diff --git a/Makefile b/Makefile index 607394a56036..57e4ff1a8b96 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 160 +SUBLEVEL = 161 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index a3f750e76b68..8f40c6c5d77e 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -153,6 +153,26 @@ int copy_thread(unsigned long clone_flags, task_thread_info(current)->thr_ptr; } + + /* + * setup usermode thread pointer #1: + * when child is picked by scheduler, __switch_to() uses @c_callee to + * populate usermode callee regs: this works (despite being in a kernel + * function) since special return path for child @ret_from_fork() + * ensures those regs are not clobbered all the way to RTIE to usermode + */ + c_callee->r25 = task_thread_info(p)->thr_ptr; + +#ifdef CONFIG_ARC_CURR_IN_REG + /* + * setup usermode thread pointer #2: + * however for this special use of r25 in kernel, __switch_to() sets + * r25 for kernel needs and only in the final return path is usermode + * r25 setup, from pt_regs->user_r25. So set that up as well + */ + c_regs->user_r25 = c_callee->r25; +#endif + return 0; } diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index c3c835290131..ca3ad5ebcd41 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -360,9 +360,9 @@ static int __init early_fadump_reserve_mem(char *p) } early_param("fadump_reserve_mem", early_fadump_reserve_mem); -static void register_fw_dump(struct fadump_mem_struct *fdm) +static int register_fw_dump(struct fadump_mem_struct *fdm) { - int rc; + int rc, err; unsigned int wait_time; pr_debug("Registering for firmware-assisted kernel dump...\n"); @@ -379,7 +379,11 @@ static void register_fw_dump(struct fadump_mem_struct *fdm) } while (wait_time); + err = -EIO; switch (rc) { + default: + pr_err("Failed to register. Unknown Error(%d).\n", rc); + break; case -1: printk(KERN_ERR "Failed to register firmware-assisted kernel" " dump. Hardware Error(%d).\n", rc); @@ -387,18 +391,22 @@ static void register_fw_dump(struct fadump_mem_struct *fdm) case -3: printk(KERN_ERR "Failed to register firmware-assisted kernel" " dump. Parameter Error(%d).\n", rc); + err = -EINVAL; break; case -9: printk(KERN_ERR "firmware-assisted kernel dump is already " " registered."); fw_dump.dump_registered = 1; + err = -EEXIST; break; case 0: printk(KERN_INFO "firmware-assisted kernel dump registration" " is successful\n"); fw_dump.dump_registered = 1; + err = 0; break; } + return err; } void crash_fadump(struct pt_regs *regs, const char *str) @@ -997,7 +1005,7 @@ static unsigned long init_fadump_header(unsigned long addr) return addr; } -static void register_fadump(void) +static int register_fadump(void) { unsigned long addr; void *vaddr; @@ -1008,7 +1016,7 @@ static void register_fadump(void) * assisted dump. */ if (!fw_dump.reserve_dump_area_size) - return; + return -ENODEV; ret = fadump_setup_crash_memory_ranges(); if (ret) @@ -1023,7 +1031,7 @@ static void register_fadump(void) fadump_create_elfcore_headers(vaddr); /* register the future kernel dump with firmware. */ - register_fw_dump(&fdm); + return register_fw_dump(&fdm); } static int fadump_unregister_dump(struct fadump_mem_struct *fdm) @@ -1208,7 +1216,6 @@ static ssize_t fadump_register_store(struct kobject *kobj, switch (buf[0]) { case '0': if (fw_dump.dump_registered == 0) { - ret = -EINVAL; goto unlock_out; } /* Un-register Firmware-assisted dump */ @@ -1216,11 +1223,11 @@ static ssize_t fadump_register_store(struct kobject *kobj, break; case '1': if (fw_dump.dump_registered == 1) { - ret = -EINVAL; + ret = -EEXIST; goto unlock_out; } /* Register Firmware-assisted dump */ - register_fadump(); + ret = register_fadump(); break; default: ret = -EINVAL; diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 5dd363d54348..049327ee8868 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -51,8 +51,9 @@ extern u8 pvclock_page notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*ts) : + "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : + "memory", "rcx", "r11"); return ret; } @@ -60,8 +61,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm("syscall" : "=a" (ret) : - "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory"); + asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) : + "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : + "memory", "rcx", "r11"); return ret; } @@ -143,13 +145,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[clock], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) + : "=a" (ret), "=m" (*ts) + : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts) : "memory", "edx"); return ret; } @@ -158,13 +160,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) { long ret; - asm( + asm ( "mov %%ebx, %%edx \n" - "mov %2, %%ebx \n" + "mov %[tv], %%ebx \n" "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" - : "=a" (ret) - : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) + : "=a" (ret), "=m" (*tv), "=m" (*tz) + : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz) : "memory", "edx"); return ret; } diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index e9b713675c7c..05409141ec07 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1355,8 +1355,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) dpm_wait_for_children(dev, async); - if (async_error) + if (async_error) { + dev->power.direct_complete = false; goto Complete; + } /* * If a device configured to wake up the system from sleep states @@ -1368,6 +1370,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_wakeup_event(dev, 0); if (pm_wakeup_pending()) { + dev->power.direct_complete = false; async_error = -EBUSY; goto Complete; } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 9712a63957e1..7525e9f6949e 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1709,6 +1709,8 @@ static int ucma_close(struct inode *inode, struct file *filp) mutex_lock(&mut); if (!ctx->closing) { mutex_unlock(&mut); + ucma_put_ctx(ctx); + wait_for_completion(&ctx->comp); /* rdma_destroy_id ensures that no event handlers are * inflight for that id before releasing it. */ diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index b59615ddf6ba..531d6f3a786e 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -3391,8 +3391,13 @@ static dm_cblock_t get_cache_dev_size(struct cache *cache) static bool can_resize(struct cache *cache, dm_cblock_t new_size) { - if (from_cblock(new_size) > from_cblock(cache->cache_size)) - return true; + if (from_cblock(new_size) > from_cblock(cache->cache_size)) { + if (cache->sized) { + DMERR("%s: unable to extend cache due to missing cache table reload", + cache_device_name(cache)); + return false; + } + } /* * We can't drop a dirty block when shrinking the cache. diff --git a/drivers/net/wireless/ath/ath10k/trace.h b/drivers/net/wireless/ath/ath10k/trace.h index 71bdb368813d..0194bebbdbf7 100644 --- a/drivers/net/wireless/ath/ath10k/trace.h +++ b/drivers/net/wireless/ath/ath10k/trace.h @@ -152,10 +152,9 @@ TRACE_EVENT(ath10k_log_dbg_dump, ); TRACE_EVENT(ath10k_wmi_cmd, - TP_PROTO(struct ath10k *ar, int id, const void *buf, size_t buf_len, - int ret), + TP_PROTO(struct ath10k *ar, int id, const void *buf, size_t buf_len), - TP_ARGS(ar, id, buf, buf_len, ret), + TP_ARGS(ar, id, buf, buf_len), TP_STRUCT__entry( __string(device, dev_name(ar->dev)) @@ -163,7 +162,6 @@ TRACE_EVENT(ath10k_wmi_cmd, __field(unsigned int, id) __field(size_t, buf_len) __dynamic_array(u8, buf, buf_len) - __field(int, ret) ), TP_fast_assign( @@ -171,17 +169,15 @@ TRACE_EVENT(ath10k_wmi_cmd, __assign_str(driver, dev_driver_string(ar->dev)); __entry->id = id; __entry->buf_len = buf_len; - __entry->ret = ret; memcpy(__get_dynamic_array(buf), buf, buf_len); ), TP_printk( - "%s %s id %d len %zu ret %d", + "%s %s id %d len %zu", __get_str(driver), __get_str(device), __entry->id, - __entry->buf_len, - __entry->ret + __entry->buf_len ) ); diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c index c72eb4464de9..c27fff39ddae 100644 --- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c +++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c @@ -1459,10 +1459,10 @@ ath10k_wmi_tlv_op_gen_start_scan(struct ath10k *ar, bssid_len = arg->n_bssids * sizeof(struct wmi_mac_addr); ie_len = roundup(arg->ie_len, 4); len = (sizeof(*tlv) + sizeof(*cmd)) + - (arg->n_channels ? sizeof(*tlv) + chan_len : 0) + - (arg->n_ssids ? sizeof(*tlv) + ssid_len : 0) + - (arg->n_bssids ? sizeof(*tlv) + bssid_len : 0) + - (arg->ie_len ? sizeof(*tlv) + ie_len : 0); + sizeof(*tlv) + chan_len + + sizeof(*tlv) + ssid_len + + sizeof(*tlv) + bssid_len + + sizeof(*tlv) + ie_len; skb = ath10k_wmi_alloc_skb(ar, len); if (!skb) diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 7569db0f69b5..5bb1be478954 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -1642,8 +1642,8 @@ int ath10k_wmi_cmd_send_nowait(struct ath10k *ar, struct sk_buff *skb, cmd_hdr->cmd_id = __cpu_to_le32(cmd); memset(skb_cb, 0, sizeof(*skb_cb)); + trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len); ret = ath10k_htc_send(&ar->htc, ar->wmi.eid, skb); - trace_ath10k_wmi_cmd(ar, cmd_id, skb->data, skb->len, ret); if (ret) goto err_pull; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 2a547ca3d443..2eac3df7dd29 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -553,6 +553,9 @@ static void __init of_unittest_parse_interrupts(void) struct of_phandle_args args; int i, rc; + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts0"); if (!np) { pr_err("missing testcase data\n"); @@ -627,6 +630,9 @@ static void __init of_unittest_parse_interrupts_extended(void) struct of_phandle_args args; int i, rc; + if (of_irq_workarounds & OF_IMAP_OLDWORLD_MAC) + return; + np = of_find_node_by_path("/testcase-data/interrupts/interrupts-extended0"); if (!np) { pr_err("missing testcase data\n"); @@ -778,15 +784,19 @@ static void __init of_unittest_platform_populate(void) pdev = of_find_device_by_node(np); unittest(pdev, "device 1 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq == -EPROBE_DEFER, "device deferred probe failed - %d\n", irq); - - /* Test that a parsing failure does not return -EPROBE_DEFER */ - np = of_find_node_by_path("/testcase-data/testcase-device2"); - pdev = of_find_device_by_node(np); - unittest(pdev, "device 2 creation failed\n"); - irq = platform_get_irq(pdev, 0); - unittest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq); + if (!(of_irq_workarounds & OF_IMAP_OLDWORLD_MAC)) { + irq = platform_get_irq(pdev, 0); + unittest(irq == -EPROBE_DEFER, + "device deferred probe failed - %d\n", irq); + + /* Test that a parsing failure does not return -EPROBE_DEFER */ + np = of_find_node_by_path("/testcase-data/testcase-device2"); + pdev = of_find_device_by_node(np); + unittest(pdev, "device 2 creation failed\n"); + irq = platform_get_irq(pdev, 0); + unittest(irq < 0 && irq != -EPROBE_DEFER, + "device parsing error failed - %d\n", irq); + } np = of_find_node_by_path("/testcase-data/platform-tests"); unittest(np, "No testcase data in device tree\n"); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 295bf1472d02..5073ab023123 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1064,12 +1064,12 @@ int pci_save_state(struct pci_dev *dev) EXPORT_SYMBOL(pci_save_state); static void pci_restore_config_dword(struct pci_dev *pdev, int offset, - u32 saved_val, int retry) + u32 saved_val, int retry, bool force) { u32 val; pci_read_config_dword(pdev, offset, &val); - if (val == saved_val) + if (!force && val == saved_val) return; for (;;) { @@ -1088,25 +1088,36 @@ static void pci_restore_config_dword(struct pci_dev *pdev, int offset, } static void pci_restore_config_space_range(struct pci_dev *pdev, - int start, int end, int retry) + int start, int end, int retry, + bool force) { int index; for (index = end; index >= start; index--) pci_restore_config_dword(pdev, 4 * index, pdev->saved_config_space[index], - retry); + retry, force); } static void pci_restore_config_space(struct pci_dev *pdev) { if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL) { - pci_restore_config_space_range(pdev, 10, 15, 0); + pci_restore_config_space_range(pdev, 10, 15, 0, false); /* Restore BARs before the command register. */ - pci_restore_config_space_range(pdev, 4, 9, 10); - pci_restore_config_space_range(pdev, 0, 3, 0); + pci_restore_config_space_range(pdev, 4, 9, 10, false); + pci_restore_config_space_range(pdev, 0, 3, 0, false); + } else if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + pci_restore_config_space_range(pdev, 12, 15, 0, false); + + /* + * Force rewriting of prefetch registers to avoid S3 resume + * issues on Intel PCI bridges that occur when these + * registers are not explicitly written. + */ + pci_restore_config_space_range(pdev, 9, 11, 0, true); + pci_restore_config_space_range(pdev, 0, 8, 0, false); } else { - pci_restore_config_space_range(pdev, 0, 15, 0); + pci_restore_config_space_range(pdev, 0, 15, 0, false); } } diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index cbf3be66f89c..d6e2199bcfe5 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -174,6 +174,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) } if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_XHCI || + pdev->device == PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI || pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) xhci->quirks |= XHCI_MISSING_CAS; diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c index 2674da40d9cd..6d6acf2c07c3 100644 --- a/drivers/usb/serial/usb-serial-simple.c +++ b/drivers/usb/serial/usb-serial-simple.c @@ -87,7 +87,8 @@ DEVICE(moto_modem, MOTO_IDS); /* Motorola Tetra driver */ #define MOTOROLA_TETRA_IDS() \ - { USB_DEVICE(0x0cad, 0x9011) } /* Motorola Solutions TETRA PEI */ + { USB_DEVICE(0x0cad, 0x9011) }, /* Motorola Solutions TETRA PEI */ \ + { USB_DEVICE(0x0cad, 0x9012) } /* MTP6550 */ DEVICE(motorola_tetra, MOTOROLA_TETRA_IDS); /* Novatel Wireless GPS driver */ diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c index 9ddfdd63b84c..34ab4f950f0a 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c @@ -496,6 +496,9 @@ static int omapfb_memory_read(struct fb_info *fbi, if (!access_ok(VERIFY_WRITE, mr->buffer, mr->buffer_size)) return -EFAULT; + if (mr->w > 4096 || mr->h > 4096) + return -EINVAL; + if (mr->w * mr->h * 3 > mr->buffer_size) return -EINVAL; @@ -509,7 +512,7 @@ static int omapfb_memory_read(struct fb_info *fbi, mr->x, mr->y, mr->w, mr->h); if (r > 0) { - if (copy_to_user(mr->buffer, buf, mr->buffer_size)) + if (copy_to_user(mr->buffer, buf, r)) r = -EFAULT; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index b51bb73b06a6..d0aaf338fa9f 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -220,12 +220,12 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) { int error; - if (buffer_verified(bh)) - return 0; - if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) return -EFSCORRUPTED; + if (buffer_verified(bh)) + return 0; + if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) return -EFSBADCRC; error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 0bb6de356451..7968b7a5e787 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1918,6 +1918,9 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) int dev, vol; char *endptr; + if (!name || !*name) + return ERR_PTR(-EINVAL); + /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2ea517c7c6b9..bffd096fae3b 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -125,4 +125,9 @@ extern unsigned int ebt_do_table(struct sk_buff *skb, /* True if the target is not a standard target */ #define INVALID_TARGET (info->target < -NUM_STANDARD_TARGETS || info->target >= 0) +static inline bool ebt_invalid_target(int target) +{ + return (target < -NUM_STANDARD_TARGETS || target >= 0); +} + #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c28bd8be290a..a490dd718654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2273,6 +2273,8 @@ static inline void __skb_queue_purge(struct sk_buff_head *list) kfree_skb(skb); } +void skb_rbtree_purge(struct rb_root *root); + void *netdev_alloc_frag(unsigned int fragsz); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, @@ -2807,6 +2809,12 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) return __pskb_trim(skb, len); } +#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) +#define skb_rb_first(root) rb_to_skb(rb_first(root)) +#define skb_rb_last(root) rb_to_skb(rb_last(root)) +#define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) +#define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 5b6df1a8dc74..747404dbe506 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -279,10 +279,9 @@ struct tcp_sock { struct sk_buff* lost_skb_hint; struct sk_buff *retransmit_skb_hint; - /* OOO segments go in this list. Note that socket lock must be held, - * as we do not use sk_buff_head lock. - */ - struct sk_buff_head out_of_order_queue; + /* OOO segments go in this rbtree. Socket lock must be held. */ + struct rb_root out_of_order_queue; + struct sk_buff *ooo_last_skb; /* cache rb_last(out_of_order_queue) */ /* SACKs data, these 2 need to be together (see tcp_options_write) */ struct tcp_sack_block duplicate_sack[1]; /* D-SACK block */ diff --git a/include/net/sock.h b/include/net/sock.h index 3d5ff7436f41..577075713ad5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2139,6 +2139,13 @@ sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb) SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops); } +static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) +{ + int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs); + + atomic_add(segs, &sk->sk_drops); +} + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, diff --git a/include/net/tcp.h b/include/net/tcp.h index 6c89238f192e..a99f75ef6a73 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -649,7 +649,7 @@ static inline void tcp_fast_path_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - if (skb_queue_empty(&tp->out_of_order_queue) && + if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && tp->rcv_wnd && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && !tp->urg_data) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4cb94b678e9f..5299618d6308 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -4083,7 +4083,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) */ do { css_task_iter_start(&from->self, &it); - task = css_task_iter_next(&it); + + do { + task = css_task_iter_next(&it); + } while (task && (task->flags & PF_EXITING)); + if (task) get_task_struct(task); css_task_iter_end(&it); diff --git a/mm/vmstat.c b/mm/vmstat.c index 5712cdaae964..8895eff2d735 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -858,6 +858,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", +#else + "", /* nr_tlb_remote_flush */ + "", /* nr_tlb_remote_flush_received */ #endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", diff --git a/net/bridge/netfilter/ebt_arpreply.c b/net/bridge/netfilter/ebt_arpreply.c index 070cf134a22f..f2660c1b29e4 100644 --- a/net/bridge/netfilter/ebt_arpreply.c +++ b/net/bridge/netfilter/ebt_arpreply.c @@ -67,6 +67,9 @@ static int ebt_arpreply_tg_check(const struct xt_tgchk_param *par) if (e->ethproto != htons(ETH_P_ARP) || e->invflags & EBT_IPROTO) return -EINVAL; + if (ebt_invalid_target(info->target)) + return -EINVAL; + return 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 55be076706e5..9703924ed071 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2377,6 +2377,25 @@ void skb_queue_purge(struct sk_buff_head *list) } EXPORT_SYMBOL(skb_queue_purge); +/** + * skb_rbtree_purge - empty a skb rbtree + * @root: root of the rbtree to empty + * + * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from + * the list and one reference dropped. This function does not take + * any lock. Synchronization should be handled by the caller (e.g., TCP + * out-of-order queue is protected by the socket lock). + */ +void skb_rbtree_purge(struct rb_root *root) +{ + struct sk_buff *skb, *next; + + rbtree_postorder_for_each_entry_safe(skb, next, root, rbnode) + kfree_skb(skb); + + *root = RB_ROOT; +} + /** * skb_queue_head - queue a buffer at the list head * @list: list to use diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5e162b8ab184..b7492aabe710 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -382,7 +382,7 @@ void tcp_init_sock(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - __skb_queue_head_init(&tp->out_of_order_queue); + tp->out_of_order_queue = RB_ROOT; tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); INIT_LIST_HEAD(&tp->tsq_node); @@ -2240,7 +2240,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); tcp_write_queue_purge(sk); - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9c4c6cd0316e..1aff93d76f24 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4073,7 +4073,7 @@ static void tcp_fin(struct sock *sk) /* It _is_ possible, that we have something out-of-order _after_ FIN. * Probably, we should reset in this case. For now drop them. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); if (tcp_is_sack(tp)) tcp_sack_reset(&tp->rx_opt); sk_mem_reclaim(sk); @@ -4233,7 +4233,7 @@ static void tcp_sack_remove(struct tcp_sock *tp) int this_sack; /* Empty ofo queue, hence, all the SACKs are eaten. Clear. */ - if (skb_queue_empty(&tp->out_of_order_queue)) { + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tp->rx_opt.num_sacks = 0; return; } @@ -4296,6 +4296,29 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static bool tcp_ooo_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + bool res = tcp_try_coalesce(sk, to, from, fragstolen); + + /* In case tcp_drop() is called later, update to->gso_segs */ + if (res) { + u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + + max_t(u16, 1, skb_shinfo(from)->gso_segs); + + skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); + } + return res; +} + +static void tcp_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + __kfree_skb(skb); +} + /* This one checks to see if we can put data from the * out_of_order queue into the receive_queue. */ @@ -4303,10 +4326,13 @@ static void tcp_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); __u32 dsack_high = tp->rcv_nxt; + bool fin, fragstolen, eaten; struct sk_buff *skb, *tail; - bool fragstolen, eaten; + struct rb_node *p; - while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) { + p = rb_first(&tp->out_of_order_queue); + while (p) { + skb = rb_entry(p, struct sk_buff, rbnode); if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) break; @@ -4316,11 +4342,12 @@ static void tcp_ofo_queue(struct sock *sk) dsack_high = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } + p = rb_next(p); + rb_erase(&skb->rbnode, &tp->out_of_order_queue); - __skb_unlink(skb, &tp->out_of_order_queue); - if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { + if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); - __kfree_skb(skb); + tcp_drop(sk, skb); continue; } SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n", @@ -4330,12 +4357,19 @@ static void tcp_ofo_queue(struct sock *sk) tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); - if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) - tcp_fin(sk); - if (eaten) + else kfree_skb_partial(skb, fragstolen); + + if (unlikely(fin)) { + tcp_fin(sk); + /* tcp_fin() purges tp->out_of_order_queue, + * so we must end this loop right now. + */ + break; + } } } @@ -4365,14 +4399,16 @@ static int tcp_try_rmem_schedule(struct sock *sk, struct sk_buff *skb, static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct rb_node **p, *q, *parent; struct sk_buff *skb1; u32 seq, end_seq; + bool fragstolen; tcp_ecn_check_ce(sk, skb); if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFODROP); - __kfree_skb(skb); + tcp_drop(sk, skb); return; } @@ -4381,89 +4417,89 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) inet_csk_schedule_ack(sk); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); + seq = TCP_SKB_CB(skb)->seq; + end_seq = TCP_SKB_CB(skb)->end_seq; SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n", - tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); + tp->rcv_nxt, seq, end_seq); - skb1 = skb_peek_tail(&tp->out_of_order_queue); - if (!skb1) { + p = &tp->out_of_order_queue.rb_node; + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) { /* Initial out of order segment, build 1 SACK. */ if (tcp_is_sack(tp)) { tp->rx_opt.num_sacks = 1; - tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq; - tp->selective_acks[0].end_seq = - TCP_SKB_CB(skb)->end_seq; - } - __skb_queue_head(&tp->out_of_order_queue, skb); - goto end; - } - - seq = TCP_SKB_CB(skb)->seq; - end_seq = TCP_SKB_CB(skb)->end_seq; - - if (seq == TCP_SKB_CB(skb1)->end_seq) { - bool fragstolen; - - if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - } else { - tcp_grow_window(sk, skb); - kfree_skb_partial(skb, fragstolen); - skb = NULL; + tp->selective_acks[0].start_seq = seq; + tp->selective_acks[0].end_seq = end_seq; } - - if (!tp->rx_opt.num_sacks || - tp->selective_acks[0].end_seq != seq) - goto add_sack; - - /* Common case: data arrive in order after hole. */ - tp->selective_acks[0].end_seq = end_seq; + rb_link_node(&skb->rbnode, NULL, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); + tp->ooo_last_skb = skb; goto end; } - /* Find place to insert this segment. */ - while (1) { - if (!after(TCP_SKB_CB(skb1)->seq, seq)) - break; - if (skb_queue_is_first(&tp->out_of_order_queue, skb1)) { - skb1 = NULL; - break; + /* In the typical case, we are adding an skb to the end of the list. + * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. + */ + if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, + skb, &fragstolen)) { +coalesce_done: + tcp_grow_window(sk, skb); + kfree_skb_partial(skb, fragstolen); + skb = NULL; + goto add_sack; + } + + /* Find place to insert this segment. Handle overlaps on the way. */ + parent = NULL; + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(seq, TCP_SKB_CB(skb1)->seq)) { + p = &parent->rb_left; + continue; } - skb1 = skb_queue_prev(&tp->out_of_order_queue, skb1); - } - /* Do skb overlap to previous one? */ - if (skb1 && before(seq, TCP_SKB_CB(skb1)->end_seq)) { - if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { - /* All the bits are present. Drop. */ - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); - skb = NULL; - tcp_dsack_set(sk, seq, end_seq); - goto add_sack; - } - if (after(seq, TCP_SKB_CB(skb1)->seq)) { - /* Partial overlap. */ - tcp_dsack_set(sk, seq, - TCP_SKB_CB(skb1)->end_seq); - } else { - if (skb_queue_is_first(&tp->out_of_order_queue, - skb1)) - skb1 = NULL; - else - skb1 = skb_queue_prev( - &tp->out_of_order_queue, - skb1); + if (before(seq, TCP_SKB_CB(skb1)->end_seq)) { + if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) { + /* All the bits are present. Drop. */ + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + tcp_drop(sk, skb); + skb = NULL; + tcp_dsack_set(sk, seq, end_seq); + goto add_sack; + } + if (after(seq, TCP_SKB_CB(skb1)->seq)) { + /* Partial overlap. */ + tcp_dsack_set(sk, seq, TCP_SKB_CB(skb1)->end_seq); + } else { + /* skb's seq == skb1's seq and skb covers skb1. + * Replace skb1 with skb. + */ + rb_replace_node(&skb1->rbnode, &skb->rbnode, + &tp->out_of_order_queue); + tcp_dsack_extend(sk, + TCP_SKB_CB(skb1)->seq, + TCP_SKB_CB(skb1)->end_seq); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPOFOMERGE); + tcp_drop(sk, skb1); + goto merge_right; + } + } else if (tcp_ooo_try_coalesce(sk, skb1, + skb, &fragstolen)) { + goto coalesce_done; } + p = &parent->rb_right; } - if (!skb1) - __skb_queue_head(&tp->out_of_order_queue, skb); - else - __skb_queue_after(&tp->out_of_order_queue, skb1, skb); - /* And clean segments covered by new one as whole. */ - while (!skb_queue_is_last(&tp->out_of_order_queue, skb)) { - skb1 = skb_queue_next(&tp->out_of_order_queue, skb); + /* Insert segment into RB tree. */ + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, &tp->out_of_order_queue); +merge_right: + /* Remove other segments covered by skb. */ + while ((q = rb_next(&skb->rbnode)) != NULL) { + skb1 = rb_entry(q, struct sk_buff, rbnode); if (!after(end_seq, TCP_SKB_CB(skb1)->seq)) break; if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) { @@ -4471,12 +4507,15 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) end_seq); break; } - __skb_unlink(skb1, &tp->out_of_order_queue); + rb_erase(&skb1->rbnode, &tp->out_of_order_queue); tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); } + /* If there is no skb after us, we are the last_skb ! */ + if (!q) + tp->ooo_last_skb = skb; add_sack: if (tcp_is_sack(tp)) @@ -4558,12 +4597,13 @@ err: static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); - int eaten = -1; bool fragstolen = false; + int eaten = -1; - if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) - goto drop; - + if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { + __kfree_skb(skb); + return; + } skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); @@ -4614,13 +4654,13 @@ queue_and_out: if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); - if (!skb_queue_empty(&tp->out_of_order_queue)) { + if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) { tcp_ofo_queue(sk); /* RFC2581. 4.2. SHOULD send immediate ACK, when * gap in queue is filled. */ - if (skb_queue_empty(&tp->out_of_order_queue)) + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) inet_csk(sk)->icsk_ack.pingpong = 0; } @@ -4645,7 +4685,7 @@ out_of_window: tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); inet_csk_schedule_ack(sk); drop: - __kfree_skb(skb); + tcp_drop(sk, skb); return; } @@ -4672,48 +4712,76 @@ drop: tcp_data_queue_ofo(sk, skb); } +static struct sk_buff *tcp_skb_next(struct sk_buff *skb, struct sk_buff_head *list) +{ + if (list) + return !skb_queue_is_last(list, skb) ? skb->next : NULL; + + return rb_entry_safe(rb_next(&skb->rbnode), struct sk_buff, rbnode); +} + static struct sk_buff *tcp_collapse_one(struct sock *sk, struct sk_buff *skb, - struct sk_buff_head *list) + struct sk_buff_head *list, + struct rb_root *root) { - struct sk_buff *next = NULL; + struct sk_buff *next = tcp_skb_next(skb, list); - if (!skb_queue_is_last(list, skb)) - next = skb_queue_next(list, skb); + if (list) + __skb_unlink(skb, list); + else + rb_erase(&skb->rbnode, root); - __skb_unlink(skb, list); __kfree_skb(skb); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRCVCOLLAPSED); return next; } +/* Insert skb into rb tree, ordered by TCP_SKB_CB(skb)->seq */ +static void tcp_rbtree_insert(struct rb_root *root, struct sk_buff *skb) +{ + struct rb_node **p = &root->rb_node; + struct rb_node *parent = NULL; + struct sk_buff *skb1; + + while (*p) { + parent = *p; + skb1 = rb_entry(parent, struct sk_buff, rbnode); + if (before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb1)->seq)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node(&skb->rbnode, parent, p); + rb_insert_color(&skb->rbnode, root); +} + /* Collapse contiguous sequence of skbs head..tail with * sequence numbers start..end. * - * If tail is NULL, this means until the end of the list. + * If tail is NULL, this means until the end of the queue. * * Segments with FIN/SYN are not collapsed (only because this * simplifies code) */ static void -tcp_collapse(struct sock *sk, struct sk_buff_head *list, - struct sk_buff *head, struct sk_buff *tail, - u32 start, u32 end) +tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root, + struct sk_buff *head, struct sk_buff *tail, u32 start, u32 end) { - struct sk_buff *skb, *n; + struct sk_buff *skb = head, *n; + struct sk_buff_head tmp; bool end_of_skbs; /* First, check that queue is collapsible and find - * the point where collapsing can be useful. */ - skb = head; + * the point where collapsing can be useful. + */ restart: - end_of_skbs = true; - skb_queue_walk_from_safe(list, skb, n) { - if (skb == tail) - break; + for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { + n = tcp_skb_next(skb, list); + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb) break; goto restart; @@ -4731,13 +4799,10 @@ restart: break; } - if (!skb_queue_is_last(list, skb)) { - struct sk_buff *next = skb_queue_next(list, skb); - if (next != tail && - TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(next)->seq) { - end_of_skbs = false; - break; - } + if (n && n != tail && + TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { + end_of_skbs = false; + break; } /* Decided to skip this, advance start seq. */ @@ -4747,17 +4812,22 @@ restart: (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) return; + __skb_queue_head_init(&tmp); + while (before(start, end)) { int copy = min_t(int, SKB_MAX_ORDER(0, 0), end - start); struct sk_buff *nskb; nskb = alloc_skb(copy, GFP_ATOMIC); if (!nskb) - return; + break; memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start; - __skb_queue_before(list, skb, nskb); + if (list) + __skb_queue_before(list, skb, nskb); + else + __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); /* Copy data, releasing collapsed skbs. */ @@ -4775,14 +4845,17 @@ restart: start += size; } if (!before(start, TCP_SKB_CB(skb)->end_seq)) { - skb = tcp_collapse_one(sk, skb, list); + skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) - return; + goto end; } } } +end: + skb_queue_walk_safe(&tmp, skb, n) + tcp_rbtree_insert(root, skb); } /* Collapse ofo queue. Algorithm: select contiguous sequence of skbs @@ -4792,34 +4865,39 @@ static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 range_truesize, sum_tiny = 0; - struct sk_buff *skb = skb_peek(&tp->out_of_order_queue); - struct sk_buff *head; + struct sk_buff *skb, *head; + struct rb_node *p; u32 start, end; - if (!skb) + p = rb_first(&tp->out_of_order_queue); + skb = rb_entry_safe(p, struct sk_buff, rbnode); +new_range: + if (!skb) { + p = rb_last(&tp->out_of_order_queue); + /* Note: This is possible p is NULL here. We do not + * use rb_entry_safe(), as ooo_last_skb is valid only + * if rbtree is not empty. + */ + tp->ooo_last_skb = rb_entry(p, struct sk_buff, rbnode); return; - + } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; range_truesize = skb->truesize; - head = skb; - for (;;) { - struct sk_buff *next = NULL; + for (head = skb;;) { + skb = tcp_skb_next(skb, NULL); - if (!skb_queue_is_last(&tp->out_of_order_queue, skb)) - next = skb_queue_next(&tp->out_of_order_queue, skb); - skb = next; - - /* Segment is terminated when we see gap or when - * we are at the end of all the queue. */ + /* Range is terminated when we see a gap or when + * we are at the queue end. + */ if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { /* Do not attempt collapsing tiny skbs */ if (range_truesize != head->truesize || end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { - tcp_collapse(sk, &tp->out_of_order_queue, + tcp_collapse(sk, NULL, &tp->out_of_order_queue, head, skb, start, end); } else { sum_tiny += range_truesize; @@ -4827,47 +4905,60 @@ static void tcp_collapse_ofo_queue(struct sock *sk) return; } - head = skb; - if (!skb) - break; - /* Start new segment */ + goto new_range; + } + + range_truesize += skb->truesize; + if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; + if (after(TCP_SKB_CB(skb)->end_seq, end)) end = TCP_SKB_CB(skb)->end_seq; - range_truesize = skb->truesize; - } else { - range_truesize += skb->truesize; - if (before(TCP_SKB_CB(skb)->seq, start)) - start = TCP_SKB_CB(skb)->seq; - if (after(TCP_SKB_CB(skb)->end_seq, end)) - end = TCP_SKB_CB(skb)->end_seq; - } } } /* * Purge the out-of-order queue. + * Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * Return true if queue was pruned. */ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - bool res = false; + struct rb_node *node, *prev; + int goal; - if (!skb_queue_empty(&tp->out_of_order_queue)) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_OFOPRUNED); - __skb_queue_purge(&tp->out_of_order_queue); + if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) + return false; - /* Reset SACK state. A conforming SACK implementation will - * do the same at a timeout based retransmit. When a connection - * is in a sad state like this, we care only about integrity - * of the connection not performance. - */ - if (tp->rx_opt.sack_ok) - tcp_sack_reset(&tp->rx_opt); - sk_mem_reclaim(sk); - res = true; - } - return res; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; + node = &tp->ooo_last_skb->rbnode; + do { + prev = rb_prev(node); + rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; + __kfree_skb(rb_to_skb(node)); + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } + + node = prev; + } while (node); + tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode); + + /* Reset SACK state. A conforming SACK implementation will + * do the same at a timeout based retransmit. When a connection + * is in a sad state like this, we care only about integrity + * of the connection not performance. + */ + if (tp->rx_opt.sack_ok) + tcp_sack_reset(&tp->rx_opt); + + return true; } /* Reduce allocated memory if we can, trying to get @@ -4895,7 +4986,7 @@ static int tcp_prune_queue(struct sock *sk) tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) - tcp_collapse(sk, &sk->sk_receive_queue, + tcp_collapse(sk, &sk->sk_receive_queue, NULL, skb_peek(&sk->sk_receive_queue), NULL, tp->copied_seq, tp->rcv_nxt); @@ -5000,7 +5091,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ - (ofo_possible && skb_peek(&tp->out_of_order_queue))) { + (ofo_possible && !RB_EMPTY_ROOT(&tp->out_of_order_queue))) { /* Then ack it now */ tcp_send_ack(sk); } else { @@ -5236,7 +5327,7 @@ syn_challenge: return true; discard: - __kfree_skb(skb); + tcp_drop(sk, skb); return false; } @@ -5454,7 +5545,7 @@ csum_error: TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS); discard: - __kfree_skb(skb); + tcp_drop(sk, skb); } EXPORT_SYMBOL(tcp_rcv_established); @@ -5684,7 +5775,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, TCP_DELACK_MAX, TCP_RTO_MAX); discard: - __kfree_skb(skb); + tcp_drop(sk, skb); return 0; } else { tcp_send_ack(sk); @@ -6041,7 +6132,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (!queued) { discard: - __kfree_skb(skb); + tcp_drop(sk, skb); } return 0; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index eeda67c3dd11..ee8399f11fd0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1716,6 +1716,7 @@ discard_it: return 0; discard_and_relse: + sk_drops_add(sk, skb); sock_put(sk); goto discard_it; @@ -1829,7 +1830,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_write_queue_purge(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ - __skb_queue_purge(&tp->out_of_order_queue); + skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d270870bf492..a48846d81b41 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -496,7 +496,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->snd_cwnd_cnt = 0; tcp_init_xmit_timers(newsk); - __skb_queue_head_init(&newtp->out_of_order_queue); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; newtp->rx_opt.saw_tstamp = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 90abe88e1b40..d6c191158e07 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1505,6 +1505,7 @@ discard_it: return 0; discard_and_relse: + sk_drops_add(sk, skb); sock_put(sk); goto discard_it; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 1f930032253a..67348d8ac35d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -219,7 +219,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ - if (key->sta && test_sta_flag(key->sta, WLAN_STA_MFP)) + if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: