key; u8 *opts = NULL; @@ -1004,7 +998,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto tx_error; - prio = ip_tunnel_ecn_encap(key->tos, iip, skb); + prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; label = info->key.label; } else { @@ -1014,7 +1008,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, goto tx_error; prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), - iip, skb); + ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) ttl = 1; From b98b0bc8c431e3ceb4b26b0dfc8db509518fb290 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Dec 2016 09:44:53 -0800 Subject: [PATCH 159/174] net: avoid signed overflows for SO_{SND|RCV}BUFFORCE CAP_NET_ADMIN users should not be allowed to set negative sk_sndbuf or sk_rcvbuf values, as it can lead to various memory corruptions, crashes, OOM... Note that before commit 82981930125a ("net: cleanups in sock_setsockopt()"), the bug was even more serious, since SO_SNDBUF and SO_RCVBUF were vulnerable. This needs to be backported to all known linux kernels. Again, many thanks to syzkaller team for discovering this gem. Signed-off-by: Eric Dumazet Reported-by: Andrey Konovalov Signed-off-by: David S. Miller --- net/core/sock.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/core/sock.c b/net/core/sock.c index 5e3ca414357e..00a074dbfe9b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -715,7 +715,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF); + sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -751,7 +751,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname, * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF); + sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_RCVBUFFORCE: From 865563924022d8a307ee6dbc6a9ab4fb4d461cce Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Fri, 2 Dec 2016 15:11:50 -0500 Subject: [PATCH 160/174] kbuild: fix building bzImage with CONFIG_TRIM_UNUSED_KSYMS enabled When building a specific target such as bzImage, modules aren't normally built. However if CONFIG_TRIM_UNUSED_KSYMS is enabled, no built modules means none of the exported symbols are used and therefore they will all be trimmed away from the final kernel. A subsequent "make modules" will fail because modpost cannot find the needed symbols for those modules in the kernel binary. Let's make sure modules are also built whenever CONFIG_TRIM_UNUSED_KSYMS is enabled and that the kernel binary is properly rebuilt accordingly. Signed-off-by: Nicolas Pitre Tested-by: Jarod Wilson Signed-off-by: Linus Torvalds --- Makefile | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 9f9c3b577c75..b816089e5dc9 100644 --- a/Makefile +++ b/Makefile @@ -607,6 +607,13 @@ else include/config/auto.conf: ; endif # $(dot-config) +# For the kernel to actually contain only the needed exported symbols, +# we have to build modules as well to determine what those symbols are. +# (this can be evaluated only once include/config/auto.conf has been included) +ifdef CONFIG_TRIM_UNUSED_KSYMS + KBUILD_MODULES := 1 +endif + # The all: target is the default when no target is given on the # command line. # This allow a user to issue only 'make' to build a kernel including modules @@ -944,7 +951,7 @@ ifdef CONFIG_GDB_SCRIPTS endif ifdef CONFIG_TRIM_UNUSED_KSYMS $(Q)$(CONFIG_SHELL) $(srctree)/scripts/adjust_autoksyms.sh \ - "$(MAKE) KBUILD_MODULES=1 -f $(srctree)/Makefile vmlinux_prereq" + "$(MAKE) -f $(srctree)/Makefile vmlinux" endif # standalone target for easier testing From 20ab67a563f5299c09a234164c372aba5a59add8 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Dec 2016 17:26:45 -0800 Subject: [PATCH 161/174] mm: workingset: fix NULL ptr in count_shadow_nodes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 0a6b76dd23fa ("mm: workingset: make shadow node shrinker memcg aware") has made the workingset shadow nodes shrinker memcg aware. The implementation is not correct though because memcg_kmem_enabled() might become true while we are doing a global reclaim when the sc->memcg might be NULL which is exactly what Marek has seen: BUG: unable to handle kernel NULL pointer dereference at 0000000000000400 IP: [] mem_cgroup_node_nr_lru_pages+0x20/0x40 PGD 0 Oops: 0000 [#1] SMP CPU: 0 PID: 60 Comm: kswapd0 Tainted: G O 4.8.10-12.pvops.qubes.x86_64 #1 task: ffff880011863b00 task.stack: ffff880011868000 RIP: mem_cgroup_node_nr_lru_pages+0x20/0x40 RSP: e02b:ffff88001186bc70 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff88001186bd20 RCX: 0000000000000002 RDX: 000000000000000c RSI: 0000000000000000 RDI: 0000000000000000 RBP: ffff88001186bc70 R08: 28f5c28f5c28f5c3 R09: 0000000000000000 R10: 0000000000006c34 R11: 0000000000000333 R12: 00000000000001f6 R13: ffffffff81c6f6a0 R14: 0000000000000000 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff880013c00000(0000) knlGS:ffff880013d00000 CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000400 CR3: 00000000122f2000 CR4: 0000000000042660 Call Trace: count_shadow_nodes+0x9a/0xa0 shrink_slab.part.42+0x119/0x3e0 shrink_node+0x22c/0x320 kswapd+0x32c/0x700 kthread+0xd8/0xf0 ret_from_fork+0x1f/0x40 Code: 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 3b 35 dd eb b1 00 55 48 89 e5 73 2c 89 d2 31 c9 31 c0 4c 63 ce 48 0f a3 ca 73 13 <4a> 8b b4 cf 00 04 00 00 41 89 c8 4a 03 84 c6 80 00 00 00 83 c1 RIP mem_cgroup_node_nr_lru_pages+0x20/0x40 RSP CR2: 0000000000000400 ---[ end trace 100494b9edbdfc4d ]--- This patch fixes the issue by checking sc->memcg rather than memcg_kmem_enabled() which is sufficient because shrink_slab makes sure that only memcg aware shrinkers will get non-NULL memcgs and only if memcg_kmem_enabled is true. Fixes: 0a6b76dd23fa ("mm: workingset: make shadow node shrinker memcg aware") Link: http://lkml.kernel.org/r/20161201132156.21450-1-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Marek Marczykowski-Górecki Tested-by: Marek Marczykowski-Górecki Acked-by: Vladimir Davydov Acked-by: Johannes Weiner Acked-by: Balbir Singh Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/workingset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/workingset.c b/mm/workingset.c index 617475f529f4..fb1f9183d89a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -348,7 +348,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); local_irq_enable(); - if (memcg_kmem_enabled()) { + if (sc->memcg) { pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, LRU_ALL_FILE); } else { From bd041733c9f612b66c519e5a8b1a98b05b94ed24 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Dec 2016 17:26:48 -0800 Subject: [PATCH 162/174] mm, vmscan: add cond_resched() into shrink_node_memcg() Boris Zhmurov has reported RCU stalls during the kswapd reclaim: INFO: rcu_sched detected stalls on CPUs/tasks: 23-...: (22 ticks this GP) idle=92f/140000000000000/0 softirq=2638404/2638404 fqs=23 (detected by 4, t=6389 jiffies, g=786259, c=786258, q=42115) Task dump for CPU 23: kswapd1 R running task 0 148 2 0x00000008 Call Trace: shrink_node+0xd2/0x2f0 kswapd+0x2cb/0x6a0 mem_cgroup_shrink_node+0x160/0x160 kthread+0xbd/0xe0 __switch_to+0x1fa/0x5c0 ret_from_fork+0x1f/0x40 kthread_create_on_node+0x180/0x180 a closer code inspection has shown that we might indeed miss all the scheduling points in the reclaim path if no pages can be isolated from the LRU list. This is a pathological case but other reports from Donald Buczek have shown that we might indeed hit such a path: clusterd-989 [009] .... 118023.654491: mm_vmscan_direct_reclaim_end: nr_reclaimed=193 kswapd1-86 [001] dN.. 118023.987475: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239830 nr_taken=0 file=1 kswapd1-86 [001] dN.. 118024.320968: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239844 nr_taken=0 file=1 kswapd1-86 [001] dN.. 118024.654375: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239858 nr_taken=0 file=1 kswapd1-86 [001] dN.. 118024.987036: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239872 nr_taken=0 file=1 kswapd1-86 [001] dN.. 118025.319651: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239886 nr_taken=0 file=1 kswapd1-86 [001] dN.. 118025.652248: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239900 nr_taken=0 file=1 kswapd1-86 [001] dN.. 118025.984870: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4239914 nr_taken=0 file=1 [...] kswapd1-86 [001] dN.. 118084.274403: mm_vmscan_lru_isolate: isolate_mode=0 classzone=0 order=0 nr_requested=32 nr_scanned=4241133 nr_taken=0 file=1 this is minute long snapshot which didn't take a single page from the LRU. It is not entirely clear why only 1303 pages have been scanned during that time (maybe there was a heavy IRQ activity interfering). In any case it looks like we can really hit long periods without scheduling on non preemptive kernels so an explicit cond_resched() in shrink_node_memcg which is independent on the reclaim operation is due. Link: http://lkml.kernel.org/r/20161202095841.16648-1-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Boris Zhmurov Tested-by: Boris Zhmurov Reported-by: Donald Buczek Reported-by: "Christopher S. Aker" Reported-by: Paul Menzel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/vmscan.c b/mm/vmscan.c index 76fda2268148..d75cdf360730 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2354,6 +2354,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc } } + cond_resched(); + if (nr_reclaimed < nr_to_reclaim || scan_adjusted) continue; From 3e5de27e940d00d8d504dfb96625fb654f641509 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 4 Dec 2016 12:50:51 -0800 Subject: [PATCH 163/174] Linux 4.9-rc8 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index b816089e5dc9..369099dc0fae 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* From a76b5b04375f974579c83433b06466758c0c552c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Dec 2016 16:17:19 -0800 Subject: [PATCH 164/174] fs: try to clone files first in vfs_copy_file_range A clone is a perfectly fine implementation of a file copy, so most file systems just implement the copy that way. Instead of duplicating this logic move it to the VFS. Currently btrfs and XFS implement copies the same way as clones and there is no behavior change for them, cifs only implements clones and grow support for copy_file_range with this patch. NFS implements both, so this will allow copy_file_range to work on servers that only implement CLONE and be lot more efficient on servers that implements CLONE and COPY. Signed-off-by: Christoph Hellwig --- fs/btrfs/ctree.h | 3 --- fs/btrfs/file.c | 1 - fs/btrfs/ioctl.c | 12 ------------ fs/read_write.c | 27 ++++++++++++++++++++++----- fs/xfs/xfs_file.c | 19 ------------------- 5 files changed, 22 insertions(+), 40 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0b8ce2b9f7d0..05f75a949af4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3232,9 +3232,6 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); -ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags); int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 3a14c87d9c92..991cc991fd29 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2998,7 +2998,6 @@ const struct file_operations btrfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_compat_ioctl, #endif - .copy_file_range = btrfs_copy_file_range, .clone_file_range = btrfs_clone_file_range, .dedupe_file_range = btrfs_dedupe_file_range, }; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7acbd2cf6192..dab746298758 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3980,18 +3980,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, return ret; } -ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags) -{ - ssize_t ret; - - ret = btrfs_clone_files(file_out, file_in, pos_in, len, pos_out); - if (ret == 0) - ret = len; - return ret; -} - int btrfs_clone_file_range(struct file *src_file, loff_t off, struct file *dst_file, loff_t destoff, u64 len) { diff --git a/fs/read_write.c b/fs/read_write.c index 190e0d362581..6674a4b83c54 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1542,20 +1542,37 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (ret) return ret; - ret = -EOPNOTSUPP; - if (file_out->f_op->copy_file_range) + /* + * Try cloning first, this is supported by more file systems, and + * more efficient if both clone and copy are supported (e.g. NFS). + */ + if (file_in->f_op->clone_file_range) { + ret = file_in->f_op->clone_file_range(file_in, pos_in, + file_out, pos_out, len); + if (ret == 0) { + ret = len; + goto done; + } + } + + if (file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); - if (ret == -EOPNOTSUPP) - ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, - len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); + if (ret != -EOPNOTSUPP) + goto done; + } + ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, + len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); + +done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } + inc_syscr(current); inc_syscw(current); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 6e4f7f900fea..86ecc9b49e15 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -909,24 +909,6 @@ xfs_file_fallocate( return error; } -STATIC ssize_t -xfs_file_copy_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - size_t len, - unsigned int flags) -{ - int error; - - error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, false); - if (error) - return error; - return len; -} - STATIC int xfs_file_clone_range( struct file *file_in, @@ -1625,7 +1607,6 @@ const struct file_operations xfs_file_operations = { .fsync = xfs_file_fsync, .get_unmapped_area = thp_get_unmapped_area, .fallocate = xfs_file_fallocate, - .copy_file_range = xfs_file_copy_range, .clone_file_range = xfs_file_clone_range, .dedupe_file_range = xfs_file_dedupe_range, }; From 876bec6f9bbfcb394916d17e35226b086c04dc45 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 9 Dec 2016 16:18:30 -0800 Subject: [PATCH 165/174] vfs: refactor clone/dedupe_file_range common functions Hoist both the XFS reflink inode state and preparation code and the XFS file blocks compare functions into the VFS so that ocfs2 can take advantage of it for reflink and dedupe. Signed-off-by: Darrick J. Wong --- fs/read_write.c | 204 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_reflink.c | 213 ++----------------------------------------- include/linux/fs.h | 6 ++ 3 files changed, 219 insertions(+), 204 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index 6674a4b83c54..dbf3f7ffdf3f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1667,6 +1667,114 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) return security_file_permission(file, write ? MAY_WRITE : MAY_READ); } +/* + * Check that the two inodes are eligible for cloning, the ranges make + * sense, and then flush all dirty data. Caller must ensure that the + * inodes have been locked against any other modifications. + */ +int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, + struct inode *inode_out, loff_t pos_out, + u64 *len, bool is_dedupe) +{ + loff_t bs = inode_out->i_sb->s_blocksize; + loff_t blen; + loff_t isize; + bool same_inode = (inode_in == inode_out); + int ret; + + /* Don't touch certain kinds of inodes */ + if (IS_IMMUTABLE(inode_out)) + return -EPERM; + + if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) + return -ETXTBSY; + + /* Don't reflink dirs, pipes, sockets... */ + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + return -EISDIR; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + return -EINVAL; + + /* Are we going all the way to the end? */ + isize = i_size_read(inode_in); + if (isize == 0) { + *len = 0; + return 0; + } + + /* Zero length dedupe exits immediately; reflink goes to EOF. */ + if (*len == 0) { + if (is_dedupe) { + *len = 0; + return 0; + } + *len = isize - pos_in; + } + + /* Ensure offsets don't wrap and the input is inside i_size */ + if (pos_in + *len < pos_in || pos_out + *len < pos_out || + pos_in + *len > isize) + return -EINVAL; + + /* Don't allow dedupe past EOF in the dest file */ + if (is_dedupe) { + loff_t disize; + + disize = i_size_read(inode_out); + if (pos_out >= disize || pos_out + *len > disize) + return -EINVAL; + } + + /* If we're linking to EOF, continue to the block boundary. */ + if (pos_in + *len == isize) + blen = ALIGN(isize, bs) - pos_in; + else + blen = *len; + + /* Only reflink if we're aligned to block boundaries */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || + !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) + return -EINVAL; + + /* Don't allow overlapped reflink within the same file */ + if (same_inode) { + if (pos_out + blen > pos_in && pos_out < pos_in + blen) + return -EINVAL; + } + + /* Wait for the completion of any pending IOs on both files */ + inode_dio_wait(inode_in); + if (!same_inode) + inode_dio_wait(inode_out); + + ret = filemap_write_and_wait_range(inode_in->i_mapping, + pos_in, pos_in + *len - 1); + if (ret) + return ret; + + ret = filemap_write_and_wait_range(inode_out->i_mapping, + pos_out, pos_out + *len - 1); + if (ret) + return ret; + + /* + * Check that the extents are the same. + */ + if (is_dedupe) { + bool is_same = false; + + ret = vfs_dedupe_file_range_compare(inode_in, pos_in, + inode_out, pos_out, *len, &is_same); + if (ret) + return ret; + if (!is_same) + return -EBADE; + } + + return 0; +} +EXPORT_SYMBOL(vfs_clone_file_prep_inodes); + int vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len) { @@ -1718,6 +1826,102 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(vfs_clone_file_range); +/* + * Read a page's worth of file data into the page cache. Return the page + * locked. + */ +static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) +{ + struct address_space *mapping; + struct page *page; + pgoff_t n; + + n = offset >> PAGE_SHIFT; + mapping = inode->i_mapping; + page = read_mapping_page(mapping, n, NULL); + if (IS_ERR(page)) + return page; + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-EIO); + } + lock_page(page); + return page; +} + +/* + * Compare extents of two files to see if they are the same. + * Caller must have locked both inodes to prevent write races. + */ +int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same) +{ + loff_t src_poff; + loff_t dest_poff; + void *src_addr; + void *dest_addr; + struct page *src_page; + struct page *dest_page; + loff_t cmp_len; + bool same; + int error; + + error = -EINVAL; + same = true; + while (len) { + src_poff = srcoff & (PAGE_SIZE - 1); + dest_poff = destoff & (PAGE_SIZE - 1); + cmp_len = min(PAGE_SIZE - src_poff, + PAGE_SIZE - dest_poff); + cmp_len = min(cmp_len, len); + if (cmp_len <= 0) + goto out_error; + + src_page = vfs_dedupe_get_page(src, srcoff); + if (IS_ERR(src_page)) { + error = PTR_ERR(src_page); + goto out_error; + } + dest_page = vfs_dedupe_get_page(dest, destoff); + if (IS_ERR(dest_page)) { + error = PTR_ERR(dest_page); + unlock_page(src_page); + put_page(src_page); + goto out_error; + } + src_addr = kmap_atomic(src_page); + dest_addr = kmap_atomic(dest_page); + + flush_dcache_page(src_page); + flush_dcache_page(dest_page); + + if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) + same = false; + + kunmap_atomic(dest_addr); + kunmap_atomic(src_addr); + unlock_page(dest_page); + unlock_page(src_page); + put_page(dest_page); + put_page(src_page); + + if (!same) + break; + + srcoff += cmp_len; + destoff += cmp_len; + len -= cmp_len; + } + + *is_same = same; + return 0; + +out_error: + return error; +} +EXPORT_SYMBOL(vfs_dedupe_file_range_compare); + int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) { struct file_dedupe_range_info *info; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index a279b4e7f5fe..95d6828967f0 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1164,111 +1164,6 @@ xfs_reflink_remap_blocks( return error; } -/* - * Read a page's worth of file data into the page cache. Return the page - * locked. - */ -static struct page * -xfs_get_page( - struct inode *inode, - xfs_off_t offset) -{ - struct address_space *mapping; - struct page *page; - pgoff_t n; - - n = offset >> PAGE_SHIFT; - mapping = inode->i_mapping; - page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) - return page; - if (!PageUptodate(page)) { - put_page(page); - return ERR_PTR(-EIO); - } - lock_page(page); - return page; -} - -/* - * Compare extents of two files to see if they are the same. - */ -static int -xfs_compare_extents( - struct inode *src, - xfs_off_t srcoff, - struct inode *dest, - xfs_off_t destoff, - xfs_off_t len, - bool *is_same) -{ - xfs_off_t src_poff; - xfs_off_t dest_poff; - void *src_addr; - void *dest_addr; - struct page *src_page; - struct page *dest_page; - xfs_off_t cmp_len; - bool same; - int error; - - error = -EINVAL; - same = true; - while (len) { - src_poff = srcoff & (PAGE_SIZE - 1); - dest_poff = destoff & (PAGE_SIZE - 1); - cmp_len = min(PAGE_SIZE - src_poff, - PAGE_SIZE - dest_poff); - cmp_len = min(cmp_len, len); - ASSERT(cmp_len > 0); - - trace_xfs_reflink_compare_extents(XFS_I(src), srcoff, cmp_len, - XFS_I(dest), destoff); - - src_page = xfs_get_page(src, srcoff); - if (IS_ERR(src_page)) { - error = PTR_ERR(src_page); - goto out_error; - } - dest_page = xfs_get_page(dest, destoff); - if (IS_ERR(dest_page)) { - error = PTR_ERR(dest_page); - unlock_page(src_page); - put_page(src_page); - goto out_error; - } - src_addr = kmap_atomic(src_page); - dest_addr = kmap_atomic(dest_page); - - flush_dcache_page(src_page); - flush_dcache_page(dest_page); - - if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) - same = false; - - kunmap_atomic(dest_addr); - kunmap_atomic(src_addr); - unlock_page(dest_page); - unlock_page(src_page); - put_page(dest_page); - put_page(src_page); - - if (!same) - break; - - srcoff += cmp_len; - destoff += cmp_len; - len -= cmp_len; - } - - *is_same = same; - return 0; - -out_error: - trace_xfs_reflink_compare_extents_error(XFS_I(dest), error, _RET_IP_); - return error; -} - /* * Link a range of blocks from one file to another. */ @@ -1286,14 +1181,11 @@ xfs_reflink_remap_range( struct inode *inode_out = file_inode(file_out); struct xfs_inode *dest = XFS_I(inode_out); struct xfs_mount *mp = src->i_mount; - loff_t bs = inode_out->i_sb->s_blocksize; bool same_inode = (inode_in == inode_out); xfs_fileoff_t sfsbno, dfsbno; xfs_filblks_t fsblen; xfs_extlen_t cowextsize; - loff_t isize; ssize_t ret; - loff_t blen; if (!xfs_sb_version_hasreflink(&mp->m_sb)) return -EOPNOTSUPP; @@ -1310,26 +1202,8 @@ xfs_reflink_remap_range( xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL); } - /* Don't touch certain kinds of inodes */ - ret = -EPERM; - if (IS_IMMUTABLE(inode_out)) - goto out_unlock; - - ret = -ETXTBSY; - if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) - goto out_unlock; - - - /* Don't reflink dirs, pipes, sockets... */ - ret = -EISDIR; - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - goto out_unlock; + /* Check file eligibility and prepare for block sharing. */ ret = -EINVAL; - if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) - goto out_unlock; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - goto out_unlock; - /* Don't reflink realtime inodes */ if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) goto out_unlock; @@ -1338,91 +1212,18 @@ xfs_reflink_remap_range( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - /* Are we going all the way to the end? */ - isize = i_size_read(inode_in); - if (isize == 0) { - ret = 0; - goto out_unlock; - } - - if (len == 0) - len = isize - pos_in; - - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + len < pos_in || pos_out + len < pos_out || - pos_in + len > isize) - goto out_unlock; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + len > disize) - goto out_unlock; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - goto out_unlock; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode) { - if (pos_out + blen > pos_in && pos_out < pos_in + blen) - goto out_unlock; - } - - /* Wait for the completion of any pending IOs on both files */ - inode_dio_wait(inode_in); - if (!same_inode) - inode_dio_wait(inode_out); - - ret = filemap_write_and_wait_range(inode_in->i_mapping, - pos_in, pos_in + len - 1); - if (ret) - goto out_unlock; - - ret = filemap_write_and_wait_range(inode_out->i_mapping, - pos_out, pos_out + len - 1); - if (ret) + ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + &len, is_dedupe); + if (ret || len == 0) goto out_unlock; trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); - /* - * Check that the extents are the same. - */ - if (is_dedupe) { - bool is_same = false; - - ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out, - len, &is_same); - if (ret) - goto out_unlock; - if (!is_same) { - ret = -EBADE; - goto out_unlock; - } - } - + /* Set flags and remap blocks. */ ret = xfs_reflink_set_inode_flag(src, dest); if (ret) goto out_unlock; - /* - * Invalidate the page cache so that we can clear any CoW mappings - * in the destination file. - */ - truncate_inode_pages_range(&inode_out->i_data, pos_out, - PAGE_ALIGN(pos_out + len) - 1); - dfsbno = XFS_B_TO_FSBT(mp, pos_out); sfsbno = XFS_B_TO_FSBT(mp, pos_in); fsblen = XFS_B_TO_FSB(mp, len); @@ -1431,6 +1232,10 @@ xfs_reflink_remap_range( if (ret) goto out_unlock; + /* Zap any page cache for the destination file's range. */ + truncate_inode_pages_range(&inode_out->i_data, pos_out, + PAGE_ALIGN(pos_out + len) - 1); + /* * Carry the cowextsize hint from src to dest if we're sharing the * entire source file to the entire destination file, the source file diff --git a/include/linux/fs.h b/include/linux/fs.h index dc0478c07b2a..caea736fa09c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1778,8 +1778,14 @@ extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *, int); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); +extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, + struct inode *inode_out, loff_t pos_out, + u64 *len, bool is_dedupe); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); +extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); From 84e40080bd6f363ddbcab75b04cb7bc742efbf12 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Nov 2016 14:13:09 -0800 Subject: [PATCH 166/174] ocfs2: convert inode refcount test to a helper Replace the open-coded inode refcount flag test with a helper function to reduce the potential for bugs. Signed-off-by: Darrick J. Wong --- fs/ocfs2/alloc.c | 3 +-- fs/ocfs2/file.c | 7 +++---- fs/ocfs2/inode.h | 6 ++++++ fs/ocfs2/move_extents.c | 10 ++-------- fs/ocfs2/refcounttree.c | 22 +++++++++------------- fs/ocfs2/xattr.c | 4 ++-- 6 files changed, 23 insertions(+), 29 deletions(-) diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index f72712f6c28d..a0ca49f09880 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5713,8 +5713,7 @@ int ocfs2_remove_btree_range(struct inode *inode, struct ocfs2_refcount_tree *ref_tree = NULL; if ((flags & OCFS2_EXT_REFCOUNTED) && len) { - BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & - OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!ocfs2_is_refcount_inode(inode)); if (!refcount_tree_locked) { ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 000c234d7bbd..d261f3a91870 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1030,7 +1030,7 @@ int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, * Only quota files call this without a bh, and they can't be * refcounted. */ - BUG_ON(!di_bh && (oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!di_bh && ocfs2_is_refcount_inode(inode)); BUG_ON(!di_bh && !(oi->ip_flags & OCFS2_INODE_SYSTEM_FILE)); clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size); @@ -1719,8 +1719,7 @@ static int ocfs2_remove_inode_range(struct inode *inode, * within one cluster(means is not exactly aligned to clustersize). */ - if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL) { - + if (ocfs2_is_refcount_inode(inode)) { ret = ocfs2_cow_file_pos(inode, di_bh, byte_start); if (ret) { mlog_errno(ret); @@ -2036,7 +2035,7 @@ int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos, struct super_block *sb = inode->i_sb; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)) || - !(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL) || + !ocfs2_is_refcount_inode(inode) || OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 5af68fcdf9d3..9b955f732bca 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -181,4 +181,10 @@ static inline struct ocfs2_inode_info *cache_info_to_inode(struct ocfs2_caching_ return container_of(ci, struct ocfs2_inode_info, ip_metadata_cache); } +/* Does this inode have the reflink flag set? */ +static inline bool ocfs2_is_refcount_inode(struct inode *inode) +{ + return (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL); +} + #endif /* OCFS2_INODE_H */ diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 4e8f32eb0bdb..e52a2852d50d 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -235,10 +235,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) { - - BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & - OCFS2_HAS_REFCOUNT_FL)); - + BUG_ON(!ocfs2_is_refcount_inode(inode)); BUG_ON(!context->refcount_loc); ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1, @@ -581,10 +578,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) { - - BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & - OCFS2_HAS_REFCOUNT_FL)); - + BUG_ON(!ocfs2_is_refcount_inode(inode)); BUG_ON(!context->refcount_loc); ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1, diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 19238512a324..3410eb105b0d 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -410,7 +410,7 @@ static int ocfs2_get_refcount_block(struct inode *inode, u64 *ref_blkno) goto out; } - BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!ocfs2_is_refcount_inode(inode)); di = (struct ocfs2_dinode *)di_bh->b_data; *ref_blkno = le64_to_cpu(di->i_refcount_loc); @@ -570,7 +570,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode, u32 num_got; u64 suballoc_loc, first_blkno; - BUG_ON(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL); + BUG_ON(ocfs2_is_refcount_inode(inode)); trace_ocfs2_create_refcount_tree( (unsigned long long)OCFS2_I(inode)->ip_blkno); @@ -708,7 +708,7 @@ static int ocfs2_set_refcount_tree(struct inode *inode, struct ocfs2_refcount_block *rb; struct ocfs2_refcount_tree *ref_tree; - BUG_ON(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL); + BUG_ON(ocfs2_is_refcount_inode(inode)); ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1, &ref_tree, &ref_root_bh); @@ -775,7 +775,7 @@ int ocfs2_remove_refcount_tree(struct inode *inode, struct buffer_head *di_bh) u64 blk = 0, bg_blkno = 0, ref_blkno = le64_to_cpu(di->i_refcount_loc); u16 bit = 0; - if (!(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)) + if (!ocfs2_is_refcount_inode(inode)) return 0; BUG_ON(!ref_blkno); @@ -2299,11 +2299,10 @@ int ocfs2_decrease_refcount(struct inode *inode, { int ret; u64 ref_blkno; - struct ocfs2_inode_info *oi = OCFS2_I(inode); struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *tree; - BUG_ON(!(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_get_refcount_block(inode, &ref_blkno); if (ret) { @@ -2533,7 +2532,6 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode, int *ref_blocks) { int ret; - struct ocfs2_inode_info *oi = OCFS2_I(inode); struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *tree; u64 start_cpos = ocfs2_blocks_to_clusters(inode->i_sb, phys_blkno); @@ -2544,7 +2542,7 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode, goto out; } - BUG_ON(!(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_get_refcount_tree(OCFS2_SB(inode->i_sb), refcount_loc, &tree); @@ -3412,14 +3410,13 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode, { int ret; u32 cow_start = 0, cow_len = 0; - struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *ref_tree; struct ocfs2_cow_context *context = NULL; - BUG_ON(!(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_refcount_cal_cow_clusters(inode, &di->id2.i_list, cpos, write_len, max_cpos, @@ -3629,11 +3626,10 @@ int ocfs2_refcount_cow_xattr(struct inode *inode, { int ret; struct ocfs2_xattr_value_root *xv = vb->vb_xv; - struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_cow_context *context = NULL; u32 cow_start, cow_len; - BUG_ON(!(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)); + BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_refcount_cal_cow_clusters(inode, &xv->xr_list, cpos, write_len, UINT_MAX, @@ -3807,7 +3803,7 @@ static int ocfs2_attach_refcount_tree(struct inode *inode, ocfs2_init_dealloc_ctxt(&dealloc); - if (!(oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL)) { + if (!ocfs2_is_refcount_inode(inode)) { ret = ocfs2_create_refcount_tree(inode, di_bh); if (ret) { mlog_errno(ret); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index cb157a34a656..3c5384d9b3a5 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -2577,7 +2577,7 @@ int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh) if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL)) return 0; - if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL) { + if (ocfs2_is_refcount_inode(inode)) { ret = ocfs2_lock_refcount_tree(OCFS2_SB(inode->i_sb), le64_to_cpu(di->i_refcount_loc), 1, &ref_tree, &ref_root_bh); @@ -3608,7 +3608,7 @@ int ocfs2_xattr_set(struct inode *inode, } /* Check whether the value is refcounted and do some preparation. */ - if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL && + if (ocfs2_is_refcount_inode(inode) && (!xis.not_found || !xbs.not_found)) { ret = ocfs2_prepare_refcount_xattr(inode, di, &xi, &xis, &xbs, &ref_tree, From 86544fbd853c49a9eccb3d0f4e7eb9317f3fccf9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Nov 2016 14:13:09 -0800 Subject: [PATCH 167/174] ocfs2: add newlines to some error messages These two error messages are missing the trailing newline. Signed-off-by: Darrick J. Wong --- fs/ocfs2/alloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index a0ca49f09880..d4ec0d8961a6 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -5194,7 +5194,7 @@ int ocfs2_change_extent_flag(handle_t *handle, rec = &el->l_recs[index]; if (new_flags && (rec->e_flags & new_flags)) { mlog(ML_ERROR, "Owner %llu tried to set %d flags on an " - "extent that already had them", + "extent that already had them\n", (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci), new_flags); goto out; @@ -5202,7 +5202,7 @@ int ocfs2_change_extent_flag(handle_t *handle, if (clear_flags && !(rec->e_flags & clear_flags)) { mlog(ML_ERROR, "Owner %llu tried to clear %d flags on an " - "extent that didn't have them", + "extent that didn't have them\n", (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci), clear_flags); goto out; From 06a70305812c3973c66824f26223656283c59b27 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Nov 2016 14:13:10 -0800 Subject: [PATCH 168/174] ocfs2: prohibit refcounted swapfiles The swapfile mechanism calls bmap once to find all the swap file mappings, which means that we cannot properly support CoW remapping. Therefore, error out if the swap code tries to call bmap on a refcounted file. Signed-off-by: Darrick J. Wong --- fs/ocfs2/aops.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index c5c5b9748ea3..4d037db84be5 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -464,6 +464,15 @@ static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block) trace_ocfs2_bmap((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)block); + /* + * The swap code (ab-)uses ->bmap to get a block mapping and then + * bypasseѕ the file system for actual I/O. We really can't allow + * that on refcounted inodes, so we have to skip out here. And yes, + * 0 is the magic code for a bmap error.. + */ + if (ocfs2_is_refcount_inode(inode)) + return 0; + /* We don't need to lock journal system files, since they aren't * accessed concurrently from multiple nodes. */ From 3e10b793fc40dfdbe51762e0d084bd6f2c8acaaa Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Nov 2016 14:13:11 -0800 Subject: [PATCH 169/174] ocfs2: budget for extent tree splits when adding refcount flag When we're adding the refcount flag to an extent, we have to budget enough space to handle a full extent btree split in addition to whatever modifications have to be made to the refcount btree. We don't currently do this, with the result that generic/186 crashes when we need an extent split but not a refcount split because meta_ac never gets allocated. Signed-off-by: Darrick J. Wong --- fs/ocfs2/refcounttree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 3410eb105b0d..6c98d567ba01 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3692,6 +3692,9 @@ int ocfs2_add_refcount_flag(struct inode *inode, struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_alloc_context *meta_ac = NULL; + /* We need to be able to handle at least an extent tree split. */ + ref_blocks = ocfs2_extend_meta_needed(data_et->et_root_el); + ret = ocfs2_calc_refcount_meta_credits(inode->i_sb, ref_ci, ref_root_bh, p_cluster, num_clusters, From 085549553dca86c866f26d233d9cfe19f169c288 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Nov 2016 14:42:49 -0800 Subject: [PATCH 170/174] ocfs2: don't eat io errors during _dio_end_io_write ocfs2_dio_end_io_write eats whatever errors may happen, which means that write errors do not propagate to userspace. Fix that. Signed-off-by: Darrick J. Wong --- fs/ocfs2/aops.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 4d037db84be5..136a49cabc12 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2263,10 +2263,10 @@ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock, return ret; } -static void ocfs2_dio_end_io_write(struct inode *inode, - struct ocfs2_dio_write_ctxt *dwc, - loff_t offset, - ssize_t bytes) +static int ocfs2_dio_end_io_write(struct inode *inode, + struct ocfs2_dio_write_ctxt *dwc, + loff_t offset, + ssize_t bytes) { struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_extent_tree et; @@ -2374,6 +2374,8 @@ static void ocfs2_dio_end_io_write(struct inode *inode, if (locked) inode_unlock(inode); ocfs2_dio_free_write_ctx(inode, dwc); + + return ret; } /* @@ -2388,6 +2390,7 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, { struct inode *inode = file_inode(iocb->ki_filp); int level; + int ret = 0; if (bytes <= 0) return 0; @@ -2396,13 +2399,13 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); if (private) - ocfs2_dio_end_io_write(inode, private, offset, bytes); + ret = ocfs2_dio_end_io_write(inode, private, offset, bytes); ocfs2_iocb_clear_rw_locked(iocb); level = ocfs2_iocb_rw_locked_level(iocb); ocfs2_rw_unlock(inode, level); - return 0; + return ret; } static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) From dbf896fc286a62bf215b904c6ff5d197df93e685 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Thu, 1 Dec 2016 16:31:14 -0800 Subject: [PATCH 171/174] ocfs2: always unlock when completing dio writes Always unlock the inode when completing dio writes, even if an error has occurrred. The caller already checks the inode and unlocks it if needed, so we might as well reduce contention. Signed-off-by: Darrick J. Wong --- fs/ocfs2/aops.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 136a49cabc12..3c531f108a21 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2392,13 +2392,10 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, int level; int ret = 0; - if (bytes <= 0) - return 0; - /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); - if (private) + if (bytes > 0 && private) ret = ocfs2_dio_end_io_write(inode, private, offset, bytes); ocfs2_iocb_clear_rw_locked(iocb); From aef73a61c01a4dca3f26c22df05039f78fe9d468 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 9 Dec 2016 16:10:15 -0800 Subject: [PATCH 172/174] ocfs2: fix bad pointer cast generic/188 triggered a dmesg stack trace because the dio completion was casting a buffer head to an on-disk inode, which is whacky. Signed-off-by: Darrick J. Wong --- fs/ocfs2/aops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 3c531f108a21..3372d82d12b6 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2317,7 +2317,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode, mlog_errno(ret); } - di = (struct ocfs2_dinode *)di_bh; + di = (struct ocfs2_dinode *)di_bh->b_data; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh); From 86e59436d406d833a5da4a94aefb3c3be6b26053 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 22 Nov 2016 13:40:27 -0800 Subject: [PATCH 173/174] ocfs2: charge quota for reflinked blocks When ocfs2 shares blocks from one file to another, it's necessary to charge that many blocks to the quota because ocfs2 tallies block charges according to the number of blocks mapped, not the number of physical blocks used. Without this patch, reflinking X blocks and then CoWing all of them causes quota usage to *decrease* by X as seen in generic/305. Signed-off-by: Darrick J. Wong --- fs/ocfs2/refcounttree.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 6c98d567ba01..dc8089af9ddf 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -3933,6 +3933,13 @@ static int ocfs2_add_refcounted_extent(struct inode *inode, ret = ocfs2_increase_refcount(handle, ref_ci, ref_root_bh, p_cluster, num_clusters, meta_ac, dealloc); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + + ret = dquot_alloc_space_nodirty(inode, + ocfs2_clusters_to_bytes(osb->sb, num_clusters)); if (ret) mlog_errno(ret); From 29ac8e856cb3694e004037de595dec4ec53d42f2 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 9 Nov 2016 14:13:11 -0800 Subject: [PATCH 174/174] ocfs2: implement the VFS clone_range, copy_range, and dedupe_range features Connect the new VFS clone_range, copy_range, and dedupe_range features to the existing reflink capability of ocfs2. Compared to the existing ocfs2 reflink ioctl We have to do things a little differently to support the VFS semantics (we can clone subranges of a file but we don't clone xattrs), but the VFS ioctls are more broadly supported. Signed-off-by: Darrick J. Wong --- v2: Convert inline data files to extents files before reflinking, and fix i_blocks so that stat(2) output is correct. v3: Make zero-length dedupe consistent with btrfs behavior. v4: Use VFS double-inode lock routines and remove MAX_DEDUPE_LEN. --- fs/ocfs2/file.c | 35 +++- fs/ocfs2/file.h | 3 + fs/ocfs2/refcounttree.c | 432 ++++++++++++++++++++++++++++++++++++++++ fs/ocfs2/refcounttree.h | 7 + 4 files changed, 474 insertions(+), 3 deletions(-) diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d261f3a91870..c4889655d32b 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1667,9 +1667,9 @@ static void ocfs2_calc_trunc_pos(struct inode *inode, *done = ret; } -static int ocfs2_remove_inode_range(struct inode *inode, - struct buffer_head *di_bh, u64 byte_start, - u64 byte_len) +int ocfs2_remove_inode_range(struct inode *inode, + struct buffer_head *di_bh, u64 byte_start, + u64 byte_len) { int ret = 0, flags = 0, done = 0, i; u32 trunc_start, trunc_len, trunc_end, trunc_cpos, phys_cpos; @@ -2439,6 +2439,31 @@ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence) return offset; } +static int ocfs2_file_clone_range(struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len) +{ + return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, + len, false); +} + +static ssize_t ocfs2_file_dedupe_range(struct file *src_file, + u64 loff, + u64 len, + struct file *dst_file, + u64 dst_loff) +{ + int error; + + error = ocfs2_reflink_remap_range(src_file, loff, dst_file, dst_loff, + len, true); + if (error) + return error; + return len; +} + const struct inode_operations ocfs2_file_iops = { .setattr = ocfs2_setattr, .getattr = ocfs2_getattr, @@ -2478,6 +2503,8 @@ const struct file_operations ocfs2_fops = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, + .clone_file_range = ocfs2_file_clone_range, + .dedupe_file_range = ocfs2_file_dedupe_range, }; const struct file_operations ocfs2_dops = { @@ -2523,6 +2550,8 @@ const struct file_operations ocfs2_fops_no_plocks = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, + .clone_file_range = ocfs2_file_clone_range, + .dedupe_file_range = ocfs2_file_dedupe_range, }; const struct file_operations ocfs2_dops_no_plocks = { diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index e8c62f22215c..897fd9a2e51d 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -82,4 +82,7 @@ int ocfs2_change_file_space(struct file *file, unsigned int cmd, int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos, size_t count); +int ocfs2_remove_inode_range(struct inode *inode, + struct buffer_head *di_bh, u64 byte_start, + u64 byte_len); #endif /* OCFS2_FILE_H */ diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index dc8089af9ddf..b18465e330b1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -34,6 +34,7 @@ #include "xattr.h" #include "namei.h" #include "ocfs2_trace.h" +#include "file.h" #include #include @@ -4448,3 +4449,434 @@ int ocfs2_reflink_ioctl(struct inode *inode, return error; } + +/* Update destination inode size, if necessary. */ +static int ocfs2_reflink_update_dest(struct inode *dest, + struct buffer_head *d_bh, + loff_t newlen) +{ + handle_t *handle; + int ret; + + dest->i_blocks = ocfs2_inode_sector_count(dest); + + if (newlen <= i_size_read(dest)) + return 0; + + handle = ocfs2_start_trans(OCFS2_SB(dest->i_sb), + OCFS2_INODE_UPDATE_CREDITS); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + mlog_errno(ret); + return ret; + } + + /* Extend i_size if needed. */ + spin_lock(&OCFS2_I(dest)->ip_lock); + if (newlen > i_size_read(dest)) + i_size_write(dest, newlen); + spin_unlock(&OCFS2_I(dest)->ip_lock); + dest->i_ctime = dest->i_mtime = current_time(dest); + + ret = ocfs2_mark_inode_dirty(handle, dest, d_bh); + if (ret) { + mlog_errno(ret); + goto out_commit; + } + +out_commit: + ocfs2_commit_trans(OCFS2_SB(dest->i_sb), handle); + return ret; +} + +/* Remap the range pos_in:len in s_inode to pos_out:len in t_inode. */ +static int ocfs2_reflink_remap_extent(struct inode *s_inode, + struct buffer_head *s_bh, + loff_t pos_in, + struct inode *t_inode, + struct buffer_head *t_bh, + loff_t pos_out, + loff_t len, + struct ocfs2_cached_dealloc_ctxt *dealloc) +{ + struct ocfs2_extent_tree s_et; + struct ocfs2_extent_tree t_et; + struct ocfs2_dinode *dis; + struct buffer_head *ref_root_bh = NULL; + struct ocfs2_refcount_tree *ref_tree; + struct ocfs2_super *osb; + loff_t pstart, plen; + u32 p_cluster, num_clusters, slast, spos, tpos; + unsigned int ext_flags; + int ret = 0; + + osb = OCFS2_SB(s_inode->i_sb); + dis = (struct ocfs2_dinode *)s_bh->b_data; + ocfs2_init_dinode_extent_tree(&s_et, INODE_CACHE(s_inode), s_bh); + ocfs2_init_dinode_extent_tree(&t_et, INODE_CACHE(t_inode), t_bh); + + spos = ocfs2_bytes_to_clusters(s_inode->i_sb, pos_in); + tpos = ocfs2_bytes_to_clusters(t_inode->i_sb, pos_out); + slast = ocfs2_clusters_for_bytes(s_inode->i_sb, pos_in + len); + + while (spos < slast) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } + + /* Look up the extent. */ + ret = ocfs2_get_clusters(s_inode, spos, &p_cluster, + &num_clusters, &ext_flags); + if (ret) { + mlog_errno(ret); + goto out; + } + + num_clusters = min_t(u32, num_clusters, slast - spos); + + /* Punch out the dest range. */ + pstart = ocfs2_clusters_to_bytes(t_inode->i_sb, tpos); + plen = ocfs2_clusters_to_bytes(t_inode->i_sb, num_clusters); + ret = ocfs2_remove_inode_range(t_inode, t_bh, pstart, plen); + if (ret) { + mlog_errno(ret); + goto out; + } + + if (p_cluster == 0) + goto next_loop; + + /* Lock the refcount btree... */ + ret = ocfs2_lock_refcount_tree(osb, + le64_to_cpu(dis->i_refcount_loc), + 1, &ref_tree, &ref_root_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + + /* Mark s_inode's extent as refcounted. */ + if (!(ext_flags & OCFS2_EXT_REFCOUNTED)) { + ret = ocfs2_add_refcount_flag(s_inode, &s_et, + &ref_tree->rf_ci, + ref_root_bh, spos, + p_cluster, num_clusters, + dealloc, NULL); + if (ret) { + mlog_errno(ret); + goto out_unlock_refcount; + } + } + + /* Map in the new extent. */ + ext_flags |= OCFS2_EXT_REFCOUNTED; + ret = ocfs2_add_refcounted_extent(t_inode, &t_et, + &ref_tree->rf_ci, + ref_root_bh, + tpos, p_cluster, + num_clusters, + ext_flags, + dealloc); + if (ret) { + mlog_errno(ret); + goto out_unlock_refcount; + } + + ocfs2_unlock_refcount_tree(osb, ref_tree, 1); + brelse(ref_root_bh); +next_loop: + spos += num_clusters; + tpos += num_clusters; + } + +out: + return ret; +out_unlock_refcount: + ocfs2_unlock_refcount_tree(osb, ref_tree, 1); + brelse(ref_root_bh); + return ret; +} + +/* Set up refcount tree and remap s_inode to t_inode. */ +static int ocfs2_reflink_remap_blocks(struct inode *s_inode, + struct buffer_head *s_bh, + loff_t pos_in, + struct inode *t_inode, + struct buffer_head *t_bh, + loff_t pos_out, + loff_t len) +{ + struct ocfs2_cached_dealloc_ctxt dealloc; + struct ocfs2_super *osb; + struct ocfs2_dinode *dis; + struct ocfs2_dinode *dit; + int ret; + + osb = OCFS2_SB(s_inode->i_sb); + dis = (struct ocfs2_dinode *)s_bh->b_data; + dit = (struct ocfs2_dinode *)t_bh->b_data; + ocfs2_init_dealloc_ctxt(&dealloc); + + /* + * If we're reflinking the entire file and the source is inline + * data, just copy the contents. + */ + if (pos_in == pos_out && pos_in == 0 && len == i_size_read(s_inode) && + i_size_read(t_inode) <= len && + (OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) { + ret = ocfs2_duplicate_inline_data(s_inode, s_bh, t_inode, t_bh); + if (ret) + mlog_errno(ret); + goto out; + } + + /* + * If both inodes belong to two different refcount groups then + * forget it because we don't know how (or want) to go merging + * refcount trees. + */ + ret = -EOPNOTSUPP; + if (ocfs2_is_refcount_inode(s_inode) && + ocfs2_is_refcount_inode(t_inode) && + le64_to_cpu(dis->i_refcount_loc) != + le64_to_cpu(dit->i_refcount_loc)) + goto out; + + /* Neither inode has a refcount tree. Add one to s_inode. */ + if (!ocfs2_is_refcount_inode(s_inode) && + !ocfs2_is_refcount_inode(t_inode)) { + ret = ocfs2_create_refcount_tree(s_inode, s_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + /* Ensure that both inodes end up with the same refcount tree. */ + if (!ocfs2_is_refcount_inode(s_inode)) { + ret = ocfs2_set_refcount_tree(s_inode, s_bh, + le64_to_cpu(dit->i_refcount_loc)); + if (ret) { + mlog_errno(ret); + goto out; + } + } + if (!ocfs2_is_refcount_inode(t_inode)) { + ret = ocfs2_set_refcount_tree(t_inode, t_bh, + le64_to_cpu(dis->i_refcount_loc)); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + /* Turn off inline data in the dest file. */ + if (OCFS2_I(t_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { + ret = ocfs2_convert_inline_data_to_extents(t_inode, t_bh); + if (ret) { + mlog_errno(ret); + goto out; + } + } + + /* Actually remap extents now. */ + ret = ocfs2_reflink_remap_extent(s_inode, s_bh, pos_in, t_inode, t_bh, + pos_out, len, &dealloc); + if (ret) { + mlog_errno(ret); + goto out; + } + +out: + if (ocfs2_dealloc_has_cluster(&dealloc)) { + ocfs2_schedule_truncate_log_flush(osb, 1); + ocfs2_run_deallocs(osb, &dealloc); + } + + return ret; +} + +/* Lock an inode and grab a bh pointing to the inode. */ +static int ocfs2_reflink_inodes_lock(struct inode *s_inode, + struct buffer_head **bh1, + struct inode *t_inode, + struct buffer_head **bh2) +{ + struct inode *inode1; + struct inode *inode2; + struct ocfs2_inode_info *oi1; + struct ocfs2_inode_info *oi2; + bool same_inode = (s_inode == t_inode); + int status; + + /* First grab the VFS and rw locks. */ + lock_two_nondirectories(s_inode, t_inode); + inode1 = s_inode; + inode2 = t_inode; + if (inode1->i_ino > inode2->i_ino) + swap(inode1, inode2); + + status = ocfs2_rw_lock(inode1, 1); + if (status) { + mlog_errno(status); + goto out_i1; + } + if (!same_inode) { + status = ocfs2_rw_lock(inode2, 1); + if (status) { + mlog_errno(status); + goto out_i2; + } + } + + /* Now go for the cluster locks */ + oi1 = OCFS2_I(inode1); + oi2 = OCFS2_I(inode2); + + trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, + (unsigned long long)oi2->ip_blkno); + + if (*bh1) + *bh1 = NULL; + if (*bh2) + *bh2 = NULL; + + /* We always want to lock the one with the lower lockid first. */ + if (oi1->ip_blkno > oi2->ip_blkno) + mlog_errno(-ENOLCK); + + /* lock id1 */ + status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); + if (status < 0) { + if (status != -ENOENT) + mlog_errno(status); + goto out_rw2; + } + + /* lock id2 */ + if (!same_inode) { + status = ocfs2_inode_lock_nested(inode2, bh2, 1, + OI_LS_REFLINK_TARGET); + if (status < 0) { + if (status != -ENOENT) + mlog_errno(status); + goto out_cl1; + } + } else + *bh2 = *bh1; + + trace_ocfs2_double_lock_end( + (unsigned long long)OCFS2_I(inode1)->ip_blkno, + (unsigned long long)OCFS2_I(inode2)->ip_blkno); + + return 0; + +out_cl1: + ocfs2_inode_unlock(inode1, 1); + brelse(*bh1); + *bh1 = NULL; +out_rw2: + ocfs2_rw_unlock(inode2, 1); +out_i2: + ocfs2_rw_unlock(inode1, 1); +out_i1: + unlock_two_nondirectories(s_inode, t_inode); + return status; +} + +/* Unlock both inodes and release buffers. */ +static void ocfs2_reflink_inodes_unlock(struct inode *s_inode, + struct buffer_head *s_bh, + struct inode *t_inode, + struct buffer_head *t_bh) +{ + ocfs2_inode_unlock(s_inode, 1); + ocfs2_rw_unlock(s_inode, 1); + brelse(s_bh); + if (s_inode != t_inode) { + ocfs2_inode_unlock(t_inode, 1); + ocfs2_rw_unlock(t_inode, 1); + brelse(t_bh); + } + unlock_two_nondirectories(s_inode, t_inode); +} + +/* Link a range of blocks from one file to another. */ +int ocfs2_reflink_remap_range(struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len, + bool is_dedupe) +{ + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); + struct ocfs2_super *osb = OCFS2_SB(inode_in->i_sb); + struct buffer_head *in_bh = NULL, *out_bh = NULL; + bool same_inode = (inode_in == inode_out); + ssize_t ret; + + if (!ocfs2_refcount_tree(osb)) + return -EOPNOTSUPP; + if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + return -EROFS; + + /* Lock both files against IO */ + ret = ocfs2_reflink_inodes_lock(inode_in, &in_bh, inode_out, &out_bh); + if (ret) + return ret; + + /* Check file eligibility and prepare for block sharing. */ + ret = -EINVAL; + if ((OCFS2_I(inode_in)->ip_flags & OCFS2_INODE_SYSTEM_FILE) || + (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) + goto out_unlock; + + ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + &len, is_dedupe); + if (ret || len == 0) + goto out_unlock; + + /* Lock out changes to the allocation maps and remap. */ + down_write(&OCFS2_I(inode_in)->ip_alloc_sem); + if (!same_inode) + down_write_nested(&OCFS2_I(inode_out)->ip_alloc_sem, + SINGLE_DEPTH_NESTING); + + ret = ocfs2_reflink_remap_blocks(inode_in, in_bh, pos_in, inode_out, + out_bh, pos_out, len); + + /* Zap any page cache for the destination file's range. */ + if (!ret) + truncate_inode_pages_range(&inode_out->i_data, pos_out, + PAGE_ALIGN(pos_out + len) - 1); + + up_write(&OCFS2_I(inode_in)->ip_alloc_sem); + if (!same_inode) + up_write(&OCFS2_I(inode_out)->ip_alloc_sem); + if (ret) { + mlog_errno(ret); + goto out_unlock; + } + + /* + * Empty the extent map so that we may get the right extent + * record from the disk. + */ + ocfs2_extent_map_trunc(inode_in, 0); + ocfs2_extent_map_trunc(inode_out, 0); + + ret = ocfs2_reflink_update_dest(inode_out, out_bh, pos_out + len); + if (ret) { + mlog_errno(ret); + goto out_unlock; + } + + ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh); + return 0; + +out_unlock: + ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh); + return ret; +} diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index 6422bbcdb525..4af55bf4b35b 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -115,4 +115,11 @@ int ocfs2_reflink_ioctl(struct inode *inode, const char __user *oldname, const char __user *newname, bool preserve); +int ocfs2_reflink_remap_range(struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len, + bool is_dedupe); + #endif /* OCFS2_REFCOUNTTREE_H */