From 5b2ed6e5382a313b0856ba676595ba35067219bc Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Wed, 23 Nov 2016 17:43:17 -0800 Subject: [PATCH 01/43] ARC: Don't use "+l" inline asm constraint commit 3c7c7a2fc8811bc7097479f69acf2527693d7562 upstream. Apparenty this is coming in the way of gcc fix which inhibits the usage of LP_COUNT as a gpr. Signed-off-by: Vineet Gupta Signed-off-by: Greg Kroah-Hartman --- 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 61ab6247366349aca80330db1c708c798b1c9774 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 30 Nov 2016 15:54:08 -0800 Subject: [PATCH 02/43] zram: fix unbalanced idr management at hot removal commit 529e71e16403830ae0d737a66c55c5f360f3576b upstream. 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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- 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 370c2f76016d..1770c455dfdd 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1368,7 +1368,8 @@ 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 995761627d97cc374f14203589b3a6385019bf0b Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Wed, 30 Nov 2016 15:54:13 -0800 Subject: [PATCH 03/43] kasan: update kasan_global for gcc 7 commit 045d599a286bc01daa3510d59272440a17b23c2e upstream. 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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- 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 eeae401a2412..287e698c28de 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -251,7 +251,9 @@ #endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ -#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 4f6c62e5c21e..37ff0ab6a8ff 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -52,6 +52,9 @@ struct kasan_global { #if KASAN_ABI_VERSION >= 4 struct kasan_source_location *location; #endif +#if KASAN_ABI_VERSION >= 5 + char *odr_indicator; +#endif }; static inline const void *kasan_shadow_to_mem(const void *shadow_addr) From 5a5f7030194da0c47201c04b4831f1ca623779a9 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sat, 19 Nov 2016 18:42:40 -0800 Subject: [PATCH 04/43] x86/traps: Ignore high word of regs->cs in early_fixup_exception() commit fc0e81b2bea0ebceb71889b61d2240856141c9ee upstream. On the 80486 DX, it seems that some exceptions may leave garbage in the high bits of CS. This causes sporadic failures in which early_fixup_exception() refuses to fix up an exception. As far as I can tell, this has been buggy for a long time, but the problem seems to have been exacerbated by commits: 1e02ce4cccdc ("x86: Store a per-cpu shadow copy of CR4") e1bfc11c5a6f ("x86/init: Fix cr4_init_shadow() on CR4-less machines") This appears to have broken for as long as we've had early exception handling. [ This backport should apply to kernels from 3.4 - 4.5. ] Fixes: 4c5023a3fa2e ("x86-32: Handle exception table entries during early boot") Cc: H. Peter Anvin Reported-by: Matthew Whitehead Signed-off-by: Andy Lutomirski Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/head_32.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 6bc9ae24b6d2..8f1a3f443f7d 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -571,7 +571,7 @@ early_idt_handler_common: movl %eax,%ds movl %eax,%es - cmpl $(__KERNEL_CS),32(%esp) + cmpw $(__KERNEL_CS),32(%esp) jne 10f leal 28(%esp),%eax # Pointer to %eip From 58cebd1a08ed114e05cc9d16dee9e5423f564c82 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 14 Apr 2016 18:02:37 +0200 Subject: [PATCH 05/43] ALSA: pcm : Call kill_fasync() in stream lock commit 3aa02cb664c5fb1042958c8d1aa8c35055a2ebc4 upstream. Currently kill_fasync() is called outside the stream lock in snd_pcm_period_elapsed(). This is potentially racy, since the stream may get released even during the irq handler is running. Although snd_pcm_release_substream() calls snd_pcm_drop(), this doesn't guarantee that the irq handler finishes, thus the kill_fasync() call outside the stream spin lock may be invoked after the substream is detached, as recently reported by KASAN. As a quick workaround, move kill_fasync() call inside the stream lock. The fasync is rarely used interface, so this shouldn't have a big impact from the performance POV. Ideally, we should implement some sync mechanism for the proper finish of stream and irq handler. But this oneliner should suffice for most cases, so far. Reported-by: Baozeng Ding Signed-off-by: Takashi Iwai Signed-off-by: Greg Kroah-Hartman --- sound/core/pcm_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 3a9b66c6e09c..0aca39762ed0 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -1886,8 +1886,8 @@ void snd_pcm_period_elapsed(struct snd_pcm_substream *substream) snd_timer_interrupt(substream->timer, 1); #endif _end: - snd_pcm_stream_unlock_irqrestore(substream, flags); kill_fasync(&runtime->fasync, SIGIO, POLL_IN); + snd_pcm_stream_unlock_irqrestore(substream, flags); } EXPORT_SYMBOL(snd_pcm_period_elapsed); From dfb704f96cd190239e7b86b09810a136cf25506e Mon Sep 17 00:00:00 2001 From: Ding Tianhong Date: Wed, 15 Jun 2016 15:27:36 +0800 Subject: [PATCH 06/43] rcu: Fix soft lockup for rcu_nocb_kthread commit bedc1969150d480c462cdac320fa944b694a7162 upstream. Carrying out the following steps results in a softlockup in the RCU callback-offload (rcuo) kthreads: 1. Connect to ixgbevf, and set the speed to 10Gb/s. 2. Use ifconfig to bring the nic up and down repeatedly. [ 317.005148] IPv6: ADDRCONF(NETDEV_CHANGE): eth2: link becomes ready [ 368.106005] BUG: soft lockup - CPU#1 stuck for 22s! [rcuos/1:15] [ 368.106005] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 368.106005] task: ffff88057dd8a220 ti: ffff88057dd9c000 task.ti: ffff88057dd9c000 [ 368.106005] RIP: 0010:[] [] fib_table_lookup+0x14/0x390 [ 368.106005] RSP: 0018:ffff88061fc83ce8 EFLAGS: 00000286 [ 368.106005] RAX: 0000000000000001 RBX: 00000000020155c0 RCX: 0000000000000001 [ 368.106005] RDX: ffff88061fc83d50 RSI: ffff88061fc83d70 RDI: ffff880036d11a00 [ 368.106005] RBP: ffff88061fc83d08 R08: 0000000000000001 R09: 0000000000000000 [ 368.106005] R10: ffff880036d11a00 R11: ffffffff819e0900 R12: ffff88061fc83c58 [ 368.106005] R13: ffffffff816154dd R14: ffff88061fc83d08 R15: 00000000020155c0 [ 368.106005] FS: 0000000000000000(0000) GS:ffff88061fc80000(0000) knlGS:0000000000000000 [ 368.106005] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 368.106005] CR2: 00007f8c2aee9c40 CR3: 000000057b222000 CR4: 00000000000407e0 [ 368.106005] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 368.106005] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 368.106005] Stack: [ 368.106005] 00000000010000c0 ffff88057b766000 ffff8802e380b000 ffff88057af03e00 [ 368.106005] ffff88061fc83dc0 ffffffff815349a6 ffff88061fc83d40 ffffffff814ee146 [ 368.106005] ffff8802e380af00 00000000e380af00 ffffffff819e0900 020155c0010000c0 [ 368.106005] Call Trace: [ 368.106005] [ 368.106005] [ 368.106005] [] ip_route_input_noref+0x516/0xbd0 [ 368.106005] [] ? skb_release_data+0xd6/0x110 [ 368.106005] [] ? kfree_skb+0x3a/0xa0 [ 368.106005] [] ip_rcv_finish+0x29f/0x350 [ 368.106005] [] ip_rcv+0x234/0x380 [ 368.106005] [] __netif_receive_skb_core+0x676/0x870 [ 368.106005] [] __netif_receive_skb+0x18/0x60 [ 368.106005] [] process_backlog+0xae/0x180 [ 368.106005] [] net_rx_action+0x152/0x240 [ 368.106005] [] __do_softirq+0xef/0x280 [ 368.106005] [] call_softirq+0x1c/0x30 [ 368.106005] [ 368.106005] [ 368.106005] [] do_softirq+0x65/0xa0 [ 368.106005] [] local_bh_enable+0x94/0xa0 [ 368.106005] [] rcu_nocb_kthread+0x232/0x370 [ 368.106005] [] ? wake_up_bit+0x30/0x30 [ 368.106005] [] ? rcu_start_gp+0x40/0x40 [ 368.106005] [] kthread+0xcf/0xe0 [ 368.106005] [] ? kthread_create_on_node+0x140/0x140 [ 368.106005] [] ret_from_fork+0x58/0x90 [ 368.106005] [] ? kthread_create_on_node+0x140/0x140 ==================================cut here============================== It turns out that the rcuos callback-offload kthread is busy processing a very large quantity of RCU callbacks, and it is not reliquishing the CPU while doing so. This commit therefore adds an cond_resched_rcu_qs() within the loop to allow other tasks to run. Signed-off-by: Ding Tianhong [ paulmck: Substituted cond_resched_rcu_qs for cond_resched. ] Signed-off-by: Paul E. McKenney Cc: Dhaval Giani Signed-off-by: Greg Kroah-Hartman --- kernel/rcu/tree_plugin.h | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 630c19772630..32cbe72bf545 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2275,6 +2275,7 @@ static int rcu_nocb_kthread(void *arg) cl++; c++; local_bh_enable(); + cond_resched_rcu_qs(); list = next; } trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); From 140ff0a348970430e4eb06a63afbbe5510f9c8d1 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 2 Nov 2016 16:35:51 -0600 Subject: [PATCH 07/43] PCI: Export pcie_find_root_port commit e784930bd645e7df78c66e7872fec282b0620075 upstream. 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 Signed-off-by: Greg Kroah-Hartman --- 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 182224acedbe..58f1419a68ae 100644 --- a/drivers/pci/pcie/aer/aer_inject.c +++ b/drivers/pci/pcie/aer/aer_inject.c @@ -283,20 +283,6 @@ 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 e89c7ee7e803..5f37614f2451 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1802,6 +1802,20 @@ 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 ac6e42d7a7201245e9a8db922ad795ef2a257568 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 23 Nov 2016 10:56:28 -0600 Subject: [PATCH 08/43] 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 commit e42010d8207f9d15a605ceb8e321bcd9648071b0 upstream. 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 Signed-off-by: Greg Kroah-Hartman --- 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 9757cf9037a2..b5843c255263 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1415,6 +1415,21 @@ 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; @@ -1444,9 +1459,20 @@ 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 d7a2c259fc1f41c3c030868b0344112c92f06c34 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 8 Nov 2016 18:28:24 -0800 Subject: [PATCH 09/43] mwifiex: printk() overflow with 32-byte SSIDs commit fcd2042e8d36cf644bd2d69c26378d17158b17df upstream. 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 Acked-by: Amitkumar Karwar Signed-off-by: Kalle Valo Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/mwifiex/cfg80211.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index 4073116e6e9f..c3331d6201c3 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -2144,8 +2144,9 @@ 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; } @@ -2202,8 +2203,8 @@ 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); ret = mwifiex_cfg80211_assoc(priv, sme->ssid_len, sme->ssid, sme->bssid, priv->bss_mode, sme->channel, sme, 0); @@ -2333,8 +2334,8 @@ 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 4fd108fa1a7438566e2b16bee74228c3227c9597 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 1 Nov 2016 11:46:39 +0100 Subject: [PATCH 10/43] pwm: Fix device reference leak commit 0e1614ac84f1719d87bed577963bb8140d0c9ce8 upstream. 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 Signed-off-by: Greg Kroah-Hartman --- drivers/pwm/sysfs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index c20163b92991..375008e2be20 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -366,6 +366,8 @@ 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 da643dc17f20e04c089c93a3fe7d89e5be80d1af Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 18 Oct 2016 11:27:46 +0100 Subject: [PATCH 11/43] arm64: cpufeature: Schedule enable() calls instead of calling them via IPI commit 2a6dcb2b5f3e21592ca8dfa198dcce7bec09b020 upstream. The enable() call for a cpufeature/errata is called using on_each_cpu(). This issues a cross-call IPI to get the work done. Implicitly, this stashes the running PSTATE in SPSR when the CPU receives the IPI, and restores it when we return. This means an enable() call can never modify PSTATE. To allow PAN to do this, change the on_each_cpu() call to use stop_machine(). This schedules the work on each CPU which allows us to modify PSTATE. This involves changing the protype of all the enable() functions. enable_cpu_capabilities() is called during boot and enables the feature on all online CPUs. This path now uses stop_machine(). CPU features for hotplug'd CPUs are enabled by verify_local_cpu_features() which only acts on the local CPU, and can already modify the running PSTATE as it is called from secondary_start_kernel(). Reported-by: Tony Thompson Reported-by: Vladimir Murzin Signed-off-by: James Morse Cc: Suzuki K Poulose Signed-off-by: Will Deacon [Removed enable() hunks for features/errata v4.4. doesn't have. Changed caps->enable arg in enable_cpu_capabilities()] Signed-off-by: James Morse Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/cpufeature.h | 2 +- arch/arm64/include/asm/processor.h | 2 +- arch/arm64/kernel/cpufeature.c | 10 +++++++++- arch/arm64/mm/fault.c | 3 ++- 4 files changed, 13 insertions(+), 4 deletions(-) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 8136afc9df0d..8884b5d5f48c 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -77,7 +77,7 @@ struct arm64_cpu_capabilities { const char *desc; u16 capability; bool (*matches)(const struct arm64_cpu_capabilities *); - void (*enable)(void *); /* Called on all active CPUs */ + int (*enable)(void *); /* Called on all active CPUs */ union { struct { /* To be used for erratum handling only */ u32 midr_model; diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 4acb7ca94fcd..d08559528927 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -186,6 +186,6 @@ static inline void spin_lock_prefetch(const void *x) #endif -void cpu_enable_pan(void *__unused); +int cpu_enable_pan(void *__unused); #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0669c63281ea..2735bf814592 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -19,7 +19,9 @@ #define pr_fmt(fmt) "CPU features: " fmt #include +#include #include +#include #include #include #include @@ -764,7 +766,13 @@ static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) for (i = 0; caps[i].desc; i++) if (caps[i].enable && cpus_have_cap(caps[i].capability)) - on_each_cpu(caps[i].enable, NULL, true); + /* + * Use stop_machine() as it schedules the work allowing + * us to modify PSTATE, instead of on_each_cpu() which + * uses an IPI, giving us a PSTATE that disappears when + * we return. + */ + stop_machine(caps[i].enable, NULL, cpu_online_mask); } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 4c1a118c1d09..d4634e6942ca 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -606,8 +606,9 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, } #ifdef CONFIG_ARM64_PAN -void cpu_enable_pan(void *__unused) +int cpu_enable_pan(void *__unused) { config_sctlr_el1(SCTLR_EL1_SPAN, 0); + return 0; } #endif /* CONFIG_ARM64_PAN */ From d24207a0d81cee81d0f06397074db99e12cc87c1 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 18 Oct 2016 11:27:47 +0100 Subject: [PATCH 12/43] arm64: mm: Set PSTATE.PAN from the cpu_enable_pan() call commit 7209c868600bd8926e37c10b9aae83124ccc1dd8 upstream. Commit 338d4f49d6f7 ("arm64: kernel: Add support for Privileged Access Never") enabled PAN by enabling the 'SPAN' feature-bit in SCTLR_EL1. This means the PSTATE.PAN bit won't be set until the next return to the kernel from userspace. On a preemptible kernel we may schedule work that accesses userspace on a CPU before it has done this. Now that cpufeature enable() calls are scheduled via stop_machine(), we can set PSTATE.PAN from the cpu_enable_pan() call. Add WARN_ON_ONCE(in_interrupt()) to check the PSTATE value we updated is not immediately discarded. Reported-by: Tony Thompson Reported-by: Vladimir Murzin Signed-off-by: James Morse [will: fixed typo in comment] Signed-off-by: Will Deacon Signed-off-by: Greg Kroah-Hartman --- arch/arm64/mm/fault.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d4634e6942ca..247bae758e1e 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -29,7 +29,9 @@ #include #include #include +#include +#include #include #include #include @@ -608,7 +610,14 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, #ifdef CONFIG_ARM64_PAN int cpu_enable_pan(void *__unused) { + /* + * We modify PSTATE. This won't work from irq context as the PSTATE + * is discarded once we return from the exception. + */ + WARN_ON_ONCE(in_interrupt()); + config_sctlr_el1(SCTLR_EL1_SPAN, 0); + asm(SET_PSTATE_PAN(1)); return 0; } #endif /* CONFIG_ARM64_PAN */ From 71710cd35a554b1f0a60f035642455beeaec0f06 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 18 Oct 2016 11:27:48 +0100 Subject: [PATCH 13/43] arm64: suspend: Reconfigure PSTATE after resume from idle commit d08544127d9fb4505635e3cb6871fd50a42947bd upstream. The suspend/resume path in kernel/sleep.S, as used by cpu-idle, does not save/restore PSTATE. As a result of this cpufeatures that were detected and have bits in PSTATE get lost when we resume from idle. UAO gets set appropriately on the next context switch. PAN will be re-enabled next time we return from user-space, but on a preemptible kernel we may run work accessing user space before this point. Add code to re-enable theses two features in __cpu_suspend_exit(). We re-use uao_thread_switch() passing current. Signed-off-by: James Morse Cc: Lorenzo Pieralisi Signed-off-by: Will Deacon [Removed UAO hooks and commit-message references: this feature is not present in v4.4] Signed-off-by: James Morse Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/suspend.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 1095aa483a1c..00c1372bf57b 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -1,7 +1,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -110,6 +112,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) */ set_my_cpu_offset(per_cpu_offset(smp_processor_id())); + /* + * PSTATE was not saved over suspend/resume, re-enable any + * detected features that might not have been set correctly. + */ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, + CONFIG_ARM64_PAN)); + /* * Restore HW breakpoint registers to sane values * before debug exceptions are possibly reenabled From e5f84c1444ae59c85bd25ba05393c6bc87067ddb Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 8 Dec 2016 07:15:46 +0100 Subject: [PATCH 14/43] Linux 4.4.37 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 705eb9e38fce..b57ec79b4941 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 36 +SUBLEVEL = 37 EXTRAVERSION = NAME = Blurry Fish Butt From 790fd11f9ed6d2558a516280c3bd1e25b0c64c90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Nov 2016 22:24:12 -0800 Subject: [PATCH 15/43] virtio-net: add a missing synchronize_net() [ Upstream commit 963abe5c8a0273a1cf5913556da1b1189de0e57a ] It seems many drivers do not respect napi_hash_del() contract. When napi_hash_del() is used before netif_napi_del(), an RCU grace period is needed before freeing NAPI object. Fixes: 91815639d880 ("virtio-net: rx busy polling support") Signed-off-by: Eric Dumazet Cc: Jason Wang Cc: Michael S. Tsirkin Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/virtio_net.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index f94ab786088f..0e2a19e58923 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1465,6 +1465,11 @@ static void virtnet_free_queues(struct virtnet_info *vi) netif_napi_del(&vi->rq[i].napi); } + /* We called napi_hash_del() before netif_napi_del(), + * we need to respect an RCU grace period before freeing vi->rq + */ + synchronize_net(); + kfree(vi->rq); kfree(vi->sq); } From 2b54505c877f71155c7aba26550015bd1e30d3dc Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Wed, 16 Nov 2016 10:27:02 -0800 Subject: [PATCH 16/43] net: check dead netns for peernet2id_alloc() [ Upstream commit cfc44a4d147ea605d66ccb917cc24467d15ff867 ] Andrei reports we still allocate netns ID from idr after we destroy it in cleanup_net(). cleanup_net(): ... idr_destroy(&net->netns_ids); ... list_for_each_entry_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); -> rollback_registered_many() -> rtmsg_ifinfo_build_skb() -> rtnl_fill_ifinfo() -> peernet2id_alloc() After that point we should not even access net->netns_ids, we should check the death of the current netns as early as we can in peernet2id_alloc(). For net-next we can consider to avoid sending rtmsg totally, it is a good optimization for netns teardown path. Fixes: 0c7aecd4bde4 ("netns: add rtnl cmd to add and get peer netns ids") Reported-by: Andrei Vagin Cc: Nicolas Dichtel Signed-off-by: Cong Wang Acked-by: Andrei Vagin Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/net_namespace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 2c2eb1b629b1..2e9a1c2818c7 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -217,6 +217,8 @@ int peernet2id_alloc(struct net *net, struct net *peer) bool alloc; int id; + if (atomic_read(&net->count) == 0) + return NETNSA_NSID_NOT_ASSIGNED; spin_lock_irqsave(&net->nsid_lock, flags); alloc = atomic_read(&peer->count) == 0 ? false : true; id = __peernet2id_alloc(net, peer, &alloc); From 49695d1e3b817743a155e63d923e1e14b97e14eb Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 16 Nov 2016 16:26:46 +0100 Subject: [PATCH 17/43] ip6_tunnel: disable caching when the traffic class is inherited [ Upstream commit b5c2d49544e5930c96e2632a7eece3f4325a1888 ] If an ip6 tunnel is configured to inherit the traffic class from the inner header, the dst_cache must be disabled or it will foul the policy routing. The issue is apprently there since at leat Linux-2.6.12-rc2. Reported-by: Liam McBirnie Cc: Liam McBirnie Acked-by: Hannes Frederic Sowa Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv6/ip6_tunnel.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index e8878886eba4..2994d1f1a661 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1043,6 +1043,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; + bool use_cache = false; int mtu; unsigned int max_headroom = sizeof(struct ipv6hdr); u8 proto; @@ -1070,7 +1071,15 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); - } else if (!fl6->flowi6_mark) + } else if (!(t->parms.flags & + (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { + /* enable the cache only only if the routing decision does + * not depend on the current inner header value + */ + use_cache = true; + } + + if (use_cache) dst = ip6_tnl_dst_get(t); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) @@ -1134,7 +1143,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb = new_skb; } - if (!fl6->flowi6_mark && ndst) + if (use_cache && ndst) ip6_tnl_dst_set(t, ndst); skb_dst_set(skb, dst); From acf9504ae220acbd1caa8ee4668c8a3a3b51d73a Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Thu, 17 Nov 2016 09:14:25 -0600 Subject: [PATCH 18/43] net: sky2: Fix shutdown crash [ Upstream commit 06ba3b2133dc203e1e9bc36cee7f0839b79a9e8b ] The sky2 frequently crashes during machine shutdown with: sky2_get_stats+0x60/0x3d8 [sky2] dev_get_stats+0x68/0xd8 rtnl_fill_stats+0x54/0x140 rtnl_fill_ifinfo+0x46c/0xc68 rtmsg_ifinfo_build_skb+0x7c/0xf0 rtmsg_ifinfo.part.22+0x3c/0x70 rtmsg_ifinfo+0x50/0x5c netdev_state_change+0x4c/0x58 linkwatch_do_dev+0x50/0x88 __linkwatch_run_queue+0x104/0x1a4 linkwatch_event+0x30/0x3c process_one_work+0x140/0x3e0 worker_thread+0x60/0x44c kthread+0xdc/0xf0 ret_from_fork+0x10/0x50 This is caused by the sky2 being called after it has been shutdown. A previous thread about this can be found here: https://lkml.org/lkml/2016/4/12/410 An alternative fix is to assure that IFF_UP gets cleared by calling dev_close() during shutdown. This is similar to what the bnx2/tg3/xgene and maybe others are doing to assure that the driver isn't being called following _shutdown(). Signed-off-by: Jeremy Linton Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/ethernet/marvell/sky2.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 5606a043063e..4b62aa1f9ff8 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5220,6 +5220,19 @@ static SIMPLE_DEV_PM_OPS(sky2_pm_ops, sky2_suspend, sky2_resume); static void sky2_shutdown(struct pci_dev *pdev) { + struct sky2_hw *hw = pci_get_drvdata(pdev); + int port; + + for (port = 0; port < hw->ports; port++) { + struct net_device *ndev = hw->dev[port]; + + rtnl_lock(); + if (netif_running(ndev)) { + dev_close(ndev); + netif_device_detach(ndev); + } + rtnl_unlock(); + } sky2_suspend(&pdev->dev); pci_wake_from_d3(pdev, device_may_wakeup(&pdev->dev)); pci_set_power_state(pdev, PCI_D3hot); From 6ef59b986190f07386b062884ab48006c16cf152 Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 17 Nov 2016 15:55:26 -0800 Subject: [PATCH 19/43] af_unix: conditionally use freezable blocking calls in read [ Upstream commit 06a77b07e3b44aea2b3c0e64de420ea2cfdcbaa9 ] Commit 2b15af6f95 ("af_unix: use freezable blocking calls in read") converts schedule_timeout() to its freezable version, it was probably correct at that time, but later, commit 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets") breaks the strong requirement for a freezable sleep, according to commit 0f9548ca1091: We shouldn't try_to_freeze if locks are held. Holding a lock can cause a deadlock if the lock is later acquired in the suspend or hibernate path (e.g. by dpm). Holding a lock can also cause a deadlock in the case of cgroup_freezer if a lock is held inside a frozen cgroup that is later acquired by a process outside that group. The pipe_lock is still held at that point. So use freezable version only for the recvmsg call path, avoid impact for Android. Fixes: 2b514574f7e8 ("net: af_unix: implement splice for stream af_unix sockets") Reported-by: Dmitry Vyukov Cc: Tejun Heo Cc: Colin Cross Cc: Rafael J. Wysocki Cc: Hannes Frederic Sowa Signed-off-by: Cong Wang Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/unix/af_unix.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 824cc1e160bc..73f75258ce46 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2194,7 +2194,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last, unsigned int last_len) + struct sk_buff *last, unsigned int last_len, + bool freezable) { struct sk_buff *tail; DEFINE_WAIT(wait); @@ -2215,7 +2216,10 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); unix_state_unlock(sk); - timeo = freezable_schedule_timeout(timeo); + if (freezable) + timeo = freezable_schedule_timeout(timeo); + else + timeo = schedule_timeout(timeo); unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) @@ -2245,7 +2249,8 @@ struct unix_stream_read_state { unsigned int splice_flags; }; -static int unix_stream_read_generic(struct unix_stream_read_state *state) +static int unix_stream_read_generic(struct unix_stream_read_state *state, + bool freezable) { struct scm_cookie scm; struct socket *sock = state->socket; @@ -2324,7 +2329,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) mutex_unlock(&u->iolock); timeo = unix_stream_data_wait(sk, timeo, last, - last_len); + last_len, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -2466,7 +2471,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, .flags = flags }; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, true); } static ssize_t skb_unix_socket_splice(struct sock *sk, @@ -2512,7 +2517,7 @@ static ssize_t unix_stream_splice_read(struct socket *sock, loff_t *ppos, flags & SPLICE_F_NONBLOCK) state.flags = MSG_DONTWAIT; - return unix_stream_read_generic(&state); + return unix_stream_read_generic(&state, false); } static int unix_shutdown(struct socket *sock, int mode) From aece024e38cb38eb5307e35862c5876e817efd33 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 18 Nov 2016 15:50:39 +0100 Subject: [PATCH 20/43] rtnetlink: fix FDB size computation [ Upstream commit f82ef3e10a870acc19fa04f80ef5877eaa26f41e ] Add missing NDA_VLAN attribute's size. Fixes: 1e53d5bb8878 ("net: Pass VLAN ID to rtnl_fdb_notify.") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/rtnetlink.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 87b91ffbdec3..b94e165a4f79 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2600,7 +2600,10 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, static inline size_t rtnl_fdb_nlmsg_size(void) { - return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN); + return NLMSG_ALIGN(sizeof(struct ndmsg)) + + nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(sizeof(u16)) + /* NDA_VLAN */ + 0; } static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type) From 56366fa0ad46a59abe2460b8acb775f7f84fbf16 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Fri, 18 Nov 2016 22:13:00 +0100 Subject: [PATCH 21/43] l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind() [ Upstream commit 32c231164b762dddefa13af5a0101032c70b50ef ] Lock socket before checking the SOCK_ZAPPED flag in l2tp_ip6_bind(). Without lock, a concurrent call could modify the socket flags between the sock_flag(sk, SOCK_ZAPPED) test and the lock_sock() call. This way, a socket could be inserted twice in l2tp_ip6_bind_table. Releasing it would then leave a stale pointer there, generating use-after-free errors when walking through the list or modifying adjacent entries. BUG: KASAN: use-after-free in l2tp_ip6_close+0x22e/0x290 at addr ffff8800081b0ed8 Write of size 8 by task syz-executor/10987 CPU: 0 PID: 10987 Comm: syz-executor Not tainted 4.8.0+ #39 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.8.2-0-g33fbe13 by qemu-project.org 04/01/2014 ffff880031d97838 ffffffff829f835b ffff88001b5a1640 ffff8800081b0ec0 ffff8800081b15a0 ffff8800081b6d20 ffff880031d97860 ffffffff8174d3cc ffff880031d978f0 ffff8800081b0e80 ffff88001b5a1640 ffff880031d978e0 Call Trace: [] dump_stack+0xb3/0x118 lib/dump_stack.c:15 [] kasan_object_err+0x1c/0x70 mm/kasan/report.c:156 [< inline >] print_address_description mm/kasan/report.c:194 [] kasan_report_error+0x1f6/0x4d0 mm/kasan/report.c:283 [< inline >] kasan_report mm/kasan/report.c:303 [] __asan_report_store8_noabort+0x3e/0x40 mm/kasan/report.c:329 [< inline >] __write_once_size ./include/linux/compiler.h:249 [< inline >] __hlist_del ./include/linux/list.h:622 [< inline >] hlist_del_init ./include/linux/list.h:637 [] l2tp_ip6_close+0x22e/0x290 net/l2tp/l2tp_ip6.c:239 [] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415 [] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422 [] sock_release+0x8d/0x1d0 net/socket.c:570 [] sock_close+0x16/0x20 net/socket.c:1017 [] __fput+0x28c/0x780 fs/file_table.c:208 [] ____fput+0x15/0x20 fs/file_table.c:244 [] task_work_run+0xf9/0x170 [] do_exit+0x85e/0x2a00 [] do_group_exit+0x108/0x330 [] get_signal+0x617/0x17a0 kernel/signal.c:2307 [] do_signal+0x7f/0x18f0 [] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156 [< inline >] prepare_exit_to_usermode arch/x86/entry/common.c:190 [] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259 [] entry_SYSCALL_64_fastpath+0xc4/0xc6 Object at ffff8800081b0ec0, in cache L2TP/IPv6 size: 1448 Allocated: PID = 10987 [ 1116.897025] [] save_stack_trace+0x16/0x20 [ 1116.897025] [] save_stack+0x46/0xd0 [ 1116.897025] [] kasan_kmalloc+0xad/0xe0 [ 1116.897025] [] kasan_slab_alloc+0x12/0x20 [ 1116.897025] [< inline >] slab_post_alloc_hook mm/slab.h:417 [ 1116.897025] [< inline >] slab_alloc_node mm/slub.c:2708 [ 1116.897025] [< inline >] slab_alloc mm/slub.c:2716 [ 1116.897025] [] kmem_cache_alloc+0xc8/0x2b0 mm/slub.c:2721 [ 1116.897025] [] sk_prot_alloc+0x69/0x2b0 net/core/sock.c:1326 [ 1116.897025] [] sk_alloc+0x38/0xae0 net/core/sock.c:1388 [ 1116.897025] [] inet6_create+0x2d7/0x1000 net/ipv6/af_inet6.c:182 [ 1116.897025] [] __sock_create+0x37b/0x640 net/socket.c:1153 [ 1116.897025] [< inline >] sock_create net/socket.c:1193 [ 1116.897025] [< inline >] SYSC_socket net/socket.c:1223 [ 1116.897025] [] SyS_socket+0xef/0x1b0 net/socket.c:1203 [ 1116.897025] [] entry_SYSCALL_64_fastpath+0x23/0xc6 Freed: PID = 10987 [ 1116.897025] [] save_stack_trace+0x16/0x20 [ 1116.897025] [] save_stack+0x46/0xd0 [ 1116.897025] [] kasan_slab_free+0x71/0xb0 [ 1116.897025] [< inline >] slab_free_hook mm/slub.c:1352 [ 1116.897025] [< inline >] slab_free_freelist_hook mm/slub.c:1374 [ 1116.897025] [< inline >] slab_free mm/slub.c:2951 [ 1116.897025] [] kmem_cache_free+0xc8/0x330 mm/slub.c:2973 [ 1116.897025] [< inline >] sk_prot_free net/core/sock.c:1369 [ 1116.897025] [] __sk_destruct+0x32b/0x4f0 net/core/sock.c:1444 [ 1116.897025] [] sk_destruct+0x44/0x80 net/core/sock.c:1452 [ 1116.897025] [] __sk_free+0x53/0x220 net/core/sock.c:1460 [ 1116.897025] [] sk_free+0x23/0x30 net/core/sock.c:1471 [ 1116.897025] [] sk_common_release+0x28c/0x3e0 ./include/net/sock.h:1589 [ 1116.897025] [] l2tp_ip6_close+0x1fe/0x290 net/l2tp/l2tp_ip6.c:243 [ 1116.897025] [] inet_release+0xed/0x1c0 net/ipv4/af_inet.c:415 [ 1116.897025] [] inet6_release+0x50/0x70 net/ipv6/af_inet6.c:422 [ 1116.897025] [] sock_release+0x8d/0x1d0 net/socket.c:570 [ 1116.897025] [] sock_close+0x16/0x20 net/socket.c:1017 [ 1116.897025] [] __fput+0x28c/0x780 fs/file_table.c:208 [ 1116.897025] [] ____fput+0x15/0x20 fs/file_table.c:244 [ 1116.897025] [] task_work_run+0xf9/0x170 [ 1116.897025] [] do_exit+0x85e/0x2a00 [ 1116.897025] [] do_group_exit+0x108/0x330 [ 1116.897025] [] get_signal+0x617/0x17a0 kernel/signal.c:2307 [ 1116.897025] [] do_signal+0x7f/0x18f0 [ 1116.897025] [] exit_to_usermode_loop+0xbf/0x150 arch/x86/entry/common.c:156 [ 1116.897025] [< inline >] prepare_exit_to_usermode arch/x86/entry/common.c:190 [ 1116.897025] [] syscall_return_slowpath+0x1a0/0x1e0 arch/x86/entry/common.c:259 [ 1116.897025] [] entry_SYSCALL_64_fastpath+0xc4/0xc6 Memory state around the buggy address: ffff8800081b0d80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8800081b0e00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff8800081b0e80: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb ^ ffff8800081b0f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8800081b0f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== The same issue exists with l2tp_ip_bind() and l2tp_ip_bind_table. Fixes: c51ce49735c1 ("l2tp: fix oops in L2TP IP sockets for connect() AF_UNSPEC case") Reported-by: Baozeng Ding Reported-by: Andrey Konovalov Tested-by: Baozeng Ding Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/l2tp/l2tp_ip.c | 5 +++-- net/l2tp/l2tp_ip6.c | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 42de4ccd159f..d0e906d39642 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -251,8 +251,6 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret; int chk_addr_ret; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr_len < sizeof(struct sockaddr_l2tpip)) return -EINVAL; if (addr->l2tp_family != AF_INET) @@ -267,6 +265,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) read_unlock_bh(&l2tp_ip_lock); lock_sock(sk); + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out; + if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip)) goto out; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9ee4ddb6b397..3c4f867d3633 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -266,8 +266,6 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int addr_type; int err; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -293,6 +291,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) lock_sock(sk); err = -EINVAL; + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out_unlock; + if (sk->sk_state != TCP_CLOSE) goto out_unlock; From 94de6f2ffb3de28f4a6c92a52e8f8cdcb7046847 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 22 Nov 2016 11:40:58 -0800 Subject: [PATCH 22/43] net: dsa: bcm_sf2: Ensure we re-negotiate EEE during after link change [ Upstream commit 76da8706d90d8641eeb9b8e579942ed80b6c0880 ] In case the link change and EEE is enabled or disabled, always try to re-negotiate this with the link partner. Fixes: 450b05c15f9c ("net: dsa: bcm_sf2: add support for controlling EEE") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/dsa/bcm_sf2.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 6f946fedbb77..0864f05633a2 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1137,6 +1137,7 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port, struct phy_device *phydev) { struct bcm_sf2_priv *priv = ds_to_priv(ds); + struct ethtool_eee *p = &priv->port_sts[port].eee; u32 id_mode_dis = 0, port_mode; const char *str = NULL; u32 reg; @@ -1211,6 +1212,9 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port, reg |= DUPLX_MODE; core_writel(priv, reg, CORE_STS_OVERRIDE_GMIIP_PORT(port)); + + if (!phydev->is_pseudo_fixed_link) + p->eee_enabled = bcm_sf2_eee_init(ds, port, phydev); } static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, From cfa7c16d4577a6e738bbd2bc83c6c8d7344e2d1a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 27 Nov 2016 01:18:01 +0100 Subject: [PATCH 23/43] net, sched: respect rcu grace period on cls destruction [ Upstream commit d936377414fadbafb4d17148d222fe45ca5442d4 ] 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 Signed-off-by: Greg Kroah-Hartman --- 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_rsvp.h | 3 ++- net/sched/cls_tcindex.c | 1 - 7 files changed, 31 insertions(+), 20 deletions(-) diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 0b8c3ace671f..1bf1f4517db6 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 5faaa5425f7b..3eef0215e53f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -199,7 +199,6 @@ 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; } @@ -210,9 +209,6 @@ 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 4c85bd3a750c..c104c2019feb 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -130,11 +130,10 @@ 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 fbfec6a18839..d7ba2b4ff0f3 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -583,7 +583,6 @@ 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 95b021243233..e5a58c82728a 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -55,7 +56,10 @@ 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 { @@ -165,6 +169,24 @@ static void fl_destroy_filter(struct rcu_head *head) kfree(f); } +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); @@ -177,10 +199,9 @@ 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_rsvp.h b/net/sched/cls_rsvp.h index f9c9fc075fe6..9992dfac6938 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 944c8ff45055..403746b20263 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -503,7 +503,6 @@ 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 6c42bd6a393c3c7b3be24f9bf57a26608df14739 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Mon, 28 Nov 2016 12:56:40 +0200 Subject: [PATCH 24/43] net/sched: pedit: make sure that offset is valid [ Upstream commit 95c2027bfeda21a28eb245121e6a249f38d0788e ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 e38a7701f154..c3434e902445 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -104,6 +104,17 @@ 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) { @@ -130,6 +141,11 @@ 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) @@ -142,10 +158,10 @@ 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 d1ed9c1dba632199c59bb8b1245c2f86e28c7380 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 28 Nov 2016 19:22:12 +0800 Subject: [PATCH 25/43] netlink: Call cb->done from a worker thread [ Upstream commit 707693c8a498697aa8db240b93eb76ec62e30892 ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 28fc283c1ec1..bbf7d2e3fe17 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -924,14 +924,11 @@ 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); } @@ -960,6 +957,28 @@ 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 14437d9b1965..df32cb92d9fc 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) @@ -53,6 +54,7 @@ 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 baaf0c65bc8ea9c7a404b09bc8cc3b8a1e4f18df Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 5 Dec 2016 15:28:21 +0800 Subject: [PATCH 26/43] netlink: Do not schedule work from sk_destruct [ Upstream commit ed5d7788a934a4b6d6d025e948ed4da496b4f12e ] It is wrong to schedule a work from sk_destruct using the socket as the memory reserve because the socket will be freed immediately after the return from sk_destruct. Instead we should do the deferral prior to sk_free. This patch does just that. Fixes: 707693c8a498 ("netlink: Call cb->done from a worker thread") Signed-off-by: Herbert Xu Tested-by: Andrey Konovalov Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/netlink/af_netlink.c | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index bbf7d2e3fe17..360700a2f46c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -924,11 +924,13 @@ 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); } @@ -962,21 +964,7 @@ 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); + sk_free(&nlk->sk); } /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on @@ -1284,8 +1272,18 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, static void deferred_put_nlk_sk(struct rcu_head *head) { struct netlink_sock *nlk = container_of(head, struct netlink_sock, rcu); + struct sock *sk = &nlk->sk; - sock_put(&nlk->sk); + if (!atomic_dec_and_test(&sk->sk_refcnt)) + return; + + if (nlk->cb_running && nlk->cb.done) { + INIT_WORK(&nlk->work, netlink_sock_destruct_work); + schedule_work(&nlk->work); + return; + } + + sk_free(sk); } static int netlink_release(struct socket *sock) From 1a15519fdcdb0f908ad1a3785178f9e18a2ebedb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 28 Nov 2016 06:26:49 -0800 Subject: [PATCH 27/43] net/dccp: fix use-after-free in dccp_invalid_packet [ Upstream commit 648f0c28df282636c0c8a7a19ca3ce5fc80a39c3 ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 861e1fa25d5e..0759f5b9180e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -698,6 +698,7 @@ 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; @@ -719,18 +720,19 @@ 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 5a01eaf19858278cc22525be118fe9c6a3c86e83 Mon Sep 17 00:00:00 2001 From: Philip Pettersson Date: Wed, 30 Nov 2016 14:55:36 -0800 Subject: [PATCH 28/43] packet: fix race condition in packet_set_ring [ Upstream commit 84ac7260236a49c79eede91617700174c2c19b0c ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 34e4fcfd240b..f223d1c80ccf 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3572,19 +3572,25 @@ 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: { @@ -4067,6 +4073,7 @@ 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)) { WARN(1, "Tx-ring is not supported.\n"); @@ -4148,7 +4155,6 @@ 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); @@ -4197,11 +4203,11 @@ 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 c36a2a14f26dd3ed95ce75ba69fb7435d7da9bf0 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 1 Dec 2016 09:45:45 -0800 Subject: [PATCH 29/43] net: bcmgenet: Utilize correct struct device for all DMA operations [ Upstream commit 8c4799ac799665065f9bf1364fd71bf4f7dc6a4a ] __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 Signed-off-by: Greg Kroah-Hartman --- 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 0fb3f8de88e9..91627561c58d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1168,6 +1168,7 @@ 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; @@ -1195,7 +1196,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, pkts_compl++; dev->stats.tx_packets++; dev->stats.tx_bytes += tx_cb_ptr->skb->len; - 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); @@ -1203,7 +1204,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { dev->stats.tx_bytes += dma_unmap_len(tx_cb_ptr, dma_len); - 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); @@ -1754,6 +1755,7 @@ 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; @@ -1761,7 +1763,7 @@ 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 a89e2ff894bc317a49b9b46ef70eb62e05a8bf7c Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Thu, 1 Dec 2016 13:32:14 -0500 Subject: [PATCH 30/43] sh_eth: remove unchecked interrupts for RZ/A1 [ Upstream commit 33d446dbba4d4d6a77e1e900d434fa99e0f02c86 ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 36fc9427418f..480f3dae0780 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -832,7 +832,7 @@ 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 6e682c528b3ef046a03994b076d832b2ac029042 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 2 Dec 2016 16:49:29 +0100 Subject: [PATCH 31/43] geneve: avoid use-after-free of skb->data [ Upstream commit 5b01014759991887b1e450c9def01e58c02ab81b ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 4827c6987ac3..f0961cbaf87e 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -815,7 +815,6 @@ 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 = geneve->sock4; struct rtable *rt = NULL; - const struct iphdr *iip; /* interior IP header */ int err = -EINVAL; struct flowi4 fl4; __u8 tos, ttl; @@ -842,8 +841,6 @@ 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; @@ -859,7 +856,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto err; - 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 { @@ -869,7 +866,7 @@ static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto err; - 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; @@ -903,7 +900,6 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs6 = geneve->sock6; struct dst_entry *dst = NULL; - const struct iphdr *iip; /* interior IP header */ int err = -EINVAL; struct flowi6 fl6; __u8 prio, ttl; @@ -927,8 +923,6 @@ 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; @@ -945,7 +939,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto err; - prio = ip_tunnel_ecn_encap(key->tos, iip, skb); + prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; } else { udp_csum = false; @@ -954,7 +948,7 @@ static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (unlikely(err)) goto err; - prio = ip_tunnel_ecn_encap(fl6.flowi6_tos, iip, skb); + prio = ip_tunnel_ecn_encap(fl6.flowi6_tos, ip_hdr(skb), skb); ttl = geneve->ttl; if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) ttl = 1; From 77125815f058d587cac9217ac2c468038a7285c4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 2 Dec 2016 09:44:53 -0800 Subject: [PATCH 32/43] net: avoid signed overflows for SO_{SND|RCV}BUFFORCE [ Upstream commit b98b0bc8c431e3ceb4b26b0dfc8db509518fb290 ] 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 Signed-off-by: Greg Kroah-Hartman --- 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 88f017854509..f4c0917e66b5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -745,7 +745,7 @@ 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; @@ -781,7 +781,7 @@ 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 06cdad2b6d921dee33c8efc84922533dfb1458c6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 5 Dec 2016 10:34:38 -0800 Subject: [PATCH 33/43] net: ping: check minimum size on ICMP header length [ Upstream commit 0eab121ef8750a5c8637d51534d5e9143fb0633f ] Prior to commit c0371da6047a ("put iov_iter into msghdr") in v3.19, there was no check that the iovec contained enough bytes for an ICMP header, and the read loop would walk across neighboring stack contents. Since the iov_iter conversion, bad arguments are noticed, but the returned error is EFAULT. Returning EINVAL is a clearer error and also solves the problem prior to v3.19. This was found using trinity with KASAN on v3.18: BUG: KASAN: stack-out-of-bounds in memcpy_fromiovec+0x60/0x114 at addr ffffffc071077da0 Read of size 8 by task trinity-c2/9623 page:ffffffbe034b9a08 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x0() page dumped because: kasan: bad access detected CPU: 0 PID: 9623 Comm: trinity-c2 Tainted: G BU 3.18.0-dirty #15 Hardware name: Google Tegra210 Smaug Rev 1,3+ (DT) Call trace: [] dump_backtrace+0x0/0x1ac arch/arm64/kernel/traps.c:90 [] show_stack+0x10/0x1c arch/arm64/kernel/traps.c:171 [< inline >] __dump_stack lib/dump_stack.c:15 [] dump_stack+0x7c/0xd0 lib/dump_stack.c:50 [< inline >] print_address_description mm/kasan/report.c:147 [< inline >] kasan_report_error mm/kasan/report.c:236 [] kasan_report+0x380/0x4b8 mm/kasan/report.c:259 [< inline >] check_memory_region mm/kasan/kasan.c:264 [] __asan_load8+0x20/0x70 mm/kasan/kasan.c:507 [] memcpy_fromiovec+0x5c/0x114 lib/iovec.c:15 [< inline >] memcpy_from_msg include/linux/skbuff.h:2667 [] ping_common_sendmsg+0x50/0x108 net/ipv4/ping.c:674 [] ping_v4_sendmsg+0xd8/0x698 net/ipv4/ping.c:714 [] inet_sendmsg+0xe0/0x12c net/ipv4/af_inet.c:749 [< inline >] __sock_sendmsg_nosec net/socket.c:624 [< inline >] __sock_sendmsg net/socket.c:632 [] sock_sendmsg+0x124/0x164 net/socket.c:643 [< inline >] SYSC_sendto net/socket.c:1797 [] SyS_sendto+0x178/0x1d8 net/socket.c:1761 CVE-2016-8399 Reported-by: Qidan He Fixes: c319b4d76b9e ("net: ipv4: add IPPROTO_ICMP socket kind") Cc: stable@vger.kernel.org Signed-off-by: Kees Cook Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ping.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aa67e0e64b69..23160d2b3f71 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -660,6 +660,10 @@ int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, if (len > 0xFFFF) return -EMSGSIZE; + /* Must have at least a full ICMP header. */ + if (len < icmph_len) + return -EINVAL; + /* * Check the flags. */ From 438e91da24fa63d3b52faafd7302081e9e79207a Mon Sep 17 00:00:00 2001 From: Andreas Larsson Date: Wed, 9 Nov 2016 10:43:05 +0100 Subject: [PATCH 34/43] sparc32: Fix inverted invalid_frame_pointer checks on sigreturns [ Upstream commit 07b5ab3f71d318e52c18cc3b73c1d44c908aacfa ] Signed-off-by: Andreas Larsson Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- arch/sparc/kernel/signal_32.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index c3c12efe0bc0..9c0c8fd0b292 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -89,7 +89,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv_and_exit; if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) @@ -150,7 +150,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) synchronize_user_stack(); sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; - if (!invalid_frame_pointer(sf, sizeof(*sf))) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv; if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) From ed7b60db00a17a3bc4705014ebec4c035577b9e5 Mon Sep 17 00:00:00 2001 From: Thomas Tai Date: Thu, 3 Nov 2016 09:19:01 -0700 Subject: [PATCH 35/43] sparc64: Fix find_node warning if numa node cannot be found [ Upstream commit 74a5ed5c4f692df2ff0a2313ea71e81243525519 ] When booting up LDOM, find_node() warns that a physical address doesn't match a NUMA node. WARNING: CPU: 0 PID: 0 at arch/sparc/mm/init_64.c:835 find_node+0xf4/0x120 find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0.Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.9.0-rc3 #4 Call Trace: [0000000000468ba0] __warn+0xc0/0xe0 [0000000000468c74] warn_slowpath_fmt+0x34/0x60 [00000000004592f4] find_node+0xf4/0x120 [0000000000dd0774] add_node_ranges+0x38/0xe4 [0000000000dd0b1c] numa_parse_mdesc+0x268/0x2e4 [0000000000dd0e9c] bootmem_init+0xb8/0x160 [0000000000dd174c] paging_init+0x808/0x8fc [0000000000dcb0d0] setup_arch+0x2c8/0x2f0 [0000000000dc68a0] start_kernel+0x48/0x424 [0000000000dcb374] start_early_boot+0x27c/0x28c [0000000000a32c08] tlb_fixup_done+0x4c/0x64 [0000000000027f08] 0x27f08 It is because linux use an internal structure node_masks[] to keep the best memory latency node only. However, LDOM mdesc can contain single latency-group with multiple memory latency nodes. If the address doesn't match the best latency node within node_masks[], it should check for an alternative via mdesc. The warning message should only be printed if the address doesn't match any node_masks[] nor within mdesc. To minimize the impact of searching mdesc every time, the last matched mask and index is stored in a variable. Signed-off-by: Thomas Tai Reviewed-by: Chris Hyser Reviewed-by: Liam Merwick Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- arch/sparc/mm/init_64.c | 65 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 61 insertions(+), 4 deletions(-) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index a5331c336b2a..83bf3418fb56 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -800,6 +800,8 @@ struct mdesc_mblock { }; static struct mdesc_mblock *mblocks; static int num_mblocks; +static int find_numa_node_for_addr(unsigned long pa, + struct node_mem_mask *pnode_mask); static unsigned long ra_to_pa(unsigned long addr) { @@ -819,6 +821,9 @@ static unsigned long ra_to_pa(unsigned long addr) static int find_node(unsigned long addr) { + static bool search_mdesc = true; + static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL }; + static int last_index; int i; addr = ra_to_pa(addr); @@ -828,10 +833,27 @@ static int find_node(unsigned long addr) if ((addr & p->mask) == p->val) return i; } - /* The following condition has been observed on LDOM guests.*/ - WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node" - " rule. Some physical memory will be owned by node 0."); - return 0; + /* The following condition has been observed on LDOM guests because + * node_masks only contains the best latency mask and value. + * LDOM guest's mdesc can contain a single latency group to + * cover multiple address range. Print warning message only if the + * address cannot be found in node_masks nor mdesc. + */ + if ((search_mdesc) && + ((addr & last_mem_mask.mask) != last_mem_mask.val)) { + /* find the available node in the mdesc */ + last_index = find_numa_node_for_addr(addr, &last_mem_mask); + numadbg("find_node: latency group for address 0x%lx is %d\n", + addr, last_index); + if ((last_index < 0) || (last_index >= num_node_masks)) { + /* WARN_ONCE() and use default group 0 */ + WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node rule. Some physical memory will be owned by node 0."); + search_mdesc = false; + last_index = 0; + } + } + + return last_index; } static u64 memblock_nid_range(u64 start, u64 end, int *nid) @@ -1158,6 +1180,41 @@ int __node_distance(int from, int to) return numa_latency[from][to]; } +static int find_numa_node_for_addr(unsigned long pa, + struct node_mem_mask *pnode_mask) +{ + struct mdesc_handle *md = mdesc_grab(); + u64 node, arc; + int i = 0; + + node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); + if (node == MDESC_NODE_NULL) + goto out; + + mdesc_for_each_node_by_name(md, node, "group") { + mdesc_for_each_arc(arc, md, node, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + struct mdesc_mlgroup *m = find_mlgroup(target); + + if (!m) + continue; + if ((pa & m->mask) == m->match) { + if (pnode_mask) { + pnode_mask->mask = m->mask; + pnode_mask->val = m->match; + } + mdesc_release(md); + return i; + } + } + i++; + } + +out: + mdesc_release(md); + return -1; +} + static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) { int i; From 899b60535a2af978cdd798932f688b887decf424 Mon Sep 17 00:00:00 2001 From: Thomas Tai Date: Fri, 11 Nov 2016 16:41:00 -0800 Subject: [PATCH 36/43] sparc64: fix compile warning section mismatch in find_node() [ Upstream commit 87a349f9cc0908bc0cfac0c9ece3179f650ae95a ] A compile warning is introduced by a commit to fix the find_node(). This patch fix the compile warning by moving find_node() into __init section. Because find_node() is only used by memblock_nid_range() which is only used by a __init add_node_ranges(). find_node() and memblock_nid_range() should also be inside __init section. Signed-off-by: Thomas Tai Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- arch/sparc/mm/init_64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 83bf3418fb56..3d3414c14792 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -803,7 +803,7 @@ static int num_mblocks; static int find_numa_node_for_addr(unsigned long pa, struct node_mem_mask *pnode_mask); -static unsigned long ra_to_pa(unsigned long addr) +static unsigned long __init ra_to_pa(unsigned long addr) { int i; @@ -819,7 +819,7 @@ static unsigned long ra_to_pa(unsigned long addr) return addr; } -static int find_node(unsigned long addr) +static int __init find_node(unsigned long addr) { static bool search_mdesc = true; static struct node_mem_mask last_mem_mask = { ~0UL, ~0UL }; @@ -856,7 +856,7 @@ static int find_node(unsigned long addr) return last_index; } -static u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 __init memblock_nid_range(u64 start, u64 end, int *nid) { *nid = find_node(start); start += PAGE_SIZE; From fd1aa12c63400ca7d5b6d189ae98570f47735180 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 10 Oct 2016 13:57:37 -0400 Subject: [PATCH 37/43] constify iov_iter_count() and iter_is_iovec() commit b57332b4105abf1d518d93886e547ee2f98cd414 upstream. [stable note, need this to prevent build warning in commit a0ac402cfcdc904f9772e1762b3fda112dcc56a0] Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- include/linux/uio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/uio.h b/include/linux/uio.h index 5f9c59da978b..e2225109b816 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -101,12 +101,12 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); -static inline size_t iov_iter_count(struct iov_iter *i) +static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } -static inline bool iter_is_iovec(struct iov_iter *i) +static inline bool iter_is_iovec(const struct iov_iter *i) { return !(i->type & (ITER_BVEC | ITER_KVEC)); } From d41fb2fbb28d3a1085960edada6c046becd1fafd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 6 Dec 2016 16:18:14 -0800 Subject: [PATCH 38/43] Don't feed anything but regular iovec's to blk_rq_map_user_iov commit a0ac402cfcdc904f9772e1762b3fda112dcc56a0 upstream. In theory we could map other things, but there's a reason that function is called "user_iov". Using anything else (like splice can do) just confuses it. Reported-and-tested-by: Johannes Thumshirn Cc: Al Viro Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- block/blk-map.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/block/blk-map.c b/block/blk-map.c index f565e11f465a..69953bd97e65 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -90,6 +90,9 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, if (!iter || !iter->count) return -EINVAL; + if (!iter_is_iovec(iter)) + return -EINVAL; + iov_for_each(iov, i, *iter) { unsigned long uaddr = (unsigned long) iov.iov_base; From 25d8b7c105e13df4a0b14159a85c448158570909 Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Thu, 1 Dec 2016 10:05:11 +0800 Subject: [PATCH 39/43] ipv6: Set skb->protocol properly for local output commit b4e479a96fc398ccf83bb1cffb4ffef8631beaf1 upstream. 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. Signed-off-by: Eli Cooper Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- 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 462f2a76b5c2..1d184322a7b1 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -148,6 +148,8 @@ int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); + 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 2176ec1c82eae70a9d43a974455d9bfe3dcd7bd2 Mon Sep 17 00:00:00 2001 From: Eli Cooper Date: Thu, 1 Dec 2016 10:05:10 +0800 Subject: [PATCH 40/43] ipv4: Set skb->protocol properly for local output commit f4180439109aa720774baafdd798b3234ab1a0d2 upstream. 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. Signed-off-by: Eli Cooper Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/ip_output.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f2ad5216c438..2b7283303650 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -102,6 +102,9 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) iph->tot_len = htons(skb->len); ip_send_check(iph); + + 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 3bf28ce9c7499477aff4e6ecf07071978c2cabcf Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 29 Nov 2016 17:05:20 +0100 Subject: [PATCH 41/43] esp4: Fix integrity verification when ESN are used commit 7c7fedd51c02f4418e8b2eed64bdab601f882aa4 upstream. 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 Signed-off-by: Greg Kroah-Hartman --- 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 52783ada69b4741cf0122bd593493cc6c3217b9b Mon Sep 17 00:00:00 2001 From: Tobias Brunner Date: Tue, 29 Nov 2016 17:05:25 +0100 Subject: [PATCH 42/43] esp6: Fix integrity verification when ESN are used commit a55e23864d381c5a4ef110df94b00b2fe121a70d upstream. 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 Signed-off-by: Greg Kroah-Hartman --- 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 c95b7f1fab0c76882764a5196119237c8ad436ee Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 10 Dec 2016 19:08:05 +0100 Subject: [PATCH 43/43] Linux 4.4.38 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index b57ec79b4941..6876efe0d735 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 37 +SUBLEVEL = 38 EXTRAVERSION = NAME = Blurry Fish Butt