6d62ca19a7
Changes in 5.10.181 driver core: add a helper to setup both the of_node and fwnode of a device drm/mipi-dsi: Set the fwnode for mipi_dsi_device ARM: 9296/1: HP Jornada 7XX: fix kernel-doc warnings net: mdio: mvusb: Fix an error handling path in mvusb_mdio_probe() linux/dim: Do nothing if no time delta between samples net: Fix load-tearing on sk->sk_stamp in sock_recv_cmsgs(). netfilter: conntrack: fix possible bug_on with enable_hooks=1 netlink: annotate accesses to nlk->cb_running net: annotate sk->sk_err write from do_recvmmsg() net: deal with most data-races in sk_wait_event() net: tap: check vlan with eth_type_vlan() method net: add vlan_get_protocol_and_depth() helper tcp: factor out __tcp_close() helper tcp: add annotations around sk->sk_shutdown accesses ipvlan:Fix out-of-bounds caused by unclear skb->cb net: datagram: fix data-races in datagram_poll() af_unix: Fix a data race of sk->sk_receive_queue->qlen. af_unix: Fix data races around sk->sk_shutdown. drm/i915/dp: prevent potential div-by-zero fbdev: arcfb: Fix error handling in arcfb_probe() ext4: remove an unused variable warning with CONFIG_QUOTA=n ext4: reflect error codes from ext4_multi_mount_protect() to its callers ext4: don't clear SB_RDONLY when remounting r/w until quota is re-enabled ext4: fix lockdep warning when enabling MMP ext4: remove redundant mb_regenerate_buddy() ext4: drop s_mb_bal_lock and convert protected fields to atomic ext4: add mballoc stats proc file ext4: allow to find by goal if EXT4_MB_HINT_GOAL_ONLY is set ext4: allow ext4_get_group_info() to fail refscale: Move shutdown from wait_event() to wait_event_idle() rcu: Protect rcu_print_task_exp_stall() ->exp_tasks access fs: hfsplus: remove WARN_ON() from hfsplus_cat_{read,write}_inode() drm/amd/display: Use DC_LOG_DC in the trasform pixel function regmap: cache: Return error in cache sync operations for REGCACHE_NONE arm64: dts: qcom: msm8996: Add missing DWC3 quirks memstick: r592: Fix UAF bug in r592_remove due to race condition firmware: arm_sdei: Fix sleep from invalid context BUG ACPI: EC: Fix oops when removing custom query handlers remoteproc: stm32_rproc: Add mutex protection for workqueue drm/tegra: Avoid potential 32-bit integer overflow ACPICA: Avoid undefined behavior: applying zero offset to null pointer ACPICA: ACPICA: check null return of ACPI_ALLOCATE_ZEROED in acpi_db_display_objects drm/amd: Fix an out of bounds error in BIOS parser wifi: ath: Silence memcpy run-time false positive warning bpf: Annotate data races in bpf_local_storage wifi: brcmfmac: cfg80211: Pass the PMK in binary instead of hex ext2: Check block size validity during mount scsi: lpfc: Prevent lpfc_debugfs_lockstat_write() buffer overflow net: pasemi: Fix return type of pasemi_mac_start_tx() net: Catch invalid index in XPS mapping scsi: target: iscsit: Free cmds before session free lib: cpu_rmap: Avoid use after free on rmap->obj array entries scsi: message: mptlan: Fix use after free bug in mptlan_remove() due to race condition gfs2: Fix inode height consistency check ext4: set goal start correctly in ext4_mb_normalize_request ext4: Fix best extent lstart adjustment logic in ext4_mb_new_inode_pa() f2fs: fix to drop all dirty pages during umount() if cp_error is set samples/bpf: Fix fout leak in hbm's run_bpf_prog wifi: iwlwifi: pcie: fix possible NULL pointer dereference wifi: iwlwifi: pcie: Fix integer overflow in iwl_write_to_user_buf null_blk: Always check queue mode setting from configfs wifi: iwlwifi: dvm: Fix memcpy: detected field-spanning write backtrace wifi: ath11k: Fix SKB corruption in REO destination ring ipvs: Update width of source for ip_vs_sync_conn_options Bluetooth: hci_bcm: Fall back to getting bdaddr from EFI if not set Bluetooth: L2CAP: fix "bad unlock balance" in l2cap_disconnect_rsp staging: rtl8192e: Replace macro RTL_PCI_DEVICE with PCI_DEVICE HID: logitech-hidpp: Don't use the USB serial for USB devices HID: logitech-hidpp: Reconcile USB and Unifying serials spi: spi-imx: fix MX51_ECSPI_* macros when cs > 3 HID: wacom: generic: Set battery quirk only when we see battery data usb: typec: tcpm: fix multiple times discover svids error serial: 8250: Reinit port->pm on port specific driver unbind mcb-pci: Reallocate memory region to avoid memory overlapping sched: Fix KCSAN noinstr violation recordmcount: Fix memory leaks in the uwrite function RDMA/core: Fix multiple -Warray-bounds warnings iommu/arm-smmu-qcom: Limit the SMR groups to 128 clk: tegra20: fix gcc-7 constant overflow warning iommu/arm-smmu-v3: Acknowledge pri/event queue overflow if any Input: xpad - add constants for GIP interface numbers phy: st: miphy28lp: use _poll_timeout functions for waits mfd: dln2: Fix memory leak in dln2_probe() btrfs: move btrfs_find_highest_objectid/btrfs_find_free_objectid to disk-io.c btrfs: replace calls to btrfs_find_free_ino with btrfs_find_free_objectid btrfs: fix space cache inconsistency after error loading it from disk xfrm: don't check the default policy if the policy allows the packet Revert "Fix XFRM-I support for nested ESP tunnels" drm/msm/dp: unregister audio driver during unbind drm/msm/dpu: Remove duplicate register defines from INTF cpupower: Make TSC read per CPU for Mperf monitor af_key: Reject optional tunnel/BEET mode templates in outbound policies net: fec: Better handle pm_runtime_get() failing in .remove() net: phy: dp83867: add w/a for packet errors seen with short cables ALSA: firewire-digi00x: prevent potential use after free ALSA: hda/realtek: Apply HP B&O top speaker profile to Pavilion 15 vsock: avoid to close connected socket after the timeout ipv4/tcp: do not use per netns ctl sockets net: Find dst with sk's xfrm policy not ctl_sk tcp: fix possible sk_priority leak in tcp_v4_send_reset() serial: arc_uart: fix of_iomap leak in `arc_serial_probe` erspan: get the proto with the md version for collect_md net: hns3: fix sending pfc frames after reset issue net: hns3: fix reset delay time to avoid configuration timeout media: netup_unidvb: fix use-after-free at del_timer() SUNRPC: Fix trace_svc_register() call site drm/exynos: fix g2d_open/close helper function definitions net: nsh: Use correct mac_offset to unwind gso skb in nsh_gso_segment() net/tipc: fix tipc header files for kernel-doc tipc: add tipc_bearer_min_mtu to calculate min mtu tipc: do not update mtu if msg_max is too small in mtu negotiation tipc: check the bearer min mtu properly when setting it by netlink net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop() net: bcmgenet: Restore phy_stop() depending upon suspend/close wifi: mac80211: fix min center freq offset tracing wifi: iwlwifi: mvm: don't trust firmware n_channels scsi: storvsc: Don't pass unused PFNs to Hyper-V host cassini: Fix a memory leak in the error handling path of cas_init_one() igb: fix bit_shift to be in [1..8] range vlan: fix a potential uninit-value in vlan_dev_hard_start_xmit() netfilter: nft_set_rbtree: fix null deref on element insertion bridge: always declare tunnel functions ALSA: usb-audio: Add a sample rate workaround for Line6 Pod Go USB: usbtmc: Fix direction for 0-length ioctl control messages usb-storage: fix deadlock when a scsi command timeouts more than once USB: UHCI: adjust zhaoxin UHCI controllers OverCurrent bit value usb: dwc3: debugfs: Resume dwc3 before accessing registers usb: gadget: u_ether: Fix host MAC address case usb: typec: altmodes/displayport: fix pin_assignment_show ALSA: hda: Fix Oops by 9.1 surround channel names ALSA: hda: Add NVIDIA codec IDs a3 through a7 to patch table ALSA: hda/realtek: Add quirk for Clevo L140AU ALSA: hda/realtek: Add a quirk for HP EliteDesk 805 ALSA: hda/realtek: Add quirk for 2nd ASUS GU603 can: j1939: recvmsg(): allow MSG_CMSG_COMPAT flag can: isotp: recvmsg(): allow MSG_CMSG_COMPAT flag can: kvaser_pciefd: Set CAN_STATE_STOPPED in kvaser_pciefd_stop() can: kvaser_pciefd: Call request_irq() before enabling interrupts can: kvaser_pciefd: Empty SRB buffer in probe can: kvaser_pciefd: Clear listen-only bit if not explicitly requested can: kvaser_pciefd: Do not send EFLUSH command on TFD interrupt can: kvaser_pciefd: Disable interrupts in probe error path statfs: enforce statfs[64] structure initialization serial: Add support for Advantech PCI-1611U card vc_screen: reload load of struct vc_data pointer in vcs_write() to avoid UAF ceph: force updating the msg pointer in non-split case tpm/tpm_tis: Disable interrupts for more Lenovo devices powerpc/64s/radix: Fix soft dirty tracking nilfs2: fix use-after-free bug of nilfs_root in nilfs_evict_inode() HID: wacom: Force pen out of prox if no events have been received in a while HID: wacom: Add new Intuos Pro Small (PTH-460) device IDs HID: wacom: add three styli to wacom_intuos_get_tool_type KVM: arm64: Link position-independent string routines into .hyp.text serial: 8250_exar: derive nr_ports from PCI ID for Acces I/O cards serial: exar: Add support for Sealevel 7xxxC serial cards serial: 8250_exar: Add support for USR298x PCI Modems s390/qdio: get rid of register asm s390/qdio: fix do_sqbs() inline assembly constraint watchdog: sp5100_tco: Immediately trigger upon starting. ARM: dts: stm32: fix AV96 board SAI2 pin muxing on stm32mp15 writeback, cgroup: remove extra percpu_ref_exit() net/sched: act_mirred: refactor the handle of xmit net/sched: act_mirred: better wording on protection against excessive stack growth act_mirred: use the backlog for nested calls to mirred ingress spi: fsl-spi: Re-organise transfer bits_per_word adaptation spi: fsl-cpm: Use 16 bit mode for large transfers with even size ocfs2: Switch to security_inode_init_security() ALSA: hda/ca0132: add quirk for EVGA X299 DARK ALSA: hda: Fix unhandled register update during auto-suspend period ALSA: hda/realtek: Enable headset onLenovo M70/M90 net: cdc_ncm: Deal with too low values of dwNtbOutMaxSize m68k: Move signal frame following exception on 68020/030 parisc: Handle kgdb breakpoints only in kernel context parisc: Allow to reboot machine after system halt gpio: mockup: Fix mode of debugfs files btrfs: use nofs when cleaning up aborted transactions dt-binding: cdns,usb3: Fix cdns,on-chip-buff-size type x86/mm: Avoid incomplete Global INVLPG flushes selftests/memfd: Fix unknown type name build failure parisc: Fix flush_dcache_page() for usage from irq context x86/topology: Fix erroneous smp_num_siblings on Intel Hybrid platforms debugobjects: Don't wake up kswapd from fill_pool() fbdev: udlfb: Fix endpoint check net: fix stack overflow when LRO is disabled for virtual interfaces udplite: Fix NULL pointer dereference in __sk_mem_raise_allocated(). USB: core: Add routines for endpoint checks in old drivers USB: sisusbvga: Add endpoint checks media: radio-shark: Add endpoint checks net: fix skb leak in __skb_tstamp_tx() selftests: fib_tests: mute cleanup error message octeontx2-pf: Fix TSOv6 offload bpf: Fix mask generation for 32-bit narrow loads of 64-bit fields ipv6: Fix out-of-bounds access in ipv6_find_tlv() power: supply: leds: Fix blink to LED on transition power: supply: bq27xxx: Fix bq27xxx_battery_update() race condition power: supply: bq27xxx: Fix I2C IRQ race on remove power: supply: bq27xxx: Fix poll_interval handling and races on remove power: supply: sbs-charger: Fix INHIBITED bit for Status reg fs: fix undefined behavior in bit shift for SB_NOUSER coresight: Fix signedness bug in tmc_etr_buf_insert_barrier_packet() xen/pvcalls-back: fix double frees with pvcalls_new_active_socket() x86/show_trace_log_lvl: Ensure stack pointer is aligned, again ASoC: Intel: Skylake: Fix declaration of enum skl_ch_cfg forcedeth: Fix an error handling path in nv_probe() net/mlx5e: do as little as possible in napi poll when budget is 0 net/mlx5: DR, Fix crc32 calculation to work on big-endian (BE) CPUs net/mlx5: Fix error message when failing to allocate device memory net/mlx5: Devcom, fix error flow in mlx5_devcom_register_device arm64: dts: imx8mn-var-som: fix PHY detection bug by adding deassert delay 3c589_cs: Fix an error handling path in tc589_probe() net: phy: mscc: add VSC8502 to MODULE_DEVICE_TABLE Linux 5.10.181 Change-Id: Iaad0b0bb7c1ad061b28ad4ee16e03db935241177 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
1334 lines
33 KiB
C
1334 lines
33 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __NET_SCHED_GENERIC_H
|
|
#define __NET_SCHED_GENERIC_H
|
|
|
|
#include <linux/netdevice.h>
|
|
#include <linux/types.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/pkt_sched.h>
|
|
#include <linux/pkt_cls.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/dynamic_queue_limits.h>
|
|
#include <linux/list.h>
|
|
#include <linux/refcount.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/hashtable.h>
|
|
#include <linux/android_kabi.h>
|
|
#include <net/gen_stats.h>
|
|
#include <net/rtnetlink.h>
|
|
#include <net/flow_offload.h>
|
|
|
|
struct Qdisc_ops;
|
|
struct qdisc_walker;
|
|
struct tcf_walker;
|
|
struct module;
|
|
struct bpf_flow_keys;
|
|
|
|
struct qdisc_rate_table {
|
|
struct tc_ratespec rate;
|
|
u32 data[256];
|
|
struct qdisc_rate_table *next;
|
|
int refcnt;
|
|
};
|
|
|
|
enum qdisc_state_t {
|
|
__QDISC_STATE_SCHED,
|
|
__QDISC_STATE_DEACTIVATED,
|
|
__QDISC_STATE_MISSED,
|
|
};
|
|
|
|
struct qdisc_size_table {
|
|
struct rcu_head rcu;
|
|
struct list_head list;
|
|
struct tc_sizespec szopts;
|
|
int refcnt;
|
|
u16 data[];
|
|
};
|
|
|
|
/* similar to sk_buff_head, but skb->prev pointer is undefined. */
|
|
struct qdisc_skb_head {
|
|
struct sk_buff *head;
|
|
struct sk_buff *tail;
|
|
__u32 qlen;
|
|
spinlock_t lock;
|
|
};
|
|
|
|
struct Qdisc {
|
|
int (*enqueue)(struct sk_buff *skb,
|
|
struct Qdisc *sch,
|
|
struct sk_buff **to_free);
|
|
struct sk_buff * (*dequeue)(struct Qdisc *sch);
|
|
unsigned int flags;
|
|
#define TCQ_F_BUILTIN 1
|
|
#define TCQ_F_INGRESS 2
|
|
#define TCQ_F_CAN_BYPASS 4
|
|
#define TCQ_F_MQROOT 8
|
|
#define TCQ_F_ONETXQUEUE 0x10 /* dequeue_skb() can assume all skbs are for
|
|
* q->dev_queue : It can test
|
|
* netif_xmit_frozen_or_stopped() before
|
|
* dequeueing next packet.
|
|
* Its true for MQ/MQPRIO slaves, or non
|
|
* multiqueue device.
|
|
*/
|
|
#define TCQ_F_WARN_NONWC (1 << 16)
|
|
#define TCQ_F_CPUSTATS 0x20 /* run using percpu statistics */
|
|
#define TCQ_F_NOPARENT 0x40 /* root of its hierarchy :
|
|
* qdisc_tree_decrease_qlen() should stop.
|
|
*/
|
|
#define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */
|
|
#define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */
|
|
#define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */
|
|
u32 limit;
|
|
const struct Qdisc_ops *ops;
|
|
struct qdisc_size_table __rcu *stab;
|
|
struct hlist_node hash;
|
|
u32 handle;
|
|
u32 parent;
|
|
|
|
struct netdev_queue *dev_queue;
|
|
|
|
struct net_rate_estimator __rcu *rate_est;
|
|
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
|
|
struct gnet_stats_queue __percpu *cpu_qstats;
|
|
int pad;
|
|
refcount_t refcnt;
|
|
|
|
/*
|
|
* For performance sake on SMP, we put highly modified fields at the end
|
|
*/
|
|
struct sk_buff_head gso_skb ____cacheline_aligned_in_smp;
|
|
struct qdisc_skb_head q;
|
|
struct gnet_stats_basic_packed bstats;
|
|
seqcount_t running;
|
|
struct gnet_stats_queue qstats;
|
|
unsigned long state;
|
|
struct Qdisc *next_sched;
|
|
struct sk_buff_head skb_bad_txq;
|
|
|
|
spinlock_t busylock ____cacheline_aligned_in_smp;
|
|
spinlock_t seqlock;
|
|
|
|
/* for NOLOCK qdisc, true if there are no enqueued skbs */
|
|
bool empty;
|
|
struct rcu_head rcu;
|
|
|
|
ANDROID_KABI_RESERVE(1);
|
|
|
|
/* private data */
|
|
long privdata[] ____cacheline_aligned;
|
|
};
|
|
|
|
static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
|
|
{
|
|
if (qdisc->flags & TCQ_F_BUILTIN)
|
|
return;
|
|
refcount_inc(&qdisc->refcnt);
|
|
}
|
|
|
|
/* Intended to be used by unlocked users, when concurrent qdisc release is
|
|
* possible.
|
|
*/
|
|
|
|
static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc)
|
|
{
|
|
if (qdisc->flags & TCQ_F_BUILTIN)
|
|
return qdisc;
|
|
if (refcount_inc_not_zero(&qdisc->refcnt))
|
|
return qdisc;
|
|
return NULL;
|
|
}
|
|
|
|
static inline bool qdisc_is_running(struct Qdisc *qdisc)
|
|
{
|
|
if (qdisc->flags & TCQ_F_NOLOCK)
|
|
return spin_is_locked(&qdisc->seqlock);
|
|
return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
|
|
}
|
|
|
|
static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
|
|
{
|
|
return q->flags & TCQ_F_CPUSTATS;
|
|
}
|
|
|
|
static inline bool qdisc_is_empty(const struct Qdisc *qdisc)
|
|
{
|
|
if (qdisc_is_percpu_stats(qdisc))
|
|
return READ_ONCE(qdisc->empty);
|
|
return !READ_ONCE(qdisc->q.qlen);
|
|
}
|
|
|
|
static inline bool qdisc_run_begin(struct Qdisc *qdisc)
|
|
{
|
|
if (qdisc->flags & TCQ_F_NOLOCK) {
|
|
if (spin_trylock(&qdisc->seqlock))
|
|
goto nolock_empty;
|
|
|
|
/* No need to insist if the MISSED flag was already set.
|
|
* Note that test_and_set_bit() also gives us memory ordering
|
|
* guarantees wrt potential earlier enqueue() and below
|
|
* spin_trylock(), both of which are necessary to prevent races
|
|
*/
|
|
if (test_and_set_bit(__QDISC_STATE_MISSED, &qdisc->state))
|
|
return false;
|
|
|
|
/* Try to take the lock again to make sure that we will either
|
|
* grab it or the CPU that still has it will see MISSED set
|
|
* when testing it in qdisc_run_end()
|
|
*/
|
|
if (!spin_trylock(&qdisc->seqlock))
|
|
return false;
|
|
|
|
nolock_empty:
|
|
WRITE_ONCE(qdisc->empty, false);
|
|
} else if (qdisc_is_running(qdisc)) {
|
|
return false;
|
|
}
|
|
/* Variant of write_seqcount_begin() telling lockdep a trylock
|
|
* was attempted.
|
|
*/
|
|
raw_write_seqcount_begin(&qdisc->running);
|
|
seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
|
|
return true;
|
|
}
|
|
|
|
static inline void qdisc_run_end(struct Qdisc *qdisc)
|
|
{
|
|
write_seqcount_end(&qdisc->running);
|
|
if (qdisc->flags & TCQ_F_NOLOCK) {
|
|
spin_unlock(&qdisc->seqlock);
|
|
|
|
/* spin_unlock() only has store-release semantic. The unlock
|
|
* and test_bit() ordering is a store-load ordering, so a full
|
|
* memory barrier is needed here.
|
|
*/
|
|
smp_mb();
|
|
|
|
if (unlikely(test_bit(__QDISC_STATE_MISSED,
|
|
&qdisc->state))) {
|
|
clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
|
|
__netif_schedule(qdisc);
|
|
}
|
|
}
|
|
}
|
|
|
|
static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
|
|
{
|
|
return qdisc->flags & TCQ_F_ONETXQUEUE;
|
|
}
|
|
|
|
static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
|
|
{
|
|
#ifdef CONFIG_BQL
|
|
/* Non-BQL migrated drivers will return 0, too. */
|
|
return dql_avail(&txq->dql);
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
struct Qdisc_class_ops {
|
|
unsigned int flags;
|
|
/* Child qdisc manipulation */
|
|
struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *);
|
|
int (*graft)(struct Qdisc *, unsigned long cl,
|
|
struct Qdisc *, struct Qdisc **,
|
|
struct netlink_ext_ack *extack);
|
|
struct Qdisc * (*leaf)(struct Qdisc *, unsigned long cl);
|
|
void (*qlen_notify)(struct Qdisc *, unsigned long);
|
|
|
|
/* Class manipulation routines */
|
|
unsigned long (*find)(struct Qdisc *, u32 classid);
|
|
int (*change)(struct Qdisc *, u32, u32,
|
|
struct nlattr **, unsigned long *,
|
|
struct netlink_ext_ack *);
|
|
int (*delete)(struct Qdisc *, unsigned long);
|
|
void (*walk)(struct Qdisc *, struct qdisc_walker * arg);
|
|
|
|
/* Filter manipulation */
|
|
struct tcf_block * (*tcf_block)(struct Qdisc *sch,
|
|
unsigned long arg,
|
|
struct netlink_ext_ack *extack);
|
|
unsigned long (*bind_tcf)(struct Qdisc *, unsigned long,
|
|
u32 classid);
|
|
void (*unbind_tcf)(struct Qdisc *, unsigned long);
|
|
|
|
/* rtnetlink specific */
|
|
int (*dump)(struct Qdisc *, unsigned long,
|
|
struct sk_buff *skb, struct tcmsg*);
|
|
int (*dump_stats)(struct Qdisc *, unsigned long,
|
|
struct gnet_dump *);
|
|
|
|
ANDROID_KABI_RESERVE(1);
|
|
};
|
|
|
|
/* Qdisc_class_ops flag values */
|
|
|
|
/* Implements API that doesn't require rtnl lock */
|
|
enum qdisc_class_ops_flags {
|
|
QDISC_CLASS_OPS_DOIT_UNLOCKED = 1,
|
|
};
|
|
|
|
struct Qdisc_ops {
|
|
struct Qdisc_ops *next;
|
|
const struct Qdisc_class_ops *cl_ops;
|
|
char id[IFNAMSIZ];
|
|
int priv_size;
|
|
unsigned int static_flags;
|
|
|
|
int (*enqueue)(struct sk_buff *skb,
|
|
struct Qdisc *sch,
|
|
struct sk_buff **to_free);
|
|
struct sk_buff * (*dequeue)(struct Qdisc *);
|
|
struct sk_buff * (*peek)(struct Qdisc *);
|
|
|
|
int (*init)(struct Qdisc *sch, struct nlattr *arg,
|
|
struct netlink_ext_ack *extack);
|
|
void (*reset)(struct Qdisc *);
|
|
void (*destroy)(struct Qdisc *);
|
|
int (*change)(struct Qdisc *sch,
|
|
struct nlattr *arg,
|
|
struct netlink_ext_ack *extack);
|
|
void (*attach)(struct Qdisc *sch);
|
|
int (*change_tx_queue_len)(struct Qdisc *, unsigned int);
|
|
|
|
int (*dump)(struct Qdisc *, struct sk_buff *);
|
|
int (*dump_stats)(struct Qdisc *, struct gnet_dump *);
|
|
|
|
void (*ingress_block_set)(struct Qdisc *sch,
|
|
u32 block_index);
|
|
void (*egress_block_set)(struct Qdisc *sch,
|
|
u32 block_index);
|
|
u32 (*ingress_block_get)(struct Qdisc *sch);
|
|
u32 (*egress_block_get)(struct Qdisc *sch);
|
|
|
|
struct module *owner;
|
|
|
|
ANDROID_KABI_RESERVE(1);
|
|
};
|
|
|
|
|
|
struct tcf_result {
|
|
union {
|
|
struct {
|
|
unsigned long class;
|
|
u32 classid;
|
|
};
|
|
const struct tcf_proto *goto_tp;
|
|
|
|
/* used in the skb_tc_reinsert function */
|
|
struct {
|
|
bool ingress;
|
|
struct gnet_stats_queue *qstats;
|
|
};
|
|
};
|
|
};
|
|
|
|
struct tcf_chain;
|
|
|
|
struct tcf_proto_ops {
|
|
struct list_head head;
|
|
char kind[IFNAMSIZ];
|
|
|
|
int (*classify)(struct sk_buff *,
|
|
const struct tcf_proto *,
|
|
struct tcf_result *);
|
|
int (*init)(struct tcf_proto*);
|
|
void (*destroy)(struct tcf_proto *tp, bool rtnl_held,
|
|
struct netlink_ext_ack *extack);
|
|
|
|
void* (*get)(struct tcf_proto*, u32 handle);
|
|
void (*put)(struct tcf_proto *tp, void *f);
|
|
int (*change)(struct net *net, struct sk_buff *,
|
|
struct tcf_proto*, unsigned long,
|
|
u32 handle, struct nlattr **,
|
|
void **, bool, bool,
|
|
struct netlink_ext_ack *);
|
|
int (*delete)(struct tcf_proto *tp, void *arg,
|
|
bool *last, bool rtnl_held,
|
|
struct netlink_ext_ack *);
|
|
bool (*delete_empty)(struct tcf_proto *tp);
|
|
void (*walk)(struct tcf_proto *tp,
|
|
struct tcf_walker *arg, bool rtnl_held);
|
|
int (*reoffload)(struct tcf_proto *tp, bool add,
|
|
flow_setup_cb_t *cb, void *cb_priv,
|
|
struct netlink_ext_ack *extack);
|
|
void (*hw_add)(struct tcf_proto *tp,
|
|
void *type_data);
|
|
void (*hw_del)(struct tcf_proto *tp,
|
|
void *type_data);
|
|
void (*bind_class)(void *, u32, unsigned long,
|
|
void *, unsigned long);
|
|
void * (*tmplt_create)(struct net *net,
|
|
struct tcf_chain *chain,
|
|
struct nlattr **tca,
|
|
struct netlink_ext_ack *extack);
|
|
void (*tmplt_destroy)(void *tmplt_priv);
|
|
|
|
/* rtnetlink specific */
|
|
int (*dump)(struct net*, struct tcf_proto*, void *,
|
|
struct sk_buff *skb, struct tcmsg*,
|
|
bool);
|
|
int (*terse_dump)(struct net *net,
|
|
struct tcf_proto *tp, void *fh,
|
|
struct sk_buff *skb,
|
|
struct tcmsg *t, bool rtnl_held);
|
|
int (*tmplt_dump)(struct sk_buff *skb,
|
|
struct net *net,
|
|
void *tmplt_priv);
|
|
|
|
struct module *owner;
|
|
int flags;
|
|
};
|
|
|
|
/* Classifiers setting TCF_PROTO_OPS_DOIT_UNLOCKED in tcf_proto_ops->flags
|
|
* are expected to implement tcf_proto_ops->delete_empty(), otherwise race
|
|
* conditions can occur when filters are inserted/deleted simultaneously.
|
|
*/
|
|
enum tcf_proto_ops_flags {
|
|
TCF_PROTO_OPS_DOIT_UNLOCKED = 1,
|
|
};
|
|
|
|
struct tcf_proto {
|
|
/* Fast access part */
|
|
struct tcf_proto __rcu *next;
|
|
void __rcu *root;
|
|
|
|
/* called under RCU BH lock*/
|
|
int (*classify)(struct sk_buff *,
|
|
const struct tcf_proto *,
|
|
struct tcf_result *);
|
|
__be16 protocol;
|
|
|
|
/* All the rest */
|
|
u32 prio;
|
|
void *data;
|
|
const struct tcf_proto_ops *ops;
|
|
struct tcf_chain *chain;
|
|
/* Lock protects tcf_proto shared state and can be used by unlocked
|
|
* classifiers to protect their private data.
|
|
*/
|
|
spinlock_t lock;
|
|
bool deleting;
|
|
refcount_t refcnt;
|
|
struct rcu_head rcu;
|
|
struct hlist_node destroy_ht_node;
|
|
};
|
|
|
|
struct qdisc_skb_cb {
|
|
struct {
|
|
unsigned int pkt_len;
|
|
u16 slave_dev_queue_mapping;
|
|
u16 tc_classid;
|
|
};
|
|
#define QDISC_CB_PRIV_LEN 20
|
|
unsigned char data[QDISC_CB_PRIV_LEN];
|
|
u16 mru;
|
|
};
|
|
|
|
typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
|
|
|
|
struct tcf_chain {
|
|
/* Protects filter_chain. */
|
|
struct mutex filter_chain_lock;
|
|
struct tcf_proto __rcu *filter_chain;
|
|
struct list_head list;
|
|
struct tcf_block *block;
|
|
u32 index; /* chain index */
|
|
unsigned int refcnt;
|
|
unsigned int action_refcnt;
|
|
bool explicitly_created;
|
|
bool flushing;
|
|
const struct tcf_proto_ops *tmplt_ops;
|
|
void *tmplt_priv;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
struct tcf_block {
|
|
/* Lock protects tcf_block and lifetime-management data of chains
|
|
* attached to the block (refcnt, action_refcnt, explicitly_created).
|
|
*/
|
|
struct mutex lock;
|
|
struct list_head chain_list;
|
|
u32 index; /* block index for shared blocks */
|
|
u32 classid; /* which class this block belongs to */
|
|
refcount_t refcnt;
|
|
struct net *net;
|
|
struct Qdisc *q;
|
|
struct rw_semaphore cb_lock; /* protects cb_list and offload counters */
|
|
struct flow_block flow_block;
|
|
struct list_head owner_list;
|
|
bool keep_dst;
|
|
atomic_t offloadcnt; /* Number of oddloaded filters */
|
|
unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
|
|
unsigned int lockeddevcnt; /* Number of devs that require rtnl lock. */
|
|
struct {
|
|
struct tcf_chain *chain;
|
|
struct list_head filter_chain_list;
|
|
} chain0;
|
|
struct rcu_head rcu;
|
|
DECLARE_HASHTABLE(proto_destroy_ht, 7);
|
|
struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */
|
|
};
|
|
|
|
#ifdef CONFIG_PROVE_LOCKING
|
|
static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain)
|
|
{
|
|
return lockdep_is_held(&chain->filter_chain_lock);
|
|
}
|
|
|
|
static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
|
|
{
|
|
return lockdep_is_held(&tp->lock);
|
|
}
|
|
#else
|
|
static inline bool lockdep_tcf_chain_is_locked(struct tcf_block *chain)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp)
|
|
{
|
|
return true;
|
|
}
|
|
#endif /* #ifdef CONFIG_PROVE_LOCKING */
|
|
|
|
#define tcf_chain_dereference(p, chain) \
|
|
rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain))
|
|
|
|
#define tcf_proto_dereference(p, tp) \
|
|
rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp))
|
|
|
|
static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
|
|
{
|
|
struct qdisc_skb_cb *qcb;
|
|
|
|
BUILD_BUG_ON(sizeof(skb->cb) < sizeof(*qcb));
|
|
BUILD_BUG_ON(sizeof(qcb->data) < sz);
|
|
}
|
|
|
|
static inline int qdisc_qlen_cpu(const struct Qdisc *q)
|
|
{
|
|
return this_cpu_ptr(q->cpu_qstats)->qlen;
|
|
}
|
|
|
|
static inline int qdisc_qlen(const struct Qdisc *q)
|
|
{
|
|
return q->q.qlen;
|
|
}
|
|
|
|
static inline int qdisc_qlen_sum(const struct Qdisc *q)
|
|
{
|
|
__u32 qlen = q->qstats.qlen;
|
|
int i;
|
|
|
|
if (qdisc_is_percpu_stats(q)) {
|
|
for_each_possible_cpu(i)
|
|
qlen += per_cpu_ptr(q->cpu_qstats, i)->qlen;
|
|
} else {
|
|
qlen += q->q.qlen;
|
|
}
|
|
|
|
return qlen;
|
|
}
|
|
|
|
static inline struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
|
|
{
|
|
return (struct qdisc_skb_cb *)skb->cb;
|
|
}
|
|
|
|
static inline spinlock_t *qdisc_lock(struct Qdisc *qdisc)
|
|
{
|
|
return &qdisc->q.lock;
|
|
}
|
|
|
|
static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc)
|
|
{
|
|
struct Qdisc *q = rcu_dereference_rtnl(qdisc->dev_queue->qdisc);
|
|
|
|
return q;
|
|
}
|
|
|
|
static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc)
|
|
{
|
|
return rcu_dereference_bh(qdisc->dev_queue->qdisc);
|
|
}
|
|
|
|
static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc)
|
|
{
|
|
return qdisc->dev_queue->qdisc_sleeping;
|
|
}
|
|
|
|
/* The qdisc root lock is a mechanism by which to top level
|
|
* of a qdisc tree can be locked from any qdisc node in the
|
|
* forest. This allows changing the configuration of some
|
|
* aspect of the qdisc tree while blocking out asynchronous
|
|
* qdisc access in the packet processing paths.
|
|
*
|
|
* It is only legal to do this when the root will not change
|
|
* on us. Otherwise we'll potentially lock the wrong qdisc
|
|
* root. This is enforced by holding the RTNL semaphore, which
|
|
* all users of this lock accessor must do.
|
|
*/
|
|
static inline spinlock_t *qdisc_root_lock(const struct Qdisc *qdisc)
|
|
{
|
|
struct Qdisc *root = qdisc_root(qdisc);
|
|
|
|
ASSERT_RTNL();
|
|
return qdisc_lock(root);
|
|
}
|
|
|
|
static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc)
|
|
{
|
|
struct Qdisc *root = qdisc_root_sleeping(qdisc);
|
|
|
|
ASSERT_RTNL();
|
|
return qdisc_lock(root);
|
|
}
|
|
|
|
static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
|
|
{
|
|
struct Qdisc *root = qdisc_root_sleeping(qdisc);
|
|
|
|
ASSERT_RTNL();
|
|
return &root->running;
|
|
}
|
|
|
|
static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc)
|
|
{
|
|
return qdisc->dev_queue->dev;
|
|
}
|
|
|
|
static inline void sch_tree_lock(const struct Qdisc *q)
|
|
{
|
|
spin_lock_bh(qdisc_root_sleeping_lock(q));
|
|
}
|
|
|
|
static inline void sch_tree_unlock(const struct Qdisc *q)
|
|
{
|
|
spin_unlock_bh(qdisc_root_sleeping_lock(q));
|
|
}
|
|
|
|
extern struct Qdisc noop_qdisc;
|
|
extern struct Qdisc_ops noop_qdisc_ops;
|
|
extern struct Qdisc_ops pfifo_fast_ops;
|
|
extern struct Qdisc_ops mq_qdisc_ops;
|
|
extern struct Qdisc_ops noqueue_qdisc_ops;
|
|
extern const struct Qdisc_ops *default_qdisc_ops;
|
|
static inline const struct Qdisc_ops *
|
|
get_default_qdisc_ops(const struct net_device *dev, int ntx)
|
|
{
|
|
return ntx < dev->real_num_tx_queues ?
|
|
default_qdisc_ops : &pfifo_fast_ops;
|
|
}
|
|
|
|
struct Qdisc_class_common {
|
|
u32 classid;
|
|
struct hlist_node hnode;
|
|
};
|
|
|
|
struct Qdisc_class_hash {
|
|
struct hlist_head *hash;
|
|
unsigned int hashsize;
|
|
unsigned int hashmask;
|
|
unsigned int hashelems;
|
|
};
|
|
|
|
static inline unsigned int qdisc_class_hash(u32 id, u32 mask)
|
|
{
|
|
id ^= id >> 8;
|
|
id ^= id >> 4;
|
|
return id & mask;
|
|
}
|
|
|
|
static inline struct Qdisc_class_common *
|
|
qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id)
|
|
{
|
|
struct Qdisc_class_common *cl;
|
|
unsigned int h;
|
|
|
|
if (!id)
|
|
return NULL;
|
|
|
|
h = qdisc_class_hash(id, hash->hashmask);
|
|
hlist_for_each_entry(cl, &hash->hash[h], hnode) {
|
|
if (cl->classid == id)
|
|
return cl;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
static inline int tc_classid_to_hwtc(struct net_device *dev, u32 classid)
|
|
{
|
|
u32 hwtc = TC_H_MIN(classid) - TC_H_MIN_PRIORITY;
|
|
|
|
return (hwtc < netdev_get_num_tc(dev)) ? hwtc : -EINVAL;
|
|
}
|
|
|
|
int qdisc_class_hash_init(struct Qdisc_class_hash *);
|
|
void qdisc_class_hash_insert(struct Qdisc_class_hash *,
|
|
struct Qdisc_class_common *);
|
|
void qdisc_class_hash_remove(struct Qdisc_class_hash *,
|
|
struct Qdisc_class_common *);
|
|
void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *);
|
|
void qdisc_class_hash_destroy(struct Qdisc_class_hash *);
|
|
|
|
int dev_qdisc_change_tx_queue_len(struct net_device *dev);
|
|
void dev_init_scheduler(struct net_device *dev);
|
|
void dev_shutdown(struct net_device *dev);
|
|
void dev_activate(struct net_device *dev);
|
|
void dev_deactivate(struct net_device *dev);
|
|
void dev_deactivate_many(struct list_head *head);
|
|
struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
|
|
struct Qdisc *qdisc);
|
|
void qdisc_reset(struct Qdisc *qdisc);
|
|
void qdisc_put(struct Qdisc *qdisc);
|
|
void qdisc_put_unlocked(struct Qdisc *qdisc);
|
|
void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len);
|
|
#ifdef CONFIG_NET_SCHED
|
|
int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
|
|
void *type_data);
|
|
void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
|
|
struct Qdisc *new, struct Qdisc *old,
|
|
enum tc_setup_type type, void *type_data,
|
|
struct netlink_ext_ack *extack);
|
|
#else
|
|
static inline int
|
|
qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type,
|
|
void *type_data)
|
|
{
|
|
q->flags &= ~TCQ_F_OFFLOADED;
|
|
return 0;
|
|
}
|
|
|
|
static inline void
|
|
qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch,
|
|
struct Qdisc *new, struct Qdisc *old,
|
|
enum tc_setup_type type, void *type_data,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
}
|
|
#endif
|
|
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
|
|
const struct Qdisc_ops *ops,
|
|
struct netlink_ext_ack *extack);
|
|
void qdisc_free(struct Qdisc *qdisc);
|
|
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
|
|
const struct Qdisc_ops *ops, u32 parentid,
|
|
struct netlink_ext_ack *extack);
|
|
void __qdisc_calculate_pkt_len(struct sk_buff *skb,
|
|
const struct qdisc_size_table *stab);
|
|
int skb_do_redirect(struct sk_buff *);
|
|
|
|
static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
return skb->tc_at_ingress;
|
|
#else
|
|
return false;
|
|
#endif
|
|
}
|
|
|
|
static inline bool skb_skip_tc_classify(struct sk_buff *skb)
|
|
{
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
if (skb->tc_skip_classify) {
|
|
skb->tc_skip_classify = 0;
|
|
return true;
|
|
}
|
|
#endif
|
|
return false;
|
|
}
|
|
|
|
/* Reset all TX qdiscs greater than index of a device. */
|
|
static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i)
|
|
{
|
|
struct Qdisc *qdisc;
|
|
|
|
for (; i < dev->num_tx_queues; i++) {
|
|
qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc);
|
|
if (qdisc) {
|
|
spin_lock_bh(qdisc_lock(qdisc));
|
|
qdisc_reset(qdisc);
|
|
spin_unlock_bh(qdisc_lock(qdisc));
|
|
}
|
|
}
|
|
}
|
|
|
|
/* Are all TX queues of the device empty? */
|
|
static inline bool qdisc_all_tx_empty(const struct net_device *dev)
|
|
{
|
|
unsigned int i;
|
|
|
|
rcu_read_lock();
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
|
const struct Qdisc *q = rcu_dereference(txq->qdisc);
|
|
|
|
if (!qdisc_is_empty(q)) {
|
|
rcu_read_unlock();
|
|
return false;
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
return true;
|
|
}
|
|
|
|
/* Are any of the TX qdiscs changing? */
|
|
static inline bool qdisc_tx_changing(const struct net_device *dev)
|
|
{
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
|
if (rcu_access_pointer(txq->qdisc) != txq->qdisc_sleeping)
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
/* Is the device using the noop qdisc on all queues? */
|
|
static inline bool qdisc_tx_is_noop(const struct net_device *dev)
|
|
{
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < dev->num_tx_queues; i++) {
|
|
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
|
|
if (rcu_access_pointer(txq->qdisc) != &noop_qdisc)
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb)
|
|
{
|
|
return qdisc_skb_cb(skb)->pkt_len;
|
|
}
|
|
|
|
/* additional qdisc xmit flags (NET_XMIT_MASK in linux/netdevice.h) */
|
|
enum net_xmit_qdisc_t {
|
|
__NET_XMIT_STOLEN = 0x00010000,
|
|
__NET_XMIT_BYPASS = 0x00020000,
|
|
};
|
|
|
|
#ifdef CONFIG_NET_CLS_ACT
|
|
#define net_xmit_drop_count(e) ((e) & __NET_XMIT_STOLEN ? 0 : 1)
|
|
#else
|
|
#define net_xmit_drop_count(e) (1)
|
|
#endif
|
|
|
|
static inline void qdisc_calculate_pkt_len(struct sk_buff *skb,
|
|
const struct Qdisc *sch)
|
|
{
|
|
#ifdef CONFIG_NET_SCHED
|
|
struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab);
|
|
|
|
if (stab)
|
|
__qdisc_calculate_pkt_len(skb, stab);
|
|
#endif
|
|
}
|
|
|
|
static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
|
|
struct sk_buff **to_free)
|
|
{
|
|
qdisc_calculate_pkt_len(skb, sch);
|
|
return sch->enqueue(skb, sch, to_free);
|
|
}
|
|
|
|
static inline void _bstats_update(struct gnet_stats_basic_packed *bstats,
|
|
__u64 bytes, __u32 packets)
|
|
{
|
|
bstats->bytes += bytes;
|
|
bstats->packets += packets;
|
|
}
|
|
|
|
static inline void bstats_update(struct gnet_stats_basic_packed *bstats,
|
|
const struct sk_buff *skb)
|
|
{
|
|
_bstats_update(bstats,
|
|
qdisc_pkt_len(skb),
|
|
skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1);
|
|
}
|
|
|
|
static inline void _bstats_cpu_update(struct gnet_stats_basic_cpu *bstats,
|
|
__u64 bytes, __u32 packets)
|
|
{
|
|
u64_stats_update_begin(&bstats->syncp);
|
|
_bstats_update(&bstats->bstats, bytes, packets);
|
|
u64_stats_update_end(&bstats->syncp);
|
|
}
|
|
|
|
static inline void bstats_cpu_update(struct gnet_stats_basic_cpu *bstats,
|
|
const struct sk_buff *skb)
|
|
{
|
|
u64_stats_update_begin(&bstats->syncp);
|
|
bstats_update(&bstats->bstats, skb);
|
|
u64_stats_update_end(&bstats->syncp);
|
|
}
|
|
|
|
static inline void qdisc_bstats_cpu_update(struct Qdisc *sch,
|
|
const struct sk_buff *skb)
|
|
{
|
|
bstats_cpu_update(this_cpu_ptr(sch->cpu_bstats), skb);
|
|
}
|
|
|
|
static inline void qdisc_bstats_update(struct Qdisc *sch,
|
|
const struct sk_buff *skb)
|
|
{
|
|
bstats_update(&sch->bstats, skb);
|
|
}
|
|
|
|
static inline void qdisc_qstats_backlog_dec(struct Qdisc *sch,
|
|
const struct sk_buff *skb)
|
|
{
|
|
sch->qstats.backlog -= qdisc_pkt_len(skb);
|
|
}
|
|
|
|
static inline void qdisc_qstats_cpu_backlog_dec(struct Qdisc *sch,
|
|
const struct sk_buff *skb)
|
|
{
|
|
this_cpu_sub(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
|
|
}
|
|
|
|
static inline void qdisc_qstats_backlog_inc(struct Qdisc *sch,
|
|
const struct sk_buff *skb)
|
|
{
|
|
sch->qstats.backlog += qdisc_pkt_len(skb);
|
|
}
|
|
|
|
static inline void qdisc_qstats_cpu_backlog_inc(struct Qdisc *sch,
|
|
const struct sk_buff *skb)
|
|
{
|
|
this_cpu_add(sch->cpu_qstats->backlog, qdisc_pkt_len(skb));
|
|
}
|
|
|
|
static inline void qdisc_qstats_cpu_qlen_inc(struct Qdisc *sch)
|
|
{
|
|
this_cpu_inc(sch->cpu_qstats->qlen);
|
|
}
|
|
|
|
static inline void qdisc_qstats_cpu_qlen_dec(struct Qdisc *sch)
|
|
{
|
|
this_cpu_dec(sch->cpu_qstats->qlen);
|
|
}
|
|
|
|
static inline void qdisc_qstats_cpu_requeues_inc(struct Qdisc *sch)
|
|
{
|
|
this_cpu_inc(sch->cpu_qstats->requeues);
|
|
}
|
|
|
|
static inline void __qdisc_qstats_drop(struct Qdisc *sch, int count)
|
|
{
|
|
sch->qstats.drops += count;
|
|
}
|
|
|
|
static inline void qstats_drop_inc(struct gnet_stats_queue *qstats)
|
|
{
|
|
qstats->drops++;
|
|
}
|
|
|
|
static inline void qstats_overlimit_inc(struct gnet_stats_queue *qstats)
|
|
{
|
|
qstats->overlimits++;
|
|
}
|
|
|
|
static inline void qdisc_qstats_drop(struct Qdisc *sch)
|
|
{
|
|
qstats_drop_inc(&sch->qstats);
|
|
}
|
|
|
|
static inline void qdisc_qstats_cpu_drop(struct Qdisc *sch)
|
|
{
|
|
this_cpu_inc(sch->cpu_qstats->drops);
|
|
}
|
|
|
|
static inline void qdisc_qstats_overlimit(struct Qdisc *sch)
|
|
{
|
|
sch->qstats.overlimits++;
|
|
}
|
|
|
|
static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch)
|
|
{
|
|
__u32 qlen = qdisc_qlen_sum(sch);
|
|
|
|
return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen);
|
|
}
|
|
|
|
static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen,
|
|
__u32 *backlog)
|
|
{
|
|
struct gnet_stats_queue qstats = { 0 };
|
|
__u32 len = qdisc_qlen_sum(sch);
|
|
|
|
__gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len);
|
|
*qlen = qstats.qlen;
|
|
*backlog = qstats.backlog;
|
|
}
|
|
|
|
static inline void qdisc_tree_flush_backlog(struct Qdisc *sch)
|
|
{
|
|
__u32 qlen, backlog;
|
|
|
|
qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
|
|
qdisc_tree_reduce_backlog(sch, qlen, backlog);
|
|
}
|
|
|
|
static inline void qdisc_purge_queue(struct Qdisc *sch)
|
|
{
|
|
__u32 qlen, backlog;
|
|
|
|
qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
|
|
qdisc_reset(sch);
|
|
qdisc_tree_reduce_backlog(sch, qlen, backlog);
|
|
}
|
|
|
|
static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh)
|
|
{
|
|
qh->head = NULL;
|
|
qh->tail = NULL;
|
|
qh->qlen = 0;
|
|
}
|
|
|
|
static inline void __qdisc_enqueue_tail(struct sk_buff *skb,
|
|
struct qdisc_skb_head *qh)
|
|
{
|
|
struct sk_buff *last = qh->tail;
|
|
|
|
if (last) {
|
|
skb->next = NULL;
|
|
last->next = skb;
|
|
qh->tail = skb;
|
|
} else {
|
|
qh->tail = skb;
|
|
qh->head = skb;
|
|
}
|
|
qh->qlen++;
|
|
}
|
|
|
|
static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch)
|
|
{
|
|
__qdisc_enqueue_tail(skb, &sch->q);
|
|
qdisc_qstats_backlog_inc(sch, skb);
|
|
return NET_XMIT_SUCCESS;
|
|
}
|
|
|
|
static inline void __qdisc_enqueue_head(struct sk_buff *skb,
|
|
struct qdisc_skb_head *qh)
|
|
{
|
|
skb->next = qh->head;
|
|
|
|
if (!qh->head)
|
|
qh->tail = skb;
|
|
qh->head = skb;
|
|
qh->qlen++;
|
|
}
|
|
|
|
static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh)
|
|
{
|
|
struct sk_buff *skb = qh->head;
|
|
|
|
if (likely(skb != NULL)) {
|
|
qh->head = skb->next;
|
|
qh->qlen--;
|
|
if (qh->head == NULL)
|
|
qh->tail = NULL;
|
|
skb->next = NULL;
|
|
}
|
|
|
|
return skb;
|
|
}
|
|
|
|
static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch)
|
|
{
|
|
struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
|
|
|
|
if (likely(skb != NULL)) {
|
|
qdisc_qstats_backlog_dec(sch, skb);
|
|
qdisc_bstats_update(sch, skb);
|
|
}
|
|
|
|
return skb;
|
|
}
|
|
|
|
/* Instead of calling kfree_skb() while root qdisc lock is held,
|
|
* queue the skb for future freeing at end of __dev_xmit_skb()
|
|
*/
|
|
static inline void __qdisc_drop(struct sk_buff *skb, struct sk_buff **to_free)
|
|
{
|
|
skb->next = *to_free;
|
|
*to_free = skb;
|
|
}
|
|
|
|
static inline void __qdisc_drop_all(struct sk_buff *skb,
|
|
struct sk_buff **to_free)
|
|
{
|
|
if (skb->prev)
|
|
skb->prev->next = *to_free;
|
|
else
|
|
skb->next = *to_free;
|
|
*to_free = skb;
|
|
}
|
|
|
|
static inline unsigned int __qdisc_queue_drop_head(struct Qdisc *sch,
|
|
struct qdisc_skb_head *qh,
|
|
struct sk_buff **to_free)
|
|
{
|
|
struct sk_buff *skb = __qdisc_dequeue_head(qh);
|
|
|
|
if (likely(skb != NULL)) {
|
|
unsigned int len = qdisc_pkt_len(skb);
|
|
|
|
qdisc_qstats_backlog_dec(sch, skb);
|
|
__qdisc_drop(skb, to_free);
|
|
return len;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline struct sk_buff *qdisc_peek_head(struct Qdisc *sch)
|
|
{
|
|
const struct qdisc_skb_head *qh = &sch->q;
|
|
|
|
return qh->head;
|
|
}
|
|
|
|
/* generic pseudo peek method for non-work-conserving qdisc */
|
|
static inline struct sk_buff *qdisc_peek_dequeued(struct Qdisc *sch)
|
|
{
|
|
struct sk_buff *skb = skb_peek(&sch->gso_skb);
|
|
|
|
/* we can reuse ->gso_skb because peek isn't called for root qdiscs */
|
|
if (!skb) {
|
|
skb = sch->dequeue(sch);
|
|
|
|
if (skb) {
|
|
__skb_queue_head(&sch->gso_skb, skb);
|
|
/* it's still part of the queue */
|
|
qdisc_qstats_backlog_inc(sch, skb);
|
|
sch->q.qlen++;
|
|
}
|
|
}
|
|
|
|
return skb;
|
|
}
|
|
|
|
static inline void qdisc_update_stats_at_dequeue(struct Qdisc *sch,
|
|
struct sk_buff *skb)
|
|
{
|
|
if (qdisc_is_percpu_stats(sch)) {
|
|
qdisc_qstats_cpu_backlog_dec(sch, skb);
|
|
qdisc_bstats_cpu_update(sch, skb);
|
|
qdisc_qstats_cpu_qlen_dec(sch);
|
|
} else {
|
|
qdisc_qstats_backlog_dec(sch, skb);
|
|
qdisc_bstats_update(sch, skb);
|
|
sch->q.qlen--;
|
|
}
|
|
}
|
|
|
|
static inline void qdisc_update_stats_at_enqueue(struct Qdisc *sch,
|
|
unsigned int pkt_len)
|
|
{
|
|
if (qdisc_is_percpu_stats(sch)) {
|
|
qdisc_qstats_cpu_qlen_inc(sch);
|
|
this_cpu_add(sch->cpu_qstats->backlog, pkt_len);
|
|
} else {
|
|
sch->qstats.backlog += pkt_len;
|
|
sch->q.qlen++;
|
|
}
|
|
}
|
|
|
|
/* use instead of qdisc->dequeue() for all qdiscs queried with ->peek() */
|
|
static inline struct sk_buff *qdisc_dequeue_peeked(struct Qdisc *sch)
|
|
{
|
|
struct sk_buff *skb = skb_peek(&sch->gso_skb);
|
|
|
|
if (skb) {
|
|
skb = __skb_dequeue(&sch->gso_skb);
|
|
if (qdisc_is_percpu_stats(sch)) {
|
|
qdisc_qstats_cpu_backlog_dec(sch, skb);
|
|
qdisc_qstats_cpu_qlen_dec(sch);
|
|
} else {
|
|
qdisc_qstats_backlog_dec(sch, skb);
|
|
sch->q.qlen--;
|
|
}
|
|
} else {
|
|
skb = sch->dequeue(sch);
|
|
}
|
|
|
|
return skb;
|
|
}
|
|
|
|
static inline void __qdisc_reset_queue(struct qdisc_skb_head *qh)
|
|
{
|
|
/*
|
|
* We do not know the backlog in bytes of this list, it
|
|
* is up to the caller to correct it
|
|
*/
|
|
ASSERT_RTNL();
|
|
if (qh->qlen) {
|
|
rtnl_kfree_skbs(qh->head, qh->tail);
|
|
|
|
qh->head = NULL;
|
|
qh->tail = NULL;
|
|
qh->qlen = 0;
|
|
}
|
|
}
|
|
|
|
static inline void qdisc_reset_queue(struct Qdisc *sch)
|
|
{
|
|
__qdisc_reset_queue(&sch->q);
|
|
}
|
|
|
|
static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
|
|
struct Qdisc **pold)
|
|
{
|
|
struct Qdisc *old;
|
|
|
|
sch_tree_lock(sch);
|
|
old = *pold;
|
|
*pold = new;
|
|
if (old != NULL)
|
|
qdisc_purge_queue(old);
|
|
sch_tree_unlock(sch);
|
|
|
|
return old;
|
|
}
|
|
|
|
static inline void rtnl_qdisc_drop(struct sk_buff *skb, struct Qdisc *sch)
|
|
{
|
|
rtnl_kfree_skbs(skb, skb);
|
|
qdisc_qstats_drop(sch);
|
|
}
|
|
|
|
static inline int qdisc_drop_cpu(struct sk_buff *skb, struct Qdisc *sch,
|
|
struct sk_buff **to_free)
|
|
{
|
|
__qdisc_drop(skb, to_free);
|
|
qdisc_qstats_cpu_drop(sch);
|
|
|
|
return NET_XMIT_DROP;
|
|
}
|
|
|
|
static inline int qdisc_drop(struct sk_buff *skb, struct Qdisc *sch,
|
|
struct sk_buff **to_free)
|
|
{
|
|
__qdisc_drop(skb, to_free);
|
|
qdisc_qstats_drop(sch);
|
|
|
|
return NET_XMIT_DROP;
|
|
}
|
|
|
|
static inline int qdisc_drop_all(struct sk_buff *skb, struct Qdisc *sch,
|
|
struct sk_buff **to_free)
|
|
{
|
|
__qdisc_drop_all(skb, to_free);
|
|
qdisc_qstats_drop(sch);
|
|
|
|
return NET_XMIT_DROP;
|
|
}
|
|
|
|
/* Length to Time (L2T) lookup in a qdisc_rate_table, to determine how
|
|
long it will take to send a packet given its size.
|
|
*/
|
|
static inline u32 qdisc_l2t(struct qdisc_rate_table* rtab, unsigned int pktlen)
|
|
{
|
|
int slot = pktlen + rtab->rate.cell_align + rtab->rate.overhead;
|
|
if (slot < 0)
|
|
slot = 0;
|
|
slot >>= rtab->rate.cell_log;
|
|
if (slot > 255)
|
|
return rtab->data[255]*(slot >> 8) + rtab->data[slot & 0xFF];
|
|
return rtab->data[slot];
|
|
}
|
|
|
|
struct psched_ratecfg {
|
|
u64 rate_bytes_ps; /* bytes per second */
|
|
u32 mult;
|
|
u16 overhead;
|
|
u16 mpu;
|
|
u8 linklayer;
|
|
u8 shift;
|
|
};
|
|
|
|
static inline u64 psched_l2t_ns(const struct psched_ratecfg *r,
|
|
unsigned int len)
|
|
{
|
|
len += r->overhead;
|
|
|
|
if (len < r->mpu)
|
|
len = r->mpu;
|
|
|
|
if (unlikely(r->linklayer == TC_LINKLAYER_ATM))
|
|
return ((u64)(DIV_ROUND_UP(len,48)*53) * r->mult) >> r->shift;
|
|
|
|
return ((u64)len * r->mult) >> r->shift;
|
|
}
|
|
|
|
void psched_ratecfg_precompute(struct psched_ratecfg *r,
|
|
const struct tc_ratespec *conf,
|
|
u64 rate64);
|
|
|
|
static inline void psched_ratecfg_getrate(struct tc_ratespec *res,
|
|
const struct psched_ratecfg *r)
|
|
{
|
|
memset(res, 0, sizeof(*res));
|
|
|
|
/* legacy struct tc_ratespec has a 32bit @rate field
|
|
* Qdisc using 64bit rate should add new attributes
|
|
* in order to maintain compatibility.
|
|
*/
|
|
res->rate = min_t(u64, r->rate_bytes_ps, ~0U);
|
|
|
|
res->overhead = r->overhead;
|
|
res->mpu = r->mpu;
|
|
res->linklayer = (r->linklayer & TC_LINKLAYER_MASK);
|
|
}
|
|
|
|
/* Mini Qdisc serves for specific needs of ingress/clsact Qdisc.
|
|
* The fast path only needs to access filter list and to update stats
|
|
*/
|
|
struct mini_Qdisc {
|
|
struct tcf_proto *filter_list;
|
|
struct tcf_block *block;
|
|
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
|
|
struct gnet_stats_queue __percpu *cpu_qstats;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
static inline void mini_qdisc_bstats_cpu_update(struct mini_Qdisc *miniq,
|
|
const struct sk_buff *skb)
|
|
{
|
|
bstats_cpu_update(this_cpu_ptr(miniq->cpu_bstats), skb);
|
|
}
|
|
|
|
static inline void mini_qdisc_qstats_cpu_drop(struct mini_Qdisc *miniq)
|
|
{
|
|
this_cpu_inc(miniq->cpu_qstats->drops);
|
|
}
|
|
|
|
struct mini_Qdisc_pair {
|
|
struct mini_Qdisc miniq1;
|
|
struct mini_Qdisc miniq2;
|
|
struct mini_Qdisc __rcu **p_miniq;
|
|
};
|
|
|
|
void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
|
|
struct tcf_proto *tp_head);
|
|
void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
|
|
struct mini_Qdisc __rcu **p_miniq);
|
|
void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
|
|
struct tcf_block *block);
|
|
|
|
/* Make sure qdisc is no longer in SCHED state. */
|
|
static inline void qdisc_synchronize(const struct Qdisc *q)
|
|
{
|
|
while (test_bit(__QDISC_STATE_SCHED, &q->state))
|
|
msleep(1);
|
|
}
|
|
|
|
#endif
|